diff options
Diffstat (limited to '')
60 files changed, 16334 insertions, 0 deletions
diff --git a/python.d/Makefile.am b/python.d/Makefile.am new file mode 100644 index 00000000..8bccba37 --- /dev/null +++ b/python.d/Makefile.am @@ -0,0 +1,84 @@ +MAINTAINERCLEANFILES= $(srcdir)/Makefile.in +CLEANFILES = \ + python-modules-installer.sh \ + $(NULL) + +include $(top_srcdir)/build/subst.inc + +SUFFIXES = .in + +dist_python_SCRIPTS = \ + apache.chart.py \ + apache_cache.chart.py \ + cpufreq.chart.py \ + dovecot.chart.py \ + example.chart.py \ + exim.chart.py \ + hddtemp.chart.py \ + ipfs.chart.py \ + memcached.chart.py \ + mysql.chart.py \ + nginx.chart.py \ + nginx_log.chart.py \ + phpfpm.chart.py \ + postfix.chart.py \ + redis.chart.py \ + sensors.chart.py \ + squid.chart.py \ + tomcat.chart.py \ + python-modules-installer.sh \ + $(NULL) + +dist_python_DATA = \ + README.md \ + $(NULL) + +pythonmodulesdir=$(pythondir)/python_modules +dist_pythonmodules_DATA = \ + python_modules/__init__.py \ + python_modules/base.py \ + python_modules/msg.py \ + python_modules/lm_sensors.py \ + $(NULL) + +pythonyaml2dir=$(pythonmodulesdir)/pyyaml2 +dist_pythonyaml2_DATA = \ + python_modules/pyyaml2/__init__.py \ + python_modules/pyyaml2/composer.py \ + python_modules/pyyaml2/constructor.py \ + python_modules/pyyaml2/cyaml.py \ + python_modules/pyyaml2/dumper.py \ + python_modules/pyyaml2/emitter.py \ + python_modules/pyyaml2/error.py \ + python_modules/pyyaml2/events.py \ + python_modules/pyyaml2/loader.py \ + python_modules/pyyaml2/nodes.py \ + python_modules/pyyaml2/parser.py \ + python_modules/pyyaml2/reader.py \ + python_modules/pyyaml2/representer.py \ + python_modules/pyyaml2/resolver.py \ + python_modules/pyyaml2/scanner.py \ + python_modules/pyyaml2/serializer.py \ + python_modules/pyyaml2/tokens.py \ + $(NULL) + +pythonyaml3dir=$(pythonmodulesdir)/pyyaml3 +dist_pythonyaml3_DATA = \ + python_modules/pyyaml3/__init__.py \ + python_modules/pyyaml3/composer.py \ + python_modules/pyyaml3/constructor.py \ + python_modules/pyyaml3/cyaml.py \ + python_modules/pyyaml3/dumper.py \ + python_modules/pyyaml3/emitter.py \ + python_modules/pyyaml3/error.py \ + python_modules/pyyaml3/events.py \ + python_modules/pyyaml3/loader.py \ + python_modules/pyyaml3/nodes.py \ + python_modules/pyyaml3/parser.py \ + python_modules/pyyaml3/reader.py \ + python_modules/pyyaml3/representer.py \ + python_modules/pyyaml3/resolver.py \ + python_modules/pyyaml3/scanner.py \ + python_modules/pyyaml3/serializer.py \ + python_modules/pyyaml3/tokens.py \ + $(NULL) diff --git a/python.d/Makefile.in b/python.d/Makefile.in new file mode 100644 index 00000000..0e1925c5 --- /dev/null +++ b/python.d/Makefile.in @@ -0,0 +1,698 @@ +# Makefile.in generated by automake 1.14.1 from Makefile.am. +# @configure_input@ + +# Copyright (C) 1994-2013 Free Software Foundation, Inc. + +# This Makefile.in is free software; the Free Software Foundation +# gives unlimited permission to copy and/or distribute it, +# with or without modifications, as long as this notice is preserved. + +# This program is distributed in the hope that it will be useful, +# but WITHOUT ANY WARRANTY, to the extent permitted by law; without +# even the implied warranty of MERCHANTABILITY or FITNESS FOR A +# PARTICULAR PURPOSE. + +@SET_MAKE@ + + +VPATH = @srcdir@ +am__is_gnu_make = test -n '$(MAKEFILE_LIST)' && test -n '$(MAKELEVEL)' +am__make_running_with_option = \ + case $${target_option-} in \ + ?) ;; \ + *) echo "am__make_running_with_option: internal error: invalid" \ + "target option '$${target_option-}' specified" >&2; \ + exit 1;; \ + esac; \ + has_opt=no; \ + sane_makeflags=$$MAKEFLAGS; \ + if $(am__is_gnu_make); then \ + sane_makeflags=$$MFLAGS; \ + else \ + case $$MAKEFLAGS in \ + *\\[\ \ ]*) \ + bs=\\; \ + sane_makeflags=`printf '%s\n' "$$MAKEFLAGS" \ + | sed "s/$$bs$$bs[$$bs $$bs ]*//g"`;; \ + esac; \ + fi; \ + skip_next=no; \ + strip_trailopt () \ + { \ + flg=`printf '%s\n' "$$flg" | sed "s/$$1.*$$//"`; \ + }; \ + for flg in $$sane_makeflags; do \ + test $$skip_next = yes && { skip_next=no; continue; }; \ + case $$flg in \ + *=*|--*) continue;; \ + -*I) strip_trailopt 'I'; skip_next=yes;; \ + -*I?*) strip_trailopt 'I';; \ + -*O) strip_trailopt 'O'; skip_next=yes;; \ + -*O?*) strip_trailopt 'O';; \ + -*l) strip_trailopt 'l'; skip_next=yes;; \ + -*l?*) strip_trailopt 'l';; \ + -[dEDm]) skip_next=yes;; \ + -[JT]) skip_next=yes;; \ + esac; \ + case $$flg in \ + *$$target_option*) has_opt=yes; break;; \ + esac; \ + done; \ + test $$has_opt = yes +am__make_dryrun = (target_option=n; $(am__make_running_with_option)) +am__make_keepgoing = (target_option=k; $(am__make_running_with_option)) +pkgdatadir = $(datadir)/@PACKAGE@ +pkgincludedir = $(includedir)/@PACKAGE@ +pkglibdir = $(libdir)/@PACKAGE@ +pkglibexecdir = $(libexecdir)/@PACKAGE@ +am__cd = CDPATH="$${ZSH_VERSION+.}$(PATH_SEPARATOR)" && cd +install_sh_DATA = $(install_sh) -c -m 644 +install_sh_PROGRAM = $(install_sh) -c +install_sh_SCRIPT = $(install_sh) -c +INSTALL_HEADER = $(INSTALL_DATA) +transform = $(program_transform_name) +NORMAL_INSTALL = : +PRE_INSTALL = : +POST_INSTALL = : +NORMAL_UNINSTALL = : +PRE_UNINSTALL = : +POST_UNINSTALL = : +build_triplet = @build@ +host_triplet = @host@ +DIST_COMMON = $(top_srcdir)/build/subst.inc $(srcdir)/Makefile.in \ + $(srcdir)/Makefile.am $(dist_python_SCRIPTS) \ + $(dist_python_DATA) $(dist_pythonmodules_DATA) \ + $(dist_pythonyaml2_DATA) $(dist_pythonyaml3_DATA) +subdir = python.d +ACLOCAL_M4 = $(top_srcdir)/aclocal.m4 +am__aclocal_m4_deps = $(top_srcdir)/m4/ax_pthread.m4 \ + $(top_srcdir)/configure.ac +am__configure_deps = $(am__aclocal_m4_deps) $(CONFIGURE_DEPENDENCIES) \ + $(ACLOCAL_M4) +mkinstalldirs = $(install_sh) -d +CONFIG_HEADER = $(top_builddir)/config.h +CONFIG_CLEAN_FILES = +CONFIG_CLEAN_VPATH_FILES = +am__vpath_adj_setup = srcdirstrip=`echo "$(srcdir)" | sed 's|.|.|g'`; +am__vpath_adj = case $$p in \ + $(srcdir)/*) f=`echo "$$p" | sed "s|^$$srcdirstrip/||"`;; \ + *) f=$$p;; \ + esac; +am__strip_dir = f=`echo $$p | sed -e 's|^.*/||'`; +am__install_max = 40 +am__nobase_strip_setup = \ + srcdirstrip=`echo "$(srcdir)" | sed 's/[].[^$$\\*|]/\\\\&/g'` +am__nobase_strip = \ + for p in $$list; do echo "$$p"; done | sed -e "s|$$srcdirstrip/||" +am__nobase_list = $(am__nobase_strip_setup); \ + for p in $$list; do echo "$$p $$p"; done | \ + sed "s| $$srcdirstrip/| |;"' / .*\//!s/ .*/ ./; s,\( .*\)/[^/]*$$,\1,' | \ + $(AWK) 'BEGIN { files["."] = "" } { files[$$2] = files[$$2] " " $$1; \ + if (++n[$$2] == $(am__install_max)) \ + { print $$2, files[$$2]; n[$$2] = 0; files[$$2] = "" } } \ + END { for (dir in files) print dir, files[dir] }' +am__base_list = \ + sed '$$!N;$$!N;$$!N;$$!N;$$!N;$$!N;$$!N;s/\n/ /g' | \ + sed '$$!N;$$!N;$$!N;$$!N;s/\n/ /g' +am__uninstall_files_from_dir = { \ + test -z "$$files" \ + || { test ! -d "$$dir" && test ! -f "$$dir" && test ! -r "$$dir"; } \ + || { echo " ( cd '$$dir' && rm -f" $$files ")"; \ + $(am__cd) "$$dir" && rm -f $$files; }; \ + } +am__installdirs = "$(DESTDIR)$(pythondir)" "$(DESTDIR)$(pythondir)" \ + "$(DESTDIR)$(pythonmodulesdir)" "$(DESTDIR)$(pythonyaml2dir)" \ + "$(DESTDIR)$(pythonyaml3dir)" +SCRIPTS = $(dist_python_SCRIPTS) +AM_V_P = $(am__v_P_@AM_V@) +am__v_P_ = $(am__v_P_@AM_DEFAULT_V@) +am__v_P_0 = false +am__v_P_1 = : +AM_V_GEN = $(am__v_GEN_@AM_V@) +am__v_GEN_ = $(am__v_GEN_@AM_DEFAULT_V@) +am__v_GEN_0 = @echo " GEN " $@; +am__v_GEN_1 = +AM_V_at = $(am__v_at_@AM_V@) +am__v_at_ = $(am__v_at_@AM_DEFAULT_V@) +am__v_at_0 = @ +am__v_at_1 = +SOURCES = +DIST_SOURCES = +am__can_run_installinfo = \ + case $$AM_UPDATE_INFO_DIR in \ + n|no|NO) false;; \ + *) (install-info --version) >/dev/null 2>&1;; \ + esac +DATA = $(dist_python_DATA) $(dist_pythonmodules_DATA) \ + $(dist_pythonyaml2_DATA) $(dist_pythonyaml3_DATA) +am__tagged_files = $(HEADERS) $(SOURCES) $(TAGS_FILES) $(LISP) +DISTFILES = $(DIST_COMMON) $(DIST_SOURCES) $(TEXINFOS) $(EXTRA_DIST) +ACLOCAL = @ACLOCAL@ +AMTAR = @AMTAR@ +AM_DEFAULT_VERBOSITY = @AM_DEFAULT_VERBOSITY@ +AUTOCONF = @AUTOCONF@ +AUTOHEADER = @AUTOHEADER@ +AUTOMAKE = @AUTOMAKE@ +AWK = @AWK@ +CC = @CC@ +CCDEPMODE = @CCDEPMODE@ +CFLAGS = @CFLAGS@ +CPP = @CPP@ +CPPFLAGS = @CPPFLAGS@ +CYGPATH_W = @CYGPATH_W@ +DEFS = @DEFS@ +DEPDIR = @DEPDIR@ +ECHO_C = @ECHO_C@ +ECHO_N = @ECHO_N@ +ECHO_T = @ECHO_T@ +EGREP = @EGREP@ +EXEEXT = @EXEEXT@ +GREP = @GREP@ +INSTALL = @INSTALL@ +INSTALL_DATA = @INSTALL_DATA@ +INSTALL_PROGRAM = @INSTALL_PROGRAM@ +INSTALL_SCRIPT = @INSTALL_SCRIPT@ +INSTALL_STRIP_PROGRAM = @INSTALL_STRIP_PROGRAM@ +LDFLAGS = @LDFLAGS@ +LIBMNL_CFLAGS = @LIBMNL_CFLAGS@ +LIBMNL_LIBS = @LIBMNL_LIBS@ +LIBOBJS = @LIBOBJS@ +LIBS = @LIBS@ +LTLIBOBJS = @LTLIBOBJS@ +MAINT = @MAINT@ +MAKEINFO = @MAKEINFO@ +MATH_CFLAGS = @MATH_CFLAGS@ +MATH_LIBS = @MATH_LIBS@ +MKDIR_P = @MKDIR_P@ +NFACCT_CFLAGS = @NFACCT_CFLAGS@ +NFACCT_LIBS = @NFACCT_LIBS@ +OBJEXT = @OBJEXT@ +OPTIONAL_MATH_CLFAGS = @OPTIONAL_MATH_CLFAGS@ +OPTIONAL_MATH_LIBS = @OPTIONAL_MATH_LIBS@ +OPTIONAL_NFACCT_CLFAGS = @OPTIONAL_NFACCT_CLFAGS@ +OPTIONAL_NFACCT_LIBS = @OPTIONAL_NFACCT_LIBS@ +OPTIONAL_UUID_CLFAGS = @OPTIONAL_UUID_CLFAGS@ +OPTIONAL_UUID_LIBS = @OPTIONAL_UUID_LIBS@ +OPTIONAL_ZLIB_CLFAGS = @OPTIONAL_ZLIB_CLFAGS@ +OPTIONAL_ZLIB_LIBS = @OPTIONAL_ZLIB_LIBS@ +PACKAGE = @PACKAGE@ +PACKAGE_BUGREPORT = @PACKAGE_BUGREPORT@ +PACKAGE_NAME = @PACKAGE_NAME@ +PACKAGE_RPM_RELEASE = @PACKAGE_RPM_RELEASE@ +PACKAGE_RPM_VERSION = @PACKAGE_RPM_VERSION@ +PACKAGE_STRING = @PACKAGE_STRING@ +PACKAGE_TARNAME = @PACKAGE_TARNAME@ +PACKAGE_URL = @PACKAGE_URL@ +PACKAGE_VERSION = @PACKAGE_VERSION@ +PATH_SEPARATOR = @PATH_SEPARATOR@ +PKG_CONFIG = @PKG_CONFIG@ +PKG_CONFIG_LIBDIR = @PKG_CONFIG_LIBDIR@ +PKG_CONFIG_PATH = @PKG_CONFIG_PATH@ +PTHREAD_CC = @PTHREAD_CC@ +PTHREAD_CFLAGS = @PTHREAD_CFLAGS@ +PTHREAD_LIBS = @PTHREAD_LIBS@ +SET_MAKE = @SET_MAKE@ +SHELL = @SHELL@ +STRIP = @STRIP@ +UUID_CFLAGS = @UUID_CFLAGS@ +UUID_LIBS = @UUID_LIBS@ +VERSION = @VERSION@ +ZLIB_CFLAGS = @ZLIB_CFLAGS@ +ZLIB_LIBS = @ZLIB_LIBS@ +abs_builddir = @abs_builddir@ +abs_srcdir = @abs_srcdir@ +abs_top_builddir = @abs_top_builddir@ +abs_top_srcdir = @abs_top_srcdir@ +ac_ct_CC = @ac_ct_CC@ +am__include = @am__include@ +am__leading_dot = @am__leading_dot@ +am__quote = @am__quote@ +am__tar = @am__tar@ +am__untar = @am__untar@ +ax_pthread_config = @ax_pthread_config@ +bindir = @bindir@ +build = @build@ +build_alias = @build_alias@ +build_cpu = @build_cpu@ +build_os = @build_os@ +build_vendor = @build_vendor@ +builddir = @builddir@ +cachedir = @cachedir@ +chartsdir = @chartsdir@ +configdir = @configdir@ +datadir = @datadir@ +datarootdir = @datarootdir@ +docdir = @docdir@ +dvidir = @dvidir@ +exec_prefix = @exec_prefix@ +host = @host@ +host_alias = @host_alias@ +host_cpu = @host_cpu@ +host_os = @host_os@ +host_vendor = @host_vendor@ +htmldir = @htmldir@ +includedir = @includedir@ +infodir = @infodir@ +install_sh = @install_sh@ +libdir = @libdir@ +libexecdir = @libexecdir@ +localedir = @localedir@ +localstatedir = @localstatedir@ +logdir = @logdir@ +mandir = @mandir@ +mkdir_p = @mkdir_p@ +nodedir = @nodedir@ +oldincludedir = @oldincludedir@ +pdfdir = @pdfdir@ +pluginsdir = @pluginsdir@ +prefix = @prefix@ +program_transform_name = @program_transform_name@ +psdir = @psdir@ +pythondir = @pythondir@ +registrydir = @registrydir@ +sbindir = @sbindir@ +sharedstatedir = @sharedstatedir@ +srcdir = @srcdir@ +sysconfdir = @sysconfdir@ +target_alias = @target_alias@ +top_build_prefix = @top_build_prefix@ +top_builddir = @top_builddir@ +top_srcdir = @top_srcdir@ +varlibdir = @varlibdir@ +webdir = @webdir@ +MAINTAINERCLEANFILES = $(srcdir)/Makefile.in +CLEANFILES = \ + python-modules-installer.sh \ + $(NULL) + +SUFFIXES = .in +dist_python_SCRIPTS = \ + apache.chart.py \ + apache_cache.chart.py \ + cpufreq.chart.py \ + dovecot.chart.py \ + example.chart.py \ + exim.chart.py \ + hddtemp.chart.py \ + ipfs.chart.py \ + memcached.chart.py \ + mysql.chart.py \ + nginx.chart.py \ + nginx_log.chart.py \ + phpfpm.chart.py \ + postfix.chart.py \ + redis.chart.py \ + sensors.chart.py \ + squid.chart.py \ + tomcat.chart.py \ + python-modules-installer.sh \ + $(NULL) + +dist_python_DATA = \ + README.md \ + $(NULL) + +pythonmodulesdir = $(pythondir)/python_modules +dist_pythonmodules_DATA = \ + python_modules/__init__.py \ + python_modules/base.py \ + python_modules/msg.py \ + python_modules/lm_sensors.py \ + $(NULL) + +pythonyaml2dir = $(pythonmodulesdir)/pyyaml2 +dist_pythonyaml2_DATA = \ + python_modules/pyyaml2/__init__.py \ + python_modules/pyyaml2/composer.py \ + python_modules/pyyaml2/constructor.py \ + python_modules/pyyaml2/cyaml.py \ + python_modules/pyyaml2/dumper.py \ + python_modules/pyyaml2/emitter.py \ + python_modules/pyyaml2/error.py \ + python_modules/pyyaml2/events.py \ + python_modules/pyyaml2/loader.py \ + python_modules/pyyaml2/nodes.py \ + python_modules/pyyaml2/parser.py \ + python_modules/pyyaml2/reader.py \ + python_modules/pyyaml2/representer.py \ + python_modules/pyyaml2/resolver.py \ + python_modules/pyyaml2/scanner.py \ + python_modules/pyyaml2/serializer.py \ + python_modules/pyyaml2/tokens.py \ + $(NULL) + +pythonyaml3dir = $(pythonmodulesdir)/pyyaml3 +dist_pythonyaml3_DATA = \ + python_modules/pyyaml3/__init__.py \ + python_modules/pyyaml3/composer.py \ + python_modules/pyyaml3/constructor.py \ + python_modules/pyyaml3/cyaml.py \ + python_modules/pyyaml3/dumper.py \ + python_modules/pyyaml3/emitter.py \ + python_modules/pyyaml3/error.py \ + python_modules/pyyaml3/events.py \ + python_modules/pyyaml3/loader.py \ + python_modules/pyyaml3/nodes.py \ + python_modules/pyyaml3/parser.py \ + python_modules/pyyaml3/reader.py \ + python_modules/pyyaml3/representer.py \ + python_modules/pyyaml3/resolver.py \ + python_modules/pyyaml3/scanner.py \ + python_modules/pyyaml3/serializer.py \ + python_modules/pyyaml3/tokens.py \ + $(NULL) + +all: all-am + +.SUFFIXES: +.SUFFIXES: .in +$(srcdir)/Makefile.in: @MAINTAINER_MODE_TRUE@ $(srcdir)/Makefile.am $(top_srcdir)/build/subst.inc $(am__configure_deps) + @for dep in $?; do \ + case '$(am__configure_deps)' in \ + *$$dep*) \ + ( cd $(top_builddir) && $(MAKE) $(AM_MAKEFLAGS) am--refresh ) \ + && { if test -f $@; then exit 0; else break; fi; }; \ + exit 1;; \ + esac; \ + done; \ + echo ' cd $(top_srcdir) && $(AUTOMAKE) --gnu python.d/Makefile'; \ + $(am__cd) $(top_srcdir) && \ + $(AUTOMAKE) --gnu python.d/Makefile +.PRECIOUS: Makefile +Makefile: $(srcdir)/Makefile.in $(top_builddir)/config.status + @case '$?' in \ + *config.status*) \ + cd $(top_builddir) && $(MAKE) $(AM_MAKEFLAGS) am--refresh;; \ + *) \ + echo ' cd $(top_builddir) && $(SHELL) ./config.status $(subdir)/$@ $(am__depfiles_maybe)'; \ + cd $(top_builddir) && $(SHELL) ./config.status $(subdir)/$@ $(am__depfiles_maybe);; \ + esac; +$(top_srcdir)/build/subst.inc: + +$(top_builddir)/config.status: $(top_srcdir)/configure $(CONFIG_STATUS_DEPENDENCIES) + cd $(top_builddir) && $(MAKE) $(AM_MAKEFLAGS) am--refresh + +$(top_srcdir)/configure: @MAINTAINER_MODE_TRUE@ $(am__configure_deps) + cd $(top_builddir) && $(MAKE) $(AM_MAKEFLAGS) am--refresh +$(ACLOCAL_M4): @MAINTAINER_MODE_TRUE@ $(am__aclocal_m4_deps) + cd $(top_builddir) && $(MAKE) $(AM_MAKEFLAGS) am--refresh +$(am__aclocal_m4_deps): +install-dist_pythonSCRIPTS: $(dist_python_SCRIPTS) + @$(NORMAL_INSTALL) + @list='$(dist_python_SCRIPTS)'; test -n "$(pythondir)" || list=; \ + if test -n "$$list"; then \ + echo " $(MKDIR_P) '$(DESTDIR)$(pythondir)'"; \ + $(MKDIR_P) "$(DESTDIR)$(pythondir)" || exit 1; \ + fi; \ + for p in $$list; do \ + if test -f "$$p"; then d=; else d="$(srcdir)/"; fi; \ + if test -f "$$d$$p"; then echo "$$d$$p"; echo "$$p"; else :; fi; \ + done | \ + sed -e 'p;s,.*/,,;n' \ + -e 'h;s|.*|.|' \ + -e 'p;x;s,.*/,,;$(transform)' | sed 'N;N;N;s,\n, ,g' | \ + $(AWK) 'BEGIN { files["."] = ""; dirs["."] = 1; } \ + { d=$$3; if (dirs[d] != 1) { print "d", d; dirs[d] = 1 } \ + if ($$2 == $$4) { files[d] = files[d] " " $$1; \ + if (++n[d] == $(am__install_max)) { \ + print "f", d, files[d]; n[d] = 0; files[d] = "" } } \ + else { print "f", d "/" $$4, $$1 } } \ + END { for (d in files) print "f", d, files[d] }' | \ + while read type dir files; do \ + if test "$$dir" = .; then dir=; else dir=/$$dir; fi; \ + test -z "$$files" || { \ + echo " $(INSTALL_SCRIPT) $$files '$(DESTDIR)$(pythondir)$$dir'"; \ + $(INSTALL_SCRIPT) $$files "$(DESTDIR)$(pythondir)$$dir" || exit $$?; \ + } \ + ; done + +uninstall-dist_pythonSCRIPTS: + @$(NORMAL_UNINSTALL) + @list='$(dist_python_SCRIPTS)'; test -n "$(pythondir)" || exit 0; \ + files=`for p in $$list; do echo "$$p"; done | \ + sed -e 's,.*/,,;$(transform)'`; \ + dir='$(DESTDIR)$(pythondir)'; $(am__uninstall_files_from_dir) +install-dist_pythonDATA: $(dist_python_DATA) + @$(NORMAL_INSTALL) + @list='$(dist_python_DATA)'; test -n "$(pythondir)" || list=; \ + if test -n "$$list"; then \ + echo " $(MKDIR_P) '$(DESTDIR)$(pythondir)'"; \ + $(MKDIR_P) "$(DESTDIR)$(pythondir)" || exit 1; \ + fi; \ + for p in $$list; do \ + if test -f "$$p"; then d=; else d="$(srcdir)/"; fi; \ + echo "$$d$$p"; \ + done | $(am__base_list) | \ + while read files; do \ + echo " $(INSTALL_DATA) $$files '$(DESTDIR)$(pythondir)'"; \ + $(INSTALL_DATA) $$files "$(DESTDIR)$(pythondir)" || exit $$?; \ + done + +uninstall-dist_pythonDATA: + @$(NORMAL_UNINSTALL) + @list='$(dist_python_DATA)'; test -n "$(pythondir)" || list=; \ + files=`for p in $$list; do echo $$p; done | sed -e 's|^.*/||'`; \ + dir='$(DESTDIR)$(pythondir)'; $(am__uninstall_files_from_dir) +install-dist_pythonmodulesDATA: $(dist_pythonmodules_DATA) + @$(NORMAL_INSTALL) + @list='$(dist_pythonmodules_DATA)'; test -n "$(pythonmodulesdir)" || list=; \ + if test -n "$$list"; then \ + echo " $(MKDIR_P) '$(DESTDIR)$(pythonmodulesdir)'"; \ + $(MKDIR_P) "$(DESTDIR)$(pythonmodulesdir)" || exit 1; \ + fi; \ + for p in $$list; do \ + if test -f "$$p"; then d=; else d="$(srcdir)/"; fi; \ + echo "$$d$$p"; \ + done | $(am__base_list) | \ + while read files; do \ + echo " $(INSTALL_DATA) $$files '$(DESTDIR)$(pythonmodulesdir)'"; \ + $(INSTALL_DATA) $$files "$(DESTDIR)$(pythonmodulesdir)" || exit $$?; \ + done + +uninstall-dist_pythonmodulesDATA: + @$(NORMAL_UNINSTALL) + @list='$(dist_pythonmodules_DATA)'; test -n "$(pythonmodulesdir)" || list=; \ + files=`for p in $$list; do echo $$p; done | sed -e 's|^.*/||'`; \ + dir='$(DESTDIR)$(pythonmodulesdir)'; $(am__uninstall_files_from_dir) +install-dist_pythonyaml2DATA: $(dist_pythonyaml2_DATA) + @$(NORMAL_INSTALL) + @list='$(dist_pythonyaml2_DATA)'; test -n "$(pythonyaml2dir)" || list=; \ + if test -n "$$list"; then \ + echo " $(MKDIR_P) '$(DESTDIR)$(pythonyaml2dir)'"; \ + $(MKDIR_P) "$(DESTDIR)$(pythonyaml2dir)" || exit 1; \ + fi; \ + for p in $$list; do \ + if test -f "$$p"; then d=; else d="$(srcdir)/"; fi; \ + echo "$$d$$p"; \ + done | $(am__base_list) | \ + while read files; do \ + echo " $(INSTALL_DATA) $$files '$(DESTDIR)$(pythonyaml2dir)'"; \ + $(INSTALL_DATA) $$files "$(DESTDIR)$(pythonyaml2dir)" || exit $$?; \ + done + +uninstall-dist_pythonyaml2DATA: + @$(NORMAL_UNINSTALL) + @list='$(dist_pythonyaml2_DATA)'; test -n "$(pythonyaml2dir)" || list=; \ + files=`for p in $$list; do echo $$p; done | sed -e 's|^.*/||'`; \ + dir='$(DESTDIR)$(pythonyaml2dir)'; $(am__uninstall_files_from_dir) +install-dist_pythonyaml3DATA: $(dist_pythonyaml3_DATA) + @$(NORMAL_INSTALL) + @list='$(dist_pythonyaml3_DATA)'; test -n "$(pythonyaml3dir)" || list=; \ + if test -n "$$list"; then \ + echo " $(MKDIR_P) '$(DESTDIR)$(pythonyaml3dir)'"; \ + $(MKDIR_P) "$(DESTDIR)$(pythonyaml3dir)" || exit 1; \ + fi; \ + for p in $$list; do \ + if test -f "$$p"; then d=; else d="$(srcdir)/"; fi; \ + echo "$$d$$p"; \ + done | $(am__base_list) | \ + while read files; do \ + echo " $(INSTALL_DATA) $$files '$(DESTDIR)$(pythonyaml3dir)'"; \ + $(INSTALL_DATA) $$files "$(DESTDIR)$(pythonyaml3dir)" || exit $$?; \ + done + +uninstall-dist_pythonyaml3DATA: + @$(NORMAL_UNINSTALL) + @list='$(dist_pythonyaml3_DATA)'; test -n "$(pythonyaml3dir)" || list=; \ + files=`for p in $$list; do echo $$p; done | sed -e 's|^.*/||'`; \ + dir='$(DESTDIR)$(pythonyaml3dir)'; $(am__uninstall_files_from_dir) +tags TAGS: + +ctags CTAGS: + +cscope cscopelist: + + +distdir: $(DISTFILES) + @srcdirstrip=`echo "$(srcdir)" | sed 's/[].[^$$\\*]/\\\\&/g'`; \ + topsrcdirstrip=`echo "$(top_srcdir)" | sed 's/[].[^$$\\*]/\\\\&/g'`; \ + list='$(DISTFILES)'; \ + dist_files=`for file in $$list; do echo $$file; done | \ + sed -e "s|^$$srcdirstrip/||;t" \ + -e "s|^$$topsrcdirstrip/|$(top_builddir)/|;t"`; \ + case $$dist_files in \ + */*) $(MKDIR_P) `echo "$$dist_files" | \ + sed '/\//!d;s|^|$(distdir)/|;s,/[^/]*$$,,' | \ + sort -u` ;; \ + esac; \ + for file in $$dist_files; do \ + if test -f $$file || test -d $$file; then d=.; else d=$(srcdir); fi; \ + if test -d $$d/$$file; then \ + dir=`echo "/$$file" | sed -e 's,/[^/]*$$,,'`; \ + if test -d "$(distdir)/$$file"; then \ + find "$(distdir)/$$file" -type d ! -perm -700 -exec chmod u+rwx {} \;; \ + fi; \ + if test -d $(srcdir)/$$file && test $$d != $(srcdir); then \ + cp -fpR $(srcdir)/$$file "$(distdir)$$dir" || exit 1; \ + find "$(distdir)/$$file" -type d ! -perm -700 -exec chmod u+rwx {} \;; \ + fi; \ + cp -fpR $$d/$$file "$(distdir)$$dir" || exit 1; \ + else \ + test -f "$(distdir)/$$file" \ + || cp -p $$d/$$file "$(distdir)/$$file" \ + || exit 1; \ + fi; \ + done +check-am: all-am +check: check-am +all-am: Makefile $(SCRIPTS) $(DATA) +installdirs: + for dir in "$(DESTDIR)$(pythondir)" "$(DESTDIR)$(pythondir)" "$(DESTDIR)$(pythonmodulesdir)" "$(DESTDIR)$(pythonyaml2dir)" "$(DESTDIR)$(pythonyaml3dir)"; do \ + test -z "$$dir" || $(MKDIR_P) "$$dir"; \ + done +install: install-am +install-exec: install-exec-am +install-data: install-data-am +uninstall: uninstall-am + +install-am: all-am + @$(MAKE) $(AM_MAKEFLAGS) install-exec-am install-data-am + +installcheck: installcheck-am +install-strip: + if test -z '$(STRIP)'; then \ + $(MAKE) $(AM_MAKEFLAGS) INSTALL_PROGRAM="$(INSTALL_STRIP_PROGRAM)" \ + install_sh_PROGRAM="$(INSTALL_STRIP_PROGRAM)" INSTALL_STRIP_FLAG=-s \ + install; \ + else \ + $(MAKE) $(AM_MAKEFLAGS) INSTALL_PROGRAM="$(INSTALL_STRIP_PROGRAM)" \ + install_sh_PROGRAM="$(INSTALL_STRIP_PROGRAM)" INSTALL_STRIP_FLAG=-s \ + "INSTALL_PROGRAM_ENV=STRIPPROG='$(STRIP)'" install; \ + fi +mostlyclean-generic: + +clean-generic: + -test -z "$(CLEANFILES)" || rm -f $(CLEANFILES) + +distclean-generic: + -test -z "$(CONFIG_CLEAN_FILES)" || rm -f $(CONFIG_CLEAN_FILES) + -test . = "$(srcdir)" || test -z "$(CONFIG_CLEAN_VPATH_FILES)" || rm -f $(CONFIG_CLEAN_VPATH_FILES) + +maintainer-clean-generic: + @echo "This command is intended for maintainers to use" + @echo "it deletes files that may require special tools to rebuild." + -test -z "$(MAINTAINERCLEANFILES)" || rm -f $(MAINTAINERCLEANFILES) +clean: clean-am + +clean-am: clean-generic mostlyclean-am + +distclean: distclean-am + -rm -f Makefile +distclean-am: clean-am distclean-generic + +dvi: dvi-am + +dvi-am: + +html: html-am + +html-am: + +info: info-am + +info-am: + +install-data-am: install-dist_pythonDATA install-dist_pythonSCRIPTS \ + install-dist_pythonmodulesDATA install-dist_pythonyaml2DATA \ + install-dist_pythonyaml3DATA + +install-dvi: install-dvi-am + +install-dvi-am: + +install-exec-am: + +install-html: install-html-am + +install-html-am: + +install-info: install-info-am + +install-info-am: + +install-man: + +install-pdf: install-pdf-am + +install-pdf-am: + +install-ps: install-ps-am + +install-ps-am: + +installcheck-am: + +maintainer-clean: maintainer-clean-am + -rm -f Makefile +maintainer-clean-am: distclean-am maintainer-clean-generic + +mostlyclean: mostlyclean-am + +mostlyclean-am: mostlyclean-generic + +pdf: pdf-am + +pdf-am: + +ps: ps-am + +ps-am: + +uninstall-am: uninstall-dist_pythonDATA uninstall-dist_pythonSCRIPTS \ + uninstall-dist_pythonmodulesDATA \ + uninstall-dist_pythonyaml2DATA uninstall-dist_pythonyaml3DATA + +.MAKE: install-am install-strip + +.PHONY: all all-am check check-am clean clean-generic cscopelist-am \ + ctags-am distclean distclean-generic distdir dvi dvi-am html \ + html-am info info-am install install-am install-data \ + install-data-am install-dist_pythonDATA \ + install-dist_pythonSCRIPTS install-dist_pythonmodulesDATA \ + install-dist_pythonyaml2DATA install-dist_pythonyaml3DATA \ + install-dvi install-dvi-am install-exec install-exec-am \ + install-html install-html-am install-info install-info-am \ + install-man install-pdf install-pdf-am install-ps \ + install-ps-am install-strip installcheck installcheck-am \ + installdirs maintainer-clean maintainer-clean-generic \ + mostlyclean mostlyclean-generic pdf pdf-am ps ps-am tags-am \ + uninstall uninstall-am uninstall-dist_pythonDATA \ + uninstall-dist_pythonSCRIPTS uninstall-dist_pythonmodulesDATA \ + uninstall-dist_pythonyaml2DATA uninstall-dist_pythonyaml3DATA + +.in: + if sed \ + -e 's#[@]localstatedir_POST@#$(localstatedir)#g' \ + -e 's#[@]sbindir_POST@#$(sbindir)#g' \ + -e 's#[@]sysconfdir_POST@#$(sysconfdir)#g' \ + -e 's#[@]pythondir_POST@#$(pythondir)#g' \ + $< > $@.tmp; then \ + mv "$@.tmp" "$@"; \ + else \ + rm -f "$@.tmp"; \ + false; \ + fi + +# Tell versions [3.59,3.63) of GNU make to not export all variables. +# Otherwise a system limit (for SysV at least) may be exceeded. +.NOEXPORT: diff --git a/python.d/README.md b/python.d/README.md new file mode 100644 index 00000000..4cc4d8d2 --- /dev/null +++ b/python.d/README.md @@ -0,0 +1,698 @@ +# Disclaimer + +Every module should be compatible with python2 and python3. +All third party libraries should be installed system-wide or in `python_modules` directory. +Module configurations are written in YAML and **pyYAML is required**. + +Every configuration file must have one of two formats: + +- Configuration for only one job: + +```yaml +update_every : 2 # update frequency +retries : 1 # how many failures in update() is tolerated +priority : 20000 # where it is shown on dashboard + +other_var1 : bla # variables passed to module +other_var2 : alb +``` + +- Configuration for many jobs (ex. mysql): + +```yaml +# module defaults: +update_every : 2 +retries : 1 +priority : 20000 + +local: # job name + update_every : 5 # job update frequency + other_var1 : some_val # module specific variable + +other_job: + priority : 5 # job position on dashboard + retries : 20 # job retries + other_var2 : val # module specific variable +``` + +`update_every`, `retries`, and `priority` are always optional. + +--- + +The following python.d modules are supported: + +# apache + +This module will monitor one or more apache servers depending on configuration. + +**Requirements:** + * apache with enabled `mod_status` + +It produces following charts: + +1. **Requests** in requests/s + * requests + +2. **Connections** + * connections + +3. **Async Connections** + * keepalive + * closing + * writing + +4. **Bandwidth** in kilobytes/s + * sent + +5. **Workers** + * idle + * busy + +6. **Lifetime Avg. Requests/s** in requests/s + * requests_sec + +7. **Lifetime Avg. Bandwidth/s** in kilobytes/s + * size_sec + +8. **Lifetime Avg. Response Size** in bytes/request + * size_req + +### configuration + +Needs only `url` to server's `server-status?auto` + +Here is an example for 2 servers: + +```yaml +update_every : 10 +priority : 90100 + +local: + url : 'http://localhost/server-status?auto' + retries : 20 + +remote: + url : 'http://www.apache.org/server-status?auto' + update_every : 5 + retries : 4 +``` + +Without configuration, module attempts to connect to `http://localhost/server-status?auto` + +--- + +# apache_cache + +Module monitors apache mod_cache log and produces only one chart: + +**cached responses** in percent cached + * hit + * miss + * other + +### configuration + +Sample: + +```yaml +update_every : 10 +priority : 120000 +retries : 5 +log_path : '/var/log/apache2/cache.log' +``` + +If no configuration is given, module will attempt to read log file at `/var/log/apache2/cache.log` + +--- + +# cpufreq + +Module shows current cpu frequency by looking at appropriate files in /sys/devices + +**Requirement:** +Processor which presents data scaling frequency data + +It produces one chart with multiple lines (one line per core). + +### configuration + +Sample: + +```yaml +sys_dir: "/sys/devices" +``` + +If no configuration is given, module will search for `scaling_cur_freq` files in `/sys/devices` directory. +Directory is also prefixed with `NETDATA_HOST_PREFIX` if specified. + +--- + +# dovecot + +This module provides statistics information from dovecot server. +Statistics are taken from dovecot socket by executing `EXPORT global` command. +More information about dovecot stats can be found on [project wiki page.](http://wiki2.dovecot.org/Statistics) + +**Requirement:** +Dovecot unix socket with R/W permissions for user netdata or dovecot with configured TCP/IP socket. + +Module gives information with following charts: + +1. **logins and sessions** + * logins + * active sessions + +2. **commands** - number of IMAP commands + * commands + +3. **Faults** + * minor + * major + +4. **Context Switches** + * volountary + * involountary + +5. **disk** in bytes/s + * read + * write + +6. **bytes** in bytes/s + * read + * write + +7. **number of syscalls** in syscalls/s + * read + * write + +8. **lookups** - number of lookups per second + * path + * attr + +9. **hits** - number of cache hits + * hits + +10. **attempts** - authorization attemts + * success + * failure + +11. **cache** - cached authorization hits + * hit + * miss + +### configuration + +Sample: + +```yaml +localtcpip: + name : 'local' + host : '127.0.0.1' + port : 24242 + +localsocket: + name : 'local' + socket : '/var/run/dovecot/stats' +``` + +If no configuration is given, module will attempt to connect to dovecot using unix socket localized in `/var/run/dovecot/stats` + +--- + +# exim + +Simple module executing `exim -bpc` to grab exim queue. +This command can take a lot of time to finish its execution thus it is not recommended to run it every second. + +It produces only one chart: + +1. **Exim Queue Emails** + * emails + +Configuration is not needed. + +--- + +# hddtemp + +Module monitors disk temperatures from one or more hddtemp daemons + +**Requirement:** +Running `hddtemp` in daemonized mode with access on tcp port + +It produces one chart **Temperature** with dynamic number of dimensions (one per disk) + +### configuration + +Sample: + +```yaml +update_every: 3 +host: "127.0.0.1" +port: 7634 +``` + +If no configuration is given, module will attempt to connect to hddtemp daemon on `127.0.0.1:7634` address + +--- + +# IPFS + +Module monitors [IPFS](https://ipfs.io) basic information. + +1. **Bandwidth** in kbits/s + * in + * out + +2. **Peers** + * peers + +### configuration + +Only url to IPFS server is needed. + +Sample: + +```yaml +localhost: + name : 'local' + url : 'http://localhost:5001' +``` + +--- + +# memcached + +Memcached monitoring module. Data grabbed from [stats interface](https://github.com/memcached/memcached/wiki/Commands#stats). + +1. **Network** in kilobytes/s + * read + * written + +2. **Connections** per second + * current + * rejected + * total + +3. **Items** in cluster + * current + * total + +4. **Evicted and Reclaimed** items + * evicted + * reclaimed + +5. **GET** requests/s + * hits + * misses + +6. **GET rate** rate in requests/s + * rate + +7. **SET rate** rate in requests/s + * rate + +8. **DELETE** requests/s + * hits + * misses + +9. **CAS** requests/s + * hits + * misses + * bad value + +10. **Increment** requests/s + * hits + * misses + +11. **Decrement** requests/s + * hits + * misses + +12. **Touch** requests/s + * hits + * misses + +13. **Touch rate** rate in requests/s + * rate + +### configuration + +Sample: + +```yaml +localtcpip: + name : 'local' + host : '127.0.0.1' + port : 24242 +``` + +If no configuration is given, module will attempt to connect to memcached instance on `127.0.0.1:11211` address. + +--- + +# mysql + +Module monitors one or more mysql servers + +**Requirements:** + * python library [MySQLdb](https://github.com/PyMySQL/mysqlclient-python) (faster) or [PyMySQL](https://github.com/PyMySQL/PyMySQL) (slower) + +It will produce following charts (if data is available): + +1. **Bandwidth** in kbps + * in + * out + +2. **Queries** in queries/sec + * queries + * questions + * slow queries + +3. **Operations** in operations/sec + * opened tables + * flush + * commit + * delete + * prepare + * read first + * read key + * read next + * read prev + * read random + * read random next + * rollback + * save point + * update + * write + +4. **Table Locks** in locks/sec + * immediate + * waited + +5. **Select Issues** in issues/sec + * full join + * full range join + * range + * range check + * scan + +6. **Sort Issues** in issues/sec + * merge passes + * range + * scan + +### configuration + +You can provide, per server, the following: + +1. username which have access to database (deafults to 'root') +2. password (defaults to none) +3. mysql my.cnf configuration file +4. mysql socket (optional) +5. mysql host (ip or hostname) +6. mysql port (defaults to 3306) + +Here is an example for 3 servers: + +```yaml +update_every : 10 +priority : 90100 +retries : 5 + +local: + 'my.cnf' : '/etc/mysql/my.cnf' + priority : 90000 + +local_2: + user : 'root' + pass : 'blablablabla' + socket : '/var/run/mysqld/mysqld.sock' + update_every : 1 + +remote: + user : 'admin' + pass : 'bla' + host : 'example.org' + port : 9000 + retries : 20 +``` + +If no configuration is given, module will attempt to connect to mysql server via unix socket at `/var/run/mysqld/mysqld.sock` without password and with username `root` + +--- + +# nginx + +This module will monitor one or more nginx servers depending on configuration. + +**Requirements:** + * nginx with configured `stub_status` + +It produces following charts: + +1. **Active Connections** + * active + +2. **Requests** in requests/s + * requests + +3. **Active Connections by Status** + * reading + * writing + * waiting + +4. **Connections Rate** in connections/s + * accepts + * handled + +### configuration + +Needs only `url` to server's `stub_status` + +Here is an example for local server: + +```yaml +update_every : 10 +priority : 90100 + +local: + url : 'http://localhost/stub_status' + retries : 10 +``` + +Without configuration, module attempts to connect to `http://localhost/stub_status` + +--- + +# nginx_log + +Module monitors nginx access log and produces only one chart: + +1. **nginx status codes** in requests/s + * 2xx + * 3xx + * 4xx + * 5xx + +### configuration + +Sample for two vhosts: + +```yaml +site_A: + path: '/var/log/nginx/access-A.log' + +site_B: + name: 'local' + path: '/var/log/nginx/access-B.log' +``` + +When no configuration file is found, module tries to parse `/var/log/nginx/access.log` file. + +--- + +# phpfpm + +This module will monitor one or more php-fpm instances depending on configuration. + +**Requirements:** + * php-fpm with enabled `status` page + * access to `status` page via web server + +It produces following charts: + +1. **Active Connections** + * active + * maxActive + * idle + +2. **Requests** in requests/s + * requests + +3. **Performance** + * reached + * slow + +### configuration + +Needs only `url` to server's `status` + +Here is an example for local instance: + +```yaml +update_every : 3 +priority : 90100 + +local: + url : 'http://localhost/status' + retries : 10 +``` + +Without configuration, module attempts to connect to `http://localhost/status` + +--- + +# postfix + +Simple module executing `postfix -p` to grab postfix queue. + +It produces only two charts: + +1. **Postfix Queue Emails** + * emails + +2. **Postfix Queue Emails Size** in KB + * size + +Configuration is not needed. + +--- + +# redis + +Get INFO data from redis instance. + +Following charts are drawn: + +1. **Operations** per second + * operations + +2. **Hit rate** in percent + * rate + +3. **Memory utilization** in kilobytes + * total + * lua + +4. **Database keys** + * lines are creates dynamically based on how many databases are there + +5. **Clients** + * connected + * blocked + +6. **Slaves** + * connected + +### configuration + +```yaml +socket: + name : 'local' + socket : '/var/lib/redis/redis.sock' + +localhost: + name : 'local' + host : 'localhost' + port : 6379 +``` + +When no configuration file is found, module tries to connect to TCP/IP socket: `localhost:6379`. + +--- + +# sensors + +System sensors information. + +Charts are created dynamically. + +### configuration + +For detailed configuration information please read [`sensors.conf`](https://github.com/firehol/netdata/blob/master/conf.d/python.d/sensors.conf) file. + +--- + +# squid + +This module will monitor one or more squid instances depending on configuration. + +It produces following charts: + +1. **Client Bandwidth** in kilobits/s + * in + * out + * hits + +2. **Client Requests** in requests/s + * requests + * hits + * errors + +3. **Server Bandwidth** in kilobits/s + * in + * out + +4. **Server Requests** in requests/s + * requests + * errors + +### configuration + +```yaml +priority : 50000 + +local: + request : 'cache_object://localhost:3128/counters' + host : 'localhost' + port : 3128 +``` + +Without any configuration module will try to autodetect where squid presents its `counters` data + +--- + +# tomcat + +Present tomcat containers memory utilization. + +Charts: + +1. **Requests** per second + * accesses + +2. **Volume** in KB/s + * volume + +3. **Threads** + * current + * busy + +4. **JVM Free Memory** in MB + * jvm + +### configuration + +```yaml +localhost: + name : 'local' + url : 'http://127.0.0.1:8080/manager/status?XML=true' + user : 'tomcat_username' + pass : 'secret_tomcat_password' +``` + +Without configuration, module attempts to connect to `http://localhost:8080/manager/status?XML=true`, without any credentials. +So it will probably fail. + +--- diff --git a/python.d/apache.chart.py b/python.d/apache.chart.py new file mode 100644 index 00000000..2e4d16dd --- /dev/null +++ b/python.d/apache.chart.py @@ -0,0 +1,108 @@ +# -*- coding: utf-8 -*- +# Description: apache netdata python.d module +# Author: Pawel Krupa (paulfantom) + +from base import UrlService + +# default module values (can be overridden per job in `config`) +# update_every = 2 +priority = 60000 +retries = 60 + +# default job configuration (overridden by python.d.plugin) +# config = {'local': { +# 'update_every': update_every, +# 'retries': retries, +# 'priority': priority, +# 'url': 'http://www.apache.org/server-status?auto' +# }} + +# charts order (can be overridden if you want less charts, or different order) +ORDER = ['requests', 'connections', 'conns_async', 'net', 'workers', 'reqpersec', 'bytespersec', 'bytesperreq'] + +CHARTS = { + 'bytesperreq': { + 'options': [None, 'apache Lifetime Avg. Response Size', 'bytes/request', 'statistics', 'apache.bytesperreq', 'area'], + 'lines': [ + ["size_req"] + ]}, + 'workers': { + 'options': [None, 'apache Workers', 'workers', 'workers', 'apache.workers', 'stacked'], + 'lines': [ + ["idle"], + ["busy"] + ]}, + 'reqpersec': { + 'options': [None, 'apache Lifetime Avg. Requests/s', 'requests/s', 'statistics', 'apache.reqpersec', 'area'], + 'lines': [ + ["requests_sec"] + ]}, + 'bytespersec': { + 'options': [None, 'apache Lifetime Avg. Bandwidth/s', 'kilobytes/s', 'statistics', 'apache.bytesperreq', 'area'], + 'lines': [ + ["size_sec", None, 'absolute', 1, 1000] + ]}, + 'requests': { + 'options': [None, 'apache Requests', 'requests/s', 'requests', 'apache.requests', 'line'], + 'lines': [ + ["requests", None, 'incremental'] + ]}, + 'net': { + 'options': [None, 'apache Bandwidth', 'kilobytes/s', 'bandwidth', 'apache.net', 'area'], + 'lines': [ + ["sent", None, 'incremental'] + ]}, + 'connections': { + 'options': [None, 'apache Connections', 'connections', 'connections', 'apache.connections', 'line'], + 'lines': [ + ["connections"] + ]}, + 'conns_async': { + 'options': [None, 'apache Async Connections', 'connections', 'connections', 'apache.conns_async', 'stacked'], + 'lines': [ + ["keepalive"], + ["closing"], + ["writing"] + ]} +} + + +class Service(UrlService): + def __init__(self, configuration=None, name=None): + UrlService.__init__(self, configuration=configuration, name=name) + if len(self.url) == 0: + self.url = "http://localhost/server-status?auto" + self.order = ORDER + self.definitions = CHARTS + self.assignment = {"BytesPerReq": 'size_req', + "IdleWorkers": 'idle', + "BusyWorkers": 'busy', + "ReqPerSec": 'requests_sec', + "BytesPerSec": 'size_sec', + "Total Accesses": 'requests', + "Total kBytes": 'sent', + "ConnsTotal": 'connections', + "ConnsAsyncKeepAlive": 'keepalive', + "ConnsAsyncClosing": 'closing', + "ConnsAsyncWriting": 'writing'} + + def _get_data(self): + """ + Format data received from http request + :return: dict + """ + try: + raw = self._get_raw_data().split("\n") + except AttributeError: + return None + data = {} + for row in raw: + tmp = row.split(":") + if str(tmp[0]) in self.assignment: + try: + data[self.assignment[tmp[0]]] = int(float(tmp[1])) + except (IndexError, ValueError): + pass + if len(data) == 0: + return None + return data diff --git a/python.d/apache_cache.chart.py b/python.d/apache_cache.chart.py new file mode 100644 index 00000000..3681a851 --- /dev/null +++ b/python.d/apache_cache.chart.py @@ -0,0 +1,60 @@ +# -*- coding: utf-8 -*- +# Description: apache cache netdata python.d module +# Author: Pawel Krupa (paulfantom) + +from base import LogService + +priority = 60000 +retries = 60 +# update_every = 3 + +ORDER = ['cache'] +CHARTS = { + 'cache': { + 'options': [None, 'apache cached responses', 'percent cached', 'cached', 'apache_cache.cache', 'stacked'], + 'lines': [ + ["hit", 'cache', "percentage-of-absolute-row"], + ["miss", None, "percentage-of-absolute-row"], + ["other", None, "percentage-of-absolute-row"] + ]} +} + + +class Service(LogService): + def __init__(self, configuration=None, name=None): + LogService.__init__(self, configuration=configuration, name=name) + if len(self.log_path) == 0: + self.log_path = "/var/log/apache2/cache.log" + self.order = ORDER + self.definitions = CHARTS + + def _get_data(self): + """ + Parse new log lines + :return: dict + """ + try: + raw = self._get_raw_data() + if raw is None: + return None + elif not raw: + return {'hit': 0, + 'miss': 0, + 'other': 0} + except (ValueError, AttributeError): + return None + + hit = 0 + miss = 0 + other = 0 + for line in raw: + if "cache hit" in line: + hit += 1 + elif "cache miss" in line: + miss += 1 + else: + other += 1 + + return {'hit': hit, + 'miss': miss, + 'other': other} diff --git a/python.d/cpufreq.chart.py b/python.d/cpufreq.chart.py new file mode 100644 index 00000000..a9de5ced --- /dev/null +++ b/python.d/cpufreq.chart.py @@ -0,0 +1,84 @@ +# -*- coding: utf-8 -*- +# Description: cpufreq netdata python.d module +# Author: Pawel Krupa (paulfantom) + +import os +from base import SimpleService + +# default module values (can be overridden per job in `config`) +# update_every = 2 + +ORDER = ['cpufreq'] + +CHARTS = { + 'cpufreq': { + 'options': [None, 'CPU Clock', 'MHz', 'cpufreq', None, 'line'], + 'lines': [ + # lines are created dynamically in `check()` method + ]} +} + + +class Service(SimpleService): + def __init__(self, configuration=None, name=None): + prefix = os.getenv('NETDATA_HOST_PREFIX', "") + if prefix.endswith('/'): + prefix = prefix[:-1] + self.sys_dir = prefix + "/sys/devices" + self.filename = "scaling_cur_freq" + SimpleService.__init__(self, configuration=configuration, name=name) + self.order = ORDER + self.definitions = CHARTS + self._orig_name = "" + self.assignment = {} + self.paths = [] + + def _get_data(self): + raw = {} + for path in self.paths: + with open(path, 'r') as f: + raw[path] = f.read() + data = {} + for path in self.paths: + data[self.assignment[path]] = raw[path] + return data + + def check(self): + try: + self.sys_dir = str(self.configuration['sys_dir']) + except (KeyError, TypeError): + self.error("No path specified. Using: '" + self.sys_dir + "'") + + self._orig_name = self.chart_name + + for dirpath, _, filenames in os.walk(self.sys_dir): + if self.filename in filenames: + self.paths.append(dirpath + "/" + self.filename) + + if len(self.paths) == 0: + self.error("cannot find", self.filename) + return False + + self.paths.sort() + i = 0 + for path in self.paths: + self.assignment[path] = "cpu" + str(i) + i += 1 + + for name in self.assignment: + dim = self.assignment[name] + self.definitions[ORDER[0]]['lines'].append([dim, dim, 'absolute', 1, 1000]) + + return True + + def create(self): + self.chart_name = "cpu" + status = SimpleService.create(self) + self.chart_name = self._orig_name + return status + + def update(self, interval): + self.chart_name = "cpu" + status = SimpleService.update(self, interval=interval) + self.chart_name = self._orig_name + return status diff --git a/python.d/dovecot.chart.py b/python.d/dovecot.chart.py new file mode 100644 index 00000000..586478cd --- /dev/null +++ b/python.d/dovecot.chart.py @@ -0,0 +1,127 @@ +# -*- coding: utf-8 -*- +# Description: dovecot netdata python.d module +# Author: Pawel Krupa (paulfantom) + +from base import SocketService + +# default module values (can be overridden per job in `config`) +# update_every = 2 +priority = 60000 +retries = 60 + +# charts order (can be overridden if you want less charts, or different order) +ORDER = ['sessions', 'commands', + 'faults', + 'context_switches', + 'disk', 'bytes', 'syscalls', + 'lookup', 'cache', + 'auth', 'auth_cache'] + +CHARTS = { + 'sessions': { + 'options': [None, "logins and sessions", 'number', 'IMAP', 'dovecot.sessions', 'line'], + 'lines': [ + ['num_logins', 'logins', 'absolute'], + ['num_connected_sessions', 'active sessions', 'absolute'] + ]}, + 'commands': { + 'options': [None, "commands", "commands", 'IMAP', 'dovecot.commands', 'line'], + 'lines': [ + ['num_cmds', 'commands', 'absolute'] + ]}, + 'faults': { + 'options': [None, "faults", "faults", 'Faults', 'dovecot.faults', 'line'], + 'lines': [ + ['min_faults', 'minor', 'absolute'], + ['maj_faults', 'major', 'absolute'] + ]}, + 'context_switches': { + 'options': [None, "context switches", '', 'Context Switches', 'dovecot.context_switches', 'line'], + 'lines': [ + ['vol_cs', 'volountary', 'absolute'], + ['invol_cs', 'involountary', 'absolute'] + ]}, + 'disk': { + 'options': [None, "disk", 'bytes/s', 'Reads and Writes', 'dovecot.disk', 'line'], + 'lines': [ + ['disk_input', 'read', 'incremental'], + ['disk_output', 'write', 'incremental'] + ]}, + 'bytes': { + 'options': [None, "bytes", 'bytes/s', 'Reads and Writes', 'dovecot.bytes', 'line'], + 'lines': [ + ['read_bytes', 'read', 'incremental'], + ['write_bytes', 'write', 'incremental'] + ]}, + 'syscalls': { + 'options': [None, "number of syscalls", 'syscalls/s', 'Reads and Writes', 'dovecot.syscalls', 'line'], + 'lines': [ + ['read_count', 'read', 'incremental'], + ['write_count', 'write', 'incremental'] + ]}, + 'lookup': { + 'options': [None, "lookups", 'number/s', 'Mail', 'dovecot.lookup', 'line'], + 'lines': [ + ['mail_lookup_path', 'path', 'incremental'], + ['mail_lookup_attr', 'attr', 'incremental'] + ]}, + 'cache': { + 'options': [None, "hits", 'hits/s', 'Mail', 'dovecot.cache', 'line'], + 'lines': [ + ['mail_cache_hits', 'hits', 'incremental'] + ]}, + 'auth': { + 'options': [None, "attempts", 'attempts', 'Authentication', 'dovecot.auth', 'stacked'], + 'lines': [ + ['auth_successes', 'success', 'absolute'], + ['auth_failures', 'failure', 'absolute'] + ]}, + 'auth_cache': { + 'options': [None, "cache", 'number', 'Authentication', 'dovecot.auth_cache', 'stacked'], + 'lines': [ + ['auth_cache_hits', 'hit', 'absolute'], + ['auth_cache_misses', 'miss', 'absolute'] + ]} +} + + +class Service(SocketService): + def __init__(self, configuration=None, name=None): + SocketService.__init__(self, configuration=configuration, name=name) + self.request = "EXPORT\tglobal\r\n" + self.host = None # localhost + self.port = None # 24242 + # self._keep_alive = True + self.unix_socket = "/var/run/dovecot/stats" + self.order = ORDER + self.definitions = CHARTS + + def _get_data(self): + """ + Format data received from socket + :return: dict + """ + try: + raw = self._get_raw_data() + except (ValueError, AttributeError): + return None + + data = raw.split('\n')[:2] + desc = data[0].split('\t') + vals = data[1].split('\t') + # ret = dict(zip(desc, vals)) + ret = {} + for i in range(len(desc)): + try: + #d = str(desc[i]) + #if d in ('user_cpu', 'sys_cpu', 'clock_time'): + # val = float(vals[i]) + #else: + # val = int(vals[i]) + #ret[d] = val + ret[str(desc[i])] = int(vals[i]) + except ValueError: + pass + if len(ret) == 0: + return None + return ret diff --git a/python.d/example.chart.py b/python.d/example.chart.py new file mode 100644 index 00000000..adf97a92 --- /dev/null +++ b/python.d/example.chart.py @@ -0,0 +1,36 @@ +# -*- coding: utf-8 -*- +# Description: example netdata python.d module +# Author: Pawel Krupa (paulfantom) + +import os +import random +from base import SimpleService + +NAME = os.path.basename(__file__).replace(".chart.py", "") + +# default module values +# update_every = 4 +priority = 90000 +retries = 60 + + +class Service(SimpleService): + def __init__(self, configuration=None, name=None): + super(self.__class__,self).__init__(configuration=configuration, name=name) + + def check(self): + return True + + def create(self): + self.chart("example.python_random", '', 'A random number', 'random number', + 'random', 'random', 'line', self.priority, self.update_every) + self.dimension('random1') + self.commit() + return True + + def update(self, interval): + self.begin("example.python_random", interval) + self.set("random1", random.randint(0, 100)) + self.end() + self.commit() + return True diff --git a/python.d/exim.chart.py b/python.d/exim.chart.py new file mode 100644 index 00000000..1858cbc7 --- /dev/null +++ b/python.d/exim.chart.py @@ -0,0 +1,39 @@ +# -*- coding: utf-8 -*- +# Description: exim netdata python.d module +# Author: Pawel Krupa (paulfantom) + +from base import ExecutableService + +# default module values (can be overridden per job in `config`) +# update_every = 2 +priority = 60000 +retries = 60 + +# charts order (can be overridden if you want less charts, or different order) +ORDER = ['qemails'] + +CHARTS = { + 'qemails': { + 'options': [None, "Exim Queue Emails", "emails", 'queue', 'exim.qemails', 'line'], + 'lines': [ + ['emails', None, 'absolute'] + ]} +} + + +class Service(ExecutableService): + def __init__(self, configuration=None, name=None): + ExecutableService.__init__(self, configuration=configuration, name=name) + self.command = "exim -bpc" + self.order = ORDER + self.definitions = CHARTS + + def _get_data(self): + """ + Format data received from shell command + :return: dict + """ + try: + return {'emails': int(self._get_raw_data()[0])} + except (ValueError, AttributeError): + return None diff --git a/python.d/hddtemp.chart.py b/python.d/hddtemp.chart.py new file mode 100644 index 00000000..4271001b --- /dev/null +++ b/python.d/hddtemp.chart.py @@ -0,0 +1,114 @@ +# -*- coding: utf-8 -*- +# Description: hddtemp netdata python.d module +# Author: Pawel Krupa (paulfantom) + +import os +from base import SocketService + +# default module values (can be overridden per job in `config`) +#update_every = 2 +priority = 60000 +retries = 60 + +# default job configuration (overridden by python.d.plugin) +# config = {'local': { +# 'update_every': update_every, +# 'retries': retries, +# 'priority': priority, +# 'host': 'localhost', +# 'port': 7634 +# }} + +ORDER = ['temperatures'] + +CHARTS = { + 'temperatures': { + 'options': ['disks_temp', 'temperature', 'Celsius', 'Disks temperature', 'hddtemp.temperatures', 'line'], + 'lines': [ + # lines are created dynamically in `check()` method + ]} +} + + +class Service(SocketService): + def __init__(self, configuration=None, name=None): + SocketService.__init__(self, configuration=configuration, name=name) + self._keep_alive = False + self.request = "" + self.host = "127.0.0.1" + self.port = 7634 + self.order = ORDER + self.definitions = CHARTS + self.disks = [] + + def _get_disks(self): + try: + disks = self.configuration['devices'] + print(disks) + except (KeyError, TypeError) as e: + self.info("Autodetecting disks") + return ["/dev/" + f for f in os.listdir("/dev") if len(f) == 3 and f.startswith("sd")] + + ret = [] + for disk in disks: + if not disk.startswith('/dev/'): + disk = "/dev/" + disk + if os.path.exists(disk): + ret.append(disk) + if len(ret) == 0: + self.error("Provided disks cannot be found in /dev directory.") + return ret + + def _check_raw_data(self, data): + if not data.endswith('|'): + return False + + if all(disk in data for disk in self.disks): + return True + + return False + + def _get_data(self): + """ + Get data from TCP/IP socket + :return: dict + """ + try: + raw = self._get_raw_data().split("|")[:-1] + except AttributeError: + self.error("no data received") + return None + data = {} + for i in range(len(raw) // 5): + if not raw[i*5+1] in self.disks: + continue + try: + val = int(raw[i*5+3]) + except ValueError: + val = 0 + data[raw[i*5+1].replace("/dev/", "")] = val + + if len(data) == 0: + self.error("received data doesn't have needed records") + return None + else: + return data + + def check(self): + """ + Parse configuration, check if hddtemp is available, and dynamically create chart lines data + :return: boolean + """ + self._parse_config() + self.disks = self._get_disks() + + data = self._get_data() + if data is None: + return False + + for name in data: + self.definitions[ORDER[0]]['lines'].append([name]) + + return True + + diff --git a/python.d/ipfs.chart.py b/python.d/ipfs.chart.py new file mode 100644 index 00000000..b0b2a965 --- /dev/null +++ b/python.d/ipfs.chart.py @@ -0,0 +1,107 @@ +# -*- coding: utf-8 -*- +# Description: IPFS netdata python.d module +# Authors: Pawel Krupa (paulfantom), davidak + +from base import UrlService +import json + +# default module values (can be overridden per job in `config`) +# update_every = 2 +priority = 60000 +retries = 60 + +# default job configuration (overridden by python.d.plugin) +# config = {'local': { +# 'update_every': update_every, +# 'retries': retries, +# 'priority': priority, +# 'url': 'http://localhost:5001' +# }} + +# charts order (can be overridden if you want less charts, or different order) +ORDER = ['bandwidth', 'peers'] + +CHARTS = { + 'bandwidth': { + 'options': [None, 'IPFS Bandwidth', 'kbits/s', 'Bandwidth', 'ipfs.bandwidth', 'line'], + 'lines': [ + ["in", None, "absolute", 8, 1000], + ["out", None, "absolute", -8, 1000] + ]}, + 'peers': { + 'options': [None, 'IPFS Peers', 'peers', 'Peers', 'ipfs.peers', 'line'], + 'lines': [ + ["peers", None, 'absolute'] + ]} +} + + +class Service(UrlService): + def __init__(self, configuration=None, name=None): + UrlService.__init__(self, configuration=configuration, name=name) + try: + self.baseurl = str(self.configuration['url']) + except (KeyError, TypeError): + self.baseurl = "http://localhost:5001" + self.order = ORDER + self.definitions = CHARTS + + def _get_bandwidth(self): + """ + Format data received from http request + :return: int, int + """ + self.url = self.baseurl + "/api/v0/stats/bw" + try: + raw = self._get_raw_data() + except AttributeError: + return None + + try: + parsed = json.loads(raw) + bw_in = int(parsed['RateIn']) + bw_out = int(parsed['RateOut']) + except: + return None + + return bw_in, bw_out + + def _get_peers(self): + """ + Format data received from http request + :return: int + """ + self.url = self.baseurl + "/api/v0/swarm/peers" + try: + raw = self._get_raw_data() + except AttributeError: + return None + + try: + parsed = json.loads(raw) + peers = len(parsed['Strings']) + except: + return None + + return peers + + def _get_data(self): + """ + Get data from API + :return: dict + """ + try: + peers = self._get_peers() + bandwidth_in, bandwidth_out = self._get_bandwidth() + except: + return None + data = {} + if peers is not None: + data['peers'] = peers + if bandwidth_in is not None and bandwidth_out is not None: + data['in'] = bandwidth_in + data['out'] = bandwidth_out + + if len(data) == 0: + return None + return data diff --git a/python.d/memcached.chart.py b/python.d/memcached.chart.py new file mode 100644 index 00000000..5a1400c9 --- /dev/null +++ b/python.d/memcached.chart.py @@ -0,0 +1,180 @@ +# -*- coding: utf-8 -*- +# Description: memcached netdata python.d module +# Author: Pawel Krupa (paulfantom) + +from base import SocketService + +# default module values (can be overridden per job in `config`) +#update_every = 2 +priority = 60000 +retries = 60 + +# default job configuration (overridden by python.d.plugin) +# config = {'local': { +# 'update_every': update_every, +# 'retries': retries, +# 'priority': priority, +# 'host': 'localhost', +# 'port': 11211, +# 'unix_socket': None +# }} + +ORDER = ['cache', 'net', 'connections', 'items', 'evicted_reclaimed', + 'get', 'get_rate', 'set_rate', 'delete', 'cas', 'increment', 'decrement', 'touch', 'touch_rate'] + +CHARTS = { + 'cache': { + 'options': [None, 'Cache Size', 'megabytes', 'Cache', 'memcached.cache', 'stacked'], + 'lines': [ + ['used', 'used', 'absolute', 1, 1048576], + ['avail', 'available', 'absolute', 1, 1048576] + ]}, + 'net': { + 'options': [None, 'Network', 'kilobytes/s', 'Network', 'memcached.net', 'line'], + 'lines': [ + ['bytes_read', 'read', 'incremental', 1, 1024], + ['bytes_written', 'written', 'incremental', 1, 1024] + ]}, + 'connections': { + 'options': [None, 'Connections', 'connections/s', 'Cluster', 'memcached.connections', 'line'], + 'lines': [ + ['curr_connections', 'current', 'incremental'], + ['rejected_connections', 'rejected', 'incremental'], + ['total_connections', 'total', 'incremental'] + ]}, + 'items': { + 'options': [None, 'Items', 'items', 'Cluster', 'memcached.items', 'line'], + 'lines': [ + ['curr_items', 'current', 'absolute'], + ['total_items', 'total', 'absolute'] + ]}, + 'evicted_reclaimed': { + 'options': [None, 'Items', 'items', 'Evicted and Reclaimed', 'memcached.evicted_reclaimed', 'line'], + 'lines': [ + ['evictions', 'evicted', 'absolute'], + ['reclaimed', 'reclaimed', 'absolute'] + ]}, + 'get': { + 'options': [None, 'Requests', 'requests', 'GET', 'memcached.get', 'stacked'], + 'lines': [ + ['get_hits', 'hits', 'percent-of-absolute-row'], + ['get_misses', 'misses', 'percent-of-absolute-row'] + ]}, + 'get_rate': { + 'options': [None, 'Rate', 'requests/s', 'GET', 'memcached.get_rate', 'line'], + 'lines': [ + ['cmd_get', 'rate', 'incremental'] + ]}, + 'set_rate': { + 'options': [None, 'Rate', 'requests/s', 'SET', 'memcached.set_rate', 'line'], + 'lines': [ + ['cmd_set', 'rate', 'incremental'] + ]}, + 'delete': { + 'options': [None, 'Requests', 'requests', 'DELETE', 'memcached.delete', 'stacked'], + 'lines': [ + ['delete_hits', 'hits', 'percent-of-absolute-row'], + ['delete_misses', 'misses', 'percent-of-absolute-row'], + ]}, + 'cas': { + 'options': [None, 'Requests', 'requests', 'CAS', 'memcached.cas', 'stacked'], + 'lines': [ + ['cas_hits', 'hits', 'percent-of-absolute-row'], + ['cas_misses', 'misses', 'percent-of-absolute-row'], + ['cas_badval', 'bad value', 'percent-of-absolute-row'] + ]}, + 'increment': { + 'options': [None, 'Requests', 'requests', 'Increment', 'memcached.increment', 'stacked'], + 'lines': [ + ['incr_hits', 'hits', 'percent-of-absolute-row'], + ['incr_misses', 'misses', 'percent-of-absolute-row'] + ]}, + 'decrement': { + 'options': [None, 'Requests', 'requests', 'Decrement', 'memcached.decrement', 'stacked'], + 'lines': [ + ['decr_hits', 'hits', 'percent-of-absolute-row'], + ['decr_misses', 'misses', 'percent-of-absolute-row'] + ]}, + 'touch': { + 'options': [None, 'Requests', 'requests', 'Touch', 'memcached.touch', 'stacked'], + 'lines': [ + ['touch_hits', 'hits', 'percent-of-absolute-row'], + ['touch_misses', 'misses', 'percent-of-absolute-row'] + ]}, + 'touch_rate': { + 'options': [None, 'Rate', 'requests/s', 'Touch', 'memcached.touch_rate', 'line'], + 'lines': [ + ['cmd_touch', 'rate', 'incremental'] + ]} +} + + +class Service(SocketService): + def __init__(self, configuration=None, name=None): + SocketService.__init__(self, configuration=configuration, name=name) + self.request = "stats\r\n" + self.host = "localhost" + self.port = 11211 + self._keep_alive = True + self.unix_socket = None + self.order = ORDER + self.definitions = CHARTS + + def _get_data(self): + """ + Get data from socket + :return: dict + """ + try: + raw = self._get_raw_data().split("\n") + except AttributeError: + self.error("no data received") + return None + if raw[0].startswith('ERROR'): + self.error("Memcached returned ERROR") + return None + data = {} + for line in raw: + if line.startswith('STAT'): + try: + t = line[5:].split(' ') + data[t[0]] = int(t[1]) + except (IndexError, ValueError): + pass + try: + data['hit_rate'] = int((data['keyspace_hits'] / float(data['keyspace_hits'] + data['keyspace_misses'])) * 100) + except: + data['hit_rate'] = 0 + + try: + data['avail'] = int(data['limit_maxbytes']) - int(data['bytes']) + data['used'] = data['bytes'] + except: + pass + + if len(data) == 0: + self.error("received data doesn't have needed records") + return None + else: + return data + + def _check_raw_data(self, data): + if data.endswith('END\r\n'): + return True + else: + return False + + def check(self): + """ + Parse configuration, check if memcached is available + :return: boolean + """ + self._parse_config() + if self.name == "": + self.name = "local" + self.chart_name += "_" + self.name + data = self._get_data() + if data is None: + return False + + return True diff --git a/python.d/mysql.chart.py b/python.d/mysql.chart.py new file mode 100644 index 00000000..7c3931ac --- /dev/null +++ b/python.d/mysql.chart.py @@ -0,0 +1,406 @@ +# -*- coding: utf-8 -*- +# Description: MySQL netdata python.d module +# Author: Pawel Krupa (paulfantom) + +from base import SimpleService +import msg + +# import 3rd party library to handle MySQL communication +try: + import MySQLdb + + # https://github.com/PyMySQL/mysqlclient-python + msg.info("using MySQLdb") +except ImportError: + try: + import pymysql as MySQLdb + + # https://github.com/PyMySQL/PyMySQL + msg.info("using pymysql") + except ImportError: + msg.error("MySQLdb or PyMySQL module is needed to use mysql.chart.py plugin") + raise ImportError + +# default module values (can be overridden per job in `config`) +# update_every = 3 +priority = 90000 +retries = 60 + +# default configuration (overridden by python.d.plugin) +# config = { +# 'local': { +# 'user': 'root', +# 'pass': '', +# 'socket': '/var/run/mysqld/mysqld.sock', +# 'update_every': update_every, +# 'retries': retries, +# 'priority': priority +# } +#} + +# query executed on MySQL server +QUERY = "SHOW GLOBAL STATUS;" + +ORDER = ['net', + 'queries', + 'handlers', + 'table_locks', + 'join_issues', 'sort_issues', + 'tmp', + 'connections', 'connection_errors', + 'binlog_cache', 'binlog_stmt_cache', + 'threads', 'thread_cache_misses', + 'innodb_io', 'innodb_io_ops', 'innodb_io_pending_ops', 'innodb_log', 'innodb_os_log', 'innodb_os_log_io', + 'innodb_cur_row_lock', 'innodb_rows', 'innodb_buffer_pool_pages', 'innodb_buffer_pool_bytes', + 'innodb_buffer_pool_read_ahead', 'innodb_buffer_pool_reqs', 'innodb_buffer_pool_ops', + 'qcache_ops', 'qcache', 'qcache_freemem', 'qcache_memblocks', + 'key_blocks', 'key_requests', 'key_disk_ops', + 'files', 'files_rate'] + +CHARTS = { + 'net': { + 'options': [None, 'mysql Bandwidth', 'kilobits/s', 'bandwidth', 'mysql.net', 'area'], + 'lines': [ + ["Bytes_received", "in", "incremental", 8, 1024], + ["Bytes_sent", "out", "incremental", -8, 1024] + ]}, + 'queries': { + 'options': [None, 'mysql Queries', 'queries/s', 'queries', 'mysql.queries', 'line'], + 'lines': [ + ["Queries", "queries", "incremental"], + ["Questions", "questions", "incremental"], + ["Slow_queries", "slow_queries", "incremental"] + ]}, + 'handlers': { + 'options': [None, 'mysql Handlers', 'handlers/s', 'handlers', 'mysql.handlers', 'line'], + 'lines': [ + ["Handler_commit", "commit", "incremental"], + ["Handler_delete", "delete", "incremental"], + ["Handler_prepare", "prepare", "incremental"], + ["Handler_read_first", "read_first", "incremental"], + ["Handler_read_key", "read_key", "incremental"], + ["Handler_read_next", "read_next", "incremental"], + ["Handler_read_prev", "read_prev", "incremental"], + ["Handler_read_rnd", "read_rnd", "incremental"], + ["Handler_read_rnd_next", "read_rnd_next", "incremental"], + ["Handler_rollback", "rollback", "incremental"], + ["Handler_savepoint", "savepoint", "incremental"], + ["Handler_savepoint_rollback", "savepoint_rollback", "incremental"], + ["Handler_update", "update", "incremental"], + ["Handler_write", "write", "incremental"] + ]}, + 'table_locks': { + 'options': [None, 'mysql Tables Locks', 'locks/s', 'locks', 'mysql.table_locks', 'line'], + 'lines': [ + ["Table_locks_immediate", "immediate", "incremental"], + ["Table_locks_waited", "waited", "incremental", -1, 1] + ]}, + 'join_issues': { + 'options': [None, 'mysql Select Join Issues', 'joins/s', 'issues', 'mysql.join_issues', 'line'], + 'lines': [ + ["Select_full_join", "full_join", "incremental"], + ["Select_full_range_join", "full_range_join", "incremental"], + ["Select_range", "range", "incremental"], + ["Select_range_check", "range_check", "incremental"], + ["Select_scan", "scan", "incremental"] + ]}, + 'sort_issues': { + 'options': [None, 'mysql Sort Issues', 'issues/s', 'issues', 'mysql.sort_issues', 'line'], + 'lines': [ + ["Sort_merge_passes", "merge_passes", "incremental"], + ["Sort_range", "range", "incremental"], + ["Sort_scan", "scan", "incremental"] + ]}, + 'tmp': { + 'options': [None, 'mysql Tmp Operations', 'counter', 'temporaries', 'mysql.tmp', 'line'], + 'lines': [ + ["Created_tmp_disk_tables", "disk_tables", "incremental"], + ["Created_tmp_files", "files", "incremental"], + ["Created_tmp_tables", "tables", "incremental"] + ]}, + 'connections': { + 'options': [None, 'mysql Connections', 'connections/s', 'connections', 'mysql.connections', 'line'], + 'lines': [ + ["Connections", "all", "incremental"], + ["Aborted_connects", "aborted", "incremental"] + ]}, + 'binlog_cache': { + 'options': [None, 'mysql Binlog Cache', 'transactions/s', 'binlog', 'mysql.binlog_cache', 'line'], + 'lines': [ + ["Binlog_cache_disk_use", "disk", "incremental"], + ["Binlog_cache_use", "all", "incremental"] + ]}, + 'threads': { + 'options': [None, 'mysql Threads', 'threads', 'threads', 'mysql.threads', 'line'], + 'lines': [ + ["Threads_connected", "connected", "absolute"], + ["Threads_created", "created", "incremental"], + ["Threads_cached", "cached", "absolute", -1, 1], + ["Threads_running", "running", "absolute"], + ]}, + 'thread_cache_misses': { + 'options': [None, 'mysql Threads Cache Misses', 'misses', 'threads', 'mysql.thread_cache_misses', 'area'], + 'lines': [ + ["Thread_cache_misses", "misses", "absolute", 1, 100] + ]}, + 'innodb_io': { + 'options': [None, 'mysql InnoDB I/O Bandwidth', 'kilobytes/s', 'innodb', 'mysql.innodb_io', 'area'], + 'lines': [ + ["Innodb_data_read", "read", "incremental", 1, 1024], + ["Innodb_data_written", "write", "incremental", -1, 1024] + ]}, + 'innodb_io_ops': { + 'options': [None, 'mysql InnoDB I/O Operations', 'operations/s', 'innodb', 'mysql.innodb_io_ops', 'line'], + 'lines': [ + ["Innodb_data_reads", "reads", "incremental"], + ["Innodb_data_writes", "writes", "incremental", -1, 1], + ["Innodb_data_fsyncs", "fsyncs", "incremental"] + ]}, + 'innodb_io_pending_ops': { + 'options': [None, 'mysql InnoDB Pending I/O Operations', 'operations', 'innodb', 'mysql.innodb_io_pending_ops', 'line'], + 'lines': [ + ["Innodb_data_pending_reads", "reads", "absolute"], + ["Innodb_data_pending_writes", "writes", "absolute", -1, 1], + ["Innodb_data_pending_fsyncs", "fsyncs", "absolute"] + ]}, + 'innodb_log': { + 'options': [None, 'mysql InnoDB Log Operations', 'operations/s', 'innodb', 'mysql.innodb_log', 'line'], + 'lines': [ + ["Innodb_log_waits", "waits", "incremental"], + ["Innodb_log_write_requests", "write_requests", "incremental", -1, 1], + ["Innodb_log_writes", "writes", "incremental", -1, 1], + ]}, + 'innodb_os_log': { + 'options': [None, 'mysql InnoDB OS Log Operations', 'operations', 'innodb', 'mysql.innodb_os_log', 'line'], + 'lines': [ + ["Innodb_os_log_fsyncs", "fsyncs", "incremental"], + ["Innodb_os_log_pending_fsyncs", "pending_fsyncs", "absolute"], + ["Innodb_os_log_pending_writes", "pending_writes", "absolute", -1, 1], + ]}, + 'innodb_os_log_io': { + 'options': [None, 'mysql InnoDB OS Log Bandwidth', 'kilobytes/s', 'innodb', 'mysql.innodb_os_log_io', 'area'], + 'lines': [ + ["Innodb_os_log_written", "write", "incremental", -1, 1024], + ]}, + 'innodb_cur_row_lock': { + 'options': [None, 'mysql InnoDB Current Row Locks', 'operations', 'innodb', 'mysql.innodb_cur_row_lock', 'area'], + 'lines': [ + ["Innodb_row_lock_current_waits", "current_waits", "absolute"] + ]}, + 'innodb_rows': { + 'options': [None, 'mysql InnoDB Row Operations', 'operations/s', 'innodb', 'mysql.innodb_rows', 'area'], + 'lines': [ + ["Innodb_rows_inserted", "read", "incremental"], + ["Innodb_rows_read", "deleted", "incremental", -1, 1], + ["Innodb_rows_updated", "inserted", "incremental", 1, 1], + ["Innodb_rows_deleted", "updated", "incremental", -1, 1], + ]}, + 'innodb_buffer_pool_pages': { + 'options': [None, 'mysql InnoDB Buffer Pool Pages', 'pages', 'innodb', 'mysql.innodb_buffer_pool_pages', 'line'], + 'lines': [ + ["Innodb_buffer_pool_pages_data", "data", "absolute"], + ["Innodb_buffer_pool_pages_dirty", "dirty", "absolute", -1, 1], + ["Innodb_buffer_pool_pages_free", "free", "absolute"], + ["Innodb_buffer_pool_pages_flushed", "flushed", "incremental", -1, 1], + ["Innodb_buffer_pool_pages_misc", "misc", "absolute", -1, 1], + ["Innodb_buffer_pool_pages_total", "total", "absolute"] + ]}, + 'innodb_buffer_pool_bytes': { + 'options': [None, 'mysql InnoDB Buffer Pool Bytes', 'MB', 'innodb', 'mysql.innodb_buffer_pool_bytes', 'area'], + 'lines': [ + ["Innodb_buffer_pool_bytes_data", "data", "absolute", 1, 1024 * 1024], + ["Innodb_buffer_pool_bytes_dirty", "dirty", "absolute", -1, 1024 * 1024] + ]}, + 'innodb_buffer_pool_read_ahead': { + 'options': [None, 'mysql InnoDB Buffer Pool Read Ahead', 'operations/s', 'innodb', 'mysql.innodb_buffer_pool_read_ahead', 'area'], + 'lines': [ + ["Innodb_buffer_pool_read_ahead", "all", "incremental"], + ["Innodb_buffer_pool_read_ahead_evicted", "evicted", "incremental", -1, 1], + ["Innodb_buffer_pool_read_ahead_rnd", "random", "incremental"] + ]}, + 'innodb_buffer_pool_reqs': { + 'options': [None, 'mysql InnoDB Buffer Pool Requests', 'requests/s', 'innodb', 'mysql.innodb_buffer_pool_reqs', 'area'], + 'lines': [ + ["Innodb_buffer_pool_read_requests", "reads", "incremental"], + ["Innodb_buffer_pool_write_requests", "writes", "incremental", -1, 1] + ]}, + 'innodb_buffer_pool_ops': { + 'options': [None, 'mysql InnoDB Buffer Pool Operations', 'operations/s', 'innodb', 'mysql.innodb_buffer_pool_ops', 'area'], + 'lines': [ + ["Innodb_buffer_pool_reads", "disk reads", "incremental"], + ["Innodb_buffer_pool_wait_free", "wait free", "incremental", -1, 1] + ]}, + 'qcache_ops': { + 'options': [None, 'mysql QCache Operations', 'queries/s', 'qcache', 'mysql.qcache_ops', 'line'], + 'lines': [ + ["Qcache_hits", "hits", "incremental"], + ["Qcache_lowmem_prunes", "lowmem prunes", "incremental", -1, 1], + ["Qcache_inserts", "inserts", "incremental"], + ["Qcache_not_cached", "not cached", "incremental", -1, 1] + ]}, + 'qcache': { + 'options': [None, 'mysql QCache Queries in Cache', 'queries', 'qcache', 'mysql.qcache', 'line'], + 'lines': [ + ["Qcache_queries_in_cache", "queries", "absolute"] + ]}, + 'qcache_freemem': { + 'options': [None, 'mysql QCache Free Memory', 'MB', 'qcache', 'mysql.qcache_freemem', 'area'], + 'lines': [ + ["Qcache_free_memory", "free", "absolute", 1, 1024 * 1024] + ]}, + 'qcache_memblocks': { + 'options': [None, 'mysql QCache Memory Blocks', 'blocks', 'qcache', 'mysql.qcache_memblocks', 'line'], + 'lines': [ + ["Qcache_free_blocks", "free", "absolute"], + ["Qcache_total_blocks", "total", "absolute"] + ]}, + 'key_blocks': { + 'options': [None, 'mysql MyISAM Key Cache Blocks', 'blocks', 'myisam', 'mysql.key_blocks', 'line'], + 'lines': [ + ["Key_blocks_unused", "unused", "absolute"], + ["Key_blocks_used", "used", "absolute", -1, 1], + ["Key_blocks_not_flushed", "not flushed", "absolute"] + ]}, + 'key_requests': { + 'options': [None, 'mysql MyISAM Key Cache Requests', 'requests/s', 'myisam', 'mysql.key_requests', 'area'], + 'lines': [ + ["Key_read_requests", "reads", "incremental"], + ["Key_write_requests", "writes", "incremental", -1, 1] + ]}, + 'key_disk_ops': { + 'options': [None, 'mysql MyISAM Key Cache Disk Operations', 'operations/s', 'myisam', 'mysql.key_disk_ops', 'area'], + 'lines': [ + ["Key_reads", "reads", "incremental"], + ["Key_writes", "writes", "incremental", -1, 1] + ]}, + 'files': { + 'options': [None, 'mysql Open Files', 'files', 'files', 'mysql.files', 'line'], + 'lines': [ + ["Open_files", "files", "absolute"] + ]}, + 'files_rate': { + 'options': [None, 'mysql Opened Files Rate', 'files/s', 'files', 'mysql.files_rate', 'line'], + 'lines': [ + ["Opened_files", "files", "incremental"] + ]}, + 'binlog_stmt_cache': { + 'options': [None, 'mysql Binlog Statement Cache', 'statements/s', 'binlog', 'mysql.binlog_stmt_cache', 'line'], + 'lines': [ + ["Binlog_stmt_cache_disk_use", "disk", "incremental"], + ["Binlog_stmt_cache_use", "all", "incremental"] + ]}, + 'connection_errors': { + 'options': [None, 'mysql Connection Errors', 'connections/s', 'connections', 'mysql.connection_errors', 'line'], + 'lines': [ + ["Connection_errors_accept", "accept", "incremental"], + ["Connection_errors_internal", "internal", "incremental"], + ["Connection_errors_max_connections", "max", "incremental"], + ["Connection_errors_peer_address", "peer_addr", "incremental"], + ["Connection_errors_select", "select", "incremental"], + ["Connection_errors_tcpwrap", "tcpwrap", "incremental"] + ]} + +} + + +class Service(SimpleService): + def __init__(self, configuration=None, name=None): + SimpleService.__init__(self, configuration=configuration, name=name) + self._parse_config(configuration) + self.order = ORDER + self.definitions = CHARTS + self.connection = None + + def _parse_config(self, configuration): + """ + Parse configuration to collect data from MySQL server + :param configuration: dict + :return: dict + """ + if self.name is None: + self.name = 'local' + if 'user' not in configuration: + self.configuration['user'] = 'root' + if 'pass' not in configuration: + self.configuration['pass'] = '' + if 'my.cnf' in configuration: + self.configuration['socket'] = '' + self.configuration['host'] = '' + self.configuration['port'] = 0 + elif 'socket' in configuration: + self.configuration['my.cnf'] = '' + self.configuration['host'] = '' + self.configuration['port'] = 0 + elif 'host' in configuration: + self.configuration['my.cnf'] = '' + self.configuration['socket'] = '' + if 'port' in configuration: + self.configuration['port'] = int(configuration['port']) + else: + self.configuration['port'] = 3306 + + def _connect(self): + """ + Try to connect to MySQL server + """ + try: + self.connection = MySQLdb.connect(user=self.configuration['user'], + passwd=self.configuration['pass'], + read_default_file=self.configuration['my.cnf'], + unix_socket=self.configuration['socket'], + host=self.configuration['host'], + port=self.configuration['port'], + connect_timeout=self.update_every) + except MySQLdb.OperationalError as e: + self.error("Cannot establish connection to MySQL.") + self.debug(str(e)) + raise RuntimeError + except Exception as e: + self.error("problem connecting to server:", e) + raise RuntimeError + + def _get_data(self): + """ + Get raw data from MySQL server + :return: dict + """ + if self.connection is None: + try: + self._connect() + except RuntimeError: + return None + try: + cursor = self.connection.cursor() + cursor.execute(QUERY) + raw_data = cursor.fetchall() + except MySQLdb.OperationalError as e: + self.debug("Reconnecting due to", str(e)) + self._connect() + cursor = self.connection.cursor() + cursor.execute(QUERY) + raw_data = cursor.fetchall() + except Exception as e: + self.error("cannot execute query.", e) + self.connection.close() + self.connection = None + return None + + data = dict(raw_data) + try: + data["Thread_cache_misses"] = int(data["Threads_created"] * 10000 / float(data["Connections"])) + except: + data["Thread_cache_misses"] = 0 + + return data + + def check(self): + """ + Check if service is able to connect to server + :return: boolean + """ + try: + self.connection = self._connect() + return True + except RuntimeError: + self.connection = None + return False diff --git a/python.d/nginx.chart.py b/python.d/nginx.chart.py new file mode 100644 index 00000000..ff8bfede --- /dev/null +++ b/python.d/nginx.chart.py @@ -0,0 +1,73 @@ +# -*- coding: utf-8 -*- +# Description: nginx netdata python.d module +# Author: Pawel Krupa (paulfantom) + +from base import UrlService + +# default module values (can be overridden per job in `config`) +# update_every = 2 +priority = 60000 +retries = 60 + +# default job configuration (overridden by python.d.plugin) +# config = {'local': { +# 'update_every': update_every, +# 'retries': retries, +# 'priority': priority, +# 'url': 'http://localhost/stub_status' +# }} + +# charts order (can be overridden if you want less charts, or different order) +ORDER = ['connections', 'requests', 'connection_status', 'connect_rate'] + +CHARTS = { + 'connections': { + 'options': [None, 'nginx Active Connections', 'connections', 'nginx', 'nginx.connections', 'line'], + 'lines': [ + ["active"] + ]}, + 'requests': { + 'options': [None, 'nginx Requests', 'requests/s', 'nginx', 'nginx.requests', 'line'], + 'lines': [ + ["requests", None, 'incremental'] + ]}, + 'connection_status': { + 'options': [None, 'nginx Active Connections by Status', 'connections', 'nginx', 'nginx.connection_status', 'line'], + 'lines': [ + ["reading"], + ["writing"], + ["waiting", "idle"] + ]}, + 'connect_rate': { + 'options': [None, 'nginx Connections Rate', 'connections/s', 'nginx', 'nginx.connect_rate', 'line'], + 'lines': [ + ["accepts", "accepted", "incremental"], + ["handled", None, "incremental"] + ]} +} + + +class Service(UrlService): + def __init__(self, configuration=None, name=None): + UrlService.__init__(self, configuration=configuration, name=name) + if len(self.url) == 0: + self.url = "http://localhost/stub_status" + self.order = ORDER + self.definitions = CHARTS + + def _get_data(self): + """ + Format data received from http request + :return: dict + """ + try: + raw = self._get_raw_data().split(" ") + return {'active': int(raw[2]), + 'requests': int(raw[9]), + 'reading': int(raw[11]), + 'writing': int(raw[13]), + 'waiting': int(raw[15]), + 'accepts': int(raw[7]), + 'handled': int(raw[8])} + except (ValueError, AttributeError): + return None diff --git a/python.d/nginx_log.chart.py b/python.d/nginx_log.chart.py new file mode 100644 index 00000000..95fb123d --- /dev/null +++ b/python.d/nginx_log.chart.py @@ -0,0 +1,69 @@ +# -*- coding: utf-8 -*- +# Description: nginx log netdata python.d module +# Author: Pawel Krupa (paulfantom) + +from base import LogService +import re + +priority = 60000 +retries = 60 +# update_every = 3 + +ORDER = ['codes'] +CHARTS = { + 'codes': { + 'options': [None, 'nginx status codes', 'requests/s', 'requests', 'nginx_log.codes', 'stacked'], + 'lines': [ + ["2xx", None, "incremental"], + ["3xx", None, "incremental"], + ["4xx", None, "incremental"], + ["5xx", None, "incremental"] + ]} +} + + +class Service(LogService): + def __init__(self, configuration=None, name=None): + LogService.__init__(self, configuration=configuration, name=name) + if len(self.log_path) == 0: + self.log_path = "/var/log/nginx/access.log" + self.order = ORDER + self.definitions = CHARTS + pattern = r'" ([0-9]{3}) ?' + #pattern = r'(?:" )([0-9][0-9][0-9]) ?' + self.regex = re.compile(pattern) + + def _get_data(self): + """ + Parse new log lines + :return: dict + """ + data = {'2xx': 0, + '3xx': 0, + '4xx': 0, + '5xx': 0} + try: + raw = self._get_raw_data() + if raw is None: + return None + elif not raw: + return data + except (ValueError, AttributeError): + return None + + regex = self.regex + for line in raw: + code = regex.search(line) + beginning = code.group(1)[0] + + if beginning == '2': + data["2xx"] += 1 + elif beginning == '3': + data["3xx"] += 1 + elif beginning == '4': + data["4xx"] += 1 + elif beginning == '5': + data["5xx"] += 1 + + return data + diff --git a/python.d/phpfpm.chart.py b/python.d/phpfpm.chart.py new file mode 100755 index 00000000..d1791d42 --- /dev/null +++ b/python.d/phpfpm.chart.py @@ -0,0 +1,78 @@ +# -*- coding: utf-8 -*- +# Description: PHP-FPM netdata python.d module +# Author: Pawel Krupa (paulfantom) + +from base import UrlService + +# default module values (can be overridden per job in `config`) +# update_every = 2 +priority = 60000 +retries = 60 + +# default job configuration (overridden by python.d.plugin) +# config = {'local': { +# 'update_every': update_every, +# 'retries': retries, +# 'priority': priority, +# 'url': 'http://localhost/status' +# }} + +# charts order (can be overridden if you want less charts, or different order) +ORDER = ['connections', 'requests', 'performance'] + +CHARTS = { + 'connections': { + 'options': [None, 'PHP-FPM Active Connections', 'connections', 'phpfpm', 'phpfpm.connections', 'line'], + 'lines': [ + ["active"], + ["maxActive", 'max active'], + ["idle"] + ]}, + 'requests': { + 'options': [None, 'PHP-FPM Requests', 'requests/s', 'phpfpm', 'phpfpm.requests', 'line'], + 'lines': [ + ["requests", None, "incremental"] + ]}, + 'performance': { + 'options': [None, 'PHP-FPM Performance', 'status', 'phpfpm', 'phpfpm.performance', 'line'], + 'lines': [ + ["reached", 'max children reached'], + ["slow", 'slow requests'] + ]} +} + + +class Service(UrlService): + def __init__(self, configuration=None, name=None): + UrlService.__init__(self, configuration=configuration, name=name) + if len(self.url) == 0: + self.url = "http://localhost/status" + self.order = ORDER + self.definitions = CHARTS + self.assignment = {"active processes": 'active', + "max active processes": 'maxActive', + "idle processes": 'idle', + "accepted conn": 'requests', + "max children reached": 'reached', + "slow requests": 'slow'} + + def _get_data(self): + """ + Format data received from http request + :return: dict + """ + try: + raw = self._get_raw_data().split('\n') + except AttributeError: + return None + data = {} + for row in raw: + tmp = row.split(":") + if str(tmp[0]) in self.assignment: + try: + data[self.assignment[tmp[0]]] = int(tmp[1]) + except (IndexError, ValueError): + pass + if len(data) == 0: + return None + return data diff --git a/python.d/postfix.chart.py b/python.d/postfix.chart.py new file mode 100644 index 00000000..ee4142aa --- /dev/null +++ b/python.d/postfix.chart.py @@ -0,0 +1,50 @@ +# -*- coding: utf-8 -*- +# Description: postfix netdata python.d module +# Author: Pawel Krupa (paulfantom) + +from base import ExecutableService + +# default module values (can be overridden per job in `config`) +# update_every = 2 +priority = 60000 +retries = 60 + +# charts order (can be overridden if you want less charts, or different order) +ORDER = ['qemails', 'qsize'] + +CHARTS = { + 'qemails': { + 'options': [None, "Postfix Queue Emails", "emails", 'queue', 'postfix.qemails', 'line'], + 'lines': [ + ['emails', None, 'absolute'] + ]}, + 'qsize': { + 'options': [None, "Postfix Queue Emails Size", "emails size in KB", 'queue', 'postfix.qsize', 'area'], + 'lines': [ + ["size", None, 'absolute'] + ]} +} + + +class Service(ExecutableService): + def __init__(self, configuration=None, name=None): + ExecutableService.__init__(self, configuration=configuration, name=name) + self.command = "postqueue -p" + self.order = ORDER + self.definitions = CHARTS + + def _get_data(self): + """ + Format data received from shell command + :return: dict + """ + try: + raw = self._get_raw_data()[-1].split(' ') + if raw[0] == 'Mail' and raw[1] == 'queue': + return {'emails': 0, + 'size': 0} + + return {'emails': raw[4], + 'size': raw[1]} + except (ValueError, AttributeError): + return None diff --git a/python.d/python-modules-installer.sh b/python.d/python-modules-installer.sh new file mode 100644 index 00000000..cda3c666 --- /dev/null +++ b/python.d/python-modules-installer.sh @@ -0,0 +1,158 @@ +#!/usr/bin/env bash + +umask 022 + +dir="/usr/local/libexec/netdata/python.d" +target="${dir}/python_modules" +pv="$(python -V 2>&1)" + +# parse parameters +while [ ! -z "${1}" ] +do + case "${1}" in + -p|--python) + pv="Python ${2}" + shift 2 + ;; + + -d|--dir) + dir="${2}" + target="${dir}/python_modules" + echo >&2 "Will install python modules in: '${target}'" + shift 2 + ;; + + -s|--system) + target= + echo >&2 "Will install python modules system-wide" + shift + ;; + + -h|--help) + echo "${0} [--dir netdata-python.d-path] [--system]" + echo "Please make sure you have installed packages: python-pip (or python3-pip) python-dev libyaml-dev libmysqlclient-dev" + exit 0 + ;; + + *) + echo >&2 "Cannot understand parameter: ${1}" + exit 1 + ;; + esac +done + + +if [ ! -z "${target}" -a ! -d "${target}" ] +then + echo >&2 "Cannot find directory: '${target}'" + exit 1 +fi + +if [[ "${pv}" =~ ^Python\ 2.* ]] +then + pv=2 + pip="$(which pip2 2>/dev/null)" +elif [[ "${pv}" =~ ^Python\ 3.* ]] +then + pv=3 + pip="$(which pip3 2>/dev/null)" +else + echo >&2 "Cannot detect python version. Is python installed?" + exit 1 +fi + +[ -z "${pip}" ] && pip="$(which pip 2>/dev/null)" +if [ -z "${pip}" ] +then + echo >&2 "pip command is required to install python v${pv} modules." + [ "${pv}" = "2" ] && echo >&2 "Please install python-pip." + [ "${pv}" = "3" ] && echo >&2 "Please install python3-pip." + exit 1 +fi + +echo >&2 "Working for python version ${pv} (pip command: '${pip}')" +echo >&2 "Installing netdata python modules in: '${target}'" + +run() { + printf "Running command:\n# " + printf "%q " "${@}" + printf "\n" + "${@}" +} + +# try to install all the python modules given as parameters +# until the first that succeeds +failed="" +installed="" +errors=0 +pip_install() { + local ret x msg="${1}" + shift + + echo >&2 + echo >&2 + echo >&2 "Installing one of: ${*}" + + for x in "${@}" + do + echo >&2 + echo >&2 "attempting to install: ${x}" + if [ ! -z "${target}" ] + then + run "${pip}" install --target "${target}" "${x}" + ret=$? + else + run "${pip}" install "${x}" + ret=$? + fi + [ ${ret} -eq 0 ] && break + echo >&2 "failed to install: ${x}. ${msg}" + done + + if [ ${ret} -ne 0 ] + then + echo >&2 + echo >&2 + echo >&2 "FAILED: could not install any of: ${*}. ${msg}" + echo >&2 + echo >&2 + errors=$(( errors + 1 )) + failed="${failed}|${*}" + else + echo >&2 + echo >&2 + echo >&2 "SUCCESS: we have: ${x}" + echo >&2 + echo >&2 + installed="${installed} ${x}" + fi + return ${ret} +} + +if [ "${pv}" = "2" ] +then + pip_install "is libyaml-dev and python-dev installed?" pyyaml + pip_install "is libmysqlclient-dev and python-dev installed?" mysqlclient mysql-python pymysql +else + pip_install "is libyaml-dev and python-dev installed?" pyyaml + pip_install "is libmysqlclient-dev and python-dev installed?" mysql-python mysqlclient pymysql +fi + +echo >&2 +echo >&2 +if [ ${errors} -ne 0 ] +then + echo >&2 "Failed to install ${errors} modules: ${failed}" + if [ ! -z "${target}" ] + then + echo >&2 + echo >&2 "If you are getting errors during cleanup from pip, there is a known bug" + echo >&2 "in certain versions of pip that prevents installing packages local to an" + echo >&2 "application. To install them system-wide please run:" + echo >&2 "$0 --system" + fi + exit 1 +else + echo >&2 "All done. We have: ${installed}" + exit 0 +fi diff --git a/python.d/python_modules/__init__.py b/python.d/python_modules/__init__.py new file mode 100755 index 00000000..8d1c8b69 --- /dev/null +++ b/python.d/python_modules/__init__.py @@ -0,0 +1 @@ + diff --git a/python.d/python_modules/base.py b/python.d/python_modules/base.py new file mode 100644 index 00000000..c2bbed2a --- /dev/null +++ b/python.d/python_modules/base.py @@ -0,0 +1,798 @@ +# -*- coding: utf-8 -*- +# Description: netdata python modules framework +# Author: Pawel Krupa (paulfantom) + +# Remember: +# ALL CODE NEEDS TO BE COMPATIBLE WITH Python > 2.7 and Python > 3.1 +# Follow PEP8 as much as it is possible +# "check" and "create" CANNOT be blocking. +# "update" CAN be blocking +# "update" function needs to be fast, so follow: +# https://wiki.python.org/moin/PythonSpeed/PerformanceTips +# basically: +# - use local variables wherever it is possible +# - avoid dots in expressions that are executed many times +# - use "join()" instead of "+" +# - use "import" only at the beginning +# +# using ".encode()" in one thread can block other threads as well (only in python2) + +import time +# import sys +import os +import socket +import select +try: + import urllib.request as urllib2 +except ImportError: + import urllib2 + +from subprocess import Popen, PIPE + +import threading +import msg + + +# class BaseService(threading.Thread): +class SimpleService(threading.Thread): + """ + Prototype of Service class. + Implemented basic functionality to run jobs by `python.d.plugin` + """ + def __init__(self, configuration=None, name=None): + """ + This needs to be initialized in child classes + :param configuration: dict + :param name: str + """ + threading.Thread.__init__(self) + self._data_stream = "" + self.daemon = True + self.retries = 0 + self.retries_left = 0 + self.priority = 140000 + self.update_every = 1 + self.name = name + self.override_name = None + self.chart_name = "" + self._dimensions = [] + self._charts = [] + self.__chart_set = False + self.__first_run = True + self.order = [] + self.definitions = {} + if configuration is None: + self.error("BaseService: no configuration parameters supplied. Cannot create Service.") + raise RuntimeError + else: + self._extract_base_config(configuration) + self.timetable = {} + self.create_timetable() + + # --- BASIC SERVICE CONFIGURATION --- + + def _extract_base_config(self, config): + """ + Get basic parameters to run service + Minimum config: + config = {'update_every':1, + 'priority':100000, + 'retries':0} + :param config: dict + """ + pop = config.pop + try: + self.override_name = pop('name') + except KeyError: + pass + self.update_every = int(pop('update_every')) + self.priority = int(pop('priority')) + self.retries = int(pop('retries')) + self.retries_left = self.retries + self.configuration = config + + def create_timetable(self, freq=None): + """ + Create service timetable. + `freq` is optional + Example: + timetable = {'last': 1466370091.3767564, + 'next': 1466370092, + 'freq': 1} + :param freq: int + """ + if freq is None: + freq = self.update_every + now = time.time() + self.timetable = {'last': now, + 'next': now - (now % freq) + freq, + 'freq': freq} + + # --- THREAD CONFIGURATION --- + + def _run_once(self): + """ + Executes self.update(interval) and draws run time chart. + Return value presents exit status of update() + :return: boolean + """ + t_start = time.time() + timetable = self.timetable + chart_name = self.chart_name + # check if it is time to execute job update() function + if timetable['next'] > t_start: + self.debug(chart_name, "will be run in", str(int((timetable['next'] - t_start) * 1000)), "ms") + return True + + since_last = int((t_start - timetable['last']) * 1000000) + self.debug(chart_name, + "ready to run, after", str(int((t_start - timetable['last']) * 1000)), + "ms (update_every:", str(timetable['freq'] * 1000), + "ms, latency:", str(int((t_start - timetable['next']) * 1000)), "ms") + if self.__first_run: + since_last = 0 + if not self.update(since_last): + self.error("update function failed.") + return False + t_end = time.time() + self.timetable['next'] = t_end - (t_end % timetable['freq']) + timetable['freq'] + # draw performance graph + run_time = str(int((t_end - t_start) * 1000)) + # noinspection SqlNoDataSourceInspection + print("BEGIN netdata.plugin_pythond_%s %s\nSET run_time = %s\nEND\n" % + (self.chart_name, str(since_last), run_time)) + # sys.stdout.write("BEGIN netdata.plugin_pythond_%s %s\nSET run_time = %s\nEND\n" % + # (self.chart_name, str(since_last), run_time)) + + self.debug(chart_name, "updated in", str(run_time), "ms") + self.timetable['last'] = t_start + self.__first_run = False + return True + + def run(self): + """ + Runs job in thread. Handles retries. + Exits when job failed or timed out. + :return: None + """ + self.timetable['last'] = time.time() + while True: # run forever, unless something is wrong + try: + status = self._run_once() + except Exception as e: + self.error("Something wrong: ", str(e)) + return + if status: # handle retries if update failed + time.sleep(self.timetable['next'] - time.time()) + self.retries_left = self.retries + else: + self.retries_left -= 1 + if self.retries_left <= 0: + self.error("no more retries. Exiting") + return + else: + time.sleep(self.timetable['freq']) + + # --- CHART --- + + @staticmethod + def _format(*args): + """ + Escape and convert passed arguments. + :param args: anything + :return: list + """ + params = [] + append = params.append + for p in args: + if p is None: + append(p) + continue + if type(p) is not str: + p = str(p) + if ' ' in p: + p = "'" + p + "'" + append(p) + return params + + def _line(self, instruction, *params): + """ + Converts *params to string and joins them with one space between every one. + Result is appended to self._data_stream + :param params: str/int/float + """ + tmp = list(map((lambda x: "''" if x is None or len(x) == 0 else x), params)) + self._data_stream += "%s %s\n" % (instruction, str(" ".join(tmp))) + + def chart(self, type_id, name="", title="", units="", family="", + category="", chart_type="line", priority="", update_every=""): + """ + Defines a new chart. + :param type_id: str + :param name: str + :param title: str + :param units: str + :param family: str + :param category: str + :param chart_type: str + :param priority: int/str + :param update_every: int/str + """ + self._charts.append(type_id) + + p = self._format(type_id, name, title, units, family, category, chart_type, priority, update_every) + self._line("CHART", *p) + + def dimension(self, id, name=None, algorithm="absolute", multiplier=1, divisor=1, hidden=False): + """ + Defines a new dimension for the chart + :param id: str + :param name: str + :param algorithm: str + :param multiplier: int/str + :param divisor: int/str + :param hidden: boolean + :return: + """ + try: + int(multiplier) + except TypeError: + self.error("malformed dimension: multiplier is not a number:", multiplier) + multiplier = 1 + try: + int(divisor) + except TypeError: + self.error("malformed dimension: divisor is not a number:", divisor) + divisor = 1 + if name is None: + name = id + if algorithm not in ("absolute", "incremental", "percentage-of-absolute-row", "percentage-of-incremental-row"): + algorithm = "absolute" + + self._dimensions.append(str(id)) + if hidden: + p = self._format(id, name, algorithm, multiplier, divisor, "hidden") + else: + p = self._format(id, name, algorithm, multiplier, divisor) + + self._line("DIMENSION", *p) + + def begin(self, type_id, microseconds=0): + """ + Begin data set + :param type_id: str + :param microseconds: int + :return: boolean + """ + if type_id not in self._charts: + self.error("wrong chart type_id:", type_id) + return False + try: + int(microseconds) + except TypeError: + self.error("malformed begin statement: microseconds are not a number:", microseconds) + microseconds = "" + + self._line("BEGIN", type_id, str(microseconds)) + return True + + def set(self, id, value): + """ + Set value to dimension + :param id: str + :param value: int/float + :return: boolean + """ + if id not in self._dimensions: + self.error("wrong dimension id:", id, "Available dimensions are:", *self._dimensions) + return False + try: + value = str(int(value)) + except TypeError: + self.error("cannot set non-numeric value:", str(value)) + return False + self._line("SET", id, "=", str(value)) + self.__chart_set = True + return True + + def end(self): + if self.__chart_set: + self._line("END") + self.__chart_set = False + else: + pos = self._data_stream.rfind("BEGIN") + self._data_stream = self._data_stream[:pos] + + def commit(self): + """ + Upload new data to netdata. + """ + print(self._data_stream) + self._data_stream = "" + + # --- ERROR HANDLING --- + + def error(self, *params): + """ + Show error message on stderr + """ + msg.error(self.chart_name, *params) + + def debug(self, *params): + """ + Show debug message on stderr + """ + msg.debug(self.chart_name, *params) + + def info(self, *params): + """ + Show information message on stderr + """ + msg.info(self.chart_name, *params) + + # --- MAIN METHODS --- + + def _get_data(self): + """ + Get some data + :return: dict + """ + return {} + + def check(self): + """ + check() prototype + :return: boolean + """ + self.debug("Module", str(self.__module__), "doesn't implement check() function. Using default.") + if self._get_data() is None or len(self._get_data()) == 0: + return False + else: + return True + + def create(self): + """ + Create charts + :return: boolean + """ + data = self._get_data() + if data is None: + return False + + idx = 0 + for name in self.order: + options = self.definitions[name]['options'] + [self.priority + idx, self.update_every] + self.chart(self.chart_name + "." + name, *options) + # check if server has this datapoint + for line in self.definitions[name]['lines']: + if line[0] in data: + self.dimension(*line) + idx += 1 + + self.commit() + return True + + def update(self, interval): + """ + Update charts + :param interval: int + :return: boolean + """ + data = self._get_data() + if data is None: + self.debug("_get_data() returned no data") + return False + + updated = False + for chart in self.order: + if self.begin(self.chart_name + "." + chart, interval): + updated = True + for dim in self.definitions[chart]['lines']: + try: + self.set(dim[0], data[dim[0]]) + except KeyError: + pass + self.end() + + self.commit() + if not updated: + self.error("no charts to update") + + return updated + + +class UrlService(SimpleService): + # TODO add support for https connections + def __init__(self, configuration=None, name=None): + self.url = "" + self.user = None + self.password = None + self.proxies = {} + SimpleService.__init__(self, configuration=configuration, name=name) + + def __add_openers(self): + # TODO add error handling + self.opener = urllib2.build_opener() + + # Proxy handling + # TODO currently self.proxies isn't parsed from configuration file + # if len(self.proxies) > 0: + # for proxy in self.proxies: + # url = proxy['url'] + # # TODO test this: + # if "user" in proxy and "pass" in proxy: + # if url.lower().startswith('https://'): + # url = 'https://' + proxy['user'] + ':' + proxy['pass'] + '@' + url[8:] + # else: + # url = 'http://' + proxy['user'] + ':' + proxy['pass'] + '@' + url[7:] + # # FIXME move proxy auth to sth like this: + # # passman = urllib2.HTTPPasswordMgrWithDefaultRealm() + # # passman.add_password(None, url, proxy['user'], proxy['password']) + # # opener.add_handler(urllib2.HTTPBasicAuthHandler(passman)) + # + # if url.lower().startswith('https://'): + # opener.add_handler(urllib2.ProxyHandler({'https': url})) + # else: + # opener.add_handler(urllib2.ProxyHandler({'https': url})) + + # HTTP Basic Auth + if self.user is not None and self.password is not None: + passman = urllib2.HTTPPasswordMgrWithDefaultRealm() + passman.add_password(None, self.url, self.user, self.password) + self.opener.add_handler(urllib2.HTTPBasicAuthHandler(passman)) + self.debug("Enabling HTTP basic auth") + + #urllib2.install_opener(opener) + + def _get_raw_data(self): + """ + Get raw data from http request + :return: str + """ + raw = None + try: + f = self.opener.open(self.url, timeout=self.update_every * 2) + # f = urllib2.urlopen(self.url, timeout=self.update_every * 2) + except Exception as e: + self.error(str(e)) + return None + + try: + raw = f.read().decode('utf-8') + except Exception as e: + self.error(str(e)) + finally: + f.close() + return raw + + def check(self): + """ + Format configuration data and try to connect to server + :return: boolean + """ + if self.name is None or self.name == str(None): + self.name = 'local' + self.chart_name += "_" + self.name + else: + self.name = str(self.name) + try: + self.url = str(self.configuration['url']) + except (KeyError, TypeError): + pass + try: + self.user = str(self.configuration['user']) + except (KeyError, TypeError): + pass + try: + self.password = str(self.configuration['pass']) + except (KeyError, TypeError): + pass + + self.__add_openers() + + test = self._get_data() + if test is None or len(test) == 0: + return False + else: + return True + + +class SocketService(SimpleService): + def __init__(self, configuration=None, name=None): + self._sock = None + self._keep_alive = False + self.host = "localhost" + self.port = None + self.unix_socket = None + self.request = "" + self.__socket_config = None + SimpleService.__init__(self, configuration=configuration, name=name) + + def _connect(self): + """ + Recreate socket and connect to it since sockets cannot be reused after closing + Available configurations are IPv6, IPv4 or UNIX socket + :return: + """ + try: + if self.unix_socket is None: + if self.__socket_config is None: + # establish ipv6 or ipv4 connection. + for res in socket.getaddrinfo(self.host, self.port, socket.AF_UNSPEC, socket.SOCK_STREAM): + try: + # noinspection SpellCheckingInspection + af, socktype, proto, canonname, sa = res + self._sock = socket.socket(af, socktype, proto) + except socket.error as e: + self.debug("Cannot create socket:", str(e)) + self._sock = None + continue + try: + self._sock.connect(sa) + except socket.error as e: + self.debug("Cannot connect to socket:", str(e)) + self._disconnect() + continue + self.__socket_config = res + break + else: + # connect to socket with previously established configuration + try: + af, socktype, proto, canonname, sa = self.__socket_config + self._sock = socket.socket(af, socktype, proto) + self._sock.connect(sa) + except socket.error as e: + self.debug("Cannot create or connect to socket:", str(e)) + self._disconnect() + else: + # connect to unix socket + try: + self._sock = socket.socket(socket.AF_UNIX, socket.SOCK_DGRAM) + self._sock.connect(self.unix_socket) + except socket.error: + self._sock = socket.socket(socket.AF_UNIX, socket.SOCK_STREAM) + self._sock.connect(self.unix_socket) + + except Exception as e: + self.error(str(e), + "Cannot create socket with following configuration: host:", str(self.host), + "port:", str(self.port), + "socket:", str(self.unix_socket)) + self._sock = None + self._sock.setblocking(0) + + def _disconnect(self): + """ + Close socket connection + :return: + """ + try: + self._sock.shutdown(2) # 0 - read, 1 - write, 2 - all + self._sock.close() + except Exception: + pass + self._sock = None + + def _send(self): + """ + Send request. + :return: boolean + """ + # Send request if it is needed + if self.request != "".encode(): + try: + self._sock.send(self.request) + except Exception as e: + self._disconnect() + self.error(str(e), + "used configuration: host:", str(self.host), + "port:", str(self.port), + "socket:", str(self.unix_socket)) + return False + return True + + def _receive(self): + """ + Receive data from socket + :return: str + """ + data = "" + while True: + try: + ready_to_read, _, in_error = select.select([self._sock], [], [], 5) + except Exception as e: + self.debug("SELECT", str(e)) + self._disconnect() + break + if len(ready_to_read) > 0: + buf = self._sock.recv(4096) + if len(buf) == 0 or buf is None: # handle server disconnect + break + data += buf.decode() + if self._check_raw_data(data): + break + else: + self.error("Socket timed out.") + self._disconnect() + break + + return data + + def _get_raw_data(self): + """ + Get raw data with low-level "socket" module. + :return: str + """ + if self._sock is None: + self._connect() + + # Send request if it is needed + if not self._send(): + return None + + data = self._receive() + + if not self._keep_alive: + self._disconnect() + + return data + + def _check_raw_data(self, data): + """ + Check if all data has been gathered from socket + :param data: str + :return: boolean + """ + return True + + def _parse_config(self): + """ + Parse configuration data + :return: boolean + """ + if self.name is None or self.name == str(None): + self.name = "" + else: + self.name = str(self.name) + try: + self.unix_socket = str(self.configuration['socket']) + except (KeyError, TypeError): + self.debug("No unix socket specified. Trying TCP/IP socket.") + try: + self.host = str(self.configuration['host']) + except (KeyError, TypeError): + self.debug("No host specified. Using: '" + self.host + "'") + try: + self.port = int(self.configuration['port']) + except (KeyError, TypeError): + self.debug("No port specified. Using: '" + str(self.port) + "'") + try: + self.request = str(self.configuration['request']) + except (KeyError, TypeError): + self.debug("No request specified. Using: '" + str(self.request) + "'") + self.request = self.request.encode() + + def check(self): + return SimpleService.check(self) + + +class LogService(SimpleService): + def __init__(self, configuration=None, name=None): + self.log_path = "" + self._last_position = 0 + # self._log_reader = None + SimpleService.__init__(self, configuration=configuration, name=name) + self.retries = 100000 # basically always retry + + def _get_raw_data(self): + """ + Get log lines since last poll + :return: list + """ + lines = [] + try: + if os.path.getsize(self.log_path) < self._last_position: + self._last_position = 0 # read from beginning if file has shrunk + elif os.path.getsize(self.log_path) == self._last_position: + self.debug("Log file hasn't changed. No new data.") + return [] # return empty list if nothing has changed + with open(self.log_path, "r") as fp: + fp.seek(self._last_position) + for i, line in enumerate(fp): + lines.append(line) + self._last_position = fp.tell() + except Exception as e: + self.error(str(e)) + + if len(lines) != 0: + return lines + else: + self.error("No data collected.") + return None + + def check(self): + """ + Parse basic configuration and check if log file exists + :return: boolean + """ + if self.name is not None or self.name != str(None): + self.name = "" + else: + self.name = str(self.name) + try: + self.log_path = str(self.configuration['path']) + except (KeyError, TypeError): + self.error("No path to log specified. Using: '" + self.log_path + "'") + + if os.access(self.log_path, os.R_OK): + return True + else: + self.error("Cannot access file: '" + self.log_path + "'") + return False + + def create(self): + # set cursor at last byte of log file + self._last_position = os.path.getsize(self.log_path) + status = SimpleService.create(self) + # self._last_position = 0 + return status + + +class ExecutableService(SimpleService): + bad_substrings = ('&', '|', ';', '>', '<') + + def __init__(self, configuration=None, name=None): + self.command = "" + SimpleService.__init__(self, configuration=configuration, name=name) + + def _get_raw_data(self): + """ + Get raw data from executed command + :return: str + """ + try: + p = Popen(self.command, stdout=PIPE, stderr=PIPE) + except Exception as e: + self.error("Executing command", self.command, "resulted in error:", str(e)) + return None + data = [] + for line in p.stdout.readlines(): + data.append(str(line.decode())) + + if len(data) == 0: + self.error("No data collected.") + return None + + return data + + def check(self): + """ + Parse basic configuration, check if command is whitelisted and is returning values + :return: boolean + """ + if self.name is not None or self.name != str(None): + self.name = "" + else: + self.name = str(self.name) + try: + self.command = str(self.configuration['command']) + except (KeyError, TypeError): + self.error("No command specified. Using: '" + self.command + "'") + command = self.command.split(' ') + + for arg in command[1:]: + if any(st in arg for st in self.bad_substrings): + self.error("Bad command argument:" + " ".join(self.command[1:])) + return False + # test command and search for it in /usr/sbin or /sbin when failed + base = command[0].split('/')[-1] + if self._get_raw_data() is None: + for prefix in ['/sbin/', '/usr/sbin/']: + command[0] = prefix + base + if os.path.isfile(command[0]): + break + self.command = command + if self._get_data() is None or len(self._get_data()) == 0: + self.error("Command", self.command, "returned no data") + return False + return True diff --git a/python.d/python_modules/lm_sensors.py b/python.d/python_modules/lm_sensors.py new file mode 100644 index 00000000..1d868f0e --- /dev/null +++ b/python.d/python_modules/lm_sensors.py @@ -0,0 +1,257 @@ +""" +@package sensors.py +Python Bindings for libsensors3 + +use the documentation of libsensors for the low level API. +see example.py for high level API usage. + +@author: Pavel Rojtberg (http://www.rojtberg.net) +@see: https://github.com/paroj/sensors.py +@copyright: LGPLv2 (same as libsensors) <http://opensource.org/licenses/LGPL-2.1> +""" + +from ctypes import * +import ctypes.util + +_libc = cdll.LoadLibrary(ctypes.util.find_library("c")) +# see https://github.com/paroj/sensors.py/issues/1 +_libc.free.argtypes = [c_void_p] +_hdl = cdll.LoadLibrary(ctypes.util.find_library("sensors")) + +version = c_char_p.in_dll(_hdl, "libsensors_version").value.decode("ascii") + + +class bus_id(Structure): + _fields_ = [("type", c_short), + ("nr", c_short)] + + +class chip_name(Structure): + _fields_ = [("prefix", c_char_p), + ("bus", bus_id), + ("addr", c_int), + ("path", c_char_p)] + + +class feature(Structure): + _fields_ = [("name", c_char_p), + ("number", c_int), + ("type", c_int)] + + # sensors_feature_type + IN = 0x00 + FAN = 0x01 + TEMP = 0x02 + POWER = 0x03 + ENERGY = 0x04 + CURR = 0x05 + HUMIDITY = 0x06 + MAX_MAIN = 0x7 + VID = 0x10 + INTRUSION = 0x11 + MAX_OTHER = 0x12 + BEEP_ENABLE = 0x18 + + +class subfeature(Structure): + _fields_ = [("name", c_char_p), + ("number", c_int), + ("type", c_int), + ("mapping", c_int), + ("flags", c_uint)] + + +_hdl.sensors_get_detected_chips.restype = POINTER(chip_name) +_hdl.sensors_get_features.restype = POINTER(feature) +_hdl.sensors_get_all_subfeatures.restype = POINTER(subfeature) +_hdl.sensors_get_label.restype = c_void_p # return pointer instead of str so we can free it +_hdl.sensors_get_adapter_name.restype = c_char_p # docs do not say whether to free this or not +_hdl.sensors_strerror.restype = c_char_p + +### RAW API ### +MODE_R = 1 +MODE_W = 2 +COMPUTE_MAPPING = 4 + + +def init(cfg_file=None): + file = _libc.fopen(cfg_file.encode("utf-8"), "r") if cfg_file is not None else None + + if _hdl.sensors_init(file) != 0: + raise Exception("sensors_init failed") + + if file is not None: + _libc.fclose(file) + + +def cleanup(): + _hdl.sensors_cleanup() + + +def parse_chip_name(orig_name): + ret = chip_name() + err = _hdl.sensors_parse_chip_name(orig_name.encode("utf-8"), byref(ret)) + + if err < 0: + raise Exception(strerror(err)) + + return ret + + +def strerror(errnum): + return _hdl.sensors_strerror(errnum).decode("utf-8") + + +def free_chip_name(chip): + _hdl.sensors_free_chip_name(byref(chip)) + + +def get_detected_chips(match, nr): + """ + @return: (chip, next nr to query) + """ + _nr = c_int(nr) + + if match is not None: + match = byref(match) + + chip = _hdl.sensors_get_detected_chips(match, byref(_nr)) + chip = chip.contents if bool(chip) else None + return chip, _nr.value + + +def chip_snprintf_name(chip, buffer_size=200): + """ + @param buffer_size defaults to the size used in the sensors utility + """ + ret = create_string_buffer(buffer_size) + err = _hdl.sensors_snprintf_chip_name(ret, buffer_size, byref(chip)) + + if err < 0: + raise Exception(strerror(err)) + + return ret.value.decode("utf-8") + + +def do_chip_sets(chip): + """ + @attention this function was not tested + """ + err = _hdl.sensors_do_chip_sets(byref(chip)) + if err < 0: + raise Exception(strerror(err)) + + +def get_adapter_name(bus): + return _hdl.sensors_get_adapter_name(byref(bus)).decode("utf-8") + + +def get_features(chip, nr): + """ + @return: (feature, next nr to query) + """ + _nr = c_int(nr) + feature = _hdl.sensors_get_features(byref(chip), byref(_nr)) + feature = feature.contents if bool(feature) else None + return feature, _nr.value + + +def get_label(chip, feature): + ptr = _hdl.sensors_get_label(byref(chip), byref(feature)) + val = cast(ptr, c_char_p).value.decode("utf-8") + _libc.free(ptr) + return val + + +def get_all_subfeatures(chip, feature, nr): + """ + @return: (subfeature, next nr to query) + """ + _nr = c_int(nr) + subfeature = _hdl.sensors_get_all_subfeatures(byref(chip), byref(feature), byref(_nr)) + subfeature = subfeature.contents if bool(subfeature) else None + return subfeature, _nr.value + + +def get_value(chip, subfeature_nr): + val = c_double() + err = _hdl.sensors_get_value(byref(chip), subfeature_nr, byref(val)) + if err < 0: + raise Exception(strerror(err)) + return val.value + + +def set_value(chip, subfeature_nr, value): + """ + @attention this function was not tested + """ + val = c_double(value) + err = _hdl.sensors_set_value(byref(chip), subfeature_nr, byref(val)) + if err < 0: + raise Exception(strerror(err)) + + +### Convenience API ### +class ChipIterator: + def __init__(self, match=None): + self.match = parse_chip_name(match) if match is not None else None + self.nr = 0 + + def __iter__(self): + return self + + def __next__(self): + chip, self.nr = get_detected_chips(self.match, self.nr) + + if chip is None: + raise StopIteration + + return chip + + def __del__(self): + if self.match is not None: + free_chip_name(self.match) + + def next(self): # python2 compability + return self.__next__() + + +class FeatureIterator: + def __init__(self, chip): + self.chip = chip + self.nr = 0 + + def __iter__(self): + return self + + def __next__(self): + feature, self.nr = get_features(self.chip, self.nr) + + if feature is None: + raise StopIteration + + return feature + + def next(self): # python2 compability + return self.__next__() + + +class SubFeatureIterator: + def __init__(self, chip, feature): + self.chip = chip + self.feature = feature + self.nr = 0 + + def __iter__(self): + return self + + def __next__(self): + subfeature, self.nr = get_all_subfeatures(self.chip, self.feature, self.nr) + + if subfeature is None: + raise StopIteration + + return subfeature + + def next(self): # python2 compability + return self.__next__()
\ No newline at end of file diff --git a/python.d/python_modules/msg.py b/python.d/python_modules/msg.py new file mode 100644 index 00000000..ecefba0a --- /dev/null +++ b/python.d/python_modules/msg.py @@ -0,0 +1,74 @@ +# -*- coding: utf-8 -*- +# Description: logging for netdata python.d modules + +import sys +from time import time, strftime + +DEBUG_FLAG = False +PROGRAM = "" +LOG_COUNTER = 2 +LOG_INTERVAL = 5 +NEXT_CHECK = 0 + +WRITE = sys.stderr.write +FLUSH = sys.stderr.flush + + +def log_msg(msg_type, *args): + """ + Print message on stderr. + :param msg_type: str + """ + global LOG_COUNTER + if not DEBUG_FLAG: + LOG_COUNTER -= 1 + now = time() + if LOG_COUNTER >= 0: + timestamp = strftime('%y-%m-%d %X') + msg = "%s: %s %s: %s" % (timestamp, PROGRAM, str(msg_type), " ".join(args)) + WRITE(msg + "\n") + FLUSH() + + global NEXT_CHECK + if NEXT_CHECK <= now: + NEXT_CHECK = now - (now % LOG_INTERVAL) + LOG_INTERVAL + if LOG_COUNTER < 0: + timestamp = strftime('%y-%m-%d %X') + msg = "%s: Prevented %s log messages from displaying" % (timestamp, str(0 - LOG_COUNTER)) + WRITE(msg + "\n") + FLUSH() + + +def debug(*args): + """ + Print debug message on stderr. + """ + if not DEBUG_FLAG: + return + + log_msg("DEBUG", *args) + + +def error(*args): + """ + Print message on stderr. + """ + log_msg("ERROR", *args) + + +def info(*args): + """ + Print message on stderr. + """ + log_msg("INFO", *args) + + +def fatal(*args): + """ + Print message on stderr and exit. + """ + log_msg("FATAL", *args) + # using sys.stdout causes IOError: Broken Pipe + print('DISABLE') + # sys.stdout.write('DISABLE\n') + sys.exit(1)
\ No newline at end of file diff --git a/python.d/python_modules/pyyaml2/__init__.py b/python.d/python_modules/pyyaml2/__init__.py new file mode 100644 index 00000000..76e19e13 --- /dev/null +++ b/python.d/python_modules/pyyaml2/__init__.py @@ -0,0 +1,315 @@ + +from error import * + +from tokens import * +from events import * +from nodes import * + +from loader import * +from dumper import * + +__version__ = '3.11' + +try: + from cyaml import * + __with_libyaml__ = True +except ImportError: + __with_libyaml__ = False + +def scan(stream, Loader=Loader): + """ + Scan a YAML stream and produce scanning tokens. + """ + loader = Loader(stream) + try: + while loader.check_token(): + yield loader.get_token() + finally: + loader.dispose() + +def parse(stream, Loader=Loader): + """ + Parse a YAML stream and produce parsing events. + """ + loader = Loader(stream) + try: + while loader.check_event(): + yield loader.get_event() + finally: + loader.dispose() + +def compose(stream, Loader=Loader): + """ + Parse the first YAML document in a stream + and produce the corresponding representation tree. + """ + loader = Loader(stream) + try: + return loader.get_single_node() + finally: + loader.dispose() + +def compose_all(stream, Loader=Loader): + """ + Parse all YAML documents in a stream + and produce corresponding representation trees. + """ + loader = Loader(stream) + try: + while loader.check_node(): + yield loader.get_node() + finally: + loader.dispose() + +def load(stream, Loader=Loader): + """ + Parse the first YAML document in a stream + and produce the corresponding Python object. + """ + loader = Loader(stream) + try: + return loader.get_single_data() + finally: + loader.dispose() + +def load_all(stream, Loader=Loader): + """ + Parse all YAML documents in a stream + and produce corresponding Python objects. + """ + loader = Loader(stream) + try: + while loader.check_data(): + yield loader.get_data() + finally: + loader.dispose() + +def safe_load(stream): + """ + Parse the first YAML document in a stream + and produce the corresponding Python object. + Resolve only basic YAML tags. + """ + return load(stream, SafeLoader) + +def safe_load_all(stream): + """ + Parse all YAML documents in a stream + and produce corresponding Python objects. + Resolve only basic YAML tags. + """ + return load_all(stream, SafeLoader) + +def emit(events, stream=None, Dumper=Dumper, + canonical=None, indent=None, width=None, + allow_unicode=None, line_break=None): + """ + Emit YAML parsing events into a stream. + If stream is None, return the produced string instead. + """ + getvalue = None + if stream is None: + from StringIO import StringIO + stream = StringIO() + getvalue = stream.getvalue + dumper = Dumper(stream, canonical=canonical, indent=indent, width=width, + allow_unicode=allow_unicode, line_break=line_break) + try: + for event in events: + dumper.emit(event) + finally: + dumper.dispose() + if getvalue: + return getvalue() + +def serialize_all(nodes, stream=None, Dumper=Dumper, + canonical=None, indent=None, width=None, + allow_unicode=None, line_break=None, + encoding='utf-8', explicit_start=None, explicit_end=None, + version=None, tags=None): + """ + Serialize a sequence of representation trees into a YAML stream. + If stream is None, return the produced string instead. + """ + getvalue = None + if stream is None: + if encoding is None: + from StringIO import StringIO + else: + from cStringIO import StringIO + stream = StringIO() + getvalue = stream.getvalue + dumper = Dumper(stream, canonical=canonical, indent=indent, width=width, + allow_unicode=allow_unicode, line_break=line_break, + encoding=encoding, version=version, tags=tags, + explicit_start=explicit_start, explicit_end=explicit_end) + try: + dumper.open() + for node in nodes: + dumper.serialize(node) + dumper.close() + finally: + dumper.dispose() + if getvalue: + return getvalue() + +def serialize(node, stream=None, Dumper=Dumper, **kwds): + """ + Serialize a representation tree into a YAML stream. + If stream is None, return the produced string instead. + """ + return serialize_all([node], stream, Dumper=Dumper, **kwds) + +def dump_all(documents, stream=None, Dumper=Dumper, + default_style=None, default_flow_style=None, + canonical=None, indent=None, width=None, + allow_unicode=None, line_break=None, + encoding='utf-8', explicit_start=None, explicit_end=None, + version=None, tags=None): + """ + Serialize a sequence of Python objects into a YAML stream. + If stream is None, return the produced string instead. + """ + getvalue = None + if stream is None: + if encoding is None: + from StringIO import StringIO + else: + from cStringIO import StringIO + stream = StringIO() + getvalue = stream.getvalue + dumper = Dumper(stream, default_style=default_style, + default_flow_style=default_flow_style, + canonical=canonical, indent=indent, width=width, + allow_unicode=allow_unicode, line_break=line_break, + encoding=encoding, version=version, tags=tags, + explicit_start=explicit_start, explicit_end=explicit_end) + try: + dumper.open() + for data in documents: + dumper.represent(data) + dumper.close() + finally: + dumper.dispose() + if getvalue: + return getvalue() + +def dump(data, stream=None, Dumper=Dumper, **kwds): + """ + Serialize a Python object into a YAML stream. + If stream is None, return the produced string instead. + """ + return dump_all([data], stream, Dumper=Dumper, **kwds) + +def safe_dump_all(documents, stream=None, **kwds): + """ + Serialize a sequence of Python objects into a YAML stream. + Produce only basic YAML tags. + If stream is None, return the produced string instead. + """ + return dump_all(documents, stream, Dumper=SafeDumper, **kwds) + +def safe_dump(data, stream=None, **kwds): + """ + Serialize a Python object into a YAML stream. + Produce only basic YAML tags. + If stream is None, return the produced string instead. + """ + return dump_all([data], stream, Dumper=SafeDumper, **kwds) + +def add_implicit_resolver(tag, regexp, first=None, + Loader=Loader, Dumper=Dumper): + """ + Add an implicit scalar detector. + If an implicit scalar value matches the given regexp, + the corresponding tag is assigned to the scalar. + first is a sequence of possible initial characters or None. + """ + Loader.add_implicit_resolver(tag, regexp, first) + Dumper.add_implicit_resolver(tag, regexp, first) + +def add_path_resolver(tag, path, kind=None, Loader=Loader, Dumper=Dumper): + """ + Add a path based resolver for the given tag. + A path is a list of keys that forms a path + to a node in the representation tree. + Keys can be string values, integers, or None. + """ + Loader.add_path_resolver(tag, path, kind) + Dumper.add_path_resolver(tag, path, kind) + +def add_constructor(tag, constructor, Loader=Loader): + """ + Add a constructor for the given tag. + Constructor is a function that accepts a Loader instance + and a node object and produces the corresponding Python object. + """ + Loader.add_constructor(tag, constructor) + +def add_multi_constructor(tag_prefix, multi_constructor, Loader=Loader): + """ + Add a multi-constructor for the given tag prefix. + Multi-constructor is called for a node if its tag starts with tag_prefix. + Multi-constructor accepts a Loader instance, a tag suffix, + and a node object and produces the corresponding Python object. + """ + Loader.add_multi_constructor(tag_prefix, multi_constructor) + +def add_representer(data_type, representer, Dumper=Dumper): + """ + Add a representer for the given type. + Representer is a function accepting a Dumper instance + and an instance of the given data type + and producing the corresponding representation node. + """ + Dumper.add_representer(data_type, representer) + +def add_multi_representer(data_type, multi_representer, Dumper=Dumper): + """ + Add a representer for the given type. + Multi-representer is a function accepting a Dumper instance + and an instance of the given data type or subtype + and producing the corresponding representation node. + """ + Dumper.add_multi_representer(data_type, multi_representer) + +class YAMLObjectMetaclass(type): + """ + The metaclass for YAMLObject. + """ + def __init__(cls, name, bases, kwds): + super(YAMLObjectMetaclass, cls).__init__(name, bases, kwds) + if 'yaml_tag' in kwds and kwds['yaml_tag'] is not None: + cls.yaml_loader.add_constructor(cls.yaml_tag, cls.from_yaml) + cls.yaml_dumper.add_representer(cls, cls.to_yaml) + +class YAMLObject(object): + """ + An object that can dump itself to a YAML stream + and load itself from a YAML stream. + """ + + __metaclass__ = YAMLObjectMetaclass + __slots__ = () # no direct instantiation, so allow immutable subclasses + + yaml_loader = Loader + yaml_dumper = Dumper + + yaml_tag = None + yaml_flow_style = None + + def from_yaml(cls, loader, node): + """ + Convert a representation node to a Python object. + """ + return loader.construct_yaml_object(node, cls) + from_yaml = classmethod(from_yaml) + + def to_yaml(cls, dumper, data): + """ + Convert a Python object to a representation node. + """ + return dumper.represent_yaml_object(cls.yaml_tag, data, cls, + flow_style=cls.yaml_flow_style) + to_yaml = classmethod(to_yaml) + diff --git a/python.d/python_modules/pyyaml2/composer.py b/python.d/python_modules/pyyaml2/composer.py new file mode 100644 index 00000000..06e5ac78 --- /dev/null +++ b/python.d/python_modules/pyyaml2/composer.py @@ -0,0 +1,139 @@ + +__all__ = ['Composer', 'ComposerError'] + +from error import MarkedYAMLError +from events import * +from nodes import * + +class ComposerError(MarkedYAMLError): + pass + +class Composer(object): + + def __init__(self): + self.anchors = {} + + def check_node(self): + # Drop the STREAM-START event. + if self.check_event(StreamStartEvent): + self.get_event() + + # If there are more documents available? + return not self.check_event(StreamEndEvent) + + def get_node(self): + # Get the root node of the next document. + if not self.check_event(StreamEndEvent): + return self.compose_document() + + def get_single_node(self): + # Drop the STREAM-START event. + self.get_event() + + # Compose a document if the stream is not empty. + document = None + if not self.check_event(StreamEndEvent): + document = self.compose_document() + + # Ensure that the stream contains no more documents. + if not self.check_event(StreamEndEvent): + event = self.get_event() + raise ComposerError("expected a single document in the stream", + document.start_mark, "but found another document", + event.start_mark) + + # Drop the STREAM-END event. + self.get_event() + + return document + + def compose_document(self): + # Drop the DOCUMENT-START event. + self.get_event() + + # Compose the root node. + node = self.compose_node(None, None) + + # Drop the DOCUMENT-END event. + self.get_event() + + self.anchors = {} + return node + + def compose_node(self, parent, index): + if self.check_event(AliasEvent): + event = self.get_event() + anchor = event.anchor + if anchor not in self.anchors: + raise ComposerError(None, None, "found undefined alias %r" + % anchor.encode('utf-8'), event.start_mark) + return self.anchors[anchor] + event = self.peek_event() + anchor = event.anchor + if anchor is not None: + if anchor in self.anchors: + raise ComposerError("found duplicate anchor %r; first occurence" + % anchor.encode('utf-8'), self.anchors[anchor].start_mark, + "second occurence", event.start_mark) + self.descend_resolver(parent, index) + if self.check_event(ScalarEvent): + node = self.compose_scalar_node(anchor) + elif self.check_event(SequenceStartEvent): + node = self.compose_sequence_node(anchor) + elif self.check_event(MappingStartEvent): + node = self.compose_mapping_node(anchor) + self.ascend_resolver() + return node + + def compose_scalar_node(self, anchor): + event = self.get_event() + tag = event.tag + if tag is None or tag == u'!': + tag = self.resolve(ScalarNode, event.value, event.implicit) + node = ScalarNode(tag, event.value, + event.start_mark, event.end_mark, style=event.style) + if anchor is not None: + self.anchors[anchor] = node + return node + + def compose_sequence_node(self, anchor): + start_event = self.get_event() + tag = start_event.tag + if tag is None or tag == u'!': + tag = self.resolve(SequenceNode, None, start_event.implicit) + node = SequenceNode(tag, [], + start_event.start_mark, None, + flow_style=start_event.flow_style) + if anchor is not None: + self.anchors[anchor] = node + index = 0 + while not self.check_event(SequenceEndEvent): + node.value.append(self.compose_node(node, index)) + index += 1 + end_event = self.get_event() + node.end_mark = end_event.end_mark + return node + + def compose_mapping_node(self, anchor): + start_event = self.get_event() + tag = start_event.tag + if tag is None or tag == u'!': + tag = self.resolve(MappingNode, None, start_event.implicit) + node = MappingNode(tag, [], + start_event.start_mark, None, + flow_style=start_event.flow_style) + if anchor is not None: + self.anchors[anchor] = node + while not self.check_event(MappingEndEvent): + #key_event = self.peek_event() + item_key = self.compose_node(node, None) + #if item_key in node.value: + # raise ComposerError("while composing a mapping", start_event.start_mark, + # "found duplicate key", key_event.start_mark) + item_value = self.compose_node(node, item_key) + #node.value[item_key] = item_value + node.value.append((item_key, item_value)) + end_event = self.get_event() + node.end_mark = end_event.end_mark + return node + diff --git a/python.d/python_modules/pyyaml2/constructor.py b/python.d/python_modules/pyyaml2/constructor.py new file mode 100644 index 00000000..635faac3 --- /dev/null +++ b/python.d/python_modules/pyyaml2/constructor.py @@ -0,0 +1,675 @@ + +__all__ = ['BaseConstructor', 'SafeConstructor', 'Constructor', + 'ConstructorError'] + +from error import * +from nodes import * + +import datetime + +import binascii, re, sys, types + +class ConstructorError(MarkedYAMLError): + pass + +class BaseConstructor(object): + + yaml_constructors = {} + yaml_multi_constructors = {} + + def __init__(self): + self.constructed_objects = {} + self.recursive_objects = {} + self.state_generators = [] + self.deep_construct = False + + def check_data(self): + # If there are more documents available? + return self.check_node() + + def get_data(self): + # Construct and return the next document. + if self.check_node(): + return self.construct_document(self.get_node()) + + def get_single_data(self): + # Ensure that the stream contains a single document and construct it. + node = self.get_single_node() + if node is not None: + return self.construct_document(node) + return None + + def construct_document(self, node): + data = self.construct_object(node) + while self.state_generators: + state_generators = self.state_generators + self.state_generators = [] + for generator in state_generators: + for dummy in generator: + pass + self.constructed_objects = {} + self.recursive_objects = {} + self.deep_construct = False + return data + + def construct_object(self, node, deep=False): + if node in self.constructed_objects: + return self.constructed_objects[node] + if deep: + old_deep = self.deep_construct + self.deep_construct = True + if node in self.recursive_objects: + raise ConstructorError(None, None, + "found unconstructable recursive node", node.start_mark) + self.recursive_objects[node] = None + constructor = None + tag_suffix = None + if node.tag in self.yaml_constructors: + constructor = self.yaml_constructors[node.tag] + else: + for tag_prefix in self.yaml_multi_constructors: + if node.tag.startswith(tag_prefix): + tag_suffix = node.tag[len(tag_prefix):] + constructor = self.yaml_multi_constructors[tag_prefix] + break + else: + if None in self.yaml_multi_constructors: + tag_suffix = node.tag + constructor = self.yaml_multi_constructors[None] + elif None in self.yaml_constructors: + constructor = self.yaml_constructors[None] + elif isinstance(node, ScalarNode): + constructor = self.__class__.construct_scalar + elif isinstance(node, SequenceNode): + constructor = self.__class__.construct_sequence + elif isinstance(node, MappingNode): + constructor = self.__class__.construct_mapping + if tag_suffix is None: + data = constructor(self, node) + else: + data = constructor(self, tag_suffix, node) + if isinstance(data, types.GeneratorType): + generator = data + data = generator.next() + if self.deep_construct: + for dummy in generator: + pass + else: + self.state_generators.append(generator) + self.constructed_objects[node] = data + del self.recursive_objects[node] + if deep: + self.deep_construct = old_deep + return data + + def construct_scalar(self, node): + if not isinstance(node, ScalarNode): + raise ConstructorError(None, None, + "expected a scalar node, but found %s" % node.id, + node.start_mark) + return node.value + + def construct_sequence(self, node, deep=False): + if not isinstance(node, SequenceNode): + raise ConstructorError(None, None, + "expected a sequence node, but found %s" % node.id, + node.start_mark) + return [self.construct_object(child, deep=deep) + for child in node.value] + + def construct_mapping(self, node, deep=False): + if not isinstance(node, MappingNode): + raise ConstructorError(None, None, + "expected a mapping node, but found %s" % node.id, + node.start_mark) + mapping = {} + for key_node, value_node in node.value: + key = self.construct_object(key_node, deep=deep) + try: + hash(key) + except TypeError, exc: + raise ConstructorError("while constructing a mapping", node.start_mark, + "found unacceptable key (%s)" % exc, key_node.start_mark) + value = self.construct_object(value_node, deep=deep) + mapping[key] = value + return mapping + + def construct_pairs(self, node, deep=False): + if not isinstance(node, MappingNode): + raise ConstructorError(None, None, + "expected a mapping node, but found %s" % node.id, + node.start_mark) + pairs = [] + for key_node, value_node in node.value: + key = self.construct_object(key_node, deep=deep) + value = self.construct_object(value_node, deep=deep) + pairs.append((key, value)) + return pairs + + def add_constructor(cls, tag, constructor): + if not 'yaml_constructors' in cls.__dict__: + cls.yaml_constructors = cls.yaml_constructors.copy() + cls.yaml_constructors[tag] = constructor + add_constructor = classmethod(add_constructor) + + def add_multi_constructor(cls, tag_prefix, multi_constructor): + if not 'yaml_multi_constructors' in cls.__dict__: + cls.yaml_multi_constructors = cls.yaml_multi_constructors.copy() + cls.yaml_multi_constructors[tag_prefix] = multi_constructor + add_multi_constructor = classmethod(add_multi_constructor) + +class SafeConstructor(BaseConstructor): + + def construct_scalar(self, node): + if isinstance(node, MappingNode): + for key_node, value_node in node.value: + if key_node.tag == u'tag:yaml.org,2002:value': + return self.construct_scalar(value_node) + return BaseConstructor.construct_scalar(self, node) + + def flatten_mapping(self, node): + merge = [] + index = 0 + while index < len(node.value): + key_node, value_node = node.value[index] + if key_node.tag == u'tag:yaml.org,2002:merge': + del node.value[index] + if isinstance(value_node, MappingNode): + self.flatten_mapping(value_node) + merge.extend(value_node.value) + elif isinstance(value_node, SequenceNode): + submerge = [] + for subnode in value_node.value: + if not isinstance(subnode, MappingNode): + raise ConstructorError("while constructing a mapping", + node.start_mark, + "expected a mapping for merging, but found %s" + % subnode.id, subnode.start_mark) + self.flatten_mapping(subnode) + submerge.append(subnode.value) + submerge.reverse() + for value in submerge: + merge.extend(value) + else: + raise ConstructorError("while constructing a mapping", node.start_mark, + "expected a mapping or list of mappings for merging, but found %s" + % value_node.id, value_node.start_mark) + elif key_node.tag == u'tag:yaml.org,2002:value': + key_node.tag = u'tag:yaml.org,2002:str' + index += 1 + else: + index += 1 + if merge: + node.value = merge + node.value + + def construct_mapping(self, node, deep=False): + if isinstance(node, MappingNode): + self.flatten_mapping(node) + return BaseConstructor.construct_mapping(self, node, deep=deep) + + def construct_yaml_null(self, node): + self.construct_scalar(node) + return None + + bool_values = { + u'yes': True, + u'no': False, + u'true': True, + u'false': False, + u'on': True, + u'off': False, + } + + def construct_yaml_bool(self, node): + value = self.construct_scalar(node) + return self.bool_values[value.lower()] + + def construct_yaml_int(self, node): + value = str(self.construct_scalar(node)) + value = value.replace('_', '') + sign = +1 + if value[0] == '-': + sign = -1 + if value[0] in '+-': + value = value[1:] + if value == '0': + return 0 + elif value.startswith('0b'): + return sign*int(value[2:], 2) + elif value.startswith('0x'): + return sign*int(value[2:], 16) + elif value[0] == '0': + return sign*int(value, 8) + elif ':' in value: + digits = [int(part) for part in value.split(':')] + digits.reverse() + base = 1 + value = 0 + for digit in digits: + value += digit*base + base *= 60 + return sign*value + else: + return sign*int(value) + + inf_value = 1e300 + while inf_value != inf_value*inf_value: + inf_value *= inf_value + nan_value = -inf_value/inf_value # Trying to make a quiet NaN (like C99). + + def construct_yaml_float(self, node): + value = str(self.construct_scalar(node)) + value = value.replace('_', '').lower() + sign = +1 + if value[0] == '-': + sign = -1 + if value[0] in '+-': + value = value[1:] + if value == '.inf': + return sign*self.inf_value + elif value == '.nan': + return self.nan_value + elif ':' in value: + digits = [float(part) for part in value.split(':')] + digits.reverse() + base = 1 + value = 0.0 + for digit in digits: + value += digit*base + base *= 60 + return sign*value + else: + return sign*float(value) + + def construct_yaml_binary(self, node): + value = self.construct_scalar(node) + try: + return str(value).decode('base64') + except (binascii.Error, UnicodeEncodeError), exc: + raise ConstructorError(None, None, + "failed to decode base64 data: %s" % exc, node.start_mark) + + timestamp_regexp = re.compile( + ur'''^(?P<year>[0-9][0-9][0-9][0-9]) + -(?P<month>[0-9][0-9]?) + -(?P<day>[0-9][0-9]?) + (?:(?:[Tt]|[ \t]+) + (?P<hour>[0-9][0-9]?) + :(?P<minute>[0-9][0-9]) + :(?P<second>[0-9][0-9]) + (?:\.(?P<fraction>[0-9]*))? + (?:[ \t]*(?P<tz>Z|(?P<tz_sign>[-+])(?P<tz_hour>[0-9][0-9]?) + (?::(?P<tz_minute>[0-9][0-9]))?))?)?$''', re.X) + + def construct_yaml_timestamp(self, node): + value = self.construct_scalar(node) + match = self.timestamp_regexp.match(node.value) + values = match.groupdict() + year = int(values['year']) + month = int(values['month']) + day = int(values['day']) + if not values['hour']: + return datetime.date(year, month, day) + hour = int(values['hour']) + minute = int(values['minute']) + second = int(values['second']) + fraction = 0 + if values['fraction']: + fraction = values['fraction'][:6] + while len(fraction) < 6: + fraction += '0' + fraction = int(fraction) + delta = None + if values['tz_sign']: + tz_hour = int(values['tz_hour']) + tz_minute = int(values['tz_minute'] or 0) + delta = datetime.timedelta(hours=tz_hour, minutes=tz_minute) + if values['tz_sign'] == '-': + delta = -delta + data = datetime.datetime(year, month, day, hour, minute, second, fraction) + if delta: + data -= delta + return data + + def construct_yaml_omap(self, node): + # Note: we do not check for duplicate keys, because it's too + # CPU-expensive. + omap = [] + yield omap + if not isinstance(node, SequenceNode): + raise ConstructorError("while constructing an ordered map", node.start_mark, + "expected a sequence, but found %s" % node.id, node.start_mark) + for subnode in node.value: + if not isinstance(subnode, MappingNode): + raise ConstructorError("while constructing an ordered map", node.start_mark, + "expected a mapping of length 1, but found %s" % subnode.id, + subnode.start_mark) + if len(subnode.value) != 1: + raise ConstructorError("while constructing an ordered map", node.start_mark, + "expected a single mapping item, but found %d items" % len(subnode.value), + subnode.start_mark) + key_node, value_node = subnode.value[0] + key = self.construct_object(key_node) + value = self.construct_object(value_node) + omap.append((key, value)) + + def construct_yaml_pairs(self, node): + # Note: the same code as `construct_yaml_omap`. + pairs = [] + yield pairs + if not isinstance(node, SequenceNode): + raise ConstructorError("while constructing pairs", node.start_mark, + "expected a sequence, but found %s" % node.id, node.start_mark) + for subnode in node.value: + if not isinstance(subnode, MappingNode): + raise ConstructorError("while constructing pairs", node.start_mark, + "expected a mapping of length 1, but found %s" % subnode.id, + subnode.start_mark) + if len(subnode.value) != 1: + raise ConstructorError("while constructing pairs", node.start_mark, + "expected a single mapping item, but found %d items" % len(subnode.value), + subnode.start_mark) + key_node, value_node = subnode.value[0] + key = self.construct_object(key_node) + value = self.construct_object(value_node) + pairs.append((key, value)) + + def construct_yaml_set(self, node): + data = set() + yield data + value = self.construct_mapping(node) + data.update(value) + + def construct_yaml_str(self, node): + value = self.construct_scalar(node) + try: + return value.encode('ascii') + except UnicodeEncodeError: + return value + + def construct_yaml_seq(self, node): + data = [] + yield data + data.extend(self.construct_sequence(node)) + + def construct_yaml_map(self, node): + data = {} + yield data + value = self.construct_mapping(node) + data.update(value) + + def construct_yaml_object(self, node, cls): + data = cls.__new__(cls) + yield data + if hasattr(data, '__setstate__'): + state = self.construct_mapping(node, deep=True) + data.__setstate__(state) + else: + state = self.construct_mapping(node) + data.__dict__.update(state) + + def construct_undefined(self, node): + raise ConstructorError(None, None, + "could not determine a constructor for the tag %r" % node.tag.encode('utf-8'), + node.start_mark) + +SafeConstructor.add_constructor( + u'tag:yaml.org,2002:null', + SafeConstructor.construct_yaml_null) + +SafeConstructor.add_constructor( + u'tag:yaml.org,2002:bool', + SafeConstructor.construct_yaml_bool) + +SafeConstructor.add_constructor( + u'tag:yaml.org,2002:int', + SafeConstructor.construct_yaml_int) + +SafeConstructor.add_constructor( + u'tag:yaml.org,2002:float', + SafeConstructor.construct_yaml_float) + +SafeConstructor.add_constructor( + u'tag:yaml.org,2002:binary', + SafeConstructor.construct_yaml_binary) + +SafeConstructor.add_constructor( + u'tag:yaml.org,2002:timestamp', + SafeConstructor.construct_yaml_timestamp) + +SafeConstructor.add_constructor( + u'tag:yaml.org,2002:omap', + SafeConstructor.construct_yaml_omap) + +SafeConstructor.add_constructor( + u'tag:yaml.org,2002:pairs', + SafeConstructor.construct_yaml_pairs) + +SafeConstructor.add_constructor( + u'tag:yaml.org,2002:set', + SafeConstructor.construct_yaml_set) + +SafeConstructor.add_constructor( + u'tag:yaml.org,2002:str', + SafeConstructor.construct_yaml_str) + +SafeConstructor.add_constructor( + u'tag:yaml.org,2002:seq', + SafeConstructor.construct_yaml_seq) + +SafeConstructor.add_constructor( + u'tag:yaml.org,2002:map', + SafeConstructor.construct_yaml_map) + +SafeConstructor.add_constructor(None, + SafeConstructor.construct_undefined) + +class Constructor(SafeConstructor): + + def construct_python_str(self, node): + return self.construct_scalar(node).encode('utf-8') + + def construct_python_unicode(self, node): + return self.construct_scalar(node) + + def construct_python_long(self, node): + return long(self.construct_yaml_int(node)) + + def construct_python_complex(self, node): + return complex(self.construct_scalar(node)) + + def construct_python_tuple(self, node): + return tuple(self.construct_sequence(node)) + + def find_python_module(self, name, mark): + if not name: + raise ConstructorError("while constructing a Python module", mark, + "expected non-empty name appended to the tag", mark) + try: + __import__(name) + except ImportError, exc: + raise ConstructorError("while constructing a Python module", mark, + "cannot find module %r (%s)" % (name.encode('utf-8'), exc), mark) + return sys.modules[name] + + def find_python_name(self, name, mark): + if not name: + raise ConstructorError("while constructing a Python object", mark, + "expected non-empty name appended to the tag", mark) + if u'.' in name: + module_name, object_name = name.rsplit('.', 1) + else: + module_name = '__builtin__' + object_name = name + try: + __import__(module_name) + except ImportError, exc: + raise ConstructorError("while constructing a Python object", mark, + "cannot find module %r (%s)" % (module_name.encode('utf-8'), exc), mark) + module = sys.modules[module_name] + if not hasattr(module, object_name): + raise ConstructorError("while constructing a Python object", mark, + "cannot find %r in the module %r" % (object_name.encode('utf-8'), + module.__name__), mark) + return getattr(module, object_name) + + def construct_python_name(self, suffix, node): + value = self.construct_scalar(node) + if value: + raise ConstructorError("while constructing a Python name", node.start_mark, + "expected the empty value, but found %r" % value.encode('utf-8'), + node.start_mark) + return self.find_python_name(suffix, node.start_mark) + + def construct_python_module(self, suffix, node): + value = self.construct_scalar(node) + if value: + raise ConstructorError("while constructing a Python module", node.start_mark, + "expected the empty value, but found %r" % value.encode('utf-8'), + node.start_mark) + return self.find_python_module(suffix, node.start_mark) + + class classobj: pass + + def make_python_instance(self, suffix, node, + args=None, kwds=None, newobj=False): + if not args: + args = [] + if not kwds: + kwds = {} + cls = self.find_python_name(suffix, node.start_mark) + if newobj and isinstance(cls, type(self.classobj)) \ + and not args and not kwds: + instance = self.classobj() + instance.__class__ = cls + return instance + elif newobj and isinstance(cls, type): + return cls.__new__(cls, *args, **kwds) + else: + return cls(*args, **kwds) + + def set_python_instance_state(self, instance, state): + if hasattr(instance, '__setstate__'): + instance.__setstate__(state) + else: + slotstate = {} + if isinstance(state, tuple) and len(state) == 2: + state, slotstate = state + if hasattr(instance, '__dict__'): + instance.__dict__.update(state) + elif state: + slotstate.update(state) + for key, value in slotstate.items(): + setattr(object, key, value) + + def construct_python_object(self, suffix, node): + # Format: + # !!python/object:module.name { ... state ... } + instance = self.make_python_instance(suffix, node, newobj=True) + yield instance + deep = hasattr(instance, '__setstate__') + state = self.construct_mapping(node, deep=deep) + self.set_python_instance_state(instance, state) + + def construct_python_object_apply(self, suffix, node, newobj=False): + # Format: + # !!python/object/apply # (or !!python/object/new) + # args: [ ... arguments ... ] + # kwds: { ... keywords ... } + # state: ... state ... + # listitems: [ ... listitems ... ] + # dictitems: { ... dictitems ... } + # or short format: + # !!python/object/apply [ ... arguments ... ] + # The difference between !!python/object/apply and !!python/object/new + # is how an object is created, check make_python_instance for details. + if isinstance(node, SequenceNode): + args = self.construct_sequence(node, deep=True) + kwds = {} + state = {} + listitems = [] + dictitems = {} + else: + value = self.construct_mapping(node, deep=True) + args = value.get('args', []) + kwds = value.get('kwds', {}) + state = value.get('state', {}) + listitems = value.get('listitems', []) + dictitems = value.get('dictitems', {}) + instance = self.make_python_instance(suffix, node, args, kwds, newobj) + if state: + self.set_python_instance_state(instance, state) + if listitems: + instance.extend(listitems) + if dictitems: + for key in dictitems: + instance[key] = dictitems[key] + return instance + + def construct_python_object_new(self, suffix, node): + return self.construct_python_object_apply(suffix, node, newobj=True) + +Constructor.add_constructor( + u'tag:yaml.org,2002:python/none', + Constructor.construct_yaml_null) + +Constructor.add_constructor( + u'tag:yaml.org,2002:python/bool', + Constructor.construct_yaml_bool) + +Constructor.add_constructor( + u'tag:yaml.org,2002:python/str', + Constructor.construct_python_str) + +Constructor.add_constructor( + u'tag:yaml.org,2002:python/unicode', + Constructor.construct_python_unicode) + +Constructor.add_constructor( + u'tag:yaml.org,2002:python/int', + Constructor.construct_yaml_int) + +Constructor.add_constructor( + u'tag:yaml.org,2002:python/long', + Constructor.construct_python_long) + +Constructor.add_constructor( + u'tag:yaml.org,2002:python/float', + Constructor.construct_yaml_float) + +Constructor.add_constructor( + u'tag:yaml.org,2002:python/complex', + Constructor.construct_python_complex) + +Constructor.add_constructor( + u'tag:yaml.org,2002:python/list', + Constructor.construct_yaml_seq) + +Constructor.add_constructor( + u'tag:yaml.org,2002:python/tuple', + Constructor.construct_python_tuple) + +Constructor.add_constructor( + u'tag:yaml.org,2002:python/dict', + Constructor.construct_yaml_map) + +Constructor.add_multi_constructor( + u'tag:yaml.org,2002:python/name:', + Constructor.construct_python_name) + +Constructor.add_multi_constructor( + u'tag:yaml.org,2002:python/module:', + Constructor.construct_python_module) + +Constructor.add_multi_constructor( + u'tag:yaml.org,2002:python/object:', + Constructor.construct_python_object) + +Constructor.add_multi_constructor( + u'tag:yaml.org,2002:python/object/apply:', + Constructor.construct_python_object_apply) + +Constructor.add_multi_constructor( + u'tag:yaml.org,2002:python/object/new:', + Constructor.construct_python_object_new) + diff --git a/python.d/python_modules/pyyaml2/cyaml.py b/python.d/python_modules/pyyaml2/cyaml.py new file mode 100644 index 00000000..68dcd751 --- /dev/null +++ b/python.d/python_modules/pyyaml2/cyaml.py @@ -0,0 +1,85 @@ + +__all__ = ['CBaseLoader', 'CSafeLoader', 'CLoader', + 'CBaseDumper', 'CSafeDumper', 'CDumper'] + +from _yaml import CParser, CEmitter + +from constructor import * + +from serializer import * +from representer import * + +from resolver import * + +class CBaseLoader(CParser, BaseConstructor, BaseResolver): + + def __init__(self, stream): + CParser.__init__(self, stream) + BaseConstructor.__init__(self) + BaseResolver.__init__(self) + +class CSafeLoader(CParser, SafeConstructor, Resolver): + + def __init__(self, stream): + CParser.__init__(self, stream) + SafeConstructor.__init__(self) + Resolver.__init__(self) + +class CLoader(CParser, Constructor, Resolver): + + def __init__(self, stream): + CParser.__init__(self, stream) + Constructor.__init__(self) + Resolver.__init__(self) + +class CBaseDumper(CEmitter, BaseRepresenter, BaseResolver): + + def __init__(self, stream, + default_style=None, default_flow_style=None, + canonical=None, indent=None, width=None, + allow_unicode=None, line_break=None, + encoding=None, explicit_start=None, explicit_end=None, + version=None, tags=None): + CEmitter.__init__(self, stream, canonical=canonical, + indent=indent, width=width, encoding=encoding, + allow_unicode=allow_unicode, line_break=line_break, + explicit_start=explicit_start, explicit_end=explicit_end, + version=version, tags=tags) + Representer.__init__(self, default_style=default_style, + default_flow_style=default_flow_style) + Resolver.__init__(self) + +class CSafeDumper(CEmitter, SafeRepresenter, Resolver): + + def __init__(self, stream, + default_style=None, default_flow_style=None, + canonical=None, indent=None, width=None, + allow_unicode=None, line_break=None, + encoding=None, explicit_start=None, explicit_end=None, + version=None, tags=None): + CEmitter.__init__(self, stream, canonical=canonical, + indent=indent, width=width, encoding=encoding, + allow_unicode=allow_unicode, line_break=line_break, + explicit_start=explicit_start, explicit_end=explicit_end, + version=version, tags=tags) + SafeRepresenter.__init__(self, default_style=default_style, + default_flow_style=default_flow_style) + Resolver.__init__(self) + +class CDumper(CEmitter, Serializer, Representer, Resolver): + + def __init__(self, stream, + default_style=None, default_flow_style=None, + canonical=None, indent=None, width=None, + allow_unicode=None, line_break=None, + encoding=None, explicit_start=None, explicit_end=None, + version=None, tags=None): + CEmitter.__init__(self, stream, canonical=canonical, + indent=indent, width=width, encoding=encoding, + allow_unicode=allow_unicode, line_break=line_break, + explicit_start=explicit_start, explicit_end=explicit_end, + version=version, tags=tags) + Representer.__init__(self, default_style=default_style, + default_flow_style=default_flow_style) + Resolver.__init__(self) + diff --git a/python.d/python_modules/pyyaml2/dumper.py b/python.d/python_modules/pyyaml2/dumper.py new file mode 100644 index 00000000..f811d2c9 --- /dev/null +++ b/python.d/python_modules/pyyaml2/dumper.py @@ -0,0 +1,62 @@ + +__all__ = ['BaseDumper', 'SafeDumper', 'Dumper'] + +from emitter import * +from serializer import * +from representer import * +from resolver import * + +class BaseDumper(Emitter, Serializer, BaseRepresenter, BaseResolver): + + def __init__(self, stream, + default_style=None, default_flow_style=None, + canonical=None, indent=None, width=None, + allow_unicode=None, line_break=None, + encoding=None, explicit_start=None, explicit_end=None, + version=None, tags=None): + Emitter.__init__(self, stream, canonical=canonical, + indent=indent, width=width, + allow_unicode=allow_unicode, line_break=line_break) + Serializer.__init__(self, encoding=encoding, + explicit_start=explicit_start, explicit_end=explicit_end, + version=version, tags=tags) + Representer.__init__(self, default_style=default_style, + default_flow_style=default_flow_style) + Resolver.__init__(self) + +class SafeDumper(Emitter, Serializer, SafeRepresenter, Resolver): + + def __init__(self, stream, + default_style=None, default_flow_style=None, + canonical=None, indent=None, width=None, + allow_unicode=None, line_break=None, + encoding=None, explicit_start=None, explicit_end=None, + version=None, tags=None): + Emitter.__init__(self, stream, canonical=canonical, + indent=indent, width=width, + allow_unicode=allow_unicode, line_break=line_break) + Serializer.__init__(self, encoding=encoding, + explicit_start=explicit_start, explicit_end=explicit_end, + version=version, tags=tags) + SafeRepresenter.__init__(self, default_style=default_style, + default_flow_style=default_flow_style) + Resolver.__init__(self) + +class Dumper(Emitter, Serializer, Representer, Resolver): + + def __init__(self, stream, + default_style=None, default_flow_style=None, + canonical=None, indent=None, width=None, + allow_unicode=None, line_break=None, + encoding=None, explicit_start=None, explicit_end=None, + version=None, tags=None): + Emitter.__init__(self, stream, canonical=canonical, + indent=indent, width=width, + allow_unicode=allow_unicode, line_break=line_break) + Serializer.__init__(self, encoding=encoding, + explicit_start=explicit_start, explicit_end=explicit_end, + version=version, tags=tags) + Representer.__init__(self, default_style=default_style, + default_flow_style=default_flow_style) + Resolver.__init__(self) + diff --git a/python.d/python_modules/pyyaml2/emitter.py b/python.d/python_modules/pyyaml2/emitter.py new file mode 100644 index 00000000..e5bcdccc --- /dev/null +++ b/python.d/python_modules/pyyaml2/emitter.py @@ -0,0 +1,1140 @@ + +# Emitter expects events obeying the following grammar: +# stream ::= STREAM-START document* STREAM-END +# document ::= DOCUMENT-START node DOCUMENT-END +# node ::= SCALAR | sequence | mapping +# sequence ::= SEQUENCE-START node* SEQUENCE-END +# mapping ::= MAPPING-START (node node)* MAPPING-END + +__all__ = ['Emitter', 'EmitterError'] + +from error import YAMLError +from events import * + +class EmitterError(YAMLError): + pass + +class ScalarAnalysis(object): + def __init__(self, scalar, empty, multiline, + allow_flow_plain, allow_block_plain, + allow_single_quoted, allow_double_quoted, + allow_block): + self.scalar = scalar + self.empty = empty + self.multiline = multiline + self.allow_flow_plain = allow_flow_plain + self.allow_block_plain = allow_block_plain + self.allow_single_quoted = allow_single_quoted + self.allow_double_quoted = allow_double_quoted + self.allow_block = allow_block + +class Emitter(object): + + DEFAULT_TAG_PREFIXES = { + u'!' : u'!', + u'tag:yaml.org,2002:' : u'!!', + } + + def __init__(self, stream, canonical=None, indent=None, width=None, + allow_unicode=None, line_break=None): + + # The stream should have the methods `write` and possibly `flush`. + self.stream = stream + + # Encoding can be overriden by STREAM-START. + self.encoding = None + + # Emitter is a state machine with a stack of states to handle nested + # structures. + self.states = [] + self.state = self.expect_stream_start + + # Current event and the event queue. + self.events = [] + self.event = None + + # The current indentation level and the stack of previous indents. + self.indents = [] + self.indent = None + + # Flow level. + self.flow_level = 0 + + # Contexts. + self.root_context = False + self.sequence_context = False + self.mapping_context = False + self.simple_key_context = False + + # Characteristics of the last emitted character: + # - current position. + # - is it a whitespace? + # - is it an indention character + # (indentation space, '-', '?', or ':')? + self.line = 0 + self.column = 0 + self.whitespace = True + self.indention = True + + # Whether the document requires an explicit document indicator + self.open_ended = False + + # Formatting details. + self.canonical = canonical + self.allow_unicode = allow_unicode + self.best_indent = 2 + if indent and 1 < indent < 10: + self.best_indent = indent + self.best_width = 80 + if width and width > self.best_indent*2: + self.best_width = width + self.best_line_break = u'\n' + if line_break in [u'\r', u'\n', u'\r\n']: + self.best_line_break = line_break + + # Tag prefixes. + self.tag_prefixes = None + + # Prepared anchor and tag. + self.prepared_anchor = None + self.prepared_tag = None + + # Scalar analysis and style. + self.analysis = None + self.style = None + + def dispose(self): + # Reset the state attributes (to clear self-references) + self.states = [] + self.state = None + + def emit(self, event): + self.events.append(event) + while not self.need_more_events(): + self.event = self.events.pop(0) + self.state() + self.event = None + + # In some cases, we wait for a few next events before emitting. + + def need_more_events(self): + if not self.events: + return True + event = self.events[0] + if isinstance(event, DocumentStartEvent): + return self.need_events(1) + elif isinstance(event, SequenceStartEvent): + return self.need_events(2) + elif isinstance(event, MappingStartEvent): + return self.need_events(3) + else: + return False + + def need_events(self, count): + level = 0 + for event in self.events[1:]: + if isinstance(event, (DocumentStartEvent, CollectionStartEvent)): + level += 1 + elif isinstance(event, (DocumentEndEvent, CollectionEndEvent)): + level -= 1 + elif isinstance(event, StreamEndEvent): + level = -1 + if level < 0: + return False + return (len(self.events) < count+1) + + def increase_indent(self, flow=False, indentless=False): + self.indents.append(self.indent) + if self.indent is None: + if flow: + self.indent = self.best_indent + else: + self.indent = 0 + elif not indentless: + self.indent += self.best_indent + + # States. + + # Stream handlers. + + def expect_stream_start(self): + if isinstance(self.event, StreamStartEvent): + if self.event.encoding and not getattr(self.stream, 'encoding', None): + self.encoding = self.event.encoding + self.write_stream_start() + self.state = self.expect_first_document_start + else: + raise EmitterError("expected StreamStartEvent, but got %s" + % self.event) + + def expect_nothing(self): + raise EmitterError("expected nothing, but got %s" % self.event) + + # Document handlers. + + def expect_first_document_start(self): + return self.expect_document_start(first=True) + + def expect_document_start(self, first=False): + if isinstance(self.event, DocumentStartEvent): + if (self.event.version or self.event.tags) and self.open_ended: + self.write_indicator(u'...', True) + self.write_indent() + if self.event.version: + version_text = self.prepare_version(self.event.version) + self.write_version_directive(version_text) + self.tag_prefixes = self.DEFAULT_TAG_PREFIXES.copy() + if self.event.tags: + handles = self.event.tags.keys() + handles.sort() + for handle in handles: + prefix = self.event.tags[handle] + self.tag_prefixes[prefix] = handle + handle_text = self.prepare_tag_handle(handle) + prefix_text = self.prepare_tag_prefix(prefix) + self.write_tag_directive(handle_text, prefix_text) + implicit = (first and not self.event.explicit and not self.canonical + and not self.event.version and not self.event.tags + and not self.check_empty_document()) + if not implicit: + self.write_indent() + self.write_indicator(u'---', True) + if self.canonical: + self.write_indent() + self.state = self.expect_document_root + elif isinstance(self.event, StreamEndEvent): + if self.open_ended: + self.write_indicator(u'...', True) + self.write_indent() + self.write_stream_end() + self.state = self.expect_nothing + else: + raise EmitterError("expected DocumentStartEvent, but got %s" + % self.event) + + def expect_document_end(self): + if isinstance(self.event, DocumentEndEvent): + self.write_indent() + if self.event.explicit: + self.write_indicator(u'...', True) + self.write_indent() + self.flush_stream() + self.state = self.expect_document_start + else: + raise EmitterError("expected DocumentEndEvent, but got %s" + % self.event) + + def expect_document_root(self): + self.states.append(self.expect_document_end) + self.expect_node(root=True) + + # Node handlers. + + def expect_node(self, root=False, sequence=False, mapping=False, + simple_key=False): + self.root_context = root + self.sequence_context = sequence + self.mapping_context = mapping + self.simple_key_context = simple_key + if isinstance(self.event, AliasEvent): + self.expect_alias() + elif isinstance(self.event, (ScalarEvent, CollectionStartEvent)): + self.process_anchor(u'&') + self.process_tag() + if isinstance(self.event, ScalarEvent): + self.expect_scalar() + elif isinstance(self.event, SequenceStartEvent): + if self.flow_level or self.canonical or self.event.flow_style \ + or self.check_empty_sequence(): + self.expect_flow_sequence() + else: + self.expect_block_sequence() + elif isinstance(self.event, MappingStartEvent): + if self.flow_level or self.canonical or self.event.flow_style \ + or self.check_empty_mapping(): + self.expect_flow_mapping() + else: + self.expect_block_mapping() + else: + raise EmitterError("expected NodeEvent, but got %s" % self.event) + + def expect_alias(self): + if self.event.anchor is None: + raise EmitterError("anchor is not specified for alias") + self.process_anchor(u'*') + self.state = self.states.pop() + + def expect_scalar(self): + self.increase_indent(flow=True) + self.process_scalar() + self.indent = self.indents.pop() + self.state = self.states.pop() + + # Flow sequence handlers. + + def expect_flow_sequence(self): + self.write_indicator(u'[', True, whitespace=True) + self.flow_level += 1 + self.increase_indent(flow=True) + self.state = self.expect_first_flow_sequence_item + + def expect_first_flow_sequence_item(self): + if isinstance(self.event, SequenceEndEvent): + self.indent = self.indents.pop() + self.flow_level -= 1 + self.write_indicator(u']', False) + self.state = self.states.pop() + else: + if self.canonical or self.column > self.best_width: + self.write_indent() + self.states.append(self.expect_flow_sequence_item) + self.expect_node(sequence=True) + + def expect_flow_sequence_item(self): + if isinstance(self.event, SequenceEndEvent): + self.indent = self.indents.pop() + self.flow_level -= 1 + if self.canonical: + self.write_indicator(u',', False) + self.write_indent() + self.write_indicator(u']', False) + self.state = self.states.pop() + else: + self.write_indicator(u',', False) + if self.canonical or self.column > self.best_width: + self.write_indent() + self.states.append(self.expect_flow_sequence_item) + self.expect_node(sequence=True) + + # Flow mapping handlers. + + def expect_flow_mapping(self): + self.write_indicator(u'{', True, whitespace=True) + self.flow_level += 1 + self.increase_indent(flow=True) + self.state = self.expect_first_flow_mapping_key + + def expect_first_flow_mapping_key(self): + if isinstance(self.event, MappingEndEvent): + self.indent = self.indents.pop() + self.flow_level -= 1 + self.write_indicator(u'}', False) + self.state = self.states.pop() + else: + if self.canonical or self.column > self.best_width: + self.write_indent() + if not self.canonical and self.check_simple_key(): + self.states.append(self.expect_flow_mapping_simple_value) + self.expect_node(mapping=True, simple_key=True) + else: + self.write_indicator(u'?', True) + self.states.append(self.expect_flow_mapping_value) + self.expect_node(mapping=True) + + def expect_flow_mapping_key(self): + if isinstance(self.event, MappingEndEvent): + self.indent = self.indents.pop() + self.flow_level -= 1 + if self.canonical: + self.write_indicator(u',', False) + self.write_indent() + self.write_indicator(u'}', False) + self.state = self.states.pop() + else: + self.write_indicator(u',', False) + if self.canonical or self.column > self.best_width: + self.write_indent() + if not self.canonical and self.check_simple_key(): + self.states.append(self.expect_flow_mapping_simple_value) + self.expect_node(mapping=True, simple_key=True) + else: + self.write_indicator(u'?', True) + self.states.append(self.expect_flow_mapping_value) + self.expect_node(mapping=True) + + def expect_flow_mapping_simple_value(self): + self.write_indicator(u':', False) + self.states.append(self.expect_flow_mapping_key) + self.expect_node(mapping=True) + + def expect_flow_mapping_value(self): + if self.canonical or self.column > self.best_width: + self.write_indent() + self.write_indicator(u':', True) + self.states.append(self.expect_flow_mapping_key) + self.expect_node(mapping=True) + + # Block sequence handlers. + + def expect_block_sequence(self): + indentless = (self.mapping_context and not self.indention) + self.increase_indent(flow=False, indentless=indentless) + self.state = self.expect_first_block_sequence_item + + def expect_first_block_sequence_item(self): + return self.expect_block_sequence_item(first=True) + + def expect_block_sequence_item(self, first=False): + if not first and isinstance(self.event, SequenceEndEvent): + self.indent = self.indents.pop() + self.state = self.states.pop() + else: + self.write_indent() + self.write_indicator(u'-', True, indention=True) + self.states.append(self.expect_block_sequence_item) + self.expect_node(sequence=True) + + # Block mapping handlers. + + def expect_block_mapping(self): + self.increase_indent(flow=False) + self.state = self.expect_first_block_mapping_key + + def expect_first_block_mapping_key(self): + return self.expect_block_mapping_key(first=True) + + def expect_block_mapping_key(self, first=False): + if not first and isinstance(self.event, MappingEndEvent): + self.indent = self.indents.pop() + self.state = self.states.pop() + else: + self.write_indent() + if self.check_simple_key(): + self.states.append(self.expect_block_mapping_simple_value) + self.expect_node(mapping=True, simple_key=True) + else: + self.write_indicator(u'?', True, indention=True) + self.states.append(self.expect_block_mapping_value) + self.expect_node(mapping=True) + + def expect_block_mapping_simple_value(self): + self.write_indicator(u':', False) + self.states.append(self.expect_block_mapping_key) + self.expect_node(mapping=True) + + def expect_block_mapping_value(self): + self.write_indent() + self.write_indicator(u':', True, indention=True) + self.states.append(self.expect_block_mapping_key) + self.expect_node(mapping=True) + + # Checkers. + + def check_empty_sequence(self): + return (isinstance(self.event, SequenceStartEvent) and self.events + and isinstance(self.events[0], SequenceEndEvent)) + + def check_empty_mapping(self): + return (isinstance(self.event, MappingStartEvent) and self.events + and isinstance(self.events[0], MappingEndEvent)) + + def check_empty_document(self): + if not isinstance(self.event, DocumentStartEvent) or not self.events: + return False + event = self.events[0] + return (isinstance(event, ScalarEvent) and event.anchor is None + and event.tag is None and event.implicit and event.value == u'') + + def check_simple_key(self): + length = 0 + if isinstance(self.event, NodeEvent) and self.event.anchor is not None: + if self.prepared_anchor is None: + self.prepared_anchor = self.prepare_anchor(self.event.anchor) + length += len(self.prepared_anchor) + if isinstance(self.event, (ScalarEvent, CollectionStartEvent)) \ + and self.event.tag is not None: + if self.prepared_tag is None: + self.prepared_tag = self.prepare_tag(self.event.tag) + length += len(self.prepared_tag) + if isinstance(self.event, ScalarEvent): + if self.analysis is None: + self.analysis = self.analyze_scalar(self.event.value) + length += len(self.analysis.scalar) + return (length < 128 and (isinstance(self.event, AliasEvent) + or (isinstance(self.event, ScalarEvent) + and not self.analysis.empty and not self.analysis.multiline) + or self.check_empty_sequence() or self.check_empty_mapping())) + + # Anchor, Tag, and Scalar processors. + + def process_anchor(self, indicator): + if self.event.anchor is None: + self.prepared_anchor = None + return + if self.prepared_anchor is None: + self.prepared_anchor = self.prepare_anchor(self.event.anchor) + if self.prepared_anchor: + self.write_indicator(indicator+self.prepared_anchor, True) + self.prepared_anchor = None + + def process_tag(self): + tag = self.event.tag + if isinstance(self.event, ScalarEvent): + if self.style is None: + self.style = self.choose_scalar_style() + if ((not self.canonical or tag is None) and + ((self.style == '' and self.event.implicit[0]) + or (self.style != '' and self.event.implicit[1]))): + self.prepared_tag = None + return + if self.event.implicit[0] and tag is None: + tag = u'!' + self.prepared_tag = None + else: + if (not self.canonical or tag is None) and self.event.implicit: + self.prepared_tag = None + return + if tag is None: + raise EmitterError("tag is not specified") + if self.prepared_tag is None: + self.prepared_tag = self.prepare_tag(tag) + if self.prepared_tag: + self.write_indicator(self.prepared_tag, True) + self.prepared_tag = None + + def choose_scalar_style(self): + if self.analysis is None: + self.analysis = self.analyze_scalar(self.event.value) + if self.event.style == '"' or self.canonical: + return '"' + if not self.event.style and self.event.implicit[0]: + if (not (self.simple_key_context and + (self.analysis.empty or self.analysis.multiline)) + and (self.flow_level and self.analysis.allow_flow_plain + or (not self.flow_level and self.analysis.allow_block_plain))): + return '' + if self.event.style and self.event.style in '|>': + if (not self.flow_level and not self.simple_key_context + and self.analysis.allow_block): + return self.event.style + if not self.event.style or self.event.style == '\'': + if (self.analysis.allow_single_quoted and + not (self.simple_key_context and self.analysis.multiline)): + return '\'' + return '"' + + def process_scalar(self): + if self.analysis is None: + self.analysis = self.analyze_scalar(self.event.value) + if self.style is None: + self.style = self.choose_scalar_style() + split = (not self.simple_key_context) + #if self.analysis.multiline and split \ + # and (not self.style or self.style in '\'\"'): + # self.write_indent() + if self.style == '"': + self.write_double_quoted(self.analysis.scalar, split) + elif self.style == '\'': + self.write_single_quoted(self.analysis.scalar, split) + elif self.style == '>': + self.write_folded(self.analysis.scalar) + elif self.style == '|': + self.write_literal(self.analysis.scalar) + else: + self.write_plain(self.analysis.scalar, split) + self.analysis = None + self.style = None + + # Analyzers. + + def prepare_version(self, version): + major, minor = version + if major != 1: + raise EmitterError("unsupported YAML version: %d.%d" % (major, minor)) + return u'%d.%d' % (major, minor) + + def prepare_tag_handle(self, handle): + if not handle: + raise EmitterError("tag handle must not be empty") + if handle[0] != u'!' or handle[-1] != u'!': + raise EmitterError("tag handle must start and end with '!': %r" + % (handle.encode('utf-8'))) + for ch in handle[1:-1]: + if not (u'0' <= ch <= u'9' or u'A' <= ch <= u'Z' or u'a' <= ch <= u'z' \ + or ch in u'-_'): + raise EmitterError("invalid character %r in the tag handle: %r" + % (ch.encode('utf-8'), handle.encode('utf-8'))) + return handle + + def prepare_tag_prefix(self, prefix): + if not prefix: + raise EmitterError("tag prefix must not be empty") + chunks = [] + start = end = 0 + if prefix[0] == u'!': + end = 1 + while end < len(prefix): + ch = prefix[end] + if u'0' <= ch <= u'9' or u'A' <= ch <= u'Z' or u'a' <= ch <= u'z' \ + or ch in u'-;/?!:@&=+$,_.~*\'()[]': + end += 1 + else: + if start < end: + chunks.append(prefix[start:end]) + start = end = end+1 + data = ch.encode('utf-8') + for ch in data: + chunks.append(u'%%%02X' % ord(ch)) + if start < end: + chunks.append(prefix[start:end]) + return u''.join(chunks) + + def prepare_tag(self, tag): + if not tag: + raise EmitterError("tag must not be empty") + if tag == u'!': + return tag + handle = None + suffix = tag + prefixes = self.tag_prefixes.keys() + prefixes.sort() + for prefix in prefixes: + if tag.startswith(prefix) \ + and (prefix == u'!' or len(prefix) < len(tag)): + handle = self.tag_prefixes[prefix] + suffix = tag[len(prefix):] + chunks = [] + start = end = 0 + while end < len(suffix): + ch = suffix[end] + if u'0' <= ch <= u'9' or u'A' <= ch <= u'Z' or u'a' <= ch <= u'z' \ + or ch in u'-;/?:@&=+$,_.~*\'()[]' \ + or (ch == u'!' and handle != u'!'): + end += 1 + else: + if start < end: + chunks.append(suffix[start:end]) + start = end = end+1 + data = ch.encode('utf-8') + for ch in data: + chunks.append(u'%%%02X' % ord(ch)) + if start < end: + chunks.append(suffix[start:end]) + suffix_text = u''.join(chunks) + if handle: + return u'%s%s' % (handle, suffix_text) + else: + return u'!<%s>' % suffix_text + + def prepare_anchor(self, anchor): + if not anchor: + raise EmitterError("anchor must not be empty") + for ch in anchor: + if not (u'0' <= ch <= u'9' or u'A' <= ch <= u'Z' or u'a' <= ch <= u'z' \ + or ch in u'-_'): + raise EmitterError("invalid character %r in the anchor: %r" + % (ch.encode('utf-8'), anchor.encode('utf-8'))) + return anchor + + def analyze_scalar(self, scalar): + + # Empty scalar is a special case. + if not scalar: + return ScalarAnalysis(scalar=scalar, empty=True, multiline=False, + allow_flow_plain=False, allow_block_plain=True, + allow_single_quoted=True, allow_double_quoted=True, + allow_block=False) + + # Indicators and special characters. + block_indicators = False + flow_indicators = False + line_breaks = False + special_characters = False + + # Important whitespace combinations. + leading_space = False + leading_break = False + trailing_space = False + trailing_break = False + break_space = False + space_break = False + + # Check document indicators. + if scalar.startswith(u'---') or scalar.startswith(u'...'): + block_indicators = True + flow_indicators = True + + # First character or preceded by a whitespace. + preceeded_by_whitespace = True + + # Last character or followed by a whitespace. + followed_by_whitespace = (len(scalar) == 1 or + scalar[1] in u'\0 \t\r\n\x85\u2028\u2029') + + # The previous character is a space. + previous_space = False + + # The previous character is a break. + previous_break = False + + index = 0 + while index < len(scalar): + ch = scalar[index] + + # Check for indicators. + if index == 0: + # Leading indicators are special characters. + if ch in u'#,[]{}&*!|>\'\"%@`': + flow_indicators = True + block_indicators = True + if ch in u'?:': + flow_indicators = True + if followed_by_whitespace: + block_indicators = True + if ch == u'-' and followed_by_whitespace: + flow_indicators = True + block_indicators = True + else: + # Some indicators cannot appear within a scalar as well. + if ch in u',?[]{}': + flow_indicators = True + if ch == u':': + flow_indicators = True + if followed_by_whitespace: + block_indicators = True + if ch == u'#' and preceeded_by_whitespace: + flow_indicators = True + block_indicators = True + + # Check for line breaks, special, and unicode characters. + if ch in u'\n\x85\u2028\u2029': + line_breaks = True + if not (ch == u'\n' or u'\x20' <= ch <= u'\x7E'): + if (ch == u'\x85' or u'\xA0' <= ch <= u'\uD7FF' + or u'\uE000' <= ch <= u'\uFFFD') and ch != u'\uFEFF': + unicode_characters = True + if not self.allow_unicode: + special_characters = True + else: + special_characters = True + + # Detect important whitespace combinations. + if ch == u' ': + if index == 0: + leading_space = True + if index == len(scalar)-1: + trailing_space = True + if previous_break: + break_space = True + previous_space = True + previous_break = False + elif ch in u'\n\x85\u2028\u2029': + if index == 0: + leading_break = True + if index == len(scalar)-1: + trailing_break = True + if previous_space: + space_break = True + previous_space = False + previous_break = True + else: + previous_space = False + previous_break = False + + # Prepare for the next character. + index += 1 + preceeded_by_whitespace = (ch in u'\0 \t\r\n\x85\u2028\u2029') + followed_by_whitespace = (index+1 >= len(scalar) or + scalar[index+1] in u'\0 \t\r\n\x85\u2028\u2029') + + # Let's decide what styles are allowed. + allow_flow_plain = True + allow_block_plain = True + allow_single_quoted = True + allow_double_quoted = True + allow_block = True + + # Leading and trailing whitespaces are bad for plain scalars. + if (leading_space or leading_break + or trailing_space or trailing_break): + allow_flow_plain = allow_block_plain = False + + # We do not permit trailing spaces for block scalars. + if trailing_space: + allow_block = False + + # Spaces at the beginning of a new line are only acceptable for block + # scalars. + if break_space: + allow_flow_plain = allow_block_plain = allow_single_quoted = False + + # Spaces followed by breaks, as well as special character are only + # allowed for double quoted scalars. + if space_break or special_characters: + allow_flow_plain = allow_block_plain = \ + allow_single_quoted = allow_block = False + + # Although the plain scalar writer supports breaks, we never emit + # multiline plain scalars. + if line_breaks: + allow_flow_plain = allow_block_plain = False + + # Flow indicators are forbidden for flow plain scalars. + if flow_indicators: + allow_flow_plain = False + + # Block indicators are forbidden for block plain scalars. + if block_indicators: + allow_block_plain = False + + return ScalarAnalysis(scalar=scalar, + empty=False, multiline=line_breaks, + allow_flow_plain=allow_flow_plain, + allow_block_plain=allow_block_plain, + allow_single_quoted=allow_single_quoted, + allow_double_quoted=allow_double_quoted, + allow_block=allow_block) + + # Writers. + + def flush_stream(self): + if hasattr(self.stream, 'flush'): + self.stream.flush() + + def write_stream_start(self): + # Write BOM if needed. + if self.encoding and self.encoding.startswith('utf-16'): + self.stream.write(u'\uFEFF'.encode(self.encoding)) + + def write_stream_end(self): + self.flush_stream() + + def write_indicator(self, indicator, need_whitespace, + whitespace=False, indention=False): + if self.whitespace or not need_whitespace: + data = indicator + else: + data = u' '+indicator + self.whitespace = whitespace + self.indention = self.indention and indention + self.column += len(data) + self.open_ended = False + if self.encoding: + data = data.encode(self.encoding) + self.stream.write(data) + + def write_indent(self): + indent = self.indent or 0 + if not self.indention or self.column > indent \ + or (self.column == indent and not self.whitespace): + self.write_line_break() + if self.column < indent: + self.whitespace = True + data = u' '*(indent-self.column) + self.column = indent + if self.encoding: + data = data.encode(self.encoding) + self.stream.write(data) + + def write_line_break(self, data=None): + if data is None: + data = self.best_line_break + self.whitespace = True + self.indention = True + self.line += 1 + self.column = 0 + if self.encoding: + data = data.encode(self.encoding) + self.stream.write(data) + + def write_version_directive(self, version_text): + data = u'%%YAML %s' % version_text + if self.encoding: + data = data.encode(self.encoding) + self.stream.write(data) + self.write_line_break() + + def write_tag_directive(self, handle_text, prefix_text): + data = u'%%TAG %s %s' % (handle_text, prefix_text) + if self.encoding: + data = data.encode(self.encoding) + self.stream.write(data) + self.write_line_break() + + # Scalar streams. + + def write_single_quoted(self, text, split=True): + self.write_indicator(u'\'', True) + spaces = False + breaks = False + start = end = 0 + while end <= len(text): + ch = None + if end < len(text): + ch = text[end] + if spaces: + if ch is None or ch != u' ': + if start+1 == end and self.column > self.best_width and split \ + and start != 0 and end != len(text): + self.write_indent() + else: + data = text[start:end] + self.column += len(data) + if self.encoding: + data = data.encode(self.encoding) + self.stream.write(data) + start = end + elif breaks: + if ch is None or ch not in u'\n\x85\u2028\u2029': + if text[start] == u'\n': + self.write_line_break() + for br in text[start:end]: + if br == u'\n': + self.write_line_break() + else: + self.write_line_break(br) + self.write_indent() + start = end + else: + if ch is None or ch in u' \n\x85\u2028\u2029' or ch == u'\'': + if start < end: + data = text[start:end] + self.column += len(data) + if self.encoding: + data = data.encode(self.encoding) + self.stream.write(data) + start = end + if ch == u'\'': + data = u'\'\'' + self.column += 2 + if self.encoding: + data = data.encode(self.encoding) + self.stream.write(data) + start = end + 1 + if ch is not None: + spaces = (ch == u' ') + breaks = (ch in u'\n\x85\u2028\u2029') + end += 1 + self.write_indicator(u'\'', False) + + ESCAPE_REPLACEMENTS = { + u'\0': u'0', + u'\x07': u'a', + u'\x08': u'b', + u'\x09': u't', + u'\x0A': u'n', + u'\x0B': u'v', + u'\x0C': u'f', + u'\x0D': u'r', + u'\x1B': u'e', + u'\"': u'\"', + u'\\': u'\\', + u'\x85': u'N', + u'\xA0': u'_', + u'\u2028': u'L', + u'\u2029': u'P', + } + + def write_double_quoted(self, text, split=True): + self.write_indicator(u'"', True) + start = end = 0 + while end <= len(text): + ch = None + if end < len(text): + ch = text[end] + if ch is None or ch in u'"\\\x85\u2028\u2029\uFEFF' \ + or not (u'\x20' <= ch <= u'\x7E' + or (self.allow_unicode + and (u'\xA0' <= ch <= u'\uD7FF' + or u'\uE000' <= ch <= u'\uFFFD'))): + if start < end: + data = text[start:end] + self.column += len(data) + if self.encoding: + data = data.encode(self.encoding) + self.stream.write(data) + start = end + if ch is not None: + if ch in self.ESCAPE_REPLACEMENTS: + data = u'\\'+self.ESCAPE_REPLACEMENTS[ch] + elif ch <= u'\xFF': + data = u'\\x%02X' % ord(ch) + elif ch <= u'\uFFFF': + data = u'\\u%04X' % ord(ch) + else: + data = u'\\U%08X' % ord(ch) + self.column += len(data) + if self.encoding: + data = data.encode(self.encoding) + self.stream.write(data) + start = end+1 + if 0 < end < len(text)-1 and (ch == u' ' or start >= end) \ + and self.column+(end-start) > self.best_width and split: + data = text[start:end]+u'\\' + if start < end: + start = end + self.column += len(data) + if self.encoding: + data = data.encode(self.encoding) + self.stream.write(data) + self.write_indent() + self.whitespace = False + self.indention = False + if text[start] == u' ': + data = u'\\' + self.column += len(data) + if self.encoding: + data = data.encode(self.encoding) + self.stream.write(data) + end += 1 + self.write_indicator(u'"', False) + + def determine_block_hints(self, text): + hints = u'' + if text: + if text[0] in u' \n\x85\u2028\u2029': + hints += unicode(self.best_indent) + if text[-1] not in u'\n\x85\u2028\u2029': + hints += u'-' + elif len(text) == 1 or text[-2] in u'\n\x85\u2028\u2029': + hints += u'+' + return hints + + def write_folded(self, text): + hints = self.determine_block_hints(text) + self.write_indicator(u'>'+hints, True) + if hints[-1:] == u'+': + self.open_ended = True + self.write_line_break() + leading_space = True + spaces = False + breaks = True + start = end = 0 + while end <= len(text): + ch = None + if end < len(text): + ch = text[end] + if breaks: + if ch is None or ch not in u'\n\x85\u2028\u2029': + if not leading_space and ch is not None and ch != u' ' \ + and text[start] == u'\n': + self.write_line_break() + leading_space = (ch == u' ') + for br in text[start:end]: + if br == u'\n': + self.write_line_break() + else: + self.write_line_break(br) + if ch is not None: + self.write_indent() + start = end + elif spaces: + if ch != u' ': + if start+1 == end and self.column > self.best_width: + self.write_indent() + else: + data = text[start:end] + self.column += len(data) + if self.encoding: + data = data.encode(self.encoding) + self.stream.write(data) + start = end + else: + if ch is None or ch in u' \n\x85\u2028\u2029': + data = text[start:end] + self.column += len(data) + if self.encoding: + data = data.encode(self.encoding) + self.stream.write(data) + if ch is None: + self.write_line_break() + start = end + if ch is not None: + breaks = (ch in u'\n\x85\u2028\u2029') + spaces = (ch == u' ') + end += 1 + + def write_literal(self, text): + hints = self.determine_block_hints(text) + self.write_indicator(u'|'+hints, True) + if hints[-1:] == u'+': + self.open_ended = True + self.write_line_break() + breaks = True + start = end = 0 + while end <= len(text): + ch = None + if end < len(text): + ch = text[end] + if breaks: + if ch is None or ch not in u'\n\x85\u2028\u2029': + for br in text[start:end]: + if br == u'\n': + self.write_line_break() + else: + self.write_line_break(br) + if ch is not None: + self.write_indent() + start = end + else: + if ch is None or ch in u'\n\x85\u2028\u2029': + data = text[start:end] + if self.encoding: + data = data.encode(self.encoding) + self.stream.write(data) + if ch is None: + self.write_line_break() + start = end + if ch is not None: + breaks = (ch in u'\n\x85\u2028\u2029') + end += 1 + + def write_plain(self, text, split=True): + if self.root_context: + self.open_ended = True + if not text: + return + if not self.whitespace: + data = u' ' + self.column += len(data) + if self.encoding: + data = data.encode(self.encoding) + self.stream.write(data) + self.whitespace = False + self.indention = False + spaces = False + breaks = False + start = end = 0 + while end <= len(text): + ch = None + if end < len(text): + ch = text[end] + if spaces: + if ch != u' ': + if start+1 == end and self.column > self.best_width and split: + self.write_indent() + self.whitespace = False + self.indention = False + else: + data = text[start:end] + self.column += len(data) + if self.encoding: + data = data.encode(self.encoding) + self.stream.write(data) + start = end + elif breaks: + if ch not in u'\n\x85\u2028\u2029': + if text[start] == u'\n': + self.write_line_break() + for br in text[start:end]: + if br == u'\n': + self.write_line_break() + else: + self.write_line_break(br) + self.write_indent() + self.whitespace = False + self.indention = False + start = end + else: + if ch is None or ch in u' \n\x85\u2028\u2029': + data = text[start:end] + self.column += len(data) + if self.encoding: + data = data.encode(self.encoding) + self.stream.write(data) + start = end + if ch is not None: + spaces = (ch == u' ') + breaks = (ch in u'\n\x85\u2028\u2029') + end += 1 + diff --git a/python.d/python_modules/pyyaml2/error.py b/python.d/python_modules/pyyaml2/error.py new file mode 100644 index 00000000..577686db --- /dev/null +++ b/python.d/python_modules/pyyaml2/error.py @@ -0,0 +1,75 @@ + +__all__ = ['Mark', 'YAMLError', 'MarkedYAMLError'] + +class Mark(object): + + def __init__(self, name, index, line, column, buffer, pointer): + self.name = name + self.index = index + self.line = line + self.column = column + self.buffer = buffer + self.pointer = pointer + + def get_snippet(self, indent=4, max_length=75): + if self.buffer is None: + return None + head = '' + start = self.pointer + while start > 0 and self.buffer[start-1] not in u'\0\r\n\x85\u2028\u2029': + start -= 1 + if self.pointer-start > max_length/2-1: + head = ' ... ' + start += 5 + break + tail = '' + end = self.pointer + while end < len(self.buffer) and self.buffer[end] not in u'\0\r\n\x85\u2028\u2029': + end += 1 + if end-self.pointer > max_length/2-1: + tail = ' ... ' + end -= 5 + break + snippet = self.buffer[start:end].encode('utf-8') + return ' '*indent + head + snippet + tail + '\n' \ + + ' '*(indent+self.pointer-start+len(head)) + '^' + + def __str__(self): + snippet = self.get_snippet() + where = " in \"%s\", line %d, column %d" \ + % (self.name, self.line+1, self.column+1) + if snippet is not None: + where += ":\n"+snippet + return where + +class YAMLError(Exception): + pass + +class MarkedYAMLError(YAMLError): + + def __init__(self, context=None, context_mark=None, + problem=None, problem_mark=None, note=None): + self.context = context + self.context_mark = context_mark + self.problem = problem + self.problem_mark = problem_mark + self.note = note + + def __str__(self): + lines = [] + if self.context is not None: + lines.append(self.context) + if self.context_mark is not None \ + and (self.problem is None or self.problem_mark is None + or self.context_mark.name != self.problem_mark.name + or self.context_mark.line != self.problem_mark.line + or self.context_mark.column != self.problem_mark.column): + lines.append(str(self.context_mark)) + if self.problem is not None: + lines.append(self.problem) + if self.problem_mark is not None: + lines.append(str(self.problem_mark)) + if self.note is not None: + lines.append(self.note) + return '\n'.join(lines) + diff --git a/python.d/python_modules/pyyaml2/events.py b/python.d/python_modules/pyyaml2/events.py new file mode 100644 index 00000000..f79ad389 --- /dev/null +++ b/python.d/python_modules/pyyaml2/events.py @@ -0,0 +1,86 @@ + +# Abstract classes. + +class Event(object): + def __init__(self, start_mark=None, end_mark=None): + self.start_mark = start_mark + self.end_mark = end_mark + def __repr__(self): + attributes = [key for key in ['anchor', 'tag', 'implicit', 'value'] + if hasattr(self, key)] + arguments = ', '.join(['%s=%r' % (key, getattr(self, key)) + for key in attributes]) + return '%s(%s)' % (self.__class__.__name__, arguments) + +class NodeEvent(Event): + def __init__(self, anchor, start_mark=None, end_mark=None): + self.anchor = anchor + self.start_mark = start_mark + self.end_mark = end_mark + +class CollectionStartEvent(NodeEvent): + def __init__(self, anchor, tag, implicit, start_mark=None, end_mark=None, + flow_style=None): + self.anchor = anchor + self.tag = tag + self.implicit = implicit + self.start_mark = start_mark + self.end_mark = end_mark + self.flow_style = flow_style + +class CollectionEndEvent(Event): + pass + +# Implementations. + +class StreamStartEvent(Event): + def __init__(self, start_mark=None, end_mark=None, encoding=None): + self.start_mark = start_mark + self.end_mark = end_mark + self.encoding = encoding + +class StreamEndEvent(Event): + pass + +class DocumentStartEvent(Event): + def __init__(self, start_mark=None, end_mark=None, + explicit=None, version=None, tags=None): + self.start_mark = start_mark + self.end_mark = end_mark + self.explicit = explicit + self.version = version + self.tags = tags + +class DocumentEndEvent(Event): + def __init__(self, start_mark=None, end_mark=None, + explicit=None): + self.start_mark = start_mark + self.end_mark = end_mark + self.explicit = explicit + +class AliasEvent(NodeEvent): + pass + +class ScalarEvent(NodeEvent): + def __init__(self, anchor, tag, implicit, value, + start_mark=None, end_mark=None, style=None): + self.anchor = anchor + self.tag = tag + self.implicit = implicit + self.value = value + self.start_mark = start_mark + self.end_mark = end_mark + self.style = style + +class SequenceStartEvent(CollectionStartEvent): + pass + +class SequenceEndEvent(CollectionEndEvent): + pass + +class MappingStartEvent(CollectionStartEvent): + pass + +class MappingEndEvent(CollectionEndEvent): + pass + diff --git a/python.d/python_modules/pyyaml2/loader.py b/python.d/python_modules/pyyaml2/loader.py new file mode 100644 index 00000000..293ff467 --- /dev/null +++ b/python.d/python_modules/pyyaml2/loader.py @@ -0,0 +1,40 @@ + +__all__ = ['BaseLoader', 'SafeLoader', 'Loader'] + +from reader import * +from scanner import * +from parser import * +from composer import * +from constructor import * +from resolver import * + +class BaseLoader(Reader, Scanner, Parser, Composer, BaseConstructor, BaseResolver): + + def __init__(self, stream): + Reader.__init__(self, stream) + Scanner.__init__(self) + Parser.__init__(self) + Composer.__init__(self) + BaseConstructor.__init__(self) + BaseResolver.__init__(self) + +class SafeLoader(Reader, Scanner, Parser, Composer, SafeConstructor, Resolver): + + def __init__(self, stream): + Reader.__init__(self, stream) + Scanner.__init__(self) + Parser.__init__(self) + Composer.__init__(self) + SafeConstructor.__init__(self) + Resolver.__init__(self) + +class Loader(Reader, Scanner, Parser, Composer, Constructor, Resolver): + + def __init__(self, stream): + Reader.__init__(self, stream) + Scanner.__init__(self) + Parser.__init__(self) + Composer.__init__(self) + Constructor.__init__(self) + Resolver.__init__(self) + diff --git a/python.d/python_modules/pyyaml2/nodes.py b/python.d/python_modules/pyyaml2/nodes.py new file mode 100644 index 00000000..c4f070c4 --- /dev/null +++ b/python.d/python_modules/pyyaml2/nodes.py @@ -0,0 +1,49 @@ + +class Node(object): + def __init__(self, tag, value, start_mark, end_mark): + self.tag = tag + self.value = value + self.start_mark = start_mark + self.end_mark = end_mark + def __repr__(self): + value = self.value + #if isinstance(value, list): + # if len(value) == 0: + # value = '<empty>' + # elif len(value) == 1: + # value = '<1 item>' + # else: + # value = '<%d items>' % len(value) + #else: + # if len(value) > 75: + # value = repr(value[:70]+u' ... ') + # else: + # value = repr(value) + value = repr(value) + return '%s(tag=%r, value=%s)' % (self.__class__.__name__, self.tag, value) + +class ScalarNode(Node): + id = 'scalar' + def __init__(self, tag, value, + start_mark=None, end_mark=None, style=None): + self.tag = tag + self.value = value + self.start_mark = start_mark + self.end_mark = end_mark + self.style = style + +class CollectionNode(Node): + def __init__(self, tag, value, + start_mark=None, end_mark=None, flow_style=None): + self.tag = tag + self.value = value + self.start_mark = start_mark + self.end_mark = end_mark + self.flow_style = flow_style + +class SequenceNode(CollectionNode): + id = 'sequence' + +class MappingNode(CollectionNode): + id = 'mapping' + diff --git a/python.d/python_modules/pyyaml2/parser.py b/python.d/python_modules/pyyaml2/parser.py new file mode 100644 index 00000000..f9e3057f --- /dev/null +++ b/python.d/python_modules/pyyaml2/parser.py @@ -0,0 +1,589 @@ + +# The following YAML grammar is LL(1) and is parsed by a recursive descent +# parser. +# +# stream ::= STREAM-START implicit_document? explicit_document* STREAM-END +# implicit_document ::= block_node DOCUMENT-END* +# explicit_document ::= DIRECTIVE* DOCUMENT-START block_node? DOCUMENT-END* +# block_node_or_indentless_sequence ::= +# ALIAS +# | properties (block_content | indentless_block_sequence)? +# | block_content +# | indentless_block_sequence +# block_node ::= ALIAS +# | properties block_content? +# | block_content +# flow_node ::= ALIAS +# | properties flow_content? +# | flow_content +# properties ::= TAG ANCHOR? | ANCHOR TAG? +# block_content ::= block_collection | flow_collection | SCALAR +# flow_content ::= flow_collection | SCALAR +# block_collection ::= block_sequence | block_mapping +# flow_collection ::= flow_sequence | flow_mapping +# block_sequence ::= BLOCK-SEQUENCE-START (BLOCK-ENTRY block_node?)* BLOCK-END +# indentless_sequence ::= (BLOCK-ENTRY block_node?)+ +# block_mapping ::= BLOCK-MAPPING_START +# ((KEY block_node_or_indentless_sequence?)? +# (VALUE block_node_or_indentless_sequence?)?)* +# BLOCK-END +# flow_sequence ::= FLOW-SEQUENCE-START +# (flow_sequence_entry FLOW-ENTRY)* +# flow_sequence_entry? +# FLOW-SEQUENCE-END +# flow_sequence_entry ::= flow_node | KEY flow_node? (VALUE flow_node?)? +# flow_mapping ::= FLOW-MAPPING-START +# (flow_mapping_entry FLOW-ENTRY)* +# flow_mapping_entry? +# FLOW-MAPPING-END +# flow_mapping_entry ::= flow_node | KEY flow_node? (VALUE flow_node?)? +# +# FIRST sets: +# +# stream: { STREAM-START } +# explicit_document: { DIRECTIVE DOCUMENT-START } +# implicit_document: FIRST(block_node) +# block_node: { ALIAS TAG ANCHOR SCALAR BLOCK-SEQUENCE-START BLOCK-MAPPING-START FLOW-SEQUENCE-START FLOW-MAPPING-START } +# flow_node: { ALIAS ANCHOR TAG SCALAR FLOW-SEQUENCE-START FLOW-MAPPING-START } +# block_content: { BLOCK-SEQUENCE-START BLOCK-MAPPING-START FLOW-SEQUENCE-START FLOW-MAPPING-START SCALAR } +# flow_content: { FLOW-SEQUENCE-START FLOW-MAPPING-START SCALAR } +# block_collection: { BLOCK-SEQUENCE-START BLOCK-MAPPING-START } +# flow_collection: { FLOW-SEQUENCE-START FLOW-MAPPING-START } +# block_sequence: { BLOCK-SEQUENCE-START } +# block_mapping: { BLOCK-MAPPING-START } +# block_node_or_indentless_sequence: { ALIAS ANCHOR TAG SCALAR BLOCK-SEQUENCE-START BLOCK-MAPPING-START FLOW-SEQUENCE-START FLOW-MAPPING-START BLOCK-ENTRY } +# indentless_sequence: { ENTRY } +# flow_collection: { FLOW-SEQUENCE-START FLOW-MAPPING-START } +# flow_sequence: { FLOW-SEQUENCE-START } +# flow_mapping: { FLOW-MAPPING-START } +# flow_sequence_entry: { ALIAS ANCHOR TAG SCALAR FLOW-SEQUENCE-START FLOW-MAPPING-START KEY } +# flow_mapping_entry: { ALIAS ANCHOR TAG SCALAR FLOW-SEQUENCE-START FLOW-MAPPING-START KEY } + +__all__ = ['Parser', 'ParserError'] + +from error import MarkedYAMLError +from tokens import * +from events import * +from scanner import * + +class ParserError(MarkedYAMLError): + pass + +class Parser(object): + # Since writing a recursive-descendant parser is a straightforward task, we + # do not give many comments here. + + DEFAULT_TAGS = { + u'!': u'!', + u'!!': u'tag:yaml.org,2002:', + } + + def __init__(self): + self.current_event = None + self.yaml_version = None + self.tag_handles = {} + self.states = [] + self.marks = [] + self.state = self.parse_stream_start + + def dispose(self): + # Reset the state attributes (to clear self-references) + self.states = [] + self.state = None + + def check_event(self, *choices): + # Check the type of the next event. + if self.current_event is None: + if self.state: + self.current_event = self.state() + if self.current_event is not None: + if not choices: + return True + for choice in choices: + if isinstance(self.current_event, choice): + return True + return False + + def peek_event(self): + # Get the next event. + if self.current_event is None: + if self.state: + self.current_event = self.state() + return self.current_event + + def get_event(self): + # Get the next event and proceed further. + if self.current_event is None: + if self.state: + self.current_event = self.state() + value = self.current_event + self.current_event = None + return value + + # stream ::= STREAM-START implicit_document? explicit_document* STREAM-END + # implicit_document ::= block_node DOCUMENT-END* + # explicit_document ::= DIRECTIVE* DOCUMENT-START block_node? DOCUMENT-END* + + def parse_stream_start(self): + + # Parse the stream start. + token = self.get_token() + event = StreamStartEvent(token.start_mark, token.end_mark, + encoding=token.encoding) + + # Prepare the next state. + self.state = self.parse_implicit_document_start + + return event + + def parse_implicit_document_start(self): + + # Parse an implicit document. + if not self.check_token(DirectiveToken, DocumentStartToken, + StreamEndToken): + self.tag_handles = self.DEFAULT_TAGS + token = self.peek_token() + start_mark = end_mark = token.start_mark + event = DocumentStartEvent(start_mark, end_mark, + explicit=False) + + # Prepare the next state. + self.states.append(self.parse_document_end) + self.state = self.parse_block_node + + return event + + else: + return self.parse_document_start() + + def parse_document_start(self): + + # Parse any extra document end indicators. + while self.check_token(DocumentEndToken): + self.get_token() + + # Parse an explicit document. + if not self.check_token(StreamEndToken): + token = self.peek_token() + start_mark = token.start_mark + version, tags = self.process_directives() + if not self.check_token(DocumentStartToken): + raise ParserError(None, None, + "expected '<document start>', but found %r" + % self.peek_token().id, + self.peek_token().start_mark) + token = self.get_token() + end_mark = token.end_mark + event = DocumentStartEvent(start_mark, end_mark, + explicit=True, version=version, tags=tags) + self.states.append(self.parse_document_end) + self.state = self.parse_document_content + else: + # Parse the end of the stream. + token = self.get_token() + event = StreamEndEvent(token.start_mark, token.end_mark) + assert not self.states + assert not self.marks + self.state = None + return event + + def parse_document_end(self): + + # Parse the document end. + token = self.peek_token() + start_mark = end_mark = token.start_mark + explicit = False + if self.check_token(DocumentEndToken): + token = self.get_token() + end_mark = token.end_mark + explicit = True + event = DocumentEndEvent(start_mark, end_mark, + explicit=explicit) + + # Prepare the next state. + self.state = self.parse_document_start + + return event + + def parse_document_content(self): + if self.check_token(DirectiveToken, + DocumentStartToken, DocumentEndToken, StreamEndToken): + event = self.process_empty_scalar(self.peek_token().start_mark) + self.state = self.states.pop() + return event + else: + return self.parse_block_node() + + def process_directives(self): + self.yaml_version = None + self.tag_handles = {} + while self.check_token(DirectiveToken): + token = self.get_token() + if token.name == u'YAML': + if self.yaml_version is not None: + raise ParserError(None, None, + "found duplicate YAML directive", token.start_mark) + major, minor = token.value + if major != 1: + raise ParserError(None, None, + "found incompatible YAML document (version 1.* is required)", + token.start_mark) + self.yaml_version = token.value + elif token.name == u'TAG': + handle, prefix = token.value + if handle in self.tag_handles: + raise ParserError(None, None, + "duplicate tag handle %r" % handle.encode('utf-8'), + token.start_mark) + self.tag_handles[handle] = prefix + if self.tag_handles: + value = self.yaml_version, self.tag_handles.copy() + else: + value = self.yaml_version, None + for key in self.DEFAULT_TAGS: + if key not in self.tag_handles: + self.tag_handles[key] = self.DEFAULT_TAGS[key] + return value + + # block_node_or_indentless_sequence ::= ALIAS + # | properties (block_content | indentless_block_sequence)? + # | block_content + # | indentless_block_sequence + # block_node ::= ALIAS + # | properties block_content? + # | block_content + # flow_node ::= ALIAS + # | properties flow_content? + # | flow_content + # properties ::= TAG ANCHOR? | ANCHOR TAG? + # block_content ::= block_collection | flow_collection | SCALAR + # flow_content ::= flow_collection | SCALAR + # block_collection ::= block_sequence | block_mapping + # flow_collection ::= flow_sequence | flow_mapping + + def parse_block_node(self): + return self.parse_node(block=True) + + def parse_flow_node(self): + return self.parse_node() + + def parse_block_node_or_indentless_sequence(self): + return self.parse_node(block=True, indentless_sequence=True) + + def parse_node(self, block=False, indentless_sequence=False): + if self.check_token(AliasToken): + token = self.get_token() + event = AliasEvent(token.value, token.start_mark, token.end_mark) + self.state = self.states.pop() + else: + anchor = None + tag = None + start_mark = end_mark = tag_mark = None + if self.check_token(AnchorToken): + token = self.get_token() + start_mark = token.start_mark + end_mark = token.end_mark + anchor = token.value + if self.check_token(TagToken): + token = self.get_token() + tag_mark = token.start_mark + end_mark = token.end_mark + tag = token.value + elif self.check_token(TagToken): + token = self.get_token() + start_mark = tag_mark = token.start_mark + end_mark = token.end_mark + tag = token.value + if self.check_token(AnchorToken): + token = self.get_token() + end_mark = token.end_mark + anchor = token.value + if tag is not None: + handle, suffix = tag + if handle is not None: + if handle not in self.tag_handles: + raise ParserError("while parsing a node", start_mark, + "found undefined tag handle %r" % handle.encode('utf-8'), + tag_mark) + tag = self.tag_handles[handle]+suffix + else: + tag = suffix + #if tag == u'!': + # raise ParserError("while parsing a node", start_mark, + # "found non-specific tag '!'", tag_mark, + # "Please check 'http://pyyaml.org/wiki/YAMLNonSpecificTag' and share your opinion.") + if start_mark is None: + start_mark = end_mark = self.peek_token().start_mark + event = None + implicit = (tag is None or tag == u'!') + if indentless_sequence and self.check_token(BlockEntryToken): + end_mark = self.peek_token().end_mark + event = SequenceStartEvent(anchor, tag, implicit, + start_mark, end_mark) + self.state = self.parse_indentless_sequence_entry + else: + if self.check_token(ScalarToken): + token = self.get_token() + end_mark = token.end_mark + if (token.plain and tag is None) or tag == u'!': + implicit = (True, False) + elif tag is None: + implicit = (False, True) + else: + implicit = (False, False) + event = ScalarEvent(anchor, tag, implicit, token.value, + start_mark, end_mark, style=token.style) + self.state = self.states.pop() + elif self.check_token(FlowSequenceStartToken): + end_mark = self.peek_token().end_mark + event = SequenceStartEvent(anchor, tag, implicit, + start_mark, end_mark, flow_style=True) + self.state = self.parse_flow_sequence_first_entry + elif self.check_token(FlowMappingStartToken): + end_mark = self.peek_token().end_mark + event = MappingStartEvent(anchor, tag, implicit, + start_mark, end_mark, flow_style=True) + self.state = self.parse_flow_mapping_first_key + elif block and self.check_token(BlockSequenceStartToken): + end_mark = self.peek_token().start_mark + event = SequenceStartEvent(anchor, tag, implicit, + start_mark, end_mark, flow_style=False) + self.state = self.parse_block_sequence_first_entry + elif block and self.check_token(BlockMappingStartToken): + end_mark = self.peek_token().start_mark + event = MappingStartEvent(anchor, tag, implicit, + start_mark, end_mark, flow_style=False) + self.state = self.parse_block_mapping_first_key + elif anchor is not None or tag is not None: + # Empty scalars are allowed even if a tag or an anchor is + # specified. + event = ScalarEvent(anchor, tag, (implicit, False), u'', + start_mark, end_mark) + self.state = self.states.pop() + else: + if block: + node = 'block' + else: + node = 'flow' + token = self.peek_token() + raise ParserError("while parsing a %s node" % node, start_mark, + "expected the node content, but found %r" % token.id, + token.start_mark) + return event + + # block_sequence ::= BLOCK-SEQUENCE-START (BLOCK-ENTRY block_node?)* BLOCK-END + + def parse_block_sequence_first_entry(self): + token = self.get_token() + self.marks.append(token.start_mark) + return self.parse_block_sequence_entry() + + def parse_block_sequence_entry(self): + if self.check_token(BlockEntryToken): + token = self.get_token() + if not self.check_token(BlockEntryToken, BlockEndToken): + self.states.append(self.parse_block_sequence_entry) + return self.parse_block_node() + else: + self.state = self.parse_block_sequence_entry + return self.process_empty_scalar(token.end_mark) + if not self.check_token(BlockEndToken): + token = self.peek_token() + raise ParserError("while parsing a block collection", self.marks[-1], + "expected <block end>, but found %r" % token.id, token.start_mark) + token = self.get_token() + event = SequenceEndEvent(token.start_mark, token.end_mark) + self.state = self.states.pop() + self.marks.pop() + return event + + # indentless_sequence ::= (BLOCK-ENTRY block_node?)+ + + def parse_indentless_sequence_entry(self): + if self.check_token(BlockEntryToken): + token = self.get_token() + if not self.check_token(BlockEntryToken, + KeyToken, ValueToken, BlockEndToken): + self.states.append(self.parse_indentless_sequence_entry) + return self.parse_block_node() + else: + self.state = self.parse_indentless_sequence_entry + return self.process_empty_scalar(token.end_mark) + token = self.peek_token() + event = SequenceEndEvent(token.start_mark, token.start_mark) + self.state = self.states.pop() + return event + + # block_mapping ::= BLOCK-MAPPING_START + # ((KEY block_node_or_indentless_sequence?)? + # (VALUE block_node_or_indentless_sequence?)?)* + # BLOCK-END + + def parse_block_mapping_first_key(self): + token = self.get_token() + self.marks.append(token.start_mark) + return self.parse_block_mapping_key() + + def parse_block_mapping_key(self): + if self.check_token(KeyToken): + token = self.get_token() + if not self.check_token(KeyToken, ValueToken, BlockEndToken): + self.states.append(self.parse_block_mapping_value) + return self.parse_block_node_or_indentless_sequence() + else: + self.state = self.parse_block_mapping_value + return self.process_empty_scalar(token.end_mark) + if not self.check_token(BlockEndToken): + token = self.peek_token() + raise ParserError("while parsing a block mapping", self.marks[-1], + "expected <block end>, but found %r" % token.id, token.start_mark) + token = self.get_token() + event = MappingEndEvent(token.start_mark, token.end_mark) + self.state = self.states.pop() + self.marks.pop() + return event + + def parse_block_mapping_value(self): + if self.check_token(ValueToken): + token = self.get_token() + if not self.check_token(KeyToken, ValueToken, BlockEndToken): + self.states.append(self.parse_block_mapping_key) + return self.parse_block_node_or_indentless_sequence() + else: + self.state = self.parse_block_mapping_key + return self.process_empty_scalar(token.end_mark) + else: + self.state = self.parse_block_mapping_key + token = self.peek_token() + return self.process_empty_scalar(token.start_mark) + + # flow_sequence ::= FLOW-SEQUENCE-START + # (flow_sequence_entry FLOW-ENTRY)* + # flow_sequence_entry? + # FLOW-SEQUENCE-END + # flow_sequence_entry ::= flow_node | KEY flow_node? (VALUE flow_node?)? + # + # Note that while production rules for both flow_sequence_entry and + # flow_mapping_entry are equal, their interpretations are different. + # For `flow_sequence_entry`, the part `KEY flow_node? (VALUE flow_node?)?` + # generate an inline mapping (set syntax). + + def parse_flow_sequence_first_entry(self): + token = self.get_token() + self.marks.append(token.start_mark) + return self.parse_flow_sequence_entry(first=True) + + def parse_flow_sequence_entry(self, first=False): + if not self.check_token(FlowSequenceEndToken): + if not first: + if self.check_token(FlowEntryToken): + self.get_token() + else: + token = self.peek_token() + raise ParserError("while parsing a flow sequence", self.marks[-1], + "expected ',' or ']', but got %r" % token.id, token.start_mark) + + if self.check_token(KeyToken): + token = self.peek_token() + event = MappingStartEvent(None, None, True, + token.start_mark, token.end_mark, + flow_style=True) + self.state = self.parse_flow_sequence_entry_mapping_key + return event + elif not self.check_token(FlowSequenceEndToken): + self.states.append(self.parse_flow_sequence_entry) + return self.parse_flow_node() + token = self.get_token() + event = SequenceEndEvent(token.start_mark, token.end_mark) + self.state = self.states.pop() + self.marks.pop() + return event + + def parse_flow_sequence_entry_mapping_key(self): + token = self.get_token() + if not self.check_token(ValueToken, + FlowEntryToken, FlowSequenceEndToken): + self.states.append(self.parse_flow_sequence_entry_mapping_value) + return self.parse_flow_node() + else: + self.state = self.parse_flow_sequence_entry_mapping_value + return self.process_empty_scalar(token.end_mark) + + def parse_flow_sequence_entry_mapping_value(self): + if self.check_token(ValueToken): + token = self.get_token() + if not self.check_token(FlowEntryToken, FlowSequenceEndToken): + self.states.append(self.parse_flow_sequence_entry_mapping_end) + return self.parse_flow_node() + else: + self.state = self.parse_flow_sequence_entry_mapping_end + return self.process_empty_scalar(token.end_mark) + else: + self.state = self.parse_flow_sequence_entry_mapping_end + token = self.peek_token() + return self.process_empty_scalar(token.start_mark) + + def parse_flow_sequence_entry_mapping_end(self): + self.state = self.parse_flow_sequence_entry + token = self.peek_token() + return MappingEndEvent(token.start_mark, token.start_mark) + + # flow_mapping ::= FLOW-MAPPING-START + # (flow_mapping_entry FLOW-ENTRY)* + # flow_mapping_entry? + # FLOW-MAPPING-END + # flow_mapping_entry ::= flow_node | KEY flow_node? (VALUE flow_node?)? + + def parse_flow_mapping_first_key(self): + token = self.get_token() + self.marks.append(token.start_mark) + return self.parse_flow_mapping_key(first=True) + + def parse_flow_mapping_key(self, first=False): + if not self.check_token(FlowMappingEndToken): + if not first: + if self.check_token(FlowEntryToken): + self.get_token() + else: + token = self.peek_token() + raise ParserError("while parsing a flow mapping", self.marks[-1], + "expected ',' or '}', but got %r" % token.id, token.start_mark) + if self.check_token(KeyToken): + token = self.get_token() + if not self.check_token(ValueToken, + FlowEntryToken, FlowMappingEndToken): + self.states.append(self.parse_flow_mapping_value) + return self.parse_flow_node() + else: + self.state = self.parse_flow_mapping_value + return self.process_empty_scalar(token.end_mark) + elif not self.check_token(FlowMappingEndToken): + self.states.append(self.parse_flow_mapping_empty_value) + return self.parse_flow_node() + token = self.get_token() + event = MappingEndEvent(token.start_mark, token.end_mark) + self.state = self.states.pop() + self.marks.pop() + return event + + def parse_flow_mapping_value(self): + if self.check_token(ValueToken): + token = self.get_token() + if not self.check_token(FlowEntryToken, FlowMappingEndToken): + self.states.append(self.parse_flow_mapping_key) + return self.parse_flow_node() + else: + self.state = self.parse_flow_mapping_key + return self.process_empty_scalar(token.end_mark) + else: + self.state = self.parse_flow_mapping_key + token = self.peek_token() + return self.process_empty_scalar(token.start_mark) + + def parse_flow_mapping_empty_value(self): + self.state = self.parse_flow_mapping_key + return self.process_empty_scalar(self.peek_token().start_mark) + + def process_empty_scalar(self, mark): + return ScalarEvent(None, None, (True, False), u'', mark, mark) + diff --git a/python.d/python_modules/pyyaml2/reader.py b/python.d/python_modules/pyyaml2/reader.py new file mode 100644 index 00000000..3249e6b9 --- /dev/null +++ b/python.d/python_modules/pyyaml2/reader.py @@ -0,0 +1,190 @@ +# This module contains abstractions for the input stream. You don't have to +# looks further, there are no pretty code. +# +# We define two classes here. +# +# Mark(source, line, column) +# It's just a record and its only use is producing nice error messages. +# Parser does not use it for any other purposes. +# +# Reader(source, data) +# Reader determines the encoding of `data` and converts it to unicode. +# Reader provides the following methods and attributes: +# reader.peek(length=1) - return the next `length` characters +# reader.forward(length=1) - move the current position to `length` characters. +# reader.index - the number of the current character. +# reader.line, stream.column - the line and the column of the current character. + +__all__ = ['Reader', 'ReaderError'] + +from error import YAMLError, Mark + +import codecs, re + +class ReaderError(YAMLError): + + def __init__(self, name, position, character, encoding, reason): + self.name = name + self.character = character + self.position = position + self.encoding = encoding + self.reason = reason + + def __str__(self): + if isinstance(self.character, str): + return "'%s' codec can't decode byte #x%02x: %s\n" \ + " in \"%s\", position %d" \ + % (self.encoding, ord(self.character), self.reason, + self.name, self.position) + else: + return "unacceptable character #x%04x: %s\n" \ + " in \"%s\", position %d" \ + % (self.character, self.reason, + self.name, self.position) + +class Reader(object): + # Reader: + # - determines the data encoding and converts it to unicode, + # - checks if characters are in allowed range, + # - adds '\0' to the end. + + # Reader accepts + # - a `str` object, + # - a `unicode` object, + # - a file-like object with its `read` method returning `str`, + # - a file-like object with its `read` method returning `unicode`. + + # Yeah, it's ugly and slow. + + def __init__(self, stream): + self.name = None + self.stream = None + self.stream_pointer = 0 + self.eof = True + self.buffer = u'' + self.pointer = 0 + self.raw_buffer = None + self.raw_decode = None + self.encoding = None + self.index = 0 + self.line = 0 + self.column = 0 + if isinstance(stream, unicode): + self.name = "<unicode string>" + self.check_printable(stream) + self.buffer = stream+u'\0' + elif isinstance(stream, str): + self.name = "<string>" + self.raw_buffer = stream + self.determine_encoding() + else: + self.stream = stream + self.name = getattr(stream, 'name', "<file>") + self.eof = False + self.raw_buffer = '' + self.determine_encoding() + + def peek(self, index=0): + try: + return self.buffer[self.pointer+index] + except IndexError: + self.update(index+1) + return self.buffer[self.pointer+index] + + def prefix(self, length=1): + if self.pointer+length >= len(self.buffer): + self.update(length) + return self.buffer[self.pointer:self.pointer+length] + + def forward(self, length=1): + if self.pointer+length+1 >= len(self.buffer): + self.update(length+1) + while length: + ch = self.buffer[self.pointer] + self.pointer += 1 + self.index += 1 + if ch in u'\n\x85\u2028\u2029' \ + or (ch == u'\r' and self.buffer[self.pointer] != u'\n'): + self.line += 1 + self.column = 0 + elif ch != u'\uFEFF': + self.column += 1 + length -= 1 + + def get_mark(self): + if self.stream is None: + return Mark(self.name, self.index, self.line, self.column, + self.buffer, self.pointer) + else: + return Mark(self.name, self.index, self.line, self.column, + None, None) + + def determine_encoding(self): + while not self.eof and len(self.raw_buffer) < 2: + self.update_raw() + if not isinstance(self.raw_buffer, unicode): + if self.raw_buffer.startswith(codecs.BOM_UTF16_LE): + self.raw_decode = codecs.utf_16_le_decode + self.encoding = 'utf-16-le' + elif self.raw_buffer.startswith(codecs.BOM_UTF16_BE): + self.raw_decode = codecs.utf_16_be_decode + self.encoding = 'utf-16-be' + else: + self.raw_decode = codecs.utf_8_decode + self.encoding = 'utf-8' + self.update(1) + + NON_PRINTABLE = re.compile(u'[^\x09\x0A\x0D\x20-\x7E\x85\xA0-\uD7FF\uE000-\uFFFD]') + def check_printable(self, data): + match = self.NON_PRINTABLE.search(data) + if match: + character = match.group() + position = self.index+(len(self.buffer)-self.pointer)+match.start() + raise ReaderError(self.name, position, ord(character), + 'unicode', "special characters are not allowed") + + def update(self, length): + if self.raw_buffer is None: + return + self.buffer = self.buffer[self.pointer:] + self.pointer = 0 + while len(self.buffer) < length: + if not self.eof: + self.update_raw() + if self.raw_decode is not None: + try: + data, converted = self.raw_decode(self.raw_buffer, + 'strict', self.eof) + except UnicodeDecodeError, exc: + character = exc.object[exc.start] + if self.stream is not None: + position = self.stream_pointer-len(self.raw_buffer)+exc.start + else: + position = exc.start + raise ReaderError(self.name, position, character, + exc.encoding, exc.reason) + else: + data = self.raw_buffer + converted = len(data) + self.check_printable(data) + self.buffer += data + self.raw_buffer = self.raw_buffer[converted:] + if self.eof: + self.buffer += u'\0' + self.raw_buffer = None + break + + def update_raw(self, size=1024): + data = self.stream.read(size) + if data: + self.raw_buffer += data + self.stream_pointer += len(data) + else: + self.eof = True + +#try: +# import psyco +# psyco.bind(Reader) +#except ImportError: +# pass + diff --git a/python.d/python_modules/pyyaml2/representer.py b/python.d/python_modules/pyyaml2/representer.py new file mode 100644 index 00000000..5f4fc70d --- /dev/null +++ b/python.d/python_modules/pyyaml2/representer.py @@ -0,0 +1,484 @@ + +__all__ = ['BaseRepresenter', 'SafeRepresenter', 'Representer', + 'RepresenterError'] + +from error import * +from nodes import * + +import datetime + +import sys, copy_reg, types + +class RepresenterError(YAMLError): + pass + +class BaseRepresenter(object): + + yaml_representers = {} + yaml_multi_representers = {} + + def __init__(self, default_style=None, default_flow_style=None): + self.default_style = default_style + self.default_flow_style = default_flow_style + self.represented_objects = {} + self.object_keeper = [] + self.alias_key = None + + def represent(self, data): + node = self.represent_data(data) + self.serialize(node) + self.represented_objects = {} + self.object_keeper = [] + self.alias_key = None + + def get_classobj_bases(self, cls): + bases = [cls] + for base in cls.__bases__: + bases.extend(self.get_classobj_bases(base)) + return bases + + def represent_data(self, data): + if self.ignore_aliases(data): + self.alias_key = None + else: + self.alias_key = id(data) + if self.alias_key is not None: + if self.alias_key in self.represented_objects: + node = self.represented_objects[self.alias_key] + #if node is None: + # raise RepresenterError("recursive objects are not allowed: %r" % data) + return node + #self.represented_objects[alias_key] = None + self.object_keeper.append(data) + data_types = type(data).__mro__ + if type(data) is types.InstanceType: + data_types = self.get_classobj_bases(data.__class__)+list(data_types) + if data_types[0] in self.yaml_representers: + node = self.yaml_representers[data_types[0]](self, data) + else: + for data_type in data_types: + if data_type in self.yaml_multi_representers: + node = self.yaml_multi_representers[data_type](self, data) + break + else: + if None in self.yaml_multi_representers: + node = self.yaml_multi_representers[None](self, data) + elif None in self.yaml_representers: + node = self.yaml_representers[None](self, data) + else: + node = ScalarNode(None, unicode(data)) + #if alias_key is not None: + # self.represented_objects[alias_key] = node + return node + + def add_representer(cls, data_type, representer): + if not 'yaml_representers' in cls.__dict__: + cls.yaml_representers = cls.yaml_representers.copy() + cls.yaml_representers[data_type] = representer + add_representer = classmethod(add_representer) + + def add_multi_representer(cls, data_type, representer): + if not 'yaml_multi_representers' in cls.__dict__: + cls.yaml_multi_representers = cls.yaml_multi_representers.copy() + cls.yaml_multi_representers[data_type] = representer + add_multi_representer = classmethod(add_multi_representer) + + def represent_scalar(self, tag, value, style=None): + if style is None: + style = self.default_style + node = ScalarNode(tag, value, style=style) + if self.alias_key is not None: + self.represented_objects[self.alias_key] = node + return node + + def represent_sequence(self, tag, sequence, flow_style=None): + value = [] + node = SequenceNode(tag, value, flow_style=flow_style) + if self.alias_key is not None: + self.represented_objects[self.alias_key] = node + best_style = True + for item in sequence: + node_item = self.represent_data(item) + if not (isinstance(node_item, ScalarNode) and not node_item.style): + best_style = False + value.append(node_item) + if flow_style is None: + if self.default_flow_style is not None: + node.flow_style = self.default_flow_style + else: + node.flow_style = best_style + return node + + def represent_mapping(self, tag, mapping, flow_style=None): + value = [] + node = MappingNode(tag, value, flow_style=flow_style) + if self.alias_key is not None: + self.represented_objects[self.alias_key] = node + best_style = True + if hasattr(mapping, 'items'): + mapping = mapping.items() + mapping.sort() + for item_key, item_value in mapping: + node_key = self.represent_data(item_key) + node_value = self.represent_data(item_value) + if not (isinstance(node_key, ScalarNode) and not node_key.style): + best_style = False + if not (isinstance(node_value, ScalarNode) and not node_value.style): + best_style = False + value.append((node_key, node_value)) + if flow_style is None: + if self.default_flow_style is not None: + node.flow_style = self.default_flow_style + else: + node.flow_style = best_style + return node + + def ignore_aliases(self, data): + return False + +class SafeRepresenter(BaseRepresenter): + + def ignore_aliases(self, data): + if data in [None, ()]: + return True + if isinstance(data, (str, unicode, bool, int, float)): + return True + + def represent_none(self, data): + return self.represent_scalar(u'tag:yaml.org,2002:null', + u'null') + + def represent_str(self, data): + tag = None + style = None + try: + data = unicode(data, 'ascii') + tag = u'tag:yaml.org,2002:str' + except UnicodeDecodeError: + try: + data = unicode(data, 'utf-8') + tag = u'tag:yaml.org,2002:str' + except UnicodeDecodeError: + data = data.encode('base64') + tag = u'tag:yaml.org,2002:binary' + style = '|' + return self.represent_scalar(tag, data, style=style) + + def represent_unicode(self, data): + return self.represent_scalar(u'tag:yaml.org,2002:str', data) + + def represent_bool(self, data): + if data: + value = u'true' + else: + value = u'false' + return self.represent_scalar(u'tag:yaml.org,2002:bool', value) + + def represent_int(self, data): + return self.represent_scalar(u'tag:yaml.org,2002:int', unicode(data)) + + def represent_long(self, data): + return self.represent_scalar(u'tag:yaml.org,2002:int', unicode(data)) + + inf_value = 1e300 + while repr(inf_value) != repr(inf_value*inf_value): + inf_value *= inf_value + + def represent_float(self, data): + if data != data or (data == 0.0 and data == 1.0): + value = u'.nan' + elif data == self.inf_value: + value = u'.inf' + elif data == -self.inf_value: + value = u'-.inf' + else: + value = unicode(repr(data)).lower() + # Note that in some cases `repr(data)` represents a float number + # without the decimal parts. For instance: + # >>> repr(1e17) + # '1e17' + # Unfortunately, this is not a valid float representation according + # to the definition of the `!!float` tag. We fix this by adding + # '.0' before the 'e' symbol. + if u'.' not in value and u'e' in value: + value = value.replace(u'e', u'.0e', 1) + return self.represent_scalar(u'tag:yaml.org,2002:float', value) + + def represent_list(self, data): + #pairs = (len(data) > 0 and isinstance(data, list)) + #if pairs: + # for item in data: + # if not isinstance(item, tuple) or len(item) != 2: + # pairs = False + # break + #if not pairs: + return self.represent_sequence(u'tag:yaml.org,2002:seq', data) + #value = [] + #for item_key, item_value in data: + # value.append(self.represent_mapping(u'tag:yaml.org,2002:map', + # [(item_key, item_value)])) + #return SequenceNode(u'tag:yaml.org,2002:pairs', value) + + def represent_dict(self, data): + return self.represent_mapping(u'tag:yaml.org,2002:map', data) + + def represent_set(self, data): + value = {} + for key in data: + value[key] = None + return self.represent_mapping(u'tag:yaml.org,2002:set', value) + + def represent_date(self, data): + value = unicode(data.isoformat()) + return self.represent_scalar(u'tag:yaml.org,2002:timestamp', value) + + def represent_datetime(self, data): + value = unicode(data.isoformat(' ')) + return self.represent_scalar(u'tag:yaml.org,2002:timestamp', value) + + def represent_yaml_object(self, tag, data, cls, flow_style=None): + if hasattr(data, '__getstate__'): + state = data.__getstate__() + else: + state = data.__dict__.copy() + return self.represent_mapping(tag, state, flow_style=flow_style) + + def represent_undefined(self, data): + raise RepresenterError("cannot represent an object: %s" % data) + +SafeRepresenter.add_representer(type(None), + SafeRepresenter.represent_none) + +SafeRepresenter.add_representer(str, + SafeRepresenter.represent_str) + +SafeRepresenter.add_representer(unicode, + SafeRepresenter.represent_unicode) + +SafeRepresenter.add_representer(bool, + SafeRepresenter.represent_bool) + +SafeRepresenter.add_representer(int, + SafeRepresenter.represent_int) + +SafeRepresenter.add_representer(long, + SafeRepresenter.represent_long) + +SafeRepresenter.add_representer(float, + SafeRepresenter.represent_float) + +SafeRepresenter.add_representer(list, + SafeRepresenter.represent_list) + +SafeRepresenter.add_representer(tuple, + SafeRepresenter.represent_list) + +SafeRepresenter.add_representer(dict, + SafeRepresenter.represent_dict) + +SafeRepresenter.add_representer(set, + SafeRepresenter.represent_set) + +SafeRepresenter.add_representer(datetime.date, + SafeRepresenter.represent_date) + +SafeRepresenter.add_representer(datetime.datetime, + SafeRepresenter.represent_datetime) + +SafeRepresenter.add_representer(None, + SafeRepresenter.represent_undefined) + +class Representer(SafeRepresenter): + + def represent_str(self, data): + tag = None + style = None + try: + data = unicode(data, 'ascii') + tag = u'tag:yaml.org,2002:str' + except UnicodeDecodeError: + try: + data = unicode(data, 'utf-8') + tag = u'tag:yaml.org,2002:python/str' + except UnicodeDecodeError: + data = data.encode('base64') + tag = u'tag:yaml.org,2002:binary' + style = '|' + return self.represent_scalar(tag, data, style=style) + + def represent_unicode(self, data): + tag = None + try: + data.encode('ascii') + tag = u'tag:yaml.org,2002:python/unicode' + except UnicodeEncodeError: + tag = u'tag:yaml.org,2002:str' + return self.represent_scalar(tag, data) + + def represent_long(self, data): + tag = u'tag:yaml.org,2002:int' + if int(data) is not data: + tag = u'tag:yaml.org,2002:python/long' + return self.represent_scalar(tag, unicode(data)) + + def represent_complex(self, data): + if data.imag == 0.0: + data = u'%r' % data.real + elif data.real == 0.0: + data = u'%rj' % data.imag + elif data.imag > 0: + data = u'%r+%rj' % (data.real, data.imag) + else: + data = u'%r%rj' % (data.real, data.imag) + return self.represent_scalar(u'tag:yaml.org,2002:python/complex', data) + + def represent_tuple(self, data): + return self.represent_sequence(u'tag:yaml.org,2002:python/tuple', data) + + def represent_name(self, data): + name = u'%s.%s' % (data.__module__, data.__name__) + return self.represent_scalar(u'tag:yaml.org,2002:python/name:'+name, u'') + + def represent_module(self, data): + return self.represent_scalar( + u'tag:yaml.org,2002:python/module:'+data.__name__, u'') + + def represent_instance(self, data): + # For instances of classic classes, we use __getinitargs__ and + # __getstate__ to serialize the data. + + # If data.__getinitargs__ exists, the object must be reconstructed by + # calling cls(**args), where args is a tuple returned by + # __getinitargs__. Otherwise, the cls.__init__ method should never be + # called and the class instance is created by instantiating a trivial + # class and assigning to the instance's __class__ variable. + + # If data.__getstate__ exists, it returns the state of the object. + # Otherwise, the state of the object is data.__dict__. + + # We produce either a !!python/object or !!python/object/new node. + # If data.__getinitargs__ does not exist and state is a dictionary, we + # produce a !!python/object node . Otherwise we produce a + # !!python/object/new node. + + cls = data.__class__ + class_name = u'%s.%s' % (cls.__module__, cls.__name__) + args = None + state = None + if hasattr(data, '__getinitargs__'): + args = list(data.__getinitargs__()) + if hasattr(data, '__getstate__'): + state = data.__getstate__() + else: + state = data.__dict__ + if args is None and isinstance(state, dict): + return self.represent_mapping( + u'tag:yaml.org,2002:python/object:'+class_name, state) + if isinstance(state, dict) and not state: + return self.represent_sequence( + u'tag:yaml.org,2002:python/object/new:'+class_name, args) + value = {} + if args: + value['args'] = args + value['state'] = state + return self.represent_mapping( + u'tag:yaml.org,2002:python/object/new:'+class_name, value) + + def represent_object(self, data): + # We use __reduce__ API to save the data. data.__reduce__ returns + # a tuple of length 2-5: + # (function, args, state, listitems, dictitems) + + # For reconstructing, we calls function(*args), then set its state, + # listitems, and dictitems if they are not None. + + # A special case is when function.__name__ == '__newobj__'. In this + # case we create the object with args[0].__new__(*args). + + # Another special case is when __reduce__ returns a string - we don't + # support it. + + # We produce a !!python/object, !!python/object/new or + # !!python/object/apply node. + + cls = type(data) + if cls in copy_reg.dispatch_table: + reduce = copy_reg.dispatch_table[cls](data) + elif hasattr(data, '__reduce_ex__'): + reduce = data.__reduce_ex__(2) + elif hasattr(data, '__reduce__'): + reduce = data.__reduce__() + else: + raise RepresenterError("cannot represent object: %r" % data) + reduce = (list(reduce)+[None]*5)[:5] + function, args, state, listitems, dictitems = reduce + args = list(args) + if state is None: + state = {} + if listitems is not None: + listitems = list(listitems) + if dictitems is not None: + dictitems = dict(dictitems) + if function.__name__ == '__newobj__': + function = args[0] + args = args[1:] + tag = u'tag:yaml.org,2002:python/object/new:' + newobj = True + else: + tag = u'tag:yaml.org,2002:python/object/apply:' + newobj = False + function_name = u'%s.%s' % (function.__module__, function.__name__) + if not args and not listitems and not dictitems \ + and isinstance(state, dict) and newobj: + return self.represent_mapping( + u'tag:yaml.org,2002:python/object:'+function_name, state) + if not listitems and not dictitems \ + and isinstance(state, dict) and not state: + return self.represent_sequence(tag+function_name, args) + value = {} + if args: + value['args'] = args + if state or not isinstance(state, dict): + value['state'] = state + if listitems: + value['listitems'] = listitems + if dictitems: + value['dictitems'] = dictitems + return self.represent_mapping(tag+function_name, value) + +Representer.add_representer(str, + Representer.represent_str) + +Representer.add_representer(unicode, + Representer.represent_unicode) + +Representer.add_representer(long, + Representer.represent_long) + +Representer.add_representer(complex, + Representer.represent_complex) + +Representer.add_representer(tuple, + Representer.represent_tuple) + +Representer.add_representer(type, + Representer.represent_name) + +Representer.add_representer(types.ClassType, + Representer.represent_name) + +Representer.add_representer(types.FunctionType, + Representer.represent_name) + +Representer.add_representer(types.BuiltinFunctionType, + Representer.represent_name) + +Representer.add_representer(types.ModuleType, + Representer.represent_module) + +Representer.add_multi_representer(types.InstanceType, + Representer.represent_instance) + +Representer.add_multi_representer(object, + Representer.represent_object) + diff --git a/python.d/python_modules/pyyaml2/resolver.py b/python.d/python_modules/pyyaml2/resolver.py new file mode 100644 index 00000000..6b5ab875 --- /dev/null +++ b/python.d/python_modules/pyyaml2/resolver.py @@ -0,0 +1,224 @@ + +__all__ = ['BaseResolver', 'Resolver'] + +from error import * +from nodes import * + +import re + +class ResolverError(YAMLError): + pass + +class BaseResolver(object): + + DEFAULT_SCALAR_TAG = u'tag:yaml.org,2002:str' + DEFAULT_SEQUENCE_TAG = u'tag:yaml.org,2002:seq' + DEFAULT_MAPPING_TAG = u'tag:yaml.org,2002:map' + + yaml_implicit_resolvers = {} + yaml_path_resolvers = {} + + def __init__(self): + self.resolver_exact_paths = [] + self.resolver_prefix_paths = [] + + def add_implicit_resolver(cls, tag, regexp, first): + if not 'yaml_implicit_resolvers' in cls.__dict__: + cls.yaml_implicit_resolvers = cls.yaml_implicit_resolvers.copy() + if first is None: + first = [None] + for ch in first: + cls.yaml_implicit_resolvers.setdefault(ch, []).append((tag, regexp)) + add_implicit_resolver = classmethod(add_implicit_resolver) + + def add_path_resolver(cls, tag, path, kind=None): + # Note: `add_path_resolver` is experimental. The API could be changed. + # `new_path` is a pattern that is matched against the path from the + # root to the node that is being considered. `node_path` elements are + # tuples `(node_check, index_check)`. `node_check` is a node class: + # `ScalarNode`, `SequenceNode`, `MappingNode` or `None`. `None` + # matches any kind of a node. `index_check` could be `None`, a boolean + # value, a string value, or a number. `None` and `False` match against + # any _value_ of sequence and mapping nodes. `True` matches against + # any _key_ of a mapping node. A string `index_check` matches against + # a mapping value that corresponds to a scalar key which content is + # equal to the `index_check` value. An integer `index_check` matches + # against a sequence value with the index equal to `index_check`. + if not 'yaml_path_resolvers' in cls.__dict__: + cls.yaml_path_resolvers = cls.yaml_path_resolvers.copy() + new_path = [] + for element in path: + if isinstance(element, (list, tuple)): + if len(element) == 2: + node_check, index_check = element + elif len(element) == 1: + node_check = element[0] + index_check = True + else: + raise ResolverError("Invalid path element: %s" % element) + else: + node_check = None + index_check = element + if node_check is str: + node_check = ScalarNode + elif node_check is list: + node_check = SequenceNode + elif node_check is dict: + node_check = MappingNode + elif node_check not in [ScalarNode, SequenceNode, MappingNode] \ + and not isinstance(node_check, basestring) \ + and node_check is not None: + raise ResolverError("Invalid node checker: %s" % node_check) + if not isinstance(index_check, (basestring, int)) \ + and index_check is not None: + raise ResolverError("Invalid index checker: %s" % index_check) + new_path.append((node_check, index_check)) + if kind is str: + kind = ScalarNode + elif kind is list: + kind = SequenceNode + elif kind is dict: + kind = MappingNode + elif kind not in [ScalarNode, SequenceNode, MappingNode] \ + and kind is not None: + raise ResolverError("Invalid node kind: %s" % kind) + cls.yaml_path_resolvers[tuple(new_path), kind] = tag + add_path_resolver = classmethod(add_path_resolver) + + def descend_resolver(self, current_node, current_index): + if not self.yaml_path_resolvers: + return + exact_paths = {} + prefix_paths = [] + if current_node: + depth = len(self.resolver_prefix_paths) + for path, kind in self.resolver_prefix_paths[-1]: + if self.check_resolver_prefix(depth, path, kind, + current_node, current_index): + if len(path) > depth: + prefix_paths.append((path, kind)) + else: + exact_paths[kind] = self.yaml_path_resolvers[path, kind] + else: + for path, kind in self.yaml_path_resolvers: + if not path: + exact_paths[kind] = self.yaml_path_resolvers[path, kind] + else: + prefix_paths.append((path, kind)) + self.resolver_exact_paths.append(exact_paths) + self.resolver_prefix_paths.append(prefix_paths) + + def ascend_resolver(self): + if not self.yaml_path_resolvers: + return + self.resolver_exact_paths.pop() + self.resolver_prefix_paths.pop() + + def check_resolver_prefix(self, depth, path, kind, + current_node, current_index): + node_check, index_check = path[depth-1] + if isinstance(node_check, basestring): + if current_node.tag != node_check: + return + elif node_check is not None: + if not isinstance(current_node, node_check): + return + if index_check is True and current_index is not None: + return + if (index_check is False or index_check is None) \ + and current_index is None: + return + if isinstance(index_check, basestring): + if not (isinstance(current_index, ScalarNode) + and index_check == current_index.value): + return + elif isinstance(index_check, int) and not isinstance(index_check, bool): + if index_check != current_index: + return + return True + + def resolve(self, kind, value, implicit): + if kind is ScalarNode and implicit[0]: + if value == u'': + resolvers = self.yaml_implicit_resolvers.get(u'', []) + else: + resolvers = self.yaml_implicit_resolvers.get(value[0], []) + resolvers += self.yaml_implicit_resolvers.get(None, []) + for tag, regexp in resolvers: + if regexp.match(value): + return tag + implicit = implicit[1] + if self.yaml_path_resolvers: + exact_paths = self.resolver_exact_paths[-1] + if kind in exact_paths: + return exact_paths[kind] + if None in exact_paths: + return exact_paths[None] + if kind is ScalarNode: + return self.DEFAULT_SCALAR_TAG + elif kind is SequenceNode: + return self.DEFAULT_SEQUENCE_TAG + elif kind is MappingNode: + return self.DEFAULT_MAPPING_TAG + +class Resolver(BaseResolver): + pass + +Resolver.add_implicit_resolver( + u'tag:yaml.org,2002:bool', + re.compile(ur'''^(?:yes|Yes|YES|no|No|NO + |true|True|TRUE|false|False|FALSE + |on|On|ON|off|Off|OFF)$''', re.X), + list(u'yYnNtTfFoO')) + +Resolver.add_implicit_resolver( + u'tag:yaml.org,2002:float', + re.compile(ur'''^(?:[-+]?(?:[0-9][0-9_]*)\.[0-9_]*(?:[eE][-+][0-9]+)? + |\.[0-9_]+(?:[eE][-+][0-9]+)? + |[-+]?[0-9][0-9_]*(?::[0-5]?[0-9])+\.[0-9_]* + |[-+]?\.(?:inf|Inf|INF) + |\.(?:nan|NaN|NAN))$''', re.X), + list(u'-+0123456789.')) + +Resolver.add_implicit_resolver( + u'tag:yaml.org,2002:int', + re.compile(ur'''^(?:[-+]?0b[0-1_]+ + |[-+]?0[0-7_]+ + |[-+]?(?:0|[1-9][0-9_]*) + |[-+]?0x[0-9a-fA-F_]+ + |[-+]?[1-9][0-9_]*(?::[0-5]?[0-9])+)$''', re.X), + list(u'-+0123456789')) + +Resolver.add_implicit_resolver( + u'tag:yaml.org,2002:merge', + re.compile(ur'^(?:<<)$'), + [u'<']) + +Resolver.add_implicit_resolver( + u'tag:yaml.org,2002:null', + re.compile(ur'''^(?: ~ + |null|Null|NULL + | )$''', re.X), + [u'~', u'n', u'N', u'']) + +Resolver.add_implicit_resolver( + u'tag:yaml.org,2002:timestamp', + re.compile(ur'''^(?:[0-9][0-9][0-9][0-9]-[0-9][0-9]-[0-9][0-9] + |[0-9][0-9][0-9][0-9] -[0-9][0-9]? -[0-9][0-9]? + (?:[Tt]|[ \t]+)[0-9][0-9]? + :[0-9][0-9] :[0-9][0-9] (?:\.[0-9]*)? + (?:[ \t]*(?:Z|[-+][0-9][0-9]?(?::[0-9][0-9])?))?)$''', re.X), + list(u'0123456789')) + +Resolver.add_implicit_resolver( + u'tag:yaml.org,2002:value', + re.compile(ur'^(?:=)$'), + [u'=']) + +# The following resolver is only for documentation purposes. It cannot work +# because plain scalars cannot start with '!', '&', or '*'. +Resolver.add_implicit_resolver( + u'tag:yaml.org,2002:yaml', + re.compile(ur'^(?:!|&|\*)$'), + list(u'!&*')) + diff --git a/python.d/python_modules/pyyaml2/scanner.py b/python.d/python_modules/pyyaml2/scanner.py new file mode 100644 index 00000000..5228fad6 --- /dev/null +++ b/python.d/python_modules/pyyaml2/scanner.py @@ -0,0 +1,1457 @@ + +# Scanner produces tokens of the following types: +# STREAM-START +# STREAM-END +# DIRECTIVE(name, value) +# DOCUMENT-START +# DOCUMENT-END +# BLOCK-SEQUENCE-START +# BLOCK-MAPPING-START +# BLOCK-END +# FLOW-SEQUENCE-START +# FLOW-MAPPING-START +# FLOW-SEQUENCE-END +# FLOW-MAPPING-END +# BLOCK-ENTRY +# FLOW-ENTRY +# KEY +# VALUE +# ALIAS(value) +# ANCHOR(value) +# TAG(value) +# SCALAR(value, plain, style) +# +# Read comments in the Scanner code for more details. +# + +__all__ = ['Scanner', 'ScannerError'] + +from error import MarkedYAMLError +from tokens import * + +class ScannerError(MarkedYAMLError): + pass + +class SimpleKey(object): + # See below simple keys treatment. + + def __init__(self, token_number, required, index, line, column, mark): + self.token_number = token_number + self.required = required + self.index = index + self.line = line + self.column = column + self.mark = mark + +class Scanner(object): + + def __init__(self): + """Initialize the scanner.""" + # It is assumed that Scanner and Reader will have a common descendant. + # Reader do the dirty work of checking for BOM and converting the + # input data to Unicode. It also adds NUL to the end. + # + # Reader supports the following methods + # self.peek(i=0) # peek the next i-th character + # self.prefix(l=1) # peek the next l characters + # self.forward(l=1) # read the next l characters and move the pointer. + + # Had we reached the end of the stream? + self.done = False + + # The number of unclosed '{' and '['. `flow_level == 0` means block + # context. + self.flow_level = 0 + + # List of processed tokens that are not yet emitted. + self.tokens = [] + + # Add the STREAM-START token. + self.fetch_stream_start() + + # Number of tokens that were emitted through the `get_token` method. + self.tokens_taken = 0 + + # The current indentation level. + self.indent = -1 + + # Past indentation levels. + self.indents = [] + + # Variables related to simple keys treatment. + + # A simple key is a key that is not denoted by the '?' indicator. + # Example of simple keys: + # --- + # block simple key: value + # ? not a simple key: + # : { flow simple key: value } + # We emit the KEY token before all keys, so when we find a potential + # simple key, we try to locate the corresponding ':' indicator. + # Simple keys should be limited to a single line and 1024 characters. + + # Can a simple key start at the current position? A simple key may + # start: + # - at the beginning of the line, not counting indentation spaces + # (in block context), + # - after '{', '[', ',' (in the flow context), + # - after '?', ':', '-' (in the block context). + # In the block context, this flag also signifies if a block collection + # may start at the current position. + self.allow_simple_key = True + + # Keep track of possible simple keys. This is a dictionary. The key + # is `flow_level`; there can be no more that one possible simple key + # for each level. The value is a SimpleKey record: + # (token_number, required, index, line, column, mark) + # A simple key may start with ALIAS, ANCHOR, TAG, SCALAR(flow), + # '[', or '{' tokens. + self.possible_simple_keys = {} + + # Public methods. + + def check_token(self, *choices): + # Check if the next token is one of the given types. + while self.need_more_tokens(): + self.fetch_more_tokens() + if self.tokens: + if not choices: + return True + for choice in choices: + if isinstance(self.tokens[0], choice): + return True + return False + + def peek_token(self): + # Return the next token, but do not delete if from the queue. + while self.need_more_tokens(): + self.fetch_more_tokens() + if self.tokens: + return self.tokens[0] + + def get_token(self): + # Return the next token. + while self.need_more_tokens(): + self.fetch_more_tokens() + if self.tokens: + self.tokens_taken += 1 + return self.tokens.pop(0) + + # Private methods. + + def need_more_tokens(self): + if self.done: + return False + if not self.tokens: + return True + # The current token may be a potential simple key, so we + # need to look further. + self.stale_possible_simple_keys() + if self.next_possible_simple_key() == self.tokens_taken: + return True + + def fetch_more_tokens(self): + + # Eat whitespaces and comments until we reach the next token. + self.scan_to_next_token() + + # Remove obsolete possible simple keys. + self.stale_possible_simple_keys() + + # Compare the current indentation and column. It may add some tokens + # and decrease the current indentation level. + self.unwind_indent(self.column) + + # Peek the next character. + ch = self.peek() + + # Is it the end of stream? + if ch == u'\0': + return self.fetch_stream_end() + + # Is it a directive? + if ch == u'%' and self.check_directive(): + return self.fetch_directive() + + # Is it the document start? + if ch == u'-' and self.check_document_start(): + return self.fetch_document_start() + + # Is it the document end? + if ch == u'.' and self.check_document_end(): + return self.fetch_document_end() + + # TODO: support for BOM within a stream. + #if ch == u'\uFEFF': + # return self.fetch_bom() <-- issue BOMToken + + # Note: the order of the following checks is NOT significant. + + # Is it the flow sequence start indicator? + if ch == u'[': + return self.fetch_flow_sequence_start() + + # Is it the flow mapping start indicator? + if ch == u'{': + return self.fetch_flow_mapping_start() + + # Is it the flow sequence end indicator? + if ch == u']': + return self.fetch_flow_sequence_end() + + # Is it the flow mapping end indicator? + if ch == u'}': + return self.fetch_flow_mapping_end() + + # Is it the flow entry indicator? + if ch == u',': + return self.fetch_flow_entry() + + # Is it the block entry indicator? + if ch == u'-' and self.check_block_entry(): + return self.fetch_block_entry() + + # Is it the key indicator? + if ch == u'?' and self.check_key(): + return self.fetch_key() + + # Is it the value indicator? + if ch == u':' and self.check_value(): + return self.fetch_value() + + # Is it an alias? + if ch == u'*': + return self.fetch_alias() + + # Is it an anchor? + if ch == u'&': + return self.fetch_anchor() + + # Is it a tag? + if ch == u'!': + return self.fetch_tag() + + # Is it a literal scalar? + if ch == u'|' and not self.flow_level: + return self.fetch_literal() + + # Is it a folded scalar? + if ch == u'>' and not self.flow_level: + return self.fetch_folded() + + # Is it a single quoted scalar? + if ch == u'\'': + return self.fetch_single() + + # Is it a double quoted scalar? + if ch == u'\"': + return self.fetch_double() + + # It must be a plain scalar then. + if self.check_plain(): + return self.fetch_plain() + + # No? It's an error. Let's produce a nice error message. + raise ScannerError("while scanning for the next token", None, + "found character %r that cannot start any token" + % ch.encode('utf-8'), self.get_mark()) + + # Simple keys treatment. + + def next_possible_simple_key(self): + # Return the number of the nearest possible simple key. Actually we + # don't need to loop through the whole dictionary. We may replace it + # with the following code: + # if not self.possible_simple_keys: + # return None + # return self.possible_simple_keys[ + # min(self.possible_simple_keys.keys())].token_number + min_token_number = None + for level in self.possible_simple_keys: + key = self.possible_simple_keys[level] + if min_token_number is None or key.token_number < min_token_number: + min_token_number = key.token_number + return min_token_number + + def stale_possible_simple_keys(self): + # Remove entries that are no longer possible simple keys. According to + # the YAML specification, simple keys + # - should be limited to a single line, + # - should be no longer than 1024 characters. + # Disabling this procedure will allow simple keys of any length and + # height (may cause problems if indentation is broken though). + for level in self.possible_simple_keys.keys(): + key = self.possible_simple_keys[level] + if key.line != self.line \ + or self.index-key.index > 1024: + if key.required: + raise ScannerError("while scanning a simple key", key.mark, + "could not found expected ':'", self.get_mark()) + del self.possible_simple_keys[level] + + def save_possible_simple_key(self): + # The next token may start a simple key. We check if it's possible + # and save its position. This function is called for + # ALIAS, ANCHOR, TAG, SCALAR(flow), '[', and '{'. + + # Check if a simple key is required at the current position. + required = not self.flow_level and self.indent == self.column + + # A simple key is required only if it is the first token in the current + # line. Therefore it is always allowed. + assert self.allow_simple_key or not required + + # The next token might be a simple key. Let's save it's number and + # position. + if self.allow_simple_key: + self.remove_possible_simple_key() + token_number = self.tokens_taken+len(self.tokens) + key = SimpleKey(token_number, required, + self.index, self.line, self.column, self.get_mark()) + self.possible_simple_keys[self.flow_level] = key + + def remove_possible_simple_key(self): + # Remove the saved possible key position at the current flow level. + if self.flow_level in self.possible_simple_keys: + key = self.possible_simple_keys[self.flow_level] + + if key.required: + raise ScannerError("while scanning a simple key", key.mark, + "could not found expected ':'", self.get_mark()) + + del self.possible_simple_keys[self.flow_level] + + # Indentation functions. + + def unwind_indent(self, column): + + ## In flow context, tokens should respect indentation. + ## Actually the condition should be `self.indent >= column` according to + ## the spec. But this condition will prohibit intuitively correct + ## constructions such as + ## key : { + ## } + #if self.flow_level and self.indent > column: + # raise ScannerError(None, None, + # "invalid intendation or unclosed '[' or '{'", + # self.get_mark()) + + # In the flow context, indentation is ignored. We make the scanner less + # restrictive then specification requires. + if self.flow_level: + return + + # In block context, we may need to issue the BLOCK-END tokens. + while self.indent > column: + mark = self.get_mark() + self.indent = self.indents.pop() + self.tokens.append(BlockEndToken(mark, mark)) + + def add_indent(self, column): + # Check if we need to increase indentation. + if self.indent < column: + self.indents.append(self.indent) + self.indent = column + return True + return False + + # Fetchers. + + def fetch_stream_start(self): + # We always add STREAM-START as the first token and STREAM-END as the + # last token. + + # Read the token. + mark = self.get_mark() + + # Add STREAM-START. + self.tokens.append(StreamStartToken(mark, mark, + encoding=self.encoding)) + + + def fetch_stream_end(self): + + # Set the current intendation to -1. + self.unwind_indent(-1) + + # Reset simple keys. + self.remove_possible_simple_key() + self.allow_simple_key = False + self.possible_simple_keys = {} + + # Read the token. + mark = self.get_mark() + + # Add STREAM-END. + self.tokens.append(StreamEndToken(mark, mark)) + + # The steam is finished. + self.done = True + + def fetch_directive(self): + + # Set the current intendation to -1. + self.unwind_indent(-1) + + # Reset simple keys. + self.remove_possible_simple_key() + self.allow_simple_key = False + + # Scan and add DIRECTIVE. + self.tokens.append(self.scan_directive()) + + def fetch_document_start(self): + self.fetch_document_indicator(DocumentStartToken) + + def fetch_document_end(self): + self.fetch_document_indicator(DocumentEndToken) + + def fetch_document_indicator(self, TokenClass): + + # Set the current intendation to -1. + self.unwind_indent(-1) + + # Reset simple keys. Note that there could not be a block collection + # after '---'. + self.remove_possible_simple_key() + self.allow_simple_key = False + + # Add DOCUMENT-START or DOCUMENT-END. + start_mark = self.get_mark() + self.forward(3) + end_mark = self.get_mark() + self.tokens.append(TokenClass(start_mark, end_mark)) + + def fetch_flow_sequence_start(self): + self.fetch_flow_collection_start(FlowSequenceStartToken) + + def fetch_flow_mapping_start(self): + self.fetch_flow_collection_start(FlowMappingStartToken) + + def fetch_flow_collection_start(self, TokenClass): + + # '[' and '{' may start a simple key. + self.save_possible_simple_key() + + # Increase the flow level. + self.flow_level += 1 + + # Simple keys are allowed after '[' and '{'. + self.allow_simple_key = True + + # Add FLOW-SEQUENCE-START or FLOW-MAPPING-START. + start_mark = self.get_mark() + self.forward() + end_mark = self.get_mark() + self.tokens.append(TokenClass(start_mark, end_mark)) + + def fetch_flow_sequence_end(self): + self.fetch_flow_collection_end(FlowSequenceEndToken) + + def fetch_flow_mapping_end(self): + self.fetch_flow_collection_end(FlowMappingEndToken) + + def fetch_flow_collection_end(self, TokenClass): + + # Reset possible simple key on the current level. + self.remove_possible_simple_key() + + # Decrease the flow level. + self.flow_level -= 1 + + # No simple keys after ']' or '}'. + self.allow_simple_key = False + + # Add FLOW-SEQUENCE-END or FLOW-MAPPING-END. + start_mark = self.get_mark() + self.forward() + end_mark = self.get_mark() + self.tokens.append(TokenClass(start_mark, end_mark)) + + def fetch_flow_entry(self): + + # Simple keys are allowed after ','. + self.allow_simple_key = True + + # Reset possible simple key on the current level. + self.remove_possible_simple_key() + + # Add FLOW-ENTRY. + start_mark = self.get_mark() + self.forward() + end_mark = self.get_mark() + self.tokens.append(FlowEntryToken(start_mark, end_mark)) + + def fetch_block_entry(self): + + # Block context needs additional checks. + if not self.flow_level: + + # Are we allowed to start a new entry? + if not self.allow_simple_key: + raise ScannerError(None, None, + "sequence entries are not allowed here", + self.get_mark()) + + # We may need to add BLOCK-SEQUENCE-START. + if self.add_indent(self.column): + mark = self.get_mark() + self.tokens.append(BlockSequenceStartToken(mark, mark)) + + # It's an error for the block entry to occur in the flow context, + # but we let the parser detect this. + else: + pass + + # Simple keys are allowed after '-'. + self.allow_simple_key = True + + # Reset possible simple key on the current level. + self.remove_possible_simple_key() + + # Add BLOCK-ENTRY. + start_mark = self.get_mark() + self.forward() + end_mark = self.get_mark() + self.tokens.append(BlockEntryToken(start_mark, end_mark)) + + def fetch_key(self): + + # Block context needs additional checks. + if not self.flow_level: + + # Are we allowed to start a key (not nessesary a simple)? + if not self.allow_simple_key: + raise ScannerError(None, None, + "mapping keys are not allowed here", + self.get_mark()) + + # We may need to add BLOCK-MAPPING-START. + if self.add_indent(self.column): + mark = self.get_mark() + self.tokens.append(BlockMappingStartToken(mark, mark)) + + # Simple keys are allowed after '?' in the block context. + self.allow_simple_key = not self.flow_level + + # Reset possible simple key on the current level. + self.remove_possible_simple_key() + + # Add KEY. + start_mark = self.get_mark() + self.forward() + end_mark = self.get_mark() + self.tokens.append(KeyToken(start_mark, end_mark)) + + def fetch_value(self): + + # Do we determine a simple key? + if self.flow_level in self.possible_simple_keys: + + # Add KEY. + key = self.possible_simple_keys[self.flow_level] + del self.possible_simple_keys[self.flow_level] + self.tokens.insert(key.token_number-self.tokens_taken, + KeyToken(key.mark, key.mark)) + + # If this key starts a new block mapping, we need to add + # BLOCK-MAPPING-START. + if not self.flow_level: + if self.add_indent(key.column): + self.tokens.insert(key.token_number-self.tokens_taken, + BlockMappingStartToken(key.mark, key.mark)) + + # There cannot be two simple keys one after another. + self.allow_simple_key = False + + # It must be a part of a complex key. + else: + + # Block context needs additional checks. + # (Do we really need them? They will be catched by the parser + # anyway.) + if not self.flow_level: + + # We are allowed to start a complex value if and only if + # we can start a simple key. + if not self.allow_simple_key: + raise ScannerError(None, None, + "mapping values are not allowed here", + self.get_mark()) + + # If this value starts a new block mapping, we need to add + # BLOCK-MAPPING-START. It will be detected as an error later by + # the parser. + if not self.flow_level: + if self.add_indent(self.column): + mark = self.get_mark() + self.tokens.append(BlockMappingStartToken(mark, mark)) + + # Simple keys are allowed after ':' in the block context. + self.allow_simple_key = not self.flow_level + + # Reset possible simple key on the current level. + self.remove_possible_simple_key() + + # Add VALUE. + start_mark = self.get_mark() + self.forward() + end_mark = self.get_mark() + self.tokens.append(ValueToken(start_mark, end_mark)) + + def fetch_alias(self): + + # ALIAS could be a simple key. + self.save_possible_simple_key() + + # No simple keys after ALIAS. + self.allow_simple_key = False + + # Scan and add ALIAS. + self.tokens.append(self.scan_anchor(AliasToken)) + + def fetch_anchor(self): + + # ANCHOR could start a simple key. + self.save_possible_simple_key() + + # No simple keys after ANCHOR. + self.allow_simple_key = False + + # Scan and add ANCHOR. + self.tokens.append(self.scan_anchor(AnchorToken)) + + def fetch_tag(self): + + # TAG could start a simple key. + self.save_possible_simple_key() + + # No simple keys after TAG. + self.allow_simple_key = False + + # Scan and add TAG. + self.tokens.append(self.scan_tag()) + + def fetch_literal(self): + self.fetch_block_scalar(style='|') + + def fetch_folded(self): + self.fetch_block_scalar(style='>') + + def fetch_block_scalar(self, style): + + # A simple key may follow a block scalar. + self.allow_simple_key = True + + # Reset possible simple key on the current level. + self.remove_possible_simple_key() + + # Scan and add SCALAR. + self.tokens.append(self.scan_block_scalar(style)) + + def fetch_single(self): + self.fetch_flow_scalar(style='\'') + + def fetch_double(self): + self.fetch_flow_scalar(style='"') + + def fetch_flow_scalar(self, style): + + # A flow scalar could be a simple key. + self.save_possible_simple_key() + + # No simple keys after flow scalars. + self.allow_simple_key = False + + # Scan and add SCALAR. + self.tokens.append(self.scan_flow_scalar(style)) + + def fetch_plain(self): + + # A plain scalar could be a simple key. + self.save_possible_simple_key() + + # No simple keys after plain scalars. But note that `scan_plain` will + # change this flag if the scan is finished at the beginning of the + # line. + self.allow_simple_key = False + + # Scan and add SCALAR. May change `allow_simple_key`. + self.tokens.append(self.scan_plain()) + + # Checkers. + + def check_directive(self): + + # DIRECTIVE: ^ '%' ... + # The '%' indicator is already checked. + if self.column == 0: + return True + + def check_document_start(self): + + # DOCUMENT-START: ^ '---' (' '|'\n') + if self.column == 0: + if self.prefix(3) == u'---' \ + and self.peek(3) in u'\0 \t\r\n\x85\u2028\u2029': + return True + + def check_document_end(self): + + # DOCUMENT-END: ^ '...' (' '|'\n') + if self.column == 0: + if self.prefix(3) == u'...' \ + and self.peek(3) in u'\0 \t\r\n\x85\u2028\u2029': + return True + + def check_block_entry(self): + + # BLOCK-ENTRY: '-' (' '|'\n') + return self.peek(1) in u'\0 \t\r\n\x85\u2028\u2029' + + def check_key(self): + + # KEY(flow context): '?' + if self.flow_level: + return True + + # KEY(block context): '?' (' '|'\n') + else: + return self.peek(1) in u'\0 \t\r\n\x85\u2028\u2029' + + def check_value(self): + + # VALUE(flow context): ':' + if self.flow_level: + return True + + # VALUE(block context): ':' (' '|'\n') + else: + return self.peek(1) in u'\0 \t\r\n\x85\u2028\u2029' + + def check_plain(self): + + # A plain scalar may start with any non-space character except: + # '-', '?', ':', ',', '[', ']', '{', '}', + # '#', '&', '*', '!', '|', '>', '\'', '\"', + # '%', '@', '`'. + # + # It may also start with + # '-', '?', ':' + # if it is followed by a non-space character. + # + # Note that we limit the last rule to the block context (except the + # '-' character) because we want the flow context to be space + # independent. + ch = self.peek() + return ch not in u'\0 \t\r\n\x85\u2028\u2029-?:,[]{}#&*!|>\'\"%@`' \ + or (self.peek(1) not in u'\0 \t\r\n\x85\u2028\u2029' + and (ch == u'-' or (not self.flow_level and ch in u'?:'))) + + # Scanners. + + def scan_to_next_token(self): + # We ignore spaces, line breaks and comments. + # If we find a line break in the block context, we set the flag + # `allow_simple_key` on. + # The byte order mark is stripped if it's the first character in the + # stream. We do not yet support BOM inside the stream as the + # specification requires. Any such mark will be considered as a part + # of the document. + # + # TODO: We need to make tab handling rules more sane. A good rule is + # Tabs cannot precede tokens + # BLOCK-SEQUENCE-START, BLOCK-MAPPING-START, BLOCK-END, + # KEY(block), VALUE(block), BLOCK-ENTRY + # So the checking code is + # if <TAB>: + # self.allow_simple_keys = False + # We also need to add the check for `allow_simple_keys == True` to + # `unwind_indent` before issuing BLOCK-END. + # Scanners for block, flow, and plain scalars need to be modified. + + if self.index == 0 and self.peek() == u'\uFEFF': + self.forward() + found = False + while not found: + while self.peek() == u' ': + self.forward() + if self.peek() == u'#': + while self.peek() not in u'\0\r\n\x85\u2028\u2029': + self.forward() + if self.scan_line_break(): + if not self.flow_level: + self.allow_simple_key = True + else: + found = True + + def scan_directive(self): + # See the specification for details. + start_mark = self.get_mark() + self.forward() + name = self.scan_directive_name(start_mark) + value = None + if name == u'YAML': + value = self.scan_yaml_directive_value(start_mark) + end_mark = self.get_mark() + elif name == u'TAG': + value = self.scan_tag_directive_value(start_mark) + end_mark = self.get_mark() + else: + end_mark = self.get_mark() + while self.peek() not in u'\0\r\n\x85\u2028\u2029': + self.forward() + self.scan_directive_ignored_line(start_mark) + return DirectiveToken(name, value, start_mark, end_mark) + + def scan_directive_name(self, start_mark): + # See the specification for details. + length = 0 + ch = self.peek(length) + while u'0' <= ch <= u'9' or u'A' <= ch <= u'Z' or u'a' <= ch <= u'z' \ + or ch in u'-_': + length += 1 + ch = self.peek(length) + if not length: + raise ScannerError("while scanning a directive", start_mark, + "expected alphabetic or numeric character, but found %r" + % ch.encode('utf-8'), self.get_mark()) + value = self.prefix(length) + self.forward(length) + ch = self.peek() + if ch not in u'\0 \r\n\x85\u2028\u2029': + raise ScannerError("while scanning a directive", start_mark, + "expected alphabetic or numeric character, but found %r" + % ch.encode('utf-8'), self.get_mark()) + return value + + def scan_yaml_directive_value(self, start_mark): + # See the specification for details. + while self.peek() == u' ': + self.forward() + major = self.scan_yaml_directive_number(start_mark) + if self.peek() != '.': + raise ScannerError("while scanning a directive", start_mark, + "expected a digit or '.', but found %r" + % self.peek().encode('utf-8'), + self.get_mark()) + self.forward() + minor = self.scan_yaml_directive_number(start_mark) + if self.peek() not in u'\0 \r\n\x85\u2028\u2029': + raise ScannerError("while scanning a directive", start_mark, + "expected a digit or ' ', but found %r" + % self.peek().encode('utf-8'), + self.get_mark()) + return (major, minor) + + def scan_yaml_directive_number(self, start_mark): + # See the specification for details. + ch = self.peek() + if not (u'0' <= ch <= u'9'): + raise ScannerError("while scanning a directive", start_mark, + "expected a digit, but found %r" % ch.encode('utf-8'), + self.get_mark()) + length = 0 + while u'0' <= self.peek(length) <= u'9': + length += 1 + value = int(self.prefix(length)) + self.forward(length) + return value + + def scan_tag_directive_value(self, start_mark): + # See the specification for details. + while self.peek() == u' ': + self.forward() + handle = self.scan_tag_directive_handle(start_mark) + while self.peek() == u' ': + self.forward() + prefix = self.scan_tag_directive_prefix(start_mark) + return (handle, prefix) + + def scan_tag_directive_handle(self, start_mark): + # See the specification for details. + value = self.scan_tag_handle('directive', start_mark) + ch = self.peek() + if ch != u' ': + raise ScannerError("while scanning a directive", start_mark, + "expected ' ', but found %r" % ch.encode('utf-8'), + self.get_mark()) + return value + + def scan_tag_directive_prefix(self, start_mark): + # See the specification for details. + value = self.scan_tag_uri('directive', start_mark) + ch = self.peek() + if ch not in u'\0 \r\n\x85\u2028\u2029': + raise ScannerError("while scanning a directive", start_mark, + "expected ' ', but found %r" % ch.encode('utf-8'), + self.get_mark()) + return value + + def scan_directive_ignored_line(self, start_mark): + # See the specification for details. + while self.peek() == u' ': + self.forward() + if self.peek() == u'#': + while self.peek() not in u'\0\r\n\x85\u2028\u2029': + self.forward() + ch = self.peek() + if ch not in u'\0\r\n\x85\u2028\u2029': + raise ScannerError("while scanning a directive", start_mark, + "expected a comment or a line break, but found %r" + % ch.encode('utf-8'), self.get_mark()) + self.scan_line_break() + + def scan_anchor(self, TokenClass): + # The specification does not restrict characters for anchors and + # aliases. This may lead to problems, for instance, the document: + # [ *alias, value ] + # can be interpteted in two ways, as + # [ "value" ] + # and + # [ *alias , "value" ] + # Therefore we restrict aliases to numbers and ASCII letters. + start_mark = self.get_mark() + indicator = self.peek() + if indicator == u'*': + name = 'alias' + else: + name = 'anchor' + self.forward() + length = 0 + ch = self.peek(length) + while u'0' <= ch <= u'9' or u'A' <= ch <= u'Z' or u'a' <= ch <= u'z' \ + or ch in u'-_': + length += 1 + ch = self.peek(length) + if not length: + raise ScannerError("while scanning an %s" % name, start_mark, + "expected alphabetic or numeric character, but found %r" + % ch.encode('utf-8'), self.get_mark()) + value = self.prefix(length) + self.forward(length) + ch = self.peek() + if ch not in u'\0 \t\r\n\x85\u2028\u2029?:,]}%@`': + raise ScannerError("while scanning an %s" % name, start_mark, + "expected alphabetic or numeric character, but found %r" + % ch.encode('utf-8'), self.get_mark()) + end_mark = self.get_mark() + return TokenClass(value, start_mark, end_mark) + + def scan_tag(self): + # See the specification for details. + start_mark = self.get_mark() + ch = self.peek(1) + if ch == u'<': + handle = None + self.forward(2) + suffix = self.scan_tag_uri('tag', start_mark) + if self.peek() != u'>': + raise ScannerError("while parsing a tag", start_mark, + "expected '>', but found %r" % self.peek().encode('utf-8'), + self.get_mark()) + self.forward() + elif ch in u'\0 \t\r\n\x85\u2028\u2029': + handle = None + suffix = u'!' + self.forward() + else: + length = 1 + use_handle = False + while ch not in u'\0 \r\n\x85\u2028\u2029': + if ch == u'!': + use_handle = True + break + length += 1 + ch = self.peek(length) + handle = u'!' + if use_handle: + handle = self.scan_tag_handle('tag', start_mark) + else: + handle = u'!' + self.forward() + suffix = self.scan_tag_uri('tag', start_mark) + ch = self.peek() + if ch not in u'\0 \r\n\x85\u2028\u2029': + raise ScannerError("while scanning a tag", start_mark, + "expected ' ', but found %r" % ch.encode('utf-8'), + self.get_mark()) + value = (handle, suffix) + end_mark = self.get_mark() + return TagToken(value, start_mark, end_mark) + + def scan_block_scalar(self, style): + # See the specification for details. + + if style == '>': + folded = True + else: + folded = False + + chunks = [] + start_mark = self.get_mark() + + # Scan the header. + self.forward() + chomping, increment = self.scan_block_scalar_indicators(start_mark) + self.scan_block_scalar_ignored_line(start_mark) + + # Determine the indentation level and go to the first non-empty line. + min_indent = self.indent+1 + if min_indent < 1: + min_indent = 1 + if increment is None: + breaks, max_indent, end_mark = self.scan_block_scalar_indentation() + indent = max(min_indent, max_indent) + else: + indent = min_indent+increment-1 + breaks, end_mark = self.scan_block_scalar_breaks(indent) + line_break = u'' + + # Scan the inner part of the block scalar. + while self.column == indent and self.peek() != u'\0': + chunks.extend(breaks) + leading_non_space = self.peek() not in u' \t' + length = 0 + while self.peek(length) not in u'\0\r\n\x85\u2028\u2029': + length += 1 + chunks.append(self.prefix(length)) + self.forward(length) + line_break = self.scan_line_break() + breaks, end_mark = self.scan_block_scalar_breaks(indent) + if self.column == indent and self.peek() != u'\0': + + # Unfortunately, folding rules are ambiguous. + # + # This is the folding according to the specification: + + if folded and line_break == u'\n' \ + and leading_non_space and self.peek() not in u' \t': + if not breaks: + chunks.append(u' ') + else: + chunks.append(line_break) + + # This is Clark Evans's interpretation (also in the spec + # examples): + # + #if folded and line_break == u'\n': + # if not breaks: + # if self.peek() not in ' \t': + # chunks.append(u' ') + # else: + # chunks.append(line_break) + #else: + # chunks.append(line_break) + else: + break + + # Chomp the tail. + if chomping is not False: + chunks.append(line_break) + if chomping is True: + chunks.extend(breaks) + + # We are done. + return ScalarToken(u''.join(chunks), False, start_mark, end_mark, + style) + + def scan_block_scalar_indicators(self, start_mark): + # See the specification for details. + chomping = None + increment = None + ch = self.peek() + if ch in u'+-': + if ch == '+': + chomping = True + else: + chomping = False + self.forward() + ch = self.peek() + if ch in u'0123456789': + increment = int(ch) + if increment == 0: + raise ScannerError("while scanning a block scalar", start_mark, + "expected indentation indicator in the range 1-9, but found 0", + self.get_mark()) + self.forward() + elif ch in u'0123456789': + increment = int(ch) + if increment == 0: + raise ScannerError("while scanning a block scalar", start_mark, + "expected indentation indicator in the range 1-9, but found 0", + self.get_mark()) + self.forward() + ch = self.peek() + if ch in u'+-': + if ch == '+': + chomping = True + else: + chomping = False + self.forward() + ch = self.peek() + if ch not in u'\0 \r\n\x85\u2028\u2029': + raise ScannerError("while scanning a block scalar", start_mark, + "expected chomping or indentation indicators, but found %r" + % ch.encode('utf-8'), self.get_mark()) + return chomping, increment + + def scan_block_scalar_ignored_line(self, start_mark): + # See the specification for details. + while self.peek() == u' ': + self.forward() + if self.peek() == u'#': + while self.peek() not in u'\0\r\n\x85\u2028\u2029': + self.forward() + ch = self.peek() + if ch not in u'\0\r\n\x85\u2028\u2029': + raise ScannerError("while scanning a block scalar", start_mark, + "expected a comment or a line break, but found %r" + % ch.encode('utf-8'), self.get_mark()) + self.scan_line_break() + + def scan_block_scalar_indentation(self): + # See the specification for details. + chunks = [] + max_indent = 0 + end_mark = self.get_mark() + while self.peek() in u' \r\n\x85\u2028\u2029': + if self.peek() != u' ': + chunks.append(self.scan_line_break()) + end_mark = self.get_mark() + else: + self.forward() + if self.column > max_indent: + max_indent = self.column + return chunks, max_indent, end_mark + + def scan_block_scalar_breaks(self, indent): + # See the specification for details. + chunks = [] + end_mark = self.get_mark() + while self.column < indent and self.peek() == u' ': + self.forward() + while self.peek() in u'\r\n\x85\u2028\u2029': + chunks.append(self.scan_line_break()) + end_mark = self.get_mark() + while self.column < indent and self.peek() == u' ': + self.forward() + return chunks, end_mark + + def scan_flow_scalar(self, style): + # See the specification for details. + # Note that we loose indentation rules for quoted scalars. Quoted + # scalars don't need to adhere indentation because " and ' clearly + # mark the beginning and the end of them. Therefore we are less + # restrictive then the specification requires. We only need to check + # that document separators are not included in scalars. + if style == '"': + double = True + else: + double = False + chunks = [] + start_mark = self.get_mark() + quote = self.peek() + self.forward() + chunks.extend(self.scan_flow_scalar_non_spaces(double, start_mark)) + while self.peek() != quote: + chunks.extend(self.scan_flow_scalar_spaces(double, start_mark)) + chunks.extend(self.scan_flow_scalar_non_spaces(double, start_mark)) + self.forward() + end_mark = self.get_mark() + return ScalarToken(u''.join(chunks), False, start_mark, end_mark, + style) + + ESCAPE_REPLACEMENTS = { + u'0': u'\0', + u'a': u'\x07', + u'b': u'\x08', + u't': u'\x09', + u'\t': u'\x09', + u'n': u'\x0A', + u'v': u'\x0B', + u'f': u'\x0C', + u'r': u'\x0D', + u'e': u'\x1B', + u' ': u'\x20', + u'\"': u'\"', + u'\\': u'\\', + u'N': u'\x85', + u'_': u'\xA0', + u'L': u'\u2028', + u'P': u'\u2029', + } + + ESCAPE_CODES = { + u'x': 2, + u'u': 4, + u'U': 8, + } + + def scan_flow_scalar_non_spaces(self, double, start_mark): + # See the specification for details. + chunks = [] + while True: + length = 0 + while self.peek(length) not in u'\'\"\\\0 \t\r\n\x85\u2028\u2029': + length += 1 + if length: + chunks.append(self.prefix(length)) + self.forward(length) + ch = self.peek() + if not double and ch == u'\'' and self.peek(1) == u'\'': + chunks.append(u'\'') + self.forward(2) + elif (double and ch == u'\'') or (not double and ch in u'\"\\'): + chunks.append(ch) + self.forward() + elif double and ch == u'\\': + self.forward() + ch = self.peek() + if ch in self.ESCAPE_REPLACEMENTS: + chunks.append(self.ESCAPE_REPLACEMENTS[ch]) + self.forward() + elif ch in self.ESCAPE_CODES: + length = self.ESCAPE_CODES[ch] + self.forward() + for k in range(length): + if self.peek(k) not in u'0123456789ABCDEFabcdef': + raise ScannerError("while scanning a double-quoted scalar", start_mark, + "expected escape sequence of %d hexdecimal numbers, but found %r" % + (length, self.peek(k).encode('utf-8')), self.get_mark()) + code = int(self.prefix(length), 16) + chunks.append(unichr(code)) + self.forward(length) + elif ch in u'\r\n\x85\u2028\u2029': + self.scan_line_break() + chunks.extend(self.scan_flow_scalar_breaks(double, start_mark)) + else: + raise ScannerError("while scanning a double-quoted scalar", start_mark, + "found unknown escape character %r" % ch.encode('utf-8'), self.get_mark()) + else: + return chunks + + def scan_flow_scalar_spaces(self, double, start_mark): + # See the specification for details. + chunks = [] + length = 0 + while self.peek(length) in u' \t': + length += 1 + whitespaces = self.prefix(length) + self.forward(length) + ch = self.peek() + if ch == u'\0': + raise ScannerError("while scanning a quoted scalar", start_mark, + "found unexpected end of stream", self.get_mark()) + elif ch in u'\r\n\x85\u2028\u2029': + line_break = self.scan_line_break() + breaks = self.scan_flow_scalar_breaks(double, start_mark) + if line_break != u'\n': + chunks.append(line_break) + elif not breaks: + chunks.append(u' ') + chunks.extend(breaks) + else: + chunks.append(whitespaces) + return chunks + + def scan_flow_scalar_breaks(self, double, start_mark): + # See the specification for details. + chunks = [] + while True: + # Instead of checking indentation, we check for document + # separators. + prefix = self.prefix(3) + if (prefix == u'---' or prefix == u'...') \ + and self.peek(3) in u'\0 \t\r\n\x85\u2028\u2029': + raise ScannerError("while scanning a quoted scalar", start_mark, + "found unexpected document separator", self.get_mark()) + while self.peek() in u' \t': + self.forward() + if self.peek() in u'\r\n\x85\u2028\u2029': + chunks.append(self.scan_line_break()) + else: + return chunks + + def scan_plain(self): + # See the specification for details. + # We add an additional restriction for the flow context: + # plain scalars in the flow context cannot contain ',', ':' and '?'. + # We also keep track of the `allow_simple_key` flag here. + # Indentation rules are loosed for the flow context. + chunks = [] + start_mark = self.get_mark() + end_mark = start_mark + indent = self.indent+1 + # We allow zero indentation for scalars, but then we need to check for + # document separators at the beginning of the line. + #if indent == 0: + # indent = 1 + spaces = [] + while True: + length = 0 + if self.peek() == u'#': + break + while True: + ch = self.peek(length) + if ch in u'\0 \t\r\n\x85\u2028\u2029' \ + or (not self.flow_level and ch == u':' and + self.peek(length+1) in u'\0 \t\r\n\x85\u2028\u2029') \ + or (self.flow_level and ch in u',:?[]{}'): + break + length += 1 + # It's not clear what we should do with ':' in the flow context. + if (self.flow_level and ch == u':' + and self.peek(length+1) not in u'\0 \t\r\n\x85\u2028\u2029,[]{}'): + self.forward(length) + raise ScannerError("while scanning a plain scalar", start_mark, + "found unexpected ':'", self.get_mark(), + "Please check http://pyyaml.org/wiki/YAMLColonInFlowContext for details.") + if length == 0: + break + self.allow_simple_key = False + chunks.extend(spaces) + chunks.append(self.prefix(length)) + self.forward(length) + end_mark = self.get_mark() + spaces = self.scan_plain_spaces(indent, start_mark) + if not spaces or self.peek() == u'#' \ + or (not self.flow_level and self.column < indent): + break + return ScalarToken(u''.join(chunks), True, start_mark, end_mark) + + def scan_plain_spaces(self, indent, start_mark): + # See the specification for details. + # The specification is really confusing about tabs in plain scalars. + # We just forbid them completely. Do not use tabs in YAML! + chunks = [] + length = 0 + while self.peek(length) in u' ': + length += 1 + whitespaces = self.prefix(length) + self.forward(length) + ch = self.peek() + if ch in u'\r\n\x85\u2028\u2029': + line_break = self.scan_line_break() + self.allow_simple_key = True + prefix = self.prefix(3) + if (prefix == u'---' or prefix == u'...') \ + and self.peek(3) in u'\0 \t\r\n\x85\u2028\u2029': + return + breaks = [] + while self.peek() in u' \r\n\x85\u2028\u2029': + if self.peek() == ' ': + self.forward() + else: + breaks.append(self.scan_line_break()) + prefix = self.prefix(3) + if (prefix == u'---' or prefix == u'...') \ + and self.peek(3) in u'\0 \t\r\n\x85\u2028\u2029': + return + if line_break != u'\n': + chunks.append(line_break) + elif not breaks: + chunks.append(u' ') + chunks.extend(breaks) + elif whitespaces: + chunks.append(whitespaces) + return chunks + + def scan_tag_handle(self, name, start_mark): + # See the specification for details. + # For some strange reasons, the specification does not allow '_' in + # tag handles. I have allowed it anyway. + ch = self.peek() + if ch != u'!': + raise ScannerError("while scanning a %s" % name, start_mark, + "expected '!', but found %r" % ch.encode('utf-8'), + self.get_mark()) + length = 1 + ch = self.peek(length) + if ch != u' ': + while u'0' <= ch <= u'9' or u'A' <= ch <= u'Z' or u'a' <= ch <= u'z' \ + or ch in u'-_': + length += 1 + ch = self.peek(length) + if ch != u'!': + self.forward(length) + raise ScannerError("while scanning a %s" % name, start_mark, + "expected '!', but found %r" % ch.encode('utf-8'), + self.get_mark()) + length += 1 + value = self.prefix(length) + self.forward(length) + return value + + def scan_tag_uri(self, name, start_mark): + # See the specification for details. + # Note: we do not check if URI is well-formed. + chunks = [] + length = 0 + ch = self.peek(length) + while u'0' <= ch <= u'9' or u'A' <= ch <= u'Z' or u'a' <= ch <= u'z' \ + or ch in u'-;/?:@&=+$,_.!~*\'()[]%': + if ch == u'%': + chunks.append(self.prefix(length)) + self.forward(length) + length = 0 + chunks.append(self.scan_uri_escapes(name, start_mark)) + else: + length += 1 + ch = self.peek(length) + if length: + chunks.append(self.prefix(length)) + self.forward(length) + length = 0 + if not chunks: + raise ScannerError("while parsing a %s" % name, start_mark, + "expected URI, but found %r" % ch.encode('utf-8'), + self.get_mark()) + return u''.join(chunks) + + def scan_uri_escapes(self, name, start_mark): + # See the specification for details. + bytes = [] + mark = self.get_mark() + while self.peek() == u'%': + self.forward() + for k in range(2): + if self.peek(k) not in u'0123456789ABCDEFabcdef': + raise ScannerError("while scanning a %s" % name, start_mark, + "expected URI escape sequence of 2 hexdecimal numbers, but found %r" % + (self.peek(k).encode('utf-8')), self.get_mark()) + bytes.append(chr(int(self.prefix(2), 16))) + self.forward(2) + try: + value = unicode(''.join(bytes), 'utf-8') + except UnicodeDecodeError, exc: + raise ScannerError("while scanning a %s" % name, start_mark, str(exc), mark) + return value + + def scan_line_break(self): + # Transforms: + # '\r\n' : '\n' + # '\r' : '\n' + # '\n' : '\n' + # '\x85' : '\n' + # '\u2028' : '\u2028' + # '\u2029 : '\u2029' + # default : '' + ch = self.peek() + if ch in u'\r\n\x85': + if self.prefix(2) == u'\r\n': + self.forward(2) + else: + self.forward() + return u'\n' + elif ch in u'\u2028\u2029': + self.forward() + return ch + return u'' + +#try: +# import psyco +# psyco.bind(Scanner) +#except ImportError: +# pass + diff --git a/python.d/python_modules/pyyaml2/serializer.py b/python.d/python_modules/pyyaml2/serializer.py new file mode 100644 index 00000000..0bf1e96d --- /dev/null +++ b/python.d/python_modules/pyyaml2/serializer.py @@ -0,0 +1,111 @@ + +__all__ = ['Serializer', 'SerializerError'] + +from error import YAMLError +from events import * +from nodes import * + +class SerializerError(YAMLError): + pass + +class Serializer(object): + + ANCHOR_TEMPLATE = u'id%03d' + + def __init__(self, encoding=None, + explicit_start=None, explicit_end=None, version=None, tags=None): + self.use_encoding = encoding + self.use_explicit_start = explicit_start + self.use_explicit_end = explicit_end + self.use_version = version + self.use_tags = tags + self.serialized_nodes = {} + self.anchors = {} + self.last_anchor_id = 0 + self.closed = None + + def open(self): + if self.closed is None: + self.emit(StreamStartEvent(encoding=self.use_encoding)) + self.closed = False + elif self.closed: + raise SerializerError("serializer is closed") + else: + raise SerializerError("serializer is already opened") + + def close(self): + if self.closed is None: + raise SerializerError("serializer is not opened") + elif not self.closed: + self.emit(StreamEndEvent()) + self.closed = True + + #def __del__(self): + # self.close() + + def serialize(self, node): + if self.closed is None: + raise SerializerError("serializer is not opened") + elif self.closed: + raise SerializerError("serializer is closed") + self.emit(DocumentStartEvent(explicit=self.use_explicit_start, + version=self.use_version, tags=self.use_tags)) + self.anchor_node(node) + self.serialize_node(node, None, None) + self.emit(DocumentEndEvent(explicit=self.use_explicit_end)) + self.serialized_nodes = {} + self.anchors = {} + self.last_anchor_id = 0 + + def anchor_node(self, node): + if node in self.anchors: + if self.anchors[node] is None: + self.anchors[node] = self.generate_anchor(node) + else: + self.anchors[node] = None + if isinstance(node, SequenceNode): + for item in node.value: + self.anchor_node(item) + elif isinstance(node, MappingNode): + for key, value in node.value: + self.anchor_node(key) + self.anchor_node(value) + + def generate_anchor(self, node): + self.last_anchor_id += 1 + return self.ANCHOR_TEMPLATE % self.last_anchor_id + + def serialize_node(self, node, parent, index): + alias = self.anchors[node] + if node in self.serialized_nodes: + self.emit(AliasEvent(alias)) + else: + self.serialized_nodes[node] = True + self.descend_resolver(parent, index) + if isinstance(node, ScalarNode): + detected_tag = self.resolve(ScalarNode, node.value, (True, False)) + default_tag = self.resolve(ScalarNode, node.value, (False, True)) + implicit = (node.tag == detected_tag), (node.tag == default_tag) + self.emit(ScalarEvent(alias, node.tag, implicit, node.value, + style=node.style)) + elif isinstance(node, SequenceNode): + implicit = (node.tag + == self.resolve(SequenceNode, node.value, True)) + self.emit(SequenceStartEvent(alias, node.tag, implicit, + flow_style=node.flow_style)) + index = 0 + for item in node.value: + self.serialize_node(item, node, index) + index += 1 + self.emit(SequenceEndEvent()) + elif isinstance(node, MappingNode): + implicit = (node.tag + == self.resolve(MappingNode, node.value, True)) + self.emit(MappingStartEvent(alias, node.tag, implicit, + flow_style=node.flow_style)) + for key, value in node.value: + self.serialize_node(key, node, None) + self.serialize_node(value, node, key) + self.emit(MappingEndEvent()) + self.ascend_resolver() + diff --git a/python.d/python_modules/pyyaml2/tokens.py b/python.d/python_modules/pyyaml2/tokens.py new file mode 100644 index 00000000..4d0b48a3 --- /dev/null +++ b/python.d/python_modules/pyyaml2/tokens.py @@ -0,0 +1,104 @@ + +class Token(object): + def __init__(self, start_mark, end_mark): + self.start_mark = start_mark + self.end_mark = end_mark + def __repr__(self): + attributes = [key for key in self.__dict__ + if not key.endswith('_mark')] + attributes.sort() + arguments = ', '.join(['%s=%r' % (key, getattr(self, key)) + for key in attributes]) + return '%s(%s)' % (self.__class__.__name__, arguments) + +#class BOMToken(Token): +# id = '<byte order mark>' + +class DirectiveToken(Token): + id = '<directive>' + def __init__(self, name, value, start_mark, end_mark): + self.name = name + self.value = value + self.start_mark = start_mark + self.end_mark = end_mark + +class DocumentStartToken(Token): + id = '<document start>' + +class DocumentEndToken(Token): + id = '<document end>' + +class StreamStartToken(Token): + id = '<stream start>' + def __init__(self, start_mark=None, end_mark=None, + encoding=None): + self.start_mark = start_mark + self.end_mark = end_mark + self.encoding = encoding + +class StreamEndToken(Token): + id = '<stream end>' + +class BlockSequenceStartToken(Token): + id = '<block sequence start>' + +class BlockMappingStartToken(Token): + id = '<block mapping start>' + +class BlockEndToken(Token): + id = '<block end>' + +class FlowSequenceStartToken(Token): + id = '[' + +class FlowMappingStartToken(Token): + id = '{' + +class FlowSequenceEndToken(Token): + id = ']' + +class FlowMappingEndToken(Token): + id = '}' + +class KeyToken(Token): + id = '?' + +class ValueToken(Token): + id = ':' + +class BlockEntryToken(Token): + id = '-' + +class FlowEntryToken(Token): + id = ',' + +class AliasToken(Token): + id = '<alias>' + def __init__(self, value, start_mark, end_mark): + self.value = value + self.start_mark = start_mark + self.end_mark = end_mark + +class AnchorToken(Token): + id = '<anchor>' + def __init__(self, value, start_mark, end_mark): + self.value = value + self.start_mark = start_mark + self.end_mark = end_mark + +class TagToken(Token): + id = '<tag>' + def __init__(self, value, start_mark, end_mark): + self.value = value + self.start_mark = start_mark + self.end_mark = end_mark + +class ScalarToken(Token): + id = '<scalar>' + def __init__(self, value, plain, start_mark, end_mark, style=None): + self.value = value + self.plain = plain + self.start_mark = start_mark + self.end_mark = end_mark + self.style = style + diff --git a/python.d/python_modules/pyyaml3/__init__.py b/python.d/python_modules/pyyaml3/__init__.py new file mode 100644 index 00000000..a5e20f94 --- /dev/null +++ b/python.d/python_modules/pyyaml3/__init__.py @@ -0,0 +1,312 @@ + +from .error import * + +from .tokens import * +from .events import * +from .nodes import * + +from .loader import * +from .dumper import * + +__version__ = '3.11' +try: + from .cyaml import * + __with_libyaml__ = True +except ImportError: + __with_libyaml__ = False + +import io + +def scan(stream, Loader=Loader): + """ + Scan a YAML stream and produce scanning tokens. + """ + loader = Loader(stream) + try: + while loader.check_token(): + yield loader.get_token() + finally: + loader.dispose() + +def parse(stream, Loader=Loader): + """ + Parse a YAML stream and produce parsing events. + """ + loader = Loader(stream) + try: + while loader.check_event(): + yield loader.get_event() + finally: + loader.dispose() + +def compose(stream, Loader=Loader): + """ + Parse the first YAML document in a stream + and produce the corresponding representation tree. + """ + loader = Loader(stream) + try: + return loader.get_single_node() + finally: + loader.dispose() + +def compose_all(stream, Loader=Loader): + """ + Parse all YAML documents in a stream + and produce corresponding representation trees. + """ + loader = Loader(stream) + try: + while loader.check_node(): + yield loader.get_node() + finally: + loader.dispose() + +def load(stream, Loader=Loader): + """ + Parse the first YAML document in a stream + and produce the corresponding Python object. + """ + loader = Loader(stream) + try: + return loader.get_single_data() + finally: + loader.dispose() + +def load_all(stream, Loader=Loader): + """ + Parse all YAML documents in a stream + and produce corresponding Python objects. + """ + loader = Loader(stream) + try: + while loader.check_data(): + yield loader.get_data() + finally: + loader.dispose() + +def safe_load(stream): + """ + Parse the first YAML document in a stream + and produce the corresponding Python object. + Resolve only basic YAML tags. + """ + return load(stream, SafeLoader) + +def safe_load_all(stream): + """ + Parse all YAML documents in a stream + and produce corresponding Python objects. + Resolve only basic YAML tags. + """ + return load_all(stream, SafeLoader) + +def emit(events, stream=None, Dumper=Dumper, + canonical=None, indent=None, width=None, + allow_unicode=None, line_break=None): + """ + Emit YAML parsing events into a stream. + If stream is None, return the produced string instead. + """ + getvalue = None + if stream is None: + stream = io.StringIO() + getvalue = stream.getvalue + dumper = Dumper(stream, canonical=canonical, indent=indent, width=width, + allow_unicode=allow_unicode, line_break=line_break) + try: + for event in events: + dumper.emit(event) + finally: + dumper.dispose() + if getvalue: + return getvalue() + +def serialize_all(nodes, stream=None, Dumper=Dumper, + canonical=None, indent=None, width=None, + allow_unicode=None, line_break=None, + encoding=None, explicit_start=None, explicit_end=None, + version=None, tags=None): + """ + Serialize a sequence of representation trees into a YAML stream. + If stream is None, return the produced string instead. + """ + getvalue = None + if stream is None: + if encoding is None: + stream = io.StringIO() + else: + stream = io.BytesIO() + getvalue = stream.getvalue + dumper = Dumper(stream, canonical=canonical, indent=indent, width=width, + allow_unicode=allow_unicode, line_break=line_break, + encoding=encoding, version=version, tags=tags, + explicit_start=explicit_start, explicit_end=explicit_end) + try: + dumper.open() + for node in nodes: + dumper.serialize(node) + dumper.close() + finally: + dumper.dispose() + if getvalue: + return getvalue() + +def serialize(node, stream=None, Dumper=Dumper, **kwds): + """ + Serialize a representation tree into a YAML stream. + If stream is None, return the produced string instead. + """ + return serialize_all([node], stream, Dumper=Dumper, **kwds) + +def dump_all(documents, stream=None, Dumper=Dumper, + default_style=None, default_flow_style=None, + canonical=None, indent=None, width=None, + allow_unicode=None, line_break=None, + encoding=None, explicit_start=None, explicit_end=None, + version=None, tags=None): + """ + Serialize a sequence of Python objects into a YAML stream. + If stream is None, return the produced string instead. + """ + getvalue = None + if stream is None: + if encoding is None: + stream = io.StringIO() + else: + stream = io.BytesIO() + getvalue = stream.getvalue + dumper = Dumper(stream, default_style=default_style, + default_flow_style=default_flow_style, + canonical=canonical, indent=indent, width=width, + allow_unicode=allow_unicode, line_break=line_break, + encoding=encoding, version=version, tags=tags, + explicit_start=explicit_start, explicit_end=explicit_end) + try: + dumper.open() + for data in documents: + dumper.represent(data) + dumper.close() + finally: + dumper.dispose() + if getvalue: + return getvalue() + +def dump(data, stream=None, Dumper=Dumper, **kwds): + """ + Serialize a Python object into a YAML stream. + If stream is None, return the produced string instead. + """ + return dump_all([data], stream, Dumper=Dumper, **kwds) + +def safe_dump_all(documents, stream=None, **kwds): + """ + Serialize a sequence of Python objects into a YAML stream. + Produce only basic YAML tags. + If stream is None, return the produced string instead. + """ + return dump_all(documents, stream, Dumper=SafeDumper, **kwds) + +def safe_dump(data, stream=None, **kwds): + """ + Serialize a Python object into a YAML stream. + Produce only basic YAML tags. + If stream is None, return the produced string instead. + """ + return dump_all([data], stream, Dumper=SafeDumper, **kwds) + +def add_implicit_resolver(tag, regexp, first=None, + Loader=Loader, Dumper=Dumper): + """ + Add an implicit scalar detector. + If an implicit scalar value matches the given regexp, + the corresponding tag is assigned to the scalar. + first is a sequence of possible initial characters or None. + """ + Loader.add_implicit_resolver(tag, regexp, first) + Dumper.add_implicit_resolver(tag, regexp, first) + +def add_path_resolver(tag, path, kind=None, Loader=Loader, Dumper=Dumper): + """ + Add a path based resolver for the given tag. + A path is a list of keys that forms a path + to a node in the representation tree. + Keys can be string values, integers, or None. + """ + Loader.add_path_resolver(tag, path, kind) + Dumper.add_path_resolver(tag, path, kind) + +def add_constructor(tag, constructor, Loader=Loader): + """ + Add a constructor for the given tag. + Constructor is a function that accepts a Loader instance + and a node object and produces the corresponding Python object. + """ + Loader.add_constructor(tag, constructor) + +def add_multi_constructor(tag_prefix, multi_constructor, Loader=Loader): + """ + Add a multi-constructor for the given tag prefix. + Multi-constructor is called for a node if its tag starts with tag_prefix. + Multi-constructor accepts a Loader instance, a tag suffix, + and a node object and produces the corresponding Python object. + """ + Loader.add_multi_constructor(tag_prefix, multi_constructor) + +def add_representer(data_type, representer, Dumper=Dumper): + """ + Add a representer for the given type. + Representer is a function accepting a Dumper instance + and an instance of the given data type + and producing the corresponding representation node. + """ + Dumper.add_representer(data_type, representer) + +def add_multi_representer(data_type, multi_representer, Dumper=Dumper): + """ + Add a representer for the given type. + Multi-representer is a function accepting a Dumper instance + and an instance of the given data type or subtype + and producing the corresponding representation node. + """ + Dumper.add_multi_representer(data_type, multi_representer) + +class YAMLObjectMetaclass(type): + """ + The metaclass for YAMLObject. + """ + def __init__(cls, name, bases, kwds): + super(YAMLObjectMetaclass, cls).__init__(name, bases, kwds) + if 'yaml_tag' in kwds and kwds['yaml_tag'] is not None: + cls.yaml_loader.add_constructor(cls.yaml_tag, cls.from_yaml) + cls.yaml_dumper.add_representer(cls, cls.to_yaml) + +class YAMLObject(metaclass=YAMLObjectMetaclass): + """ + An object that can dump itself to a YAML stream + and load itself from a YAML stream. + """ + + __slots__ = () # no direct instantiation, so allow immutable subclasses + + yaml_loader = Loader + yaml_dumper = Dumper + + yaml_tag = None + yaml_flow_style = None + + @classmethod + def from_yaml(cls, loader, node): + """ + Convert a representation node to a Python object. + """ + return loader.construct_yaml_object(node, cls) + + @classmethod + def to_yaml(cls, dumper, data): + """ + Convert a Python object to a representation node. + """ + return dumper.represent_yaml_object(cls.yaml_tag, data, cls, + flow_style=cls.yaml_flow_style) + diff --git a/python.d/python_modules/pyyaml3/composer.py b/python.d/python_modules/pyyaml3/composer.py new file mode 100644 index 00000000..d5c6a7ac --- /dev/null +++ b/python.d/python_modules/pyyaml3/composer.py @@ -0,0 +1,139 @@ + +__all__ = ['Composer', 'ComposerError'] + +from .error import MarkedYAMLError +from .events import * +from .nodes import * + +class ComposerError(MarkedYAMLError): + pass + +class Composer: + + def __init__(self): + self.anchors = {} + + def check_node(self): + # Drop the STREAM-START event. + if self.check_event(StreamStartEvent): + self.get_event() + + # If there are more documents available? + return not self.check_event(StreamEndEvent) + + def get_node(self): + # Get the root node of the next document. + if not self.check_event(StreamEndEvent): + return self.compose_document() + + def get_single_node(self): + # Drop the STREAM-START event. + self.get_event() + + # Compose a document if the stream is not empty. + document = None + if not self.check_event(StreamEndEvent): + document = self.compose_document() + + # Ensure that the stream contains no more documents. + if not self.check_event(StreamEndEvent): + event = self.get_event() + raise ComposerError("expected a single document in the stream", + document.start_mark, "but found another document", + event.start_mark) + + # Drop the STREAM-END event. + self.get_event() + + return document + + def compose_document(self): + # Drop the DOCUMENT-START event. + self.get_event() + + # Compose the root node. + node = self.compose_node(None, None) + + # Drop the DOCUMENT-END event. + self.get_event() + + self.anchors = {} + return node + + def compose_node(self, parent, index): + if self.check_event(AliasEvent): + event = self.get_event() + anchor = event.anchor + if anchor not in self.anchors: + raise ComposerError(None, None, "found undefined alias %r" + % anchor, event.start_mark) + return self.anchors[anchor] + event = self.peek_event() + anchor = event.anchor + if anchor is not None: + if anchor in self.anchors: + raise ComposerError("found duplicate anchor %r; first occurence" + % anchor, self.anchors[anchor].start_mark, + "second occurence", event.start_mark) + self.descend_resolver(parent, index) + if self.check_event(ScalarEvent): + node = self.compose_scalar_node(anchor) + elif self.check_event(SequenceStartEvent): + node = self.compose_sequence_node(anchor) + elif self.check_event(MappingStartEvent): + node = self.compose_mapping_node(anchor) + self.ascend_resolver() + return node + + def compose_scalar_node(self, anchor): + event = self.get_event() + tag = event.tag + if tag is None or tag == '!': + tag = self.resolve(ScalarNode, event.value, event.implicit) + node = ScalarNode(tag, event.value, + event.start_mark, event.end_mark, style=event.style) + if anchor is not None: + self.anchors[anchor] = node + return node + + def compose_sequence_node(self, anchor): + start_event = self.get_event() + tag = start_event.tag + if tag is None or tag == '!': + tag = self.resolve(SequenceNode, None, start_event.implicit) + node = SequenceNode(tag, [], + start_event.start_mark, None, + flow_style=start_event.flow_style) + if anchor is not None: + self.anchors[anchor] = node + index = 0 + while not self.check_event(SequenceEndEvent): + node.value.append(self.compose_node(node, index)) + index += 1 + end_event = self.get_event() + node.end_mark = end_event.end_mark + return node + + def compose_mapping_node(self, anchor): + start_event = self.get_event() + tag = start_event.tag + if tag is None or tag == '!': + tag = self.resolve(MappingNode, None, start_event.implicit) + node = MappingNode(tag, [], + start_event.start_mark, None, + flow_style=start_event.flow_style) + if anchor is not None: + self.anchors[anchor] = node + while not self.check_event(MappingEndEvent): + #key_event = self.peek_event() + item_key = self.compose_node(node, None) + #if item_key in node.value: + # raise ComposerError("while composing a mapping", start_event.start_mark, + # "found duplicate key", key_event.start_mark) + item_value = self.compose_node(node, item_key) + #node.value[item_key] = item_value + node.value.append((item_key, item_value)) + end_event = self.get_event() + node.end_mark = end_event.end_mark + return node + diff --git a/python.d/python_modules/pyyaml3/constructor.py b/python.d/python_modules/pyyaml3/constructor.py new file mode 100644 index 00000000..981543ae --- /dev/null +++ b/python.d/python_modules/pyyaml3/constructor.py @@ -0,0 +1,686 @@ + +__all__ = ['BaseConstructor', 'SafeConstructor', 'Constructor', + 'ConstructorError'] + +from .error import * +from .nodes import * + +import collections, datetime, base64, binascii, re, sys, types + +class ConstructorError(MarkedYAMLError): + pass + +class BaseConstructor: + + yaml_constructors = {} + yaml_multi_constructors = {} + + def __init__(self): + self.constructed_objects = {} + self.recursive_objects = {} + self.state_generators = [] + self.deep_construct = False + + def check_data(self): + # If there are more documents available? + return self.check_node() + + def get_data(self): + # Construct and return the next document. + if self.check_node(): + return self.construct_document(self.get_node()) + + def get_single_data(self): + # Ensure that the stream contains a single document and construct it. + node = self.get_single_node() + if node is not None: + return self.construct_document(node) + return None + + def construct_document(self, node): + data = self.construct_object(node) + while self.state_generators: + state_generators = self.state_generators + self.state_generators = [] + for generator in state_generators: + for dummy in generator: + pass + self.constructed_objects = {} + self.recursive_objects = {} + self.deep_construct = False + return data + + def construct_object(self, node, deep=False): + if node in self.constructed_objects: + return self.constructed_objects[node] + if deep: + old_deep = self.deep_construct + self.deep_construct = True + if node in self.recursive_objects: + raise ConstructorError(None, None, + "found unconstructable recursive node", node.start_mark) + self.recursive_objects[node] = None + constructor = None + tag_suffix = None + if node.tag in self.yaml_constructors: + constructor = self.yaml_constructors[node.tag] + else: + for tag_prefix in self.yaml_multi_constructors: + if node.tag.startswith(tag_prefix): + tag_suffix = node.tag[len(tag_prefix):] + constructor = self.yaml_multi_constructors[tag_prefix] + break + else: + if None in self.yaml_multi_constructors: + tag_suffix = node.tag + constructor = self.yaml_multi_constructors[None] + elif None in self.yaml_constructors: + constructor = self.yaml_constructors[None] + elif isinstance(node, ScalarNode): + constructor = self.__class__.construct_scalar + elif isinstance(node, SequenceNode): + constructor = self.__class__.construct_sequence + elif isinstance(node, MappingNode): + constructor = self.__class__.construct_mapping + if tag_suffix is None: + data = constructor(self, node) + else: + data = constructor(self, tag_suffix, node) + if isinstance(data, types.GeneratorType): + generator = data + data = next(generator) + if self.deep_construct: + for dummy in generator: + pass + else: + self.state_generators.append(generator) + self.constructed_objects[node] = data + del self.recursive_objects[node] + if deep: + self.deep_construct = old_deep + return data + + def construct_scalar(self, node): + if not isinstance(node, ScalarNode): + raise ConstructorError(None, None, + "expected a scalar node, but found %s" % node.id, + node.start_mark) + return node.value + + def construct_sequence(self, node, deep=False): + if not isinstance(node, SequenceNode): + raise ConstructorError(None, None, + "expected a sequence node, but found %s" % node.id, + node.start_mark) + return [self.construct_object(child, deep=deep) + for child in node.value] + + def construct_mapping(self, node, deep=False): + if not isinstance(node, MappingNode): + raise ConstructorError(None, None, + "expected a mapping node, but found %s" % node.id, + node.start_mark) + mapping = {} + for key_node, value_node in node.value: + key = self.construct_object(key_node, deep=deep) + if not isinstance(key, collections.Hashable): + raise ConstructorError("while constructing a mapping", node.start_mark, + "found unhashable key", key_node.start_mark) + value = self.construct_object(value_node, deep=deep) + mapping[key] = value + return mapping + + def construct_pairs(self, node, deep=False): + if not isinstance(node, MappingNode): + raise ConstructorError(None, None, + "expected a mapping node, but found %s" % node.id, + node.start_mark) + pairs = [] + for key_node, value_node in node.value: + key = self.construct_object(key_node, deep=deep) + value = self.construct_object(value_node, deep=deep) + pairs.append((key, value)) + return pairs + + @classmethod + def add_constructor(cls, tag, constructor): + if not 'yaml_constructors' in cls.__dict__: + cls.yaml_constructors = cls.yaml_constructors.copy() + cls.yaml_constructors[tag] = constructor + + @classmethod + def add_multi_constructor(cls, tag_prefix, multi_constructor): + if not 'yaml_multi_constructors' in cls.__dict__: + cls.yaml_multi_constructors = cls.yaml_multi_constructors.copy() + cls.yaml_multi_constructors[tag_prefix] = multi_constructor + +class SafeConstructor(BaseConstructor): + + def construct_scalar(self, node): + if isinstance(node, MappingNode): + for key_node, value_node in node.value: + if key_node.tag == 'tag:yaml.org,2002:value': + return self.construct_scalar(value_node) + return super().construct_scalar(node) + + def flatten_mapping(self, node): + merge = [] + index = 0 + while index < len(node.value): + key_node, value_node = node.value[index] + if key_node.tag == 'tag:yaml.org,2002:merge': + del node.value[index] + if isinstance(value_node, MappingNode): + self.flatten_mapping(value_node) + merge.extend(value_node.value) + elif isinstance(value_node, SequenceNode): + submerge = [] + for subnode in value_node.value: + if not isinstance(subnode, MappingNode): + raise ConstructorError("while constructing a mapping", + node.start_mark, + "expected a mapping for merging, but found %s" + % subnode.id, subnode.start_mark) + self.flatten_mapping(subnode) + submerge.append(subnode.value) + submerge.reverse() + for value in submerge: + merge.extend(value) + else: + raise ConstructorError("while constructing a mapping", node.start_mark, + "expected a mapping or list of mappings for merging, but found %s" + % value_node.id, value_node.start_mark) + elif key_node.tag == 'tag:yaml.org,2002:value': + key_node.tag = 'tag:yaml.org,2002:str' + index += 1 + else: + index += 1 + if merge: + node.value = merge + node.value + + def construct_mapping(self, node, deep=False): + if isinstance(node, MappingNode): + self.flatten_mapping(node) + return super().construct_mapping(node, deep=deep) + + def construct_yaml_null(self, node): + self.construct_scalar(node) + return None + + bool_values = { + 'yes': True, + 'no': False, + 'true': True, + 'false': False, + 'on': True, + 'off': False, + } + + def construct_yaml_bool(self, node): + value = self.construct_scalar(node) + return self.bool_values[value.lower()] + + def construct_yaml_int(self, node): + value = self.construct_scalar(node) + value = value.replace('_', '') + sign = +1 + if value[0] == '-': + sign = -1 + if value[0] in '+-': + value = value[1:] + if value == '0': + return 0 + elif value.startswith('0b'): + return sign*int(value[2:], 2) + elif value.startswith('0x'): + return sign*int(value[2:], 16) + elif value[0] == '0': + return sign*int(value, 8) + elif ':' in value: + digits = [int(part) for part in value.split(':')] + digits.reverse() + base = 1 + value = 0 + for digit in digits: + value += digit*base + base *= 60 + return sign*value + else: + return sign*int(value) + + inf_value = 1e300 + while inf_value != inf_value*inf_value: + inf_value *= inf_value + nan_value = -inf_value/inf_value # Trying to make a quiet NaN (like C99). + + def construct_yaml_float(self, node): + value = self.construct_scalar(node) + value = value.replace('_', '').lower() + sign = +1 + if value[0] == '-': + sign = -1 + if value[0] in '+-': + value = value[1:] + if value == '.inf': + return sign*self.inf_value + elif value == '.nan': + return self.nan_value + elif ':' in value: + digits = [float(part) for part in value.split(':')] + digits.reverse() + base = 1 + value = 0.0 + for digit in digits: + value += digit*base + base *= 60 + return sign*value + else: + return sign*float(value) + + def construct_yaml_binary(self, node): + try: + value = self.construct_scalar(node).encode('ascii') + except UnicodeEncodeError as exc: + raise ConstructorError(None, None, + "failed to convert base64 data into ascii: %s" % exc, + node.start_mark) + try: + if hasattr(base64, 'decodebytes'): + return base64.decodebytes(value) + else: + return base64.decodestring(value) + except binascii.Error as exc: + raise ConstructorError(None, None, + "failed to decode base64 data: %s" % exc, node.start_mark) + + timestamp_regexp = re.compile( + r'''^(?P<year>[0-9][0-9][0-9][0-9]) + -(?P<month>[0-9][0-9]?) + -(?P<day>[0-9][0-9]?) + (?:(?:[Tt]|[ \t]+) + (?P<hour>[0-9][0-9]?) + :(?P<minute>[0-9][0-9]) + :(?P<second>[0-9][0-9]) + (?:\.(?P<fraction>[0-9]*))? + (?:[ \t]*(?P<tz>Z|(?P<tz_sign>[-+])(?P<tz_hour>[0-9][0-9]?) + (?::(?P<tz_minute>[0-9][0-9]))?))?)?$''', re.X) + + def construct_yaml_timestamp(self, node): + value = self.construct_scalar(node) + match = self.timestamp_regexp.match(node.value) + values = match.groupdict() + year = int(values['year']) + month = int(values['month']) + day = int(values['day']) + if not values['hour']: + return datetime.date(year, month, day) + hour = int(values['hour']) + minute = int(values['minute']) + second = int(values['second']) + fraction = 0 + if values['fraction']: + fraction = values['fraction'][:6] + while len(fraction) < 6: + fraction += '0' + fraction = int(fraction) + delta = None + if values['tz_sign']: + tz_hour = int(values['tz_hour']) + tz_minute = int(values['tz_minute'] or 0) + delta = datetime.timedelta(hours=tz_hour, minutes=tz_minute) + if values['tz_sign'] == '-': + delta = -delta + data = datetime.datetime(year, month, day, hour, minute, second, fraction) + if delta: + data -= delta + return data + + def construct_yaml_omap(self, node): + # Note: we do not check for duplicate keys, because it's too + # CPU-expensive. + omap = [] + yield omap + if not isinstance(node, SequenceNode): + raise ConstructorError("while constructing an ordered map", node.start_mark, + "expected a sequence, but found %s" % node.id, node.start_mark) + for subnode in node.value: + if not isinstance(subnode, MappingNode): + raise ConstructorError("while constructing an ordered map", node.start_mark, + "expected a mapping of length 1, but found %s" % subnode.id, + subnode.start_mark) + if len(subnode.value) != 1: + raise ConstructorError("while constructing an ordered map", node.start_mark, + "expected a single mapping item, but found %d items" % len(subnode.value), + subnode.start_mark) + key_node, value_node = subnode.value[0] + key = self.construct_object(key_node) + value = self.construct_object(value_node) + omap.append((key, value)) + + def construct_yaml_pairs(self, node): + # Note: the same code as `construct_yaml_omap`. + pairs = [] + yield pairs + if not isinstance(node, SequenceNode): + raise ConstructorError("while constructing pairs", node.start_mark, + "expected a sequence, but found %s" % node.id, node.start_mark) + for subnode in node.value: + if not isinstance(subnode, MappingNode): + raise ConstructorError("while constructing pairs", node.start_mark, + "expected a mapping of length 1, but found %s" % subnode.id, + subnode.start_mark) + if len(subnode.value) != 1: + raise ConstructorError("while constructing pairs", node.start_mark, + "expected a single mapping item, but found %d items" % len(subnode.value), + subnode.start_mark) + key_node, value_node = subnode.value[0] + key = self.construct_object(key_node) + value = self.construct_object(value_node) + pairs.append((key, value)) + + def construct_yaml_set(self, node): + data = set() + yield data + value = self.construct_mapping(node) + data.update(value) + + def construct_yaml_str(self, node): + return self.construct_scalar(node) + + def construct_yaml_seq(self, node): + data = [] + yield data + data.extend(self.construct_sequence(node)) + + def construct_yaml_map(self, node): + data = {} + yield data + value = self.construct_mapping(node) + data.update(value) + + def construct_yaml_object(self, node, cls): + data = cls.__new__(cls) + yield data + if hasattr(data, '__setstate__'): + state = self.construct_mapping(node, deep=True) + data.__setstate__(state) + else: + state = self.construct_mapping(node) + data.__dict__.update(state) + + def construct_undefined(self, node): + raise ConstructorError(None, None, + "could not determine a constructor for the tag %r" % node.tag, + node.start_mark) + +SafeConstructor.add_constructor( + 'tag:yaml.org,2002:null', + SafeConstructor.construct_yaml_null) + +SafeConstructor.add_constructor( + 'tag:yaml.org,2002:bool', + SafeConstructor.construct_yaml_bool) + +SafeConstructor.add_constructor( + 'tag:yaml.org,2002:int', + SafeConstructor.construct_yaml_int) + +SafeConstructor.add_constructor( + 'tag:yaml.org,2002:float', + SafeConstructor.construct_yaml_float) + +SafeConstructor.add_constructor( + 'tag:yaml.org,2002:binary', + SafeConstructor.construct_yaml_binary) + +SafeConstructor.add_constructor( + 'tag:yaml.org,2002:timestamp', + SafeConstructor.construct_yaml_timestamp) + +SafeConstructor.add_constructor( + 'tag:yaml.org,2002:omap', + SafeConstructor.construct_yaml_omap) + +SafeConstructor.add_constructor( + 'tag:yaml.org,2002:pairs', + SafeConstructor.construct_yaml_pairs) + +SafeConstructor.add_constructor( + 'tag:yaml.org,2002:set', + SafeConstructor.construct_yaml_set) + +SafeConstructor.add_constructor( + 'tag:yaml.org,2002:str', + SafeConstructor.construct_yaml_str) + +SafeConstructor.add_constructor( + 'tag:yaml.org,2002:seq', + SafeConstructor.construct_yaml_seq) + +SafeConstructor.add_constructor( + 'tag:yaml.org,2002:map', + SafeConstructor.construct_yaml_map) + +SafeConstructor.add_constructor(None, + SafeConstructor.construct_undefined) + +class Constructor(SafeConstructor): + + def construct_python_str(self, node): + return self.construct_scalar(node) + + def construct_python_unicode(self, node): + return self.construct_scalar(node) + + def construct_python_bytes(self, node): + try: + value = self.construct_scalar(node).encode('ascii') + except UnicodeEncodeError as exc: + raise ConstructorError(None, None, + "failed to convert base64 data into ascii: %s" % exc, + node.start_mark) + try: + if hasattr(base64, 'decodebytes'): + return base64.decodebytes(value) + else: + return base64.decodestring(value) + except binascii.Error as exc: + raise ConstructorError(None, None, + "failed to decode base64 data: %s" % exc, node.start_mark) + + def construct_python_long(self, node): + return self.construct_yaml_int(node) + + def construct_python_complex(self, node): + return complex(self.construct_scalar(node)) + + def construct_python_tuple(self, node): + return tuple(self.construct_sequence(node)) + + def find_python_module(self, name, mark): + if not name: + raise ConstructorError("while constructing a Python module", mark, + "expected non-empty name appended to the tag", mark) + try: + __import__(name) + except ImportError as exc: + raise ConstructorError("while constructing a Python module", mark, + "cannot find module %r (%s)" % (name, exc), mark) + return sys.modules[name] + + def find_python_name(self, name, mark): + if not name: + raise ConstructorError("while constructing a Python object", mark, + "expected non-empty name appended to the tag", mark) + if '.' in name: + module_name, object_name = name.rsplit('.', 1) + else: + module_name = 'builtins' + object_name = name + try: + __import__(module_name) + except ImportError as exc: + raise ConstructorError("while constructing a Python object", mark, + "cannot find module %r (%s)" % (module_name, exc), mark) + module = sys.modules[module_name] + if not hasattr(module, object_name): + raise ConstructorError("while constructing a Python object", mark, + "cannot find %r in the module %r" + % (object_name, module.__name__), mark) + return getattr(module, object_name) + + def construct_python_name(self, suffix, node): + value = self.construct_scalar(node) + if value: + raise ConstructorError("while constructing a Python name", node.start_mark, + "expected the empty value, but found %r" % value, node.start_mark) + return self.find_python_name(suffix, node.start_mark) + + def construct_python_module(self, suffix, node): + value = self.construct_scalar(node) + if value: + raise ConstructorError("while constructing a Python module", node.start_mark, + "expected the empty value, but found %r" % value, node.start_mark) + return self.find_python_module(suffix, node.start_mark) + + def make_python_instance(self, suffix, node, + args=None, kwds=None, newobj=False): + if not args: + args = [] + if not kwds: + kwds = {} + cls = self.find_python_name(suffix, node.start_mark) + if newobj and isinstance(cls, type): + return cls.__new__(cls, *args, **kwds) + else: + return cls(*args, **kwds) + + def set_python_instance_state(self, instance, state): + if hasattr(instance, '__setstate__'): + instance.__setstate__(state) + else: + slotstate = {} + if isinstance(state, tuple) and len(state) == 2: + state, slotstate = state + if hasattr(instance, '__dict__'): + instance.__dict__.update(state) + elif state: + slotstate.update(state) + for key, value in slotstate.items(): + setattr(object, key, value) + + def construct_python_object(self, suffix, node): + # Format: + # !!python/object:module.name { ... state ... } + instance = self.make_python_instance(suffix, node, newobj=True) + yield instance + deep = hasattr(instance, '__setstate__') + state = self.construct_mapping(node, deep=deep) + self.set_python_instance_state(instance, state) + + def construct_python_object_apply(self, suffix, node, newobj=False): + # Format: + # !!python/object/apply # (or !!python/object/new) + # args: [ ... arguments ... ] + # kwds: { ... keywords ... } + # state: ... state ... + # listitems: [ ... listitems ... ] + # dictitems: { ... dictitems ... } + # or short format: + # !!python/object/apply [ ... arguments ... ] + # The difference between !!python/object/apply and !!python/object/new + # is how an object is created, check make_python_instance for details. + if isinstance(node, SequenceNode): + args = self.construct_sequence(node, deep=True) + kwds = {} + state = {} + listitems = [] + dictitems = {} + else: + value = self.construct_mapping(node, deep=True) + args = value.get('args', []) + kwds = value.get('kwds', {}) + state = value.get('state', {}) + listitems = value.get('listitems', []) + dictitems = value.get('dictitems', {}) + instance = self.make_python_instance(suffix, node, args, kwds, newobj) + if state: + self.set_python_instance_state(instance, state) + if listitems: + instance.extend(listitems) + if dictitems: + for key in dictitems: + instance[key] = dictitems[key] + return instance + + def construct_python_object_new(self, suffix, node): + return self.construct_python_object_apply(suffix, node, newobj=True) + +Constructor.add_constructor( + 'tag:yaml.org,2002:python/none', + Constructor.construct_yaml_null) + +Constructor.add_constructor( + 'tag:yaml.org,2002:python/bool', + Constructor.construct_yaml_bool) + +Constructor.add_constructor( + 'tag:yaml.org,2002:python/str', + Constructor.construct_python_str) + +Constructor.add_constructor( + 'tag:yaml.org,2002:python/unicode', + Constructor.construct_python_unicode) + +Constructor.add_constructor( + 'tag:yaml.org,2002:python/bytes', + Constructor.construct_python_bytes) + +Constructor.add_constructor( + 'tag:yaml.org,2002:python/int', + Constructor.construct_yaml_int) + +Constructor.add_constructor( + 'tag:yaml.org,2002:python/long', + Constructor.construct_python_long) + +Constructor.add_constructor( + 'tag:yaml.org,2002:python/float', + Constructor.construct_yaml_float) + +Constructor.add_constructor( + 'tag:yaml.org,2002:python/complex', + Constructor.construct_python_complex) + +Constructor.add_constructor( + 'tag:yaml.org,2002:python/list', + Constructor.construct_yaml_seq) + +Constructor.add_constructor( + 'tag:yaml.org,2002:python/tuple', + Constructor.construct_python_tuple) + +Constructor.add_constructor( + 'tag:yaml.org,2002:python/dict', + Constructor.construct_yaml_map) + +Constructor.add_multi_constructor( + 'tag:yaml.org,2002:python/name:', + Constructor.construct_python_name) + +Constructor.add_multi_constructor( + 'tag:yaml.org,2002:python/module:', + Constructor.construct_python_module) + +Constructor.add_multi_constructor( + 'tag:yaml.org,2002:python/object:', + Constructor.construct_python_object) + +Constructor.add_multi_constructor( + 'tag:yaml.org,2002:python/object/apply:', + Constructor.construct_python_object_apply) + +Constructor.add_multi_constructor( + 'tag:yaml.org,2002:python/object/new:', + Constructor.construct_python_object_new) + diff --git a/python.d/python_modules/pyyaml3/cyaml.py b/python.d/python_modules/pyyaml3/cyaml.py new file mode 100644 index 00000000..d5cb87e9 --- /dev/null +++ b/python.d/python_modules/pyyaml3/cyaml.py @@ -0,0 +1,85 @@ + +__all__ = ['CBaseLoader', 'CSafeLoader', 'CLoader', + 'CBaseDumper', 'CSafeDumper', 'CDumper'] + +from _yaml import CParser, CEmitter + +from .constructor import * + +from .serializer import * +from .representer import * + +from .resolver import * + +class CBaseLoader(CParser, BaseConstructor, BaseResolver): + + def __init__(self, stream): + CParser.__init__(self, stream) + BaseConstructor.__init__(self) + BaseResolver.__init__(self) + +class CSafeLoader(CParser, SafeConstructor, Resolver): + + def __init__(self, stream): + CParser.__init__(self, stream) + SafeConstructor.__init__(self) + Resolver.__init__(self) + +class CLoader(CParser, Constructor, Resolver): + + def __init__(self, stream): + CParser.__init__(self, stream) + Constructor.__init__(self) + Resolver.__init__(self) + +class CBaseDumper(CEmitter, BaseRepresenter, BaseResolver): + + def __init__(self, stream, + default_style=None, default_flow_style=None, + canonical=None, indent=None, width=None, + allow_unicode=None, line_break=None, + encoding=None, explicit_start=None, explicit_end=None, + version=None, tags=None): + CEmitter.__init__(self, stream, canonical=canonical, + indent=indent, width=width, encoding=encoding, + allow_unicode=allow_unicode, line_break=line_break, + explicit_start=explicit_start, explicit_end=explicit_end, + version=version, tags=tags) + Representer.__init__(self, default_style=default_style, + default_flow_style=default_flow_style) + Resolver.__init__(self) + +class CSafeDumper(CEmitter, SafeRepresenter, Resolver): + + def __init__(self, stream, + default_style=None, default_flow_style=None, + canonical=None, indent=None, width=None, + allow_unicode=None, line_break=None, + encoding=None, explicit_start=None, explicit_end=None, + version=None, tags=None): + CEmitter.__init__(self, stream, canonical=canonical, + indent=indent, width=width, encoding=encoding, + allow_unicode=allow_unicode, line_break=line_break, + explicit_start=explicit_start, explicit_end=explicit_end, + version=version, tags=tags) + SafeRepresenter.__init__(self, default_style=default_style, + default_flow_style=default_flow_style) + Resolver.__init__(self) + +class CDumper(CEmitter, Serializer, Representer, Resolver): + + def __init__(self, stream, + default_style=None, default_flow_style=None, + canonical=None, indent=None, width=None, + allow_unicode=None, line_break=None, + encoding=None, explicit_start=None, explicit_end=None, + version=None, tags=None): + CEmitter.__init__(self, stream, canonical=canonical, + indent=indent, width=width, encoding=encoding, + allow_unicode=allow_unicode, line_break=line_break, + explicit_start=explicit_start, explicit_end=explicit_end, + version=version, tags=tags) + Representer.__init__(self, default_style=default_style, + default_flow_style=default_flow_style) + Resolver.__init__(self) + diff --git a/python.d/python_modules/pyyaml3/dumper.py b/python.d/python_modules/pyyaml3/dumper.py new file mode 100644 index 00000000..0b691287 --- /dev/null +++ b/python.d/python_modules/pyyaml3/dumper.py @@ -0,0 +1,62 @@ + +__all__ = ['BaseDumper', 'SafeDumper', 'Dumper'] + +from .emitter import * +from .serializer import * +from .representer import * +from .resolver import * + +class BaseDumper(Emitter, Serializer, BaseRepresenter, BaseResolver): + + def __init__(self, stream, + default_style=None, default_flow_style=None, + canonical=None, indent=None, width=None, + allow_unicode=None, line_break=None, + encoding=None, explicit_start=None, explicit_end=None, + version=None, tags=None): + Emitter.__init__(self, stream, canonical=canonical, + indent=indent, width=width, + allow_unicode=allow_unicode, line_break=line_break) + Serializer.__init__(self, encoding=encoding, + explicit_start=explicit_start, explicit_end=explicit_end, + version=version, tags=tags) + Representer.__init__(self, default_style=default_style, + default_flow_style=default_flow_style) + Resolver.__init__(self) + +class SafeDumper(Emitter, Serializer, SafeRepresenter, Resolver): + + def __init__(self, stream, + default_style=None, default_flow_style=None, + canonical=None, indent=None, width=None, + allow_unicode=None, line_break=None, + encoding=None, explicit_start=None, explicit_end=None, + version=None, tags=None): + Emitter.__init__(self, stream, canonical=canonical, + indent=indent, width=width, + allow_unicode=allow_unicode, line_break=line_break) + Serializer.__init__(self, encoding=encoding, + explicit_start=explicit_start, explicit_end=explicit_end, + version=version, tags=tags) + SafeRepresenter.__init__(self, default_style=default_style, + default_flow_style=default_flow_style) + Resolver.__init__(self) + +class Dumper(Emitter, Serializer, Representer, Resolver): + + def __init__(self, stream, + default_style=None, default_flow_style=None, + canonical=None, indent=None, width=None, + allow_unicode=None, line_break=None, + encoding=None, explicit_start=None, explicit_end=None, + version=None, tags=None): + Emitter.__init__(self, stream, canonical=canonical, + indent=indent, width=width, + allow_unicode=allow_unicode, line_break=line_break) + Serializer.__init__(self, encoding=encoding, + explicit_start=explicit_start, explicit_end=explicit_end, + version=version, tags=tags) + Representer.__init__(self, default_style=default_style, + default_flow_style=default_flow_style) + Resolver.__init__(self) + diff --git a/python.d/python_modules/pyyaml3/emitter.py b/python.d/python_modules/pyyaml3/emitter.py new file mode 100644 index 00000000..34cb145a --- /dev/null +++ b/python.d/python_modules/pyyaml3/emitter.py @@ -0,0 +1,1137 @@ + +# Emitter expects events obeying the following grammar: +# stream ::= STREAM-START document* STREAM-END +# document ::= DOCUMENT-START node DOCUMENT-END +# node ::= SCALAR | sequence | mapping +# sequence ::= SEQUENCE-START node* SEQUENCE-END +# mapping ::= MAPPING-START (node node)* MAPPING-END + +__all__ = ['Emitter', 'EmitterError'] + +from .error import YAMLError +from .events import * + +class EmitterError(YAMLError): + pass + +class ScalarAnalysis: + def __init__(self, scalar, empty, multiline, + allow_flow_plain, allow_block_plain, + allow_single_quoted, allow_double_quoted, + allow_block): + self.scalar = scalar + self.empty = empty + self.multiline = multiline + self.allow_flow_plain = allow_flow_plain + self.allow_block_plain = allow_block_plain + self.allow_single_quoted = allow_single_quoted + self.allow_double_quoted = allow_double_quoted + self.allow_block = allow_block + +class Emitter: + + DEFAULT_TAG_PREFIXES = { + '!' : '!', + 'tag:yaml.org,2002:' : '!!', + } + + def __init__(self, stream, canonical=None, indent=None, width=None, + allow_unicode=None, line_break=None): + + # The stream should have the methods `write` and possibly `flush`. + self.stream = stream + + # Encoding can be overriden by STREAM-START. + self.encoding = None + + # Emitter is a state machine with a stack of states to handle nested + # structures. + self.states = [] + self.state = self.expect_stream_start + + # Current event and the event queue. + self.events = [] + self.event = None + + # The current indentation level and the stack of previous indents. + self.indents = [] + self.indent = None + + # Flow level. + self.flow_level = 0 + + # Contexts. + self.root_context = False + self.sequence_context = False + self.mapping_context = False + self.simple_key_context = False + + # Characteristics of the last emitted character: + # - current position. + # - is it a whitespace? + # - is it an indention character + # (indentation space, '-', '?', or ':')? + self.line = 0 + self.column = 0 + self.whitespace = True + self.indention = True + + # Whether the document requires an explicit document indicator + self.open_ended = False + + # Formatting details. + self.canonical = canonical + self.allow_unicode = allow_unicode + self.best_indent = 2 + if indent and 1 < indent < 10: + self.best_indent = indent + self.best_width = 80 + if width and width > self.best_indent*2: + self.best_width = width + self.best_line_break = '\n' + if line_break in ['\r', '\n', '\r\n']: + self.best_line_break = line_break + + # Tag prefixes. + self.tag_prefixes = None + + # Prepared anchor and tag. + self.prepared_anchor = None + self.prepared_tag = None + + # Scalar analysis and style. + self.analysis = None + self.style = None + + def dispose(self): + # Reset the state attributes (to clear self-references) + self.states = [] + self.state = None + + def emit(self, event): + self.events.append(event) + while not self.need_more_events(): + self.event = self.events.pop(0) + self.state() + self.event = None + + # In some cases, we wait for a few next events before emitting. + + def need_more_events(self): + if not self.events: + return True + event = self.events[0] + if isinstance(event, DocumentStartEvent): + return self.need_events(1) + elif isinstance(event, SequenceStartEvent): + return self.need_events(2) + elif isinstance(event, MappingStartEvent): + return self.need_events(3) + else: + return False + + def need_events(self, count): + level = 0 + for event in self.events[1:]: + if isinstance(event, (DocumentStartEvent, CollectionStartEvent)): + level += 1 + elif isinstance(event, (DocumentEndEvent, CollectionEndEvent)): + level -= 1 + elif isinstance(event, StreamEndEvent): + level = -1 + if level < 0: + return False + return (len(self.events) < count+1) + + def increase_indent(self, flow=False, indentless=False): + self.indents.append(self.indent) + if self.indent is None: + if flow: + self.indent = self.best_indent + else: + self.indent = 0 + elif not indentless: + self.indent += self.best_indent + + # States. + + # Stream handlers. + + def expect_stream_start(self): + if isinstance(self.event, StreamStartEvent): + if self.event.encoding and not hasattr(self.stream, 'encoding'): + self.encoding = self.event.encoding + self.write_stream_start() + self.state = self.expect_first_document_start + else: + raise EmitterError("expected StreamStartEvent, but got %s" + % self.event) + + def expect_nothing(self): + raise EmitterError("expected nothing, but got %s" % self.event) + + # Document handlers. + + def expect_first_document_start(self): + return self.expect_document_start(first=True) + + def expect_document_start(self, first=False): + if isinstance(self.event, DocumentStartEvent): + if (self.event.version or self.event.tags) and self.open_ended: + self.write_indicator('...', True) + self.write_indent() + if self.event.version: + version_text = self.prepare_version(self.event.version) + self.write_version_directive(version_text) + self.tag_prefixes = self.DEFAULT_TAG_PREFIXES.copy() + if self.event.tags: + handles = sorted(self.event.tags.keys()) + for handle in handles: + prefix = self.event.tags[handle] + self.tag_prefixes[prefix] = handle + handle_text = self.prepare_tag_handle(handle) + prefix_text = self.prepare_tag_prefix(prefix) + self.write_tag_directive(handle_text, prefix_text) + implicit = (first and not self.event.explicit and not self.canonical + and not self.event.version and not self.event.tags + and not self.check_empty_document()) + if not implicit: + self.write_indent() + self.write_indicator('---', True) + if self.canonical: + self.write_indent() + self.state = self.expect_document_root + elif isinstance(self.event, StreamEndEvent): + if self.open_ended: + self.write_indicator('...', True) + self.write_indent() + self.write_stream_end() + self.state = self.expect_nothing + else: + raise EmitterError("expected DocumentStartEvent, but got %s" + % self.event) + + def expect_document_end(self): + if isinstance(self.event, DocumentEndEvent): + self.write_indent() + if self.event.explicit: + self.write_indicator('...', True) + self.write_indent() + self.flush_stream() + self.state = self.expect_document_start + else: + raise EmitterError("expected DocumentEndEvent, but got %s" + % self.event) + + def expect_document_root(self): + self.states.append(self.expect_document_end) + self.expect_node(root=True) + + # Node handlers. + + def expect_node(self, root=False, sequence=False, mapping=False, + simple_key=False): + self.root_context = root + self.sequence_context = sequence + self.mapping_context = mapping + self.simple_key_context = simple_key + if isinstance(self.event, AliasEvent): + self.expect_alias() + elif isinstance(self.event, (ScalarEvent, CollectionStartEvent)): + self.process_anchor('&') + self.process_tag() + if isinstance(self.event, ScalarEvent): + self.expect_scalar() + elif isinstance(self.event, SequenceStartEvent): + if self.flow_level or self.canonical or self.event.flow_style \ + or self.check_empty_sequence(): + self.expect_flow_sequence() + else: + self.expect_block_sequence() + elif isinstance(self.event, MappingStartEvent): + if self.flow_level or self.canonical or self.event.flow_style \ + or self.check_empty_mapping(): + self.expect_flow_mapping() + else: + self.expect_block_mapping() + else: + raise EmitterError("expected NodeEvent, but got %s" % self.event) + + def expect_alias(self): + if self.event.anchor is None: + raise EmitterError("anchor is not specified for alias") + self.process_anchor('*') + self.state = self.states.pop() + + def expect_scalar(self): + self.increase_indent(flow=True) + self.process_scalar() + self.indent = self.indents.pop() + self.state = self.states.pop() + + # Flow sequence handlers. + + def expect_flow_sequence(self): + self.write_indicator('[', True, whitespace=True) + self.flow_level += 1 + self.increase_indent(flow=True) + self.state = self.expect_first_flow_sequence_item + + def expect_first_flow_sequence_item(self): + if isinstance(self.event, SequenceEndEvent): + self.indent = self.indents.pop() + self.flow_level -= 1 + self.write_indicator(']', False) + self.state = self.states.pop() + else: + if self.canonical or self.column > self.best_width: + self.write_indent() + self.states.append(self.expect_flow_sequence_item) + self.expect_node(sequence=True) + + def expect_flow_sequence_item(self): + if isinstance(self.event, SequenceEndEvent): + self.indent = self.indents.pop() + self.flow_level -= 1 + if self.canonical: + self.write_indicator(',', False) + self.write_indent() + self.write_indicator(']', False) + self.state = self.states.pop() + else: + self.write_indicator(',', False) + if self.canonical or self.column > self.best_width: + self.write_indent() + self.states.append(self.expect_flow_sequence_item) + self.expect_node(sequence=True) + + # Flow mapping handlers. + + def expect_flow_mapping(self): + self.write_indicator('{', True, whitespace=True) + self.flow_level += 1 + self.increase_indent(flow=True) + self.state = self.expect_first_flow_mapping_key + + def expect_first_flow_mapping_key(self): + if isinstance(self.event, MappingEndEvent): + self.indent = self.indents.pop() + self.flow_level -= 1 + self.write_indicator('}', False) + self.state = self.states.pop() + else: + if self.canonical or self.column > self.best_width: + self.write_indent() + if not self.canonical and self.check_simple_key(): + self.states.append(self.expect_flow_mapping_simple_value) + self.expect_node(mapping=True, simple_key=True) + else: + self.write_indicator('?', True) + self.states.append(self.expect_flow_mapping_value) + self.expect_node(mapping=True) + + def expect_flow_mapping_key(self): + if isinstance(self.event, MappingEndEvent): + self.indent = self.indents.pop() + self.flow_level -= 1 + if self.canonical: + self.write_indicator(',', False) + self.write_indent() + self.write_indicator('}', False) + self.state = self.states.pop() + else: + self.write_indicator(',', False) + if self.canonical or self.column > self.best_width: + self.write_indent() + if not self.canonical and self.check_simple_key(): + self.states.append(self.expect_flow_mapping_simple_value) + self.expect_node(mapping=True, simple_key=True) + else: + self.write_indicator('?', True) + self.states.append(self.expect_flow_mapping_value) + self.expect_node(mapping=True) + + def expect_flow_mapping_simple_value(self): + self.write_indicator(':', False) + self.states.append(self.expect_flow_mapping_key) + self.expect_node(mapping=True) + + def expect_flow_mapping_value(self): + if self.canonical or self.column > self.best_width: + self.write_indent() + self.write_indicator(':', True) + self.states.append(self.expect_flow_mapping_key) + self.expect_node(mapping=True) + + # Block sequence handlers. + + def expect_block_sequence(self): + indentless = (self.mapping_context and not self.indention) + self.increase_indent(flow=False, indentless=indentless) + self.state = self.expect_first_block_sequence_item + + def expect_first_block_sequence_item(self): + return self.expect_block_sequence_item(first=True) + + def expect_block_sequence_item(self, first=False): + if not first and isinstance(self.event, SequenceEndEvent): + self.indent = self.indents.pop() + self.state = self.states.pop() + else: + self.write_indent() + self.write_indicator('-', True, indention=True) + self.states.append(self.expect_block_sequence_item) + self.expect_node(sequence=True) + + # Block mapping handlers. + + def expect_block_mapping(self): + self.increase_indent(flow=False) + self.state = self.expect_first_block_mapping_key + + def expect_first_block_mapping_key(self): + return self.expect_block_mapping_key(first=True) + + def expect_block_mapping_key(self, first=False): + if not first and isinstance(self.event, MappingEndEvent): + self.indent = self.indents.pop() + self.state = self.states.pop() + else: + self.write_indent() + if self.check_simple_key(): + self.states.append(self.expect_block_mapping_simple_value) + self.expect_node(mapping=True, simple_key=True) + else: + self.write_indicator('?', True, indention=True) + self.states.append(self.expect_block_mapping_value) + self.expect_node(mapping=True) + + def expect_block_mapping_simple_value(self): + self.write_indicator(':', False) + self.states.append(self.expect_block_mapping_key) + self.expect_node(mapping=True) + + def expect_block_mapping_value(self): + self.write_indent() + self.write_indicator(':', True, indention=True) + self.states.append(self.expect_block_mapping_key) + self.expect_node(mapping=True) + + # Checkers. + + def check_empty_sequence(self): + return (isinstance(self.event, SequenceStartEvent) and self.events + and isinstance(self.events[0], SequenceEndEvent)) + + def check_empty_mapping(self): + return (isinstance(self.event, MappingStartEvent) and self.events + and isinstance(self.events[0], MappingEndEvent)) + + def check_empty_document(self): + if not isinstance(self.event, DocumentStartEvent) or not self.events: + return False + event = self.events[0] + return (isinstance(event, ScalarEvent) and event.anchor is None + and event.tag is None and event.implicit and event.value == '') + + def check_simple_key(self): + length = 0 + if isinstance(self.event, NodeEvent) and self.event.anchor is not None: + if self.prepared_anchor is None: + self.prepared_anchor = self.prepare_anchor(self.event.anchor) + length += len(self.prepared_anchor) + if isinstance(self.event, (ScalarEvent, CollectionStartEvent)) \ + and self.event.tag is not None: + if self.prepared_tag is None: + self.prepared_tag = self.prepare_tag(self.event.tag) + length += len(self.prepared_tag) + if isinstance(self.event, ScalarEvent): + if self.analysis is None: + self.analysis = self.analyze_scalar(self.event.value) + length += len(self.analysis.scalar) + return (length < 128 and (isinstance(self.event, AliasEvent) + or (isinstance(self.event, ScalarEvent) + and not self.analysis.empty and not self.analysis.multiline) + or self.check_empty_sequence() or self.check_empty_mapping())) + + # Anchor, Tag, and Scalar processors. + + def process_anchor(self, indicator): + if self.event.anchor is None: + self.prepared_anchor = None + return + if self.prepared_anchor is None: + self.prepared_anchor = self.prepare_anchor(self.event.anchor) + if self.prepared_anchor: + self.write_indicator(indicator+self.prepared_anchor, True) + self.prepared_anchor = None + + def process_tag(self): + tag = self.event.tag + if isinstance(self.event, ScalarEvent): + if self.style is None: + self.style = self.choose_scalar_style() + if ((not self.canonical or tag is None) and + ((self.style == '' and self.event.implicit[0]) + or (self.style != '' and self.event.implicit[1]))): + self.prepared_tag = None + return + if self.event.implicit[0] and tag is None: + tag = '!' + self.prepared_tag = None + else: + if (not self.canonical or tag is None) and self.event.implicit: + self.prepared_tag = None + return + if tag is None: + raise EmitterError("tag is not specified") + if self.prepared_tag is None: + self.prepared_tag = self.prepare_tag(tag) + if self.prepared_tag: + self.write_indicator(self.prepared_tag, True) + self.prepared_tag = None + + def choose_scalar_style(self): + if self.analysis is None: + self.analysis = self.analyze_scalar(self.event.value) + if self.event.style == '"' or self.canonical: + return '"' + if not self.event.style and self.event.implicit[0]: + if (not (self.simple_key_context and + (self.analysis.empty or self.analysis.multiline)) + and (self.flow_level and self.analysis.allow_flow_plain + or (not self.flow_level and self.analysis.allow_block_plain))): + return '' + if self.event.style and self.event.style in '|>': + if (not self.flow_level and not self.simple_key_context + and self.analysis.allow_block): + return self.event.style + if not self.event.style or self.event.style == '\'': + if (self.analysis.allow_single_quoted and + not (self.simple_key_context and self.analysis.multiline)): + return '\'' + return '"' + + def process_scalar(self): + if self.analysis is None: + self.analysis = self.analyze_scalar(self.event.value) + if self.style is None: + self.style = self.choose_scalar_style() + split = (not self.simple_key_context) + #if self.analysis.multiline and split \ + # and (not self.style or self.style in '\'\"'): + # self.write_indent() + if self.style == '"': + self.write_double_quoted(self.analysis.scalar, split) + elif self.style == '\'': + self.write_single_quoted(self.analysis.scalar, split) + elif self.style == '>': + self.write_folded(self.analysis.scalar) + elif self.style == '|': + self.write_literal(self.analysis.scalar) + else: + self.write_plain(self.analysis.scalar, split) + self.analysis = None + self.style = None + + # Analyzers. + + def prepare_version(self, version): + major, minor = version + if major != 1: + raise EmitterError("unsupported YAML version: %d.%d" % (major, minor)) + return '%d.%d' % (major, minor) + + def prepare_tag_handle(self, handle): + if not handle: + raise EmitterError("tag handle must not be empty") + if handle[0] != '!' or handle[-1] != '!': + raise EmitterError("tag handle must start and end with '!': %r" % handle) + for ch in handle[1:-1]: + if not ('0' <= ch <= '9' or 'A' <= ch <= 'Z' or 'a' <= ch <= 'z' \ + or ch in '-_'): + raise EmitterError("invalid character %r in the tag handle: %r" + % (ch, handle)) + return handle + + def prepare_tag_prefix(self, prefix): + if not prefix: + raise EmitterError("tag prefix must not be empty") + chunks = [] + start = end = 0 + if prefix[0] == '!': + end = 1 + while end < len(prefix): + ch = prefix[end] + if '0' <= ch <= '9' or 'A' <= ch <= 'Z' or 'a' <= ch <= 'z' \ + or ch in '-;/?!:@&=+$,_.~*\'()[]': + end += 1 + else: + if start < end: + chunks.append(prefix[start:end]) + start = end = end+1 + data = ch.encode('utf-8') + for ch in data: + chunks.append('%%%02X' % ord(ch)) + if start < end: + chunks.append(prefix[start:end]) + return ''.join(chunks) + + def prepare_tag(self, tag): + if not tag: + raise EmitterError("tag must not be empty") + if tag == '!': + return tag + handle = None + suffix = tag + prefixes = sorted(self.tag_prefixes.keys()) + for prefix in prefixes: + if tag.startswith(prefix) \ + and (prefix == '!' or len(prefix) < len(tag)): + handle = self.tag_prefixes[prefix] + suffix = tag[len(prefix):] + chunks = [] + start = end = 0 + while end < len(suffix): + ch = suffix[end] + if '0' <= ch <= '9' or 'A' <= ch <= 'Z' or 'a' <= ch <= 'z' \ + or ch in '-;/?:@&=+$,_.~*\'()[]' \ + or (ch == '!' and handle != '!'): + end += 1 + else: + if start < end: + chunks.append(suffix[start:end]) + start = end = end+1 + data = ch.encode('utf-8') + for ch in data: + chunks.append('%%%02X' % ord(ch)) + if start < end: + chunks.append(suffix[start:end]) + suffix_text = ''.join(chunks) + if handle: + return '%s%s' % (handle, suffix_text) + else: + return '!<%s>' % suffix_text + + def prepare_anchor(self, anchor): + if not anchor: + raise EmitterError("anchor must not be empty") + for ch in anchor: + if not ('0' <= ch <= '9' or 'A' <= ch <= 'Z' or 'a' <= ch <= 'z' \ + or ch in '-_'): + raise EmitterError("invalid character %r in the anchor: %r" + % (ch, anchor)) + return anchor + + def analyze_scalar(self, scalar): + + # Empty scalar is a special case. + if not scalar: + return ScalarAnalysis(scalar=scalar, empty=True, multiline=False, + allow_flow_plain=False, allow_block_plain=True, + allow_single_quoted=True, allow_double_quoted=True, + allow_block=False) + + # Indicators and special characters. + block_indicators = False + flow_indicators = False + line_breaks = False + special_characters = False + + # Important whitespace combinations. + leading_space = False + leading_break = False + trailing_space = False + trailing_break = False + break_space = False + space_break = False + + # Check document indicators. + if scalar.startswith('---') or scalar.startswith('...'): + block_indicators = True + flow_indicators = True + + # First character or preceded by a whitespace. + preceeded_by_whitespace = True + + # Last character or followed by a whitespace. + followed_by_whitespace = (len(scalar) == 1 or + scalar[1] in '\0 \t\r\n\x85\u2028\u2029') + + # The previous character is a space. + previous_space = False + + # The previous character is a break. + previous_break = False + + index = 0 + while index < len(scalar): + ch = scalar[index] + + # Check for indicators. + if index == 0: + # Leading indicators are special characters. + if ch in '#,[]{}&*!|>\'\"%@`': + flow_indicators = True + block_indicators = True + if ch in '?:': + flow_indicators = True + if followed_by_whitespace: + block_indicators = True + if ch == '-' and followed_by_whitespace: + flow_indicators = True + block_indicators = True + else: + # Some indicators cannot appear within a scalar as well. + if ch in ',?[]{}': + flow_indicators = True + if ch == ':': + flow_indicators = True + if followed_by_whitespace: + block_indicators = True + if ch == '#' and preceeded_by_whitespace: + flow_indicators = True + block_indicators = True + + # Check for line breaks, special, and unicode characters. + if ch in '\n\x85\u2028\u2029': + line_breaks = True + if not (ch == '\n' or '\x20' <= ch <= '\x7E'): + if (ch == '\x85' or '\xA0' <= ch <= '\uD7FF' + or '\uE000' <= ch <= '\uFFFD') and ch != '\uFEFF': + unicode_characters = True + if not self.allow_unicode: + special_characters = True + else: + special_characters = True + + # Detect important whitespace combinations. + if ch == ' ': + if index == 0: + leading_space = True + if index == len(scalar)-1: + trailing_space = True + if previous_break: + break_space = True + previous_space = True + previous_break = False + elif ch in '\n\x85\u2028\u2029': + if index == 0: + leading_break = True + if index == len(scalar)-1: + trailing_break = True + if previous_space: + space_break = True + previous_space = False + previous_break = True + else: + previous_space = False + previous_break = False + + # Prepare for the next character. + index += 1 + preceeded_by_whitespace = (ch in '\0 \t\r\n\x85\u2028\u2029') + followed_by_whitespace = (index+1 >= len(scalar) or + scalar[index+1] in '\0 \t\r\n\x85\u2028\u2029') + + # Let's decide what styles are allowed. + allow_flow_plain = True + allow_block_plain = True + allow_single_quoted = True + allow_double_quoted = True + allow_block = True + + # Leading and trailing whitespaces are bad for plain scalars. + if (leading_space or leading_break + or trailing_space or trailing_break): + allow_flow_plain = allow_block_plain = False + + # We do not permit trailing spaces for block scalars. + if trailing_space: + allow_block = False + + # Spaces at the beginning of a new line are only acceptable for block + # scalars. + if break_space: + allow_flow_plain = allow_block_plain = allow_single_quoted = False + + # Spaces followed by breaks, as well as special character are only + # allowed for double quoted scalars. + if space_break or special_characters: + allow_flow_plain = allow_block_plain = \ + allow_single_quoted = allow_block = False + + # Although the plain scalar writer supports breaks, we never emit + # multiline plain scalars. + if line_breaks: + allow_flow_plain = allow_block_plain = False + + # Flow indicators are forbidden for flow plain scalars. + if flow_indicators: + allow_flow_plain = False + + # Block indicators are forbidden for block plain scalars. + if block_indicators: + allow_block_plain = False + + return ScalarAnalysis(scalar=scalar, + empty=False, multiline=line_breaks, + allow_flow_plain=allow_flow_plain, + allow_block_plain=allow_block_plain, + allow_single_quoted=allow_single_quoted, + allow_double_quoted=allow_double_quoted, + allow_block=allow_block) + + # Writers. + + def flush_stream(self): + if hasattr(self.stream, 'flush'): + self.stream.flush() + + def write_stream_start(self): + # Write BOM if needed. + if self.encoding and self.encoding.startswith('utf-16'): + self.stream.write('\uFEFF'.encode(self.encoding)) + + def write_stream_end(self): + self.flush_stream() + + def write_indicator(self, indicator, need_whitespace, + whitespace=False, indention=False): + if self.whitespace or not need_whitespace: + data = indicator + else: + data = ' '+indicator + self.whitespace = whitespace + self.indention = self.indention and indention + self.column += len(data) + self.open_ended = False + if self.encoding: + data = data.encode(self.encoding) + self.stream.write(data) + + def write_indent(self): + indent = self.indent or 0 + if not self.indention or self.column > indent \ + or (self.column == indent and not self.whitespace): + self.write_line_break() + if self.column < indent: + self.whitespace = True + data = ' '*(indent-self.column) + self.column = indent + if self.encoding: + data = data.encode(self.encoding) + self.stream.write(data) + + def write_line_break(self, data=None): + if data is None: + data = self.best_line_break + self.whitespace = True + self.indention = True + self.line += 1 + self.column = 0 + if self.encoding: + data = data.encode(self.encoding) + self.stream.write(data) + + def write_version_directive(self, version_text): + data = '%%YAML %s' % version_text + if self.encoding: + data = data.encode(self.encoding) + self.stream.write(data) + self.write_line_break() + + def write_tag_directive(self, handle_text, prefix_text): + data = '%%TAG %s %s' % (handle_text, prefix_text) + if self.encoding: + data = data.encode(self.encoding) + self.stream.write(data) + self.write_line_break() + + # Scalar streams. + + def write_single_quoted(self, text, split=True): + self.write_indicator('\'', True) + spaces = False + breaks = False + start = end = 0 + while end <= len(text): + ch = None + if end < len(text): + ch = text[end] + if spaces: + if ch is None or ch != ' ': + if start+1 == end and self.column > self.best_width and split \ + and start != 0 and end != len(text): + self.write_indent() + else: + data = text[start:end] + self.column += len(data) + if self.encoding: + data = data.encode(self.encoding) + self.stream.write(data) + start = end + elif breaks: + if ch is None or ch not in '\n\x85\u2028\u2029': + if text[start] == '\n': + self.write_line_break() + for br in text[start:end]: + if br == '\n': + self.write_line_break() + else: + self.write_line_break(br) + self.write_indent() + start = end + else: + if ch is None or ch in ' \n\x85\u2028\u2029' or ch == '\'': + if start < end: + data = text[start:end] + self.column += len(data) + if self.encoding: + data = data.encode(self.encoding) + self.stream.write(data) + start = end + if ch == '\'': + data = '\'\'' + self.column += 2 + if self.encoding: + data = data.encode(self.encoding) + self.stream.write(data) + start = end + 1 + if ch is not None: + spaces = (ch == ' ') + breaks = (ch in '\n\x85\u2028\u2029') + end += 1 + self.write_indicator('\'', False) + + ESCAPE_REPLACEMENTS = { + '\0': '0', + '\x07': 'a', + '\x08': 'b', + '\x09': 't', + '\x0A': 'n', + '\x0B': 'v', + '\x0C': 'f', + '\x0D': 'r', + '\x1B': 'e', + '\"': '\"', + '\\': '\\', + '\x85': 'N', + '\xA0': '_', + '\u2028': 'L', + '\u2029': 'P', + } + + def write_double_quoted(self, text, split=True): + self.write_indicator('"', True) + start = end = 0 + while end <= len(text): + ch = None + if end < len(text): + ch = text[end] + if ch is None or ch in '"\\\x85\u2028\u2029\uFEFF' \ + or not ('\x20' <= ch <= '\x7E' + or (self.allow_unicode + and ('\xA0' <= ch <= '\uD7FF' + or '\uE000' <= ch <= '\uFFFD'))): + if start < end: + data = text[start:end] + self.column += len(data) + if self.encoding: + data = data.encode(self.encoding) + self.stream.write(data) + start = end + if ch is not None: + if ch in self.ESCAPE_REPLACEMENTS: + data = '\\'+self.ESCAPE_REPLACEMENTS[ch] + elif ch <= '\xFF': + data = '\\x%02X' % ord(ch) + elif ch <= '\uFFFF': + data = '\\u%04X' % ord(ch) + else: + data = '\\U%08X' % ord(ch) + self.column += len(data) + if self.encoding: + data = data.encode(self.encoding) + self.stream.write(data) + start = end+1 + if 0 < end < len(text)-1 and (ch == ' ' or start >= end) \ + and self.column+(end-start) > self.best_width and split: + data = text[start:end]+'\\' + if start < end: + start = end + self.column += len(data) + if self.encoding: + data = data.encode(self.encoding) + self.stream.write(data) + self.write_indent() + self.whitespace = False + self.indention = False + if text[start] == ' ': + data = '\\' + self.column += len(data) + if self.encoding: + data = data.encode(self.encoding) + self.stream.write(data) + end += 1 + self.write_indicator('"', False) + + def determine_block_hints(self, text): + hints = '' + if text: + if text[0] in ' \n\x85\u2028\u2029': + hints += str(self.best_indent) + if text[-1] not in '\n\x85\u2028\u2029': + hints += '-' + elif len(text) == 1 or text[-2] in '\n\x85\u2028\u2029': + hints += '+' + return hints + + def write_folded(self, text): + hints = self.determine_block_hints(text) + self.write_indicator('>'+hints, True) + if hints[-1:] == '+': + self.open_ended = True + self.write_line_break() + leading_space = True + spaces = False + breaks = True + start = end = 0 + while end <= len(text): + ch = None + if end < len(text): + ch = text[end] + if breaks: + if ch is None or ch not in '\n\x85\u2028\u2029': + if not leading_space and ch is not None and ch != ' ' \ + and text[start] == '\n': + self.write_line_break() + leading_space = (ch == ' ') + for br in text[start:end]: + if br == '\n': + self.write_line_break() + else: + self.write_line_break(br) + if ch is not None: + self.write_indent() + start = end + elif spaces: + if ch != ' ': + if start+1 == end and self.column > self.best_width: + self.write_indent() + else: + data = text[start:end] + self.column += len(data) + if self.encoding: + data = data.encode(self.encoding) + self.stream.write(data) + start = end + else: + if ch is None or ch in ' \n\x85\u2028\u2029': + data = text[start:end] + self.column += len(data) + if self.encoding: + data = data.encode(self.encoding) + self.stream.write(data) + if ch is None: + self.write_line_break() + start = end + if ch is not None: + breaks = (ch in '\n\x85\u2028\u2029') + spaces = (ch == ' ') + end += 1 + + def write_literal(self, text): + hints = self.determine_block_hints(text) + self.write_indicator('|'+hints, True) + if hints[-1:] == '+': + self.open_ended = True + self.write_line_break() + breaks = True + start = end = 0 + while end <= len(text): + ch = None + if end < len(text): + ch = text[end] + if breaks: + if ch is None or ch not in '\n\x85\u2028\u2029': + for br in text[start:end]: + if br == '\n': + self.write_line_break() + else: + self.write_line_break(br) + if ch is not None: + self.write_indent() + start = end + else: + if ch is None or ch in '\n\x85\u2028\u2029': + data = text[start:end] + if self.encoding: + data = data.encode(self.encoding) + self.stream.write(data) + if ch is None: + self.write_line_break() + start = end + if ch is not None: + breaks = (ch in '\n\x85\u2028\u2029') + end += 1 + + def write_plain(self, text, split=True): + if self.root_context: + self.open_ended = True + if not text: + return + if not self.whitespace: + data = ' ' + self.column += len(data) + if self.encoding: + data = data.encode(self.encoding) + self.stream.write(data) + self.whitespace = False + self.indention = False + spaces = False + breaks = False + start = end = 0 + while end <= len(text): + ch = None + if end < len(text): + ch = text[end] + if spaces: + if ch != ' ': + if start+1 == end and self.column > self.best_width and split: + self.write_indent() + self.whitespace = False + self.indention = False + else: + data = text[start:end] + self.column += len(data) + if self.encoding: + data = data.encode(self.encoding) + self.stream.write(data) + start = end + elif breaks: + if ch not in '\n\x85\u2028\u2029': + if text[start] == '\n': + self.write_line_break() + for br in text[start:end]: + if br == '\n': + self.write_line_break() + else: + self.write_line_break(br) + self.write_indent() + self.whitespace = False + self.indention = False + start = end + else: + if ch is None or ch in ' \n\x85\u2028\u2029': + data = text[start:end] + self.column += len(data) + if self.encoding: + data = data.encode(self.encoding) + self.stream.write(data) + start = end + if ch is not None: + spaces = (ch == ' ') + breaks = (ch in '\n\x85\u2028\u2029') + end += 1 + diff --git a/python.d/python_modules/pyyaml3/error.py b/python.d/python_modules/pyyaml3/error.py new file mode 100644 index 00000000..b796b4dc --- /dev/null +++ b/python.d/python_modules/pyyaml3/error.py @@ -0,0 +1,75 @@ + +__all__ = ['Mark', 'YAMLError', 'MarkedYAMLError'] + +class Mark: + + def __init__(self, name, index, line, column, buffer, pointer): + self.name = name + self.index = index + self.line = line + self.column = column + self.buffer = buffer + self.pointer = pointer + + def get_snippet(self, indent=4, max_length=75): + if self.buffer is None: + return None + head = '' + start = self.pointer + while start > 0 and self.buffer[start-1] not in '\0\r\n\x85\u2028\u2029': + start -= 1 + if self.pointer-start > max_length/2-1: + head = ' ... ' + start += 5 + break + tail = '' + end = self.pointer + while end < len(self.buffer) and self.buffer[end] not in '\0\r\n\x85\u2028\u2029': + end += 1 + if end-self.pointer > max_length/2-1: + tail = ' ... ' + end -= 5 + break + snippet = self.buffer[start:end] + return ' '*indent + head + snippet + tail + '\n' \ + + ' '*(indent+self.pointer-start+len(head)) + '^' + + def __str__(self): + snippet = self.get_snippet() + where = " in \"%s\", line %d, column %d" \ + % (self.name, self.line+1, self.column+1) + if snippet is not None: + where += ":\n"+snippet + return where + +class YAMLError(Exception): + pass + +class MarkedYAMLError(YAMLError): + + def __init__(self, context=None, context_mark=None, + problem=None, problem_mark=None, note=None): + self.context = context + self.context_mark = context_mark + self.problem = problem + self.problem_mark = problem_mark + self.note = note + + def __str__(self): + lines = [] + if self.context is not None: + lines.append(self.context) + if self.context_mark is not None \ + and (self.problem is None or self.problem_mark is None + or self.context_mark.name != self.problem_mark.name + or self.context_mark.line != self.problem_mark.line + or self.context_mark.column != self.problem_mark.column): + lines.append(str(self.context_mark)) + if self.problem is not None: + lines.append(self.problem) + if self.problem_mark is not None: + lines.append(str(self.problem_mark)) + if self.note is not None: + lines.append(self.note) + return '\n'.join(lines) + diff --git a/python.d/python_modules/pyyaml3/events.py b/python.d/python_modules/pyyaml3/events.py new file mode 100644 index 00000000..f79ad389 --- /dev/null +++ b/python.d/python_modules/pyyaml3/events.py @@ -0,0 +1,86 @@ + +# Abstract classes. + +class Event(object): + def __init__(self, start_mark=None, end_mark=None): + self.start_mark = start_mark + self.end_mark = end_mark + def __repr__(self): + attributes = [key for key in ['anchor', 'tag', 'implicit', 'value'] + if hasattr(self, key)] + arguments = ', '.join(['%s=%r' % (key, getattr(self, key)) + for key in attributes]) + return '%s(%s)' % (self.__class__.__name__, arguments) + +class NodeEvent(Event): + def __init__(self, anchor, start_mark=None, end_mark=None): + self.anchor = anchor + self.start_mark = start_mark + self.end_mark = end_mark + +class CollectionStartEvent(NodeEvent): + def __init__(self, anchor, tag, implicit, start_mark=None, end_mark=None, + flow_style=None): + self.anchor = anchor + self.tag = tag + self.implicit = implicit + self.start_mark = start_mark + self.end_mark = end_mark + self.flow_style = flow_style + +class CollectionEndEvent(Event): + pass + +# Implementations. + +class StreamStartEvent(Event): + def __init__(self, start_mark=None, end_mark=None, encoding=None): + self.start_mark = start_mark + self.end_mark = end_mark + self.encoding = encoding + +class StreamEndEvent(Event): + pass + +class DocumentStartEvent(Event): + def __init__(self, start_mark=None, end_mark=None, + explicit=None, version=None, tags=None): + self.start_mark = start_mark + self.end_mark = end_mark + self.explicit = explicit + self.version = version + self.tags = tags + +class DocumentEndEvent(Event): + def __init__(self, start_mark=None, end_mark=None, + explicit=None): + self.start_mark = start_mark + self.end_mark = end_mark + self.explicit = explicit + +class AliasEvent(NodeEvent): + pass + +class ScalarEvent(NodeEvent): + def __init__(self, anchor, tag, implicit, value, + start_mark=None, end_mark=None, style=None): + self.anchor = anchor + self.tag = tag + self.implicit = implicit + self.value = value + self.start_mark = start_mark + self.end_mark = end_mark + self.style = style + +class SequenceStartEvent(CollectionStartEvent): + pass + +class SequenceEndEvent(CollectionEndEvent): + pass + +class MappingStartEvent(CollectionStartEvent): + pass + +class MappingEndEvent(CollectionEndEvent): + pass + diff --git a/python.d/python_modules/pyyaml3/loader.py b/python.d/python_modules/pyyaml3/loader.py new file mode 100644 index 00000000..08c8f01b --- /dev/null +++ b/python.d/python_modules/pyyaml3/loader.py @@ -0,0 +1,40 @@ + +__all__ = ['BaseLoader', 'SafeLoader', 'Loader'] + +from .reader import * +from .scanner import * +from .parser import * +from .composer import * +from .constructor import * +from .resolver import * + +class BaseLoader(Reader, Scanner, Parser, Composer, BaseConstructor, BaseResolver): + + def __init__(self, stream): + Reader.__init__(self, stream) + Scanner.__init__(self) + Parser.__init__(self) + Composer.__init__(self) + BaseConstructor.__init__(self) + BaseResolver.__init__(self) + +class SafeLoader(Reader, Scanner, Parser, Composer, SafeConstructor, Resolver): + + def __init__(self, stream): + Reader.__init__(self, stream) + Scanner.__init__(self) + Parser.__init__(self) + Composer.__init__(self) + SafeConstructor.__init__(self) + Resolver.__init__(self) + +class Loader(Reader, Scanner, Parser, Composer, Constructor, Resolver): + + def __init__(self, stream): + Reader.__init__(self, stream) + Scanner.__init__(self) + Parser.__init__(self) + Composer.__init__(self) + Constructor.__init__(self) + Resolver.__init__(self) + diff --git a/python.d/python_modules/pyyaml3/nodes.py b/python.d/python_modules/pyyaml3/nodes.py new file mode 100644 index 00000000..c4f070c4 --- /dev/null +++ b/python.d/python_modules/pyyaml3/nodes.py @@ -0,0 +1,49 @@ + +class Node(object): + def __init__(self, tag, value, start_mark, end_mark): + self.tag = tag + self.value = value + self.start_mark = start_mark + self.end_mark = end_mark + def __repr__(self): + value = self.value + #if isinstance(value, list): + # if len(value) == 0: + # value = '<empty>' + # elif len(value) == 1: + # value = '<1 item>' + # else: + # value = '<%d items>' % len(value) + #else: + # if len(value) > 75: + # value = repr(value[:70]+u' ... ') + # else: + # value = repr(value) + value = repr(value) + return '%s(tag=%r, value=%s)' % (self.__class__.__name__, self.tag, value) + +class ScalarNode(Node): + id = 'scalar' + def __init__(self, tag, value, + start_mark=None, end_mark=None, style=None): + self.tag = tag + self.value = value + self.start_mark = start_mark + self.end_mark = end_mark + self.style = style + +class CollectionNode(Node): + def __init__(self, tag, value, + start_mark=None, end_mark=None, flow_style=None): + self.tag = tag + self.value = value + self.start_mark = start_mark + self.end_mark = end_mark + self.flow_style = flow_style + +class SequenceNode(CollectionNode): + id = 'sequence' + +class MappingNode(CollectionNode): + id = 'mapping' + diff --git a/python.d/python_modules/pyyaml3/parser.py b/python.d/python_modules/pyyaml3/parser.py new file mode 100644 index 00000000..13a5995d --- /dev/null +++ b/python.d/python_modules/pyyaml3/parser.py @@ -0,0 +1,589 @@ + +# The following YAML grammar is LL(1) and is parsed by a recursive descent +# parser. +# +# stream ::= STREAM-START implicit_document? explicit_document* STREAM-END +# implicit_document ::= block_node DOCUMENT-END* +# explicit_document ::= DIRECTIVE* DOCUMENT-START block_node? DOCUMENT-END* +# block_node_or_indentless_sequence ::= +# ALIAS +# | properties (block_content | indentless_block_sequence)? +# | block_content +# | indentless_block_sequence +# block_node ::= ALIAS +# | properties block_content? +# | block_content +# flow_node ::= ALIAS +# | properties flow_content? +# | flow_content +# properties ::= TAG ANCHOR? | ANCHOR TAG? +# block_content ::= block_collection | flow_collection | SCALAR +# flow_content ::= flow_collection | SCALAR +# block_collection ::= block_sequence | block_mapping +# flow_collection ::= flow_sequence | flow_mapping +# block_sequence ::= BLOCK-SEQUENCE-START (BLOCK-ENTRY block_node?)* BLOCK-END +# indentless_sequence ::= (BLOCK-ENTRY block_node?)+ +# block_mapping ::= BLOCK-MAPPING_START +# ((KEY block_node_or_indentless_sequence?)? +# (VALUE block_node_or_indentless_sequence?)?)* +# BLOCK-END +# flow_sequence ::= FLOW-SEQUENCE-START +# (flow_sequence_entry FLOW-ENTRY)* +# flow_sequence_entry? +# FLOW-SEQUENCE-END +# flow_sequence_entry ::= flow_node | KEY flow_node? (VALUE flow_node?)? +# flow_mapping ::= FLOW-MAPPING-START +# (flow_mapping_entry FLOW-ENTRY)* +# flow_mapping_entry? +# FLOW-MAPPING-END +# flow_mapping_entry ::= flow_node | KEY flow_node? (VALUE flow_node?)? +# +# FIRST sets: +# +# stream: { STREAM-START } +# explicit_document: { DIRECTIVE DOCUMENT-START } +# implicit_document: FIRST(block_node) +# block_node: { ALIAS TAG ANCHOR SCALAR BLOCK-SEQUENCE-START BLOCK-MAPPING-START FLOW-SEQUENCE-START FLOW-MAPPING-START } +# flow_node: { ALIAS ANCHOR TAG SCALAR FLOW-SEQUENCE-START FLOW-MAPPING-START } +# block_content: { BLOCK-SEQUENCE-START BLOCK-MAPPING-START FLOW-SEQUENCE-START FLOW-MAPPING-START SCALAR } +# flow_content: { FLOW-SEQUENCE-START FLOW-MAPPING-START SCALAR } +# block_collection: { BLOCK-SEQUENCE-START BLOCK-MAPPING-START } +# flow_collection: { FLOW-SEQUENCE-START FLOW-MAPPING-START } +# block_sequence: { BLOCK-SEQUENCE-START } +# block_mapping: { BLOCK-MAPPING-START } +# block_node_or_indentless_sequence: { ALIAS ANCHOR TAG SCALAR BLOCK-SEQUENCE-START BLOCK-MAPPING-START FLOW-SEQUENCE-START FLOW-MAPPING-START BLOCK-ENTRY } +# indentless_sequence: { ENTRY } +# flow_collection: { FLOW-SEQUENCE-START FLOW-MAPPING-START } +# flow_sequence: { FLOW-SEQUENCE-START } +# flow_mapping: { FLOW-MAPPING-START } +# flow_sequence_entry: { ALIAS ANCHOR TAG SCALAR FLOW-SEQUENCE-START FLOW-MAPPING-START KEY } +# flow_mapping_entry: { ALIAS ANCHOR TAG SCALAR FLOW-SEQUENCE-START FLOW-MAPPING-START KEY } + +__all__ = ['Parser', 'ParserError'] + +from .error import MarkedYAMLError +from .tokens import * +from .events import * +from .scanner import * + +class ParserError(MarkedYAMLError): + pass + +class Parser: + # Since writing a recursive-descendant parser is a straightforward task, we + # do not give many comments here. + + DEFAULT_TAGS = { + '!': '!', + '!!': 'tag:yaml.org,2002:', + } + + def __init__(self): + self.current_event = None + self.yaml_version = None + self.tag_handles = {} + self.states = [] + self.marks = [] + self.state = self.parse_stream_start + + def dispose(self): + # Reset the state attributes (to clear self-references) + self.states = [] + self.state = None + + def check_event(self, *choices): + # Check the type of the next event. + if self.current_event is None: + if self.state: + self.current_event = self.state() + if self.current_event is not None: + if not choices: + return True + for choice in choices: + if isinstance(self.current_event, choice): + return True + return False + + def peek_event(self): + # Get the next event. + if self.current_event is None: + if self.state: + self.current_event = self.state() + return self.current_event + + def get_event(self): + # Get the next event and proceed further. + if self.current_event is None: + if self.state: + self.current_event = self.state() + value = self.current_event + self.current_event = None + return value + + # stream ::= STREAM-START implicit_document? explicit_document* STREAM-END + # implicit_document ::= block_node DOCUMENT-END* + # explicit_document ::= DIRECTIVE* DOCUMENT-START block_node? DOCUMENT-END* + + def parse_stream_start(self): + + # Parse the stream start. + token = self.get_token() + event = StreamStartEvent(token.start_mark, token.end_mark, + encoding=token.encoding) + + # Prepare the next state. + self.state = self.parse_implicit_document_start + + return event + + def parse_implicit_document_start(self): + + # Parse an implicit document. + if not self.check_token(DirectiveToken, DocumentStartToken, + StreamEndToken): + self.tag_handles = self.DEFAULT_TAGS + token = self.peek_token() + start_mark = end_mark = token.start_mark + event = DocumentStartEvent(start_mark, end_mark, + explicit=False) + + # Prepare the next state. + self.states.append(self.parse_document_end) + self.state = self.parse_block_node + + return event + + else: + return self.parse_document_start() + + def parse_document_start(self): + + # Parse any extra document end indicators. + while self.check_token(DocumentEndToken): + self.get_token() + + # Parse an explicit document. + if not self.check_token(StreamEndToken): + token = self.peek_token() + start_mark = token.start_mark + version, tags = self.process_directives() + if not self.check_token(DocumentStartToken): + raise ParserError(None, None, + "expected '<document start>', but found %r" + % self.peek_token().id, + self.peek_token().start_mark) + token = self.get_token() + end_mark = token.end_mark + event = DocumentStartEvent(start_mark, end_mark, + explicit=True, version=version, tags=tags) + self.states.append(self.parse_document_end) + self.state = self.parse_document_content + else: + # Parse the end of the stream. + token = self.get_token() + event = StreamEndEvent(token.start_mark, token.end_mark) + assert not self.states + assert not self.marks + self.state = None + return event + + def parse_document_end(self): + + # Parse the document end. + token = self.peek_token() + start_mark = end_mark = token.start_mark + explicit = False + if self.check_token(DocumentEndToken): + token = self.get_token() + end_mark = token.end_mark + explicit = True + event = DocumentEndEvent(start_mark, end_mark, + explicit=explicit) + + # Prepare the next state. + self.state = self.parse_document_start + + return event + + def parse_document_content(self): + if self.check_token(DirectiveToken, + DocumentStartToken, DocumentEndToken, StreamEndToken): + event = self.process_empty_scalar(self.peek_token().start_mark) + self.state = self.states.pop() + return event + else: + return self.parse_block_node() + + def process_directives(self): + self.yaml_version = None + self.tag_handles = {} + while self.check_token(DirectiveToken): + token = self.get_token() + if token.name == 'YAML': + if self.yaml_version is not None: + raise ParserError(None, None, + "found duplicate YAML directive", token.start_mark) + major, minor = token.value + if major != 1: + raise ParserError(None, None, + "found incompatible YAML document (version 1.* is required)", + token.start_mark) + self.yaml_version = token.value + elif token.name == 'TAG': + handle, prefix = token.value + if handle in self.tag_handles: + raise ParserError(None, None, + "duplicate tag handle %r" % handle, + token.start_mark) + self.tag_handles[handle] = prefix + if self.tag_handles: + value = self.yaml_version, self.tag_handles.copy() + else: + value = self.yaml_version, None + for key in self.DEFAULT_TAGS: + if key not in self.tag_handles: + self.tag_handles[key] = self.DEFAULT_TAGS[key] + return value + + # block_node_or_indentless_sequence ::= ALIAS + # | properties (block_content | indentless_block_sequence)? + # | block_content + # | indentless_block_sequence + # block_node ::= ALIAS + # | properties block_content? + # | block_content + # flow_node ::= ALIAS + # | properties flow_content? + # | flow_content + # properties ::= TAG ANCHOR? | ANCHOR TAG? + # block_content ::= block_collection | flow_collection | SCALAR + # flow_content ::= flow_collection | SCALAR + # block_collection ::= block_sequence | block_mapping + # flow_collection ::= flow_sequence | flow_mapping + + def parse_block_node(self): + return self.parse_node(block=True) + + def parse_flow_node(self): + return self.parse_node() + + def parse_block_node_or_indentless_sequence(self): + return self.parse_node(block=True, indentless_sequence=True) + + def parse_node(self, block=False, indentless_sequence=False): + if self.check_token(AliasToken): + token = self.get_token() + event = AliasEvent(token.value, token.start_mark, token.end_mark) + self.state = self.states.pop() + else: + anchor = None + tag = None + start_mark = end_mark = tag_mark = None + if self.check_token(AnchorToken): + token = self.get_token() + start_mark = token.start_mark + end_mark = token.end_mark + anchor = token.value + if self.check_token(TagToken): + token = self.get_token() + tag_mark = token.start_mark + end_mark = token.end_mark + tag = token.value + elif self.check_token(TagToken): + token = self.get_token() + start_mark = tag_mark = token.start_mark + end_mark = token.end_mark + tag = token.value + if self.check_token(AnchorToken): + token = self.get_token() + end_mark = token.end_mark + anchor = token.value + if tag is not None: + handle, suffix = tag + if handle is not None: + if handle not in self.tag_handles: + raise ParserError("while parsing a node", start_mark, + "found undefined tag handle %r" % handle, + tag_mark) + tag = self.tag_handles[handle]+suffix + else: + tag = suffix + #if tag == '!': + # raise ParserError("while parsing a node", start_mark, + # "found non-specific tag '!'", tag_mark, + # "Please check 'http://pyyaml.org/wiki/YAMLNonSpecificTag' and share your opinion.") + if start_mark is None: + start_mark = end_mark = self.peek_token().start_mark + event = None + implicit = (tag is None or tag == '!') + if indentless_sequence and self.check_token(BlockEntryToken): + end_mark = self.peek_token().end_mark + event = SequenceStartEvent(anchor, tag, implicit, + start_mark, end_mark) + self.state = self.parse_indentless_sequence_entry + else: + if self.check_token(ScalarToken): + token = self.get_token() + end_mark = token.end_mark + if (token.plain and tag is None) or tag == '!': + implicit = (True, False) + elif tag is None: + implicit = (False, True) + else: + implicit = (False, False) + event = ScalarEvent(anchor, tag, implicit, token.value, + start_mark, end_mark, style=token.style) + self.state = self.states.pop() + elif self.check_token(FlowSequenceStartToken): + end_mark = self.peek_token().end_mark + event = SequenceStartEvent(anchor, tag, implicit, + start_mark, end_mark, flow_style=True) + self.state = self.parse_flow_sequence_first_entry + elif self.check_token(FlowMappingStartToken): + end_mark = self.peek_token().end_mark + event = MappingStartEvent(anchor, tag, implicit, + start_mark, end_mark, flow_style=True) + self.state = self.parse_flow_mapping_first_key + elif block and self.check_token(BlockSequenceStartToken): + end_mark = self.peek_token().start_mark + event = SequenceStartEvent(anchor, tag, implicit, + start_mark, end_mark, flow_style=False) + self.state = self.parse_block_sequence_first_entry + elif block and self.check_token(BlockMappingStartToken): + end_mark = self.peek_token().start_mark + event = MappingStartEvent(anchor, tag, implicit, + start_mark, end_mark, flow_style=False) + self.state = self.parse_block_mapping_first_key + elif anchor is not None or tag is not None: + # Empty scalars are allowed even if a tag or an anchor is + # specified. + event = ScalarEvent(anchor, tag, (implicit, False), '', + start_mark, end_mark) + self.state = self.states.pop() + else: + if block: + node = 'block' + else: + node = 'flow' + token = self.peek_token() + raise ParserError("while parsing a %s node" % node, start_mark, + "expected the node content, but found %r" % token.id, + token.start_mark) + return event + + # block_sequence ::= BLOCK-SEQUENCE-START (BLOCK-ENTRY block_node?)* BLOCK-END + + def parse_block_sequence_first_entry(self): + token = self.get_token() + self.marks.append(token.start_mark) + return self.parse_block_sequence_entry() + + def parse_block_sequence_entry(self): + if self.check_token(BlockEntryToken): + token = self.get_token() + if not self.check_token(BlockEntryToken, BlockEndToken): + self.states.append(self.parse_block_sequence_entry) + return self.parse_block_node() + else: + self.state = self.parse_block_sequence_entry + return self.process_empty_scalar(token.end_mark) + if not self.check_token(BlockEndToken): + token = self.peek_token() + raise ParserError("while parsing a block collection", self.marks[-1], + "expected <block end>, but found %r" % token.id, token.start_mark) + token = self.get_token() + event = SequenceEndEvent(token.start_mark, token.end_mark) + self.state = self.states.pop() + self.marks.pop() + return event + + # indentless_sequence ::= (BLOCK-ENTRY block_node?)+ + + def parse_indentless_sequence_entry(self): + if self.check_token(BlockEntryToken): + token = self.get_token() + if not self.check_token(BlockEntryToken, + KeyToken, ValueToken, BlockEndToken): + self.states.append(self.parse_indentless_sequence_entry) + return self.parse_block_node() + else: + self.state = self.parse_indentless_sequence_entry + return self.process_empty_scalar(token.end_mark) + token = self.peek_token() + event = SequenceEndEvent(token.start_mark, token.start_mark) + self.state = self.states.pop() + return event + + # block_mapping ::= BLOCK-MAPPING_START + # ((KEY block_node_or_indentless_sequence?)? + # (VALUE block_node_or_indentless_sequence?)?)* + # BLOCK-END + + def parse_block_mapping_first_key(self): + token = self.get_token() + self.marks.append(token.start_mark) + return self.parse_block_mapping_key() + + def parse_block_mapping_key(self): + if self.check_token(KeyToken): + token = self.get_token() + if not self.check_token(KeyToken, ValueToken, BlockEndToken): + self.states.append(self.parse_block_mapping_value) + return self.parse_block_node_or_indentless_sequence() + else: + self.state = self.parse_block_mapping_value + return self.process_empty_scalar(token.end_mark) + if not self.check_token(BlockEndToken): + token = self.peek_token() + raise ParserError("while parsing a block mapping", self.marks[-1], + "expected <block end>, but found %r" % token.id, token.start_mark) + token = self.get_token() + event = MappingEndEvent(token.start_mark, token.end_mark) + self.state = self.states.pop() + self.marks.pop() + return event + + def parse_block_mapping_value(self): + if self.check_token(ValueToken): + token = self.get_token() + if not self.check_token(KeyToken, ValueToken, BlockEndToken): + self.states.append(self.parse_block_mapping_key) + return self.parse_block_node_or_indentless_sequence() + else: + self.state = self.parse_block_mapping_key + return self.process_empty_scalar(token.end_mark) + else: + self.state = self.parse_block_mapping_key + token = self.peek_token() + return self.process_empty_scalar(token.start_mark) + + # flow_sequence ::= FLOW-SEQUENCE-START + # (flow_sequence_entry FLOW-ENTRY)* + # flow_sequence_entry? + # FLOW-SEQUENCE-END + # flow_sequence_entry ::= flow_node | KEY flow_node? (VALUE flow_node?)? + # + # Note that while production rules for both flow_sequence_entry and + # flow_mapping_entry are equal, their interpretations are different. + # For `flow_sequence_entry`, the part `KEY flow_node? (VALUE flow_node?)?` + # generate an inline mapping (set syntax). + + def parse_flow_sequence_first_entry(self): + token = self.get_token() + self.marks.append(token.start_mark) + return self.parse_flow_sequence_entry(first=True) + + def parse_flow_sequence_entry(self, first=False): + if not self.check_token(FlowSequenceEndToken): + if not first: + if self.check_token(FlowEntryToken): + self.get_token() + else: + token = self.peek_token() + raise ParserError("while parsing a flow sequence", self.marks[-1], + "expected ',' or ']', but got %r" % token.id, token.start_mark) + + if self.check_token(KeyToken): + token = self.peek_token() + event = MappingStartEvent(None, None, True, + token.start_mark, token.end_mark, + flow_style=True) + self.state = self.parse_flow_sequence_entry_mapping_key + return event + elif not self.check_token(FlowSequenceEndToken): + self.states.append(self.parse_flow_sequence_entry) + return self.parse_flow_node() + token = self.get_token() + event = SequenceEndEvent(token.start_mark, token.end_mark) + self.state = self.states.pop() + self.marks.pop() + return event + + def parse_flow_sequence_entry_mapping_key(self): + token = self.get_token() + if not self.check_token(ValueToken, + FlowEntryToken, FlowSequenceEndToken): + self.states.append(self.parse_flow_sequence_entry_mapping_value) + return self.parse_flow_node() + else: + self.state = self.parse_flow_sequence_entry_mapping_value + return self.process_empty_scalar(token.end_mark) + + def parse_flow_sequence_entry_mapping_value(self): + if self.check_token(ValueToken): + token = self.get_token() + if not self.check_token(FlowEntryToken, FlowSequenceEndToken): + self.states.append(self.parse_flow_sequence_entry_mapping_end) + return self.parse_flow_node() + else: + self.state = self.parse_flow_sequence_entry_mapping_end + return self.process_empty_scalar(token.end_mark) + else: + self.state = self.parse_flow_sequence_entry_mapping_end + token = self.peek_token() + return self.process_empty_scalar(token.start_mark) + + def parse_flow_sequence_entry_mapping_end(self): + self.state = self.parse_flow_sequence_entry + token = self.peek_token() + return MappingEndEvent(token.start_mark, token.start_mark) + + # flow_mapping ::= FLOW-MAPPING-START + # (flow_mapping_entry FLOW-ENTRY)* + # flow_mapping_entry? + # FLOW-MAPPING-END + # flow_mapping_entry ::= flow_node | KEY flow_node? (VALUE flow_node?)? + + def parse_flow_mapping_first_key(self): + token = self.get_token() + self.marks.append(token.start_mark) + return self.parse_flow_mapping_key(first=True) + + def parse_flow_mapping_key(self, first=False): + if not self.check_token(FlowMappingEndToken): + if not first: + if self.check_token(FlowEntryToken): + self.get_token() + else: + token = self.peek_token() + raise ParserError("while parsing a flow mapping", self.marks[-1], + "expected ',' or '}', but got %r" % token.id, token.start_mark) + if self.check_token(KeyToken): + token = self.get_token() + if not self.check_token(ValueToken, + FlowEntryToken, FlowMappingEndToken): + self.states.append(self.parse_flow_mapping_value) + return self.parse_flow_node() + else: + self.state = self.parse_flow_mapping_value + return self.process_empty_scalar(token.end_mark) + elif not self.check_token(FlowMappingEndToken): + self.states.append(self.parse_flow_mapping_empty_value) + return self.parse_flow_node() + token = self.get_token() + event = MappingEndEvent(token.start_mark, token.end_mark) + self.state = self.states.pop() + self.marks.pop() + return event + + def parse_flow_mapping_value(self): + if self.check_token(ValueToken): + token = self.get_token() + if not self.check_token(FlowEntryToken, FlowMappingEndToken): + self.states.append(self.parse_flow_mapping_key) + return self.parse_flow_node() + else: + self.state = self.parse_flow_mapping_key + return self.process_empty_scalar(token.end_mark) + else: + self.state = self.parse_flow_mapping_key + token = self.peek_token() + return self.process_empty_scalar(token.start_mark) + + def parse_flow_mapping_empty_value(self): + self.state = self.parse_flow_mapping_key + return self.process_empty_scalar(self.peek_token().start_mark) + + def process_empty_scalar(self, mark): + return ScalarEvent(None, None, (True, False), '', mark, mark) + diff --git a/python.d/python_modules/pyyaml3/reader.py b/python.d/python_modules/pyyaml3/reader.py new file mode 100644 index 00000000..f70e920f --- /dev/null +++ b/python.d/python_modules/pyyaml3/reader.py @@ -0,0 +1,192 @@ +# This module contains abstractions for the input stream. You don't have to +# looks further, there are no pretty code. +# +# We define two classes here. +# +# Mark(source, line, column) +# It's just a record and its only use is producing nice error messages. +# Parser does not use it for any other purposes. +# +# Reader(source, data) +# Reader determines the encoding of `data` and converts it to unicode. +# Reader provides the following methods and attributes: +# reader.peek(length=1) - return the next `length` characters +# reader.forward(length=1) - move the current position to `length` characters. +# reader.index - the number of the current character. +# reader.line, stream.column - the line and the column of the current character. + +__all__ = ['Reader', 'ReaderError'] + +from .error import YAMLError, Mark + +import codecs, re + +class ReaderError(YAMLError): + + def __init__(self, name, position, character, encoding, reason): + self.name = name + self.character = character + self.position = position + self.encoding = encoding + self.reason = reason + + def __str__(self): + if isinstance(self.character, bytes): + return "'%s' codec can't decode byte #x%02x: %s\n" \ + " in \"%s\", position %d" \ + % (self.encoding, ord(self.character), self.reason, + self.name, self.position) + else: + return "unacceptable character #x%04x: %s\n" \ + " in \"%s\", position %d" \ + % (self.character, self.reason, + self.name, self.position) + +class Reader(object): + # Reader: + # - determines the data encoding and converts it to a unicode string, + # - checks if characters are in allowed range, + # - adds '\0' to the end. + + # Reader accepts + # - a `bytes` object, + # - a `str` object, + # - a file-like object with its `read` method returning `str`, + # - a file-like object with its `read` method returning `unicode`. + + # Yeah, it's ugly and slow. + + def __init__(self, stream): + self.name = None + self.stream = None + self.stream_pointer = 0 + self.eof = True + self.buffer = '' + self.pointer = 0 + self.raw_buffer = None + self.raw_decode = None + self.encoding = None + self.index = 0 + self.line = 0 + self.column = 0 + if isinstance(stream, str): + self.name = "<unicode string>" + self.check_printable(stream) + self.buffer = stream+'\0' + elif isinstance(stream, bytes): + self.name = "<byte string>" + self.raw_buffer = stream + self.determine_encoding() + else: + self.stream = stream + self.name = getattr(stream, 'name', "<file>") + self.eof = False + self.raw_buffer = None + self.determine_encoding() + + def peek(self, index=0): + try: + return self.buffer[self.pointer+index] + except IndexError: + self.update(index+1) + return self.buffer[self.pointer+index] + + def prefix(self, length=1): + if self.pointer+length >= len(self.buffer): + self.update(length) + return self.buffer[self.pointer:self.pointer+length] + + def forward(self, length=1): + if self.pointer+length+1 >= len(self.buffer): + self.update(length+1) + while length: + ch = self.buffer[self.pointer] + self.pointer += 1 + self.index += 1 + if ch in '\n\x85\u2028\u2029' \ + or (ch == '\r' and self.buffer[self.pointer] != '\n'): + self.line += 1 + self.column = 0 + elif ch != '\uFEFF': + self.column += 1 + length -= 1 + + def get_mark(self): + if self.stream is None: + return Mark(self.name, self.index, self.line, self.column, + self.buffer, self.pointer) + else: + return Mark(self.name, self.index, self.line, self.column, + None, None) + + def determine_encoding(self): + while not self.eof and (self.raw_buffer is None or len(self.raw_buffer) < 2): + self.update_raw() + if isinstance(self.raw_buffer, bytes): + if self.raw_buffer.startswith(codecs.BOM_UTF16_LE): + self.raw_decode = codecs.utf_16_le_decode + self.encoding = 'utf-16-le' + elif self.raw_buffer.startswith(codecs.BOM_UTF16_BE): + self.raw_decode = codecs.utf_16_be_decode + self.encoding = 'utf-16-be' + else: + self.raw_decode = codecs.utf_8_decode + self.encoding = 'utf-8' + self.update(1) + + NON_PRINTABLE = re.compile('[^\x09\x0A\x0D\x20-\x7E\x85\xA0-\uD7FF\uE000-\uFFFD]') + def check_printable(self, data): + match = self.NON_PRINTABLE.search(data) + if match: + character = match.group() + position = self.index+(len(self.buffer)-self.pointer)+match.start() + raise ReaderError(self.name, position, ord(character), + 'unicode', "special characters are not allowed") + + def update(self, length): + if self.raw_buffer is None: + return + self.buffer = self.buffer[self.pointer:] + self.pointer = 0 + while len(self.buffer) < length: + if not self.eof: + self.update_raw() + if self.raw_decode is not None: + try: + data, converted = self.raw_decode(self.raw_buffer, + 'strict', self.eof) + except UnicodeDecodeError as exc: + character = self.raw_buffer[exc.start] + if self.stream is not None: + position = self.stream_pointer-len(self.raw_buffer)+exc.start + else: + position = exc.start + raise ReaderError(self.name, position, character, + exc.encoding, exc.reason) + else: + data = self.raw_buffer + converted = len(data) + self.check_printable(data) + self.buffer += data + self.raw_buffer = self.raw_buffer[converted:] + if self.eof: + self.buffer += '\0' + self.raw_buffer = None + break + + def update_raw(self, size=4096): + data = self.stream.read(size) + if self.raw_buffer is None: + self.raw_buffer = data + else: + self.raw_buffer += data + self.stream_pointer += len(data) + if not data: + self.eof = True + +#try: +# import psyco +# psyco.bind(Reader) +#except ImportError: +# pass + diff --git a/python.d/python_modules/pyyaml3/representer.py b/python.d/python_modules/pyyaml3/representer.py new file mode 100644 index 00000000..67cd6fd2 --- /dev/null +++ b/python.d/python_modules/pyyaml3/representer.py @@ -0,0 +1,374 @@ + +__all__ = ['BaseRepresenter', 'SafeRepresenter', 'Representer', + 'RepresenterError'] + +from .error import * +from .nodes import * + +import datetime, sys, copyreg, types, base64 + +class RepresenterError(YAMLError): + pass + +class BaseRepresenter: + + yaml_representers = {} + yaml_multi_representers = {} + + def __init__(self, default_style=None, default_flow_style=None): + self.default_style = default_style + self.default_flow_style = default_flow_style + self.represented_objects = {} + self.object_keeper = [] + self.alias_key = None + + def represent(self, data): + node = self.represent_data(data) + self.serialize(node) + self.represented_objects = {} + self.object_keeper = [] + self.alias_key = None + + def represent_data(self, data): + if self.ignore_aliases(data): + self.alias_key = None + else: + self.alias_key = id(data) + if self.alias_key is not None: + if self.alias_key in self.represented_objects: + node = self.represented_objects[self.alias_key] + #if node is None: + # raise RepresenterError("recursive objects are not allowed: %r" % data) + return node + #self.represented_objects[alias_key] = None + self.object_keeper.append(data) + data_types = type(data).__mro__ + if data_types[0] in self.yaml_representers: + node = self.yaml_representers[data_types[0]](self, data) + else: + for data_type in data_types: + if data_type in self.yaml_multi_representers: + node = self.yaml_multi_representers[data_type](self, data) + break + else: + if None in self.yaml_multi_representers: + node = self.yaml_multi_representers[None](self, data) + elif None in self.yaml_representers: + node = self.yaml_representers[None](self, data) + else: + node = ScalarNode(None, str(data)) + #if alias_key is not None: + # self.represented_objects[alias_key] = node + return node + + @classmethod + def add_representer(cls, data_type, representer): + if not 'yaml_representers' in cls.__dict__: + cls.yaml_representers = cls.yaml_representers.copy() + cls.yaml_representers[data_type] = representer + + @classmethod + def add_multi_representer(cls, data_type, representer): + if not 'yaml_multi_representers' in cls.__dict__: + cls.yaml_multi_representers = cls.yaml_multi_representers.copy() + cls.yaml_multi_representers[data_type] = representer + + def represent_scalar(self, tag, value, style=None): + if style is None: + style = self.default_style + node = ScalarNode(tag, value, style=style) + if self.alias_key is not None: + self.represented_objects[self.alias_key] = node + return node + + def represent_sequence(self, tag, sequence, flow_style=None): + value = [] + node = SequenceNode(tag, value, flow_style=flow_style) + if self.alias_key is not None: + self.represented_objects[self.alias_key] = node + best_style = True + for item in sequence: + node_item = self.represent_data(item) + if not (isinstance(node_item, ScalarNode) and not node_item.style): + best_style = False + value.append(node_item) + if flow_style is None: + if self.default_flow_style is not None: + node.flow_style = self.default_flow_style + else: + node.flow_style = best_style + return node + + def represent_mapping(self, tag, mapping, flow_style=None): + value = [] + node = MappingNode(tag, value, flow_style=flow_style) + if self.alias_key is not None: + self.represented_objects[self.alias_key] = node + best_style = True + if hasattr(mapping, 'items'): + mapping = list(mapping.items()) + try: + mapping = sorted(mapping) + except TypeError: + pass + for item_key, item_value in mapping: + node_key = self.represent_data(item_key) + node_value = self.represent_data(item_value) + if not (isinstance(node_key, ScalarNode) and not node_key.style): + best_style = False + if not (isinstance(node_value, ScalarNode) and not node_value.style): + best_style = False + value.append((node_key, node_value)) + if flow_style is None: + if self.default_flow_style is not None: + node.flow_style = self.default_flow_style + else: + node.flow_style = best_style + return node + + def ignore_aliases(self, data): + return False + +class SafeRepresenter(BaseRepresenter): + + def ignore_aliases(self, data): + if data in [None, ()]: + return True + if isinstance(data, (str, bytes, bool, int, float)): + return True + + def represent_none(self, data): + return self.represent_scalar('tag:yaml.org,2002:null', 'null') + + def represent_str(self, data): + return self.represent_scalar('tag:yaml.org,2002:str', data) + + def represent_binary(self, data): + if hasattr(base64, 'encodebytes'): + data = base64.encodebytes(data).decode('ascii') + else: + data = base64.encodestring(data).decode('ascii') + return self.represent_scalar('tag:yaml.org,2002:binary', data, style='|') + + def represent_bool(self, data): + if data: + value = 'true' + else: + value = 'false' + return self.represent_scalar('tag:yaml.org,2002:bool', value) + + def represent_int(self, data): + return self.represent_scalar('tag:yaml.org,2002:int', str(data)) + + inf_value = 1e300 + while repr(inf_value) != repr(inf_value*inf_value): + inf_value *= inf_value + + def represent_float(self, data): + if data != data or (data == 0.0 and data == 1.0): + value = '.nan' + elif data == self.inf_value: + value = '.inf' + elif data == -self.inf_value: + value = '-.inf' + else: + value = repr(data).lower() + # Note that in some cases `repr(data)` represents a float number + # without the decimal parts. For instance: + # >>> repr(1e17) + # '1e17' + # Unfortunately, this is not a valid float representation according + # to the definition of the `!!float` tag. We fix this by adding + # '.0' before the 'e' symbol. + if '.' not in value and 'e' in value: + value = value.replace('e', '.0e', 1) + return self.represent_scalar('tag:yaml.org,2002:float', value) + + def represent_list(self, data): + #pairs = (len(data) > 0 and isinstance(data, list)) + #if pairs: + # for item in data: + # if not isinstance(item, tuple) or len(item) != 2: + # pairs = False + # break + #if not pairs: + return self.represent_sequence('tag:yaml.org,2002:seq', data) + #value = [] + #for item_key, item_value in data: + # value.append(self.represent_mapping(u'tag:yaml.org,2002:map', + # [(item_key, item_value)])) + #return SequenceNode(u'tag:yaml.org,2002:pairs', value) + + def represent_dict(self, data): + return self.represent_mapping('tag:yaml.org,2002:map', data) + + def represent_set(self, data): + value = {} + for key in data: + value[key] = None + return self.represent_mapping('tag:yaml.org,2002:set', value) + + def represent_date(self, data): + value = data.isoformat() + return self.represent_scalar('tag:yaml.org,2002:timestamp', value) + + def represent_datetime(self, data): + value = data.isoformat(' ') + return self.represent_scalar('tag:yaml.org,2002:timestamp', value) + + def represent_yaml_object(self, tag, data, cls, flow_style=None): + if hasattr(data, '__getstate__'): + state = data.__getstate__() + else: + state = data.__dict__.copy() + return self.represent_mapping(tag, state, flow_style=flow_style) + + def represent_undefined(self, data): + raise RepresenterError("cannot represent an object: %s" % data) + +SafeRepresenter.add_representer(type(None), + SafeRepresenter.represent_none) + +SafeRepresenter.add_representer(str, + SafeRepresenter.represent_str) + +SafeRepresenter.add_representer(bytes, + SafeRepresenter.represent_binary) + +SafeRepresenter.add_representer(bool, + SafeRepresenter.represent_bool) + +SafeRepresenter.add_representer(int, + SafeRepresenter.represent_int) + +SafeRepresenter.add_representer(float, + SafeRepresenter.represent_float) + +SafeRepresenter.add_representer(list, + SafeRepresenter.represent_list) + +SafeRepresenter.add_representer(tuple, + SafeRepresenter.represent_list) + +SafeRepresenter.add_representer(dict, + SafeRepresenter.represent_dict) + +SafeRepresenter.add_representer(set, + SafeRepresenter.represent_set) + +SafeRepresenter.add_representer(datetime.date, + SafeRepresenter.represent_date) + +SafeRepresenter.add_representer(datetime.datetime, + SafeRepresenter.represent_datetime) + +SafeRepresenter.add_representer(None, + SafeRepresenter.represent_undefined) + +class Representer(SafeRepresenter): + + def represent_complex(self, data): + if data.imag == 0.0: + data = '%r' % data.real + elif data.real == 0.0: + data = '%rj' % data.imag + elif data.imag > 0: + data = '%r+%rj' % (data.real, data.imag) + else: + data = '%r%rj' % (data.real, data.imag) + return self.represent_scalar('tag:yaml.org,2002:python/complex', data) + + def represent_tuple(self, data): + return self.represent_sequence('tag:yaml.org,2002:python/tuple', data) + + def represent_name(self, data): + name = '%s.%s' % (data.__module__, data.__name__) + return self.represent_scalar('tag:yaml.org,2002:python/name:'+name, '') + + def represent_module(self, data): + return self.represent_scalar( + 'tag:yaml.org,2002:python/module:'+data.__name__, '') + + def represent_object(self, data): + # We use __reduce__ API to save the data. data.__reduce__ returns + # a tuple of length 2-5: + # (function, args, state, listitems, dictitems) + + # For reconstructing, we calls function(*args), then set its state, + # listitems, and dictitems if they are not None. + + # A special case is when function.__name__ == '__newobj__'. In this + # case we create the object with args[0].__new__(*args). + + # Another special case is when __reduce__ returns a string - we don't + # support it. + + # We produce a !!python/object, !!python/object/new or + # !!python/object/apply node. + + cls = type(data) + if cls in copyreg.dispatch_table: + reduce = copyreg.dispatch_table[cls](data) + elif hasattr(data, '__reduce_ex__'): + reduce = data.__reduce_ex__(2) + elif hasattr(data, '__reduce__'): + reduce = data.__reduce__() + else: + raise RepresenterError("cannot represent object: %r" % data) + reduce = (list(reduce)+[None]*5)[:5] + function, args, state, listitems, dictitems = reduce + args = list(args) + if state is None: + state = {} + if listitems is not None: + listitems = list(listitems) + if dictitems is not None: + dictitems = dict(dictitems) + if function.__name__ == '__newobj__': + function = args[0] + args = args[1:] + tag = 'tag:yaml.org,2002:python/object/new:' + newobj = True + else: + tag = 'tag:yaml.org,2002:python/object/apply:' + newobj = False + function_name = '%s.%s' % (function.__module__, function.__name__) + if not args and not listitems and not dictitems \ + and isinstance(state, dict) and newobj: + return self.represent_mapping( + 'tag:yaml.org,2002:python/object:'+function_name, state) + if not listitems and not dictitems \ + and isinstance(state, dict) and not state: + return self.represent_sequence(tag+function_name, args) + value = {} + if args: + value['args'] = args + if state or not isinstance(state, dict): + value['state'] = state + if listitems: + value['listitems'] = listitems + if dictitems: + value['dictitems'] = dictitems + return self.represent_mapping(tag+function_name, value) + +Representer.add_representer(complex, + Representer.represent_complex) + +Representer.add_representer(tuple, + Representer.represent_tuple) + +Representer.add_representer(type, + Representer.represent_name) + +Representer.add_representer(types.FunctionType, + Representer.represent_name) + +Representer.add_representer(types.BuiltinFunctionType, + Representer.represent_name) + +Representer.add_representer(types.ModuleType, + Representer.represent_module) + +Representer.add_multi_representer(object, + Representer.represent_object) + diff --git a/python.d/python_modules/pyyaml3/resolver.py b/python.d/python_modules/pyyaml3/resolver.py new file mode 100644 index 00000000..0eece258 --- /dev/null +++ b/python.d/python_modules/pyyaml3/resolver.py @@ -0,0 +1,224 @@ + +__all__ = ['BaseResolver', 'Resolver'] + +from .error import * +from .nodes import * + +import re + +class ResolverError(YAMLError): + pass + +class BaseResolver: + + DEFAULT_SCALAR_TAG = 'tag:yaml.org,2002:str' + DEFAULT_SEQUENCE_TAG = 'tag:yaml.org,2002:seq' + DEFAULT_MAPPING_TAG = 'tag:yaml.org,2002:map' + + yaml_implicit_resolvers = {} + yaml_path_resolvers = {} + + def __init__(self): + self.resolver_exact_paths = [] + self.resolver_prefix_paths = [] + + @classmethod + def add_implicit_resolver(cls, tag, regexp, first): + if not 'yaml_implicit_resolvers' in cls.__dict__: + cls.yaml_implicit_resolvers = cls.yaml_implicit_resolvers.copy() + if first is None: + first = [None] + for ch in first: + cls.yaml_implicit_resolvers.setdefault(ch, []).append((tag, regexp)) + + @classmethod + def add_path_resolver(cls, tag, path, kind=None): + # Note: `add_path_resolver` is experimental. The API could be changed. + # `new_path` is a pattern that is matched against the path from the + # root to the node that is being considered. `node_path` elements are + # tuples `(node_check, index_check)`. `node_check` is a node class: + # `ScalarNode`, `SequenceNode`, `MappingNode` or `None`. `None` + # matches any kind of a node. `index_check` could be `None`, a boolean + # value, a string value, or a number. `None` and `False` match against + # any _value_ of sequence and mapping nodes. `True` matches against + # any _key_ of a mapping node. A string `index_check` matches against + # a mapping value that corresponds to a scalar key which content is + # equal to the `index_check` value. An integer `index_check` matches + # against a sequence value with the index equal to `index_check`. + if not 'yaml_path_resolvers' in cls.__dict__: + cls.yaml_path_resolvers = cls.yaml_path_resolvers.copy() + new_path = [] + for element in path: + if isinstance(element, (list, tuple)): + if len(element) == 2: + node_check, index_check = element + elif len(element) == 1: + node_check = element[0] + index_check = True + else: + raise ResolverError("Invalid path element: %s" % element) + else: + node_check = None + index_check = element + if node_check is str: + node_check = ScalarNode + elif node_check is list: + node_check = SequenceNode + elif node_check is dict: + node_check = MappingNode + elif node_check not in [ScalarNode, SequenceNode, MappingNode] \ + and not isinstance(node_check, str) \ + and node_check is not None: + raise ResolverError("Invalid node checker: %s" % node_check) + if not isinstance(index_check, (str, int)) \ + and index_check is not None: + raise ResolverError("Invalid index checker: %s" % index_check) + new_path.append((node_check, index_check)) + if kind is str: + kind = ScalarNode + elif kind is list: + kind = SequenceNode + elif kind is dict: + kind = MappingNode + elif kind not in [ScalarNode, SequenceNode, MappingNode] \ + and kind is not None: + raise ResolverError("Invalid node kind: %s" % kind) + cls.yaml_path_resolvers[tuple(new_path), kind] = tag + + def descend_resolver(self, current_node, current_index): + if not self.yaml_path_resolvers: + return + exact_paths = {} + prefix_paths = [] + if current_node: + depth = len(self.resolver_prefix_paths) + for path, kind in self.resolver_prefix_paths[-1]: + if self.check_resolver_prefix(depth, path, kind, + current_node, current_index): + if len(path) > depth: + prefix_paths.append((path, kind)) + else: + exact_paths[kind] = self.yaml_path_resolvers[path, kind] + else: + for path, kind in self.yaml_path_resolvers: + if not path: + exact_paths[kind] = self.yaml_path_resolvers[path, kind] + else: + prefix_paths.append((path, kind)) + self.resolver_exact_paths.append(exact_paths) + self.resolver_prefix_paths.append(prefix_paths) + + def ascend_resolver(self): + if not self.yaml_path_resolvers: + return + self.resolver_exact_paths.pop() + self.resolver_prefix_paths.pop() + + def check_resolver_prefix(self, depth, path, kind, + current_node, current_index): + node_check, index_check = path[depth-1] + if isinstance(node_check, str): + if current_node.tag != node_check: + return + elif node_check is not None: + if not isinstance(current_node, node_check): + return + if index_check is True and current_index is not None: + return + if (index_check is False or index_check is None) \ + and current_index is None: + return + if isinstance(index_check, str): + if not (isinstance(current_index, ScalarNode) + and index_check == current_index.value): + return + elif isinstance(index_check, int) and not isinstance(index_check, bool): + if index_check != current_index: + return + return True + + def resolve(self, kind, value, implicit): + if kind is ScalarNode and implicit[0]: + if value == '': + resolvers = self.yaml_implicit_resolvers.get('', []) + else: + resolvers = self.yaml_implicit_resolvers.get(value[0], []) + resolvers += self.yaml_implicit_resolvers.get(None, []) + for tag, regexp in resolvers: + if regexp.match(value): + return tag + implicit = implicit[1] + if self.yaml_path_resolvers: + exact_paths = self.resolver_exact_paths[-1] + if kind in exact_paths: + return exact_paths[kind] + if None in exact_paths: + return exact_paths[None] + if kind is ScalarNode: + return self.DEFAULT_SCALAR_TAG + elif kind is SequenceNode: + return self.DEFAULT_SEQUENCE_TAG + elif kind is MappingNode: + return self.DEFAULT_MAPPING_TAG + +class Resolver(BaseResolver): + pass + +Resolver.add_implicit_resolver( + 'tag:yaml.org,2002:bool', + re.compile(r'''^(?:yes|Yes|YES|no|No|NO + |true|True|TRUE|false|False|FALSE + |on|On|ON|off|Off|OFF)$''', re.X), + list('yYnNtTfFoO')) + +Resolver.add_implicit_resolver( + 'tag:yaml.org,2002:float', + re.compile(r'''^(?:[-+]?(?:[0-9][0-9_]*)\.[0-9_]*(?:[eE][-+][0-9]+)? + |\.[0-9_]+(?:[eE][-+][0-9]+)? + |[-+]?[0-9][0-9_]*(?::[0-5]?[0-9])+\.[0-9_]* + |[-+]?\.(?:inf|Inf|INF) + |\.(?:nan|NaN|NAN))$''', re.X), + list('-+0123456789.')) + +Resolver.add_implicit_resolver( + 'tag:yaml.org,2002:int', + re.compile(r'''^(?:[-+]?0b[0-1_]+ + |[-+]?0[0-7_]+ + |[-+]?(?:0|[1-9][0-9_]*) + |[-+]?0x[0-9a-fA-F_]+ + |[-+]?[1-9][0-9_]*(?::[0-5]?[0-9])+)$''', re.X), + list('-+0123456789')) + +Resolver.add_implicit_resolver( + 'tag:yaml.org,2002:merge', + re.compile(r'^(?:<<)$'), + ['<']) + +Resolver.add_implicit_resolver( + 'tag:yaml.org,2002:null', + re.compile(r'''^(?: ~ + |null|Null|NULL + | )$''', re.X), + ['~', 'n', 'N', '']) + +Resolver.add_implicit_resolver( + 'tag:yaml.org,2002:timestamp', + re.compile(r'''^(?:[0-9][0-9][0-9][0-9]-[0-9][0-9]-[0-9][0-9] + |[0-9][0-9][0-9][0-9] -[0-9][0-9]? -[0-9][0-9]? + (?:[Tt]|[ \t]+)[0-9][0-9]? + :[0-9][0-9] :[0-9][0-9] (?:\.[0-9]*)? + (?:[ \t]*(?:Z|[-+][0-9][0-9]?(?::[0-9][0-9])?))?)$''', re.X), + list('0123456789')) + +Resolver.add_implicit_resolver( + 'tag:yaml.org,2002:value', + re.compile(r'^(?:=)$'), + ['=']) + +# The following resolver is only for documentation purposes. It cannot work +# because plain scalars cannot start with '!', '&', or '*'. +Resolver.add_implicit_resolver( + 'tag:yaml.org,2002:yaml', + re.compile(r'^(?:!|&|\*)$'), + list('!&*')) + diff --git a/python.d/python_modules/pyyaml3/scanner.py b/python.d/python_modules/pyyaml3/scanner.py new file mode 100644 index 00000000..494d975b --- /dev/null +++ b/python.d/python_modules/pyyaml3/scanner.py @@ -0,0 +1,1448 @@ + +# Scanner produces tokens of the following types: +# STREAM-START +# STREAM-END +# DIRECTIVE(name, value) +# DOCUMENT-START +# DOCUMENT-END +# BLOCK-SEQUENCE-START +# BLOCK-MAPPING-START +# BLOCK-END +# FLOW-SEQUENCE-START +# FLOW-MAPPING-START +# FLOW-SEQUENCE-END +# FLOW-MAPPING-END +# BLOCK-ENTRY +# FLOW-ENTRY +# KEY +# VALUE +# ALIAS(value) +# ANCHOR(value) +# TAG(value) +# SCALAR(value, plain, style) +# +# Read comments in the Scanner code for more details. +# + +__all__ = ['Scanner', 'ScannerError'] + +from .error import MarkedYAMLError +from .tokens import * + +class ScannerError(MarkedYAMLError): + pass + +class SimpleKey: + # See below simple keys treatment. + + def __init__(self, token_number, required, index, line, column, mark): + self.token_number = token_number + self.required = required + self.index = index + self.line = line + self.column = column + self.mark = mark + +class Scanner: + + def __init__(self): + """Initialize the scanner.""" + # It is assumed that Scanner and Reader will have a common descendant. + # Reader do the dirty work of checking for BOM and converting the + # input data to Unicode. It also adds NUL to the end. + # + # Reader supports the following methods + # self.peek(i=0) # peek the next i-th character + # self.prefix(l=1) # peek the next l characters + # self.forward(l=1) # read the next l characters and move the pointer. + + # Had we reached the end of the stream? + self.done = False + + # The number of unclosed '{' and '['. `flow_level == 0` means block + # context. + self.flow_level = 0 + + # List of processed tokens that are not yet emitted. + self.tokens = [] + + # Add the STREAM-START token. + self.fetch_stream_start() + + # Number of tokens that were emitted through the `get_token` method. + self.tokens_taken = 0 + + # The current indentation level. + self.indent = -1 + + # Past indentation levels. + self.indents = [] + + # Variables related to simple keys treatment. + + # A simple key is a key that is not denoted by the '?' indicator. + # Example of simple keys: + # --- + # block simple key: value + # ? not a simple key: + # : { flow simple key: value } + # We emit the KEY token before all keys, so when we find a potential + # simple key, we try to locate the corresponding ':' indicator. + # Simple keys should be limited to a single line and 1024 characters. + + # Can a simple key start at the current position? A simple key may + # start: + # - at the beginning of the line, not counting indentation spaces + # (in block context), + # - after '{', '[', ',' (in the flow context), + # - after '?', ':', '-' (in the block context). + # In the block context, this flag also signifies if a block collection + # may start at the current position. + self.allow_simple_key = True + + # Keep track of possible simple keys. This is a dictionary. The key + # is `flow_level`; there can be no more that one possible simple key + # for each level. The value is a SimpleKey record: + # (token_number, required, index, line, column, mark) + # A simple key may start with ALIAS, ANCHOR, TAG, SCALAR(flow), + # '[', or '{' tokens. + self.possible_simple_keys = {} + + # Public methods. + + def check_token(self, *choices): + # Check if the next token is one of the given types. + while self.need_more_tokens(): + self.fetch_more_tokens() + if self.tokens: + if not choices: + return True + for choice in choices: + if isinstance(self.tokens[0], choice): + return True + return False + + def peek_token(self): + # Return the next token, but do not delete if from the queue. + while self.need_more_tokens(): + self.fetch_more_tokens() + if self.tokens: + return self.tokens[0] + + def get_token(self): + # Return the next token. + while self.need_more_tokens(): + self.fetch_more_tokens() + if self.tokens: + self.tokens_taken += 1 + return self.tokens.pop(0) + + # Private methods. + + def need_more_tokens(self): + if self.done: + return False + if not self.tokens: + return True + # The current token may be a potential simple key, so we + # need to look further. + self.stale_possible_simple_keys() + if self.next_possible_simple_key() == self.tokens_taken: + return True + + def fetch_more_tokens(self): + + # Eat whitespaces and comments until we reach the next token. + self.scan_to_next_token() + + # Remove obsolete possible simple keys. + self.stale_possible_simple_keys() + + # Compare the current indentation and column. It may add some tokens + # and decrease the current indentation level. + self.unwind_indent(self.column) + + # Peek the next character. + ch = self.peek() + + # Is it the end of stream? + if ch == '\0': + return self.fetch_stream_end() + + # Is it a directive? + if ch == '%' and self.check_directive(): + return self.fetch_directive() + + # Is it the document start? + if ch == '-' and self.check_document_start(): + return self.fetch_document_start() + + # Is it the document end? + if ch == '.' and self.check_document_end(): + return self.fetch_document_end() + + # TODO: support for BOM within a stream. + #if ch == '\uFEFF': + # return self.fetch_bom() <-- issue BOMToken + + # Note: the order of the following checks is NOT significant. + + # Is it the flow sequence start indicator? + if ch == '[': + return self.fetch_flow_sequence_start() + + # Is it the flow mapping start indicator? + if ch == '{': + return self.fetch_flow_mapping_start() + + # Is it the flow sequence end indicator? + if ch == ']': + return self.fetch_flow_sequence_end() + + # Is it the flow mapping end indicator? + if ch == '}': + return self.fetch_flow_mapping_end() + + # Is it the flow entry indicator? + if ch == ',': + return self.fetch_flow_entry() + + # Is it the block entry indicator? + if ch == '-' and self.check_block_entry(): + return self.fetch_block_entry() + + # Is it the key indicator? + if ch == '?' and self.check_key(): + return self.fetch_key() + + # Is it the value indicator? + if ch == ':' and self.check_value(): + return self.fetch_value() + + # Is it an alias? + if ch == '*': + return self.fetch_alias() + + # Is it an anchor? + if ch == '&': + return self.fetch_anchor() + + # Is it a tag? + if ch == '!': + return self.fetch_tag() + + # Is it a literal scalar? + if ch == '|' and not self.flow_level: + return self.fetch_literal() + + # Is it a folded scalar? + if ch == '>' and not self.flow_level: + return self.fetch_folded() + + # Is it a single quoted scalar? + if ch == '\'': + return self.fetch_single() + + # Is it a double quoted scalar? + if ch == '\"': + return self.fetch_double() + + # It must be a plain scalar then. + if self.check_plain(): + return self.fetch_plain() + + # No? It's an error. Let's produce a nice error message. + raise ScannerError("while scanning for the next token", None, + "found character %r that cannot start any token" % ch, + self.get_mark()) + + # Simple keys treatment. + + def next_possible_simple_key(self): + # Return the number of the nearest possible simple key. Actually we + # don't need to loop through the whole dictionary. We may replace it + # with the following code: + # if not self.possible_simple_keys: + # return None + # return self.possible_simple_keys[ + # min(self.possible_simple_keys.keys())].token_number + min_token_number = None + for level in self.possible_simple_keys: + key = self.possible_simple_keys[level] + if min_token_number is None or key.token_number < min_token_number: + min_token_number = key.token_number + return min_token_number + + def stale_possible_simple_keys(self): + # Remove entries that are no longer possible simple keys. According to + # the YAML specification, simple keys + # - should be limited to a single line, + # - should be no longer than 1024 characters. + # Disabling this procedure will allow simple keys of any length and + # height (may cause problems if indentation is broken though). + for level in list(self.possible_simple_keys): + key = self.possible_simple_keys[level] + if key.line != self.line \ + or self.index-key.index > 1024: + if key.required: + raise ScannerError("while scanning a simple key", key.mark, + "could not found expected ':'", self.get_mark()) + del self.possible_simple_keys[level] + + def save_possible_simple_key(self): + # The next token may start a simple key. We check if it's possible + # and save its position. This function is called for + # ALIAS, ANCHOR, TAG, SCALAR(flow), '[', and '{'. + + # Check if a simple key is required at the current position. + required = not self.flow_level and self.indent == self.column + + # A simple key is required only if it is the first token in the current + # line. Therefore it is always allowed. + assert self.allow_simple_key or not required + + # The next token might be a simple key. Let's save it's number and + # position. + if self.allow_simple_key: + self.remove_possible_simple_key() + token_number = self.tokens_taken+len(self.tokens) + key = SimpleKey(token_number, required, + self.index, self.line, self.column, self.get_mark()) + self.possible_simple_keys[self.flow_level] = key + + def remove_possible_simple_key(self): + # Remove the saved possible key position at the current flow level. + if self.flow_level in self.possible_simple_keys: + key = self.possible_simple_keys[self.flow_level] + + if key.required: + raise ScannerError("while scanning a simple key", key.mark, + "could not found expected ':'", self.get_mark()) + + del self.possible_simple_keys[self.flow_level] + + # Indentation functions. + + def unwind_indent(self, column): + + ## In flow context, tokens should respect indentation. + ## Actually the condition should be `self.indent >= column` according to + ## the spec. But this condition will prohibit intuitively correct + ## constructions such as + ## key : { + ## } + #if self.flow_level and self.indent > column: + # raise ScannerError(None, None, + # "invalid intendation or unclosed '[' or '{'", + # self.get_mark()) + + # In the flow context, indentation is ignored. We make the scanner less + # restrictive then specification requires. + if self.flow_level: + return + + # In block context, we may need to issue the BLOCK-END tokens. + while self.indent > column: + mark = self.get_mark() + self.indent = self.indents.pop() + self.tokens.append(BlockEndToken(mark, mark)) + + def add_indent(self, column): + # Check if we need to increase indentation. + if self.indent < column: + self.indents.append(self.indent) + self.indent = column + return True + return False + + # Fetchers. + + def fetch_stream_start(self): + # We always add STREAM-START as the first token and STREAM-END as the + # last token. + + # Read the token. + mark = self.get_mark() + + # Add STREAM-START. + self.tokens.append(StreamStartToken(mark, mark, + encoding=self.encoding)) + + + def fetch_stream_end(self): + + # Set the current intendation to -1. + self.unwind_indent(-1) + + # Reset simple keys. + self.remove_possible_simple_key() + self.allow_simple_key = False + self.possible_simple_keys = {} + + # Read the token. + mark = self.get_mark() + + # Add STREAM-END. + self.tokens.append(StreamEndToken(mark, mark)) + + # The steam is finished. + self.done = True + + def fetch_directive(self): + + # Set the current intendation to -1. + self.unwind_indent(-1) + + # Reset simple keys. + self.remove_possible_simple_key() + self.allow_simple_key = False + + # Scan and add DIRECTIVE. + self.tokens.append(self.scan_directive()) + + def fetch_document_start(self): + self.fetch_document_indicator(DocumentStartToken) + + def fetch_document_end(self): + self.fetch_document_indicator(DocumentEndToken) + + def fetch_document_indicator(self, TokenClass): + + # Set the current intendation to -1. + self.unwind_indent(-1) + + # Reset simple keys. Note that there could not be a block collection + # after '---'. + self.remove_possible_simple_key() + self.allow_simple_key = False + + # Add DOCUMENT-START or DOCUMENT-END. + start_mark = self.get_mark() + self.forward(3) + end_mark = self.get_mark() + self.tokens.append(TokenClass(start_mark, end_mark)) + + def fetch_flow_sequence_start(self): + self.fetch_flow_collection_start(FlowSequenceStartToken) + + def fetch_flow_mapping_start(self): + self.fetch_flow_collection_start(FlowMappingStartToken) + + def fetch_flow_collection_start(self, TokenClass): + + # '[' and '{' may start a simple key. + self.save_possible_simple_key() + + # Increase the flow level. + self.flow_level += 1 + + # Simple keys are allowed after '[' and '{'. + self.allow_simple_key = True + + # Add FLOW-SEQUENCE-START or FLOW-MAPPING-START. + start_mark = self.get_mark() + self.forward() + end_mark = self.get_mark() + self.tokens.append(TokenClass(start_mark, end_mark)) + + def fetch_flow_sequence_end(self): + self.fetch_flow_collection_end(FlowSequenceEndToken) + + def fetch_flow_mapping_end(self): + self.fetch_flow_collection_end(FlowMappingEndToken) + + def fetch_flow_collection_end(self, TokenClass): + + # Reset possible simple key on the current level. + self.remove_possible_simple_key() + + # Decrease the flow level. + self.flow_level -= 1 + + # No simple keys after ']' or '}'. + self.allow_simple_key = False + + # Add FLOW-SEQUENCE-END or FLOW-MAPPING-END. + start_mark = self.get_mark() + self.forward() + end_mark = self.get_mark() + self.tokens.append(TokenClass(start_mark, end_mark)) + + def fetch_flow_entry(self): + + # Simple keys are allowed after ','. + self.allow_simple_key = True + + # Reset possible simple key on the current level. + self.remove_possible_simple_key() + + # Add FLOW-ENTRY. + start_mark = self.get_mark() + self.forward() + end_mark = self.get_mark() + self.tokens.append(FlowEntryToken(start_mark, end_mark)) + + def fetch_block_entry(self): + + # Block context needs additional checks. + if not self.flow_level: + + # Are we allowed to start a new entry? + if not self.allow_simple_key: + raise ScannerError(None, None, + "sequence entries are not allowed here", + self.get_mark()) + + # We may need to add BLOCK-SEQUENCE-START. + if self.add_indent(self.column): + mark = self.get_mark() + self.tokens.append(BlockSequenceStartToken(mark, mark)) + + # It's an error for the block entry to occur in the flow context, + # but we let the parser detect this. + else: + pass + + # Simple keys are allowed after '-'. + self.allow_simple_key = True + + # Reset possible simple key on the current level. + self.remove_possible_simple_key() + + # Add BLOCK-ENTRY. + start_mark = self.get_mark() + self.forward() + end_mark = self.get_mark() + self.tokens.append(BlockEntryToken(start_mark, end_mark)) + + def fetch_key(self): + + # Block context needs additional checks. + if not self.flow_level: + + # Are we allowed to start a key (not nessesary a simple)? + if not self.allow_simple_key: + raise ScannerError(None, None, + "mapping keys are not allowed here", + self.get_mark()) + + # We may need to add BLOCK-MAPPING-START. + if self.add_indent(self.column): + mark = self.get_mark() + self.tokens.append(BlockMappingStartToken(mark, mark)) + + # Simple keys are allowed after '?' in the block context. + self.allow_simple_key = not self.flow_level + + # Reset possible simple key on the current level. + self.remove_possible_simple_key() + + # Add KEY. + start_mark = self.get_mark() + self.forward() + end_mark = self.get_mark() + self.tokens.append(KeyToken(start_mark, end_mark)) + + def fetch_value(self): + + # Do we determine a simple key? + if self.flow_level in self.possible_simple_keys: + + # Add KEY. + key = self.possible_simple_keys[self.flow_level] + del self.possible_simple_keys[self.flow_level] + self.tokens.insert(key.token_number-self.tokens_taken, + KeyToken(key.mark, key.mark)) + + # If this key starts a new block mapping, we need to add + # BLOCK-MAPPING-START. + if not self.flow_level: + if self.add_indent(key.column): + self.tokens.insert(key.token_number-self.tokens_taken, + BlockMappingStartToken(key.mark, key.mark)) + + # There cannot be two simple keys one after another. + self.allow_simple_key = False + + # It must be a part of a complex key. + else: + + # Block context needs additional checks. + # (Do we really need them? They will be catched by the parser + # anyway.) + if not self.flow_level: + + # We are allowed to start a complex value if and only if + # we can start a simple key. + if not self.allow_simple_key: + raise ScannerError(None, None, + "mapping values are not allowed here", + self.get_mark()) + + # If this value starts a new block mapping, we need to add + # BLOCK-MAPPING-START. It will be detected as an error later by + # the parser. + if not self.flow_level: + if self.add_indent(self.column): + mark = self.get_mark() + self.tokens.append(BlockMappingStartToken(mark, mark)) + + # Simple keys are allowed after ':' in the block context. + self.allow_simple_key = not self.flow_level + + # Reset possible simple key on the current level. + self.remove_possible_simple_key() + + # Add VALUE. + start_mark = self.get_mark() + self.forward() + end_mark = self.get_mark() + self.tokens.append(ValueToken(start_mark, end_mark)) + + def fetch_alias(self): + + # ALIAS could be a simple key. + self.save_possible_simple_key() + + # No simple keys after ALIAS. + self.allow_simple_key = False + + # Scan and add ALIAS. + self.tokens.append(self.scan_anchor(AliasToken)) + + def fetch_anchor(self): + + # ANCHOR could start a simple key. + self.save_possible_simple_key() + + # No simple keys after ANCHOR. + self.allow_simple_key = False + + # Scan and add ANCHOR. + self.tokens.append(self.scan_anchor(AnchorToken)) + + def fetch_tag(self): + + # TAG could start a simple key. + self.save_possible_simple_key() + + # No simple keys after TAG. + self.allow_simple_key = False + + # Scan and add TAG. + self.tokens.append(self.scan_tag()) + + def fetch_literal(self): + self.fetch_block_scalar(style='|') + + def fetch_folded(self): + self.fetch_block_scalar(style='>') + + def fetch_block_scalar(self, style): + + # A simple key may follow a block scalar. + self.allow_simple_key = True + + # Reset possible simple key on the current level. + self.remove_possible_simple_key() + + # Scan and add SCALAR. + self.tokens.append(self.scan_block_scalar(style)) + + def fetch_single(self): + self.fetch_flow_scalar(style='\'') + + def fetch_double(self): + self.fetch_flow_scalar(style='"') + + def fetch_flow_scalar(self, style): + + # A flow scalar could be a simple key. + self.save_possible_simple_key() + + # No simple keys after flow scalars. + self.allow_simple_key = False + + # Scan and add SCALAR. + self.tokens.append(self.scan_flow_scalar(style)) + + def fetch_plain(self): + + # A plain scalar could be a simple key. + self.save_possible_simple_key() + + # No simple keys after plain scalars. But note that `scan_plain` will + # change this flag if the scan is finished at the beginning of the + # line. + self.allow_simple_key = False + + # Scan and add SCALAR. May change `allow_simple_key`. + self.tokens.append(self.scan_plain()) + + # Checkers. + + def check_directive(self): + + # DIRECTIVE: ^ '%' ... + # The '%' indicator is already checked. + if self.column == 0: + return True + + def check_document_start(self): + + # DOCUMENT-START: ^ '---' (' '|'\n') + if self.column == 0: + if self.prefix(3) == '---' \ + and self.peek(3) in '\0 \t\r\n\x85\u2028\u2029': + return True + + def check_document_end(self): + + # DOCUMENT-END: ^ '...' (' '|'\n') + if self.column == 0: + if self.prefix(3) == '...' \ + and self.peek(3) in '\0 \t\r\n\x85\u2028\u2029': + return True + + def check_block_entry(self): + + # BLOCK-ENTRY: '-' (' '|'\n') + return self.peek(1) in '\0 \t\r\n\x85\u2028\u2029' + + def check_key(self): + + # KEY(flow context): '?' + if self.flow_level: + return True + + # KEY(block context): '?' (' '|'\n') + else: + return self.peek(1) in '\0 \t\r\n\x85\u2028\u2029' + + def check_value(self): + + # VALUE(flow context): ':' + if self.flow_level: + return True + + # VALUE(block context): ':' (' '|'\n') + else: + return self.peek(1) in '\0 \t\r\n\x85\u2028\u2029' + + def check_plain(self): + + # A plain scalar may start with any non-space character except: + # '-', '?', ':', ',', '[', ']', '{', '}', + # '#', '&', '*', '!', '|', '>', '\'', '\"', + # '%', '@', '`'. + # + # It may also start with + # '-', '?', ':' + # if it is followed by a non-space character. + # + # Note that we limit the last rule to the block context (except the + # '-' character) because we want the flow context to be space + # independent. + ch = self.peek() + return ch not in '\0 \t\r\n\x85\u2028\u2029-?:,[]{}#&*!|>\'\"%@`' \ + or (self.peek(1) not in '\0 \t\r\n\x85\u2028\u2029' + and (ch == '-' or (not self.flow_level and ch in '?:'))) + + # Scanners. + + def scan_to_next_token(self): + # We ignore spaces, line breaks and comments. + # If we find a line break in the block context, we set the flag + # `allow_simple_key` on. + # The byte order mark is stripped if it's the first character in the + # stream. We do not yet support BOM inside the stream as the + # specification requires. Any such mark will be considered as a part + # of the document. + # + # TODO: We need to make tab handling rules more sane. A good rule is + # Tabs cannot precede tokens + # BLOCK-SEQUENCE-START, BLOCK-MAPPING-START, BLOCK-END, + # KEY(block), VALUE(block), BLOCK-ENTRY + # So the checking code is + # if <TAB>: + # self.allow_simple_keys = False + # We also need to add the check for `allow_simple_keys == True` to + # `unwind_indent` before issuing BLOCK-END. + # Scanners for block, flow, and plain scalars need to be modified. + + if self.index == 0 and self.peek() == '\uFEFF': + self.forward() + found = False + while not found: + while self.peek() == ' ': + self.forward() + if self.peek() == '#': + while self.peek() not in '\0\r\n\x85\u2028\u2029': + self.forward() + if self.scan_line_break(): + if not self.flow_level: + self.allow_simple_key = True + else: + found = True + + def scan_directive(self): + # See the specification for details. + start_mark = self.get_mark() + self.forward() + name = self.scan_directive_name(start_mark) + value = None + if name == 'YAML': + value = self.scan_yaml_directive_value(start_mark) + end_mark = self.get_mark() + elif name == 'TAG': + value = self.scan_tag_directive_value(start_mark) + end_mark = self.get_mark() + else: + end_mark = self.get_mark() + while self.peek() not in '\0\r\n\x85\u2028\u2029': + self.forward() + self.scan_directive_ignored_line(start_mark) + return DirectiveToken(name, value, start_mark, end_mark) + + def scan_directive_name(self, start_mark): + # See the specification for details. + length = 0 + ch = self.peek(length) + while '0' <= ch <= '9' or 'A' <= ch <= 'Z' or 'a' <= ch <= 'z' \ + or ch in '-_': + length += 1 + ch = self.peek(length) + if not length: + raise ScannerError("while scanning a directive", start_mark, + "expected alphabetic or numeric character, but found %r" + % ch, self.get_mark()) + value = self.prefix(length) + self.forward(length) + ch = self.peek() + if ch not in '\0 \r\n\x85\u2028\u2029': + raise ScannerError("while scanning a directive", start_mark, + "expected alphabetic or numeric character, but found %r" + % ch, self.get_mark()) + return value + + def scan_yaml_directive_value(self, start_mark): + # See the specification for details. + while self.peek() == ' ': + self.forward() + major = self.scan_yaml_directive_number(start_mark) + if self.peek() != '.': + raise ScannerError("while scanning a directive", start_mark, + "expected a digit or '.', but found %r" % self.peek(), + self.get_mark()) + self.forward() + minor = self.scan_yaml_directive_number(start_mark) + if self.peek() not in '\0 \r\n\x85\u2028\u2029': + raise ScannerError("while scanning a directive", start_mark, + "expected a digit or ' ', but found %r" % self.peek(), + self.get_mark()) + return (major, minor) + + def scan_yaml_directive_number(self, start_mark): + # See the specification for details. + ch = self.peek() + if not ('0' <= ch <= '9'): + raise ScannerError("while scanning a directive", start_mark, + "expected a digit, but found %r" % ch, self.get_mark()) + length = 0 + while '0' <= self.peek(length) <= '9': + length += 1 + value = int(self.prefix(length)) + self.forward(length) + return value + + def scan_tag_directive_value(self, start_mark): + # See the specification for details. + while self.peek() == ' ': + self.forward() + handle = self.scan_tag_directive_handle(start_mark) + while self.peek() == ' ': + self.forward() + prefix = self.scan_tag_directive_prefix(start_mark) + return (handle, prefix) + + def scan_tag_directive_handle(self, start_mark): + # See the specification for details. + value = self.scan_tag_handle('directive', start_mark) + ch = self.peek() + if ch != ' ': + raise ScannerError("while scanning a directive", start_mark, + "expected ' ', but found %r" % ch, self.get_mark()) + return value + + def scan_tag_directive_prefix(self, start_mark): + # See the specification for details. + value = self.scan_tag_uri('directive', start_mark) + ch = self.peek() + if ch not in '\0 \r\n\x85\u2028\u2029': + raise ScannerError("while scanning a directive", start_mark, + "expected ' ', but found %r" % ch, self.get_mark()) + return value + + def scan_directive_ignored_line(self, start_mark): + # See the specification for details. + while self.peek() == ' ': + self.forward() + if self.peek() == '#': + while self.peek() not in '\0\r\n\x85\u2028\u2029': + self.forward() + ch = self.peek() + if ch not in '\0\r\n\x85\u2028\u2029': + raise ScannerError("while scanning a directive", start_mark, + "expected a comment or a line break, but found %r" + % ch, self.get_mark()) + self.scan_line_break() + + def scan_anchor(self, TokenClass): + # The specification does not restrict characters for anchors and + # aliases. This may lead to problems, for instance, the document: + # [ *alias, value ] + # can be interpteted in two ways, as + # [ "value" ] + # and + # [ *alias , "value" ] + # Therefore we restrict aliases to numbers and ASCII letters. + start_mark = self.get_mark() + indicator = self.peek() + if indicator == '*': + name = 'alias' + else: + name = 'anchor' + self.forward() + length = 0 + ch = self.peek(length) + while '0' <= ch <= '9' or 'A' <= ch <= 'Z' or 'a' <= ch <= 'z' \ + or ch in '-_': + length += 1 + ch = self.peek(length) + if not length: + raise ScannerError("while scanning an %s" % name, start_mark, + "expected alphabetic or numeric character, but found %r" + % ch, self.get_mark()) + value = self.prefix(length) + self.forward(length) + ch = self.peek() + if ch not in '\0 \t\r\n\x85\u2028\u2029?:,]}%@`': + raise ScannerError("while scanning an %s" % name, start_mark, + "expected alphabetic or numeric character, but found %r" + % ch, self.get_mark()) + end_mark = self.get_mark() + return TokenClass(value, start_mark, end_mark) + + def scan_tag(self): + # See the specification for details. + start_mark = self.get_mark() + ch = self.peek(1) + if ch == '<': + handle = None + self.forward(2) + suffix = self.scan_tag_uri('tag', start_mark) + if self.peek() != '>': + raise ScannerError("while parsing a tag", start_mark, + "expected '>', but found %r" % self.peek(), + self.get_mark()) + self.forward() + elif ch in '\0 \t\r\n\x85\u2028\u2029': + handle = None + suffix = '!' + self.forward() + else: + length = 1 + use_handle = False + while ch not in '\0 \r\n\x85\u2028\u2029': + if ch == '!': + use_handle = True + break + length += 1 + ch = self.peek(length) + handle = '!' + if use_handle: + handle = self.scan_tag_handle('tag', start_mark) + else: + handle = '!' + self.forward() + suffix = self.scan_tag_uri('tag', start_mark) + ch = self.peek() + if ch not in '\0 \r\n\x85\u2028\u2029': + raise ScannerError("while scanning a tag", start_mark, + "expected ' ', but found %r" % ch, self.get_mark()) + value = (handle, suffix) + end_mark = self.get_mark() + return TagToken(value, start_mark, end_mark) + + def scan_block_scalar(self, style): + # See the specification for details. + + if style == '>': + folded = True + else: + folded = False + + chunks = [] + start_mark = self.get_mark() + + # Scan the header. + self.forward() + chomping, increment = self.scan_block_scalar_indicators(start_mark) + self.scan_block_scalar_ignored_line(start_mark) + + # Determine the indentation level and go to the first non-empty line. + min_indent = self.indent+1 + if min_indent < 1: + min_indent = 1 + if increment is None: + breaks, max_indent, end_mark = self.scan_block_scalar_indentation() + indent = max(min_indent, max_indent) + else: + indent = min_indent+increment-1 + breaks, end_mark = self.scan_block_scalar_breaks(indent) + line_break = '' + + # Scan the inner part of the block scalar. + while self.column == indent and self.peek() != '\0': + chunks.extend(breaks) + leading_non_space = self.peek() not in ' \t' + length = 0 + while self.peek(length) not in '\0\r\n\x85\u2028\u2029': + length += 1 + chunks.append(self.prefix(length)) + self.forward(length) + line_break = self.scan_line_break() + breaks, end_mark = self.scan_block_scalar_breaks(indent) + if self.column == indent and self.peek() != '\0': + + # Unfortunately, folding rules are ambiguous. + # + # This is the folding according to the specification: + + if folded and line_break == '\n' \ + and leading_non_space and self.peek() not in ' \t': + if not breaks: + chunks.append(' ') + else: + chunks.append(line_break) + + # This is Clark Evans's interpretation (also in the spec + # examples): + # + #if folded and line_break == '\n': + # if not breaks: + # if self.peek() not in ' \t': + # chunks.append(' ') + # else: + # chunks.append(line_break) + #else: + # chunks.append(line_break) + else: + break + + # Chomp the tail. + if chomping is not False: + chunks.append(line_break) + if chomping is True: + chunks.extend(breaks) + + # We are done. + return ScalarToken(''.join(chunks), False, start_mark, end_mark, + style) + + def scan_block_scalar_indicators(self, start_mark): + # See the specification for details. + chomping = None + increment = None + ch = self.peek() + if ch in '+-': + if ch == '+': + chomping = True + else: + chomping = False + self.forward() + ch = self.peek() + if ch in '0123456789': + increment = int(ch) + if increment == 0: + raise ScannerError("while scanning a block scalar", start_mark, + "expected indentation indicator in the range 1-9, but found 0", + self.get_mark()) + self.forward() + elif ch in '0123456789': + increment = int(ch) + if increment == 0: + raise ScannerError("while scanning a block scalar", start_mark, + "expected indentation indicator in the range 1-9, but found 0", + self.get_mark()) + self.forward() + ch = self.peek() + if ch in '+-': + if ch == '+': + chomping = True + else: + chomping = False + self.forward() + ch = self.peek() + if ch not in '\0 \r\n\x85\u2028\u2029': + raise ScannerError("while scanning a block scalar", start_mark, + "expected chomping or indentation indicators, but found %r" + % ch, self.get_mark()) + return chomping, increment + + def scan_block_scalar_ignored_line(self, start_mark): + # See the specification for details. + while self.peek() == ' ': + self.forward() + if self.peek() == '#': + while self.peek() not in '\0\r\n\x85\u2028\u2029': + self.forward() + ch = self.peek() + if ch not in '\0\r\n\x85\u2028\u2029': + raise ScannerError("while scanning a block scalar", start_mark, + "expected a comment or a line break, but found %r" % ch, + self.get_mark()) + self.scan_line_break() + + def scan_block_scalar_indentation(self): + # See the specification for details. + chunks = [] + max_indent = 0 + end_mark = self.get_mark() + while self.peek() in ' \r\n\x85\u2028\u2029': + if self.peek() != ' ': + chunks.append(self.scan_line_break()) + end_mark = self.get_mark() + else: + self.forward() + if self.column > max_indent: + max_indent = self.column + return chunks, max_indent, end_mark + + def scan_block_scalar_breaks(self, indent): + # See the specification for details. + chunks = [] + end_mark = self.get_mark() + while self.column < indent and self.peek() == ' ': + self.forward() + while self.peek() in '\r\n\x85\u2028\u2029': + chunks.append(self.scan_line_break()) + end_mark = self.get_mark() + while self.column < indent and self.peek() == ' ': + self.forward() + return chunks, end_mark + + def scan_flow_scalar(self, style): + # See the specification for details. + # Note that we loose indentation rules for quoted scalars. Quoted + # scalars don't need to adhere indentation because " and ' clearly + # mark the beginning and the end of them. Therefore we are less + # restrictive then the specification requires. We only need to check + # that document separators are not included in scalars. + if style == '"': + double = True + else: + double = False + chunks = [] + start_mark = self.get_mark() + quote = self.peek() + self.forward() + chunks.extend(self.scan_flow_scalar_non_spaces(double, start_mark)) + while self.peek() != quote: + chunks.extend(self.scan_flow_scalar_spaces(double, start_mark)) + chunks.extend(self.scan_flow_scalar_non_spaces(double, start_mark)) + self.forward() + end_mark = self.get_mark() + return ScalarToken(''.join(chunks), False, start_mark, end_mark, + style) + + ESCAPE_REPLACEMENTS = { + '0': '\0', + 'a': '\x07', + 'b': '\x08', + 't': '\x09', + '\t': '\x09', + 'n': '\x0A', + 'v': '\x0B', + 'f': '\x0C', + 'r': '\x0D', + 'e': '\x1B', + ' ': '\x20', + '\"': '\"', + '\\': '\\', + 'N': '\x85', + '_': '\xA0', + 'L': '\u2028', + 'P': '\u2029', + } + + ESCAPE_CODES = { + 'x': 2, + 'u': 4, + 'U': 8, + } + + def scan_flow_scalar_non_spaces(self, double, start_mark): + # See the specification for details. + chunks = [] + while True: + length = 0 + while self.peek(length) not in '\'\"\\\0 \t\r\n\x85\u2028\u2029': + length += 1 + if length: + chunks.append(self.prefix(length)) + self.forward(length) + ch = self.peek() + if not double and ch == '\'' and self.peek(1) == '\'': + chunks.append('\'') + self.forward(2) + elif (double and ch == '\'') or (not double and ch in '\"\\'): + chunks.append(ch) + self.forward() + elif double and ch == '\\': + self.forward() + ch = self.peek() + if ch in self.ESCAPE_REPLACEMENTS: + chunks.append(self.ESCAPE_REPLACEMENTS[ch]) + self.forward() + elif ch in self.ESCAPE_CODES: + length = self.ESCAPE_CODES[ch] + self.forward() + for k in range(length): + if self.peek(k) not in '0123456789ABCDEFabcdef': + raise ScannerError("while scanning a double-quoted scalar", start_mark, + "expected escape sequence of %d hexdecimal numbers, but found %r" % + (length, self.peek(k)), self.get_mark()) + code = int(self.prefix(length), 16) + chunks.append(chr(code)) + self.forward(length) + elif ch in '\r\n\x85\u2028\u2029': + self.scan_line_break() + chunks.extend(self.scan_flow_scalar_breaks(double, start_mark)) + else: + raise ScannerError("while scanning a double-quoted scalar", start_mark, + "found unknown escape character %r" % ch, self.get_mark()) + else: + return chunks + + def scan_flow_scalar_spaces(self, double, start_mark): + # See the specification for details. + chunks = [] + length = 0 + while self.peek(length) in ' \t': + length += 1 + whitespaces = self.prefix(length) + self.forward(length) + ch = self.peek() + if ch == '\0': + raise ScannerError("while scanning a quoted scalar", start_mark, + "found unexpected end of stream", self.get_mark()) + elif ch in '\r\n\x85\u2028\u2029': + line_break = self.scan_line_break() + breaks = self.scan_flow_scalar_breaks(double, start_mark) + if line_break != '\n': + chunks.append(line_break) + elif not breaks: + chunks.append(' ') + chunks.extend(breaks) + else: + chunks.append(whitespaces) + return chunks + + def scan_flow_scalar_breaks(self, double, start_mark): + # See the specification for details. + chunks = [] + while True: + # Instead of checking indentation, we check for document + # separators. + prefix = self.prefix(3) + if (prefix == '---' or prefix == '...') \ + and self.peek(3) in '\0 \t\r\n\x85\u2028\u2029': + raise ScannerError("while scanning a quoted scalar", start_mark, + "found unexpected document separator", self.get_mark()) + while self.peek() in ' \t': + self.forward() + if self.peek() in '\r\n\x85\u2028\u2029': + chunks.append(self.scan_line_break()) + else: + return chunks + + def scan_plain(self): + # See the specification for details. + # We add an additional restriction for the flow context: + # plain scalars in the flow context cannot contain ',', ':' and '?'. + # We also keep track of the `allow_simple_key` flag here. + # Indentation rules are loosed for the flow context. + chunks = [] + start_mark = self.get_mark() + end_mark = start_mark + indent = self.indent+1 + # We allow zero indentation for scalars, but then we need to check for + # document separators at the beginning of the line. + #if indent == 0: + # indent = 1 + spaces = [] + while True: + length = 0 + if self.peek() == '#': + break + while True: + ch = self.peek(length) + if ch in '\0 \t\r\n\x85\u2028\u2029' \ + or (not self.flow_level and ch == ':' and + self.peek(length+1) in '\0 \t\r\n\x85\u2028\u2029') \ + or (self.flow_level and ch in ',:?[]{}'): + break + length += 1 + # It's not clear what we should do with ':' in the flow context. + if (self.flow_level and ch == ':' + and self.peek(length+1) not in '\0 \t\r\n\x85\u2028\u2029,[]{}'): + self.forward(length) + raise ScannerError("while scanning a plain scalar", start_mark, + "found unexpected ':'", self.get_mark(), + "Please check http://pyyaml.org/wiki/YAMLColonInFlowContext for details.") + if length == 0: + break + self.allow_simple_key = False + chunks.extend(spaces) + chunks.append(self.prefix(length)) + self.forward(length) + end_mark = self.get_mark() + spaces = self.scan_plain_spaces(indent, start_mark) + if not spaces or self.peek() == '#' \ + or (not self.flow_level and self.column < indent): + break + return ScalarToken(''.join(chunks), True, start_mark, end_mark) + + def scan_plain_spaces(self, indent, start_mark): + # See the specification for details. + # The specification is really confusing about tabs in plain scalars. + # We just forbid them completely. Do not use tabs in YAML! + chunks = [] + length = 0 + while self.peek(length) in ' ': + length += 1 + whitespaces = self.prefix(length) + self.forward(length) + ch = self.peek() + if ch in '\r\n\x85\u2028\u2029': + line_break = self.scan_line_break() + self.allow_simple_key = True + prefix = self.prefix(3) + if (prefix == '---' or prefix == '...') \ + and self.peek(3) in '\0 \t\r\n\x85\u2028\u2029': + return + breaks = [] + while self.peek() in ' \r\n\x85\u2028\u2029': + if self.peek() == ' ': + self.forward() + else: + breaks.append(self.scan_line_break()) + prefix = self.prefix(3) + if (prefix == '---' or prefix == '...') \ + and self.peek(3) in '\0 \t\r\n\x85\u2028\u2029': + return + if line_break != '\n': + chunks.append(line_break) + elif not breaks: + chunks.append(' ') + chunks.extend(breaks) + elif whitespaces: + chunks.append(whitespaces) + return chunks + + def scan_tag_handle(self, name, start_mark): + # See the specification for details. + # For some strange reasons, the specification does not allow '_' in + # tag handles. I have allowed it anyway. + ch = self.peek() + if ch != '!': + raise ScannerError("while scanning a %s" % name, start_mark, + "expected '!', but found %r" % ch, self.get_mark()) + length = 1 + ch = self.peek(length) + if ch != ' ': + while '0' <= ch <= '9' or 'A' <= ch <= 'Z' or 'a' <= ch <= 'z' \ + or ch in '-_': + length += 1 + ch = self.peek(length) + if ch != '!': + self.forward(length) + raise ScannerError("while scanning a %s" % name, start_mark, + "expected '!', but found %r" % ch, self.get_mark()) + length += 1 + value = self.prefix(length) + self.forward(length) + return value + + def scan_tag_uri(self, name, start_mark): + # See the specification for details. + # Note: we do not check if URI is well-formed. + chunks = [] + length = 0 + ch = self.peek(length) + while '0' <= ch <= '9' or 'A' <= ch <= 'Z' or 'a' <= ch <= 'z' \ + or ch in '-;/?:@&=+$,_.!~*\'()[]%': + if ch == '%': + chunks.append(self.prefix(length)) + self.forward(length) + length = 0 + chunks.append(self.scan_uri_escapes(name, start_mark)) + else: + length += 1 + ch = self.peek(length) + if length: + chunks.append(self.prefix(length)) + self.forward(length) + length = 0 + if not chunks: + raise ScannerError("while parsing a %s" % name, start_mark, + "expected URI, but found %r" % ch, self.get_mark()) + return ''.join(chunks) + + def scan_uri_escapes(self, name, start_mark): + # See the specification for details. + codes = [] + mark = self.get_mark() + while self.peek() == '%': + self.forward() + for k in range(2): + if self.peek(k) not in '0123456789ABCDEFabcdef': + raise ScannerError("while scanning a %s" % name, start_mark, + "expected URI escape sequence of 2 hexdecimal numbers, but found %r" + % self.peek(k), self.get_mark()) + codes.append(int(self.prefix(2), 16)) + self.forward(2) + try: + value = bytes(codes).decode('utf-8') + except UnicodeDecodeError as exc: + raise ScannerError("while scanning a %s" % name, start_mark, str(exc), mark) + return value + + def scan_line_break(self): + # Transforms: + # '\r\n' : '\n' + # '\r' : '\n' + # '\n' : '\n' + # '\x85' : '\n' + # '\u2028' : '\u2028' + # '\u2029 : '\u2029' + # default : '' + ch = self.peek() + if ch in '\r\n\x85': + if self.prefix(2) == '\r\n': + self.forward(2) + else: + self.forward() + return '\n' + elif ch in '\u2028\u2029': + self.forward() + return ch + return '' + +#try: +# import psyco +# psyco.bind(Scanner) +#except ImportError: +# pass + diff --git a/python.d/python_modules/pyyaml3/serializer.py b/python.d/python_modules/pyyaml3/serializer.py new file mode 100644 index 00000000..fe911e67 --- /dev/null +++ b/python.d/python_modules/pyyaml3/serializer.py @@ -0,0 +1,111 @@ + +__all__ = ['Serializer', 'SerializerError'] + +from .error import YAMLError +from .events import * +from .nodes import * + +class SerializerError(YAMLError): + pass + +class Serializer: + + ANCHOR_TEMPLATE = 'id%03d' + + def __init__(self, encoding=None, + explicit_start=None, explicit_end=None, version=None, tags=None): + self.use_encoding = encoding + self.use_explicit_start = explicit_start + self.use_explicit_end = explicit_end + self.use_version = version + self.use_tags = tags + self.serialized_nodes = {} + self.anchors = {} + self.last_anchor_id = 0 + self.closed = None + + def open(self): + if self.closed is None: + self.emit(StreamStartEvent(encoding=self.use_encoding)) + self.closed = False + elif self.closed: + raise SerializerError("serializer is closed") + else: + raise SerializerError("serializer is already opened") + + def close(self): + if self.closed is None: + raise SerializerError("serializer is not opened") + elif not self.closed: + self.emit(StreamEndEvent()) + self.closed = True + + #def __del__(self): + # self.close() + + def serialize(self, node): + if self.closed is None: + raise SerializerError("serializer is not opened") + elif self.closed: + raise SerializerError("serializer is closed") + self.emit(DocumentStartEvent(explicit=self.use_explicit_start, + version=self.use_version, tags=self.use_tags)) + self.anchor_node(node) + self.serialize_node(node, None, None) + self.emit(DocumentEndEvent(explicit=self.use_explicit_end)) + self.serialized_nodes = {} + self.anchors = {} + self.last_anchor_id = 0 + + def anchor_node(self, node): + if node in self.anchors: + if self.anchors[node] is None: + self.anchors[node] = self.generate_anchor(node) + else: + self.anchors[node] = None + if isinstance(node, SequenceNode): + for item in node.value: + self.anchor_node(item) + elif isinstance(node, MappingNode): + for key, value in node.value: + self.anchor_node(key) + self.anchor_node(value) + + def generate_anchor(self, node): + self.last_anchor_id += 1 + return self.ANCHOR_TEMPLATE % self.last_anchor_id + + def serialize_node(self, node, parent, index): + alias = self.anchors[node] + if node in self.serialized_nodes: + self.emit(AliasEvent(alias)) + else: + self.serialized_nodes[node] = True + self.descend_resolver(parent, index) + if isinstance(node, ScalarNode): + detected_tag = self.resolve(ScalarNode, node.value, (True, False)) + default_tag = self.resolve(ScalarNode, node.value, (False, True)) + implicit = (node.tag == detected_tag), (node.tag == default_tag) + self.emit(ScalarEvent(alias, node.tag, implicit, node.value, + style=node.style)) + elif isinstance(node, SequenceNode): + implicit = (node.tag + == self.resolve(SequenceNode, node.value, True)) + self.emit(SequenceStartEvent(alias, node.tag, implicit, + flow_style=node.flow_style)) + index = 0 + for item in node.value: + self.serialize_node(item, node, index) + index += 1 + self.emit(SequenceEndEvent()) + elif isinstance(node, MappingNode): + implicit = (node.tag + == self.resolve(MappingNode, node.value, True)) + self.emit(MappingStartEvent(alias, node.tag, implicit, + flow_style=node.flow_style)) + for key, value in node.value: + self.serialize_node(key, node, None) + self.serialize_node(value, node, key) + self.emit(MappingEndEvent()) + self.ascend_resolver() + diff --git a/python.d/python_modules/pyyaml3/tokens.py b/python.d/python_modules/pyyaml3/tokens.py new file mode 100644 index 00000000..4d0b48a3 --- /dev/null +++ b/python.d/python_modules/pyyaml3/tokens.py @@ -0,0 +1,104 @@ + +class Token(object): + def __init__(self, start_mark, end_mark): + self.start_mark = start_mark + self.end_mark = end_mark + def __repr__(self): + attributes = [key for key in self.__dict__ + if not key.endswith('_mark')] + attributes.sort() + arguments = ', '.join(['%s=%r' % (key, getattr(self, key)) + for key in attributes]) + return '%s(%s)' % (self.__class__.__name__, arguments) + +#class BOMToken(Token): +# id = '<byte order mark>' + +class DirectiveToken(Token): + id = '<directive>' + def __init__(self, name, value, start_mark, end_mark): + self.name = name + self.value = value + self.start_mark = start_mark + self.end_mark = end_mark + +class DocumentStartToken(Token): + id = '<document start>' + +class DocumentEndToken(Token): + id = '<document end>' + +class StreamStartToken(Token): + id = '<stream start>' + def __init__(self, start_mark=None, end_mark=None, + encoding=None): + self.start_mark = start_mark + self.end_mark = end_mark + self.encoding = encoding + +class StreamEndToken(Token): + id = '<stream end>' + +class BlockSequenceStartToken(Token): + id = '<block sequence start>' + +class BlockMappingStartToken(Token): + id = '<block mapping start>' + +class BlockEndToken(Token): + id = '<block end>' + +class FlowSequenceStartToken(Token): + id = '[' + +class FlowMappingStartToken(Token): + id = '{' + +class FlowSequenceEndToken(Token): + id = ']' + +class FlowMappingEndToken(Token): + id = '}' + +class KeyToken(Token): + id = '?' + +class ValueToken(Token): + id = ':' + +class BlockEntryToken(Token): + id = '-' + +class FlowEntryToken(Token): + id = ',' + +class AliasToken(Token): + id = '<alias>' + def __init__(self, value, start_mark, end_mark): + self.value = value + self.start_mark = start_mark + self.end_mark = end_mark + +class AnchorToken(Token): + id = '<anchor>' + def __init__(self, value, start_mark, end_mark): + self.value = value + self.start_mark = start_mark + self.end_mark = end_mark + +class TagToken(Token): + id = '<tag>' + def __init__(self, value, start_mark, end_mark): + self.value = value + self.start_mark = start_mark + self.end_mark = end_mark + +class ScalarToken(Token): + id = '<scalar>' + def __init__(self, value, plain, start_mark, end_mark, style=None): + self.value = value + self.plain = plain + self.start_mark = start_mark + self.end_mark = end_mark + self.style = style + diff --git a/python.d/redis.chart.py b/python.d/redis.chart.py new file mode 100644 index 00000000..218401e1 --- /dev/null +++ b/python.d/redis.chart.py @@ -0,0 +1,140 @@ +# -*- coding: utf-8 -*- +# Description: redis netdata python.d module +# Author: Pawel Krupa (paulfantom) + +from base import SocketService + +# default module values (can be overridden per job in `config`) +#update_every = 2 +priority = 60000 +retries = 60 + +# default job configuration (overridden by python.d.plugin) +# config = {'local': { +# 'update_every': update_every, +# 'retries': retries, +# 'priority': priority, +# 'host': 'localhost', +# 'port': 6379, +# 'unix_socket': None +# }} + +ORDER = ['operations', 'hit_rate', 'memory', 'keys', 'clients', 'slaves'] + +CHARTS = { + 'operations': { + 'options': [None, 'Operations', 'operations/s', 'Statistics', 'redis.operations', 'line'], + 'lines': [ + ['instantaneous_ops_per_sec', 'operations', 'absolute'] + ]}, + 'hit_rate': { + 'options': [None, 'Hit rate', 'percent', 'Statistics', 'redis.hit_rate', 'line'], + 'lines': [ + ['hit_rate', 'rate', 'absolute'] + ]}, + 'memory': { + 'options': [None, 'Memory utilization', 'kilobytes', 'Memory', 'redis.memory', 'line'], + 'lines': [ + ['used_memory', 'total', 'absolute', 1, 1024], + ['used_memory_lua', 'lua', 'absolute', 1, 1024] + ]}, + 'keys': { + 'options': [None, 'Database keys', 'keys', 'Keys', 'redis.keys', 'line'], + 'lines': [ + # lines are created dynamically in `check()` method + ]}, + 'clients': { + 'options': [None, 'Clients', 'clients', 'Clients', 'redis.clients', 'line'], + 'lines': [ + ['connected_clients', 'connected', 'absolute'], + ['blocked_clients', 'blocked', 'absolute'] + ]}, + 'slaves': { + 'options': [None, 'Slaves', 'slaves', 'Replication', 'redis.slaves', 'line'], + 'lines': [ + ['connected_slaves', 'connected', 'absolute'] + ]} +} + + +class Service(SocketService): + def __init__(self, configuration=None, name=None): + SocketService.__init__(self, configuration=configuration, name=name) + self.request = "INFO\r\n" + self.host = "localhost" + self.port = 6379 + self.unix_socket = None + self.order = ORDER + self.definitions = CHARTS + self._keep_alive = True + self.chart_name = "" + + def _get_data(self): + """ + Get data from socket + :return: dict + """ + try: + raw = self._get_raw_data().split("\n") + except AttributeError: + self.error("no data received") + return None + data = {} + for line in raw: + if line.startswith(('instantaneous', 'keyspace', 'used_memory', 'connected', 'blocked')): + try: + t = line.split(':') + data[t[0]] = int(t[1]) + except (IndexError, ValueError): + pass + elif line.startswith('db'): + tmp = line.split(',')[0].replace('keys=', '') + record = tmp.split(':') + data[record[0]] = int(record[1]) + try: + data['hit_rate'] = int((data['keyspace_hits'] / float(data['keyspace_hits'] + data['keyspace_misses'])) * 100) + except: + data['hit_rate'] = 0 + + if len(data) == 0: + self.error("received data doesn't have needed records") + return None + else: + return data + + def _check_raw_data(self, data): + """ + Check if all data has been gathered from socket. + Parse first line containing message length and check against received message + :param data: str + :return: boolean + """ + length = len(data) + supposed = data.split('\n')[0][1:] + offset = len(supposed) + 4 # 1 dollar sing, 1 new line character + 1 ending sequence '\r\n' + supposed = int(supposed) + if length - offset >= supposed: + return True + else: + return False + + return False + + def check(self): + """ + Parse configuration, check if redis is available, and dynamically create chart lines data + :return: boolean + """ + self._parse_config() + if self.name == "": + self.name = "local" + self.chart_name += "_" + self.name + data = self._get_data() + if data is None: + return False + + for name in data: + if name.startswith('db'): + self.definitions['keys']['lines'].append([name, None, 'absolute']) + + return True diff --git a/python.d/sensors.chart.py b/python.d/sensors.chart.py new file mode 100644 index 00000000..7abe7f08 --- /dev/null +++ b/python.d/sensors.chart.py @@ -0,0 +1,134 @@ +# -*- coding: utf-8 -*- +# Description: sensors netdata python.d plugin +# Author: Pawel Krupa (paulfantom) + +from base import SimpleService +import lm_sensors as sensors + +# default module values (can be overridden per job in `config`) +# update_every = 2 + +ORDER = ['temperature', 'fan', 'voltage', 'current', 'power', 'energy', 'humidity'] + +# This is a prototype of chart definition which is used to dynamically create self.definitions +CHARTS = { + 'temperature': { + 'options': [None, ' temperature', 'Celsius', 'temperature', 'sensors.temperature', 'line'], + 'lines': [ + [None, None, 'absolute', 1, 1000] + ]}, + 'voltage': { + 'options': [None, ' voltage', 'Volts', 'voltage', 'sensors.voltage', 'line'], + 'lines': [ + [None, None, 'absolute', 1, 1000] + ]}, + 'current': { + 'options': [None, ' current', 'Ampere', 'current', 'sensors.current', 'line'], + 'lines': [ + [None, None, 'absolute', 1, 1000] + ]}, + 'power': { + 'options': [None, ' power', 'Watt', 'power', 'sensors.power', 'line'], + 'lines': [ + [None, None, 'absolute', 1, 1000000] + ]}, + 'fan': { + 'options': [None, ' fans speed', 'Rotations/min', 'fans', 'sensors.fan', 'line'], + 'lines': [ + [None, None, 'absolute', 1, 1000] + ]}, + 'energy': { + 'options': [None, ' energy', 'Joule', 'energy', 'sensors.energy', 'areastack'], + 'lines': [ + [None, None, 'incremental', 1, 1000000] + ]}, + 'humidity': { + 'options': [None, ' humidity', 'Percent', 'humidity', 'sensors.humidity', 'line'], + 'lines': [ + [None, None, 'absolute', 1, 1000] + ]} +} + +TYPE_MAP = { + 0: 'voltage', + 1: 'fan', + 2: 'temperature', + 3: 'power', + 4: 'energy', + 5: 'current', + 6: 'humidity', + 7: 'max_main', + 16: 'vid', + 17: 'intrusion', + 18: 'max_other', + 24: 'beep_enable' +} + + +class Service(SimpleService): + def __init__(self, configuration=None, name=None): + SimpleService.__init__(self, configuration=configuration, name=name) + self.order = [] + self.definitions = {} + self.chips = [] + + def _get_data(self): + data = {} + try: + for chip in sensors.ChipIterator(): + prefix = sensors.chip_snprintf_name(chip) + for feature in sensors.FeatureIterator(chip): + sfi = sensors.SubFeatureIterator(chip, feature) + for sf in sfi: + val = sensors.get_value(chip, sf.number) + break + data[prefix + "_" + str(feature.name.decode())] = int(val * 1000) + except Exception as e: + self.error(e) + return None + + if len(data) == 0: + return None + return data + + def _create_definitions(self): + prev_chip = "" + for type in ORDER: + for chip in sensors.ChipIterator(): + chip_name = sensors.chip_snprintf_name(chip) + if len(self.chips) != 0 and not any([chip_name.startswith(ex) for ex in self.chips]): + continue + for feature in sensors.FeatureIterator(chip): + sfi = sensors.SubFeatureIterator(chip, feature) + vals = [sensors.get_value(chip, sf.number) for sf in sfi] + if vals[0] == 0: + continue + if TYPE_MAP[feature.type] == type: + # create chart + if chip_name != prev_chip: + name = chip_name + "_" + TYPE_MAP[feature.type] + if name not in self.order: + self.order.append(name) + chart_def = list(CHARTS[type]['options']) + chart_def[1] = chip_name + chart_def[1] + self.definitions[name] = {'options': chart_def} + self.definitions[name]['lines'] = [] + line = list(CHARTS[type]['lines'][0]) + line[0] = chip_name + "_" + str(feature.name.decode()) + line[1] = sensors.get_label(chip, feature) + self.definitions[name]['lines'].append(line) + prev_chip = chip_name + + def check(self): + try: + sensors.init() + except Exception as e: + self.error(e) + return False + + try: + self._create_definitions() + except Exception as e: + self.error(e) + return False + return True diff --git a/python.d/squid.chart.py b/python.d/squid.chart.py new file mode 100644 index 00000000..8300d9ba --- /dev/null +++ b/python.d/squid.chart.py @@ -0,0 +1,112 @@ +# -*- coding: utf-8 -*- +# Description: squid netdata python.d module +# Author: Pawel Krupa (paulfantom) + +from base import SocketService +import select + +# default module values (can be overridden per job in `config`) +# update_every = 2 +priority = 60000 +retries = 60 + +# charts order (can be overridden if you want less charts, or different order) +ORDER = ['clients_net', 'clients_requests', 'servers_net', 'servers_requests'] + +CHARTS = { + 'clients_net': { + 'options': [None, "Squid Client Bandwidth", "kilobits/s", "clients", "squid.clients_net", "area"], + 'lines': [ + ["client_http_kbytes_in", "in", "incremental", 8, 1], + ["client_http_kbytes_out", "out", "incremental", -8, 1], + ["client_http_hit_kbytes_out", "hits", "incremental", -8, 1] + ]}, + 'clients_requests': { + 'options': [None, "Squid Client Requests", "requests/s", "clients", "squid.clients_requests", 'line'], + 'lines': [ + ["client_http_requests", "requests", "incremental"], + ["client_http_hits", "hits", "incremental"], + ["client_http_errors", "errors", "incremental", -1, 1] + ]}, + 'servers_net': { + 'options': [None, "Squid Server Bandwidth", "kilobits/s", "servers", "squid.servers_net", "area"], + 'lines': [ + ["server_all_kbytes_in", "in", "incremental", 8, 1], + ["server_all_kbytes_out", "out", "incremental", -8, 1] + ]}, + 'servers_requests': { + 'options': [None, "Squid Server Requests", "requests/s", "servers", "squid.servers_requests", 'line'], + 'lines': [ + ["server_all_requests", "requests", "incremental"], + ["server_all_errors", "errors", "incremental", -1, 1] + ]} +} + + +class Service(SocketService): + def __init__(self, configuration=None, name=None): + SocketService.__init__(self, configuration=configuration, name=name) + self._keep_alive = True + self.request = "" + self.host = "localhost" + self.port = 3128 + self.order = ORDER + self.definitions = CHARTS + + def _get_data(self): + """ + Get data via http request + :return: dict + """ + data = {} + try: + raw = "" + for tmp in self._get_raw_data().split('\r\n'): + if tmp.startswith("sample_time"): + raw = tmp + break + if raw.startswith('<'): + self.error("invalid data received") + return None + for row in raw.split('\n'): + if row.startswith(("client", "server.all")): + tmp = row.split("=") + data[tmp[0].replace('.', '_').strip(' ')] = int(tmp[1]) + except (ValueError, AttributeError, TypeError): + self.error("invalid data received") + return None + + if len(data) == 0: + self.error("no data received") + return None + else: + return data + + def _check_raw_data(self, data): + if "Connection: keep-alive" in data[:1024]: + self._keep_alive = True + else: + self._keep_alive = False + + if data[-7:] == "\r\n0\r\n\r\n" and "Transfer-Encoding: chunked" in data[:1024]: # HTTP/1.1 response + return True + else: + return False + + def check(self): + """ + Parse essential configuration, autodetect squid configuration (if needed), and check if data is available + :return: boolean + """ + self._parse_config() + # format request + req = self.request.decode() + if not req.startswith("GET"): + req = "GET " + req + if not req.endswith(" HTTP/1.1\r\n\r\n"): + req += " HTTP/1.1\r\n\r\n" + self.request = req.encode() + if self._get_data() is not None: + return True + else: + return False diff --git a/python.d/tomcat.chart.py b/python.d/tomcat.chart.py new file mode 100644 index 00000000..31f6ab24 --- /dev/null +++ b/python.d/tomcat.chart.py @@ -0,0 +1,111 @@ +# -*- coding: utf-8 -*- +# Description: tomcat netdata python.d module +# Author: Pawel Krupa (paulfantom) + +# Python version higher than 2.7 is needed to run this module. + +from base import UrlService +import xml.etree.ElementTree as ET # phone home... +#from xml.parsers.expat import errors + +# default module values (can be overridden per job in `config`) +# update_every = 2 +priority = 60000 +retries = 60 + +# charts order (can be overridden if you want less charts, or different order) +ORDER = ['accesses', 'volume', 'threads', 'jvm'] + +CHARTS = { + 'accesses': { + 'options': [None, "Requests", "requests/s", "statistics", "tomcat.accesses", "area"], + 'lines': [ + ["accesses", None, 'incremental'] + ]}, + 'volume': { + 'options': [None, "Volume", "KB/s", "volume", "tomcat.volume", "area"], + 'lines': [ + ["volume", None, 'incremental', 1, 1024] + ]}, + 'threads': { + 'options': [None, "Threads", "current threads", "statistics", "tomcat.threads", "line"], + 'lines': [ + ["current", None, "absolute"], + ["busy", None, "absolute"] + ]}, + 'jvm': { + 'options': [None, "JVM Free Memory", "MB", "statistics", "tomcat.jvm", "area"], + 'lines': [ + ["jvm", None, "absolute", 1, 1048576] + ]} +} + + +class Service(UrlService): + def __init__(self, configuration=None, name=None): + UrlService.__init__(self, configuration=configuration, name=name) + if len(self.url) == 0: + self.url = "http://localhost:8080/manager/status?XML=true" + self.order = ORDER + self.definitions = CHARTS + self.port = 8080 + + def check(self): + if UrlService.check(self): + return True + + # get port from url + self.port = 0 + for i in self.url.split('/'): + try: + int(i[-1]) + self.port = i.split(':')[-1] + break + except: + pass + if self.port == 0: + self.port = 80 + + test = self._get_data() + if test is None or len(test) == 0: + return False + else: + return True + + def _get_data(self): + """ + Format data received from http request + :return: dict + """ + try: + raw = self._get_raw_data() + try: + data = ET.fromstring(raw) + except ET.ParseError as e: + # if e.code == errors.codes[errors.XML_ERROR_JUNK_AFTER_DOC_ELEMENT]: + if e.code == 9: + end = raw.find('</status>') + end += 9 + raw = raw[:end] + self.debug(raw) + data = ET.fromstring(raw) + else: + raise Exception(e) + + memory = data.find('./jvm/memory') + threads = data.find("./connector[@name='\"http-bio-" + str(self.port) + "\"']/threadInfo") + requests = data.find("./connector[@name='\"http-bio-" + str(self.port) + "\"']/requestInfo") + + return {'accesses': requests.attrib['requestCount'], + 'volume': requests.attrib['bytesSent'], + 'current': threads.attrib['currentThreadCount'], + 'busy': threads.attrib['currentThreadsBusy'], + 'jvm': memory.attrib['free']} + except (ValueError, AttributeError) as e: + self.debug(str(e)) + return None + except SyntaxError as e: + self.error("Tomcat module needs python 2.7 at least. Stopping") + self.debug(str(e)) + except Exception as e: + self.debug(str(e)) |