summaryrefslogtreecommitdiffstats
path: root/src/lib-charset
diff options
context:
space:
mode:
Diffstat (limited to 'src/lib-charset')
-rw-r--r--src/lib-charset/Makefile.am37
-rw-r--r--src/lib-charset/Makefile.in862
-rw-r--r--src/lib-charset/charset-iconv.c147
-rw-r--r--src/lib-charset/charset-utf8-only.c51
-rw-r--r--src/lib-charset/charset-utf8-private.h21
-rw-r--r--src/lib-charset/charset-utf8.c99
-rw-r--r--src/lib-charset/charset-utf8.h53
-rw-r--r--src/lib-charset/test-charset.c231
8 files changed, 1501 insertions, 0 deletions
diff --git a/src/lib-charset/Makefile.am b/src/lib-charset/Makefile.am
new file mode 100644
index 0000000..5c41f07
--- /dev/null
+++ b/src/lib-charset/Makefile.am
@@ -0,0 +1,37 @@
+noinst_LTLIBRARIES = libcharset.la
+
+AM_CPPFLAGS = \
+ -I$(top_srcdir)/src/lib \
+ -I$(top_srcdir)/src/lib-test
+
+libcharset_la_LIBADD = $(LTLIBICONV)
+libcharset_la_SOURCES = \
+ charset-iconv.c \
+ charset-utf8.c \
+ charset-utf8-only.c
+
+headers = \
+ charset-utf8.h \
+ charset-utf8-private.h
+
+pkginc_libdir=$(pkgincludedir)
+pkginc_lib_HEADERS = $(headers)
+
+test_programs = \
+ test-charset
+
+noinst_PROGRAMS = $(test_programs)
+
+test_libs = \
+ ../lib-test/libtest.la \
+ ../lib/liblib.la
+test_deps = $(noinst_LTLIBRARIES) $(test_libs)
+
+test_charset_SOURCES = test-charset.c
+test_charset_LDADD = libcharset.la $(test_libs)
+test_charset_DEPENDENCIES = libcharset.la $(test_deps)
+
+check-local:
+ for bin in $(test_programs); do \
+ if ! $(RUN_TEST) ./$$bin; then exit 1; fi; \
+ done
diff --git a/src/lib-charset/Makefile.in b/src/lib-charset/Makefile.in
new file mode 100644
index 0000000..6c18a40
--- /dev/null
+++ b/src/lib-charset/Makefile.in
@@ -0,0 +1,862 @@
+# Makefile.in generated by automake 1.16.1 from Makefile.am.
+# @configure_input@
+
+# Copyright (C) 1994-2018 Free Software Foundation, Inc.
+
+# This Makefile.in is free software; the Free Software Foundation
+# gives unlimited permission to copy and/or distribute it,
+# with or without modifications, as long as this notice is preserved.
+
+# This program is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY, to the extent permitted by law; without
+# even the implied warranty of MERCHANTABILITY or FITNESS FOR A
+# PARTICULAR PURPOSE.
+
+@SET_MAKE@
+
+
+
+VPATH = @srcdir@
+am__is_gnu_make = { \
+ if test -z '$(MAKELEVEL)'; then \
+ false; \
+ elif test -n '$(MAKE_HOST)'; then \
+ true; \
+ elif test -n '$(MAKE_VERSION)' && test -n '$(CURDIR)'; then \
+ true; \
+ else \
+ false; \
+ fi; \
+}
+am__make_running_with_option = \
+ case $${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@
+noinst_PROGRAMS = $(am__EXEEXT_1)
+subdir = src/lib-charset
+ACLOCAL_M4 = $(top_srcdir)/aclocal.m4
+am__aclocal_m4_deps = $(top_srcdir)/m4/ac_checktype2.m4 \
+ $(top_srcdir)/m4/ac_typeof.m4 $(top_srcdir)/m4/arc4random.m4 \
+ $(top_srcdir)/m4/blockdev.m4 $(top_srcdir)/m4/c99_vsnprintf.m4 \
+ $(top_srcdir)/m4/clock_gettime.m4 $(top_srcdir)/m4/crypt.m4 \
+ $(top_srcdir)/m4/crypt_xpg6.m4 $(top_srcdir)/m4/dbqlk.m4 \
+ $(top_srcdir)/m4/dirent_dtype.m4 $(top_srcdir)/m4/dovecot.m4 \
+ $(top_srcdir)/m4/fd_passing.m4 $(top_srcdir)/m4/fdatasync.m4 \
+ $(top_srcdir)/m4/flexible_array_member.m4 \
+ $(top_srcdir)/m4/glibc.m4 $(top_srcdir)/m4/gmtime_max.m4 \
+ $(top_srcdir)/m4/gmtime_tm_gmtoff.m4 \
+ $(top_srcdir)/m4/ioloop.m4 $(top_srcdir)/m4/iovec.m4 \
+ $(top_srcdir)/m4/ipv6.m4 $(top_srcdir)/m4/libcap.m4 \
+ $(top_srcdir)/m4/libtool.m4 $(top_srcdir)/m4/libwrap.m4 \
+ $(top_srcdir)/m4/linux_mremap.m4 $(top_srcdir)/m4/ltoptions.m4 \
+ $(top_srcdir)/m4/ltsugar.m4 $(top_srcdir)/m4/ltversion.m4 \
+ $(top_srcdir)/m4/lt~obsolete.m4 $(top_srcdir)/m4/mmap_write.m4 \
+ $(top_srcdir)/m4/mntctl.m4 $(top_srcdir)/m4/modules.m4 \
+ $(top_srcdir)/m4/notify.m4 $(top_srcdir)/m4/nsl.m4 \
+ $(top_srcdir)/m4/off_t_max.m4 $(top_srcdir)/m4/pkg.m4 \
+ $(top_srcdir)/m4/pr_set_dumpable.m4 \
+ $(top_srcdir)/m4/q_quotactl.m4 $(top_srcdir)/m4/quota.m4 \
+ $(top_srcdir)/m4/random.m4 $(top_srcdir)/m4/rlimit.m4 \
+ $(top_srcdir)/m4/sendfile.m4 $(top_srcdir)/m4/size_t_signed.m4 \
+ $(top_srcdir)/m4/sockpeercred.m4 $(top_srcdir)/m4/sql.m4 \
+ $(top_srcdir)/m4/ssl.m4 $(top_srcdir)/m4/st_tim.m4 \
+ $(top_srcdir)/m4/static_array.m4 $(top_srcdir)/m4/test_with.m4 \
+ $(top_srcdir)/m4/time_t.m4 $(top_srcdir)/m4/typeof.m4 \
+ $(top_srcdir)/m4/typeof_dev_t.m4 \
+ $(top_srcdir)/m4/uoff_t_max.m4 $(top_srcdir)/m4/vararg.m4 \
+ $(top_srcdir)/m4/want_apparmor.m4 \
+ $(top_srcdir)/m4/want_bsdauth.m4 \
+ $(top_srcdir)/m4/want_bzlib.m4 \
+ $(top_srcdir)/m4/want_cassandra.m4 \
+ $(top_srcdir)/m4/want_cdb.m4 \
+ $(top_srcdir)/m4/want_checkpassword.m4 \
+ $(top_srcdir)/m4/want_clucene.m4 $(top_srcdir)/m4/want_db.m4 \
+ $(top_srcdir)/m4/want_gssapi.m4 $(top_srcdir)/m4/want_icu.m4 \
+ $(top_srcdir)/m4/want_ldap.m4 $(top_srcdir)/m4/want_lua.m4 \
+ $(top_srcdir)/m4/want_lz4.m4 $(top_srcdir)/m4/want_lzma.m4 \
+ $(top_srcdir)/m4/want_mysql.m4 $(top_srcdir)/m4/want_pam.m4 \
+ $(top_srcdir)/m4/want_passwd.m4 $(top_srcdir)/m4/want_pgsql.m4 \
+ $(top_srcdir)/m4/want_prefetch.m4 \
+ $(top_srcdir)/m4/want_shadow.m4 \
+ $(top_srcdir)/m4/want_sodium.m4 $(top_srcdir)/m4/want_solr.m4 \
+ $(top_srcdir)/m4/want_sqlite.m4 \
+ $(top_srcdir)/m4/want_stemmer.m4 \
+ $(top_srcdir)/m4/want_systemd.m4 \
+ $(top_srcdir)/m4/want_textcat.m4 \
+ $(top_srcdir)/m4/want_unwind.m4 $(top_srcdir)/m4/want_zlib.m4 \
+ $(top_srcdir)/m4/want_zstd.m4 $(top_srcdir)/configure.ac
+am__configure_deps = $(am__aclocal_m4_deps) $(CONFIGURE_DEPENDENCIES) \
+ $(ACLOCAL_M4)
+DIST_COMMON = $(srcdir)/Makefile.am $(pkginc_lib_HEADERS) \
+ $(am__DIST_COMMON)
+mkinstalldirs = $(install_sh) -d
+CONFIG_HEADER = $(top_builddir)/config.h
+CONFIG_CLEAN_FILES =
+CONFIG_CLEAN_VPATH_FILES =
+am__EXEEXT_1 = test-charset$(EXEEXT)
+PROGRAMS = $(noinst_PROGRAMS)
+LTLIBRARIES = $(noinst_LTLIBRARIES)
+am__DEPENDENCIES_1 =
+libcharset_la_DEPENDENCIES = $(am__DEPENDENCIES_1)
+am_libcharset_la_OBJECTS = charset-iconv.lo charset-utf8.lo \
+ charset-utf8-only.lo
+libcharset_la_OBJECTS = $(am_libcharset_la_OBJECTS)
+AM_V_lt = $(am__v_lt_@AM_V@)
+am__v_lt_ = $(am__v_lt_@AM_DEFAULT_V@)
+am__v_lt_0 = --silent
+am__v_lt_1 =
+am_test_charset_OBJECTS = test-charset.$(OBJEXT)
+test_charset_OBJECTS = $(am_test_charset_OBJECTS)
+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 =
+DEFAULT_INCLUDES = -I.@am__isrc@ -I$(top_builddir)
+depcomp = $(SHELL) $(top_srcdir)/depcomp
+am__maybe_remake_depfiles = depfiles
+am__depfiles_remade = ./$(DEPDIR)/charset-iconv.Plo \
+ ./$(DEPDIR)/charset-utf8-only.Plo ./$(DEPDIR)/charset-utf8.Plo \
+ ./$(DEPDIR)/test-charset.Po
+am__mv = mv -f
+COMPILE = $(CC) $(DEFS) $(DEFAULT_INCLUDES) $(INCLUDES) $(AM_CPPFLAGS) \
+ $(CPPFLAGS) $(AM_CFLAGS) $(CFLAGS)
+LTCOMPILE = $(LIBTOOL) $(AM_V_lt) --tag=CC $(AM_LIBTOOLFLAGS) \
+ $(LIBTOOLFLAGS) --mode=compile $(CC) $(DEFS) \
+ $(DEFAULT_INCLUDES) $(INCLUDES) $(AM_CPPFLAGS) $(CPPFLAGS) \
+ $(AM_CFLAGS) $(CFLAGS)
+AM_V_CC = $(am__v_CC_@AM_V@)
+am__v_CC_ = $(am__v_CC_@AM_DEFAULT_V@)
+am__v_CC_0 = @echo " CC " $@;
+am__v_CC_1 =
+CCLD = $(CC)
+LINK = $(LIBTOOL) $(AM_V_lt) --tag=CC $(AM_LIBTOOLFLAGS) \
+ $(LIBTOOLFLAGS) --mode=link $(CCLD) $(AM_CFLAGS) $(CFLAGS) \
+ $(AM_LDFLAGS) $(LDFLAGS) -o $@
+AM_V_CCLD = $(am__v_CCLD_@AM_V@)
+am__v_CCLD_ = $(am__v_CCLD_@AM_DEFAULT_V@)
+am__v_CCLD_0 = @echo " CCLD " $@;
+am__v_CCLD_1 =
+SOURCES = $(libcharset_la_SOURCES) $(test_charset_SOURCES)
+DIST_SOURCES = $(libcharset_la_SOURCES) $(test_charset_SOURCES)
+am__can_run_installinfo = \
+ case $$AM_UPDATE_INFO_DIR in \
+ n|no|NO) false;; \
+ *) (install-info --version) >/dev/null 2>&1;; \
+ esac
+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 = "$(DESTDIR)$(pkginc_libdir)"
+HEADERS = $(pkginc_lib_HEADERS)
+am__tagged_files = $(HEADERS) $(SOURCES) $(TAGS_FILES) $(LISP)
+# Read a list of newline-separated strings from the standard input,
+# and print each of them once, without duplicates. Input order is
+# *not* preserved.
+am__uniquify_input = $(AWK) '\
+ BEGIN { nonempty = 0; } \
+ { items[$$0] = 1; nonempty = 1; } \
+ END { if (nonempty) { for (i in items) print i; }; } \
+'
+# Make sure the list of sources is unique. This is necessary because,
+# e.g., the same source file might be shared among _SOURCES variables
+# for different programs/libraries.
+am__define_uniq_tagged_files = \
+ list='$(am__tagged_files)'; \
+ unique=`for i in $$list; do \
+ if test -f "$$i"; then echo $$i; else echo $(srcdir)/$$i; fi; \
+ done | $(am__uniquify_input)`
+ETAGS = etags
+CTAGS = ctags
+am__DIST_COMMON = $(srcdir)/Makefile.in $(top_srcdir)/depcomp
+DISTFILES = $(DIST_COMMON) $(DIST_SOURCES) $(TEXINFOS) $(EXTRA_DIST)
+ACLOCAL = @ACLOCAL@
+ACLOCAL_AMFLAGS = @ACLOCAL_AMFLAGS@
+AMTAR = @AMTAR@
+AM_DEFAULT_VERBOSITY = @AM_DEFAULT_VERBOSITY@
+APPARMOR_LIBS = @APPARMOR_LIBS@
+AR = @AR@
+AUTH_CFLAGS = @AUTH_CFLAGS@
+AUTH_LIBS = @AUTH_LIBS@
+AUTOCONF = @AUTOCONF@
+AUTOHEADER = @AUTOHEADER@
+AUTOMAKE = @AUTOMAKE@
+AWK = @AWK@
+BINARY_CFLAGS = @BINARY_CFLAGS@
+BINARY_LDFLAGS = @BINARY_LDFLAGS@
+BISON = @BISON@
+CASSANDRA_CFLAGS = @CASSANDRA_CFLAGS@
+CASSANDRA_LIBS = @CASSANDRA_LIBS@
+CC = @CC@
+CCDEPMODE = @CCDEPMODE@
+CDB_LIBS = @CDB_LIBS@
+CFLAGS = @CFLAGS@
+CLUCENE_CFLAGS = @CLUCENE_CFLAGS@
+CLUCENE_LIBS = @CLUCENE_LIBS@
+COMPRESS_LIBS = @COMPRESS_LIBS@
+CPP = @CPP@
+CPPFLAGS = @CPPFLAGS@
+CRYPT_LIBS = @CRYPT_LIBS@
+CXX = @CXX@
+CXXCPP = @CXXCPP@
+CXXDEPMODE = @CXXDEPMODE@
+CXXFLAGS = @CXXFLAGS@
+CYGPATH_W = @CYGPATH_W@
+DEFS = @DEFS@
+DEPDIR = @DEPDIR@
+DICT_LIBS = @DICT_LIBS@
+DLLIB = @DLLIB@
+DLLTOOL = @DLLTOOL@
+DSYMUTIL = @DSYMUTIL@
+DUMPBIN = @DUMPBIN@
+ECHO_C = @ECHO_C@
+ECHO_N = @ECHO_N@
+ECHO_T = @ECHO_T@
+EGREP = @EGREP@
+EXEEXT = @EXEEXT@
+FGREP = @FGREP@
+FLEX = @FLEX@
+FUZZER_CPPFLAGS = @FUZZER_CPPFLAGS@
+FUZZER_LDFLAGS = @FUZZER_LDFLAGS@
+GREP = @GREP@
+INSTALL = @INSTALL@
+INSTALL_DATA = @INSTALL_DATA@
+INSTALL_PROGRAM = @INSTALL_PROGRAM@
+INSTALL_SCRIPT = @INSTALL_SCRIPT@
+INSTALL_STRIP_PROGRAM = @INSTALL_STRIP_PROGRAM@
+KRB5CONFIG = @KRB5CONFIG@
+KRB5_CFLAGS = @KRB5_CFLAGS@
+KRB5_LIBS = @KRB5_LIBS@
+LD = @LD@
+LDAP_LIBS = @LDAP_LIBS@
+LDFLAGS = @LDFLAGS@
+LD_NO_WHOLE_ARCHIVE = @LD_NO_WHOLE_ARCHIVE@
+LD_WHOLE_ARCHIVE = @LD_WHOLE_ARCHIVE@
+LIBCAP = @LIBCAP@
+LIBDOVECOT = @LIBDOVECOT@
+LIBDOVECOT_COMPRESS = @LIBDOVECOT_COMPRESS@
+LIBDOVECOT_DEPS = @LIBDOVECOT_DEPS@
+LIBDOVECOT_DSYNC = @LIBDOVECOT_DSYNC@
+LIBDOVECOT_LA_LIBS = @LIBDOVECOT_LA_LIBS@
+LIBDOVECOT_LDA = @LIBDOVECOT_LDA@
+LIBDOVECOT_LDAP = @LIBDOVECOT_LDAP@
+LIBDOVECOT_LIBFTS = @LIBDOVECOT_LIBFTS@
+LIBDOVECOT_LIBFTS_DEPS = @LIBDOVECOT_LIBFTS_DEPS@
+LIBDOVECOT_LOGIN = @LIBDOVECOT_LOGIN@
+LIBDOVECOT_LUA = @LIBDOVECOT_LUA@
+LIBDOVECOT_LUA_DEPS = @LIBDOVECOT_LUA_DEPS@
+LIBDOVECOT_SQL = @LIBDOVECOT_SQL@
+LIBDOVECOT_STORAGE = @LIBDOVECOT_STORAGE@
+LIBDOVECOT_STORAGE_DEPS = @LIBDOVECOT_STORAGE_DEPS@
+LIBEXTTEXTCAT_CFLAGS = @LIBEXTTEXTCAT_CFLAGS@
+LIBEXTTEXTCAT_LIBS = @LIBEXTTEXTCAT_LIBS@
+LIBICONV = @LIBICONV@
+LIBICU_CFLAGS = @LIBICU_CFLAGS@
+LIBICU_LIBS = @LIBICU_LIBS@
+LIBOBJS = @LIBOBJS@
+LIBS = @LIBS@
+LIBSODIUM_CFLAGS = @LIBSODIUM_CFLAGS@
+LIBSODIUM_LIBS = @LIBSODIUM_LIBS@
+LIBTIRPC_CFLAGS = @LIBTIRPC_CFLAGS@
+LIBTIRPC_LIBS = @LIBTIRPC_LIBS@
+LIBTOOL = @LIBTOOL@
+LIBUNWIND_CFLAGS = @LIBUNWIND_CFLAGS@
+LIBUNWIND_LIBS = @LIBUNWIND_LIBS@
+LIBWRAP_LIBS = @LIBWRAP_LIBS@
+LINKED_STORAGE_LDADD = @LINKED_STORAGE_LDADD@
+LIPO = @LIPO@
+LN_S = @LN_S@
+LTLIBICONV = @LTLIBICONV@
+LTLIBOBJS = @LTLIBOBJS@
+LT_SYS_LIBRARY_PATH = @LT_SYS_LIBRARY_PATH@
+LUA_CFLAGS = @LUA_CFLAGS@
+LUA_LIBS = @LUA_LIBS@
+MAINT = @MAINT@
+MAKEINFO = @MAKEINFO@
+MANIFEST_TOOL = @MANIFEST_TOOL@
+MKDIR_P = @MKDIR_P@
+MODULE_LIBS = @MODULE_LIBS@
+MODULE_SUFFIX = @MODULE_SUFFIX@
+MYSQL_CFLAGS = @MYSQL_CFLAGS@
+MYSQL_CONFIG = @MYSQL_CONFIG@
+MYSQL_LIBS = @MYSQL_LIBS@
+NM = @NM@
+NMEDIT = @NMEDIT@
+NOPLUGIN_LDFLAGS = @NOPLUGIN_LDFLAGS@
+OBJDUMP = @OBJDUMP@
+OBJEXT = @OBJEXT@
+OTOOL = @OTOOL@
+OTOOL64 = @OTOOL64@
+PACKAGE = @PACKAGE@
+PACKAGE_BUGREPORT = @PACKAGE_BUGREPORT@
+PACKAGE_NAME = @PACKAGE_NAME@
+PACKAGE_STRING = @PACKAGE_STRING@
+PACKAGE_TARNAME = @PACKAGE_TARNAME@
+PACKAGE_URL = @PACKAGE_URL@
+PACKAGE_VERSION = @PACKAGE_VERSION@
+PANDOC = @PANDOC@
+PATH_SEPARATOR = @PATH_SEPARATOR@
+PGSQL_CFLAGS = @PGSQL_CFLAGS@
+PGSQL_LIBS = @PGSQL_LIBS@
+PG_CONFIG = @PG_CONFIG@
+PIE_CFLAGS = @PIE_CFLAGS@
+PIE_LDFLAGS = @PIE_LDFLAGS@
+PKG_CONFIG = @PKG_CONFIG@
+PKG_CONFIG_LIBDIR = @PKG_CONFIG_LIBDIR@
+PKG_CONFIG_PATH = @PKG_CONFIG_PATH@
+QUOTA_LIBS = @QUOTA_LIBS@
+RANLIB = @RANLIB@
+RELRO_LDFLAGS = @RELRO_LDFLAGS@
+RPCGEN = @RPCGEN@
+RUN_TEST = @RUN_TEST@
+SED = @SED@
+SETTING_FILES = @SETTING_FILES@
+SET_MAKE = @SET_MAKE@
+SHELL = @SHELL@
+SQLITE_CFLAGS = @SQLITE_CFLAGS@
+SQLITE_LIBS = @SQLITE_LIBS@
+SQL_CFLAGS = @SQL_CFLAGS@
+SQL_LIBS = @SQL_LIBS@
+SSL_CFLAGS = @SSL_CFLAGS@
+SSL_LIBS = @SSL_LIBS@
+STRIP = @STRIP@
+SYSTEMD_CFLAGS = @SYSTEMD_CFLAGS@
+SYSTEMD_LIBS = @SYSTEMD_LIBS@
+VALGRIND = @VALGRIND@
+VERSION = @VERSION@
+ZSTD_CFLAGS = @ZSTD_CFLAGS@
+ZSTD_LIBS = @ZSTD_LIBS@
+abs_builddir = @abs_builddir@
+abs_srcdir = @abs_srcdir@
+abs_top_builddir = @abs_top_builddir@
+abs_top_srcdir = @abs_top_srcdir@
+ac_ct_AR = @ac_ct_AR@
+ac_ct_CC = @ac_ct_CC@
+ac_ct_CXX = @ac_ct_CXX@
+ac_ct_DUMPBIN = @ac_ct_DUMPBIN@
+am__include = @am__include@
+am__leading_dot = @am__leading_dot@
+am__quote = @am__quote@
+am__tar = @am__tar@
+am__untar = @am__untar@
+bindir = @bindir@
+build = @build@
+build_alias = @build_alias@
+build_cpu = @build_cpu@
+build_os = @build_os@
+build_vendor = @build_vendor@
+builddir = @builddir@
+datadir = @datadir@
+datarootdir = @datarootdir@
+dict_drivers = @dict_drivers@
+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@
+mandir = @mandir@
+mkdir_p = @mkdir_p@
+moduledir = @moduledir@
+oldincludedir = @oldincludedir@
+pdfdir = @pdfdir@
+prefix = @prefix@
+program_transform_name = @program_transform_name@
+psdir = @psdir@
+rundir = @rundir@
+runstatedir = @runstatedir@
+sbindir = @sbindir@
+sharedstatedir = @sharedstatedir@
+sql_drivers = @sql_drivers@
+srcdir = @srcdir@
+ssldir = @ssldir@
+statedir = @statedir@
+sysconfdir = @sysconfdir@
+systemdservicetype = @systemdservicetype@
+systemdsystemunitdir = @systemdsystemunitdir@
+target_alias = @target_alias@
+top_build_prefix = @top_build_prefix@
+top_builddir = @top_builddir@
+top_srcdir = @top_srcdir@
+noinst_LTLIBRARIES = libcharset.la
+AM_CPPFLAGS = \
+ -I$(top_srcdir)/src/lib \
+ -I$(top_srcdir)/src/lib-test
+
+libcharset_la_LIBADD = $(LTLIBICONV)
+libcharset_la_SOURCES = \
+ charset-iconv.c \
+ charset-utf8.c \
+ charset-utf8-only.c
+
+headers = \
+ charset-utf8.h \
+ charset-utf8-private.h
+
+pkginc_libdir = $(pkgincludedir)
+pkginc_lib_HEADERS = $(headers)
+test_programs = \
+ test-charset
+
+test_libs = \
+ ../lib-test/libtest.la \
+ ../lib/liblib.la
+
+test_deps = $(noinst_LTLIBRARIES) $(test_libs)
+test_charset_SOURCES = test-charset.c
+test_charset_LDADD = libcharset.la $(test_libs)
+test_charset_DEPENDENCIES = libcharset.la $(test_deps)
+all: all-am
+
+.SUFFIXES:
+.SUFFIXES: .c .lo .o .obj
+$(srcdir)/Makefile.in: @MAINTAINER_MODE_TRUE@ $(srcdir)/Makefile.am $(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) --foreign src/lib-charset/Makefile'; \
+ $(am__cd) $(top_srcdir) && \
+ $(AUTOMAKE) --foreign src/lib-charset/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__maybe_remake_depfiles)'; \
+ cd $(top_builddir) && $(SHELL) ./config.status $(subdir)/$@ $(am__maybe_remake_depfiles);; \
+ esac;
+
+$(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):
+
+clean-noinstPROGRAMS:
+ @list='$(noinst_PROGRAMS)'; test -n "$$list" || exit 0; \
+ echo " rm -f" $$list; \
+ rm -f $$list || exit $$?; \
+ test -n "$(EXEEXT)" || exit 0; \
+ list=`for p in $$list; do echo "$$p"; done | sed 's/$(EXEEXT)$$//'`; \
+ echo " rm -f" $$list; \
+ rm -f $$list
+
+clean-noinstLTLIBRARIES:
+ -test -z "$(noinst_LTLIBRARIES)" || rm -f $(noinst_LTLIBRARIES)
+ @list='$(noinst_LTLIBRARIES)'; \
+ locs=`for p in $$list; do echo $$p; done | \
+ sed 's|^[^/]*$$|.|; s|/[^/]*$$||; s|$$|/so_locations|' | \
+ sort -u`; \
+ test -z "$$locs" || { \
+ echo rm -f $${locs}; \
+ rm -f $${locs}; \
+ }
+
+libcharset.la: $(libcharset_la_OBJECTS) $(libcharset_la_DEPENDENCIES) $(EXTRA_libcharset_la_DEPENDENCIES)
+ $(AM_V_CCLD)$(LINK) $(libcharset_la_OBJECTS) $(libcharset_la_LIBADD) $(LIBS)
+
+test-charset$(EXEEXT): $(test_charset_OBJECTS) $(test_charset_DEPENDENCIES) $(EXTRA_test_charset_DEPENDENCIES)
+ @rm -f test-charset$(EXEEXT)
+ $(AM_V_CCLD)$(LINK) $(test_charset_OBJECTS) $(test_charset_LDADD) $(LIBS)
+
+mostlyclean-compile:
+ -rm -f *.$(OBJEXT)
+
+distclean-compile:
+ -rm -f *.tab.c
+
+@AMDEP_TRUE@@am__include@ @am__quote@./$(DEPDIR)/charset-iconv.Plo@am__quote@ # am--include-marker
+@AMDEP_TRUE@@am__include@ @am__quote@./$(DEPDIR)/charset-utf8-only.Plo@am__quote@ # am--include-marker
+@AMDEP_TRUE@@am__include@ @am__quote@./$(DEPDIR)/charset-utf8.Plo@am__quote@ # am--include-marker
+@AMDEP_TRUE@@am__include@ @am__quote@./$(DEPDIR)/test-charset.Po@am__quote@ # am--include-marker
+
+$(am__depfiles_remade):
+ @$(MKDIR_P) $(@D)
+ @echo '# dummy' >$@-t && $(am__mv) $@-t $@
+
+am--depfiles: $(am__depfiles_remade)
+
+.c.o:
+@am__fastdepCC_TRUE@ $(AM_V_CC)$(COMPILE) -MT $@ -MD -MP -MF $(DEPDIR)/$*.Tpo -c -o $@ $<
+@am__fastdepCC_TRUE@ $(AM_V_at)$(am__mv) $(DEPDIR)/$*.Tpo $(DEPDIR)/$*.Po
+@AMDEP_TRUE@@am__fastdepCC_FALSE@ $(AM_V_CC)source='$<' object='$@' libtool=no @AMDEPBACKSLASH@
+@AMDEP_TRUE@@am__fastdepCC_FALSE@ DEPDIR=$(DEPDIR) $(CCDEPMODE) $(depcomp) @AMDEPBACKSLASH@
+@am__fastdepCC_FALSE@ $(AM_V_CC@am__nodep@)$(COMPILE) -c -o $@ $<
+
+.c.obj:
+@am__fastdepCC_TRUE@ $(AM_V_CC)$(COMPILE) -MT $@ -MD -MP -MF $(DEPDIR)/$*.Tpo -c -o $@ `$(CYGPATH_W) '$<'`
+@am__fastdepCC_TRUE@ $(AM_V_at)$(am__mv) $(DEPDIR)/$*.Tpo $(DEPDIR)/$*.Po
+@AMDEP_TRUE@@am__fastdepCC_FALSE@ $(AM_V_CC)source='$<' object='$@' libtool=no @AMDEPBACKSLASH@
+@AMDEP_TRUE@@am__fastdepCC_FALSE@ DEPDIR=$(DEPDIR) $(CCDEPMODE) $(depcomp) @AMDEPBACKSLASH@
+@am__fastdepCC_FALSE@ $(AM_V_CC@am__nodep@)$(COMPILE) -c -o $@ `$(CYGPATH_W) '$<'`
+
+.c.lo:
+@am__fastdepCC_TRUE@ $(AM_V_CC)$(LTCOMPILE) -MT $@ -MD -MP -MF $(DEPDIR)/$*.Tpo -c -o $@ $<
+@am__fastdepCC_TRUE@ $(AM_V_at)$(am__mv) $(DEPDIR)/$*.Tpo $(DEPDIR)/$*.Plo
+@AMDEP_TRUE@@am__fastdepCC_FALSE@ $(AM_V_CC)source='$<' object='$@' libtool=yes @AMDEPBACKSLASH@
+@AMDEP_TRUE@@am__fastdepCC_FALSE@ DEPDIR=$(DEPDIR) $(CCDEPMODE) $(depcomp) @AMDEPBACKSLASH@
+@am__fastdepCC_FALSE@ $(AM_V_CC@am__nodep@)$(LTCOMPILE) -c -o $@ $<
+
+mostlyclean-libtool:
+ -rm -f *.lo
+
+clean-libtool:
+ -rm -rf .libs _libs
+install-pkginc_libHEADERS: $(pkginc_lib_HEADERS)
+ @$(NORMAL_INSTALL)
+ @list='$(pkginc_lib_HEADERS)'; test -n "$(pkginc_libdir)" || list=; \
+ if test -n "$$list"; then \
+ echo " $(MKDIR_P) '$(DESTDIR)$(pkginc_libdir)'"; \
+ $(MKDIR_P) "$(DESTDIR)$(pkginc_libdir)" || 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_HEADER) $$files '$(DESTDIR)$(pkginc_libdir)'"; \
+ $(INSTALL_HEADER) $$files "$(DESTDIR)$(pkginc_libdir)" || exit $$?; \
+ done
+
+uninstall-pkginc_libHEADERS:
+ @$(NORMAL_UNINSTALL)
+ @list='$(pkginc_lib_HEADERS)'; test -n "$(pkginc_libdir)" || list=; \
+ files=`for p in $$list; do echo $$p; done | sed -e 's|^.*/||'`; \
+ dir='$(DESTDIR)$(pkginc_libdir)'; $(am__uninstall_files_from_dir)
+
+ID: $(am__tagged_files)
+ $(am__define_uniq_tagged_files); mkid -fID $$unique
+tags: tags-am
+TAGS: tags
+
+tags-am: $(TAGS_DEPENDENCIES) $(am__tagged_files)
+ set x; \
+ here=`pwd`; \
+ $(am__define_uniq_tagged_files); \
+ shift; \
+ if test -z "$(ETAGS_ARGS)$$*$$unique"; then :; else \
+ test -n "$$unique" || unique=$$empty_fix; \
+ if test $$# -gt 0; then \
+ $(ETAGS) $(ETAGSFLAGS) $(AM_ETAGSFLAGS) $(ETAGS_ARGS) \
+ "$$@" $$unique; \
+ else \
+ $(ETAGS) $(ETAGSFLAGS) $(AM_ETAGSFLAGS) $(ETAGS_ARGS) \
+ $$unique; \
+ fi; \
+ fi
+ctags: ctags-am
+
+CTAGS: ctags
+ctags-am: $(TAGS_DEPENDENCIES) $(am__tagged_files)
+ $(am__define_uniq_tagged_files); \
+ test -z "$(CTAGS_ARGS)$$unique" \
+ || $(CTAGS) $(CTAGSFLAGS) $(AM_CTAGSFLAGS) $(CTAGS_ARGS) \
+ $$unique
+
+GTAGS:
+ here=`$(am__cd) $(top_builddir) && pwd` \
+ && $(am__cd) $(top_srcdir) \
+ && gtags -i $(GTAGS_ARGS) "$$here"
+cscopelist: cscopelist-am
+
+cscopelist-am: $(am__tagged_files)
+ list='$(am__tagged_files)'; \
+ case "$(srcdir)" in \
+ [\\/]* | ?:[\\/]*) sdir="$(srcdir)" ;; \
+ *) sdir=$(subdir)/$(srcdir) ;; \
+ esac; \
+ for i in $$list; do \
+ if test -f "$$i"; then \
+ echo "$(subdir)/$$i"; \
+ else \
+ echo "$$sdir/$$i"; \
+ fi; \
+ done >> $(top_builddir)/cscope.files
+
+distclean-tags:
+ -rm -f TAGS ID GTAGS GRTAGS GSYMS GPATH tags
+
+distdir: $(BUILT_SOURCES)
+ $(MAKE) $(AM_MAKEFLAGS) distdir-am
+
+distdir-am: $(DISTFILES)
+ @srcdirstrip=`echo "$(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
+ $(MAKE) $(AM_MAKEFLAGS) check-local
+check: check-am
+all-am: Makefile $(PROGRAMS) $(LTLIBRARIES) $(HEADERS)
+installdirs:
+ for dir in "$(DESTDIR)$(pkginc_libdir)"; 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:
+
+distclean-generic:
+ -test -z "$(CONFIG_CLEAN_FILES)" || rm -f $(CONFIG_CLEAN_FILES)
+ -test . = "$(srcdir)" || test -z "$(CONFIG_CLEAN_VPATH_FILES)" || rm -f $(CONFIG_CLEAN_VPATH_FILES)
+
+maintainer-clean-generic:
+ @echo "This command is intended for maintainers to use"
+ @echo "it deletes files that may require special tools to rebuild."
+clean: clean-am
+
+clean-am: clean-generic clean-libtool clean-noinstLTLIBRARIES \
+ clean-noinstPROGRAMS mostlyclean-am
+
+distclean: distclean-am
+ -rm -f ./$(DEPDIR)/charset-iconv.Plo
+ -rm -f ./$(DEPDIR)/charset-utf8-only.Plo
+ -rm -f ./$(DEPDIR)/charset-utf8.Plo
+ -rm -f ./$(DEPDIR)/test-charset.Po
+ -rm -f Makefile
+distclean-am: clean-am distclean-compile distclean-generic \
+ distclean-tags
+
+dvi: dvi-am
+
+dvi-am:
+
+html: html-am
+
+html-am:
+
+info: info-am
+
+info-am:
+
+install-data-am: install-pkginc_libHEADERS
+
+install-dvi: install-dvi-am
+
+install-dvi-am:
+
+install-exec-am:
+
+install-html: install-html-am
+
+install-html-am:
+
+install-info: install-info-am
+
+install-info-am:
+
+install-man:
+
+install-pdf: install-pdf-am
+
+install-pdf-am:
+
+install-ps: install-ps-am
+
+install-ps-am:
+
+installcheck-am:
+
+maintainer-clean: maintainer-clean-am
+ -rm -f ./$(DEPDIR)/charset-iconv.Plo
+ -rm -f ./$(DEPDIR)/charset-utf8-only.Plo
+ -rm -f ./$(DEPDIR)/charset-utf8.Plo
+ -rm -f ./$(DEPDIR)/test-charset.Po
+ -rm -f Makefile
+maintainer-clean-am: distclean-am maintainer-clean-generic
+
+mostlyclean: mostlyclean-am
+
+mostlyclean-am: mostlyclean-compile mostlyclean-generic \
+ mostlyclean-libtool
+
+pdf: pdf-am
+
+pdf-am:
+
+ps: ps-am
+
+ps-am:
+
+uninstall-am: uninstall-pkginc_libHEADERS
+
+.MAKE: check-am install-am install-strip
+
+.PHONY: CTAGS GTAGS TAGS all all-am am--depfiles check check-am \
+ check-local clean clean-generic clean-libtool \
+ clean-noinstLTLIBRARIES clean-noinstPROGRAMS cscopelist-am \
+ ctags ctags-am distclean distclean-compile distclean-generic \
+ distclean-libtool distclean-tags distdir dvi dvi-am html \
+ html-am info info-am install install-am install-data \
+ install-data-am 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-pkginc_libHEADERS install-ps install-ps-am \
+ install-strip installcheck installcheck-am installdirs \
+ maintainer-clean maintainer-clean-generic mostlyclean \
+ mostlyclean-compile mostlyclean-generic mostlyclean-libtool \
+ pdf pdf-am ps ps-am tags tags-am uninstall uninstall-am \
+ uninstall-pkginc_libHEADERS
+
+.PRECIOUS: Makefile
+
+
+check-local:
+ for bin in $(test_programs); do \
+ if ! $(RUN_TEST) ./$$bin; then exit 1; fi; \
+ done
+
+# 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/src/lib-charset/charset-iconv.c b/src/lib-charset/charset-iconv.c
new file mode 100644
index 0000000..7b29219
--- /dev/null
+++ b/src/lib-charset/charset-iconv.c
@@ -0,0 +1,147 @@
+/* Copyright (c) 2002-2018 Dovecot authors, see the included COPYING file */
+
+#include "lib.h"
+#include "buffer.h"
+#include "charset-utf8-private.h"
+
+#ifdef HAVE_ICONV
+
+#include <iconv.h>
+#include <ctype.h>
+
+struct charset_translation {
+ iconv_t cd;
+ normalizer_func_t *normalizer;
+};
+
+static int
+iconv_charset_to_utf8_begin(const char *charset, normalizer_func_t *normalizer,
+ struct charset_translation **t_r)
+{
+ struct charset_translation *t;
+ iconv_t cd;
+
+ if (charset_is_utf8(charset))
+ cd = (iconv_t)-1;
+ else {
+ if (strcmp(charset, "UTF-8//TEST") == 0)
+ charset = "UTF-8";
+ cd = iconv_open("UTF-8", charset);
+ if (cd == (iconv_t)-1)
+ return -1;
+ }
+
+ t = i_new(struct charset_translation, 1);
+ t->cd = cd;
+ t->normalizer = normalizer;
+ *t_r = t;
+ return 0;
+}
+
+static void iconv_charset_to_utf8_end(struct charset_translation *t)
+{
+ if (t->cd != (iconv_t)-1)
+ iconv_close(t->cd);
+ i_free(t);
+}
+
+static void iconv_charset_to_utf8_reset(struct charset_translation *t)
+{
+ if (t->cd != (iconv_t)-1)
+ (void)iconv(t->cd, NULL, NULL, NULL, NULL);
+}
+
+static bool
+charset_to_utf8_try(struct charset_translation *t,
+ const unsigned char *src, size_t *src_size, buffer_t *dest,
+ enum charset_result *result)
+{
+ ICONV_CONST char *ic_srcbuf;
+ char tmpbuf[8192], *ic_destbuf;
+ size_t srcleft, destleft, tmpbuf_used;
+ bool ret = TRUE;
+
+ if (t->cd == (iconv_t)-1) {
+ /* input is already supposed to be UTF-8 */
+ *result = charset_utf8_to_utf8(t->normalizer, src, src_size, dest);
+ return TRUE;
+ }
+ destleft = sizeof(tmpbuf);
+ ic_destbuf = tmpbuf;
+ srcleft = *src_size;
+ ic_srcbuf = (ICONV_CONST char *) src;
+
+ if (iconv(t->cd, &ic_srcbuf, &srcleft,
+ &ic_destbuf, &destleft) != SIZE_MAX) {
+ i_assert(srcleft == 0);
+ *result = CHARSET_RET_OK;
+ } else if (errno == E2BIG) {
+ /* set result just to avoid compiler warning */
+ *result = CHARSET_RET_INCOMPLETE_INPUT;
+ ret = FALSE;
+ } else if (errno == EINVAL) {
+ i_assert(srcleft <= CHARSET_MAX_PENDING_BUF_SIZE);
+ *result = CHARSET_RET_INCOMPLETE_INPUT;
+ } else {
+ /* should be EILSEQ */
+ *result = CHARSET_RET_INVALID_INPUT;
+ ret = FALSE;
+ }
+ *src_size -= srcleft;
+
+ /* we just converted data to UTF-8. it shouldn't be invalid, but
+ Solaris iconv appears to pass invalid data through sometimes
+ (e.g. 8 bit characters with UTF-7) */
+ tmpbuf_used = sizeof(tmpbuf) - destleft;
+ if (charset_utf8_to_utf8(t->normalizer, (void *)tmpbuf,
+ &tmpbuf_used, dest) != CHARSET_RET_OK)
+ *result = CHARSET_RET_INVALID_INPUT;
+ return ret;
+}
+
+static enum charset_result
+iconv_charset_to_utf8(struct charset_translation *t,
+ const unsigned char *src, size_t *src_size,
+ buffer_t *dest)
+{
+ enum charset_result result;
+ size_t pos, size;
+ size_t prev_invalid_pos = SIZE_MAX;
+ bool ret;
+
+ for (pos = 0;;) {
+ i_assert(pos <= *src_size);
+ size = *src_size - pos;
+ ret = charset_to_utf8_try(t, src + pos, &size, dest, &result);
+ pos += size;
+
+ if (ret)
+ break;
+
+ if (result == CHARSET_RET_INVALID_INPUT) {
+ if (prev_invalid_pos != dest->used) {
+ buffer_append(dest, UNICODE_REPLACEMENT_CHAR_UTF8,
+ strlen(UNICODE_REPLACEMENT_CHAR_UTF8));
+ prev_invalid_pos = dest->used;
+ }
+ if (pos < *src_size)
+ pos++;
+ }
+ }
+
+ if (prev_invalid_pos != SIZE_MAX)
+ result = CHARSET_RET_INVALID_INPUT;
+
+ i_assert(*src_size - pos <= CHARSET_MAX_PENDING_BUF_SIZE);
+ *src_size = pos;
+ return result;
+}
+
+const struct charset_utf8_vfuncs charset_iconv = {
+ .to_utf8_begin = iconv_charset_to_utf8_begin,
+ .to_utf8_end = iconv_charset_to_utf8_end,
+ .to_utf8_reset = iconv_charset_to_utf8_reset,
+ .to_utf8 = iconv_charset_to_utf8,
+};
+
+#endif
diff --git a/src/lib-charset/charset-utf8-only.c b/src/lib-charset/charset-utf8-only.c
new file mode 100644
index 0000000..e8ea810
--- /dev/null
+++ b/src/lib-charset/charset-utf8-only.c
@@ -0,0 +1,51 @@
+/* Copyright (c) 2002-2018 Dovecot authors, see the included COPYING file */
+
+#include "lib.h"
+#include "charset-utf8-private.h"
+
+struct charset_translation {
+ normalizer_func_t *normalizer;
+};
+
+static int
+utf8only_charset_to_utf8_begin(const char *charset,
+ normalizer_func_t *normalizer,
+ struct charset_translation **t_r)
+{
+ struct charset_translation *t;
+
+ if (!charset_is_utf8(charset)) {
+ /* no support for charsets that need translation */
+ return -1;
+ }
+
+ t = i_new(struct charset_translation, 1);
+ t->normalizer = normalizer;
+ *t_r = t;
+ return 0;
+}
+
+static void utf8only_charset_to_utf8_end(struct charset_translation *t)
+{
+ i_free(t);
+}
+
+static void
+utf8only_charset_to_utf8_reset(struct charset_translation *t ATTR_UNUSED)
+{
+}
+
+static enum charset_result
+utf8only_charset_to_utf8(struct charset_translation *t,
+ const unsigned char *src, size_t *src_size,
+ buffer_t *dest)
+{
+ return charset_utf8_to_utf8(t->normalizer, src, src_size, dest);
+}
+
+const struct charset_utf8_vfuncs charset_utf8only = {
+ .to_utf8_begin = utf8only_charset_to_utf8_begin,
+ .to_utf8_end = utf8only_charset_to_utf8_end,
+ .to_utf8_reset = utf8only_charset_to_utf8_reset,
+ .to_utf8 = utf8only_charset_to_utf8,
+};
diff --git a/src/lib-charset/charset-utf8-private.h b/src/lib-charset/charset-utf8-private.h
new file mode 100644
index 0000000..0f5064b
--- /dev/null
+++ b/src/lib-charset/charset-utf8-private.h
@@ -0,0 +1,21 @@
+#ifndef CHARSET_UTF8_PRIVATE_H
+#define CHARSET_UTF8_PRIVATE_H
+
+#include "unichar.h"
+#include "charset-utf8.h"
+
+struct charset_utf8_vfuncs {
+ int (*to_utf8_begin)(const char *charset, normalizer_func_t *normalizer,
+ struct charset_translation **t_r);
+ void (*to_utf8_end)(struct charset_translation *t);
+ void (*to_utf8_reset)(struct charset_translation *t);
+
+ enum charset_result (*to_utf8)(struct charset_translation *t,
+ const unsigned char *src,
+ size_t *src_size, buffer_t *dest);
+};
+
+extern const struct charset_utf8_vfuncs charset_utf8only;
+extern const struct charset_utf8_vfuncs charset_iconv;
+
+#endif
diff --git a/src/lib-charset/charset-utf8.c b/src/lib-charset/charset-utf8.c
new file mode 100644
index 0000000..22038e5
--- /dev/null
+++ b/src/lib-charset/charset-utf8.c
@@ -0,0 +1,99 @@
+/* Copyright (c) 2002-2018 Dovecot authors, see the included COPYING file */
+
+#include "lib.h"
+#include "buffer.h"
+#include "str.h"
+#include "charset-utf8-private.h"
+
+#include <ctype.h>
+
+#ifdef HAVE_ICONV
+const struct charset_utf8_vfuncs *charset_utf8_vfuncs = &charset_iconv;
+#else
+const struct charset_utf8_vfuncs *charset_utf8_vfuncs = &charset_utf8only;
+#endif
+
+bool charset_is_utf8(const char *charset)
+{
+ return strcasecmp(charset, "us-ascii") == 0 ||
+ strcasecmp(charset, "ascii") == 0 ||
+ strcasecmp(charset, "UTF-8") == 0 ||
+ strcasecmp(charset, "UTF8") == 0;
+}
+
+int charset_to_utf8_str(const char *charset, normalizer_func_t *normalizer,
+ const char *input, string_t *output,
+ enum charset_result *result_r)
+{
+ struct charset_translation *t;
+ size_t len = strlen(input);
+
+ if (charset_to_utf8_begin(charset, normalizer, &t) < 0)
+ return -1;
+
+ *result_r = charset_to_utf8(t, (const unsigned char *)input,
+ &len, output);
+ charset_to_utf8_end(&t);
+ return 0;
+}
+
+struct charset_translation *
+charset_utf8_to_utf8_begin(normalizer_func_t *normalizer)
+{
+ struct charset_translation *trans;
+
+ if (charset_to_utf8_begin("UTF-8", normalizer, &trans) < 0)
+ i_unreached();
+ return trans;
+}
+
+enum charset_result
+charset_utf8_to_utf8(normalizer_func_t *normalizer,
+ const unsigned char *src, size_t *src_size, buffer_t *dest)
+{
+ enum charset_result res = CHARSET_RET_OK;
+ size_t pos;
+
+ uni_utf8_partial_strlen_n(src, *src_size, &pos);
+ if (pos < *src_size) {
+ i_assert(*src_size - pos <= CHARSET_MAX_PENDING_BUF_SIZE);
+ *src_size = pos;
+ res = CHARSET_RET_INCOMPLETE_INPUT;
+ }
+
+ if (normalizer != NULL) {
+ if (normalizer(src, *src_size, dest) < 0)
+ return CHARSET_RET_INVALID_INPUT;
+ } else if (!uni_utf8_get_valid_data(src, *src_size, dest)) {
+ return CHARSET_RET_INVALID_INPUT;
+ } else {
+ buffer_append(dest, src, *src_size);
+ }
+ return res;
+}
+
+int charset_to_utf8_begin(const char *charset, normalizer_func_t *normalizer,
+ struct charset_translation **t_r)
+{
+ return charset_utf8_vfuncs->to_utf8_begin(charset, normalizer, t_r);
+}
+
+void charset_to_utf8_end(struct charset_translation **_t)
+{
+ struct charset_translation *t = *_t;
+
+ *_t = NULL;
+ charset_utf8_vfuncs->to_utf8_end(t);
+}
+
+void charset_to_utf8_reset(struct charset_translation *t)
+{
+ charset_utf8_vfuncs->to_utf8_reset(t);
+}
+
+enum charset_result
+charset_to_utf8(struct charset_translation *t,
+ const unsigned char *src, size_t *src_size, buffer_t *dest)
+{
+ return charset_utf8_vfuncs->to_utf8(t, src, src_size, dest);
+}
diff --git a/src/lib-charset/charset-utf8.h b/src/lib-charset/charset-utf8.h
new file mode 100644
index 0000000..c17ab30
--- /dev/null
+++ b/src/lib-charset/charset-utf8.h
@@ -0,0 +1,53 @@
+#ifndef CHARSET_UTF8_H
+#define CHARSET_UTF8_H
+
+#include "unichar.h"
+
+/* Max number of bytes that iconv can require for a single character.
+ UTF-8 takes max 6 bytes per character. Not sure about others, but I'd think
+ 10 is more than enough for everyone.. */
+#define CHARSET_MAX_PENDING_BUF_SIZE 10
+
+struct charset_translation;
+
+enum charset_result {
+ CHARSET_RET_OK = 1,
+ CHARSET_RET_INCOMPLETE_INPUT = -1,
+ CHARSET_RET_INVALID_INPUT = -2
+};
+
+/* Begin translation to UTF-8. Returns -1 if charset is unknown. */
+int charset_to_utf8_begin(const char *charset, normalizer_func_t *normalizer,
+ struct charset_translation **t_r)
+ ATTR_NULL(2);
+/* Translate UTF-8 to UTF-8 while validating the input. */
+struct charset_translation *
+charset_utf8_to_utf8_begin(normalizer_func_t *normalizer);
+void charset_to_utf8_end(struct charset_translation **t);
+void charset_to_utf8_reset(struct charset_translation *t);
+
+/* Returns TRUE if charset is UTF-8 or ASCII */
+bool charset_is_utf8(const char *charset) ATTR_PURE;
+
+/* Translate src to UTF-8. src_size is updated to contain the number of
+ characters actually translated from src. The src_size should never shrink
+ more than CHARSET_MAX_PENDING_BUF_SIZE bytes.
+
+ If src contains invalid input, UNICODE_REPLACEMENT_CHAR is placed in such
+ positions and the invalid input is skipped over. Return value is also
+ CHARSET_RET_INCOMPLETE_INPUT in that case. */
+enum charset_result
+charset_to_utf8(struct charset_translation *t,
+ const unsigned char *src, size_t *src_size, buffer_t *dest);
+
+/* Translate a single string to UTF8. */
+int charset_to_utf8_str(const char *charset, normalizer_func_t *normalizer,
+ const char *input, string_t *output,
+ enum charset_result *result_r) ATTR_NULL(2);
+
+/* INTERNAL: */
+enum charset_result
+charset_utf8_to_utf8(normalizer_func_t *normalizer,
+ const unsigned char *src, size_t *src_size, buffer_t *dest);
+
+#endif
diff --git a/src/lib-charset/test-charset.c b/src/lib-charset/test-charset.c
new file mode 100644
index 0000000..2f9ba2b
--- /dev/null
+++ b/src/lib-charset/test-charset.c
@@ -0,0 +1,231 @@
+/* Copyright (c) 2015-2018 Dovecot authors, see the included COPYING file */
+
+#include "lib.h"
+#include "istream.h"
+#include "str.h"
+#include "test-common.h"
+#include "charset-utf8.h"
+
+#include <unistd.h>
+
+static void test_charset_is_utf8(void)
+{
+ test_begin("charset_is_utf8");
+ test_assert(charset_is_utf8("AScII"));
+ test_assert(charset_is_utf8("us-AScII"));
+ test_assert(charset_is_utf8("uTF8"));
+ test_assert(charset_is_utf8("uTF-8"));
+ test_end();
+}
+
+static void test_charset_utf8_common(const char *input_charset)
+{
+ static const struct {
+ const char *input;
+ const char *output;
+ enum charset_result result;
+ } tests[] = {
+ { "p\xC3\xA4\xC3", "p\xC3\xA4", CHARSET_RET_INCOMPLETE_INPUT },
+ { "p\xC3\xA4\xC3""a", "p\xC3\xA4"UNICODE_REPLACEMENT_CHAR_UTF8"a", CHARSET_RET_INVALID_INPUT }
+ };
+ string_t *src, *str = t_str_new(256);
+ enum charset_result result;
+ unsigned int i;
+
+ for (i = 0; i < N_ELEMENTS(tests); i++) {
+ str_truncate(str, 0);
+ test_assert_idx(charset_to_utf8_str(input_charset, NULL,
+ tests[i].input, str, &result) == 0, i);
+ test_assert_idx(strcmp(tests[i].output, str_c(str)) == 0, i);
+ test_assert_idx(result == tests[i].result, i);
+ }
+ /* check that E2BIG handling works. We assume that iconv() is called
+ with 8192 byte buffer (tmpbuf[8192]) */
+ src = str_new(default_pool, 16384);
+ for (i = 0; i < 8190; i++)
+ str_append_c(src, 'a' + i % ('z'-'a'+1));
+ for (i = 0; i < 256; i++) {
+ str_truncate(str, 0);
+ str_append_c(src, 'A' + i % ('Z'-'A'+1));
+ test_assert_idx(charset_to_utf8_str(input_charset, NULL,
+ str_c(src), str, &result) == 0, i);
+ }
+ str_free(&src);
+}
+
+static void test_charset_utf8(void)
+{
+ test_begin("charset utf8");
+ test_charset_utf8_common("UTF-8");
+ test_end();
+}
+
+#ifdef HAVE_ICONV
+static void test_charset_iconv(void)
+{
+ static const struct {
+ const char *charset;
+ const char *input;
+ const char *output;
+ enum charset_result result;
+ } tests[] = {
+ { "ISO-8859-1", "p\xE4\xE4", "p\xC3\xA4\xC3\xA4", CHARSET_RET_OK },
+ { "UTF-7", "+AOQA5AD2AOQA9gDkAPYA5AD2AOQA9gDkAPYA5AD2AOQA9gDkAPYA5AD2AOQA9gDkAPYA5AD2AOQA9gDkAPYA5AD2AOQA9gDk",
+ "\xC3\xA4\xC3\xA4\xC3\xB6\xC3\xA4\xC3\xB6\xC3\xA4\xC3\xB6\xC3\xA4"
+ "\xC3\xB6\xC3\xA4\xC3\xB6\xC3\xA4\xC3\xB6\xC3\xA4\xC3\xB6\xC3\xA4"
+ "\xC3\xB6\xC3\xA4\xC3\xB6\xC3\xA4\xC3\xB6\xC3\xA4\xC3\xB6\xC3\xA4"
+ "\xC3\xB6\xC3\xA4\xC3\xB6\xC3\xA4\xC3\xB6\xC3\xA4\xC3\xB6\xC3\xA4"
+ "\xC3\xB6\xC3\xA4\xC3\xB6\xC3\xA4", CHARSET_RET_OK }
+ };
+ string_t *str = t_str_new(128);
+ struct charset_translation *trans;
+ enum charset_result result;
+ size_t pos, left, limit, len;
+ unsigned int i;
+
+ test_begin("charset iconv");
+ for (i = 0; i < N_ELEMENTS(tests); i++) {
+ str_truncate(str, 0);
+ test_assert_idx(charset_to_utf8_str(tests[i].charset, NULL,
+ tests[i].input, str, &result) == 0, i);
+ test_assert_idx(strcmp(tests[i].output, str_c(str)) == 0, i);
+ test_assert_idx(result == tests[i].result, i);
+
+ str_truncate(str, 0);
+ test_assert_idx(charset_to_utf8_begin(tests[i].charset, NULL, &trans) == 0, i);
+ len = strlen(tests[i].input);
+ for (pos = 0, limit = 1; limit <= len; pos += left, limit++) {
+ left = limit - pos;
+ result = charset_to_utf8(trans, (const void *)(tests[i].input + pos),
+ &left, str);
+ if (result != CHARSET_RET_INCOMPLETE_INPUT &&
+ result != CHARSET_RET_OK)
+ break;
+ }
+ test_assert_idx(strcmp(tests[i].output, str_c(str)) == 0, i);
+ test_assert_idx(result == tests[i].result, i);
+ charset_to_utf8_end(&trans);
+ }
+ /* Use //IGNORE just to force handling to be done by iconv
+ instead of our own UTF-8 routines. */
+ test_charset_utf8_common("UTF-8//TEST");
+ test_end();
+}
+static void test_charset_iconv_crashes(void)
+{
+ static const struct {
+ const char *charset;
+ const char *input;
+ } tests[] = {
+ { "CP932", "\203\334" }
+ };
+ string_t *str = t_str_new(128);
+ enum charset_result result;
+ unsigned int i;
+
+ test_begin("charset iconv crashes");
+ for (i = 0; i < N_ELEMENTS(tests); i++) {
+ str_truncate(str, 0);
+ /* we don't care about checking the result. we only want to
+ verify that there's no crash. */
+ (void)charset_to_utf8_str(tests[i].charset, NULL,
+ tests[i].input, str, &result);
+ }
+ test_end();
+}
+
+static void test_charset_iconv_utf7_state(void)
+{
+ struct charset_translation *trans;
+ string_t *str = t_str_new(32);
+ unsigned char nextbuf[5+CHARSET_MAX_PENDING_BUF_SIZE+1];
+ size_t size;
+
+ test_begin("charset iconv utf7 state");
+ test_assert(charset_to_utf8_begin("UTF-7", NULL, &trans) == 0);
+ size = 2;
+ test_assert(charset_to_utf8(trans, (const void *)"a+", &size, str) == CHARSET_RET_INCOMPLETE_INPUT);
+ test_assert(strcmp(str_c(str), "a") == 0);
+ test_assert(size == 1);
+ memset(nextbuf, '?', sizeof(nextbuf));
+ memcpy(nextbuf, "+AOQ-", 5);
+ size = sizeof(nextbuf);
+ test_assert(charset_to_utf8(trans, nextbuf, &size, str) == CHARSET_RET_OK);
+ test_assert(strcmp(str_c(str), "a\xC3\xA4???????????") == 0);
+ charset_to_utf8_end(&trans);
+ test_end();
+}
+#endif
+
+static int convert(const char *charset, const char *path)
+{
+ struct istream *input;
+ const unsigned char *data;
+ size_t size;
+ struct charset_translation *trans;
+ buffer_t *buf = buffer_create_dynamic(default_pool, IO_BLOCK_SIZE);
+ enum charset_result last_ret = CHARSET_RET_OK;
+ bool seen_invalid_input = FALSE;
+
+ input = path == NULL ? i_stream_create_fd(STDIN_FILENO, IO_BLOCK_SIZE) :
+ i_stream_create_file(path, IO_BLOCK_SIZE);
+
+ if (charset_to_utf8_begin(charset, NULL, &trans) < 0)
+ i_fatal("Failed to initialize charset '%s'", charset);
+
+ size_t need = 1;
+ while (i_stream_read_bytes(input, &data, &size, need) > 0) {
+ last_ret = charset_to_utf8(trans, data, &size, buf);
+ if (size > 0)
+ need = 1;
+ i_stream_skip(input, size);
+ switch (last_ret) {
+ case CHARSET_RET_OK:
+ break;
+ case CHARSET_RET_INCOMPLETE_INPUT:
+ need++;
+ break;
+ case CHARSET_RET_INVALID_INPUT:
+ seen_invalid_input = TRUE;
+ break;
+ }
+ if (write(STDOUT_FILENO, buf->data, buf->used) != (ssize_t)buf->used)
+ i_fatal("write(stdout) failed: %m");
+ buffer_set_used_size(buf, 0);
+ }
+ if (input->stream_errno != 0)
+ i_error("read() failed: %s", i_stream_get_error(input));
+ charset_to_utf8_end(&trans);
+ i_stream_destroy(&input);
+ buffer_free(&buf);
+
+ if (seen_invalid_input) {
+ i_error("Seen invalid input");
+ return 1;
+ }
+ if (last_ret == CHARSET_RET_INCOMPLETE_INPUT) {
+ i_error("Incomplete input");
+ return 2;
+ }
+ return 0;
+}
+
+int main(int argc, char *argv[])
+{
+ static void (*const test_functions[])(void) = {
+ test_charset_is_utf8,
+ test_charset_utf8,
+#ifdef HAVE_ICONV
+ test_charset_iconv,
+ test_charset_iconv_crashes,
+ test_charset_iconv_utf7_state,
+#endif
+ NULL
+ };
+
+ if (argc >= 2) {
+ /* <charset> [<input path>] */
+ return convert(argv[1], argv[2]);
+ }
+ return test_run(test_functions);
+}
generated by cgit v1.2.3 (git 2.39.1) at 2024-12-22 21:14:36 +0000