From 36d22d82aa202bb199967e9512281e9a53db42c9 Mon Sep 17 00:00:00 2001 From: Daniel Baumann Date: Sun, 7 Apr 2024 21:33:14 +0200 Subject: Adding upstream version 115.7.0esr. Signed-off-by: Daniel Baumann --- intl/icu/source/tools/escapesrc/Makefile.in | 112 +++++ intl/icu/source/tools/escapesrc/cptbl.h | 521 ++++++++++++++++++++++ intl/icu/source/tools/escapesrc/escapesrc.cpp | 427 ++++++++++++++++++ intl/icu/source/tools/escapesrc/expect-simple.cpp | 17 + intl/icu/source/tools/escapesrc/tblgen.cpp | 80 ++++ intl/icu/source/tools/escapesrc/test-nochange.cpp | 5 + intl/icu/source/tools/escapesrc/test-simple.cpp | 17 + 7 files changed, 1179 insertions(+) create mode 100644 intl/icu/source/tools/escapesrc/Makefile.in create mode 100644 intl/icu/source/tools/escapesrc/cptbl.h create mode 100644 intl/icu/source/tools/escapesrc/escapesrc.cpp create mode 100644 intl/icu/source/tools/escapesrc/expect-simple.cpp create mode 100644 intl/icu/source/tools/escapesrc/tblgen.cpp create mode 100644 intl/icu/source/tools/escapesrc/test-nochange.cpp create mode 100644 intl/icu/source/tools/escapesrc/test-simple.cpp (limited to 'intl/icu/source/tools/escapesrc') diff --git a/intl/icu/source/tools/escapesrc/Makefile.in b/intl/icu/source/tools/escapesrc/Makefile.in new file mode 100644 index 0000000000..7580ccdc31 --- /dev/null +++ b/intl/icu/source/tools/escapesrc/Makefile.in @@ -0,0 +1,112 @@ +## Makefile.in for ICU - tools/escapesrc +## Copyright (C) 2016 and later: Unicode, Inc. and others. +## License & terms of use: http://www.unicode.org/copyright.html +## Copyright (c) 1999-2011, International Business Machines Corporation and +## others. All Rights Reserved. +## Steven R. Loomis + +# To avoid recursion +SKIP_ESCAPING=YES + +## Source directory information +srcdir = @srcdir@ +top_srcdir = @top_srcdir@ + +top_builddir = ../.. + +include $(top_builddir)/icudefs.mk + +## Build directory information +subdir = tools/escapesrc + +TARGET_STUB_NAME = escapesrc + +SECTION = 8 + +#MAN_FILES = $(TARGET_STUB_NAME).$(SECTION) + +## Extra files to remove for 'make clean' +CLEANFILES = *~ $(DEPS) $(MAN_FILES) ./output-*.cpp + +## Target information +TARGET = $(BINDIR)/$(TARGET_STUB_NAME)$(EXEEXT) + +CPPFLAGS += -I$(top_srcdir)/common -I$(srcdir)/../toolutil +#LIBS = $(LIBICUTOOLUTIL) $(LIBICUI18N) $(LIBICUUC) +LIBS += $(DEFAULT_LIBS) $(LIB_M) + +OBJECTS = escapesrc.o + +DEPS = $(OBJECTS:.o=.d) + +## List of phony targets +.PHONY : all all-local install install-local clean clean-local \ +distclean distclean-local dist dist-local check check-local install-man + +## Clear suffix list +.SUFFIXES : + +## List of standard targets +all: all-local +install: install-local +clean: clean-local +distclean : distclean-local +dist: dist-local +check: all check-local + +all-local: $(TARGET) $(MAN_FILES) + +install-local: all-local install-man + $(MKINSTALLDIRS) $(DESTDIR)$(sbindir) + $(INSTALL) $(TARGET) $(DESTDIR)$(sbindir) + +install-man: $(MAN_FILES) +# $(MKINSTALLDIRS) $(DESTDIR)$(mandir)/man$(SECTION) +# $(INSTALL_DATA) $? $(DESTDIR)$(mandir)/man$(SECTION) + + +dist-local: + +clean-local: + test -z "$(CLEANFILES)" || $(RMV) $(CLEANFILES) + $(RMV) $(TARGET) $(OBJECTS) + +distclean-local: clean-local + $(RMV) Makefile + +check-local: all-local + @echo Testing test-nochange.cpp + @$(INVOKE) $(TARGET) $(srcdir)/test-nochange.cpp ./output-nochange.cpp + @-diff -I '#line.*' $(srcdir)/test-nochange.cpp ./output-nochange.cpp || (echo >&2 'warning: diff failed or not found' ; true) + @echo Testing test-simple.cpp + @$(INVOKE) $(TARGET) $(srcdir)/test-simple.cpp ./output-simple.cpp + @-diff -I '#line.*' $(srcdir)/expect-simple.cpp ./output-simple.cpp || (echo >&2 'warning: diff failed or not found' ; true) + +Makefile: $(srcdir)/Makefile.in $(top_builddir)/config.status + cd $(top_builddir) \ + && CONFIG_FILES=$(subdir)/$@ CONFIG_HEADERS= $(SHELL) ./config.status + +$(TARGET) : $(OBJECTS) + $(LINK.cc) $(OUTOPT)$@ $^ $(LIBS) + $(POST_BUILD_STEP) + + +%.$(SECTION): $(srcdir)/%.$(SECTION).in + cd $(top_builddir) \ + && CONFIG_FILES=$(subdir)/$@ CONFIG_HEADERS= $(SHELL) ./config.status + +# depends on ICU being built +gen-table: tblgen$(EXEEXT) + $(INVOKE) ./tblgen$(EXEEXT) > $(srcdir)/cptbl.h + +tblgen$(EXEEXT): tblgen.o + $(LINK.cc) $(OUTOPT)$@ $^ $(LIBS) $(LIBICUUC) + +ifeq (,$(MAKECMDGOALS)) +-include $(DEPS) +else +ifneq ($(patsubst %clean,,$(MAKECMDGOALS)),) +-include $(DEPS) +endif +endif + diff --git a/intl/icu/source/tools/escapesrc/cptbl.h b/intl/icu/source/tools/escapesrc/cptbl.h new file mode 100644 index 0000000000..898e16c925 --- /dev/null +++ b/intl/icu/source/tools/escapesrc/cptbl.h @@ -0,0 +1,521 @@ +// Copyright (C) 2016 and later: Unicode, Inc. and others. License & terms of use: http://www.unicode.org/copyright.html +// generated by tblgen. You weren't going to edit it by hand, were you? + +static const char cp1047_8859_1[256] = { + (char)0x00, /* 00 */ + (char)0x01, /* 01 */ + (char)0x02, /* 02 */ + (char)0x03, /* 03 */ + (char)0x9C, /* 04 */ + (char)0x09, /* 05 */ + (char)0x86, /* 06 */ + (char)0x7F, /* 07 */ + (char)0x97, /* 08 */ + (char)0x8D, /* 09 */ + (char)0x8E, /* 0A */ + (char)0x0B, /* 0B */ + (char)0x0C, /* 0C */ + (char)0x0D, /* 0D */ + (char)0x0E, /* 0E */ + (char)0x0F, /* 0F */ + (char)0x10, /* 10 */ + (char)0x11, /* 11 */ + (char)0x12, /* 12 */ + (char)0x13, /* 13 */ + (char)0x9D, /* 14 */ + (char)0x85, /* 15 */ + (char)0x08, /* 16 */ + (char)0x87, /* 17 */ + (char)0x18, /* 18 */ + (char)0x19, /* 19 */ + (char)0x92, /* 1A */ + (char)0x8F, /* 1B */ + (char)0x1C, /* 1C */ + (char)0x1D, /* 1D */ + (char)0x1E, /* 1E */ + (char)0x1F, /* 1F */ + (char)0x80, /* 20 */ + (char)0x81, /* 21 */ + (char)0x82, /* 22 */ + (char)0x83, /* 23 */ + (char)0x84, /* 24 */ + (char)0x0A, /* 25 */ + (char)0x17, /* 26 */ + (char)0x1B, /* 27 */ + (char)0x88, /* 28 */ + (char)0x89, /* 29 */ + (char)0x8A, /* 2A */ + (char)0x8B, /* 2B */ + (char)0x8C, /* 2C */ + (char)0x05, /* 2D */ + (char)0x06, /* 2E */ + (char)0x07, /* 2F */ + (char)0x90, /* 30 */ + (char)0x91, /* 31 */ + (char)0x16, /* 32 */ + (char)0x93, /* 33 */ + (char)0x94, /* 34 */ + (char)0x95, /* 35 */ + (char)0x96, /* 36 */ + (char)0x04, /* 37 */ + (char)0x98, /* 38 */ + (char)0x99, /* 39 */ + (char)0x9A, /* 3A */ + (char)0x9B, /* 3B */ + (char)0x14, /* 3C */ + (char)0x15, /* 3D */ + (char)0x9E, /* 3E */ + (char)0x1A, /* 3F */ + (char)0x20, /* 40 */ + (char)0xA0, /* 41 */ + (char)0xE2, /* 42 */ + (char)0xE4, /* 43 */ + (char)0xE0, /* 44 */ + (char)0xE1, /* 45 */ + (char)0xE3, /* 46 */ + (char)0xE5, /* 47 */ + (char)0xE7, /* 48 */ + (char)0xF1, /* 49 */ + (char)0xA2, /* 4A */ + (char)0x2E, /* 4B */ + (char)0x3C, /* 4C */ + (char)0x28, /* 4D */ + (char)0x2B, /* 4E */ + (char)0x7C, /* 4F */ + (char)0x26, /* 50 */ + (char)0xE9, /* 51 */ + (char)0xEA, /* 52 */ + (char)0xEB, /* 53 */ + (char)0xE8, /* 54 */ + (char)0xED, /* 55 */ + (char)0xEE, /* 56 */ + (char)0xEF, /* 57 */ + (char)0xEC, /* 58 */ + (char)0xDF, /* 59 */ + (char)0x21, /* 5A */ + (char)0x24, /* 5B */ + (char)0x2A, /* 5C */ + (char)0x29, /* 5D */ + (char)0x3B, /* 5E */ + (char)0x5E, /* 5F */ + (char)0x2D, /* 60 */ + (char)0x2F, /* 61 */ + (char)0xC2, /* 62 */ + (char)0xC4, /* 63 */ + (char)0xC0, /* 64 */ + (char)0xC1, /* 65 */ + (char)0xC3, /* 66 */ + (char)0xC5, /* 67 */ + (char)0xC7, /* 68 */ + (char)0xD1, /* 69 */ + (char)0xA6, /* 6A */ + (char)0x2C, /* 6B */ + (char)0x25, /* 6C */ + (char)0x5F, /* 6D */ + (char)0x3E, /* 6E */ + (char)0x3F, /* 6F */ + (char)0xF8, /* 70 */ + (char)0xC9, /* 71 */ + (char)0xCA, /* 72 */ + (char)0xCB, /* 73 */ + (char)0xC8, /* 74 */ + (char)0xCD, /* 75 */ + (char)0xCE, /* 76 */ + (char)0xCF, /* 77 */ + (char)0xCC, /* 78 */ + (char)0x60, /* 79 */ + (char)0x3A, /* 7A */ + (char)0x23, /* 7B */ + (char)0x40, /* 7C */ + (char)0x27, /* 7D */ + (char)0x3D, /* 7E */ + (char)0x22, /* 7F */ + (char)0xD8, /* 80 */ + (char)0x61, /* 81 */ + (char)0x62, /* 82 */ + (char)0x63, /* 83 */ + (char)0x64, /* 84 */ + (char)0x65, /* 85 */ + (char)0x66, /* 86 */ + (char)0x67, /* 87 */ + (char)0x68, /* 88 */ + (char)0x69, /* 89 */ + (char)0xAB, /* 8A */ + (char)0xBB, /* 8B */ + (char)0xF0, /* 8C */ + (char)0xFD, /* 8D */ + (char)0xFE, /* 8E */ + (char)0xB1, /* 8F */ + (char)0xB0, /* 90 */ + (char)0x6A, /* 91 */ + (char)0x6B, /* 92 */ + (char)0x6C, /* 93 */ + (char)0x6D, /* 94 */ + (char)0x6E, /* 95 */ + (char)0x6F, /* 96 */ + (char)0x70, /* 97 */ + (char)0x71, /* 98 */ + (char)0x72, /* 99 */ + (char)0xAA, /* 9A */ + (char)0xBA, /* 9B */ + (char)0xE6, /* 9C */ + (char)0xB8, /* 9D */ + (char)0xC6, /* 9E */ + (char)0xA4, /* 9F */ + (char)0xB5, /* A0 */ + (char)0x7E, /* A1 */ + (char)0x73, /* A2 */ + (char)0x74, /* A3 */ + (char)0x75, /* A4 */ + (char)0x76, /* A5 */ + (char)0x77, /* A6 */ + (char)0x78, /* A7 */ + (char)0x79, /* A8 */ + (char)0x7A, /* A9 */ + (char)0xA1, /* AA */ + (char)0xBF, /* AB */ + (char)0xD0, /* AC */ + (char)0x5B, /* AD */ + (char)0xDE, /* AE */ + (char)0xAE, /* AF */ + (char)0xAC, /* B0 */ + (char)0xA3, /* B1 */ + (char)0xA5, /* B2 */ + (char)0xB7, /* B3 */ + (char)0xA9, /* B4 */ + (char)0xA7, /* B5 */ + (char)0xB6, /* B6 */ + (char)0xBC, /* B7 */ + (char)0xBD, /* B8 */ + (char)0xBE, /* B9 */ + (char)0xDD, /* BA */ + (char)0xA8, /* BB */ + (char)0xAF, /* BC */ + (char)0x5D, /* BD */ + (char)0xB4, /* BE */ + (char)0xD7, /* BF */ + (char)0x7B, /* C0 */ + (char)0x41, /* C1 */ + (char)0x42, /* C2 */ + (char)0x43, /* C3 */ + (char)0x44, /* C4 */ + (char)0x45, /* C5 */ + (char)0x46, /* C6 */ + (char)0x47, /* C7 */ + (char)0x48, /* C8 */ + (char)0x49, /* C9 */ + (char)0xAD, /* CA */ + (char)0xF4, /* CB */ + (char)0xF6, /* CC */ + (char)0xF2, /* CD */ + (char)0xF3, /* CE */ + (char)0xF5, /* CF */ + (char)0x7D, /* D0 */ + (char)0x4A, /* D1 */ + (char)0x4B, /* D2 */ + (char)0x4C, /* D3 */ + (char)0x4D, /* D4 */ + (char)0x4E, /* D5 */ + (char)0x4F, /* D6 */ + (char)0x50, /* D7 */ + (char)0x51, /* D8 */ + (char)0x52, /* D9 */ + (char)0xB9, /* DA */ + (char)0xFB, /* DB */ + (char)0xFC, /* DC */ + (char)0xF9, /* DD */ + (char)0xFA, /* DE */ + (char)0xFF, /* DF */ + (char)0x5C, /* E0 */ + (char)0xF7, /* E1 */ + (char)0x53, /* E2 */ + (char)0x54, /* E3 */ + (char)0x55, /* E4 */ + (char)0x56, /* E5 */ + (char)0x57, /* E6 */ + (char)0x58, /* E7 */ + (char)0x59, /* E8 */ + (char)0x5A, /* E9 */ + (char)0xB2, /* EA */ + (char)0xD4, /* EB */ + (char)0xD6, /* EC */ + (char)0xD2, /* ED */ + (char)0xD3, /* EE */ + (char)0xD5, /* EF */ + (char)0x30, /* F0 */ + (char)0x31, /* F1 */ + (char)0x32, /* F2 */ + (char)0x33, /* F3 */ + (char)0x34, /* F4 */ + (char)0x35, /* F5 */ + (char)0x36, /* F6 */ + (char)0x37, /* F7 */ + (char)0x38, /* F8 */ + (char)0x39, /* F9 */ + (char)0xB3, /* FA */ + (char)0xDB, /* FB */ + (char)0xDC, /* FC */ + (char)0xD9, /* FD */ + (char)0xDA, /* FE */ + (char)0x9F, /* FF */ +}; + +static const bool oldIllegal[256] = { + false, /* U+0000 */ + false, /* U+0001 */ + false, /* U+0002 */ + false, /* U+0003 */ + false, /* U+0004 */ + false, /* U+0005 */ + false, /* U+0006 */ + false, /* U+0007 */ + false, /* U+0008 */ + false, /* U+0009 */ + false, /* U+000A */ + false, /* U+000B */ + false, /* U+000C */ + false, /* U+000D */ + false, /* U+000E */ + false, /* U+000F */ + false, /* U+0010 */ + false, /* U+0011 */ + false, /* U+0012 */ + false, /* U+0013 */ + false, /* U+0014 */ + false, /* U+0015 */ + false, /* U+0016 */ + false, /* U+0017 */ + false, /* U+0018 */ + false, /* U+0019 */ + false, /* U+001A */ + false, /* U+001B */ + false, /* U+001C */ + false, /* U+001D */ + false, /* U+001E */ + false, /* U+001F */ + true, /* U+0020 */ + true, /* U+0021 */ + true, /* U+0022 */ + true, /* U+0023 */ + false, /* U+0024 */ + true, /* U+0025 */ + true, /* U+0026 */ + true, /* U+0027 */ + true, /* U+0028 */ + true, /* U+0029 */ + true, /* U+002A */ + true, /* U+002B */ + true, /* U+002C */ + true, /* U+002D */ + true, /* U+002E */ + true, /* U+002F */ + true, /* U+0030 */ + true, /* U+0031 */ + true, /* U+0032 */ + true, /* U+0033 */ + true, /* U+0034 */ + true, /* U+0035 */ + true, /* U+0036 */ + true, /* U+0037 */ + true, /* U+0038 */ + true, /* U+0039 */ + true, /* U+003A */ + true, /* U+003B */ + true, /* U+003C */ + true, /* U+003D */ + true, /* U+003E */ + true, /* U+003F */ + false, /* U+0040 */ + true, /* U+0041 */ + true, /* U+0042 */ + true, /* U+0043 */ + true, /* U+0044 */ + true, /* U+0045 */ + true, /* U+0046 */ + true, /* U+0047 */ + true, /* U+0048 */ + true, /* U+0049 */ + true, /* U+004A */ + true, /* U+004B */ + true, /* U+004C */ + true, /* U+004D */ + true, /* U+004E */ + true, /* U+004F */ + true, /* U+0050 */ + true, /* U+0051 */ + true, /* U+0052 */ + true, /* U+0053 */ + true, /* U+0054 */ + true, /* U+0055 */ + true, /* U+0056 */ + true, /* U+0057 */ + true, /* U+0058 */ + true, /* U+0059 */ + true, /* U+005A */ + true, /* U+005B */ + false, /* U+005C */ + true, /* U+005D */ + true, /* U+005E */ + true, /* U+005F */ + false, /* U+0060 */ + true, /* U+0061 */ + true, /* U+0062 */ + true, /* U+0063 */ + true, /* U+0064 */ + true, /* U+0065 */ + true, /* U+0066 */ + true, /* U+0067 */ + true, /* U+0068 */ + true, /* U+0069 */ + true, /* U+006A */ + true, /* U+006B */ + true, /* U+006C */ + true, /* U+006D */ + true, /* U+006E */ + true, /* U+006F */ + true, /* U+0070 */ + true, /* U+0071 */ + true, /* U+0072 */ + true, /* U+0073 */ + true, /* U+0074 */ + true, /* U+0075 */ + true, /* U+0076 */ + true, /* U+0077 */ + true, /* U+0078 */ + true, /* U+0079 */ + true, /* U+007A */ + true, /* U+007B */ + true, /* U+007C */ + true, /* U+007D */ + true, /* U+007E */ + false, /* U+007F */ + false, /* U+0080 */ + false, /* U+0081 */ + false, /* U+0082 */ + false, /* U+0083 */ + false, /* U+0084 */ + false, /* U+0085 */ + false, /* U+0086 */ + false, /* U+0087 */ + false, /* U+0088 */ + false, /* U+0089 */ + false, /* U+008A */ + false, /* U+008B */ + false, /* U+008C */ + false, /* U+008D */ + false, /* U+008E */ + false, /* U+008F */ + false, /* U+0090 */ + false, /* U+0091 */ + false, /* U+0092 */ + false, /* U+0093 */ + false, /* U+0094 */ + false, /* U+0095 */ + false, /* U+0096 */ + false, /* U+0097 */ + false, /* U+0098 */ + false, /* U+0099 */ + false, /* U+009A */ + false, /* U+009B */ + false, /* U+009C */ + false, /* U+009D */ + false, /* U+009E */ + false, /* U+009F */ + false, /* U+00A0 */ + false, /* U+00A1 */ + false, /* U+00A2 */ + false, /* U+00A3 */ + false, /* U+00A4 */ + false, /* U+00A5 */ + false, /* U+00A6 */ + false, /* U+00A7 */ + false, /* U+00A8 */ + false, /* U+00A9 */ + false, /* U+00AA */ + false, /* U+00AB */ + false, /* U+00AC */ + false, /* U+00AD */ + false, /* U+00AE */ + false, /* U+00AF */ + false, /* U+00B0 */ + false, /* U+00B1 */ + false, /* U+00B2 */ + false, /* U+00B3 */ + false, /* U+00B4 */ + false, /* U+00B5 */ + false, /* U+00B6 */ + false, /* U+00B7 */ + false, /* U+00B8 */ + false, /* U+00B9 */ + false, /* U+00BA */ + false, /* U+00BB */ + false, /* U+00BC */ + false, /* U+00BD */ + false, /* U+00BE */ + false, /* U+00BF */ + false, /* U+00C0 */ + false, /* U+00C1 */ + false, /* U+00C2 */ + false, /* U+00C3 */ + false, /* U+00C4 */ + false, /* U+00C5 */ + false, /* U+00C6 */ + false, /* U+00C7 */ + false, /* U+00C8 */ + false, /* U+00C9 */ + false, /* U+00CA */ + false, /* U+00CB */ + false, /* U+00CC */ + false, /* U+00CD */ + false, /* U+00CE */ + false, /* U+00CF */ + false, /* U+00D0 */ + false, /* U+00D1 */ + false, /* U+00D2 */ + false, /* U+00D3 */ + false, /* U+00D4 */ + false, /* U+00D5 */ + false, /* U+00D6 */ + false, /* U+00D7 */ + false, /* U+00D8 */ + false, /* U+00D9 */ + false, /* U+00DA */ + false, /* U+00DB */ + false, /* U+00DC */ + false, /* U+00DD */ + false, /* U+00DE */ + false, /* U+00DF */ + false, /* U+00E0 */ + false, /* U+00E1 */ + false, /* U+00E2 */ + false, /* U+00E3 */ + false, /* U+00E4 */ + false, /* U+00E5 */ + false, /* U+00E6 */ + false, /* U+00E7 */ + false, /* U+00E8 */ + false, /* U+00E9 */ + false, /* U+00EA */ + false, /* U+00EB */ + false, /* U+00EC */ + false, /* U+00ED */ + false, /* U+00EE */ + false, /* U+00EF */ + false, /* U+00F0 */ + false, /* U+00F1 */ + false, /* U+00F2 */ + false, /* U+00F3 */ + false, /* U+00F4 */ + false, /* U+00F5 */ + false, /* U+00F6 */ + false, /* U+00F7 */ + false, /* U+00F8 */ + false, /* U+00F9 */ + false, /* U+00FA */ + false, /* U+00FB */ + false, /* U+00FC */ + false, /* U+00FD */ + false, /* U+00FE */ + false, /* U+00FF */ +}; + diff --git a/intl/icu/source/tools/escapesrc/escapesrc.cpp b/intl/icu/source/tools/escapesrc/escapesrc.cpp new file mode 100644 index 0000000000..10ac3d1aef --- /dev/null +++ b/intl/icu/source/tools/escapesrc/escapesrc.cpp @@ -0,0 +1,427 @@ +// © 2016 and later: Unicode, Inc. and others. +// License & terms of use: http://www.unicode.org/copyright.html + +#include +#include +#include +#include +#include +#include +#include + +// We only use U8_* macros, which are entirely inline. +#include "unicode/utf8.h" + +// This contains a codepage and ISO 14882:1998 illegality table. +// Use "make gen-table" to rebuild it. +#include "cptbl.h" + +/** + * What is this? + * + * "This" is a preprocessor that makes an attempt to convert fully valid C++11 source code + * in utf-8 into something consumable by certain compilers (Solaris, xlC) + * which aren't quite standards compliant. + * + * - u"" or u'' gets converted to u"\uNNNN" or u'\uNNNN' + * - u8"" gets converted to "\xAA\xBB\xCC\xDD" etc. + * (some compilers do not support the u8 prefix correctly.) + * - if the system is EBCDIC-based, that is used to correct the input characters. + * + * Usage: + * escapesrc infile.cpp outfile.cpp + * Normally this is invoked by the build stage, with a rule such as: + * + * _%.cpp: $(srcdir)/%.cpp + * @$(BINDIR)/escapesrc$(EXEEXT) $< $@ + * %.o: _%.cpp + * $(COMPILE.cc) ... $@ $< + * + * In the Makefiles, SKIP_ESCAPING=YES is used to prevent escapesrc.cpp + * from being itself escaped. + */ + + +static const char + kSPACE = 0x20, + kTAB = 0x09, + kLF = 0x0A, + kCR = 0x0D; + +// For convenience +# define cp1047_to_8859(c) cp1047_8859_1[c] + +// Our app's name +std::string prog; + +/** + * Give the usual 1-line documentation and exit + */ +void usage() { + fprintf(stderr, "%s: usage: %s infile.cpp outfile.cpp\n", prog.c_str(), prog.c_str()); +} + +/** + * Delete the output file (if any) + * We want to delete even if we didn't generate, because it might be stale. + */ +int cleanup(const std::string &outfile) { + const char *outstr = outfile.c_str(); + if(outstr && *outstr) { + int rc = std::remove(outstr); + if(rc == 0) { + fprintf(stderr, "%s: deleted %s\n", prog.c_str(), outstr); + return 0; + } else { + if( errno == ENOENT ) { + return 0; // File did not exist - no error. + } else { + perror("std::remove"); + return 1; + } + } + } + return 0; +} + +/** + * Skip across any known whitespace. + * @param p startpoint + * @param e limit + * @return first non-whitespace char + */ +inline const char *skipws(const char *p, const char *e) { + for(;p0; pos2++,trail--) { + linestr[pos2] = cp1047_to_8859(linestr[pos2]); + if(linestr[pos2] == 0x0A) { + linestr[pos2] = 0x85; // NL is ambiguous here + } + } +#endif + + // Proceed to decode utf-8 + const uint8_t *s = (const uint8_t*) (linestr.c_str()); + int32_t length = linestr.size(); + UChar32 c; + if(U8_IS_SINGLE((uint8_t)s[i]) && oldIllegal[s[i]]) { +#if (U_CHARSET_FAMILY == U_EBCDIC_FAMILY) + linestr[pos] = old_byte; // put it back +#endif + continue; // single code point not previously legal for \u escaping + } + + // otherwise, convert it to \u / \U + { + U8_NEXT(s, i, length, c); + } + if(c<0) { + fprintf(stderr, "Illegal utf-8 sequence at Column: %d\n", (int)old_pos); + fprintf(stderr, "Line: >>%s<<\n", linestr.c_str()); + return true; + } + + size_t seqLen = (i-pos); + + //printf("U+%04X pos %d [len %d]\n", c, pos, seqLen);fflush(stdout); + + char newSeq[20]; + if( c <= 0xFFFF) { + snprintf(newSeq, sizeof(newSeq), "\\u%04X", c); + } else { + snprintf(newSeq, sizeof(newSeq), "\\U%08X", c); + } + linestr.replace(pos, seqLen, newSeq); + pos += strlen(newSeq) - 1; + } + } + + return false; +} + +/** + * Fixup an entire line + * false = no err + * true = had err + * @param no the line number (not used) + * @param linestr the string to fix + * @return true if any err, else false + */ +bool fixLine(int /*no*/, std::string &linestr) { + const char *line = linestr.c_str(); + size_t len = linestr.size(); + + // no u' in the line? + if(!strstr(line, "u'") && !strstr(line, "u\"") && !strstr(line, "u8\"")) { + return false; // Nothing to do. No u' or u" detected + } + + // start from the end and find all u" cases + size_t pos = len = linestr.size(); + if(len>INT32_MAX/2) { + return true; + } + while((pos>0) && (pos = linestr.rfind("u\"", pos)) != std::string::npos) { + //printf("found doublequote at %d\n", pos); + if(fixAt(linestr, pos)) return true; + if(pos == 0) break; + pos--; + } + + // reset and find all u' cases + pos = len = linestr.size(); + while((pos>0) && (pos = linestr.rfind("u'", pos)) != std::string::npos) { + //printf("found singlequote at %d\n", pos); + if(fixAt(linestr, pos)) return true; + if(pos == 0) break; + pos--; + } + + // reset and find all u8" cases + pos = len = linestr.size(); + while((pos>0) && (pos = linestr.rfind("u8\"", pos)) != std::string::npos) { + if(fixAt(linestr, pos)) return true; + if(pos == 0) break; + pos--; + } + + //fprintf(stderr, "%d - fixed\n", no); + return false; +} + +/** + * Convert a whole file + * @param infile + * @param outfile + * @return 1 on err, 0 otherwise + */ +int convert(const std::string &infile, const std::string &outfile) { + fprintf(stderr, "escapesrc: %s -> %s\n", infile.c_str(), outfile.c_str()); + + std::ifstream inf; + + inf.open(infile.c_str(), std::ios::in); + + if(!inf.is_open()) { + fprintf(stderr, "%s: could not open input file %s\n", prog.c_str(), infile.c_str()); + cleanup(outfile); + return 1; + } + + std::ofstream outf; + + outf.open(outfile.c_str(), std::ios::out); + + if(!outf.is_open()) { + fprintf(stderr, "%s: could not open output file %s\n", prog.c_str(), outfile.c_str()); + return 1; + } + + // TODO: any platform variations of #line? + outf << "#line 1 \"" << infile << "\"" << '\n'; + + int no = 0; + std::string linestr; + while( getline( inf, linestr)) { + no++; + if(fixLine(no, linestr)) { + goto fail; + } + outf << linestr << '\n'; + } + + if(inf.eof()) { + return 0; + } +fail: + outf.close(); + fprintf(stderr, "%s:%d: Fixup failed by %s\n", infile.c_str(), no, prog.c_str()); + cleanup(outfile); + return 1; +} + +/** + * Main function + */ +int main(int argc, const char *argv[]) { + prog = argv[0]; + + if(argc != 3) { + usage(); + return 1; + } + + std::string infile = argv[1]; + std::string outfile = argv[2]; + + return convert(infile, outfile); +} diff --git a/intl/icu/source/tools/escapesrc/expect-simple.cpp b/intl/icu/source/tools/escapesrc/expect-simple.cpp new file mode 100644 index 0000000000..a6019a8d40 --- /dev/null +++ b/intl/icu/source/tools/escapesrc/expect-simple.cpp @@ -0,0 +1,17 @@ +// © 2016 and later: Unicode, Inc. and others. +// License & terms of use: http://www.unicode.org/copyright.html + +u"sa\u0127\u0127a"; +u'\u6587'; +u"\U000219F2"; +u"\u039C\u03C5\u03C3\u03C4\u03AE\u03C1\u03B9\u03BF"; + + u"sa\u0127\u0127a"; + u'\u6587'; u"\U000219F2"; + +"\x20\xCC\x81"; +"\xCC\x88\x20"; +"\x73\x61\xC4\xA7\xC4\xA7\x61"; +"\xE6\x96\x87"; +"\xF0\xA1\xA7\xB2"; +"\x73\x61\xC4\xA7\xC4\xA7\x61"; diff --git a/intl/icu/source/tools/escapesrc/tblgen.cpp b/intl/icu/source/tools/escapesrc/tblgen.cpp new file mode 100644 index 0000000000..dce4af6867 --- /dev/null +++ b/intl/icu/source/tools/escapesrc/tblgen.cpp @@ -0,0 +1,80 @@ +// © 2016 and later: Unicode, Inc. and others. +// License & terms of use: http://www.unicode.org/copyright.html + +#include "unicode/utypes.h" +#include "unicode/ucnv.h" +#include "unicode/uniset.h" +#include + +static const char *kConverter = "ibm-1047"; + +int main(int argc, const char *argv[]) { + printf("// %s\n", U_COPYRIGHT_STRING); + printf("// generated by tblgen. You weren't going to edit it by hand, were you?\n"); + printf("\n"); + + UErrorCode status = U_ZERO_ERROR; + LocalUConverterPointer cnv(ucnv_open(kConverter, &status)); + + if(U_FAILURE(status)) { + fprintf(stderr, "Failed to open %s: %s\n", kConverter, u_errorName(status)); + return 1; + } + + printf("static const char cp1047_8859_1[256] = { \n"); + for(int i=0x00; i<0x100; i++) { + char cp1047[1]; + cp1047[0] = i; + char16_t u[1]; + char16_t *target = u; + const char *source = cp1047; + ucnv_toUnicode(cnv.getAlias(), &target, u+1, &source, cp1047+1, nullptr, true, &status); + if(U_FAILURE(status)) { + fprintf(stderr, "Conversion failure at #%X: %s\n", i, u_errorName(status)); + return 2; + } + printf(" (char)0x%02X, /* %02X */\n", u[0], i); + } + printf("};\n\n"); + + // + // UnicodeSet oldIllegal("[:print:]", status); // [a-zA-Z0-9_}{#)(><%:;.?*+-/^&|~!=,\\u005b\\u005d\\u005c]", status); + UnicodeSet oldIllegal("[0-9 a-z A-Z " + "_ \\{ \\} \\[ \\] # \\( \\) < > % \\: ; . " + "? * + \\- / \\^ \\& | ~ ! = , \\ \" ' ]", status); + + /* + +http://www.lirmm.fr/~ducour/Doc-objets/ISO+IEC+14882-1998.pdf ( note: 1998 ) page 10, section 2.2 says: + +1 The basic source character set consists of 96 characters: the space character, the control characters repre- 15) +senting horizontal tab, vertical tab, form feed, and new-line, plus the following 91 graphical characters: +a b c d e f g h i j k l m n opqrstuvwxyz +A B C D E F G H I J K L M N OPQRSTUVWXYZ +0 12 3 4 5 6 7 8 9 + _ { } [ ] # ( ) < > % : ; . ?*+-/^&|~!=,\" +2 The universal-character-name construct provides a way to name other characters. hex-quad: +hexadecimal-digit hexadecimal-digit hexadecimal-digit hexadecimal-digit +universal-character-name: \u hex-quad +\U hex-quad hex-quad +The character designated by the universal-character-name \UNNNNNNNN is that character whose character short name in ISO/IEC 10646 is NNNNNNNN; the character designated by the universal-character-name \uNNNN is that character whose character short name in ISO/IEC 10646 is 0000NNNN. If the hexadecimal value for a universal character name is less than 0x20 or in the range 0x7F-0x9F (inclusive), or if the uni- versal character name designates a character in the basic source character set, then the program is ill- formed. + + +So basically: printable ASCII plus 0x00-0x1F, 0x7F-0x9F, was all illegal. + +Some discussion at http://unicode.org/mail-arch/unicode-ml/y2003-m10/0471.html + + */ + + + + printf("static const bool oldIllegal[256] = { \n"); + for(char16_t i=0x00; i<0x100;i++) { + printf(" %s, /* U+%04X */\n", + (oldIllegal.contains(i))?" true":"false", + i); + } + printf("};\n\n"); + + return 0; +} diff --git a/intl/icu/source/tools/escapesrc/test-nochange.cpp b/intl/icu/source/tools/escapesrc/test-nochange.cpp new file mode 100644 index 0000000000..8c0d04b809 --- /dev/null +++ b/intl/icu/source/tools/escapesrc/test-nochange.cpp @@ -0,0 +1,5 @@ +// © 2016 and later: Unicode, Inc. and others. +// License & terms of use: http://www.unicode.org/copyright.html + +// This is a source file with no changes needed in it. +// In fact, the only non-ASCII character is the comment line at top. diff --git a/intl/icu/source/tools/escapesrc/test-simple.cpp b/intl/icu/source/tools/escapesrc/test-simple.cpp new file mode 100644 index 0000000000..b03f28f706 --- /dev/null +++ b/intl/icu/source/tools/escapesrc/test-simple.cpp @@ -0,0 +1,17 @@ +// © 2016 and later: Unicode, Inc. and others. +// License & terms of use: http://www.unicode.org/copyright.html + +u"saħħa"; +u'文'; +u"𡧲"; +u"Μυστήριο"; + + u"saħħa"; + u'文'; u"𡧲"; + +u8" \u0301"; +u8"\u0308 "; +u8"saħħa"; +u8"文"; +u8"𡧲"; +u8"saħ\u0127a"; -- cgit v1.2.3