AuroraMiddleware/scuffed-code
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

ICU-8972 merge gencase into genprops

Browse Source 
X-SVN-Rev: 31189
This commit is contained in:
Markus Scherer 2012-01-10 07:23:44 +00:00
parent 6390003c87
commit f712c8bc00
16 changed files with 1243 additions and 2764 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

16
.gitignore vendored
View File

@ -964,22 +964,6 @@ tools/trac/IcuCodeTools/0.11/icucodetools/*.pyc
tools/trac/IcuCodeTools/0.12/*.egg-info
tools/trac/IcuCodeTools/0.12/build
tools/trac/IcuCodeTools/0.12/icucodetools/*.pyc
tools/unicode/c/gencase/*.d
tools/unicode/c/gencase/*.ncb
tools/unicode/c/gencase/*.o
tools/unicode/c/gencase/*.opt
tools/unicode/c/gencase/*.pdb
tools/unicode/c/gencase/*.plg
tools/unicode/c/gencase/Debug
tools/unicode/c/gencase/Makefile
tools/unicode/c/gencase/Release
tools/unicode/c/gencase/debug
tools/unicode/c/gencase/gencase
tools/unicode/c/gencase/gencase.[0-9]
tools/unicode/c/gencase/gencase.vcproj.*.*.user
tools/unicode/c/gencase/release
tools/unicode/c/gencase/x64
tools/unicode/c/gencase/x86
tools/unicode/c/genprops/*.d
tools/unicode/c/genprops/*.ncb
tools/unicode/c/genprops/*.o

1
tools/unicode/c/CMakeLists.txt
View File

@ -17,7 +17,6 @@ include_directories(
${ICU_SRC_DIR}/source/i18n
${ICU_SRC_DIR}/source/tools/toolutil)
link_directories(${ICU_INST_DIR}/lib)
add_subdirectory(gencase)
add_subdirectory(genprops)
add_subdirectory(genuca)
add_subdirectory(genuts46)

9
tools/unicode/c/gencase/CMakeLists.txt
View File

@ -1,9 +0,0 @@
# Copyright (C) 2010, International Business Machines
# Corporation and others. All Rights Reserved.
#
# created on: 2010jun03
# created by: Markus W. Scherer
# edited on: 2010jul20
# edited by: Stuart G. Gill
add_executable(gencase gencase.c store.c)
target_link_libraries(gencase icuuc icutu)

95
tools/unicode/c/gencase/Makefile.in
View File

@ -1,95 +0,0 @@
## Makefile.in for ICU - tools/gencase
## Copyright (c) 1999-2005, International Business Machines Corporation and
## others. All Rights Reserved.
## Steven R. Loomis
## Source directory information
srcdir = @srcdir@
top_srcdir = @top_srcdir@
top_builddir = ../..
include $(top_builddir)/icudefs.mk
## Build directory information
subdir = tools/gencase
TARGET_STUB_NAME = gencase
SECTION = 8
#MAN_FILES = $(TARGET_STUB_NAME).$(SECTION)
## Extra files to remove for 'make clean'
CLEANFILES = *~ $(DEPS) $(MAN_FILES)
## Target information
TARGET = $(BINDIR)/$(TARGET_STUB_NAME)$(EXEEXT)
ifneq ($(top_builddir),$(top_srcdir))
CPPFLAGS += -I$(top_builddir)/common
endif
CPPFLAGS += -I$(top_srcdir)/common -I$(srcdir)/../toolutil
LIBS = $(LIBICUTOOLUTIL) $(LIBICUI18N) $(LIBICUUC) $(DEFAULT_LIBS) $(LIB_M)
OBJECTS = gencase.o store.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
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
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= $(SHELL) ./config.status
ifeq (,$(MAKECMDGOALS))
-include $(DEPS)
else
ifneq ($(patsubst %clean,,$(MAKECMDGOALS)),)
-include $(DEPS)
endif
endif

865
tools/unicode/c/gencase/gencase.c
View File

@ -1,865 +0,0 @@
/*
*******************************************************************************
*
* Copyright (C) 2004-2011, International Business Machines
* Corporation and others. All Rights Reserved.
*
*******************************************************************************
* file name: gencase.c
* encoding: US-ASCII
* tab size: 8 (not used)
* indentation:4
*
* created on: 2004aug28
* created by: Markus W. Scherer
*
* This program reads several of the Unicode character database text files,
* parses them, and the case mapping properties for each character.
* It then writes a binary file containing the properties
* that is designed to be used directly for random-access to
* the properties of each Unicode character.
*/
#include <stdio.h>
#include "unicode/utypes.h"
#include "unicode/uchar.h"
#include "unicode/uset.h"
#include "unicode/putil.h"
#include "unicode/uclean.h"
#include "cmemory.h"
#include "cstring.h"
#include "uarrsort.h"
#include "unewdata.h"
#include "uoptions.h"
#include "uparse.h"
#include "uprops.h"
#include "propsvec.h"
#include "gencase.h"
#define LENGTHOF(array) (sizeof(array)/sizeof((array)[0]))
/* data --------------------------------------------------------------------- */
UPropsVectors *pv;
UBool beVerbose=FALSE, haveCopyright=TRUE;
/*
* Unicode set collecting the case-sensitive characters;
* see uchar.h UCHAR_CASE_SENSITIVE.
* Add code points from case mappings/foldings in
* the root locale and with default options.
*/
static USet *caseSensitive;
/* prototypes --------------------------------------------------------------- */
static void
parseSpecialCasing(const char *filename, UErrorCode *pErrorCode);
static void
parseCaseFolding(const char *filename, UErrorCode *pErrorCode);
static void
parseDB(const char *filename, UErrorCode *pErrorCode);
/* parse files with multiple binary properties ------------------------------ */
/* TODO: more common code, move functions to uparse.h|c */
/* TODO: similar to genprops/props2.c but not the same */
struct Binary {
const char *propName;
int32_t vecWord;
uint32_t vecValue, vecMask;
};
typedef struct Binary Binary;
struct Binaries {
const char *ucdFile;
const Binary *binaries;
int32_t binariesCount;
};
typedef struct Binaries Binaries;
static const Binary
propListNames[]={
{ "Soft_Dotted", 0, UCASE_SOFT_DOTTED, UCASE_DOT_MASK }
};
static const Binaries
propListBinaries={
"PropList", propListNames, LENGTHOF(propListNames)
};
static const Binary
derCorePropsNames[]={
{ "Lowercase", 0, UCASE_LOWER, UCASE_TYPE_MASK },
{ "Uppercase", 0, UCASE_UPPER, UCASE_TYPE_MASK },
/* Unicode 5.2 adds Case_Ignorable as a public property. See comments in store.c. */
{ "Case_Ignorable", 1, U_MASK(UGENCASE_IS_MID_LETTER_SHIFT), U_MASK(UGENCASE_IS_MID_LETTER_SHIFT) }
};
static const Binaries
derCorePropsBinaries={
"DerivedCoreProperties", derCorePropsNames, LENGTHOF(derCorePropsNames)
};
/*
* Treat Word_Break=MidLetter and MidNumLet as a single binary property.
* We need not distinguish between them because both add to case-ignorable.
* We ignore all other Word_Break values.
*/
static const Binary
wordBreakNames[]={
{ "MidLetter", 1, U_MASK(UGENCASE_IS_MID_LETTER_SHIFT), U_MASK(UGENCASE_IS_MID_LETTER_SHIFT) },
{ "MidNumLet", 1, U_MASK(UGENCASE_IS_MID_LETTER_SHIFT), U_MASK(UGENCASE_IS_MID_LETTER_SHIFT) }
};
static const Binaries
wordBreakBinaries={
"WordBreakProperty", wordBreakNames, LENGTHOF(wordBreakNames)
};
static void U_CALLCONV
binariesLineFn(void *context,
char *fields[][2], int32_t fieldCount,
UErrorCode *pErrorCode) {
const Binaries *bin;
char *s;
uint32_t start, end;
int32_t i;
bin=(const Binaries *)context;
u_parseCodePointRange(fields[0][0], &start, &end, pErrorCode);
if(U_FAILURE(*pErrorCode)) {
fprintf(stderr, "gencase: syntax error in %s.txt field 0 at %s\n", bin->ucdFile, fields[0][0]);
exit(*pErrorCode);
}
/* parse binary property name */
s=(char *)u_skipWhitespace(fields[1][0]);
for(i=0;; ++i) {
if(i==bin->binariesCount) {
/* ignore unrecognized properties */
return;
}
if(isToken(bin->binaries[i].propName, s)) {
break;
}
}
if(bin->binaries[i].vecMask==0) {
fprintf(stderr, "gencase error: mask value %d==0 for %s %s\n",
(int)bin->binaries[i].vecMask, bin->ucdFile, bin->binaries[i].propName);
exit(U_INTERNAL_PROGRAM_ERROR);
}
upvec_setValue(pv, start, end, bin->binaries[i].vecWord, bin->binaries[i].vecValue, bin->binaries[i].vecMask, pErrorCode);
if(U_FAILURE(*pErrorCode)) {
fprintf(stderr, "gencase error: unable to set %s, code: %s\n",
bin->binaries[i].propName, u_errorName(*pErrorCode));
exit(*pErrorCode);
}
}
static void
parseBinariesFile(char *filename, char *basename, const char *suffix,
const Binaries *bin,
UErrorCode *pErrorCode) {
char *fields[2][2];
if(pErrorCode==NULL || U_FAILURE(*pErrorCode)) {
return;
}
writeUCDFilename(basename, bin->ucdFile, suffix);
u_parseDelimitedFile(filename, ';', fields, 2, binariesLineFn, (void *)bin, pErrorCode);
if(U_FAILURE(*pErrorCode)) {
fprintf(stderr, "error parsing %s.txt: %s\n", bin->ucdFile, u_errorName(*pErrorCode));
}
}
/* -------------------------------------------------------------------------- */
enum
{
HELP_H,
HELP_QUESTION_MARK,
VERBOSE,
COPYRIGHT,
DESTDIR,
SOURCEDIR,
UNICODE_VERSION,
ICUDATADIR,
CSOURCE
};
/* Keep these values in sync with the above enums */
static UOption options[]={
UOPTION_HELP_H,
UOPTION_HELP_QUESTION_MARK,
UOPTION_VERBOSE,
UOPTION_COPYRIGHT,
UOPTION_DESTDIR,
UOPTION_SOURCEDIR,
UOPTION_DEF("unicode", 'u', UOPT_REQUIRES_ARG),
UOPTION_ICUDATADIR,
UOPTION_DEF("csource", 'C', UOPT_NO_ARG)
};
extern int
main(int argc, char* argv[]) {
char filename[300];
const char *srcDir=NULL, *destDir=NULL, *suffix=NULL;
char *basename=NULL;
UErrorCode errorCode=U_ZERO_ERROR;
U_MAIN_INIT_ARGS(argc, argv);
/* preset then read command line options */
options[DESTDIR].value=u_getDataDirectory();
options[SOURCEDIR].value="";
options[UNICODE_VERSION].value="";
options[ICUDATADIR].value=u_getDataDirectory();
argc=u_parseArgs(argc, argv, sizeof(options)/sizeof(options[0]), options);
/* error handling, printing usage message */
if(argc<0) {
fprintf(stderr,
"error in command line argument \"%s\"\n",
argv[-argc]);
}
if(argc<0 || options[HELP_H].doesOccur || options[HELP_QUESTION_MARK].doesOccur) {
/*
* Broken into chunks because the C89 standard says the minimum
* required supported string length is 509 bytes.
*/
fprintf(stderr,
"Usage: %s [-options] [suffix]\n"
"\n"
"read the UnicodeData.txt file and other Unicode properties files and\n"
"create a binary file " UCASE_DATA_NAME "." UCASE_DATA_TYPE " with the case mapping properties\n"
"\n",
argv[0]);
fprintf(stderr,
"Options:\n"
"\t-h or -? or --help this usage text\n"
"\t-v or --verbose verbose output\n"
"\t-c or --copyright include a copyright notice\n"
"\t-u or --unicode Unicode version, followed by the version like 3.0.0\n"
"\t-C or --csource generate a .c source file rather than the .icu binary\n");
fprintf(stderr,
"\t-d or --destdir destination directory, followed by the path\n"
"\t-s or --sourcedir source directory, followed by the path\n"
"\t-i or --icudatadir directory for locating any needed intermediate data files,\n"
"\t followed by path, defaults to %s\n"
"\tsuffix suffix that is to be appended with a '-'\n"
"\t to the source file basenames before opening;\n"
"\t 'gencase new' will read UnicodeData-new.txt etc.\n",
u_getDataDirectory());
return argc<0 ? U_ILLEGAL_ARGUMENT_ERROR : U_ZERO_ERROR;
}
/* get the options values */
beVerbose=options[VERBOSE].doesOccur;
haveCopyright=options[COPYRIGHT].doesOccur;
srcDir=options[SOURCEDIR].value;
destDir=options[DESTDIR].value;
if(argc>=2) {
suffix=argv[1];
} else {
suffix=NULL;
}
if(options[UNICODE_VERSION].doesOccur) {
setUnicodeVersion(options[UNICODE_VERSION].value);
}
/* else use the default dataVersion in store.c */
if (options[ICUDATADIR].doesOccur) {
u_setDataDirectory(options[ICUDATADIR].value);
}
/* prepare the filename beginning with the source dir */
uprv_strcpy(filename, srcDir);
basename=filename+uprv_strlen(filename);
if(basename>filename && *(basename-1)!=U_FILE_SEP_CHAR) {
*basename++=U_FILE_SEP_CHAR;
}
/* initialize */
pv=upvec_open(2, &errorCode);
caseSensitive=uset_open(1, 0); /* empty set (start>end) */
/* process SpecialCasing.txt */
writeUCDFilename(basename, "SpecialCasing", suffix);
parseSpecialCasing(filename, &errorCode);
if(U_FAILURE(errorCode)) {
fprintf(stderr, "error parsing SpecialCasing.txt: %s\n", u_errorName(errorCode));
return errorCode;
}
/* process CaseFolding.txt */
writeUCDFilename(basename, "CaseFolding", suffix);
parseCaseFolding(filename, &errorCode);
if(U_FAILURE(errorCode)) {
fprintf(stderr, "error parsing CaseFolding.txt: %s\n", u_errorName(errorCode));
return errorCode;
}
/* process additional properties files */
*basename=0;
parseBinariesFile(filename, basename, suffix, &propListBinaries, &errorCode);
parseBinariesFile(filename, basename, suffix, &derCorePropsBinaries, &errorCode);
if(ucdVersion>=UNI_4_1) {
parseBinariesFile(filename, basename, suffix, &wordBreakBinaries, &errorCode);
}
/* process UnicodeData.txt */
writeUCDFilename(basename, "UnicodeData", suffix);
parseDB(filename, &errorCode);
if(U_FAILURE(errorCode)) {
fprintf(stderr, "error parsing UnicodeData.txt: %s\n", u_errorName(errorCode));
return errorCode;
}
/* process parsed data */
makeCaseClosure();
makeExceptions();
if(U_SUCCESS(errorCode)) {
/* write the properties data file */
generateData(destDir, options[CSOURCE].doesOccur);
}
u_cleanup();
return errorCode;
}
U_CFUNC void
writeUCDFilename(char *basename, const char *filename, const char *suffix) {
int32_t length=(int32_t)uprv_strlen(filename);
uprv_strcpy(basename, filename);
if(suffix!=NULL) {
basename[length++]='-';
uprv_strcpy(basename+length, suffix);
length+=(int32_t)uprv_strlen(suffix);
}
uprv_strcpy(basename+length, ".txt");
}
/* TODO: move to toolutil */
U_CFUNC UBool
isToken(const char *token, const char *s) {
const char *z;
int32_t j;
s=u_skipWhitespace(s);
for(j=0;; ++j) {
if(token[j]!=0) {
if(s[j]!=token[j]) {
break;
}
} else {
z=u_skipWhitespace(s+j);
if(*z==';' || *z==0) {
return TRUE;
} else {
break;
}
}
}
return FALSE;
}
static int32_t
getTokenIndex(const char *const tokens[], int32_t countTokens, const char *s) {
const char *t, *z;
int32_t i, j;
s=u_skipWhitespace(s);
for(i=0; i<countTokens; ++i) {
t=tokens[i];
if(t!=NULL) {
for(j=0;; ++j) {
if(t[j]!=0) {
if(s[j]!=t[j]) {
break;
}
} else {
z=u_skipWhitespace(s+j);
if(*z==';' || *z==0 || *z=='#' || *z=='\r' || *z=='\n') {
return i;
} else {
break;
}
}
}
}
}
return -1;
}
static void
_set_addAll(USet *set, const UChar *s, int32_t length) {
UChar32 c;
int32_t i;
/* needs length>=0 */
for(i=0; i<length; /* U16_NEXT advances i */) {
U16_NEXT(s, i, length, c);
uset_add(set, c);
}
}
/* parser for SpecialCasing.txt --------------------------------------------- */
#define MAX_SPECIAL_CASING_COUNT 500
static SpecialCasing specialCasings[MAX_SPECIAL_CASING_COUNT];
static int32_t specialCasingCount=0;
static void U_CALLCONV
specialCasingLineFn(void *context,
char *fields[][2], int32_t fieldCount,
UErrorCode *pErrorCode) {
char *end;
/* get code point */
const char *s=u_skipWhitespace(fields[0][0]);
if(0==uprv_strncmp(s, "0000..10FFFF", 12)) {
/*
* Ignore the line
* # @missing: 0000..10FFFF; <slc>; <stc>; <suc>;
* because maps-to-self is already our default, and this line breaks this parser.
*/
return;
}
specialCasings[specialCasingCount].code=(UChar32)uprv_strtoul(s, &end, 16);
end=(char *)u_skipWhitespace(end);
if(end<=fields[0][0] || end!=fields[0][1]) {
fprintf(stderr, "gencase: syntax error in SpecialCasing.txt field 0 at %s\n", fields[0][0]);
*pErrorCode=U_PARSE_ERROR;
exit(U_PARSE_ERROR);
}
/* is this a complex mapping? */
if(*(end=(char *)u_skipWhitespace(fields[4][0]))!=0 && *end!=';' && *end!='#') {
/* there is some condition text in the fifth field */
specialCasings[specialCasingCount].isComplex=TRUE;
/* do not store any actual mappings for this */
specialCasings[specialCasingCount].lowerCase[0]=0;
specialCasings[specialCasingCount].upperCase[0]=0;
specialCasings[specialCasingCount].titleCase[0]=0;
} else {
/* just set the "complex" flag and get the case mappings */
specialCasings[specialCasingCount].isComplex=FALSE;
specialCasings[specialCasingCount].lowerCase[0]=
(UChar)u_parseString(fields[1][0], specialCasings[specialCasingCount].lowerCase+1, 31, NULL, pErrorCode);
specialCasings[specialCasingCount].upperCase[0]=
(UChar)u_parseString(fields[3][0], specialCasings[specialCasingCount].upperCase+1, 31, NULL, pErrorCode);
specialCasings[specialCasingCount].titleCase[0]=
(UChar)u_parseString(fields[2][0], specialCasings[specialCasingCount].titleCase+1, 31, NULL, pErrorCode);
if(U_FAILURE(*pErrorCode)) {
fprintf(stderr, "gencase: error parsing special casing at %s\n", fields[0][0]);
exit(*pErrorCode);
}
uset_add(caseSensitive, (UChar32)specialCasings[specialCasingCount].code);
_set_addAll(caseSensitive, specialCasings[specialCasingCount].lowerCase+1, specialCasings[specialCasingCount].lowerCase[0]);
_set_addAll(caseSensitive, specialCasings[specialCasingCount].upperCase+1, specialCasings[specialCasingCount].upperCase[0]);
_set_addAll(caseSensitive, specialCasings[specialCasingCount].titleCase+1, specialCasings[specialCasingCount].titleCase[0]);
}
if(++specialCasingCount==MAX_SPECIAL_CASING_COUNT) {
fprintf(stderr, "gencase: too many special casing mappings\n");
*pErrorCode=U_INDEX_OUTOFBOUNDS_ERROR;
exit(U_INDEX_OUTOFBOUNDS_ERROR);
}
}
static int32_t U_CALLCONV
compareSpecialCasings(const void *context, const void *left, const void *right) {
return ((const SpecialCasing *)left)->code-((const SpecialCasing *)right)->code;
}
static void
parseSpecialCasing(const char *filename, UErrorCode *pErrorCode) {
char *fields[5][2];
int32_t i, j;
if(pErrorCode==NULL || U_FAILURE(*pErrorCode)) {
return;
}
u_parseDelimitedFile(filename, ';', fields, 5, specialCasingLineFn, NULL, pErrorCode);
/* sort the special casing entries by code point */
if(specialCasingCount>0) {
uprv_sortArray(specialCasings, specialCasingCount, sizeof(SpecialCasing),
compareSpecialCasings, NULL, FALSE, pErrorCode);
}
if(U_FAILURE(*pErrorCode)) {
return;
}
/* replace multiple entries for any code point by one "complex" one */
j=0;
for(i=1; i<specialCasingCount; ++i) {
if(specialCasings[i-1].code==specialCasings[i].code) {
/* there is a duplicate code point */
specialCasings[i-1].code=0x7fffffff; /* remove this entry in the following sorting */
specialCasings[i].isComplex=TRUE; /* make the following one complex */
specialCasings[i].lowerCase[0]=0;
specialCasings[i].upperCase[0]=0;
specialCasings[i].titleCase[0]=0;
++j;
}
}
/* if some entries just were removed, then re-sort */
if(j>0) {
uprv_sortArray(specialCasings, specialCasingCount, sizeof(SpecialCasing),
compareSpecialCasings, NULL, FALSE, pErrorCode);
specialCasingCount-=j;
}
if(U_FAILURE(*pErrorCode)) {
return;
}
/*
* Add one complex mapping to caseSensitive that was filtered out above:
* Greek final Sigma has a conditional mapping but not locale-sensitive,
* and it is taken when lowercasing just U+03A3 alone.
* 03A3; 03C2; 03A3; 03A3; Final_Sigma; # GREEK CAPITAL LETTER SIGMA
*/
uset_add(caseSensitive, 0x3c2);
}
/* parser for CaseFolding.txt ----------------------------------------------- */
#define MAX_CASE_FOLDING_COUNT 2000
static CaseFolding caseFoldings[MAX_CASE_FOLDING_COUNT];
static int32_t caseFoldingCount=0;
static void U_CALLCONV
caseFoldingLineFn(void *context,
char *fields[][2], int32_t fieldCount,
UErrorCode *pErrorCode) {
char *end;
static UChar32 prevCode=0;
int32_t count;
char status;
/* get code point */
const char *s=u_skipWhitespace(fields[0][0]);
if(0==uprv_strncmp(s, "0000..10FFFF", 12)) {
/*
* Ignore the line
* # @missing: 0000..10FFFF; C; <code point>
* because maps-to-self is already our default, and this line breaks this parser.
*/
return;
}
caseFoldings[caseFoldingCount].code=(UChar32)uprv_strtoul(s, &end, 16);
end=(char *)u_skipWhitespace(end);
if(end<=fields[0][0] || end!=fields[0][1]) {
fprintf(stderr, "gencase: syntax error in CaseFolding.txt field 0 at %s\n", fields[0][0]);
*pErrorCode=U_PARSE_ERROR;
exit(U_PARSE_ERROR);
}
/* get the status of this mapping */
caseFoldings[caseFoldingCount].status=status=*u_skipWhitespace(fields[1][0]);
if(status!='L' && status!='E' && status!='C' && status!='S' && status!='F' && status!='I' && status!='T') {
fprintf(stderr, "gencase: unrecognized status field in CaseFolding.txt at %s\n", fields[0][0]);
*pErrorCode=U_PARSE_ERROR;
exit(U_PARSE_ERROR);
}
/* ignore all case folding mappings that are the same as the UnicodeData.txt lowercase mappings */
if(status=='L') {
return;
}
/* get the mapping */
count=caseFoldings[caseFoldingCount].full[0]=
(UChar)u_parseString(fields[2][0], caseFoldings[caseFoldingCount].full+1, 31, (uint32_t *)&caseFoldings[caseFoldingCount].simple, pErrorCode);
if(U_FAILURE(*pErrorCode)) {
fprintf(stderr, "gencase: error parsing CaseFolding.txt mapping at %s\n", fields[0][0]);
exit(*pErrorCode);
}
/* there is a simple mapping only if there is exactly one code point (count is in UChars) */
if(count==0 || count>2 || (count==2 && UTF_IS_SINGLE(caseFoldings[caseFoldingCount].full[1]))) {
caseFoldings[caseFoldingCount].simple=0;
}
/* update the case-sensitive set */
if(status!='T') {
uset_add(caseSensitive, (UChar32)caseFoldings[caseFoldingCount].code);
_set_addAll(caseSensitive, caseFoldings[caseFoldingCount].full+1, caseFoldings[caseFoldingCount].full[0]);
}
/* check the status */
if(status=='S') {
/* check if there was a full mapping for this code point before */
if( caseFoldingCount>0 &&
caseFoldings[caseFoldingCount-1].code==caseFoldings[caseFoldingCount].code &&
caseFoldings[caseFoldingCount-1].status=='F'
) {
/* merge the two entries */
caseFoldings[caseFoldingCount-1].simple=caseFoldings[caseFoldingCount].simple;
return;
}
} else if(status=='F') {
/* check if there was a simple mapping for this code point before */
if( caseFoldingCount>0 &&
caseFoldings[caseFoldingCount-1].code==caseFoldings[caseFoldingCount].code &&
caseFoldings[caseFoldingCount-1].status=='S'
) {
/* merge the two entries */
uprv_memcpy(caseFoldings[caseFoldingCount-1].full, caseFoldings[caseFoldingCount].full, 32*U_SIZEOF_UCHAR);
return;
}
} else if(status=='I' || status=='T') {
/* check if there was a default mapping for this code point before (remove it) */
while(caseFoldingCount>0 &&
caseFoldings[caseFoldingCount-1].code==caseFoldings[caseFoldingCount].code
) {
prevCode=0;
--caseFoldingCount;
}
/* store only a marker for special handling for cases like dotless i */
caseFoldings[caseFoldingCount].simple=0;
caseFoldings[caseFoldingCount].full[0]=0;
}
/* check that the code points (caseFoldings[caseFoldingCount].code) are in ascending order */
if(caseFoldings[caseFoldingCount].code<=prevCode && caseFoldings[caseFoldingCount].code>0) {
fprintf(stderr, "gencase: error - CaseFolding entries out of order, U+%04lx after U+%04lx\n",
(unsigned long)caseFoldings[caseFoldingCount].code,
(unsigned long)prevCode);
*pErrorCode=U_PARSE_ERROR;
exit(U_PARSE_ERROR);
}
prevCode=caseFoldings[caseFoldingCount].code;
if(++caseFoldingCount==MAX_CASE_FOLDING_COUNT) {
fprintf(stderr, "gencase: too many case folding mappings\n");
*pErrorCode=U_INDEX_OUTOFBOUNDS_ERROR;
exit(U_INDEX_OUTOFBOUNDS_ERROR);
}
}
static void
parseCaseFolding(const char *filename, UErrorCode *pErrorCode) {
char *fields[3][2];
if(pErrorCode==NULL || U_FAILURE(*pErrorCode)) {
return;
}
u_parseDelimitedFile(filename, ';', fields, 3, caseFoldingLineFn, NULL, pErrorCode);
}
/* parser for UnicodeData.txt ----------------------------------------------- */
/* general categories */
const char *const
genCategoryNames[U_CHAR_CATEGORY_COUNT]={
"Cn",
"Lu", "Ll", "Lt", "Lm", "Lo", "Mn", "Me",
"Mc", "Nd", "Nl", "No",
"Zs", "Zl", "Zp",
"Cc", "Cf", "Co", "Cs",
"Pd", "Ps", "Pe", "Pc", "Po",
"Sm", "Sc", "Sk", "So",
"Pi", "Pf"
};
static int32_t specialCasingIndex=0, caseFoldingIndex=0;
static void U_CALLCONV
unicodeDataLineFn(void *context,
char *fields[][2], int32_t fieldCount,
UErrorCode *pErrorCode) {
Props p;
char *end;
static UChar32 prevCode=0;
UChar32 value;
int32_t i;
/* reset the properties */
uprv_memset(&p, 0, sizeof(Props));
/* get the character code, field 0 */
p.code=(UChar32)uprv_strtoul(fields[0][0], &end, 16);
if(end<=fields[0][0] || end!=fields[0][1]) {
fprintf(stderr, "gencase: syntax error in field 0 at %s\n", fields[0][0]);
*pErrorCode=U_PARSE_ERROR;
exit(U_PARSE_ERROR);
}
/* get general category, field 2 */
i=getTokenIndex(genCategoryNames, U_CHAR_CATEGORY_COUNT, fields[2][0]);
if(i>=0) {
p.gc=(uint8_t)i;
} else {
fprintf(stderr, "gencase: unknown general category \"%s\" at code 0x%lx\n",
fields[2][0], (unsigned long)p.code);
*pErrorCode=U_PARSE_ERROR;
exit(U_PARSE_ERROR);
}
/* get canonical combining class, field 3 */
value=(UChar32)uprv_strtoul(fields[3][0], &end, 10);
if(end<=fields[3][0] || end!=fields[3][1] || value>0xff) {
fprintf(stderr, "gencase: syntax error in field 3 at %s\n", fields[0][0]);
*pErrorCode=U_PARSE_ERROR;
exit(U_PARSE_ERROR);
}
p.cc=(uint8_t)value;
/* get uppercase mapping, field 12 */
value=(UChar32)uprv_strtoul(fields[12][0], &end, 16);
if(end!=fields[12][1]) {
fprintf(stderr, "gencase: syntax error in field 12 at code 0x%lx\n",
(unsigned long)p.code);
*pErrorCode=U_PARSE_ERROR;
exit(U_PARSE_ERROR);
}
if(value!=0 && value!=p.code) {
p.upperCase=value;
uset_add(caseSensitive, p.code);
uset_add(caseSensitive, value);
}
/* get lowercase value, field 13 */
value=(UChar32)uprv_strtoul(fields[13][0], &end, 16);
if(end!=fields[13][1]) {
fprintf(stderr, "gencase: syntax error in field 13 at code 0x%lx\n",
(unsigned long)p.code);
*pErrorCode=U_PARSE_ERROR;
exit(U_PARSE_ERROR);
}
if(value!=0 && value!=p.code) {
p.lowerCase=value;
uset_add(caseSensitive, p.code);
uset_add(caseSensitive, value);
}
/* get titlecase value, field 14 */
value=(UChar32)uprv_strtoul(fields[14][0], &end, 16);
if(end!=fields[14][1]) {
fprintf(stderr, "gencase: syntax error in field 14 at code 0x%lx\n",
(unsigned long)p.code);
*pErrorCode=U_PARSE_ERROR;
exit(U_PARSE_ERROR);
}
if(value!=0 && value!=p.code) {
p.titleCase=value;
uset_add(caseSensitive, p.code);
uset_add(caseSensitive, value);
}
/* set additional properties from previously parsed files */
if(specialCasingIndex<specialCasingCount && p.code==specialCasings[specialCasingIndex].code) {
p.specialCasing=specialCasings+specialCasingIndex++;
} else {
p.specialCasing=NULL;
}
if(caseFoldingIndex<caseFoldingCount && p.code==caseFoldings[caseFoldingIndex].code) {
p.caseFolding=caseFoldings+caseFoldingIndex++;
/* ignore "Common" mappings (simple==full) that map to the same code point as the regular lowercase mapping */
if( p.caseFolding->status=='C' &&
p.caseFolding->simple==p.lowerCase
) {
p.caseFolding=NULL;
}
} else {
p.caseFolding=NULL;
}
/* check for non-character code points */
if((p.code&0xfffe)==0xfffe || (uint32_t)(p.code-0xfdd0)<0x20) {
fprintf(stderr, "gencase: error - properties for non-character code point U+%04lx\n",
(unsigned long)p.code);
*pErrorCode=U_PARSE_ERROR;
exit(U_PARSE_ERROR);
}
/* check that the code points (p.code) are in ascending order */
if(p.code<=prevCode && p.code>0) {
fprintf(stderr, "gencase: error - UnicodeData entries out of order, U+%04lx after U+%04lx\n",
(unsigned long)p.code, (unsigned long)prevCode);
*pErrorCode=U_PARSE_ERROR;
exit(U_PARSE_ERROR);
}
/* properties for a single code point */
setProps(&p);
prevCode=p.code;
}
static void
parseDB(const char *filename, UErrorCode *pErrorCode) {
char *fields[15][2];
UChar32 start, end;
int32_t i;
if(pErrorCode==NULL || U_FAILURE(*pErrorCode)) {
return;
}
u_parseDelimitedFile(filename, ';', fields, 15, unicodeDataLineFn, NULL, pErrorCode);
/* are all sub-properties consumed? */
if(specialCasingIndex<specialCasingCount) {
fprintf(stderr, "gencase: error - some code points in SpecialCasing.txt are missing from UnicodeData.txt\n");
*pErrorCode=U_PARSE_ERROR;
exit(U_PARSE_ERROR);
}
if(caseFoldingIndex<caseFoldingCount) {
fprintf(stderr, "gencase: error - some code points in CaseFolding.txt are missing from UnicodeData.txt\n");
*pErrorCode=U_PARSE_ERROR;
exit(U_PARSE_ERROR);
}
if(U_FAILURE(*pErrorCode)) {
return;
}
for(i=0;
0==uset_getItem(caseSensitive, i, &start, &end, NULL, 0, pErrorCode) && U_SUCCESS(*pErrorCode);
++i
) {
addCaseSensitive(start, end);
}
if(*pErrorCode==U_INDEX_OUTOFBOUNDS_ERROR) {
*pErrorCode=U_ZERO_ERROR;
}
}
/*
* Hey, Emacs, please set the following:
*
* Local Variables:
* indent-tabs-mode: nil
* End:
*
*/

132
tools/unicode/c/gencase/gencase.h
View File

@ -1,132 +0,0 @@
/*
*******************************************************************************
*
* Copyright (C) 2004-2009, International Business Machines
* Corporation and others. All Rights Reserved.
*
*******************************************************************************
* file name: gencase.h
* encoding: US-ASCII
* tab size: 8 (not used)
* indentation:4
*
* created on: 2004aug28
* created by: Markus W. Scherer
*/
#ifndef __GENCASE_H__
#define __GENCASE_H__
#include "unicode/utypes.h"
#include "utrie.h"
#include "propsvec.h"
#include "ucase.h"
U_CDECL_BEGIN
/* Unicode versions --------------------------------------------------------- */
enum {
UNI_1_0,
UNI_1_1,
UNI_2_0,
UNI_3_0,
UNI_3_1,
UNI_3_2,
UNI_4_0,
UNI_4_0_1,
UNI_4_1,
UNI_5_1,
UNI_5_2,
UNI_6_0,
UNI_VER_COUNT
};
extern int32_t ucdVersion;
/* gencase ------------------------------------------------------------------ */
#define UGENCASE_EXC_SHIFT 16
#define UGENCASE_EXC_MASK 0xffff0000
/*
* Values for the ucase.icu unfold[] data array, see store.c.
* The values are stored in ucase.icu so that the runtime code will work with
* changing values, but they are hardcoded for gencase for simplicity.
* They are optimized, that is, provide for minimal table column widths,
* for the actual Unicode data, so that the table size is minimized.
* Future versions of Unicode may require increases of some of these values.
*/
enum {
UGENCASE_UNFOLD_STRING_WIDTH=3,
UGENCASE_UNFOLD_CP_WIDTH=2,
UGENCASE_UNFOLD_WIDTH=UGENCASE_UNFOLD_STRING_WIDTH+UGENCASE_UNFOLD_CP_WIDTH,
UGENCASE_UNFOLD_MAX_ROWS=250
};
/* Values for additional data stored in pv column 1 */
enum {
UGENCASE_IS_MID_LETTER_SHIFT /* bit 0 WB=MidLetter or WB=MidNumLet */
};
/* special casing data */
typedef struct {
UChar32 code;
UBool isComplex;
UChar lowerCase[32], upperCase[32], titleCase[32];
} SpecialCasing;
/* case folding data */
typedef struct {
UChar32 code, simple;
char status;
UChar full[32];
} CaseFolding;
/* case mapping properties */
typedef struct {
UChar32 code, lowerCase, upperCase, titleCase;
UChar32 closure[8];
SpecialCasing *specialCasing;
CaseFolding *caseFolding;
uint8_t gc, cc;
UBool isCaseIgnorable;
} Props;
/* global flags */
extern UBool beVerbose, haveCopyright;
/* properties vectors in gencase.c */
extern UPropsVectors *pv;
/* prototypes */
U_CFUNC void
writeUCDFilename(char *basename, const char *filename, const char *suffix);
U_CFUNC UBool
isToken(const char *token, const char *s);
extern void
setUnicodeVersion(const char *v);
extern void
setProps(Props *p);
U_CFUNC uint32_t U_EXPORT2
getFoldedPropsValue(UNewTrie *trie, UChar32 start, int32_t offset);
extern void
addCaseSensitive(UChar32 first, UChar32 last);
extern void
makeCaseClosure(void);
extern void
makeExceptions(void);
extern void
generateData(const char *dataDir, UBool csource);
U_CDECL_END
#endif

422
tools/unicode/c/gencase/gencase.vcproj
View File

@ -1,422 +0,0 @@
<?xml version="1.0" encoding="Windows-1252"?>
<VisualStudioProject
ProjectType="Visual C++"
Version="9.00"
Name="gencase"
ProjectGUID="{DB312A49-12A9-4E07-9E96-451DC2D8FF61}"
TargetFrameworkVersion="131072"
>
<Platforms>
<Platform
Name="Win32"
/>
<Platform
Name="x64"
/>
</Platforms>
<ToolFiles>
</ToolFiles>
<Configurations>
<Configuration
Name="Release|Win32"
OutputDirectory=".\x86\Release"
IntermediateDirectory=".\x86\Release"
ConfigurationType="1"
InheritedPropertySheets="$(VCInstallDir)VCProjectDefaults\UpgradeFromVC71.vsprops"
UseOfMFC="0"
ATLMinimizesCRunTimeLibraryUsage="false"
CharacterSet="2"
>
<Tool
Name="VCPreBuildEventTool"
/>
<Tool
Name="VCCustomBuildTool"
CommandLine="copy &quot;$(TargetPath)&quot; ..\..\..\bin&#x0D;&#x0A;"
Outputs="..\..\..\bin\$(TargetFileName)"
/>
<Tool
Name="VCXMLDataGeneratorTool"
/>
<Tool
Name="VCWebServiceProxyGeneratorTool"
/>
<Tool
Name="VCMIDLTool"
TypeLibraryName=".\x86\Release/gencase.tlb"
/>
<Tool
Name="VCCLCompilerTool"
AdditionalIncludeDirectories="..\..\common;..\toolutil"
PreprocessorDefinitions="WIN32;NDEBUG;_CRT_SECURE_NO_DEPRECATE"
StringPooling="true"
RuntimeLibrary="2"
EnableFunctionLevelLinking="true"
DisableLanguageExtensions="true"
TreatWChar_tAsBuiltInType="true"
PrecompiledHeaderFile=".\x86\Release/gencase.pch"
AssemblerListingLocation=".\x86\Release/"
ObjectFile=".\x86\Release/"
ProgramDataBaseFileName=".\x86\Release/"
WarningLevel="3"
SuppressStartupBanner="true"
CompileAs="0"
/>
<Tool
Name="VCManagedResourceCompilerTool"
/>
<Tool
Name="VCResourceCompilerTool"
PreprocessorDefinitions="NDEBUG"
Culture="1033"
/>
<Tool
Name="VCPreLinkEventTool"
/>
<Tool
Name="VCLinkerTool"
OutputFile=".\x86\Release/gencase.exe"
LinkIncremental="1"
SuppressStartupBanner="true"
ProgramDatabaseFile=".\x86\Release/gencase.pdb"
SubSystem="1"
RandomizedBaseAddress="1"
DataExecutionPrevention="0"
/>
<Tool
Name="VCALinkTool"
/>
<Tool
Name="VCManifestTool"
/>
<Tool
Name="VCXDCMakeTool"
/>
<Tool
Name="VCBscMakeTool"
/>
<Tool
Name="VCFxCopTool"
/>
<Tool
Name="VCAppVerifierTool"
/>
<Tool
Name="VCPostBuildEventTool"
/>
</Configuration>
<Configuration
Name="Debug|Win32"
OutputDirectory=".\x86\Debug"
IntermediateDirectory=".\x86\Debug"
ConfigurationType="1"
InheritedPropertySheets="$(VCInstallDir)VCProjectDefaults\UpgradeFromVC71.vsprops"
UseOfMFC="0"
ATLMinimizesCRunTimeLibraryUsage="false"
CharacterSet="2"
>
<Tool
Name="VCPreBuildEventTool"
/>
<Tool
Name="VCCustomBuildTool"
CommandLine="copy &quot;$(TargetPath)&quot; ..\..\..\bin&#x0D;&#x0A;"
Outputs="..\..\..\bin\$(TargetFileName)"
/>
<Tool
Name="VCXMLDataGeneratorTool"
/>
<Tool
Name="VCWebServiceProxyGeneratorTool"
/>
<Tool
Name="VCMIDLTool"
TypeLibraryName=".\x86\Debug/gencase.tlb"
/>
<Tool
Name="VCCLCompilerTool"
Optimization="0"
AdditionalIncludeDirectories="..\..\common;..\toolutil"
PreprocessorDefinitions="WIN32;_DEBUG;_CRT_SECURE_NO_DEPRECATE"
BasicRuntimeChecks="3"
RuntimeLibrary="3"
BufferSecurityCheck="true"
DisableLanguageExtensions="true"
TreatWChar_tAsBuiltInType="true"
PrecompiledHeaderFile=".\x86\Debug/gencase.pch"
AssemblerListingLocation=".\x86\Debug/"
ObjectFile=".\x86\Debug/"
ProgramDataBaseFileName=".\x86\Debug/"
BrowseInformation="1"
WarningLevel="3"
SuppressStartupBanner="true"
DebugInformationFormat="4"
CompileAs="0"
/>
<Tool
Name="VCManagedResourceCompilerTool"
/>
<Tool
Name="VCResourceCompilerTool"
PreprocessorDefinitions="_DEBUG"
Culture="1033"
/>
<Tool
Name="VCPreLinkEventTool"
/>
<Tool
Name="VCLinkerTool"
OutputFile=".\x86\Debug/gencase.exe"
LinkIncremental="2"
SuppressStartupBanner="true"
GenerateDebugInformation="true"
ProgramDatabaseFile=".\x86\Debug/gencase.pdb"
SubSystem="1"
RandomizedBaseAddress="1"
DataExecutionPrevention="0"
/>
<Tool
Name="VCALinkTool"
/>
<Tool
Name="VCManifestTool"
UseFAT32Workaround="true"
/>
<Tool
Name="VCXDCMakeTool"
/>
<Tool
Name="VCBscMakeTool"
/>
<Tool
Name="VCFxCopTool"
/>
<Tool
Name="VCAppVerifierTool"
/>
<Tool
Name="VCPostBuildEventTool"
/>
</Configuration>
<Configuration
Name="Release|x64"
OutputDirectory=".\x64\Release"
IntermediateDirectory=".\x64\Release"
ConfigurationType="1"
InheritedPropertySheets="$(VCInstallDir)VCProjectDefaults\UpgradeFromVC71.vsprops"
UseOfMFC="0"
ATLMinimizesCRunTimeLibraryUsage="false"
CharacterSet="2"
>
<Tool
Name="VCPreBuildEventTool"
/>
<Tool
Name="VCCustomBuildTool"
CommandLine="copy &quot;$(TargetPath)&quot; ..\..\..\bin64&#x0D;&#x0A;"
Outputs="..\..\..\bin64\$(TargetFileName)"
/>
<Tool
Name="VCXMLDataGeneratorTool"
/>
<Tool
Name="VCWebServiceProxyGeneratorTool"
/>
<Tool
Name="VCMIDLTool"
TargetEnvironment="3"
TypeLibraryName=".\x64\Release/gencase.tlb"
/>
<Tool
Name="VCCLCompilerTool"
AdditionalIncludeDirectories="..\..\common;..\toolutil"
PreprocessorDefinitions="WIN64;WIN32;NDEBUG;_CRT_SECURE_NO_DEPRECATE"
StringPooling="true"
RuntimeLibrary="2"
EnableFunctionLevelLinking="true"
DisableLanguageExtensions="true"
TreatWChar_tAsBuiltInType="true"
PrecompiledHeaderFile=".\x64\Release/gencase.pch"
AssemblerListingLocation=".\x64\Release/"
ObjectFile=".\x64\Release/"
ProgramDataBaseFileName=".\x64\Release/"
WarningLevel="3"
SuppressStartupBanner="true"
CompileAs="0"
/>
<Tool
Name="VCManagedResourceCompilerTool"
/>
<Tool
Name="VCResourceCompilerTool"
PreprocessorDefinitions="NDEBUG"
Culture="1033"
/>
<Tool
Name="VCPreLinkEventTool"
/>
<Tool
Name="VCLinkerTool"
OutputFile=".\x64\Release/gencase.exe"
LinkIncremental="1"
SuppressStartupBanner="true"
ProgramDatabaseFile=".\x64\Release/gencase.pdb"
SubSystem="1"
TargetMachine="17"
/>
<Tool
Name="VCALinkTool"
/>
<Tool
Name="VCManifestTool"
/>
<Tool
Name="VCXDCMakeTool"
/>
<Tool
Name="VCBscMakeTool"
/>
<Tool
Name="VCFxCopTool"
/>
<Tool
Name="VCAppVerifierTool"
/>
<Tool
Name="VCWebDeploymentTool"
/>
<Tool
Name="VCPostBuildEventTool"
/>
</Configuration>
<Configuration
Name="Debug|x64"
OutputDirectory=".\x64\Debug"
IntermediateDirectory=".\x64\Debug"
ConfigurationType="1"
InheritedPropertySheets="$(VCInstallDir)VCProjectDefaults\UpgradeFromVC71.vsprops"
UseOfMFC="0"
ATLMinimizesCRunTimeLibraryUsage="false"
CharacterSet="2"
>
<Tool
Name="VCPreBuildEventTool"
/>
<Tool
Name="VCCustomBuildTool"
CommandLine="copy &quot;$(TargetPath)&quot; ..\..\..\bin64&#x0D;&#x0A;"
Outputs="..\..\..\bin64\$(TargetFileName)"
/>
<Tool
Name="VCXMLDataGeneratorTool"
/>
<Tool
Name="VCWebServiceProxyGeneratorTool"
/>
<Tool
Name="VCMIDLTool"
TargetEnvironment="3"
TypeLibraryName=".\x64\Debug/gencase.tlb"
/>
<Tool
Name="VCCLCompilerTool"
Optimization="0"
AdditionalIncludeDirectories="..\..\common;..\toolutil"
PreprocessorDefinitions="WIN64;WIN32;_DEBUG;_CRT_SECURE_NO_DEPRECATE"
BasicRuntimeChecks="3"
RuntimeLibrary="3"
BufferSecurityCheck="true"
DisableLanguageExtensions="true"
TreatWChar_tAsBuiltInType="true"
PrecompiledHeaderFile=".\x64\Debug/gencase.pch"
AssemblerListingLocation=".\x64\Debug/"
ObjectFile=".\x64\Debug/"
ProgramDataBaseFileName=".\x64\Debug/"
BrowseInformation="1"
WarningLevel="3"
SuppressStartupBanner="true"
DebugInformationFormat="3"
CompileAs="0"
/>
<Tool
Name="VCManagedResourceCompilerTool"
/>
<Tool
Name="VCResourceCompilerTool"
PreprocessorDefinitions="_DEBUG"
Culture="1033"
/>
<Tool
Name="VCPreLinkEventTool"
/>
<Tool
Name="VCLinkerTool"
OutputFile=".\x64\Debug/gencase.exe"
LinkIncremental="2"
SuppressStartupBanner="true"
GenerateDebugInformation="true"
ProgramDatabaseFile=".\x64\Debug/gencase.pdb"
SubSystem="1"
TargetMachine="17"
/>
<Tool
Name="VCALinkTool"
/>
<Tool
Name="VCManifestTool"
UseFAT32Workaround="true"
/>
<Tool
Name="VCXDCMakeTool"
/>
<Tool
Name="VCBscMakeTool"
/>
<Tool
Name="VCFxCopTool"
/>
<Tool
Name="VCAppVerifierTool"
/>
<Tool
Name="VCWebDeploymentTool"
/>
<Tool
Name="VCPostBuildEventTool"
/>
</Configuration>
</Configurations>
<References>
</References>
<Files>
<Filter
Name="Source Files"
Filter="c;cpp;rc"
>
<File
RelativePath=".\gencase.c"
>
</File>
<File
RelativePath=".\store.c"
>
</File>
</Filter>
<Filter
Name="Header Files"
Filter="h"
>
<File
RelativePath=".\gencase.h"
>
</File>
</Filter>
<Filter
Name="Resource Files"
Filter="ico;cur;bmp;dlg;rc2;rct;bin;rgs;gif;jpg;jpeg;jpe"
>
</Filter>
</Files>
<Globals>
</Globals>
</VisualStudioProject>

1201
tools/unicode/c/gencase/store.c
View File

File diff suppressed because it is too large Load Diff

2
tools/unicode/c/genprops/CMakeLists.txt
View File

@ -7,6 +7,6 @@
# edited by: Stuart G. Gill
add_executable(genprops genprops.cpp
pnamesbuilder.cpp corepropsbuilder.cpp
bidipropsbuilder.cpp
bidipropsbuilder.cpp casepropsbuilder.cpp
namespropsbuilder.cpp)
target_link_libraries(genprops icuuc icutu)

13
tools/unicode/c/genprops/bidipropsbuilder.cpp
View File

@ -421,7 +421,7 @@ BiDiPropsBuilder::build(UErrorCode &errorCode) {
4*mirrorTop+
(jgLimit-jgStart);
if(beVerbose) {
if(!beQuiet) {
puts("* ubidi.icu stats *");
printf("trie size in bytes: %5d\n", (int)trieSize);
printf("size in bytes of mirroring table: %5d\n", (int)(4*mirrorTop));
@ -439,8 +439,8 @@ void
BiDiPropsBuilder::writeCSourceFile(const char *path, UErrorCode &errorCode) {
if(U_FAILURE(errorCode)) { return; }
FILE *f=usrc_createFromGenerator(path, "ubidi_props_data.h",
"icu/tools/unicode/c/genprops/bidipropsbuilder.cpp");
FILE *f=usrc_create(path, "ubidi_props_data.h",
"icu/tools/unicode/c/genprops/bidipropsbuilder.cpp");
if(f==NULL) {
errorCode=U_FILE_ACCESS_ERROR;
return;
@ -503,13 +503,14 @@ BiDiPropsBuilder::writeBinaryData(const char *path, UBool withCopyright, UErrorC
long dataLength=udata_finish(pData, &errorCode);
if(U_FAILURE(errorCode)) {
fprintf(stderr, "genprops: error %d writing the output file\n", errorCode);
fprintf(stderr, "genprops error: bidipropsbuilder %d writing the output file\n", errorCode);
return;
}
if(dataLength!=indexes[UBIDI_IX_LENGTH]) {
fprintf(stderr, "genprops: data length %ld != calculated size %d\n",
dataLength, (int)indexes[UBIDI_IX_LENGTH]);
fprintf(stderr,
"udata_finish(ubidi.icu) reports %ld bytes written but should be %ld\n",
dataLength, (long)indexes[UBIDI_IX_LENGTH]);
errorCode=U_INTERNAL_PROGRAM_ERROR;
}
}

1217
tools/unicode/c/genprops/casepropsbuilder.cpp Normal file
View File

File diff suppressed because it is too large Load Diff

9
tools/unicode/c/genprops/corepropsbuilder.cpp
View File

@ -704,7 +704,7 @@ CorePropsBuilder::build(UErrorCode &errorCode) {
(((int32_t)U_GCB_COUNT-1)<<UPROPS_GCB_SHIFT)|
((int32_t)U_DT_COUNT-1);
if(beVerbose) {
if(!beQuiet) {
puts("* uprops.icu stats *");
printf("trie size in bytes: %5u\n", (int)trieSize);
printf("size in bytes of additional props trie:%5u\n", (int)props2TrieSize);
@ -723,8 +723,8 @@ CorePropsBuilder::writeCSourceFile(const char *path, UErrorCode &errorCode) {
const uint32_t *pvArray=upvec_getArray(pv, &pvRows, NULL);
int32_t pvCount=pvRows*UPROPS_VECTOR_WORDS;
FILE *f=usrc_createFromGenerator(path, "uchar_props_data.h",
"icu/tools/unicode/c/genprops/corepropsbuilder.cpp");
FILE *f=usrc_create(path, "uchar_props_data.h",
"icu/tools/unicode/c/genprops/corepropsbuilder.cpp");
if(f==NULL) {
errorCode=U_FILE_ACCESS_ERROR;
return;
@ -802,7 +802,8 @@ CorePropsBuilder::writeBinaryData(const char *path, UBool withCopyright, UErrorC
}
if(dataLength!=(long)totalSize) {
fprintf(stderr, "genprops: data length %ld != calculated size %ld\n",
fprintf(stderr,
"udata_finish(uprops.icu) reports %ld bytes written but should be %ld\n",
dataLength, (long)totalSize);
errorCode=U_INTERNAL_PROGRAM_ERROR;
}

6
tools/unicode/c/genprops/genprops.cpp
View File

@ -103,6 +103,7 @@ main(int argc, char* argv[]) {
LocalPointer<PNamesBuilder> pnamesBuilder(createPNamesBuilder(errorCode));
LocalPointer<PropsBuilder> corePropsBuilder(createCorePropsBuilder(errorCode));
LocalPointer<PropsBuilder> bidiPropsBuilder(createBiDiPropsBuilder(errorCode));
LocalPointer<PropsBuilder> casePropsBuilder(createCasePropsBuilder(errorCode));
LocalPointer<PropsBuilder> namesPropsBuilder(createNamesPropsBuilder(errorCode));
if(errorCode.isFailure()) {
fprintf(stderr, "genprops: unable to create PropsBuilders - %s\n", errorCode.errorName());
@ -144,11 +145,13 @@ main(int argc, char* argv[]) {
const UniProps *props=ppucd.getProps(newValues, errorCode);
corePropsBuilder->setProps(*props, newValues, errorCode);
bidiPropsBuilder->setProps(*props, newValues, errorCode);
casePropsBuilder->setProps(*props, newValues, errorCode);
namesPropsBuilder->setProps(*props, newValues, errorCode);
} else if(lineType==PreparsedUCD::UNICODE_VERSION_LINE) {
const UVersionInfo &version=ppucd.getUnicodeVersion();
corePropsBuilder->setUnicodeVersion(version);
bidiPropsBuilder->setUnicodeVersion(version);
casePropsBuilder->setUnicodeVersion(version);
namesPropsBuilder->setUnicodeVersion(version);
} else if(lineType==PreparsedUCD::ALG_NAMES_RANGE_LINE) {
UChar32 start, end;
@ -168,6 +171,7 @@ main(int argc, char* argv[]) {
corePropsBuilder->build(errorCode);
bidiPropsBuilder->build(errorCode);
casePropsBuilder->build(errorCode);
namesPropsBuilder->build(errorCode);
if(errorCode.isFailure()) {
fprintf(stderr, "genprops error: failure finalizing the data - %s\n",
@ -190,6 +194,8 @@ main(int argc, char* argv[]) {
corePropsBuilder->writeBinaryData(sourceDataIn.data(), withCopyright, errorCode);
bidiPropsBuilder->writeCSourceFile(sourceCommon.data(), errorCode);
bidiPropsBuilder->writeBinaryData(sourceDataIn.data(), withCopyright, errorCode);
casePropsBuilder->writeCSourceFile(sourceCommon.data(), errorCode);
casePropsBuilder->writeBinaryData(sourceDataIn.data(), withCopyright, errorCode);
namesPropsBuilder->writeBinaryData(sourceDataIn.data(), withCopyright, errorCode);
return errorCode;

1
tools/unicode/c/genprops/genprops.h
View File

@ -46,6 +46,7 @@ public:
PNamesBuilder *createPNamesBuilder(UErrorCode &errorCode);
PropsBuilder *createCorePropsBuilder(UErrorCode &errorCode);
PropsBuilder *createBiDiPropsBuilder(UErrorCode &errorCode);
PropsBuilder *createCasePropsBuilder(UErrorCode &errorCode);
PropsBuilder *createNamesPropsBuilder(UErrorCode &errorCode);
/* global flags */

10
tools/unicode/c/genprops/namespropsbuilder.cpp
View File

@ -144,6 +144,8 @@
/* generator data ----------------------------------------------------------- */
U_NAMESPACE_USE
/* UDataInfo cf. udata.h */
static UDataInfo dataInfo={
sizeof(UDataInfo),
@ -516,13 +518,11 @@ compress(UErrorCode &errorCode) {
for(i=0, wordNumber=0; wordNumber<(int16_t)wordCount; ++i) {
if(tokens[i]!=-1) {
tokens[i]=wordNumber;
#ifdef DEBUG_NAMES
if(beVerbose) {
printf("tokens[0x%03x]: word%8ld \"%.*s\"\n",
(int)i, (long)words[wordNumber].weight,
words[wordNumber].length, words[wordNumber].s);
}
#endif
++wordNumber;
}
}
@ -572,13 +572,11 @@ compress(UErrorCode &errorCode) {
/* set token 0 to word 0 */
tokens[0]=0;
#ifdef DEBUG_NAMES
if(beVerbose) {
printf("tokens[0x000]: word%8ld \"%.*s\"\n",
(long)words[0].weight,
words[0].length, words[0].s);
}
#endif
wordNumber=1;
/* set the lead byte tokens */
@ -591,13 +589,11 @@ compress(UErrorCode &errorCode) {
/* if store10Names then the parser set tokens[NAME_SEPARATOR_CHAR]=-1 */
if(tokens[i]!=-1) {
tokens[i]=wordNumber;
#ifdef DEBUG_NAMES
if(beVerbose) {
printf("tokens[0x%03x]: word%8ld \"%.*s\"\n",
(int)i, (long)words[wordNumber].weight,
words[wordNumber].length, words[wordNumber].s);
}
#endif
++wordNumber;
}
}
@ -608,13 +604,11 @@ compress(UErrorCode &errorCode) {
tokens[i]=-1; /* do not use NAME_SEPARATOR_CHAR as a second token byte */
} else {
tokens[i]=wordNumber;
#ifdef DEBUG_NAMES
if(beVerbose) {
printf("tokens[0x%03x]: word%8ld \"%.*s\"\n",
(int)i, (long)words[wordNumber].weight,
words[wordNumber].length, words[wordNumber].s);
}
#endif
++wordNumber;
}
}

8
tools/unicode/c/genprops/pnamesbuilder.cpp
View File

@ -279,7 +279,7 @@ public:
indexes[i]=0;
}
if(beVerbose) {
if(!beQuiet) {
puts("* pnames.icu stats *");
printf("length of all value maps: %6ld\n", (long)valueMaps.size());
printf("length of all BytesTries: %6ld\n", (long)bytesTries.length());
@ -487,11 +487,11 @@ PNamesBuilderImpl::writeBinaryData(const char *path, UBool withCopyright, UError
void
PNamesBuilderImpl::writeCSourceFile(const char *path, UErrorCode &errorCode) {
if(U_FAILURE(errorCode)) { return; }
FILE *f=usrc_createFromGenerator(path, "propname_data.h",
"icu/tools/unicode/c/genprops/pnamesbuilder.cpp");
FILE *f=usrc_create(path, "propname_data.h",
"icu/tools/unicode/c/genprops/pnamesbuilder.cpp");
if(f==NULL) {
errorCode=U_FILE_ACCESS_ERROR;
return; // usrc_create() reported an error.
return;
}
fputs("#ifndef INCLUDED_FROM_PROPNAME_CPP\n"