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

ICU-820 test Unicode::getCombiningClass() with UnicodeData.txt using toolutil/uparse

Browse Source 
X-SVN-Rev: 3467
This commit is contained in:
Markus Scherer 2001-01-23 23:52:49 +00:00
parent 2b041cf380
commit 5f5c348447
4 changed files with 153 additions and 90 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
icu4c/source/test/intltest/Makefile.in
View File

@ -23,7 +23,7 @@ CLEANFILES = *~ $(DEPS)
TARGET = intltest
DEFS = @DEFS@
CPPFLAGS = @CPPFLAGS@ -I$(top_builddir)/common -I$(top_srcdir)/common -I$(top_srcdir)/i18n -DU_SRCDATADIR=\"$(top_srcdir)/../data/\"
CPPFLAGS = @CPPFLAGS@ -I$(top_builddir)/common -I$(top_srcdir)/common -I$(top_srcdir)/i18n -I$(top_srcdir)/tools/toolutil -DU_SRCDATADIR=\"$(top_srcdir)/../data/\"
CFLAGS = @CFLAGS@
CXXFLAGS = @CXXFLAGS@
LDFLAGS = @LDFLAGS@ \
@ -32,8 +32,8 @@ ifeq ($(ENABLE_RPATH),YES)
RPATHLDFLAGS = $(LD_RPATH)$(LD_RPATH_PRE)$(libdir)
endif
LDFLAGS = @LDFLAGS@ $(RPATHLDFLAGS)
INVOKE = $(LDLIBRARYPATH_ENVVAR)=$(top_builddir)/common:$(top_builddir)/i18n:$$$(LDLIBRARYPATH_ENVVAR)
LIBS = $(LIBICUI18N) $(LIBICUUC) @LIBS@ @LIB_M@
INVOKE = $(LDLIBRARYPATH_ENVVAR)=$(top_builddir)/common:$(top_builddir)/i18n:$(top_builddir)/tools/toolutil:$$$(LDLIBRARYPATH_ENVVAR)
LIBS = $(LIBICUI18N) $(LIBICUUC) $(LIBICUTOOLUTIL) @LIBS@ @LIB_M@
OBJECTS = allcoll.o apicoll.o callimts.o calregts.o caltest.o \
caltztst.o citrtest.o cppcnvt.o cputilst.o currcoll.o dacoll.o \

8
icu4c/source/test/intltest/intltest.dsp
View File

@ -42,7 +42,7 @@ RSC=rc.exe
# PROP Ignore_Export_Lib 0
# PROP Target_Dir ""
# ADD BASE CPP /nologo /W3 /GX /O2 /D "WIN32" /D "NDEBUG" /D "_CONSOLE" /D "_MBCS" /YX /FD /c
# ADD CPP /nologo /MD /W3 /GX /Z7 /I "..\..\..\include" /I "..\..\..\source\common" /D "WIN32" /D "NDEBUG" /D "_CONSOLE" /D "_MBCS" /YX /FD /c
# ADD CPP /nologo /MD /W3 /GX /Z7 /I "..\..\..\include" /I "..\..\..\source\common" /I "..\..\tools\toolutil" /D "WIN32" /D "NDEBUG" /D "_CONSOLE" /D "_MBCS" /YX /FD /c
# ADD BASE RSC /l 0x409 /d "NDEBUG"
# ADD RSC /l 0x409 /d "NDEBUG"
BSC32=bscmake.exe
@ -50,7 +50,7 @@ BSC32=bscmake.exe
# ADD BSC32 /nologo
LINK32=link.exe
# ADD BASE LINK32 kernel32.lib user32.lib gdi32.lib winspool.lib comdlg32.lib advapi32.lib shell32.lib ole32.lib oleaut32.lib uuid.lib odbc32.lib odbccp32.lib kernel32.lib user32.lib gdi32.lib winspool.lib comdlg32.lib advapi32.lib shell32.lib ole32.lib oleaut32.lib uuid.lib odbc32.lib odbccp32.lib /nologo /subsystem:console /machine:I386
# ADD LINK32 icuuc.lib icuin.lib /nologo /subsystem:console /debug /machine:I386 /pdbtype:sept /libpath:"..\..\..\lib"
# ADD LINK32 icuuc.lib icuin.lib icutu.lib /nologo /subsystem:console /debug /machine:I386 /pdbtype:sept /libpath:"..\..\..\lib"
# SUBTRACT LINK32 /pdb:none
!ELSEIF "$(CFG)" == "intltest - Win32 Debug"
@ -67,7 +67,7 @@ LINK32=link.exe
# PROP Ignore_Export_Lib 0
# PROP Target_Dir ""
# ADD BASE CPP /nologo /W3 /Gm /GX /ZI /Od /D "WIN32" /D "_DEBUG" /D "_CONSOLE" /D "_MBCS" /YX /FD /GZ /c
# ADD CPP /nologo /MDd /W3 /Gm /GX /ZI /Od /I "..\..\..\include" /I "..\..\..\source\common" /D "WIN32" /D "_DEBUG" /D "_CONSOLE" /D "_MBCS" /D "UDATA_MAP_DLL" /YX /FD /GZ /c
# ADD CPP /nologo /MDd /W3 /Gm /GX /ZI /Od /I "..\..\..\include" /I "..\..\..\source\common" /I "..\..\tools\toolutil" /D "WIN32" /D "_DEBUG" /D "_CONSOLE" /D "_MBCS" /D "UDATA_MAP_DLL" /YX /FD /GZ /c
# ADD BASE RSC /l 0x409 /d "_DEBUG"
# ADD RSC /l 0x409 /d "_DEBUG"
BSC32=bscmake.exe
@ -75,7 +75,7 @@ BSC32=bscmake.exe
# ADD BSC32 /nologo
LINK32=link.exe
# ADD BASE LINK32 kernel32.lib user32.lib gdi32.lib winspool.lib comdlg32.lib advapi32.lib shell32.lib ole32.lib oleaut32.lib uuid.lib odbc32.lib odbccp32.lib kernel32.lib user32.lib gdi32.lib winspool.lib comdlg32.lib advapi32.lib shell32.lib ole32.lib oleaut32.lib uuid.lib odbc32.lib odbccp32.lib /nologo /subsystem:console /debug /machine:I386 /pdbtype:sept
# ADD LINK32 icuucd.lib icuind.lib /nologo /subsystem:console /debug /machine:I386 /pdbtype:sept /libpath:"..\..\..\lib\\"
# ADD LINK32 icuucd.lib icuind.lib icutud.lib /nologo /subsystem:console /debug /machine:I386 /pdbtype:sept /libpath:"..\..\..\lib\\"
!ENDIF

224
icu4c/source/test/intltest/ucdtest.cpp
View File

@ -4,13 +4,15 @@
* others. All Rights Reserved.
********************************************************************/
#include <stdio.h>
#include <string.h>
#include <assert.h>
#include "ucdtest.h"
#include "unicode/unicode.h"
#include "unicode/ustring.h"
#include "unicode/uchar.h"
#include <stdio.h>
#include <string.h>
#include <assert.h>
#include "cstring.h"
#include "uparse.h"
UnicodeTest::UnicodeTest()
{
@ -307,19 +309,139 @@ void UnicodeTest::TestIdentifier()
}
}
/* tests for getType(), isTitleCase(), and toTitleCase() as well as characterDirection()*/
/* for each line of UnicodeData.txt, check some of the properties */
void
UnicodeTest::unicodeDataLineFn(void *context,
char *fields[][2], int32_t fieldCount,
UErrorCode *pErrorCode) {
char *end;
uint32_t value;
UChar32 c;
int8_t type;
UnicodeTest *me=(UnicodeTest *)context;
/* get the character code, field 0 */
c=uprv_strtoul(fields[0][0], &end, 16);
if(end<=fields[0][0] || end!=fields[0][1]) {
me->errln("error: syntax error in field 0 at %s\n" + UnicodeString(fields[0][0], ""));
return;
}
if((uint32_t)c>=0x110000) {
me->errln("error in UnicodeData.txt: code point %lu out of range\n" + c);
return;
}
/* get general category, field 2 */
/* we override the general category of some control characters */
switch(c) {
case 9:
case 0xb:
case 0x1f:
type = U_SPACE_SEPARATOR;
break;
case 0xc:
type = U_LINE_SEPARATOR;
break;
case 0xa:
case 0xd:
case 0x1c:
case 0x1d:
case 0x1e:
case 0x85:
type = U_PARAGRAPH_SEPARATOR;
break;
default:
*fields[2][1]=0;
type = (int8_t)tagValues[me->MakeProp(fields[2][0])];
break;
}
if(Unicode::getType(c)!=type) {
me->errln("error: Unicode::getType(U+%04lx)==%u instead of %u\n", c, Unicode::getType(c), type);
}
/* get canonical combining class, field 3 */
value=uprv_strtoul(fields[3][0], &end, 10);
if(end<=fields[3][0] || end!=fields[3][1]) {
me->errln("error: syntax error in field 3 at code 0x%lx\n", c);
return;
}
if(value>255) {
me->errln("error in UnicodeData.txt: combining class %lu out of range\n", value);
return;
}
if(value!=Unicode::getCombiningClass(c)) {
me->errln("error: Unicode::getCombiningClass(U+%04lx)==%hu instead of %lu\n", c, Unicode::getCombiningClass(c), value);
}
/* get BiDi category, field 4 */
*fields[4][1]=0;
if(Unicode::characterDirection(c)!=me->MakeDir(fields[4][0])) {
me->errln("error: Unicode::characterDirection(U+%04lx)==%u instead of %u (%s)\n", c, Unicode::characterDirection(c), me->MakeDir(fields[4][0]), fields[4][0]);
}
/* get uppercase mapping, field 12 */
if(fields[12][0]!=fields[12][1]) {
value=uprv_strtoul(fields[12][0], &end, 16);
if(end!=fields[12][1]) {
me->errln("error: syntax error in field 12 at code 0x%lx\n", c);
return;
}
if((UChar32)value!=Unicode::toUpperCase(c)) {
me->errln("error: Unicode::toUpperCase(U+%04lx)==U+%04lx instead of U+%04lx\n", c, Unicode::toUpperCase(c), value);
}
} else {
/* no case mapping: the API must map the code point to itself */
if(c!=Unicode::toUpperCase(c)) {
me->errln("error: U+%04lx does not have an uppercase mapping but Unicode::toUpperCase()==U+%04lx\n", c, Unicode::toUpperCase(c));
}
}
/* get lowercase mapping, field 13 */
if(fields[13][0]!=fields[13][1]) {
value=uprv_strtoul(fields[13][0], &end, 16);
if(end!=fields[13][1]) {
me->errln("error: syntax error in field 13 at code 0x%lx\n", c);
return;
}
if((UChar32)value!=Unicode::toLowerCase(c)) {
me->errln("error: Unicode::toLowerCase(U+%04lx)==U+%04lx instead of U+%04lx\n", c, Unicode::toLowerCase(c), value);
}
} else {
/* no case mapping: the API must map the code point to itself */
if(c!=Unicode::toLowerCase(c)) {
me->errln("error: U+%04lx does not have a lowercase mapping but Unicode::toLowerCase()==U+%04lx\n", c, Unicode::toLowerCase(c));
}
}
/* get titlecase mapping, field 14 */
if(fields[14][0]!=fields[14][1]) {
value=uprv_strtoul(fields[14][0], &end, 16);
if(end!=fields[14][1]) {
me->errln("error: syntax error in field 14 at code 0x%lx\n", c);
return;
}
if((UChar32)value!=Unicode::toTitleCase(c)) {
me->errln("error: Unicode::toTitleCase(U+%04lx)==U+%04lx instead of U+%04lx\n", c, Unicode::toTitleCase(c), value);
}
} else {
/* no case mapping: the API must map the code point to itself */
if(c!=Unicode::toTitleCase(c)) {
me->errln("error: U+%04lx does not have a titlecase mapping but Unicode::toTitleCase()==U+%04lx\n", c, Unicode::toTitleCase(c));
}
}
}
/* tests for several properties */
void UnicodeTest::TestUnicodeData()
{
FILE* input;
char buffer[1000];
char* bufferPtr, *dirPtr;
char newPath[256];
char backupPath[256];
char *fields[15][2];
UErrorCode errorCode;
/* Look inside ICU_DATA first */
strcpy(newPath, u_getDataDirectory());
strcat(newPath, "unidata" U_FILE_SEP_STRING "UnicodeData");
strcat(newPath, ".txt");
strcat(newPath, "unidata" U_FILE_SEP_STRING "UnicodeData.txt");
#if defined (U_SRCDATADIR) /* points to the icu/data directory */
/* If defined, we'll try an alternate directory second */
@ -329,85 +451,21 @@ void UnicodeTest::TestUnicodeData()
strcat(backupPath, ".." U_FILE_SEP_STRING ".." U_FILE_SEP_STRING "data");
strcat(backupPath, U_FILE_SEP_STRING);
#endif
strcat(backupPath, "unidata" U_FILE_SEP_STRING "UnicodeData");
strcat(backupPath, ".txt");
strcat(backupPath, "unidata" U_FILE_SEP_STRING "UnicodeData.txt");
input = fopen(newPath, "r");
if (input == 0) {
input = fopen(backupPath, "r");
if (input == 0) {
errln("Failed to open either " + UnicodeString(newPath) + " or " + UnicodeString(backupPath) );
return;
}
errorCode=U_ZERO_ERROR;
u_parseDelimitedFile(backupPath, ';', fields, 15, unicodeDataLineFn, this, &errorCode);
if(errorCode==U_FILE_ACCESS_ERROR) {
errorCode=U_ZERO_ERROR;
u_parseDelimitedFile(newPath, ';', fields, 15, unicodeDataLineFn, this, &errorCode);
}
int32_t unicode;
int8_t type;
for(;;) {
bufferPtr = fgets(buffer, 999, input);
if (bufferPtr == NULL)
break;
if (bufferPtr[0] == '#' || bufferPtr[0] == '\n' || bufferPtr[0] == 0)
continue;
sscanf(bufferPtr, "%X", &unicode);
assert(0 <= unicode && unicode < 65536);
if (unicode == LAST_CHAR_CODE_IN_FILE)
break;
bufferPtr = strchr(bufferPtr, ';');
assert(bufferPtr != NULL);
bufferPtr = strchr(bufferPtr + 1, ';'); // go to start of third field
assert(bufferPtr != NULL);
dirPtr = bufferPtr;
dirPtr = strchr(dirPtr + 1, ';');
assert(dirPtr != NULL);
dirPtr = strchr(dirPtr + 1, ';');
assert(dirPtr != NULL);
bufferPtr++;
bufferPtr[2] = 0;
// logln((UnicodeString)"testing " + (int32_t)unicode + "...");
/* we override the general category of some control characters */
switch(unicode) {
case 9:
case 0xb:
case 0x1f:
type = U_SPACE_SEPARATOR;
break;
case 0xc:
type = U_LINE_SEPARATOR;
break;
case 0xa:
case 0xd:
case 0x1c:
case 0x1d:
case 0x1e:
case 0x85:
type = U_PARAGRAPH_SEPARATOR;
break;
default:
type = (int8_t)tagValues[MakeProp(bufferPtr)];
break;
}
if (Unicode::getType((UChar)unicode) != type)
errln("Unicode character type failed at " + unicode);
// test title case
if ((Unicode::toTitleCase((UChar)unicode) != Unicode::toUpperCase((UChar)unicode)) &&
!(Unicode::isTitleCase(Unicode::toTitleCase((UChar)unicode))))
errln("Title case test failed at " + unicode);
bufferPtr = strchr(dirPtr + 1, ';');
dirPtr++;
bufferPtr[0] = 0;
if (Unicode::characterDirection((UChar)unicode) != MakeDir(dirPtr))
errln("Unicode character directionality failed at\n " + unicode);
if(U_FAILURE(errorCode)) {
errln("error parsing UnicodeData.txt: %s\n" + UnicodeString(u_errorName(errorCode), ""));
}
if (input)
fclose(input);
// test Unicode::getCharName()
// a more thorough test of u_charName() is in cintltst/cucdtst.c
char buffer[100];
UTextOffset length=Unicode::getCharName(0x284, buffer, sizeof(buffer));
// use invariant-character conversion to Unicode

5
icu4c/source/test/intltest/ucdtest.h
View File

@ -37,6 +37,11 @@ public:
* Tests methods isDefined(), isBaseForm(), isSpaceChar() and getCellWidth()
**/
void TestMisc(void);
/** Helper function for TestUnicodeData */
static void unicodeDataLineFn(void *context,
char *fields[][2], int32_t fieldCount,
UErrorCode *pErrorCode);
/**
* tests methods getType(), isTitleCase(), and toTitleCase()
* as well as characterDirection()