organicmaps/icu
13
Fork 0
mirror of https://github.com/unicode-org/icu.git synced 2025-04-07 22:44:49 +00:00
Code Issues 1 Projects Releases Wiki Activity Actions 2

ICU-1923 upgrade to Unicode 3.2: add new scripts; fix script name comparisons to perform loose matches according to Property[Value]Aliases.txt (use uprv_comparePropertyNames); make hardcoded arrays more maintainable

Browse source 
X-SVN-Rev: 8765
This commit is contained in:
Markus Scherer 2002-06-01 00:43:07 +00:00
parent 067b86e8a3
commit 869dfa4583
1 changed files with 133 additions and 229 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

362
icu4c/source/common/uscript.c
View file

@ -15,6 +15,7 @@
#include "unicode/uscript.h"
#include "unicode/ures.h"
#include "uprops.h"
#include "cmemory.h"
#include "cstring.h"
@ -43,202 +44,124 @@ static int8_t highBit(int32_t value);
static const char kLocaleScript[] = "LocaleScript";
static const char * const scriptNames[]={
"ARABIC", /* USCRIPT_ARABIC */
"ARMENIAN", /* USCRIPT_ARMENIAN */
"BENGALI", /* USCRIPT_BENGALI */
"BOPOMOFO", /* USCRIPT_BOPOMOFO */
"CANADIAN-ABORIGINAL", /* USCRIPT_UCAS */
"CHEROKEE", /* USCRIPT_CHEROKEE */
"COMMON", /* USCRIPT_COMMON */
"CYRILLIC", /* USCRIPT_CYRILLIC */
"DESERET", /* USCRIPT_DESERET */
"DEVANAGARI", /* USCRIPT_DEVANAGARI */
"ETHIOPIC", /* USCRIPT_ETHIOPIC */
"GEORGIAN", /* USCRIPT_GEORGIAN */
"GOTHIC", /* USCRIPT_GOTHIC */
"GREEK", /* USCRIPT_GREEK */
"GUJARATI", /* USCRIPT_GUJARATI */
"GURMUKHI", /* USCRIPT_GURMUKHI */
"HAN", /* USCRIPT_HAN */
"HANGUL", /* USCRIPT_HANGUL */
"HEBREW", /* USCRIPT_HEBREW */
"HIRAGANA", /* USCRIPT_HIRAGANA */
"INHERITED", /* USCRIPT_INHERITED */
"KANNADA", /* USCRIPT_KANNADA */
"KATAKANA", /* USCRIPT_KATAKANA */
"KHMER", /* USCRIPT_KHMER */
"LATIN", /* USCRIPT_LATIN */
"MALAYALAM", /* USCRIPT_MALAYALAM */
"MONGOLIAN", /* USCRIPT_MONGOLIAN */
"MYANMAR", /* USCRIPT_MYANMAR */
"OGHAM", /* USCRIPT_OGHAM */
"OLD-ITALIC", /* USCRIPT_OLD_ITALIC */
"ORIYA", /* USCRIPT_ORIYA */
"RUNIC", /* USCRIPT_RUNIC */
"SINHALA", /* USCRIPT_SINHALA */
"SYRIAC", /* USCRIPT_SYRIAC */
"TAMIL", /* USCRIPT_TAMIL */
"TELUGU", /* USCRIPT_TELUGU */
"THAANA", /* USCRIPT_THANA */
"THAI", /* USCRIPT_THAI */
"TIBETAN", /* USCRIPT_TIBETAN */
"UCAS", /* USCRIPT_UCAS */
"YI" /* USCRIPT_YI */
/*
* Use pairs of (name, code) instead of separate arrays to simplify maintenance
* of these arrays.
*/
struct NameCodePair {
const char *name;
int32_t code;
};
typedef struct NameCodePair NameCodePair;
/* script names with codes, sorted by names */
static const NameCodePair
scriptNames[]={
{ "ARABIC", USCRIPT_ARABIC },
{ "ARMENIAN", USCRIPT_ARMENIAN },
{ "BENGALI", USCRIPT_BENGALI },
{ "BOPOMOFO", USCRIPT_BOPOMOFO },
{ "BUHID", USCRIPT_BUHID },
{ "CANADIAN_ABORIGINAL", USCRIPT_UCAS },
{ "CHEROKEE", USCRIPT_CHEROKEE },
{ "COMMON", USCRIPT_COMMON },
{ "CYRILLIC", USCRIPT_CYRILLIC },
{ "DESERET", USCRIPT_DESERET },
{ "DEVANAGARI", USCRIPT_DEVANAGARI },
{ "ETHIOPIC", USCRIPT_ETHIOPIC },
{ "GEORGIAN", USCRIPT_GEORGIAN },
{ "GOTHIC", USCRIPT_GOTHIC },
{ "GREEK", USCRIPT_GREEK },
{ "GUJARATI", USCRIPT_GUJARATI },
{ "GURMUKHI", USCRIPT_GURMUKHI },
{ "HAN", USCRIPT_HAN },
{ "HANGUL", USCRIPT_HANGUL },
{ "HANUNOO", USCRIPT_HANUNOO },
{ "HEBREW", USCRIPT_HEBREW },
{ "HIRAGANA", USCRIPT_HIRAGANA },
{ "INHERITED", USCRIPT_INHERITED },
{ "KANNADA", USCRIPT_KANNADA },
{ "KATAKANA", USCRIPT_KATAKANA },
{ "KHMER", USCRIPT_KHMER },
{ "LATIN", USCRIPT_LATIN },
{ "MALAYALAM", USCRIPT_MALAYALAM },
{ "MONGOLIAN", USCRIPT_MONGOLIAN },
{ "MYANMAR", USCRIPT_MYANMAR },
{ "OGHAM", USCRIPT_OGHAM },
{ "OLD_ITALIC", USCRIPT_OLD_ITALIC },
{ "ORIYA", USCRIPT_ORIYA },
{ "RUNIC", USCRIPT_RUNIC },
{ "SINHALA", USCRIPT_SINHALA },
{ "SYRIAC", USCRIPT_SYRIAC },
{ "TAGALOG", USCRIPT_TAGALOG },
{ "TAGBANWA", USCRIPT_TAGBANWA },
{ "TAMIL", USCRIPT_TAMIL },
{ "TELUGU", USCRIPT_TELUGU },
{ "THAANA", USCRIPT_THAANA },
{ "THAI", USCRIPT_THAI },
{ "TIBETAN", USCRIPT_TIBETAN },
{ "UCAS", USCRIPT_UCAS },
{ "YI", USCRIPT_YI }
};
static const char * const scriptAbbr[]= {
"Arab", /* USCRIPT_ARABIC */
"Armn", /* USCRIPT_ARMENIAN */
"Beng", /* USCRIPT_BENGALI */
"Bopo", /* USCRIPT_BOPOMOFO */
"Cans", /* USCRIPT_UCAS */
"Cher", /* USCRIPT_CHEROKEE */
"Cyrl", /* USCRIPT_CYRILLIC */
/* "Cyrs", */ /* USCRIPT_CYRILLIC */
"Deva", /* USCRIPT_DEVANAGARI */
"Dsrt", /* USCRIPT_DESERET */
"Ethi", /* USCRIPT_ETHIOPIC */
/* "Geoa", */ /* USCRIPT_GEORGIAN */
/* "Geon", */ /* USCRIPT_GEORGIAN */
"Geor", /* USCRIPT_GEORGIAN */
"Goth", /* USCRIPT_GOTHIC */
"Grek", /* USCRIPT_GREEK */
"Gujr", /* USCRIPT_GUJARATI */
"Guru", /* USCRIPT_GURMUKHI */
"Hang", /* USCRIPT_HANGUL */
"Hani", /* USCRIPT_HAN */
"Hebr", /* USCRIPT_HEBREW */
"Hira", /* USCRIPT_HIRAGANA */
"Ital", /* USCRIPT_OLD_ITALIC */
"Kana", /* USCRIPT_KATAKANA */
"Khmr", /* USCRIPT_KHMER */
"Knda", /* USCRIPT_KANNADA */
"Lao", /* USCRIPT_LAO */
/*"Laoo", */ /* USCRIPT_LAO */
/*"Latf", */ /* USCRIPT_LATIN */
/*"Latg", */ /* USCRIPT_LATIN */
"Latn", /* USCRIPT_LATIN */
"Mlym", /* USCRIPT_MALAYALAM */
"Mong", /* USCRIPT_MONGOLIAN */
"Mymr", /* USCRIPT_MYANMAR */
"Ogam", /* USCRIPT_OGHAM */
"Orya", /* USCRIPT_ORIYA */
"Qaac", /* USCRIPT_COPTIC */
"Qaai", /* USCRIPT_INHERITED */
"Runr", /* USCRIPT_RUNIC */
"Sinh", /* USCRIPT_SINHALA */
"Syrc", /* USCRIPT_SYRIAC */
/* "Syre", */ /* USCRIPT_SYRIAC */
/* "Syrj", */ /* USCRIPT_SYRIAC */
/* "Syrn", */ /* USCRIPT_SYRIAC */
"Taml", /* USCRIPT_TAMIL */
"Telu", /* USCRIPT_TELUGU */
"Thaa", /* USCRIPT_THANA */
"Thai", /* USCRIPT_THAI */
"Tibt", /* USCRIPT_TIBETAN */
"Yiii", /* USCRIPT_YI */
"Zyyy" /* USCRIPT_COMMON */
};
static const UScriptCode scriptNameCodes[]= {
USCRIPT_ARABIC ,
USCRIPT_ARMENIAN ,
USCRIPT_BENGALI ,
USCRIPT_BOPOMOFO ,
USCRIPT_UCAS ,
USCRIPT_CHEROKEE ,
USCRIPT_COMMON ,
USCRIPT_CYRILLIC ,
USCRIPT_DESERET ,
USCRIPT_DEVANAGARI ,
USCRIPT_ETHIOPIC ,
USCRIPT_GEORGIAN ,
USCRIPT_GOTHIC ,
USCRIPT_GREEK ,
USCRIPT_GUJARATI ,
USCRIPT_GURMUKHI ,
USCRIPT_HAN ,
USCRIPT_HANGUL ,
USCRIPT_HEBREW ,
USCRIPT_HIRAGANA ,
USCRIPT_INHERITED ,
USCRIPT_KANNADA ,
USCRIPT_KATAKANA ,
USCRIPT_KHMER ,
USCRIPT_LATIN ,
USCRIPT_MALAYALAM ,
USCRIPT_MONGOLIAN ,
USCRIPT_MYANMAR ,
USCRIPT_OGHAM ,
USCRIPT_OLD_ITALIC ,
USCRIPT_ORIYA ,
USCRIPT_RUNIC ,
USCRIPT_SINHALA ,
USCRIPT_SYRIAC ,
USCRIPT_TAMIL ,
USCRIPT_TELUGU ,
USCRIPT_THAANA ,
USCRIPT_THAI ,
USCRIPT_TIBETAN ,
USCRIPT_UCAS ,
USCRIPT_YI
};
static const UScriptCode scriptAbbrCodes[] = {
USCRIPT_ARABIC ,
USCRIPT_ARMENIAN ,
USCRIPT_BENGALI ,
USCRIPT_BOPOMOFO ,
USCRIPT_UCAS ,
USCRIPT_CHEROKEE ,
USCRIPT_CYRILLIC ,
/* USCRIPT_CYRILLIC , */
USCRIPT_DEVANAGARI ,
USCRIPT_DESERET ,
USCRIPT_ETHIOPIC ,
/* USCRIPT_GEORGIAN , */
/* USCRIPT_GEORGIAN , */
USCRIPT_GEORGIAN ,
USCRIPT_GOTHIC ,
USCRIPT_GREEK ,
USCRIPT_GUJARATI ,
USCRIPT_GURMUKHI ,
USCRIPT_HANGUL ,
USCRIPT_HAN ,
USCRIPT_HEBREW ,
USCRIPT_HIRAGANA ,
USCRIPT_OLD_ITALIC ,
USCRIPT_KATAKANA ,
USCRIPT_KHMER ,
USCRIPT_KANNADA ,
USCRIPT_LAO ,
/* USCRIPT_LAO , */
/* USCRIPT_LATIN , */
/* USCRIPT_LATIN , */
USCRIPT_LATIN ,
USCRIPT_MALAYALAM ,
USCRIPT_MONGOLIAN ,
USCRIPT_MYANMAR ,
USCRIPT_OGHAM ,
USCRIPT_ORIYA ,
USCRIPT_COPTIC ,
USCRIPT_INHERITED ,
USCRIPT_RUNIC ,
USCRIPT_SINHALA ,
USCRIPT_SYRIAC ,
/* USCRIPT_SYRIAC , */
/* USCRIPT_SYRIAC , */
/* USCRIPT_SYRIAC , */
USCRIPT_TAMIL ,
USCRIPT_TELUGU ,
USCRIPT_THAANA ,
USCRIPT_THAI ,
USCRIPT_TIBETAN ,
USCRIPT_YI ,
USCRIPT_COMMON
/* script abbreviations with codes, sorted by abbreviations */
static const NameCodePair
scriptAbbr[]= {
{ "Arab", USCRIPT_ARABIC },
{ "Armn", USCRIPT_ARMENIAN },
{ "Beng", USCRIPT_BENGALI },
{ "Bopo", USCRIPT_BOPOMOFO },
{ "Buhd", USCRIPT_BUHID },
{ "Cans", USCRIPT_UCAS },
{ "Cher", USCRIPT_CHEROKEE },
{ "Cyrl", USCRIPT_CYRILLIC },
/* { "Cyrs", USCRIPT_CYRILLIC }, */
{ "Deva", USCRIPT_DEVANAGARI },
{ "Dsrt", USCRIPT_DESERET },
{ "Ethi", USCRIPT_ETHIOPIC },
/* { "Geoa", USCRIPT_GEORGIAN }, */
/* { "Geon", USCRIPT_GEORGIAN }, */
{ "Geor", USCRIPT_GEORGIAN },
{ "Goth", USCRIPT_GOTHIC },
{ "Grek", USCRIPT_GREEK },
{ "Gujr", USCRIPT_GUJARATI },
{ "Guru", USCRIPT_GURMUKHI },
{ "Hang", USCRIPT_HANGUL },
{ "Hani", USCRIPT_HAN },
{ "Hano", USCRIPT_HANUNOO },
{ "Hebr", USCRIPT_HEBREW },
{ "Hira", USCRIPT_HIRAGANA },
{ "Ital", USCRIPT_OLD_ITALIC },
{ "Kana", USCRIPT_KATAKANA },
{ "Khmr", USCRIPT_KHMER },
{ "Knda", USCRIPT_KANNADA },
{ "Lao", USCRIPT_LAO },
/* { "Laoo", USCRIPT_LAO }, */
/* { "Latf", USCRIPT_LATIN }, */
/* { "Latg", USCRIPT_LATIN }, */
{ "Latn", USCRIPT_LATIN },
{ "Mlym", USCRIPT_MALAYALAM },
{ "Mong", USCRIPT_MONGOLIAN },
{ "Mymr", USCRIPT_MYANMAR },
{ "Ogam", USCRIPT_OGHAM },
{ "Orya", USCRIPT_ORIYA },
{ "Qaac", USCRIPT_COPTIC },
{ "Qaai", USCRIPT_INHERITED },
{ "Runr", USCRIPT_RUNIC },
{ "Sinh", USCRIPT_SINHALA },
{ "Syrc", USCRIPT_SYRIAC },
/* { "Syre", USCRIPT_SYRIAC }, */
/* { "Syrj", USCRIPT_SYRIAC }, */
/* { "Syrn", USCRIPT_SYRIAC }, */
{ "Tagb", USCRIPT_TAGBANWA },
{ "Taml", USCRIPT_TAMIL },
{ "Telu", USCRIPT_TELUGU },
{ "Tglg", USCRIPT_TAGALOG },
{ "Thaa", USCRIPT_THAANA },
{ "Thai", USCRIPT_THAI },
{ "Tibt", USCRIPT_TIBETAN },
{ "Yiii", USCRIPT_YI },
{ "Zyyy", USCRIPT_COMMON }
};
static const UChar32 pairedChars[] = {
@ -269,14 +192,15 @@ static const int32_t pairedCharExtra = pairedCharCount - pairedCharPower;
/* binary search the string array */
U_INLINE static int
findStringIndex(const char* const *sortedArr, const char* target, int size){
int left, middle, right,rc;
findStringIndex(const NameCodePair sortedArr[], const char *target, int32_t size) {
int32_t left, middle, right, rc;
left =0;
right= size-1;
while(left <= right){
middle = (left+right)/2;
rc=uprv_stricmp(sortedArr[middle],target);
rc=uprv_comparePropertyNames(sortedArr[middle].name, target);
if(rc<0){
left = middle+1;
}else if(rc >0){
@ -288,32 +212,12 @@ findStringIndex(const char* const *sortedArr, const char* target, int size){
return -1;
}
/*
static int
findCodeIndex(const UScriptCode sorted[], const UScriptCode target, int size){
int left, middle, right;
left =0;
right= size-1;
while(left <= right){
middle = (left+right)/2;
if(sorted[middle] < target){
left=middle+1;
}else if(sorted[middle]>target){
right=middle-1;
}else{
return middle;
}
}
return -1;
}
*/
/* linearly search the array and return the index */
U_INLINE static int
findCodeIndex(const UScriptCode unsorted[], const UScriptCode target, int size){
findCodeIndex(const NameCodePair unsorted[], const UScriptCode target, int size){
int i=0;
while(i<size){
if(target == unsorted[i]){
if(target == unsorted[i].code){
return i;
}
i++;
@ -412,17 +316,17 @@ uscript_getCode(const char* nameOrAbbrOrLocale,
return numFilled;
}
/* try the Names array first */
strIndex = findStringIndex(scriptNames, nameOrAbbrOrLocale, sizeof(scriptNames)/sizeof(*scriptNames));
strIndex = findStringIndex(scriptNames, nameOrAbbrOrLocale, ARRAY_SIZE(scriptNames));
if(strIndex>=0){
code = (UScriptCode) scriptNameCodes[strIndex];
code = (UScriptCode) scriptNames[strIndex].code;
len = 1;
}
/* we did not find in names array so try abbr array*/
if(code ==USCRIPT_INVALID_CODE){
strIndex = findStringIndex(scriptAbbr, nameOrAbbrOrLocale, sizeof(scriptAbbr)/sizeof(*scriptAbbr));
strIndex = findStringIndex(scriptAbbr, nameOrAbbrOrLocale, ARRAY_SIZE(scriptAbbr));
if(strIndex>=0){
code = (UScriptCode) scriptAbbrCodes[strIndex];
code = (UScriptCode) scriptAbbr[strIndex].code;
len = 1;
}
}
@ -440,8 +344,8 @@ uscript_getCode(const char* nameOrAbbrOrLocale,
if(U_SUCCESS(*err)){
char cName[50] = {'\0'};
u_UCharsToChars(name,cName,len);
index = findStringIndex(scriptAbbr, cName, sizeof(scriptAbbr)/sizeof(*scriptAbbr));
code = (UScriptCode) scriptAbbrCodes[index];
index = findStringIndex(scriptAbbr, cName, ARRAY_SIZE(scriptAbbr));
code = (UScriptCode) scriptAbbr[index].code;
/* got the script code now fill in the buffer */
if(numFilled<=capacity){
*(fillIn)++=code;
@ -478,9 +382,9 @@ uscript_getName(UScriptCode scriptCode){
if(scriptCode > USCRIPT_CODE_LIMIT){
return "";
}
index = findCodeIndex(scriptNameCodes,scriptCode,sizeof(scriptNameCodes)/sizeof(*scriptNameCodes));
index = findCodeIndex(scriptNames, scriptCode, ARRAY_SIZE(scriptNames));
if(index >=0){
return scriptNames[index];
return scriptNames[index].name;
}else{
return "";
}
@ -492,9 +396,9 @@ uscript_getShortName(UScriptCode scriptCode){
if(scriptCode > USCRIPT_CODE_LIMIT){
return "";
}
index = findCodeIndex(scriptAbbrCodes,scriptCode,sizeof(scriptAbbrCodes)/sizeof(*scriptAbbrCodes));
index = findCodeIndex(scriptAbbr, scriptCode, ARRAY_SIZE(scriptAbbr));
if(index >=0){
return scriptAbbr[index];
return scriptAbbr[index].name;
}else{
return "";
}