mirror of
https://github.com/unicode-org/icu.git
synced 2025-04-15 09:45:26 +00:00
ICU-899 change uscript_getCode() API to accept fillin buffer and capacity
X-SVN-Rev: 6389
This commit is contained in:
Ram Viswanadha
parent
f7a2890b94
commit
5a3494cf54
5 changed files with 145 additions and 80 deletions
|
|
@ -67,16 +67,20 @@ typedef enum UScriptCode {
|
|||
|
||||
|
||||
/**
|
||||
* Gets a script code associated with the given locale or ISO 15924 abbreviation or name.
|
||||
* Returns USCRIPT_MALAYAM given "Malayam" OR "Mlym".
|
||||
* Returns USCRIPT_LATIN given "en" OR "en_US"
|
||||
* Gets script codes associated with the given locale or ISO 15924 abbreviation or name.
|
||||
* Fills in USCRIPT_MALAYAM given "Malayam" OR "Mlym".
|
||||
* Fills in USCRIPT_LATIN given "en" OR "en_US"
|
||||
* If required capacity is greater than capacity of the destination buffer then the error code
|
||||
* is set to U_BUFFER_OVERFLOW_ERROR and the required capacity is returned
|
||||
* @param nameOrAbbrOrLocale name of the script or ISO 15924 code or locale
|
||||
* @param fillIn the UScriptCode buffer to fill in the script code
|
||||
* @param capacity the capacity (size) fo UScriptCode buffer passed in.
|
||||
* @param err the error status code.
|
||||
* @return The UScriptCode
|
||||
* @return The number of script codes filled in the buffer passed in
|
||||
* @draft
|
||||
*/
|
||||
U_CAPI UScriptCode
|
||||
uscript_getCode(const char* nameOrAbbrOrLocale,UErrorCode *err);
|
||||
U_CAPI int32_t
|
||||
uscript_getCode(const char* nameOrAbbrOrLocale,UScriptCode* fillIn,int32_t capacity,UErrorCode *err);
|
||||
|
||||
/**
|
||||
* Gets a script name associated with the given script code.
|
||||
|
|
|
|||
|
|
@ -210,7 +210,7 @@ static const UScriptCode scriptAbbrCodes[] = {
|
|||
USCRIPT_SYRIAC ,
|
||||
/* USCRIPT_SYRIAC , */
|
||||
/* USCRIPT_SYRIAC , */
|
||||
USCRIPT_SYRIAC ,
|
||||
/* USCRIPT_SYRIAC , */
|
||||
USCRIPT_TAMIL ,
|
||||
USCRIPT_TELUGU ,
|
||||
USCRIPT_THAANA ,
|
||||
|
|
@ -768,48 +768,77 @@ findCodeIndex(const UScriptCode unsorted[], const UScriptCode target, int size){
|
|||
return -1;
|
||||
}
|
||||
|
||||
U_CAPI UScriptCode
|
||||
uscript_getCode(const char* nameOrAbbrOrLocale, UErrorCode* err){
|
||||
U_CAPI int32_t
|
||||
uscript_getCode(const char* nameOrAbbrOrLocale,
|
||||
UScriptCode* fillIn,
|
||||
int32_t capacity,
|
||||
UErrorCode* err){
|
||||
|
||||
UScriptCode code = USCRIPT_INVALID_CODE;
|
||||
int strIndex=0;
|
||||
|
||||
int32_t numFilled=0;
|
||||
int32_t len=0;
|
||||
/* check arguments */
|
||||
if(U_FAILURE(*err)){
|
||||
return code;
|
||||
return numFilled;
|
||||
}
|
||||
/* try the Names array first */
|
||||
strIndex = findStringIndex(scriptNames, nameOrAbbrOrLocale, USCRIPT_NAMES_ARRAY_SIZE);
|
||||
|
||||
if(strIndex>=0 && strIndex < USCRIPT_NAMES_ARRAY_SIZE){
|
||||
code = (UScriptCode) scriptNameCodes[strIndex];
|
||||
len = 1;
|
||||
}
|
||||
/* we did not find in names array so try abbr array*/
|
||||
if(code ==USCRIPT_INVALID_CODE){
|
||||
strIndex = findStringIndex(scriptAbbr, nameOrAbbrOrLocale, USCRIPT_ABBR_ARRAY_SIZE);
|
||||
if(strIndex>=0 && strIndex < USCRIPT_NAMES_ARRAY_SIZE){
|
||||
code = (UScriptCode) scriptAbbrCodes[strIndex];
|
||||
len = 1;
|
||||
}
|
||||
}
|
||||
|
||||
/* we still haven't found it try locale */
|
||||
if(code==USCRIPT_INVALID_CODE){
|
||||
UResourceBundle* resB = ures_open(u_getDataDirectory(),nameOrAbbrOrLocale,err);
|
||||
if(U_SUCCESS(*err)&& *err != U_USING_DEFAULT_ERROR){
|
||||
int32_t len=0;
|
||||
UResourceBundle* resD = ures_getByKey(resB,kLocaleScript,NULL,err);
|
||||
int index =0;
|
||||
const UChar* name = ures_getStringByIndex(resD,0,&len,err);
|
||||
if(U_SUCCESS(*err) ){
|
||||
char cName[50] = {'\0'};
|
||||
u_UCharsToChars(name,cName,len);
|
||||
index = findStringIndex(scriptNames, cName, USCRIPT_NAMES_ARRAY_SIZE);
|
||||
code = (UScriptCode) scriptNameCodes[index];
|
||||
len =0;
|
||||
while(ures_hasNext(resD)){
|
||||
const UChar* name = ures_getNextString(resD,&len,NULL,err);
|
||||
if(U_SUCCESS(*err)){
|
||||
char cName[50] = {'\0'};
|
||||
u_UCharsToChars(name,cName,len);
|
||||
index = findStringIndex(scriptAbbr, cName, USCRIPT_NAMES_ARRAY_SIZE);
|
||||
code = (UScriptCode) scriptAbbrCodes[index];
|
||||
/* got the script code now fill in the buffer */
|
||||
if(numFilled<=capacity){
|
||||
*(fillIn)++=code;
|
||||
numFilled++;
|
||||
}else{
|
||||
*err=U_BUFFER_OVERFLOW_ERROR;
|
||||
return len;
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
ures_close(resD);
|
||||
|
||||
}
|
||||
ures_close(resB);
|
||||
}else{
|
||||
/* we found it */
|
||||
if(numFilled<=capacity){
|
||||
*(fillIn)++=code;
|
||||
numFilled++;
|
||||
}else{
|
||||
*err=U_BUFFER_OVERFLOW_ERROR;
|
||||
return len;
|
||||
}
|
||||
}
|
||||
return code;
|
||||
return numFilled;
|
||||
}
|
||||
|
||||
U_CAPI const char*
|
||||
|
|
|
|||
|
|
@ -169,10 +169,10 @@ Spec::Spec(const UnicodeString& theSpec) : top(theSpec) {
|
|||
// Canonicalize script name -or- do locale->script mapping
|
||||
status = U_ZERO_ERROR;
|
||||
CharString spc(top);
|
||||
UScriptCode s = uscript_getCode(spc, &status);
|
||||
if (s != USCRIPT_INVALID_CODE) {
|
||||
scriptName = UnicodeString(uscript_getName(s), "");
|
||||
}
|
||||
const int32_t capacity = 10;
|
||||
UScriptCode script[capacity]={USCRIPT_INVALID_CODE};
|
||||
int32_t num = uscript_getCode(spc,script,capacity, &status);
|
||||
|
||||
|
||||
// Canonicalize top
|
||||
char buf[256];
|
||||
|
|
|
|||
|
|
@ -4,8 +4,8 @@
|
|||
* Corporation and others. All Rights Reserved.
|
||||
**********************************************************************
|
||||
* $Source: /xsrl/Nsvn/icu/icu/source/i18n/Attic/upropset.cpp,v $
|
||||
* $Date: 2001/10/17 19:20:41 $
|
||||
* $Revision: 1.1 $
|
||||
* $Date: 2001/10/23 02:00:50 $
|
||||
* $Revision: 1.2 $
|
||||
**********************************************************************
|
||||
*/
|
||||
#include "upropset.h"
|
||||
|
|
@ -272,12 +272,15 @@ UnicodeSet* UnicodePropertySet::createCategorySet(const UnicodeString& valueName
|
|||
UnicodeSet* UnicodePropertySet::createScriptSet(const UnicodeString& valueName) {
|
||||
_CharString cvalueName(valueName);
|
||||
UErrorCode ec = U_ZERO_ERROR;
|
||||
UScriptCode script = uscript_getCode(cvalueName, &ec);
|
||||
if (script == USCRIPT_INVALID_CODE || U_FAILURE(ec)) {
|
||||
const int32_t capacity = 10;
|
||||
UScriptCode script[capacity]={USCRIPT_INVALID_CODE};
|
||||
int32_t num = uscript_getCode(cvalueName,script,capacity, &ec);
|
||||
|
||||
if (script[0] == USCRIPT_INVALID_CODE || U_FAILURE(ec)) {
|
||||
// Syntax error; unknown short name
|
||||
return NULL;
|
||||
}
|
||||
return new UnicodeSet(getScriptSet(script));
|
||||
return new UnicodeSet(getScriptSet(script[0]));
|
||||
}
|
||||
|
||||
//----------------------------------------------------------------
|
||||
|
|
|
|||
|
|
@ -1778,64 +1778,93 @@ TestCaseCompare() {
|
|||
}
|
||||
|
||||
static void TestUScriptCodeAPI(){
|
||||
const char* testNames[]={
|
||||
/* test locale */
|
||||
"en", "en_US", "sr", "ta" , "te_IN",
|
||||
"hi", "he", "ar",
|
||||
/* test abbr */
|
||||
"Hani", "Hang","Hebr","Hira",
|
||||
"Knda","Kana","Khmr","Lao",
|
||||
"Latn",/*"Latf","Latg",*/
|
||||
"Mlym", "Mong",
|
||||
|
||||
/* test names */
|
||||
"CYRILLIC","DESERET","DEVANAGARI","ETHIOPIC","GEORGIAN",
|
||||
"GOTHIC", "GREEK", "GUJARATI",
|
||||
/* test lower case names */
|
||||
"malayalam", "mongolian", "myanmar", "ogham", "old-italic",
|
||||
"oriya", "runic", "sinhala", "syriac","tamil",
|
||||
"telugu", "thaana", "thai", "tibetan",
|
||||
/* test the bounds*/
|
||||
"ucas", "arabic",
|
||||
/* test bogus */
|
||||
"asfdasd", "5464", "12235",
|
||||
'\0'
|
||||
};
|
||||
UScriptCode expected[] ={
|
||||
/* locales should return */
|
||||
USCRIPT_LATIN, USCRIPT_LATIN, USCRIPT_CYRILLIC, USCRIPT_TAMIL, USCRIPT_TELUGU,
|
||||
USCRIPT_DEVANAGARI, USCRIPT_HEBREW, USCRIPT_ARABIC,
|
||||
/* abbr should return */
|
||||
USCRIPT_HAN, USCRIPT_HANGUL, USCRIPT_HEBREW, USCRIPT_HIRAGANA,
|
||||
USCRIPT_KANNADA, USCRIPT_KATAKANA, USCRIPT_KHMER, USCRIPT_LAO,
|
||||
USCRIPT_LATIN,/* USCRIPT_LATIN, USCRIPT_LATIN,*/
|
||||
USCRIPT_MALAYALAM, USCRIPT_MONGOLIAN,
|
||||
/* names should return */
|
||||
USCRIPT_CYRILLIC, USCRIPT_DESERET, USCRIPT_DEVANAGARI, USCRIPT_ETHIOPIC, USCRIPT_GEORGIAN,
|
||||
USCRIPT_GOTHIC, USCRIPT_GREEK, USCRIPT_GUJARATI,
|
||||
/* lower case names should return */
|
||||
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,
|
||||
/* bounds */
|
||||
USCRIPT_UCAS, USCRIPT_ARABIC,
|
||||
/* bogus names should return invalid code */
|
||||
USCRIPT_INVALID_CODE, USCRIPT_INVALID_CODE, USCRIPT_INVALID_CODE,
|
||||
};
|
||||
int i =0;
|
||||
int numErrors =0;
|
||||
UErrorCode err = U_ZERO_ERROR;
|
||||
for( ; testNames[i]!='\0'; i++){
|
||||
UScriptCode code = uscript_getCode(testNames[i],&err);
|
||||
if( code != expected[i]){
|
||||
log_verbose("Error getting script code Got: %i Expected: %i for name %s\n",
|
||||
code,expected[i],testNames[i]);
|
||||
numErrors++;
|
||||
{
|
||||
const char* testNames[]={
|
||||
/* test locale */
|
||||
"en", "en_US", "sr", "ta" , "te_IN",
|
||||
"hi", "he", "ar",
|
||||
/* test abbr */
|
||||
"Hani", "Hang","Hebr","Hira",
|
||||
"Knda","Kana","Khmr","Lao",
|
||||
"Latn",/*"Latf","Latg",*/
|
||||
"Mlym", "Mong",
|
||||
|
||||
/* test names */
|
||||
"CYRILLIC","DESERET","DEVANAGARI","ETHIOPIC","GEORGIAN",
|
||||
"GOTHIC", "GREEK", "GUJARATI",
|
||||
/* test lower case names */
|
||||
"malayalam", "mongolian", "myanmar", "ogham", "old-italic",
|
||||
"oriya", "runic", "sinhala", "syriac","tamil",
|
||||
"telugu", "thaana", "thai", "tibetan",
|
||||
/* test the bounds*/
|
||||
"ucas", "arabic",
|
||||
/* test bogus */
|
||||
"asfdasd", "5464", "12235",
|
||||
'\0'
|
||||
};
|
||||
UScriptCode expected[] ={
|
||||
/* locales should return */
|
||||
USCRIPT_LATIN, USCRIPT_LATIN, USCRIPT_CYRILLIC, USCRIPT_TAMIL, USCRIPT_TELUGU,
|
||||
USCRIPT_DEVANAGARI, USCRIPT_HEBREW, USCRIPT_ARABIC,
|
||||
/* abbr should return */
|
||||
USCRIPT_HAN, USCRIPT_HANGUL, USCRIPT_HEBREW, USCRIPT_HIRAGANA,
|
||||
USCRIPT_KANNADA, USCRIPT_KATAKANA, USCRIPT_KHMER, USCRIPT_LAO,
|
||||
USCRIPT_LATIN,/* USCRIPT_LATIN, USCRIPT_LATIN,*/
|
||||
USCRIPT_MALAYALAM, USCRIPT_MONGOLIAN,
|
||||
/* names should return */
|
||||
USCRIPT_CYRILLIC, USCRIPT_DESERET, USCRIPT_DEVANAGARI, USCRIPT_ETHIOPIC, USCRIPT_GEORGIAN,
|
||||
USCRIPT_GOTHIC, USCRIPT_GREEK, USCRIPT_GUJARATI,
|
||||
/* lower case names should return */
|
||||
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,
|
||||
/* bounds */
|
||||
USCRIPT_UCAS, USCRIPT_ARABIC,
|
||||
/* bogus names should return invalid code */
|
||||
USCRIPT_INVALID_CODE, USCRIPT_INVALID_CODE, USCRIPT_INVALID_CODE,
|
||||
};
|
||||
|
||||
UErrorCode err = U_ZERO_ERROR;
|
||||
|
||||
const int32_t capacity = 10;
|
||||
|
||||
for( ; testNames[i]!='\0'; i++){
|
||||
UScriptCode script[10]={USCRIPT_INVALID_CODE};
|
||||
int32_t num = uscript_getCode(testNames[i],script,capacity, &err);
|
||||
if( script[0] != expected[i]){
|
||||
log_verbose("Error getting script code Got: %i Expected: %i for name %s\n",
|
||||
script[0],expected[i],testNames[i]);
|
||||
numErrors++;
|
||||
}
|
||||
}
|
||||
if(numErrors >0 ){
|
||||
log_err("Errors uchar_getScriptCode() : %i \n",numErrors);
|
||||
}
|
||||
}
|
||||
if(numErrors >0 ){
|
||||
log_err("Errors uchar_getScriptCode() : %i \n",numErrors);
|
||||
{
|
||||
UErrorCode err = U_ZERO_ERROR;
|
||||
int32_t capacity=0;
|
||||
UScriptCode jaCode[2]={ USCRIPT_KATAKANA,USCRIPT_HIRAGANA};
|
||||
UScriptCode script[10]={USCRIPT_INVALID_CODE};
|
||||
int32_t num = uscript_getCode("ja",script,capacity, &err);
|
||||
/* preflight */
|
||||
if(err==U_BUFFER_OVERFLOW_ERROR){
|
||||
err = U_ZERO_ERROR;
|
||||
capacity = 10;
|
||||
num = uscript_getCode("ja",script,capacity, &err);
|
||||
if(num!=(sizeof(jaCode)/sizeof(UScriptCode)) || script[0]!=jaCode[0] || script[1]!=jaCode[1]){
|
||||
log_err("Errors uscript_getScriptCode() for Japaneese locale \n");
|
||||
}
|
||||
}else{
|
||||
log_err("Errors in uscript_getScriptCode() expected error : %s got: %s \n",
|
||||
"U_BUFFER_OVERFLOW_ERROR",
|
||||
u_errorName(err));
|
||||
}
|
||||
|
||||
}
|
||||
|
||||
{
|
||||
UScriptCode testAbbr[]={
|
||||
/* names should return */
|
||||
|
|
|
|||
Loading…
Add table
Reference in a new issue