Skip to content

C
core
Kaydet (Commit) a3c627fe authored tarafından Eike Rathke's avatar Eike Rathke
Dosyalara gözat
Seçenekler

resolve crashes with ICU 53.1 in locales with collator data, fdo#77071 

ICU 53.1 changed API behavior:
https://ssl.icu-project.org/apiref/icu4c/classicu_1_1RuleBasedCollator.html#a2f4c7eeaf020ad68e3bd9722dd272357
isn't correct anymore:

length: size of the image. If negative, the API will try to figure out the
        length of the image

        NO, IT WILL NOT! It bails out with an error instead.
        Introduced a function to obtain the length for each collator data.

base:  collator, usually root. The base is required to be present through the
       lifetime of the collator. Currently it cannot be NULL.

       NOT "usually root"! There's a check now that bails out if
       if(base->tailoring != CollationRoot::getRoot(errorCode))
       So using an instance created with icu::Locale::getRoot()

Change-Id: Ia9c4e27d5ef4f8083bbe57e4e2f4b3ff63bb42ed
üst cbb9efa6
Show whitespace changes
Inline Side-by-side
Showing with 94 additions and 6 deletions
i18npool/source/collator/collator_unicode.cxx
Dosyayı görüntüle @ a3c627fe
......@@ -121,6 +121,7 @@ Collator_Unicode::loadCollatorAlgorithm(const OUString& rAlgorithm, const lang::
}
if (!collator && OUString::createFromAscii(LOCAL_RULE_LANGS).indexOf(rLocale.Language) >= 0) {
const sal_uInt8* (*func)() = NULL;
size_t (*funclen)() = NULL;
#ifndef DISABLE_DYNLOADING
OUStringBuffer aBuf;
......@@ -133,11 +134,21 @@ Collator_Unicode::loadCollatorAlgorithm(const OUString& rAlgorithm, const lang::
aBuf.appendAscii("get_").append(rLocale.Language).appendAscii("_");
if ( rLocale.Language == "zh" ) {
OUString func_base = aBuf.makeStringAndClear();
OUString funclen_base = func_base + "_length";
if (OUString("TW HK MO").indexOf(rLocale.Country) >= 0)
func=(const sal_uInt8* (*)()) osl_getFunctionSymbol(hModule,
{
func = (const sal_uInt8* (*)()) osl_getFunctionSymbol(hModule,
OUString(func_base + "TW_" + rAlgorithm).pData);
funclen = (size_t (*)()) osl_getFunctionSymbol(hModule,
OUString(funclen_base + "TW_" + rAlgorithm).pData);
}
if (!func)
func=(const sal_uInt8* (*)()) osl_getFunctionSymbol(hModule, OUString(func_base + rAlgorithm).pData);
{
func = (const sal_uInt8* (*)()) osl_getFunctionSymbol(
hModule, OUString(func_base + rAlgorithm).pData);
funclen = (size_t (*)()) osl_getFunctionSymbol(
hModule, OUString(funclen_base + rAlgorithm).pData);
}
} else {
if ( rLocale.Language == "ja" ) {
// replace algorithm name to implementation name.
......@@ -150,7 +161,10 @@ Collator_Unicode::loadCollatorAlgorithm(const OUString& rAlgorithm, const lang::
} else {
aBuf.append(rAlgorithm);
}
func=(const sal_uInt8* (*)()) osl_getFunctionSymbol(hModule, aBuf.makeStringAndClear().pData);
OUString func_base = aBuf.makeStringAndClear();
OUString funclen_base = func_base + "_length";
func = (const sal_uInt8* (*)()) osl_getFunctionSymbol(hModule, func_base.pData);
funclen = (size_t (*)()) osl_getFunctionSymbol(hModule, funclen_base.pData);
}
}
#else
......@@ -159,87 +173,159 @@ Collator_Unicode::loadCollatorAlgorithm(const OUString& rAlgorithm, const lang::
#if WITH_LOCALE_ALL || WITH_LOCALE_ca
} else if ( rLocale.Language == "ca" ) {
if ( rAlgorithm == "charset" )
{
func = get_collator_data_ca_charset;
funclen = get_collator_data_ca_charset_length;
}
#endif
#if WITH_LOCALE_ALL || WITH_LOCALE_dz
} else if ( rLocale.Language == "dz" || rLocale.Language == "bo" ) {
// 'bo' Tibetan uses the same collation rules as 'dz' Dzongkha
if ( rAlgorithm == "charset" )
{
func = get_collator_data_dz_charset;
funclen = get_collator_data_dz_charset_length;
}
#endif
#if WITH_LOCALE_ALL || WITH_LOCALE_hu
} else if ( rLocale.Language == "hu" ) {
if ( rAlgorithm == "charset" )
{
func = get_collator_data_hu_charset;
funclen = get_collator_data_hu_charset_length;
}
#endif
#if WITH_LOCALE_ALL || WITH_LOCALE_ja
} else if ( rLocale.Language == "ja" ) {
if ( rAlgorithm == "charset" )
{
func = get_collator_data_ja_charset;
funclen = get_collator_data_ja_charset_length;
}
else if ( rAlgorithm == "phonetic (alphanumeric first)" )
{
func = get_collator_data_ja_phonetic_alphanumeric_first;
funclen = get_collator_data_ja_phonetic_alphanumeric_first_length;
}
else if ( rAlgorithm == "phonetic (alphanumeric last)" )
{
func = get_collator_data_ja_phonetic_alphanumeric_last;
funclen = get_collator_data_ja_phonetic_alphanumeric_last_length;
}
#endif
#if WITH_LOCALE_ALL || WITH_LOCALE_ko
#if (U_ICU_VERSION_MAJOR_NUM < 53)
} else if ( rLocale.Language == "ko" ) {
if ( rAlgorithm == "charset" )
{
func = get_collator_data_ko_charset;
funclen = get_collator_data_ko_charset_length;
}
#endif
#endif
#if WITH_LOCALE_ALL || WITH_LOCALE_ku
} else if ( rLocale.Language == "ku" ) {
if ( rAlgorithm == "alphanumeric" )
{
func = get_collator_data_ku_alphanumeric;
funclen = get_collator_data_ku_alphanumeric_length;
}
#endif
#if WITH_LOCALE_ALL || WITH_LOCALE_ln
} else if ( rLocale.Language == "ln" ) {
if ( rAlgorithm == "charset" )
{
func = get_collator_data_ln_charset;
funclen = get_collator_data_ln_charset_length;
}
#endif
#if WITH_LOCALE_ALL || WITH_LOCALE_my
} else if ( rLocale.Language == "my" ) {
if ( rAlgorithm == "dictionary" )
{
func = get_collator_data_my_dictionary;
funclen = get_collator_data_my_dictionary_length;
}
#endif
#if WITH_LOCALE_ALL || WITH_LOCALE_ne
} else if ( rLocale.Language == "ne" ) {
if ( rAlgorithm == "charset" )
{
func = get_collator_data_ne_charset;
funclen = get_collator_data_ne_charset_length;
}
#endif
#if WITH_LOCALE_ALL || WITH_LOCALE_sid
} else if ( rLocale.Language == "sid" ) {
if ( rAlgorithm == "charset" )
{
func = get_collator_data_sid_charset;
funclen = get_collator_data_sid_charset_length;
}
#endif
#if WITH_LOCALE_ALL || WITH_LOCALE_zh
} else if ( rLocale.Language == "zh" && (rLocale.Country == "TW" || rLocale.Country == "HK" || rLocale.Country == "MO") ) {
if ( rAlgorithm == "charset" )
{
func = get_collator_data_zh_TW_charset;
funclen = get_collator_data_zh_TW_charset_length;
}
else if ( rAlgorithm == "radical" )
{
func = get_collator_data_zh_TW_radical;
funclen = get_collator_data_zh_TW_radical_length;
}
else if ( rAlgorithm == "stroke" )
{
func = get_collator_data_zh_TW_stroke;
funclen = get_collator_data_zh_TW_stroke_length;
}
} else if ( rLocale.Language == "zh" ) {
if ( rAlgorithm == "charset" )
{
func = get_collator_data_zh_charset;
funclen = get_collator_data_zh_charset_length;
}
else if ( rAlgorithm == "pinyin" )
{
func = get_collator_data_zh_pinyin;
funclen = get_collator_data_zh_pinyin_length;
}
else if ( rAlgorithm == "radical" )
{
func = get_collator_data_zh_radical;
funclen = get_collator_data_zh_radical_length;
}
else if ( rAlgorithm == "stroke" )
{
func = get_collator_data_zh_stroke;
funclen = get_collator_data_zh_stroke_length;
}
else if ( rAlgorithm == "zhuyin" )
{
func = get_collator_data_zh_zhuyin;
funclen = get_collator_data_zh_zhuyin_length;
}
#endif
}
#endif // DISABLE_DYNLOADING
if (func) {
if (func && funclen) {
const sal_uInt8* ruleImage=func();
uca_base = new RuleBasedCollator(static_cast<UChar*>(NULL), status);
size_t ruleImageSize = funclen();
// Not only changed ICU 53.1 the API behavior that a negative
// length (ruleImageSize) now leads to failure, but also that
// the base RuleBasedCollator passed as uca_base here needs to
// have a base->tailoring == CollationRoot::getRoot() otherwise
// the init bails out as well, as it does for the previously
// used "empty" RuleBasedCollator.
// The default collator of the en-US locale would also fulfill
// the requirement. The collator of the actual locale or the
// NULL (default) locale does not.
uca_base = static_cast<RuleBasedCollator*>(icu::Collator::createInstance(
icu::Locale::getRoot(), status));
if (! U_SUCCESS(status)) throw RuntimeException();
collator = new RuleBasedCollator(reinterpret_cast<const uint8_t*>(ruleImage), -1, uca_base, status);
collator = new RuleBasedCollator(
reinterpret_cast<const uint8_t*>(ruleImage), ruleImageSize, uca_base, status);
if (! U_SUCCESS(status)) throw RuntimeException();
}
}
......
i18npool/source/collator/gencoll_rule.cxx
Dosyayı görüntüle @ a3c627fe
......@@ -65,8 +65,10 @@ void data_write(char* file, char* name, sal_uInt8 *data, sal_Int32 len)
fprintf(fp, "#ifndef DISABLE_DYNLOADING\n");
fprintf(fp, "SAL_DLLPUBLIC_EXPORT const sal_uInt8* get_%s() { return %s; }\n", name, name);
fprintf(fp, "SAL_DLLPUBLIC_EXPORT size_t get_%s_length() { return sizeof(%s); }\n", name, name);
fprintf(fp, "#else\n");
fprintf(fp, "SAL_DLLPUBLIC_EXPORT const sal_uInt8* get_collator_data_%s() { return %s; }\n", name, name);
fprintf(fp, "SAL_DLLPUBLIC_EXPORT size_t get_collator_data_%s_length() { return sizeof(%s); }\n", name, name);
fprintf(fp, "#endif\n");
fprintf(fp, "\n");
fprintf (fp, "}\n");
......
Markdown is supported
0% or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment