archive/php-src
1
0
Fork 0
mirror of https://github.com/php/php-src.git synced 2025-08-16 05:58:45 +02:00
Code Issues Projects Releases Packages Wiki Activity Actions 3

Improve locale character tables handling and reduce pattern cache size

Browse source 
If a locale other than C is active, character tables are saved into the
compile context. Every compiled pattern will have a pointer to the
character table, that was present in the context at the time of the
pattern compilation. Thus, the cache entries don't need to carry char
tables pointer, which reduces their size to 8 bytes on 64-bit. Instead,
the generated character tables are tracked in a separate HashTable. If a
character table was generated before, it'll be assigned to the compile
context when the locale changes. Otherwise a new char table will be
generated and cached.
This commit is contained in:
Anatol Belski 2018-06-22 14:37:59 +02:00
parent 34e58a6447
commit 684ce24eec
1 changed files with 26 additions and 15 deletions
Download patch file Download diff file Expand all files Collapse all files

39
ext/pcre/php_pcre.c
View file

@ -55,9 +55,6 @@ struct _pcre_cache_entry {
uint32_t compile_options;
uint32_t extra_compile_options;
uint32_t refcount;
#if HAVE_SETLOCALE
const uint8_t *tables;
#endif
};
enum {
@ -100,6 +97,16 @@ static MUTEX_T pcre_mt = NULL;
#define php_pcre_mutex_unlock()
#endif
#if HAVE_SETLOCALE
ZEND_TLS HashTable char_tables;
static void php_pcre_free_char_table(zval *data)
{/*{{{*/
void *ptr = Z_PTR_P(data);
pefree(ptr, 1);
}/*}}}*/
#endif
static void pcre_handle_exec_error(int pcre_code) /* {{{ */
{
int preg_code = 0;
@ -141,9 +148,6 @@ static void php_free_pcre_cache(zval *data) /* {{{ */
pcre_cache_entry *pce = (pcre_cache_entry *) Z_PTR_P(data);
if (!pce) return;
pcre2_code_free(pce->re);
#if HAVE_SETLOCALE
if ((void*)pce->tables) pefree((void*)pce->tables, 1);
#endif
pefree(pce, 1);
}
/* }}} */
@ -262,6 +266,9 @@ static PHP_GINIT_FUNCTION(pcre) /* {{{ */
#endif
php_pcre_init_pcre2(1);
#if HAVE_SETLOCALE
zend_hash_init(&char_tables, 1, NULL, php_pcre_free_char_table, 1);
#endif
}
/* }}} */
@ -270,6 +277,9 @@ static PHP_GSHUTDOWN_FUNCTION(pcre) /* {{{ */
zend_hash_destroy(&pcre_globals->pcre_cache);
php_pcre_shutdown_pcre2();
#if HAVE_SETLOCALE
zend_hash_destroy(&char_tables);
#endif
php_pcre_mutex_free();
}
@ -535,6 +545,7 @@ PHPAPI pcre_cache_entry* pcre_get_compiled_regex_cache(zend_string *regex)
size_t pattern_len;
uint32_t poptions = 0;
const uint8_t *tables = NULL;
uint8_t save_tables = 0;
zval *zv;
pcre_cache_entry new_entry;
int rc;
@ -705,13 +716,11 @@ PHPAPI pcre_cache_entry* pcre_get_compiled_regex_cache(zend_string *regex)
#if HAVE_SETLOCALE
if (key != regex) {
/* XXX a better solution here were to create a copy of cctx
and to cache it along with the generated tables. Once same locale
is encountered, the cached cctx and tables would be fetched.
Currently the tables are generated every time a locale based
pattern is used, and the tables are overwritten in the global
cctx. */
tables = (uint8_t *)zend_hash_find_ptr(&char_tables, BG(locale_string));
if (!tables) {
save_tables = 1;
tables = pcre2_maketables(gctx);
}
pcre2_set_character_tables(cctx, tables);
}
#endif
@ -739,7 +748,7 @@ PHPAPI pcre_cache_entry* pcre_get_compiled_regex_cache(zend_string *regex)
php_error_docref(NULL,E_WARNING, "Compilation failed: %s at offset %zu", error, erroffset);
pcre_handle_exec_error(PCRE2_ERROR_INTERNAL);
efree(pattern);
if (tables) {
if (save_tables) {
pefree((void*)tables, 1);
}
return NULL;
@ -779,7 +788,9 @@ PHPAPI pcre_cache_entry* pcre_get_compiled_regex_cache(zend_string *regex)
new_entry.compile_options = coptions;
new_entry.extra_compile_options = extra_coptions;
#if HAVE_SETLOCALE
new_entry.tables = tables;
if (save_tables) {
zend_hash_add_ptr(&char_tables, BG(locale_string), (void *)tables);
}
#endif
new_entry.refcount = 0;