-
-
Notifications
You must be signed in to change notification settings - Fork 8
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
- Loading branch information
Showing
11 changed files
with
146 additions
and
137 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
|
|
@@ -12,6 +12,6 @@ __pycache__ | |
| /htmlcov | ||
|
|
||
| /jiten/.version | ||
| /jiten/_sqlite3_pcre.*.so | ||
| /jiten/_sqlite3_pcre*.so | ||
| /tmp | ||
| /tmp-html | ||
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file was deleted.
Oops, something went wrong.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,129 @@ | ||
| /* | ||
| * Written by Alexey Tourbin <[email protected]>. | ||
| * Modified by FC (Fay) Stegerman <[email protected]>. | ||
| * | ||
| * The author has dedicated the code to the public domain. Anyone is free | ||
| * to copy, modify, publish, use, compile, sell, or distribute the original | ||
| * code, either in source code form or as a compiled binary, for any purpose, | ||
| * commercial or non-commercial, and by any means. | ||
| */ | ||
| #define PCRE2_CODE_UNIT_WIDTH 8 | ||
| #include <assert.h> | ||
| #include <stdlib.h> | ||
| #include <string.h> | ||
| #include <pcre2.h> | ||
| #include <sqlite3ext.h> | ||
| SQLITE_EXTENSION_INIT1 | ||
|
|
||
| typedef struct { | ||
| char *str; | ||
| pcre2_code *code; | ||
| pcre2_match_data *match_data; | ||
| } cache_entry; | ||
|
|
||
| #ifndef CACHE_SIZE | ||
| #define CACHE_SIZE 16 | ||
| #endif | ||
|
|
||
| static void regexp(sqlite3_context *ctx, int argc, sqlite3_value **argv) | ||
| { | ||
| const char *re, *str; | ||
| pcre2_code *code; | ||
| pcre2_match_data *match_data; | ||
|
|
||
| assert(argc == 2); | ||
|
|
||
| re = (const char *) sqlite3_value_text(argv[0]); | ||
| if (re == NULL) { | ||
| sqlite3_result_error(ctx, "[REGEXP] no regexp", -1); | ||
| return; | ||
| } | ||
|
|
||
| str = (const char *) sqlite3_value_text(argv[1]); | ||
| if (str == NULL) { | ||
| sqlite3_result_error(ctx, "[REGEXP] no string", -1); | ||
| return; | ||
| } | ||
|
|
||
| /* simple LRU cache */ | ||
| { | ||
| int i; | ||
| int found = 0; | ||
| cache_entry *cache = sqlite3_user_data(ctx); | ||
|
|
||
| assert(cache != NULL); | ||
|
|
||
| for (i = 0; i < CACHE_SIZE && cache[i].str; i++) { | ||
| if (strcmp(re, cache[i].str) == 0) { | ||
| found = 1; | ||
| break; | ||
| } | ||
| } | ||
| if (found) { | ||
| if (i > 0) { | ||
| cache_entry c = cache[i]; | ||
| memmove(cache + 1, cache, i * sizeof(cache_entry)); | ||
| cache[0] = c; | ||
| } | ||
| } | ||
| else { | ||
| cache_entry c; | ||
| int err_no; | ||
| PCRE2_SIZE err_off; | ||
| c.code = pcre2_compile((PCRE2_SPTR)re, PCRE2_ZERO_TERMINATED, | ||
| PCRE2_UTF | PCRE2_UCP, &err_no, &err_off, NULL); | ||
| if (c.code == NULL) { | ||
| PCRE2_UCHAR err[256]; | ||
| pcre2_get_error_message(err_no, err, sizeof(err)); | ||
| char *e = sqlite3_mprintf("[REGEXP] %s: %s (offset %d)", re, err, err_off); | ||
| sqlite3_result_error(ctx, e, -1); | ||
| sqlite3_free(e); | ||
| return; | ||
| } | ||
| c.match_data = pcre2_match_data_create_from_pattern(c.code, NULL); | ||
| if (c.match_data == NULL) { | ||
| sqlite3_result_error(ctx, "[REGEXP] pcre2_match_data_create_from_pattern: ENOMEM", -1); | ||
| pcre2_code_free(c.code); | ||
| return; | ||
| } | ||
| c.str = strdup(re); | ||
| if (c.str == NULL) { | ||
| sqlite3_result_error(ctx, "[REGEXP] strdup: ENOMEM", -1); | ||
| pcre2_match_data_free(c.match_data); | ||
| pcre2_code_free(c.code); | ||
| return; | ||
| } | ||
| i = CACHE_SIZE - 1; | ||
| if (cache[i].str) { | ||
| free(cache[i].str); | ||
| assert(cache[i].code != NULL); | ||
| pcre2_match_data_free(cache[i].match_data); | ||
| pcre2_code_free(cache[i].code); | ||
| } | ||
| memmove(cache + 1, cache, i * sizeof(cache_entry)); | ||
| cache[0] = c; | ||
| } | ||
| code = cache[0].code; | ||
| match_data = cache[0].match_data; | ||
| } | ||
|
|
||
| { | ||
| int rc; | ||
| assert(code != NULL); | ||
| rc = pcre2_match(code, (PCRE2_SPTR)str, PCRE2_ZERO_TERMINATED, 0, 0, match_data, NULL); | ||
| sqlite3_result_int(ctx, rc >= 0); | ||
| return; | ||
| } | ||
| } | ||
|
|
||
| int sqlite3_extension_init(sqlite3 *db, char **err, const sqlite3_api_routines *api) | ||
| { | ||
| SQLITE_EXTENSION_INIT2(api) | ||
| cache_entry *cache = calloc(CACHE_SIZE, sizeof(cache_entry)); | ||
| if (cache == NULL) { | ||
| *err = "[REGEXP] calloc: ENOMEM"; | ||
| return 1; | ||
| } | ||
| sqlite3_create_function(db, "REGEXP", 2, SQLITE_UTF8, cache, regexp, NULL, NULL); | ||
| return 0; | ||
| } |