Many hyperlinks are disabled.
Use anonymous login
to enable hyperlinks.
Overview
| Comment: | Fix the initial-prefix optimization for the REGEXP extension such that it works even if the prefix contains characters that require a 3-byte UTF8 encoding. This should fix the problem reported by forum post 96692f8ba5. |
|---|---|
| Downloads: | Tarball | ZIP archive | SQL archive |
| Timelines: | family | ancestors | descendants | both | trunk |
| Files: | files | file ages | folders |
| SHA3-256: |
c94595a6e15490b432f099fefbe2429f |
| User & Date: | drh 2022-07-03 14:25:47 |
Context
|
2022-07-03
| ||
| 18:12 | Enhance the REGEXP extension so that the end-of-input indicate ("$") is allowed to occur on one branch of an OR ("|"). Forum post 0107d5d40dd273e2, second issue. (check-in: 3c04d21e user: drh tags: trunk) | |
| 14:32 | Fix the initial-prefix optimization for the REGEXP extension such that it works even if the prefix contains characters that require a 3-byte UTF8 encoding. This should fix the problem reported by forum post 96692f8ba5. (check-in: 7a32cccc user: drh tags: branch-3.39) | |
| 14:25 | Fix the initial-prefix optimization for the REGEXP extension such that it works even if the prefix contains characters that require a 3-byte UTF8 encoding. This should fix the problem reported by forum post 96692f8ba5. (check-in: c94595a6 user: drh tags: trunk) | |
| 11:16 | Improved comment on sqlite3VdbeSwap(). No changes to code. (check-in: 6a8e4fb7 user: drh tags: trunk) | |
Changes
Changes to ext/misc/regexp.c.
| ︙ | ︙ | |||
681 682 683 684 685 686 687 |
unsigned x = pRe->aArg[i];
if( x<=127 ){
pRe->zInit[j++] = (unsigned char)x;
}else if( x<=0xfff ){
pRe->zInit[j++] = (unsigned char)(0xc0 | (x>>6));
pRe->zInit[j++] = 0x80 | (x&0x3f);
}else if( x<=0xffff ){
| | | 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 |
unsigned x = pRe->aArg[i];
if( x<=127 ){
pRe->zInit[j++] = (unsigned char)x;
}else if( x<=0xfff ){
pRe->zInit[j++] = (unsigned char)(0xc0 | (x>>6));
pRe->zInit[j++] = 0x80 | (x&0x3f);
}else if( x<=0xffff ){
pRe->zInit[j++] = (unsigned char)(0xe0 | (x>>12));
pRe->zInit[j++] = 0x80 | ((x>>6)&0x3f);
pRe->zInit[j++] = 0x80 | (x&0x3f);
}else{
break;
}
}
if( j>0 && pRe->zInit[j-1]==0 ) j--;
|
| ︙ | ︙ |
Changes to test/regexp1.test.
| ︙ | ︙ | |||
235 236 237 238 239 240 241 242 |
'abc$¢€xyz' REGEXP '^abc[\u0024\u00A2\u20AC]{3}xyz$',
'abc$¢€xyz' REGEXP '^abc[\x24][\xa2\u20ac]+xyz$'
} {1 1 1}
do_execsql_test regexp1-2.22 {
SELECT 'abc$¢€xyz' REGEXP '^abc[^\u0025-X][^ -\u007f][^\u20ab]xyz$'
} {1}
finish_test
| > > > > > > > > > > > > > > > > > > > > > > | 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 |
'abc$¢€xyz' REGEXP '^abc[\u0024\u00A2\u20AC]{3}xyz$',
'abc$¢€xyz' REGEXP '^abc[\x24][\xa2\u20ac]+xyz$'
} {1 1 1}
do_execsql_test regexp1-2.22 {
SELECT 'abc$¢€xyz' REGEXP '^abc[^\u0025-X][^ -\u007f][^\u20ab]xyz$'
} {1}
# 2022-07-03
# https://sqlite.org/forum/forumpost/96692f8ba5
# The REGEXP extension mishandles the prefix search optimization when
# the prefix contains 3-byte UTF8 characters.
#
reset_db
load_static_extension db regexp
do_execsql_test regexp1-3.1 {
CREATE TABLE t1(id INTEGER PRIMARY KEY, a TEXT);
INSERT INTO t1(id, a) VALUES(1, '日本語');
SELECT a, hex(a), length(a) FROM t1;
} {日本語 E697A5E69CACE8AA9E 3}
do_execsql_test regexp1-3.2 {
SELECT * FROM t1 WHERE a='日本語';
} {1 日本語}
do_execsql_test regexp1-3.3 {
SELECT * FROM t1 WHERE a LIKE '日本語';
} {1 日本語}
do_execsql_test regexp1-3.4 {
SELECT * FROM t1 wHERE a REGEXP '日本語';
} {1 日本語}
finish_test
|