This is an automated email from the ASF dual-hosted git repository.
yiguolei pushed a commit to branch master
in repository https://gitbox.apache.org/repos/asf/doris.git
The following commit(s) were added to refs/heads/master by this push:
new 888a0460093 [Fix](regexp) make dot match newline in regexp_fn by
default (#60831)
888a0460093 is described below
commit 888a04600936ada7ab83e02d474715db257adf14
Author: linrrarity <[email protected]>
AuthorDate: Thu Feb 26 17:05:17 2026 +0800
[Fix](regexp) make dot match newline in regexp_fn by default (#60831)
### What problem does this PR solve?
Issue Number: close #xxx
Related PR: #xxx
Problem Summary:
### Release note
doc: https://github.com/apache/doris-website/pull/3410
Keep the behavior of `regexp_fn` consistent with `regexp`
before:
```text
Doris> SELECT REGEXP_EXTRACT('foo\nbar', '^(.+)$', 1);
+-----------------------------------------+
| REGEXP_EXTRACT('foo\nbar', '^(.+)$', 1) |
+-----------------------------------------+
| |
+-----------------------------------------+
```
After
```text
Doris> SELECT REGEXP_EXTRACT('foo\nbar', '^(.+)$', 1);
+-----------------------------------------+
| REGEXP_EXTRACT('foo\nbar', '^(.+)$', 1) |
+-----------------------------------------+
| foo
bar |
+-----------------------------------------+
```
None
### Check List (For Author)
- Test <!-- At least one of them must be included. -->
- [ ] Regression test
- [ ] Unit Test
- [ ] Manual test (add detailed scripts or steps below)
- [ ] No need to test or manual test. Explain why:
- [ ] This is a refactor/code format and no logic has been changed.
- [ ] Previous test can cover this change.
- [ ] No code files have been changed.
- [ ] Other reason <!-- Add your reason? -->
- Behavior changed:
- [ ] No.
- [ ] Yes. <!-- Explain the behavior change -->
- Does this need documentation?
- [ ] No.
- [ ] Yes. <!-- Add document PR link here. eg:
https://github.com/apache/doris-website/pull/1214 -->
### Check List (For Reviewer who merge this PR)
- [ ] Confirm the release note
- [ ] Confirm test cases
- [ ] Confirm document
- [ ] Add branch pick label <!-- Add branch pick label that this PR
should merge into -->
---
be/src/vec/functions/function_regexp.cpp | 1 +
.../test_string_function_regexp.out | 45 ++++++++++++++++++++++
.../test_string_function_regexp.groovy | 18 +++++++++
3 files changed, 64 insertions(+)
diff --git a/be/src/vec/functions/function_regexp.cpp
b/be/src/vec/functions/function_regexp.cpp
index bc51ddb21a6..efa61b05cdd 100644
--- a/be/src/vec/functions/function_regexp.cpp
+++ b/be/src/vec/functions/function_regexp.cpp
@@ -66,6 +66,7 @@ struct RegexpExtractEngine {
RegexpExtractEngine& engine, bool
enable_extended_regex) {
re2::RE2::Options options;
options.set_log_errors(false); // avoid RE2 printing to stderr; we
handle errors ourselves
+ options.set_dot_nl(true); // make '.' match '\n' by default,
consistent with REGEXP/LIKE
engine.re2_regex =
std::make_unique<re2::RE2>(re2::StringPiece(pattern.data,
pattern.size), options);
diff --git
a/regression-test/data/query_p0/sql_functions/string_functions/test_string_function_regexp.out
b/regression-test/data/query_p0/sql_functions/string_functions/test_string_function_regexp.out
index d7994943fd5..d7422abb0e7 100644
---
a/regression-test/data/query_p0/sql_functions/string_functions/test_string_function_regexp.out
+++
b/regression-test/data/query_p0/sql_functions/string_functions/test_string_function_regexp.out
@@ -163,6 +163,21 @@ EdgeCase1
-- !regexp_extract_3 --
AA-1
+-- !regexp_extract_4 --
+foo\nbar
+
+-- !regexp_extract_5 --
+
+
+-- !regexp_extract_6 --
+foo\nbar
+
+-- !regexp_extract_7 --
+aXb
+
+-- !regexp_extract_8 --
+aXb
+
-- !sql --
b
@@ -178,6 +193,21 @@ d
-- !regexp_extract_or_null_2 --
B
+-- !regexp_extract_or_null_3 --
+foo\nbar
+
+-- !regexp_extract_or_null_4 --
+\N
+
+-- !regexp_extract_or_null_5 --
+foo\nbar
+
+-- !regexp_extract_or_null_6 --
+aXb
+
+-- !regexp_extract_or_null_7 --
+aXb
+
-- !sql --
['18','17']
@@ -217,6 +247,21 @@ B
-- !sql_regexp_extract_all_5 --
['Case1','Case2','Case3']
+-- !sql_regexp_extract_all_6 --
+['foo\nbar']
+
+-- !sql_regexp_extract_all_7 --
+
+
+-- !sql_regexp_extract_all_8 --
+['foo\nbar']
+
+-- !sql_regexp_extract_all_9 --
+['aXb','cXd']
+
+-- !sql_regexp_extract_all_10 --
+['aXb','cXd']
+
-- !sql --
a-b-c
diff --git
a/regression-test/suites/query_p0/sql_functions/string_functions/test_string_function_regexp.groovy
b/regression-test/suites/query_p0/sql_functions/string_functions/test_string_function_regexp.groovy
index 7c9876d32d6..3a219a2e619 100644
---
a/regression-test/suites/query_p0/sql_functions/string_functions/test_string_function_regexp.groovy
+++
b/regression-test/suites/query_p0/sql_functions/string_functions/test_string_function_regexp.groovy
@@ -76,6 +76,12 @@ suite("test_string_function_regexp") {
qt_regexp_extract_3 'SELECT regexp_extract(\'ID:AA-1,ID:BB-2,ID:CC-3\',
\'(?<=ID:)([A-Z]{2}-\\\\d)(?=,ID|$)\', 1);'
sql "set enable_extended_regex = false;"
+ qt_regexp_extract_4 "SELECT REGEXP_EXTRACT(concat('foo', char(10), 'bar'),
'(foo.bar)', 1);"
+ qt_regexp_extract_5 "SELECT REGEXP_EXTRACT(concat('foo', char(10), 'bar'),
'(?-s)(foo.bar)', 1);"
+ qt_regexp_extract_6 "SELECT REGEXP_EXTRACT(concat('foo', char(10), 'bar'),
'(?s)(foo.bar)', 1);"
+ qt_regexp_extract_7 "SELECT REGEXP_EXTRACT(concat('aXb', char(10), 'cXd'),
'(?-s)(a.b)', 1);"
+ qt_regexp_extract_8 "SELECT REGEXP_EXTRACT(concat('aXb', char(10), 'cXd'),
'(a.b)', 1);"
+
qt_sql "SELECT regexp_extract_or_null('AbCdE',
'([[:lower:]]+)C([[:lower:]]+)', 1);"
qt_sql "SELECT regexp_extract_or_null('AbCdE',
'([[:lower:]]+)C([[:lower:]]+)', 2);"
qt_sql "SELECT regexp_extract_or_null('AbCdE',
'([[:lower:]]+)C([[:lower:]]+)', 3);"
@@ -90,6 +96,12 @@ suite("test_string_function_regexp") {
qt_regexp_extract_or_null_2 "SELECT regexp_extract_or_null('TokenA TokenB
TokenC', '(?<=Token)([A-Z])(?= TokenC)', 1);"
sql "set enable_extended_regex = false;"
+ qt_regexp_extract_or_null_3 "SELECT REGEXP_EXTRACT_OR_NULL(concat('foo',
char(10), 'bar'), '(foo.bar)', 1);"
+ qt_regexp_extract_or_null_4 "SELECT REGEXP_EXTRACT_OR_NULL(concat('foo',
char(10), 'bar'), '(?-s)(foo.bar)', 1);"
+ qt_regexp_extract_or_null_5 "SELECT REGEXP_EXTRACT_OR_NULL(concat('foo',
char(10), 'bar'), '(?s)(foo.bar)', 1);"
+ qt_regexp_extract_or_null_6 "SELECT REGEXP_EXTRACT_OR_NULL(concat('aXb',
char(10), 'cXd'), '(?-s)(a.b)', 1);"
+ qt_regexp_extract_or_null_7 "SELECT REGEXP_EXTRACT_OR_NULL(concat('aXb',
char(10), 'cXd'), '(a.b)', 1);"
+
qt_sql "SELECT regexp_extract_all('x=a3&x=18abc&x=2&y=3&x=4&x=17bcd',
'x=([0-9]+)([a-z]+)');"
qt_sql "SELECT regexp_extract_all('http://a.m.baidu.com/i41915i73660.htm',
'i([0-9]+)');"
qt_sql "SELECT regexp_extract_all('abc=111, def=222, ghi=333',
'(\"[^\"]+\"|\\\\w+)=(\"[^\"]+\"|\\\\w+)');"
@@ -110,6 +122,12 @@ suite("test_string_function_regexp") {
qt_sql_regexp_extract_all_5 'SELECT
REGEXP_EXTRACT_ALL(\'EdgeCase1EdgeCase2EdgeCase3\',
\'(?<=Edge)(Case\\\\d)(?=Edge|$)\');'
sql "set enable_extended_regex = false;"
+ qt_sql_regexp_extract_all_6 "SELECT REGEXP_EXTRACT_ALL(concat('foo',
char(10), 'bar'), '(foo.bar)');"
+ qt_sql_regexp_extract_all_7 "SELECT REGEXP_EXTRACT_ALL(concat('foo',
char(10), 'bar'), '(?-s)(foo.bar)');"
+ qt_sql_regexp_extract_all_8 "SELECT REGEXP_EXTRACT_ALL(concat('foo',
char(10), 'bar'), '(?s)(foo.bar)');"
+ qt_sql_regexp_extract_all_9 "SELECT REGEXP_EXTRACT_ALL(concat('aXb',
char(10), 'cXd'), '(?-s)(\\\\w.\\\\w)');"
+ qt_sql_regexp_extract_all_10 "SELECT REGEXP_EXTRACT_ALL(concat('aXb',
char(10), 'cXd'), '(\\\\w.\\\\w)');"
+
qt_sql "SELECT regexp_replace('a b c', \" \", \"-\");"
qt_sql "SELECT regexp_replace('a b c','(b)','<\\\\1>');"
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
