This is an automated email from the ASF dual-hosted git repository.
jianliangqi 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 43f00507d29 [fix](inverted index) Fix match_regexp to correctly handle
empty string patterns (#39503)
43f00507d29 is described below
commit 43f00507d29233b00c9654bbdd3dc52916b830f6
Author: zzzxl <[email protected]>
AuthorDate: Thu Aug 22 15:42:10 2024 +0800
[fix](inverted index) Fix match_regexp to correctly handle empty string
patterns (#39503)
1. Handle empty strings consistently for match_phrase with and without an
index.
---
be/src/vec/functions/match.cpp | 9 ---------
.../data/inverted_index_p0/test_index_match_regexp.out | 3 +++
regression-test/data/inverted_index_p0/test_no_index_match.out | 3 +++
.../suites/inverted_index_p0/test_index_match_regexp.groovy | 1 +
.../suites/inverted_index_p0/test_no_index_match.groovy | 2 ++
5 files changed, 9 insertions(+), 9 deletions(-)
diff --git a/be/src/vec/functions/match.cpp b/be/src/vec/functions/match.cpp
index e21e467d096..a506dfac325 100644
--- a/be/src/vec/functions/match.cpp
+++ b/be/src/vec/functions/match.cpp
@@ -406,15 +406,6 @@ Status FunctionMatchRegexp::execute_match(FunctionContext*
context, const std::s
VLOG_DEBUG << "begin to run FunctionMatchRegexp::execute_match,
parser_type: "
<<
inverted_index_parser_type_to_string(inverted_index_ctx->parser_type);
- if (match_query_str.empty()) {
- VLOG_DEBUG << fmt::format(
- "token parser result is empty for query, "
- "please check your query: '{}' and index parser: '{}'",
- match_query_str,
-
inverted_index_parser_type_to_string(inverted_index_ctx->parser_type));
- return Status::OK();
- }
-
const std::string& pattern = match_query_str;
hs_database_t* database = nullptr;
diff --git a/regression-test/data/inverted_index_p0/test_index_match_regexp.out
b/regression-test/data/inverted_index_p0/test_index_match_regexp.out
index f9a9caf6d74..fb5d23ad266 100644
--- a/regression-test/data/inverted_index_p0/test_index_match_regexp.out
+++ b/regression-test/data/inverted_index_p0/test_index_match_regexp.out
@@ -2,6 +2,9 @@
-- !sql --
1000
+-- !sql --
+1000
+
-- !sql --
54
diff --git a/regression-test/data/inverted_index_p0/test_no_index_match.out
b/regression-test/data/inverted_index_p0/test_no_index_match.out
index 932dd55fc5a..ea3bd71bcd6 100644
--- a/regression-test/data/inverted_index_p0/test_no_index_match.out
+++ b/regression-test/data/inverted_index_p0/test_no_index_match.out
@@ -20,3 +20,6 @@
-- !sql --
0
+-- !sql --
+1000
+
diff --git
a/regression-test/suites/inverted_index_p0/test_index_match_regexp.groovy
b/regression-test/suites/inverted_index_p0/test_index_match_regexp.groovy
index 3458f086740..31863432707 100644
--- a/regression-test/suites/inverted_index_p0/test_index_match_regexp.groovy
+++ b/regression-test/suites/inverted_index_p0/test_index_match_regexp.groovy
@@ -80,6 +80,7 @@ suite("test_index_match_regexp", "p0"){
sql "sync"
+ qt_sql """ select count() from test_index_match_regexp where request
match_regexp ''; """
qt_sql """ select count() from test_index_match_regexp where request
match_regexp '^h'; """
qt_sql """ select count() from test_index_match_regexp where request
match_regexp '^team'; """
qt_sql """ select count() from test_index_match_regexp where request
match_regexp 's\$'; """
diff --git
a/regression-test/suites/inverted_index_p0/test_no_index_match.groovy
b/regression-test/suites/inverted_index_p0/test_no_index_match.groovy
index 2df40235a3f..7947844565c 100644
--- a/regression-test/suites/inverted_index_p0/test_no_index_match.groovy
+++ b/regression-test/suites/inverted_index_p0/test_no_index_match.groovy
@@ -94,6 +94,8 @@ suite("test_no_index_match", "p0") {
qt_sql """ select count() from ${testTable} where (request
match_phrase '欧冶工业品'); """
qt_sql """ select count() from ${testTable} where (request
match_phrase_prefix '欧冶工业品'); """
+
+ qt_sql """ select count() from ${testTable} where (request
match_regexp ''); """
} finally {
}
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
