Merge pull request #52840 from hanfei1991/hanfei/analyze-named-group

make regexp analyzer recognize named capturing groups
ClickHouse · Aug 1, 2023 · d900486 · d900486
2 parents c681405 + 7aecec8
commit d900486
Show file tree

Hide file tree

Showing 4 changed files with 30 additions and 0 deletions.
diff --git a/src/Common/OptimizedRegularExpression.cpp b/src/Common/OptimizedRegularExpression.cpp
@@ -45,6 +45,25 @@ size_t shortest_literal_length(const Literals & literals)
     return shortest;
 }
 
+const char * skipNameCapturingGroup(const char * pos, size_t offset, const char * end)
+{
+    const char special = *(pos + offset) == '<' ? '>' : '\'';
+    offset ++;
+    while (pos + offset < end)
+    {
+        const char cur = *(pos + offset);
+        if (cur == special)
+        {
+            return pos + offset;
+        }
+        if (('0' <= cur && cur <= '9') || ('a' <= cur && cur <= 'z') || ('A' <= cur && cur <= 'Z'))
+            offset ++;
+        else
+            return pos;
+    }
+    return pos;
+}
+
 const char * analyzeImpl(
     std::string_view regexp,
     const char * pos,
@@ -247,10 +266,15 @@ const char * analyzeImpl(
                                 break;
                         }
                     }
+                    /// (?:regex) means non-capturing parentheses group
                     if (pos + 2 < end && pos[1] == '?' && pos[2] == ':')
                     {
                         pos += 2;
                     }
+                    if (pos + 3 < end && pos[1] == '?' && (pos[2] == '<' || pos[2] == '\'' || (pos[2] == 'P' && pos[3] == '<')))
+                    {
+                        pos = skipNameCapturingGroup(pos, pos[2] == 'P' ? 3: 2, end);
+                    }
                     Literal group_required_substr;
                     bool group_is_trival = true;
                     Literals group_alters;

diff --git a/src/Common/tests/gtest_optimize_re.cpp b/src/Common/tests/gtest_optimize_re.cpp
@@ -47,4 +47,8 @@ TEST(OptimizeRE, analyze)
     test_f("abc|(:?xx|yy|zz|x?)def", "", {"abc", "def"});
     test_f("abc|(:?xx|yy|zz|x?){1,2}def", "", {"abc", "def"});
     test_f(R"(\\A(?:(?:[-0-9_a-z]+(?:\\.[-0-9_a-z]+)*)/k8s1)\\z)", "/k8s1");
+    test_f("[a-zA-Z]+(?P<num>\\d+)", "");
+    test_f("[a-zA-Z]+(?<num>\\d+)", "");
+    test_f("[a-zA-Z]+(?'num'\\d+)", "");
+    test_f("[a-zA-Z]+(?x<num>\\d+)", "x<num>");
 }
diff --git a/tests/queries/0_stateless/02751_match_constant_needle.reference b/tests/queries/0_stateless/02751_match_constant_needle.reference
@@ -1 +1,2 @@
 1
+1
diff --git a/tests/queries/0_stateless/02751_match_constant_needle.sql b/tests/queries/0_stateless/02751_match_constant_needle.sql
@@ -1 +1,2 @@
 select match('default/k8s1', '\\A(?:(?:[-0-9_a-z]+(?:\\.[-0-9_a-z]+)*)/k8s1)\\z');
+select match('abc123', '[a-zA-Z]+(?P<num>\\d+)');