From 1326bffe606b92e5501db0d62668234005b7790b Mon Sep 17 00:00:00 2001
From: Alexey Milovidov <milovidov@clickhouse.com>
Date: Sat, 23 Sep 2023 04:14:03 +0200
Subject: [PATCH] Allow LIKE over binary data

---
 src/Common/OptimizedRegularExpression.cpp     |  8 ++++++
 .../0_stateless/02886_binary_like.reference   | 24 +++++++++++++++++
 .../queries/0_stateless/02886_binary_like.sql | 26 +++++++++++++++++++
 3 files changed, 58 insertions(+)
 create mode 100644 tests/queries/0_stateless/02886_binary_like.reference
 create mode 100644 tests/queries/0_stateless/02886_binary_like.sql

diff --git a/src/Common/OptimizedRegularExpression.cpp b/src/Common/OptimizedRegularExpression.cpp
index 3501a355c19..d64b26a28a3 100644
--- a/src/Common/OptimizedRegularExpression.cpp
+++ b/src/Common/OptimizedRegularExpression.cpp
@@ -496,6 +496,14 @@ OptimizedRegularExpression::OptimizedRegularExpression(const std::string & regex
             regexp_options.set_dot_nl(true);
 
         re2 = std::make_unique<re2::RE2>(regexp_, regexp_options);
+
+        /// Fallback to latin1 to allow matching binary data.
+        if (!re2->ok() && re2->error_code() == re2::RE2::ErrorCode::ErrorBadUTF8)
+        {
+            regexp_options.set_encoding(re2::RE2::Options::EncodingLatin1);
+            re2 = std::make_unique<re2::RE2>(regexp_, regexp_options);
+        }
+
         if (!re2->ok())
         {
             throw DB::Exception(DB::ErrorCodes::CANNOT_COMPILE_REGEXP,
diff --git a/tests/queries/0_stateless/02886_binary_like.reference b/tests/queries/0_stateless/02886_binary_like.reference
new file mode 100644
index 00000000000..c23ceaf9784
--- /dev/null
+++ b/tests/queries/0_stateless/02886_binary_like.reference
@@ -0,0 +1,24 @@
+1
+1
+1
+1
+1
+0
+0
+1
+1
+1
+1
+1
+1
+0
+0
+1
+1
+1
+1
+1
+1
+0
+0
+1
diff --git a/tests/queries/0_stateless/02886_binary_like.sql b/tests/queries/0_stateless/02886_binary_like.sql
new file mode 100644
index 00000000000..ba11f1fc060
--- /dev/null
+++ b/tests/queries/0_stateless/02886_binary_like.sql
@@ -0,0 +1,26 @@
+SELECT 'aяb' LIKE 'a_b';
+SELECT 'a\0b' LIKE 'a_b';
+SELECT 'a\0b' LIKE 'a\0b';
+SELECT 'a\0b' LIKE 'a%\0b';
+SELECT 'a\xFFb' LIKE 'a%\xFFb';
+SELECT 'a\xFFb' LIKE 'a%\xFF\xFEb';
+SELECT 'a\xFFb' LIKE '%a\xFF\xFEb';
+SELECT 'a\xFF\xFEb' LIKE '%a\xFF\xFEb';
+
+SELECT materialize('aяb') LIKE 'a_b';
+SELECT materialize('a\0b') LIKE 'a_b';
+SELECT materialize('a\0b') LIKE 'a\0b';
+SELECT materialize('a\0b') LIKE 'a%\0b';
+SELECT materialize('a\xFFb') LIKE 'a%\xFFb';
+SELECT materialize('a\xFFb') LIKE 'a%\xFF\xFEb';
+SELECT materialize('a\xFFb') LIKE '%a\xFF\xFEb';
+SELECT materialize('a\xFF\xFEb') LIKE '%a\xFF\xFEb';
+
+SELECT materialize('aяb') LIKE materialize('a_b');
+SELECT materialize('a\0b') LIKE materialize('a_b');
+SELECT materialize('a\0b') LIKE materialize('a\0b');
+SELECT materialize('a\0b') LIKE materialize('a%\0b');
+SELECT materialize('a\xFFb') LIKE materialize('a%\xFFb');
+SELECT materialize('a\xFFb') LIKE materialize('a%\xFF\xFEb');
+SELECT materialize('a\xFFb') LIKE materialize('%a\xFF\xFEb');
+SELECT materialize('a\xFF\xFEb') LIKE materialize('%a\xFF\xFEb');