CHANGELOG, docs

Author: serprex

CHANGELOG.md

@@ -36,6 +36,8 @@ All notable changes to this project will be documented in this file. It uses the
     `&&` (`hasAny`).
 *   Array slice syntax (`arr[L:U]`, `arr[:U]`, `arr[L:]`) now pushes down
     as `arraySlice()`.
+*   Added pushdown for [pg_re2] extension functions to their ClickHouse
+    equivalents (e.g., `re2match` → `match`, `re2extractall` → `extractAll`).
 
 ### ⬆️ Dependency Updates
 
@@ -52,6 +54,8 @@ All notable changes to this project will be documented in this file. It uses the
     `string_to_array(3-arg)` now evaluate locally instead of being pushed to
     ClickHouse where they would fail.
 
+  [pg_re2]: https://github.com/ClickHouse/pg_re2
+    "pg_re2: ClickHouse-compatible regex functions using RE2"
   [v0.1.11]: https://github.com/ClickHouse/pg_clickhouse/compare/v0.1.10...v0.1.11
 
 ## [v0.1.10] — 2026-04-06

META.json

@@ -17,6 +17,9 @@
       "requires": {
         "PostgreSQL": "13.0.0"
       }
+    },
+    "recommends": {
+      "re2": "0.1.0"
     }
   },
   "provides": {

doc/pg_clickhouse.md

@@ -1088,6 +1088,32 @@ any of these functions cannot be pushed down they will raise an exception.
 
 *   [dictGet](https://clickhouse.com/docs/sql-reference/functions/ext-dict-functions#dictget-dictgetordefault-dictgetornull)
 
+### Extension Pushdown
+
+pg_clickhouse recognizes functions from select core and third-party extensions,
+pushing them down to their ClickHouse equivalents.
+
+#### [pg_re2]
+
+All [pg_re2] functions push down 1:1 to ClickHouse:
+
+*   `re2match` → [match](https://clickhouse.com/docs/sql-reference/functions/string-search-functions#match)
+*   `re2extract` → [extract](https://clickhouse.com/docs/sql-reference/functions/string-search-functions#extract)
+*   `re2extractall` → [extractAll](https://clickhouse.com/docs/sql-reference/functions/string-search-functions#extractAll)
+*   `re2regexpextract` → [regexpExtract](https://clickhouse.com/docs/sql-reference/functions/string-search-functions#regexpExtract)
+*   `re2extractgroups` → [extractGroups](https://clickhouse.com/docs/sql-reference/functions/string-search-functions#extractGroups)
+*   `re2replaceregexpone` → [replaceRegexpOne](https://clickhouse.com/docs/sql-reference/functions/string-replace-functions#replaceRegexpOne)
+*   `re2replaceregexpall` → [replaceRegexpAll](https://clickhouse.com/docs/sql-reference/functions/string-replace-functions#replaceRegexpAll)
+*   `re2countmatches` → [countMatches](https://clickhouse.com/docs/sql-reference/functions/string-search-functions#countMatches)
+*   `re2countmatchescaseinsensitive` → [countMatchesCaseInsensitive](https://clickhouse.com/docs/sql-reference/functions/string-search-functions#countMatchesCaseInsensitive)
+*   `re2multimatchany` → [multiMatchAny](https://clickhouse.com/docs/sql-reference/functions/string-search-functions#multiMatchAny)
+*   `re2multimatchanyindex` → [multiMatchAnyIndex](https://clickhouse.com/docs/sql-reference/functions/string-search-functions#multiMatchAnyIndex)
+*   `re2multimatchallindices` → [multiMatchAllIndices](https://clickhouse.com/docs/sql-reference/functions/string-search-functions#multiMatchAllIndices)
+
+#### [intarray]
+
+*   `idx` → [indexOf](https://clickhouse.com/docs/sql-reference/functions/array-functions#indexOf)
+
 ### Pushdown Casts
 
 pg_clickhouse pushes down casts such as `CAST(x AS bigint)` for compatible
@@ -1323,3 +1349,7 @@ Copyright (c) 2025-2026, ClickHouse.
   [Postgres flags]: https://www.postgresql.org/docs/18/functions-matching.html#POSIX-EMBEDDED-OPTIONS-TABLE
     "PostgreSQL Docs: ARE Embedded-Option Letters"
   [RE2 Regular Expressions]: https://github.com/google/re2/wiki/Syntax "RE2 Syntax"
+  [pg_re2]: https://github.com/ClickHouse/pg_re2
+    "pg_re2: ClickHouse-compatible regex functions using RE2"
+  [intarray]: https://www.postgresql.org/docs/current/intarray.html
+    "PostgreSQL Docs: intarray"

test/expected/re2_functions.out

@@ -1,3 +1,5 @@
+SELECT EXISTS(SELECT 1 FROM pg_available_extensions WHERE name = 're2') AS have_re2 \gset
+\if :have_re2
 CREATE SERVER re2_svr FOREIGN DATA WRAPPER clickhouse_fdw OPTIONS(dbname 're2_test');
 CREATE USER MAPPING FOR CURRENT_USER SERVER re2_svr;
 SELECT clickhouse_raw_query('DROP DATABASE IF EXISTS re2_test');
@@ -144,3 +146,6 @@ SELECT clickhouse_raw_query('DROP DATABASE re2_test');
 
 DROP SERVER re2_svr CASCADE;
 NOTICE:  drop cascades to foreign table t1
+\else
+\echo 'SKIP: re2 extension not available'
+\endif

test/expected/re2_functions_1.out

@@ -1,113 +1,42 @@
+SELECT EXISTS(SELECT 1 FROM pg_available_extensions WHERE name = 're2') AS have_re2 \gset
+\if :have_re2
 CREATE SERVER re2_svr FOREIGN DATA WRAPPER clickhouse_fdw OPTIONS(dbname 're2_test');
 CREATE USER MAPPING FOR CURRENT_USER SERVER re2_svr;
 SELECT clickhouse_raw_query('DROP DATABASE IF EXISTS re2_test');
- clickhouse_raw_query 
-----------------------
- 
-(1 row)
-
 SELECT clickhouse_raw_query('CREATE DATABASE re2_test');
- clickhouse_raw_query 
-----------------------
- 
-(1 row)
-
 SELECT clickhouse_raw_query($$
     CREATE TABLE re2_test.t1 (
         id   Int32,
         val  String
     ) ENGINE = MergeTree ORDER BY id
 $$);
- clickhouse_raw_query 
-----------------------
- 
-(1 row)
-
 SELECT clickhouse_raw_query($$
     INSERT INTO re2_test.t1 VALUES
         (1, 'POSIX uses BRE and ERE'),
         (2, 're2 uses finite automata'),
         (3, 'PCRE supports backtracking')
 $$);
- clickhouse_raw_query 
-----------------------
- 
-(1 row)
-
 CREATE SCHEMA re2_test;
 IMPORT FOREIGN SCHEMA re2_test FROM SERVER re2_svr INTO re2_test;
 SET search_path = re2_test, public;
 CREATE EXTENSION re2;
-ERROR:  extension "re2" is not available
-HINT:  The extension must first be installed on the system where PostgreSQL is running.
 EXPLAIN (VERBOSE, COSTS OFF) SELECT * FROM t1 WHERE re2match(val, 're2');
-ERROR:  function re2match(text, unknown) does not exist
-LINE 1: ...PLAIN (VERBOSE, COSTS OFF) SELECT * FROM t1 WHERE re2match(v...
-                                                             ^
-HINT:  No function matches the given name and argument types. You might need to add explicit type casts.
 EXPLAIN (VERBOSE, COSTS OFF) SELECT * FROM t1 WHERE re2extract(val, '(re2)') = 're2';
-ERROR:  function re2extract(text, unknown) does not exist
-LINE 1: ...PLAIN (VERBOSE, COSTS OFF) SELECT * FROM t1 WHERE re2extract...
-                                                             ^
-HINT:  No function matches the given name and argument types. You might need to add explicit type casts.
 EXPLAIN (VERBOSE, COSTS OFF) SELECT * FROM t1 WHERE re2extractall(val, '[A-Z]+') = ARRAY['POSIX','BRE','ERE'];
-ERROR:  function re2extractall(text, unknown) does not exist
-LINE 1: ...PLAIN (VERBOSE, COSTS OFF) SELECT * FROM t1 WHERE re2extract...
-                                                             ^
-HINT:  No function matches the given name and argument types. You might need to add explicit type casts.
 EXPLAIN (VERBOSE, COSTS OFF) SELECT * FROM t1 WHERE re2regexpextract(val, '(re2)', 1) = 're2';
-ERROR:  function re2regexpextract(text, unknown, integer) does not exist
-LINE 1: ...PLAIN (VERBOSE, COSTS OFF) SELECT * FROM t1 WHERE re2regexpe...
-                                                             ^
-HINT:  No function matches the given name and argument types. You might need to add explicit type casts.
 EXPLAIN (VERBOSE, COSTS OFF) SELECT * FROM t1 WHERE re2extractgroups(val, '(POSIX) uses (BRE)') = ARRAY['POSIX','BRE'];
-ERROR:  function re2extractgroups(text, unknown) does not exist
-LINE 1: ...PLAIN (VERBOSE, COSTS OFF) SELECT * FROM t1 WHERE re2extract...
-                                                             ^
-HINT:  No function matches the given name and argument types. You might need to add explicit type casts.
 EXPLAIN (VERBOSE, COSTS OFF) SELECT * FROM t1 WHERE re2replaceregexpone(val, 'POSIX', 're2') = 're2 uses BRE and ERE';
-ERROR:  function re2replaceregexpone(text, unknown, unknown) does not exist
-LINE 1: ...PLAIN (VERBOSE, COSTS OFF) SELECT * FROM t1 WHERE re2replace...
-                                                             ^
-HINT:  No function matches the given name and argument types. You might need to add explicit type casts.
 EXPLAIN (VERBOSE, COSTS OFF) SELECT * FROM t1 WHERE re2replaceregexpall(val, ' ', '-') = 're2-uses-finite-automata';
-ERROR:  function re2replaceregexpall(text, unknown, unknown) does not exist
-LINE 1: ...PLAIN (VERBOSE, COSTS OFF) SELECT * FROM t1 WHERE re2replace...
-                                                             ^
-HINT:  No function matches the given name and argument types. You might need to add explicit type casts.
 EXPLAIN (VERBOSE, COSTS OFF) SELECT * FROM t1 WHERE re2countmatches(val, 'e') > 0;
-ERROR:  function re2countmatches(text, unknown) does not exist
-LINE 1: ...PLAIN (VERBOSE, COSTS OFF) SELECT * FROM t1 WHERE re2countma...
-                                                             ^
-HINT:  No function matches the given name and argument types. You might need to add explicit type casts.
 EXPLAIN (VERBOSE, COSTS OFF) SELECT * FROM t1 WHERE re2countmatchescaseinsensitive(val, 'E') > 0;
-ERROR:  function re2countmatchescaseinsensitive(text, unknown) does not exist
-LINE 1: ...PLAIN (VERBOSE, COSTS OFF) SELECT * FROM t1 WHERE re2countma...
-                                                             ^
-HINT:  No function matches the given name and argument types. You might need to add explicit type casts.
 EXPLAIN (VERBOSE, COSTS OFF) SELECT * FROM t1 WHERE re2multimatchany(val, ARRAY['POSIX','PCRE']);
-ERROR:  function re2multimatchany(text, text[]) does not exist
-LINE 1: ...PLAIN (VERBOSE, COSTS OFF) SELECT * FROM t1 WHERE re2multima...
-                                                             ^
-HINT:  No function matches the given name and argument types. You might need to add explicit type casts.
 EXPLAIN (VERBOSE, COSTS OFF) SELECT * FROM t1 WHERE re2multimatchanyindex(val, ARRAY['POSIX','PCRE']) > 0;
-ERROR:  function re2multimatchanyindex(text, text[]) does not exist
-LINE 1: ...PLAIN (VERBOSE, COSTS OFF) SELECT * FROM t1 WHERE re2multima...
-                                                             ^
-HINT:  No function matches the given name and argument types. You might need to add explicit type casts.
 EXPLAIN (VERBOSE, COSTS OFF) SELECT * FROM t1 WHERE re2multimatchallindices(val, ARRAY['POSIX','PCRE']) = ARRAY[1];
-ERROR:  function re2multimatchallindices(text, text[]) does not exist
-LINE 1: ...PLAIN (VERBOSE, COSTS OFF) SELECT * FROM t1 WHERE re2multima...
-                                                             ^
-HINT:  No function matches the given name and argument types. You might need to add explicit type casts.
 DROP EXTENSION re2;
-ERROR:  extension "re2" does not exist
 DROP USER MAPPING FOR CURRENT_USER SERVER re2_svr;
 SELECT clickhouse_raw_query('DROP DATABASE re2_test');
- clickhouse_raw_query 
-----------------------
- 
-(1 row)
-
 DROP SERVER re2_svr CASCADE;
-NOTICE:  drop cascades to foreign table t1
+\else
+\echo 'SKIP: re2 extension not available'
+SKIP: re2 extension not available
+\endif