parser: sync latest pg regression suite & update create schema parsing

crates/squawk_parser/src/grammar.rs

@@ -12839,11 +12839,6 @@ fn drop_schema(p: &mut Parser<'_>) -> CompletedMarker {
 }
 
 // An SQL statement defining an object to be created within the schema.
-//
-// Currently, only CREATE TABLE, CREATE VIEW, CREATE INDEX, CREATE SEQUENCE,
-// CREATE TRIGGER and GRANT are accepted as clauses within CREATE SCHEMA. Other
-// kinds of objects may be created in separate commands after the schema is
-// created.
 fn opt_schema_elements(p: &mut Parser<'_>) {
     while !p.at(EOF) {
         match (p.current(), p.nth(1)) {
@@ -12864,9 +12859,11 @@ fn opt_schema_elements(p: &mut Parser<'_>) {
             }
             (CREATE_KW, OR_KW) => {
                 match p.nth(3) {
+                    AGGREGATE_KW => create_aggregate(p),
                     CONSTRAINT_KW | TRIGGER_KW => create_trigger(p),
+                    PROCEDURE_KW => create_procedure(p),
                     RECURSIVE_KW | TEMP_KW | TEMPORARY_KW | VIEW_KW => create_view(p),
-                    _ => return,
+                    _ => create_function(p),
                 };
             }
             (CREATE_KW, RECURSIVE_KW | VIEW_KW) => {
@@ -12884,6 +12881,43 @@ fn opt_schema_elements(p: &mut Parser<'_>) {
             (CREATE_KW, INDEX_KW | UNIQUE_KW) => {
                 create_index(p);
             }
+            (CREATE_KW, AGGREGATE_KW) => {
+                create_aggregate(p);
+            }
+            (CREATE_KW, COLLATION_KW) => {
+                create_collation(p);
+            }
+            (CREATE_KW, DOMAIN_KW) => {
+                create_domain(p);
+            }
+            (CREATE_KW, FUNCTION_KW) => {
+                create_function(p);
+            }
+            (CREATE_KW, OPERATOR_KW) => {
+                match p.nth(2) {
+                    CLASS_KW => create_operator_class(p),
+                    FAMILY_KW => create_operator_family(p),
+                    _ => create_operator(p),
+                };
+            }
+            (CREATE_KW, PROCEDURE_KW) => {
+                create_procedure(p);
+            }
+            (CREATE_KW, TEXT_KW) if p.nth_at(2, SEARCH_KW) => {
+                match p.nth(3) {
+                    CONFIGURATION_KW => create_text_search_config(p),
+                    DICTIONARY_KW => create_text_search_dict(p),
+                    PARSER_KW => create_text_search_parser(p),
+                    TEMPLATE_KW => create_text_search_template(p),
+                    _ => return,
+                };
+            }
+            (CREATE_KW, TYPE_KW) => {
+                create_type(p);
+            }
+            (GRANT_KW, _) => {
+                grant(p);
+            }
             _ => return,
         };
     }

crates/squawk_parser/tests/snapshots/tests__regression_compression_pglz.snap

@@ -0,0 +1,5 @@
+---
+source: crates/squawk_parser/tests/tests.rs
+input_file: postgres/regression_suite/compression_pglz.sql
+---
+

crates/squawk_parser/tests/snapshots/tests__regression_database_ddl.snap

@@ -0,0 +1,5 @@
+---
+source: crates/squawk_parser/tests/tests.rs
+input_file: postgres/regression_suite/database_ddl.sql
+---
+

crates/squawk_parser/tests/snapshots/tests__regression_role_ddl.snap

@@ -0,0 +1,5 @@
+---
+source: crates/squawk_parser/tests/tests.rs
+input_file: postgres/regression_suite/role_ddl.sql
+---
+

crates/squawk_parser/tests/snapshots/tests__regression_tablespace_ddl.snap

@@ -0,0 +1,5 @@
+---
+source: crates/squawk_parser/tests/tests.rs
+input_file: postgres/regression_suite/tablespace_ddl.sql
+---
+

postgres/regression_suite/cluster.sql

@@ -248,6 +248,9 @@ REPACK clstrpart;
 CREATE TEMP TABLE new_cluster_info AS SELECT relname, level, relfilenode, relkind FROM pg_partition_tree('clstrpart'::regclass) AS tree JOIN pg_class c ON c.oid=tree.relid ;
 SELECT relname, old.level, old.relkind, old.relfilenode = new.relfilenode FROM old_cluster_info AS old JOIN new_cluster_info AS new USING (relname) ORDER BY relname COLLATE "C";
 
+-- CONCURRENTLY doesn't like partitioned tables
+REPACK (CONCURRENTLY) clstrpart;
+
 DROP TABLE clstrpart;
 
 -- Ownership of partitions is checked
@@ -383,6 +386,9 @@ JOIN relnodes_new n ON o.relname = n.relname
 WHERE o.relfilenode <> n.relfilenode
 ORDER BY o.relname;
 
+-- concurrently
+REPACK (CONCURRENTLY) pg_class;
+
 -- clean up
 DROP TABLE clustertest;
 DROP TABLE clstr_1;

postgres/regression_suite/collate.icu.utf8.sql

@@ -990,6 +990,51 @@ RESET enable_partitionwise_aggregate;
 RESET max_parallel_workers_per_gather;
 RESET enable_incremental_sort;
 
+--
+-- Test for eager aggregation non-deterministic collation bug
+--
+
+CREATE TABLE eager_agg_t1 (id int, val text COLLATE case_insensitive);
+CREATE TABLE eager_agg_t2 (val text COLLATE case_insensitive);
+
+INSERT INTO eager_agg_t1 SELECT 1, 'a' FROM generate_series(1, 50);
+INSERT INTO eager_agg_t1 SELECT 1, 'A' FROM generate_series(1, 50);
+INSERT INTO eager_agg_t2 VALUES ('A');
+
+ANALYZE eager_agg_t1;
+ANALYZE eager_agg_t2;
+
+-- Ensure that eager aggregation is not used for t1.val due to the
+-- non-deterministic collation.
+EXPLAIN (COSTS OFF)
+SELECT t1.id, count(t1.val)
+  FROM eager_agg_t1 t1
+  JOIN eager_agg_t2 t2 ON t1.val = t2.val COLLATE "C"
+GROUP BY t1.id;
+
+-- Ensure it returns 1 row with count = 50
+SELECT t1.id, count(t1.val)
+  FROM eager_agg_t1 t1
+  JOIN eager_agg_t2 t2 ON t1.val = t2.val COLLATE "C"
+GROUP BY t1.id;
+
+-- Ensure that eager aggregation is not used when grouping by a column with
+-- non-deterministic collation.
+EXPLAIN (COSTS OFF)
+SELECT t1.id, t1.val, count(t1.val)
+  FROM eager_agg_t1 t1
+  JOIN eager_agg_t2 t2 ON t1.val = t2.val COLLATE "C"
+GROUP BY t1.id, t1.val;
+
+-- Ensure it returns 1 row with count = 50
+SELECT t1.id, t1.val, count(t1.val)
+  FROM eager_agg_t1 t1
+  JOIN eager_agg_t2 t2 ON t1.val = t2.val COLLATE "C"
+GROUP BY t1.id, t1.val;
+
+DROP TABLE eager_agg_t1;
+DROP TABLE eager_agg_t2;
+
 -- virtual generated columns
 CREATE TABLE t5 (
     a int,

postgres/regression_suite/compression_pglz.sql

@@ -0,0 +1,53 @@
+--
+-- Tests for PGLZ compression
+--
+
+-- directory paths and dlsuffix are passed to us in environment variables
+-- \getenv libdir PG_LIBDIR
+-- \getenv dlsuffix PG_DLSUFFIX
+
+-- \set regresslib :libdir '/regress' :dlsuffix
+
+CREATE FUNCTION test_pglz_compress(bytea)
+  RETURNS bytea
+  AS 'regresslib' LANGUAGE C STRICT;
+CREATE FUNCTION test_pglz_decompress(bytea, int4, bool)
+  RETURNS bytea
+  AS 'regresslib' LANGUAGE C STRICT;
+
+-- Round-trip with pglz: compress then decompress.
+SELECT test_pglz_decompress(test_pglz_compress(
+    decode(repeat('abcd', 100), 'escape')), 400, false) =
+    decode(repeat('abcd', 100), 'escape') AS roundtrip_ok;
+SELECT test_pglz_decompress(test_pglz_compress(
+    decode(repeat('abcd', 100), 'escape')), 400, true) =
+    decode(repeat('abcd', 100), 'escape') AS roundtrip_ok;
+
+-- Decompression with rawsize too large, fails to fill the destination
+-- buffer.
+SELECT test_pglz_decompress(test_pglz_compress(
+    decode(repeat('abcd', 100), 'escape')), 500, true);
+
+-- Decompression with rawsize too small, fails with source not fully
+-- consumed.
+SELECT test_pglz_decompress(test_pglz_compress(
+    decode(repeat('abcd', 100), 'escape')), 100, true);
+
+-- Corrupted compressed data.  Set control bit with read of a match tag,
+-- no data follows.
+SELECT length(test_pglz_decompress('\x01'::bytea, 1024, false)) AS ctrl_only_len;
+SELECT test_pglz_decompress('\x01'::bytea, 1024, true);
+
+-- Corrupted compressed data.  Set control bit with read of a match tag,
+-- 1 byte follows.
+SELECT test_pglz_decompress('\x01ff'::bytea, 1024, false);
+SELECT test_pglz_decompress('\x01ff'::bytea, 1024, true);
+
+-- Corrupted compressed data.  Set control bit with match tag where length
+-- nibble is 3 bytes (extended length), no data follows.
+SELECT test_pglz_decompress('\x010f01'::bytea, 1024, false);
+SELECT test_pglz_decompress('\x010f01'::bytea, 1024, true);
+
+-- Clean up
+DROP FUNCTION test_pglz_compress;
+DROP FUNCTION test_pglz_decompress;

postgres/regression_suite/conversion.sql

@@ -329,7 +329,6 @@ select description, inbytes, (test_conv(inbytes, 'iso8859-5', 'iso8859-5')).* fr
 -- Test conversions from ISO-8859-5
 select description, inbytes, (test_conv(inbytes, 'iso8859-5', 'utf8')).* from iso8859_5_inputs;
 select description, inbytes, (test_conv(inbytes, 'iso8859-5', 'koi8r')).* from iso8859_5_inputs;
-select description, inbytes, (test_conv(inbytes, 'iso8859_5', 'mule_internal')).* from iso8859_5_inputs;
 
 --
 -- Big5
@@ -346,29 +345,3 @@ insert into big5_inputs  values
 select description, inbytes, (test_conv(inbytes, 'big5', 'big5')).* from big5_inputs;
 -- Test conversions from Big5
 select description, inbytes, (test_conv(inbytes, 'big5', 'utf8')).* from big5_inputs;
-select description, inbytes, (test_conv(inbytes, 'big5', 'mule_internal')).* from big5_inputs;
-
---
--- MULE_INTERNAL
---
-CREATE TABLE mic_inputs (inbytes bytea, description text);
-insert into mic_inputs  values
-  ('\x666f6f',		'valid, pure ASCII'),
-  ('\x8bc68bcf8bcf',	'valid (in KOI8R)'),
-  ('\x8bc68bcf8b',	'invalid,incomplete char'),
-  ('\x92bedd',		'valid (in SHIFT_JIS)'),
-  ('\x92be',		'invalid, incomplete char)'),
-  ('\x666f6f95a3c1',	'valid (in Big5)'),
-  ('\x666f6f95a3',	'invalid, incomplete char'),
-  ('\x9200bedd',	'invalid, NUL byte'),
-  ('\x92bedd00',	'invalid, NUL byte'),
-  ('\x8b00c68bcf8bcf',	'invalid, NUL byte');
-
--- Test MULE_INTERNAL verification
-select description, inbytes, (test_conv(inbytes, 'mule_internal', 'mule_internal')).* from mic_inputs;
--- Test conversions from MULE_INTERNAL
-select description, inbytes, (test_conv(inbytes, 'mule_internal', 'koi8r')).* from mic_inputs;
-select description, inbytes, (test_conv(inbytes, 'mule_internal', 'iso8859-5')).* from mic_inputs;
-select description, inbytes, (test_conv(inbytes, 'mule_internal', 'sjis')).* from mic_inputs;
-select description, inbytes, (test_conv(inbytes, 'mule_internal', 'big5')).* from mic_inputs;
-select description, inbytes, (test_conv(inbytes, 'mule_internal', 'euc_jp')).* from mic_inputs;

postgres/regression_suite/copy2.sql

@@ -168,6 +168,8 @@ COPY x from stdin WHERE a IN (generate_series(1,5));
 -- 
 COPY x from stdin WHERE a = row_number() over(b);
 -- 
+COPY x from stdin WHERE tableoid = 'x'::regclass;
+-- 
 -- 
 -- -- check results of copy in
 SELECT * FROM x;