parser: pg regression suite tidying (#515)

Now we keep snapshots of the errors as well as having a test keep track of files that have errors and the error count.

We can gradually burn down the files & error counts!


Also fix a few panics that the regression suite had with select

Author: sbdchd

.github/workflows/rust.yml

@@ -388,6 +388,9 @@ jobs:
       - name: Cache
         uses: Swatinem/rust-cache@9d47c6ad4b02e050fd481d890b2ea34778fd09d6 # pin@v2
 
+      - name: Install ripgrep
+        run: cargo install ripgrep
+
       - name: Test
         run: ./s/test
 

Cargo.lock

@@ -20,6 +20,7 @@ insta.workspace = true
 dir-test.workspace = true
 camino.workspace = true
 pg_query.workspace = true
+xshell.workspace = true
 
 [lints]
 workspace = true

crates/squawk_parser/Cargo.toml

@@ -4163,8 +4163,8 @@ const EXPR_FIRST: TokenSet = LHS_FIRST;
 const ATTRIBUTE_FIRST: TokenSet = TokenSet::new(&[POUND, GROUP_KW]);
 
 const TARGET_FOLLOW: TokenSet = TokenSet::new(&[
-    FROM_KW, WHERE_KW, LIMIT_KW, ORDER_KW, OFFSET_KW, GROUP_KW, HAVING_KW, WINDOW_KW, HAVING_KW,
-    FETCH_KW, FOR_KW, R_PAREN, R_BRACK,
+    SELECT_KW, FROM_KW, WHERE_KW, LIMIT_KW, ORDER_KW, OFFSET_KW, GROUP_KW, INTO_KW, HAVING_KW,
+    WINDOW_KW, HAVING_KW, FETCH_KW, FOR_KW, R_PAREN, R_BRACK,
 ])
 .union(COMPOUND_SELECT_FIRST);
 
@@ -4216,7 +4216,7 @@ fn opt_as_col_label(p: &mut Parser<'_>) -> bool {
 }
 
 fn opt_target_list(p: &mut Parser) -> Option<CompletedMarker> {
-    if !p.at_ts(TARGET_LIST_START) || p.at(SELECT_KW) {
+    if !p.at_ts(TARGET_LIST_START) || p.at_ts(TARGET_FOLLOW) {
         return None;
     }
     let m = p.start();

crates/squawk_parser/src/grammar.rs

@@ -127,6 +127,9 @@ select json_array(a absent on null);
 select json_array(a absent on null returning foo format json);
 select json_array(1, true, json '{"a":null}');
 select json_array(1, b, '3' format json, 4);
+-- regression test
+select json_array(select from t);
+select json_array(select into t from u);
 
 -- query_expression
 select json_array(select 1);

crates/squawk_parser/tests/data/ok/select_funcs.sql

@@ -0,0 +1,17 @@
+---
+source: crates/squawk_parser/tests/tests.rs
+input_file: crates/squawk_parser/tests/data/regression_suite/alter_generic.sql
+---
+ERROR@15151: expected R_PAREN
+ERROR@15152: expected OPERATOR, or FUNCTION
+ERROR@15152: expected SEMICOLON
+ERROR@15153: expected command, found IDENT
+ERROR@15157: expected command, found R_PAREN
+ERROR@21020: expected type name
+ERROR@21020: expected R_PAREN
+ERROR@21020: expected SEMICOLON
+ERROR@21020: expected command, found L_BRACK
+ERROR@21021: expected command, found R_BRACK
+ERROR@21022: expected command, found COMMA
+ERROR@21024: expected command, found IDENT
+ERROR@21028: expected command, found R_PAREN

crates/squawk_parser/tests/snapshots/.gitignore

@@ -0,0 +1,140 @@
+---
+source: crates/squawk_parser/tests/tests.rs
+input_file: crates/squawk_parser/tests/data/regression_suite/alter_table.sql
+---
+ERROR@12719: expected VALID_KW
+ERROR@12719: expected SEMICOLON
+ERROR@12720: expected command, found ENFORCED_KW
+ERROR@15268: expected R_PAREN
+ERROR@15268: expected SEMICOLON
+ERROR@15269: expected command, found NOT_KW
+ERROR@15273: expected command, found VALID_KW
+ERROR@15278: expected command, found R_PAREN
+ERROR@33822: expected FOREIGN_KW
+ERROR@33822: expected KEY_KW
+ERROR@33822: expected column list
+ERROR@33822: expected REFERENCES_KW
+ERROR@33826: expected SEMICOLON
+ERROR@33827: expected command, found NULL_KW
+ERROR@33832: expected command, found IDENT
+ERROR@33835: expected command, found NOT_KW
+ERROR@33839: expected command, found VALID_KW
+ERROR@33940: expected FOREIGN_KW
+ERROR@33940: expected KEY_KW
+ERROR@33940: expected column list
+ERROR@33940: expected REFERENCES_KW
+ERROR@33944: expected SEMICOLON
+ERROR@33945: expected command, found NULL_KW
+ERROR@33950: expected command, found IDENT
+ERROR@38443: expected L_PAREN
+ERROR@38448: expected R_PAREN
+ERROR@38448: expected SEMICOLON
+ERROR@38449: expected command, found OIDS_KW
+ERROR@42440: expected command, found INT_NUMBER
+ERROR@42443: expected command, found INT_NUMBER
+ERROR@42446: expected command, found INT_NUMBER
+ERROR@42495: expected command, found INT_NUMBER
+ERROR@42498: expected command, found INT_NUMBER
+ERROR@42635: expected command, found INT_NUMBER
+ERROR@42638: expected command, found INT_NUMBER
+ERROR@43987: expected NULL_KW
+ERROR@43987: expected SEMICOLON
+ERROR@43988: expected command, found ENFORCED_KW
+ERROR@44078: expected NULL_KW
+ERROR@44078: expected SEMICOLON
+ERROR@44079: expected command, found ENFORCED_KW
+ERROR@44088: expected command, found ENFORCED_KW
+ERROR@67262: expected type name
+ERROR@67262: expected SEMICOLON
+ERROR@67262: expected command, found DOT
+ERROR@67263: expected command, found IDENT
+ERROR@67270: expected command, found INTEGER_KW
+ERROR@67278: expected command, found CHECK_KW
+ERROR@67284: expected command, found L_PAREN
+ERROR@67285: expected command, found VALUE_KW
+ERROR@67291: expected command, found R_ANGLE
+ERROR@67293: expected command, found INT_NUMBER
+ERROR@67294: expected command, found R_PAREN
+ERROR@67380: expected R_PAREN
+ERROR@67380: expected function option
+ERROR@67380: expected SEMICOLON
+ERROR@67380: expected command, found DOT
+ERROR@67381: expected command, found IDENT
+ERROR@67386: expected command, found COMMA
+ERROR@67388: expected command, found IDENT
+ERROR@67394: expected command, found DOT
+ERROR@67395: expected command, found IDENT
+ERROR@67400: expected command, found R_PAREN
+ERROR@67402: expected command, found RETURNS_KW
+ERROR@67410: expected command, found BOOLEAN_KW
+ERROR@67418: expected command, found LANGUAGE_KW
+ERROR@67427: expected command, found SQL_KW
+ERROR@67431: expected command, found AS_KW
+ERROR@67434: expected command, found STRING
+ERROR@68763: expected R_PAREN
+ERROR@68763: expected function option
+ERROR@68763: expected SEMICOLON
+ERROR@68763: expected command, found DOT
+ERROR@68764: expected command, found IDENT
+ERROR@68769: expected command, found COMMA
+ERROR@68771: expected command, found IDENT
+ERROR@68777: expected command, found DOT
+ERROR@68778: expected command, found IDENT
+ERROR@68783: expected command, found R_PAREN
+ERROR@68795: expected EQ
+ERROR@71700: expected type name
+ERROR@74909: expected FOREIGN_KW
+ERROR@74909: expected KEY_KW
+ERROR@74909: expected column list
+ERROR@74909: expected REFERENCES_KW
+ERROR@74913: expected R_PAREN
+ERROR@74913: expected SEMICOLON
+ERROR@74914: expected command, found NULL_KW
+ERROR@74919: expected command, found IDENT
+ERROR@74921: expected command, found COMMA
+ERROR@74925: expected command, found IDENT
+ERROR@74938: expected command, found INT_KW
+ERROR@74942: expected command, found CHECK_KW
+ERROR@74948: expected command, found L_PAREN
+ERROR@74949: expected command, found IDENT
+ERROR@74962: expected command, found R_ANGLE
+ERROR@74964: expected command, found INT_NUMBER
+ERROR@74965: expected command, found R_PAREN
+ERROR@74966: expected command, found COMMA
+ERROR@74970: expected command, found IDENT
+ERROR@74982: expected command, found INT_KW
+ERROR@74985: expected command, found COMMA
+ERROR@74989: expected command, found CONSTRAINT_KW
+ERROR@75000: expected command, found IDENT
+ERROR@75016: expected command, found PRIMARY_KW
+ERROR@75024: expected command, found KEY_KW
+ERROR@75028: expected command, found L_PAREN
+ERROR@75029: expected command, found IDENT
+ERROR@75031: expected command, found R_PAREN
+ERROR@75032: expected command, found R_PAREN
+ERROR@86438: expected name
+ERROR@86438: expected type name
+ERROR@86447: expected SEMICOLON
+ERROR@86448: expected command, found IDENT
+ERROR@91452: expected R_PAREN
+ERROR@91452: expected SEMICOLON
+ERROR@91453: expected command, found NO_KW
+ERROR@91456: expected command, found INHERIT_KW
+ERROR@91463: expected command, found COMMA
+ERROR@91466: expected command, found IDENT
+ERROR@91468: expected command, found CHAR_KW
+ERROR@91472: expected command, found L_PAREN
+ERROR@91473: expected command, found INT_NUMBER
+ERROR@91474: expected command, found R_PAREN
+ERROR@91476: expected command, found COLLATE_KW
+ERROR@91484: expected command, found IDENT
+ERROR@91487: expected command, found COMMA
+ERROR@91490: expected command, found CONSTRAINT_KW
+ERROR@91501: expected command, found IDENT
+ERROR@91509: expected command, found CHECK_KW
+ERROR@91515: expected command, found L_PAREN
+ERROR@91516: expected command, found IDENT
+ERROR@91518: expected command, found R_ANGLE
+ERROR@91520: expected command, found INT_NUMBER
+ERROR@91521: expected command, found R_PAREN
+ERROR@91523: expected command, found R_PAREN