Additional PL/pgSQL parsing fixes

scripts/extract_source.rb

@@ -544,6 +544,8 @@ def write_out
 		} else if (list_length(origtypname->names) == 2) {
 			ns = linitial_node(String, origtypname->names)->sval;
 			ident = lsecond_node(String, origtypname->names)->sval;
+			if (strcmp(ns, "pg_catalog") != 0)
+				typ->ttype = PLPGSQL_TTYPE_REC;
 		}
 	} else {
 		typ->typoid = typeOid;
@@ -570,8 +572,31 @@ def write_out
 	return typ;
 }
 ))
-runner.mock('parse_datatype', 'static PLpgSQL_type * parse_datatype(const char *string, int location) { PLpgSQL_type *typ; typ = (PLpgSQL_type *) palloc0(sizeof(PLpgSQL_type)); typ->typname = pstrdup(string); typ->ttype = strcmp(string, "RECORD") == 0 ? PLPGSQL_TTYPE_REC : PLPGSQL_TTYPE_SCALAR; return typ; }')
-runner.mock('get_collation_oid', 'Oid get_collation_oid(List *name, bool missing_ok) { return -1; }')
+runner.mock('parse_datatype', %(
+#include "catalog/pg_collation_d.h"
+static PLpgSQL_type * parse_datatype(const char *string, int location) {
+	PLpgSQL_type *typ;
+
+	/* Ignore trailing spaces */
+	size_t len = strlen(string);
+	while (len > 0 && scanner_isspace(string[len - 1])) --len;
+
+	typ = (PLpgSQL_type *) palloc0(sizeof(PLpgSQL_type));
+	typ->typname = pstrdup(string);
+	typ->ttype = pg_strncasecmp(string, "RECORD", len) == 0 ? PLPGSQL_TTYPE_REC : PLPGSQL_TTYPE_SCALAR;
+	if (pg_strncasecmp(string, "REFCURSOR", len) == 0 || pg_strncasecmp(string, "CURSOR", len) == 0)
+	{
+		typ->typoid = REFCURSOROID;
+	}
+	else if (pg_strncasecmp(string, "TEXT", len) == 0)
+	{
+		typ->typoid = TEXTOID;
+		typ->collation = DEFAULT_COLLATION_OID;
+	}
+	return typ;
+}
+))
+runner.mock('get_collation_oid', 'Oid get_collation_oid(List *name, bool missing_ok) { return DEFAULT_COLLATION_OID; }')
 runner.mock('plpgsql_parse_wordtype', 'PLpgSQL_type * plpgsql_parse_wordtype(char *ident) { return NULL; }')
 runner.mock('plpgsql_parse_wordrowtype', 'PLpgSQL_type * plpgsql_parse_wordrowtype(char *ident) { return NULL; }')
 runner.mock('plpgsql_parse_cwordtype', 'PLpgSQL_type * plpgsql_parse_cwordtype(List *idents) { return NULL; }')
@@ -665,6 +690,7 @@ def write_out
 
 # Other required functions
 runner.deep_resolve('pg_printf')
+runner.deep_resolve('pg_strncasecmp')
 
 # Retain these functions for optional 32-bit support
 # (see BITS_PER_BITMAPWORD checks in bitmapset.c)

src/pg_query_parse_plpgsql.c

@@ -219,20 +219,19 @@ static PLpgSQL_function *compile_create_function_stmt(CreateFunctionStmt* stmt)
 	foreach(lc, stmt->parameters)
 	{
 		FunctionParameter *param = lfirst_node(FunctionParameter, lc);
+		char buf[32];
+		PLpgSQL_type *argdtype;
+		PLpgSQL_variable *argvariable;
+		PLpgSQL_nsitem_type argitemtype;
+		snprintf(buf, sizeof(buf), "$%d", foreach_current_index(lc) + 1);
+		argdtype = plpgsql_build_datatype(UNKNOWNOID, -1, InvalidOid, param->argType);
+		argvariable = plpgsql_build_variable(param->name ? param->name : buf, 0, argdtype, false);
+		if (param->mode == FUNC_PARAM_OUT || param->mode == FUNC_PARAM_INOUT || param->mode == FUNC_PARAM_TABLE)
+			function->out_param_varno = argvariable->dno;
+		argitemtype = argvariable->dtype == PLPGSQL_DTYPE_VAR ? PLPGSQL_NSTYPE_VAR : PLPGSQL_NSTYPE_REC;
+		plpgsql_ns_additem(argitemtype, argvariable->dno, buf);
 		if (param->name != NULL)
-		{
-			char buf[32];
-			PLpgSQL_type *argdtype;
-			PLpgSQL_variable *argvariable;
-			PLpgSQL_nsitem_type argitemtype;
-			snprintf(buf, sizeof(buf), "$%d", foreach_current_index(lc) + 1);
-			argdtype = plpgsql_build_datatype(UNKNOWNOID, -1, InvalidOid, param->argType);
-			argvariable = plpgsql_build_variable(param->name ? param->name : buf, 0, argdtype, false);
-			argitemtype = argvariable->dtype == PLPGSQL_DTYPE_VAR ? PLPGSQL_NSTYPE_VAR : PLPGSQL_NSTYPE_REC;
-			plpgsql_ns_additem(argitemtype, argvariable->dno, buf);
-			if (param->name != NULL)
-				plpgsql_ns_additem(argitemtype, argvariable->dno, param->name);
-		}
+			plpgsql_ns_additem(argitemtype, argvariable->dno, param->name);
 	}
 
 	/* Set up as though in a function returning VOID */

src/postgres/src_backend_catalog_namespace.c

@@ -905,7 +905,7 @@ NameListToString(List *names)
  * Note that this will only find collations that work with the current
  * database's encoding.
  */
-Oid get_collation_oid(List *name, bool missing_ok) { return -1; }
+Oid get_collation_oid(List *name, bool missing_ok) { return DEFAULT_COLLATION_OID; }
 
 
 /*

src/postgres/src_pl_plpgsql_src_pl_comp.c

@@ -898,6 +898,8 @@ PLpgSQL_type * plpgsql_build_datatype(Oid typeOid, int32 typmod, Oid collation,
 		} else if (list_length(origtypname->names) == 2) {
 			ns = linitial_node(String, origtypname->names)->sval;
 			ident = lsecond_node(String, origtypname->names)->sval;
+			if (strcmp(ns, "pg_catalog") != 0)
+				typ->ttype = PLPGSQL_TTYPE_REC;
 		}
 	} else {
 		typ->typoid = typeOid;

src/postgres/src_pl_plpgsql_src_pl_gram.c

@@ -6090,7 +6090,30 @@ plpgsql_sql_error_callback(void *arg)
  * This is handled the same as in check_sql_expr(), and we likewise
  * expect that the given string is a copy from the source text.
  */
-static PLpgSQL_type * parse_datatype(const char *string, int location) { PLpgSQL_type *typ; typ = (PLpgSQL_type *) palloc0(sizeof(PLpgSQL_type)); typ->typname = pstrdup(string); typ->ttype = strcmp(string, "RECORD") == 0 ? PLPGSQL_TTYPE_REC : PLPGSQL_TTYPE_SCALAR; return typ; }
+
+#include "catalog/pg_collation_d.h"
+static PLpgSQL_type * parse_datatype(const char *string, int location) {
+	PLpgSQL_type *typ;
+
+	/* Ignore trailing spaces */
+	size_t len = strlen(string);
+	while (len > 0 && scanner_isspace(string[len - 1])) --len;
+
+	typ = (PLpgSQL_type *) palloc0(sizeof(PLpgSQL_type));
+	typ->typname = pstrdup(string);
+	typ->ttype = pg_strncasecmp(string, "RECORD", len) == 0 ? PLPGSQL_TTYPE_REC : PLPGSQL_TTYPE_SCALAR;
+	if (pg_strncasecmp(string, "REFCURSOR", len) == 0 || pg_strncasecmp(string, "CURSOR", len) == 0)
+	{
+		typ->typoid = REFCURSOROID;
+	}
+	else if (pg_strncasecmp(string, "TEXT", len) == 0)
+	{
+		typ->typoid = TEXTOID;
+		typ->collation = DEFAULT_COLLATION_OID;
+	}
+	return typ;
+}
+
 
 
 /*

src/postgres/src_port_pgstrcasecmp.c

@@ -2,6 +2,7 @@
  * Symbols referenced in this file:
  * - pg_strcasecmp
  * - pg_toupper
+ * - pg_strncasecmp
  *--------------------------------------------------------------------
  */
 
@@ -72,7 +73,34 @@ pg_strcasecmp(const char *s1, const char *s2)
  * Case-independent comparison of two not-necessarily-null-terminated strings.
  * At most n bytes will be examined from each string.
  */
+int
+pg_strncasecmp(const char *s1, const char *s2, size_t n)
+{
+	while (n-- > 0)
+	{
+		unsigned char ch1 = (unsigned char) *s1++;
+		unsigned char ch2 = (unsigned char) *s2++;
 
+		if (ch1 != ch2)
+		{
+			if (ch1 >= 'A' && ch1 <= 'Z')
+				ch1 += 'a' - 'A';
+			else if (IS_HIGHBIT_SET(ch1) && isupper(ch1))
+				ch1 = tolower(ch1);
+
+			if (ch2 >= 'A' && ch2 <= 'Z')
+				ch2 += 'a' - 'A';
+			else if (IS_HIGHBIT_SET(ch2) && isupper(ch2))
+				ch2 = tolower(ch2);
+
+			if (ch1 != ch2)
+				return (int) ch1 - (int) ch2;
+		}
+		if (ch1 == 0)
+			break;
+	}
+	return 0;
+}
 
 /*
  * Fold a character to upper case.

test/plpgsql_samples.sql

@@ -76,43 +76,43 @@ END;$$;
 --   EXECUTE func_cmd;
 -- END;$func$;
 
--- CREATE OR REPLACE FUNCTION cs_parse_url(
---     v_url IN VARCHAR,
---     v_host OUT VARCHAR,  -- This will be passed back
---     v_path OUT VARCHAR,  -- This one too
---     v_query OUT VARCHAR) -- And this one
--- AS $$
--- DECLARE
---     a_pos1 INTEGER;
---     a_pos2 INTEGER;
--- BEGIN
---     v_host := NULL;
---     v_path := NULL;
---     v_query := NULL;
---     a_pos1 := instr(v_url, '//');
---
---     IF a_pos1 = 0 THEN
---         RETURN;
---     END IF;
---     a_pos2 := instr(v_url, '/', a_pos1 + 2);
---     IF a_pos2 = 0 THEN
---         v_host := substr(v_url, a_pos1 + 2);
---         v_path := '/';
---         RETURN;
---     END IF;
---
---     v_host := substr(v_url, a_pos1 + 2, a_pos2 - a_pos1 - 2);
---     a_pos1 := instr(v_url, '?', a_pos2 + 1);
---
---     IF a_pos1 = 0 THEN
---         v_path := substr(v_url, a_pos2);
---         RETURN;
---     END IF;
---
---     v_path := substr(v_url, a_pos2, a_pos1 - a_pos2);
---     v_query := substr(v_url, a_pos1 + 1);
--- END;
--- $$ LANGUAGE plpgsql;
+CREATE OR REPLACE FUNCTION cs_parse_url(
+    v_url IN VARCHAR,
+    v_host OUT VARCHAR,  -- This will be passed back
+    v_path OUT VARCHAR,  -- This one too
+    v_query OUT VARCHAR) -- And this one
+AS $$
+DECLARE
+    a_pos1 INTEGER;
+    a_pos2 INTEGER;
+BEGIN
+    v_host := NULL;
+    v_path := NULL;
+    v_query := NULL;
+    a_pos1 := instr(v_url, '//');
+
+    IF a_pos1 = 0 THEN
+        RETURN;
+    END IF;
+    a_pos2 := instr(v_url, '/', a_pos1 + 2);
+    IF a_pos2 = 0 THEN
+        v_host := substr(v_url, a_pos1 + 2);
+        v_path := '/';
+        RETURN;
+    END IF;
+
+    v_host := substr(v_url, a_pos1 + 2, a_pos2 - a_pos1 - 2);
+    a_pos1 := instr(v_url, '?', a_pos2 + 1);
+
+    IF a_pos1 = 0 THEN
+        v_path := substr(v_url, a_pos2);
+        RETURN;
+    END IF;
+
+    v_path := substr(v_url, a_pos2, a_pos1 - a_pos2);
+    v_query := substr(v_url, a_pos1 + 1);
+END;
+$$ LANGUAGE plpgsql;
 
 CREATE OR REPLACE FUNCTION cs_create_job(v_job_id integer) RETURNS void AS $$
 DECLARE
@@ -545,3 +545,68 @@ CREATE FUNCTION test_cursor() RETURNS void AS $$
   END
 $$ language plpgsql;
 
+CREATE FUNCTION public.dz_sumfunc(
+    IN  p_in  INTEGER
+    ,OUT p_out public.dz_sumthing
+)
+AS $BODY$
+DECLARE
+BEGIN
+    p_out.sumattribute := p_in;
+END;
+$BODY$
+LANGUAGE plpgsql;
+
+-- Examples from https://www.postgresql.org/docs/16/plpgsql-declarations.html#PLPGSQL-DECLARATION-PARAMETERS
+CREATE FUNCTION sales_tax(real) RETURNS real AS $$
+DECLARE
+    subtotal ALIAS FOR $1;
+BEGIN
+    RETURN subtotal * 0.06;
+END;
+$$ LANGUAGE plpgsql;
+
+-- RETURN NEXT; with no expression https://www.postgresql.org/docs/16/plpgsql-control-structures.html#PLPGSQL-STATEMENTS-RETURNING-RETURN-NEXT
+CREATE OR REPLACE FUNCTION public.test_pl(s integer, e integer)
+  RETURNS TABLE(id INTEGER) AS $$
+BEGIN
+  id := s;
+LOOP
+  EXIT WHEN id>e;
+  RETURN NEXT;
+  id := id + 1;
+END LOOP;
+END
+$$
+  LANGUAGE plpgsql;
+
+CREATE OR REPLACE FUNCTION trgfn()
+ RETURNS trigger AS $$
+DECLARE
+ prior ALIAS FOR old;
+ updated ALIAS FOR new;
+BEGIN
+ RETURN;
+END;
+$$
+  LANGUAGE plpgsql;
+
+-- Example from https://www.postgresql.org/docs/16/plpgsql-cursors.html
+CREATE FUNCTION reffunc2() RETURNS refcursor AS '
+DECLARE
+    ref refcursor;
+BEGIN
+    OPEN ref FOR SELECT col FROM test;
+    RETURN ref;
+END;
+' LANGUAGE plpgsql;
+
+-- Example from https://www.postgresql.org/docs/16/plpgsql-declarations.html#PLPGSQL-DECLARATION-COLLATION
+CREATE FUNCTION less_than(a text, b text) RETURNS boolean AS $$
+DECLARE
+    local_a text COLLATE "en_US" := a;
+    local_b text := b;
+BEGIN
+    RETURN local_a < local_b;
+END;
+$$ LANGUAGE plpgsql;