From 350d1242b6585576719e681276987f325d15628d Mon Sep 17 00:00:00 2001
From: Zsolt Parragi <zsolt.parragi@percona.com>
Date: Mon, 20 Jul 2026 09:44:15 +0000
Subject: [PATCH v2 4/8] Add JSON5 single-quoted string support to the JSON
 lexer

When json5 is set, accept single-quote-delimited strings with the same
escape handling as double-quoted strings.
---
 src/common/jsonapi.c                          | 31 ++++++++++++++++---
 .../test_json_parser/json5_strings.json5      |  8 +++++
 .../test_json_parser/json5_strings.out        | 13 ++++++++
 .../test_json_parser/t/005_test_json5.pl      |  3 +-
 4 files changed, 50 insertions(+), 5 deletions(-)
 create mode 100644 src/test/modules/test_json_parser/json5_strings.json5
 create mode 100644 src/test/modules/test_json_parser/json5_strings.out

diff --git a/src/common/jsonapi.c b/src/common/jsonapi.c
index 96d739a79e7..f6d804a23b2 100644
--- a/src/common/jsonapi.c
+++ b/src/common/jsonapi.c
@@ -2293,6 +2293,19 @@ json_lex(JsonLexContext *lex)
 				lex->token_terminator = s + 1;
 				lex->token_type = JSON_TOKEN_COLON;
 				break;
+			case '\'':
+				if (!lex->json5)
+				{
+					lex->prev_token_terminator = lex->token_terminator;
+					lex->token_terminator = s + 1;
+					return JSON_INVALID_TOKEN;
+				}
+
+				/*
+				 * json5 single-quoted string.  Share the call below, so that
+				 * json_lex_string() still gets inlined.
+				 */
+				pg_fallthrough;
 			case '"':
 				/* string */
 				result = json_lex_string(lex);
@@ -2417,6 +2430,7 @@ json_lex_string(JsonLexContext *lex)
 	const char *s;
 	const char *const end = lex->input + lex->input_length;
 	int			hi_surrogate = -1;
+	char		quote_char = *lex->token_start;
 	JsonParseErrorType result;
 
 	/* Convenience macros for error exits */
@@ -2460,7 +2474,7 @@ json_lex_string(JsonLexContext *lex)
 		/* Premature end of the string. */
 		if (s >= end)
 			FAIL_OR_INCOMPLETE_AT_CHAR_START(JSON_INVALID_TOKEN);
-		else if (*s == '"')
+		else if (*s == quote_char)
 			break;
 		else if (*s == '\\')
 		{
@@ -2539,6 +2553,14 @@ json_lex_string(JsonLexContext *lex)
 					case '/':
 						jsonapi_appendStringInfoChar(lex->strval, *s);
 						break;
+					case '\'':
+						if (!lex->json5)
+						{
+							lex->token_start = s;
+							FAIL_AT_CHAR_END(JSON_ESCAPING_INVALID);
+						}
+						jsonapi_appendStringInfoChar(lex->strval, *s);
+						break;
 					case 'b':
 						jsonapi_appendStringInfoChar(lex->strval, '\b');
 						break;
@@ -2565,7 +2587,8 @@ json_lex_string(JsonLexContext *lex)
 						FAIL_AT_CHAR_END(JSON_ESCAPING_INVALID);
 				}
 			}
-			else if (strchr("\"\\/bfnrt", *s) == NULL)
+			else if (strchr("\"\\/bfnrt", *s) == NULL &&
+					 !(lex->json5 && *s == '\''))
 			{
 				/*
 				 * Simpler processing if we're not bothered about de-escaping
@@ -2591,13 +2614,13 @@ json_lex_string(JsonLexContext *lex)
 			 */
 			while (p < end - sizeof(Vector8) &&
 				   !pg_lfind8('\\', (const uint8 *) p, sizeof(Vector8)) &&
-				   !pg_lfind8('"', (const uint8 *) p, sizeof(Vector8)) &&
+				   !pg_lfind8(quote_char, (const uint8 *) p, sizeof(Vector8)) &&
 				   !pg_lfind8_le(31, (const uint8 *) p, sizeof(Vector8)))
 				p += sizeof(Vector8);
 
 			for (; p < end; p++)
 			{
-				if (*p == '\\' || *p == '"')
+				if (*p == '\\' || *p == quote_char)
 					break;
 				else if ((unsigned char) *p <= 31)
 				{
diff --git a/src/test/modules/test_json_parser/json5_strings.json5 b/src/test/modules/test_json_parser/json5_strings.json5
new file mode 100644
index 00000000000..7345d8a452f
--- /dev/null
+++ b/src/test/modules/test_json_parser/json5_strings.json5
@@ -0,0 +1,8 @@
+{
+  a: 'single quoted',
+  b: 'embedded "double" quotes',
+  c: 'escaped \' apostrophe',
+  d: "double with 'single' inside",
+  e: 'line1\nline2',
+  arr: [ 'x', "y", 'z' ]
+}
diff --git a/src/test/modules/test_json_parser/json5_strings.out b/src/test/modules/test_json_parser/json5_strings.out
new file mode 100644
index 00000000000..3efe7a744db
--- /dev/null
+++ b/src/test/modules/test_json_parser/json5_strings.out
@@ -0,0 +1,13 @@
+{
+"a": "single quoted",
+"b": "embedded \"double\" quotes",
+"c": "escaped ' apostrophe",
+"d": "double with 'single' inside",
+"e": "line1\nline2",
+"arr": [
+"x",
+"y",
+"z"
+]
+
+}
diff --git a/src/test/modules/test_json_parser/t/005_test_json5.pl b/src/test/modules/test_json_parser/t/005_test_json5.pl
index aa077d751e7..9447aee0801 100644
--- a/src/test/modules/test_json_parser/t/005_test_json5.pl
+++ b/src/test/modules/test_json_parser/t/005_test_json5.pl
@@ -75,7 +75,8 @@ my @features = (
 		error => qr/Token "\/" is invalid/,
 	},
 	{ name => 'trailing commas', file => 'json5_trailing_commas' },
-	{ name => 'unquoted keys', file => 'json5_keys' },);
+	{ name => 'unquoted keys', file => 'json5_keys' },
+	{ name => 'single-quoted strings', file => 'json5_strings' },);
 
 # Inputs that stay invalid even in json5 mode.
 my @json5_invalid = (
-- 
2.55.0