json: expand ESCAPED_IN_REGEXPS_BUT_NOT_IN_LITERALS charset

common/json-schema-to-grammar.cpp

@@ -316,7 +316,7 @@ std::unordered_map<char, std::string> GRAMMAR_LITERAL_ESCAPES = {
 };
 
 std::unordered_set<char> NON_LITERAL_SET = {'|', '.', '(', ')', '[', ']', '{', '}', '*', '+', '?'};
-std::unordered_set<char> ESCAPED_IN_REGEXPS_BUT_NOT_IN_LITERALS = {'[', ']', '(', ')', '|', '{', '}', '*', '+', '?'};
+std::unordered_set<char> ESCAPED_IN_REGEXPS_BUT_NOT_IN_LITERALS = {'^', '$', '.', '[', ']', '(', ')', '|', '{', '}', '*', '+', '?'};
 
 template <typename Iterator>
 std::string join(Iterator begin, Iterator end, const std::string & separator) {

examples/json_schema_to_grammar.py

@@ -231,7 +231,7 @@ GRAMMAR_RANGE_LITERAL_ESCAPE_RE = re.compile(r'[\r\n"\]\-\\]')
 GRAMMAR_LITERAL_ESCAPES = {'\r': '\\r', '\n': '\\n', '"': '\\"', '-': '\\-', ']': '\\]'}
 
 NON_LITERAL_SET = set('|.()[]{}*+?')
-ESCAPED_IN_REGEXPS_BUT_NOT_IN_LITERALS = set('[]()|{}*+?')
+ESCAPED_IN_REGEXPS_BUT_NOT_IN_LITERALS = set('^$.[]()|{}*+?')
 
 
 class SchemaConverter:

examples/server/public/json-schema-to-grammar.mjs

@@ -259,7 +259,7 @@ const GRAMMAR_RANGE_LITERAL_ESCAPE_RE = /[\n\r"\]\-\\]/g;
 const GRAMMAR_LITERAL_ESCAPES = { '\r': '\\r', '\n': '\\n', '"': '\\"', '-': '\\-', ']': '\\]' };
 
 const NON_LITERAL_SET = new Set('|.()[]{}*+?');
-const ESCAPED_IN_REGEXPS_BUT_NOT_IN_LITERALS = new Set('[]()|{}*+?');
+const ESCAPED_IN_REGEXPS_BUT_NOT_IN_LITERALS = new Set('^$.[]()|{}*+?');
 
 export class SchemaConverter {
   constructor(options) {

tests/test-grammar-integration.cpp

@@ -993,6 +993,40 @@ static void test_json_schema() {
         }
     );
 
+    test_schema(
+        "simple pattern",
+        // Schema
+        R"""({
+            "pattern": "^[a-zA-Z0-9_-]*$"
+        })""",
+        // Passing strings
+        {
+            R"""("")""",
+            R"""("He_llo-12")""",
+        },
+        // Failing strings
+        {
+            R"""("!")""",
+            R"""("Hello World")""",
+        }
+    );
+
+    test_schema(
+        "pattern with escapes",
+        // Schema
+        R"""({
+            "pattern": "^a\\^\\$\\.\\[\\]\\(\\)\\|\\{\\}\\*\\+\\?b$"
+        })""",
+        // Passing strings
+        {
+            R"""("a^$.[]()|{}*+?b")""",
+        },
+        // Failing strings
+        {
+            R"""("ab")""",
+        }
+    );
+
     test_schema(
         "",
         // Schema