common/json-schema: fix: handle non-capturing groups (?:...) in JSON schema pattern...

The regex-to-grammar converter in _visit_pattern() crashes with SIGSEGV
when a JSON schema "pattern" field contains a non-capturing group (?:...).

Root cause: when the parser sees '(' followed by '?', it pushes a warning
but does not advance past '?:'. The recursive transform() call then
interprets '?' as a quantifier and calls seq.back() on an empty vector,
causing undefined behavior.

This commonly occurs when serving OpenAI-compatible tool calls from
clients that include complex regex patterns in their JSON schemas (e.g.,
date validation patterns like ^(?:(?:\d\d[2468][048]|...)-02-29|...)$).

The fix:
- Skip '?:' after '(' to treat non-capturing groups as regular groups
- For unsupported syntax (?=, ?!, etc.), skip to matching ')' safely,
  handling escaped characters to avoid miscounting parenthesis depth
- Adjust the ')' unbalanced-parentheses check using direct char
  comparisons instead of substr
- Add test cases for non-capturing groups (C++ only, as the JS/Python
  implementations do not yet support this syntax)

diff --git a/common/json-schema-to-grammar.cpp b/common/json-schema-to-grammar.cpp
index c7057d651d16a5a34f2d7784c4483a4973746e1e..e2c4d6ce22e536e3c69115fae40ad14fe5516c22 100644 (file)
--- a/common/json-schema-to-grammar.cpp
+++ b/common/json-schema-to-grammar.cpp
@@ -416,15 +416,30 @@ private:
                     i++;
                 } else if (c == '(') {
                     i++;
-                    if (i < length) {
-                        if (sub_pattern[i] == '?') {
+                    if (i < length && sub_pattern[i] == '?') {
+                        if (i + 1 < length && sub_pattern[i + 1] == ':') {
+                            i += 2; // skip "?:" for non-capturing group, treat as regular group
+                        } else {
+                            // lookahead/lookbehind (?=, ?!, ?<=, ?<!) - not supported
                             _warnings.push_back("Unsupported pattern syntax");
+                            // skip to matching ')' to avoid UB on empty seq
+                            int depth = 1;
+                            while (i < length && depth > 0) {
+                                if (sub_pattern[i] == '\\' && i + 1 < length) {
+                                    i += 2; // skip escaped character
+                                } else {
+                                    if (sub_pattern[i] == '(') depth++;
+                                    else if (sub_pattern[i] == ')') depth--;
+                                    i++;
+                                }
+                            }
+                            continue;
                         }
                     }
                     seq.emplace_back("(" + to_rule(transform()) + ")", false);
                 } else if (c == ')') {
                     i++;
-                    if (start > 0 && sub_pattern[start - 1] != '(') {
+                    if (start > 0 && sub_pattern[start - 1] != '(' && (start < 2 || sub_pattern[start - 2] != '?' || sub_pattern[start - 1] != ':')) {
                         _errors.push_back("Unbalanced parentheses");
                     }
                     return join_seq();

diff --git a/tests/test-json-schema-to-grammar.cpp b/tests/test-json-schema-to-grammar.cpp
index ac697c4d24682598d95747ba760e1112b78addaf..85584ef12b017ed70629b7a51e3e9738cd100062 100755 (executable)
--- a/tests/test-json-schema-to-grammar.cpp
+++ b/tests/test-json-schema-to-grammar.cpp
@@ -1525,6 +1525,47 @@ int main() {
         }
     });
 
+    // C++ only tests (features not yet supported in JS/Python implementations)
+    {
+        fprintf(stderr, "#\n# Testing C++ only features\n#\n");
+        auto run = [](const TestCase & tc) {
+            fprintf(stderr, "- %s\n", tc.name.c_str());
+            try {
+                tc.verify(json_schema_to_grammar(nlohmann::ordered_json::parse(tc.schema), true));
+                tc.verify_status(SUCCESS);
+            } catch (const std::invalid_argument & ex) {
+                fprintf(stderr, "Error: %s\n", ex.what());
+                tc.verify_status(FAILURE);
+            }
+        };
+
+        run({
+            SUCCESS,
+            "regexp with non-capturing group",
+            R"""({
+                "type": "string",
+                "pattern": "^(?:foo|bar)baz$"
+            })""",
+            R"""(
+                root ::= "\"" (("foo" | "bar") "baz") "\"" space
+                space ::= | " " | "\n"{1,2} [ \t]{0,20}
+            )""",
+        });
+
+        run({
+            SUCCESS,
+            "regexp with nested non-capturing groups",
+            R"""({
+                "type": "string",
+                "pattern": "^(?:(?:ab)+c)?d$"
+            })""",
+            R"""(
+                root ::= "\"" ((("ab")+ "c")? "d") "\"" space
+                space ::= | " " | "\n"{1,2} [ \t]{0,20}
+            )""",
+        });
+    }
+
     if (getenv("LLAMA_SKIP_TESTS_SLOW_ON_EMULATOR")) {
         fprintf(stderr, "\033[33mWARNING: Skipping slow tests on emulator.\n\033[0m");
     } else {