Fix #123, Merge pull request #125 from mangiucugna/codex/fix-infinite-loop-with-in-repair-json

Fix comment parser infinite loop

Author: mangiucugna

README.md

@@ -64,6 +64,7 @@ then you can use use it in your code like this
     good_json_string = repair_json(bad_json_string)
     # If the string was super broken this will return an empty string
 
+
 You can use this library to completely replace `json.loads()`:
 
     import json_repair

pyproject.toml

@@ -3,7 +3,7 @@ requires = ["setuptools>=61.0"]
 build-backend = "setuptools.build_meta"
 [project]
 name = "json_repair"
-version = "0.45.0"
+version = "0.45.1"
 license = {file = "LICENSE"}
 authors = [
   { name="Stefano Baccianella", email="[email protected]" },

src/json_repair/json_parser.py

@@ -790,6 +790,11 @@ def parse_comment(self) -> str:
                         break
                 self.log(f"Found block comment: {comment}")
                 return ""
+            else:
+                # Skip standalone '/' characters that are not part of a comment
+                # to avoid getting stuck in an infinite loop
+                self.index += 1
+                return ""
         return ""  # pragma: no cover
 
     def get_char_at(self, count: int = 0) -> str | Literal[False]:

tests/test_json_repair.py

@@ -83,6 +83,7 @@ def test_general_edge_cases():
     assert repair_json("[[1\n\n]") == "[[1]]"
     assert repair_json("string") == ""
     assert repair_json("stringbeforeobject {}") == "{}"
+    assert repair_json("/") == ""
 
 
 def test_mixed_data_types():