Release 0.15.0

Added

• Adding a logging capability to understand what has been repaired. This was a feature request that was bubbling up in the issues, probably still incomplete but a good start if anyone is interested in understanding more about the errors found.
  You can enable logging by passing logging=True to repair_json() and it will return a tuple instead of just the corrected json

Release 0.14.0

Added

• Fixed #26 by adding a more general way to handle special cases with html tags and markdown in which the LLM uses the wrong quotation mark. Thanks to @nikolaysm not only for reporting but also for pointing me in the right direction to solve this problem more elegantly

Release 0.13.1

Fixed

• Fixed #24, fixed how the library handles the change of context when objects and arrays are mixed. Before this case would cause a crash. Thanks to @ftudisco for reporting the issue!

Release 0.13.0

Added

• New function load(fd) that is a drop in replacement for json.load()
• New function from_file(string_file_path) that makes it easier to write scripts to batch process json files

Thank to @ajmeese7 for the feature request in #21 !

Release 0.12.3

Fixed

• Fix #23, if a dangling quotation mark followed a number or a boolean it would break the json string. Thanks @AloXado320 for reporting!

Release 0.12.2

Fixed

• Generalize the double quotation fix

0.12.1

Fixed

• Fix a corner case in case the double quotation marks aren't repeated

Release 0.12.0

Added

• Fix #20, support double quotation marks as string delimiters. Thanks to @pd2871 for reporting!

Release 0.11.1

Fixed

• Fixed a bug, removing a character needs the counter to be decreased by 1 or the parser will eat the next character. Updated Unit Tests to check for this corner case

Release 0.11.0

Added

• Fixed #19, trailing backslashes cause json.loads() to throw an exception. Removing those unless are a valid escaping sequence. Thanks to @rbren for reporting the issue.