json-repair 0.1.0 → 0.3.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 17c6b285b495a3c053ae838e701205ec682f7648856cadb52d00da5d348f393c
-  data.tar.gz: 644acd7c8840e0a1edf4399297c1bbcc17739cdd13ab6ee9102880981a00bc84
+  metadata.gz: db2b6fb7849a2e75329405c1f85fa7de836b0fa2f079623032571f42d359514d
+  data.tar.gz: 1c845714c4c443bad3c9277a2ceae6cef8ff346125f52f89473aaa50b9ff2132
 SHA512:
-  metadata.gz: 6bbe9f8d1e5558ab344987a867dc1aae6859c7e33b537cf20b78d97b5db4734c33388d7514b5db85decf8ca156d91efd4fe98d7cd8b42bc2c2fa81822a0ce9bd
-  data.tar.gz: '0175953daedfe95efb9dc1777d38c2e6034e1822b0463fe50cf52dc946a17cd5a363bab862bc776399bd2e34c249b682298c2989f5ce7fa959cd667c4845d013'
+  metadata.gz: 53929154af31033e2f380ed89979430f4339c97c94c088b6f85da27ac251d658b98840e44085c4ba9b4972bab75c1bb0f8ad750beddd4bb79e439efb135e0386
+  data.tar.gz: b4b5150aee81c518eaee8847bb2f5d8d8131a15719bb93badce465a2d447ddc361888155b2d33125fdd69d2568424c08440772c61a7f7f5b35922a4d1270adf8

data/.rubocop.yml

@@ -10,32 +10,32 @@ Style/Documentation:
 
 Metrics/ClassLength:
   Exclude:
-    - lib/json/repair/repairer.rb
+    - lib/json/repairer.rb
 
 Metrics/AbcSize:
   Exclude:
-    - lib/json/repair/repairer.rb
+    - lib/json/repairer.rb
 
 Metrics/MethodLength:
   Exclude:
-    - lib/json/repair/repairer.rb
+    - lib/json/repairer.rb
 
 Metrics/CyclomaticComplexity:
   Exclude:
-    - lib/json/repair/repairer.rb
+    - lib/json/repairer.rb
 
 Metrics/PerceivedComplexity:
   Exclude:
-    - lib/json/repair/repairer.rb
+    - lib/json/repairer.rb
 
 Metrics/BlockLength:
   Exclude:
-    - lib/json/repair/repairer.rb
+    - lib/json/repairer.rb
     - spec/**/*
 
 Metrics/BlockNesting:
   Exclude:
-    - lib/json/repair/repairer.rb
+    - lib/json/repairer.rb
 
 Metrics/ModuleLength:
   Exclude:

data/README.md

@@ -1,6 +1,6 @@
-# JSON::Repair
+# JSON::Repair [![Gem Version](https://badge.fury.io/rb/json-repair.svg)](https://badge.fury.io/rb/json-repair) [![Build Status](https://github.com/sashazykov/json-repair-rb/actions/workflows/main.yml/badge.svg?branch=main)](https://github.com/sashazykov/json-repair-rb/actions) [![Stand With Ukraine](https://raw.githubusercontent.com/vshymanskyy/StandWithUkraine/main/badges/StandWithUkraine.svg)](https://stand-with-ukraine.pp.ua)
 
-This is a Ruby gem designed to repair broken JSON strings. Inspired by the [jsonrepair js library](https://github.com/josdejong/jsonrepair/). It efficiently handles and corrects malformed JSON data, making it especially useful in scenarios where JSON output from LLMs might not strictly adhere to JSON standards. Whether it's missing quotes, misplaced commas, or unexpected characters, it ensures that the JSON data is valid and can be parsed correctly.
+This is a Ruby gem designed to repair broken JSON strings. Inspired by and based on the [jsonrepair js library](https://github.com/josdejong/jsonrepair/). It efficiently handles and corrects malformed JSON data, making it especially useful in scenarios where JSON output from LLMs might not strictly adhere to JSON standards. Whether it's missing quotes, misplaced commas, or unexpected characters, it ensures that the JSON data is valid and can be parsed correctly.
 
 ## Installation
 
@@ -25,7 +25,7 @@ require 'json/repair'
 
 # Example of repairing a JSON string
 broken_json = '{name: Alice, "age": 25,}'
-repaired_json = JSON::Repair.repair(broken_json)
+repaired_json = JSON.repair(broken_json)
 puts repaired_json  # Outputs: {"name": "Alice", "age": 25}
 ```
 
@@ -48,3 +48,10 @@ The gem is available as open source under the terms of the [ISC License](https:/
 ## Code of Conduct
 
 Everyone interacting in the JSON::Repair project's codebases, issue trackers, chat rooms, and mailing lists is expected to follow the [code of conduct](https://github.com/sashazykov/json-repair-rb/blob/main/CODE_OF_CONDUCT.md).
+
+## Similar libraries in other languages
+
+- Typescript: https://github.com/josdejong/jsonrepair
+- Go: https://github.com/RealAlexandreAI/json-repair
+- JavaScript: https://github.com/RyanMarcus/dirty-json
+- Python: https://github.com/mangiucugna/json_repair

data/Steepfile

@@ -0,0 +1,6 @@
+# frozen_string_literal: true
+
+target :lib do
+  signature 'sig'
+  check 'lib'
+end

data/lib/json/repair/string_utils.rb

@@ -35,21 +35,28 @@ module JSON
       LOWERCASE_E = 'e' # 0x65
       UPPERCASE_F = 'F' # 0x46
       LOWERCASE_F = 'f' # 0x66
-      NON_BREAKING_SPACE = "\u00a0" # 0xa0
-      EN_QUAD = "\u2000" # 0x2000
-      HAIR_SPACE = "\u200a" # 0x200a
-      NARROW_NO_BREAK_SPACE = "\u202f" # 0x202f
-      MEDIUM_MATHEMATICAL_SPACE = "\u205f" # 0x205f
-      IDEOGRAPHIC_SPACE = "\u3000" # 0x3000
-      DOUBLE_QUOTE_LEFT = "\u201c" # 0x201c
-      DOUBLE_QUOTE_RIGHT = "\u201d" # 0x201d
-      QUOTE_LEFT = "\u2018" # 0x2018
-      QUOTE_RIGHT = "\u2019" # 0x2019
+      NON_BREAKING_SPACE = ' ' # 0xa0
+      MONGOLIAN_VOWEL_SEPARATOR = '᠎' # 0x180e
+      EN_QUAD = ' ' # 0x2000
+      ZERO_WIDTH_SPACE = '​' # 0x200b
+      NARROW_NO_BREAK_SPACE = ' ' # 0x202f
+      MEDIUM_MATHEMATICAL_SPACE = ' ' # 0x205f
+      IDEOGRAPHIC_SPACE = '　' # 0x3000
+      ZERO_WIDTH_NO_BREAK_SPACE = '' # 0xfeff
+      DOUBLE_QUOTE_LEFT = '“' # 0x201c
+      DOUBLE_QUOTE_RIGHT = '”' # 0x201d
+      QUOTE_LEFT = '‘' # 0x2018
+      QUOTE_RIGHT = '’' # 0x2019
       GRAVE_ACCENT = '`' # 0x0060
-      ACUTE_ACCENT = "\u00b4" # 0x00b4
+      ACUTE_ACCENT = '´' # 0x00b4
 
       REGEX_DELIMITER = %r{^[,:\[\]/{}()\n+]+$}
+      REGEX_UNQUOTED_STRING_DELIMITER = %r{^[,\[\]/{}\n+]+$}
       REGEX_START_OF_VALUE = /^[\[{\w-]$/
+      # matches "https://" and other schemas
+      REGEX_URL_START = %r{^(http|https|ftp|mailto|file|data|irc)://$}
+      # matches all valid URL characters EXCEPT "[", "]", and "," (important JSON delimiters)
+      REGEX_URL_CHAR = %r{^[A-Za-z0-9\-._~:/?#@!$&'()*+;=]$}
 
       # Functions to check character chars
       def hex?(char)
@@ -70,8 +77,19 @@ module JSON
         REGEX_DELIMITER.match?(char)
       end
 
-      def delimiter_except_slash?(char)
-        delimiter?(char) && char != SLASH
+      def unquoted_string_delimiter?(char)
+        REGEX_UNQUOTED_STRING_DELIMITER.match?(char)
+      end
+
+      REGEX_FUNCTION_NAME_CHAR_START = /\A[a-zA-Z_$]\z/
+      REGEX_FUNCTION_NAME_CHAR = /\A[a-zA-Z0-9_$]\z/
+
+      def function_name_char_start?(char)
+        !char.nil? && REGEX_FUNCTION_NAME_CHAR_START.match?(char)
+      end
+
+      def function_name_char?(char)
+        !char.nil? && REGEX_FUNCTION_NAME_CHAR.match?(char)
       end
 
       def start_of_value?(char)
@@ -86,11 +104,22 @@ module JSON
         [SPACE, NEWLINE, TAB, RETURN].include?(char)
       end
 
+      def whitespace_except_newline?(char)
+        [SPACE, TAB, RETURN].include?(char)
+      end
+
       def special_whitespace?(char)
+        return false unless char
+
         [
-          NON_BREAKING_SPACE, NARROW_NO_BREAK_SPACE, MEDIUM_MATHEMATICAL_SPACE, IDEOGRAPHIC_SPACE
+          NON_BREAKING_SPACE,
+          MONGOLIAN_VOWEL_SEPARATOR,
+          NARROW_NO_BREAK_SPACE,
+          MEDIUM_MATHEMATICAL_SPACE,
+          IDEOGRAPHIC_SPACE,
+          ZERO_WIDTH_NO_BREAK_SPACE
         ].include?(char) ||
-          (char >= EN_QUAD && char <= HAIR_SPACE)
+          (char >= EN_QUAD && char <= ZERO_WIDTH_SPACE)
       end
 
       def quote?(char)
@@ -149,7 +178,7 @@ module JSON
 
       def parse_keyword(name, value)
         if @json[@index, name.length] == name
-          @output += value
+          @output << value
           @index += name.length
           true
         else
@@ -161,10 +190,6 @@ module JSON
         text[0...start] + text[start + count..]
       end
 
-      def function_name?(text)
-        /^\w+$/.match?(text)
-      end
-
       def ends_with_comma_or_newline?(text)
         /[,\n][ \t\r]*$/.match?(text)
       end

data/lib/json/repair/version.rb

@@ -2,6 +2,6 @@
 
 module JSON
   module Repair
-    VERSION = '0.1.0'
+    VERSION = '0.3.0'
   end
 end

data/lib/json/repair.rb

@@ -1,14 +1,12 @@
 # frozen_string_literal: true
 
 require_relative 'repair/version'
-require_relative 'repair/repairer'
+require_relative 'repairer'
 
 module JSON
-  module Repair
-    class JSONRepairError < StandardError; end
+  class JSONRepairError < StandardError; end
 
-    def self.repair(json)
-      Repairer.new(json).repair
-    end
+  def self.repair(json)
+    Repairer.new(json).repair
   end
 end