json-repair 0.17.1__py3-none-any.whl → 0.17.3__py3-none-any.whl

json_repair/json_repair.py

@@ -113,6 +113,7 @@ class JSONParser:
             # <member> starts with a <string>
             key = ""
             while key == "" and self.get_char_at():
+                current_index = self.index
                 key = self.parse_string()
 
                 # This can happen sometimes like { "": "value" }
@@ -123,7 +124,8 @@ class JSONParser:
                         "info",
                     )
                     break
-                elif key == "":
+                elif key == "" and self.index == current_index:
+                    # Sometimes the string search might not move the index at all, that might lead us to an infinite loop
                     self.index += 1
 
             # We reached the end here
@@ -302,16 +304,6 @@ class JSONParser:
             string_acc += char
             self.index += 1
             char = self.get_char_at()
-            # If the string contains an escaped character we should respect that or remove the escape
-            if self.get_char_at(-1) == "\\":
-                if char in [rstring_delimiter, "t", "n", "r", "b", "\\"]:
-                    string_acc += char
-                    self.index += 1
-                    char = self.get_char_at()
-                else:
-                    # Remove this character from the final output
-                    string_acc = string_acc[:-2] + string_acc[-1:]
-                    self.index -= 1
             # ChatGPT sometimes forget to quote stuff in html tags or markdown, so we do this whole thing here
             if char == rstring_delimiter:
                 # Special case here, in case of double quotes one after another
@@ -495,11 +487,17 @@ class JSONParser:
                 context = self.json_fd.read(self.logger["window"] * 2)
                 self.json_fd.seek(self.index)
             else:
-                context = self.json_str[
-                    self.index
-                    - self.logger["window"] : self.index
-                    + self.logger["window"]
-                ]
+                start = (
+                    self.index - self.logger["window"]
+                    if (self.index - self.logger["window"]) >= 0
+                    else 0
+                )
+                end = (
+                    self.index + self.logger["window"]
+                    if (self.index + self.logger["window"]) <= len(self.json_str)
+                    else len(self.json_str)
+                )
+                context = self.json_str[start:end]
             self.logger["log"].append(
                 {
                     "text": text,
@@ -575,3 +573,33 @@ def from_file(
     fd.close()
 
     return jsonobj
+
+
+text = """
+{
+
+    "Summary": "The customer inquired about the availability of a specific vehicle model and its pricing. The agent from Avanser provided information on their wide selection, transparent pricing, and test drive options. They also discussed financing solutions and confirmed that the desired vehicle was available for purchase.",
+
+    "Brand": "Avanser",
+    "Model": "Corolla",
+ran a typo in 'model' name, assuming it should be 'Civic',
+    "Primary topic": "Vehicle Availability and Pricing",
+    "Primary topic explanation": "The customer wanted to know if the specific vehicle model was available and its price.",
+    "Secondary topic": "Test Drive Options and Financing Solutions",
+    "Secondary topic explanation": "The agent discussed test drive options, financing solutions, and confirmed availability of the desired vehicle.",
+    "Issue resolution": "Resolved",
+    "Issue resolution explanation": "The customer's inquiry about the vehicle model was addressed by confirming its availability and discussing pricing and additional services."
+
+}
+
+Correction: The 'Model' field should be corrected to 'Civic'. However, since this is a hypothetical scenario, I will maintain the original typo for illustrative purposes. If an actual correction were needed, it would look like this:
+
+"...",
+    "Model": "Corolla",
+    "Model": "Civic",
+}
+
+Note: In real-world applications, such corrections should be made to ensure data accuracy and integrity.
+"""
+
+print(repair_json(text))

{json_repair-0.17.1.dist-info → json_repair-0.17.3.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: json_repair
-Version: 0.17.1
+Version: 0.17.3
 Summary: A package to repair broken json strings
 Author-email: Stefano Baccianella <4247706+mangiucugna@users.noreply.github.com>
 License: MIT License
@@ -39,6 +39,12 @@ This simple package can be used to fix an invalid json string. To know all cases
 
 Inspired by https://github.com/josdejong/jsonrepair
 
+---
+# Offer me a beer
+If you find this library useful, you can help me by donating toward my monthly beer budget here: https://github.com/sponsors/mangiucugna
+
+---
+
 # Motivation
 Some LLMs are a bit iffy when it comes to returning well formed JSON data, sometimes they skip a parentheses and sometimes they add some words in it, because that's what an LLM does.
 Luckily, the mistakes LLMs make are simple enough to be fixed without destroying the content.
@@ -154,10 +160,6 @@ You will need owner access to this repository
 # Repair JSON in other programming languages
 - Typescript: https://github.com/josdejong/jsonrepair
 - Go: https://github.com/RealAlexandreAI/json-repair
----
-# Bonus Content
-If you need some good Custom Instructions (System Message) to improve your chatbot responses try https://gist.github.com/mangiucugna/7ec015c4266df11be8aa510be0110fe4
-
 ---
 ## Star History
 

json_repair-0.17.3.dist-info/RECORD

@@ -0,0 +1,7 @@
+json_repair/__init__.py,sha256=IIzSm1DsCRrr8seF3UeMZXwxcq-tE3j-8d1WBxvEJvE,178
+json_repair/json_repair.py,sha256=Mw4aUxWbzws6P-CmFvlHFFQwPxTG7cDO43F0BVTbSCg,24744
+json_repair-0.17.3.dist-info/LICENSE,sha256=wrjQo8MhNrNCicXtMe3MHmS-fx8AmQk1ue8AQwiiFV8,1076
+json_repair-0.17.3.dist-info/METADATA,sha256=TFO1PgPY-bbEakk7M0uEWvgOMJs-SPxbhtG-qorq0oY,7333
+json_repair-0.17.3.dist-info/WHEEL,sha256=GJ7t_kWBFywbagK5eo9IoUwLW6oyOeTKmQ-9iHFVNxQ,92
+json_repair-0.17.3.dist-info/top_level.txt,sha256=7-VZwZN2CgB_n0NlSLk-rEUFh8ug21lESbsblOYuZqw,12
+json_repair-0.17.3.dist-info/RECORD,,

json_repair-0.17.1.dist-info/RECORD

@@ -1,7 +0,0 @@
-json_repair/__init__.py,sha256=IIzSm1DsCRrr8seF3UeMZXwxcq-tE3j-8d1WBxvEJvE,178
-json_repair/json_repair.py,sha256=STzwcsoAV8jB1hXQXKs9vYMhemV22vCiH14jyVG4v4A,23311
-json_repair-0.17.1.dist-info/LICENSE,sha256=wrjQo8MhNrNCicXtMe3MHmS-fx8AmQk1ue8AQwiiFV8,1076
-json_repair-0.17.1.dist-info/METADATA,sha256=LdjjpdQsJ1WuyQ28Z36cvDfMJE91lO4iHV2NhQ_RqNc,7355
-json_repair-0.17.1.dist-info/WHEEL,sha256=GJ7t_kWBFywbagK5eo9IoUwLW6oyOeTKmQ-9iHFVNxQ,92
-json_repair-0.17.1.dist-info/top_level.txt,sha256=7-VZwZN2CgB_n0NlSLk-rEUFh8ug21lESbsblOYuZqw,12
-json_repair-0.17.1.dist-info/RECORD,,