From 3eaf561561b3f562709670d69b70eb3b3605c222 Mon Sep 17 00:00:00 2001
From: Bruno Alvisio <bruno.alvisio@gmail.com>
Date: Fri, 7 Feb 2025 15:18:21 -0800
Subject: [PATCH] core: Handle unterminated escape character when parsing
 partial JSON (#29065)

**Description**
Currently, when parsing a partial JSON, if a string ends with the escape
character, the whole key/value is removed. For example:

```
>>> from langchain_core.utils.json import parse_partial_json
>>> my_str = '{"foo": "bar", "baz": "qux\\'
>>>
>>> parse_partial_json(my_str)
{'foo': 'bar'}
```

My expectation (and with this fix) would be for `parse_partial_json()`
to return:
```
>>> from langchain_core.utils.json import parse_partial_json
>>>
>>> my_str = '{"foo": "bar", "baz": "qux\\'
>>> parse_partial_json(my_str)
{'foo': 'bar', 'baz': 'qux'}
```

Notes:
1. It could be argued that current behavior is still desired.
2. I have experienced this issue when the streaming output from an LLM
and the chunk happens to end with `\\`
3. I haven't included tests. Will do if change is accepted.
4. This is specially troublesome when this function is used by

https://github.com/langchain-ai/langchain/blob/187131c55c1b788da38124c6e7917151249746d6/libs/core/langchain_core/output_parsers/transform.py#L111

since what happens is that, for example, if the received sequence of
chunks are: `{"foo": "b` , `ar\\` :

Then, the result of calling `self.parse_result()` is:
```
{"foo": "b"}
```
and the second time:
```
{}
```

Co-authored-by: Erick Friis <erick@langchain.dev>
---
 libs/core/langchain_core/utils/json.py                 | 2 ++
 libs/core/tests/unit_tests/output_parsers/test_json.py | 1 +
 2 files changed, 3 insertions(+)

diff --git a/libs/core/langchain_core/utils/json.py b/libs/core/langchain_core/utils/json.py
index 8aedfaf339b..472ef94b7a3 100644
--- a/libs/core/langchain_core/utils/json.py
+++ b/libs/core/langchain_core/utils/json.py
@@ -94,6 +94,8 @@ def parse_partial_json(s: str, *, strict: bool = False) -> Any:
     # If we're still inside a string at the end of processing,
     # we need to close the string.
     if is_inside_string:
+        if escaped:  # Remoe unterminated escape character
+            new_chars.pop()
         new_chars.append('"')
 
     # Reverse the stack to get the closing characters.
diff --git a/libs/core/tests/unit_tests/output_parsers/test_json.py b/libs/core/tests/unit_tests/output_parsers/test_json.py
index 108b9f2a9cf..4198a467143 100644
--- a/libs/core/tests/unit_tests/output_parsers/test_json.py
+++ b/libs/core/tests/unit_tests/output_parsers/test_json.py
@@ -242,6 +242,7 @@ TEST_CASES_PARTIAL = [
     ('{"foo": "bar", "bar":', '{"foo": "bar"}'),
     ('{"foo": "bar", "bar"', '{"foo": "bar"}'),
     ('{"foo": "bar", ', '{"foo": "bar"}'),
+    ('{"foo":"bar\\', '{"foo": "bar"}'),
 ]