[feat] Add support for parsing JSON with text prefix and postfix

README.md

@@ -102,6 +102,28 @@ If the JSON string is malformed, the `parse` function will throw an error:
 loads("wrong")  # MalformedJSON: Malformed node or string on line 1
 ```
 
+### Handling text around JSON
+
+Sometimes JSON might be embedded in other text. You can use `PREFIX` and `POSTFIX` options to handle this:
+
+```python
+from partial_json_parser import loads, PREFIX, POSTFIX
+
+# Handle text before JSON
+result = loads('This is your JSON: {"key": "value"}', PREFIX)
+print(result)  # Outputs: {'key': 'value'}
+
+# Handle text after JSON
+result = loads('{"key": "value"} - end of JSON', POSTFIX)
+print(result)  # Outputs: {'key': 'value'}
+
+# Handle both
+result = loads('Start of JSON: {"key": "value"} - end of JSON', PREFIX | POSTFIX)
+print(result)  # Outputs: {'key': 'value'}
+```
+
+Note that `PREFIX` looks for the first `{` or `[` character and `POSTFIX` looks for the last `}` or `]` character to determine the JSON boundaries.
+
 ## API Reference
 
 ### loads(json_string, [allow_partial], [parser])
@@ -149,7 +171,9 @@ Enum class that specifies what kind of partialness is allowed during JSON parsin
 - `SPECIAL`: Allow all special values.
 - `ATOM`: Allow all atomic values.
 - `COLLECTION`: Allow all collection values.
-- `ALL`: Allow all values.
+- `PREFIX`: Allow text before the JSON string starts (e.g. `This is your JSON: {"key": "value"}`).
+- `POSTFIX`: Allow text after the JSON string ends (e.g. `{"key": "value"} - end of JSON`).
+- `ALL`: Allow all values
 
 ## Testing
 

src/partial_json_parser/core/myelin.py

@@ -20,6 +20,78 @@ def join_closing_tokens(stack: List[Tuple[int, str]]):
 
 def fix_fast(json_string: str, allow_partial: Union[Allow, int] = ALL):
     allow = Allow(allow_partial)
+
+    # Handle PREFIX by finding first { or [
+    if PREFIX in allow:
+        first_brace = json_string.find('{')
+        first_bracket = json_string.find('[')
+
+        if first_brace != -1 and (first_bracket == -1 or first_brace < first_bracket):
+            json_string = json_string[first_brace:]
+        elif first_bracket != -1:
+            json_string = json_string[first_bracket:]
+
+    # Handle POSTFIX by finding last } or ]
+    if POSTFIX in allow:
+        last_brace = json_string.rfind('}')
+        last_bracket = json_string.rfind(']')
+
+        if last_brace != -1 and (last_bracket == -1 or last_brace > last_bracket):
+            json_string = json_string[:last_brace + 1]
+        elif last_bracket != -1:
+            json_string = json_string[:last_bracket + 1]
+
+    # Always enable STR when handling PREFIX/POSTFIX
+    if PREFIX in allow or POSTFIX in allow:
+        allow = Allow(allow | STR)
+
+    return _fix(json_string, allow, True)
+
+
+def fix_fast_old(json_string: str, allow_partial: Union[Allow, int] = ALL):
+    allow = Allow(allow_partial)
+    original_allow = allow
+
+    # Handle PREFIX by finding first { or [
+    if PREFIX in allow:
+        first_brace = json_string.find('{')
+        first_bracket = json_string.find('[')
+
+        if first_brace != -1 and (first_bracket == -1 or first_brace < first_bracket):
+            json_string = json_string[first_brace:]
+        elif first_bracket != -1:
+            json_string = json_string[first_bracket:]
+
+    # Handle POSTFIX by finding matching closing brace/bracket
+    if POSTFIX in allow:
+        # Find opening token
+        first_char = json_string[0] if json_string else ''
+        if first_char not in '{[':
+            # No valid JSON start found
+            return _fix(json_string, original_allow, True)
+
+        # Find matching closing token
+        closing_char = '}' if first_char == '{' else ']'
+        stack = []
+        in_string = False
+
+        for i, char in enumerate(json_string):
+            if char == '"' and (i == 0 or json_string[i-1] != '\\'):
+                in_string = not in_string
+            elif not in_string:
+                if char in '{[':
+                    stack.append(char)
+                elif char in ']}':
+                    if not stack:
+                        break
+                    if (char == '}' and stack[-1] == '{') or (char == ']' and stack[-1] == '['):
+                        stack.pop()
+                        if not stack:  # Found matching closing token
+                            json_string = json_string[:i+1]
+                            break
+
+        # Remove PREFIX/POSTFIX from allow since we've handled them
+        allow = Allow(allow & ~(PREFIX | POSTFIX))
 
     def is_escaped(index: int):
         text_before = json_string[:index]

src/partial_json_parser/core/options.py

@@ -13,12 +13,14 @@ class Allow(IntFlag):
     NAN = auto()
     INFINITY = auto()
     _INFINITY = auto()
+    PREFIX = auto()
+    POSTFIX = auto()
 
     INF = INFINITY | _INFINITY
     SPECIAL = NULL | BOOL | INF | NAN
     ATOM = STR | NUM | SPECIAL
     COLLECTION = ARR | OBJ
-    ALL = ATOM | COLLECTION
+    ALL = ATOM | COLLECTION | PREFIX | POSTFIX
 
 
 STR = Allow.STR
@@ -35,6 +37,8 @@ class Allow(IntFlag):
 ATOM = Allow.ATOM
 COLLECTION = Allow.COLLECTION
 ALL = Allow.ALL
+PREFIX = Allow.PREFIX
+POSTFIX = Allow.POSTFIX
 
 
 __all__ = [
@@ -53,4 +57,6 @@ class Allow(IntFlag):
     "ATOM",
     "COLLECTION",
     "ALL",
+    "PREFIX",
+    "POSTFIX",
 ]