Miscs (Interro 28)

post-correction.py

@@ -7,6 +7,46 @@ import argparse
 if len(sys.argv) < 2:
     sys.exit("Usage: python script.py <InputDir>")
 
+def escape_latex_underscores(text):
+    r"""
+    Escape '_' outside LaTeX math environments.
+    Supports:
+      - $...$
+      - $$...$$
+      - \( ... \)
+      - \[ ... \]
+    """
+
+    # Regex matching LaTeX math blocks
+    math_pattern = re.compile(
+        r'(\$\$.*?\$\$|'      # $$...$$
+        r'\$.*?\$|'           # $...$
+        r'\\\(.*?\\\)|'       # \( ... \)
+        r'\\\[.*?\\\])',      # \[ ... \]
+        re.DOTALL
+    )
+
+    parts = []
+    last_end = 0
+
+    for match in math_pattern.finditer(text):
+        start, end = match.span()
+
+        # Escape underscores outside math
+        outside = text[last_end:start].replace('_', r'\_')
+        parts.append(outside)
+
+        # Keep math block unchanged
+        parts.append(match.group(0))
+
+        last_end = end
+
+    # Remaining text after last math block
+    outside = text[last_end:].replace('_', r'\_')
+    parts.append(outside)
+
+    return ''.join(parts)
+
 arg_path = Path(sys.argv[1])
 tasks = [] # List of tuples: (filepath_str, label_str)
 results = {}
@@ -79,7 +119,8 @@ def clean_string(s: str) -> str:
     if '\x00' in s:
         s = fast_fix(s)
         s = s.replace('\x00', '')
-    return some_other_replacements(s)
+    s = some_other_replacements(s)
+    return escape_latex_underscores(s)
 
 
 def clean_obj(obj):