Add fix for broken page numbers (UTF-8 issue)

doi2bibtex/process.py

@@ -56,6 +56,9 @@ def postprocess_bibtex(
     # Fix broken ampersand in A&A journal name
     bibtex_dict = fix_broken_ampersand(bibtex_dict)
 
+    # Fix broken page numbers (e.g., "160–175" instead of "160--175")
+    bibtex_dict = fix_broken_pagenumbers(bibtex_dict)
+
     # Convert escaped LaTeX character to proper Unicode
     if config.convert_latex_chars:
         bibtex_dict = convert_latex_chars(bibtex_dict)
@@ -205,6 +208,19 @@ def fix_broken_ampersand(bibtex_dict: dict) -> dict:
     return bibtex_dict
 
 
+def fix_broken_pagenumbers(bibtex_dict: dict) -> dict:
+    """
+    Fix broken pagenumbers (UTF-8 issue: "–" is an en-dash).
+    """
+
+    if "pages" in bibtex_dict:
+        bibtex_dict["pages"] = bibtex_dict["pages"].replace(
+            "–", "--"
+        )
+
+    return bibtex_dict
+
+
 def format_author_names(bibtex_dict: dict) -> dict:
     """
     Clean up the `author` field of a BibTeX entry by splitting it into