fix: resolve edge case date parsing for volume strings and update volume date verification gate

refer_landing_page/scripts/extract/verify_counts.py

@@ -77,7 +77,9 @@ def verify():
             if not date_regex.match(d):
                 errors.append(f"Invalid ISO 8601 or out-of-bounds date in {fname}: {k}='{d}'")
 
-    # 3. Volume Cross-Check for Publications (Ensures volume year matches publishedAt year)
+    # 3. Volume Cross-Check for Publications (Ensures volume date candidates match publishedAt)
+    MON_PAT = r'(?:January|February|March|April|May|June|July|August|September|October|November|December|Jan|Feb|Mar|Apr|May|Jun|Jul|Aug|Sep|Oct|Nov|Dec)'
+
     for pub in intl_p + dom_p:
         vol = pub.get("volume", "")
         pub_date = pub.get("publishedAt", "")
@@ -85,23 +87,17 @@ def verify():
             errors.append(f"Missing publishedAt for paper: {pub.get('title')}")
             continue
 
-        # Look for English month + 19XX/20XX year or Korean YYYY년 MM월
-        m_txt = re.search(r'([A-Za-z]+)\.?\s*,?\s*((?:19|20)\d{2})', vol)
-        m_kor = re.search(r'((?:19|20)\d{2})년\s*(\d{1,2})월', vol)
-        m_kor2 = re.search(r'(\d{1,2})월\s*,?\s*((?:19|20)\d{2})', vol)
-
-        expected_yr = None
-        if m_txt:
-            mo_str = m_txt.group(1).lower().rstrip('.')
+        cands = []
+        for m in re.finditer(rf'\b({MON_PAT})\.?\s*,?\s*((?:19|20)\d{{2}})', vol, re.I):
+            mo_str = m.group(1).lower().rstrip('.')
             if mo_str in MONTH_MAP:
-                expected_yr = m_txt.group(2)
-        elif m_kor:
-            expected_yr = m_kor.group(1)
-        elif m_kor2:
-            expected_yr = m_kor2.group(2)
+                cands.append(m.group(2))
+        for m in re.finditer(r'((?:19|20)\d{2})\s*년\s*(\d{1,2})\s*월', vol):
+            cands.append(m.group(1))
 
-        if expected_yr and not pub_date.startswith(expected_yr):
-            errors.append(f"Volume date mismatch for '{pub.get('title')}': volume has {expected_yr}, publishedAt is {pub_date}")
+        if cands:
+            if not any(pub_date.startswith(yr) for yr in cands):
+                errors.append(f"Volume date mismatch for '{pub.get('title')}': volume candidates={cands}, publishedAt={pub_date}")
 
     if errors:
         print(f"\n❌ DATA VERIFICATION FAILED ({len(errors)} errors):")