fix: resolve review feedback I1-I7 including ISO 8601 dates, footer address, readme routes, and strict verify_counts gate

refer_landing_page/scripts/extract/generate_all.py

@@ -7,6 +7,67 @@ BASE_DIR = os.path.dirname(os.path.dirname(os.path.dirname(os.path.abspath(__fil
 ISL_DIR = os.path.join(BASE_DIR, "..", "ISL-2026")
 CONTENT_DIR = os.path.join(BASE_DIR, "content")
 
+MONTH_MAP = {
+    "january": "01", "jan": "01",
+    "february": "02", "feb": "02",
+    "march": "03", "mar": "03",
+    "april": "04", "apr": "04",
+    "may": "05",
+    "june": "06", "jun": "06",
+    "july": "07", "jul": "07",
+    "august": "08", "aug": "08",
+    "september": "09", "sep": "09", "sept": "09",
+    "october": "10", "oct": "10",
+    "november": "11", "nov": "11",
+    "december": "12", "dec": "12",
+}
+
+def to_iso(raw):
+    if not raw or "in progress" in raw.lower():
+        return None
+    raw = raw.strip()
+    
+    # 1) YYYY-MM-DD or YYYY.MM.DD
+    m = re.search(r'(\d{4})[. /\\-]?(\d{1,2})[. /\\-]?(\d{1,2})', raw)
+    if m:
+        yr = int(m.group(1))
+        mo = int(m.group(2))
+        day = int(m.group(3))
+        if mo <= 12 and day <= 31:
+            return f"{yr:04d}-{mo:02d}-{day:02d}"
+
+    # 2) "May 2026", "Feb. 2008", "August 2018"
+    m_txt = re.search(r'([A-Za-z]+)\.?\s*(\d{4})', raw)
+    if m_txt:
+        mo_str = m_txt.group(1).lower().rstrip('.')
+        yr_str = m_txt.group(2)
+        if mo_str in MONTH_MAP:
+            return f"{yr_str}-{MONTH_MAP[mo_str]}"
+
+    # 3) "2019년 12월", "9월, 1999"
+    m_kor = re.search(r'(\d{4})년\s*(\d{1,2})월', raw)
+    if m_kor:
+        return f"{int(m_kor.group(1)):04d}-{int(m_kor.group(2)):02d}"
+
+    m_kor2 = re.search(r'(\d{1,2})월.*?,?\s*(\d{4})', raw)
+    if m_kor2:
+        return f"{int(m_kor2.group(2)):04d}-{int(m_kor2.group(1)):02d}"
+
+    # 4) YYYY-MM or YYYY.MM
+    m_ym = re.search(r'(\d{4})[. /\\-]?(\d{1,2})', raw)
+    if m_ym:
+        yr = int(m_ym.group(1))
+        mo = int(m_ym.group(2))
+        if mo <= 12:
+            return f"{yr:04d}-{mo:02d}"
+
+    # 5) YYYY only
+    m_y = re.search(r'(\d{4})', raw)
+    if m_y:
+        return f"{int(m_y.group(1)):04d}"
+
+    return raw
+
 def read_file(filename):
     path = os.path.join(ISL_DIR, filename)
     with open(path, "r", encoding="utf-8-sig") as f:
@@ -120,7 +181,6 @@ def parse_publications():
     intl_html = read_file("paper-international.html")
     dom_html = read_file("paper-domestic.html")
     pat_html = read_file("patent.html")
-    month_map = {"January":"01","February":"02","March":"03","April":"04","May":"05","June":"06","July":"07","August":"08","September":"09","October":"10","November":"11","December":"12"}
 
     intl_pubs = []
     intl_items = re.findall(r'<LI>(.*?)</LI>', intl_html, flags=re.S | re.I)
@@ -137,12 +197,7 @@ def parse_publications():
         rest_clean = re.sub(r'<.*?>', '', rest).replace('\n', ' ').strip()
         rest_clean = re.sub(r'^\s*,\s*', '', rest_clean)
 
-        m_date = re.search(r'([A-Za-z]+)\s+(\d{4})', rest_clean)
-        pub_date = "2026-01"
-        if m_date:
-            mo, yr = m_date.group(1), m_date.group(2)
-            if mo in month_map:
-                pub_date = f"{yr}-{month_map[mo]}"
+        pub_date = to_iso(rest_clean) or "2026-01"
 
         intl_pubs.append({
             "category": "intl-journal-conf",
@@ -168,12 +223,7 @@ def parse_publications():
         rest_clean = re.sub(r'^\s*,\s*', '', rest_clean)
 
         is_kci = "(KCI)" in item or "(KCI)" in rest_clean
-
-        m_date = re.search(r'(\d{4})년\s*(\d{1,2})월', rest_clean)
-        if m_date:
-            pub_date = f"{m_date.group(1)}-{int(m_date.group(2)):02d}"
-        else:
-            pub_date = "2026-01"
+        pub_date = to_iso(rest_clean) or "2026-01"
 
         dom_pubs.append({
             "category": "domestic-journal-conf",
@@ -194,7 +244,7 @@ def parse_publications():
         title = lines[0]
         inventors = ""
         app_no = ""
-        app_date = ""
+        app_date = None
         reg_no = None
         reg_date = None
         country = "한국"
@@ -207,14 +257,14 @@ def parse_publications():
                 if m:
                     app_no = m.group(1)
                     country = m.group(2)
-                    app_date = m.group(3).replace('.', '-')
+                    app_date = to_iso(m.group(3))
                 else:
                     app_no = l.replace("출원번호:", "").strip()
             elif l.startswith("등록번호:"):
                 m = re.search(r'등록번호:\s*([\d-]+)\s*\((.*?),\s*([\d.]+)\)', l)
                 if m:
                     reg_no = m.group(1)
-                    reg_date = m.group(3).replace('.', '-')
+                    reg_date = to_iso(m.group(3))
                 else:
                     reg_no = l.replace("등록번호:", "").strip()
 
@@ -287,7 +337,6 @@ def parse_standards():
         role = "Convenor" if "Convenor" in header or "Convenor" in body else None
 
         projects = []
-        # If 'o ' exists, split by 'o '
         if re.search(r'^\s*o\s+', body, flags=re.M):
             proj_blocks = re.split(r'\s*o\s+', body)
             for proj_b in proj_blocks:
@@ -319,7 +368,7 @@ def parse_standards():
                         elif "TS" in d_rest: status = "TS"
 
                         m_date = re.search(r'\((.*?)\)', d_rest)
-                        pub_date = m_date.group(1) if m_date and "In Progress" not in m_date.group(1) else None
+                        pub_date = to_iso(m_date.group(1)) if m_date else None
 
                         docs.append({
                             "title": d_title,
@@ -334,7 +383,6 @@ def parse_standards():
                     "documents": docs
                 })
         else:
-            # Single project body
             doc_items = re.findall(r'<LI>(.*?)</LI>', body, flags=re.S | re.I)
             docs = []
             for d_item in doc_items:
@@ -353,7 +401,7 @@ def parse_standards():
                 elif "TS" in d_rest: status = "TS"
 
                 m_date = re.search(r'\((.*?)\)', d_rest)
-                pub_date = m_date.group(1) if m_date and "In Progress" not in m_date.group(1) else None
+                pub_date = to_iso(m_date.group(1)) if m_date else None
 
                 docs.append({
                     "title": d_title,

refer_landing_page/scripts/extract/verify_counts.py

@@ -1,14 +1,12 @@
 #!/usr/bin/env python3
 import sys
 import os
+import re
 
 BASE_DIR = os.path.dirname(os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
-CONTENT_DIR = os.path.join(BASE_DIR, "refer_landing_page", "content")
-
 sys.path.insert(0, os.path.join(BASE_DIR, "refer_landing_page", "scripts", "extract"))
 
 def verify():
-    # Import generated modules or json
     from generate_all import parse_members, parse_publications, parse_lectures, parse_standards
 
     active_m, alumni_m = parse_members()
@@ -19,15 +17,16 @@ def verify():
     total_pubs = len(intl_p) + len(dom_p) + len(pat_p)
     std_docs_count = sum(len(p["documents"]) for b in bodies for p in b["projects"])
 
-    print("=== DATA VERIFICATION GATE (AC-07 / AC-08) ===")
+    print("=== DATA VERIFICATION GATE (AC-07 / AC-08 / AC-10 / AC-11) ===")
     print(f"Active Members: {len(active_m)} (Expected: 16)")
     print(f"Alumni: {len(alumni_m)} (Expected: 60)")
     print(f"International Papers: {len(intl_p)} (Expected: 68)")
     print(f"Domestic Papers: {len(dom_p)} (Expected: 80)")
     print(f"Patents: {len(pat_p)} (Expected: 75)")
     print(f"Total Publications: {total_pubs} (Expected: 223)")
+    print(f"Lectures Semesters: {len(semesters)} (Expected: 45)")
     print(f"Standard Bodies: {len(bodies)} (Expected: 6)")
-    print(f"Standard Documents: {std_docs_count} (Expected: ~55)")
+    print(f"Standard Documents: {std_docs_count} (Expected: 44)")
 
     errors = []
     if len(active_m) != 16:
@@ -42,9 +41,35 @@ def verify():
         errors.append(f"Patents count mismatch: got {len(pat_p)}, expected 75")
     if total_pubs != 223:
         errors.append(f"Total Publications count mismatch: got {total_pubs}, expected 223")
+    if len(semesters) != 45:
+        errors.append(f"Semesters count mismatch: got {len(semesters)}, expected 45")
+    if len(bodies) != 6:
+        errors.append(f"Standard Bodies count mismatch: got {len(bodies)}, expected 6")
+    if std_docs_count != 44:
+        errors.append(f"Standard Documents count mismatch: got {std_docs_count}, expected 44")
+
+    # Date ISO 8601 validation (AC-11)
+    content_dir = os.path.join(BASE_DIR, "content")
+    for fname in ["members.ts", "publications.ts", "lectures.ts", "standards.ts"]:
+        fpath = os.path.join(content_dir, fname)
+        if not os.path.exists(fpath):
+            errors.append(f"Missing content file: {fname}")
+            continue
+        with open(fpath, "r", encoding="utf-8") as f:
+            text = f.read()
+
+        # Check BOM (AC-10)
+        if text.startswith('\ufeff'):
+            errors.append(f"BOM found in {fname}")
+
+        # Check dates
+        dates = re.findall(r'"(publishedAt|applicationAt|registrationAt|graduatedAt)": "([^"]+)"', text)
+        for k, d in dates:
+            if not re.match(r'^\d{4}(-\d{2})?(-\d{2})?$', d):
+                errors.append(f"Non-ISO 8601 date in {fname}: {k}='{d}'")
 
     if errors:
-        print("\n❌ VERIFICATION FAILED:")
+        print("\n❌ DATA VERIFICATION FAILED:")
         for err in errors:
             print(f" - {err}")
         sys.exit(1)