Files
landing_page/refer_landing_page/scripts/extract/verify_counts.py
T

136 lines
6.1 KiB
Python

#!/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__))))
sys.path.insert(0, os.path.join(BASE_DIR, "refer_landing_page", "scripts", "extract"))
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 verify():
from generate_all import parse_members, parse_publications, parse_lectures, parse_standards, parse_projects
active_m, alumni_m = parse_members()
intl_p, dom_p, pat_p = parse_publications()
semesters = parse_lectures()
bodies = parse_standards()
projects = parse_projects()
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 / AC-10 / AC-11 / AC-30 / VOLUME CROSS-CHECK) ===")
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: 44)")
print(f"Research Projects: {len(projects)} (Expected: 3)")
errors = []
if len(projects) != 3:
errors.append(f"Research Projects count mismatch: got {len(projects)}, expected 3")
# AC-30: Keyword Substring Verification & AC-32 Deliverable WG Attribution
for proj in projects:
abstract = proj.get("abstract", "")
for kw in proj.get("keywords", []):
if kw not in abstract:
errors.append(f"AC-30 Keyword Violation in project '{proj.get('slug')}': keyword '{kw}' not in abstract")
if proj["slug"] == "ccis":
for d in proj.get("deliverables", []):
if "63246" not in d["ref"]:
errors.append(f"AC-32 Violation: CCIS project deliverable '{d['ref']}' does not belong to CCIS WG (IEC 63246)")
# N1: Title artifact check (No trailing quotes or commas in publication titles)
for p in intl_p + dom_p + pat_p:
t = p.get("title", "")
if re.search(r'["“”]|,$', t):
errors.append(f"N1 Title Artifact Violation in publication '{p.get('id')}': title '{t}' contains quotes or trailing comma")
# 1. Count checks
if len(active_m) != 16:
errors.append(f"Active Members count mismatch: got {len(active_m)}, expected 16")
if len(alumni_m) != 60:
errors.append(f"Alumni count mismatch: got {len(alumni_m)}, expected 60")
if len(intl_p) != 68:
errors.append(f"International Papers count mismatch: got {len(intl_p)}, expected 68")
if len(dom_p) != 80:
errors.append(f"Domestic Papers count mismatch: got {len(dom_p)}, expected 80")
if len(pat_p) != 75:
errors.append(f"Patents count mismatch: got {len(pat_p)}, expected 75")
if total_pubs != 223:
errors.append(f"Total Publications count mismatch: got {total_pubs}, expected 223")
if len(semesters) != 45:
errors.append(f"Semesters count mismatch: got {len(semesters)}, expected 45")
if len(bodies) != 6:
errors.append(f"Standard Bodies count mismatch: got {len(bodies)}, expected 6")
if std_docs_count != 44:
errors.append(f"Standard Documents count mismatch: got {std_docs_count}, expected 44")
# 2. File checks (BOM, Strict ISO 8601, and Semantic Date Ranges)
content_dir = os.path.join(BASE_DIR, "content")
date_regex = re.compile(r'^(19|20)\d{2}(-(0[1-9]|1[0-2]))?(-(0[1-9]|[12]\d|3[01]))?$')
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()
if text.startswith('\ufeff'):
errors.append(f"BOM (U+FEFF) found in {fname}")
dates = re.findall(r'"(publishedAt|applicationAt|registrationAt|graduatedAt)": "([^"]+)"', text)
for k, d in dates:
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 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", "")
if not pub_date:
errors.append(f"Missing publishedAt for paper: {pub.get('title')}")
continue
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:
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 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):")
for err in errors:
print(f" - {err}")
sys.exit(1)
else:
print("\n✅ ALL DATA VERIFICATION GATES PASSED CLEAN (Exit Code 0)")
sys.exit(0)
if __name__ == "__main__":
verify()