landing_page/backend/scripts/export_ts_to_json.py

#!/usr/bin/env python3
"""
Exports curated data from refer_landing_page/content/*.ts and app/page.tsx into backend/seed/data/*.json.
Ensures is_highlight is properly tagged on the 5 representative publications.
"""

import json
import os
import re
import sys

REPO_ROOT = os.path.dirname(os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
CONTENT_DIR = os.path.join(REPO_ROOT, "refer_landing_page", "content")
SEED_DATA_DIR = os.path.join(REPO_ROOT, "backend", "seed", "data")
PAGE_TSX = os.path.join(REPO_ROOT, "refer_landing_page", "app", "page.tsx")

os.makedirs(SEED_DATA_DIR, exist_ok=True)

HIGHLIGHT_TITLES = {
    "Globally Integrated Trust Authority (GITA) for Resource-Constrained Edge Devices in IoT and 6G",
    "Application Level Trust Authority (APPLETA) for Resource-Constrained Edge Devices in IoT and 6G",
    "mQUIC: Use of QUIC for Handover Support with Connection Migration in Wireless/Mobile Networks",
    "Use of QUIC for CoAP Transport in IoT Networks",
    "Use of QUIC for Mobile-Oriented Future Internet (Q-MOFI)",
}

def clean_json_str(s):
    # Remove trailing commas before ] or }
    s = re.sub(r',\s*\]', ']', s)
    s = re.sub(r',\s*\}', '}', s)
    return s

def extract_json_array_from_ts(filepath, var_name):
    with open(filepath, "r", encoding="utf-8") as f:
        content = f.read()
    
    # Match export const <var_name>[: Type] = [ ... ];
    pattern = rf'export\s+const\s+{var_name}(?:\s*:\s*[^=]+)?\s*=\s*(\[\s*[\s\S]*?\s*\]);'
    match = re.search(pattern, content)
    if not match:
        raise ValueError(f"Could not find array literal for '{var_name}' in {filepath}")
    
    array_str = clean_json_str(match.group(1))
    return json.loads(array_str)

def main():
    print("=== Extracting TypeScript content to JSON for SQLite seeding ===")
    
    # 1. Projects
    projects_file = os.path.join(CONTENT_DIR, "projects.ts")
    projects = extract_json_array_from_ts(projects_file, "researchProjects")
    with open(os.path.join(SEED_DATA_DIR, "research_projects.json"), "w", encoding="utf-8") as f:
        json.dump(projects, f, indent=2, ensure_ascii=False)
    print(f"✓ Extracted {len(projects)} research projects")

    # 2. Research Areas (from app/page.tsx)
    with open(PAGE_TSX, "r", encoding="utf-8") as f:
        page_src = f.read()
    areas_match = re.search(r'const\s+RESEARCH_AREAS(?:\s*:\s*[^=]+)?\s*=\s*(\[\s*[\s\S]*?\s*\]);', page_src)
    if not areas_match:
        raise ValueError("Could not find RESEARCH_AREAS in app/page.tsx")
    areas_str = clean_json_str(areas_match.group(1))
    areas_list = json.loads(areas_str)
    research_areas = [{"name_en": name, "name_kr": None, "display_order": i + 1} for i, name in enumerate(areas_list)]
    with open(os.path.join(SEED_DATA_DIR, "research_areas.json"), "w", encoding="utf-8") as f:
        json.dump(research_areas, f, indent=2, ensure_ascii=False)
    print(f"✓ Extracted {len(research_areas)} research areas")

    # 3. Members & Alumni
    members_file = os.path.join(CONTENT_DIR, "members.ts")
    active_members = extract_json_array_from_ts(members_file, "activeMembers")
    alumni = extract_json_array_from_ts(members_file, "alumni")
    
    # Format active members with is_advisor
    formatted_members = []
    for i, m in enumerate(active_members):
        formatted_members.append({
            "name_ko": m["ko"],
            "name_en": m["en"],
            "degree": m["degree"],
            "affiliation": m.get("affiliation"),
            "email": "sjkoh@knu.ac.kr" if m["degree"] == "Professor" else None,
            "is_advisor": m["degree"] == "Professor",
            "display_order": i + 1,
        })
    with open(os.path.join(SEED_DATA_DIR, "members.json"), "w", encoding="utf-8") as f:
        json.dump(formatted_members, f, indent=2, ensure_ascii=False)
    print(f"✓ Extracted {len(formatted_members)} active members")

    formatted_alumni = []
    for a in alumni:
        formatted_alumni.append({
            "name_ko": a["ko"],
            "name_en": a["en"],
            "degree": a["degree"],
            "graduated_at": a["graduatedAt"],
            "major": a.get("major"),
            "current_position": a.get("currentPosition"),
        })
    with open(os.path.join(SEED_DATA_DIR, "alumni.json"), "w", encoding="utf-8") as f:
        json.dump(formatted_alumni, f, indent=2, ensure_ascii=False)
    print(f"✓ Extracted {len(formatted_alumni)} alumni")

    # 4. Publications & Patents
    pubs_file = os.path.join(CONTENT_DIR, "publications.ts")
    raw_pubs = extract_json_array_from_ts(pubs_file, "publications")
    raw_patents = extract_json_array_from_ts(pubs_file, "patents")

    matched_highlights = []
    formatted_pubs = []
    for p in raw_pubs:
        title_clean = p["title"].strip()
        is_hl = title_clean in HIGHLIGHT_TITLES
        if is_hl:
            matched_highlights.append(title_clean)
        formatted_pubs.append({
            "category": p["category"],
            "title": p["title"],
            "authors": p.get("authors"),
            "venue": p["venue"],
            "volume": p.get("volume"),
            "published_at": p["publishedAt"],
            "kci": bool(p.get("kci", False)),
            "doi": p.get("doi"),
            "is_highlight": is_hl,
        })
    
    if len(matched_highlights) != 5:
        raise ValueError(f"Highlight matching error: expected exactly 5 matched highlights, found {len(matched_highlights)}: {matched_highlights}")

    with open(os.path.join(SEED_DATA_DIR, "publications.json"), "w", encoding="utf-8") as f:
        json.dump(formatted_pubs, f, indent=2, ensure_ascii=False)
    print(f"✓ Extracted {len(formatted_pubs)} publications (exactly {len(matched_highlights)} highlights tagged)")

    formatted_patents = []
    for pat in raw_patents:
        formatted_patents.append({
            "title": pat["title"],
            "inventors": pat["inventors"],
            "application_no": pat["applicationNo"],
            "application_at": pat["applicationAt"],
            "registration_no": pat.get("registrationNo"),
            "registration_at": pat.get("registrationAt"),
            "country": pat["country"],
            "published_at": pat["publishedAt"],
        })
    with open(os.path.join(SEED_DATA_DIR, "patents.json"), "w", encoding="utf-8") as f:
        json.dump(formatted_patents, f, indent=2, ensure_ascii=False)
    print(f"✓ Extracted {len(formatted_patents)} patents")

    # 5. Lectures (Semesters & Courses)
    lectures_file = os.path.join(CONTENT_DIR, "lectures.ts")
    raw_semesters = extract_json_array_from_ts(lectures_file, "semesters")
    with open(os.path.join(SEED_DATA_DIR, "lectures.json"), "w", encoding="utf-8") as f:
        json.dump(raw_semesters, f, indent=2, ensure_ascii=False)
    
    total_courses = sum(len(s.get("courses", [])) for s in raw_semesters)
    print(f"✓ Extracted {len(raw_semesters)} semesters with {total_courses} courses")

    # 6. Standardization
    standards_file = os.path.join(CONTENT_DIR, "standards.ts")
    raw_standards = extract_json_array_from_ts(standards_file, "standardsBodies")
    with open(os.path.join(SEED_DATA_DIR, "standards.json"), "w", encoding="utf-8") as f:
        json.dump(raw_standards, f, indent=2, ensure_ascii=False)
    
    total_docs = sum(
        sum(len(p.get("documents", [])) for p in b.get("projects", []))
        for b in raw_standards
    )
    print(f"✓ Extracted {len(raw_standards)} standards bodies with {total_docs} documents")

    print("=== Extraction completed successfully ===")

if __name__ == "__main__":
    main()