Files

111 lines
3.6 KiB
Python

import os
import re
import uuid
import sys
from datetime import datetime
# UTF-8 출력 보정
if sys.stdout.encoding != 'utf-8':
import io
sys.stdout = io.TextIOWrapper(sys.stdout.buffer, encoding='utf-8')
base_dir = r"e:\Wiki\2nd"
raw_dir = os.path.join(base_dir, "00_Raw", "2026-04-20")
wiki_base = os.path.join(base_dir, "10_Wiki", "💡 Topics")
batch_files = [
"3D Gaussian Splatting (3DGS).md",
"3D Web-based HMI.md",
"ABA(Applied Behavior Analysis).md",
"Abstract Syntax Tree (AST).md",
"Accessibility (A11y).md",
"Addiction Neuroscience.md",
"Adaptive-Learning-Systems.md",
"Adversarial Attack (적대적 공격).md",
"ACL-Injury-Prevention-Protocols.md",
"API-First Architecture.md"
]
mapping = {
"3D Gaussian Splatting (3DGS).md": "Graphics & Performance",
"3D Web-based HMI.md": "Automation & Industry",
"ABA(Applied Behavior Analysis).md": "Psychology & Behavior",
"Abstract Syntax Tree (AST).md": "Programming & Language",
"Accessibility (A11y).md": "Design & Experience",
"Addiction Neuroscience.md": "Psychology & Behavior",
"Adaptive-Learning-Systems.md": "Education & AI",
"Adversarial Attack (적대적 공격).md": "Security & AI",
"ACL-Injury-Prevention-Protocols.md": "Health & Science",
"API-First Architecture.md": "Software Architecture"
}
def wikify(filename):
raw_path = os.path.join(raw_dir, filename)
if not os.path.exists(raw_path):
print(f"File not found: {raw_path}")
return
with open(raw_path, "r", encoding="utf-8") as f:
content = f.read()
title_match = re.search(r'^#\s*\[\[(.*?)\]\]', content, re.M)
if not title_match:
title_match = re.search(r'^\[\[(.*?)\]\]', content, re.M)
title = title_match.group(1) if title_match else filename.replace(".md", "")
sub_folder = mapping.get(filename, "Uncategorized")
category_path = f"10_Wiki/💡 Topics/{sub_folder}"
# Extract sections
summary_match = re.search(r'##?\s*📌\s*Brief Summary\n(.*?)(?=\n##|$)', content, re.S)
summary = summary_match.group(1).strip() if summary_match else ""
core_match = re.search(r'##?\s*📖\s*Core Content\n(.*?)(?=\n##|$)', content, re.S)
core = core_match.group(1).strip() if core_match else ""
conn_match = re.search(r'##?\s*🔗\s*Knowledge Connections\n(.*?)(?=\n##|$)', content, re.S)
conn = conn_match.group(1).strip() if conn_match else ""
doc_id = f"P-REINFORCE-AI-{uuid.uuid4().hex[:6].upper()}"
today = datetime.now().strftime("%Y-%m-%d")
wiki_content = f"""---
id: {doc_id}
category: "[[{category_path}]]"
confidence_score: 0.95
tags: []
last_reinforced: {today}
github_commit: "[P-Reinforce] Batch 9 - Wikified {title}"
---
# [[{title}]]
## 📌 한 줄 통찰 (The Karpathy Summary)
> {summary}
## 📖 구조화된 지식 (Synthesized Content)
{core}
## ⚠️ 모순 및 업데이트 (Contradictions & RL Update)
- **과거 데이터와의 충돌:** 신규 문서로, 기존 정보와의 충돌 분석 예정.
- **정책 변화:** {sub_folder} 카테고리의 지식 연결망 강화를 위한 표준 위키화 적용.
## 🔗 지식 연결 (Graph)
{conn}
- Raw Source: [[00_Raw/2026-04-20/{filename}]]
---
"""
target_dir = os.path.join(base_dir, category_path.replace("/", os.sep))
if not os.path.exists(target_dir):
os.makedirs(target_dir)
target_path = os.path.join(target_dir, f"{title}.md")
with open(target_path, "w", encoding="utf-8") as f:
f.write(wiki_content)
print(f"Processed: {filename} -> {target_path}")
if __name__ == "__main__":
for f in batch_files:
wikify(f)