codex_extractor_codexmode.py

import os
import json
import sys
import re

def parse_codex_blocks(md_text):
    entries = []
    current_entry = {}
    lines = md_text.splitlines()
    for line in lines:
        line = line.strip()
        if line.startswith("@"):
            if "@category:" in line and current_entry:
                entries.append(current_entry)
                current_entry = {}
            if ":" in line:
                key, value = line.split(":", 1)
                key = key.strip().lstrip("@")
                value = value.strip()
                try:
                    parsed_value = json.loads(value)
                    current_entry[key] = parsed_value
                except:
                    # fallback: handle manually typed arrays like [tag1, tag2]
                    if value.startswith("[") and value.endswith("]") and "," in value:
                        stripped = value[1:-1]
                        parts = [part.strip().strip('"').strip("'") for part in stripped.split(",")]
                        current_entry[key] = parts
                    else:
                        current_entry[key] = value.strip('"')
        elif line.startswith("#") and current_entry:
            current_entry["title"] = line.lstrip("#").strip()
    if current_entry:
        entries.append(current_entry)
    return entries

def write_codex_json(chapter_file, entries):
    output_dir = os.path.join(os.path.dirname(__file__), "codex_json")
    os.makedirs(output_dir, exist_ok=True)
    base_name = os.path.basename(chapter_file).replace(".md", "")
    json_filename = os.path.join(output_dir, f"codex_{base_name}.json")
    with open(json_filename, "w") as f:
        json.dump(entries, f, indent=2)
    print(f"[✓] Codex exported to: {json_filename}")
    return json_filename, os.path.join(output_dir, f"codex_{base_name}_scan.log")

def scan_symbols(md_text):
    results = []
    symbol_map = {
        '"': 'Double Quote',
        "'": 'Single Quote',
        '{': 'Curly Brace Open',
        '}': 'Curly Brace Close',
        '[': 'Square Bracket Open',
        ']': 'Square Bracket Close',
        '(': 'Parenthesis Open',
        ')': 'Parenthesis Close',
        '<': 'Angle Bracket Open',
        '>': 'Angle Bracket Close'
    }
    for i, line in enumerate(md_text.splitlines(), 1):
        for symbol in symbol_map:
            if symbol in line:
                results.append(f"Line {i}: {symbol_map[symbol]} → {line.strip()}")
    return results

if __name__ == "__main__":
    if len(sys.argv) != 2:
        print("Usage: python3 codex_extractor_codexmode_v3.py <chapter_file.md>")
        sys.exit(1)

    chapter_file = sys.argv[1]
    if not os.path.exists(chapter_file):
        print(f"[ERROR] File not found: {chapter_file}")
        sys.exit(1)

    with open(chapter_file, "r") as f:
        md_text = f.read()

    # Extract codex blocks
    codex_entries = parse_codex_blocks(md_text)
    json_path, log_path = write_codex_json(chapter_file, codex_entries)

    # Run and save symbol scan
    print("\n=== Symbol Scan ===")
    symbol_results = scan_symbols(md_text)
    with open(log_path, "w") as log_file:
        for res in symbol_results:
            print(res)
            log_file.write(res + "\n")