Legalize Es Spanish Legislation

import osimport yaml
def parse_law(filepath):    """Parse a law Markdown file and return frontmatter + body."""    with open(filepath, 'r', encoding='utf-8') as f:        content = f.read()        # Extract YAML frontmatter between --- delimiters    if content.startswith('---'):        parts = content.split('---', 2)        if len(parts) >= 3:            metadata = yaml.safe_load(parts[1])            body = parts[2].strip()            return metadata, body        return {}, content
# Example: list all active lawslaws_dir = 'spain'active_laws = []
for filename in os.listdir(laws_dir):    if filename.endswith('.md'):        filepath = os.path.join(laws_dir, filename)        meta, body = parse_law(filepath)        if meta.get('estado') == 'vigente':            active_laws.append({                'id': meta.get('identificador'),                'titulo': meta.get('titulo'),                'rango': meta.get('rango'),                'ultima_actualizacion': meta.get('ultima_actualizacion'),            })
# Sort by last updateactive_laws.sort(key=lambda x: x['ultima_actualizacion'] or '', reverse=True)for law in active_laws[:10]:    print(f"{law['ultima_actualizacion']} [{law['rango']}] {law['titulo']}")

import subprocessimport json
def get_reform_history(boe_id):    """Get all commits that modified a law file."""    filepath = f"spain/{boe_id}.md"    result = subprocess.run(        ['git', 'log', '--format=%H|%ad|%s', '--date=short', '--', filepath],        capture_output=True, text=True    )    reforms = []    for line in result.stdout.strip().split('\n'):        if line:            hash_, date, subject = line.split('|', 2)            reforms.append({'hash': hash_, 'date': date, 'subject': subject})    return reforms
# Example usagehistory = get_reform_history('BOE-A-1978-31229')for reform in history:    print(f"{reform['date']} {reform['hash'][:7]} {reform['subject']}")

import subprocess
def diff_law_versions(boe_id, commit_before, commit_after):    """Get unified diff between two versions of a law."""    filepath = f"spain/{boe_id}.md"    result = subprocess.run(        ['git', 'diff', f'{commit_before}..{commit_after}', '--', filepath],        capture_output=True, text=True    )    return result.stdout
def get_law_at_date(boe_id, date_str):    """Get the text of a law as it was on a given date (YYYY-MM-DD)."""    filepath = f"spain/{boe_id}.md"    # Find the last commit before date    rev = subprocess.run(        ['git', 'rev-list', '-1', f'--before={date_str}', 'HEAD'],        capture_output=True, text=True    ).stdout.strip()        if not rev:        return None        content = subprocess.run(        ['git', 'show', f'{rev}:{filepath}'],        capture_output=True, text=True    ).stdout    return content
# Example: see Constitution before and after 2011 reformold_text = get_law_at_date('BOE-A-1978-31229', '2011-09-26')new_text = get_law_at_date('BOE-A-1978-31229', '2011-09-28')print("Pre-reform length:", len(old_text))print("Post-reform length:", len(new_text))

import osimport re
def search_laws(query, laws_dir='spain', rango=None, estado='vigente'):    """Search for a regex pattern across all laws."""    results = []    pattern = re.compile(query, re.IGNORECASE)        for filename in os.listdir(laws_dir):        if not filename.endswith('.md'):            continue        filepath = os.path.join(laws_dir, filename)        with open(filepath, 'r', encoding='utf-8') as f:            content = f.read()                # Filter by frontmatter fields        if estado and f'estado: "{estado}"' not in content:            continue        if rango and f'rango: "{rango}"' not in content:            continue                matches = list(pattern.finditer(content))        if matches:            titulo_match = re.search(r'titulo: "([^"]+)"', content)            titulo = titulo_match.group(1) if titulo_match else filename            results.append({                'file': filename,                'titulo': titulo,                'match_count': len(matches),                'first_match_context': content[max(0, matches[0].start()-100):matches[0].end()+100]            })        return sorted(results, key=lambda x: x['match_count'], reverse=True)
# Example: find all active organic laws mentioning "privacidad"hits = search_laws("privacidad", rango="ley-organica")for h in hits:    print(f"[{h['match_count']} matches] {h['titulo']}")    print(f"  Context: ...{h['first_match_context'].strip()[:150]}...")    print()

import os, yaml, json
laws = []for fname in os.listdir('spain'):    if not fname.endswith('.md'):        continue    with open(f'spain/{fname}', 'r', encoding='utf-8') as f:        content = f.read()    if content.startswith('---'):        parts = content.split('---', 2)        if len(parts) >= 3:            meta = yaml.safe_load(parts[1])            meta['filename'] = fname            laws.append(meta)
with open('laws_index.json', 'w', encoding='utf-8') as f:    json.dump(laws, f, ensure_ascii=False, indent=2, default=str)
print(f"Exported {len(laws)} laws")