summarize.py

import argparse, csv, json, datetime
from collections import defaultdict, Counter

def load_schema(p):
    with open(p,'r',encoding='utf-8') as f: return json.load(f)

def tag_text(text, schema):
    text_l = text.lower(); preds=set()
    for tag,kws in schema.items():
        for kw in kws:
            if kw in text_l: preds.add(tag); break
    return preds

def main():
    ap=argparse.ArgumentParser()
    ap.add_argument('--notes', required=True)
    ap.add_argument('--schema', default='tag_schema.json')
    ap.add_argument('--out', required=True)
    args=ap.parse_args()

    schema = load_schema(args.schema)
    rows = list(csv.DictReader(open(args.notes,encoding='utf-8')))
    weeks = defaultdict(list)
    for r in rows:
        d = datetime.date.fromisoformat(r['date'])
        year,week,_ = d.isocalendar()
        weeks[(year,week)].append(r)

    lines=[]
    for (year,week), items in sorted(weeks.items()):
        lines.append(f"# Week {year}-W{week}\n\n")
        tag_counts = Counter()
        for it in items:
            tag_counts.update(tag_text(it['note'], schema))
        lines.append("## Tag highlights\n")
        for t,c in tag_counts.most_common():
            lines.append(f"- {t}: {c}\n")
        lines.append("\n## Notes\n")
        for it in items:
            lines.append(f"- {it['date']} ({it['child']}): {it['note']}\n")
        lines.append("\n---\n\n")
    with open(args.out,'w',encoding='utf-8') as f: f.write(''.join(lines))
    print(f"Wrote {args.out}")

if __name__=='__main__': main()