#!/usr/bin/env python3
"""Extract a ranked file-extension census for the committed ledger directory.

Source of truth: the committed inventory file `wizard-work/ledger/repo_files.tsv`,
a (rank, path) inventory of the troupe worktree. Only rows whose path lives under
`wizard-work/ledger/` are counted.

Normalization: take the basename, lower-case the suffix, leading dot on the
suffix unless there is none, which is emitted as the literal "(none)".

Output (ledger-dir-census.csv):
  rank,extension,file_count
  1,.py,217
  ...

and ledger-dir-census.md (ranked table + totals).

Run:  python3 extract_ledger_dir_census.py
"""
import csv
import os
import sys
from collections import Counter

REPO = os.path.dirname(os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
LEDGER_DIR = os.path.join(REPO, "wizard-work", "ledger")
SRC = os.path.join(LEDGER_DIR, "repo_files.tsv")

OUT_CSV = os.path.join(LEDGER_DIR, "ledger-dir-census.csv")
OUT_MD = os.path.join(LEDGER_DIR, "ledger-dir-census.md")


def clean_path(raw):
    s = raw.strip()
    if len(s) >= 2 and s[0] == '"' and s[-1] == '"':
        s = s[1:-1]
    s = s.encode("latin-1").decode("unicode_escape", "replace")
    return s


def ext_of(path):
    base = os.path.basename(path.rstrip("/"))
    if not base or base in (".", ".."):
        return "(none)"
    if "." in base:
        return "." + base.rsplit(".", 1)[1].lower()
    return "(none)"


def main():
    counts = Counter()
    total = 0
    with open(SRC, "r", encoding="utf-8", errors="replace") as f:
        for line in f:
            line = line.rstrip("\n").rstrip("\r")
            if "\t" not in line:
                continue
            rank, path = line.split("\t", 1)
            path = clean_path(path)
            if not path.startswith("wizard-work/ledger/"):
                continue
            total += 1
            counts[ext_of(path)] += 1

    ordered = sorted(counts.items(), key=lambda kv: (-kv[1], kv[0]))

    with open(OUT_CSV, "w", newline="", encoding="utf-8") as f:
        w = csv.writer(f)
        w.writerow(["rank", "extension", "file_count"])
        for i, (ext, n) in enumerate(ordered, 1):
            w.writerow([i, ext, n])

    md = [
        "# Ledger directory census",
        "",
        "Ranked census of file extensions inside `wizard-work/ledger/`,",
        "re-derived from the committed inventory `repo_files.tsv` by",
        "`extract_ledger_dir_census.py`.",
        "",
        "| rank | extension | file_count |",
        "|---|---|---|",
    ]
    for i, (ext, n) in enumerate(ordered, 1):
        md.append("| %d | %s | %d |" % (i, ext, n))
    md += [
        "",
        "**Total files: %d**" % total,
        "**Unique extensions: %d**" % len(ordered),
        "",
    ]
    with open(OUT_MD, "w", encoding="utf-8") as f:
        f.write("\n".join(md))

    print("rows=%d total_files=%d extensions=%d" % (total, total, len(ordered)))
    print("top10=%s" % ordered[:10])
    return 0


if __name__ == "__main__":
    sys.exit(main())