#!/usr/bin/env python3
"""Extract a ranked file-extension census from wizard-work/ledger/repo_files.tsv.

Source: repo_files.tsv is a (rank, path) inventory of the troupe worktree:
  rank<TAB>path

Some path cells were written through a Python repr/json serializer and carry
escaped quotes/newlines; we de-escape, take the basename, and count
extensions (lowercased, leading dot on the suffix unless there is none,
which is emitted as the literal "(none)").

Output (extension-census.csv):
  rank,extension,file_count
  1,.md,829
  ...

and extension-census.md (ranked + totals row).  Run:
  python3 extract_extension_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__))))
SRC = os.path.join(REPO, "repo_files.tsv")
OUT_CSV = os.path.join(REPO, "wizard-work", "ledger", "extension-census.csv")
OUT_MD = os.path.join(REPO, "wizard-work", "ledger", "extension-census.md")


def clean_path(raw: str) -> str:
    s = raw.strip()
    # De-quote a cell that was wrapped in double quotes (Python repr / json).
    if len(s) >= 2 and s[0] == '"' and s[-1] == '"':
        s = s[1:-1]
    # De-escape backslash escapes: \\ -> \, \" -> ", \n -> newline, \t -> tab.
    s = s.encode("latin-1").decode("unicode_escape")
    return s


def ext_of(path: str) -> str:
    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() -> int:
    counts: Counter = Counter()
    total_rows = 0
    with open(SRC, newline="", encoding="utf-8") as f:
        for line in f:
            line = line.rstrip("\n").rstrip("\r")
            if not line.strip():
                continue
            if "\t" not in line:
                continue
            rank, path = line.split("\t", 1)
            path = clean_path(path)
            total_rows += 1
            ext = ext_of(path)
            counts[ext] += 1
    # order: by count desc, then extension asc
    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])
    total_files = sum(counts.values())
    md = []
    md.append("# Extension census")
    md.append("")
    md.append("Ranked census of file extensions across the troupe worktree "
              "(re-derived from `repo_files.tsv` by `extract_extension_census.py`).")
    md.append("")
    md.append("| rank | extension | file_count |")
    md.append("|---|---|---|")
    for i, (ext, n) in enumerate(ordered, 1):
        md.append("| %d | %s | %d |" % (i, ext, n))
    md.append("")
    md.append("**Total files: %d**" % total_files)
    md.append("**Unique extensions: %d**" % len(ordered))
    md.append("")
    with open(OUT_MD, "w", encoding="utf-8") as f:
        f.write("\n".join(md) + "\n")
    print("rows=%d total_files=%d extensions=%d"
          % (total_rows, total_files, len(ordered)))
    print("top10=%s" % ordered[:10])
    return 0


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