ledger: extension census 2026-11-03 verified 31 rows

CHECK-extension-census-2026-11-03

@@ -0,0 +1,7 @@
+#!/usr/bin/env bash
+# CHECK -- extension census (extract lane). Exit 0 iff the committed
+# wizard-work/ledger/extension-census.csv is byte-identical to a fresh
+# re-derivation from repo_files.tsv.
+set -u
+cd "$(dirname "${BASH_SOURCE[0]}")" || exit 2
+exec python3 wizard-work/ledger/verify_extension_census.py

wizard-work/ledger/README-extension-census.md

@@ -0,0 +1,27 @@
+# Extension census 2026-11-03
+
+Ranked census of file extensions across the troupe worktree.
+
+- **Source:** `repo_files.tsv` (rank<TAB>path inventory, 3345 file rows).
+- **Artifact:** `extension-census.csv` (rank, extension, file_count) — 31 rows.
+- **Interactive view:** `extension-census.md` (ranked table + totals).
+- **Independent verifier:** `verify_extension_census.py` — re-derives from
+  `repo_files.tsv` with a standalone loop and asserts byte-match; exit 0.
+- **CHECK file:** `../CHECK-extension-census-2026-11-03`.
+
+Ranked top of the census (full list in `extension-census.csv`):
+
+| rank | extension | file_count |
+|---|---|---|
+| 1 | .md | 829 |
+| 2 | .png | 803 |
+| 3 | .py | 653 |
+| 4 | .txt | 551 |
+| 5 | .json | 231 |
+| 6 | .sh | 56 |
+| 7 | .html | 55 |
+| 8 | .csv | 43 |
+| 9 | .svg | 31 |
+| 10 | .age | 16 |
+
+**Totals:** 3345 files, 31 unique extensions.

wizard-work/ledger/extension-census.csv

@@ -0,0 +1,32 @@
+rank,extension,file_count
+1,.md,829
+2,.png,803
+3,.py,653
+4,.txt,551
+5,.json,231
+6,.sh,56
+7,.html,55
+8,.csv,43
+9,.svg,31
+10,.age,16
+11,.tsv,15
+12,.xml,12
+13,(none),11
+14,.gitignore,5
+15,.log,5
+16,.pdf,4
+17,.sha256,4
+18,.jsonl,3
+19,.mp3,3
+20,.c,2
+21,.diff,2
+22,.jpg,2
+23,.check,1
+24,.dl,1
+25,.goyiwz,1
+26,.gz,1
+27,.mailmap,1
+28,.md5,1
+29,".py""""",1
+30,.rc,1
+31,.yaml,1

wizard-work/ledger/extension-census.manifest.json

@@ -0,0 +1,10 @@
+{
+  "source": "repo_files.tsv",
+  "rows": 31,
+  "total_files": 3345,
+  "unique_extensions": 31,
+  "extractor": "extract_extension_census.py",
+  "verifier": "verify_extension_census.py",
+  "check": "CHECK-extension-census-2026-11-03",
+  "created_utc": "2026-11-03T00:00:00Z"
+}

wizard-work/ledger/extension-census.md

@@ -0,0 +1,41 @@
+# Extension census
+
+Ranked census of file extensions across the troupe worktree (re-derived from `repo_files.tsv` by `extract_extension_census.py`).
+
+| rank | extension | file_count |
+|---|---|---|
+| 1 | .md | 829 |
+| 2 | .png | 803 |
+| 3 | .py | 653 |
+| 4 | .txt | 551 |
+| 5 | .json | 231 |
+| 6 | .sh | 56 |
+| 7 | .html | 55 |
+| 8 | .csv | 43 |
+| 9 | .svg | 31 |
+| 10 | .age | 16 |
+| 11 | .tsv | 15 |
+| 12 | .xml | 12 |
+| 13 | (none) | 11 |
+| 14 | .gitignore | 5 |
+| 15 | .log | 5 |
+| 16 | .pdf | 4 |
+| 17 | .sha256 | 4 |
+| 18 | .jsonl | 3 |
+| 19 | .mp3 | 3 |
+| 20 | .c | 2 |
+| 21 | .diff | 2 |
+| 22 | .jpg | 2 |
+| 23 | .check | 1 |
+| 24 | .dl | 1 |
+| 25 | .goyiwz | 1 |
+| 26 | .gz | 1 |
+| 27 | .mailmap | 1 |
+| 28 | .md5 | 1 |
+| 29 | .py"" | 1 |
+| 30 | .rc | 1 |
+| 31 | .yaml | 1 |
+
+**Total files: 3345**
+**Unique extensions: 31**
+

wizard-work/ledger/extract_extension_census.py

@@ -0,0 +1,96 @@
+#!/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())

wizard-work/ledger/verify_extension_census.py

@@ -0,0 +1,83 @@
+#!/usr/bin/env python3
+"""Independent verifier for the extension census.
+
+Re-derives the census from the SOURCE file `repo_files.tsv` (rank<TAB>path,
+CRLF) with a standalone loop -- it never imports extract_extension_census --
+normalizes CRLF line endings, and asserts the resulting ranked (extension,
+count) table byte-matches `extension-census.csv` produced by that script.
+
+Exit code 0 = artifact matches re-derivation; 1 = mismatch; 2 = misuse.
+"""
+import csv
+import os
+import sys
+
+REPO = os.path.dirname(os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
+SRC = os.path.join(REPO, "repo_files.tsv")
+ART = os.path.join(REPO, "wizard-work", "ledger", "extension-census.csv")
+
+PASS = 0
+
+
+def clean_path(raw):
+    s = raw.strip()
+    if len(s) >= 2 and s[0] == '"' and s[-1] == '"':
+        s = s[1:-1]
+    return s.encode("latin-1", "replace").decode("unicode_escape", "replace")
+
+
+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 re_derivation():
+    counts = {}
+    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
+            path = clean_path(line.split("\t", 1)[1])
+            total += 1
+            ext = ext_of(path)
+            counts[ext] = counts.get(ext, 0) + 1
+    return sorted(counts.items(), key=lambda kv: (-kv[1], kv[0]))
+
+
+def read_artifact():
+    rows = []
+    with open(ART, newline="", encoding="utf-8") as f:
+        for row in csv.reader(f):
+            rows.append(row)
+    return rows[0], rows[1:]
+
+
+def main():
+    global PASS
+    header, rows = read_artifact()
+    if header != ["rank", "extension", "file_count"]:
+        print("FAIL: bad header %r" % (header,))
+        return 1
+    expected = re_derivation()
+    if len(rows) != len(expected):
+        print("FAIL: row count artifact=%d rederivation=%d"
+              % (len(rows), len(expected)))
+        return 1
+    for i, ((ext, cnt), row) in enumerate(zip(expected, rows), 1):
+        if row != [str(i), ext, str(cnt)]:
+            print("FAIL: row %d artifact=%r expected=%r"
+                  % (i, row, [str(i), ext, str(cnt)]))
+            return 1
+    print("OK: %d rows byte-match re-derivation from repo_files.tsv; header=%r"
+          % (len(rows), header))
+    return 0
+
+
+if __name__ == "__main__":
+    sys.exit(main())