Add CLI dedupe command using canonical form

Author: SaridakisStamatisChristos

README.md

@@ -46,6 +46,9 @@ sudoku-dlx rate  --grid "<81chars>"
 sudoku-dlx canon --grid "<81chars>"  # D4 × bands/stacks × inner row/col × digit relabel
 # Produces a stable 81-char string for deduping datasets.
 
+# Dedupe a file of puzzles (fast)
+sudoku-dlx dedupe --in puzzles.txt --out unique.txt
+
 # Generate a unique puzzle (deterministic with seed)
 sudoku-dlx gen   --seed 123 --givens 30           # ~target clue count (approx)
 sudoku-dlx gen   --seed 123 --givens 30 --pretty

src/sudoku_dlx/cli.py

@@ -1,4 +1,5 @@
 import argparse
+import pathlib
 import sys
 from typing import Optional
 
@@ -69,6 +70,32 @@ def cmd_canon(ns: argparse.Namespace) -> int:
     return 0
 
 
+def cmd_dedupe(ns: argparse.Namespace) -> int:
+    inp = pathlib.Path(ns.in_path)
+    outp = pathlib.Path(ns.out_path)
+    seen: set[str] = set()
+    uniq: list[str] = []
+    with inp.open("r", encoding="utf-8") as handle:
+        for line in handle:
+            s = "".join(ch for ch in line.strip() if not ch.isspace())
+            if not s:
+                continue
+            try:
+                grid = from_string(s)
+            except Exception:
+                continue
+            canon = canonical_form(grid)
+            if canon not in seen:
+                seen.add(canon)
+                uniq.append(canon)
+    outp.parent.mkdir(parents=True, exist_ok=True)
+    with outp.open("w", encoding="utf-8") as handle:
+        for value in uniq:
+            handle.write(value + "\n")
+    print(f"# unique: {len(uniq)}", file=sys.stderr)
+    return 0
+
+
 def main(argv: Optional[list[str]] = None) -> int:
     parser = argparse.ArgumentParser(
         prog="sudoku-dlx",
@@ -88,6 +115,31 @@ def main(argv: Optional[list[str]] = None) -> int:
     rate_parser.add_argument("--file", help="path to a file with 9 lines of 9 chars")
     rate_parser.set_defaults(func=cmd_rate)
 
+    canon_parser = sub.add_parser(
+        "canon",
+        help=(
+            "print canonical 81-char form (D4 × bands/stacks × inner row/col swaps × digit relabel)"
+        ),
+    )
+    canon_parser.add_argument("--grid", help="81-char string; 0/./- for blanks")
+    canon_parser.add_argument("--file", help="path to a file with 9 lines of 9 chars")
+    canon_parser.set_defaults(func=cmd_canon)
+
+    dedupe_parser = sub.add_parser(
+        "dedupe",
+        help="dedupe puzzles by canonical form (one 81-char grid per line)",
+    )
+    dedupe_parser.add_argument(
+        "--in", dest="in_path", required=True, help="input text file with one grid per line"
+    )
+    dedupe_parser.add_argument(
+        "--out",
+        dest="out_path",
+        required=True,
+        help="output file path for unique canonical grids",
+    )
+    dedupe_parser.set_defaults(func=cmd_dedupe)
+
     gen_parser = sub.add_parser("gen", help="generate a puzzle")
     gen_parser.add_argument("--seed", type=int, default=None)
     gen_parser.add_argument("--givens", type=int, default=28, help="target number of clues (approx)")
@@ -105,16 +157,6 @@ def main(argv: Optional[list[str]] = None) -> int:
     gen_parser.add_argument("--pretty", action="store_true")
     gen_parser.set_defaults(func=cmd_gen)
 
-    canon_parser = sub.add_parser(
-        "canon",
-        help=(
-            "print canonical 81-char form (D4 × bands/stacks × inner row/col swaps × digit relabel)"
-        ),
-    )
-    canon_parser.add_argument("--grid", help="81-char string; 0/./- for blanks")
-    canon_parser.add_argument("--file", help="path to a file with 9 lines of 9 chars")
-    canon_parser.set_defaults(func=cmd_canon)
-
     args = parser.parse_args(argv)
     if not hasattr(args, "func"):
         parser.print_help()

tests/test_dedupe.py

@@ -0,0 +1,31 @@
+import os
+import tempfile
+
+from sudoku_dlx import cli
+
+S = (
+    "53..7...."
+    "6..195..."
+    ".98....6."
+    "8...6...3"
+    "4..8.3..1"
+    "7...2...6"
+    ".6....28."
+    "...419..5"
+    "....8..79"
+)
+
+
+def test_cli_dedupe_makes_unique_file():
+    s180 = "".join(reversed(S))
+    with tempfile.TemporaryDirectory() as tmpdir:
+        infile = os.path.join(tmpdir, "in.txt")
+        outfile = os.path.join(tmpdir, "out.txt")
+        with open(infile, "w", encoding="utf-8") as handle:
+            handle.write(S + "\n")
+            handle.write(s180 + "\n")
+        rc = cli.main(["dedupe", "--in", infile, "--out", outfile])
+        assert rc == 0
+        with open(outfile, "r", encoding="utf-8") as handle:
+            lines = [line.strip() for line in handle if line.strip()]
+        assert len(lines) == 1