Remove Spanish-specific TSV tooling

src/saiki/cli.py

@@ -15,7 +15,7 @@ from .importer import (
     supported_tts_backends,
     synthesize_tts_sample,
 )
-from .words import compare_word_files, compare_word_lists, extract_words, extract_words_from_file, lint_anki_cards_main
+from .words import compare_word_files, compare_word_lists, extract_words, extract_words_from_file
 from .youtube import run_youtube
 
 
@@ -98,12 +98,13 @@ def build_parser(config: Config | None = None) -> argparse.ArgumentParser:
     words.add_argument("--out", "--output", dest="out")
     words.add_argument("--full-field", action="store_true")
     words.add_argument("--spacy-model")
-    words.add_argument("--include-proper-nouns", action="store_true", help="Include proper nouns (PROPN).")
-    words.add_argument("--function-words", action="store_true", help="Extract function words separately.")
     words.add_argument("--debug", help="Path for debug TSV output.")
-    words.add_argument("--lemma-corrections", help="Path to bad<TAB>good TSV of lemma corrections.")
-    words.add_argument("--bad-lemma-file", help="Path to file listing lemmas to skip.")
-    words.add_argument("--include-tags", action="store_true", help="Include tags column in parsing.")
+    words.add_argument(
+        "--field-section",
+        choices=["all", "first"],
+        default="all",
+        help="Which blank-line-separated TSV field section to mine.",
+    )
     words.add_argument("--debug-min-freq", type=int, default=0,
                        help="Minimum frequency for debug output (default: all).")
     words.add_argument("--no-clean", action="store_true",
@@ -121,12 +122,6 @@ def build_parser(config: Config | None = None) -> argparse.ArgumentParser:
     compare_new.add_argument("--min-frequency", type=int, default=0,
                              help="Minimum frequency for deck words to count.")
 
-    lint_es = sub.add_parser("lint-anki-es", help="Check Spanish Anki cards for suspicious patterns.")
-    lint_es.add_argument("--input", required=True, help="Anki TSV export file.")
-    lint_es.add_argument("--field", type=int, default=2, help="1-based column index (default 2).")
-    lint_es.add_argument("--output", default="suspicious_cards_es.tsv", help="Output TSV path.")
-    lint_es.add_argument("--verbose", action="store_true", help="Output all cards, not just suspicious ones.")
-
     youtube = sub.add_parser("youtube", help="Mine a YouTube transcript.")
     youtube.add_argument("lang", choices=choices)
     youtube.add_argument("video")
@@ -195,12 +190,6 @@ def main(argv: list[str] | None = None) -> int:
     if args.command == "words":
         if args.input:
             # File-based extraction
-            if config.language_name(args.lang) != "spanish":
-                print(
-                    "Error: TSV file-based word extraction is currently Spanish-only.",
-                    file=sys.stderr,
-                )
-                return 1
             if args.field and not args.field.isdigit():
                 print(
                     f"Error: --field must be a 1-based column index (integer) "
@@ -221,25 +210,16 @@ def main(argv: list[str] | None = None) -> int:
                 min_freq=args.min_freq,
                 outdir=args.outdir,
                 out=args.out,
-                include_proper_nouns=args.include_proper_nouns,
-                function_words=args.function_words,
                 debug=args.debug,
-                lemma_corrections=args.lemma_corrections,
-                bad_lemma_file=args.bad_lemma_file,
                 spacy_model=args.spacy_model,
-                include_tags=args.include_tags,
                 debug_min_freq=args.debug_min_freq,
                 no_clean=args.no_clean,
+                field_section=args.field_section,
             )
             print(f"Parsed {result['records']} records")
-            print(f"Wrote {result['written']} content entries to: {result['out']}")
+            print(f"Wrote {result['written']} entries to: {result['out']}")
             if result.get("debug"):
                 print(f"Debug output: {result['debug']}")
-            if result.get("proper_nouns"):
-                print(f"Proper nouns: {result['proper_nouns']}")
-            if result.get("function_words"):
-                print(f"Function words: {result['function_words']}")
-            print(f"Suspicious tokens: {result.get('suspicious', '')}")
         else:
             result = extract_words(
                 config, args.lang, args.query, args.deck, args.field, args.min_freq,
@@ -279,24 +259,6 @@ def main(argv: list[str] | None = None) -> int:
             print(f"Seen words written to: {args.seen_output}")
         return 0
 
-    if args.command == "lint-anki-es":
-        if args.field < 1:
-            print(
-                f"Error: --field must be a 1-based column index >= 1, got: {args.field}",
-                file=sys.stderr,
-            )
-            return 1
-        result = lint_anki_cards_main(
-            args.input,
-            field_index=args.field,
-            output_path=args.output,
-            verbose=args.verbose,
-        )
-        print(f"Checked {result['records']} cards")
-        print(f"Found {result['issues']} suspicious card(s)")
-        print(f"Report written to: {result['path']}")
-        return 0
-
     if args.command == "youtube":
         result = run_youtube(
             config, args.lang, args.video, args.mode, args.top, args.no_stopwords,