fix(curator): contractions are words of their own

Wiktionary tags a contraction as an abbreviation and an alternative of
its first word (im: in + dem), so German's im, zum and ins, which every
subtitle has, were neither entries nor found as forms. A contraction is
now an entry of its own, as text writes it.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Signed-off-by: Tizian 「ティツィアーン」 <raisondetredev@pm.me>

halkyon_learn_curator/lib/src/sources/wiktionary.dart

@@ -178,10 +178,15 @@ Future<List<File>> wiktionaryDictionaries(
         continue;
       }
       final senses = _maps(json['senses']);
+      // A contraction (im, of in and dem; don't) is a word of its own,
+      // which text writes as it is.
+      bool contraction(Map<String, Object?> sense) =>
+          _strings(sense['tags']).contains('contraction');
       // Senses saying the word is a form of another ("dative plural of
       // Haus") make it a key of that one.
       for (final sense in senses) {
-        if (_strings(sense['tags']).any(_shortForms.contains)) {
+        if (_strings(sense['tags']).any(_shortForms.contains) ||
+            contraction(sense)) {
           continue;
         }
         for (final target in [
@@ -195,8 +200,9 @@ Future<List<File>> wiktionaryDictionaries(
       }
       final own = [
         for (final sense in senses)
-          if (_maps(sense['form_of']).isEmpty &&
-              _maps(sense['alt_of']).isEmpty &&
+          if ((contraction(sense) ||
+                  _maps(sense['form_of']).isEmpty &&
+                      _maps(sense['alt_of']).isEmpty) &&
               _strings(sense['glosses']).isNotEmpty)
             sense,
       ];

halkyon_learn_curator/test/fixtures/README.md

@@ -30,9 +30,9 @@ declarations of the entities they use: JMdict is © the Electronic Dictionary
 Research and Development Group, used under its licence, CC BY-SA 4.0
 (<https://www.edrdg.org/edrdg/licence.html>).
 
-`wiktionary-sample.jsonl` holds 29 lines of kaikki.org's Wiktextract data of the
+`wiktionary-sample.jsonl` holds 30 lines of kaikki.org's Wiktextract data of the
 English Wiktionary (the dump of 2026-10-03, read per word from kaikki.org): the
-German Haus, Häuser, Häusern, essen, aß, gegessen and Straße, the Greek σπίτι,
+German Haus, Häuser, Häusern, essen, aß, gegessen, Straße and im, the Greek σπίτι,
 σπιτιού and γράφω, the English house, houses, go and went, the French maison,
 and the Korean 먹다, 집 and 학생, each shortened to the fields the curator reads (no categories,
 etymologies or related words; at most six senses, two examples, 40 forms, two

halkyon_learn_curator/test/fixtures/wiktionary-sample.jsonl

@@ -27,3 +27,4 @@
 {"senses": [{"examples": [{"text": "집에 돌아오다", "bold_text_offsets": [[0, 1]], "roman": "jib-e doraoda", "bold_roman_offsets": [[0, 3]], "translation": "to return home", "english": "to return home", "bold_translation_offsets": [[10, 14]], "type": "example"}, {"text": "집에 온 이후부터", "bold_text_offsets": [[0, 1]], "roman": "jib-e on ihubuteo", "bold_roman_offsets": [[0, 3]], "translation": "since I got home", "english": "since I got home", "bold_translation_offsets": [[12, 16]], "type": "example"}], "glosses": ["home, house"]}, {"synonyms": [{"word": "댁", "alt": "宅"}], "glosses": ["household"]}, {"glosses": ["sheath, case"]}], "pos": "noun", "head_templates": [{"name": "ko-noun", "args": {}, "expansion": "집 • (jip)"}], "forms": [{"form": "jip", "tags": ["romanization"]}], "etymology_number": "1", "sounds": [{"tags": ["SK-Standard", "Seoul"], "ipa": "[t͡ɕip̚]"}], "word": "집", "lang": "Korean", "lang_code": "ko"}
 {"senses": [{"examples": [{"text": "작품(作品) (jakpum, “works”) + 집(集) (jip, “collection”) → 작품집(作品集) (jakpumjip, “collected works”)", "type": "example"}], "glosses": ["collection of bound works; anthology, collected works"], "tags": ["morpheme"]}], "pos": "suffix", "head_templates": [{"name": "ko-suffix", "args": {"hanja": "集"}, "expansion": "—집 • (-jip) (hanja 集)"}], "forms": [{"form": "—집", "tags": ["canonical"]}, {"form": "-jip", "tags": ["romanization"]}, {"form": "集", "tags": ["hanja"]}], "etymology_number": "2", "word": "집", "lang": "Korean", "lang_code": "ko"}
 {"senses": [{"examples": [{"text": "최근에 박사 과정을 시작했는데 다시 학생이 돼서 기분이 좋습니다.", "bold_text_offsets": [[20, 23]], "roman": "Choegeun-e baksa gwajeong-eul sijakhaenneunde dasi haksaeng-i dwaeseo gibun-i joseumnida.", "bold_roman_offsets": [[51, 61]], "translation": "I recently started a PhD program, and it feels good to be a student again.", "english": "I recently started a PhD program, and it feels good to be a student again.", "bold_translation_offsets": [[60, 67]], "type": "example"}], "glosses": ["student, scholar, school pupil"]}], "pos": "noun", "head_templates": [{"name": "ko-noun", "args": {"hanja": "學生", "count": "명(名)"}, "expansion": "학생 • (haksaeng) (counter 명(名), hanja 學生)"}], "forms": [{"form": "haksaeng", "tags": ["romanization"]}, {"form": "명", "tags": ["counter", "error-unknown-tag"]}, {"form": "學生", "tags": ["hanja"]}], "sounds": [{"tags": ["SK-Standard", "Seoul"], "ipa": "[ha̠ks͈ɛŋ]"}, {"tags": ["SK-Standard", "Seoul"], "ipa": "[ha̠ks͈e̞ŋ]"}], "word": "학생", "lang": "Korean", "lang_code": "ko"}
+{"senses": [{"glosses": ["contraction of in + dem; in the"], "tags": ["abbreviation", "alt-of", "contraction"], "alt_of": [{"word": "in", "extra": "+ dem; in the"}]}], "pos": "contraction", "head_templates": [{"name": "head", "args": {"1": "de", "2": "contraction"}, "expansion": "im"}], "forms": [{"form": "no-table-tags", "source": "declension", "tags": ["table-tags"]}, {"form": "l", "source": "declension", "tags": ["inflection-template"]}, {"form": "in den", "tags": ["accusative", "masculine"], "source": "declension"}, {"form": "ins", "tags": ["accusative", "neuter"], "source": "declension"}, {"form": "in die", "tags": ["accusative", "feminine"], "source": "declension"}, {"form": "in die", "tags": ["accusative", "plural"], "source": "declension"}, {"form": "im", "tags": ["dative", "masculine"], "source": "declension"}, {"form": "im", "tags": ["dative", "neuter"], "source": "declension"}, {"form": "in der", "tags": ["dative", "feminine"], "source": "declension"}, {"form": "in den", "tags": ["dative", "plural"], "source": "declension"}], "sounds": [{"ipa": "/ɪm/"}, {"audio": "De-im.ogg", "ogg_url": "https://upload.wikimedia.org/wikipedia/commons/7/71/De-im.ogg", "mp3_url": "https://upload.wikimedia.org/wikipedia/commons/transcoded/7/71/De-im.ogg/De-im.ogg.mp3"}, {"audio": "De-im2.ogg", "tags": ["Germany", "Berlin"], "ogg_url": "https://upload.wikimedia.org/wikipedia/commons/4/44/De-im2.ogg", "mp3_url": "https://upload.wikimedia.org/wikipedia/commons/transcoded/4/44/De-im2.ogg/De-im2.ogg.mp3"}], "word": "im", "lang": "German", "lang_code": "de"}

halkyon_learn_curator/test/wiktionary_test.dart

@@ -140,6 +140,8 @@ void main() {
         (essen['textKeys']! as List).cast<String>(),
         containsAll(['isst', 'aß', 'gegessen']),
       );
+      // A contraction is a word of its own: im, of in and dem.
+      expect(ids, contains('im/contraction'));
       // Typed with `ss`.
       expect(
         (entryOf('wiktionary-de-en.jsonl.gz', 'Straße/noun')['looseKeys']!
@@ -246,8 +248,14 @@ void main() {
       for (final line in linesOf('wiktionary-de-en.jsonl.gz').skip(1))
         (line['headword'], line['rank']! as int, line['labels']),
     ]..sort((a, b) => a.$2.compareTo(b.$2));
-    expect(ranked.first.$1, 'Haus');
-    expect(ranked.first.$3, ['common']);
+    expect(
+      [
+        for (final (word, _, _) in ranked)
+          if (['im', 'Haus', 'Straße'].contains(word)) word,
+      ],
+      ['im', 'Haus', 'Straße'],
+    );
+    expect(ranked.firstWhere((each) => each.$1 == 'Haus').$3, ['common']);
   });
 
   group('folding', () {