feat: prioritize kana matches when searching with kana

Fixes #1610 and fixes #1657.

CHANGELOG.md

@@ -21,6 +21,10 @@ app.
   elements
   thanks to [@StarScape](https://github.com/StarScape)
   ([#1678](https://github.com/birchill/10ten-ja-reader/issues/1678)).
+- When searching using just kana (e.g. し and ヤク), made kana matches be
+  prioritized
+  ([#1610](https://github.com/birchill/10ten-ja-reader/issues/1610)
+  [#1657](https://github.com/birchill/10ten-ja-reader/issues/1657)).
 
 ## [1.18.0] - 2024-02-26
 

package.json

@@ -63,7 +63,7 @@
   "dependencies": {
     "@birchill/bugsnag-zero": "0.6.8",
     "@birchill/discriminator": "0.3.0",
-    "@birchill/jpdict-idb": "2.3.2",
+    "@birchill/jpdict-idb": "2.4.0",
     "@birchill/normal-jp": "1.5.0",
     "classname-variants": "1.3.3",
     "husky": "9.0.11",

src/background/flat-file.ts

@@ -17,7 +17,7 @@ import { stripFields } from '../utils/strip-fields';
 import { Overwrite } from '../utils/type-helpers';
 
 import { DictionaryWordResult, Sense } from './search-result';
-import { sortMatchesByPriority } from './word-match-sorting';
+import { sortWordResults } from './word-match-sorting';
 
 interface FlatFileDatabaseOptions {
   // Although the v7 API of bugsnag-js can operate on a singleton client we
@@ -199,7 +199,7 @@ class FlatFileDatabase {
     }
 
     // Sort before capping the number of results
-    sortMatchesByPriority(result);
+    sortWordResults(result);
     result.splice(maxResults);
 
     return result;

src/background/word-match-sorting.ts

@@ -8,13 +8,82 @@ import { WordResult } from './search-result';
 
 // As with Array.prototype.sort, sorts `results` in-place, but returns the
 // result to support chaining.
-export function sortMatchesByPriority(
-  results: Array<WordResult>
-): Array<WordResult> {
-  results.sort((a, b) => getPriority(b) - getPriority(a));
+export function sortWordResults(results: Array<WordResult>): Array<WordResult> {
+  const sortMeta: Map<number, { priority: number; type: number }> = new Map();
+
+  for (const result of results) {
+    // Determine the headword match type
+    //
+    // 1 = match on a kanji, or kana which is not just the reading for a kanji
+    // 2 = match on a kana reading for a kanji
+    const kanaReading = result.r.find((r) => !!r.matchRange);
+    const rt = kanaReading ? getKanaHeadwordType(kanaReading, result) : 1;
+
+    // Priority
+    const priority = getPriority(result);
+
+    sortMeta.set(result.id, { priority, type: rt });
+  }
+
+  results.sort((a, b) => {
+    const metaA = sortMeta.get(a.id)!;
+    const metaB = sortMeta.get(b.id)!;
+
+    if (metaA.type !== metaB.type) {
+      return metaA.type - metaB.type;
+    }
+
+    return metaB.priority - metaA.priority;
+  });
+
   return results;
 }
 
+function getKanaHeadwordType(
+  r: WordResult['r'][number],
+  result: WordResult
+): 1 | 2 {
+  // We don't want to prioritize readings marked as `ok` etc. or else we'll end
+  // up prioritizing words like `檜` and `羆` being prioritized when searching
+  // for `ひ`.
+  const isReadingObscure =
+    r.i?.includes('ok') ||
+    r.i?.includes('rk') ||
+    r.i?.includes('sk') ||
+    r.i?.includes('ik');
+
+  if (isReadingObscure) {
+    return 2;
+  }
+
+  // Kana headwords are type 1 (i.e. they are a primary headword, not just a
+  // reading for a kanji headword) if:
+  //
+  // (a) the entry has no kanji headwords or all the kanji headwords are marked
+  //     as `rK`, `sK`, or `iK`.
+  if (
+    !result.k.length ||
+    result.k.every(
+      (k) => k.i?.includes('rK') || k.i?.includes('sK') || k.i?.includes('iK')
+    )
+  ) {
+    return 1;
+  }
+
+  // (b) all senses for the entry have a `uk` (usually kana) `misc` field
+  //     and the reading is not marked as `ok` (old kana usage).
+  //
+  // We wanted to make the condition here be just one sense being marked as `uk`
+  // but then you get words like `梓` being prioritized when searching for `し`
+  // because of one sense out of many being usually kana.
+  if (result.s.every((s) => s.misc?.includes('uk'))) {
+    return 1;
+  }
+
+  // (c) the headword is marked as `nokanji`
+  return r.app === 0 ? 1 : 2;
+}
+
 function getPriority(result: WordResult): number {
   const scores: Array<number> = [0];
 

yarn.lock

@@ -89,10 +89,10 @@
   resolved "https://registry.yarnpkg.com/@birchill/discriminator/-/discriminator-0.3.0.tgz#77d09d754e1ed14fc6fbc94af16724bc4f46d97b"
   integrity sha512-IXkLc1FZLSjFUcPYUnAdg+AWPHC9vPz8hS2IDwPAvnAipeNKIkzQ/B4WY5z14UO1Ex0aOdlHtgwUUXc/Ngkhyg==
 
-"@birchill/jpdict-idb@2.3.2":
-  version "2.3.2"
-  resolved "https://registry.yarnpkg.com/@birchill/jpdict-idb/-/jpdict-idb-2.3.2.tgz#856fd9ee3b658d011d26e614214dfd92b6aa82b5"
-  integrity sha512-2qryn/VIVw3Aj2XUTY7wjDwpMw5ZRmtPC5lb6XEew2eOOXT8VYX4jKkK1Ebe0S7qMVA4Fc/O+XdLF8YBMvqswA==
+"@birchill/jpdict-idb@2.4.0":
+  version "2.4.0"
+  resolved "https://registry.yarnpkg.com/@birchill/jpdict-idb/-/jpdict-idb-2.4.0.tgz#565356d98a2cd57c263d5fe2a0a7f62b6a4ad302"
+  integrity sha512-9pKQGLvB7rdtV8CZNClG6z50kU6NnJ/4gRSCQCDI/r3K7pxv2SVjtTbiXlGr3PJt2NZ6zVrneX1qp9xO/prwow==
   dependencies:
     "@birchill/json-equalish" "^1.1.2"
     "@birchill/normal-jp" "^1.5.0"
@@ -8796,16 +8796,7 @@ string-template@^1.0.0:
   resolved "https://registry.yarnpkg.com/string-template/-/string-template-1.0.0.tgz#9e9f2233dc00f218718ec379a28a5673ecca8b96"
   integrity sha512-SLqR3GBUXuoPP5MmYtD7ompvXiG87QjT6lzOszyXjTM86Uu7At7vNnt2xgyTLq5o9T4IxTYFyGxcULqpsmsfdg==
 
-"string-width-cjs@npm:string-width@^4.2.0":
-  version "4.2.3"
-  resolved "https://registry.yarnpkg.com/string-width/-/string-width-4.2.3.tgz#269c7117d27b05ad2e536830a8ec895ef9c6d010"
-  integrity sha512-wKyQRQpjJ0sIp62ErSZdGsjMJWsap5oRNihHhu6G7JVO/9jIB6UyevL+tXuOqrng8j/cxKTWyWUwvSTriiZz/g==
-  dependencies:
-    emoji-regex "^8.0.0"
-    is-fullwidth-code-point "^3.0.0"
-    strip-ansi "^6.0.1"
-
-string-width@^4.1.0, string-width@^4.2.0, string-width@^4.2.3:
+"string-width-cjs@npm:string-width@^4.2.0", string-width@^4.1.0, string-width@^4.2.0, string-width@^4.2.3:
   version "4.2.3"
   resolved "https://registry.yarnpkg.com/string-width/-/string-width-4.2.3.tgz#269c7117d27b05ad2e536830a8ec895ef9c6d010"
   integrity sha512-wKyQRQpjJ0sIp62ErSZdGsjMJWsap5oRNihHhu6G7JVO/9jIB6UyevL+tXuOqrng8j/cxKTWyWUwvSTriiZz/g==
@@ -8887,14 +8878,7 @@ string_decoder@~1.1.1:
   dependencies:
     safe-buffer "~5.1.0"
 
-"strip-ansi-cjs@npm:strip-ansi@^6.0.1":
-  version "6.0.1"
-  resolved "https://registry.yarnpkg.com/strip-ansi/-/strip-ansi-6.0.1.tgz#9e26c63d30f53443e9489495b2105d37b67a85d9"
-  integrity sha512-Y38VPSHcqkFrCpFnQ9vuSXmquuv5oXOKpGeT6aGrr3o3Gc9AlVa6JBfUSOCnbxGGZF+/0ooI7KrPuUSztUdU5A==
-  dependencies:
-    ansi-regex "^5.0.1"
-
-strip-ansi@^6.0.0, strip-ansi@^6.0.1:
+"strip-ansi-cjs@npm:strip-ansi@^6.0.1", strip-ansi@^6.0.0, strip-ansi@^6.0.1:
   version "6.0.1"
   resolved "https://registry.yarnpkg.com/strip-ansi/-/strip-ansi-6.0.1.tgz#9e26c63d30f53443e9489495b2105d37b67a85d9"
   integrity sha512-Y38VPSHcqkFrCpFnQ9vuSXmquuv5oXOKpGeT6aGrr3o3Gc9AlVa6JBfUSOCnbxGGZF+/0ooI7KrPuUSztUdU5A==
@@ -10136,7 +10120,7 @@ [email protected]:
   resolved "https://registry.yarnpkg.com/workerpool/-/workerpool-6.2.1.tgz#46fc150c17d826b86a008e5a4508656777e9c343"
   integrity sha512-ILEIE97kDZvF9Wb9f6h5aXK4swSlKGUcOEGiIYb2OOu/IrDU9iwj0fD//SsA6E5ibwJxpEvhullJY4Sl4GcpAw==
 
-"wrap-ansi-cjs@npm:wrap-ansi@^7.0.0":
+"wrap-ansi-cjs@npm:wrap-ansi@^7.0.0", wrap-ansi@^7.0.0:
   version "7.0.0"
   resolved "https://registry.yarnpkg.com/wrap-ansi/-/wrap-ansi-7.0.0.tgz#67e145cff510a6a6984bdf1152911d69d2eb9e43"
   integrity sha512-YVGIj2kamLSTxw6NsZjoBxfSwsn0ycdesmc4p+Q21c5zPuZ1pl+NfxVdxPtdHvmNVOQ6XSYG4AUtyt/Fi7D16Q==
@@ -10154,15 +10138,6 @@ wrap-ansi@^6.2.0:
     string-width "^4.1.0"
     strip-ansi "^6.0.0"
 
-wrap-ansi@^7.0.0:
-  version "7.0.0"
-  resolved "https://registry.yarnpkg.com/wrap-ansi/-/wrap-ansi-7.0.0.tgz#67e145cff510a6a6984bdf1152911d69d2eb9e43"
-  integrity sha512-YVGIj2kamLSTxw6NsZjoBxfSwsn0ycdesmc4p+Q21c5zPuZ1pl+NfxVdxPtdHvmNVOQ6XSYG4AUtyt/Fi7D16Q==
-  dependencies:
-    ansi-styles "^4.0.0"
-    string-width "^4.1.0"
-    strip-ansi "^6.0.0"
-
 wrap-ansi@^8.1.0:
   version "8.1.0"
   resolved "https://registry.yarnpkg.com/wrap-ansi/-/wrap-ansi-8.1.0.tgz#56dc22368ee570face1b49819975d9b9a5ead214"