cspell-lib 10.3.0-alpha.0 → 10.3.1-alpha.0

package/dist/lib/Settings/sanitizeSettings.js

@@ -60,6 +60,8 @@ const handlers = {
     readonly: skip,
     reporters: skip,
     showStatus: copy1,
+    softWordBreakDefinitions: copy1,
+    softWordBreaks: copy1,
     spellCheckDelayMs: copy1,
     substitutionDefinitions: copy1,
     substitutions: copy1,
@@ -180,6 +182,8 @@ const LanguageSettingsHandlers = {
     name: skip,
     noSuggestDictionaries: copy1,
     patterns: copyPatternsField,
+    softWordBreaks: copy1,
+    softWordBreakDefinitions: copy1,
     substitutionDefinitions: copy1,
     substitutions: copy1,
     suggestWords: copy1,
@@ -241,6 +245,8 @@ const OverridesHandlers = {
     numSuggestions: copy1,
     patterns: copyPatternsField,
     pnpFiles: skip,
+    softWordBreaks: copy1,
+    softWordBreakDefinitions: copy1,
     substitutionDefinitions: copy1,
     substitutions: copy1,
     suggestionNumChanges: copy1,

package/dist/lib/SpellingDictionary/DictionaryController/DictionaryLoader.js

@@ -52,7 +52,7 @@ var __disposeResources = (this && this.__disposeResources) || (function (Suppres
 });
 import { opConcatMap, opFilter, opMap, pipe } from '@cspell/cspell-pipe/sync';
 import { StrongWeakMap } from '@cspell/strong-weak-map';
-import { createFailedToLoadDictionary, createFlagWordsDictionary, createFlagWordsDictionaryFromTrieFile, createInlineSpellingDictionary, createSpellingDictionary, createSpellingDictionaryFromTrieFile, } from 'cspell-dictionary';
+import { createFailedToLoadDictionary, createFlagWordsDictionary, createFlagWordsDictionaryFromTrieFile, createInlineSpellingDictionary, createSpellingDictionary, createSpellingDictionaryFromTrieFile, createSuggestDictionary, createSuggestDictionaryFromTrieFile, } from 'cspell-dictionary';
 import { compareStats, toFileURL, urlBasename } from 'cspell-io';
 import { measurePerf } from '../../perf/index.js';
 import { isDictionaryDefinitionInlineInternal, isDictionaryFileDefinitionInternal } from '../../Settings/index.js';
@@ -257,6 +257,9 @@ async function legacyWordList(reader, filename, options) {
         if (options.kind === 'flag-words') {
             return createFlagWordsDictionary([...words], options.name, filename.toString());
         }
+        if (options.kind === 'suggest-words') {
+            return createSuggestDictionary([...words], options.name, filename.toString());
+        }
         return createSpellingDictionary(words, options.name, filename.toString(), applyKind(options), true);
     }
     catch (e_1) {
@@ -277,6 +280,9 @@ async function wordsPerLineWordList(reader, filename, options) {
     if (options.kind === 'flag-words') {
         return createFlagWordsDictionary([...words], options.name, filename.href);
     }
+    if (options.kind === 'suggest-words') {
+        return createSuggestDictionary([...words], options.name, filename.href);
+    }
     return createSpellingDictionary(words, options.name, filename.href, applyKind(options), true);
 }
 async function loadSimpleWordList(reader, filename, options) {
@@ -287,6 +293,9 @@ async function loadSimpleWordList(reader, filename, options) {
         if (options.kind === 'flag-words') {
             return createFlagWordsDictionary(lines, options.name, filename.href);
         }
+        if (options.kind === 'suggest-words') {
+            return createSuggestDictionary(lines, options.name, filename.href);
+        }
         return createSpellingDictionary(lines, options.name, filename.href, applyKind(options));
     }
     catch (e_2) {
@@ -305,6 +314,9 @@ async function loadTrie(reader, filename, options) {
         if (options.kind === 'flag-words') {
             return createFlagWordsDictionaryFromTrieFile(content, options.name, filename.href);
         }
+        if (options.kind === 'suggest-words') {
+            return createSuggestDictionaryFromTrieFile(content, options.name, filename.href);
+        }
         return createSpellingDictionaryFromTrieFile(content, options.name, filename.href, applyKind(options));
     }
     catch (e_3) {
@@ -317,7 +329,8 @@ async function loadTrie(reader, filename, options) {
 }
 /**
  * Apply the effect of `kind` on the options passed to a normal `words` dictionary loader.
- * `flag-words` is handled by the callers directly since it uses a different dictionary implementation.
+ * `flag-words` and `suggest-words` are handled by the callers directly since they use a different
+ * dictionary implementation.
  */
 function applyKind(options) {
     return options.kind === 'ignore-words' && !options.noSuggest ? { ...options, noSuggest: true } : options;

package/dist/lib/util/text.js

@@ -2,14 +2,10 @@ import { opConcatMap, opMap, pipe } from '@cspell/cspell-pipe/sync';
 import { binarySearch } from './search.js';
 import { regExAccents, regExAllLower, regExAllUpper, regExFirstUpper, regExIgnoreCharacters, regExpCamelCaseWordBreaksWithEnglishSuffix, regExWords, regExWordsAndDigits, } from './textRegex.js';
 import { toUri } from './Uri.js';
-import { scanMap } from './util.js';
 export { stringToRegExp } from './textRegex.js';
 // CSpell:ignore ings ning gimuy tsmerge
 export function splitCamelCaseWordWithOffset(wo) {
-    return splitCamelCaseWord(wo.text).map(scanMap((last, text) => ({ text, offset: last.offset + last.text.length }), {
-        text: '',
-        offset: wo.offset,
-    }));
+    return splitWordWithOffset(wo, regExpCamelCaseWordBreaksWithEnglishSuffix);
 }
 /**
  * Split camelCase words into an array of strings.
@@ -18,10 +14,23 @@ export function splitCamelCaseWord(word) {
     return splitWord(word, regExpCamelCaseWordBreaksWithEnglishSuffix);
 }
 export function splitWordWithOffset(wo, regExpWordBreaks) {
-    return splitWord(wo.text, regExpWordBreaks).map(scanMap((last, text) => ({ text, offset: last.offset + last.text.length }), {
-        text: '',
-        offset: wo.offset,
-    }));
+    const wText = wo.text;
+    const absOffset = wo.offset;
+    const words = [];
+    let lastRelOffset = 0;
+    const r = new RegExp(regExpWordBreaks);
+    for (const m of wText.matchAll(r)) {
+        const text = wText.slice(lastRelOffset, m.index);
+        const offset = absOffset + lastRelOffset;
+        lastRelOffset = m.index + m[0].length;
+        words.push({ text, offset });
+    }
+    if (lastRelOffset < wText.length) {
+        const text = wText.slice(lastRelOffset);
+        const offset = absOffset + lastRelOffset;
+        words.push({ text, offset });
+    }
+    return words;
 }
 /**
  * Split camelCase words into an array of strings.

package/dist/lib/util/textRegex.js

@@ -2,7 +2,7 @@
 export const regExUpperSOrIng = /([\p{Lu}\p{M}]+(?:\\?['’])?(?:s|ing|ies|es|ings|ed|ning))(?!\p{Ll})/gu;
 export const regExSplitWords = /(\p{Ll}\p{M}?)(\p{Lu})/gu;
 export const regExSplitWords2 = /(\p{Lu}\p{M}?)((\p{Lu}\p{M}?)\p{Ll})/gu;
-export const regExpCamelCaseWordBreaksWithEnglishSuffix = /(?<=\p{Ll}\p{M}?)(?=\p{Lu})|(?<=\p{Lu}\p{M}?)(?=\p{Lu}\p{M}?\p{Ll})(?!\p{Lu}\p{M}?(?:s|ing|ies|es|ings|ed|ning)(?!\p{Ll}))/gu;
+export const regExpCamelCaseWordBreaksWithEnglishSuffix = /(?<=\p{Ll}\p{M}?)(?=\p{Lu})|(?<=\p{Lu}\p{M}?)(?=\p{Lu}\p{M}?\p{Ll})(?!\p{Lu}\p{M}?(?:s|ing|ies|es|ings|ed|ning)(?!\p{Ll}))|\u00AD/gu;
 export const regExpCamelCaseWordBreaks_NOT_USED = /(?<=\p{Ll}\p{M}?)(?=\p{Lu})|(?<=\p{Lu}\p{M}?)(?=\p{Lu}\p{M}?\p{Ll})/gu;
 export const regExpAllPossibleWordBreaks_NOT_USED = /(?<=\p{Ll}\p{M}?)(?=\p{Lu})|(?<=\p{Lu}\p{M}?)(?=\p{Lu}\p{M}?\p{Ll})|(?<=\p{Lu}\p{M}?\p{Lu}\p{M}?)(?=\p{Ll})|(?<=\p{L}\p{M}?)(?=\P{L})|(?<=\P{L})(?=\p{L})/gu;
 export const regExWords = /\p{L}\p{M}?(?:(?:\\?['’])?\p{L}\p{M}?)*/gu;

package/package.json

@@ -4,7 +4,7 @@
     "access": "public",
     "provenance": true
   },
-  "version": "10.3.0-alpha.0",
+  "version": "10.3.1-alpha.0",
   "description": "A library of useful functions used across various cspell tools.",
   "type": "module",
   "sideEffects": false,
@@ -75,22 +75,22 @@
   },
   "homepage": "https://github.com/streetsidesoftware/cspell/tree/main/packages/cspell-lib#readme",
   "dependencies": {
-    "@cspell/cspell-bundled-dicts": "10.3.0-alpha.0",
-    "@cspell/cspell-performance-monitor": "10.3.0-alpha.0",
-    "@cspell/cspell-pipe": "10.3.0-alpha.0",
-    "@cspell/cspell-resolver": "10.3.0-alpha.0",
-    "@cspell/cspell-types": "10.3.0-alpha.0",
-    "@cspell/dynamic-import": "10.3.0-alpha.0",
-    "@cspell/filetypes": "10.3.0-alpha.0",
-    "@cspell/rpc": "10.3.0-alpha.0",
-    "@cspell/strong-weak-map": "10.3.0-alpha.0",
-    "@cspell/url": "10.3.0-alpha.0",
-    "cspell-config-lib": "10.3.0-alpha.0",
-    "cspell-dictionary": "10.3.0-alpha.0",
-    "cspell-glob": "10.3.0-alpha.0",
-    "cspell-grammar": "10.3.0-alpha.0",
-    "cspell-io": "10.3.0-alpha.0",
-    "cspell-trie-lib": "10.3.0-alpha.0",
+    "@cspell/cspell-bundled-dicts": "10.3.1-alpha.0",
+    "@cspell/cspell-performance-monitor": "10.3.1-alpha.0",
+    "@cspell/cspell-pipe": "10.3.1-alpha.0",
+    "@cspell/cspell-resolver": "10.3.1-alpha.0",
+    "@cspell/cspell-types": "10.3.1-alpha.0",
+    "@cspell/dynamic-import": "10.3.1-alpha.0",
+    "@cspell/filetypes": "10.3.1-alpha.0",
+    "@cspell/rpc": "10.3.1-alpha.0",
+    "@cspell/strong-weak-map": "10.3.1-alpha.0",
+    "@cspell/url": "10.3.1-alpha.0",
+    "cspell-config-lib": "10.3.1-alpha.0",
+    "cspell-dictionary": "10.3.1-alpha.0",
+    "cspell-glob": "10.3.1-alpha.0",
+    "cspell-grammar": "10.3.1-alpha.0",
+    "cspell-io": "10.3.1-alpha.0",
+    "cspell-trie-lib": "10.3.1-alpha.0",
     "env-paths": "^4.0.0",
     "gensequence": "^8.0.8",
     "import-fresh": "^4.0.0",
@@ -103,7 +103,7 @@
     "node": ">=22.18.0"
   },
   "devDependencies": {
-    "@cspell/cspell-tools": "10.3.0-alpha.0",
+    "@cspell/cspell-tools": "10.3.1-alpha.0",
     "@cspell/dict-cpp": "^7.1.0",
     "@cspell/dict-csharp": "^4.0.8",
     "@cspell/dict-css": "^4.1.2",
@@ -123,5 +123,5 @@
     "lorem-ipsum": "^3.0.0",
     "perf-insight": "^2.0.1"
   },
-  "gitHead": "39297075c7a4946feb1a4f0a509e329cfb0b4f11"
+  "gitHead": "1fee574fa870bffd6296aef8a9c68115b9589933"
 }