hunspell-reader - npm Package Compare versions

Comparing version 3.1.5 to 3.2.0

dist/aff.d.ts

@@ -45,3 +45,3 @@ import { Converter } from './converter';
 export interface AffInfo extends AffTransformFlags {
-    SET?: string;
+    SET: string;
     TRY?: string;
@@ -77,2 +77,6 @@ KEY?: string;
 }
+/**
+ * AffWordFlags are the flags applied to a word after the hunspell rules have been applied.
+ * They are either `true` or `undefined`.
+ */
 export interface AffWordFlags {
@@ -85,5 +89,4 @@ /**
      *
-     * @default false
      */
-    isCompoundPermitted?: boolean;
+    isCompoundPermitted?: true;
     /**
@@ -94,5 +97,4 @@ * COMPOUNDBEGIN flag
      *
-     * @default false
      */
-    canBeCompoundBegin?: boolean;
+    canBeCompoundBegin?: true;
     /**
@@ -103,5 +105,4 @@ * COMPOUNDMIDDLE flag
      *
-     * @default false
      */
-    canBeCompoundMiddle?: boolean;
+    canBeCompoundMiddle?: true;
     /**
@@ -112,5 +113,4 @@ * COMPOUNDLAST flag
      *
-     * @default false
      */
-    canBeCompoundEnd?: boolean;
+    canBeCompoundEnd?: true;
     /**
@@ -122,5 +122,4 @@ * COMPOUNDPERMITFLAG flag
      *
-     * @default false
      */
-    isOnlyAllowedInCompound?: boolean;
+    isOnlyAllowedInCompound?: true;
     /**
@@ -131,5 +130,4 @@ * COMPOUNDFORBIDFLAG flag
      *
-     * @default false
      */
-    isCompoundForbidden?: boolean;
+    isCompoundForbidden?: true;
     /**
@@ -140,3 +138,3 @@ * WARN flag
      */
-    isWarning?: boolean;
+    isWarning?: true;
     /**
@@ -149,3 +147,3 @@ * KEEPCASE flag
      */
-    isKeepCase?: boolean;
+    isKeepCase?: true;
     /**
@@ -158,3 +156,3 @@ * FORCEUCASE flag
      */
-    isForceUCase?: boolean;
+    isForceUCase?: true;
     /**
@@ -166,3 +164,3 @@ * FORBIDDENWORD flag
      */
-    isForbiddenWord?: boolean;
+    isForbiddenWord?: true;
     /**
@@ -174,3 +172,3 @@ * NOSUGGEST flag
      */
-    isNoSuggest?: boolean;
+    isNoSuggest?: true;
     /**
@@ -182,3 +180,3 @@ * NEEDAFFIX flag
      */
-    isNeedAffix?: boolean;
+    isNeedAffix?: true;
 }
@@ -226,2 +224,3 @@ export interface AffWord {
 }
+declare function signature(aff: AffWord): string;
 export declare function processRules(affInfo: AffInfo): Map<string, Rule>;
@@ -238,1 +237,5 @@ export declare function logAffWord(affWord: AffWord, message: string): AffWord;
 export declare function filterAff(): (t: AffWord) => boolean;
+export declare const debug: {
+    signature: typeof signature;
+};
+export {};

dist/aff.js

@@ -82,3 +82,3 @@ "use strict";
             : '';
-        const flags = Object.assign(Object.assign({}, affWord.flags), { isNeedAffix: false });
+        const flags = affWord.flags.isNeedAffix ? removeNeedAffix(affWord.flags) : affWord.flags;
         const matchingSubstitutions = [...affix.substitutionSets.values()]
@@ -159,3 +159,3 @@ .filter(sub => sub.match.test(word));
     const { word, flags } = aff;
-    const sig = Object.keys(flags).map(f => flagToStringMap[f]).sort().join('|');
+    const sig = Object.entries(flags).filter(e => e[1]).map(f => flagToStringMap[f[0]]).sort().join('');
     return word + '|' + sig;
@@ -257,2 +257,10 @@ }
 exports.filterAff = filterAff;
+exports.debug = {
+    signature,
+};
+function removeNeedAffix(flags) {
+    const newFlags = Object.assign({}, flags);
+    delete newFlags.isNeedAffix;
+    return newFlags;
+}
 //# sourceMappingURL=aff.js.map

dist/affReader.d.ts

@@ -21,3 +21,3 @@ import { AffInfo, Aff, Fx } from './aff';
 export declare function parseAffFile(filename: string, encoding?: string): Promise<AffInfo>;
-export declare function parseAff(affFileContent: string, _encoding?: string): AffInfo;
+export declare function parseAff(affFileContent: string, encoding?: string): AffInfo;
 export declare function parseAffFileToAff(filename: string, encoding?: string): Promise<Aff>;
@@ -24,0 +24,0 @@ declare function parseLine(line: string): AffLine;

dist/affReader.js

@@ -222,3 +222,3 @@ "use strict";
 exports.parseAffFile = parseAffFile;
-function parseAff(affFileContent, _encoding = UTF8) {
+function parseAff(affFileContent, encoding = UTF8) {
     const lines = affFileContent.split(/\r?\n/g);
@@ -240,3 +240,3 @@ return lines
         return aff;
-    }, {});
+    }, { SET: encoding });
 }
@@ -243,0 +243,0 @@ exports.parseAff = parseAff;

dist/app.js

@@ -40,2 +40,5 @@ #!/usr/bin/env node
     .option('-n, --number <limit>', 'Limit the number of words to output.')
+    .option('--forbidden', 'include forbidden words')
+    .option('--partial_compounds', 'include words that must be part of a compound word')
+    .option('--only_forbidden', 'includes only words that are forbidden')
     .description('Output all the words in the <hunspell.dic> file.')
@@ -110,3 +113,3 @@ .action(action);
         displayHelp = false;
-        const { sort = false, unique = false, output: outputFile, lower_case: lowerCase = false, transform = true, infix = false, rules = false, progress: showProgress = false, max_depth, } = options;
+        const { sort = false, unique = false, output: outputFile, lower_case: lowerCase = false, transform = true, infix = false, rules = false, progress: showProgress = false, max_depth, forbidden = false, only_forbidden: onlyForbidden = false, partial_compounds: partialCompoundsAllowed = false, } = options;
         logStream = outputFile ? process.stdout : process.stderr;
@@ -128,2 +131,9 @@ const log = notify;
         const transformers = [];
+        const filters = [];
+        if (!forbidden && !onlyForbidden)
+            filters.push((aff => !aff.flags.isForbiddenWord));
+        if (onlyForbidden)
+            filters.push((aff => !!aff.flags.isForbiddenWord));
+        if (!partialCompoundsAllowed)
+            filters.push((aff => !aff.flags.isOnlyAllowedInCompound));
         if (infix) {
@@ -152,3 +162,5 @@ transformers.push(affWordToInfix);
         const applyTransformers = (aff) => transformers.reduce((aff, fn) => fn(aff), aff);
+        const applyFilters = (aff) => filters.reduce((cur, fn) => cur && fn(aff), true);
         const allWords = seqWords
+            .filter(applyFilters)
             .map(applyTransformers)
@@ -155,0 +167,0 @@ .filter(filterUnique)

dist/IterableHunspellReader.d.ts

@@ -1,2 +0,2 @@
-import { Aff } from './aff';
+import { Aff, AffWord } from './aff';
 import { Sequence } from 'gensequence';
@@ -31,3 +31,3 @@ import { WordInfo } from './types';
      * Iterator for all the words in the dictionary. The words are in the order found in the .dic after the
-     * transformations have been applied. No filtering is done based upon the AFF flags.
+     * transformations have been applied. Forbidden and CompoundOnly words are filtered out.
      */
@@ -41,4 +41,14 @@ [Symbol.iterator](): Sequence<string>;
      */
-    seqAffWords(tapPreApplyRules?: (w: string, index: number) => any, maxDepth?: number): Sequence<import("./aff").AffWord>;
+    seqAffWords(tapPreApplyRules?: (dicEntry: string, index: number) => any, maxDepth?: number): Sequence<AffWord>;
     /**
+     * create an iterable sequence of the words in the dictionary.
+     *
+     * @param tapPreApplyRules -- optional function to be called before rules are applied to a word.
+     *                            It is mostly used for monitoring progress in combination with `size`.
+     */
+    seqTransformDictionaryEntries(tapPreApplyRules?: (dicEntry: string, index: number) => any, maxDepth?: number): Sequence<AffWord[]>;
+    /**
+     * Iterator for all the words in the dictionary. The words are in the order found in the .dic after the
+     * transformations have been applied. Forbidden and CompoundOnly ARE INCLUDED.
+     *
      * @internal
@@ -48,2 +58,6 @@ */
     /**
+     * Returns an iterable that will only return stand alone words.
+     */
+    wholeWords(): Sequence<string>;
+    /**
      * @internal
@@ -50,0 +64,0 @@ */

dist/IterableHunspellReader.js

@@ -57,5 +57,5 @@ "use strict";
      * Iterator for all the words in the dictionary. The words are in the order found in the .dic after the
-     * transformations have been applied. No filtering is done based upon the AFF flags.
+     * transformations have been applied. Forbidden and CompoundOnly words are filtered out.
      */
-    [Symbol.iterator]() { return this.seqWords(); }
+    [Symbol.iterator]() { return this.wholeWords(); }
     /**
@@ -68,2 +68,11 @@ * create an iterable sequence of the words in the dictionary.
     seqAffWords(tapPreApplyRules, maxDepth) {
+        return this.seqTransformDictionaryEntries(tapPreApplyRules, maxDepth).concatMap(a => a);
+    }
+    /**
+     * create an iterable sequence of the words in the dictionary.
+     *
+     * @param tapPreApplyRules -- optional function to be called before rules are applied to a word.
+     *                            It is mostly used for monitoring progress in combination with `size`.
+     */
+    seqTransformDictionaryEntries(tapPreApplyRules, maxDepth) {
         const seq = gensequence_1.genSequence(this.src.dic);
@@ -73,12 +82,26 @@ let count = 0;
         return dicWords
-            .filter(a => !!a.trim())
-            .concatMap(dicWord => this.aff.applyRulesToDicEntry(dicWord, maxDepth));
+            .map(dicWord => this.aff.applyRulesToDicEntry(dicWord, maxDepth));
     }
     /**
+     * Iterator for all the words in the dictionary. The words are in the order found in the .dic after the
+     * transformations have been applied. Forbidden and CompoundOnly ARE INCLUDED.
+     *
      * @internal
      */
     seqWords() {
-        return this.seqAffWords().map(w => w.word).filter(createMatchingWordsFilter());
+        return this.seqAffWords()
+            .map(w => w.word)
+            .filter(createMatchingWordsFilter());
     }
     /**
+     * Returns an iterable that will only return stand alone words.
+     */
+    wholeWords() {
+        return this.seqAffWords()
+            // Filter out words that are forbidden or only allowed in Compounds.
+            .filter(w => !w.flags.isForbiddenWord && !w.flags.isOnlyAllowedInCompound)
+            .map(w => w.word)
+            .filter(createMatchingWordsFilter());
+    }
+    /**
      * @internal
@@ -91,7 +114,8 @@ */
         return __awaiter(this, void 0, void 0, function* () {
-            const aff = yield affReader_1.parseAffFileToAff(affFile);
+            const aff = yield affReader_1.parseAffFileToAff(affFile, defaultEncoding);
             const buffer = yield fs.readFile(dicFile);
-            const dicFileContent = iconv_lite_1.decode(buffer, aff.affInfo.SET || defaultEncoding);
+            const dicFileContent = iconv_lite_1.decode(buffer, aff.affInfo.SET);
             const dic = dicFileContent.split('\n')
                 .slice(1) // The first entry is the count of entries.
+                .map(a => a.trim())
                 .filter(line => !!line);
@@ -98,0 +122,0 @@ return new IterableHunspellReader({ aff, dic });

package.json

 {
   "name": "hunspell-reader",
-  "version": "3.1.5",
+  "version": "3.2.0",
   "description": "A library for reading Hunspell Dictionary Files",
@@ -5,0 +5,0 @@ "bin": "bin.js",

New alerts

License Policy Violation

License

This package is not allowed per your license policy. Review the package's license to ensure compliance.

Found 1 instance in 1 package

Fixed alerts

License Policy Violation

License

This package is not allowed per your license policy. Review the package's license to ensure compliance.

Found 1 instance in 1 package

Improved metrics

Total package byte prevSize

55718

increased by5.53%

Lines of code

1336

increased by4.87%

No dependency changes