cspell-lib 6.8.2 → 6.9.0

package/dist/Settings/patterns.js

@@ -1,7 +1,7 @@
 "use strict";
 Object.defineProperty(exports, "__esModule", { value: true });
 exports.resolvePatterns = void 0;
-const text_1 = require("../util/text");
+const textRegex_1 = require("../util/textRegex");
 const util_1 = require("../util/util");
 function resolvePatterns(regExpList = [], patternDefinitions = []) {
     const patternMap = new Map(patternDefinitions.map((def) => [def.name.toLowerCase(), def.pattern]));
@@ -27,6 +27,6 @@ function resolvePatterns(regExpList = [], patternDefinitions = []) {
 }
 exports.resolvePatterns = resolvePatterns;
 function toRegExp(pattern) {
-    return pattern instanceof RegExp ? new RegExp(pattern) : (0, text_1.stringToRegExp)(pattern, 'gim', 'g');
+    return pattern instanceof RegExp ? new RegExp(pattern) : (0, textRegex_1.stringToRegExp)(pattern, 'gim', 'g');
 }
 //# sourceMappingURL=patterns.js.map

package/dist/util/text.d.ts

@@ -1,4 +1,5 @@
 import type { TextDocumentOffset, TextOffset } from '@cspell/cspell-types';
+export { stringToRegExp } from './textRegex';
 export declare function splitCamelCaseWordWithOffset(wo: TextOffset): Array<TextOffset>;
 /**
  * Split camelCase words into an array of strings.
@@ -38,7 +39,6 @@ export declare function camelToSnake(word: string): string;
 export declare function matchCase(example: string, word: string): string;
 export declare function textOffset(text: string, offset?: number): TextOffset;
 export declare function extractText(textOffset: TextOffset, startPos: number, endPos: number): string;
-export declare function stringToRegExp(pattern: string | RegExp, defaultFlags?: string, forceFlags?: string): RegExp | undefined;
 export declare function calculateTextDocumentOffsets<T extends TextOffset>(uri: string, doc: string, wordOffsets: T[]): (TextDocumentOffset & T)[];
 export declare function removeAccents(text: string): string;
 export declare const __testing__: {

package/dist/util/text.js

@@ -1,11 +1,13 @@
 "use strict";
 Object.defineProperty(exports, "__esModule", { value: true });
-exports.__testing__ = exports.removeAccents = exports.calculateTextDocumentOffsets = exports.stringToRegExp = exports.extractText = exports.textOffset = exports.matchCase = exports.camelToSnake = exports.snakeToCamel = exports.lcFirst = exports.ucFirst = exports.isFirstCharacterLower = exports.isFirstCharacterUpper = exports.isLowerCase = exports.isUpperCase = exports.extractWordsFromCodeTextOffset = exports.extractWordsFromCode = exports.extractPossibleWordsFromTextOffset = exports.cleanTextOffset = exports.cleanText = exports.extractWordsFromTextOffset = exports.extractWordsFromText = exports.extractLinesOfText = exports.matchToTextOffset = exports.matchStringToTextOffset = exports.match = exports.splitCamelCaseWord = exports.splitCamelCaseWordWithOffset = void 0;
+exports.__testing__ = exports.removeAccents = exports.calculateTextDocumentOffsets = exports.extractText = exports.textOffset = exports.matchCase = exports.camelToSnake = exports.snakeToCamel = exports.lcFirst = exports.ucFirst = exports.isFirstCharacterLower = exports.isFirstCharacterUpper = exports.isLowerCase = exports.isUpperCase = exports.extractWordsFromCodeTextOffset = exports.extractWordsFromCode = exports.extractPossibleWordsFromTextOffset = exports.cleanTextOffset = exports.cleanText = exports.extractWordsFromTextOffset = exports.extractWordsFromText = exports.extractLinesOfText = exports.matchToTextOffset = exports.matchStringToTextOffset = exports.match = exports.splitCamelCaseWord = exports.splitCamelCaseWordWithOffset = exports.stringToRegExp = void 0;
 const cspell_pipe_1 = require("@cspell/cspell-pipe");
 const gensequence_1 = require("gensequence");
 const search_1 = require("./search");
 const textRegex_1 = require("./textRegex");
 const util_1 = require("./util");
+var textRegex_2 = require("./textRegex");
+Object.defineProperty(exports, "stringToRegExp", { enumerable: true, get: function () { return textRegex_2.stringToRegExp; } });
 // CSpell:ignore ings ning gimuy tsmerge
 function splitCamelCaseWordWithOffset(wo) {
     return splitCamelCaseWord(wo.text).map((0, util_1.scanMap)((last, text) => ({ text, offset: last.offset + last.text.length }), {
@@ -155,25 +157,6 @@ exports.extractText = extractText;
 function offsetMap(offset) {
     return (xo) => ({ ...xo, offset: xo.offset + offset });
 }
-function stringToRegExp(pattern, defaultFlags = 'gimu', forceFlags = 'g') {
-    if (pattern instanceof RegExp) {
-        return pattern;
-    }
-    try {
-        const [, pat, flag] = [...(pattern.match(textRegex_1.regExMatchRegExParts) || ['', pattern, defaultFlags]), forceFlags];
-        // Make sure the flags are unique.
-        const flags = [...new Set(forceFlags + flag)].join('').replace(/[^gimuy]/g, '');
-        if (pat) {
-            const regex = new RegExp(pat, flags);
-            return regex;
-        }
-    }
-    catch (e) {
-        /* empty */
-    }
-    return undefined;
-}
-exports.stringToRegExp = stringToRegExp;
 function calculateTextDocumentOffsets(uri, doc, wordOffsets) {
     const lines = [
         -1,

package/dist/util/textRegex.d.ts

@@ -16,4 +16,5 @@ export declare const regExEscapeCharacters: RegExp;
 export declare const regExDanglingQuote: RegExp;
 /** Match tailing endings after CAPS words */
 export declare const regExTrailingEndings: RegExp;
+export declare function stringToRegExp(pattern: string | RegExp, defaultFlags?: string, forceFlags?: string): RegExp | undefined;
 //# sourceMappingURL=textRegex.d.ts.map

package/dist/util/textRegex.js

@@ -1,7 +1,7 @@
 "use strict";
-// cspell:ignore ings ning gimuy anrvtbf
+// cspell:ignore ings ning gimuy anrvtbf gimuxy
 Object.defineProperty(exports, "__esModule", { value: true });
-exports.regExTrailingEndings = exports.regExDanglingQuote = exports.regExEscapeCharacters = exports.regExAccents = exports.regExMatchRegExParts = exports.regExPossibleWordBreaks = exports.regExAllLower = exports.regExAllUpper = exports.regExFirstUpper = exports.regExIgnoreCharacters = exports.regExWordsAndDigits = exports.regExWords = exports.regExSplitWords2 = exports.regExSplitWords = exports.regExUpperSOrIng = exports.regExLines = void 0;
+exports.stringToRegExp = exports.regExTrailingEndings = exports.regExDanglingQuote = exports.regExEscapeCharacters = exports.regExAccents = exports.regExMatchRegExParts = exports.regExPossibleWordBreaks = exports.regExAllLower = exports.regExAllUpper = exports.regExFirstUpper = exports.regExIgnoreCharacters = exports.regExWordsAndDigits = exports.regExWords = exports.regExSplitWords2 = exports.regExSplitWords = exports.regExUpperSOrIng = exports.regExLines = void 0;
 exports.regExLines = /.*(\r?\n|$)/g;
 exports.regExUpperSOrIng = /([\p{Lu}\p{M}]+\\?['’]?(?:s|ing|ies|es|ings|ed|ning))(?!\p{Ll})/gu;
 exports.regExSplitWords = /(\p{Ll}\p{M}?)(\p{Lu})/gu;
@@ -13,11 +13,118 @@ exports.regExFirstUpper = /^\p{Lu}\p{M}?\p{Ll}+$/u;
 exports.regExAllUpper = /^(?:\p{Lu}\p{M}?)+$/u;
 exports.regExAllLower = /^(?:\p{Ll}\p{M}?)+$/u;
 exports.regExPossibleWordBreaks = /[-_’']/g;
-exports.regExMatchRegExParts = /^\/(.*)\/([gimuy]*)$/;
+exports.regExMatchRegExParts = /^\s*\/([\s\S]*?)\/([gimuxy]*)\s*$/;
 exports.regExAccents = /\p{M}/gu;
 exports.regExEscapeCharacters = /(?<=\\)[anrvtbf]/gi;
 /** Matches against leading `'` or `{single letter}'` */
 exports.regExDanglingQuote = /(?<=(?:^|(?!\p{M})\P{L})(?:\p{L}\p{M}?)?)[']/gu;
 /** Match tailing endings after CAPS words */
 exports.regExTrailingEndings = /(?<=(?:\p{Lu}\p{M}?){2})['’]?(?:s|d|ings?|ies|e[ds]?|ning|th|nth)(?!\p{Ll})/gu;
+function stringToRegExp(pattern, defaultFlags = 'gimu', forceFlags = 'g') {
+    if (pattern instanceof RegExp) {
+        return pattern;
+    }
+    try {
+        const [, pat, flag] = [
+            ...(pattern.match(exports.regExMatchRegExParts) || ['', pattern.trim(), defaultFlags]),
+            forceFlags,
+        ];
+        if (pat) {
+            const regPattern = flag.includes('x') ? removeVerboseFromRegExp(pat) : pat;
+            // Make sure the flags are unique.
+            const flags = [...new Set(forceFlags + flag)].join('').replace(/[^gimuy]/g, '');
+            const regex = new RegExp(regPattern, flags);
+            return regex;
+        }
+    }
+    catch (e) {
+        /* empty */
+    }
+    return undefined;
+}
+exports.stringToRegExp = stringToRegExp;
+const SPACES = {
+    ' ': true,
+    '\n': true,
+    '\r': true,
+    '\t': true,
+};
+/**
+ * Remove all whitespace and comments from a regexp string. The format follows Pythons Verbose.
+ * Note: this is a best attempt. Special cases for comments: `#` and spaces should be proceeded with a `\`
+ *
+ * All space must be proceeded by a `\` or in a character class `[]`
+ *
+ * @param pattern - the pattern to clean
+ */
+function removeVerboseFromRegExp(pattern) {
+    function escape(acc) {
+        const char = pattern[acc.idx];
+        if (char !== '\\')
+            return undefined;
+        const next = pattern[++acc.idx];
+        acc.idx++;
+        if (next === '#') {
+            acc.result += '#';
+            return acc;
+        }
+        if (!(next in SPACES)) {
+            acc.result += '\\' + next;
+            return acc;
+        }
+        acc.result += next;
+        if (next === '\r' && pattern[acc.idx] === '\n') {
+            acc.result += '\n';
+            acc.idx++;
+        }
+        return acc;
+    }
+    function braces(acc) {
+        const char = pattern[acc.idx];
+        if (char !== '[')
+            return undefined;
+        acc.result += char;
+        acc.idx++;
+        let escCount = 0;
+        while (acc.idx < pattern.length) {
+            const char = pattern[acc.idx];
+            acc.result += char;
+            acc.idx++;
+            if (char === ']' && !(escCount & 1))
+                break;
+            escCount = char === '\\' ? escCount + 1 : 0;
+        }
+        return acc;
+    }
+    function spaces(acc) {
+        const char = pattern[acc.idx];
+        if (!(char in SPACES))
+            return undefined;
+        acc.idx++;
+        return acc;
+    }
+    function comments(acc) {
+        const char = pattern[acc.idx];
+        if (char !== '#')
+            return undefined;
+        while (acc.idx < pattern.length && pattern[acc.idx] !== '\n') {
+            acc.idx++;
+        }
+        return acc;
+    }
+    function copy(acc) {
+        const char = pattern[acc.idx++];
+        acc.result += char;
+        return acc;
+    }
+    const reducers = [escape, braces, spaces, comments, copy];
+    const result = { idx: 0, result: '' };
+    while (result.idx < pattern.length) {
+        for (const r of reducers) {
+            if (r(result))
+                break;
+        }
+    }
+    return result.result;
+}
 //# sourceMappingURL=textRegex.js.map

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "cspell-lib",
-  "version": "6.8.2",
+  "version": "6.9.0",
   "description": "A library of useful functions used across various cspell tools.",
   "main": "dist/index.js",
   "typings": "dist/index.d.ts",
@@ -48,17 +48,17 @@
   },
   "homepage": "https://github.com/streetsidesoftware/cspell#readme",
   "dependencies": {
-    "@cspell/cspell-bundled-dicts": "^6.8.2",
-    "@cspell/cspell-pipe": "^6.8.2",
-    "@cspell/cspell-types": "^6.8.2",
+    "@cspell/cspell-bundled-dicts": "^6.9.0",
+    "@cspell/cspell-pipe": "^6.9.0",
+    "@cspell/cspell-types": "^6.9.0",
     "clear-module": "^4.1.2",
     "comment-json": "^4.2.3",
     "configstore": "^5.0.1",
     "cosmiconfig": "^7.0.1",
-    "cspell-glob": "^6.8.2",
-    "cspell-grammar": "^6.8.2",
-    "cspell-io": "^6.8.2",
-    "cspell-trie-lib": "^6.8.2",
+    "cspell-glob": "^6.9.0",
+    "cspell-grammar": "^6.9.0",
+    "cspell-io": "^6.9.0",
+    "cspell-trie-lib": "^6.9.0",
     "fast-equals": "^4.0.3",
     "find-up": "^5.0.0",
     "fs-extra": "^10.1.0",
@@ -83,15 +83,15 @@
     "@cspell/dict-python": "^2.0.6",
     "@types/configstore": "^5.0.1",
     "@types/fs-extra": "^9.0.13",
-    "@types/jest": "^29.0.1",
-    "@types/node": "^18.7.16",
+    "@types/jest": "^29.0.2",
+    "@types/node": "^18.7.18",
     "cspell-dict-nl-nl": "^1.1.2",
     "jest": "^29.0.3",
     "lorem-ipsum": "^2.0.8",
     "rimraf": "^3.0.2",
     "rollup": "^2.79.0",
     "rollup-plugin-dts": "^4.2.2",
-    "ts-jest": "^29.0.0"
+    "ts-jest": "^29.0.1"
   },
-  "gitHead": "fb47a5f2f93d333fe5540142f3217e4981a7c27d"
+  "gitHead": "d68b540deb382bafb2dce1be8f14935cc0d3cd5d"
 }