How to use the cspell-util-bundle.xregexp function in cspell-util-bundle

To help you get started, we’ve selected a few cspell-util-bundle examples, based on popular ways it is used in public projects.

Secure your code as it's written. Use Snyk Code to scan source code in minutes - no build needed - and fix issues immediately.

github streetsidesoftware / cspell / packages / cspell-tools / src / compiler / text.ts View on Github external
// cSpell:ignore ings ning gimuy
// cSpell:words xregexp

import { xregexp as XRegExp } from 'cspell-util-bundle';

const regExUpperSOrIng = XRegExp('(\\p{Lu}+\'?(?:s|ing|ies|es|ings|ed|ning))(?!\\p{Ll})', 'g');
const regExSplitWords = XRegExp('(\\p{Ll})(\\p{Lu})', 'g');
const regExSplitWords2 = XRegExp('(\\p{Lu})(\\p{Lu}\\p{Ll})', 'g');

/**
 * Split camelCase words into an array of strings.
 */
export function splitCamelCaseWord(word: string): string[] {
    const wPrime = word.replace(regExUpperSOrIng, s => s[0] + s.substr(1).toLowerCase());
    const separator = '_<^*_*^>_';
    const pass1 = XRegExp.replace(wPrime, regExSplitWords, '$1' + separator + '$2');
    const pass2 = XRegExp.replace(pass1, regExSplitWords2, '$1' + separator + '$2');
    return XRegExp.split(pass2, separator);
}
github streetsidesoftware / cspell / packages / cspell-lib / src / util / text.ts View on Github external
export function extractWordsFromTextOffset(text: TextOffset): Sequence {
    const reg = XRegExp(regExWords);
    const reg2 = XRegExp(regExWords);
    return matchToTextOffset(reg, text)
        // remove characters that match against \p{L} but are not letters (Chinese characters are an example).
        .map(({ text, offset }) => ({
            text: XRegExp.replace(text, regExIgnoreCharacters, (match: string) => ' '.repeat(match.length)),
            offset,
        }))
        .concatMap(wo => matchToTextOffset(reg2, wo))
        .filter(wo => !!wo.text);
}
github streetsidesoftware / cspell / packages / cspell-lib / src / util / text.ts View on Github external
}

export interface TextDocumentOffset extends TextOffset {
    uri?: string;
    doc: string;
    row: number;
    col: number;
}

const regExLines = /.*(\r?\n|$)/g;
// const regExIdentifiers = XRegExp('(?:\\p{L}|[0-9_\'])+', 'gi');
const regExUpperSOrIng = XRegExp('(\\p{Lu}+\\\\?[\'’]?(?:s|ing|ies|es|ings|ed|ning))(?!\\p{Ll})', 'g');
const regExSplitWords = XRegExp('(\\p{Ll})(\\p{Lu})', 'g');
const regExSplitWords2 = XRegExp('(\\p{Lu})(\\p{Lu}\\p{Ll})', 'g');
const regExWords = XRegExp("\\p{L}(?:\\\\?['’]\\p{L}|\\p{L})+|\\p{L}", 'g');
const regExIgnoreCharacters = XRegExp('\\p{Hiragana}|\\p{Han}|\\p{Katakana}|[\\u30A0-\\u30FF]|[\\p{Hangul}]', 'g');
const regExFirstUpper = XRegExp('^\\p{Lu}\\p{Ll}+$');
const regExAllUpper = XRegExp('^\\p{Lu}+$');
const regExAllLower = XRegExp('^\\p{Ll}+$');

const regExMatchRegExParts = /^\/(.*)\/([gimuy]*)$/;

const regExAccents = XRegExp('\\p{M}', 'g');

export function splitCamelCaseWordWithOffset(wo: TextOffset): Array {
    return splitCamelCaseWord(wo.text)
        .map(scanMap(
            (last, text) => ({ text, offset: last.offset + last.text.length }),
            { text: '', offset: wo.offset }
        ));
}
github streetsidesoftware / cspell / packages / cspell-lib / src / util / text.ts View on Github external
}

const regExLines = /.*(\r?\n|$)/g;
// const regExIdentifiers = XRegExp('(?:\\p{L}|[0-9_\'])+', 'gi');
const regExUpperSOrIng = XRegExp('(\\p{Lu}+\\\\?[\'’]?(?:s|ing|ies|es|ings|ed|ning))(?!\\p{Ll})', 'g');
const regExSplitWords = XRegExp('(\\p{Ll})(\\p{Lu})', 'g');
const regExSplitWords2 = XRegExp('(\\p{Lu})(\\p{Lu}\\p{Ll})', 'g');
const regExWords = XRegExp("\\p{L}(?:\\\\?['’]\\p{L}|\\p{L})+|\\p{L}", 'g');
const regExIgnoreCharacters = XRegExp('\\p{Hiragana}|\\p{Han}|\\p{Katakana}|[\\u30A0-\\u30FF]|[\\p{Hangul}]', 'g');
const regExFirstUpper = XRegExp('^\\p{Lu}\\p{Ll}+$');
const regExAllUpper = XRegExp('^\\p{Lu}+$');
const regExAllLower = XRegExp('^\\p{Ll}+$');

const regExMatchRegExParts = /^\/(.*)\/([gimuy]*)$/;

const regExAccents = XRegExp('\\p{M}', 'g');

export function splitCamelCaseWordWithOffset(wo: TextOffset): Array {
    return splitCamelCaseWord(wo.text)
        .map(scanMap(
            (last, text) => ({ text, offset: last.offset + last.text.length }),
            { text: '', offset: wo.offset }
        ));
}

/**
 * Split camelCase words into an array of strings.
 */
export function splitCamelCaseWord(word: string): string[] {
    const wPrime = word.replace(regExUpperSOrIng, s => s[0] + s.substr(1).toLowerCase());
    const separator = '_<^*_*^>_';
    const pass1 = XRegExp.replace(wPrime, regExSplitWords, '$1' + separator + '$2');
github streetsidesoftware / cspell / packages / cspell-lib / src / util / text.ts View on Github external
export interface TextOffset {
    text: string;
    offset: number;
}

export interface TextDocumentOffset extends TextOffset {
    uri?: string;
    doc: string;
    row: number;
    col: number;
}

const regExLines = /.*(\r?\n|$)/g;
// const regExIdentifiers = XRegExp('(?:\\p{L}|[0-9_\'])+', 'gi');
const regExUpperSOrIng = XRegExp('(\\p{Lu}+\\\\?[\'’]?(?:s|ing|ies|es|ings|ed|ning))(?!\\p{Ll})', 'g');
const regExSplitWords = XRegExp('(\\p{Ll})(\\p{Lu})', 'g');
const regExSplitWords2 = XRegExp('(\\p{Lu})(\\p{Lu}\\p{Ll})', 'g');
const regExWords = XRegExp("\\p{L}(?:\\\\?['’]\\p{L}|\\p{L})+|\\p{L}", 'g');
const regExIgnoreCharacters = XRegExp('\\p{Hiragana}|\\p{Han}|\\p{Katakana}|[\\u30A0-\\u30FF]|[\\p{Hangul}]', 'g');
const regExFirstUpper = XRegExp('^\\p{Lu}\\p{Ll}+$');
const regExAllUpper = XRegExp('^\\p{Lu}+$');
const regExAllLower = XRegExp('^\\p{Ll}+$');

const regExMatchRegExParts = /^\/(.*)\/([gimuy]*)$/;

const regExAccents = XRegExp('\\p{M}', 'g');

export function splitCamelCaseWordWithOffset(wo: TextOffset): Array {
    return splitCamelCaseWord(wo.text)
        .map(scanMap(
            (last, text) => ({ text, offset: last.offset + last.text.length }),
github streetsidesoftware / cspell / packages / cspell-lib / src / util / text.ts View on Github external
export function extractWordsFromTextOffset(text: TextOffset): Sequence {
    const reg = XRegExp(regExWords);
    const reg2 = XRegExp(regExWords);
    return matchToTextOffset(reg, text)
        // remove characters that match against \p{L} but are not letters (Chinese characters are an example).
        .map(({ text, offset }) => ({
            text: XRegExp.replace(text, regExIgnoreCharacters, (match: string) => ' '.repeat(match.length)),
            offset,
        }))
        .concatMap(wo => matchToTextOffset(reg2, wo))
        .filter(wo => !!wo.text);
}
github streetsidesoftware / cspell / packages / cspell-lib / src / util / text.ts View on Github external
uri?: string;
    doc: string;
    row: number;
    col: number;
}

const regExLines = /.*(\r?\n|$)/g;
// const regExIdentifiers = XRegExp('(?:\\p{L}|[0-9_\'])+', 'gi');
const regExUpperSOrIng = XRegExp('(\\p{Lu}+\\\\?[\'’]?(?:s|ing|ies|es|ings|ed|ning))(?!\\p{Ll})', 'g');
const regExSplitWords = XRegExp('(\\p{Ll})(\\p{Lu})', 'g');
const regExSplitWords2 = XRegExp('(\\p{Lu})(\\p{Lu}\\p{Ll})', 'g');
const regExWords = XRegExp("\\p{L}(?:\\\\?['’]\\p{L}|\\p{L})+|\\p{L}", 'g');
const regExIgnoreCharacters = XRegExp('\\p{Hiragana}|\\p{Han}|\\p{Katakana}|[\\u30A0-\\u30FF]|[\\p{Hangul}]', 'g');
const regExFirstUpper = XRegExp('^\\p{Lu}\\p{Ll}+$');
const regExAllUpper = XRegExp('^\\p{Lu}+$');
const regExAllLower = XRegExp('^\\p{Ll}+$');

const regExMatchRegExParts = /^\/(.*)\/([gimuy]*)$/;

const regExAccents = XRegExp('\\p{M}', 'g');

export function splitCamelCaseWordWithOffset(wo: TextOffset): Array {
    return splitCamelCaseWord(wo.text)
        .map(scanMap(
            (last, text) => ({ text, offset: last.offset + last.text.length }),
            { text: '', offset: wo.offset }
        ));
}

/**
 * Split camelCase words into an array of strings.
 */
github streetsidesoftware / cspell / packages / cspell-tools / src / compiler / wordListCompiler.ts View on Github external
import { xregexp as XRegExp } from 'cspell-util-bundle';
import { genSequence, Sequence } from 'gensequence';
import * as Text from './text';
import * as path from 'path';
import { mkdirp } from 'fs-extra';
import * as Trie from 'cspell-trie-lib';
import { writeSeqToFile } from './fileWriter';
import { uniqueFilter } from 'hunspell-reader/dist/util';

const regNonWordOrSpace = XRegExp("[^\\p{L}' ]+", 'gi');
const regExpSpaceOrDash = /(?:\s+)|(?:-+)/g;
const regExpRepeatChars = /(.)\1{3,}/i;

export type Logger = (message?: any, ...optionalParams: any[]) => void;

let log: Logger = defaultLogger;

export function setLogger(logger?: Logger) {
    log = logger ?? defaultLogger;
}

function defaultLogger(message?: any, ...optionalParams: any[]) {
    console.log(message, ...optionalParams);
}

export function normalizeWords(lines: Sequence) {

cspell-util-bundle

This is a bundle of external libraries used by cspell bundled into a single `.js`

MIT
Latest version published 4 years ago

Package Health Score

69 / 100
Full package analysis

Similar packages