druid/node_modules/cspell-lib/dist/textValidator.js

"use strict";
var __createBinding = (this && this.__createBinding) || (Object.create ? (function(o, m, k, k2) {
    if (k2 === undefined) k2 = k;
    Object.defineProperty(o, k2, { enumerable: true, get: function() { return m[k]; } });
}) : (function(o, m, k, k2) {
    if (k2 === undefined) k2 = k;
    o[k2] = m[k];
}));
var __setModuleDefault = (this && this.__setModuleDefault) || (Object.create ? (function(o, v) {
    Object.defineProperty(o, "default", { enumerable: true, value: v });
}) : function(o, v) {
    o["default"] = v;
});
var __importStar = (this && this.__importStar) || function (mod) {
    if (mod && mod.__esModule) return mod;
    var result = {};
    if (mod != null) for (var k in mod) if (k !== "default" && Object.prototype.hasOwnProperty.call(mod, k)) __createBinding(result, mod, k);
    __setModuleDefault(result, mod);
    return result;
};
Object.defineProperty(exports, "__esModule", { value: true });
exports._testMethods = exports.hasWordCheck = exports.isWordValid = exports.calcTextInclusionRanges = exports.validateText = exports.minWordSplitLen = exports.defaultMinWordLength = exports.defaultMaxDuplicateProblems = exports.defaultMaxNumberOfProblems = void 0;
const Text = __importStar(require("./util/text"));
const TextRange = __importStar(require("./util/TextRange"));
const RxPat = __importStar(require("./Settings/RegExpPatterns"));
exports.defaultMaxNumberOfProblems = 200;
exports.defaultMaxDuplicateProblems = 5;
exports.defaultMinWordLength = 4;
exports.minWordSplitLen = 3;
function validateText(text, dict, options) {
    const { maxNumberOfProblems = exports.defaultMaxNumberOfProblems, maxDuplicateProblems = exports.defaultMaxDuplicateProblems, } = options;
    const mapOfProblems = new Map();
    const includeRanges = calcTextInclusionRanges(text, options);
    const validator = lineValidator(dict, options);
    return Text.extractLinesOfText(text)
        .concatMap(mapTextOffsetsAgainstRanges(includeRanges))
        .concatMap(validator)
        .filter((wo) => {
        const word = wo.text;
        // Keep track of the number of times we have seen the same problem
        mapOfProblems.set(word, (mapOfProblems.get(word) || 0) + 1);
        // Filter out if there is too many
        return mapOfProblems.get(word) < maxDuplicateProblems;
    })
        .take(maxNumberOfProblems);
}
exports.validateText = validateText;
function calcTextInclusionRanges(text, options) {
    const { ignoreRegExpList = [], includeRegExpList = [] } = options;
    const filteredIncludeList = includeRegExpList.filter((a) => !!a);
    const finalIncludeList = filteredIncludeList.length ? filteredIncludeList : ['.*'];
    const includeRanges = TextRange.excludeRanges(TextRange.findMatchingRangesForPatterns(finalIncludeList, text), TextRange.findMatchingRangesForPatterns(ignoreRegExpList, text));
    return includeRanges;
}
exports.calcTextInclusionRanges = calcTextInclusionRanges;
function lineValidator(dict, options) {
    const { minWordLength = exports.defaultMinWordLength, flagWords = [], ignoreWords = [], allowCompoundWords = false, ignoreCase = true, caseSensitive = false, } = options;
    const checkOptions = {
        ...options,
        allowCompoundWords,
        ignoreCase,
        caseSensitive,
    };
    const setOfFlagWords = new Set(flagWords);
    const mappedIgnoreWords = options.caseSensitive
        ? ignoreWords
        : ignoreWords.concat(ignoreWords.map((a) => a.toLowerCase()));
    const ignoreWordsSet = new Set(mappedIgnoreWords);
    const setOfKnownSuccessfulWords = new Set();
    const rememberFilter = (fn) => (v) => {
        const keep = fn(v);
        if (!keep) {
            setOfKnownSuccessfulWords.add(v.text);
        }
        return keep;
    };
    const filterAlreadyChecked = (wo) => {
        return !setOfKnownSuccessfulWords.has(wo.text);
    };
    function testForFlaggedWord(wo) {
        return setOfFlagWords.has(wo.text) || setOfFlagWords.has(wo.text.toLowerCase());
    }
    function checkFlagWords(word) {
        const isFlagged = testForFlaggedWord(word);
        word.isFlagged = isFlagged;
        return word;
    }
    function checkWord(word, options) {
        const isFlagged = testForFlaggedWord(word);
        const isFound = isFlagged ? undefined : isWordValid(dict, word, word.line, options);
        return { ...word, isFlagged, isFound };
    }
    const fn = (lineSegment) => {
        function checkFullWord(vr) {
            if (vr.isFlagged) {
                return [vr];
            }
            const codeWordResults = Text.extractWordsFromCodeTextOffset(vr)
                .filter(filterAlreadyChecked)
                .filter(rememberFilter((wo) => wo.text.length >= minWordLength))
                .map((t) => ({ ...t, line: vr.line }))
                .map((wo) => {
                const vr = { ...wo, text: wo.text.toLowerCase() };
                return vr;
            })
                .map((wo) => (wo.isFlagged ? wo : checkWord(wo, checkOptions)))
                .filter(rememberFilter((wo) => wo.isFlagged || !wo.isFound))
                .filter(rememberFilter((wo) => !ignoreWordsSet.has(wo.text)))
                .filter(rememberFilter((wo) => !RxPat.regExHexDigits.test(wo.text))) // Filter out any hex numbers
                .filter(rememberFilter((wo) => !RxPat.regExRepeatedChar.test(wo.text))) // Filter out any repeated characters like xxxxxxxxxx
                // get back the original text.
                .map((wo) => ({ ...wo, text: Text.extractText(lineSegment, wo.offset, wo.offset + wo.text.length) }))
                .toArray();
            if (!codeWordResults.length || ignoreWordsSet.has(vr.text) || checkWord(vr, checkOptions).isFound) {
                rememberFilter((_) => false)(vr);
                return [];
            }
            return codeWordResults;
        }
        // Check the whole words, not yet split
        const checkedWords = Text.extractWordsFromTextOffset(lineSegment)
            .filter(filterAlreadyChecked)
            .filter(rememberFilter((wo) => wo.text.length >= minWordLength))
            .map((wo) => ({ ...wo, line: lineSegment }))
            .map(checkFlagWords)
            .concatMap(checkFullWord);
        return checkedWords;
    };
    return fn;
}
function isWordValid(dict, wo, line, options) {
    const firstTry = hasWordCheck(dict, wo.text, options);
    return (firstTry ||
        // Drop the first letter if it is preceded by a '\'.
        (line.text[wo.offset - line.offset - 1] === '\\' && hasWordCheck(dict, wo.text.slice(1), options)));
}
exports.isWordValid = isWordValid;
function hasWordCheck(dict, word, options) {
    word = word.replace(/\\/g, '');
    // Do not pass allowCompounds down if it is false, that allows for the dictionary to override the value based upon its own settings.
    return dict.has(word, convertCheckOptionsToHasOptions(options));
}
exports.hasWordCheck = hasWordCheck;
function convertCheckOptionsToHasOptions(opt) {
    const { ignoreCase, allowCompoundWords } = opt;
    return {
        ignoreCase,
        useCompounds: allowCompoundWords || undefined,
    };
}
/**
 * Returns a mapper function that will
 * @param includeRanges Allowed ranges for words.
 */
function mapTextOffsetsAgainstRanges(includeRanges) {
    let rangePos = 0;
    const mapper = (textOffset) => {
        if (!includeRanges.length) {
            return [];
        }
        const parts = [];
        const { text, offset } = textOffset;
        const wordEndPos = offset + text.length;
        let wordStartPos = offset;
        while (rangePos && (rangePos >= includeRanges.length || includeRanges[rangePos].startPos > wordStartPos)) {
            rangePos -= 1;
        }
        while (wordStartPos < wordEndPos) {
            while (includeRanges[rangePos] && includeRanges[rangePos].endPos <= wordStartPos) {
                rangePos += 1;
            }
            if (!includeRanges[rangePos] || wordEndPos < includeRanges[rangePos].startPos) {
                break;
            }
            const { startPos, endPos } = includeRanges[rangePos];
            const a = Math.max(wordStartPos, startPos);
            const b = Math.min(wordEndPos, endPos);
            parts.push({ offset: a, text: text.slice(a - offset, b - offset) });
            wordStartPos = b;
        }
        return parts.filter((wo) => !!wo.text);
    };
    return mapper;
}
exports._testMethods = {
    mapWordsAgainstRanges: mapTextOffsetsAgainstRanges,
};
//# sourceMappingURL=textValidator.js.map