rosaenlg-filter/dist/index.js

Filtering feature of RosaeNLG

"use strict";
/**
 * @license
 * Copyright 2019 Ludan Stoecklé
 * SPDX-License-Identifier: Apache-2.0
 */
var __createBinding = (this && this.__createBinding) || (Object.create ? (function(o, m, k, k2) {
    if (k2 === undefined) k2 = k;
    var desc = Object.getOwnPropertyDescriptor(m, k);
    if (!desc || ("get" in desc ? !m.__esModule : desc.writable || desc.configurable)) {
      desc = { enumerable: true, get: function() { return m[k]; } };
    }
    Object.defineProperty(o, k2, desc);
}) : (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.filter = exports.EATSPACE = exports.inlineHtmlElts = exports.blockLevelHtmlElts = void 0;
const punctuation = __importStar(require("./punctuation"));
const clean = __importStar(require("./clean"));
const titlecase_1 = require("./titlecase");
const protect = __importStar(require("./protect"));
const protectTag_1 = require("./protectTag");
const html = __importStar(require("./html"));
const languageFilterHelper_1 = require("./languageFilterHelper");
exports.blockLevelHtmlElts = html.blockLevelElts;
exports.inlineHtmlElts = html.inlineElts;
exports.EATSPACE = punctuation.EATSPACE;
function egg(input) {
    let res = input;
    const x = '\x41\x64\x64\x76\x65\x6E\x74\x61';
    const regex = new RegExp(x, 'g');
    res = res.replace(regex, x + ' 👍');
    return res;
}
function filter(input, languageCommon, filterParams) {
    const languageFilter = (0, languageFilterHelper_1.languageFilterFromLanguageCommon)(languageCommon);
    let res = input;
    // PROTECT HTML SEQ
    res = html.protectHtmlEscapeSeq(res);
    // PROTECT HTML TAGS
    const replacedHtml = html.replaceHtml(res);
    res = replacedHtml.replaced;
    // ADD START to avoid the problem of the ^ in regexp
    res = 'START. ' + res;
    // must be done after protecting html tags
    res = languageFilter.protectRawNumbers(res);
    // transform <protect>...</protect> into §...§
    // must be done before 'beforeProtect', as 'beforeProtect' relies on § knowledge
    res = (0, protectTag_1.processProtectHtmlTags)(res);
    res = languageFilter.beforeProtect(res);
    // PROTECT § BLOCKS
    const protectedMappings = protect.protectBlocks(res);
    res = protectedMappings.protectedString;
    res = clean.joinLines(res);
    // do it early so that all the rest does not have to care for ¤
    res = clean.specialSpacesToNormalSpaces(res);
    res = punctuation.duplicatePunctuation(res, languageFilter);
    res = languageFilter.contractions(res);
    res = clean.cleanStruct(res, languageFilter.constants);
    res = punctuation.parenthesis(res, languageFilter);
    // must be before cleanSpacesPunctuation as it can introduce double spaces
    res = punctuation.quotes(res);
    res = punctuation.cleanSpacesPunctuation(res, languageFilter);
    // must be before contractions otherwise difficult to find words
    res = punctuation.addCaps(res, languageFilter);
    res = egg(res);
    res = (0, titlecase_1.titlecase)(res, languageFilter);
    // must be done at the very end, as there is a recapitalization process
    res = languageFilter.justBeforeUnprotect(res);
    // UNPROTECT § BLOCKS
    res = protect.unprotect(res, protectedMappings.mappings);
    // REMOVE START - has to be before UNPROTECT HTML TAGS
    const regexRemoveStart = /^START([☞\s\.]+)/;
    res = res.replace(regexRemoveStart, (_match, before) => {
        return `${before.replace(/[\s\.]*/g, '')}`;
    });
    // UNPROTECT HTML TAGS
    res = html.replacePlaceholders(res, replacedHtml.elts);
    if (filterParams.renderDebug) {
        res = html.changeRenderDebug(res);
    }
    res = clean.cleanStructAfterUnprotect(res);
    // UNPROTECT HTML SEQ
    res = html.unProtectHtmlEscapeSeq(res);
    // REMOVE spaces at the beginning and at the end
    res = res.trim();
    return res;
}
exports.filter = filter;
//# sourceMappingURL=index.js.map