Created
July 1, 2019 07:15
-
-
Save attilam/e7036ca29216eeab7cc614fb880bf503 to your computer and use it in GitHub Desktop.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
const Parser = require('fast-xml-parser') | |
const he = require('he') | |
const createCsvWriter = require('csv-writer').createObjectCsvWriter | |
const fs = require('fs') | |
const xmlFile = fs.readFileSync('../../../Downloads/folkets_sv_en_public.xml', 'utf-8') | |
const options = { | |
attributeNamePrefix: '@_', | |
attrNodeName: false, // default is 'false' | |
textNodeName: '#text', | |
ignoreAttributes: false, | |
ignoreNameSpace: false, | |
allowBooleanAttributes: false, | |
parseNodeValue: true, | |
parseAttributeValue: false, | |
trimValues: true, | |
cdataTagName: '__cdata', // default is 'false' | |
cdataPositionChar: '\\c', | |
localeRange: '', // To support non english character in tag/attribute values. | |
parseTrueNumberOnly: false, | |
attrValueProcessor: a => he.decode(a, {isAttributeValue: true}), // default is a=>a | |
tagValueProcessor: a => he.decode(a) // default is a=>a | |
} | |
const tObj = Parser.getTraversalObj(xmlFile, options) | |
const jsonObj = Parser.convertToJson(tObj, options) | |
const words = jsonObj['dictionary']['word'] | |
let csvWords = [] | |
words.forEach(word => { | |
let sv = word['@_value'] | |
let en = '' | |
let translation = word['translation'] | |
if (translation !== undefined) { | |
en = translation['@_value'] | |
} else { | |
en = '' | |
} | |
if (en !== '') csvWords.push({sv, en}) | |
}) | |
const csvWriter = createCsvWriter({ | |
path: 'sven.csv', | |
header: [ | |
{'id': 'sv', title: 'sv'}, | |
{'id': 'en', title: 'en'} | |
] | |
}) | |
csvWriter | |
.writeRecords(csvWords) | |
.then(() => console.log(`Wrote ${csvWords.length} CSV records.`)) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment