Created
July 17, 2022 15:48
-
-
Save euberdeveloper/a423bc5498123dcd608e75d819b7cc40 to your computer and use it in GitHub Desktop.
A script that shows the ranking of the chinese characters, based on their sound without considering the tones
This file contains 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 https = require('https'); | |
const fs = require('fs'); | |
function analyzeInputData(charactersText) { | |
const ranking = charactersText.split('\n').map(line => line.trim()).filter(line => !!line).map(line => JSON.parse(line)).map(line => { | |
if (line.frequency_rank === '8220') { | |
line.pinyin = 'y\u01cen'; | |
} | |
else if (line.frequency_rank === '9019') { | |
line.pinyin = 'ni\u00e1n'; | |
} | |
return line; | |
}) | |
.map(obj => ({ | |
frequencyRank: obj.frequency_rank, | |
character: obj.charcter, | |
pinyinWithTones: obj.pinyin, | |
pinyin: obj.pinyin | |
.replace('\u0101', 'a') | |
.replace('\u00e1', 'a') | |
.replace('\u01ce', 'a') | |
.replace('\u00e0', 'a') | |
.replace('\u0113', 'e') | |
.replace('\u00e9', 'e') | |
.replace('\u011b', 'e') | |
.replace('\u00e8', 'e') | |
.replace('\u012b', 'i') | |
.replace('\u00ec', 'i') | |
.replace('\u00ed', 'i') | |
.replace('\u01d0', 'i') | |
.replace('\u014d', 'o') | |
.replace('\u00f3', 'o') | |
.replace('\u01d2', 'o') | |
.replace('\u00f2', 'o') | |
.replace('\u016b', 'u') | |
.replace('\u00fa', 'u') | |
.replace('\u01d4', 'u') | |
.replace('\u00f9', 'u') | |
.replace('\u00fc', 'ü') | |
.replace('\u01d6', 'ü') | |
.replace('\u01d8', 'ü') | |
.replace('\u01da', 'ü') | |
.replace('\u01dc', 'ü') | |
})) | |
.reduce((acc, curr) => { | |
if (acc[curr.pinyin]) { | |
if (!acc[curr.pinyin].find(c => c.character === curr.character)) { | |
acc[curr.pinyin].push(curr); | |
} | |
} else { | |
acc[curr.pinyin] = [curr]; | |
} | |
return acc; | |
}, {}); | |
const result = Object.keys(ranking).sort((x, y) => ranking[y].length - ranking[x].length).map(key => ({ | |
pinyin: key, | |
length: ranking[key].length, | |
characters: ranking[key] | |
})); | |
fs.writeFileSync('ranking.json', JSON.stringify(result, null, 3)); | |
} | |
function requestDataAndExecute(cb) { | |
const options = { | |
hostname: 'raw.githubusercontent.com', | |
port: 443, | |
path: '/ruddfawcett/hanziDB.csv/master/data/hanziDB.json', | |
method: 'GET', | |
}; | |
const req = https.request(options, res => { | |
const chunks = []; | |
res.on('data', data => { | |
chunks.push(data); | |
}); | |
res.on('close', d => { | |
cb(Buffer.concat(chunks).toString()); | |
}); | |
}); | |
req.on('error', error => { | |
console.error(error); | |
}); | |
req.end(); | |
} | |
function main() { | |
requestDataAndExecute(analyzeInputData); | |
} | |
main(); | |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment