-
-
Notifications
You must be signed in to change notification settings - Fork 193
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
chore: experiment with loripsum.net (#3169)
- Loading branch information
Showing
5 changed files
with
6,871 additions
and
2 deletions.
There are no files selected for viewing
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
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,21 @@ | ||
# Words from https://loripsum.net/ | ||
|
||
<!--- cspell:locale en, la ---> | ||
|
||
This is an experiment to see how many words https://loripsum.net/ has in its dictionary. | ||
|
||
It downloads samples and puts them into a word frequency table. [./words.txt](./words.txt). | ||
|
||
Sample: | ||
|
||
```csv | ||
*,5116693 | ||
a,30492 | ||
ab,16790 | ||
abducam,6 | ||
abducas,144 | ||
abducat,87 | ||
abducere,155 | ||
``` | ||
|
||
Where `*` is the total word count. |
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
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,6 @@ | ||
import: | ||
- ../cspell-ext.json | ||
- ../../la/cspell-ext.json | ||
language: lorem, la, en | ||
ignorePaths: | ||
- words.txt |
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
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,93 @@ | ||
import fs from 'node:fs'; | ||
|
||
async function run() { | ||
for (let i = 0; i < 1000; i++) { | ||
await process(); | ||
await waitFor(250); | ||
} | ||
} | ||
|
||
async function process() { | ||
const knownWords = readWordFreq('./words.txt'); | ||
const numWords = Math.max(knownWords.size - 1, 0); | ||
const wordCount = knownWords.get('*') || 0; | ||
|
||
console.log('Known words:', numWords); | ||
console.log('Total words:', wordCount); | ||
|
||
const sourceWords = await fetchWords(); | ||
addWordsToFreqMap(knownWords, sourceWords); | ||
|
||
console.log('New words:', knownWords.size - numWords - 1); | ||
console.log('Added words:', knownWords.get('*') - wordCount); | ||
|
||
writeWordFreq('./words.txt', knownWords); | ||
} | ||
|
||
function readFile(path) { | ||
try { | ||
return fs.readFileSync(path, 'utf8'); | ||
} catch { | ||
return undefined; | ||
} | ||
} | ||
|
||
/** | ||
* | ||
* @param {string} text | ||
* @returns {string[]} | ||
*/ | ||
function textToWords(text) { | ||
const words = text | ||
.replaceAll(/[^a-zA-Z]/g, ' ') | ||
.toLowerCase() | ||
.split(' ') | ||
.filter((a) => a); | ||
return words; | ||
} | ||
|
||
async function fetchWords() { | ||
const response = await fetch('https://loripsum.net/api/20/verylong/plaintext'); | ||
const text = await response.text(); | ||
return textToWords(text); | ||
} | ||
|
||
/** | ||
* | ||
* @param {string} path | ||
* @returns {Map<string, number>} | ||
*/ | ||
function readWordFreq(path) { | ||
const text = readFile(path) || ''; | ||
const freq = new Map(); | ||
text.split('\n').forEach((line) => { | ||
if (!line.trim()) return; | ||
const [word, count] = line.split(','); | ||
freq.set(word, Number(count)); | ||
}); | ||
return freq; | ||
} | ||
|
||
function writeWordFreq(path, freqMap) { | ||
const lines = [...freqMap.entries()].map(([word, count]) => `${word},${count}`); | ||
fs.writeFileSync(path, lines.sort().join('\n')); | ||
} | ||
|
||
function waitFor(ms) { | ||
return new Promise((resolve) => setTimeout(resolve, ms)); | ||
} | ||
|
||
function addWordsToFreqMap(map, words) { | ||
for (const word of words) { | ||
addWordToFreqMap(map, word); | ||
} | ||
} | ||
|
||
function addWordToFreqMap(map, key, n = 1) { | ||
const v = map.get(key) || 0; | ||
map.set(key, v + n); | ||
const t = map.get('*') || 0; | ||
map.set('*', t + n); | ||
} | ||
|
||
run(); |
Oops, something went wrong.