Files
libre-bible-data/scripts/lib.js
T
2026-07-15 20:12:22 -05:00

88 lines
2.4 KiB
JavaScript
Raw Blame History

This file contains ambiguous Unicode characters
This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.
import { createHash } from 'node:crypto'
import { createWriteStream } from 'node:fs'
import { mkdir, readFile, stat, writeFile } from 'node:fs/promises'
import path from 'node:path'
export async function readJson(filePath) {
return JSON.parse(await readFile(filePath, 'utf8'))
}
export async function writeJson(filePath, value) {
await mkdir(path.dirname(filePath), { recursive: true })
await writeFile(filePath, `${JSON.stringify(value, null, 2)}\n`, 'utf8')
}
export async function exists(filePath) {
try {
await stat(filePath)
return true
} catch {
return false
}
}
export async function downloadFile(url, filePath) {
await mkdir(path.dirname(filePath), { recursive: true })
const response = await fetch(url)
if (!response.ok || !response.body) {
throw new Error(`Download failed ${response.status} ${response.statusText}: ${url}`)
}
const output = createWriteStream(filePath)
await new Promise((resolve, reject) => {
response.body.pipeTo(
new WritableStream({
write(chunk) {
output.write(Buffer.from(chunk))
},
close() {
output.end(resolve)
},
abort(reason) {
output.destroy(reason)
reject(reason)
},
}),
).catch(reject)
})
}
export async function sha256File(filePath) {
const data = await readFile(filePath)
return createHash('sha256').update(data).digest('hex')
}
export function normalizeStrong(value) {
const match = /^([GH])0*([0-9]+)$/i.exec(value)
return match ? `${match[1].toUpperCase()}${Number(match[2])}` : value.toUpperCase()
}
export function cleanUsfmText(input) {
return input
.replace(/…/g, '...')
.replace(/…/g, '...')
.replace(/’/g, "'")
.replace(/’/g, "'")
.replace(//g, "'")
.replace(//g, "'")
.replace(/“/g, '"')
.replace(/”/g, '"')
.replace(/“/g, '"')
.replace(/”/g, '"')
.replace(/“/g, '"')
.replace(/”/g, '"')
.replace(/—/g, '-')
.replace(/–/g, '-')
.replace(/—/g, '-')
.replace(//g, '-')
.replace(/\\f [\s\S]*?\\f\*/g, '')
.replace(/\\x [\s\S]*?\\x\*/g, '')
.replace(/\\add\s+([^\\]+)\\add\*/g, '$1')
.replace(/\\nd\s+([\s\S]*?)\\nd\*/g, '$1')
.replace(/\\[+\w]+\*/g, '')
.replace(/\\[a-z0-9+]+(?:\s+)?/gi, '')
.replace(/\s+/g, ' ')
.replace(/\s+([,.;:?!])/g, '$1')
.trim()
}