Initial Bible data repository

2026-07-11 21:36:31 -05:00
commit a7cbe14eae
14 changed files with 380611 additions and 0 deletions
@@ -0,0 +1,71 @@
+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(/\\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()
+}