Add episode transcripts, expand chatbot Q&A database to 28 entries, and build scripts

2026-04-13 10:29:06 -04:00
parent 6e8b360398
commit 063f5d2a0e
31 changed files with 2779 additions and 134 deletions
@@ -0,0 +1,92 @@
+import { execSync } from 'child_process'
+import { readFileSync, writeFileSync } from 'fs'
+import { randomUUID } from 'crypto'
+
+const BASE = "/Users/nate.emmert/Documents/github/Siteforge/Verse by Verse with Nate Complete Series"
+const CHATBOT_FILE = "/Users/nate.emmert/Documents/github/Siteforge/data/chatbot-content.json"
+
+const FILES = [
+  { file: `${BASE}/Done/Verse_by_Verse_with_Nate_Episode02.docx`, ep: 2 },
+  { file: `${BASE}/Done/Verse_by_Verse_with_Nate_Episode03.docx`, ep: 3 },
+  { file: `${BASE}/Done/Verse_by_Verse_with_Nate_Episode04_Updated.docx`, ep: 4 },
+  { file: `${BASE}/Verse_by_Verse_with_Nate_Episode05.docx`, ep: 5 },
+  { file: `${BASE}/Verse_by_Verse_with_Nate_Episode06_expanded.docx`, ep: 6 },
+  { file: `${BASE}/Verse_by_Verse_with_Nate_Episode07.docx`, ep: 7 },
+  { file: `${BASE}/Verse_by_Verse_with_Nate_Episode08.docx`, ep: 8 },
+  { file: `${BASE}/Verse_by_Verse_with_Nate_Episode09.docx`, ep: 9 },
+  { file: `${BASE}/Verse_by_Verse_with_Nate_Episode10.docx`, ep: 10 },
+  { file: `${BASE}/Verse_by_Verse_with_Nate_Episode11.docx`, ep: 11 },
+  { file: `${BASE}/Verse_by_Verse_with_Nate_Episode12.docx`, ep: 12 },
+  { file: `${BASE}/Verse_by_Verse_with_Nate_Episode13.docx`, ep: 13 },
+  { file: `${BASE}/Verse_by_Verse_with_Nate_Episode14.docx`, ep: 14 },
+]
+
+function extractText(filePath) {
+  const xml = execSync(`unzip -p "${filePath}" word/document.xml 2>/dev/null`, { encoding: 'utf8' })
+  return xml
+    .replace(/<[^>]+>/g, ' ')
+    .replace(/&amp;/g, '&').replace(/&lt;/g, '<').replace(/&gt;/g, '>').replace(/&quot;/g, '"').replace(/&#39;/g, "'")
+    .replace(/\s+/g, ' ')
+    .trim()
+}
+
+function parseEpisode(raw, epNum) {
+  // Extract episode subtitle and passage reference from header
+  const headerMatch = raw.match(/EPISODE\s+\d+\s*[—\-\u2013\u2014]+\s*(.+?)\s+(Titus\s+[\d:]+(?:\s*[\-\u2013\u2014]+\s*[\d:]+)?)\s*·/i)
+  const subtitle = headerMatch ? headerMatch[1].trim().replace(/\s+/g, ' ') : ''
+  const passageRef = headerMatch ? headerMatch[2].trim() : 'Titus'
+  const episodeTitle = `Episode ${epNum} — ${subtitle || 'Verse by Verse with Nate'}`
+
+  // Find where the actual teaching content starts
+  let contentStart = raw.indexOf('SEGMENT 1')
+  if (contentStart === -1) contentStart = raw.indexOf('WHO WAS PAUL')
+  if (contentStart === -1) contentStart = raw.indexOf('COLD OPEN')
+  if (contentStart === -1) contentStart = 400
+
+  const rawContent = raw.slice(contentStart, contentStart + 4000)
+  const content = rawContent
+    .replace(/\[[^\]]{0,100}\]/g, '')                    // remove [stage directions]
+    .replace(/[✝🎙️📖💬🧠💡🔑✅◀▶]/gu, '')              // remove emoji
+    .replace(/SEGMENT\s+\d+\s*[—\-\u2013]+\s*/g, '\n\n') // turn SEGMENT headers into breaks
+    .replace(/\s{2,}/g, ' ')
+    .trim()
+
+  // Build keyword list
+  const verseRefs = [...new Set((raw.match(/Titus\s+\d+:\d+/g) || []))].slice(0, 5).map(k => k.toLowerCase())
+  const titleWords = subtitle.toLowerCase().replace(/[^a-z0-9\s]/g, ' ').split(/\s+/).filter(w => w.length > 3)
+  const keywords = [...new Set([
+    'titus', `episode ${epNum}`, passageRef.toLowerCase(),
+    ...verseRefs, ...titleWords
+  ])].slice(0, 20)
+
+  return {
+    id: randomUUID(),
+    type: 'episode',
+    title: `${episodeTitle} (${passageRef})`,
+    content: content.slice(0, 3900),
+    keywords,
+    createdAt: new Date().toISOString(),
+    updatedAt: new Date().toISOString(),
+  }
+}
+
+// Load existing entries (keep the 8 hand-written ones)
+const existing = JSON.parse(readFileSync(CHATBOT_FILE, 'utf8'))
+// Remove any previously generated episode entries to avoid duplication
+const baseEntries = existing.filter(e => e.type !== 'episode')
+
+const newEntries = []
+for (const { file, ep } of FILES) {
+  try {
+    const raw = extractText(file)
+    const entry = parseEpisode(raw, ep)
+    newEntries.push(entry)
+    console.log(`✓ Ep ${ep}: ${entry.title.slice(0, 80)}`)
+  } catch (err) {
+    console.error(`✗ Ep ${ep}: ${err.message}`)
+  }
+}
+
+const combined = [...baseEntries, ...newEntries]
+writeFileSync(CHATBOT_FILE, JSON.stringify(combined, null, 2), 'utf8')
+console.log(`\nDone. ${newEntries.length} episode entries added. Total: ${combined.length}`)