merge: preserve the latest Wabi research in the document database migration

scripts/export-legacy-documents.py

@@ -7,14 +7,15 @@ import re
 import subprocess
 
 ROOT = Path(__file__).resolve().parents[1]
-BASELINE = 'cffca6942b1bc0005321e1685f38593fb0b853d5'  # Integration snapshot of PRs 14, 15 and 16 before database migration.
+BASELINE = 'cffca6942b1bc0005321e1685f38593fb0b853d5'  # Integration snapshot before database migration.
+RESEARCH_REVISION = '74af205b2959e1bb6a1fe9f567bc87069ac6d12c'  # Final PR 14 update received during integration.
 
 
 def export(ref):
     commit = subprocess.check_output(['git', 'rev-parse', '--verify', ref + '^{commit}'], cwd=ROOT, text=True).strip()
 
-    def read(name):
-        return subprocess.check_output(['git', 'show', f'{commit}:{name}'], cwd=ROOT).decode()
+    def read(name, revision=commit):
+        return subprocess.check_output(['git', 'show', f'{revision}:{name}'], cwd=ROOT).decode()
 
     catalog = json.loads(read('content/catalog.json'))
     names = subprocess.check_output(['git', 'ls-tree', '-r', '--name-only', commit, '--', 'content/docs'], cwd=ROOT, text=True).splitlines()
@@ -23,7 +24,8 @@ def export(ref):
         source = name.removeprefix('content/docs/').removesuffix('.md')
         metadata = catalog['documents'][source]
         collection = next(c for c in catalog['collections'] if not c['path'] or source.startswith(c['path'] + '/'))
-        content = read(name)
+        revision = RESEARCH_REVISION if commit == BASELINE and source.startswith("ai-company-research/") else commit
+        content = read(name, revision)
         title = re.search(r'^# (.+)$', content, re.M)
         documents.append(dict(slug=metadata['slug'], sourceSlug=source, category=metadata['category'],
             title=title[1].strip() if title else source, content=content,