Search inside documents: PDF text, Tesseract OCR for scans (in the image), optional Claude; nightly catch-up

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
This commit is contained in:
rickyandClaude Opus 5.5 committed 2026-11-11 21:09:12 -05:00
1 parent 2953b9a18d
commit 08ba017c7e
14 files changed
+271 -6

No files matched your search

+6
View File
@@ -31,6 +31,12 @@ class Document < ApplicationRecord
def to_s = name
def type_label = TYPES[doc_type]
def expired?(today = Date.current) = expires_on.present? && today > expires_on
# The page files the search text was read from; when they change, it's read again.
def pages_source_key = pages.map(&:blob_id).sort.join(",")
def pages_text_stale? = pages_text_source.to_s != pages_source_key
after_commit(on: %i[create update]) { DocumentTextJob.perform_later(id) if pages.attached? && pages_text_stale? }
def expiry_warning_days = EXPIRY_WARNING_DAYS.fetch(doc_type, 30)
# nil visibility inherits from the collection; uncollected docs default to private.