From 87a59802bfbe2e79cde951b5b4cfeb6ed7f23b93 Mon Sep 17 00:00:00 2001
From: Alex-Gilbert <alexp.gilbert@pm.me>
Date: Fri, 20 Feb 2026 12:34:58 -0600
Subject: [PATCH] feat: add ocr_lines field to page_data structure

Add an ocr_lines slot (initially None) to each page's data dictionary
in the upload endpoint. This prepares for OCR caching so results can
be reused between the auto-detect and spot-redaction pipelines.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
---
 unredact/app.py | 1 +
 1 file changed, 1 insertion(+)

diff --git a/unredact/app.py b/unredact/app.py
index 3196adb..7e499e8 100644
--- a/unredact/app.py
+++ b/unredact/app.py
@@ -93,6 +93,7 @@ async def upload_pdf(file: UploadFile):
         page_data[i] = {
             "original": page_img,
             "analysis": None,
+            "ocr_lines": None,
         }
 
     _docs[doc_id] = {