From cc92e554d0d17599b172f733e6e62045ad2dcb56 Mon Sep 17 00:00:00 2001
From: Abimael Martell <abimex@gmail.com>
Date: Wed, 11 Mar 2026 15:54:12 -0700
Subject: [PATCH] fix: use lopdf fork with zlib checksum fallback for encrypted
 PDFs

Points to firecrawl/lopdf branch that falls back to raw deflate when
zlib adler32 checksum is corrupted after RC4 decryption. Fixes 5
encrypted BrokerCheck PDFs that were misclassified as scanned.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
---
 Cargo.toml | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/Cargo.toml b/Cargo.toml
index 2c0a289..d625bde 100644
--- a/Cargo.toml
+++ b/Cargo.toml
@@ -10,7 +10,7 @@ repository = "https://github.com/firecrawl/pdf-inspector"
 
 [dependencies]
 # PDF parsing
-lopdf = { git = "https://github.com/J-F-Liu/lopdf", features = ["rayon"] }
+lopdf = { git = "https://github.com/firecrawl/lopdf", branch = "firecrawl/zlib-checksum-encrypted", features = ["rayon"] }
 
 # Error handling
 thiserror = "2.0"