From ff29d6109da177b9f81921f85afffa76fc1b467a Mon Sep 17 00:00:00 2001
From: Ellie <6687206+wizzeh@users.noreply.github.com>
Date: Wed, 25 Feb 2026 13:25:50 -0800
Subject: [PATCH] feat: try pdftotext before marker-pdf for conversion

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
---
 src/main.rs | 50 +++++++++++++++++++++++++++++++++++++++++++++++++-
 1 file changed, 49 insertions(+), 1 deletion(-)

diff --git a/src/main.rs b/src/main.rs
index baab9fc..bd75521 100644
--- a/src/main.rs
+++ b/src/main.rs
@@ -304,16 +304,64 @@ fn pdftotext_output_is_good(text: &str) -> bool {
     ratio > 0.8
 }
 
+/// Try extracting text from a PDF using pdftotext.
+/// Returns Some(text) if pdftotext succeeds and the output looks good,
+/// None otherwise.
+fn try_pdftotext(pdf_bytes: &[u8]) -> Option<String> {
+    let tmp_dir = tempfile::tempdir().ok()?;
+    let pdf_path = tmp_dir.path().join("paper.pdf");
+    std::fs::write(&pdf_path, pdf_bytes).ok()?;
+
+    eprintln!("Trying pdftotext…");
+
+    let output = Command::new("pdftotext")
+        .arg("-layout")
+        .arg(&pdf_path)
+        .arg("-")
+        .output();
+
+    match output {
+        Err(e) if e.kind() == io::ErrorKind::NotFound => {
+            eprintln!("pdftotext not found on PATH, skipping simple extraction");
+            None
+        }
+        Err(e) => {
+            eprintln!("pdftotext failed: {e}");
+            None
+        }
+        Ok(o) if !o.status.success() => {
+            eprintln!("pdftotext exited with {}", o.status);
+            None
+        }
+        Ok(o) => {
+            let text = String::from_utf8_lossy(&o.stdout).into_owned();
+            if pdftotext_output_is_good(&text) {
+                eprintln!("pdftotext output looks good, skipping marker");
+                Some(text)
+            } else {
+                eprintln!("pdftotext output is low quality, falling back to marker");
+                None
+            }
+        }
+    }
+}
+
 /// Write PDF bytes to a temp file, run marker_single, and return the
 /// resulting markdown.
 fn convert_to_markdown(pdf_bytes: &[u8]) -> anyhow::Result<String> {
+    // Try simple extraction first.
+    if let Some(text) = try_pdftotext(pdf_bytes) {
+        return Ok(text);
+    }
+
+    // Fall back to marker-pdf.
     let tmp_dir = tempfile::tempdir().context("failed to create temp directory")?;
     let pdf_path = tmp_dir.path().join("paper.pdf");
     let out_dir = tmp_dir.path().join("output");
 
     std::fs::write(&pdf_path, pdf_bytes).context("failed to write temp PDF")?;
 
-    eprintln!("Converting PDF to markdown…");
+    eprintln!("Converting PDF to markdown with marker…");
 
     let status = Command::new("marker_single")
         .arg(&pdf_path)