diff --git a/napi/Cargo.lock b/napi/Cargo.lock
index 8a11ccd..8aa8837 100644
--- a/napi/Cargo.lock
+++ b/napi/Cargo.lock
@@ -129,12 +129,6 @@ version = "3.20.2"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "5d20789868f4b01b2f2caec9f5c4e0213b41e3e5702a50157d699ae31ced2fcb"
 
-[[package]]
-name = "bytecount"
-version = "0.6.9"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "175812e0be2bccb6abe50bb8d566126198344f707e304f45c648fd8f2cc0365e"
-
 [[package]]
 name = "cbc"
 version = "0.1.2"
@@ -679,7 +673,7 @@ checksum = "5e5032e24019045c762d3c0f28f5b6b8bbf38563a65908389bf7978758920897"
 [[package]]
 name = "lopdf"
 version = "0.40.0"
-source = "git+https://github.com/J-F-Liu/lopdf?rev=052674053814a9f4897af94f0b8e46a545c9b329#052674053814a9f4897af94f0b8e46a545c9b329"
+source = "git+https://github.com/J-F-Liu/lopdf?rev=7a05512d831415b1f2b1ce522391d6beab8a1284#7a05512d831415b1f2b1ce522391d6beab8a1284"
 dependencies = [
  "aes",
  "bitflags",
@@ -695,7 +689,6 @@ dependencies = [
  "log",
  "md-5",
  "nom",
- "nom_locate",
  "rand",
  "rangemap",
  "rayon",
@@ -807,17 +800,6 @@ dependencies = [
  "memchr",
 ]
 
-[[package]]
-name = "nom_locate"
-version = "5.0.0"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "0b577e2d69827c4740cba2b52efaad1c4cc7c73042860b199710b3575c68438d"
-dependencies = [
- "bytecount",
- "memchr",
- "nom",
-]
-
 [[package]]
 name = "num-conv"
 version = "0.2.1"
diff --git a/napi/package.json b/napi/package.json
index 52bd043..5bbc4df 100644
--- a/napi/package.json
+++ b/napi/package.json
@@ -1,6 +1,6 @@
 {
   "name": "firecrawl-pdf-inspector",
-  "version": "0.3.3",
+  "version": "0.3.4",
   "description": "Fast PDF classification and text extraction. Detect text-based vs scanned PDFs, extract text by region with quality checks. Native Rust performance via napi-rs.",
   "main": "index.js",
   "types": "index.d.ts",
diff --git a/src/lib.rs b/src/lib.rs
index 588e492..194e0f6 100644
--- a/src/lib.rs
+++ b/src/lib.rs
@@ -525,9 +525,6 @@ fn collect_text_in_region_with_options(
     adaptive_threshold: f32,
 ) -> String {
     let bounds = region_bounds(rx1, ry1, rx2, ry2, page_height, coord_space);
-    let Some(page) = items.first().map(|item| item.page) else {
-        return String::new();
-    };
     let matched: Vec<TextItem> = items
         .iter()
         .filter(|item| region_overlaps_item(item, bounds))
@@ -536,11 +533,39 @@ fn collect_text_in_region_with_options(
     if matched.is_empty() {
         return String::new();
     }
-    let mut thresholds = HashMap::new();
-    if adaptive_threshold > 0.10 {
-        thresholds.insert(page, adaptive_threshold);
+
+    // Simple extraction: the caller (fire-pdf) already handles reading order
+    // and column splitting via the layout model. We just need to sort items
+    // top-to-bottom, left-to-right and group into lines.
+    let mut sorted = matched;
+    sorted.sort_by(|a, b| b.y.total_cmp(&a.y).then(a.x.total_cmp(&b.x)));
+
+    let y_tolerance = 3.0;
+    let mut lines: Vec<extractor::TextLine> = Vec::new();
+
+    for item in sorted {
+        let should_merge = lines.last().is_some_and(|last_line: &extractor::TextLine| {
+            last_line.page == item.page && (last_line.y - item.y).abs() < y_tolerance
+        });
+        if should_merge {
+            lines.last_mut().unwrap().items.push(item);
+        } else {
+            let y = item.y;
+            let page = item.page;
+            lines.push(extractor::TextLine {
+                items: vec![item],
+                y,
+                page,
+                adaptive_threshold,
+            });
+        }
     }
-    let lines = extractor::group_into_lines_with_thresholds(matched, &thresholds, &HashSet::new());
+
+    // Sort items within each line by X position
+    for line in &mut lines {
+        text_utils::sort_line_items(&mut line.items);
+    }
+
     lines
         .into_iter()
         .map(|line| line.text())