fix(columns): Skip table detection on wide multi-column text pages

Multi-column text layouts (e.g., creditor matrices with 3 address columns)
were incorrectly claimed by body-font table detection. Now runs column
detection before table detection and skips tables on pages where all
detected columns are wider than 150pt, letting group_into_lines handle
the column-by-column reading order correctly.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

src/extractor.rs

@@ -2109,9 +2109,9 @@ fn effective_width(item: &TextItem) -> f32 {
 
 /// Represents a column region on a page
 #[derive(Debug, Clone)]
-struct ColumnRegion {
+pub(crate) struct ColumnRegion {
-    x_min: f32,
+    pub(crate) x_min: f32,
-    x_max: f32,
+    pub(crate) x_max: f32,
 }
 
 /// Detect column boundaries on a page using a horizontal projection profile.
@@ -2119,7 +2119,7 @@ struct ColumnRegion {
 /// Builds an occupancy histogram across the page width and finds empty valleys
 /// (gutters) where no text exists. Validates valleys with vertical consistency
 /// checks to avoid false positives.
-fn detect_columns(items: &[TextItem], page: u32) -> Vec<ColumnRegion> {
+pub(crate) fn detect_columns(items: &[TextItem], page: u32) -> Vec<ColumnRegion> {
     const BIN_WIDTH: f32 = 2.0;
     const MIN_GUTTER_WIDTH: f32 = 8.0;
     const MIN_VERTICAL_SPAN_RATIO: f32 = 0.30;

src/markdown.rs

@@ -190,6 +190,22 @@ pub fn to_markdown_from_items(items: Vec<TextItem>, options: MarkdownOptions) ->
         let group = page_groups.get(&page).unwrap();
         let page_items: Vec<TextItem> = group.iter().map(|(_, item)| (*item).clone()).collect();
 
+        // Skip table detection on pages with clear multi-column text layout.
+        // Column detection in group_into_lines handles these correctly, and
+        // table detection would incorrectly claim columnar text as table rows.
+        // Only skip when all detected columns are wide (>150pt ~ 2 inches),
+        // indicating true text columns rather than narrow table columns.
+        let columns = crate::extractor::detect_columns(&page_items, page);
+        if columns.len() >= 2 {
+            let min_col_width = columns
+                .iter()
+                .map(|c| c.x_max - c.x_min)
+                .fold(f32::INFINITY, f32::min);
+            if min_col_width > 150.0 {
+                continue;
+            }
+        }
+
         let tables = detect_tables(&page_items, base_size);
 
         for table in tables {