format tables code

src/bin/debug_order.rs

@@ -2,29 +2,45 @@ use pdf_inspector::extract_text_with_positions;
 
 fn main() {
     let items = extract_text_with_positions("samples/tables/doc.pdf").unwrap();
-    
+
     // Find items containing "Description" or section numbers
     println!("Items containing section markers:");
     for item in items.iter().filter(|i| i.page == 1) {
-        if item.text.contains("Description") || 
-           item.text.starts_with("3 ") ||
-           item.text.starts_with("3  ") {
+        if item.text.contains("Description")
+            || item.text.starts_with("3 ")
+            || item.text.starts_with("3  ")
+        {
             println!("  x={:6.1} y={:6.1} \"{}\"", item.x, item.y, item.text);
         }
     }
-    
+
     // Look at the Y range for right column
-    let right_col: Vec<_> = items.iter()
+    let right_col: Vec<_> = items
+        .iter()
         .filter(|i| i.page == 1 && i.x > 300.0 && i.x < 400.0)
         .collect();
-    
+
     let y_min = right_col.iter().map(|i| i.y).fold(f32::INFINITY, f32::min);
-    let y_max = right_col.iter().map(|i| i.y).fold(f32::NEG_INFINITY, f32::max);
-    println!("\nRight column (x=300-400) Y range: {:.1} to {:.1}", y_min, y_max);
-    
+    let y_max = right_col
+        .iter()
+        .map(|i| i.y)
+        .fold(f32::NEG_INFINITY, f32::max);
+    println!(
+        "\nRight column (x=300-400) Y range: {:.1} to {:.1}",
+        y_min, y_max
+    );
+
     // Show items near Y=675 (where "3 Description" appears)
     println!("\nItems near Y=675 (±10):");
-    for item in items.iter().filter(|i| i.page == 1 && (i.y - 675.0).abs() < 10.0) {
-        println!("  x={:6.1} y={:6.1} \"{}\"", item.x, item.y, &item.text[..item.text.len().min(50)]);
+    for item in items
+        .iter()
+        .filter(|i| i.page == 1 && (i.y - 675.0).abs() < 10.0)
+    {
+        println!(
+            "  x={:6.1} y={:6.1} \"{}\"",
+            item.x,
+            item.y,
+            &item.text[..item.text.len().min(50)]
+        );
     }
 }

src/markdown.rs

@@ -111,7 +111,9 @@ pub fn to_markdown_from_items(items: Vec<TextItem>, options: MarkdownOptions) ->
 
     // Calculate base font size for table detection
     let font_stats = calculate_font_stats_from_items(&items);
-    let base_size = options.base_font_size.unwrap_or(font_stats.most_common_size);
+    let base_size = options
+        .base_font_size
+        .unwrap_or(font_stats.most_common_size);
 
     // Detect tables on each page
     let mut table_items: HashSet<usize> = HashSet::new();
@@ -124,11 +126,7 @@ pub fn to_markdown_from_items(items: Vec<TextItem>, options: MarkdownOptions) ->
     pages.dedup();
 
     for page in pages {
-        let page_items: Vec<TextItem> = items
-            .iter()
-            .filter(|i| i.page == page)
-            .cloned()
-            .collect();
+        let page_items: Vec<TextItem> = items.iter().filter(|i| i.page == page).cloned().collect();
 
         let tables = detect_tables(&page_items, base_size);
 

src/tables.rs

@@ -159,9 +159,7 @@ fn check_column_alignment(items: &[(usize, &TextItem)], columns: &[f32]) -> f32
     let tolerance = 40.0;
     let aligned = items
         .iter()
-        .filter(|(_, item)| {
-            columns.iter().any(|&col| (item.x - col).abs() < tolerance)
-        })
+        .filter(|(_, item)| columns.iter().any(|&col| (item.x - col).abs() < tolerance))
         .count();
 
     aligned as f32 / items.len() as f32