chore: bump version from 1.3.0 to 1.4.0

Minor bump for the new per-page markdown extraction API exposed through
the Python and Node bindings.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

src/extractor/layout.rs

@@ -626,33 +626,6 @@ fn find_relative_valleys(
     valleys
 }
 
-/// Detect whether a side of a gutter consists predominantly of list-marker
-/// glyphs (•, ●, ○, ◦, ▪, ▫, ◆, ◇). A column of bullets on the left margin
-/// creates a spurious histogram valley between the bullet and the content.
-/// Treating it as a real column splits each list item's text across two
-/// "columns," so we reject these candidates.
-fn is_list_marker_column(items: &[&&TextItem]) -> bool {
-    const LIST_MARKERS: &[char] = &['•', '●', '○', '◦', '▪', '▫', '◆', '◇', '■', '□'];
-    if items.is_empty() {
-        return false;
-    }
-    let marker_count = items
-        .iter()
-        .filter(|i| {
-            let t = i.text.trim();
-            let mut chars = t.chars();
-            match (chars.next(), chars.next()) {
-                (Some(c), None) => LIST_MARKERS.contains(&c),
-                _ => false,
-            }
-        })
-        .count();
-    // Require ≥80% of items on this side to be standalone markers. A handful
-    // of non-marker items (stray page numbers, footnote refs) shouldn't
-    // defeat the check.
-    marker_count as f32 / items.len() as f32 >= 0.8
-}
-
 /// Validate valley candidates with vertical consistency checks and build column regions.
 ///
 /// When `center_assign` is true, items are assigned to columns based on their
@@ -721,19 +694,6 @@ fn validate_and_build_columns(
             continue;
         }
 
-        // Reject valleys where the smaller side is just a column of list
-        // markers (bullets aligned at the left margin). This is a common
-        // pattern in PDFs where ● starts each list item: histogram detection
-        // sees the gap between bullet and content as a gutter.
-        let smaller_items: &[&&TextItem] = if left_items.len() <= right_items.len() {
-            &left_items
-        } else {
-            &right_items
-        };
-        if is_list_marker_column(smaller_items) {
-            continue;
-        }
-
         // Check vertical overlap
         if y_range > 0.0 {
             let left_y_min = left_items.iter().map(|i| i.y).fold(f32::INFINITY, f32::min);
@@ -1820,63 +1780,6 @@ mod tests {
         );
     }
 
-    #[test]
-    fn bullet_marker_column_not_detected_as_column() {
-        // Pattern: every line is `● <content>`, with ● at x=90 and content
-        // starting at x=104. Histogram detection sees a gutter between them
-        // and would split the page into a "bullet column" and "content column",
-        // scrambling every list item.
-        let mut items = Vec::new();
-        for i in 0..15 {
-            let y = 750.0 - i as f32 * 30.0;
-            items.push(make_item(1, 90.0, y, "●"));
-            items.push(make_item(
-                1,
-                104.0,
-                y,
-                "FullContentLineTextHere________________",
-            ));
-        }
-        // Pad with content to satisfy min item count for column detection.
-        for i in 0..15 {
-            let y = 300.0 - i as f32 * 14.0;
-            items.push(make_item(1, 72.0, y, "FootnoteText_____________________"));
-        }
-
-        let cols = detect_columns(&items, 1, false);
-        assert_eq!(
-            cols.len(),
-            1,
-            "Bullet markers aligned at left margin should not be treated as their own column"
-        );
-    }
-
-    #[test]
-    fn is_list_marker_column_detects_bullets() {
-        let items = vec![
-            make_item(1, 90.0, 100.0, "●"),
-            make_item(1, 90.0, 114.0, "●"),
-            make_item(1, 90.0, 128.0, "●"),
-            make_item(1, 90.0, 142.0, "●"),
-        ];
-        let refs: Vec<&TextItem> = items.iter().collect();
-        let wrapped: Vec<&&TextItem> = refs.iter().collect();
-        assert!(is_list_marker_column(&wrapped));
-    }
-
-    #[test]
-    fn is_list_marker_column_rejects_prose() {
-        let items = vec![
-            make_item(1, 30.0, 100.0, "Regular prose line"),
-            make_item(1, 30.0, 114.0, "Another sentence"),
-            make_item(1, 30.0, 128.0, "Third line"),
-            make_item(1, 30.0, 142.0, "Fourth line"),
-        ];
-        let refs: Vec<&TextItem> = items.iter().collect();
-        let wrapped: Vec<&&TextItem> = refs.iter().collect();
-        assert!(!is_list_marker_column(&wrapped));
-    }
-
     #[test]
     fn premask_narrow_line_not_masked() {
         // Items that form a line spanning only ~40% of column width → not masked

src/markdown/classify.rs

@@ -64,22 +64,6 @@ pub(crate) fn is_caption_line(text: &str) -> bool {
     false
 }
 
-/// Check if text starts with an unambiguous bullet marker (●, •, ○, ◦).
-///
-/// Narrower than [`is_list_item`]: it excludes numbered/lettered patterns
-/// like `1.` or `a)`, which legitimately appear as section headings in many
-/// documents. Used by the heading classifier to reject bullet lines without
-/// also demoting numbered headings.
-pub(crate) fn starts_with_bullet_marker(text: &str) -> bool {
-    let trimmed = text.trim_start();
-    trimmed.starts_with("• ")
-        || trimmed.starts_with("● ")
-        || trimmed.starts_with("○ ")
-        || trimmed.starts_with("◦ ")
-        || trimmed.starts_with("- ")
-        || trimmed.starts_with("* ")
-}
-
 /// Check if text looks like a list item
 pub(crate) fn is_list_item(text: &str) -> bool {
     let trimmed = text.trim_start();
@@ -131,16 +115,6 @@ pub(crate) fn format_list_item(text: &str) -> String {
         if let Some(rest) = trimmed.strip_prefix(*bullet) {
             return format!("- {}", rest.trim_start());
         }
-        // Bullet inside a leading bold/italic run (e.g. "**● Label:** rest").
-        // The run wraps both the marker and the following label because both
-        // use a bold font in the PDF.
-        for wrapper in ["**", "*"] {
-            if let Some(after_open) = trimmed.strip_prefix(wrapper) {
-                if let Some(rest) = after_open.strip_prefix(*bullet) {
-                    return format!("- {}{}", wrapper, rest.trim_start());
-                }
-            }
-        }
     }
 
     if trimmed.starts_with("- ") || trimmed.starts_with("* ") {
@@ -224,42 +198,3 @@ pub(crate) fn is_monospace_font(font_name: &str) -> bool {
 
     patterns.iter().any(|p| lower.contains(p))
 }
-
-#[cfg(test)]
-mod tests {
-    use super::*;
-
-    #[test]
-    fn format_list_item_plain_bullet() {
-        assert_eq!(format_list_item("● Item"), "- Item");
-        assert_eq!(format_list_item("• Item"), "- Item");
-    }
-
-    #[test]
-    fn format_list_item_bullet_inside_bold() {
-        // PDF that uses bold font for both the marker and the label produces
-        // a single bold run like "**● Label:** rest"; the bullet must still
-        // be stripped and the bold wrapper preserved on the label.
-        assert_eq!(
-            format_list_item("**● Fraud: Willing cooperation;**"),
-            "- **Fraud: Willing cooperation;**"
-        );
-        assert_eq!(
-            format_list_item("**● Label:** rest of line"),
-            "- **Label:** rest of line"
-        );
-        assert_eq!(format_list_item("*● Italic:* rest"), "- *Italic:* rest");
-    }
-
-    #[test]
-    fn format_list_item_already_dash() {
-        assert_eq!(format_list_item("- existing"), "- existing");
-    }
-
-    #[test]
-    fn is_list_item_with_bullet_space() {
-        assert!(is_list_item("● Item"));
-        assert!(is_list_item("• Item"));
-        assert!(is_list_item("- Item"));
-    }
-}

src/markdown/convert.rs

@@ -9,9 +9,7 @@ use super::analysis::{
     bold_heading_level, calculate_font_stats, compute_heading_tiers, compute_paragraph_threshold,
     detect_header_level, font_size_rarity, has_dot_leaders,
 };
-use super::classify::{
-    format_list_item, is_caption_line, is_list_item, is_monospace_font, starts_with_bullet_marker,
-};
+use super::classify::{format_list_item, is_caption_line, is_list_item, is_monospace_font};
 use super::postprocess::clean_markdown;
 use super::preprocess::{merge_drop_caps, merge_heading_lines};
 use super::MarkdownOptions;
@@ -589,7 +587,6 @@ pub(super) fn to_markdown_from_lines_with_tables_and_images(
         let heuristic_heading = if options.detect_headers
             && plain_trimmed.len() > 3
             && plain_trimmed.split_whitespace().count() <= 15
-            && !starts_with_bullet_marker(plain_trimmed)
         {
             let line_font_size = line.items.first().map(|i| i.font_size).unwrap_or(base_size);
             detect_header_level(line_font_size, base_size, &heading_tiers).or_else(|| {
@@ -644,16 +641,11 @@ pub(super) fn to_markdown_from_lines_with_tables_and_images(
             continue;
         }
 
-        // Structure-tree list item (LI only — LBody is a continuation, not a new item).
-        // Some tagged PDFs use a "flat" style where every wrapped line in a list item
-        // gets its own MCID tagged directly under LI. When we're already inside a list
-        // and the line has no visible bullet marker, treat it as a continuation (falls
-        // through to the continuation logic below) rather than a new list item.
+        // Structure-tree list item (LI only — LBody is a continuation, not a new item)
         if struct_role
             .as_ref()
             .is_some_and(|r| matches!(r, StructRole::LI))
             && !is_list_item(plain_trimmed)
-            && !in_list
         {
             if in_paragraph {
                 output.push_str("\n\n");
@@ -1098,59 +1090,6 @@ mod tests {
         );
     }
 
-    #[test]
-    fn test_struct_role_li_flat_continuation_lines_merge() {
-        // Regression: some tagged PDFs put each wrapped visual line of a list
-        // item under its own MCID, all tagged directly as LI. Continuation
-        // lines (no bullet marker) must merge into the bulleted parent item,
-        // not each become their own list item.
-        let make = |text: &str, mcid: i64, x: f32, y: f32| {
-            let mut item = make_item(text, 1, Some(mcid));
-            item.x = x;
-            item.y = y;
-            item
-        };
-        let lines = vec![
-            make_line(vec![make("● First item that wraps onto", 0, 90.0, 322.0)]),
-            make_line(vec![make("a continuation line.", 1, 108.0, 306.0)]),
-            make_line(vec![make("● Second bullet also wraps", 2, 90.0, 290.0)]),
-            make_line(vec![make("to a second line here.", 3, 108.0, 274.0)]),
-        ];
-
-        let mut page_roles = HashMap::new();
-        for mcid in 0..4 {
-            page_roles.insert(mcid, StructRole::LI);
-        }
-        let mut roles = HashMap::new();
-        roles.insert(1u32, page_roles);
-
-        let md = to_markdown_from_lines_with_tables_and_images(
-            lines,
-            MarkdownOptions::default(),
-            HashMap::new(),
-            HashMap::new(),
-            &std::collections::HashSet::new(),
-            Some(&roles),
-        );
-
-        assert!(
-            md.contains("- First item that wraps onto a continuation line."),
-            "continuation should merge into first bullet: {md}"
-        );
-        assert!(
-            md.contains("- Second bullet also wraps to a second line here."),
-            "continuation should merge into second bullet: {md}"
-        );
-        assert!(
-            !md.contains("- a continuation line."),
-            "continuation line should not get its own bullet: {md}"
-        );
-        assert!(
-            !md.contains("- to a second line here."),
-            "continuation line should not get its own bullet: {md}"
-        );
-    }
-
     #[test]
     fn test_struct_role_blockquote() {
         let lines = vec![make_line(vec![make_item("Quoted text", 1, Some(0))])];