fix(pdf-inspector): relax vector table confidence gates

napi/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@firecrawl/pdf-inspector",
-  "version": "1.9.4",
+  "version": "1.9.1",
   "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",

src/lib.rs

@@ -823,8 +823,7 @@ pub fn extract_tables_in_regions_mem(
                     // symmetrically low under font-decode failure — this
                     // guard breaks that symmetry by comparing against
                     // bbox area, which is independent of extraction.
-                    if source != TableCandidateSource::KeyValue
-                        && region_text_density_too_low(region_text_chars, region_area)
+                    if region_text_density_too_low(region_text_chars, region_area)
                         && !markdown_table_body_is_dense(&md)
                     {
                         return None;
@@ -837,10 +836,8 @@ pub fn extract_tables_in_regions_mem(
                         Some(TableCandidateIssue::LineRowUndercount)
                     } else if wide_table_sparse_prefix_undercount(&md) {
                         Some(TableCandidateIssue::SparseWideUndercount)
-                    } else if !matches!(
-                        source,
-                        TableCandidateSource::Line | TableCandidateSource::KeyValue
-                    ) && text_cluster_column_undercount(&matched, shape)
+                    } else if source != TableCandidateSource::Line
+                        && text_cluster_column_undercount(&matched, shape)
                     {
                         Some(TableCandidateIssue::TextColumnUndercount)
                     } else if prose_grid_fragment_needs_ocr(&md) {
@@ -884,16 +881,6 @@ pub fn extract_tables_in_regions_mem(
             {
                 candidates.push(candidate);
             }
-            if let Some(table) = tables::try_build_table_from_columns(&matched, page_1idx) {
-                if let Some(candidate) = evaluate(TableCandidateSource::Column, &table) {
-                    candidates.push(candidate);
-                }
-            }
-            if let Some(table) = tables::try_build_key_value_table_from_rows(&matched, page_1idx) {
-                if let Some(candidate) = evaluate(TableCandidateSource::KeyValue, &table) {
-                    candidates.push(candidate);
-                }
-            }
 
             match select_table_candidate(&candidates) {
                 Some(candidate) => page_results.push(RegionText {
@@ -3765,8 +3752,6 @@ enum TableCandidateSource {
     Rect,
     Line,
     Heuristic,
-    Column,
-    KeyValue,
 }
 
 #[derive(Debug, Clone, Copy, PartialEq, Eq)]
@@ -3801,12 +3786,8 @@ fn select_table_candidate(candidates: &[TableCandidate]) -> Option<&TableCandida
     // serving a tidy-looking fragment.
     if first.issue == Some(TableCandidateIssue::LineRowUndercount) {
         return candidates.iter().find(|candidate| {
-            matches!(
-                candidate.source,
-                TableCandidateSource::Heuristic
-                    | TableCandidateSource::Column
-                    | TableCandidateSource::KeyValue
-            ) && candidate.issue.is_none()
+            candidate.source == TableCandidateSource::Heuristic
+                && candidate.issue.is_none()
                 && candidate.shape.cols * 10 >= first.shape.cols * 13
         });
     }
@@ -3824,31 +3805,14 @@ fn select_table_candidate(candidates: &[TableCandidate]) -> Option<&TableCandida
         TableCandidateSource::Rect | TableCandidateSource::Line
     ) {
         if let Some(heuristic) = candidates.iter().find(|candidate| {
-            matches!(
-                candidate.source,
-                TableCandidateSource::Heuristic
-                    | TableCandidateSource::Column
-                    | TableCandidateSource::KeyValue
-            ) && candidate.issue.is_none()
+            candidate.source == TableCandidateSource::Heuristic
+                && candidate.issue.is_none()
                 && heuristic_substantially_better(candidate.shape, accepted.shape)
         }) {
             accepted = heuristic;
         }
     }
 
-    if accepted.source == TableCandidateSource::Heuristic {
-        if let Some(layout_candidate) = candidates.iter().find(|candidate| {
-            matches!(
-                candidate.source,
-                TableCandidateSource::Column | TableCandidateSource::KeyValue
-            ) && candidate.issue.is_none()
-                && candidate.shape.cols >= accepted.shape.cols
-                && candidate.shape.rows > accepted.shape.rows
-        }) {
-            accepted = layout_candidate;
-        }
-    }
-
     Some(accepted)
 }
 
@@ -4350,9 +4314,7 @@ fn looks_like_partial_table_ex(markdown: &str, layout_assisted: bool) -> bool {
                         cell.trim().is_empty() && header_empty_indices.contains(&idx)
                     })
                     && layout_assisted_empty_header_has_dense_body(markdown, n_cols);
-                let sparse_row_is_section_label = layout_assisted
-                    && layout_assisted_sparse_section_row_is_ok(data_inner, markdown, n_cols);
-                if !sparse_row_shares_header_spacer && !sparse_row_is_section_label {
+                if !sparse_row_shares_header_spacer {
                     return true;
                 }
             }
@@ -4444,26 +4406,6 @@ fn layout_assisted_empty_header_has_dense_body(markdown: &str, n_cols: usize) ->
         && filled_cells * 100 >= total_cells * 45
 }
 
-fn layout_assisted_sparse_section_row_is_ok(row: &[&str], markdown: &str, n_cols: usize) -> bool {
-    let labels: Vec<&str> = row
-        .iter()
-        .map(|cell| cell.trim())
-        .filter(|cell| !cell.is_empty())
-        .collect();
-    if labels.len() != 1 {
-        return false;
-    }
-    let label = labels[0];
-    if label.len() > 40 || !label.chars().any(|ch| ch.is_alphabetic()) {
-        return false;
-    }
-    if label.ends_with('.') || label.ends_with('!') || label.ends_with('?') || label.ends_with(':')
-    {
-        return false;
-    }
-    layout_assisted_empty_header_has_dense_body(markdown, n_cols)
-}
-
 fn markdown_table_body_is_dense(markdown: &str) -> bool {
     let rows = markdown_pipe_rows(markdown);
     let data_rows: Vec<&Vec<&str>> = rows
@@ -4845,16 +4787,6 @@ mod table_candidate_selection_tests {
         assert_eq!(selected.source, TableCandidateSource::Heuristic);
     }
 
-    #[test]
-    fn prefers_clean_column_fallback_when_it_recovers_more_rows() {
-        let candidates = vec![
-            candidate(TableCandidateSource::Heuristic, 6, 5, None),
-            candidate(TableCandidateSource::Column, 7, 5, None),
-        ];
-        let selected = select_table_candidate(&candidates).unwrap();
-        assert_eq!(selected.source, TableCandidateSource::Column);
-    }
-
     #[test]
     fn line_candidate_collapsing_captured_y_clusters_is_suspicious() {
         let long = "value value value value value value value value value value value value";
@@ -5159,24 +5091,6 @@ mod looks_like_partial_table_tests {
         );
     }
 
-    #[test]
-    fn sparse_section_row_passes_when_layout_assisted_body_is_dense() {
-        let md = "|Properties|Conditions|Method|Typical values|Units|\n\
-                  |---|---|---|---|---|\n\
-                  |Rheology|||||\n\
-                  |Melt Flow Rate|230 C/2.16 kg|ASTM D1238|3.0|g/10 min|\n\
-                  |Tensile Stress at Yield|50 mm/min|ASTM D638|31|MPa|\n\
-                  |Elongation at Yield|50 mm/min|ASTM D638|8|%|";
-        assert!(
-            looks_like_partial_table(md),
-            "strict mode rejects the sparse first row"
-        );
-        assert!(
-            !looks_like_partial_table_ex(md, true),
-            "layout-assisted should allow a short section label above dense table rows"
-        );
-    }
-
     #[test]
     fn paragraph_still_rejected_when_layout_assisted() {
         // Paragraph detection is not relaxed — it's a genuine extraction issue.

src/tables/format.rs

@@ -208,24 +208,6 @@ fn looks_like_compact_entry_label(cell: &str) -> bool {
     (1..=6).contains(&words)
 }
 
-fn looks_like_plain_section_label(cell: &str) -> bool {
-    let trimmed = cell.trim();
-    if trimmed.len() < 4 || trimmed.len() > 40 {
-        return false;
-    }
-    if trimmed.ends_with(['.', ',', ';', ':']) || trimmed.contains(|ch: char| ch.is_ascii_digit()) {
-        return false;
-    }
-    if trimmed.len() <= 4 && trimmed.chars().all(|ch| !ch.is_lowercase()) {
-        return false;
-    }
-    trimmed
-        .chars()
-        .all(|ch| ch.is_alphabetic() || ch.is_whitespace() || matches!(ch, '&' | '/' | '-'))
-        && starts_with_uppercase_alpha(trimmed)
-        && (1..=4).contains(&alpha_word_count(trimmed))
-}
-
 fn ends_like_incomplete_phrase(cell: &str) -> bool {
     let lower = cell.trim_end().to_ascii_lowercase();
     lower.ends_with(" and")
@@ -323,10 +305,6 @@ fn clean_table_cells(cells: &[Vec<String>]) -> (Vec<Vec<String>>, Vec<String>) {
             .and_then(|r| r.first())
             .map(|c| c.trim())
             .unwrap_or("");
-        let header_filled = cleaned
-            .first()
-            .map(|r| r.iter().filter(|c| !c.trim().is_empty()).count())
-            .unwrap_or(num_cols);
         let looks_like_spanning_first_column_row = first_cell.is_empty()
             && row.len() >= 4
             && non_first_cells.len() == row.len().saturating_sub(1)
@@ -350,10 +328,6 @@ fn clean_table_cells(cells: &[Vec<String>]) -> (Vec<Vec<String>>, Vec<String>) {
             && non_first_cells
                 .iter()
                 .any(|cell| looks_like_compact_entry_label(cell));
-        let looks_like_section_label_row = !first_cell.is_empty()
-            && filled_cells == 1
-            && header_filled >= 3
-            && looks_like_plain_section_label(first_cell);
         // Classic continuation: first cell empty, content in other cells
         let is_classic_continuation = first_cell.is_empty()
             && !non_first_cells.is_empty()
@@ -370,6 +344,10 @@ fn clean_table_cells(cells: &[Vec<String>]) -> (Vec<Vec<String>>, Vec<String>) {
             .last()
             .map(|r| r.iter().filter(|c| !c.trim().is_empty()).count())
             .unwrap_or(0);
+        let header_filled = cleaned
+            .first()
+            .map(|r| r.iter().filter(|c| !c.trim().is_empty()).count())
+            .unwrap_or(num_cols);
         // Merge when the row has significantly fewer filled cells than header.
         // For wide tables (5+ cols), require ≤50% of header cells.
         // For narrow tables (2-4 cols), require fewer than header cells.
@@ -391,7 +369,6 @@ fn clean_table_cells(cells: &[Vec<String>]) -> (Vec<Vec<String>>, Vec<String>) {
             && !looks_like_spanning_first_column_row
             && !looks_like_hierarchical_subrow
             && !looks_like_new_first_column_entry
-            && !looks_like_section_label_row
             && !is_short_subheader;
 
         let is_continuation = is_classic_continuation || is_wrapped_continuation;
@@ -537,44 +514,6 @@ mod tests {
         assert!(cleaned[1][1].contains("continued text here"));
     }
 
-    #[test]
-    fn test_clean_table_cells_first_column_section_label_not_merged() {
-        let cells = vec![
-            vec![
-                "Properties".into(),
-                "Conditions".into(),
-                "Method".into(),
-                "Typical values".into(),
-                "Units".into(),
-            ],
-            vec![
-                "Melt Flow Rate".into(),
-                "230 C/2.16 kg".into(),
-                "ASTM D1238".into(),
-                "3.0".into(),
-                "g/10 min".into(),
-            ],
-            vec![
-                "Mechanical".into(),
-                "".into(),
-                "".into(),
-                "".into(),
-                "".into(),
-            ],
-            vec![
-                "Tensile Stress at Yield".into(),
-                "50 mm/min".into(),
-                "ASTM D638".into(),
-                "31".into(),
-                "MPa".into(),
-            ],
-        ];
-        let (cleaned, _) = clean_table_cells(&cells);
-
-        assert_eq!(cleaned.len(), 4);
-        assert_eq!(cleaned[2][0], "Mechanical");
-    }
-
     #[test]
     fn test_clean_table_cells_short_subheader_not_merged() {
         let cells = vec![