fix: reject cell-rect "tables" that are actually prose in a framed box

The rect-based cell fallback in detect_row_stripe_table_from_cell_rects
derives columns purely from text X-position clustering. When prose
wraps inside a bounding-box rect (chat transcripts, stylized figures),
the word-boundary gaps cluster into many spurious columns, producing
a multi-column "table" that is just fragmented prose.

Count cells containing common English function words (articles,
prepositions, pronouns, common verbs) and reject the fallback when
20%+ of non-empty cells contain any such word. Real tabular data —
labels, units, numbers, short identifiers — rarely contains these.

Update the td9264 snapshot: the government document section that
previously rendered as a malformed table now renders as cleaner
prose + a proper CFR list.

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

src/tables/detect_rects.rs

@@ -1158,14 +1158,19 @@ fn propagate_merged_cells(
 
             // Find first and last grid rows that the rect spans.
             //
-            // A merged-cell rect CONTAINS the rows it spans — its bottom sits
+            // Require a rect to actually overlap the row by more than `tol`
-            // at or below the row bottom and its top sits at or above the row
+            // to count as a span. A "rect bottom ≤ row top + tol AND rect
-            // top (within tol). A pure overlap check (any overlap within tol)
+            // top ≥ row bottom − tol" check gives false positives at shared
-            // gives false positives at shared row boundaries: a rect whose
+            // row boundaries — a rect whose top equals row N's bottom lies
-            // top equals row N's bottom would be considered to span row N
+            // entirely below the row but still passes the tolerance-slack
-            // even though it lies entirely below, cascading body text from
+            // check, cascading body text from unrelated rows into one
-            // unrelated rows into a single header cell.
+            // merged cell.
-            let spans = |r: usize| ry <= row_edges[r + 1] + tol && (ry + rh) >= row_edges[r] - tol;
+            let spans = |r: usize| {
+                let row_top = row_edges[r];
+                let row_bot = row_edges[r + 1];
+                let overlap = (row_top.min(ry + rh) - row_bot.max(ry)).max(0.0);
+                overlap > tol
+            };
             let first_row = (0..num_rows).find(|&r| spans(r));
             let last_row = (0..num_rows).rfind(|&r| spans(r));
 
@@ -1674,6 +1679,49 @@ fn detect_row_stripe_table_from_cell_rects(
         return None;
     }
 
+    // Reject "tables" that are actually prose in a framed region.
+    // Columns here come from text X-position clustering; when prose wraps
+    // inside a bounding-box rect (e.g. chat-transcript figures) the
+    // word-boundary gaps cluster into many spurious columns, and the
+    // resulting cells hold sentence fragments riddled with common English
+    // function words. Count cells with any such word and reject when
+    // 20%+ of non-empty cells match — real tabular data (labels, units,
+    // numbers) rarely contains these words.
+    if num_cols >= 4 {
+        const PROSE_WORDS: &[&str] = &[
+            "a", "an", "the", "of", "to", "is", "was", "are", "were", "be", "been", "in", "on",
+            "at", "with", "for", "by", "as", "and", "or", "but", "this", "that", "these", "those",
+            "from", "into", "has", "have", "had", "not", "don't", "doesn't", "it's", "its", "it",
+            "i", "me", "my", "we", "our", "us", "you", "your", "they", "them", "their", "he",
+            "she", "his", "her",
+        ];
+        let mut prose_cells = 0usize;
+        let mut counted = 0usize;
+        for row in &cells {
+            for cell in row {
+                let t = cell.trim();
+                if t.is_empty() {
+                    continue;
+                }
+                counted += 1;
+                let lower = t.to_ascii_lowercase();
+                let has_prose_word = lower
+                    .split(|c: char| !c.is_ascii_alphabetic() && c != '\'')
+                    .any(|w| PROSE_WORDS.contains(&w));
+                if has_prose_word {
+                    prose_cells += 1;
+                }
+            }
+        }
+        if counted > 0 && prose_cells * 5 >= counted {
+            debug!(
+                "  cell-rect rejected: {}/{} cells contain prose function words — likely prose",
+                prose_cells, counted
+            );
+            return None;
+        }
+    }
+
     let column_centers: Vec<f32> = (0..num_cols)
         .map(|c| (col_edges[c] + col_edges[c + 1]) / 2.0)
         .collect();

tests/snapshots/td9264.md

@@ -157,14 +157,33 @@ section and paragraph
 |§1.6043-2(a)|or 1.1081-11|3T(a), or §1.1081-11T|
 |The first sentence of §301.6011-5T(a) (twice)|§1.6012-2|paragraphs (a), (b) and (d) through (j) of §1.6012- 2, and paragraph (c) of §1.6012-2T|
 
-|||PART 602--OMB CONTROL NUMBERS UNDER THE PAPERWORK||
+PART 602--OMB CONTROL NUMBERS UNDER THE PAPERWORK REDUCTION ACT Par. 54. The authority citation for part 602 continues to read as follows: Authority: 26 U.S.C. 7805. Par. 55. In §602.101, paragraph (b) is amended to read as follows:
-|---|---|---|---|
+
-||REDUCTION ACT Authority: 26 U.S.C. 7805. 1. The following entries to the table are removed: §602.101 OMB Control numbers.|Par. 54. The authority citation for part 602 continues to read as follows: Par. 55. In §602.101, paragraph (b) is amended to read as follows:||
+1. The following entries to the table are removed:
-|* * * * *|(b) * * * CFR part or section where identified or described||Current OMB control No.|
+§602.101 OMB Control numbers.
-|* * * * *|1.332-6………………………………………………………………….|1.382-11……………………………………………………………….. 1545-2019 1.351-3…………………………………………………………………. 1545-2019 1.355-5…………………………………………………………………. 1545-2019 1.368-3…………………………………………………………………. 1545-2019 1.1081-11………………………………………………………………. 1545-2019|1545-2019|
+
-|* * * * *|§602.101 OMB Control numbers.|______________________________________________________________ 2. The following entries are added in numerical order to the table:||
+* * * * *
-|* * * * *|(b) * * * CFR part or section where identified or described||Current OMB control No.|
+(b) * * *
-|* * * * *|1.302-2T………………………………………………………………… 1545 1.302-4T………………………………………………………………… 1545||-2019 -2019|
+CFR part or section where Current OMB identified or described control No.
+
+* * * * *
+1.332-6…………………………………………………………………. 1545-2019
+1.382-11……………………………………………………………….. 1545-2019
+1.351-3…………………………………………………………………. 1545-2019
+1.355-5…………………………………………………………………. 1545-2019
+1.368-3…………………………………………………………………. 1545-2019
+1.1081-11………………………………………………………………. 1545-2019
+* * * * * **______________________________________________________________**
+2. The following entries are added in numerical order to the table:
+§602.101 OMB Control numbers.
+
+* * * * *
+(b) * * *
+CFR part or section where Current OMB identified or described control No.
+
+* * * * *
+1.302-2T………………………………………………………………… 1545-2019
+1.302-4T………………………………………………………………… 1545-2019
 
 |1.331-1T………………………………………………………………… 1545|-2019|
 |---|---|