Render textbook vocab as paired Spanish→English grid

Previously the chapter reader showed vocab tables as a flat list of OCR
lines — because Vision reads columns top-to-bottom, the Spanish column
appeared as one block followed by the English column, making pairings
illegible.

Now every vocab table renders as a 2-column grid with Spanish on the
left and English on the right. Supporting changes:

- New ocr_all_vocab.swift: bounding-box OCR over all 931 vocab images,
  cluster lines into rows by Y-coordinate, split rows by largest X-gap,
  detect 2- / 3- / 4-column layouts automatically. ~2800 pairs extracted
  this pass vs ~1100 from the old block-alternation heuristic.
- merge_pdf_into_book.py now prefers bounding-box pairs when present,
  falls back to the heuristic, embeds the resulting pairs as
  vocab_table.cards in book.json.
- DataLoader passes cards through to TextbookBlock on seed.
- TextbookChapterView renders cards via SwiftUI Grid (2 cols).
- fix_vocab.py quarantine rule relaxed — only mis-pairs where both
  sides are clearly the same language are removed. "unknown" sides
  stay (bbox pipeline already oriented them correctly).

Textbook card count jumps from 1044 → 3118 active pairs.
textbookDataVersion bumped to 9.

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

Conjuga/Scripts/textbook/merge_pdf_into_book.py

@@ -33,6 +33,7 @@ CHAPTERS_JSON = HERE / "chapters.json"
 ANSWERS_JSON = HERE / "answers.json"
 OCR_JSON = HERE / "ocr.json"
 PDF_OCR_JSON = HERE / "pdf_ocr.json"
+PAIRED_VOCAB_JSON = HERE / "paired_vocab.json"  # bounding-box pairs (preferred)
 OUT_BOOK = HERE / "book.json"
 OUT_VOCAB = HERE / "vocab_cards.json"
 
@@ -222,7 +223,9 @@ def main() -> None:
     epub_ocr = load(OCR_JSON)
     pdf_ocr_raw = load(PDF_OCR_JSON) if PDF_OCR_JSON.exists() else {}
     pdf_pages = build_pdf_page_index(pdf_ocr_raw) if pdf_ocr_raw else {}
+    paired_vocab = load(PAIRED_VOCAB_JSON) if PAIRED_VOCAB_JSON.exists() else {}
     print(f"Mapped {len(pdf_pages)} PDF pages to book page numbers")
+    print(f"Loaded bounding-box pairs for {len(paired_vocab)} vocab images")
 
     # Build a global set of EPUB narrative lines (for subtraction when pulling vocab)
     narrative_set = set()
@@ -279,19 +282,48 @@ def main() -> None:
                 if repairs > 0:
                     merged_pages += 1
 
-                derived = build_vocab_cards_for_block(
+                # Prefer bounding-box pairs (from paired_vocab.json) when
+                # present. Fall back to the block-alternation heuristic.
+                bbox = paired_vocab.get(src, {})
+                bbox_pairs = bbox.get("pairs", []) if isinstance(bbox, dict) else []
+                heuristic = build_vocab_cards_for_block(
                     {"src": src},
                     {"lines": merged_lines, "confidence": merged_conf},
                     ch, current_section_title, bi
                 )
-                all_vocab_cards.extend(derived)
+
+                if bbox_pairs:
+                    cards_for_block = [
+                        {"front": p["es"], "back": p["en"]}
+                        for p in bbox_pairs
+                        if p.get("es") and p.get("en")
+                    ]
+                    # Also feed the flashcard deck
+                    for p in bbox_pairs:
+                        if p.get("es") and p.get("en"):
+                            all_vocab_cards.append({
+                                "front": p["es"],
+                                "back": p["en"],
+                                "chapter": ch["number"],
+                                "chapterTitle": ch["title"],
+                                "section": current_section_title,
+                                "sourceImage": src,
+                            })
+                    pair_source = "bbox"
+                else:
+                    cards_for_block = [{"front": c["front"], "back": c["back"]} for c in heuristic]
+                    all_vocab_cards.extend(heuristic)
+                    pair_source = "heuristic"
+
                 out_blocks.append({
                     "kind": "vocab_table",
                     "sourceImage": src,
                     "ocrLines": merged_lines,
                     "ocrConfidence": merged_conf,
-                    "cardCount": len(derived),
-                    "source": "pdf-repaired" if repairs > 0 else ("epub" if epub_lines else "pdf"),
+                    "cardCount": len(cards_for_block),
+                    "cards": cards_for_block,
+                    "columnCount": bbox.get("columnCount", 2) if isinstance(bbox, dict) else 2,
+                    "source": pair_source,
                     "bookPage": book_page,
                     "repairs": repairs,
                 })