fix(ocr): guard Kraken block extraction against missing boundary/baseline

extract_page_blocks() walked `record.boundary` and `record.baseline`
unconditionally, so a record that arrived without either (malformed
kraken output, or a MagicMock in tests that iterates to nothing)
crashed with "min() arg is an empty sequence".

Coerce both attributes through list(), require at least 3 points for
the polygon path, fall back to the baseline path when the polygon is
missing, and skip the record entirely when neither is usable —
emitting no block is safer than emitting one with garbage coordinates.

The test helper now sets `boundary` and `baseline` explicitly to
mirror real Kraken 7.0 records (and so the happy-path test exercises
the polygon branch). A new regression test covers the skip path.

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>

ocr-service/engines/kraken.py

@@ -122,16 +122,27 @@ def extract_page_blocks(image: Image, page_idx: int, language: str = "de",
     pred_it = rpred.rpred(active_model, image, baseline_seg)
 
     for record in pred_it:
-        polygon_pts = record.boundary if hasattr(record, "boundary") and record.boundary else []
+        # Coerce via list() so unexpected shapes (None, truthy mocks that
+        # iterate to nothing, empty lists) collapse to [] and can't blow up
+        # the min/max calls below.
+        boundary_attr = getattr(record, "boundary", None)
+        polygon_pts = list(boundary_attr) if boundary_attr else []
 
-        if polygon_pts:
+        if len(polygon_pts) >= 3:
             xs = [p[0] for p in polygon_pts]
             ys = [p[1] for p in polygon_pts]
             x1, y1 = min(xs), min(ys)
             x2, y2 = max(xs), max(ys)
         else:
-            xs = [p[0] for p in record.baseline]
-            ys = [p[1] for p in record.baseline]
+            baseline_attr = getattr(record, "baseline", None)
+            baseline_pts = list(baseline_attr) if baseline_attr else []
+            if not baseline_pts:
+                # No polygon and no baseline — we have no way to place the
+                # block on the page, so drop it rather than emit garbage
+                # coordinates.
+                continue
+            xs = [p[0] for p in baseline_pts]
+            ys = [p[1] for p in baseline_pts]
             x1, y1 = min(xs), min(ys) - 5
             x2, y2 = max(xs), max(ys) + 5
 

ocr-service/test_engines.py

@@ -115,11 +115,16 @@ def test_surya_extract_blocks_delegates_to_extract_page_blocks():
 # ─── Kraken extract_page_blocks ──────────────────────────────────────────────
 
 
-def _make_kraken_record(text, cuts, confidences=None):
+def _make_kraken_record(text, cuts, confidences=None, boundary=None, baseline=None):
     record = MagicMock()
     record.prediction = text
     record.cuts = cuts
     record.line = cuts
+    # Real kraken records expose `boundary` (polygon) and `baseline` lists.
+    # Mirror that here so the extract path doesn't take the "missing data"
+    # branch during normal tests.
+    record.boundary = boundary if boundary is not None else cuts
+    record.baseline = baseline if baseline is not None else cuts
     record.confidences = confidences or [0.9] * len(text)
     return record
 
@@ -179,6 +184,33 @@ def test_kraken_extract_blocks_delegates_to_extract_page_blocks():
     assert blocks[1]["pageNumber"] == 2
 
 
+def test_kraken_extract_page_blocks_skips_records_without_positional_data():
+    """Records that arrive without a usable boundary polygon OR baseline must
+    be dropped rather than crash min() with an empty sequence."""
+    import sys
+
+    image = Image.new("RGB", (100, 200))
+    mock_blla = MagicMock()
+    mock_blla.segment.return_value = MagicMock()
+    mock_rpred = MagicMock()
+
+    malformed = _make_kraken_record("Noise", [], boundary=[], baseline=[])
+    mock_rpred.rpred.return_value = [malformed]
+
+    sys.modules["kraken"] = MagicMock(blla=mock_blla, rpred=mock_rpred)
+    sys.modules["kraken.blla"] = mock_blla
+    sys.modules["kraken.rpred"] = mock_rpred
+    try:
+        with patch.object(kraken, "_model", MagicMock()):
+            blocks = kraken.extract_page_blocks(image, page_idx=1, language="de")
+    finally:
+        sys.modules.pop("kraken", None)
+        sys.modules.pop("kraken.blla", None)
+        sys.modules.pop("kraken.rpred", None)
+
+    assert blocks == []
+
+
 # ─── Engine signatures must match ─────────────────────────────────────────────
 #
 # main.py resolves `engine = kraken_engine if use_kraken else surya_engine` and