Honour a page's /Rotate when extracting a scan

A scan fed sideways stores its image landscape and sets /Rotate 90 so a
viewer turns it upright. Extracting the image by xref — which is how a
raster source is read, to keep the scan's native resolution — bypasses
that, so every system ran down the page and detection found nothing.

Apply the page rotation to the extracted raster. Quarter turns only;
nothing produces anything else.

noteman_slicer/pdf.py

@@ -90,13 +90,28 @@ def page_raster(source: Source, index: int) -> np.ndarray:
             # Pixmap(doc, xref) rather than decoding extract_image() bytes:
             # MuPDF handles JBIG2 and CCITT, which no image library will.
             pix = pymupdf.Pixmap(source.doc, xref)
-            return _to_gray(pix)
+            # The embedded image is in its own orientation, not the page's: a
+            # scanner that fed the sheet sideways stores it landscape and the
+            # PDF sets /Rotate so viewers turn it upright. Extracting by xref
+            # bypasses that, so apply it here — otherwise every system runs
+            # down the page and detection finds nothing.
+            return _rotate(_to_gray(pix), page.rotation)
         # A scanned PDF whose page has no embedded image (a blank, or a
         # cover typeset in vector). Rendering is the only option left.
 
     return _to_gray(page.get_pixmap(dpi=source.render_dpi, colorspace=pymupdf.csGRAY))
 
 
+def _rotate(gray: np.ndarray, degrees: int) -> np.ndarray:
+    """Turn a page raster clockwise by a multiple of 90°, as /Rotate means it.
+
+    ponytail: quarter turns only. A page rotated by anything else would need
+    resampling, and no scanner produces one.
+    """
+    turns = round(degrees / 90) % 4
+    return np.ascontiguousarray(np.rot90(gray, -turns)) if turns else gray
+
+
 def _to_gray(pix: pymupdf.Pixmap) -> np.ndarray:
     if pix.alpha or pix.colorspace is None or pix.colorspace.n != 1:
         pix = pymupdf.Pixmap(pymupdf.csGRAY, pix)

tests/test_pdf.py

@@ -28,15 +28,21 @@ def _vector_pdf(path: Path, pages: int = 2) -> None:
     doc.save(path)
 
 
-def _scan_pdf(path: Path, pages: int = 2, w: int = 1653, h: int = 2332) -> None:
-    """Each page is one full-page grayscale image — what a real scan looks like."""
+def _scan_pdf(path: Path, pages: int = 2, w: int = 1653, h: int = 2332, rotation: int = 0) -> None:
+    """Each page is one full-page grayscale image — what a real scan looks like.
+
+    `rotation` reproduces a sheet fed sideways: the image is stored in its own
+    orientation and /Rotate turns it upright for a viewer.
+    """
     art = np.full((h, w), 255, np.uint8)
     art[500:505, 100 : w - 100] = 0  # a staff line, so it isn't uniform
+    art[:60, :60] = 0  # a corner mark, so orientation is checkable
     pix = pymupdf.Pixmap(pymupdf.csGRAY, w, h, bytearray(art.tobytes()), False)
     doc = pymupdf.open()
     for _ in range(pages):
-        page = doc.new_page(width=A4.width, height=A4.height)
+        page = doc.new_page(width=A4.width, height=A4.width * h / w)
         page.insert_image(page.rect, pixmap=pix)
+        page.set_rotation(rotation)
     doc.save(path)
 
 
@@ -64,6 +70,22 @@ def main() -> int:
     assert page.min() == 0 and page.max() == 255, (page.min(), page.max())
     src.close()
 
+    # The corner mark sits top-left in an upright scan.
+    assert page[:60, :60].max() == 0 and page[:60, -60:].min() == 255
+
+    # A sideways scan comes back upright: the page's /Rotate applies to the
+    # image extracted by xref, which bypasses it. Okular gets this right and
+    # the slicer used to not.
+    sideways = tmp / "sideways.pdf"
+    _scan_pdf(sideways, pages=1, w=2332, h=1653, rotation=90)
+    src = open_source(sideways)
+    assert src.type is SourceType.RASTER
+    turned = page_raster(src, 0)
+    assert turned.shape == (2332, 1653), turned.shape
+    # Turned clockwise, so the mark that was top-left is now top-right.
+    assert turned[:60, -60:].max() == 0 and turned[:60, :60].min() == 255
+    src.close()
+
     # An override must win over detection, and say so.
     src = open_source(scan, SourceType.VECTOR)
     assert src.type is SourceType.VECTOR and src.detected is SourceType.RASTER
@@ -71,7 +93,7 @@ def main() -> int:
     assert page_raster(src, 0).shape[1] > 4000, "override must force a render"
     src.close()
 
-    for f in (vec, scan):
+    for f in (vec, scan, sideways):
         f.unlink()
     tmp.rmdir()
     print("ok")