Merge branch 'feature/hocrdebug'

src/ocrmypdf/_graft.py

@@ -292,6 +292,7 @@ class OcrGrafter:
             # finally move the lower left corner to match the mediabox. All transforms
             # must be premultiplied so they are applied in reverse order here.
             ctm = corner @ untranslate @ scale @ rotate @ translate
+            log.debug("Grafting with ctm %r", ctm)
 
             base_resources = _ensure_dictionary(base_page.obj, Name.Resources)
             base_xobjs = _ensure_dictionary(base_resources, Name.XObject)
@@ -311,9 +312,16 @@ class OcrGrafter:
 
             if strip_old_text:
                 strip_invisible_text(self.pdf_base, base_page)
-
+            base_page.contents_coalesce()
+            if self.render_mode == RenderMode.ON_TOP:
+                # Add q/Q to ensure content we append is drawn correctly
+                # Strictly speaking this needs to trace the whole q/Q stack in case
+                # stack is not balanced.
+                original = base_page.Contents.read_bytes()
+                base_page.Contents.write(b'q\n' + original + b'\nQ\n')
             base_page.contents_add(
-                new_text_layer, prepend=self.render_mode == RenderMode.ON_TOP
+                new_text_layer, prepend=self.render_mode == RenderMode.UNDERNEATH
             )
+            base_page.contents_coalesce()
 
             _update_resources(obj=base_page.obj, font=font, font_key=font_key)

src/ocrmypdf/_pipeline.py

@@ -34,7 +34,8 @@ from ocrmypdf.exceptions import (
     UnsupportedImageFormatError,
 )
 from ocrmypdf.helpers import IMG2PDF_KWARGS, Resolution, safe_symlink
-from ocrmypdf.hocrtransform import HocrTransform
+from ocrmypdf.hocrtransform import DebugRenderOptions, HocrTransform
+from ocrmypdf.hocrtransform._font import Courier
 from ocrmypdf.pdfa import generate_pdfa_ps
 from ocrmypdf.pdfinfo import Colorspace, Encoding, PageInfo, PdfInfo
 from ocrmypdf.pluginspec import OrientationConfidence
@@ -741,15 +742,25 @@ def render_hocr_page(hocr: Path, page_context: PageContext) -> Path:
         return output_file
 
     dpi = get_page_square_dpi(page_context, calculate_image_dpi(page_context))
-    debug_mode = options.pdf_renderer == 'hocrdebug'
-
+    debug_kwargs = {}
+    if options.pdf_renderer == 'hocrdebug':
+        debug_kwargs = dict(
+            debug_render_options=DebugRenderOptions(
+                render_baseline=True,
+                render_triangle=True,
+                render_line_bbox=False,
+                render_word_bbox=True,
+                render_paragraph_bbox=False,
+                render_space_bbox=False,
+            ),
+            font=Courier(),
+        )
     HocrTransform(
-        hocr_filename=hocr,
-        dpi=dpi.to_scalar(),  # square
-        debug=debug_mode,
+        hocr_filename=hocr, dpi=dpi.to_scalar(), **debug_kwargs  # square
     ).to_pdf(
         out_filename=output_file,
         image_filename=None,
+        invisible_text=True if not debug_kwargs else False,
     )
     return output_file
 

src/ocrmypdf/hocrtransform/_font.py

@@ -18,7 +18,12 @@ from pikepdf.canvas import Font
 log = logging.getLogger(__name__)
 
 
-class GlyphlessFont(Font):
+class EncodableFont(Font):
+    def text_encode(self, text: str) -> bytes:
+        raise NotImplementedError()
+
+
+class GlyphlessFont(EncodableFont):
     CID_TO_GID_DATA = zlib.compress(b"\x00\x01" * 65536)
     GLYPHLESS_FONT_NAME = 'pdf.ttf'
     GLYPHLESS_FONT = (package_files('ocrmypdf.data') / GLYPHLESS_FONT_NAME).read_bytes()
@@ -27,11 +32,14 @@ class GlyphlessFont(Font):
     def __init__(self):
         pass
 
-    def text_width(self, text: str, fontsize: float) -> int:
+    def text_width(self, text: str, fontsize: float) -> float:
         """Estimate the width of a text string when rendered with the given font."""
         # NFKC: split ligatures, combine diacritics
         return len(unicodedata.normalize("NFKC", text)) * (fontsize / self.CHAR_ASPECT)
 
+    def text_encode(self, text: str) -> bytes:
+        return text.encode('utf-16be')
+
     def register(self, pdf: Pdf):
         """Register the glyphless font.
 
@@ -110,3 +118,24 @@ class GlyphlessFont(Font):
         font_descriptor.FontFile2 = pdf.make_stream(self.GLYPHLESS_FONT)
         cid_font_type2.FontDescriptor = font_descriptor
         return basefont
+
+
+class Courier(EncodableFont):
+    """Courier font."""
+
+    def text_width(self, text: str, fontsize: float) -> float:
+        """Estimate the width of a text string when rendered with the given font."""
+        return len(text) * fontsize
+
+    def text_encode(self, text: str) -> bytes:
+        return text.encode('pdfdoc', errors='ignore')
+
+    def register(self, pdf: Pdf) -> Dictionary:
+        """Register the font."""
+        return pdf.make_indirect(
+            Dictionary(
+                BaseFont=Name.Courier,
+                Type=Name.Font,
+                Subtype=Name.Type1,
+            )
+        )

src/ocrmypdf/hocrtransform/_hocr.py

@@ -27,11 +27,11 @@ from pikepdf.canvas import (
     MAGENTA,
     RED,
     Canvas,
-    Font,
     Text,
     TextDirection,
 )
 
+from ocrmypdf.hocrtransform._font import EncodableFont as Font
 from ocrmypdf.hocrtransform._font import GlyphlessFont
 
 log = logging.getLogger(__name__)
@@ -45,12 +45,12 @@ Element = ElementTree.Element
 class DebugRenderOptions:
     """A class for managing rendering options."""
 
-    render_paragraph_bbox: bool
-    render_baseline: bool
-    render_triangle: bool
-    render_line_bbox: bool
-    render_word_bbox: bool
-    render_space_bbox: bool
+    render_paragraph_bbox: bool = False
+    render_baseline: bool = False
+    render_triangle: bool = False
+    render_line_bbox: bool = False
+    render_word_bbox: bool = False
+    render_space_bbox: bool = False
 
 
 class HocrTransformError(Exception):
@@ -81,8 +81,22 @@ class HocrTransform:
         debug: bool = False,
         fontname: Name = Name("/f-0-0"),
         font: Font = GlyphlessFont(),
+        debug_render_options: DebugRenderOptions | None = None,
     ):
         """Initialize the HocrTransform object."""
+
+        if debug:
+            log.warning("Use debug_render_options instead", DeprecationWarning)
+            self.render_options = DebugRenderOptions(
+                render_baseline=debug,
+                render_triangle=debug,
+                render_line_bbox=False,
+                render_word_bbox=debug,
+                render_paragraph_bbox=False,
+                render_space_bbox=False,
+            )
+        else:
+            self.render_options = debug_render_options or DebugRenderOptions()
         self.dpi = dpi
         self.hocr = ElementTree.parse(os.fspath(hocr_filename))
         self._fontname = fontname
@@ -103,14 +117,6 @@ class HocrTransform:
             self.height = (coords.ury - coords.lly) / (self.dpi / INCH)
             # Stop after first div that has page coordinates
             break
-        self.render_options = DebugRenderOptions(
-            render_baseline=debug,
-            render_triangle=debug,
-            render_line_bbox=False,
-            render_word_bbox=debug,
-            render_paragraph_bbox=False,
-            render_space_bbox=False,
-        )
 
     def _get_element_text(self, element: Element):
         """Return the textual content of the element and its children."""
@@ -220,7 +226,7 @@ class HocrTransform:
                     root,
                     "ocrx_word",
                     invisible_text,
-                    TextDirection.LTR,
+                    direction,
                     True,
                 )
         # put the image on the page, scaled to fill the page
@@ -311,8 +317,7 @@ class HocrTransform:
             line_box_height = abs(line_box.height) / cos(angle)
             fontsize = line_box_height + intercept
             text.font(self._fontname, fontsize)
-            if invisible_text or True:
-                text.render_mode(3)  # Invisible (indicates OCR text)
+            text.render_mode(3 if invisible_text else 0)
 
             self._debug_draw_baseline(
                 canvas, line_matrix.inverse().transform(line_box), 0
@@ -362,10 +367,17 @@ class HocrTransform:
         self._debug_draw_word_bbox(canvas, box)
 
         # If this word is 0 units wide, our best bet seems to be to suppress this text
+        if text_direction == TextDirection.RTL:
+            log.info("RTL: %s", elemtxt)
         if font_width > 0:
-            text.text_transform(Matrix(1, 0, 0, 1, box.llx, 0))
+            if text_direction == TextDirection.LTR:
+                text.text_transform(Matrix(1, 0, 0, -1, box.llx, 0))
+            elif text_direction == TextDirection.RTL:
+                text.text_transform(Matrix(-1, 0, 0, -1, box.llx + box.width, 0))
             text.horiz_scale(100 * box.width / font_width)
-            text.show(elemtxt.encode('utf-16be'))
+            text.show(self._font.text_encode(elemtxt))
+            # elif text_direction == TextDirection.RTL:
+            #     text.show(self._font.text_encode(elemtxt[::-1]))
 
         # Get coordinates of the next word (if there is one)
         hocr_next_box = (
@@ -385,11 +397,16 @@ class HocrTransform:
         elif text_direction == TextDirection.RTL:
             space_box = Rectangle(next_box.urx, box.lly, box.llx, next_box.ury)
         self._debug_draw_space_bbox(canvas, space_box)
-        text.text_transform(Matrix(1, 0, 0, 1, space_box.llx, 0))
         space_width = self._font.text_width(' ', fontsize)
         if space_width > 0:
+            if text_direction == TextDirection.LTR:
+                text.text_transform(Matrix(1, 0, 0, -1, space_box.llx, 0))
+            elif text_direction == TextDirection.RTL:
+                text.text_transform(
+                    Matrix(-1, 0, 0, -1, space_box.llx + space_box.width, 0)
+                )
             text.horiz_scale(100 * space_box.width / space_width)
-            text.show(' '.encode('utf-16be'))
+            text.show(self._font.text_encode(' '))
 
     def _debug_draw_paragraph_boxes(self, canvas: Canvas, color=CYAN):
         """Draw boxes around paragraphs in the document."""