def _process_content_streams( *, pdf: Pdf, container: Object, shorthand=None ) -> Iterator[Union[VectorMarker, TextMarker, ImageInfo]]: """Find all individual instances of images drawn in the container Usually the container is a page, but it may also be a Form XObject. On a typical page images are stored inline or as regular images in an XObject. Form XObjects may include inline images, XObject images, and recursively, other Form XObjects; and also vector graphic objects. Every instance of an image being drawn somewhere is flattened and treated as a unique image, since if the same image is drawn multiple times on one page it may be drawn at differing resolutions, and our objective is to find the resolution at which the page can be rastered without downsampling. """ if container.get('/Type') == '/Page' and '/Contents' in container: initial_shorthand = shorthand or UNIT_SQUARE elif container.get( '/Type') == '/XObject' and container['/Subtype'] == '/Form': # Set the CTM to the state it was when the "Do" operator was # encountered that is drawing this instance of the Form XObject ctm = PdfMatrix(shorthand) if shorthand else PdfMatrix.identity() # A Form XObject may provide its own matrix to map form space into # user space. Get this if one exists form_shorthand = container.get('/Matrix', PdfMatrix.identity()) form_matrix = PdfMatrix(form_shorthand) # Concatenate form matrix with CTM to ensure CTM is correct for # drawing this instance of the XObject ctm = form_matrix @ ctm initial_shorthand = ctm.shorthand else: return contentsinfo = _interpret_contents(container, initial_shorthand) if contentsinfo.found_vector: yield VectorMarker() if contentsinfo.found_text: yield TextMarker() yield from _find_inline_images(contentsinfo) yield from _find_regular_images(container, contentsinfo) yield from _find_form_xobject_images(pdf, container, contentsinfo)
def test_unparse_cs(): instructions = [ ([], Operator('q')), ([*PdfMatrix.identity().shorthand], Operator('cm')), ([], Operator('Q')), ] assert unparse_content_stream(instructions).strip() == b'q\n1 0 0 1 0 0 cm\n Q'
def _process_content_streams(*, pdf, container, shorthand=None): """Find all individual instances of images drawn in the container Usually the container is a page, but it may also be a Form XObject. On a typical page images are stored inline or as regular images in an XObject. Form XObjects may include inline images, XObject images, and recursively, other Form XObjects; and also vector graphic objects. Every instance of an image being drawn somewhere is flattened and treated as a unique image, since if the same image is drawn multiple times on one page it may be drawn at differing resolutions, and our objective is to find the resolution at which the page can be rastered without downsampling. """ if container.get('/Type') == '/Page' and '/Contents' in container: initial_shorthand = shorthand or UNIT_SQUARE elif container.get('/Type') == '/XObject' and container['/Subtype'] == '/Form': # Set the CTM to the state it was when the "Do" operator was # encountered that is drawing this instance of the Form XObject ctm = PdfMatrix(shorthand) if shorthand else PdfMatrix.identity() # A Form XObject may provide its own matrix to map form space into # user space. Get this if one exists form_shorthand = container.get('/Matrix', PdfMatrix.identity()) form_matrix = PdfMatrix(form_shorthand) # Concatenate form matrix with CTM to ensure CTM is correct for # drawing this instance of the XObject ctm = form_matrix @ ctm initial_shorthand = ctm.shorthand else: return contentsinfo = _interpret_contents(container, initial_shorthand) if contentsinfo.found_vector: yield VectorInfo() yield from _find_inline_images(contentsinfo) yield from _find_regular_images(container, contentsinfo) yield from _find_form_xobject_images(pdf, container, contentsinfo)
def _simple_interpret_content_stream(page: Union[Page, Object]): ctm = PdfMatrix.identity() stack: List[PdfMatrix] = [] for instruction in parse_content_stream(page, operators='q Q cm Do'): if isinstance(instruction, ContentStreamInlineImage): continue operands, op = instruction.operands, instruction.operator if op == Operator('q'): stack.append(ctm) elif op == Operator('Q'): ctm = stack.pop() elif op == Operator('cm'): ctm = PdfMatrix(operands) @ ctm elif op == Operator('Do'): xobj_name = operands[0] yield (xobj_name, ctm)