release v2.1.4

MANIFEST.in

@@ -3,4 +3,5 @@ include borb/io/write/document/resources/*.icm
 include borb/pdf/canvas/font/composite_font/cmaps/*
 include borb/pdf/canvas/font/simple_font/afm/*.afm
 include borb/pdf/canvas/layout/emoji/resources/*.png
-include borb/pdf/canvas/layout/hyphenation/resources/*.json
+include borb/pdf/canvas/layout/hyphenation/resources/*.json
+include borb/pdf/canvas/lipsum/resources/*.json

README.md

@@ -6,6 +6,8 @@
 [![Corpus Coverage : 100.0%](https://img.shields.io/badge/corpus%20coverage-100.0%25-green)]()
 [![Text Extraction : 93.1%](https://img.shields.io/badge/text%20extraction-93.1%25-green)]()
 [![Public Method Documentation : 100%](https://img.shields.io/badge/public%20method%20documentation-100%25-green)]()
+[![Number of Tests : 396](https://img.shields.io/badge/number%20of%20tests-396-green)]()
+
 
 [![Downloads](https://pepy.tech/badge/borb)](https://pepy.tech/project/borb)
 [![Downloads](https://pepy.tech/badge/borb/month)](https://pepy.tech/project/borb)

borb/io/read/postfix/postfix_eval.py

@@ -237,7 +237,9 @@ def evaluate(s: str, args: typing.List[Decimal]) -> typing.List[Decimal]:
                     assert len(stk) >= 1, "Unable to apply operator exp, stack underflow"
                     # fmt: on
                     x = stk[-1]
-                    assert isinstance(x, Decimal)
+                    assert isinstance(
+                        x, Decimal
+                    ), "Unable to apply operator exp, unexpected type"
                     stk.pop(len(stk) - 1)
                     stk.append(Decimal(exp(x)))
                     continue
@@ -251,7 +253,9 @@ def evaluate(s: str, args: typing.List[Decimal]) -> typing.List[Decimal]:
                     assert len(stk) >= 1, "Unable to apply operator floor, stack underflow"
                     # fmt: on
                     x = stk[-1]
-                    assert isinstance(x, Decimal)
+                    assert isinstance(
+                        x, Decimal
+                    ), "Unable to apply operator floor, unexpected type"
                     stk.pop(len(stk) - 1)
                     stk.append(Decimal(floor(x)))
                     continue
@@ -260,8 +264,12 @@ def evaluate(s: str, args: typing.List[Decimal]) -> typing.List[Decimal]:
                     assert len(stk) >= 2, "Unable to apply operator ge, stack underflow"
                     x = stk[-1]
                     y = stk[-2]
-                    assert isinstance(x, Decimal)
-                    assert isinstance(y, Decimal)
+                    assert isinstance(
+                        x, Decimal
+                    ), "Unable to apply operator ge, unexpected type"
+                    assert isinstance(
+                        y, Decimal
+                    ), "Unable to apply operator ge, unexpected type"
                     stk.pop(len(stk) - 1)
                     stk.pop(len(stk) - 1)
                     stk.append(y >= x)

borb/io/read/reference/xref_transformer.py

@@ -63,10 +63,11 @@ def transform(
         """
 
         # update context
-        assert context is not None
+        assert context is not None, "context must be defined to read XREF objects"
         assert isinstance(object_to_transform, io.BufferedIOBase) or isinstance(
             object_to_transform, io.RawIOBase
         )
+
         context.root_object = Document()
         context.source = object_to_transform
         context.tokenizer = HighLevelTokenizer(context.source)

borb/io/read/types.py

@@ -330,7 +330,8 @@ def __setitem__(self, key, value):
         super(Dictionary, self).__setitem__(key, value)
 
     def __deepcopy__(self, memodict={}):
-        out = Dictionary()
+        out = type(self).__new__(type(self))
+        Dictionary.__init__(out)
         for k, v in self.items():
             out[copy.deepcopy(k, memodict)] = copy.deepcopy(v, memodict)
         return out

borb/io/write/ascii_art/ascii_logo.txt

@@ -1,2 +1,2 @@
-borb version 2.1.2
+borb version 2.1.4
 Joris Schellekens

borb/io/write/document/catalog_transformer.py

@@ -20,6 +20,7 @@
 )
 from borb.io.write.object.dictionary_transformer import DictionaryTransformer
 from borb.io.write.transformer import WriteTransformerState
+from borb.pdf import Document
 
 logger = logging.getLogger(__name__)
 
@@ -90,7 +91,10 @@ def transform(
 
         # /OutputIntents
         # fmt: off
-        needs_outputintents: bool = (context is not None and context.conformance_level is not None)
+
+        needs_outputintents: bool = (context is not None
+                                     and isinstance(context.root_object, Document)
+                                     and context.root_object.get_document_info().get_write_conformance_level() is not None)
         if needs_outputintents:
             self._build_rgb_outputintent_dictionary(object_to_transform)
         # fmt: on

borb/io/write/document/information_dictionary_transformer.py

@@ -269,14 +269,17 @@ def transform(
                                    and "Trailer" in document["XRef"]                        \
                                    and "Root" in document["XRef"]["Trailer"]                \
                                    and "Metadata" in document["XRef"]["Trailer"]["Root"]
-        needs_xmp_metadata = has_xmp_metadata or (context is not None and context.conformance_level is not None)
+        needs_xmp_metadata = has_xmp_metadata or (document.get_document_info().get_write_conformance_level() is not None)
         # fmt: on
 
         if needs_xmp_metadata:
+            conformance_level: ConformanceLevel = (
+                document.get_document_info().get_write_conformance_level()
+            )
 
             # write XMP /Metadata
             xmp_metadata_stream: Stream = self._write_xmp_metadata_stream(
-                new_info_dictionary, context.conformance_level
+                new_info_dictionary, conformance_level
             )
             assert context is not None
             document["XRef"]["Trailer"]["Root"][Name("Metadata")] = self.get_reference(

borb/io/write/reference/xref_transformer.py

@@ -45,41 +45,41 @@ def transform(
         trailer_out = Dictionary()
 
         # /Root
-        trailer_out[Name("Root")] = self.get_reference(
-            object_to_transform["Trailer"]["Root"], context
-        )
+        # fmt: off
+        trailer_out[Name("Root")] = self.get_reference(object_to_transform["Trailer"]["Root"], context)
+        # fmt: on
 
         # /Info
+        # fmt: off
         if "Info" in object_to_transform["Trailer"]:
-            trailer_out[Name("Info")] = self.get_reference(
-                object_to_transform["Trailer"]["Info"], context
-            )
+            trailer_out[Name("Info")] = self.get_reference(object_to_transform["Trailer"]["Info"], context)
+        # fmt: on
 
         # /Size
-        if (
-            "Trailer" in object_to_transform
-            and "Size" in object_to_transform["Trailer"]
-        ):
+        # fmt: off
+        if ("Trailer" in object_to_transform and "Size" in object_to_transform["Trailer"]):
             trailer_out[Name("Size")] = object_to_transform["Trailer"]["Size"]
         else:
-            trailer_out[Name("Size")] = Decimal(
-                0
-            )  # we'll recalculate this later anyway
+            trailer_out[Name("Size")] = Decimal(0)  # we'll recalculate this later anyway
+        # fmt: on
 
         # /ID
         if "ID" in object_to_transform["Trailer"]:
             trailer_out[Name("ID")] = object_to_transform["Trailer"]["ID"]
 
         # write /Info object
+        # fmt: off
         if "Info" in object_to_transform["Trailer"]:
-            self.get_root_transformer().transform(
-                object_to_transform["Trailer"]["Info"], context
-            )
+            self.get_root_transformer().transform(object_to_transform["Trailer"]["Info"], context)
+        # fmt: on
+
+        # write /Root /StructTreeRoot
+        # TODO
 
         # write /Root object
-        self.get_root_transformer().transform(
-            object_to_transform["Trailer"]["Root"], context
-        )
+        # fmt: off
+        self.get_root_transformer().transform(object_to_transform["Trailer"]["Root"], context)
+        # fmt: on
 
         # write /XREF
         start_of_xref = context.destination.tell()

borb/io/write/transformer.py

@@ -27,7 +27,6 @@ def __init__(
         self,
         destination: Optional[typing.Union[io.BufferedIOBase, io.RawIOBase]] = None,
         root_object: Optional[AnyPDFType] = None,
-        conformance_level: typing.Optional[ConformanceLevel] = None,
     ):
         # fmt: off
         self.destination = destination                                                      # this is the destination to write to (file, byte-buffer, etc)
@@ -36,7 +35,6 @@ def __init__(
         self.indirect_objects_by_hash: typing.Dict[int, typing.List[AnyPDFType]] = {}       # these are the indirect objects (by hash)
         self.resolved_references: typing.List[Reference] = []                               # these references have already been written
         self.compression_level: int = 9                                                     # default compression level
-        self.conformance_level: typing.Optional[ConformanceLevel] = conformance_level       # default conformance level
         self.apply_font_subsetting: bool = False                                            # whether to apply Font subsetting or not
         # fmt: on
 

borb/pdf/__init__.py

@@ -83,6 +83,7 @@
 # Shape
 from .canvas.layout.shape.connected_shape import ConnectedShape
 from .canvas.layout.shape.disconnected_shape import DisconnectedShape
+from .canvas.layout.smart_art.smart_art import SmartArt
 
 # Table
 from .canvas.layout.table.fixed_column_width_table import FixedColumnWidthTable
@@ -105,6 +106,7 @@
 from .canvas.layout.text.heterogeneous_paragraph import HeterogeneousParagraph
 from .canvas.layout.text.heading import Heading
 from .canvas.layout.text.chunk_of_text import ChunkOfText
+from .canvas.lipsum.lipsum import Lipsum
 
 # Document, Page, PDF
 from .document.document import Document

borb/pdf/canvas/layout/horizontal_rule.py

@@ -65,4 +65,4 @@ def _paint_content_box(self, page: Page, available_space: Rectangle) -> None:
         )
 
         # modify content stream
-        page._append_to_content_stream(content)
+        page.append_to_content_stream(content)

borb/pdf/canvas/layout/image/image.py

@@ -132,4 +132,4 @@ def _paint_content_box(self, page: Page, bounding_box: Rectangle):
         )
 
         # write content
-        page._append_to_content_stream(content)
+        page.append_to_content_stream(content)

borb/pdf/canvas/layout/layout_element.py

@@ -138,6 +138,22 @@ def __init__(
         # linkage (for lists, tables, etc)
         self._parent = parent
 
+    def _needs_to_be_tagged(self, p: "Page") -> bool:
+        """
+        This function returns whether this LayoutElement needs to be tagged
+        :param p:   the Page on which this LayoutElement is to be painted
+        :return:    true if this LayoutElement needs to be tagged, False otherwise
+        """
+        document: typing.Optional["Document"] = p.get_document()
+        if document is None:
+            return False
+        conformance_level: typing.Optional[
+            "ConformanceLevel"
+        ] = document.get_document_info().get_write_conformance_level()
+        if conformance_level is None:
+            return False
+        return conformance_level.get_conformance_level() in ["A", "U"]
+
     def get_font_size(self) -> Decimal:
         """
         This function returns the font size of this LayoutElement
@@ -267,12 +283,15 @@ def paint(self, page: "Page", available_space: Rectangle) -> None:  # type: igno
         :param available_space:     the available space (as a Rectangle) on which to paint this LayoutElement
         :return:                    None
         """
+
+        # calculate horizontal_border_width
         horizontal_border_width: Decimal = Decimal(0)
         if self._border_left:
             horizontal_border_width += self._border_width
         if self._border_right:
             horizontal_border_width += self._border_width
 
+        # calculate vertical_border_width
         vertical_border_width: Decimal = Decimal(0)
         if self._border_top:
             vertical_border_width += self._border_width
@@ -523,7 +542,7 @@ def _paint_background(
                 background_box.get_y() + background_box.get_height(),   # ul_y
             )
             # fmt: on
-            page._append_to_content_stream(content)
+            page.append_to_content_stream(content)
             return
 
         # remember border state
@@ -564,7 +583,7 @@ def _paint_background(
             assert p is not None
             content += " %f %f l" % (float(p[0]), float(p[1]))
         content += " f Q"
-        page._append_to_content_stream(content)
+        page.append_to_content_stream(content)
 
     def _paint_borders(self, page: "Page", border_box: Rectangle):  # type: ignore[name-defined]
         # border is not wanted on any side
@@ -604,4 +623,4 @@ def _paint_borders(self, page: "Page", border_box: Rectangle):  # type: ignore[n
                 float(p1[1]),
             )
         content += " Q"
-        page._append_to_content_stream(content)
+        page.append_to_content_stream(content)

borb/pdf/canvas/layout/page_layout/header_footer_multi_column_layout.py

@@ -10,6 +10,7 @@
 import typing
 from decimal import Decimal
 
+from borb.pdf import ChunkOfText
 from borb.pdf.canvas.geometry.rectangle import Rectangle
 from borb.pdf.canvas.layout.page_layout.multi_column_layout import MultiColumnLayout
 from borb.pdf.page.page import Page
@@ -24,20 +25,18 @@ class HeaderFooterMultiColumnLayout(MultiColumnLayout):
     """
 
     def __init__(
+        # fmt: off
         self,
         page: Page,
         number_of_columns: int = 2,
         horizontal_margin: typing.Optional[Decimal] = None,
         vertical_margin: typing.Optional[Decimal] = None,
-        header_callable: typing.Optional[
-            typing.Callable[[Page, Rectangle], None]
-        ] = None,
+        header_callable: typing.Optional[typing.Callable[[Page, Rectangle], None]] = None,
         header_height: Decimal = Decimal(12 * 3 * 1.2),
         footer_height: Decimal = Decimal(12 * 3 * 1.2),
-        footer_callable: typing.Optional[
-            typing.Callable[[Page, Rectangle], None]
-        ] = None,
+        footer_callable: typing.Optional[typing.Callable[[Page, Rectangle], None]] = None,
         inter_column_margin: typing.Optional[Decimal] = None,
+        # fmt: on
     ):
         super(HeaderFooterMultiColumnLayout, self).__init__(
             page,
@@ -58,12 +57,6 @@ def __init__(
         if self._footer_callable is None:
             self._footer_height = Decimal(0)
 
-        # size of Page is updated to ensure the layout algorithm does not attempt
-        # to fill the Page entirely
-        assert self._page_height is not None
-        self._page_height -= self._header_height
-        self._page_height -= self._footer_height
-
         # modify margins
         self._vertical_margin_bottom += self._footer_height
         self._vertical_margin_top += self._header_height
@@ -81,7 +74,7 @@ def _add_header_footer_to_current_page(self) -> None:
                 self.get_page(),
                 Rectangle(
                     self._horizontal_margin,
-                    self._page_height - self._vertical_margin_top,
+                    self._page_height - self._vertical_margin_top - self._header_height,
                     self._page_width - self._horizontal_margin * Decimal(2),
                     self._header_height,
                 ),
@@ -100,6 +93,18 @@ def _add_header_footer_to_current_page(self) -> None:
                 ),
             )
 
+        # previous LayoutElement
+        self._previous_element = ChunkOfText("")
+        self._previous_element._previous_paint_box = Rectangle(
+            self._horizontal_margin,
+            self._page_height - self._vertical_margin_top - self._header_height,
+            self._page_width - self._horizontal_margin * Decimal(2),
+            self._header_height,
+        )
+        self._previous_element._previous_layout_box = (
+            self._previous_element._previous_paint_box
+        )
+
     def switch_to_next_page(self) -> "PageLayout":  # type: ignore[name-defined]
         """
         This function forces this PageLayout to switch to the nex Page

borb/pdf/canvas/layout/page_layout/single_column_layout_with_overflow.py

@@ -10,7 +10,7 @@
 import typing
 from decimal import Decimal
 
-from borb.pdf import SingleColumnLayout, Page
+from borb.pdf import SingleColumnLayout
 from borb.pdf.canvas.geometry.rectangle import Rectangle
 from borb.pdf.canvas.layout.layout_element import LayoutElement
 
@@ -24,7 +24,7 @@ class SingleColumnLayoutWithOverflow(SingleColumnLayout):
 
     def __init__(
         self,
-        page: Page,
+        page: "Page",
         horizontal_margin: typing.Optional[Decimal] = None,
         vertical_margin: typing.Optional[Decimal] = None,
     ):

borb/pdf/canvas/layout/shape/connected_shape.py

@@ -215,4 +215,4 @@ def _paint_content_box(self, page: Page, available_space: Rectangle) -> None:
         content += " Q"
 
         # append to page
-        page._append_to_content_stream(content)
+        page.append_to_content_stream(content)

borb/pdf/canvas/layout/shape/disconnected_shape.py

@@ -194,4 +194,4 @@ def _paint_content_box(self, page: Page, available_space: Rectangle) -> None:
         content += " S Q"
 
         # append to page
-        page._append_to_content_stream(content)
+        page.append_to_content_stream(content)