diff --git a/CHANGELOG.rst b/CHANGELOG.rst
index 2db78527..6d3004d5 100644
--- a/CHANGELOG.rst
+++ b/CHANGELOG.rst
@@ -1,6 +1,8 @@
-**0.9.7**
+**dev**
- Text colors other than black and white are no longer ignored
+- Textboxes have been implemented. We no longer lose the content inside of
+ them.
**0.9.6**
diff --git a/pydocx/export/base.py b/pydocx/export/base.py
index d5008caa..baae919b 100644
--- a/pydocx/export/base.py
+++ b/pydocx/export/base.py
@@ -15,7 +15,7 @@
NumberingSpan,
NumberingSpanBuilder,
)
-from pydocx.openxml import wordprocessing, vml
+from pydocx.openxml import markup_compatibility, vml, wordprocessing
from pydocx.openxml.packaging import WordprocessingDocument
@@ -64,9 +64,13 @@ def __init__(self, path):
wordprocessing.SimpleField: self.export_simple_field,
vml.Shape: self.export_vml_shape,
vml.ImageData: self.export_vml_image_data,
+ vml.Textbox: self.export_textbox,
wordprocessing.EmbeddedObject: self.export_embedded_object,
NumberingSpan: self.export_numbering_span,
NumberingItem: self.export_numbering_item,
+ markup_compatibility.AlternateContent: self.export_markup_compatibility_alternate_content, # noqa
+ markup_compatibility.Fallback: self.export_markup_compatibility_fallback,
+ wordprocessing.TxBxContent: self.export_textbox_content,
}
self.field_type_to_export_func_map = {
'HYPERLINK': getattr(self, 'export_field_hyperlink', None),
@@ -535,3 +539,15 @@ def export_field_char(self, field_char):
def export_field_code(self, field_code):
pass
+
+ def export_textbox(self, textbox):
+ return self.yield_nested(textbox.children, self.export_node)
+
+ def export_textbox_content(self, textbox_content):
+ return self.yield_nested(textbox_content.children, self.export_node)
+
+ def export_markup_compatibility_alternate_content(self, alternate_content):
+ return self.yield_nested(alternate_content.children, self.export_node)
+
+ def export_markup_compatibility_fallback(self, fallback):
+ return self.yield_nested(fallback.children, self.export_node)
diff --git a/pydocx/models.py b/pydocx/models.py
index e8e70545..960f3963 100644
--- a/pydocx/models.py
+++ b/pydocx/models.py
@@ -5,6 +5,7 @@
unicode_literals,
)
+import importlib
import inspect
from collections import defaultdict
@@ -120,9 +121,24 @@ class ParkingLot(XmlModel):
def __init__(self, *types, **kwargs):
default = kwargs.pop('default', [])
super(XmlCollection, self).__init__(self, default=default)
- self.types = set(types)
+ self._types = types
self._name_to_type_map = None
+ @property
+ def types(self):
+ return set(self._set_types(*self._types))
+
+ def _set_types(self, *types):
+ base_path = 'pydocx.openxml.{0}'
+ for _type in types:
+ try:
+ path, klass = _type.rsplit('.', 1)
+ except AttributeError:
+ yield _type
+ else:
+ module = importlib.import_module(base_path.format(path))
+ yield getattr(module, klass)
+
@property
def name_to_type_map(self):
if self._name_to_type_map is None:
diff --git a/pydocx/openxml/markup_compatibility/__init__.py b/pydocx/openxml/markup_compatibility/__init__.py
new file mode 100644
index 00000000..14f8fbbe
--- /dev/null
+++ b/pydocx/openxml/markup_compatibility/__init__.py
@@ -0,0 +1,7 @@
+from pydocx.openxml.markup_compatibility.alternate_content import AlternateContent
+from pydocx.openxml.markup_compatibility.fallback import Fallback
+
+__all__ = [
+ 'AlternateContent',
+ 'Fallback',
+]
diff --git a/pydocx/openxml/markup_compatibility/alternate_content.py b/pydocx/openxml/markup_compatibility/alternate_content.py
new file mode 100644
index 00000000..78fb8b4e
--- /dev/null
+++ b/pydocx/openxml/markup_compatibility/alternate_content.py
@@ -0,0 +1,14 @@
+# coding: utf-8
+from __future__ import (
+ absolute_import,
+ print_function,
+ unicode_literals,
+)
+
+from pydocx.models import XmlModel, XmlCollection
+from pydocx.openxml.markup_compatibility.fallback import Fallback
+
+
+class AlternateContent(XmlModel):
+ XML_TAG = 'AlternateContent'
+ children = XmlCollection(Fallback)
diff --git a/pydocx/openxml/markup_compatibility/fallback.py b/pydocx/openxml/markup_compatibility/fallback.py
new file mode 100644
index 00000000..397091e4
--- /dev/null
+++ b/pydocx/openxml/markup_compatibility/fallback.py
@@ -0,0 +1,15 @@
+# coding: utf-8
+from __future__ import (
+ absolute_import,
+ print_function,
+ unicode_literals,
+)
+
+from pydocx.models import XmlModel, XmlCollection
+from pydocx.openxml.wordprocessing.picture import Picture
+
+
+class Fallback(XmlModel):
+ XML_TAG = 'Fallback'
+ # TODO #204: actually include all of the children defined in the spec.
+ children = XmlCollection(Picture)
diff --git a/pydocx/openxml/vml/__init__.py b/pydocx/openxml/vml/__init__.py
index f44a969f..a2547821 100644
--- a/pydocx/openxml/vml/__init__.py
+++ b/pydocx/openxml/vml/__init__.py
@@ -1,8 +1,10 @@
# coding: utf-8
from pydocx.openxml.vml.image_data import ImageData
from pydocx.openxml.vml.shape import Shape
+from pydocx.openxml.vml.textbox import Textbox
__all__ = [
'ImageData',
'Shape',
+ 'Textbox',
]
diff --git a/pydocx/openxml/vml/shape.py b/pydocx/openxml/vml/shape.py
index 457b6c67..c73ceeaa 100644
--- a/pydocx/openxml/vml/shape.py
+++ b/pydocx/openxml/vml/shape.py
@@ -13,8 +13,7 @@ class Shape(XmlModel):
XML_TAG = 'shape'
style = XmlAttribute()
- children = XmlCollection(ImageData)
-
+ children = XmlCollection(ImageData, 'vml.Textbox')
# TODO perhaps we could have a prepare_style, or clean_style convention?
def get_style(self):
diff --git a/pydocx/openxml/vml/textbox.py b/pydocx/openxml/vml/textbox.py
new file mode 100644
index 00000000..8cf196dd
--- /dev/null
+++ b/pydocx/openxml/vml/textbox.py
@@ -0,0 +1,16 @@
+# coding: utf-8
+from __future__ import (
+ absolute_import,
+ print_function,
+ unicode_literals,
+)
+
+from pydocx.models import XmlModel, XmlCollection
+
+
+class Textbox(XmlModel):
+ XML_TAG = 'textbox'
+
+ children = XmlCollection(
+ 'wordprocessing.TxBxContent',
+ )
diff --git a/pydocx/openxml/wordprocessing/__init__.py b/pydocx/openxml/wordprocessing/__init__.py
index 916f2cf8..2430064d 100644
--- a/pydocx/openxml/wordprocessing/__init__.py
+++ b/pydocx/openxml/wordprocessing/__init__.py
@@ -40,6 +40,7 @@
from pydocx.openxml.wordprocessing.table_cell_properties import TableCellProperties # noqa
from pydocx.openxml.wordprocessing.table_row import TableRow
from pydocx.openxml.wordprocessing.text import Text
+from pydocx.openxml.wordprocessing.textbox_content import TxBxContent
__all__ = [
'AbstractNum',
@@ -82,4 +83,5 @@
'TableCell',
'TableRow',
'Text',
+ 'TxBxContent',
]
diff --git a/pydocx/openxml/wordprocessing/deleted_run.py b/pydocx/openxml/wordprocessing/deleted_run.py
index dedf6917..3d55ff69 100644
--- a/pydocx/openxml/wordprocessing/deleted_run.py
+++ b/pydocx/openxml/wordprocessing/deleted_run.py
@@ -16,7 +16,6 @@ class DeletedRun(XmlModel):
children = XmlCollection(
Run,
SmartTagRun,
+ 'wordprocessing.DeletedRun',
# TODO Needs InsertedRun
)
-
-DeletedRun.children.types.add(DeletedRun)
diff --git a/pydocx/openxml/wordprocessing/inserted_run.py b/pydocx/openxml/wordprocessing/inserted_run.py
index cc19ec72..7fc0255c 100644
--- a/pydocx/openxml/wordprocessing/inserted_run.py
+++ b/pydocx/openxml/wordprocessing/inserted_run.py
@@ -16,7 +16,6 @@ class InsertedRun(XmlModel):
children = XmlCollection(
Run,
SmartTagRun,
+ 'wordprocessing.InsertedRun',
# TODO Needs DeletedRun
)
-
-InsertedRun.children.types.add(InsertedRun)
diff --git a/pydocx/openxml/wordprocessing/run.py b/pydocx/openxml/wordprocessing/run.py
index fcd9f6f0..2acdb944 100644
--- a/pydocx/openxml/wordprocessing/run.py
+++ b/pydocx/openxml/wordprocessing/run.py
@@ -20,6 +20,7 @@
from pydocx.openxml.wordprocessing.footnote_reference import FootnoteReference
from pydocx.openxml.wordprocessing.footnote_reference_mark import FootnoteReferenceMark
from pydocx.openxml.wordprocessing.embedded_object import EmbeddedObject
+from pydocx.openxml.markup_compatibility import AlternateContent
from pydocx.util.memoize import memoized
@@ -41,6 +42,7 @@ class Run(XmlModel):
FootnoteReferenceMark,
FieldChar,
FieldCode,
+ AlternateContent,
)
def get_style_chain_stack(self):
diff --git a/pydocx/openxml/wordprocessing/smart_tag_run.py b/pydocx/openxml/wordprocessing/smart_tag_run.py
index e56fd0fe..dfa906f9 100644
--- a/pydocx/openxml/wordprocessing/smart_tag_run.py
+++ b/pydocx/openxml/wordprocessing/smart_tag_run.py
@@ -14,6 +14,5 @@ class SmartTagRun(XmlModel):
children = XmlCollection(
Run,
+ 'wordprocessing.SmartTagRun',
)
-
-SmartTagRun.children.types.add(SmartTagRun)
diff --git a/pydocx/openxml/wordprocessing/table.py b/pydocx/openxml/wordprocessing/table.py
index 2fc85907..61314b29 100644
--- a/pydocx/openxml/wordprocessing/table.py
+++ b/pydocx/openxml/wordprocessing/table.py
@@ -8,7 +8,6 @@
from collections import defaultdict
from pydocx.models import XmlModel, XmlCollection
-from pydocx.openxml.wordprocessing.table_cell import TableCell
from pydocx.openxml.wordprocessing.table_row import TableRow
@@ -46,7 +45,3 @@ def calculate_table_cell_spans(self):
if active_rowspan_for_column:
cell_to_rowspan_count[active_rowspan_for_column] += 1 # noqa
return dict(cell_to_rowspan_count)
-
-
-# Python makes defining nested class hierarchies at the global level difficult
-TableCell.children.types.add(Table)
diff --git a/pydocx/openxml/wordprocessing/table_cell.py b/pydocx/openxml/wordprocessing/table_cell.py
index 7df2dc31..8a538e86 100644
--- a/pydocx/openxml/wordprocessing/table_cell.py
+++ b/pydocx/openxml/wordprocessing/table_cell.py
@@ -17,5 +17,5 @@ class TableCell(XmlModel):
children = XmlCollection(
Paragraph,
- # Table is added in wordprocessing.table
+ 'wordprocessing.Table',
)
diff --git a/pydocx/openxml/wordprocessing/textbox_content.py b/pydocx/openxml/wordprocessing/textbox_content.py
new file mode 100644
index 00000000..a6176804
--- /dev/null
+++ b/pydocx/openxml/wordprocessing/textbox_content.py
@@ -0,0 +1,15 @@
+# coding: utf-8
+from __future__ import (
+ absolute_import,
+ print_function,
+ unicode_literals,
+)
+
+from pydocx.models import XmlModel, XmlCollection
+
+
+class TxBxContent(XmlModel):
+ XML_TAG = 'txbxContent'
+ children = XmlCollection(
+ 'wordprocessing.Paragraph',
+ )
diff --git a/tests/export/html/test_markup_compatibility.py b/tests/export/html/test_markup_compatibility.py
new file mode 100644
index 00000000..b98c2192
--- /dev/null
+++ b/tests/export/html/test_markup_compatibility.py
@@ -0,0 +1,93 @@
+# coding: utf-8
+
+from __future__ import (
+ absolute_import,
+ print_function,
+ unicode_literals,
+)
+
+from pydocx.test import DocumentGeneratorTestCase
+from pydocx.test.utils import WordprocessingDocumentFactory
+from pydocx.openxml.packaging import MainDocumentPart
+
+
+class TableTestCase(DocumentGeneratorTestCase):
+ def test_textbox_with_content(self):
+ document_xml = '''
+
+
+
+
+
+
+
+
+
+
+ AAA
+
+
+
+
+
+
+
+
+
+
+ '''
+
+ document = WordprocessingDocumentFactory()
+ document.add(MainDocumentPart, document_xml)
+
+ expected_html = '''
+
+
+ AAA
+
+
+ '''
+ self.assert_document_generates_html(document, expected_html)
+
+ def test_textbox_with_content_outside_of_textbox(self):
+ document_xml = '''
+
+ AAA
+
+ BBB
+
+
+
+
+
+
+
+
+ CCC
+
+
+
+
+
+
+
+
+ DDD
+
+ EEE
+
+ '''
+
+ document = WordprocessingDocumentFactory()
+ document.add(MainDocumentPart, document_xml)
+
+ expected_html = '''
+
+ AAABBB
+
+ CCC
+
+ DDDEEE
+
+ '''
+ self.assert_document_generates_html(document, expected_html)
diff --git a/tests/export/html/test_textbox.py b/tests/export/html/test_textbox.py
new file mode 100644
index 00000000..6d7cc5da
--- /dev/null
+++ b/tests/export/html/test_textbox.py
@@ -0,0 +1,85 @@
+# coding: utf-8
+
+from __future__ import (
+ absolute_import,
+ print_function,
+ unicode_literals,
+)
+
+from pydocx.test import DocumentGeneratorTestCase
+from pydocx.test.utils import WordprocessingDocumentFactory
+from pydocx.openxml.packaging import MainDocumentPart
+
+
+class TableTestCase(DocumentGeneratorTestCase):
+ def test_textbox_with_content(self):
+ document_xml = '''
+
+
+
+
+
+
+
+
+ AAA
+
+
+
+
+
+
+
+
+ '''
+
+ document = WordprocessingDocumentFactory()
+ document.add(MainDocumentPart, document_xml)
+
+ expected_html = '''
+
+
+ AAA
+
+
+ '''
+ self.assert_document_generates_html(document, expected_html)
+
+ def test_textbox_with_content_outside_of_textbox(self):
+ document_xml = '''
+
+ AAA
+
+ BBB
+
+
+
+
+
+
+ CCC
+
+
+
+
+
+
+ DDD
+
+ EEE
+
+ '''
+
+ document = WordprocessingDocumentFactory()
+ document.add(MainDocumentPart, document_xml)
+
+ expected_html = '''
+
+ AAABBB
+
+ CCC
+
+ DDDEEE
+
+ '''
+ self.assert_document_generates_html(document, expected_html)
diff --git a/tests/export/test_docx.py b/tests/export/test_docx.py
index b0812d5f..8ebe3f47 100644
--- a/tests/export/test_docx.py
+++ b/tests/export/test_docx.py
@@ -24,16 +24,15 @@ def convert(path, *args, **kwargs):
class ConvertDocxToHtmlTestCase(DocXFixtureTestCaseFactory):
cases = (
- 'read_same_image_multiple_times',
'all_configured_styles',
+ 'export_from_googledocs',
+ 'external_image',
+ 'has_missing_image',
+ 'has_missing_image',
'has_title',
'inline_tags',
- 'has_missing_image',
'justification',
'list_in_table',
- 'external_image',
- 'export_from_googledocs',
- 'has_missing_image',
'lists_with_styles',
'missing_numbering',
'missing_style',
@@ -41,6 +40,8 @@ class ConvertDocxToHtmlTestCase(DocXFixtureTestCaseFactory):
'nested_table_rowspan',
'nested_tables',
'no_break_hyphen',
+ 'read_same_image_multiple_times',
+ 'rotate_image',
'shift_enter',
'simple',
'simple_lists',
@@ -49,10 +50,10 @@ class ConvertDocxToHtmlTestCase(DocXFixtureTestCaseFactory):
'styled_bolding',
'styled_color',
'table_col_row_span',
+ 'table_with_multi_rowspan',
'tables_in_lists',
+ 'textbox',
'track_changes_on',
- 'table_with_multi_rowspan',
- 'rotate_image'
)
@raises(MalformedDocxException)
diff --git a/tests/fixtures/textbox.docx b/tests/fixtures/textbox.docx
new file mode 100644
index 00000000..5ad956b2
Binary files /dev/null and b/tests/fixtures/textbox.docx differ
diff --git a/tests/fixtures/textbox.html b/tests/fixtures/textbox.html
new file mode 100644
index 00000000..2640dda2
--- /dev/null
+++ b/tests/fixtures/textbox.html
@@ -0,0 +1,5 @@
+
+
AAA
+BBB
+CCCDDD
+
diff --git a/tox.ini b/tox.ini
index 8c79be6f..253c446f 100644
--- a/tox.ini
+++ b/tox.ini
@@ -12,6 +12,7 @@ commands =
deps =
-rrequirements/testing.txt
defusedxml: defusedxml==0.4.1
+ py26: importlib
[testenv:docs]
commands =