def test_spanning_single_paragraph(self):
document_xml = '''
<p>
<r><t>Link: </t></r>
<r>
<fldChar fldCharType="begin"/>
</r>
<r>
<instrText> HYPERLINK "http://www.google.com/"</instrText>
</r>
<r>
<fldChar fldCharType="separate"/>
</r>
<r>
<t>AAA</t>
</r>
<r>
<fldChar fldCharType="end"/>
</r>
<r><t>.</t></r>
</p>
'''
document = WordprocessingDocumentFactory()
document.add(MainDocumentPart, document_xml)
expected_html = '<p>Link: <a href="http://www.google.com/">AAA</a>.</p>'
self.assert_document_generates_html(document, expected_html)
def test_lowerLetter_numbering_format_is_handled(self):
num_id = '2'
numbering_xml = '''
<num numId="{num_id}">
<abstractNumId val="1"/>
</num>
<abstractNum abstractNumId="1">
<lvl ilvl="0">
<numFmt val="lowerLetter"/>
</lvl>
</abstractNum>
'''.format(num_id=num_id)
document_xml = '''
<p>
<pPr>
<numPr>
<ilvl val="0" />
<numId val="{num_id}" />
</numPr>
</pPr>
<r><t>AAA</t></r>
</p>
'''.format(num_id=num_id)
document = WordprocessingDocumentFactory()
document.add(NumberingDefinitionsPart, numbering_xml)
document.add(MainDocumentPart, document_xml)
expected_html = '''
<ol class="pydocx-list-style-type-lowerLetter">
<li>AAA</li>
</ol>
'''
self.assert_document_generates_html(document, expected_html)
def test_missing_fld_char_end(self):
# According to 17.16.18, "If a complex field is not closed before the
# end of a document story, then no field shall be generated and each
# individual run shall be processed as if the field characters did not
# exist"
document_xml = '''
<p>
<r><t>Link: </t></r>
<r>
<fldChar fldCharType="begin"/>
</r>
<r>
<instrText> HYPERLINK "http://www.google.com/"</instrText>
</r>
<r>
<fldChar fldCharType="separate"/>
</r>
<r>
<t>AAA</t>
</r>
<r><t>.</t></r>
</p>
'''
document = WordprocessingDocumentFactory()
document.add(MainDocumentPart, document_xml)
expected_html = '<p>Link: AAA.</p>'
self.assert_document_generates_html(document, expected_html)
def test_with_line_break(self):
document_xml = """
<p>
<hyperlink id="foobar">
<r>
<t>li</t>
<br />
<t>nk</t>
</r>
</hyperlink>
<r>
<t>.</t>
</r>
</p>
"""
document = WordprocessingDocumentFactory()
document_rels = document.relationship_format.format(
id="foobar", type="foo/hyperlink", target="http://google.com", target_mode="External"
)
document.add(MainDocumentPart, document_xml, document_rels)
expected_html = '<p><a href="http://google.com">li<br />nk</a>.</p>'
self.assert_document_generates_html(document, expected_html)
def test_one_row_one_cell_with_whitespace_after_other_paragraph(self):
document_xml = '''
<tbl>
<tr>
<tc>
<p>
<r><t>Foo</t></r>
</p>
<p>
<r><t> </t></r>
</p>
</tc>
</tr>
</tbl>
'''
document = WordprocessingDocumentFactory()
document.add(MainDocumentPart, document_xml)
expected_html = '''
<table border="1">
<tr>
<td>Foo</td>
</tr>
</table>
'''
self.assert_document_generates_html(document, expected_html)
def test_character_stylings_are_ignored(self):
# Even though the heading1 style has bold enabled, it's being ignored
# because the style is for a header
style_xml = '''
<style styleId="heading1" type="paragraph">
<name val="Heading 1"/>
<rPr>
<b val="on"/>
</rPr>
</style>
'''
document_xml = '''
<p>
<pPr>
<pStyle val="heading1"/>
</pPr>
<r>
<t>aaa</t>
</r>
</p>
'''
document = WordprocessingDocumentFactory()
document.add(StyleDefinitionsPart, style_xml)
document.add(MainDocumentPart, document_xml)
expected_html = '''
<h1>aaa</h1>
'''
self.assert_document_generates_html(document, expected_html)
def test_multiple_runs(self):
document_xml = '''
<p>
<hyperlink id="foobar">
<r>
<t>l</t>
<t>i</t>
<t>n</t>
<t>k</t>
</r>
</hyperlink>
<r>
<t>.</t>
</r>
</p>
'''
document = WordprocessingDocumentFactory()
document_rels = document.relationship_format.format(
id='foobar',
type='foo/hyperlink',
target='http://google.com',
target_mode='External',
)
document.add(MainDocumentPart, document_xml, document_rels)
expected_html = '<p><a href="http://google.com">link</a>.</p>'
self.assert_document_generates_html(document, expected_html)
def test_textbox_with_content(self):
document_xml = '''
<p>
<r>
<pict>
<shape>
<textbox>
<txbxContent>
<p>
<r>
<t>AAA</t>
</r>
</p>
</txbxContent>
</textbox>
</shape>
</pict>
</r>
</p>
'''
document = WordprocessingDocumentFactory()
document.add(MainDocumentPart, document_xml)
expected_html = '''
<p>
<p>
AAA
</p>
</p>
'''
self.assert_document_generates_html(document, expected_html)
def test_unsupported_instr_content_is_not_ignored(self):
document_xml = '''
<p>
<r><t>AAA</t></r>
<r>
<fldChar fldCharType="begin"/>
</r>
<r>
<instrText> FOOBAR baz</instrText>
</r>
<r>
<fldChar fldCharType="separate"/>
</r>
<r>
<t>BBB</t>
</r>
<r>
<fldChar fldCharType="end"/>
</r>
<r><t>CCC</t></r>
</p>
'''
document = WordprocessingDocumentFactory()
document.add(MainDocumentPart, document_xml)
expected_html = '<p>AAABBBCCC</p>'
self.assert_document_generates_html(document, expected_html)
def test_entity_blowup(self):
try:
import defusedxml
except ImportError:
defusedxml = None
if defusedxml is None:
raise SkipTest('This test case only applies when using defusedxml')
document_xml = '''
<p>
<r>
<t>&a;</t>
</r>
</p>
'''
xml_header = '''<?xml version="1.0" encoding="UTF-8"?>
<!DOCTYPE xml [
<!ENTITY a "123">
]>
'''
document = WordprocessingDocumentFactory(xml_header=xml_header)
document.add(MainDocumentPart, document_xml)
expected_html = '<p>123</p>'
try:
self.assert_document_generates_html(document, expected_html)
raise AssertionError(
'Expected "EntitiesForbidden" exception did not occur',
)
except defusedxml.EntitiesForbidden:
pass
def test_invalid_vals_do_not_create_strong(self):
vals = [
'foo',
'bar',
]
paragraph_template = '''
<p>
<r>
<rPr>
<b val="%s" />
</rPr>
<t>foo</t>
</r>
</p>
'''
document_xml = ''.join(
paragraph_template % val
for val in vals
)
document = WordprocessingDocumentFactory()
document.add(MainDocumentPart, document_xml)
expected_html = '''
<p>foo</p>
<p>foo</p>
'''
self.assert_document_generates_html(document, expected_html)
def test_with_bookmark_option(self):
document_xml = '''
<p>
<r><t>Link: </t></r>
<r>
<fldChar fldCharType="begin"/>
</r>
<r>
<instrText> HYPERLINK "http://www.google.com/" \\l awesome</instrText>
</r>
<r>
<fldChar fldCharType="separate"/>
</r>
<r>
<t>AAA</t>
</r>
<r>
<fldChar fldCharType="end"/>
</r>
<r><t>.</t></r>
</p>
'''
document = WordprocessingDocumentFactory()
document.add(MainDocumentPart, document_xml)
expected_html = '<p>Link: <a href="http://www.google.com/#awesome">AAA</a>.</p>'
self.assert_document_generates_html(document, expected_html)
def test_no_sup_because_position_is_zero(self):
document_xml = '''
<p>
<pPr>
<pStyle val="faked_superscript"/>
</pPr>
<r>
<t>n</t>
</r>
<r>
<rPr>
<position val="0"/>
<sz val="19"/>
</rPr>
<t>th</t>
</r>
</p>
'''
document = WordprocessingDocumentFactory()
document.add(StyleDefinitionsPart, self.style_xml)
document.add(MainDocumentPart, document_xml)
expected_html = '<p>nth</p>'
self.assert_document_generates_html(document, expected_html)
def test_no_sup_detected_for_size_set_in_rPrChange(self):
# Test for issue #116
document_xml = '''
<p>
<pPr>
<pStyle val="faked_superscript"/>
</pPr>
<r>
<t>n</t>
</r>
<r>
<rPr>
<position val="8"/>
<rPrChange id="1" author="john" date="2015-02-10T14:33:00Z">
<sz val="19"/>
</rPrChange>
</rPr>
<t>th</t>
</r>
</p>
'''
document = WordprocessingDocumentFactory()
document.add(StyleDefinitionsPart, self.style_xml)
document.add(MainDocumentPart, document_xml)
expected_html = '<p>nth</p>'
self.assert_document_generates_html(document, expected_html)
def test_cell_with_character_styles_applied(self):
document_xml = '''
<tbl>
<tr>
<tc>
<p>
<r>
<rPr>
<b />
<i />
</rPr>
<t>Foo</t>
</r>
</p>
</tc>
</tr>
</tbl>
'''
document = WordprocessingDocumentFactory()
document.add(MainDocumentPart, document_xml)
expected_html = '''
<table border="1">
<tr>
<td><em><strong>Foo</strong></em></td>
</tr>
</table>
'''
self.assert_document_generates_html(document, expected_html)
def test_instr_missing_target(self):
document_xml = '''
<p>
<r><t>Link: </t></r>
<r>
<fldChar fldCharType="begin"/>
</r>
<r>
<instrText> HYPERLINK </instrText>
</r>
<r>
<fldChar fldCharType="separate"/>
</r>
<r>
<t>AAA</t>
</r>
<r>
<fldChar fldCharType="end"/>
</r>
<r><t>.</t></r>
</p>
'''
document = WordprocessingDocumentFactory()
document.add(MainDocumentPart, document_xml)
expected_html = '<p>Link: AAA.</p>'
self.assert_document_generates_html(document, expected_html)
def test_sub_detected_pStyle_has_smaller_size_and_negative_position(self):
document_xml = '''
<p>
<pPr>
<pStyle val="faked_subscript"/>
</pPr>
<r>
<t>H</t>
</r>
<r>
<rPr>
<position val="-8"/>
<sz val="19"/>
</rPr>
<t>2</t>
</r>
<r>
<t>O</t>
</r>
</p>
'''
document = WordprocessingDocumentFactory()
document.add(StyleDefinitionsPart, self.style_xml)
document.add(MainDocumentPart, document_xml)
expected_html = '<p>H<sub>2</sub>O</p>'
self.assert_document_generates_html(document, expected_html)
def test_root_level_decimal_list_not_converted_to_heading(self):
document_xml = ''.join([
self.list_item.format(
content='AAA',
num_id=1,
level=0,
),
])
numbering_xml = '''
<num numId="1">
<abstractNumId val="1"/>
</num>
<abstractNum abstractNumId="1">
<lvl ilvl="0">
<numFmt val="decimal"/>
</lvl>
</abstractNum>
'''
document = WordprocessingDocumentFactory()
document.add(NumberingDefinitionsPart, numbering_xml)
document.add(MainDocumentPart, document_xml)
expected_html = '''
<ol class="pydocx-list-style-type-decimal">
<li>AAA</li>
</ol>
'''
self.assert_document_generates_html(document, expected_html)
def test_no_sub_detected_because_local_size_larger_than_pStyle_size(self):
document_xml = '''
<p>
<pPr>
<pStyle val="faked_subscript"/>
</pPr>
<r>
<t>H</t>
</r>
<r>
<rPr>
<position val="-8"/>
<sz val="30"/>
</rPr>
<t>2</t>
</r>
<r>
<t>O</t>
</r>
</p>
'''
document = WordprocessingDocumentFactory()
document.add(StyleDefinitionsPart, self.style_xml)
document.add(MainDocumentPart, document_xml)
expected_html = '<p>H2O</p>'
self.assert_document_generates_html(document, expected_html)
def test_root_level_upperRoman_list_not_converted_to_heading(self):
document_xml = ''.join([
self.list_item.format(
content='AAA',
num_id=1,
level=0,
),
])
numbering_xml = '''
<num numId="1">
<abstractNumId val="1"/>
</num>
<abstractNum abstractNumId="1">
<lvl ilvl="0">
<numFmt val="upperRoman"/>
</lvl>
</abstractNum>
'''
document = WordprocessingDocumentFactory()
document.add(NumberingDefinitionsPart, numbering_xml)
document.add(MainDocumentPart, document_xml)
expected_html = '<h2>AAA</h2>'
self.assert_document_generates_html(document, expected_html)
def test_one_row_one_cell_multiple_paragraphs(self):
document_xml = '''
<tbl>
<tr>
<tc>
<p>
<r>
<t>Foo</t>
</r>
</p>
<p>
<r>
<t>Bar</t>
</r>
</p>
</tc>
</tr>
</tbl>
'''
document = WordprocessingDocumentFactory()
document.add(MainDocumentPart, document_xml)
expected_html = '''
<table border="1">
<tr>
<td>Foo<br />Bar</td>
</tr>
</table>
'''
self.assert_document_generates_html(document, expected_html)
def test_blip_embed_refers_to_undefined_image_relationship(self):
# Ensure that if a blip embed refers to an undefined image
# relationshipp, the image rendering is skipped
document_xml = '''
<p>
<r>
<t>Foo</t>
<drawing>
<anchor>
<graphic>
<graphicData>
<pic>
<blipFill>
<blip embed="foobar" />
</blipFill>
</pic>
</graphicData>
</graphic>
</anchor>
</drawing>
<t>Bar</t>
</r>
</p>
'''
document = WordprocessingDocumentFactory()
document.add(MainDocumentPart, document_xml)
expected_html = '<p>FooBar</p>'
self.assert_document_generates_html(document, expected_html)
def test_sup_detected_pStyle_has_larger_size_and_positive_position(self):
document_xml = '''
<p>
<pPr>
<pStyle val="faked_superscript"/>
</pPr>
<r>
<t>n</t>
</r>
<r>
<rPr>
<position val="8"/>
<sz val="19"/>
</rPr>
<t>th</t>
</r>
</p>
'''
document = WordprocessingDocumentFactory()
document.add(StyleDefinitionsPart, self.style_xml)
document.add(MainDocumentPart, document_xml)
expected_html = '<p>n<sup>th</sup></p>'
self.assert_document_generates_html(document, expected_html)
def test_multiple_runs(self):
document_xml = '''
<p>
<fldSimple instr="HYPERLINK http://www.google.com">
<r>
<rPr>
<b />
</rPr>
<t>AAA</t>
</r>
<r>
<rPr>
<i />
</rPr>
<t>BBB</t>
</r>
</fldSimple>
</p>
'''
document = WordprocessingDocumentFactory()
document.add(MainDocumentPart, document_xml)
expected_html = '''
<p>
<a href="http://www.google.com">
<strong>AAA</strong>
<em>BBB</em>
</a>
</p>
'''
self.assert_document_generates_html(document, expected_html)
def test_styles_are_ignored(self):
style_xml = '''
<style styleId="heading1" type="paragraph">
<name val="Heading 1"/>
<rPr>
<b val="on"/>
<caps val="on"/>
<smallCaps val="on"/>
<strike val="on"/>
<dstrike val="on"/>
</rPr>
</style>
'''
document_xml = '''
<p>
<pPr>
<pStyle val="heading1"/>
</pPr>
<fldSimple instr="FOO bar">
<r>
<t>AAA</t>
</r>
</fldSimple>
</p>
'''
document = WordprocessingDocumentFactory()
document.add(StyleDefinitionsPart, style_xml)
document.add(MainDocumentPart, document_xml)
expected_html = '''
<h1>AAA</h1>
'''
self.assert_document_generates_html(document, expected_html)
def test_spanning_multiple_paragraphs(self):
document_xml = '''
<p>
<r><t>Link: </t></r>
</p>
<p>
<r>
<fldChar fldCharType="begin"/>
</r>
<r>
<instrText> HYPERLINK "http://www.google.com/"</instrText>
</r>
</p>
<p>
<r>
<fldChar fldCharType="separate"/>
</r>
<r>
<t>AAA</t>
</r>
<r>
<t>BBB</t>
</r>
</p>
<p><r><t>CCC</t></r></p>
<p>
<r><t>DDD</t></r>
<r>
<fldChar fldCharType="end"/>
</r>
<r><t>.</t></r>
</p>
'''
document = WordprocessingDocumentFactory()
document.add(MainDocumentPart, document_xml)
expected_html = '''
<p>Link: </p>
<p><a href="http://www.google.com/">AAABBB</a></p>
<p><a href="http://www.google.com/">CCC</a></p>
<p><a href="http://www.google.com/">DDD</a>.</p>
'''
self.assert_document_generates_html(document, expected_html)
def test_with_bookmark_option(self):
document_xml = '''
<p>
<fldSimple instr="HYPERLINK http://www.google.com \\l awesome">
<r>
<t>AAA</t>
</r>
</fldSimple>
</p>
'''
document = WordprocessingDocumentFactory()
document.add(MainDocumentPart, document_xml)
expected_html = '''
<p>
<a href="http://www.google.com#awesome">AAA</a>
</p>
'''
self.assert_document_generates_html(document, expected_html)
def test_undefined_relationship(self):
document_xml = '''
<p>
<hyperlink id="foobar">
<r>
<t>link</t>
</r>
</hyperlink>
<r>
<t>.</t>
</r>
</p>
'''
document = WordprocessingDocumentFactory()
document.add(MainDocumentPart, document_xml)
expected_html = '<p>link.</p>'
self.assert_document_generates_html(document, expected_html)
def test_no_link_text(self):
document_xml = '''
<p>
<hyperlink id="foobar" />
</p>
'''
document = WordprocessingDocumentFactory()
document_rels = document.relationship_format.format(
id='foobar',
type='foo/hyperlink',
target='http://google.com',
target_mode='External',
)
document.add(MainDocumentPart, document_xml, document_rels)
expected_html = ''
self.assert_document_generates_html(document, expected_html)
def test_textbox_with_content_outside_of_textbox(self):
document_xml = '''
<p>
<r><t>AAA</t></r>
<r>
<t>BBB</t>
<AlternateContent>
<Fallback>
<pict>
<shape>
<textbox>
<txbxContent>
<p>
<r>
<t>CCC</t>
</r>
</p>
</txbxContent>
</textbox>
</shape>
</pict>
</Fallback>
</AlternateContent>
<t>DDD</t>
</r>
<r><t>EEE</t></r>
</p>
'''
document = WordprocessingDocumentFactory()
document.add(MainDocumentPart, document_xml)
expected_html = '''
<p>
AAABBB
<p>
CCC
</p>
DDDEEE
</p>
'''
self.assert_document_generates_html(document, expected_html)
def test_fallback_is_in_root(self):
document_xml = '''
<AlternateContent>
<Fallback>
<p>
<r>
<t>AAA</t>
</r>
</p>
</Fallback>
</AlternateContent>
'''
document = WordprocessingDocumentFactory()
document.add(MainDocumentPart, document_xml)
expected_html = '''
<p>AAA</p>
'''
self.assert_document_generates_html(document, expected_html)
def test_after_text_run(self):
document_xml = '''
<p>
<r>
<t>aaa</t>
<br type="page"/>
</r>
</p>
<p>
<r>
<t>bbb</t>
</r>
</p>
'''
document = WordprocessingDocumentFactory()
document.add(MainDocumentPart, document_xml)
expected_html = '<p>aaa<hr /></p><p>bbb</p>'
self.assert_document_generates_html(document, expected_html)
def test_footnotes_property_is_a_Footnotes_instance(self):
factory = WordprocessingDocumentFactory()
factory.add(FootnotesPart, '')
factory.add(MainDocumentPart, '')
package = create_zip_archive(factory.to_zip_dict())
# TODO the interface for creating a new WordprocessingDocument sucks
document = WordprocessingDocument(path=package)
part = document.main_document_part.footnotes_part
assert isinstance(part.footnotes, Footnotes), part.footnotes
def test_numbering_property_is_a_Numbering_instance(self):
factory = WordprocessingDocumentFactory()
factory.add(NumberingDefinitionsPart, '')
factory.add(MainDocumentPart, '')
package = create_zip_archive(factory.to_zip_dict())
# TODO the interface for creating a new WordprocessingDocument sucks
document = WordprocessingDocument(path=package)
part = document.main_document_part.numbering_definitions_part
assert isinstance(part.numbering, Numbering), part.numbering
def test_styles_are_ignored(self):
style_xml = '''
<style styleId="heading1" type="paragraph">
<name val="Heading 1"/>
<rPr>
<b val="on"/>
<caps val="on"/>
<smallCaps val="on"/>
<strike val="on"/>
<dstrike val="on"/>
</rPr>
</style>
'''
document_xml = '''
<p>
<pPr>
<pStyle val="heading1"/>
</pPr>
<fldSimple instr="FOO bar">
<r>
<t>AAA</t>
</r>
</fldSimple>
</p>
'''
document = WordprocessingDocumentFactory()
document.add(StyleDefinitionsPart, style_xml)
document.add(MainDocumentPart, document_xml)
expected_html = '''
<h1>AAA</h1>
'''
self.assert_document_generates_html(document, expected_html)
def test_no_sup_detected_for_size_set_in_rPrChange(self):
# Test for issue #116
document_xml = '''
<p>
<pPr>
<pStyle val="faked_superscript"/>
</pPr>
<r>
<t>n</t>
</r>
<r>
<rPr>
<position val="8"/>
<rPrChange id="1" author="john" date="2015-02-10T14:33:00Z">
<sz val="19"/>
</rPrChange>
</rPr>
<t>th</t>
</r>
</p>
'''
document = WordprocessingDocumentFactory()
document.add(StyleDefinitionsPart, self.style_xml)
document.add(MainDocumentPart, document_xml)
expected_html = '<p>nth</p>'
self.assert_document_generates_html(document, expected_html)
def test_run_paragraph_mark_style_is_not_used_as_run_style(self):
style_xml = '''
<style styleId="foo" type="paragraph">
<pPr>
<rPr>
<b val="on"/>
</rPr>
</pPr>
</style>
'''
document_xml = '''
<p>
<pPr>
<pStyle val="foo"/>
</pPr>
<r>
<t>aaa</t>
</r>
</p>
'''
document = WordprocessingDocumentFactory()
document.add(StyleDefinitionsPart, style_xml)
document.add(MainDocumentPart, document_xml)
expected_html = '<p>aaa</p>'
self.assert_document_generates_html(document, expected_html)
def test_character_style_referenced_by_paragraph_is_ignored(self):
style_xml = '''
<style styleId="foo" type="character">
<rPr>
<b val="on"/>
</rPr>
</style>
'''
document_xml = '''
<p>
<pPr>
<pStyle val="foo"/>
</pPr>
<r>
<t>aaa</t>
</r>
</p>
'''
document = WordprocessingDocumentFactory()
document.add(StyleDefinitionsPart, style_xml)
document.add(MainDocumentPart, document_xml)
expected_html = '<p>aaa</p>'
self.assert_document_generates_html(document, expected_html)
def test_heading_with_bookmark(self):
document_xml = '''
<p>
<pPr>
<pStyle val="heading1"/>
</pPr>
<bookmarkStart name="testing"/>
<bookmarkEnd/>
<r>
<t>aaa</t>
</r>
</p>
'''
style_xml = '''
<style styleId="heading1" type="paragraph">
<name val="Heading 1"/>
</style>
'''
document = WordprocessingDocumentFactory()
document.add(StyleDefinitionsPart, style_xml)
document.add(MainDocumentPart, document_xml)
expected_html = '<h1 id="testing">aaa</h1>'
self.assert_document_generates_html(document, expected_html)
def test_global_run_paragraph_and_character_styles(self):
style_xml = '''
<style styleId="foo" type="paragraph">
<rPr>
<b val="on"/>
</rPr>
</style>
<style styleId="bar" type="character">
<rPr>
<i val="on"/>
</rPr>
</style>
'''
document_xml = '''
<p>
<pPr>
<pStyle val="foo"/>
</pPr>
<r>
<rPr>
<rStyle val="bar"/>
</rPr>
<t>aaa</t>
</r>
</p>
'''
document = WordprocessingDocumentFactory()
document.add(StyleDefinitionsPart, style_xml)
document.add(MainDocumentPart, document_xml)
expected_html = '<p><em><strong>aaa</strong></em></p>'
self.assert_document_generates_html(document, expected_html)
def test_sup_detected_pStyle_has_larger_size_and_positive_position(self):
document_xml = '''
<p>
<pPr>
<pStyle val="faked_superscript"/>
</pPr>
<r>
<t>n</t>
</r>
<r>
<rPr>
<position val="8"/>
<sz val="19"/>
</rPr>
<t>th</t>
</r>
</p>
'''
document = WordprocessingDocumentFactory()
document.add(StyleDefinitionsPart, self.style_xml)
document.add(MainDocumentPart, document_xml)
expected_html = '<p>n<sup>th</sup></p>'
self.assert_document_generates_html(document, expected_html)
def test_no_sup_because_position_is_zero(self):
document_xml = '''
<p>
<pPr>
<pStyle val="faked_superscript"/>
</pPr>
<r>
<t>n</t>
</r>
<r>
<rPr>
<position val="0"/>
<sz val="19"/>
</rPr>
<t>th</t>
</r>
</p>
'''
document = WordprocessingDocumentFactory()
document.add(StyleDefinitionsPart, self.style_xml)
document.add(MainDocumentPart, document_xml)
expected_html = '<p>nth</p>'
self.assert_document_generates_html(document, expected_html)
def test_sub_detected_pStyle_has_smaller_size_and_negative_position(self):
document_xml = '''
<p>
<pPr>
<pStyle val="faked_subscript"/>
</pPr>
<r>
<t>H</t>
</r>
<r>
<rPr>
<position val="-8"/>
<sz val="19"/>
</rPr>
<t>2</t>
</r>
<r>
<t>O</t>
</r>
</p>
'''
document = WordprocessingDocumentFactory()
document.add(StyleDefinitionsPart, self.style_xml)
document.add(MainDocumentPart, document_xml)
expected_html = '<p>H<sub>2</sub>O</p>'
self.assert_document_generates_html(document, expected_html)
def test_no_sub_detected_because_local_size_larger_than_pStyle_size(self):
document_xml = '''
<p>
<pPr>
<pStyle val="faked_subscript"/>
</pPr>
<r>
<t>H</t>
</r>
<r>
<rPr>
<position val="-8"/>
<sz val="30"/>
</rPr>
<t>2</t>
</r>
<r>
<t>O</t>
</r>
</p>
'''
document = WordprocessingDocumentFactory()
document.add(StyleDefinitionsPart, self.style_xml)
document.add(MainDocumentPart, document_xml)
expected_html = '<p>H2O</p>'
self.assert_document_generates_html(document, expected_html)
def test_style_chain_ends_when_loop_is_detected(self):
style_xml = '''
<style styleId="one">
<basedOn val="three"/>
<rPr>
<b val="on"/>
</rPr>
</style>
<style styleId="two">
<basedOn val="one"/>
</style>
<style styleId="three">
<basedOn val="two"/>
</style>
'''
document_xml = '''
<p>
<pPr>
<pStyle val="three"/>
</pPr>
<r>
<t>aaa</t>
</r>
</p>
'''
document = WordprocessingDocumentFactory()
document.add(StyleDefinitionsPart, style_xml)
document.add(MainDocumentPart, document_xml)
expected_html = '<p><strong>aaa</strong></p>'
self.assert_document_generates_html(document, expected_html)
def test_basedon_ignored_for_character_based_on_paragraph(self):
# character styles may only be based on other character styles
# otherwise, the based on specification should be ignored
style_xml = '''
<style styleId="one" type="paragraph">
<rPr>
<b val="on"/>
</rPr>
</style>
<style styleId="two" type="character">
<basedOn val="one"/>
<rPr>
<i val="on"/>
</rPr>
</style>
'''
document_xml = '''
<p>
<r>
<rPr>
<rStyle val="two"/>
</rPr>
<t>aaa</t>
</r>
</p>
'''
document = WordprocessingDocumentFactory()
document.add(StyleDefinitionsPart, style_xml)
document.add(MainDocumentPart, document_xml)
expected_html = '<p><em>aaa</em></p>'
self.assert_document_generates_html(document, expected_html)
def test_single_styled_whitespace_in_text_run_is_preserved(self):
document_xml = '''
<p>
<r>
<t>Foo</t>
</r>
<r>
<rPr>
<b />
</rPr>
<t> </t>
</r>
<r>
<t>Bar</t>
</r>
</p>
'''
document = WordprocessingDocumentFactory()
document.add(MainDocumentPart, document_xml)
expected_html = '<p>Foo Bar</p>'
self.assert_document_generates_html(document, expected_html)
def test_textbox_with_a_table(self):
document_xml = '''
<p>
<r>
<pict>
<shape>
<textbox>
<txbxContent>
<tbl>
<tr>
<tc>
<p>
<r>
<t>AAA</t>
</r>
</p>
</tc>
</tr>
</tbl>
</txbxContent>
</textbox>
</shape>
</pict>
</r>
</p>
'''
document = WordprocessingDocumentFactory()
document.add(MainDocumentPart, document_xml)
expected_html = '''
<table border="1">
<tr>
<td>AAA</td>
</tr>
</table>
'''
self.assert_document_generates_html(document, expected_html)
def test_each_heading_level(self):
style_template = '''
<style styleId="heading%s" type="paragraph">
<name val="Heading %s"/>
</style>
'''
style_xml = ''.join(
style_template % (i, i)
for i in range(1, 11)
)
paragraph_template = '''
<p>
<pPr>
<pStyle val="%s"/>
</pPr>
<r>
<t>%s</t>
</r>
</p>
'''
style_to_text = [
('heading1', 'aaa'),
('heading2', 'bbb'),
('heading3', 'ccc'),
('heading4', 'ddd'),
('heading5', 'eee'),
('heading6', 'fff'),
('heading7', 'ggg'),
('heading8', 'hhh'),
('heading9', 'iii'),
('heading10', 'jjj'),
]
document_xml = ''.join(
paragraph_template % entry
for entry in style_to_text
)
document = WordprocessingDocumentFactory()
document.add(StyleDefinitionsPart, style_xml)
document.add(MainDocumentPart, document_xml)
expected_html = '''
<h1>aaa</h1>
<h2>bbb</h2>
<h3>ccc</h3>
<h4>ddd</h4>
<h5>eee</h5>
<h6>fff</h6>
<h6>ggg</h6>
<h6>hhh</h6>
<h6>iii</h6>
<h6>jjj</h6>
'''
self.assert_document_generates_html(document, expected_html)
def test_single_run(self):
document_xml = '''
<p>
<fldSimple instr="HYPERLINK http://www.google.com">
<r>
<rPr>
<b />
</rPr>
<t>AAA</t>
</r>
</fldSimple>
</p>
'''
document = WordprocessingDocumentFactory()
document.add(MainDocumentPart, document_xml)
expected_html = '''
<p>
<a href="http://www.google.com">
<strong>AAA</strong>
</a>
</p>
'''
self.assert_document_generates_html(document, expected_html)
def test_fallback_is_only_text(self):
document_xml = '''
<p>
<r><t>AAA</t></r>
<r>
<t>BBB</t>
<AlternateContent>
<Fallback>
<t>CCC</t>
</Fallback>
</AlternateContent>
<t>DDD</t>
</r>
<r><t>EEE</t></r>
</p>
'''
document = WordprocessingDocumentFactory()
document.add(MainDocumentPart, document_xml)
expected_html = '''
<p>AAABBBCCCDDDEEE</p>
'''
self.assert_document_generates_html(document, expected_html)
def test_single_list_lvl_with_heading_is_converted_to_list_strong(self):
style_xml = '''
<style styleId="heading1" type="paragraph">
<name val="Heading 1"/>
</style>
'''
numbering_xml = '''
<num numId="1">
<abstractNumId val="1"/>
</num>
<abstractNum abstractNumId="1">
<lvl ilvl="0">
<numFmt val="decimal"/>
</lvl>
</abstractNum>
'''
document_xml = '''
<p>
<pPr>
<pStyle val="heading1"/>
<numPr>
<ilvl val="0" />
<numId val="1" />
</numPr>
</pPr>
<r>
<t>foo</t>
</r>
</p>
'''
document = WordprocessingDocumentFactory()
document.add(StyleDefinitionsPart, style_xml)
document.add(NumberingDefinitionsPart, numbering_xml)
document.add(MainDocumentPart, document_xml)
expected_html = '''
<ol class="pydocx-list-style-type-decimal">
<li>
<strong>foo</strong>
</li>
</ol>
'''
self.assert_document_generates_html(document, expected_html)
def test_basic_footnote_with_styling(self):
document_xml = '''
<p>
<r>
<t>Foo</t>
</r>
<r>
<rPr>
<vertAlign val="superscript"/>
</rPr>
<footnoteReference id="abc"/>
</r>
</p>
<p>
<r>
<t>Footnotes should appear below this</t>
</r>
</p>
'''
footnotes_xml = '''
<footnote id="abc">
<p>
<r>
<rPr>
<b val="on"/>
</rPr>
<footnoteRef/>
<t>Bar</t>
</r>
</p>
</footnote>
'''
document = WordprocessingDocumentFactory()
document.add(FootnotesPart, footnotes_xml)
document.add(MainDocumentPart, document_xml)
expected_html = '''
<p>
Foo
<sup>
<a href="#footnote-abc" name="footnote-ref-abc">1</a>
</sup>
</p>
<p>Footnotes should appear below this</p>
<hr />
<ol class="pydocx-list-style-type-decimal">
<li><p><strong>
<a href="#footnote-ref-abc" name="footnote-abc">^</a>
Bar
</strong></p></li>
</ol>
'''
self.assert_document_generates_html(document, expected_html)
def test_styles_are_inherited(self):
style_xml = '''
<style styleId="one">
<rPr>
<b val="on"/>
</rPr>
</style>
<style styleId="two">
<basedOn val="one"/>
<rPr>
<i val="on"/>
</rPr>
</style>
<style styleId="three">
<basedOn val="two"/>
<rPr>
<u val="single"/>
</rPr>
</style>
'''
document_xml = '''
<p>
<pPr>
<pStyle val="three"/>
</pPr>
<r>
<t>aaa</t>
</r>
</p>
'''
document = WordprocessingDocumentFactory()
document.add(StyleDefinitionsPart, style_xml)
document.add(MainDocumentPart, document_xml)
expected_html = '''
<p>
<span class="pydocx-underline">
<em>
<strong>aaa</strong>
</em>
</span>
</p>
'''
self.assert_document_generates_html(document, expected_html)
def test_italic_preserved(self):
style_xml = '''
<style styleId="heading1" type="paragraph">
<name val="Heading 1"/>
<rPr>
<i val="on"/>
</rPr>
</style>
'''
document = WordprocessingDocumentFactory()
document.add(StyleDefinitionsPart, style_xml)
document.add(MainDocumentPart, self.document_xml)
expected_html = '''
<h1><em>aaa</em></h1>
'''
self.assert_document_generates_html(document, expected_html)
