def multiple_paragraphs_are_converted_to_multiple_paragraphs():
result = convert_document_element_to_html(
documents.document([
documents.paragraph(children=[_run_with_text("Hello")]),
documents.paragraph(children=[_run_with_text("there")]),
]))
assert_equal('<p>Hello</p><p>there</p>', result.value)
def multiple_paragraphs_are_converted_to_multiple_paragraphs():
result = convert_document_element_to_html(
documents.document([
documents.paragraph(children=[_run_with_text("Hello")]),
documents.paragraph(children=[_run_with_text("there")]),
])
)
assert_equal('<p>Hello</p><p>there</p>', result.value)
def bulleted_paragraphs_are_converted_using_matching_styles():
result = convert_document_element_to_html(
documents.paragraph(children=[_run_with_text("Hello")],
numbering=documents.numbering_level(
level_index=0, is_ordered=False)),
style_map=[_style_mapping("p:unordered-list(1) => ul > li:fresh")])
assert_equal('<ul><li>Hello</li></ul>', result.value)
def default_paragraph_style_is_used_if_no_matching_style_is_found():
result = convert_document_element_to_html(
documents.paragraph(style_id="TipsParagraph", children=[
_run_with_text("Tip")
]),
)
assert_equal('<p>Tip</p>', result.value)
def style_mappings_using_style_names_can_be_used_to_map_paragraphs():
result = convert_document_element_to_html(
documents.paragraph(style_id="TipsParagraph",
style_name="Tips Paragraph",
children=[_run_with_text("Tip")]),
style_map=[_style_mapping("p[style-name='Tips Paragraph'] => p.tip")])
assert_equal('<p class="tip">Tip</p>', result.value)
def main_document_is_found_using_package_relationships():
fileobj = _create_zip({
"word/document2.xml": textwrap.dedent("""\
<?xml version="1.0" encoding="utf-8" ?>
<w:document xmlns:w="http://schemas.openxmlformats.org/wordprocessingml/2006/main">
<w:body>
<w:p>
<w:r>
<w:t>Hello.</w:t>
</w:r>
</w:p>
</w:body>
</w:document>
"""),
"_rels/.rels": textwrap.dedent("""\
<?xml version="1.0" encoding="utf-8"?>
<Relationships xmlns="http://schemas.openxmlformats.org/package/2006/relationships">
<Relationship Type="http://schemas.openxmlformats.org/officeDocument/2006/relationships/officeDocument" Target="/word/document2.xml" Id="rId1"/>
</Relationships>
"""),
})
result = docx.read(fileobj=fileobj)
expected_document = documents.document([
documents.paragraph([
documents.run([
documents.text("Hello.")
])
])
])
assert_equal(expected_document, result.value)
def comment_references_are_linked_to_comment_after_main_body():
reference = documents.comment_reference("4")
comment = documents.comment(
comment_id="4",
body=[_paragraph_with_text("Who's there?")],
author_name="The Piemaker",
author_initials="TP",
)
document = documents.document(
[
documents.paragraph(
[_run_with_text("Knock knock"),
documents.run([reference])])
],
comments=[comment],
)
result = convert_document_element_to_html(
document,
id_prefix="doc-42-",
style_map=[_style_mapping("comment-reference => sup")],
)
expected_html = (
'<p>Knock knock<sup><a href="#doc-42-comment-4" id="doc-42-comment-ref-4">[TP1]</a></sup></p>'
+
'<dl><dt id="doc-42-comment-4">Comment [TP1]</dt><dd><p>Who\'s there? <a href="#doc-42-comment-ref-4">↑</a></p></dd></dl>'
)
assert_equal(expected_html, result.value)
def can_read_text_within_document(self):
element = _document_element_with_text("Hello!")
assert_equal(
documents.document([
documents.paragraph(
[documents.run([documents.Text("Hello!")])])
]), _read_and_get_document_xml_element(element))
def style_names_in_style_mappings_are_case_insensitive():
result = convert_document_element_to_html(
documents.paragraph(style_id="TipsParagraph",
style_name="Tips Paragraph",
children=[_run_with_text("Tip")]),
style_map=[_style_mapping("p[style-name='tips paragraph'] => p.tip")])
assert_equal('<p class="tip">Tip</p>', result.value)
def comment_references_are_linked_to_comment_after_main_body():
reference = documents.comment_reference("4")
comment = documents.comment(
comment_id="4",
body=[_paragraph_with_text("Who's there?")],
author_name="The Piemaker",
author_initials="TP",
)
document = documents.document(
[documents.paragraph([
_run_with_text("Knock knock"),
documents.run([reference])
])],
comments=[comment],
)
result = convert_document_element_to_html(
document,
id_prefix="doc-42-",
style_map=[
_style_mapping("comment-reference => sup")
],
)
expected_html = (
'<p>Knock knock<sup><a href="#doc-42-comment-4" id="doc-42-comment-ref-4">[TP1]</a></sup></p>' +
'<dl><dt id="doc-42-comment-4">Comment [TP1]</dt><dd><p>Who\'s there? <a href="#doc-42-comment-ref-4">↑</a></p></dd></dl>'
)
assert_equal(expected_html, result.value)
def warning_is_emitted_if_paragraph_style_is_unrecognised():
result = convert_document_element_to_html(
documents.paragraph(style_name="TipsParagraph", children=[
_run_with_text("Tip")
]),
)
assert_equal([results.warning("Unrecognised paragraph style: TipsParagraph")], result.messages)
def default_paragraph_style_is_used_if_no_matching_style_is_found():
result = convert_document_element_to_html(
documents.paragraph(style_id="TipsParagraph", children=[
_run_with_text("Tip")
]),
)
assert_equal('<p>Tip</p>', result.value)
def main_document_is_found_using_package_relationships():
fileobj = _create_zip({
"word/document2.xml":
textwrap.dedent("""\
<?xml version="1.0" encoding="utf-8" ?>
<w:document xmlns:w="http://schemas.openxmlformats.org/wordprocessingml/2006/main">
<w:body>
<w:p>
<w:r>
<w:t>Hello.</w:t>
</w:r>
</w:p>
</w:body>
</w:document>
"""),
"_rels/.rels":
textwrap.dedent("""\
<?xml version="1.0" encoding="utf-8"?>
<Relationships xmlns="http://schemas.openxmlformats.org/package/2006/relationships">
<Relationship Type="http://schemas.openxmlformats.org/officeDocument/2006/relationships/officeDocument" Target="/word/document2.xml" Id="rId1"/>
</Relationships>
"""),
})
result = docx.read(fileobj=fileobj)
expected_document = documents.document(
[documents.paragraph([documents.run([documents.text("Hello.")])])])
assert_equal(expected_document, result.value)
def bulleted_styles_dont_match_plain_paragraph():
result = convert_document_element_to_html(
documents.paragraph(children=[_run_with_text("Hello")]),
style_map=[
style_reader.read_style("p:unordered-list(1) => ul > li:fresh")
])
assert_equal('<p>Hello</p>', result.value)
def id_and_body_of_comment_is_read():
body = [xml_element("w:p")]
comments = create_comments_reader(body_xml.reader())(xml_element("w:comments", {}, [
xml_element("w:comment", {"w:id": "1"}, body),
]))
assert_equal(1, len(comments.value))
assert_equal(comments.value[0].body, [documents.paragraph(children=[])])
assert_equal("1", comments.value[0].comment_id)
def bulleted_paragraphs_are_converted_using_matching_styles():
result = convert_document_element_to_html(
documents.paragraph(
children=[_run_with_text("Hello")], numbering=documents.numbering_level(level_index=0, is_ordered=False)
),
style_map=[style_reader.read_style("p:unordered-list(1) => ul > li:fresh")],
)
assert_equal("<ul><li>Hello</li></ul>", result.value)
def paragraphs_are_terminated_with_newlines():
element = documents.paragraph(children=[
documents.Text("Hello "),
documents.Text("world."),
], )
result = extract_raw_text_from_element(element)
assert_equal("Hello world.\n\n", result)
def can_read_document_with_single_paragraph_with_single_run_of_text(self):
with open(test_path("single-paragraph.docx"), "rb") as fileobj:
result = docx.read(fileobj=fileobj)
expected_document = documents.document([
documents.paragraph([
documents.run([documents.text("Walking on imported air")])
])
])
assert_equal(expected_document, result.value)
def warning_is_emitted_if_paragraph_style_is_unrecognised():
result = convert_document_element_to_html(
documents.paragraph(style_id="Heading1",
style_name="Heading 1",
children=[_run_with_text("Tip")]), )
assert_equal([
results.warning(
"Unrecognised paragraph style: Heading 1 (Style ID: Heading1)")
], result.messages)
def id_and_body_of_comment_is_read():
body = [xml_element("w:p")]
comments = create_comments_reader(body_xml.reader())(xml_element(
"w:comments", {}, [
xml_element("w:comment", {"w:id": "1"}, body),
]))
assert_equal(1, len(comments.value))
assert_equal(comments.value[0].body, [documents.paragraph(children=[])])
assert_equal("1", comments.value[0].comment_id)
def style_mappings_using_style_names_can_be_used_to_map_paragraphs():
result = convert_document_element_to_html(
documents.paragraph(style_id="TipsParagraph", style_name="Tips Paragraph", children=[
_run_with_text("Tip")
]),
style_map=[
_style_mapping("p[style-name='Tips Paragraph'] => p.tip")
]
)
assert_equal('<p class="tip">Tip</p>', result.value)
def children_are_recursively_converted_to_text():
element = documents.document([
documents.paragraph(
[documents.text("Hello "),
documents.text("world.")], {})
])
result = extract_raw_text_from_element(element)
assert_equal("Hello world.\n\n", result)
def style_names_in_style_mappings_are_case_insensitive():
result = convert_document_element_to_html(
documents.paragraph(style_id="TipsParagraph", style_name="Tips Paragraph", children=[
_run_with_text("Tip")
]),
style_map=[
_style_mapping("p[style-name='tips paragraph'] => p.tip")
]
)
assert_equal('<p class="tip">Tip</p>', result.value)
def _assert_children_are_converted_normally(tag_name):
element = xml_element("w:p", {}, [
xml_element(tag_name, {}, [
xml_element("w:r")
])
])
assert_equal(
documents.paragraph([documents.run([])]),
_read_and_get_document_xml_element(element)
)
def _assert_children_are_converted_normally(tag_name):
element = xml_element("w:p", {}, [
xml_element(tag_name, {}, [
xml_element("w:r")
])
])
assert_equal(
documents.paragraph([documents.run([])]),
_read_and_get_document_xml_element(element)
)
def default_paragraph_style_is_specified_by_mapping_plain_paragraphs():
result = convert_document_element_to_html(
documents.paragraph(style_id="TipsParagraph", children=[
_run_with_text("Tip")
]),
style_map=[
_style_mapping("p => p.tip")
]
)
assert_equal('<p class="tip">Tip</p>', result.value)
def children_of_w_smart_tag_are_converted_normally(self):
element = xml_element("w:p", {}, [
xml_element("w:smartTag", {}, [
xml_element("w:r")
])
])
assert_equal(
documents.paragraph([documents.run([])]),
_read_and_get_document_xml_element(element)
)
def default_paragraph_style_is_specified_by_mapping_plain_paragraphs():
result = convert_document_element_to_html(
documents.paragraph(style_id="TipsParagraph", children=[
_run_with_text("Tip")
]),
style_map=[
style_reader.read_style("p => p.tip")
]
)
assert_equal('<p class="tip">Tip</p>', result.value)
def footnotes_of_document_are_read(self):
notes = [documents.note("footnote", "4", [documents.paragraph([])])]
body_xml = xml_element("w:body")
document_xml = xml_element("w:document", {}, [body_xml])
document = _read_and_get_document_xml_element(document_xml, notes=notes)
footnote = document.notes.find_note("footnote", "4")
assert_equal("4", footnote.note_id)
assert isinstance(footnote.body[0], documents.Paragraph)
def paragraphs_are_converted_by_satisfying_matching_paths():
result = convert_document_element_to_html(
documents.paragraph(style_name="TipsParagraph", children=[
_run_with_text("Tip")
]),
style_map=[
style_reader.read_style("p.TipsParagraph => p.tip")
]
)
assert_equal('<p class="tip">Tip</p>', result.value)
def bulleted_styles_dont_match_plain_paragraph():
result = convert_document_element_to_html(
documents.paragraph(children=[
_run_with_text("Hello")
]),
style_map=[
_style_mapping("p:unordered-list(1) => ul > li:fresh")
]
)
assert_equal('<p>Hello</p>', result.value)
def children_of_w_smart_tag_are_converted_normally(self):
element = xml_element("w:p", {}, [
xml_element("w:smartTag", {}, [
xml_element("w:r")
])
])
assert_equal(
documents.paragraph([documents.run([])]),
_read_and_get_document_xml_element(element)
)
def can_read_document_with_single_paragraph_with_single_run_of_text(self):
with open(test_path("single-paragraph.docx"), "rb") as fileobj:
result = docx.read(fileobj=fileobj)
expected_document = documents.document([
documents.paragraph([
documents.run([
documents.text("Walking on imported air")
])
])
])
assert_equal(expected_document, result.value)
def footnotes_of_document_are_read(self):
notes = [documents.note("footnote", "4", [documents.paragraph([])])]
body_xml = xml_element("w:body")
document_xml = xml_element("w:document", {}, [body_xml])
document = _read_and_get_document_xml_element(document_xml,
notes=notes)
footnote = document.notes.find_note("footnote", "4")
assert_equal("4", footnote.note_id)
assert isinstance(footnote.body[0], documents.Paragraph)
def footnotes_are_included_after_the_main_body():
footnote_reference = documents.note_reference("footnote", "4")
document = documents.document(
[documents.paragraph([_run_with_text("Knock knock"), documents.run([footnote_reference])])],
notes=documents.notes([documents.note("footnote", "4", [_paragraph_with_text("Who's there?")])]),
)
result = convert_document_element_to_html(document, id_prefix="doc-42")
expected_html = (
'<p>Knock knock<sup><a href="#doc-42-footnote-4" id="doc-42-footnote-ref-4">[1]</a></sup></p>'
+ '<ol><li id="doc-42-footnote-4"><p>Who\'s there? <a href="#doc-42-footnote-ref-4">↑</a></p></li></ol>'
)
assert_equal(expected_html, result.value)
def word_table_is_read_as_document_table_element(self):
element = xml_element("w:tbl", {}, [
xml_element("w:tr", {}, [
xml_element("w:tc", {}, [xml_element("w:p", {}, [])]),
]),
])
table = _read_and_get_document_xml_element(element)
expected_result = documents.table([
documents.table_row(
[documents.table_cell([documents.paragraph([])])])
])
assert_equal(expected_result, table)
def comments_are_ignored_by_default():
reference = documents.comment_reference("4")
comment = documents.comment(
comment_id="4",
body=[_paragraph_with_text("Who's there?")],
)
document = documents.document(
[documents.paragraph([
_run_with_text("Knock knock"),
documents.run([reference])
])],
comments=[comment],
)
result = convert_document_element_to_html(document, id_prefix="doc-42-")
expected_html = '<p>Knock knock</p>'
assert_equal(expected_html, result.value)
def gridspan_is_read_as_colspan_for_table_cell(self):
element = xml_element("w:tbl", {}, [
xml_element("w:tr", {}, [
xml_element("w:tc", {}, [
xml_element("w:tcPr", {},
[xml_element("w:gridSpan", {"w:val": "2"})]),
xml_element("w:p", {}, [])
]),
]),
])
table = _read_and_get_document_xml_element(element)
expected_result = documents.table([
documents.table_row(
[documents.table_cell([documents.paragraph([])], colspan=2)])
])
assert_equal(expected_result, table)
def comments_are_ignored_by_default():
reference = documents.comment_reference("4")
comment = documents.comment(
comment_id="4",
body=[_paragraph_with_text("Who's there?")],
)
document = documents.document(
[documents.paragraph([
_run_with_text("Knock knock"),
documents.run([reference])
])],
comments=[comment],
)
result = convert_document_element_to_html(document, id_prefix="doc-42-")
expected_html = '<p>Knock knock</p>'
assert_equal(expected_html, result.value)
def word_table_is_read_as_document_table_element(self):
element = xml_element("w:tbl", {}, [
xml_element("w:tr", {}, [
xml_element("w:tc", {}, [
xml_element("w:p", {}, [])
]),
]),
])
table = _read_and_get_document_xml_element(element)
expected_result = documents.table([
documents.table_row([
documents.table_cell([
documents.paragraph([])
])
])
])
assert_equal(expected_result, table)
def footnotes_are_included_after_the_main_body():
footnote_reference = documents.note_reference("footnote", "4")
document = documents.document(
[documents.paragraph([
_run_with_text("Knock knock"),
documents.run([footnote_reference])
])],
notes=documents.notes([
documents.note("footnote", "4", [_paragraph_with_text("Who's there?")])
])
)
result = convert_document_element_to_html(
document,
id_prefix="doc-42"
)
expected_html = ('<p>Knock knock<sup><a href="#doc-42-footnote-4" id="doc-42-footnote-ref-4">[1]</a></sup></p>' +
'<ol><li id="doc-42-footnote-4"><p>Who\'s there? <a href="#doc-42-footnote-ref-4">↑</a></p></li></ol>')
assert_equal(expected_html, result.value)
def gridspan_is_read_as_colspan_for_table_cell(self):
element = xml_element("w:tbl", {}, [
xml_element("w:tr", {}, [
xml_element("w:tc", {}, [
xml_element("w:tcPr", {}, [
xml_element("w:gridSpan", {"w:val": "2"})
]),
xml_element("w:p", {}, [])
]),
]),
])
table = _read_and_get_document_xml_element(element)
expected_result = documents.table([
documents.table_row([
documents.table_cell([
documents.paragraph([])
], colspan=2)
])
])
assert_equal(expected_result, table)
def footnotes_are_included_after_the_main_body():
footnote_reference = documents.footnote_reference("4")
document = documents.document(
[
documents.paragraph([
_run_with_text("Knock knock"),
documents.run([footnote_reference])
])
],
footnotes=documents.Footnotes({
"4":
documents.Footnote("4", [_paragraph_with_text("Who's there?")])
}))
result = convert_document_element_to_html(document,
generate_uniquifier=lambda: 42)
expected_html = (
'<p>Knock knock<sup><a href="#footnote-42-4" id="footnote-ref-42-4">[1]</a></sup></p>'
+
'<ol><li id="footnote-42-4"><p>Who\'s there? <a href="#footnote-ref-42-4">↑</a></p></li></ol>'
)
assert_equal(expected_html, result.value)
def empty_paragraphs_are_ignored():
result = convert_document_element_to_html(
documents.paragraph(children=[_run_with_text("")])
)
assert_equal('', result.value)
def includes_indirect_descendants(self):
grandchild = documents.text("grandchild")
child = documents.run(children=[grandchild])
element = documents.paragraph(children=[child])
assert_equal([grandchild, child], get_descendants(element))
def non_paragraph_elements_are_not_transformed(self):
paragraph = documents.paragraph(children=[])
result = transforms.run(lambda _: documents.tab())(paragraph)
assert_equal(documents.paragraph(children=[]), result)
def _paragraph_with_text(text):
return documents.paragraph(children=[_run_with_text(text)])
def empty_paragraphs_are_ignored():
result = convert_document_element_to_html(
documents.paragraph(children=[_run_with_text("")]))
assert_equal('', result.value)
def filters_descendants_to_type(self):
tab = documents.tab()
run = documents.run(children=[])
element = documents.paragraph(children=[tab, run])
assert_equal([run], get_descendants_of_type(element, documents.Run))
def includes_indirect_descendants(self):
grandchild = documents.text("grandchild")
child = documents.run(children=[grandchild])
element = documents.paragraph(children=[child])
assert_equal([grandchild, child], get_descendants(element))
def includes_children(self):
children = [documents.text("child 1"), documents.text("child 2")]
element = documents.paragraph(children=children)
assert_equal(children, get_descendants(element))
def raw_text_of_paragraph_is_terminated_with_newlines():
paragraph = documents.paragraph(children=[documents.Text("Hello")])
assert_equal("Hello\n\n", extract_raw_text_from_element(paragraph))
def filters_descendants_to_type(self):
tab = documents.tab()
run = documents.run(children=[])
element = documents.paragraph(children=[tab, run])
assert_equal([run], get_descendants_of_type(element, documents.Run))
def can_read_text_within_paragraph(self):
element = _paragraph_element_with_text("Hello!")
assert_equal(
documents.paragraph([documents.run([documents.Text("Hello!")])]),
_read_and_get_document_xml_element(element)
)
def plain_paragraph_is_converted_to_plain_paragraph():
result = convert_document_element_to_html(
documents.paragraph(children=[_run_with_text("Hello")]))
assert_equal('<p>Hello</p>', result.value)
def no_warning_if_there_is_no_style_for_plain_paragraphs():
result = convert_document_element_to_html(
documents.paragraph(children=[_run_with_text("Tip")]),
)
assert_equal([], result.messages)
def _paragraph_with_text(text):
return documents.paragraph(children=[_run_with_text(text)])
def plain_paragraph_is_converted_to_plain_paragraph():
result = convert_document_element_to_html(
documents.paragraph(children=[_run_with_text("Hello")])
)
assert_equal('<p>Hello</p>', result.value)
def returns_nothing_if_element_has_empty_children(self):
assert_equal([], get_descendants(documents.paragraph(children=[])))
def no_warning_if_there_is_no_style_for_plain_paragraphs():
result = convert_document_element_to_html(
documents.paragraph(children=[_run_with_text("Tip")]), )
assert_equal([], result.messages)
