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 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 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 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 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 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 docx_hyperlinks_can_be_collapsed():
result = convert_document_element_to_html(
documents.document(children=[
documents.hyperlink(href="http://example.com",
children=[documents.Text("Hello ")]),
documents.hyperlink(href="http://example.com",
children=[documents.Text("world")]),
]))
assert_equal('<a href="http://example.com">Hello world</a>', result.value)
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 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 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_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 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 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 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 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 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)
)
