def extract_from_nimbus_attachment_caption(
div_tag, processing_options: NimbusProcessingOptions):
if div_tag.name != 'div':
return
if div_tag.text == '':
# catches captions that are empty and just have <br> in them
return Caption(processing_options, [TextItem(processing_options, '')])
text_items = process_child_items(div_tag, processing_options)
return Caption(processing_options, text_items)
def extract_embed_block_quote_if_present():
"""
Inner function to extract a block quote and caption from an embed div.
A twitter block quote repeats itself twice in nimbus html so using the above blockquote extractor. This also
result int the contents being indented as a blockquote like a twitter tweet does.
"""
embed_content_tag = div_tag.find('blockquote')
if embed_content_tag:
data = html_data_extractors.extract_from_blockquote(
embed_content_tag, processing_options)
# NOTE the exported remote frame and iframe work using process_child items
# but a twitter block quote repeats itself twice in nimbus html so using the above blockquote extractor.
# This also indents the contents as a blockquote like a twitter tweet does
# and because we have extracted just the blockquote we need to now try and get the caption
try:
caption_items = extract_from_nimbus_attachment_caption(
div_tag.find('div', class_='attachment-caption'),
processing_options)
except AttributeError:
# all is OK just no caption data asking for forgiveness approach we make an empty entry
caption_items = Caption(processing_options,
[TextItem(processing_options, '')])
if data:
return EmbedNimbus(processing_options, data, caption_items)
def extract_from_figure_caption(
tag,
processing_options: ProcessingOptions,
note_specific_tag_cleaning: Optional[Callable] = None):
caption_text = process_child_items(tag, processing_options,
note_specific_tag_cleaning)
return Caption(processing_options, caption_text)
def test_figure_none_for_image(self, processing_options):
image_object = None
caption_object = caption_object = Caption(processing_options, [TextItem(processing_options, "a caption")])
expected = '<figure><figcaption>a caption</figcaption></figure>'
result = html_string_builders.figure((image_object, caption_object))
assert result == expected
def test_figure(self, processing_options):
image_object = ImageEmbed(processing_options, "an image", "image.png", Path("image.pdf"), "200", "300" )
image_object.target_path = Path("image.png")
caption_object = Caption(processing_options, [TextItem(processing_options, "a caption")])
expected = '<figure><img src="image.png" alt="an image" width="200" height="300"><figcaption>a caption</figcaption></figure>'
result = html_string_builders.figure((image_object, caption_object))
assert result == expected
def test_figure_none_for_image(self, processing_options):
image_object = None
caption_object = Caption(processing_options, [TextItem(processing_options, "a caption")])
contents = (image_object, caption_object)
figure = Figure(processing_options, contents)
expected = '*a caption*\n\n'
result = figure.markdown()
assert result == expected
def test_figure(self, processing_options):
image_object = ImageEmbed(processing_options, "an image", "image.png", Path("image.pdf"), "200", "300")
image_object.target_path = Path("image.png")
caption_object = Caption(processing_options, [TextItem(processing_options, "a caption")])
contents = (image_object, caption_object)
figure = Figure(processing_options, contents)
expected = '\n*a caption*\n\n'
result = figure.markdown()
assert result == expected
def get_caption_text(div_tag, processing_options):
try:
if div_tag.get('class') and 'attachment-caption' in div_tag['class']:
tag_to_use = div_tag
else:
tag_to_use = div_tag.find('div', class_='attachment-caption')
caption_text = extract_from_nimbus_attachment_caption(
tag_to_use, processing_options)
except AttributeError:
caption_text = Caption(processing_options,
[TextItem(processing_options, '')])
return caption_text