def test_table_item_markdown(self, processing_options):
item = TableItem(processing_options, [TextItem(processing_options, 'Column 1')])
expected = 'Column 1'
result = item.markdown()
assert result == expected
def test_html_output(self, processing_options):
contents = [
TableItem(processing_options, [TextItem(processing_options, 'Column 1')]),
TableItem(processing_options, [TextItem(processing_options, 'Column 2')]),
]
row = TableRow(processing_options, contents)
expected = "<tr><tr><td>Column 1</td><td>Column 2</td></tr>"
result = row.html()
assert result == expected
def extract_from_nimbus_table_select_item(
cell_tag, processing_options: NimbusProcessingOptions):
"""
Extract data form a Nimbus table select item.
Nimbus HTML uses a tag class to specify a select item. Returns a text as a TextItem in a TableItem wrapper
Parameters
==========
processing_options : NimbusProcessingOptions
Processing options for nimbus html conversion
cell_tag : beautiful soup <td> tag object
Returns
=======
TableItem
Select text as a TextItem in a TableItem wrapper
"""
if cell_tag.name != 'td':
return
span_tags = cell_tag.find_all('span', class_="select-label-text")
if not span_tags:
return
cell_text = ''
for span in span_tags:
cell_text = f"{cell_text}{span.text} "
cell_text = cell_text.strip()
return TableItem(processing_options,
[TextItem(processing_options, cell_text)])
def extract_from_nimbus_table_collaboration_item(
cell_tag, processing_options: NimbusProcessingOptions):
"""
Extract data form a Nimbus table collaboration item.
Nimbus HTML uses a tag class to specify a collaboration item. Returns a text as a TextItem in a TableItem wrapper
Parameters
==========
processing_options : NimbusProcessingOptions
Processing options for nimbus html conversion
cell_tag : beautiful soup <td> tag object
Returns
=======
TableItem
collaboration text as a TextItem in a TableItem wrapper
"""
if cell_tag.name != 'td':
return
span_tag = cell_tag.find('span', class_="collaborate-item")
if not span_tag:
return
return TableItem(
processing_options,
[TableCollaborator(processing_options, span_tag["data-mention-name"])])
def extract_from_nimbus_table_date_item(
cell_tag, processing_options: NimbusProcessingOptions):
"""
Extract data form a Nimbus table date item.
Nimbus HTML uses a tag class to specify a the date item. Returns a text as a TextItem in a TableItem wrapper
Parameters
==========
processing_options : NimbusProcessingOptions
Processing options for nimbus html conversion
cell_tag : beautiful soup <td> tag object
Returns
=======
TableItem
Date text as a TextItem in a TableItem wrapper
"""
if cell_tag.name != 'td':
return
span_tag = cell_tag.find('span', class_="input-date-text")
if not span_tag:
return
return TableItem(processing_options,
[TextItem(processing_options, span_tag.text)])
def extract_from_nimbus_table_hyperlink_item(
cell_tag, processing_options: NimbusProcessingOptions):
"""
Extract data form a Nimbus table hyperlink item.
Nimbus HTML uses a tag class to specify a the date item. Returns a Hyperlink object in a TableItem wrapper
Parameters
==========
processing_options : NimbusProcessingOptions
Processing options for nimbus html conversion
cell_tag : beautiful soup <td> tag object
Returns
=======
TableItem
Hyperlink object in a TableItem wrapper
"""
if cell_tag.name != 'td':
return
a_tag_search = cell_tag.find_all('a')
if a_tag_search:
a_tag = a_tag_search[0]
hyperlink = html_data_extractors.extract_from_hyperlink(
a_tag, processing_options)
return TableItem(processing_options, [hyperlink])
def extract_from_nimbus_table_rating_item(
cell_tag, processing_options: NimbusProcessingOptions):
"""
Extract data form a Nimbus table rating item.
Nimbus HTML uses a <span> tag and tag class to specify each star in the rating. Count the number of active stars
and return a rating string. Returns a Hyperlink object in a TableItem wrapper
Parameters
==========
processing_options : NimbusProcessingOptions
Processing options for nimbus html conversion
cell_tag : beautiful soup <td> tag object
Returns
=======
TableItem
Hyperlink object in a TableItem wrapper
"""
if cell_tag.name != 'td':
return
active_stars = cell_tag.find_all('span', class_="rating-active")
if active_stars:
rating_text = f'Rating {len(active_stars)}/5 stars'
return TableItem(processing_options,
[TextItem(processing_options, rating_text)])
def extract_from_nimbus_table_progress_item(
cell_tag, processing_options: NimbusProcessingOptions):
"""
Extract data form a Nimbus table progress item.
Nimbus HTML uses a <span> tag and tag class to specify the progress as a text value. Returns a Hyperlink object
in a TableItem wrapper
Parameters
==========
processing_options : NimbusProcessingOptions
Processing options for nimbus html conversion
cell_tag : beautiful soup <td> tag object
Returns
=======
TableItem
TextItem object in a TableItem wrapper
"""
if cell_tag.name != 'td':
return
progress_span = cell_tag.find('span', class_="progress-value")
if progress_span:
progress_text = f'Progress {progress_span.text}'
return TableItem(processing_options,
[TextItem(processing_options, progress_text)])
def test_table_markdown(self, processing_options):
contents = [
TableItem(processing_options, [TextItem(processing_options, 'Column 1')]),
TableItem(processing_options, [TextItem(processing_options, 'Column 2')]),
]
header_row = TableHeader(processing_options, contents)
row_contents = [
TableItem(processing_options, [TextItem(processing_options, 'Row 1')]),
TableItem(processing_options, [TextItem(processing_options, 'Row 2')]),
]
row = TableRow(processing_options, row_contents)
table = Table(processing_options, [header_row, row])
expected = '\n|Column 1|Column 2|\n|--|--|\n|Row 1|Row 2|\n\n'
result = table.markdown()
assert result == expected
def test_table_html(self, processing_options):
contents = [
TableItem(processing_options, [TextItem(processing_options, 'Column 1')]),
TableItem(processing_options, [TextItem(processing_options, 'Column 2')]),
]
header_row = TableHeader(processing_options, contents)
row_contents = [
TableItem(processing_options, [TextItem(processing_options, 'Row 1')]),
TableItem(processing_options, [TextItem(processing_options, 'Row 2')]),
]
row = TableRow(processing_options, row_contents)
table = Table(processing_options, [header_row, row])
expected = '<table border="1"><tr><tr><th>Column 1</th><th>Column 2</th></tr><tr><tr><td>Row 1</td><td>Row 2</td></tr></table>'
result = table.html()
assert result == expected
def extract_from_123abc_table_header_row(cells, processing_options):
"""
If 123 and ABC row and columns headers are to be kept extract and return the ABC row
Parameters
----------
cells : list[Tag]
lost of <th> tags form a nimbus html table. No check is made that the provided tags are <th> tags
processing_options : NimbusProcessingOptions
processing settings for the current conversion
Returns
-------
list
list of TableItem objects
"""
skip_next = False
data = []
for cell in cells:
if skip_next:
skip_next = False
continue
if cell.get('class') and 'table-head-start' in cell['class']:
skip_next = True
# append an empty cell where numbers and letters row/columns meet
data.append(
TableItem(processing_options,
[TextItem(processing_options, '')]))
continue
header_div = cell.find('div', class_="item-title")
cell_text = process_child_items(header_div, processing_options)
data.append(TableItem(processing_options, cell_text))
return data
def extract_from_nimbus_table_mention_item(
cell_tag, processing_options: NimbusProcessingOptions):
"""
Extract data form a Nimbus table mention item.
Nimbus HTML uses a tag class to specify a mention item. Returns a text as a TextItem in a TableItem wrapper
Parameters
==========
processing_options : NimbusProcessingOptions
Processing options for nimbus html conversion
cell_tag : beautiful soup <td> tag object
Returns
=======
TableItem
Mention text as a TextItem in a TableItem wrapper
"""
if cell_tag.name != 'td':
return
def span_has_data_mention_type(tag):
return tag.has_attr('data-mention-type')
if cell_tag.get('class') and 'cell-mention' in cell_tag.attrs['class']:
# NOTE here passing function to find so we can get the correct tag with out iterating all the spans
# to find the right one.
mention_tag = cell_tag.find(span_has_data_mention_type)
if not mention_tag:
return
mention_item = extract_from_nimbus_mention_span(
mention_tag, processing_options)
return TableItem(processing_options, [mention_item])
def extract_from_table_row(cells, processing_options):
keep_abc_123_columns = processing_options.keep_abc_123_columns
skip_next = False
data = []
for cell in cells:
if skip_next:
skip_next = False
continue
# if cell.name == 'td':
if cell.get('class'):
if 'table-head-item' in cell['class']:
skip_next = True
if not keep_abc_123_columns:
continue
if 'add-row' in cell['class']:
break
table_check_item = extract_from_nimbus_table_check_item(
cell, processing_options)
if table_check_item:
data.append(table_check_item)
continue
table_select_item = extract_from_nimbus_table_select_item(
cell, processing_options)
if table_select_item:
data.append(table_select_item)
continue
table_mention_item = extract_from_nimbus_table_mention_item(
cell, processing_options)
if table_mention_item:
data.append(table_mention_item)
continue
table_collaboration_item = extract_from_nimbus_table_collaboration_item(
cell, processing_options)
if table_collaboration_item:
data.append(table_collaboration_item)
continue
table_date_item = extract_from_nimbus_table_date_item(
cell, processing_options)
if table_date_item:
data.append(table_date_item)
continue
table_cell_hyperlink = extract_from_nimbus_table_hyperlink_item(
cell, processing_options)
if table_cell_hyperlink:
data.append(table_cell_hyperlink)
continue
table_cell_rating = extract_from_nimbus_table_rating_item(
cell, processing_options)
if table_cell_rating:
data.append(table_cell_rating)
continue
table_cell_progress_bar = extract_from_nimbus_table_progress_item(
cell, processing_options)
if table_cell_progress_bar:
data.append(table_cell_progress_bar)
continue
cell_text = extract_from_nimbus_table_text_item(
cell, processing_options)
if cell_text:
data.append(TableItem(processing_options, cell_text))
continue
# handle empty cells <td></td> or unrecognised cells e.g. table-attachements are currently there but
# have no content
# <td class="cell-attachment"><div class="table-attachment-wrap"><div><div class="table-attachment">
# <div class="attachment-item"></div></div></div></div></td>
data.append(
TableItem(processing_options, [TextItem(processing_options, '')]))
return data