def add_link_markup(tag):
"""Add necessary markup to the given link and return if modified.
Add an external link icon if the input is not a CFPB (internal) link.
Add an external link redirect if the input is not a gov link.
If it contains a descendent that should not get an icon, return the link.
If not, add a download icon if the input is a file.
Otherwise (internal link that is not a file), return None.
"""
icon = False
tag = BeautifulSoup(tag, 'html.parser').find('a', href=True)
if tag is None:
return None
if not tag.attrs.get('class', None):
tag.attrs.update({'class': []})
if tag['href'].startswith('/external-site/?'):
# Sets the icon to indicate you're leaving consumerfinance.gov
icon = 'external-link'
components = urlparse(tag['href'])
arguments = parse_qs(components.query)
if 'ext_url' in arguments:
external_url = arguments['ext_url'][0]
# Add the redirect notice as well
tag['href'] = signed_redirect(external_url)
elif NON_CFPB_LINKS.match(tag['href']):
# Sets the icon to indicate you're leaving consumerfinance.gov
icon = 'external-link'
if NON_GOV_LINKS.match(tag['href']):
# Add the redirect notice as well
tag['href'] = signed_redirect(tag['href'])
elif DOWNLOAD_LINKS.search(tag['href']):
# Sets the icon to indicate you're downloading a file
icon = 'download'
if tag.select(', '.join(ICONLESS_LINK_CHILD_ELEMENTS)):
# If this tag has any children that are in our list of child elements
# that should not get an icon, it doesn't get the icon. It might still
# be an external link and modified accordingly above.
return str(tag)
if icon:
tag.attrs['class'].append(LINK_ICON_CLASSES)
# Wraps the link text in a span that provides the underline
contents = tag.contents
span = BeautifulSoup('', 'html.parser').new_tag('span')
span['class'] = LINK_ICON_TEXT_CLASSES
span.contents = contents
tag.contents = [span, NavigableString(' ')]
# Appends the SVG icon
tag.contents.append(BeautifulSoup(svg_icon(icon), 'html.parser'))
return str(tag)
return None
def add_link_markup(tags):
for tag in tags:
added_icon = False
if not tag.attrs.get('class', None):
tag.attrs.update({'class': []})
if tag['href'].startswith('/external-site/?'):
components = urlparse(tag['href'])
arguments = parse_qs(components.query)
if 'ext_url' in arguments:
external_url = arguments['ext_url'][0]
tag['href'] = signed_redirect(external_url)
elif NONCFPB_LINK_PATTERN.match(tag['href']):
# Sets the icon to indicate you're leaving consumerfinance.gov
tag.attrs['class'].append(EXTERNAL_A_CSS)
if EXTERNAL_LINK_PATTERN.match(tag['href']):
tag['href'] = signed_redirect(tag['href'])
added_icon = True
elif DOWNLOAD_LINK_PATTERN.search(tag['href']):
# Sets the icon to indicate you're downloading a file
tag.attrs['class'].append(DOWNLOAD_A_CSS)
added_icon = True
if added_icon:
# Wraps the link text in a span that provides the underline
contents = tag.contents
span = BeautifulSoup('', 'html.parser').new_tag('span')
span['class'] = EXTERNAL_SPAN_CSS
span.contents = contents
tag.contents = [span, NavigableString(' ')]
elif not FILES_LINK_PATTERN.match(tag['href']):
fix_link(tag)
def add_link_markup(tags):
for tag in tags:
added_icon = False
if not tag.attrs.get('class', None):
tag.attrs.update({'class': []})
if NONCFPB_LINK_PATTERN.match(tag['href']):
# Sets the icon to indicate you're leaving consumerfinance.gov
tag.attrs['class'].append(EXTERNAL_A_CSS)
if EXTERNAL_LINK_PATTERN.match(tag['href']):
# Sets the link to an external one if you're leaving .gov
tag['href'] = '/external-site/?ext_url=' + tag['href']
added_icon = True
elif DOWNLOAD_LINK_PATTERN.search(tag['href']):
# Sets the icon to indicate you're downloading a file
tag.attrs['class'].append(DOWNLOAD_A_CSS)
added_icon = True
if added_icon:
# Wraps the link text in a span that provides the underline
contents = tag.contents
span = BeautifulSoup('').new_tag('span')
span['class'] = EXTERNAL_SPAN_CSS
span.contents = contents
tag.contents = [span, NavigableString(' ')]
elif not FILES_LINK_PATTERN.match(tag['href']):
fix_link(tag)
def add_link_markup(tags):
for tag in tags:
added_icon = False
if not tag.attrs.get('class', None):
tag.attrs.update({'class': []})
if tag['href'].startswith('/external-site/?'):
components = urlparse(tag['href'])
arguments = parse_qs(components.query)
if 'ext_url' in arguments:
external_url = arguments['ext_url'][0]
tag['href'] = signed_redirect(external_url)
elif NONCFPB_LINK_PATTERN.match(tag['href']):
# Sets the icon to indicate you're leaving consumerfinance.gov
tag.attrs['class'].append(EXTERNAL_A_CSS)
if EXTERNAL_LINK_PATTERN.match(tag['href']):
tag['href'] = signed_redirect(tag['href'])
added_icon = True
elif DOWNLOAD_LINK_PATTERN.search(tag['href']):
# Sets the icon to indicate you're downloading a file
tag.attrs['class'].append(DOWNLOAD_A_CSS)
added_icon = True
if added_icon:
# Wraps the link text in a span that provides the underline
contents = tag.contents
span = BeautifulSoup('', 'html.parser').new_tag('span')
span['class'] = EXTERNAL_SPAN_CSS
span.contents = contents
tag.contents = [span, NavigableString(' ')]
elif not FILES_LINK_PATTERN.match(tag['href']):
fix_link(tag)
def add_link_markup(tags):
for tag in tags:
added_icon = False
if not tag.attrs.get('class', None):
tag.attrs.update({'class': []})
if NONCFPB_LINK_PATTERN.match(tag['href']):
# Sets the icon to indicate you're leaving consumerfinance.gov
tag.attrs['class'].append(EXTERNAL_A_CSS)
if EXTERNAL_LINK_PATTERN.match(tag['href']):
# Sets the link to an external one if you're leaving .gov
tag['href'] = '/external-site/?ext_url=' + tag['href']
added_icon = True
elif DOWNLOAD_LINK_PATTERN.search(tag['href']):
# Sets the icon to indicate you're downloading a file
tag.attrs['class'].append(DOWNLOAD_A_CSS)
added_icon = True
if added_icon:
# Wraps the link text in a span that provides the underline
contents = tag.contents
span = BeautifulSoup('', 'html.parser').new_tag('span')
span['class'] = EXTERNAL_SPAN_CSS
span.contents = contents
tag.contents = [span, NavigableString(' ')]
elif not FILES_LINK_PATTERN.match(tag['href']):
fix_link(tag)
def plain_content(readability_content, content_digests, node_indexes):
# Load article as DOM
soup = BeautifulSoup(readability_content, 'html.parser')
# Make all elements plain
elements = plain_elements(soup.contents, content_digests, node_indexes)
if node_indexes:
# Add node index attributes to nodes
elements = [add_node_indexes(element) for element in elements]
# Replace article contents with plain elements
soup.contents = elements
return str(soup)
def add_link_markup(tag):
"""Add necessary markup to the given link and return if modified.
Add an external link icon if the input is not a CFPB (internal) link.
Add an external link redirect if the input is not a gov link.
Add a download icon if the input is a file.
Otherwise (internal link that is not a file), return None.
"""
icon = False
if not tag.attrs.get('class', None):
tag.attrs.update({'class': []})
if tag['href'].startswith('/external-site/?'):
# Sets the icon to indicate you're leaving consumerfinance.gov
icon = 'external-link'
components = urlparse(tag['href'])
arguments = parse_qs(components.query)
if 'ext_url' in arguments:
external_url = arguments['ext_url'][0]
# Add the redirect notice as well
tag['href'] = signed_redirect(external_url)
elif NON_CFPB_LINKS.match(tag['href']):
# Sets the icon to indicate you're leaving consumerfinance.gov
icon = 'external-link'
if NON_GOV_LINKS.match(tag['href']):
# Add the redirect notice as well
tag['href'] = signed_redirect(tag['href'])
elif DOWNLOAD_LINKS.search(tag['href']):
# Sets the icon to indicate you're downloading a file
icon = 'download'
if icon:
tag.attrs['class'].append(LINK_ICON_CLASSES)
# Wraps the link text in a span that provides the underline
contents = tag.contents
span = BeautifulSoup('', 'html.parser').new_tag('span')
span['class'] = LINK_ICON_TEXT_CLASSES
span.contents = contents
tag.contents = [span, NavigableString(' ')]
# Appends the SVG icon
tag.contents.append(BeautifulSoup(svg_icon(icon), 'html.parser'))
return str(tag)
return None
def add_link_markup(tag):
"""Add necessary markup to the given link and return if modified.
Add an external link icon if the input is not a CFPB (internal) link.
Add an external link redirect if the input is not a gov link.
Add a download icon if the input is a file.
Otherwise (internal link that is not a file), return None.
"""
icon = False
if not tag.attrs.get('class', None):
tag.attrs.update({'class': []})
if tag['href'].startswith('/external-site/?'):
# Sets the icon to indicate you're leaving consumerfinance.gov
icon = 'external-link'
components = urlparse(tag['href'])
arguments = parse_qs(components.query)
if 'ext_url' in arguments:
external_url = arguments['ext_url'][0]
# Add the redirect notice as well
tag['href'] = signed_redirect(external_url)
elif NON_CFPB_LINKS.match(tag['href']):
# Sets the icon to indicate you're leaving consumerfinance.gov
icon = 'external-link'
if NON_GOV_LINKS.match(tag['href']):
# Add the redirect notice as well
tag['href'] = signed_redirect(tag['href'])
elif DOWNLOAD_LINKS.search(tag['href']):
# Sets the icon to indicate you're downloading a file
icon = 'download'
if icon:
tag.attrs['class'].append(LINK_ICON_CLASSES)
# Wraps the link text in a span that provides the underline
contents = tag.contents
span = BeautifulSoup('', 'html.parser').new_tag('span')
span['class'] = LINK_ICON_TEXT_CLASSES
span.contents = contents
tag.contents = [span, NavigableString(' ')]
# Appends the SVG icon
tag.contents.append(BeautifulSoup(svg_icon(icon), 'html.parser'))
return str(tag)
return None
def render_table_odt(elem, doc):
table = elem.content[0]
table_number = tuple(
str(i) for i in utils.get_elem_count(doc, pf.Table, register="table"))
table_name = "Table{}".format("_".join(str(i) for i in table_number))
#
table_root = BeautifulSoup("", "xml")
if hasattr(table, "caption") and table.caption:
colon = ": "
caption = "".join(pf.stringify(c) for c in table.caption)
else:
colon = ""
caption = ""
caption_odt = utils.create_nested_tags(
**{
"name":
"text:p",
"attrs": {
"text:style-name": "Table"
},
"contents": [
{
"name":
"text:span",
"attrs": {
"text:style-name": "Strong_20_Emphasis"
},
"contents": [
"Table ",
{
"name": "text:sequence",
"attrs": {
"text:ref-name": f"ref{table_name}",
"text:name": "Table",
"text:formula": "ooow:Table+1",
"style:num-format": "1",
},
"contents": [".".join(table_number)],
},
colon,
],
},
caption,
],
})
table_root.contents.append(caption_odt)
table_odt = utils.create_nested_tags(
**{
"name": "table:table",
"attrs": {
"table:name": table_name,
"table:style-name": table_name,
"table:template-name": "Default Style",
},
})
table_root.contents.append(table_odt)
unoccupied_width = 1 - sum(table.width)
unspecified_widths = len([w for w in table.width if not w])
remaining_for_each = unoccupied_width / unspecified_widths
widths = [w if w else remaining_for_each for w in table.width]
# We want the table to occupy a maximum width
widths = map(lambda x: x * table.total_width, widths)
column_style_names, column_styles, column_definitions = zip(
*create_column_definitions(widths, table_name))
pf.debug(column_style_names, column_styles, column_definitions)
styles = BeautifulSoup("", "xml")
styles.contents = list(column_styles)
table_odt.contents.extend(column_definitions)
for r, row in enumerate(table.content):
row_odt = Tag(name="table:table-row")
row_odt.attrs = {
"table:style-name":
"{table_name}.{r}".format(table_name=table_name, r=r + 1)
}
row_cell_styles = []
for c, cell in enumerate(row.content):
if cell.covered:
cell_odt = Tag(name="table:covered-table-cell")
row_odt.contents.append(cell_odt)
row_cell_styles.append(None)
else:
cell_odt = Tag(name="table:table-cell")
cell_style_name = "{column_style}{r}".format(
column_style=column_style_names[c], r=r + 1)
cell_style = Tag(name="style:style")
cell_style.attrs = {
"style:name": cell_style_name,
"style:family": "table-cell",
"style:writing-mode": "page",
}
style_cell_properies = Tag(name="style:table-cell-properties")
style_cell_properies.attrs = {
"fo:padding-left": "0.10cm",
"fo:padding-right": "0.10cm",
"fo:padding-top": "0.10cm",
"fo:padding-bottom": "0.10cm",
"style:vertical-align": "bottom",
}
style_background_image = Tag(name="style:background-image")
style_cell_properies.contents.append(style_background_image)
cell_style.contents.append(style_cell_properies)
row_cell_styles.append(cell_style)
cell_odt.attrs = {
"table:style-name": cell_style_name,
"office:value-type": "string",
}
if cell.col_span > 1:
cell_odt.attrs[
"table:number-columns-spanned"] = cell.col_span
if cell.content:
cell_content = utils.panflute2output(
cell.content, format="opendocument").strip()
cell_content = BeautifulSoup(cell_content,
"lxml").html.body
text_p = re.compile("text:p")
for t in cell_content.find_all(text_p):
if cell.heading == 1:
t["text:style-name"] = "Table_20_Heading"
elif cell.heading == 2:
t["text:style-name"] = "Table_20_Subheading"
else:
t["text:style-name"] = "Table_20_Contents"
if cell.vertical:
t_contents = t.contents
t.contents = [
utils.create_nested_tags(
**{
"name": "text:span",
"attrs": {
"text:style-name": "Vertical"
},
"contents": t_contents,
})
]
cell_odt.contents = cell_content.contents
else:
cell_content = Tag(name="text:p")
cell_content.attrs = {
"text:style-name": "Table_20_contents"
}
cell_odt.contents.append(cell_content)
row_odt.contents.append(cell_odt)
if row.underlines:
for underline in row.underlines:
start = underline[0]
stop = underline[1]
for i in range(start - 1, stop):
cell_style = row_cell_styles[i]
if cell_style is None:
pass
else:
cell_style.contents[0].attrs[
"fo:border-bottom"] = "0.5pt solid #000000"
add_top_space = table.content[r - 1].btm_space if r else False
if row.top_space or add_top_space:
for cell_style in row_cell_styles:
if cell_style is not None:
padding_top = cell_style.contents[0].attrs[
"fo:padding-top"]
padding_top = (float(padding_top.strip("cm")) +
0.05 * add_top_space + 0.05 * row.top_space)
cell_style.contents[0].attrs[
"fo:padding-top"] = f"{padding_top}cm"
row_cell_styles = [cs for cs in row_cell_styles if cs is not None]
styles.contents.extend(row_cell_styles)
table_odt.contents.append(row_odt)
try:
footer = elem.content[1].content[0]
except IndexError:
footer = None
if footer is not None:
for definition_item in footer.content:
term = "".join(pf.stringify(e) for e in definition_item.term)
definitions = [
utils.panflute2output(d.content, format="opendocument")
for d in definition_item.definitions
]
definitions_parsed = BeautifulSoup("".join(definitions),
"lxml").html.body.contents
for t in definitions_parsed:
if t.name == "text:p":
t.name = "text:span"
t.contents.insert(0, NavigableString(" "))
definition = utils.create_nested_tags(
**{
"name":
"text:p",
"attrs": {
"text:style-name": "Table_20_Legend"
},
"contents": [{
"name": "text:span",
"attrs": {
"text:style-name": "Superscript"
},
"contents": [term],
}] + definitions_parsed,
})
table_root.contents.append(definition)
styles = "\n".join(c.prettify() for c in styles.contents)
doc.auto_styles.append(styles)
table = "\n".join(str(c) for c in table_root.contents)
# pf.debug(table)
return table
