def handle_col_floats(root):
for node in root.xpath('//*[contains(@class, "infobox")]'):
w, h = node_size(node)
if h < config.min_float_height or (h < 2 * config.min_float_height
and node_is_floatable(node, w, h)):
utils.append_class(node, "pp_no_float")
elif "pp_float_table" in node.get("class", ""):
utils.remove_class(node, "pp_float_table")
def map_classes(article):
class_map = get_map(_class_map, article.language)
if not class_map:
return
for node in article.dom.xpath("//*[@class]"):
class_list = node.get("class").split(" ")
for cls in class_map:
if cls in class_list:
utils.remove_class(node, cls)
utils.append_class(node, class_map[cls])
def map_class_to_style(article):
class_to_style_map = get_map(_class_to_style_map, article.language)
if not class_to_style_map:
return
for css_class in class_to_style_map:
style_attr, style_val = class_to_style_map[css_class]
for node in article.dom.xpath(
'//*[contains(@class, "{}")]'.format(css_class)):
utils.add_node_style(node, style_attr, style_val)
utils.remove_class(node, css_class)
def add_figure_numbers(root):
classes = [
"pp_singlecol",
# 'infobox', # infoboxes are not referenced despite floating
"pp_figure",
"pp_twocol_span",
]
pred = " or ".join('contains(@class, "{}")'.format(cls) for cls in classes)
total_figures = 0
for article in root.xpath("//article"):
figure_num = 0
for node in article.xpath(".//*[{}]".format(pred)):
utils.remove_class(node, "infobox")
figure_num += 1
total_figures += 1
cls = [c for c in classes if c in node.get("class")][0]
nr = ".".join([article.get("pp_article_num"), str(figure_num)])
caption_txt = "Figure {nr} ".format(nr=nr)
reference = E.p({"class": "pp_figure_ref"}, u"\u21AA " + caption_txt)
if cls == "pp_figure":
caption = node.xpath('.//*[contains(@class, "thumbcaption")]')
if caption:
node.addnext(reference)
caption = caption[0]
prefix = E.b(caption_txt)
caption.insert(0, prefix)
prefix.tail = caption.text
caption.text = None
utils.append_class(caption, "pp_figure_caption")
continue
wrapper = utils.wrap_node(node, "div", {"class": cls})
caption = E.div({"class": "pp_figure_caption"}, E.b(caption_txt))
wrapper.append(caption)
utils.remove_class(node, cls)
wrapper.addnext(reference)
_combine_references(root)
def remove_low_ppi(root):
result = root.xpath('//img[contains(@class, "low-ppi")]')
for img in result:
utils.remove_class(img, "low-ppi")