def test_cleanup_html_fix_img_links(self):
html_input_path = os.path.join(
os.path.dirname(__file__), 'input', 'image_sample.html')
html_input = open(html_input_path, 'rb').read()
result, img_map = cleanup_html(
html_input, 'sample.html', fix_img_links=True)
assert len(img_map) == 4
def process(self, path, metadata):
ext = os.path.splitext(path)[1]
if ext not in self.supported_extensions:
return path, metadata
basename = os.path.basename(path)
src_path = os.path.join(copy_to_secure_location(path), basename)
src_dir = os.path.dirname(src_path)
remove_file_dir(path)
new_html, img_name_map = cleanup_html(
codecs.open(src_path, 'r', 'utf-8').read(),
basename,
fix_head_nums=self.options['html_cleaner_fix_heading_numbers'],
fix_img_links=self.options['html_cleaner_fix_image_links'],
fix_sdfields=self.options['html_cleaner_fix_sd_fields'],
)
with codecs.open(src_path, 'wb', 'utf-8') as fd:
fd.write(new_html)
# Rename images
self.rename_img_files(src_dir, img_name_map)
return src_path, metadata
def process(self, path, metadata):
ext = os.path.splitext(path)[1]
if ext not in self.supported_extensions:
return path, metadata
basename = os.path.basename(path)
src_path = os.path.join(
copy_to_secure_location(path), basename)
src_dir = os.path.dirname(src_path)
remove_file_dir(path)
new_html, img_name_map = cleanup_html(
codecs.open(src_path, 'r', 'utf-8').read(),
basename,
fix_head_nums=self.options['html_cleaner_fix_heading_numbers'],
fix_img_links=self.options['html_cleaner_fix_image_links'],
fix_sdfields=self.options['html_cleaner_fix_sd_fields'],
)
with codecs.open(src_path, 'wb', 'utf-8') as fd:
fd.write(new_html)
# Rename images
self.rename_img_files(src_dir, img_name_map)
return src_path, metadata
def test_cleanup_html_dont_fix_sdfields(self):
html_input = '<p>Blah<sdfield type="PAGE">8</sdfield></p>'
result, img_map = cleanup_html(html_input, 'sample.html',
fix_sdfields=False)
assert html_input == result
def test_cleanup_html_fix_sdfields(self):
html_input = '<p>Blah<sdfield type="PAGE">8</sdfield></p>'
result, img_map = cleanup_html(html_input, 'sample.html')
expected = '<p>Blah<span class="sdfield" type="PAGE">8</span></p>'
assert result == expected
def test_cleanup_html_fix_head_nums_linebreaks(self):
html_input = '<body><h1>\n 1.1.Heading</h1></body>'
result, img_map = cleanup_html(html_input, 'sample.html')
expected = '<body><h1>\n <span class="u-o-headnum">%s</span>'
expected += 'Heading</h1></body>'
assert result == expected % ('1.1.')
def test_cleanup_html_fix_head_nums_tag_attrs(self):
html_input = '<body><h6 class="foo">1.1.Heading</h6></body>'
result, img_map = cleanup_html(html_input, 'sample.html')
expected = '<body><h6 class="foo"><span class="u-o-headnum">%s'
expected += '</span>Heading</h6></body>'
assert result == expected % ('1.1.')
def test_cleanup_html_fix_head_nums_no_nums(self):
html_input = '<body><h1>Heading</h1></body>'
result, img_map = cleanup_html(html_input, 'sample.html')
assert result == '<body><h1>Heading</h1></body>'
def test_cleanup_html_no_minify_by_default(self):
# by default, cleanup_html does not minify code
html_input = '<span>\n<span>foo</span>\n</span>'
result, img_map = cleanup_html(html_input, 'sample.html')
assert result == html_input
def test_cleanup_html_fix_img_links(self, samples_dir):
# we do fix links to images.
html_input = samples_dir.join("image_sample.html").read()
result, img_map = cleanup_html(
html_input, 'sample.html', fix_img_links=True)
assert len(img_map) == 4
