def test_non_html_ignored(self, workdir):
# Non .html/.xhtml files are ignored
proc = HTMLCleaner()
sample_path = workdir / "src" / "sample.txt"
resultpath, metadata = proc.process(str(sample_path), {'error': False})
# input was not touched
assert resultpath == str(sample_path)
def test_option_fix_head_nums_false(self, samples_dir, workdir):
# Make sure we respect the `fix_head_nums` option if false.
samples_dir.join("sample3.html").copy(workdir / "src" / "sample.html")
proc = HTMLCleaner(options={'html-cleaner-fix-head-nums': 'False'})
resultpath, metadata = proc.process(
str(workdir / "src" / "sample.html"), {'error': False})
contents = codecs.open(resultpath, 'r', 'utf-8').read()
assert u'<span class="u-o-headnum">1</span>Häding1' not in contents
def test_option_invalid(self):
# Make sure we complain when trash is set as `fix_head_nums`.
with pytest.raises(ArgumentParserError):
HTMLCleaner(options={'html-cleaner-fix-head-nums': 'foo'})
with pytest.raises(ArgumentParserError):
HTMLCleaner(options={'html-cleaner-fix-img-links': 'foo'})
with pytest.raises(ArgumentParserError):
HTMLCleaner(options={'html-cleaner-fix-sdfields': 'foo'})
def test_option_fix_sdfields_true(self, samples_dir, workdir):
# Make sure we respect the `fix_sdtags` option if false
samples_dir.join("sample3.html").copy(workdir / "src" / "sample.html")
proc = HTMLCleaner(options={'html-cleaner-fix-sd-fields': '1'})
resultpath, metadata = proc.process(
str(workdir / "src" / "sample.html"), {'error': False})
contents = codecs.open(resultpath, 'r', 'utf-8').read()
assert u'<sdfield type="PAGE">' not in contents
def test_rename_img_files_src_is_dir(self, workdir):
# We cope with src files that are in fact dirs
proc = HTMLCleaner(
options={'html-cleaner-fix-img-links': '1'})
proc.rename_img_files(
str(workdir), {'src': 'sample.jpg'})
list_dir = os.listdir(str(workdir))
assert 'sample.jpg' not in list_dir
def test_non_html_ignored(self, workdir):
# Non .html/.xhtml files are ignored
proc = HTMLCleaner()
sample_path = workdir / "src" / "sample.txt"
resultpath, metadata = proc.process(
str(sample_path), {'error': False})
# input was not touched
assert resultpath == str(sample_path)
def test_rename_img_files_no_src(self, samples_dir, workdir):
# We cope with not existing source files
samples_dir.join("image_sample_html_m20918026.gif").copy(
workdir / "src" / "image_sample_html_m20918026.gif")
proc = HTMLCleaner(options={'html-cleaner-fix-img-links': '1'})
proc.rename_img_files(str(workdir / "src"),
{'not-existing-filename': 'sample_1.gif'})
list_dir = os.listdir(str(workdir / "src"))
assert 'sample_1.gif' not in list_dir
def test_non_html_ignored(self):
# Non .html/.xhtml files are ignored
proc = HTMLCleaner()
sample_path = os.path.join(self.workdir, 'sample.txt')
open(sample_path, 'w').write('Sample file.')
self.resultpath, metadata = proc.process(
sample_path, {'error': False})
# input was not touched
assert self.resultpath == sample_path
def test_rename_img_files(self):
proc = HTMLCleaner(
options={'html-cleaner-fix-img-links': '1'})
proc.rename_img_files(
self.workdir2,
{'image_sample_html_m20918026.gif': 'sample_1.gif'}
)
list_dir = os.listdir(self.workdir2)
assert 'sample_1.gif' in list_dir
assert 'image_sample_html_m20918026.gif' not in list_dir
def test_option_fix_sdfields_true(self):
# Make sure we respect the `fix_sdtags` option if false
proc = HTMLCleaner(
options={
'html-cleaner-fix-sd-fields': '1'})
self.resultpath, metadata = proc.process(
self.sample_path, {'error': False})
contents = open(self.resultpath, 'rb').read()
snippet = '<sdfield type="PAGE">'
assert snippet not in contents
def test_rename_img_files_no_src(self):
# We cope with not existing source files
proc = HTMLCleaner(
options={'html-cleaner-fix-img-links': '1'})
proc.rename_img_files(
self.workdir2,
{'not-existing-filename': 'sample_1.gif'}
)
list_dir = os.listdir(self.workdir2)
assert 'sample_1.gif' not in list_dir
def test_option_fix_head_nums_false(self, samples_dir, workdir):
# Make sure we respect the `fix_head_nums` option if false.
samples_dir.join("sample3.html").copy(workdir / "src" / "sample.html")
proc = HTMLCleaner(
options={
'html-cleaner-fix-head-nums': 'False'})
resultpath, metadata = proc.process(
str(workdir / "src" / "sample.html"), {'error': False})
contents = codecs.open(resultpath, 'r', 'utf-8').read()
assert u'<span class="u-o-headnum">1</span>Häding1' not in contents
def test_option_fix_sdfields_true(self, samples_dir, workdir):
# Make sure we respect the `fix_sdtags` option if false
samples_dir.join("sample3.html").copy(workdir / "src" / "sample.html")
proc = HTMLCleaner(
options={
'html-cleaner-fix-sd-fields': '1'})
resultpath, metadata = proc.process(
str(workdir / "src" / "sample.html"), {'error': False})
contents = codecs.open(resultpath, 'r', 'utf-8').read()
assert u'<sdfield type="PAGE">' not in contents
def test_cleaner(self, workdir, samples_dir):
# make sure erranous headings are fixed by default.
samples_dir.join("sample3.html").copy(workdir / "src" / "sample.html")
proc = HTMLCleaner()
resultpath, metadata = proc.process(
str(workdir / "src" / "sample.html"), {'error': False})
contents = codecs.open(resultpath, 'r', 'utf-8').read()
u'<span class="u-o-headnum">1</span>Häding1' in contents
u'<span class="u-o-headnum">1.1</span>Heading1.1' in contents
u'<span class="u-o-headnum">1.2.</span>Heading1.2.' in contents
def test_cleaner(self, workdir, samples_dir):
# make sure erranous headings are fixed by default.
samples_dir.join("sample3.html").copy(workdir / "src" / "sample.html")
proc = HTMLCleaner()
resultpath, metadata = proc.process(
str(workdir / "src" / "sample.html"), {'error': False})
contents = codecs.open(resultpath, 'r', 'utf-8').read()
u'<span class="u-o-headnum">1</span>Häding1' in contents
u'<span class="u-o-headnum">1.1</span>Heading1.1' in contents
u'<span class="u-o-headnum">1.2.</span>Heading1.2.' in contents
def test_rename_img_files_src_is_dir(self):
# We cope with src files that are in fact dirs
proc = HTMLCleaner(
options={'html-cleaner-fix-img-links': '1'})
os.mkdir(os.path.join(self.workdir2, 'some_dir'))
proc.rename_img_files(
self.workdir2,
{'some_dir': 'sample.jpg'}
)
list_dir = os.listdir(self.workdir2)
assert 'sample.jpg' not in list_dir
def test_rename_img_files_dst_exists_already(self):
# We cope with dest files that already exist
proc = HTMLCleaner(
options={'html-cleaner-fix-img-links': '1'})
proc.rename_img_files(
self.workdir2,
{'image_sample_html_m20918026.gif':
'image_sample_html_m20918026.gif'}
)
list_dir = os.listdir(self.workdir2)
assert 'image_sample_html_m20918026.gif' in list_dir
def test_rename_img_files_dst_exists_already(self, samples_dir, workdir):
# We cope with dest files that already exist
samples_dir.join("image_sample_html_m20918026.gif").copy(
workdir / "src" / "image_sample_html_m20918026.gif")
proc = HTMLCleaner(options={'html-cleaner-fix-img-links': '1'})
proc.rename_img_files(str(workdir / "src"), {
'image_sample_html_m20918026.gif':
'image_sample_html_m20918026.gif'
})
list_dir = os.listdir(str(workdir / "src"))
assert 'image_sample_html_m20918026.gif' in list_dir
def test_rename_img_files(self, samples_dir, workdir):
# we can rename image files
samples_dir.join("image_sample_html_m20918026.gif").copy(
workdir / "src" / "image_sample_html_m20918026.gif")
proc = HTMLCleaner(options={'html-cleaner-fix-img-links': '1'})
proc.rename_img_files(
str(workdir / "src"),
{'image_sample_html_m20918026.gif': 'sample_1.gif'})
list_dir = os.listdir(str(workdir / "src"))
assert 'sample_1.gif' in list_dir
assert 'image_sample_html_m20918026.gif' not in list_dir
def test_rename_img_files_no_src(self, samples_dir, workdir):
# We cope with not existing source files
samples_dir.join("image_sample_html_m20918026.gif").copy(
workdir / "src" / "image_sample_html_m20918026.gif")
proc = HTMLCleaner(
options={'html-cleaner-fix-img-links': '1'})
proc.rename_img_files(
str(workdir / "src"),
{'not-existing-filename': 'sample_1.gif'}
)
list_dir = os.listdir(str(workdir / "src"))
assert 'sample_1.gif' not in list_dir
def test_option_fix_head_nums_false(self):
# Make sure we respect the `fix_head_nums` option if false.
proc = HTMLCleaner(
options={
'html-cleaner-fix-head-nums': 'False'})
self.resultpath, metadata = proc.process(
self.sample_path, {'error': False})
contents = open(self.resultpath, 'rb').read()
snippet1 = "%s" % (
'<h1 class="foo"><span class="u-o-headnum">1</span>Häding1</h1>')
assert snippet1 not in contents
def test_rename_img_files(self, samples_dir, workdir):
# we can rename image files
samples_dir.join("image_sample_html_m20918026.gif").copy(
workdir / "src" / "image_sample_html_m20918026.gif")
proc = HTMLCleaner(
options={'html-cleaner-fix-img-links': '1'})
proc.rename_img_files(
str(workdir / "src"),
{'image_sample_html_m20918026.gif': 'sample_1.gif'}
)
list_dir = os.listdir(str(workdir / "src"))
assert 'sample_1.gif' in list_dir
assert 'image_sample_html_m20918026.gif' not in list_dir
def test_option_fix_img_links_true(self):
# Make sure we respect the `fix_img_links` option if true
proc = HTMLCleaner(
options={
'html-cleaner-fix-img-links': '1'})
self.resultpath, metadata = proc.process(
self.img_sample_path, {'error': False})
contents = open(self.resultpath, 'rb').read()
resultdir = os.path.dirname(self.resultpath)
snippet = '<IMG SRC="image_sample_html_m20918026.gif"'
list_dir = os.listdir(resultdir)
assert snippet not in contents
assert 'image_sample_html_m20918026.gif' not in list_dir
assert 'sample_1.gif' in list_dir
def test_rename_img_files_dst_exists_already(self, samples_dir, workdir):
# We cope with dest files that already exist
samples_dir.join("image_sample_html_m20918026.gif").copy(
workdir / "src" / "image_sample_html_m20918026.gif")
proc = HTMLCleaner(
options={'html-cleaner-fix-img-links': '1'})
proc.rename_img_files(
str(workdir / "src"),
{
'image_sample_html_m20918026.gif':
'image_sample_html_m20918026.gif'
}
)
list_dir = os.listdir(str(workdir / "src"))
assert 'image_sample_html_m20918026.gif' in list_dir
def test_option_fix_img_links_true(self, samples_dir, workdir):
# Make sure we respect the `fix_img_links` option if true
samples_dir.join("image_sample.html").copy(workdir / "src" /
"sample.html")
samples_dir.join("image_sample_html_m20918026.gif").copy(
workdir / "src" / "image_sample_html_m20918026.gif")
proc = HTMLCleaner(options={'html-cleaner-fix-img-links': '1'})
resultpath, metadata = proc.process(
str(workdir / "src" / "sample.html"), {'error': False})
contents = open(resultpath, 'r').read()
resultdir = os.path.dirname(resultpath)
snippet = '<IMG SRC="image_sample_html_m20918026.gif"'
list_dir = os.listdir(resultdir)
assert snippet not in contents
assert 'image_sample_html_m20918026.gif' not in list_dir
assert 'sample_1.gif' in list_dir
def test_cleaner(self):
# make sure erranous headings are fixed by default.
proc = HTMLCleaner()
self.resultpath, metadata = proc.process(
self.sample_path, {'error': False})
contents = open(self.resultpath, 'rb').read()
snippet1 = "%s" % (
'<span class="u-o-headnum">1</span>Häding1')
snippet2 = "%s" % (
'<span class="u-o-headnum">1.1</span>Heading1.1')
snippet3 = "%s" % (
'<span class="u-o-headnum">1.2.</span>Heading1.2.')
assert snippet1 in contents
assert snippet2 in contents
assert snippet3 in contents
def test_option_fix_img_links_true(self, samples_dir, workdir):
# Make sure we respect the `fix_img_links` option if true
samples_dir.join("image_sample.html").copy(
workdir / "src" / "sample.html")
samples_dir.join("image_sample_html_m20918026.gif").copy(
workdir / "src" / "image_sample_html_m20918026.gif")
proc = HTMLCleaner(
options={
'html-cleaner-fix-img-links': '1'})
resultpath, metadata = proc.process(
str(workdir / "src" / "sample.html"), {'error': False})
contents = open(resultpath, 'r').read()
resultdir = os.path.dirname(resultpath)
snippet = '<IMG SRC="image_sample_html_m20918026.gif"'
list_dir = os.listdir(resultdir)
assert snippet not in contents
assert 'image_sample_html_m20918026.gif' not in list_dir
assert 'sample_1.gif' in list_dir
def test_rename_img_files_src_is_dir(self, workdir):
# We cope with src files that are in fact dirs
proc = HTMLCleaner(options={'html-cleaner-fix-img-links': '1'})
proc.rename_img_files(str(workdir), {'src': 'sample.jpg'})
list_dir = os.listdir(str(workdir))
assert 'sample.jpg' not in list_dir