def test_default_xhtml(self):
# make sure by default we get XHTML output from HTML.
proc = Tidy()
self.resultpath, metadata = proc.process(
self.sample_path, {'error': False})
contents = open(self.resultpath, 'rb').read()
assert 'xmlns="http://www.w3.org/1999/xhtml"' in contents
def test_default_xhtml(self, workdir, samples_dir):
# make sure by default we get XHTML output from HTML.
samples_dir.join("sample1.html").copy(workdir / "src" / "sample.html")
proc = Tidy()
resultpath, metadata = proc.process(
str(workdir / "src" / "sample.html"), {'error': False})
contents = open(resultpath, 'rb').read()
assert b'xmlns="http://www.w3.org/1999/xhtml"' in contents
def test_encoding_utf8(self):
# make sure we get UTF-8 output and no special stuff.
proc = Tidy()
self.resultpath, metadata = proc.process(
self.sample_path, {'error': False})
contents = open(self.resultpath, 'rb').read()
assert 'Ü' in contents
assert 'Ü' not in contents
def test_non_html_ignored(self, workdir):
# we do not try to tidy non html/xhtml files
proc = Tidy()
sample_path = workdir / "sample.txt"
sample_path.write('Sample file.')
resultpath, metadata = proc.process(str(sample_path), {'error': False})
# the document path hasn't changed
assert resultpath == str(sample_path)
def test_default_xhtml(self, workdir, samples_dir):
# make sure by default we get XHTML output from HTML.
samples_dir.join("sample1.html").copy(workdir / "src" / "sample.html")
proc = Tidy()
resultpath, metadata = proc.process(
str(workdir / "src" / "sample.html"), {'error': False})
contents = open(resultpath, 'rb').read()
assert b'xmlns="http://www.w3.org/1999/xhtml"' in contents
def test_non_html_ignored(self, workdir):
# we do not try to tidy non html/xhtml files
proc = Tidy()
sample_path = workdir / "sample.txt"
sample_path.write('Sample file.')
resultpath, metadata = proc.process(
str(sample_path), {'error': False})
# the document path hasn't changed
assert resultpath == str(sample_path)
def test_encoding_utf8(self, workdir, samples_dir):
# make sure we get UTF-8 output and no special stuff.
samples_dir.join("sample1.html").copy(workdir / "src" / "sample.html")
proc = Tidy()
resultpath, metadata = proc.process(
str(workdir / "src" / "sample.html"), {'error': False})
contents = codecs.open(resultpath, 'r', encoding='utf-8').read()
assert u'Ü' in contents
assert u'Ü' not in contents
def test_non_html_ignored(self):
# we do not try to tidy non html/xhtml files
proc = Tidy()
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})
# the document path hasn't changed
assert self.resultpath == sample_path
def test_encoding_utf8(self, workdir, samples_dir):
# make sure we get UTF-8 output and no special stuff.
samples_dir.join("sample1.html").copy(workdir / "src" / "sample.html")
proc = Tidy()
resultpath, metadata = proc.process(
str(workdir / "src" / "sample.html"), {'error': False})
contents = codecs.open(resultpath, 'r', encoding='utf-8').read()
assert u'Ü' in contents
assert u'Ü' not in contents
