def EpozTidy(self, html, pageurl):
""" Take html and deliver xhtml if mxTidy is installed;
call EpozPostTidy for html-postprocessings before returning the result
"""
errors = 0
output = html
errordata = ""
input = html.encode("utf-8")
input = EPOZ_SCRIPT.sub('<script ', input)
input = input.replace('</epoz:script>', '</script>')
if uWordUnmunger:
input = unmungeString(input)
if mxTidyIsAvailable:
(errors, warnings, output, errordata) = Tidy.tidy(
input, drop_empty_paras=1, logical_emphasis=1, indent_spaces=1,
indent="no", output_xhtml=1, word_2000=1, wrap=0, alt_text='',
char_encoding="utf8")
# (errors, warnings, output, errordata) = Tidy.tidy(
# input, drop_empty_paras=1, indent_spaces=1, indent="auto",
# output_xhtml=1, word_2000=1, wrap=79, char_encoding="utf8")
if errors:
output = html
elif uTidyIsAvailable:
parsed = tidy.parseString(
input, drop_empty_paras=1, indent_spaces=1, indent="auto",
output_xhtml=1, word_2000=1, wrap=79, char_encoding="utf8",
add_xml_decl=0, doctype="omit", indent_attributes=1,
drop_proprietary_attributes=1, bare=1, clean=1,
enclose_text=1, tidy_mark=0)
reports = parsed.get_errors()
all_errors = [str(x) for x in reports if x.severity != 'W']
errors = len(all_errors)
errordata = '\n'.join(all_errors)
if errors:
output = html
else:
output = str(parsed)
output = MSO_CLASS.sub(r"<\1>", output)
result = HTML_BODY.search(output)
if result:
output = result.group(1)
# Call External Method / PythonScript for postprocessing
# The script should expect two parameters:
# self = called context (=server)
# html = the htmlbody to postprocess
# pathname = path of edited object (maybe with template!)
# The script should return the new htmlbody
EpozPostTidy = getattr(self, 'EpozPostTidy', None)
if EpozPostTidy is not None:
output = EpozPostTidy(self, output, pageurl)
return (errors, output, errordata)
</head>
<body>
---ö---ü---
</body>
</html>
"""
### Testing string buffer interface...
print 'Testing file parsing...',
open('testWalter.xml', 'wb').write(data)
(nerrors, nwarnings, outputdata,
error) = Tidy.tidy(open('testWalter.xml', 'rb'),
open('output.xml', 'wb'),
numeric_entities=1,
output_xhtml=1,
char_encoding="latin1")
print error,
outputdata = open('output.xml', 'rb').read()
if outputdata != verifydata:
print '*** Output does NOT verify OK !'
else:
print 'OK'
print
### Testing file interface...
print 'Testing data parsing...',
(nerrors, nwarnings, outputdata, error) = Tidy.tidy(data,
numeric_entities=1,
<title>---ä---ä---</title>
</head>
<body>
---ö---ü---
</body>
</html>
"""
### Testing string buffer interface...
print 'Testing file parsing...',
open('testWalter.xml', 'wb').write(data)
(nerrors, nwarnings, outputdata, error) = Tidy.tidy(open('testWalter.xml', 'rb'),
open('output.xml', 'wb'),
numeric_entities=1,
output_xhtml=1,
char_encoding="latin1")
print error,
outputdata = open('output.xml', 'rb').read()
if outputdata != verifydata:
print '*** Output does NOT verify OK !'
else:
print 'OK'
print
### Testing file interface...
print 'Testing data parsing...',
(nerrors, nwarnings, outputdata, error) = Tidy.tidy(data,
numeric_entities=1,