def convert_oo_to_html_and_xhtml(input):
from oo_converters import convert
html_input, images = convert(input, 'html')
xhtml_input, _not_used_ = convert(input, 'xhtml')
enc = chardet.detect(xhtml_input)['encoding']
try_encodings = [enc, 'utf8', 'latin1']
for encoding in try_encodings:
try:
res_content_html = unicode(html_input, encoding)
res_content_xhtml = unicode(xhtml_input, encoding)
break;
except UnicodeDecodeError:
pass
res_content_xhtml = fix_img_path(res_content_html, res_content_xhtml, images)
res_content_html = fix_html_img_path(res_content_html)
if not res_content_html or not res_content_xhtml:
raise Exception('UnicodeDecodeError: could not decode')
return res_content_html, cleanup(res_content_xhtml), images
def convert_oo_to_html(input):
from oo_converters import convert
html_input, images = convert(input, 'html')
enc = chardet.detect(html_input)['encoding']
try_encodings = [enc, 'utf8', 'latin1']
for encoding in try_encodings:
try:
res_content_html = unicode(html_input, encoding)
break;
except UnicodeDecodeError:
pass
if not res_content_html:
raise Exception('UnicodeDecodeError: could not decode')
return res_content_html, images
