def html(self):
htmlfile = open(self.fullname + '.htm', 'r')
html = htmlfile.read()
htmlfile.close()
html = SafeHTML().scrub_html(html)
body = bodyfinder(html)
return body
def html(self):
htmlfile = open(self.fullname + '.htm', 'r')
html = htmlfile.read()
htmlfile.close()
html = SafeHTML().scrub_html(html)
body = bodyfinder(html)
return body
def html(self):
htmlfile = open("%s/%s.html" % (self.tmpdir, self.__name__), 'r')
html = htmlfile.read()
htmlfile.close()
html = scrubHTMLNoRaise(html)
body = bodyfinder(html)
return body
def html(self):
htmlfile = open(self.fullname + '.htm', 'r')
html = htmlfile.read()
htmlfile.close()
html = scrubHTMLNoRaise(html)
body = bodyfinder(html)
return body
def html(self):
htmlfile = open(self.outputfile, 'r')
html = htmlfile.read()
htmlfile.close()
html = scrubHTML(html)
body = bodyfinder(html)
return body
def html(self):
htmlfile = open(self.fullname + '.htm', 'r')
html = htmlfile.read()
htmlfile.close()
html = scrubHTMLNoRaise(html)
body = bodyfinder(html)
return body
def html(self):
htmlfile = open("%s/%s.html" % (self.tmpdir, self.__name__), 'r')
html = htmlfile.read()
htmlfile.close()
html = scrubHTML(html)
body = bodyfinder(html)
return body
def html(self):
htmlfile = open(self.outputfile, "r")
html = htmlfile.read()
htmlfile.close()
html = scrubHTMLNoRaise(html)
body = bodyfinder(html)
return body
def html(self):
htmlfile = open(self.fullname + ".htm", "r")
html = htmlfile.read()
htmlfile.close()
html = scrubHTML(html)
body = bodyfinder(html)
return body
def _html(self):
htmlfile = open(pjoin(self.tmpdir, self.__name__+".html"), 'r')
html = htmlfile.read()
htmlfile.close()
#html = scrubHTML(html)
body = bodyfinder(html)
body = xmltag + body
return body
def _html(self):
htmlfile = open(pjoin(self.tmpdir, self.__name__ + ".html"), 'r')
html = htmlfile.read()
htmlfile.close()
#html = scrubHTML(html)
body = bodyfinder(html)
body = xmltag + body
return body
def _html(self):
htmlfile = open(pjoin(self.tmpdir, self.__name__+".html"), 'r')
html = htmlfile.read()
if process_double_encoding:
html = noDoubleEncoding(html)
htmlfile.close()
html = scrubHTML(html)
body = bodyfinder(html)
return body
def _html(self):
htmlfile = open(pjoin(self.tmpdir, self.__name__+".html"), 'r')
html = htmlfile.read()
if process_double_encoding:
html = noDoubleEncoding(html)
htmlfile.close()
html = scrubHTML(html)
body = bodyfinder(html)
return body
class document(commandtransform):
file_ext = ''
def __init__(self, name, data, exec_prefix=None):
""" Initialization: create tmp work directory and copy the
document into a file"""
tika_path = 'tika'
if exec_prefix is not None:
tika_path = os.path.join(exec_prefix, 'tika-bin')
if not os.path.exists(tika_path):
tika_path = os.path.join(exec_prefix, 'tika')
if not os.path.exists(tika_path):
log.warn('no tika-bin or tika found in exec-prefix: %s' %
tika_path)
tika_path = 'tika'
commandtransform.__init__(self, name, binary=tika_path)
name = self.name()
if not name.endswith(self.file_ext):
name = name + self.file_ext
self.tmpdir, self.fullname = self.initialize_tmpdir(data,
filename=name)
def convert(self):
"Convert the document"
tmpdir = self.tmpdir
htmlfile = open("%s/%s.html" % (self.tmpdir, self.__name__), 'w')
# for windows, install wvware from GnuWin32 at C:\Program Files\GnuWin32\bin
# you can use:
# wvware.exe -c ..\share\wv\wvHtml.xml --charset=utf-8 -d d:\temp d:\temp\test.doc > test.html
if os.name == 'posix':
try:
subprocess.check_call([self.binary, self.fullname],
stdout=htmlfile,
cwd=tmpdir)
except subprocess.CalledProcessError as cpe:
log.warn('Could not transform %s: %s' % (self.fullname, cpe))
htmlfile.close()
def html(self):
htmlfile = open("%s/%s.html" % (self.tmpdir, self.__name__), 'r')
html = htmlfile.read()
htmlfile.close()
html = safe_unicode(html)
try:
html = laundryutils.sanitize(html, HTMLCleaner)
except Exception, err:
html = ''
# scrubHTML is EVIL, takes ages!
#html = scrubHTML(html)
body = bodyfinder(html)
body = body.encode('utf-8')
return body
def convert(self, data, cache, **kwargs):
tmp = NamedTemporaryFile()
tmp.write(data)
tmp.flush()
cmd = ['xlhtml', tmp.name]
p = Popen(cmd, stdout=PIPE, stderr=PIPE)
stdout, stderr = p.communicate()
body = bodyfinder(stdout)
cache.setData(body)
return cache
def convert(self, data, cache, **kwargs):
kwargs['filename'] = 'unknown.pdf'
tmpdir, fullname = self.initialize_tmpdir(data, **kwargs)
html = self.invokeCommand(tmpdir, fullname)
path, images = self.subObjects(tmpdir)
objects = {}
if images:
self.fixImages(path, images, objects)
self.cleanDir(tmpdir)
cache.setData(bodyfinder(html))
cache.setSubObjects(objects)
return cache
def _html(self):
try:
htmlfile = open(pjoin(self.tmpdir, self.__name__+".html"), 'r')
html = htmlfile.read()
except IOError:
return ""
if process_double_encoding :
html = noDoubleEncoding(html)
htmlfile.close()
#xlhtml gives verry complex html ; scrubHTML takes soooo long !
#html = scrubHTML(html)
body = bodyfinder(html)
return body
def convert(self, data, cache, **kwargs):
kwargs['filename'] = 'unknow.rtf'
tmpdir, fullname = self.initialize_tmpdir(data, **kwargs)
html = self.invokeCommand(tmpdir, fullname)
path, images = self.subObjects(tmpdir)
objects = {}
if images:
self.fixImages(path, images, objects)
self.cleanDir(tmpdir)
cache.setData(bodyfinder(html))
cache.setSubObjects(objects)
return cache
def get_text_from_view(view_name):
"""
Text get from a browser view template <body> tag
"""
portal = api.portal.get()
request = getattr(portal, "REQUEST", None)
if request is not None:
view = api.content.get_view(name=view_name, context=portal, request=request)
if view is not None:
text = bodyfinder(view.index()).strip()
if not isinstance(text, text_type):
text = text.decode("utf-8")
return text
return ""
def _html(self):
try:
htmlfile = open(pjoin(self.tmpdir, self.__name__ + ".html"), 'r')
html = htmlfile.read()
except IOError:
return ""
htmlfile.close()
if process_double_encoding:
# This operation can be very memory-consuming ...
try:
html = noDoubleEncoding(html)
except MemoryError:
return ""
#xlhtml gives verry complex html ; scrubHTML takes soooo long !
#html = scrubHTML(html)
body = bodyfinder(html)
return body
def _html(self):
try:
htmlfile = open(pjoin(self.tmpdir, self.__name__+".html"), 'r')
html = htmlfile.read()
except IOError:
return ""
htmlfile.close()
if process_double_encoding :
# This operation can be very memory-consuming ...
try:
html = noDoubleEncoding(html)
except MemoryError:
return ""
#xlhtml gives verry complex html ; scrubHTML takes soooo long !
#html = scrubHTML(html)
body = bodyfinder(html)
return body
def get_default_text(context):
"""
Text get from a browser view template <body> tag
"""
portal = api.portal.get()
view_name = 'default_gdpr_text'
request = getattr(portal, 'REQUEST', None)
if request is not None:
view = api.content.get_view(
name=view_name,
context=portal,
request=request
)
if view is not None:
text = bodyfinder(view.index()).strip()
if not isinstance(text, unicode):
text = text.decode("utf-8")
return text
return u''
def getData(self, couterr):
return bodyfinder(couterr.read())
def getData(self, couterr):
return bodyfinder(couterr.read())
def convert(self, orig, data, **kwargs):
body = bodyfinder(orig)
data.setData(body)
return data
def convert(self, orig, data, **kwargs):
body = bodyfinder(orig)
data.setData(body)
return data
