def process(self):
try:
# Convert from other office format to odt if needed
filename, extension = os.path.splitext(self.original_filename)
odt_filename = str(filename) + '.odt'
if(extension != '.odt'):
self._convert_to_odt(filename)
# Convert and save all the resulting files.
tree, files, errors = transform(odt_filename)
cnxml = clean_cnxml(etree.tostring(tree))
save_cnxml(self.save_dir, cnxml, files.items())
# now validate with jing
validate_cnxml(cnxml)
except ConversionError as e:
return render_conversionerror(self.request, e.msg)
except Exception:
tb = traceback.format_exc()
self.write_traceback_to_zipfile(tb)
templatePath = 'templates/error.pt'
response = {'traceback': tb}
if('title' in self.request.session):
del self.request.session['title']
return render_to_response(templatePath, response, request=self.request)
self.request.session.flash(self.message)
return HTTPFound(location=self.request.route_url(self.nextStep()))
def process_gdocs_resource(self, save_dir, gdocs_resource_id, gdocs_access_token=None):
# login to gdocs and get a client object
gd_client = getAuthorizedGoogleDocsClient()
# Create a AuthSub Token based on gdocs_access_token String
auth_sub_token = gdata.gauth.AuthSubToken(gdocs_access_token) \
if gdocs_access_token \
else None
# get the Google Docs Entry
gd_entry = gd_client.GetDoc(gdocs_resource_id, None, auth_sub_token)
# Get the contents of the document
gd_entry_url = gd_entry.content.src
html = gd_client.get_file_content(gd_entry_url, auth_sub_token)
# Transformation and get images
cnxml, objects = gdocs_to_cnxml(html, bDownloadImages=True)
cnxml = clean_cnxml(cnxml)
save_cnxml(save_dir, cnxml, objects.items())
validate_cnxml(cnxml)
# Return the title and filename. Old comment states
# that returning this filename might kill the ability to
# do multiple tabs in parallel, unless it gets offloaded
# onto the form again.
return (gd_entry.title.text, "Google Document")
def _process_gdocs_resource(klass, save_dir, html):
# Transformation and get images
cnxml, objects = gdocs_to_cnxml(html, bDownloadImages=True)
cnxml = clean_cnxml(cnxml)
save_cnxml(save_dir, cnxml, objects.items())
validate_cnxml(cnxml)
return "Google Document"
def process(self):
try:
f = open(self.original_filename)
latex_archive = f.read()
# LaTeX 2 CNXML transformation
cnxml, objects = latex_to_cnxml(latex_archive, self.original_filename)
cnxml = clean_cnxml(cnxml)
save_cnxml(self.save_dir, cnxml, objects.items())
validate_cnxml(cnxml)
except ConversionError as e:
return render_conversionerror(self.request, e.msg)
except Exception:
tb = traceback.format_exc()
self.write_traceback_to_zipfile(tb)
templatePath = 'templates/error.pt'
response = {'traceback': tb}
if('title' in self.request.session):
del self.request.session['title']
return render_to_response(templatePath, response, request=self.request)
self.request.session.flash(self.message)
return HTTPFound(location=self.request.route_url(self.nextStep()))
def process(self, form):
try:
# Convert from other office format to odt if needed
filename, extension = os.path.splitext(self.original_filename)
odt_filename = str(filename) + '.odt'
if (extension != '.odt'):
self._convert_to_odt(filename)
# Convert and save all the resulting files.
tree, files, errors = transform(odt_filename)
cnxml = clean_cnxml(etree.tostring(tree))
save_cnxml(self.save_dir, cnxml, files.items())
# now validate with jing
validate_cnxml(cnxml)
except ConversionError as e:
return render_conversionerror(self.request, e.msg)
except Exception:
tb = traceback.format_exc()
self.write_traceback_to_zipfile(tb, form)
templatePath = 'templates/error.pt'
response = {'traceback': tb}
if ('title' in self.request.session):
del self.request.session['title']
return render_to_response(templatePath,
response,
request=self.request)
self.request.session.flash(self.message)
return HTTPFound(location=self.request.route_url(self.nextStep()))
def process(self, form):
try:
f = open(self.original_filename)
latex_archive = f.read()
# LaTeX 2 CNXML transformation
cnxml, objects = latex_to_cnxml(latex_archive,
self.original_filename)
cnxml = clean_cnxml(cnxml)
save_cnxml(self.save_dir, cnxml, objects.items())
validate_cnxml(cnxml)
except ConversionError as e:
return render_conversionerror(self.request, e.msg)
except Exception:
tb = traceback.format_exc()
self.write_traceback_to_zipfile(tb, form)
templatePath = 'templates/error.pt'
response = {'traceback': tb}
if ('title' in self.request.session):
del self.request.session['title']
return render_to_response(templatePath,
response,
request=self.request)
self.request.session.flash(self.message)
return HTTPFound(location=self.request.route_url(self.nextStep()))
def _process_gdocs_resource(klass, save_dir, html, kix=None):
# Transformation and get images
cnxml, objects = gdocs_to_cnxml(html,
kixcontent=kix,
bDownloadImages=True)
cnxml = clean_cnxml(cnxml)
save_cnxml(save_dir, cnxml, objects.items())
validate_cnxml(cnxml)
return "Google Document"
def process(self):
try:
url = self.form.data['url_text']
# Build a regex for Google Docs URLs
regex = re.compile(
"^https:\/\/docs\.google\.com\/.*document\/[^\/]\/([^\/]+)\/")
r = regex.search(url)
# Take special action for Google Docs URLs
if r:
gdocs_resource_id = r.groups()[0]
doc_id = "document:" + gdocs_resource_id
title, filename = self.process_gdocs_resource(self.save_dir,
doc_id)
self.request.session['title'] = title
self.request.session['filename'] = filename
else:
# download html:
# Simple urlopen() will fail on mediawiki websites eg. Wikipedia!
import_opener = urllib2.build_opener()
import_opener.addheaders = [('User-agent', 'Mozilla/5.0')]
import_request = import_opener.open(url)
html = import_request.read()
# transformation
cnxml, objects, html_title = htmlsoup_to_cnxml(
html, bDownloadImages=True, base_or_source_url=url)
self.request.session['title'] = html_title
cnxml = clean_cnxml(cnxml)
save_cnxml(self.save_dir, cnxml, objects.items())
# Keep the info we need for next uploads. Note that
# this might kill the ability to do multiple tabs in
# parallel, unless it gets offloaded onto the form
# again.
self.request.session['filename'] = "HTML Document"
validate_cnxml(cnxml)
except ConversionError as e:
return render_conversionerror(self.request, e.msg)
except Exception:
tb = traceback.format_exc()
self.write_traceback_to_zipfile(tb)
templatePath = 'templates/error.pt'
response = {'traceback': tb}
if('title' in self.request.session):
del self.request.session['title']
return render_to_response(templatePath, response, request=self.request)
self.request.session.flash(self.message)
return HTTPFound(location=self.request.route_url(self.nextStep()))
def process(self, zip_filename):
try:
self.zip_archive = zipfile.ZipFile(zip_filename, 'r')
# Unzip into transform directory
self.zip_archive.extractall(path=self.save_dir)
# Rename ZIP file so that the user can download it again
os.rename(zip_filename, os.path.join(self.save_dir, 'upload.zip'))
# Read CNXML
with open(os.path.join(self.save_dir, 'index.cnxml'), 'rt') as fp:
cnxml = fp.read()
# Convert the CNXML to XHTML for preview
html = cnxml_to_htmlpreview(cnxml)
with open(os.path.join(self.save_dir, 'index.xhtml'),
'w') as index:
index.write(html)
cnxml = clean_cnxml(cnxml)
validate_cnxml(cnxml)
except ConversionError as e:
return render_conversionerror(self.request, e.msg)
except Exception:
tb = traceback.format_exc()
self.write_traceback_to_zipfile(tb, form)
templatePath = 'templates/error.pt'
response = {'traceback': tb}
if ('title' in self.request.session):
del self.request.session['title']
return render_to_response(templatePath,
response,
request=self.request)
self.request.session.flash(self.message)
return HTTPFound(location=self.request.route_url(self.nextStep()))
def process(self, zip_filename):
try:
self.zip_archive = zipfile.ZipFile(zip_filename, 'r')
# Unzip into transform directory
self.zip_archive.extractall(path=self.save_dir)
# Rename ZIP file so that the user can download it again
os.rename(zip_filename,
os.path.join(self.save_dir, 'upload.zip'))
# Read CNXML
with open(os.path.join(self.save_dir, 'index.cnxml'), 'rt') as fp:
cnxml = fp.read()
# Convert the CNXML to XHTML for preview
html = cnxml_to_htmlpreview(cnxml)
with open(os.path.join(self.save_dir, 'index.xhtml'), 'w') as index:
index.write(html)
cnxml = clean_cnxml(cnxml)
validate_cnxml(cnxml)
except ConversionError as e:
return render_conversionerror(self.request, e.msg)
except Exception:
tb = traceback.format_exc()
self.write_traceback_to_zipfile(tb)
templatePath = 'templates/error.pt'
response = {'traceback': tb}
if('title' in self.request.session):
del self.request.session['title']
return render_to_response(templatePath, response, request=self.request)
self.request.session.flash(self.message)
return HTTPFound(location=self.request.route_url(self.nextStep()))
def process(self, form):
try:
url = form.data['url_text']
# Build a regex for Google Docs URLs
regex = re.compile(
"^https:\/\/docs\.google\.com\/.*document\/[^\/]\/([^\/]+)\/")
r = regex.search(url)
# Take special action for Google Docs URLs
if r is not None:
gdocs_resource_id = r.groups()[0]
http = httplib2.Http()
http.follow_redirects = False
try:
resp, html = http.request(
'https://docs.google.com/document/d/%s/export?format=html&confirm=no_antivirus' % gdocs_resource_id)
except HttpError:
pass
else:
# Check that status was OK, google docs sends a redirect to a login
# page if not.
if resp.status / 100 == 2:
# Get the title (does not work anymore)
title = 'Untitled Google Document'
# Process it
P = GoogleDocProcessor(self.request)
return P.process_gdocs_resource(html, title, form)
self.request.session.flash('Failed to convert google document')
return HTTPFound(location=self.request.route_url('choose'))
else:
# download html:
# Simple urlopen() will fail on mediawiki websites eg. Wikipedia!
import_opener = urllib2.build_opener()
import_opener.addheaders = [('User-agent', 'Mozilla/5.0')]
import_request = import_opener.open(url)
html = import_request.read()
# transformation
cnxml, objects, html_title = htmlsoup_to_cnxml(
html, bDownloadImages=True, base_or_source_url=url)
self.request.session['title'] = html_title
cnxml = clean_cnxml(cnxml)
save_cnxml(self.save_dir, cnxml, objects.items())
# Keep the info we need for next uploads. Note that
# this might kill the ability to do multiple tabs in
# parallel, unless it gets offloaded onto the form
# again.
self.request.session['filename'] = "HTML Document"
validate_cnxml(cnxml)
except ConversionError as e:
return render_conversionerror(self.request, e.msg)
except Exception:
tb = traceback.format_exc()
self.write_traceback_to_zipfile(tb, form)
templatePath = 'templates/error.pt'
response = {'traceback': tb}
if('title' in self.request.session):
del self.request.session['title']
return render_to_response(templatePath, response, request=self.request)
self.request.session.flash(self.message)
return HTTPFound(location=self.request.route_url(self.nextStep()))
def process(self, form):
try:
url = form.data['url_text']
# Build a regex for Google Docs URLs
regex = re.compile(
"^https:\/\/docs\.google\.com\/.*document\/[^\/]\/([^\/]+)\/")
r = regex.search(url)
# Take special action for Google Docs URLs
if r is not None:
gdocs_resource_id = r.groups()[0]
http = httplib2.Http()
http.follow_redirects = False
try:
resp, html = http.request(
'https://docs.google.com/document/d/%s/export?format=html&confirm=no_antivirus'
% gdocs_resource_id)
resp2, kix = http.request(
'https://docs.google.com/feeds/download/documents/export/Export?id=%s&exportFormat=kix'
% gdocs_resource_id)
except HttpError:
pass
else:
# Check that status was OK, google docs sends a redirect to a login
# page if not.
if resp.status / 100 == 2:
# Get the title
title = 'Untitled Google Document'
# Process it
P = GoogleDocProcessor(self.request)
return P.process_gdocs_resource(html, title, form, kix)
self.request.session.flash('Failed to convert google document')
return HTTPFound(location=self.request.route_url('choose'))
else:
# download html:
# Simple urlopen() will fail on mediawiki websites eg. Wikipedia!
import_opener = urllib2.build_opener()
import_opener.addheaders = [('User-agent', 'Mozilla/5.0')]
import_request = import_opener.open(url)
html = import_request.read()
# transformation
cnxml, objects, html_title = htmlsoup_to_cnxml(
html, bDownloadImages=True, base_or_source_url=url)
self.request.session['title'] = html_title
cnxml = clean_cnxml(cnxml)
save_cnxml(self.save_dir, cnxml, objects.items())
# Keep the info we need for next uploads. Note that
# this might kill the ability to do multiple tabs in
# parallel, unless it gets offloaded onto the form
# again.
self.request.session['filename'] = "HTML Document"
validate_cnxml(cnxml)
except ConversionError as e:
return render_conversionerror(self.request, e.msg)
except Exception:
tb = traceback.format_exc()
self.write_traceback_to_zipfile(tb, form)
templatePath = 'templates/error.pt'
response = {'traceback': tb}
if ('title' in self.request.session):
del self.request.session['title']
return render_to_response(templatePath,
response,
request=self.request)
self.request.session.flash(self.message)
return HTTPFound(location=self.request.route_url(self.nextStep()))