def __init__(self, config_dir, data_dir):
self.doc = None
self.config_dir = config_dir
self.data_dir = data_dir
os.chdir(data_dir)
libxml2.initializeCatalog()
libxml2.loadCatalog(os.path.join(data_dir, "catalog.xml"))
parser = libxml2.createFileParserCtxt(
os.path.join(config_dir, "jjigw.xml"))
parser.validate(1)
parser.parseDocument()
if not parser.isValid():
raise JJIGWFatalError, "Invalid configuration"
self.doc = parser.doc()
self.connect = ConnectConfig(self.doc.xpathEval("jjigw/connect")[0])
self.jid = None
self.networks = {}
for n in self.doc.xpathEval("jjigw/network"):
network = NetworkConfig(n)
if not self.jid:
self.jid = network.jid
self.networks[network.jid.domain] = network
spidentd = self.doc.xpathEval("jjigw/spidentd")
if spidentd:
self.spidentd = SPIdentDConfig(spidentd[0])
else:
self.spidentd = None
self.admins = []
for n in self.doc.xpathEval("jjigw/admin"):
self.admins.append(JID(n.getContent()))
def __init__(self,config_dir,data_dir):
self.doc=None
self.config_dir=config_dir
self.data_dir=data_dir
os.chdir(data_dir)
libxml2.initializeCatalog()
libxml2.loadCatalog(os.path.join(data_dir,"catalog.xml"))
parser=libxml2.createFileParserCtxt(os.path.join(config_dir,"jjigw.xml"))
parser.validate(1)
parser.parseDocument()
if not parser.isValid():
raise JJIGWFatalError,"Invalid configuration"
self.doc=parser.doc()
self.connect=ConnectConfig(self.doc.xpathEval("jjigw/connect")[0])
self.jid=None
self.networks={}
for n in self.doc.xpathEval("jjigw/network"):
network=NetworkConfig(n)
if not self.jid:
self.jid=network.jid
self.networks[network.jid.domain]=network
spidentd=self.doc.xpathEval("jjigw/spidentd")
if spidentd:
self.spidentd=SPIdentDConfig(spidentd[0])
else:
self.spidentd=None
self.admins=[]
for n in self.doc.xpathEval("jjigw/admin"):
self.admins.append(JID(n.getContent()))
def load(self):
""" Load the document """
if self.filepath is None:
raise DocumentError('The document source file path is not defined.')
# Create the catalog lists
catalogs = self.get_catalogs_list()
# Load the catalogs
for catalog in catalogs:
libxml2.loadCatalog(catalog)
# Load the document
self.xml = libxml2.parseFile(self.filepath)
# Process the XInclude part
res = self.xml.xincludeProcess()
def xsl_transform(content, bDownloadImages):
# 1
strTidiedHtml = tidy_and_premail(content)
# 2 Settings for libxml2 for transforming XHTML entities to valid XML
libxml2.loadCatalog(XHTML_ENTITIES)
libxml2.lineNumbersDefault(1)
libxml2.substituteEntitiesDefault(1)
# 3 First XSLT transformation
styleDoc1 = libxml2.parseFile(GDOCS2CNXML_XSL1)
style1 = libxslt.parseStylesheetDoc(styleDoc1)
# doc1 = libxml2.parseFile(afile))
doc1 = libxml2.parseDoc(strTidiedHtml)
result1 = style1.applyStylesheet(doc1, None)
#style1.saveResultToFilename(os.path.join('output', docFilename + '_meta.xml'), result1, 1)
strResult1 = style1.saveResultToString(result1)
style1.freeStylesheet()
doc1.freeDoc()
result1.freeDoc()
# Parse XML with etree from lxml for TeX2MathML and image download
etreeXml = etree.fromstring(strResult1)
# 4 Convert TeX to MathML with Blahtex
etreeXml = tex2mathml(etreeXml)
# 5 Optional: Download Google Docs Images
imageObjects = {}
if bDownloadImages:
etreeXml, imageObjects = downloadImages(etreeXml)
# Convert etree back to string
strXml = etree.tostring(etreeXml) # pretty_print=True)
# 6 Second transformation
styleDoc2 = libxml2.parseFile(GDOCS2CNXML_XSL2)
style2 = libxslt.parseStylesheetDoc(styleDoc2)
doc2 = libxml2.parseDoc(strXml)
result2 = style2.applyStylesheet(doc2, None)
#style2.saveResultToFilename('tempresult.xml', result2, 0) # just for debugging
strResult2 = style2.saveResultToString(result2)
style2.freeStylesheet()
doc2.freeDoc()
result2.freeDoc()
return strResult2, imageObjects
def xsl_transform(content, bDownloadImages):
# 1
strTidiedHtml = tidy_and_premail(content)
# 2 Settings for libxml2 for transforming XHTML entities to valid XML
libxml2.loadCatalog(XHTML_ENTITIES)
libxml2.lineNumbersDefault(1)
libxml2.substituteEntitiesDefault(1)
# 3 First XSLT transformation
styleDoc1 = libxml2.parseFile(GDOCS2CNXML_XSL1)
style1 = libxslt.parseStylesheetDoc(styleDoc1)
# doc1 = libxml2.parseFile(afile))
doc1 = libxml2.parseDoc(strTidiedHtml)
result1 = style1.applyStylesheet(doc1, None)
#style1.saveResultToFilename(os.path.join('output', docFilename + '_meta.xml'), result1, 1)
strResult1 = style1.saveResultToString(result1)
style1.freeStylesheet()
doc1.freeDoc()
result1.freeDoc()
# Parse XML with etree from lxml for TeX2MathML and image download
etreeXml = etree.fromstring(strResult1)
# 4 Convert TeX to MathML with Blahtex
etreeXml = tex2mathml(etreeXml)
# 5 Optional: Download Google Docs Images
imageObjects = {}
if bDownloadImages:
etreeXml, imageObjects = downloadImages(etreeXml)
# Convert etree back to string
strXml = etree.tostring(etreeXml) # pretty_print=True)
# 6 Second transformation
styleDoc2 = libxml2.parseFile(GDOCS2CNXML_XSL2)
style2 = libxslt.parseStylesheetDoc(styleDoc2)
doc2 = libxml2.parseDoc(strXml)
result2 = style2.applyStylesheet(doc2, None)
#style2.saveResultToFilename('tempresult.xml', result2, 0) # just for debugging
strResult2 = style2.saveResultToString(result2)
style2.freeStylesheet()
doc2.freeDoc()
result2.freeDoc()
return strResult2, imageObjects
def xsl_transform(content, bDownloadImages, base_or_source_url='.'):
use_readability = True
# 1 get title with readability
html_title = "Untitled"
try:
html_title = Document(content).title()
except:
pass
# 2 use readabilty to get content
if use_readability:
readable_article = Document(content).summary()
else:
readable_article = content
# 3 tidy and premail
strTidiedHtml = tidy_and_premail(readable_article)
# 4 Load XHTML catalog files: Makes XHTML entities readable.
libxml2.loadCatalog(XHTML_ENTITIES)
libxml2.lineNumbersDefault(1)
libxml2.substituteEntitiesDefault(1)
# 5 XSLT transformation
styleDoc1 = libxml2.parseFile(XHTML2CNXML_XSL1)
style1 = libxslt.parseStylesheetDoc(styleDoc1)
# doc1 = libxml2.parseFile(afile))
doc1 = libxml2.parseDoc(strTidiedHtml)
result1 = style1.applyStylesheet(doc1, None)
#style1.saveResultToFilename(os.path.join('output', docFilename + '_meta.xml'), result1, 1)
strResult1 = style1.saveResultToString(result1)
# print strResult1
style1.freeStylesheet()
doc1.freeDoc()
result1.freeDoc()
# Parse XML with etree from lxml for TeX2MathML and image download
etreeXml = etree.fromstring(strResult1)
# 6 Convert TeX to MathML with Blahtex (not in XHTML)
# etreeXml = tex2mathml(etreeXml)
# 7 Optional: Download Google Docs Images
imageObjects = {}
if bDownloadImages:
etreeXml, imageObjects = downloadImages(etreeXml, base_or_source_url)
# 8 add title from html
etreeXml = add_cnxml_title(etreeXml, html_title)
# Convert etree back to string
strXml = etree.tostring(etreeXml) # pretty_print=True)
# 9 Second transformation
styleDoc2 = libxml2.parseFile(XHTML2CNXML_XSL2)
style2 = libxslt.parseStylesheetDoc(styleDoc2)
doc2 = libxml2.parseDoc(strXml)
result2 = style2.applyStylesheet(doc2, None)
#style2.saveResultToFilename('tempresult.xml', result2, 0) # just for debugging
strResult2 = style2.saveResultToString(result2)
style2.freeStylesheet()
doc2.freeDoc()
result2.freeDoc()
return strResult2, imageObjects, html_title
def init_libxml2(xml):
libxml2.loadCatalog(XHTML_ENTITIES)
libxml2.lineNumbersDefault(1)
libxml2.substituteEntitiesDefault(1)
return xml, {}
def xsl_transform(content, bDownloadImages, base_or_source_url='.'):
html_title = "Untitled"
# 1 get title with readability
# ONLY MAKES SENSE FOR AN UNKNOWN HTML, SO I COMMENTED IT OUT FOR https://github.com/Connexions/rhaptos.html2cnxml
#try:
# html_title = Document(content).title()
#except:
# pass
# 2 use readabilty to get content
# ONLY MAKES SENSE FOR AN UNKNOWN HTML, SO I COMMENTED IT OUT FOR https://github.com/Connexions/rhaptos.html2cnxml
#readable_article = Document(content).summary()
readable_article = content
# 3 tidy and premail
strTidiedHtml = tidy_and_premail(readable_article)
# 4 Load XHTML catalog files: Makes XHTML entities readable.
libxml2.loadCatalog(XHTML_ENTITIES)
libxml2.lineNumbersDefault(1)
libxml2.substituteEntitiesDefault(1)
# 5 XSLT transformation
styleDoc1 = libxml2.parseFile(XHTML2CNXML_XSL1)
style1 = libxslt.parseStylesheetDoc(styleDoc1)
# doc1 = libxml2.parseFile(afile))
doc1 = libxml2.parseDoc(strTidiedHtml)
result1 = style1.applyStylesheet(doc1, None)
#style1.saveResultToFilename(os.path.join('output', docFilename + '_meta.xml'), result1, 1)
strResult1 = style1.saveResultToString(result1)
style1.freeStylesheet()
doc1.freeDoc()
result1.freeDoc()
# Parse XML with etree from lxml for TeX2MathML and image download
etreeXml = etree.fromstring(strResult1)
# 6 Convert TeX to MathML with Blahtex (not in XHTML)
# etreeXml = tex2mathml(etreeXml)
# 7 Optional: Download Google Docs Images
imageObjects = {}
if bDownloadImages:
etreeXml, imageObjects = downloadImages(etreeXml, base_or_source_url)
# 8 add title from html
etreeXml = add_cnxml_title(etreeXml, html_title)
# Convert etree back to string
strXml = etree.tostring(etreeXml) # pretty_print=True)
# 9 Second transformation
styleDoc2 = libxml2.parseFile(XHTML2CNXML_XSL2)
style2 = libxslt.parseStylesheetDoc(styleDoc2)
doc2 = libxml2.parseDoc(strXml)
result2 = style2.applyStylesheet(doc2, None)
#style2.saveResultToFilename('tempresult.xml', result2, 0) # just for debugging
strResult2 = style2.saveResultToString(result2)
style2.freeStylesheet()
doc2.freeDoc()
result2.freeDoc()
return strResult2, imageObjects, html_title
def init_libxml2(xml):
libxml2.loadCatalog(XHTML_ENTITIES)
libxml2.lineNumbersDefault(1)
libxml2.substituteEntitiesDefault(1)
return xml, {}
