def is_cache_full(self):
"""
Check if cache has more than one document
"""
if os.path.exists(self.cache_file):
reader = SAXReader()
cache_doc = reader.read(
File(self.cache_file)
)
pinfo = ParliamentInfoParams()
list_of_cached_nodes = cache_doc.selectNodes(
pinfo._xpath_content_types()
)
if not self.bicameral:
"""
If its unicameral
"""
if len(list_of_cached_nodes) == 1:
return True
else:
return False
else:
"""
If its bicameral
"""
if len(list_of_cached_nodes) == 2:
return True
else:
return False
return False
def append_to_cache(self, input_file):
reader = SAXReader()
new_doc = reader.read(
File(input_file)
)
element_to_import = new_doc.getRootElement()
self.append_element_into_cache_document(element_to_import)
def getPayloadContent(self):
format = self.__metadata.getField("dc_format")
slash = self.__oid.rfind("/")
pid = self.__oid[slash+1:]
print " *** payload content, format: %s, pid: %s *** " % (format, pid)
contentStr = ""
if format.startswith("text"):
contentStr = "<pre>"
payload = self.__storage.getPayload(self.__oid, pid)
str = StringWriter()
IOUtils.copy(payload.getInputStream(), str)
contentStr += str.toString()
contentStr += "</pre>"
elif format.find("vnd.ms-")>-1 or format.find("vnd.oasis.opendocument.")>-1:
#get the html version if exist....
pid = pid[:pid.find(".")] + ".htm"
payload = self.__storage.getPayload(self.__oid, pid)
saxReader = SAXReader()
document = saxReader.read(payload.getInputStream())
slideNode = document.selectSingleNode("//div[@class='body']")
#linkNodes = slideNode.selectNodes("//img")
#contentStr = slideNode.asXML();
# encode character entities correctly
out = ByteArrayOutputStream()
format = OutputFormat.createPrettyPrint()
format.setSuppressDeclaration(True)
writer = XMLWriter(out, format)
writer.write(slideNode)
writer.close()
contentStr = out.toString("UTF-8")
return contentStr
def getPayloadContent(self):
mimeType = self.__mimeType
print " * single.py: payload content mimeType=%s" % mimeType
contentStr = ""
if mimeType.startswith("text/"):
if mimeType == "text/html":
contentStr = '<iframe class="iframe-preview" src="%s/%s/download/%s"></iframe>' % (
contextPath,
portalId,
self.__oid,
)
else:
pid = self.__oid[self.__oid.rfind("/") + 1 :]
payload = self.__storage.getPayload(self.__oid, pid)
print " * single.py: pid=%s payload=%s" % (pid, payload)
if payload is not None:
sw = StringWriter()
sw.write("<pre>")
IOUtils.copy(payload.getInputStream(), sw)
sw.write("</pre>")
sw.flush()
contentStr = sw.toString()
elif (
mimeType == "application/pdf"
or mimeType.find("vnd.ms") > -1
or mimeType.find("vnd.oasis.opendocument.") > -1
):
# get the html version if exist...
pid = os.path.splitext(self.__pid)[0] + ".htm"
print " * single.py: pid=%s" % pid
# contentStr = '<iframe class="iframe-preview" src="%s/%s/download/%s/%s"></iframe>' % \
# (contextPath, portalId, self.__oid, pid)
payload = self.__storage.getPayload(self.__oid, pid)
saxReader = SAXReader(Boolean.parseBoolean("false"))
try:
document = saxReader.read(payload.getInputStream())
slideNode = document.selectSingleNode("//*[local-name()='body']")
# linkNodes = slideNode.selectNodes("//img")
# contentStr = slideNode.asXML();
# encode character entities correctly
slideNode.setName("div")
out = ByteArrayOutputStream()
format = OutputFormat.createPrettyPrint()
format.setSuppressDeclaration(True)
format.setExpandEmptyElements(True)
writer = XMLWriter(out, format)
writer.write(slideNode)
writer.close()
contentStr = out.toString("UTF-8")
except:
traceback.print_exc()
contentStr = '<p class="error">No preview available</p>'
elif mimeType.startswith("image/"):
src = "%s/%s" % (self.__oid, self.__pid)
contentStr = (
'<a class="image" href="%(src)s" style="max-width:98%%">'
'<img src="%(src)s" style="max-width:100%%" /></a>' % {"src": self.__pid}
)
return contentStr
def getPayloadContent(self):
mimeType = self.__mimeType
print " * detail.py: payload content mimeType=%s" % mimeType
contentStr = ""
if mimeType == "application/octet-stream":
dcFormat = self.__json.get("response/docs/dc_format")
if dcFormat is not None:
dcFormat = dcFormat[1:-1]
print dcFormat, mimeType
if dcFormat != mimeType:
return "<div><em>(File not found)</em></div>"
else:
return "<div><em>(Binary file)</em></div>"
elif mimeType.startswith("text/"):
if mimeType == "text/html":
contentStr = '<iframe class="iframe-preview" src="%s/%s/download/%s"></iframe>' % \
(contextPath, portalId, self.__oid)
else:
pid = self.__oid[self.__oid.rfind("/")+1:]
payload = self.__storage.getPayload(self.__oid, pid)
#print " * detail.py: pid=%s payload=%s" % (pid, payload)
if payload is not None:
sw = StringWriter()
sw.write("<pre>")
IOUtils.copy(payload.getInputStream(), sw)
sw.write("</pre>")
sw.flush()
contentStr = sw.toString()
elif mimeType == "application/pdf" or mimeType.find("vnd.ms")>-1 or mimeType.find("vnd.oasis.opendocument.")>-1:
# get the html version if exist...
pid = os.path.splitext(self.__pid)[0] + ".htm"
print " * detail.py: pid=%s" % pid
#contentStr = '<iframe class="iframe-preview" src="%s/%s/download/%s/%s"></iframe>' % \
# (contextPath, portalId, self.__oid, pid)
payload = self.__storage.getPayload(self.__oid, pid)
saxReader = SAXReader(Boolean.parseBoolean("false"))
try:
document = saxReader.read(payload.getInputStream())
slideNode = document.selectSingleNode("//*[local-name()='body']")
#linkNodes = slideNode.selectNodes("//img")
#contentStr = slideNode.asXML();
# encode character entities correctly
slideNode.setName("div")
out = ByteArrayOutputStream()
format = OutputFormat.createPrettyPrint()
format.setSuppressDeclaration(True)
format.setExpandEmptyElements(True)
writer = XMLWriter(out, format)
writer.write(slideNode)
writer.close()
contentStr = out.toString("UTF-8")
except:
traceback.print_exc()
contentStr = "<p class=\"error\">No preview available</p>"
return contentStr
def loadConfig():
"""
Load the configuration file
return Document
"""
document = None
reader = SAXReader()
try:
document = reader.read(CONF_FILE)
except DocumentException, detail:
print "Error: %s" % detail.getMessage()
def test(docname):
"""Test the functions in this module.
"""
reader = SAXReader()
doc = reader.read(docname)
show_tree(doc, 'Original tree:')
date = time.ctime()
modify_tree(doc, 'person', 'date', date)
show_tree(doc, 'After walk and modify:')
modify_tree_xpath(doc, '//people/person/name', 'date', date)
show_tree(doc, 'After XPath modify:')
def append_to_cache(self, input_file, search_node):
reader = SAXReader()
new_doc = reader.read(
File(input_file)
)
found_node = new_doc.selectSingleNode(search_node)
found_id = found_node.getText()
if not self.does_item_exist_in_cache(found_id):
element_to_import = new_doc.getRootElement()
self.append_element_into_cache_document(element_to_import)
else:
LOG.info(found_id + " already exists in cache")
def append_to_cache(self, input_file):
reader = SAXReader()
new_doc = reader.read(
File(input_file)
)
parl_node = new_doc.selectSingleNode("/contenttype[@name='parliament']/field[@name='parliament_id']")
parliament_id = parl_node.getText()
if not self.does_parliament_exists_in_cache(parliament_id):
element_to_import = new_doc.getRootElement()
self.append_element_into_cache_document(element_to_import)
else:
LOG.info(parliament_id + " already exists in cache")
def getPayloadContent(self):
mimeType = self.__mimeType
print " * single.py: payload content mimeType=%s" % mimeType
contentStr = ""
if mimeType.startswith("text/"):
if mimeType == "text/html":
contentStr = '<iframe class="iframe-preview" src="%s/download/%s"></iframe>' % \
(portalPath, self.__oid)
else:
pid = self.__oid[self.__oid.rfind("/") + 1:]
payload = self.__storage.getPayload(self.__oid, pid)
print " * single.py: pid=%s payload=%s" % (pid, payload)
if payload is not None:
sw = StringWriter()
sw.write("<pre>")
IOUtils.copy(payload.getInputStream(), sw)
sw.write("</pre>")
sw.flush()
contentStr = sw.toString()
elif mimeType == "application/pdf" or mimeType.find(
"vnd.ms") > -1 or mimeType.find(
"vnd.oasis.opendocument.") > -1:
# get the html version if exist...
pid = os.path.splitext(self.__pid)[0] + ".htm"
print " * single.py: pid=%s" % pid
#contentStr = '<iframe class="iframe-preview" src="%s/download/%s/%s"></iframe>' % \
# (portalPath, self.__oid, pid)
payload = self.__storage.getPayload(self.__oid, pid)
saxReader = SAXReader(Boolean.parseBoolean("false"))
try:
document = saxReader.read(payload.getInputStream())
slideNode = document.selectSingleNode(
"//*[local-name()='body']")
#linkNodes = slideNode.selectNodes("//img")
#contentStr = slideNode.asXML();
# encode character entities correctly
slideNode.setName("div")
out = ByteArrayOutputStream()
format = OutputFormat.createPrettyPrint()
format.setSuppressDeclaration(True)
format.setExpandEmptyElements(True)
writer = XMLWriter(out, format)
writer.write(slideNode)
writer.close()
contentStr = out.toString("UTF-8")
except:
traceback.print_exc()
contentStr = "<p class=\"error\">No preview available</p>"
elif mimeType.startswith("image/"):
src = "%s/%s" % (self.__oid, self.__pid)
contentStr = '<a class="image" href="%(src)s" style="max-width:98%%">' \
'<img src="%(src)s" style="max-width:100%%" /></a>' % { "src": self.__pid }
return contentStr
def new_cache(self, input_file):
"""
Takes the input file, creates a new empty cache document,
and adds the input file to the cache
"""
self.new_cache_document()
reader = SAXReader()
new_doc = reader.read(
File(input_file)
)
element_to_import = new_doc.getRootElement()
self.append_element_into_cache_document(element_to_import)
def __activate__(self, context):
self.log = context["log"]
self.config = context["systemConfig"]
response = context["response"]
try:
## Variable prep
defaultPath = FascinatorHome.getPath("alerts")
self.alertsPath = self.config.getString(defaultPath,
["alerts", "path"])
self.configFile = None # We'll allocate this later... if needed
self.redboxVersion = self.config.getString(
"", "redbox.version.string")
self.csvDialect = csv.excel
self.csvDialect.skipinitialspace = True
## XML Parsing
docFactory = DocumentFactory()
##docFactory.setXPathNamespaceURIs(namespaces)
self.saxReader = SAXReader(docFactory)
## Do our job
(success, failed) = self.__processDir()
## Send response to the client (if debugging in browser)
writer = response.getPrintWriter("text/plain; charset=UTF-8")
writer.println("%s successful, %s failed" % (success, failed))
writer.close()
except Exception, e:
response.setStatus(500)
writer = response.getPrintWriter("text/plain; charset=UTF-8")
writer.println("Unexpected error during script execution:\n%s" %
str(e))
writer.close()
def is_cache_full(self):
"""
Check if cache has more than one document
"""
if os.path.exists(self.cache_file):
reader = SAXReader()
cache_doc = reader.read(
File(self.cache_file)
)
#pinfo = ParliamentInfoParams()
list_of_cached_nodes = cache_doc.selectNodes(
self.axis_to_check_cache_full()
)
if len(list_of_cached_nodes) == self.chambers_required:
return True
else:
return False
return False
def __init__(self, file, config, baseline):
AlertHandler.__init__(self, file, config, baseline)
docFactory = DocumentFactory()
self.saxReader = SAXReader(docFactory)
self.xmlMapFile = StrSubstitutor.replaceSystemProperties(
config['xmlMap'])
if not os.path.exists(self.xmlMapFile):
raise AlertException("Requested xmlMap file %s does not exist." %
self.xmlMapFile)
## Make sure we can see our mappings
inStream = FileInputStream(File(self.xmlMapFile))
xmlMappings = JsonSimple(inStream)
self.map = xmlMappings.getObject(["mappings"])
self.exceptions = xmlMappings.getObject(["exceptions"])
self.defaultNamespace = xmlMappings.getObject(["defaultNamespace"])
self.mappedExceptionCount = 0
def __getPayloadContent(self, oid, pid):
print " * combined.py: oid='%s' pid='%s'" % (oid, pid)
payload = self.__storage.getPayload(oid, pid)
if payload is None:
return "<div>Error: No content for '%s'</div>" % oid
mimeType = payload.contentType
contentStr = ""
if mimeType.startswith("text/"):
if mimeType == "text/html":
contentStr = '<iframe class="iframe-preview" src="%s/download/%s"></iframe>' % \
(portalPath, oid)
else:
sw = StringWriter()
sw.write("<pre>")
IOUtils.copy(payload.getInputStream(), sw)
sw.write("</pre>")
sw.flush()
contentStr = sw.toString()
elif mimeType == "application/pdf" or mimeType.find("vnd.ms")>-1 or mimeType.find("vnd.oasis.opendocument.")>-1:
# get the html version if exist...
pid = os.path.splitext(pid)[0] + ".htm"
print " * combined.py: pid=%s" % pid
payload = self.__storage.getPayload(oid, pid)
saxReader = SAXReader(False)
try:
document = saxReader.read(payload.getInputStream())
slideNode = document.selectSingleNode("//*[local-name()='body']")
slideNode.setName("div")
out = ByteArrayOutputStream()
format = OutputFormat.createPrettyPrint()
format.setSuppressDeclaration(True)
format.setExpandEmptyElements(True)
writer = XMLWriter(out, format)
writer.write(slideNode)
writer.close()
contentStr = out.toString("UTF-8")
except:
traceback.print_exc()
contentStr = "<p class=\"error\">No preview available</p>"
elif mimeType.startswith("image/"):
src = "%s/%s" % (oid, pid)
contentStr = '<a class="image" href="%(src)s" style="max-width:98%%">' \
'<img src="%(src)s" style="max-width:100%%" /></a>' % { "src": pid }
return contentStr
def getPayloadContent(self):
mimeType = self.__mimeType
print " * detail.py: payload content mimeType=%s" % mimeType
contentStr = ""
if mimeType.startswith("text/"):
if mimeType == "text/html":
contentStr = '<iframe class="iframe-preview" src="%s/%s/download/%s"></iframe>' % \
(contextPath, portalId, self.__oid)
else:
pid = self.__oid[self.__oid.rfind("/")+1:]
payload = self.__storage.getPayload(self.__oid, pid)
print " * detail.py: pid=%s payload=%s" % (pid, payload)
if payload is not None:
sw = StringWriter()
sw.write("<pre>")
IOUtils.copy(payload.getInputStream(), sw)
sw.write("</pre>")
sw.flush()
contentStr = sw.toString()
elif mimeType == "application/pdf" or mimeType.find("vnd")>-1 or mimeType.find("vnd.oasis.opendocument.")>-1:
# get the html version if exist...
pid = os.path.splitext(self.__pid)[0] + ".htm"
print " * detail.py: pid=%s" % pid
#contentStr = '<iframe class="iframe-preview" src="%s/%s/download/%s/%s"></iframe>' % \
# (contextPath, portalId, self.__oid, pid)
payload = self.__storage.getPayload(self.__oid, pid)
saxReader = SAXReader(Boolean.parseBoolean("false"))
try:
document = saxReader.read(payload.getInputStream())
except:
traceback.print_exc()
#slideNode = document.selectSingleNode("//div[@class='body']")
slideNode = document.selectSingleNode("//*[local-name()='body']")
#linkNodes = slideNode.selectNodes("//img")
#contentStr = slideNode.asXML();
# encode character entities correctly
out = ByteArrayOutputStream()
format = OutputFormat.createPrettyPrint()
format.setSuppressDeclaration(True)
writer = XMLWriter(out, format)
writer.write(slideNode)
writer.close()
contentStr = out.toString("UTF-8")
return contentStr
def __init__(self, file, config, baseline):
AlertHandler.__init__(self, file, config, baseline)
docFactory = DocumentFactory()
self.saxReader = SAXReader(docFactory)
self.xmlMapFile = StrSubstitutor.replaceSystemProperties(config['xmlMap'])
if not os.path.exists(self.xmlMapFile):
raise AlertException("Requested xmlMap file %s does not exist." % self.xmlMapFile)
## Make sure we can see our mappings
inStream = FileInputStream(File(self.xmlMapFile))
xmlMappings = JsonSimple(inStream)
self.map = xmlMappings.getObject(["mappings"])
self.exceptions = xmlMappings.getObject(["exceptions"])
self.defaultNamespace = xmlMappings.getObject(["defaultNamespace"])
self.mappedExceptionCount = 0
def test(indocname):
reader = SAXReader()
doc = reader.read(indocname)
visitor = Visitor()
doc.accept(visitor)
def __createEpub(self):
title = self.__manifest.get("title")
response.setHeader("Content-Disposition", "attachment; filename=%s.epub" % urllib.quote(title))
out = response.getOutputStream("application/epub+zip")
zipOutputStream = ZipOutputStream(out)
#save mimetype... and the rest of standard files in epub
zipOutputStream.putNextEntry(ZipEntry("mimetype"))
epubMimetypeStream = self.__getResourceAsStream("/epub/mimetype")
IOUtils.copy(epubMimetypeStream, zipOutputStream)
zipOutputStream.closeEntry()
zipOutputStream.putNextEntry(ZipEntry("META-INF/container.xml"))
epubContainerStream = self.__getResourceAsStream("/epub/container.xml")
IOUtils.copy(epubContainerStream, zipOutputStream)
zipOutputStream.closeEntry()
zipOutputStream.putNextEntry(ZipEntry("OEBPS/epub.css"))
epubcss = self.__getResourceAsStream("/epub/epub.css")
IOUtils.copy(epubcss, zipOutputStream)
zipOutputStream.closeEntry()
#### Creating toc.ncx ####
tocXml = ElementTree.Element("ncx", {"version": "2005-1", "xml:lang":"en", "xmlns":"http://www.daisy.org/z3986/2005/ncx/"})
headNode = ElementTree.Element("head")
tocXml.append(headNode)
headNode.append(ElementTree.Element("meta", {"name": "dtb:uid", "content": "1"}))
headNode.append(ElementTree.Element("meta", {"name": "dtb:depth", "content": "1"}))
headNode.append(ElementTree.Element("meta", {"name": "dtb:totalPageCount", "content": "1"}))
headNode.append(ElementTree.Element("meta", {"name": "dtb:maxPageNumber", "content": "1"}))
headNode.append(ElementTree.Element("meta", {"name": "dtb:generator", "content": "ICE v2"}))
#docTitle
docTitle = ElementTree.Element("docTitle")
textNode = ElementTree.Element("text")
textNode.text = title
docTitle.append(textNode)
tocXml.append(docTitle)
#docAuthor
docAuthor = ElementTree.Element("docAuthor")
textNode = ElementTree.Element("text")
textNode.text = "ICE v2"
docAuthor.append(textNode)
tocXml.append(docAuthor)
#navMap
navMap = ElementTree.Element("navMap")
tocXml.append(navMap)
#### Creating content.opf ####
contentXml = ElementTree.Element("package", {"version": "2.0", "xmlns":"http://www.idpf.org/2007/opf",
"unique-identifier":"BookId"})
metadataNode = ElementTree.Element("metadata", {"xmlns:dc": "http://purl.org/dc/elements/1.1/",
"xmlns:opf": "http://www.idpf.org/2007/opf"})
contentXml.append(metadataNode)
#metadata information
metadata = ElementTree.Element("dc:title")
metadata.text = title
metadataNode.append(metadata)
metadata = ElementTree.Element("dc:language")
metadata.text = "en-AU"
metadataNode.append(metadata)
metadata = ElementTree.Element("dc:creator", {"opf:role":"aut"})
metadata.text = "ICE"
metadataNode.append(metadata)
metadata = ElementTree.Element("dc:publisher")
metadata.text = "University of Southern Queensland"
metadataNode.append(metadata)
metadata = ElementTree.Element("dc:identifier", {"id":"BookId"})
metadata.text = title
metadataNode.append(metadata)
#manifest
manifest = ElementTree.Element("manifest")
contentXml.append(manifest)
spine = ElementTree.Element("spine", {"toc":"ncx"})
contentXml.append(spine)
item = ElementTree.Element("item", {"id":"ncx", "href":"toc.ncx", "media-type":"text/xml"})
manifest.append(item)
css = ElementTree.Element("item", {"id":"style", "href":"epub.css", "media-type":"text/css"})
manifest.append(css)
count = 1
for itemHash in self.__orderedItem:
id, title, htmlFileName, payloadDict, isImage = self.__itemRefDict[itemHash]
for payloadId in payloadDict:
payload, payloadType = payloadDict[payloadId]
if isinstance(payload, Payload):
payloadId = payloadId.lower()
zipEntryId = payloadId.replace(" ", "_").replace("\\", "/")
if payloadType == "application/xhtml+xml":
zipOutputStream.putNextEntry(ZipEntry("OEBPS/%s" % zipEntryId))
##process the html....
saxReader = SAXReader(False)
try:
saxDoc = saxReader.read(payload.open())
payload.close()
# ## remove class or style nodes
# classOrStyleNodes = saxDoc.selectNodes("//@class | //@style ")
# for classOrStyleNode in classOrStyleNodes:
# node = classOrStyleNode
# if classOrStyleNode.getParent():
# node = classOrStyleNode.getParent()
# if node.getQualifiedName() == "img":
# attr = node.attribute(QName("class"))
# attr = node.attribute(QName("class"))
# if attr:
# node.remove(attr)
# attr = node.attribute(QName("style"))
# if attr:
# node.remove(attr)
## remove name in a tags
ahrefs = saxDoc.selectNodes("//*[local-name()='a' and @name!='']")
for a in ahrefs:
attr = a.attribute(QName("name"))
if attr:
a.remove(attr)
## fix images src name.... replace space with underscore and all lower case
imgs = saxDoc.selectNodes("//*[local-name()='img' and contains(@src, '_files')]")
for img in imgs:
srcAttr = img.attribute(QName("src"))
if srcAttr:
src = srcAttr.getValue()
#hash the sourcename
filepath, filename = os.path.split(src)
filename, ext = os.path.splitext(filename)
filename = hashlib.md5(filename).hexdigest()
src = os.path.join(filepath.lower().replace(" ", "_"), "node-%s%s" % (filename, ext))
img.addAttribute(QName("src"), src.replace(" ", "_"))
bodyNode = saxDoc.selectSingleNode("//*[local-name()='div' and @class='body']")
bodyNode.setName("div")
out = ByteArrayOutputStream()
format = OutputFormat.createPrettyPrint()
format.setSuppressDeclaration(True)
writer = XMLWriter(out, format)
writer.write(bodyNode)
writer.flush()
contentStr = out.toString("UTF-8")
htmlString = """<?xml version="1.0" encoding="UTF-8"?>
<html xmlns="http://www.w3.org/1999/xhtml"><head><title>%s</title>
<link rel="stylesheet" href="epub.css"/>
</head><body>%s</body></html>"""
htmlString = htmlString % (title, contentStr)
self.__copyString(htmlString, zipOutputStream)
includeFile = False
except:
traceback.print_exc()
else:
#images....
zipOutputStream.putNextEntry(ZipEntry("OEBPS/%s" % zipEntryId))
IOUtils.copy(payload.open(), zipOutputStream)
payload.close()
zipOutputStream.closeEntry()
else:
zipOutputStream.putNextEntry(ZipEntry("OEBPS/%s" % zipEntryId))
IOUtils.copy(payload, zipOutputStream)
zipOutputStream.closeEntry()
itemNode = ElementTree.Element("item", {"media-type":payloadType, "href": zipEntryId})
if payloadId == htmlFileName.lower():
itemNode.set("id", itemHash)
else:
itemNode.set("id", payloadId.replace("/", "_"))
manifest.append(itemNode)
if not isImage:
navPoint = ElementTree.Element("navPoint", {"class":"chapter", "id":"%s" % itemHash,
"playOrder":"%s" % count})
else:
navPoint = ElementTree.Element("navPoint", {"class":"chapter", "id":"%s" % htmlFileName,
"playOrder":"%s" % count})
navMap.append(navPoint)
navLabel = ElementTree.Element("navLabel")
navPoint.append(navLabel)
textNode = ElementTree.Element("text")
textNode.text = title
navLabel.append(textNode)
content = ElementTree.Element("content")
navPoint.append(content)
content.set("src", htmlFileName)
count +=1
itemRefNode = ElementTree.Element("itemref")
spine.append(itemRefNode)
itemRefNode.set("idref", itemHash)
#saving content.opf...
zipOutputStream.putNextEntry(ZipEntry("OEBPS/content.opf"))
self.__copyString(ElementTree.tostring(contentXml), zipOutputStream)
zipOutputStream.closeEntry()
#saving toc.ncx
zipOutputStream.putNextEntry(ZipEntry("OEBPS/toc.ncx"))
self.__copyString(ElementTree.tostring(tocXml), zipOutputStream)
zipOutputStream.closeEntry()
zipOutputStream.close()
def __load_xml__(self):
xml_file = File(self.xmlfile)
sr = SAXReader()
self.xmldoc = sr.read(xml_file)
class XMLAlertHandler(AlertHandler):
''''Processing class for a single XML File.
Each XML file is expected to contain only a single Collection
'''
def __init__(self, file, config, baseline):
AlertHandler.__init__(self, file, config, baseline)
docFactory = DocumentFactory()
self.saxReader = SAXReader(docFactory)
self.xmlMapFile = StrSubstitutor.replaceSystemProperties(config['xmlMap'])
if not os.path.exists(self.xmlMapFile):
raise AlertException("Requested xmlMap file %s does not exist." % self.xmlMapFile)
## Make sure we can see our mappings
inStream = FileInputStream(File(self.xmlMapFile))
xmlMappings = JsonSimple(inStream)
self.map = xmlMappings.getObject(["mappings"])
self.exceptions = xmlMappings.getObject(["exceptions"])
self.defaultNamespace = xmlMappings.getObject(["defaultNamespace"])
self.mappedExceptionCount = 0
def process(self):
'''Read the XML file and map xpath items to metadata
Return a list with 1 JsonSimple object (at most)
'''
jsonList = []
data = None
reader = None
inStream = None
document = None
# Run the XML through our parser
try:
inStream = FileInputStream(File(self.file))
reader = InputStreamReader(inStream, "UTF-8")
document = self.saxReader.read(reader)
# Parse fails
except:
raise
# Close our file access objects
finally:
if reader is not None:
reader.close()
if inStream is not None:
inStream.close()
# Now go looking for all our data
data = self.getNewJsonObject()
self.__mapXpathToFields(document, self.map, data)
if data is None:
return None
jsonList.append(JsonSimple(data))
return jsonList
## Used recursively
def __mapXpathToFields(self, sourceData, map, responseData, index = 1):
for xpath in map.keySet():
field = map.get(xpath)
if xpath != "":
xpathobj = DefaultXPath(xpath)
if not self.defaultNamespace is None:
xpathobj.setNamespaceContext(SimpleNamespaceContext(self.defaultNamespace))
nodes = xpathobj.selectNodes(sourceData)
if isinstance(field, JsonObject):
#The XPath key provides a dictionary containing sub xpath queries mapped to fields
i = 1
for node in nodes:
self.__mapXpathToFields(node, field, responseData, i)
i += 1
else:
# Lists indicate we're copying the several fields
if isinstance(field, JSONArray):
for eachField in field:
self.__insertFieldData(nodes, eachField, responseData, index)
# or just one field
else:
self.__insertFieldData(nodes, field, responseData, index)
def __insertFieldData(self, xmlNodes, field, responseData, index):
multiValue = False
multiIndex = 1
fieldString = ""
if self.exceptions["fields"].containsKey(field):
#The field is an exception
excepted = True
output = self.exceptions["output"]
self.mappedExceptionCount += 1
else:
# Nope, just normal
excepted = False
if ('.0.' in field and len(xmlNodes) > 1):
#In ReDBox, a field such as dc:subject.vivo:keyword.0.rdf:PlainLiteral indicates a list of values, using the number as a counter.
#In the code below, if a field contains this number element, we can increment the counter and add more and more.
#If there is no number, we just overwrite the value.
multiValue = True
#we'll do the fieldString index change a little later
fieldString = field
else:
fieldString = field.replace(".0.", ".%s."%index, 1)
for node in xmlNodes:
text = node.getTextTrim()
if fieldString != "" and text != "":
if excepted:
exceptionString = "%s: '%s' (%s)" % (exceptions["fields"][field], text, field)
responseData.put(fieldString, exceptionString)
else:
if multiValue:
fieldString = field.replace(".0.", ".%s."%multiIndex, 1)
multiIndex += 1
responseData.put(fieldString, text)
def __doc_cache_file(self):
reader = SAXReader()
cache_doc = reader.read(
File(self.cache_file)
)
return cache_doc
def __createEpub(self):
title = self.__manifest.getString(None, "title")
self.vc("response").setHeader(
"Content-Disposition",
"attachment; filename=%s.epub" % urllib.quote(title))
out = self.vc("response").getOutputStream("application/epub+zip")
zipOutputStream = ZipOutputStream(out)
#save mimetype... and the rest of standard files in epub
zipOutputStream.putNextEntry(ZipEntry("mimetype"))
epubMimetypeStream = self.__getResourceAsStream("/epub/mimetype")
IOUtils.copy(epubMimetypeStream, zipOutputStream)
zipOutputStream.closeEntry()
zipOutputStream.putNextEntry(ZipEntry("META-INF/container.xml"))
epubContainerStream = self.__getResourceAsStream("/epub/container.xml")
IOUtils.copy(epubContainerStream, zipOutputStream)
zipOutputStream.closeEntry()
zipOutputStream.putNextEntry(ZipEntry("OEBPS/epub.css"))
epubcss = self.__getResourceAsStream("/epub/epub.css")
IOUtils.copy(epubcss, zipOutputStream)
zipOutputStream.closeEntry()
#### Creating toc.ncx ####
tocXml = ElementTree.Element(
"ncx", {
"version": "2005-1",
"xml:lang": "en",
"xmlns": "http://www.daisy.org/z3986/2005/ncx/"
})
headNode = ElementTree.Element("head")
tocXml.append(headNode)
headNode.append(
ElementTree.Element("meta", {
"name": "dtb:uid",
"content": "1"
}))
headNode.append(
ElementTree.Element("meta", {
"name": "dtb:depth",
"content": "1"
}))
headNode.append(
ElementTree.Element("meta", {
"name": "dtb:totalPageCount",
"content": "1"
}))
headNode.append(
ElementTree.Element("meta", {
"name": "dtb:maxPageNumber",
"content": "1"
}))
headNode.append(
ElementTree.Element("meta", {
"name": "dtb:generator",
"content": "ICE v2"
}))
#docTitle
docTitle = ElementTree.Element("docTitle")
textNode = ElementTree.Element("text")
textNode.text = title
docTitle.append(textNode)
tocXml.append(docTitle)
#docAuthor
docAuthor = ElementTree.Element("docAuthor")
textNode = ElementTree.Element("text")
textNode.text = "ICE v2"
docAuthor.append(textNode)
tocXml.append(docAuthor)
#navMap
navMap = ElementTree.Element("navMap")
tocXml.append(navMap)
#### Creating content.opf ####
contentXml = ElementTree.Element(
"package", {
"version": "2.0",
"xmlns": "http://www.idpf.org/2007/opf",
"unique-identifier": "BookId"
})
metadataNode = ElementTree.Element(
"metadata", {
"xmlns:dc": "http://purl.org/dc/elements/1.1/",
"xmlns:opf": "http://www.idpf.org/2007/opf"
})
contentXml.append(metadataNode)
#metadata information
metadata = ElementTree.Element("dc:title")
metadata.text = title
metadataNode.append(metadata)
metadata = ElementTree.Element("dc:language")
metadata.text = "en-AU"
metadataNode.append(metadata)
metadata = ElementTree.Element("dc:creator", {"opf:role": "aut"})
metadata.text = "ICE"
metadataNode.append(metadata)
metadata = ElementTree.Element("dc:publisher")
metadata.text = "University of Southern Queensland"
metadataNode.append(metadata)
metadata = ElementTree.Element("dc:identifier", {"id": "BookId"})
metadata.text = title
metadataNode.append(metadata)
#manifest
manifest = ElementTree.Element("manifest")
contentXml.append(manifest)
spine = ElementTree.Element("spine", {"toc": "ncx"})
contentXml.append(spine)
item = ElementTree.Element("item", {
"id": "ncx",
"href": "toc.ncx",
"media-type": "text/xml"
})
manifest.append(item)
css = ElementTree.Element("item", {
"id": "style",
"href": "epub.css",
"media-type": "text/css"
})
manifest.append(css)
count = 1
for itemHash in self.__orderedItem:
id, title, htmlFileName, payloadDict, isImage = self.__itemRefDict[
itemHash]
for payloadId in payloadDict:
payload, payloadType = payloadDict[payloadId]
if isinstance(payload, Payload):
payloadId = payloadId.lower()
zipEntryId = payloadId.replace(" ", "_").replace("\\", "/")
if payloadType == "application/xhtml+xml":
zipOutputStream.putNextEntry(
ZipEntry("OEBPS/%s" % zipEntryId))
##process the html....
saxReader = SAXReader(False)
try:
saxDoc = saxReader.read(payload.open())
payload.close()
# ## remove class or style nodes
# classOrStyleNodes = saxDoc.selectNodes("//@class | //@style ")
# for classOrStyleNode in classOrStyleNodes:
# node = classOrStyleNode
# if classOrStyleNode.getParent():
# node = classOrStyleNode.getParent()
# if node.getQualifiedName() == "img":
# attr = node.attribute(QName("class"))
# attr = node.attribute(QName("class"))
# if attr:
# node.remove(attr)
# attr = node.attribute(QName("style"))
# if attr:
# node.remove(attr)
## remove name in a tags
ahrefs = saxDoc.selectNodes(
"//*[local-name()='a' and @name!='']")
for a in ahrefs:
attr = a.attribute(QName("name"))
if attr:
a.remove(attr)
## fix images src name.... replace space with underscore and all lower case
imgs = saxDoc.selectNodes(
"//*[local-name()='img' and contains(@src, '_files')]"
)
for img in imgs:
srcAttr = img.attribute(QName("src"))
if srcAttr:
src = srcAttr.getValue()
#hash the sourcename
filepath, filename = os.path.split(src)
filename, ext = os.path.splitext(filename)
filename = hashlib.md5(
filename).hexdigest()
src = os.path.join(
filepath.lower().replace(" ", "_"),
"node-%s%s" % (filename, ext))
img.addAttribute(QName("src"),
src.replace(" ", "_"))
bodyNode = saxDoc.selectSingleNode(
"//*[local-name()='div' and @class='body']")
bodyNode.setName("div")
out = ByteArrayOutputStream()
format = OutputFormat.createPrettyPrint()
format.setSuppressDeclaration(True)
writer = XMLWriter(out, format)
writer.write(bodyNode)
writer.flush()
contentStr = out.toString("UTF-8")
htmlString = """<?xml version="1.0" encoding="UTF-8"?>
<html xmlns="http://www.w3.org/1999/xhtml"><head><title>%s</title>
<link rel="stylesheet" href="epub.css"/>
</head><body>%s</body></html>"""
htmlString = htmlString % (title, contentStr)
self.__copyString(htmlString, zipOutputStream)
includeFile = False
except:
traceback.print_exc()
else:
#images....
zipOutputStream.putNextEntry(
ZipEntry("OEBPS/%s" % zipEntryId))
IOUtils.copy(payload.open(), zipOutputStream)
payload.close()
zipOutputStream.closeEntry()
else:
zipOutputStream.putNextEntry(
ZipEntry("OEBPS/%s" % zipEntryId))
IOUtils.copy(payload, zipOutputStream)
zipOutputStream.closeEntry()
itemNode = ElementTree.Element("item", {
"media-type": payloadType,
"href": zipEntryId
})
if payloadId == htmlFileName.lower():
itemNode.set("id", itemHash)
else:
itemNode.set("id", payloadId.replace("/", "_"))
manifest.append(itemNode)
if not isImage:
navPoint = ElementTree.Element(
"navPoint", {
"class": "chapter",
"id": "%s" % itemHash,
"playOrder": "%s" % count
})
else:
navPoint = ElementTree.Element(
"navPoint", {
"class": "chapter",
"id": "%s" % htmlFileName,
"playOrder": "%s" % count
})
navMap.append(navPoint)
navLabel = ElementTree.Element("navLabel")
navPoint.append(navLabel)
textNode = ElementTree.Element("text")
textNode.text = title
navLabel.append(textNode)
content = ElementTree.Element("content")
navPoint.append(content)
content.set("src", htmlFileName)
count += 1
itemRefNode = ElementTree.Element("itemref")
spine.append(itemRefNode)
itemRefNode.set("idref", itemHash)
#saving content.opf...
zipOutputStream.putNextEntry(ZipEntry("OEBPS/content.opf"))
self.__copyString(ElementTree.tostring(contentXml), zipOutputStream)
zipOutputStream.closeEntry()
#saving toc.ncx
zipOutputStream.putNextEntry(ZipEntry("OEBPS/toc.ncx"))
self.__copyString(ElementTree.tostring(tocXml), zipOutputStream)
zipOutputStream.closeEntry()
zipOutputStream.close()
class XMLAlertHandler(AlertHandler):
''''Processing class for a single XML File.
Each XML file is expected to contain only a single Collection
'''
def __init__(self, file, config, baseline):
AlertHandler.__init__(self, file, config, baseline)
docFactory = DocumentFactory()
self.saxReader = SAXReader(docFactory)
self.xmlMapFile = StrSubstitutor.replaceSystemProperties(
config['xmlMap'])
if not os.path.exists(self.xmlMapFile):
raise AlertException("Requested xmlMap file %s does not exist." %
self.xmlMapFile)
## Make sure we can see our mappings
inStream = FileInputStream(File(self.xmlMapFile))
xmlMappings = JsonSimple(inStream)
self.map = xmlMappings.getObject(["mappings"])
self.exceptions = xmlMappings.getObject(["exceptions"])
self.defaultNamespace = xmlMappings.getObject(["defaultNamespace"])
self.mappedExceptionCount = 0
def process(self):
'''Read the XML file and map xpath items to metadata
Return a list with 1 JsonSimple object (at most)
'''
jsonList = []
data = None
reader = None
inStream = None
document = None
# Run the XML through our parser
try:
inStream = FileInputStream(File(self.file))
reader = InputStreamReader(inStream, "UTF-8")
document = self.saxReader.read(reader)
# Parse fails
except:
raise
# Close our file access objects
finally:
if reader is not None:
reader.close()
if inStream is not None:
inStream.close()
# Now go looking for all our data
data = self.getNewJsonObject()
self.__mapXpathToFields(document, self.map, data)
if data is None:
return None
jsonList.append(JsonSimple(data))
return jsonList
## Used recursively
def __mapXpathToFields(self, sourceData, map, responseData, index=1):
for xpath in map.keySet():
field = map.get(xpath)
if xpath != "":
xpathobj = DefaultXPath(xpath)
if not self.defaultNamespace is None:
xpathobj.setNamespaceContext(
SimpleNamespaceContext(self.defaultNamespace))
nodes = xpathobj.selectNodes(sourceData)
if isinstance(field, JsonObject):
#The XPath key provides a dictionary containing sub xpath queries mapped to fields
i = 1
for node in nodes:
self.__mapXpathToFields(node, field, responseData, i)
i += 1
else:
# Lists indicate we're copying the several fields
if isinstance(field, JSONArray):
for eachField in field:
self.__insertFieldData(nodes, eachField,
responseData, index)
# or just one field
else:
self.__insertFieldData(nodes, field, responseData,
index)
def __insertFieldData(self, xmlNodes, field, responseData, index):
multiValue = False
multiIndex = 1
fieldString = ""
if self.exceptions["fields"].containsKey(field):
#The field is an exception
excepted = True
output = self.exceptions["output"]
self.mappedExceptionCount += 1
else:
# Nope, just normal
excepted = False
if ('.0.' in field and len(xmlNodes) > 1):
#In ReDBox, a field such as dc:subject.vivo:keyword.0.rdf:PlainLiteral indicates a list of values, using the number as a counter.
#In the code below, if a field contains this number element, we can increment the counter and add more and more.
#If there is no number, we just overwrite the value.
multiValue = True
#we'll do the fieldString index change a little later
fieldString = field
else:
fieldString = field.replace(".0.", ".%s." % index, 1)
for node in xmlNodes:
try:
text = node.getTextTrim()
except:
try:
text = node.getValue().strip()
except:
text = node
if fieldString != "" and text != "":
if excepted:
exceptionString = "%s: '%s' (%s)" % (
exceptions["fields"][field], text, field)
responseData.put(fieldString, exceptionString)
else:
if multiValue:
fieldString = field.replace(".0.", ".%s." % multiIndex,
1)
multiIndex += 1
responseData.put(fieldString, text)