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
class SyncXmlFilesWalker(GenericDirWalkerXML):
"""
Synchronizes XML files one-by-one with the eXist XML repository
"""
def __init__(self, input_params = None):
"""
input_params - the parameters for the callback function
"""
super(GenericDirWalkerXML, self).__init__()
self.main_cfg = input_params["main_config"]
self.webdav_cfg = input_params["webdav_config"]
self.transformer = Transformer(self.main_cfg)
def create_sync_file(self):
OutputFormat.createPrettyPrint()
self.format = OutputFormat.createCompactFormat()
self.document = DocumentFactory.getInstance().createDocument()
self.root = self.document.addElement("collection")
self.root.addAttribute("name", "synclist")
return self.root
def add_item_to_repo(self,repo_bound_file):
name = self.root.addElement("file")
name.addText(repo_bound_file)
def close_sync_file(self):
self.format = OutputFormat.createPrettyPrint()
self.writer = XMLWriter(FileWriter(self.main_cfg.get_temp_files_folder()+"reposync.xml"), self.format)
try:
self.writer.write(self.document)
self.writer.flush()
except Exception, ex:
LOG.error("Error while writing sync file reposync.xml", ex)
finally:
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 write_to_disk(self):
#print "XXXX write_to_disk ", self.xmlfile
#print "XXXX write_to_disk writing dom ", self.xmldoc.asXML()
format = OutputFormat.createPrettyPrint()
writer = XMLWriter(FileWriter(self.xmlfile), format)
try:
writer.write(self.xmldoc)
writer.flush()
except Exception, ex:
LOG.error("Error while writing %s to disk" % self.xmlfile, ex)
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 write_cache_doc_to_file(self, cache_doc):
format = OutputFormat.createPrettyPrint()
writer = XMLWriter(
FileWriter(self.cache_file),
format
)
try:
writer.write(cache_doc)
writer.flush()
except Exception, e:
print "Error WRITE_CACHE_DOC_TO_FILE ", e
def write_cache_doc_to_file(self, cache_doc):
#print "XXXX WRITE CACHE TO FILE ", cache_doc.getRootElement().getDocument().asXML()
format = OutputFormat.createPrettyPrint()
writer = XMLWriter(
FileWriter(self.cache_file),
format
)
try:
writer.write(cache_doc)
writer.flush()
except Exception, e:
print "Error WRITE_CACHE_DOC_TO_FILE ", e
def close_sync_file(self):
self.format = OutputFormat.createPrettyPrint()
self.writer = XMLWriter(FileWriter(self.main_cfg.get_temp_files_folder()+"reposync.xml"), self.format)
try:
self.writer.write(self.document)
self.writer.flush()
except Exception, ex:
LOG.error("Error while writing sync file reposync.xml", ex)
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 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 save_xml(self, path , pretty = True):
"""
Saves the xml document to file
"""
self.backup_xml(path)
format = None
xmlwriter = None
if pretty == True:
format = OutputFormat.createPrettyPrint()
format.setIndent(" ")
format.setLineSeparator("\r\n")
if format is None:
xmlwriter = XMLWriter(FileWriter(path))
else:
xmlwriter = XMLWriter(FileWriter(path), format)
xmlwriter.write(self.xmldoc)
xmlwriter.close()
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 __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 __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()
