def compile(wd,args):
print "changing working directory to %s" % wd
System.setProperty("user.dir",wd);
print args
outstream = ByteArrayOutputStream()
errstream = ByteArrayOutputStream()
System.setOut(PrintStream(outstream))
System.setErr(PrintStream(errstream))
try: Tom.exec(config + args)
except: pass
return str((outstream.toString(),errstream.toString()))
def crawl(site, trm , depth, linksfile):
from java.net import URL
from org.w3c.tidy import Tidy
pattern = re.compile('href="/wiki/(.*?)"')
f = open(linksfile, 'a+')
#try:
if depth < MAX_DEPTH:
print 'crawling [%s]...' % trm,
print >> f, '[%s]' % trm
td = Tidy()
td.setXmlOut(1)
u = URL(site + trm)
input = BufferedInputStream(u.openStream())
output = ByteArrayOutputStream()
#tidy.setInputEncoding("UTF8")
#tidy.setOutputEncoding("UTF8")
td.parse(input, output)
content = output.toString()
hits = pattern.findall(content)
for hit in hits:
if hit.find(":") == -1:
print >> f, hit
print 'done.'
print >> f, ''
for hit in hits:
if hit.find(":") == -1:
crawl(site, hit, depth + 1, linksfile)
#except:
# print "wrong"
f.close()
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 showImgWithLegend(width=None,height=None):
""" This function shows the image and legend from current IDV window while in GUI mode. Optional arguments are width and height in pixels, they currently default to 600 and 400"""
from java.util import Base64 ##only in java8
from javax.imageio import ImageIO
from java.io import ByteArrayOutputStream
from ucar.unidata.ui.ImageUtils import resize,toBufferedImage
import java
import java.awt.Robot as Robot
import java.awt.Rectangle as Rectangle
import java.awt.Toolkit as Toolkit
from ucar.unidata.util import Misc
VM=idv.getViewManager()
VMC=VM.getContents()
VMCC=VMC.getComponent(1) # the view and legend ; 0 is left most part of view window with controls for perspective views
siz=VMCC.getSize()
loc= VMCC.getLocationOnScreen()
gc= VMCC.getGraphicsConfiguration()
loc.x -= gc.getBounds().x
loc.y -= gc.getBounds().y
robotx=Robot(gc.getDevice())
VM.toFront()
Misc.sleep(250)
img = robotx.createScreenCapture(Rectangle(loc.x, loc.y,siz.width, siz.height))
if width != None and height != None:
img=toBufferedImage(resize(img,width,height));
bos=ByteArrayOutputStream();
ImageIO.write(img, "png", Base64.getEncoder().wrap(bos));
data = bos.toString("UTF-8");
return {"display":"image","data":data}
def tostring(element_or_tree, encoding=None, method='xml',
xml_declaration=None, pretty_print=False, with_tail=True,
standalone=None, doctype=None, exclusive=False,
with_comments=True, inclusive_ns_prefixes=None):
if isinstance(element_or_tree, _ElementTree):
source = DOMSource(element_or_tree._dom_doc)
else:
source = DOMSource(element_or_tree._dom_element)
outputstream = ByteArrayOutputStream()
result = StreamResult(outputstream)
transformer = transformfac.newTransformer()
if xml_declaration:
transformer.setOutputProperty(OutputKeys.OMIT_XML_DECLARATION,
'no')
else:
transformer.setOutputProperty(OutputKeys.OMIT_XML_DECLARATION,
'yes')
if pretty_print:
transformer.setOutputProperty(OutputKeys.INDENT, 'yes')
else:
transformer.setOutputProperty(OutputKeys.INDENT, 'no')
transformer.transform(source, result)
if encoding is None:
encoding = 'ascii'
return outputstream.toString(encoding)
def showImgWithFullWindow(width=None, height=None):
""" This function shows the image from current IDV window while in GUI mode. optional arguments are width and height in pixels, they
currently default to 600 and 400"""
from java.util import Base64 ##only in java8
from javax.imageio import ImageIO
from java.io import ByteArrayOutputStream
from ucar.unidata.ui.ImageUtils import resize, toBufferedImage
import java
import java.awt.Robot as Robot
import java.awt.Rectangle as Rectangle
import java.awt.Toolkit as Toolkit
from ucar.unidata.util import Misc
VM = idv.getViewManager()
myframe = VM.getDisplayWindow().getComponent()
robotx = Robot(myframe.getGraphicsConfiguration().getDevice())
VM.toFront()
#robotx.delay(250)
Misc.sleep(350)
pause()
img = robotx.createScreenCapture(
Rectangle(myframe.getX(), myframe.getY(), myframe.getWidth(),
myframe.getHeight()))
if width != None and height != None:
img = toBufferedImage(resize(img, width, height))
bos = ByteArrayOutputStream()
ImageIO.write(img, "png",
Base64.getEncoder().wrap(bos))
data = bos.toString("UTF-8")
return {"display": "image", "data": data}
def handle(self):
try:
raw_xml = self.rfile.readline().strip()
marc_xmlfile = NamedTemporaryFile(delete=False)
marc_xmlfile.write(raw_xml)
marc_xmlfile.close()
print(marc_xmlfile.name)
dynamic_context = saxon.query.DynamicQueryContext(CONFIG)
## xml_doc = CONFIG.buildDocument(
## StreamSource(ByteArrayInputStream(raw_xml)))
## dynamic_context.setContextItem(xml_doc)
dynamic_context.setParameter(
"baseuri",
INFO.get('base_uri', 'http://catalog/'))
dynamic_context.setParameter(
"marcxmluri",
os.path.normpath(marc_xmlfile.name).replace("\\", "/"))
dynamic_context.setParameter("serialization", "rdfxml")
output_stream = ByteArrayOutputStream()
result = StreamResult(output_stream)
print("Before query")
COMPLIED_XQUERY.run(dynamic_context, result, None)
self.wfile.write(output_stream.toString().encode('ascii',
errors='ignore'))
os.remove(marc_xmlfile.name)
except:
self.wfile.write("Error processing MARC XML:\n\t{}".format(sys.exc_info()[0]))
def showImgWithLegend(width=None, height=None):
""" This function shows the image and legend from current IDV window while in GUI mode. Optional arguments are width and height in pixels, they currently default to 600 and 400"""
from java.util import Base64 ##only in java8
from javax.imageio import ImageIO
from java.io import ByteArrayOutputStream
from ucar.unidata.ui.ImageUtils import resize, toBufferedImage
import java
import java.awt.Robot as Robot
import java.awt.Rectangle as Rectangle
import java.awt.Toolkit as Toolkit
from ucar.unidata.util import Misc
VM = idv.getViewManager()
VMC = VM.getContents()
VMCC = VMC.getComponent(
1
) # the view and legend ; 0 is left most part of view window with controls for perspective views
siz = VMCC.getSize()
loc = VMCC.getLocationOnScreen()
gc = VMCC.getGraphicsConfiguration()
loc.x -= gc.getBounds().x
loc.y -= gc.getBounds().y
robotx = Robot(gc.getDevice())
VM.toFront()
Misc.sleep(250)
img = robotx.createScreenCapture(
Rectangle(loc.x, loc.y, siz.width, siz.height))
if width != None and height != None:
img = toBufferedImage(resize(img, width, height))
bos = ByteArrayOutputStream()
ImageIO.write(img, "png",
Base64.getEncoder().wrap(bos))
data = bos.toString("UTF-8")
return {"display": "image", "data": data}
def pageContent(self):
# Object ID
oid = self.metadata.get("id")
# Determine MIME Type
mimeType = "Unknown"
mimeList = self.metadata.getList("dc_format")
if mimeList is not None and not mimeList.isEmpty():
mimeType = mimeList.get(0)
# The HTML payload is the real object, display in a frame because we
# have no idea what kind of object it is.
if mimeType == "text/html":
objectPath = "http://%s:%s%s/%s/download/%s/" % \
(self.req.serverName, self.serverPort, self.contextPath, self.portalId, oid)
objectLink = '<a class="iframe-link-alt" href="%s">View outside the frame</a>' % objectPath
objectFrame = '<iframe class="iframe-preview" src="%s"></iframe>' % objectPath
return objectLink + "<br/>" + objectFrame
# We are just rendering a HTML preview
else:
preview = self.metadata.get("preview")
try:
object = Services.getStorage().getObject(oid)
payload = object.getPayload(preview)
out = ByteArrayOutputStream()
IOUtils.copy(payload.open(), out)
payload.close()
return out.toString("UTF-8")
except StorageException, e:
return
def showImgWithFullWindow(width=None,height=None):
""" This function shows the image from current IDV window while in GUI mode. optional arguments are width and height in pixels, they
currently default to 600 and 400"""
from java.util import Base64 ##only in java8
from javax.imageio import ImageIO
from java.io import ByteArrayOutputStream
from ucar.unidata.ui.ImageUtils import resize,toBufferedImage
import java
import java.awt.Robot as Robot
import java.awt.Rectangle as Rectangle
import java.awt.Toolkit as Toolkit
from ucar.unidata.util import Misc
VM=idv.getViewManager()
myframe=VM.getDisplayWindow().getComponent()
robotx = Robot(myframe.getGraphicsConfiguration().getDevice())
VM.toFront();
#robotx.delay(250)
Misc.sleep(350)
pause()
img=robotx.createScreenCapture(Rectangle( myframe.getX(),myframe.getY(),myframe.getWidth(),myframe.getHeight()))
if width != None and height != None:
img=toBufferedImage(resize(img,width,height));
bos=ByteArrayOutputStream();
ImageIO.write(img, "png", Base64.getEncoder().wrap(bos));
data = bos.toString("UTF-8");
return {"display":"image","data":data}
def __load(self, oid):
template = """<div class="title" /><div class="page-toc" /><div class="body"><div>%s</div></div>"""
print "Loading HTML preview for %s..." % oid
if oid == "blank":
return template % "<p>This page intentionally left blank.</p>"
else:
object = Services.getStorage().getObject(oid)
# get preview payload or source if no preview
pid = self.__getPreviewPid(object)
payload = object.getPayload(pid)
mimeType = payload.getContentType()
print "pid=%s mimeType=%s" % (pid, mimeType)
isHtml = mimeType in ["text/html", "application/xhtml+xml"]
if isHtml or mimeType.startswith("text/"):
out = ByteArrayOutputStream()
IOUtils.copy(payload.open(), out)
content = out.toString("UTF-8")
if content.find('class="body"'): ## assumes ICE content
return content
elif isHtml:
return template % content
elif mimeType == "text/plain":
return template % ('<pre>%s</pre>' % content)
else:
return content
elif mimeType.startswith("image/"):
return template % ('<div rel="%s"><img src="%s" /></div>' % (oid, pid))
else:
return '<a href="%s" rel="%s">%s</a>' % (oid, mimeType, pid)
payload.close()
object.close()
def parseFFmpeg(self, parent):
if parent is not None:
object = parent.getObject()
if object is not None:
payload = None
try:
payload = object.getPayload("ffmpeg.info")
# Stream the content out to string
out = ByteArrayOutputStream()
IOUtils.copy(payload.open(), out)
payload.close()
self.__ffmpegRaw = out.toString("UTF-8")
out.close()
payload.close()
# And parse it
self.__ffmpegData = JsonSimple(self.__ffmpegRaw)
if self.__ffmpegData is None:
return False
else:
self.__ffmpegOutputs = self.__ffmpegData.getJsonSimpleMap(["outputs"])
return True
except:
if payload is not None:
payload.close()
return False
def parseFFmpeg(self, parent):
if parent is not None:
object = parent.getObject()
if object is not None:
payload = None
try:
payload = object.getPayload("ffmpeg.info")
# Stream the content out to string
out = ByteArrayOutputStream()
IOUtils.copy(payload.open(), out)
payload.close()
self.__ffmpegRaw = out.toString("UTF-8")
out.close()
payload.close()
# And parse it
jsonData = JsonConfigHelper(self.__ffmpegRaw)
if jsonData is None:
return False
else:
self.__ffmpegData = jsonData.getJsonMap("/outputs")
return True
except:
if payload is not None:
payload.close()
return False
def export(self, exportType):
exportQuery = "%s:%s" % (self.facetField, self.facetFieldValue)
outputType = "text/%s; charset=UTF-8" % type
responseHeader = "attachment; filename=%s.%s" % (self.facetFieldValue, exportType)
try:
out = ByteArrayOutputStream()
recnumreq = SearchRequest(exportQuery)
recnumreq.setParam("fl","create_timestamp")
recnumreq.setParam("rows", "0")
self.indexer.search(recnumreq, out)
recnumres = SolrResult(ByteArrayInputStream(out.toByteArray()))
self.__rowsFoundSolr = "%s" % recnumres.getNumFound()
except:
self.errorMsg = "Export query failure. The issue has been logged (%s - %s)." % (sys.exc_info()[0], sys.exc_info()[1])
self.log.error("Export query threw an exception (package type was %s): %s - %s" % (self.facetFieldValue, sys.exc_info()[0], sys.exc_info()[1]))
return
out = ByteArrayOutputStream()
req = SearchRequest(exportQuery)
req.setParam("wt", exportType)
req.setParam("rows", self.__rowsFoundSolr)
self.indexer.search(req, out)
self.response.setHeader("Content-Disposition", responseHeader)
writer = self.response.getPrintWriter(outputType)
writer.println(out.toString("UTF-8"))
writer.close()
def tostring(element_or_tree,
encoding=None,
method='xml',
xml_declaration=None,
pretty_print=False,
with_tail=True,
standalone=None,
doctype=None,
exclusive=False,
with_comments=True,
inclusive_ns_prefixes=None):
if isinstance(element_or_tree, _ElementTree):
source = DOMSource(element_or_tree._dom_doc)
else:
source = DOMSource(element_or_tree._dom_element)
outputstream = ByteArrayOutputStream()
result = StreamResult(outputstream)
transformer = transformfac.newTransformer()
if xml_declaration:
transformer.setOutputProperty(OutputKeys.OMIT_XML_DECLARATION, 'no')
else:
transformer.setOutputProperty(OutputKeys.OMIT_XML_DECLARATION, 'yes')
if pretty_print:
transformer.setOutputProperty(OutputKeys.INDENT, 'yes')
else:
transformer.setOutputProperty(OutputKeys.INDENT, 'no')
transformer.transform(source, result)
if encoding is None:
encoding = 'ascii'
return outputstream.toString(encoding)
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 __call__(self, _input, profile_run=False, **kw):
nsmap = dict(xsl='http://www.w3.org/1999/XSL/Transform')
output_method = 'xml'
output_encoding = 'utf-8'
nodes = self.xsl_tree.xpath('xsl:output/@method', namespaces=nsmap)
if len(nodes) > 0:
output_method = nodes[0]
nodes = self.xsl_tree.xpath('xsl:output/@encoding', namespaces=nsmap)
if len(nodes) > 0:
output_encoding = nodes[0]
#print tostring(_input)
if isinstance(_input, _ElementTree):
doc_source = DOMSource(_input._dom_doc)
elif isinstance(_input, _Element):
# Xalan-J 2.7.1 does not support a DOMSource from an Element
# so we build new document
dom_doc = builder.newDocument()
dom_root = dom_doc.importNode(_input._dom_element, True)
dom_doc.appendChild(dom_root)
doc_source = DOMSource(dom_doc)
else:
raise NotImplementedError()
if output_method in ('xml', 'html'):
# TODO: for testing
outputstream = ByteArrayOutputStream()
result = StreamResult(outputstream)
self.transformer.transform(doc_source, result)
bytes = outputstream.toByteArray()
inputstream = ByteArrayInputStream(bytes)
try:
dom_doc = builder.parse(inputstream)
except:
import sys
sys.stderr.write(bytes.tostring())
raise
result_tree = _ElementTree(dom_doc)
return result_tree
result = DOMResult()
self.transformer.transform(doc_source, result)
dom_doc = result.getNode()
result_tree = _ElementTree(dom_doc)
#print tostring(result_tree)
return result_tree
else:
outputstream = ByteArrayOutputStream()
result = StreamResult(outputstream)
self.transformer.transform(doc_source, result)
resultdoc = builder.newDocument()
resulttree = _XSLTResultTree(resultdoc)
resulttree._text = outputstream.toString(output_encoding)
return resulttree
def __call__(self, _input, profile_run=False, **kw):
nsmap = dict(xsl='http://www.w3.org/1999/XSL/Transform')
output_method = 'xml'
output_encoding = 'utf-8'
nodes = self.xsl_tree.xpath('xsl:output/@method', namespaces=nsmap)
if len(nodes) > 0:
output_method = nodes[0]
nodes = self.xsl_tree.xpath('xsl:output/@encoding', namespaces=nsmap)
if len(nodes) > 0:
output_encoding = nodes[0]
#print tostring(_input)
if isinstance(_input, _ElementTree):
doc_source = DOMSource(_input._dom_doc)
elif isinstance(_input, _Element):
# Xalan-J 2.7.1 does not support a DOMSource from an Element
# so we build new document
dom_doc = builder.newDocument()
dom_root = dom_doc.importNode(_input._dom_element, True)
dom_doc.appendChild(dom_root)
doc_source = DOMSource(dom_doc)
else:
raise NotImplementedError()
if output_method in ('xml', 'html'):
# TODO: for testing
outputstream = ByteArrayOutputStream()
result = StreamResult(outputstream)
self.transformer.transform(doc_source, result)
bytes = outputstream.toByteArray()
inputstream = ByteArrayInputStream(bytes)
try:
dom_doc = builder.parse(inputstream)
except:
import sys
sys.stderr.write(bytes.tostring())
raise
result_tree = _ElementTree(dom_doc)
return result_tree
result = DOMResult()
self.transformer.transform(doc_source, result)
dom_doc = result.getNode()
result_tree = _ElementTree(dom_doc)
#print tostring(result_tree)
return result_tree
else:
outputstream = ByteArrayOutputStream()
result = StreamResult(outputstream)
self.transformer.transform(doc_source, result)
resultdoc = builder.newDocument()
resulttree = _XSLTResultTree(resultdoc)
resulttree._text = outputstream.toString(output_encoding)
return resulttree
def BufferedImgToNotebook(img):
from java.io import ByteArrayOutputStream
from java.util import Base64 ##only in java8
from javax.imageio import ImageIO
bos=ByteArrayOutputStream();
ImageIO.write(img, "png", Base64.getEncoder().wrap(bos));
data = bos.toString("UTF-8");
return {"display":"image","data":data}
def BufferedImgToNotebook(img):
from java.io import ByteArrayOutputStream
from java.util import Base64 ##only in java8
from javax.imageio import ImageIO
bos = ByteArrayOutputStream()
ImageIO.write(img, "png",
Base64.getEncoder().wrap(bos))
data = bos.toString("UTF-8")
return {"display": "image", "data": data}
def mouseClicked(self, s, g) : x = JOptionPane.showInputDialog(self.client_state, "Type your text here:") if x is None: x = '' bout = ByteArrayOutputStream() eout = EscapingOutputStream(bout) eout.write(x) y = bout.toString() return self._getmetadata() + "|" + "(%d,%d)|%s " % (s.x, s.y, y)
def getStreamData(stream):
baos = ByteArrayOutputStream()
lenRead = 0
while lenRead >= 0:
bytes = jarray.zeros(4096, 'b')
lenRead = stream.read(bytes, 0, 4096)
if lenRead > 0:
baos.write(bytes, 0, lenRead)
stream.close();
return baos.toString()
def retrieveBody(delivery):
if delivery.properties.contentEncoding == "DEF":
compressed = Base64.decodeBase64(String(delivery.body).getBytes("UTF-8"))
inflated = ByteArrayOutputStream()
inflatedOs = InflaterOutputStream(inflated)
inflatedOs.write(compressed)
inflatedOs.close()
return inflated.toString("UTF-8")
else:
return String(delivery.body, "UTF-8")
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 retrieveBody(delivery):
if delivery.properties.contentEncoding == "DEF":
compressed = Base64.decodeBase64(
String(delivery.body).getBytes("UTF-8"))
inflated = ByteArrayOutputStream()
inflatedOs = InflaterOutputStream(inflated)
inflatedOs.write(compressed)
inflatedOs.close()
return inflated.toString("UTF-8")
else:
return String(delivery.body, "UTF-8")
def asmify(clazz, skipdebug=False):
""" Print the ASM java code calls necessary to construct the clazz on the fly.
Works only for classes loaded by the Fiji startup ClassLoader from .class files.
See org.objectweb.asm.util.Printer.main method at: https://gitlab.ow2.org/asm/asm/blob/master/asm-util/src/main/java/org/objectweb/asm/util/Printer.java#L1225
To see the ASM java code calls for an arbitrary .class file, run instead:
$ java --classpath .:/path/to/Fiji.app/jars/asm-5.0.4.jar:/path/to/Fiji.app/jars/asm-util.4.0.jar org.objectweb.asm.util.ASMfier <package>/classname.class """
baos = ByteArrayOutputStream() # expands size as needed
tcv = TraceClassVisitor(None, ASMifier(), PrintWriter(baos))
ClassReader(clazz).accept(tcv, ClassReader.SKIP_DEBUG if skipdebug else 0)
return baos.toString()
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 __tidy(self, content):
tidy = Tidy()
tidy.setIndentAttributes(False)
tidy.setIndentContent(False)
tidy.setPrintBodyOnly(True)
tidy.setSmartIndent(False)
tidy.setWraplen(0)
tidy.setXHTML(False)
tidy.setNumEntities(True)
out = ByteArrayOutputStream()
doc = tidy.parseDOM(ByteArrayInputStream(String(content).getBytes()), out)
content = out.toString("UTF-8")
return content, doc
def getPdf(htmlString):
converter = CYaHPConverter()
encoder = ByteArrayOutputStream()
out = MimeUtility.encode(encoder, "base64");
#out = ByteArrayOutputStream()
properties = HashMap()
headerFooterList = ArrayList()
properties.put(IHtmlToPdfTransformer.PDF_RENDERER_CLASS, IHtmlToPdfTransformer.FLYINGSAUCER_PDF_RENDERER)
converter.convertToPdf(htmlString, IHtmlToPdfTransformer.A4P, headerFooterList, 'https://reflexsystems.com/', out, properties)
out.close()
#return out.toString()
return encoder.toString()
def showImg(width=400,height=300):
""" This function shows the image from current IDV frame, optional arguments are width and height in pixels, they
currently default to 400 and 300"""
from java.util import Base64 ##only in java8
from javax.imageio import ImageIO
from java.io import ByteArrayOutputStream
from ucar.unidata.ui.ImageUtils import resize,toBufferedImage
pause()
img=getImage()
img=toBufferedImage(resize(img,width,height));
bos=ByteArrayOutputStream();
ImageIO.write(img, "png", Base64.getEncoder().wrap(bos));
data = bos.toString("UTF-8");
return {"display":"image","data":data}
def __tidy(self, content):
tidy = Tidy()
tidy.setIndentAttributes(False)
tidy.setIndentContent(False)
tidy.setPrintBodyOnly(True)
tidy.setSmartIndent(False)
tidy.setWraplen(0)
tidy.setXHTML(True)
tidy.setNumEntities(True)
tidy.setShowWarnings(False)
tidy.setQuiet(True)
out = ByteArrayOutputStream()
tidy.parse(IOUtils.toInputStream(content, "UTF-8"), out)
return out.toString("UTF-8")
def showImg(width=None,height=None):
""" This function shows the image from current IDV frame, optional arguments are width and height in pixels, they
currently default to 400 and 300"""
from java.util import Base64 ##only in java8
from javax.imageio import ImageIO
from java.io import ByteArrayOutputStream
from ucar.unidata.ui.ImageUtils import resize,toBufferedImage
pause()
#imgx=getImage() currently not working with new changes to idv
img=idv.getViewManager().getMaster().getImage(True)
if width != None and height != None:
img=toBufferedImage(resize(img,width,height));
bos=ByteArrayOutputStream();
ImageIO.write(img, "png", Base64.getEncoder().wrap(bos));
data = bos.toString("UTF-8");
return {"display":"image","data":data}
def showImg(width=None, height=None):
""" This function shows the image from current IDV frame, optional arguments are width and height in pixels, they
currently default to 400 and 300"""
from java.util import Base64 ##only in java8
from javax.imageio import ImageIO
from java.io import ByteArrayOutputStream
from ucar.unidata.ui.ImageUtils import resize, toBufferedImage
pause()
#imgx=getImage() currently not working with new changes to idv
img = idv.getViewManager().getMaster().getImage(True)
if width != None and height != None:
img = toBufferedImage(resize(img, width, height))
bos = ByteArrayOutputStream()
ImageIO.write(img, "png",
Base64.getEncoder().wrap(bos))
data = bos.toString("UTF-8")
return {"display": "image", "data": data}
def pageContent(self):
# Object ID
oid = self.metadata.getFirst("id")
# Determine MIME Type
mimeType = "Unknown"
mimeList = self.metadata.getList("dc_format")
if mimeList is not None and not mimeList.isEmpty():
mimeType = mimeList.get(0)
# The HTML payload is the real object, display in a frame because we
# have no idea what kind of object it is.
if mimeType == "text/html":
urlBase = self.config.getString(None, ["urlBase"])
if urlBase is None:
"http://%s:%s%s/" % (self.req.serverName, self.serverPort,
self.contextPath)
objectPath = "%s%s/download/%s/" % (urlBase, self.portalId, oid)
return self.frameContent(objectPath)
# We are rendering a HTML preview...
else:
preview = self.metadata.getFirst("preview")
# ... of an IMS package or zipped website. Treat as per html above.
if mimeType == "application/zip":
urlBase = self.config.getString(None, ["urlBase"])
if urlBase is None:
"http://%s:%s%s/" % (self.req.serverName, self.serverPort,
self.contextPath)
objectPath = "%s%s/download/%s/%s" % (urlBase, self.portalId,
oid, preview)
return self.frameContent(objectPath)
# ... of an HTML excerpt, such as an ICE rendition. Render in page.
else:
try:
object = Services.getStorage().getObject(oid)
payload = object.getPayload(preview)
out = ByteArrayOutputStream()
IOUtils.copy(payload.open(), out)
payload.close()
return out.toString("UTF-8")
except StorageException, e:
return
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
class JavaCapturer(object):
def __init__(self, stdout=True):
if stdout:
self._original = System.out
self._set_stream = System.setOut
else:
self._original = System.err
self._set_stream = System.setErr
self._bytes = ByteArrayOutputStream()
self._stream = PrintStream(self._bytes, False, "UTF-8")
self._set_stream(self._stream)
def release(self):
# Original stream must be restored before closing the current
self._set_stream(self._original)
self._stream.close()
output = self._bytes.toString("UTF-8")
self._bytes.reset()
return output
class JavaCapturer(object):
def __init__(self, stdout=True):
if stdout:
self._original = System.out
self._set_stream = System.setOut
else:
self._original = System.err
self._set_stream = System.setErr
self._bytes = ByteArrayOutputStream()
self._stream = PrintStream(self._bytes, False, 'UTF-8')
self._set_stream(self._stream)
def release(self):
# Original stream must be restored before closing the current
self._set_stream(self._original)
self._stream.close()
output = self._bytes.toString('UTF-8')
self._bytes.reset()
return output
def cleanData(data):
from org.w3c.tidy import Tidy
tidy = Tidy()
tidy.setXHTML(True)
tidy.setInputEncoding("UTF-8")
tidy.setOutputEncoding("UTF-8")
tidy.setMakeClean(False)
tidy.setDropEmptyParas(False)
tidy.setPrintBodyOnly(True)
tidy.setQuoteAmpersand(True)
tidy.setTrimEmptyElements(False)
inputStream = ByteArrayInputStream(String(data).getBytes("UTF-8"))
outputStream = ByteArrayOutputStream()
tidy.parseDOM(inputStream, outputStream)
return outputStream.toString("UTF-8")
def pageContent(self):
# Object ID
oid = self.metadata.getFirst("id")
# Determine MIME Type
mimeType = "Unknown"
mimeList = self.metadata.getList("dc_format")
if mimeList is not None and not mimeList.isEmpty():
mimeType = mimeList.get(0)
# The HTML payload is the real object, display in a frame because we
# have no idea what kind of object it is.
if mimeType == "text/html":
urlBase = self.config.getString(None, ["urlBase"])
if urlBase is None:
"http://%s:%s%s/" % (self.req.serverName, self.serverPort, self.contextPath)
objectPath = "%s%s/download/%s/" % (urlBase, self.portalId, oid)
return self.frameContent(objectPath)
# We are rendering a HTML preview...
else:
preview = self.metadata.getFirst("preview")
# ... of an IMS package or zipped website. Treat as per html above.
if mimeType == "application/zip":
urlBase = self.config.getString(None, ["urlBase"])
if urlBase is None:
"http://%s:%s%s/" % (self.req.serverName, self.serverPort, self.contextPath)
objectPath = "%s%s/download/%s/%s" % (urlBase, self.portalId, oid, preview)
return self.frameContent(objectPath)
# ... of an HTML excerpt, such as an ICE rendition. Render in page.
else:
try:
object = Services.getStorage().getObject(oid)
payload = object.getPayload(preview)
out = ByteArrayOutputStream()
IOUtils.copy(payload.open(), out)
payload.close()
return out.toString("UTF-8")
except StorageException, e:
return
def _transform(self):
try:
input = FileInputStream(self.xsl)
xslSource = StreamSource(input)
xslTemplate = TransformerFactory.newInstance().newTemplates(xslSource);
transformer = xslTemplate.newTransformer()
output = ByteArrayOutputStream()
result = StreamResult(output)
source = StreamSource(FileInputStream(self.sourceXml))
transformer.transform(source, result)
f = open(self.targetXml, 'w')
f.write(output.toString())
return True
except:
print ("Something went wrong when trying to transform the XML. Please be sure jython is properly installed and configured.")
return False
def __getContent(self, oid):
slash = oid.rfind("/")
pid = os.path.splitext(oid[slash+1:])[0] + ".htm"
payload = Services.storage.getObject(oid).getPayload(pid)
tidy = Tidy()
tidy.setIndentAttributes(False)
tidy.setIndentContent(False)
tidy.setPrintBodyOnly(True)
tidy.setSmartIndent(False)
tidy.setWraplen(0)
tidy.setXHTML(False)
tidy.setNumEntities(True)
out = ByteArrayOutputStream()
try:
doc = tidy.parseDOM(payload.getInputStream(), out)
content = out.toString("UTF-8")
content = self.__processMedia(oid, doc, content)
#print "[\n%s\n]" % content
except Exception, e:
print " * blog.py: Failed to get content: %s" % e.getMessage()
def getSourceSample(self, id, limit):
# Get source payload
object = self.services.getStorage().getObject(id)
if object is not None:
payload = object.getPayload(object.getSourceId())
# Read to a string
if payload is not None:
out = ByteArrayOutputStream()
IOUtils.copy(payload.open(), out)
payload.close()
string = out.toString("UTF-8")
# Return response
if string is not None:
if (len(string)) > limit:
return string[0:limit] + "..."
else:
return string
else:
return ""
def getSourceSample(self, id, limit):
# Get source payload
object = self.services.getStorage().getObject(id)
if object is not None:
payload = object.getPayload(object.getSourceId())
# Read to a string
if payload is not None:
out = ByteArrayOutputStream()
IOUtils.copy(payload.open(), out)
payload.close()
string = out.toString("UTF-8")
# Return response
if string is not None:
if (len(string)) > limit:
return string[0:limit] + "..."
else:
return string
else:
return ""
def alt_handle(self):
try:
raw_xml = self.rfile.readline().strip()
marc_xmlfile = NamedTemporaryFile(delete=False)
marc_xmlfile.write(raw_xml)
marc_xmlfile.close()
base_uri = INFO.get('base_uri','http://catalog/')
args = [INFO.get('saxon_xqy'),
'marcxmluri={}'.format(
os.path.normpath(marc_xmlfile.name).replace("\\", "/")),
'baseuri={}'.format(INFO.get('base_uri',
'http://catalog/')),
'serialization=rdfxml']
query = saxon.Query()
output_stream = ByteArrayOutputStream()
System.setOut(PrintStream(output_stream))
query.main(args)
self.wfile.write(output_stream.toString().encode('ascii',
errors='ignore'))
os.remove(marc_xmlfile.name)
except:
self.wfile.write("Error processing MARC XML:\n\t{}".format(sys.exc_info()[0]))
def getContent(self, oid, metadata):
# Get the object
object = Services.getStorage().getObject(oid)
if object is None:
return ""
# Get the preview/source payload
pid = metadata.getFirst("preview")
if pid is None:
pid = object.getSourceId()
if pid is None:
return ""
payload = object.getPayload(object.getSourceId())
if payload is None:
return ""
# Stream the content out to string
out = ByteArrayOutputStream()
IOUtils.copy(payload.open(), out)
payload.close()
string = out.toString("UTF-8")
return "<pre>" + StringEscapeUtils.escapeHtml(string) + "</pre>"
class VTLKernel(Kernel):
implementation = 'VTL Engine'
implementation_version = '${python.package.version}'
language = 'VTL'
language_version = '2.1'
language_info = {
'name': 'VTL',
'mimetype': 'text/x-vtl',
'file_extension': '.vtl',
}
banner = "${project.description}"
queryPattern = re.compile(r"^\s*\?\s*(\S+)\s*$")
def __init__(self, *args, **kwargs):
super(VTLKernel, self).__init__(*args, **kwargs)
startJVM()
from java.lang import System
from java.io import ByteArrayOutputStream
from java.io import PrintStream
self.baos = ByteArrayOutputStream()
ps = PrintStream(self.baos)
System.setOut(ps)
System.setErr(ps)
it = JPackage('it')
self.VTLSession = it.bancaditalia.oss.vtl.config.ConfigurationManager.getDefault().createSession()
def sendLog(self):
self.send_response(self.iopub_socket, 'stream', {
'name':'Log',
'text':str(self.baos.toString())
})
self.baos.reset()
def sendData(self, alias, value):
if isinstance(value, JPackage('it').bancaditalia.oss.vtl.model.data.DataSet):
html = convertDataSet(value)
else:
html = convertScalar(alias, value)
self.send_response(self.iopub_socket, 'display_data', {
'data': {
'text/html': html
},
'metadata': {},
'transient': {}
})
def do_execute(self, code, silent, store_history=True, user_expressions=None, allow_stdin=False):
from java.lang import Exception
matcher = self.queryPattern.fullmatch(code)
try:
user_expressions = {}
if matcher is not None:
name = matcher.group(1)
self.sendData(name, self.VTLSession.resolve(name))
self.sendLog()
else:
statements = self.VTLSession.addStatements(code).getWorkspace().getRules()
self.sendLog()
self.VTLSession.compile()
self.sendLog()
for statement in statements:
name = statement.getId()
self.sendData(name, self.VTLSession.resolve(name))
self.sendLog()
user_expressions = { str(statement.getId()): str(statement.getExpression().toString()) for statement in statements }
response = {
'status': 'ok',
'execution_count': self.execution_count,
'user_expressions': user_expressions
}
except Exception as ex:
ex.printStackTrace()
self.sendLog()
traceback = [str(tr.toString()) for tr in ex.getStackTrace()]
while ex.getCause() != None:
ex = ex.getCause()
traceback.append("Caused by " + str(ex.getClass().getName()) + ": " + str(ex.getMessage()))
traceback.append([str(tr.toString()) for tr in ex.getStackTrace()])
response = {
'status' : 'error',
'ename' : str(ex.getClass().getName()),
'evalue' : str(ex.getMessage()),
'traceback' : traceback
}
return response
def do_shutdown(self, restart):
if restart:
if not jpype.isJVMStarted():
startJVM()
self.VTLSession = JPackage('it').bancaditalia.oss.vtl.config.ConfigurationManager.getDefault().createSession()
else:
jpype.shutdownJVM()
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()
