def test_mergeXMLDocs():
# test without a namespace
parentXML = libxml2.parseDoc("<a><b/></a>")
childXML = libxml2.parseDoc("<c>Hello World</c>")
expectedXML = libxml2.parseDoc("<a><b><c>Hello World</c></b></a>")
xpath = "//b"
foxml = fedoraObject(fedoraObject.inactiveState, "test:99",
"test import object", "VITAL2")
mergedXML = foxml.mergeXMLDocs(parentXML, childXML, xpath, None)
assert diff_util.sameXml(mergedXML.serialize(), expectedXML.serialize())
#Test with non ascii characters
parentXML = libxml2.parseDoc("<a><b/></a>")
unicodeXML = libxml2.parseFile("../xml_data/umlaut.xml")
expectedXML = libxml2.parseFile("../xml_data/merged-umlaut.xml")
mergedXML = foxml.mergeXMLDocs(parentXML, unicodeXML, xpath, None)
assert diff_util.sameXml(mergedXML.serialize(), expectedXML.serialize())
#Merge changes the parent doc!
#assert diff_util.sameXml(parentXML.serialize(), expectedXML.serialize())
# test with a namespace
foxml = fedoraObject(fedoraObject.inactiveState, "test:99",
"test import object", "VITAL2")
parentXML = libxml2.parseDoc(foxml.serialize())
xpathContext = parentXML.xpathNewContext()
xpathContext.xpathRegisterNs(
"foxml", "http://www.fedora.info/resources/faq.shtml#rdfproperties")
childXML = libxml2.parseFile("../xml_data/rubric_DC.xml")
expectedXML = libxml2.parseFile("../xml_data/rubric_mergeXML_test.xml")
expectedXML = libxml2.parseDoc(xml_normalize.normalizeXml(expectedXML))
xpath = "//foxml:digitalObject"
mergedXML = foxml.mergeXMLDocs(parentXML, childXML, xpath, xpathContext)
assert diff_util.sameXml(mergedXML.serialize(), expectedXML.serialize())
def test_bodyHtmlToXML():
targetBodyFile = open("xml_data/body_item.xml", 'r')
targetBody = targetBodyFile.read()
htmlFile2 = open("html_data/thompson-index.html", 'r')
bodyHtml = htmlFile2.read()
testThis2 = xml_util.xml(targetBody)
resultBody = bodyHtmlToXML(bodyHtml)
assert diff_util.sameXml(targetBody,resultBody)
def test_htmlToXML():
targetFile = open("xml_data/meta_lowercase.xml", 'r')
target = targetFile.read()
htmlFile = open("html_data/thompson-index.html", 'r')
html = htmlFile.read()
testThis = xml_util.xml(target)
result = htmlToXML(html)
assert diff_util.sameXml(target, result)
def test_createDCXML():
htmlFile3 = open("html_data/thompson-index.html", 'r')
fullHtml = htmlFile3.read()
dcXML = createDCXML(fullHtml)
targetFileDC = open("xml_data/DCMurdoch.xml", 'r')
targetDC = targetFileDC.read()
#testThis = xml_util.xml(targetDC)
assert diff_util.sameXml(targetDC,dcXML)
def test_addDublinCore():
foxml = fedoraObject(fedoraObject.inactiveState, "test:99",
"test import object", "VITAL2")
dublinCore = libxml2.parseFile("../xml_data/rubric_DC.xml")
#testxml = libxml2.parseFile("../xml_data/rubric_with_DC_A.xml")
#testxml = libxml2.parseFile("../xml_data/rubric_with_DC_B.xml")
testxml = libxml2.parseFile("../xml_data/rubric_with_DC_C.xml")
foxml.addDublinCore(dublinCore, fedoraObject.inactiveState)
assert diff_util.sameXml(foxml.serialize(), testxml.serialize())
def test_htmlToXML():
targetFile = open("../xml_data/meta_lowercase.xml", 'r')
target = targetFile.read()
htmlFile = open("../html_data/thompson-index.html", 'r')
html = htmlFile.read()
testThis = libxml2.parseDoc(target)
result = htmlToXML(html, "PhD Doctorate")
print result
assert diff_util.sameXml(target, result)
def test_addCreator():
testXml = """<?xml version="1.0" encoding="UTF-8"?>
<oai_dc:dc xmlns:oai_dc="http://www.openarchives.org/OAI/2.0/oai_dc/" xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
xsi:schemaLocation="http://www.openarchives.org/OAI/2.0/oai_dc/ http://www.openarchives.org/OAI/2.0/oai_dc.xsd">
<dc:creator>James Bond</dc:creator>
</oai_dc:dc>
"""
testXmlDoc = libxml2.parseDoc(testXml)
testVitalDublinCore = dublin_core.vitalDublinCore()
testVitalDublinCore.addCreator("James Bond")
assert diff_util.sameXml(testVitalDublinCore.serialize(),
testXmlDoc.serialize())
def test_addExternalDataStream():
foxml = fedoraObject(fedoraObject.inactiveState, "test:99",
"test import object", "VITAL2")
inlineXML = libxml2.parseFile("../xml_data/rubric_inlineXML.xml")
dublinCore = libxml2.parseFile("../xml_data/rubric_DC.xml")
testxml = libxml2.parseFile(
"../xml_data/rubric_with_external_datastream.xml")
foxml.addDublinCore(dublinCore, fedoraObject.inactiveState)
foxml.addInlineXML("rubric", "rubric-inline", inlineXML,
fedoraObject.inactiveState)
foxml.addExternalDataStream("rubric-external", "application/pdf",
"rubric-test-external-pdf",
"http://localhost/test.pdf",
fedoraObject.activeState)
assert diff_util.sameXml(foxml.serialize(), testxml.serialize())
def test_Unicode_characters():
foxml = fedoraObject(fedoraObject.inactiveState, "test:99",
"test import object", "VITAL")
inlineXML = libxml2.parseFile("../xml_data/unicode_input.xml")
dublinCore = libxml2.parseFile("../xml_data/rubric_vital_DC.xml")
testxml = libxml2.parseFile("../xml_data/unicode_output.xml")
foxml.addDublinCore(dublinCore, fedoraObject.inactiveState)
foxml.addInlineXML("MARC", "MARCXML", inlineXML,
fedoraObject.inactiveState)
foxml.addManagedDataStream("DS1", "application/pdf", "Journal Article",
"http://localhost/managed.pdf",
fedoraObject.activeState)
foxml.writeFile("/tmp/foxml_test_output.xml")
assert diff_util.sameXml(foxml.serialize(), testxml.serialize())
assert os.path.exists("/tmp/foxml_test_output.xml")
def test_addAllNodes():
testXmlDoc = libxml2.parseFile("../xml_data/test_dublin_core.xml")
testVitalDublinCore = dublin_core.vitalDublinCore()
testVitalDublinCore.addTitle("This is a test title")
testVitalDublinCore.addCreator("This is a test author")
testVitalDublinCore.addSubject("This is a test subject")
testVitalDublinCore.addDescription("This is a test description")
testVitalDublinCore.addPublisher("This is a test publisher")
testVitalDublinCore.addContributor("This is a test contributor")
testVitalDublinCore.addDate("This is a test date")
testVitalDublinCore.addType("This is a test type")
testVitalDublinCore.addFormat("This is a test format")
testVitalDublinCore.addIdentifier("This is a test identifier")
testVitalDublinCore.addSource("This is a test source")
testVitalDublinCore.addLanguage("This is a test language")
testVitalDublinCore.addRelation("This is a test relation")
testVitalDublinCore.addCoverage("This is a test coverage")
testVitalDublinCore.addRights("This is a test right")
assert diff_util.sameXml(testVitalDublinCore.serialize(),
testXmlDoc.serialize())
def processTest(name, xsltSrc, xmlSrc, expectedXml):
print "--- Test: '%s' ---" % name
xslt = xslt_util.xslt(xsltSrc)
r = "<root"
for ns in nsList:
r += " xmlns:" + ns[0] + '="' + ns[1] + '"\n'
r += ">\n"
r += xmlSrc + "\n</root>"
xml = IceCommon.Xml(r, nsList)
newXml = xml.applyXslt(xslt)
xslt.close()
xml.close()
expected = expectedXml.replace("utfx:expected",
"body").replace(' validate="no"', "")
html = """<html xmlns="http://www.w3.org/1999/xhtml">
<head>
<meta content="text/html; charset=UTF-8" http-equiv="Content-Type"></meta>
<title> Untitled </title>
<style type="text/css" xml:space="preserve">table {border-spacing: 0;empty-cells: show;} </style>
</head>
<body>
</body>
</html>"""
xml = IceCommon.Xml(expected, nsList)
import diff_util
same = diff_util.sameXml(newXml.getNode("//body"), xml.getNode("//body"),
False)
print "Same=", same
if same is False:
for node in newXml.getNode("//body").getChildren():
if node.getType() != "text":
print node
print
for node in xml.getNode("//body").getChildren():
if node.getType() != "text":
print node
newXml.close()
xml.close()
print "--- Done ---\n"
def test_fedoraObject():
foxml = fedoraObject(fedoraObject.inactiveState, "test:99",
"test import object", "VITAL2")
testxml = libxml2.parseFile("../xml_data/rubric_base_foxml.xml")
assert diff_util.sameXml(foxml.serialize(), testxml.serialize())
