def testAssertions(self):
# TQA-02.4
with self.assertRaises(KeyError):
Document('testdocs/bad_extension.doc')
self.assertEqual(self.test_stdout.getvalue(),
'File extension is not an OOXML file type')
# Skip this test: The document doesn't follow the spec, but is still openable
# with self.assertRaisesRegexp(AssertionError,
# 'content_type of Part is empty'):
# Document('testdocs/missing_content_type.docx')
with self.assertRaises(KeyError):
Document('testdocs/missing_part.docx')
self.assertEqual(
self.test_stdout.getvalue(),
'target_path is not a valid Part: /word/endnotes.xml')
with self.assertRaises(KeyError):
Document('testdocs/missing_rel_target.docx')
self.assertEqual(self.test_stdout.getvalue(),
'target_path is not a valid Part: /')
with self.assertRaises(etree.XMLSyntaxError):
Document('testdocs/corrupt_xml.docx')
self.assertEqual(
self.test_stdout.getvalue(),
'part cannot be parsed successfully: Part [/[Content_Types].xml]'
)
def testFileName(self):
doc1 = Document('testdocs/test.docx')
self.assertTrue(doc1.type == 'Word')
doc2 = Document('testdocs/test.xlsx')
self.assertTrue(doc2.type == 'Excel')
doc3 = Document('testdocs/test.pptx')
self.assertTrue(doc3.type == 'PowerPoint')
def testRelationships(self):
doc1 = Document('testdocs/test.docx')
self.assertEqual(len(doc1.relationships), 13)
reltype = 'http://schemas.openxmlformats.org/officeDocument/2006/relationships/officeDocument'
self.assertEqual(doc1.relationships_dict[reltype][0].target,
'word/document.xml')
self.assertEqual(
doc1.find_relationships_by_type('metadata/core-properties')
[0].source.name, 'RootPart')
self.assertEqual(
doc1.find_relationships_by_type('metadata/core-properties')
[0].source.content_type(), '(virtual root part)')
self.assertEqual(
doc1.find_relationships_by_type('metadata/core-properties')[0].id,
'rId2')
self.assertEqual(
doc1.find_relationships_by_type('metadata/core-properties')
[0].target, 'docProps/core.xml')
self.assertEqual(
doc1.find_relationships_by_type('metadata/core-properties')
[0].target_part.name, '/docProps/core.xml')
self.assertEqual(
doc1.find_relationships_by_type(
'metadata/core-properties')[0].type,
'http://schemas.openxmlformats.org/package/2006/relationships/metadata/core-properties'
)
self.assertEqual(
doc1.find_relationships_by_type('metadata/core-properties')
[0].is_external, False)
doc2 = Document('testdocs/216688.docx')
self.assertEqual(
doc2.find_relationships_by_type('hyperlink')[0].is_external, True)
self.assertEqual(
doc1.part_by_name['/word/document.xml'].relationships_out()[2].id,
'rId7')
self.assertEqual(
doc1.part_by_name['/docProps/app.xml'].relationships_out(), [])
self.assertEqual(
doc1.part_by_name['/docProps/app.xml'].relationships_in()[0].id,
'rId3')
self.assertEqual(doc1.root_part.relationships_out()[1].id, 'rId2')
self.assertEqual(
doc1.parts_by_relationship_type('extended-properties')[0].name,
'/docProps/app.xml')
self.assertEqual(
doc1.parts_by_relationship_type('ships/extended-properties')
[0].name, '/docProps/app.xml')
self.assertEqual(doc1.main_part().name, '/word/document.xml')
def testBugs(self):
# Regression test for BUG OXPA-83
# Make sure Target_Part='NULL', in this case a Relationship with
# Type 'image', is handled properly
doc1 = Document('testdocs/037027.pptx')
for image in doc1.features.images:
test = image.name
def testFeatures(self):
doc1 = Document('testdocs/content.docx')
self.assertEqual(doc1.features.custom_properties, [])
self.assertEqual(len(doc1.features.images), 14)
self.assertEqual([
i.content_type()
for i in doc1.features.images if i.name == '/word/media/image1.png'
], ['image/png'])
self.assertEqual(
sorted(doc1.features.images,
key=lambda part: part.name)[0].content_type(), 'image/png')
self.assertEqual(len(doc1.features.videos), 0)
self.assertEqual(len(doc1.features.fonts), 2)
self.assertEqual(
sorted(doc1.features.fonts, key=lambda part: part.name)[0].name,
'/word/fonts/font1.odttf')
doc2 = Document('testdocs/sounds.pptx')
self.assertEqual(
sorted(doc2.features.sounds, key=lambda part: part.name)[0].name,
'/ppt/media/audio1.wav')
self.assertEqual(
sorted(doc2.features.sounds,
key=lambda part: part.name)[0].content_type(), 'audio/wav')
doc3 = Document('testdocs/macros.xlsm')
self.assertEqual(
sorted(doc3.features.macros, key=lambda part: part.name)[0].name,
'/xl/vbaProject.bin')
self.assertEqual(
sorted(doc3.features.embedded_controls,
key=lambda part: part.name)[0].name,
'/xl/activeX/activeX1.xml')
doc4 = Document('testdocs/content2.docx')
self.assertEqual(
sorted(doc4.features.embedded_packages,
key=lambda part: part.name)[2].name,
'/word/embeddings/Microsoft_Excel-Arbeitsblatt3.xlsx')
self.assertEqual(len(doc1.features.embedded_objects), 10)
self.assertEqual(
sorted(doc1.features.embedded_objects,
key=lambda part: part.name)[2].name,
'/word/embeddings/Microsoft_Office_PowerPoint_97-2003_Presentation7.ppt'
)
def testPartCollection(self):
doc1 = Document('testdocs/test.docx')
self.assertEquals(doc1.parts[0].name, '/[Content_Types].xml')
self.assertEquals(doc1.parts[0].stream().read(10),
b'\x3C\x3F\x78\x6D\x6C\x20\x76\x65\x72\x73')
self.assertEquals(doc1.parts[2].name, '/word/_rels/document.xml.rels')
self.assertEquals(doc1.part_by_name['/[Content_Types].xml'].name,
'/[Content_Types].xml')
self.assertEquals(
doc1.part_by_name['/[Content_Types].xml'].stream().read(10),
b'\x3C\x3F\x78\x6D\x6C\x20\x76\x65\x72\x73')
def testContentTypes(self):
doc1 = Document('testdocs/test.docx')
part1 = doc1.part_by_name['/word/document.xml']
self.assertEquals(
part1.content_type(),
'application/vnd.openxmlformats-officedocument.wordprocessingml.document.main+xml'
)
part2 = Document(
'testdocs/test.docx').part_by_name['/customXml/item1.xml']
self.assertEquals(part2.content_type(), 'application/xml')
self.assertEqual(
doc1.parts_by_content_type(
'application/vnd.ms-word.stylesWithEffects+xml')[0].name,
'/word/stylesWithEffects.xml')
self.assertEqual(
doc1.parts_by_content_type_regex('footnotes')[0].name,
'/word/footnotes.xml')
self.assertEqual(
doc1.parts_by_content_type_regex('properties')[1].name,
'/docProps/app.xml')
def testZipfileProperties(self):
doc1 = Document('testdocs/test.docx')
self.assertEquals(doc1.zip().namelist()[0], '[Content_Types].xml')
self.assertEquals(doc1.zip().comment, '')
self.assertEquals(
doc1.zip().part_extract('[Content_Types].xml').read(10),
b'\x3C\x3F\x78\x6D\x6C\x20\x76\x65\x72\x73')
self.assertEquals(len(doc1.zip().namelist()), 17)
doc2 = Document('testdocs/testzipattrib.docx')
self.assertEquals(
doc2.zip().part_info('[Content_Types].xml').file_size, 1818)
self.assertEquals(
doc2.zip().part_info('[Content_Types].xml').compress_size, 406)
self.assertEquals(
doc2.zip().part_info('[Content_Types].xml').date_time,
(2013, 07, 03, 15, 22, 12))
self.assertEquals(doc2.zip().part_info('[Content_Types].xml').comment,
'')
with self.assertRaises(ZipCRCError):
Document('testdocs/badcrc.docx').zip()
def testCoreProperties(self):
doc1 = Document('testdocs/test.docx')
self.assertEqual(doc1.core_properties.name, '/docProps/core.xml')
self.assertEqual(doc1.core_properties.category, 'Auxiliary')
self.assertEqual(doc1.core_properties.content_status, '')
self.assertEqual(doc1.core_properties.created, '2010-10-21T08:54:00Z')
self.assertEqual(doc1.core_properties.creator, 'Klaus-Peter Eckert')
self.assertEqual(doc1.core_properties.description,
'Footnotes and endnotes in different sections')
self.assertEqual(doc1.core_properties.identifier, '')
self.assertEqual(doc1.core_properties.keywords,
'rainbow, color, colour, couleur')
self.assertEqual(doc1.core_properties.language, '')
self.assertEqual(doc1.core_properties.last_modified_by,
'Klaus-Peter Eckert')
self.assertEqual(doc1.core_properties.last_printed, '')
self.assertEqual(doc1.core_properties.modified, '2010-10-21T09:05:00Z')
self.assertEqual(doc1.core_properties.revision, '4')
self.assertEqual(doc1.core_properties.subject, '')
self.assertEqual(doc1.core_properties.title, '')
self.assertEqual(doc1.core_properties.version, '')
doc2 = Document('testdocs/no_core_props.docx')
self.assertEqual(doc2.core_properties.name, '')
def testExportJSON(self):
doc1 = Document('testdocs/test.docx')
self.assertEqual(
doc1.part_by_name['/word/document.xml'].to_reference(),
'Part [/word/document.xml]')
self.assertEqual(
doc1.part_by_name['/word/document.xml'].relationships_out()
[2].to_reference(),
'Relationship [rId7] (source Part [/word/document.xml])')
self.assertEqual(
doc1.part_by_name['/word/document.xml'].to_json()[0:30],
'{\n "content-type": "applica')
self.assertEqual(doc1.relationships[0].to_json()[0:32],
'{\n "source": "Part [RootPart]')
self.assertEqual(doc1.to_json()[0:20], '{\n "document": [\n')
self.assertEqual(
doc1.to_json(include_stream=True)[285:325],
' "stream_b64": "PD94bWwgdmVyc2lvbj0i')
def testPartXML(self):
part1 = Document(
'testdocs/test.docx').part_by_name['/word/document.xml']
self.assertEquals(
list(part1.xml().getroot().iterchildren())[0].tag,
'{http://schemas.openxmlformats.org/wordprocessingml/2006/main}body'
)
self.assertEquals(
part1.xpath('//@w:val',
part1.xml().getroot().nsmap)[2], 'Funotenzeichen')
part2 = Document(
'testdocs/test.docx').part_by_name['/[Content_Types].xml']
xmlns = {
'ct':
'http://schemas.openxmlformats.org/package/2006/content-types'
}
self.assertEqual(
part2.xpath('/ct:Types/ct:Override/@PartName', xmlns)[0],
'/word/document.xml')
part3 = Document(
'testdocs/testutf16.docx').part_by_name['/word/document.xml']
self.assertEquals(
part3.xml().xpath(
'//*[local-name() = "lang"]/@*[local-name() = "val"]')[0],
'en-US')
part4 = Document(
'testdocs/testascii.docx').part_by_name['/word/document.xml']
self.assertEquals(
part4.xml().xpath(
'//*[local-name() = "lang"]/@*[local-name() = "val"]')[0],
'en-US')
doc5 = Document('testdocs/macros-non-standard.xlsm')
self.assertEqual(doc5.features.macros[0].name, '/xl/new_name.bin')
part6 = Document('testdocs/non-standard-namespace.docx'
).part_by_name['/word/document.xml']
self.assertEquals(
part1.xpath('//@fake:val',
part6.xml().getroot().nsmap)[2], 'Funotenzeichen')
def testDenialOfService(self):
doc = Document('testdocs/dos.docx')
def testPseudoFile(self):
with open("testdocs/macros.xlsm", 'rb') as f:
pf = BytesIO(f.read())
Document(pseudofile=pf, filename='macros.xlsm')
def testPart(self):
part1 = Part(Document('testdocs/test.docx'), '/[Content_Types].xml')
self.assertEquals(part1.name, '/[Content_Types].xml')
self.assertEquals(part1.stream().read(10),
b'\x3C\x3F\x78\x6D\x6C\x20\x76\x65\x72\x73')
def testDocOpen(self):
cur_dir = os.path.dirname(os.path.realpath(__file__))
corpus_path = [
os.path.join(cur_dir, 'govdocs'),
os.path.join(cur_dir, 'fraunhoferlibrary')
]
files = []
for dir_ in corpus_path:
for f in os.listdir(dir_):
file_ = os.path.join(dir_, f)
if os.path.isfile(file_):
files.append(file_)
log = codecs.open('smoke_tests.log',
'w',
encoding='utf-8',
errors="surrogateescape")
errorlog = codecs.open('smoke_tests_error.log',
'w',
encoding='utf-8',
errors="surrogateescape")
# Write error log header
errorlog.write(
'Three files from govdocs (govdocs/641559.docx, govdocs/500968.xlsx, and\n'
'govdocs/974690.xlsx) are apparently corrupt and do not open in Microsoft\n'
'Office 2010; hence, error messages should appear for them. (Note that govdocs\n'
'is a random sample and explicitly includes bad or corrupt files.)\n'
'No other error messages should appear here.\n\n\n')
for docfile in files:
if (sys.version_info < (3, 0)):
to_print = docfile.decode('utf8', 'replace')
else:
to_print = docfile
print('\nTesting %s...' % to_print)
log.write('\nTesting %s...\n' % to_print)
try:
doc1 = Document(docfile)
except ZipCRCError:
msg = 'Error: Bad CRC for file: %s\n' % to_print
print(msg)
log.write(msg)
errorlog.write(msg)
continue
except Exception as e:
msg = 'Error: File: %s: %s - %s\n' % (
to_print, sys.exc_info()[0].__name__, e)
print(msg)
log.write(msg)
errorlog.write(msg)
continue
log.write(' Document type is: %s\n' % doc1.type)
log.write(' Document is macro enabled: %s\n' %
doc1.is_macro_enabled)
log.write(' Document is a template: %s\n' % doc1.is_template)
print(' Testing zip.part_info method...')
log.write(' Testing zip.part_info method...\n')
log.write(
' zip.part_info([Content_Types].xml).file_size: %s\n' %
doc1.zip().part_info('[Content_Types].xml').file_size)
log.write(
' zip.part_info([Content_Types].xml).compress_size: %s\n' %
doc1.zip().part_info('[Content_Types].xml').compress_size)
print(' Done.')
log.write(' Done.\n')
second_part = doc1.parts[1]
print(' Testing Part: %s' % second_part.name)
log.write(' Testing Part: %s\n' % second_part.name)
doc_stream = doc1.part_by_name[second_part.name].stream().read(10)
print(' Part stream successfully captured.')
log.write(' Part stream successfully captured.\n')
partxml = doc1.part_by_name[second_part.name].xml()
print(' Part XML successfully parsed.')
log.write(' Part XML successfully parsed.\n')
print(' Checking doc.xpath method...')
log.write(' Checking doc.xpath method...\n')
log.write(' XPath Result: %s\n' %
doc1.part_by_name['/[Content_Types].xml'].xpath(
'*/@ContentType')[0])
print(' Done.')
log.write(' Done.\n')
print(' Checking that all Parts can get Content_Type...')
log.write(' Checking that all Parts can get Content_Type...\n')
for part in doc1.parts:
ct = part.content_type()
log.write(' Part %s is Content_Type: %s\n' %
(part.name, ct))
print(' Done.')
log.write(' Done.\n')
print(' Checking that Document has main_part...')
log.write(' Checking that Document has main_part...\n')
doc_main = doc1.main_part()
log.write(' Main Part: %s\n' % doc_main.name)
print(' Done.')
log.write(' Done.\n')
print(
' Checking all source and target Relationships for each part...'
)
log.write(
' Checking all source and target Relationships for each part...\n'
)
for part in doc1.parts:
rel_in = part.relationships_in()
rel_out = part.relationships_out()
log.write(' Part %s: Relationships in source name: %s\n' %
(part.name, [r.source.name for r in rel_in]))
log.write(' Part %s: Relationships out: %s\n' %
(part.name, [r.target for r in rel_out]))
print(' Done.')
log.write(' Done.\n')
print(
' Testing Document methods to find by Part or Relationship...'
)
log.write(
' Testing Document methods to find by Part or Relationship...\n'
)
log.write(' doc.parts_by_content_type(application/xml): %s\n' %
doc1.parts_by_content_type('application/xml')[0])
log.write(' doc.parts_by_content_type_regex(ation/xm): %s\n' %
doc1.parts_by_content_type_regex('ation/xm')[0])
log.write(
' doc.parts_by_relationship_type(/relationships/officeDocument: %s\n'
% doc1.parts_by_relationship_type(
'/relationships/officeDocument')[0].name)
log.write(
' doc.find_relationship_by_type(/relationships/officeDocument).source: %s\n'
% doc1.find_relationships_by_type(
'/relationships/officeDocument')[0].source)
print(' Done.')
log.write(' Done.\n')
print(' Checking for all Features...')
log.write(' Checking for Features...\n')
for image in doc1.features.images:
log.write(' Image: %s\n' % image.name)
for video in doc1.features.videos:
log.write(' Video: %s\n' % video.name)
for sound in doc1.features.sounds:
log.write(' Sound: %s\n' % sound.name)
for font in doc1.features.fonts:
log.write(' Font: %s\n' % font.name)
for macro in doc1.features.macros:
log.write(' Macro content: %s\n' % macro.name)
for comment in doc1.features.comments:
log.write(' Comment content: %s\n' % comment.name)
for customX in doc1.features.custom_xml:
log.write(' Custom XML content: %s\n' % customX.name)
for embedded_control in doc1.features.embedded_controls:
log.write(' Embedded Control content: %s\n' %
embedded_control.name)
for embedded_object in doc1.features.embedded_objects:
log.write(' Embedded Object content: %s\n' %
embedded_object.name)
for embedded_package in doc1.features.embedded_packages:
log.write(' Embedded Package content: %s\n' %
embedded_package.name)
for digital_signature in doc1.features.digital_signatures:
log.write(' Digital Signature content: %s\n' %
digital_signature.name)
print(' Done.')
log.write(' Done.\n')
print(' Checking Core Properties...')
log.write(' Checking Core Properties...\n')
log.write(' Category: %s\n' % doc1.core_properties.category)
log.write(' Content status: %s\n' %
doc1.core_properties.content_status)
log.write(' Created: %s\n' % doc1.core_properties.created)
log.write(' Creator: %s\n' % doc1.core_properties.creator)
log.write(' Description: %s\n' %
doc1.core_properties.description)
log.write(' Identifier: %s\n' % doc1.core_properties.identifier)
log.write(' Keywords: %s\n' % doc1.core_properties.keywords)
log.write(' Language: %s\n' % doc1.core_properties.language)
log.write(' Last modified by: %s\n' %
doc1.core_properties.last_modified_by)
log.write(' Last printed: %s\n' %
doc1.core_properties.last_printed)
log.write(' Modified: %s\n' % doc1.core_properties.modified)
log.write(' Revision: %s\n' % doc1.core_properties.revision)
log.write(' Subject: %s\n' % doc1.core_properties.subject)
log.write(' Title: %s\n' % doc1.core_properties.title)
log.write(' Version: %s\n' % doc1.core_properties.version)
print(' Done.')
log.write(' Done.\n')
print(' Checking export to JSON...')
log.write(' Checking export to JSON...\n')
doc_json = doc1.to_json()
log.write(' Beginning of JSON: %s\n' % doc_json[0:50])
print(' Done.')
log.write(' Done.\n')
print('Done.')
log.write('Done.\n')
log.close()
errorlog.close()
def testIfFileExists(self):
with self.assertRaises(IOError):
Document('fakefile.docx')
def testFileTemplate(self):
doc1 = Document('testdocs/test.docx')
self.assertFalse(doc1.is_template)
doc1 = Document('testdocs/test.dotx')
self.assertTrue(doc1.is_template)
def testFileMacro(self):
doc1 = Document('testdocs/test.docx')
self.assertFalse(doc1.is_macro_enabled)
doc2 = Document('testdocs/test.docm')
self.assertTrue(doc2.is_macro_enabled)