def test_lookup(self):
"Test the lookup of the standard printers"
# Check the constants are supported
self.assertTrue(lookup(XML_W) is not None)
self.assertTrue(lookup(HTML_W) is not None)
self.assertTrue(lookup(XHTML_W) is not None)
# Check unknown values raise ValueError
self.assertRaises(ValueError, lookup, 'bogus')
def test_lookup(self):
"Test the lookup of the standard printers"
# Check the constants are supported
self.assertTrue(lookup(XML_W) is not None)
self.assertTrue(lookup(HTML_W) is not None)
self.assertTrue(lookup(XHTML_W) is not None)
# Check unknown values raise ValueError
self.assertRaises(ValueError, lookup, 'bogus')
def convert_body(body, content_type, encoding, writer):
if isinstance(body, str):
if content_type is None:
content_type = "text/plain"
return [body], content_type, len(body)
if isinstance(body, tree.entity):
# XXX have Amara tell me the content type (with encoding)
# This is trac #29
if content_type is None:
if "html" in writer.lower():
content_type = "text/html"
else:
content_type = "application/xml"
w = writers.lookup(writer)
body = body.xml_encode(w, encoding)
return [body], content_type, len(body)
if isinstance(body, unicode):
body = body.encode(encoding)
if content_type is None:
content_type = "text/plain; charset=%s" % (encoding, )
return [body], content_type, len(body)
# Probably one of the normal WSGI responses
if content_type is None:
content_type = "text/plain"
return body, content_type, None
def scanXMLDocument(self, path):
i=0
self.XML_W = lookup("xml")
self.doc = bindery.parse(path)
self.control.SetText(open(path).read())
self.control.EmptyUndoBuffer()
self.control.Colourise(0, -1)
# line numbers in the margin
self.control.SetMarginType(1, wx.stc.STC_MARGIN_NUMBER)
self.control.SetMarginWidth(1, 25)
#self.control.BeginTextColour((255,0,0))
#self.control.SetValue(self.doc.xml_encode(self.XML_W))
self.Sentences = []
for i in range (0, self.control.GetNumberOfLines()):
Line = self.control.GetLineText(i)
Line.strip()
#To remove spaces in the line
Line = re.sub(r"\s+", "", Line, flags=re.UNICODE)
if (Line[0]=='<') & (Line[1]=='S') & (Line[2]=='i'):
"""
Everytime we encouter '<Si' at the beginning
of a line, we append the Sentence Tab with
the line number
"""
self.Sentences.append(i)
def convert_body(body, content_type, encoding, writer):
if isinstance(body, str):
if content_type is None:
content_type = "text/plain"
return [body], content_type, len(body)
if isinstance(body, tree.entity):
# XXX have Amara tell me the content type (with encoding)
# This is trac #29
if content_type is None:
if "html" in writer.lower():
content_type = "text/html"
else:
content_type = "application/xml"
w = writers.lookup(writer)
body = body.xml_encode(w, encoding)
return [body], content_type, len(body)
if isinstance(body, unicode):
body = body.encode(encoding)
if content_type is None:
content_type = "text/plain; charset=%s" % (encoding,)
return [body], content_type, len(body)
# Probably one of the normal WSGI responses
if content_type is None:
content_type = "text/plain"
return body, content_type, None
def test_xbel_2(self):
#BM1 = 'http://hg.4suite.org/amara/trunk/raw-file/bb6c40828b2d/demo/7days/bm1.xbel'
#BM2 = 'http://hg.4suite.org/amara/trunk/raw-file/bb6c40828b2d/demo/7days/bm2.xbel'
doc1 = bindery.parse(FILE('bm1.xbel'))
doc2 = bindery.parse(FILE('bm2.xbel'))
merge(doc1.xbel, doc2.xbel)
normalize_whitespace(doc1)
output = doc1.xml_encode(lookup("xml-indent")) + '\n'
self.assertEqual(output, open(FILE('merged-2.xbel')).read())
def test_write_to_stdout(self):
"Check that the default output is to stdout"
xml_w = lookup('xml')
t = tree.parse("<root>entrée</root>")
stream = StringIO()
try:
sys.stdout = stream
t.xml_write()
self.assertEqual(
stream.getvalue(), '<?xml version="1.0" encoding="UTF-8"?>\n'
'<root>entr\xc3\xa9e</root>')
finally:
sys.stdout = sys.__stdout__
def test_write_to_stdout(self):
"Check that the default output is to stdout"
xml_w = lookup('xml')
t = tree.parse("<root>entrée</root>")
stream = StringIO()
try:
sys.stdout = stream
t.xml_write()
self.assertEqual(stream.getvalue(),
'<?xml version="1.0" encoding="UTF-8"?>\n'
'<root>entr\xc3\xa9e</root>')
finally:
sys.stdout = sys.__stdout__
def parseXMLDocument(self, path):
i=0
self.XML_W = lookup("xml")
self.doc = bindery.parse(path)
#self.control.SetText(open(path).read())
self.control.EmptyUndoBuffer()
self.control.Colourise(0, -1)
# line numbers in the margin
self.control.SetMarginType(1, wx.stc.STC_MARGIN_NUMBER)
self.control.SetMarginWidth(1, 25)
#self.control.BeginTextColour((255,0,0))
self.control.SetValue(self.doc.xml_encode(self.XML_W))
self.Sentences = []
def parseXMLDocument(self, path):
i=0
self.XML_W = lookup("xml")
try:
self.doc = bindery.parse(path)
except amara.lib.IriError:
self.doc = bindery.parse(path, standalone=True)
#self.control.SetText(open(path).read())
self.control.EmptyUndoBuffer()
self.control.Colourise(0, -1)
# line numbers in the margin
self.control.SetMarginType(1, wx.stc.STC_MARGIN_NUMBER)
self.control.SetMarginWidth(1, 25)
self.control.SetValue(self.doc.xml_encode(self.XML_W).decode("utf-8").replace("<S id=","\n <S id=").replace("<", u"\u2039").replace(">", u"\u203A"))
def test_encode(self):
xml_w = lookup('xml')
t = tree.parse("<root>entrée</root>")
# Default is UTF-8.
self.assert_(xml_compare(t.xml_encode(),
'<?xml version="1.0" encoding="UTF-8"?>\n'
'<root>entr\xc3\xa9e</root>'))
self.assert_(xml_compare(t.xml_encode(XML_W),
'<?xml version="1.0" encoding="UTF-8"?>\n'
'<root>entr\xc3\xa9e</root>'))
self.assert_(xml_compare(t.xml_encode(xml_w),
'<?xml version="1.0" encoding="UTF-8"?>\n'
'<root>entr\xc3\xa9e</root>'))
# Try latin-1 output.
self.assert_(xml_compare(t.xml_encode(encoding='iso-8859-1'),
'<?xml version="1.0" encoding="iso-8859-1"?>\n'
'<root>entr\xe9e</root>'))
def test_html(self):
"Simple check of HTML output"
t = tree.parse("""<?xml version='1.0'?>
<disclaimer>
<p>The opinions represented herein represent those of the individual
and should not be interpreted as official policy endorsed by this
organization.</p>
</disclaimer>
""")
self.assertEqual(t.xml_encode(HTML_W), """<disclaimer>
<p>The opinions represented herein represent those of the individual
and should not be interpreted as official policy endorsed by this
organization.</p>
</disclaimer>""")
html_w = lookup(HTML_W)
self.assertEqual(t.xml_encode(html_w), """<disclaimer>
<p>The opinions represented herein represent those of the individual
and should not be interpreted as official policy endorsed by this
organization.</p>
</disclaimer>""")
def parseXMLDocument(self, path):
i=0
self.XML_W = lookup("xml")
try:
self.doc = bindery.parse(path)
except amara.lib.IriError:
schema = "../Musica/Archive.dtd"
self.doc = bindery.parse(path, uri=schema, validate=True)
#xml_print(self.doc)
#self.control.SetText(open(path).read())
self.control.EmptyUndoBuffer()
self.control.Colourise(0, -1)
# line numbers in the margin
self.control.SetMarginType(1, wx.stc.STC_MARGIN_NUMBER)
self.control.SetMarginWidth(1, 25)
#self.control.BeginTextColour((255,0,0))
self.control.SetValue(self.doc.xml_encode(self.XML_W).decode("utf-8"))
#self.control.SetValue(unicode(open(path).read()))
self.Sentences = []
def test_html(self):
"Simple check of HTML output"
t = tree.parse("""<?xml version='1.0'?>
<disclaimer>
<p>The opinions represented herein represent those of the individual
and should not be interpreted as official policy endorsed by this
organization.</p>
</disclaimer>
""")
self.assertEqual(
t.xml_encode(HTML_W), """<disclaimer>
<p>The opinions represented herein represent those of the individual
and should not be interpreted as official policy endorsed by this
organization.</p>
</disclaimer>""")
html_w = lookup(HTML_W)
self.assertEqual(
t.xml_encode(html_w), """<disclaimer>
<p>The opinions represented herein represent those of the individual
and should not be interpreted as official policy endorsed by this
organization.</p>
</disclaimer>""")
def scanXMLDocument(self, path):
i=0
self.XML_W = lookup("xml")
self.doc = bindery.parse(path)
#self.control.BeginTextColour((255,0,0))
self.control.SetValue(self.doc.xml_encode(self.XML_W))
self.Sentences = []
for i in range (0, self.control.GetNumberOfLines()):
Line = self.control.GetLineText(i)
Line.strip()
#To remove spaces in the line
Line = re.sub(r"\s+", "", Line, flags=re.UNICODE)
if (Line[0]=='<') & (Line[1]=='S') & (Line[2]=='i'):
"""
Everytime we encouter '<Si' at the beginning
of a line, we append the Sentence Tab with
the line number
"""
self.Sentences.append(i)
def test_encode(self):
xml_w = lookup('xml')
t = tree.parse("<root>entrée</root>")
# Default is UTF-8.
self.assert_(
xml_compare(
t.xml_encode(), '<?xml version="1.0" encoding="UTF-8"?>\n'
'<root>entr\xc3\xa9e</root>'))
self.assert_(
xml_compare(
t.xml_encode(XML_W), '<?xml version="1.0" encoding="UTF-8"?>\n'
'<root>entr\xc3\xa9e</root>'))
self.assert_(
xml_compare(
t.xml_encode(xml_w), '<?xml version="1.0" encoding="UTF-8"?>\n'
'<root>entr\xc3\xa9e</root>'))
# Try latin-1 output.
self.assert_(
xml_compare(
t.xml_encode(encoding='iso-8859-1'),
'<?xml version="1.0" encoding="iso-8859-1"?>\n'
'<root>entr\xe9e</root>'))
def test_register(self):
"Check that register() works"
self.assertRaises(ValueError, lookup, "new-printer")
register('new-printer', object)
self.assertTrue(lookup('new-printer') is not None)
def test_register(self):
"Check that register() works"
self.assertRaises(ValueError, lookup, "new-printer")
register('new-printer', object)
self.assertTrue(lookup('new-printer') is not None)