def test_os_path_to_uri(self):
for osname in ('posix', 'nt'):
for path, nt_uri, posix_uri in file_paths:
if isinstance(path, unicode):
testname = repr(path)
else:
testname = path
if osname == 'nt':
uri = nt_uri
elif osname == 'posix':
uri = posix_uri
else:
break
if uri is None:
self.assertRaises(
iri.IriError,
lambda path=path, osname=osname: iri.os_path_to_uri(
path, attemptAbsolute=False, osname=osname),
osname + ': ' + testname)
else:
self.assertEqual(
uri,
iri.os_path_to_uri(path,
attemptAbsolute=False,
osname=osname),
osname + ': ' + testname + ': ' + uri)
def test_os_path_to_uri(self):
for osname in ("posix", "nt"):
for path, nt_uri, posix_uri in file_paths:
if isinstance(path, unicode):
testname = repr(path)
else:
testname = path
if osname == "nt":
uri = nt_uri
elif osname == "posix":
uri = posix_uri
else:
break
if uri is None:
self.assertRaises(
iri.IriError,
lambda path=path, osname=osname: iri.os_path_to_uri(path, attemptAbsolute=False, osname=osname),
osname + ": " + testname,
)
else:
self.assertEqual(
uri,
iri.os_path_to_uri(path, attemptAbsolute=False, osname=osname),
osname + ": " + testname + ": " + uri,
)
def test_apply_import1():
_run_xml(
source_xml="<example><spam/></example>",
transform_uri=iri.os_path_to_uri(__file__),
transform_xml="""\
<xsl:transform version="1.0"
xmlns:xsl="http://www.w3.org/1999/XSL/Transform"
>
<xsl:import href="cs_20070210-1.xslt"/>
<xsl:template match="/">
<xsl:apply-templates mode="foo"/>
</xsl:template>
<xsl:template match="example" mode="foo">
<div>
<span>b</span>
<xsl:apply-imports/>
</div>
</xsl:template>
</xsl:transform>""",
expected="""<?xml version="1.0" encoding="UTF-8"?>
<div><span>b</span><span>a</span></div>""",
)
def test_apply_import1():
_run_xml(
source_xml = "<example><spam/></example>",
transform_uri = iri.os_path_to_uri(__file__),
transform_xml = """\
<xsl:transform version="1.0"
xmlns:xsl="http://www.w3.org/1999/XSL/Transform"
>
<xsl:import href="cs_20070210-1.xslt"/>
<xsl:template match="/">
<xsl:apply-templates mode="foo"/>
</xsl:template>
<xsl:template match="example" mode="foo">
<div>
<span>b</span>
<xsl:apply-imports/>
</div>
</xsl:template>
</xsl:transform>""",
expected = """<?xml version="1.0" encoding="UTF-8"?>
<div><span>b</span><span>a</span></div>""",
)
def __new__(cls, arg, uri=None, encoding=None, resolver=None, sourcetype=0):
"""
arg - a string, Unicode object (only if you really know what you're doing),
file-like object (stream), file path or URI. You can also pass an
InputSource object, in which case the return value is just the same
object, possibly with the URI modified
uri - optional override URI. The base URI for the IS will be set to this
value
Returns an input source which can be passed to Amara APIs.
"""
#do the imports within the function to avoid circular crap
#from amara._xmlstring import IsXml as isxml
#These importa are tucked in here because amara.lib.iri is an expensive import
from amara.lib.iri import is_absolute, os_path_to_uri
from amara.lib.irihelpers import DEFAULT_RESOLVER
resolver = resolver or DEFAULT_RESOLVER
if isinstance(arg, InputSource):
return arg
#if arg == (u'', ''): -> UnicodeWarning: Unicode equal comparison failed to convert both arguments to Unicode - interpreting them as being unequal
if arg == '':
#FIXME L10N
raise ValueError("Cannot parse an empty string as XML")
if isinstance(arg, urllib2.Request):
uri = arg.get_full_url() #One of the rightly labeled "lame" helper methods in urllib2 ;)
stream = resolver.resolve(arg)
elif hasattr(arg, 'read'):
#Create dummy Uri to use as base
uri = uri or uuid4().urn
stream = arg
#XXX: Should we at this point refuse to proceed unless it's a basestring?
elif sourcetype == XMLSTRING or isxml(arg):
#See this article about XML detection heuristics
#http://www.xml.com/pub/a/2007/02/28/what-does-xml-smell-like.html
uri = uri or uuid4().urn
stream = StringIO(arg)
elif is_absolute(arg) and not os.path.isfile(arg):
uri = arg
stream = resolver.resolve(uri)
#If the arg is beyond a certain length, don't even try it as a URI
elif len(arg) < MAX_URI_LENGTH_FOR_HEURISTIC:
uri = os_path_to_uri(arg)
stream = resolver.resolve(uri)
else:
#FIXME L10N
raise ValueError("Does not appear to be well-formed XML")
#We might add the ability to load zips, gzips & bzip2s
#http://docs.python.org/lib/module-zlib.html
#http://docs.python.org/lib/module-gzip.html
#http://docs.python.org/lib/module-bz2.html
#http://docs.python.org/lib/zipfile-objects.html
#import inspect; print inspect.stack()
#InputSource.__new__ is in C: expat/input_source.c:inputsource_new
return InputSource.__new__(cls, stream, uri, encoding)
def __init__(self, source, uri=None, validate=False, xinclude=True,
external=False):
if not uri:
# it is relative to the calling module
module = sys._getframe(1).f_globals['__name__']
module = sys.modules[module]
moduledir = os.path.dirname(os.path.abspath(module.__file__))
path = str(uuid.uuid4())
uri = iri.os_path_to_uri(os.path.join(moduledir, path))
testsource.__init__(self, source, uri, validate, xinclude)
def test_cdm1():
print >> sys.stderr, FILE('data/cdm1.html')
toppage = iri.os_path_to_uri(FILE('data/cdm1.html'))
results = read_contentdm(toppage + '?', collection='/jthom', limit=1)
#read_contentdm(toppage, collection='/jthom', limit=None)
header = results.next()
EXPECTED1 = {}
assert header['basequeryurl'].startswith(toppage), (header, )
item = results.next()
EXPECTED2 = {}
assert item == EXPECTED2, (item, EXPECTED2)
#import pprint; pprint.pprint(result, stream=sys.stderr)
return
def test_uri_jail(self):
start_uri = iri.os_path_to_uri(FILE('test_irihelpers.py'))
#raise start_uri
#print >> sys.stderr, "GRIPPO", start_uri
start_base = start_uri.rsplit('/', 1)[0] + '/'
#Only allow access files in the same directory as sampleresource.txt via URL jails
auths = [(lambda u: u.rsplit('/', 1)[0] + '/' == start_base, True)]
resolver = irihelpers.resolver(authorizations=auths)
start_isrc = inputsource(start_uri, resolver=resolver)
new_isrc = start_isrc.resolve('sampleresource.txt', start_base)
self.assertEqual('Spam', new_isrc.stream.read().strip())
self.assertRaises(iri.IriError, resolver.resolve,
'http://google.com', start_base)
def __init__(self,
source,
uri=None,
validate=False,
xinclude=True,
external=False):
if not uri:
# it is relative to the calling module
module = sys._getframe(1).f_globals['__name__']
module = sys.modules[module]
moduledir = os.path.dirname(os.path.abspath(module.__file__))
path = str(uuid.uuid4())
uri = iri.os_path_to_uri(os.path.join(moduledir, path))
testsource.__init__(self, source, uri, validate, xinclude)
def get_processor(self, transform_hash, ext_functions=None, ext_elements=None):
try:
# First make sure we avoid race conditions...
self._main_lock.acquire()
if transform_hash not in self._granular_locks:
self._granular_locks[transform_hash] = thread.allocate_lock()
finally:
self._main_lock.release()
proc = None
try:
self._granular_locks[transform_hash].acquire()
# If we do not have that stylesheet yet in the pool, let's add it
if not self._processors.has_key(transform_hash):
processor = Processor()
self._processors[transform_hash] = processor_info(
thread.allocate_lock(), stat(transform_hash)[ST_MTIME], processor
)
for (ns, local), func in ext_functions.items():
processor.registerExtensionFunction(ns, local, func)
for (ns, local), elem in ext_elements.items():
processor.registerExtensionElement(ns, local, elem)
self._processors[transform_hash].instance.append_transform(iri.os_path_to_uri(transform_hash))
# If the stylesheet has been modified, reload it
elif stat(transform_hash)[ST_MTIME] != self._processors[transform_hash].last_modified:
self._processors[transform_hash].instance.reset()
self._processors[transform_hash].last_modified = stat(transform_hash)[ST_MTIME]
self._processors[transform_hash].instance.append_transform(iri.os_path_to_uri(transform_hash))
# now we can lock the processor...
self._processors[transform_hash]['lock'].acquire()
proc = self._processors[transform_hash].instance
finally:
self._granular_locks[transform_hash].release()
# ... and return it
return proc
def __init__(self,
location=None,
graph=None,
debug=False,
nsBindings = None,
owlEmbeddings = False):
self.owlEmbeddings = owlEmbeddings
self.nsBindings = nsBindings if nsBindings else {}
self.location = location
self.rules = {}
self.debug = debug
if graph:
assert location is None,"Must supply one of graph or location"
self.graph = graph
if debug:
print "RIF in RDF graph was provided"
else:
assert graph is None,"Must supply one of graph or location"
if debug:
print "RIF document URL provided ", location
if self.location.find('http:')+1:
req = urllib2.Request(self.location)
##From: http://www.diveintopython.org/http_web_services/redirects.html
#points an 'opener' to the address to 'sniff' out final Location header
opener = urllib2.build_opener(SmartRedirectHandler())
f = opener.open(req)
self.content = f.read()
else:
try:
self.content = urllib2.urlopen(self.location).read()
except ValueError:
self.content = urllib2.urlopen(iri.os_path_to_uri(self.location)).read()
# self.content = open(self.location).read()
try:
rdfContent = transform(self.content,inputsource(TRANSFORM_URI))
self.graph = Graph().parse(StringIO(rdfContent))
if debug:
print "Extracted rules from RIF XML format"
except ValueError:
try:
self.graph = Graph().parse(StringIO(self.content),format='xml')
except:
self.graph = Graph().parse(StringIO(self.content),format='n3')
if debug:
print "Extracted rules from RIF in RDF document"
self.nsBindings.update(dict(self.graph.namespaces()))
def test_xslt_nested_imports_with_names_that_clash_across_import_precedence_mb_20020527():
_run_xml(
source_xml = "<foo/>",
transform_uri = iri.os_path_to_uri(__file__),
transform_xml = """<?xml version="1.0" encoding="utf-8"?>
<xsl:stylesheet version="1.0"
xmlns:xsl="http://www.w3.org/1999/XSL/Transform">
<xsl:import href="resources/mb_20020527-1.xsl"/>
<xsl:template name="i">
<foo>import.xsl</foo>
</xsl:template>
</xsl:stylesheet>
""",
expected = """<?xml version="1.0" encoding="UTF-8"?>\n<out><foo>import.xsl</foo></out>""",
)
def test_xslt_include_with_variables_dm_20010506():
try:
_run_html(source_xml=commonsource,
transform_uri=iri.os_path_to_uri(__file__),
transform_xml="""<?xml version="1.0"?>
<xsl:stylesheet
xmlns:xsl="http://www.w3.org/1999/XSL/Transform"
version='1.0'>
<xsl:include href="dm_20010506-1.xslt"/>
<xsl:variable name="section.autolabel" select="1" />
<xsl:variable name="html.stylesheet">book.xsl</xsl:variable>
<xsl:variable name="html.stylesheet.type">text/css</xsl:variable>
</xsl:stylesheet>""",
expected=None)
except XsltError, err:
assert err.code == XsltError.DUPLICATE_TOP_LEVEL_VAR, err
def test_xslt_include_with_variables_dm_20010506():
try:
_run_html(
source_xml = commonsource,
transform_uri = iri.os_path_to_uri(__file__),
transform_xml = """<?xml version="1.0"?>
<xsl:stylesheet
xmlns:xsl="http://www.w3.org/1999/XSL/Transform"
version='1.0'>
<xsl:include href="dm_20010506-1.xslt"/>
<xsl:variable name="section.autolabel" select="1" />
<xsl:variable name="html.stylesheet">book.xsl</xsl:variable>
<xsl:variable name="html.stylesheet.type">text/css</xsl:variable>
</xsl:stylesheet>""",
expected = None)
except XsltError, err:
assert err.code == XsltError.DUPLICATE_TOP_LEVEL_VAR, err
def test_basic_uri_resolver(self):
data = [('http://foo.com/root/', 'path', 'http://foo.com/root/path'),
('http://foo.com/root', 'path', 'http://foo.com/path'),
]
#import sys; print >> sys.stderr, filesource('sampleresource.txt').uri
start_isrc = inputsource(FILE('sampleresource.txt'))
#start_isrc = inputsource(filesource('sampleresource.txt').uri)
for base, uri, exp in data:
res = start_isrc.absolutize(uri, base)
self.assertEqual(exp, res, "absolutize: %s %s" % (base, uri))
base = 'foo:foo.com'
uri = 'path'
self.assertRaises(iri.IriError, start_isrc.absolutize, uri, base)
base = os.getcwd()
if base[-1] != os.sep:
base += os.sep
new_isrc = start_isrc.resolve(FILE('sampleresource.txt'), iri.os_path_to_uri(base))
self.assertEqual('Spam', new_isrc.stream.readline().rstrip(), 'resolve')
def test_xslt_nested_imports_with_names_that_clash_across_import_precedence_mb_20020527(
):
_run_xml(
source_xml="<foo/>",
transform_uri=iri.os_path_to_uri(__file__),
transform_xml="""<?xml version="1.0" encoding="utf-8"?>
<xsl:stylesheet version="1.0"
xmlns:xsl="http://www.w3.org/1999/XSL/Transform">
<xsl:import href="resources/mb_20020527-1.xsl"/>
<xsl:template name="i">
<foo>import.xsl</foo>
</xsl:template>
</xsl:stylesheet>
""",
expected=
"""<?xml version="1.0" encoding="UTF-8"?>\n<out><foo>import.xsl</foo></out>""",
)
def test_xslt_import_with_params_dm_20010506():
_run_html(
source_xml=commonsource,
transform_uri=iri.os_path_to_uri(__file__),
transform_xml="""<?xml version="1.0"?>
<xsl:stylesheet
xmlns:xsl="http://www.w3.org/1999/XSL/Transform"
version='1.0'>
<xsl:import href="dm_20010506-1.xslt"/>
<xsl:param name="section.autolabel" select="1" />
<xsl:param name="html.stylesheet">book.xsl</xsl:param>
<xsl:param name="html.stylesheet.type">text/css</xsl:param>
</xsl:stylesheet>""",
expected="""\
<html>
START
<link type='text/css' rel='stylesheet' href='book.xsl'>
END
</html>""",
)
def test_xslt_import_with_params_dm_20010506():
_run_html(
source_xml = commonsource,
transform_uri = iri.os_path_to_uri(__file__),
transform_xml = """<?xml version="1.0"?>
<xsl:stylesheet
xmlns:xsl="http://www.w3.org/1999/XSL/Transform"
version='1.0'>
<xsl:import href="dm_20010506-1.xslt"/>
<xsl:param name="section.autolabel" select="1" />
<xsl:param name="html.stylesheet">book.xsl</xsl:param>
<xsl:param name="html.stylesheet.type">text/css</xsl:param>
</xsl:stylesheet>""",
expected = """\
<html>
START
<link type='text/css' rel='stylesheet' href='book.xsl'>
END
</html>""",
)
########################################################################
# test/xslt/og_20010503.py
# Oliver Graf <*****@*****.**> has indentation probs with
# ft:write-file
import tempfile
from amara.lib import iri
from amara.test.xslt.xslt_support import _run_xml
BASENAME = tempfile.mktemp()
BASENAME_URI = iri.os_path_to_uri(BASENAME)
file_expected = """<?xml version="1.0" encoding="ISO-8859-1"?>
<datatree>
<name>%s</name>
<what>test</what>
</datatree>"""
def test_xslt_ft_write_file_og_20010503():
_run_xml(
source_xml="""\
<?xml version="1.0" encoding="ISO-8859-1"?>
<test>
<data>11</data>
<data>12</data>
<data>13</data>
<data>14</data>
<data>15</data>
</test>
result = urllib2.HTTPRedirectHandler.http_error_302(
self, req, fp, code, msg, headers)
result.status = code
return result
RIF_NS = Namespace('http://www.w3.org/2007/rif#')
XSD_NS = Namespace('http://www.w3.org/2001/XMLSchema#')
ENT = Namespace("http://www.w3.org/ns/entailment/")
mimetypes = {
'application/rdf+xml' : 'xml',
'text/n3' : 'n3',
'text/turtle' : 'turtle',
}
TRANSFORM_URI = iri.absolutize('rif-core-rdf.xsl',iri.os_path_to_uri(__file__))
IMPORT_PARTS=\
"""
SELECT DISTINCT ?location ?profile {
[] a rif:Import;
rif:location ?location;
rif:profile ?profile .
}"""
IMPLIES_PARTS=\
"""
SELECT DISTINCT ?impl ?body ?bodyType ?head ?headType {
?impl a rif:Implies;
rif:if ?body;
rif:then ?head .
########################################################################
# test/xslt/og_20010507.py
# Oliver Graf <*****@*****.**>:
# ft:output cdata-section-elements is not used
import tempfile
from amara.lib import iri
from amara.test.xslt.xslt_support import _run_text
FILESTEM = tempfile.mktemp()
FILESTEM_URI = iri.os_path_to_uri(FILESTEM)
file_expected_1 = """\
<?xml version="1.0" encoding="ISO-8859-1"?>
<datatree>
<content>
<num><![CDATA[1000]]></num>
<str><![CDATA[test]]></str>
</content>
<what>test</what>
</datatree>"""
def test_xslt_cdata_section_elements_og_20010507():
_run_text(source_xml="""\
<?xml version="1.0" encoding="ISO-8859-1"?>
<test>
<data>
<num>1000</num>
<str>test</str>
######################################################################## # test/xslt/jk_20050406.py # See http://bugs.4suite.org/1180509 import tempfile, os import cStringIO import unittest from amara.lib import treecompare from amara.test import test_main from amara.test.xslt import xslt_test, filesource, stringsource from amara.lib.iri import os_path_to_uri fname = tempfile.mktemp() furi = os_path_to_uri(fname) commonsource = "<dummy/>" commontransform = """<?xml version="1.0" encoding="utf-8"?> <xsl:stylesheet version="1.0" xmlns:xsl="http://www.w3.org/1999/XSL/Transform" xmlns:exsl="http://exslt.org/common" extension-element-prefixes="exsl" exclude-result-prefixes="exsl"> <xsl:output method="html" indent="no"/> <xsl:param name="URL" select="'%s'"/> <xsl:template match="/">
######################################################################## # test/xslt/jk_20050406.py # See http://bugs.4suite.org/1180509 import tempfile, os import cStringIO import unittest from amara.lib import treecompare from amara.test import test_main from amara.test.xslt import xslt_test, filesource, stringsource from amara.lib.iri import os_path_to_uri fname = tempfile.mktemp() furi = os_path_to_uri(fname) commonsource = "<dummy/>" commontransform = """<?xml version="1.0" encoding="utf-8"?> <xsl:stylesheet version="1.0" xmlns:xsl="http://www.w3.org/1999/XSL/Transform" xmlns:exsl="http://exslt.org/common" extension-element-prefixes="exsl" exclude-result-prefixes="exsl"> <xsl:output method="html" indent="no"/> <xsl:param name="URL" select="'%s'"/> <xsl:template match="/">
def test_xslt_count_children_via_incrementing_counter_dn_20010504():
_run_text(
source_xml = """\
<numbers>
<num>3</num>
<num>2</num>
<num>9</num>
<num>4</num>
<num>6</num>
<num>5</num>
<num>7</num>
<num>8</num>
<num>1</num>
</numbers>""",
transform_uri = iri.os_path_to_uri(__file__),
transform_xml = """\
<xsl:stylesheet version="1.0"
xmlns:xsl="http://www.w3.org/1999/XSL/Transform"
xmlns:num="num"
xmlns:num2="num2"
>
<num:node>num</num:node>
<num2:node>num2</num2:node>
<xsl:output method="text" />
<xsl:variable name="document" select="document('')" />
<xsl:variable name="gtNum-node" select="$document//num:*"/>
<xsl:variable name="gtNum2-node" select="$document//num2:*"/>
<xsl:template match="/">
<xsl:call-template name="get-max">
<xsl:with-param name="greaterSelector" select="$gtNum-node" />
<xsl:with-param name="nodes" select="/numbers/num" />
</xsl:call-template>
<xsl:text>
</xsl:text>
<xsl:call-template name="get-max">
<xsl:with-param name="greaterSelector" select="$gtNum2-node" />
<xsl:with-param name="nodes" select="/numbers/num" />
</xsl:call-template>
</xsl:template>
<xsl:template name="get-max">
<xsl:param name="greaterSelector" select="/*"/>
<xsl:param name="nodes" />
<xsl:choose>
<xsl:when test="$nodes">
<xsl:variable name="max-of-rest">
<xsl:call-template name="get-max">
<xsl:with-param name="greaterSelector" select="$greaterSelector" />
<xsl:with-param name="nodes" select="$nodes[position()!=1]" />
</xsl:call-template>
</xsl:variable>
<xsl:variable name="isGreater">
<xsl:apply-templates select="$greaterSelector" >
<xsl:with-param name="n1" select="$nodes[1]"/>
<xsl:with-param name="n2" select="$max-of-rest"/>
</xsl:apply-templates>
</xsl:variable>
<xsl:choose>
<xsl:when test="$isGreater = 'true'">
<xsl:value-of select="$nodes[1]" />
</xsl:when>
<xsl:otherwise>
<xsl:value-of select="$max-of-rest" />
</xsl:otherwise>
</xsl:choose>
</xsl:when>
<xsl:otherwise>
<xsl:value-of select="-999999999" />
<!-- minus infinity -->
</xsl:otherwise>
</xsl:choose>
</xsl:template>
<xsl:template name="isGreaterNum" match="node()[namespace-uri()='num']">
<xsl:param name="n1"/>
<xsl:param name="n2"/>
<xsl:value-of select="$n1 > $n2"/>
</xsl:template>
<xsl:template name="isGreaterNum2" match="node()[namespace-uri()='num2']">
<xsl:param name="n1"/>
<xsl:param name="n2"/>
<xsl:value-of select="1 div $n1 > 1 div $n2"/>
</xsl:template>
</xsl:stylesheet>""",
expected = """\
9
1""")
########################################################################
# test/xslt/og_20010503.py
# Oliver Graf <*****@*****.**> has indentation probs with
# ft:write-file
import tempfile
from amara.lib import iri
from amara.test.xslt.xslt_support import _run_xml
BASENAME = tempfile.mktemp()
BASENAME_URI = iri.os_path_to_uri(BASENAME)
file_expected = """<?xml version="1.0" encoding="ISO-8859-1"?>
<datatree>
<name>%s</name>
<what>test</what>
</datatree>"""
def test_xslt_ft_write_file_og_20010503():
_run_xml(
source_xml = """\
<?xml version="1.0" encoding="ISO-8859-1"?>
<test>
<data>11</data>
<data>12</data>
<data>13</data>
<data>14</data>
<data>15</data>
</test>
# -*- encoding: utf-8 -*-
########################################################################
# test/xslt/borrowed/uo_20010503.py
# From original 4Suite cvs:
#This source doc used to bomb cDomlette just on parse, as Uche found out
import os
from amara.lib import iri
from amara.test.xslt.xslt_support import _run_xml
BASE_URI = iri.os_path_to_uri(os.path.abspath(__file__), attemptAbsolute=True)
common_transform = """
<xsl:stylesheet
xmlns:xsl="http://www.w3.org/1999/XSL/Transform"
version="1.0"
>
<xsl:template match="@*|node()">
<xsl:copy>
<xsl:apply-templates select="@*|node()"/>
</xsl:copy>
</xsl:template>
</xsl:stylesheet>
"""
def test_xslt_uo_20010503_1():
_run_xml(
def test_wwwlog2json_maxrecords_large():
# Size is greater than the number of records
results = _make_log2json_request("?maxrecords=1000")
items = results["items"]
assert len(items) == 200, len(items)
def test_wwwlog2json_nobots():
results = _make_log2json_request("?nobots=1")
items = results["items"]
assert len(items) == 183, len(items)
# xslt.py
XML_DATA = open(os.path.join(RESOURCE_DIR, "xslt_spec_example.xml")).read()
XSLT_URL = iri.os_path_to_uri(
os.path.join(RESOURCE_DIR, "xslt_spec_example.xslt"))
def test_xslt():
url = server() + "akara.xslt?" + urllib.urlencode({"@xslt": XSLT_URL})
req = urllib2.Request(url)
req.add_header("Content-Type", "text/xml")
response = urllib2.urlopen(req, XML_DATA)
doc = bindery.parse(response)
assert str(doc.html.head.title) == "Document Title", repr(
str(doc.html.head.title))
if __name__ == "__main__":
raise SystemExit("Use nosetests")
# -*- encoding: utf-8 -*-
########################################################################
# test/xslt/borrowed/uo_20010503.py
# From original 4Suite cvs:
#This source doc used to bomb cDomlette just on parse, as Uche found out
import os
from amara.lib import iri
from amara.test.xslt.xslt_support import _run_xml
BASE_URI = iri.os_path_to_uri(os.path.abspath(__file__), attemptAbsolute=True)
common_transform = """
<xsl:stylesheet
xmlns:xsl="http://www.w3.org/1999/XSL/Transform"
version="1.0"
>
<xsl:template match="@*|node()">
<xsl:copy>
<xsl:apply-templates select="@*|node()"/>
</xsl:copy>
</xsl:template>
</xsl:stylesheet>
"""
def test_xslt_uo_20010503_1():
def __new__(cls,
arg,
uri=None,
encoding=None,
resolver=None,
sourcetype=0):
"""
arg - a string, Unicode object (only if you really know what you're doing),
file-like object (stream), file path or URI. You can also pass an
InputSource object, in which case the return value is just the same
object, possibly with the URI modified
uri - optional override URI. The base URI for the IS will be set to this
value
Returns an input source which can be passed to Amara APIs.
"""
#do the imports within the function to avoid circular crap
#from amara._xmlstring import IsXml as isxml
#These importa are tucked in here because amara.lib.iri is an expensive import
from amara.lib.iri import is_absolute, os_path_to_uri
from amara.lib.irihelpers import DEFAULT_RESOLVER
resolver = resolver or DEFAULT_RESOLVER
if isinstance(arg, InputSource):
return arg
#if arg == (u'', ''): -> UnicodeWarning: Unicode equal comparison failed to convert both arguments to Unicode - interpreting them as being unequal
if arg == '':
#FIXME L10N
raise ValueError("Cannot parse an empty string as XML")
if isinstance(arg, urllib2.Request):
uri = arg.get_full_url(
) #One of the rightly labeled "lame" helper methods in urllib2 ;)
stream = resolver.resolve(arg)
elif hasattr(arg, 'read'):
#Create dummy Uri to use as base
uri = uri or uuid4().urn
stream = arg
#XXX: Should we at this point refuse to proceed unless it's a basestring?
elif sourcetype == XMLSTRING or isxml(arg):
#See this article about XML detection heuristics
#http://www.xml.com/pub/a/2007/02/28/what-does-xml-smell-like.html
uri = uri or uuid4().urn
stream = StringIO(arg)
elif is_absolute(arg) and not os.path.isfile(arg):
uri = arg
stream = resolver.resolve(uri)
#If the arg is beyond a certain length, don't even try it as a URI
elif len(arg) < MAX_URI_LENGTH_FOR_HEURISTIC:
uri = os_path_to_uri(arg)
stream = resolver.resolve(uri)
else:
#FIXME L10N
raise ValueError("Does not appear to be well-formed XML")
#We might add the ability to load zips, gzips & bzip2s
#http://docs.python.org/lib/module-zlib.html
#http://docs.python.org/lib/module-gzip.html
#http://docs.python.org/lib/module-bz2.html
#http://docs.python.org/lib/zipfile-objects.html
#import inspect; print inspect.stack()
#InputSource.__new__ is in C: expat/input_source.c:inputsource_new
return InputSource.__new__(cls, stream, uri, encoding)
########################################################################
# test/xslt/tg_20010628.py
# Thomas Guettler <*****@*****.**> wants to use XInclude in
# his stylesheets
import os
from amara.test.xslt.xslt_support import _run_html
from amara.lib import iri
INCLUDE_URI = iri.os_path_to_uri(os.path.join(os.path.dirname(__file__),
"resources", "tg_20010628-include.xml"))
def test_xslt_xinclude_tg_20010628():
_run_html(
source_xml = """\
<?xml version="1.0" encoding="iso-8859-1"?>
<html xmlns:xinclude="http://www.w3.org/2001/XInclude">
<head>
<title>MyTitle</title>
</head>
<body>
<xinclude:include href="%(uri)s"/>
</body>
</html>""" % {'uri' : INCLUDE_URI},
transform_xml = """\
<?xml version="1.0" encoding="iso-8859-1"?>
<xsl:stylesheet version="1.0"
xmlns:xsl="http://www.w3.org/1999/XSL/Transform"
xmlns:xinclude="http://www.w3.org/2001/XInclude">
items = results["items"]
assert len(items) == 10, len(items)
assert items[0]["origin"] == "host-24-225-218-245.patmedia.net"
assert items[-1]["timestamp"] == "2006-10-01T06:33:55-07:00", items[-1]["timestamp"]
def test_wwwlog2json_maxrecords_large():
# Size is greater than the number of records
results = _make_log2json_request("?maxrecords=1000")
items = results["items"]
assert len(items) == 200, len(items)
def test_wwwlog2json_nobots():
results = _make_log2json_request("?nobots=1")
items = results["items"]
assert len(items) == 183, len(items)
# xslt.py
XML_DATA = open(os.path.join(RESOURCE_DIR, "xslt_spec_example.xml")).read()
XSLT_URL = iri.os_path_to_uri(os.path.join(RESOURCE_DIR, "xslt_spec_example.xslt"))
def test_xslt():
url = server() + "akara.xslt?" + urllib.urlencode({"@xslt": XSLT_URL})
req = urllib2.Request(url)
req.add_header("Content-Type", "text/xml")
response = urllib2.urlopen(req, XML_DATA)
doc = bindery.parse(response)
assert str(doc.html.head.title) == "Document Title", repr(str(doc.html.head.title))
if __name__ == "__main__":
raise SystemExit("Use nosetests")
########################################################################
# test/xslt/og_20010507.py
# Oliver Graf <*****@*****.**>:
# ft:output cdata-section-elements is not used
import tempfile
from amara.lib import iri
from amara.test.xslt.xslt_support import _run_text
FILESTEM = tempfile.mktemp()
FILESTEM_URI = iri.os_path_to_uri(FILESTEM)
file_expected_1 = """\
<?xml version="1.0" encoding="ISO-8859-1"?>
<datatree>
<content>
<num><![CDATA[1000]]></num>
<str><![CDATA[test]]></str>
</content>
<what>test</what>
</datatree>"""
def test_xslt_cdata_section_elements_og_20010507():
_run_text(
source_xml = """\
<?xml version="1.0" encoding="ISO-8859-1"?>
<test>
<data>
<num>1000</num>
<str>test</str>