def test20_as_xml(self):
rl = ResourceList()
rl.add( Resource('a',timestamp=1) )
rl.add( Resource('b',timestamp=2) )
xml = rl.as_xml()
self.assertTrue( re.search(r'<rs:md .*capability="resourcelist"', xml), 'XML has capability' )
self.assertTrue( re.search(r'<url><loc>a</loc><lastmod>1970-01-01T00:00:01Z</lastmod></url>', xml), 'XML has resource a' )
def test_build_ex_01(self):
"""Simple Resource List document """
rl = ResourceList()
rl.md_at = '2013-01-03T09:00:00Z'
rl.add( Resource('http://example.com/res1') )
rl.add( Resource('http://example.com/res2') )
ex_xml = self._open_ex('resourcesync_ex_1').read()
self._assert_xml_equal( rl.as_xml(), ex_xml )
def test20_as_xml(self):
rl = ResourceList()
rl.add( Resource('a',timestamp=1) )
rl.add( Resource('b',timestamp=2) )
xml = rl.as_xml()
print xml
self.assertTrue( re.search(r'<rs:md .*capability="resourcelist"', xml), 'XML has capability' )
self.assertTrue( re.search(r'<url><loc>a</loc><lastmod>1970-01-01T00:00:01Z</lastmod></url>', xml), 'XML has resource a' )
def test20_as_xml(self):
rl = ResourceList()
rl.add( Resource('a',timestamp=1) )
rl.add( Resource('b',timestamp=2) )
xml = rl.as_xml()
print xml
self.assertTrue( re.search(r'<rs:md .*capability="resourcelist"', xml), 'XML has capability' )
self.assertTrue( re.search(r'<rs:md .*modified="\d\d\d\d\-\d\d\-\d\dT\d\d:\d\d:\d\dZ"', xml), 'XML has modified to seconds precision (and not more)' )
self.assertTrue( re.search(r'<url><loc>a</loc><lastmod>1970-01-01T00:00:01Z</lastmod></url>', xml), 'XML has resource a' )
def test_build_ex_02(self):
"""Slightly more complex Resource List document """
rl = ResourceList()
rl.md_at = '2013-01-03T09:00:00Z'
rl.add( Resource(uri='http://example.com/res1',
lastmod='2013-01-02T13:00:00Z',
md5='1584abdf8ebdc9802ac0c6a7402c03b6') )
r2 = Resource(uri='http://example.com/res2',
lastmod='2013-01-02T14:00:00Z',
md5='1e0d5cb8ef6ba40c99b14c0237be735e')
r2.link_set(rel="duplicate",href="http://mirror.example.com/res2")
rl.add( r2 )
ex_xml = self._open_ex('resourcesync_ex_2').read()
self._assert_xml_equal( rl.as_xml(), ex_xml )
def test_build_ex_15(self):
"""Resource List Index with metadata"""
rl = ResourceList(resources_class=ResourceListOrdered) #order in example is non-canonical
rl.sitemapindex=True
rl.up='http://example.com/dataset1/capabilitylist.xml'
rl.md_at="2013-01-03T09:00:00Z"
rl.md_completed="2013-01-03T09:10:00Z"
rl.add( Resource( uri='http://example.com/resourcelist1.xml',
md_at='2013-01-03T09:00:00Z' ))
rl.add( Resource( uri='http://example.com/resourcelist2.xml',
md_at='2013-01-03T09:03:00Z' ))
rl.add( Resource( uri='http://example.com/resourcelist3.xml',
md_at='2013-01-03T09:07:00Z' ))
ex_xml = self._open_ex('resourcesync_ex_15').read()
self._assert_xml_equal( rl.as_xml(), ex_xml )
def test_build_ex_08(self):
"""Simple Resource List Index document
This is not something that would usually be created directly
but instead would be created as part of the process of
writing a large Resource List in multiple files. However,
it is possible to create manually.
"""
rli = ResourceList()
rli.sitemapindex=True
rli.md_at = '2013-01-03T09:00:00Z'
rli.add( Resource(uri='http://example.com/resourcelist-part1.xml') )
rli.add( Resource(uri='http://example.com/resourcelist-part2.xml') )
ex_xml = self._open_ex('resourcesync_ex_8').read()
self._assert_xml_equal( rli.as_xml(), ex_xml )
def test_build_ex_16(self):
rl = ResourceList()
rl.up = 'http://example.com/dataset1/capabilitylist.xml'
rl.index = 'http://example.com/dataset1/resourcelist-index.xml'
rl.md_at="2013-01-03T09:00:00Z"
rl.add( Resource( uri='http://example.com/res3',
lastmod='2013-01-02T13:00:00Z',
md5='1584abdf8ebdc9802ac0c6a7402c8753',
length=4385,
mime_type="application/pdf" ))
rl.add( Resource( uri='http://example.com/res4',
lastmod='2013-01-02T14:00:00Z',
md5='4556abdf8ebdc9802ac0c6a7402c9881',
length=883,
mime_type="image/png" ))
ex_xml = self._open_ex('resourcesync_ex_16').read()
self._assert_xml_equal( rl.as_xml(), ex_xml )
def test_build_ex_14(self):
"""Resource List with 2 entries and some metadata"""
rl = ResourceList()
rl.up='http://example.com/dataset1/capabilitylist.xml'
rl.md_at="2013-01-03T09:00:00Z"
rl.md_completed="2013-01-03T09:01:00Z"
rl.add( Resource( uri='http://example.com/res1',
lastmod='2013-01-02T13:00:00Z',
md5='1584abdf8ebdc9802ac0c6a7402c03b6',
length=8876,
mime_type="text/html" ))
rl.add( Resource( uri='http://example.com/res2',
lastmod='2013-01-02T14:00:00Z',
md5='1e0d5cb8ef6ba40c99b14c0237be735e',
sha256='854f61290e2e197a11bc91063afce22e43f8ccc655237050ace766adc68dc784',
length=14599,
mime_type="application/pdf" ))
ex_xml = self._open_ex('resourcesync_ex_14').read()
self._assert_xml_equal( rl.as_xml(), ex_xml )
continue
_, raw_ts = filename.split("-")
ts = (
raw_ts[:4] + "-" +
raw_ts[4:6] + "-" +
raw_ts[6:8] + "T" +
raw_ts[8:10] + ":" +
raw_ts[10:12] + ":" +
raw_ts[12:14] + "Z"
)
timestamps.append(ts)
rl.add(Resource(args.resource_url + filename, lastmod=ts))
# Print to file at args.resource_dir + "/resource-list.xml"
resource_list_file = open(args.resource_dir + "/resource-list.xml", "w")
resource_list_file.write(rl.as_xml())
resource_list_file.close()
print "Wrote resource list to: " + args.resource_dir + "/resource-list.xml"
timestamps.sort()
caps = CapabilityList()
caps.add_capability(rl, args.resource_url + "resource-list.xml")
if len(timestamps) > 0:
caps.md['from'] = timestamps[0]
# Print to file at args.resource_dir + "/capability-list.xml"
capability_list_file = open(args.resource_dir + "/capability-list.xml", "w")
capability_list_file.write(caps.as_xml())
capability_list_file.close()
from resync.resource_list import ResourceList
from resync.resource import Resource
from resync.sitemap import Sitemap
rl = ResourceList()
rl.add(Resource('http://example.com/res1', lastmod='2013-01-01'))
rl.add(Resource('http://example.com/res2', lastmod='2013-01-02'))
print rl.as_xml(pretty_xml=True)
raise IOError(args.resource_dir + " is not a directory")
rl = ResourceList()
timestamps = []
for filename in listdir(args.resource_dir):
if filename[:len("rdfpatch-")] != "rdfpatch-":
continue
_, raw_ts = filename.split("-")
ts = (raw_ts[:4] + "-" + raw_ts[4:6] + "-" + raw_ts[6:8] + "T" +
raw_ts[8:10] + ":" + raw_ts[10:12] + ":" + raw_ts[12:14] + "Z")
timestamps.append(ts)
rl.add(Resource(args.resource_url + filename, lastmod=ts))
# Print to file at args.resource_dir + "/resource-list.xml"
resource_list_file = open(args.resource_dir + "/resource-list.xml", "w")
resource_list_file.write(rl.as_xml())
resource_list_file.close()
print "Wrote resource list to: " + args.resource_dir + "/resource-list.xml"
timestamps.sort()
caps = CapabilityList()
caps.add_capability(rl, args.resource_url + "resource-list.xml")
if len(timestamps) > 0:
caps.md['from'] = timestamps[0]
# Print to file at args.resource_dir + "/capability-list.xml"
capability_list_file = open(args.resource_dir + "/capability-list.xml", "w")
capability_list_file.write(caps.as_xml())
capability_list_file.close()
from resync.resource_list import ResourceList
from resync.resource import Resource
from resync.sitemap import Sitemap
rl = ResourceList()
rl.add( Resource('http://example.com/res1', lastmod='2013-01-01') )
rl.add( Resource('http://example.com/res2', lastmod='2013-01-02') )
print rl.as_xml(pretty_xml=True)
