def test04_dump_multi_file_max_size(self):
rl = ResourceList()
for letter in map(chr, range(ord('a'), ord('l') + 1)):
uri = 'http://ex.org/%s' % (letter)
fname = 'tests/testdata/a_to_z/%s' % (letter)
rl.add(Resource(uri, path=fname))
self.assertEqual(len(rl), 12)
d2 = Dump(rl)
tmpbase = os.path.join(self.tmpdir, 'test0f_')
d2.max_size = 2000
n = d2.write(tmpbase)
self.assertEqual(n, 2, 'expect to write 2 dump files')
self.assertTrue(os.path.isfile(tmpbase + '00000.zip'))
self.assertTrue(os.path.isfile(tmpbase + '00001.zip'))
# Look at the first file in detail
zipf = tmpbase + '00000.zip'
zo = zipfile.ZipFile(zipf, 'r')
self.assertEqual(zo.namelist(),
['manifest.xml', 'a', 'b', 'c', 'd', 'e', 'f'])
#self.assertEqual( zo.getinfo('manifest.xml').file_size, 470 )
self.assertEqual(zo.getinfo('a').file_size, 9)
self.assertEqual(zo.getinfo('b').file_size, 1116)
self.assertEqual(zo.getinfo('c').file_size, 32)
self.assertEqual(zo.getinfo('d').file_size, 13)
self.assertEqual(zo.getinfo('e').file_size, 20)
self.assertEqual(zo.getinfo('f').file_size, 1625)
zo.close()
os.unlink(zipf)
# Check second and third files have expected contents
zipf = tmpbase + '00001.zip'
zo = zipfile.ZipFile(zipf, 'r')
self.assertEqual(zo.namelist(),
['manifest.xml', 'g', 'h', 'i', 'j', 'k', 'l'])
zo.close()
os.unlink(zipf)
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 test00_dump_creation(self):
i = ResourceList()
i.add(Resource("http://ex.org/a", length=1, path="resync/test/testdata/a"))
i.add(Resource("http://ex.org/b", length=2, path="resync/test/testdata/b"))
d = Dump()
d.check_files(resource_list=i)
self.assertEqual(d.total_size, 28)
def test11_bad_size(self):
rl = ResourceList()
rl.add(
Resource('http://ex.org/a', length=9999, path='tests/testdata/a'))
d = Dump(rl)
self.assertTrue(d.check_files(check_length=False))
self.assertRaises(DumpError, d.check_files)
def test5_add_changed_resources(self):
added = ResourceList()
added.add( Resource('a',timestamp=1) )
added.add( Resource('d',timestamp=4))
self.assertEqual(len(added), 2, "2 things in added resource_list")
changes = ChangeList()
changes.add_changed_resources( added, change='created' )
self.assertEqual(len(changes), 2, "2 things added")
i = iter(changes)
first = i.next()
self.assertEqual(first.uri, 'a', "changes[0].uri=a")
self.assertEqual(first.timestamp, 1, "changes[0].timestamp=1")
self.assertEqual(first.change, 'created') #, "changes[0].change=created")
second = i.next()
self.assertEqual(second.timestamp, 4, "changes[1].timestamp=4")
self.assertEqual(second.change, 'created', "changes[1].change=created")
# Now add some with updated (one same, one diff)
updated = ResourceList()
updated.add( Resource('a',timestamp=5) )
updated.add( Resource('b',timestamp=6))
self.assertEqual(len(updated), 2, "2 things in updated resource_list")
changes.add_changed_resources( updated, change='updated' )
self.assertEqual(len(changes), 4, "4 = 2 old + 2 things updated")
# Make new resource_list from the changes which should not have dupes
dst = ResourceList()
dst.add( changes, replace=True )
self.assertEqual(len(dst), 3, "3 unique resources")
self.assertEqual(dst.resources['a'].timestamp, 5 ) # 5 was later in last the 1
self.assertEqual(dst.resources['a'].change, 'updated')
self.assertEqual(dst.resources['b'].timestamp, 6)
self.assertEqual(dst.resources['b'].change, 'updated')
self.assertEqual(dst.resources['d'].timestamp, 4)
self.assertEqual(dst.resources['d'].change, 'created')
def test04_dump_multi_file_max_size(self):
rl=ResourceList()
for letter in map(chr,xrange(ord('a'),ord('l')+1)):
uri='http://ex.org/%s' % (letter)
fname='resync/test/testdata/a_to_z/%s' % (letter)
rl.add( Resource(uri, path=fname) )
self.assertEqual( len(rl), 12 )
d2=Dump(rl)
tmpbase=os.path.join(self.tmpdir,'test0f_')
d2.max_size=2000
n=d2.write(tmpbase)
self.assertEqual( n, 2, 'expect to write 2 dump files' )
self.assertTrue( os.path.isfile(tmpbase+'00000.zip') )
self.assertTrue( os.path.isfile(tmpbase+'00001.zip') )
# Look at the first file in detail
zipf=tmpbase+'00000.zip'
zo=zipfile.ZipFile(zipf,'r')
self.assertEqual( zo.namelist(), ['manifest.xml','a','b','c','d','e','f'] )
#self.assertEqual( zo.getinfo('manifest.xml').file_size, 470 )
self.assertEqual( zo.getinfo('a').file_size, 9 )
self.assertEqual( zo.getinfo('b').file_size, 1116 )
self.assertEqual( zo.getinfo('c').file_size, 32 )
self.assertEqual( zo.getinfo('d').file_size, 13 )
self.assertEqual( zo.getinfo('e').file_size, 20 )
self.assertEqual( zo.getinfo('f').file_size, 1625 )
zo.close()
os.unlink(zipf)
# Check second and third files have expected contents
zipf=tmpbase+'00001.zip'
zo=zipfile.ZipFile(zipf,'r')
self.assertEqual( zo.namelist(), ['manifest.xml','g','h','i','j','k','l'] )
zo.close()
os.unlink(zipf)
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 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 test_09_print_from_iter(self):
r1 = Resource(uri='a',lastmod='2001-01-01',length=1234)
r2 = Resource(uri='b',lastmod='2002-02-02',length=56789)
m = ResourceList()
m.add(r1)
m.add(r2)
i = iter(m)
self.assertEqual( Sitemap().resources_as_xml(i), "<?xml version='1.0' encoding='UTF-8'?>\n<urlset xmlns=\"http://www.sitemaps.org/schemas/sitemap/0.9\" xmlns:rs=\"http://www.openarchives.org/rs/terms/\"><url><loc>a</loc><lastmod>2001-01-01T00:00:00Z</lastmod><rs:md length=\"1234\" /></url><url><loc>b</loc><lastmod>2002-02-02T00:00:00Z</lastmod><rs:md length=\"56789\" /></url></urlset>")
def test_08_print_non_ascii_uri(self):
"""Verify that valid Unicode uri values give good XML out."""
m = ResourceList(md={'capability': 'resourcelist', 'modified': None})
m.add(Resource(uri=u'a_\u00c3_b'))
m.add(Resource(uri=u'c_\u1234_d'))
xml = Sitemap().resources_as_xml(m)
self.assertTrue(re.search(u'<loc>a_.*_b</loc>', xml))
self.assertTrue(re.search(u'<loc>a_\u00c3_b</loc>', xml))
self.assertTrue(re.search(u'<loc>c_\u1234_d</loc>', xml))
def test10_no_path(self):
rl = ResourceList()
rl.add(
Resource('http://ex.org/a',
length=7,
path='resync/test/testdata/a'))
rl.add(Resource('http://ex.org/b', length=21))
d = Dump(rl)
self.assertRaises(DumpError, d.check_files)
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_08_print_non_ascii_uri(self):
"""Verify that valid Unicode uri values give good XML out."""
m = ResourceList(md={'capability': 'resourcelist', 'modified': None})
m.add(Resource(uri=u'a_\u00c3_b'))
m.add(Resource(uri=u'c_\u1234_d'))
xml = Sitemap().resources_as_xml(m)
self.assertTrue(re.search(u'<loc>a_.*_b</loc>', xml))
self.assertTrue(re.search(u'<loc>a_\u00c3_b</loc>', xml))
self.assertTrue(re.search(u'<loc>c_\u1234_d</loc>', xml))
def test07_has_md5(self):
r1 = Resource(uri='a')
r2 = Resource(uri='b')
i = ResourceList()
self.assertFalse( i.has_md5() )
i.add(r1)
i.add(r2)
self.assertFalse( i.has_md5() )
r1.md5="aabbcc"
self.assertTrue( i.has_md5() )
def test07_has_md5(self):
r1 = Resource(uri='a')
r2 = Resource(uri='b')
i = ResourceList()
self.assertFalse( i.has_md5() )
i.add(r1)
i.add(r2)
self.assertFalse( i.has_md5() )
r1.md5="aabbcc"
self.assertTrue( i.has_md5() )
def test_08_print(self):
r1 = Resource(uri='a',lastmod='2001-01-01',length=1234)
r2 = Resource(uri='b',lastmod='2002-02-02',length=56789)
r3 = Resource(uri='c',lastmod='2003-03-03',length=0)
m = ResourceList(md={'capability':'resourcelist','modified':None})
m.add(r1)
m.add(r2)
m.add(r3)
#print m
self.assertEqual( Sitemap().resources_as_xml(m), "<?xml version='1.0' encoding='UTF-8'?>\n<urlset xmlns=\"http://www.sitemaps.org/schemas/sitemap/0.9\" xmlns:rs=\"http://www.openarchives.org/rs/terms/\"><rs:md capability=\"resourcelist\" /><url><loc>a</loc><lastmod>2001-01-01T00:00:00Z</lastmod><rs:md length=\"1234\" /></url><url><loc>b</loc><lastmod>2002-02-02T00:00:00Z</lastmod><rs:md length=\"56789\" /></url><url><loc>c</loc><lastmod>2003-03-03T00:00:00Z</lastmod><rs:md length=\"0\" /></url></urlset>")
def test_09_print_from_iter(self):
r1 = Resource(uri='a', lastmod='2001-01-01', length=1234)
r2 = Resource(uri='b', lastmod='2002-02-02', length=56789)
m = ResourceList()
m.add(r1)
m.add(r2)
i = iter(m)
self.assertEqual(
Sitemap().resources_as_xml(i),
"<?xml version='1.0' encoding='UTF-8'?>\n<urlset xmlns=\"http://www.sitemaps.org/schemas/sitemap/0.9\" xmlns:rs=\"http://www.openarchives.org/rs/terms/\"><url><loc>a</loc><lastmod>2001-01-01T00:00:00Z</lastmod><rs:md length=\"1234\" /></url><url><loc>b</loc><lastmod>2002-02-02T00:00:00Z</lastmod><rs:md length=\"56789\" /></url></urlset>"
)
def test_11_write_multifile(self):
tempdir = tempfile.mkdtemp(prefix='test_resource_list_multifile')
rl = ResourceList()
rl.mapper = Mapper(['http://localhost/=%s/' % (tempdir)])
rl.add(Resource(uri='http://localhost/a'))
rl.add(Resource(uri='http://localhost/b'))
rl.add(Resource(uri='http://localhost/c'))
rl.add(Resource(uri='http://localhost/d'))
rl.max_sitemap_entries = 2
# first try writing without mutlifile allowed
rl.allow_multifile = False
self.assertRaises(ListBaseIndexError,
rl.write,
basename=os.path.join(tempdir, 'sitemap.xml'))
# second actually do it
rl.allow_multifile = True
rl.write(basename=os.path.join(tempdir, 'sitemap.xml'))
# check the two component sitemaps
rl1 = ResourceList()
rl1.read(os.path.join(tempdir, 'sitemap00000.xml'))
self.assertEquals(len(rl1), 2)
self.assertEquals(rl1.capability, 'resourcelist')
self.assertFalse(rl1.sitemapindex)
i = iter(rl1)
self.assertEquals(next(i).uri, 'http://localhost/a')
self.assertEquals(next(i).uri, 'http://localhost/b')
rl2 = ResourceList()
rl2.read(os.path.join(tempdir, 'sitemap00001.xml'))
self.assertEquals(len(rl2), 2)
i = iter(rl2)
self.assertEquals(next(i).uri, 'http://localhost/c')
self.assertEquals(next(i).uri, 'http://localhost/d')
# check the sitemapindex (read just as index)
rli = ResourceList()
rli.read(os.path.join(tempdir, 'sitemap.xml'), index_only=True)
self.assertEquals(len(rli), 2)
i = iter(rli)
self.assertEquals(rli.capability, 'resourcelist')
self.assertTrue(rli.sitemapindex)
self.assertEquals(next(i).uri, 'http://localhost/sitemap00000.xml')
self.assertEquals(next(i).uri, 'http://localhost/sitemap00001.xml')
# check the sitemapindex and components
rli = ResourceList(mapper=rl.mapper)
rli.read(os.path.join(tempdir, 'sitemap.xml'))
self.assertEquals(len(rli), 4)
self.assertEquals(rli.capability, 'resourcelist')
self.assertFalse(rli.sitemapindex)
i = iter(rli)
self.assertEquals(next(i).uri, 'http://localhost/a')
self.assertEquals(next(i).uri, 'http://localhost/b')
self.assertEquals(next(i).uri, 'http://localhost/c')
self.assertEquals(next(i).uri, 'http://localhost/d')
# cleanup tempdir
shutil.rmtree(tempdir)
def test07_hashes(self):
r1 = Resource(uri='a')
r2 = Resource(uri='b')
i = ResourceList()
self.assertEqual(i.hashes(), set())
i.add(r1)
i.add(r2)
self.assertEqual(i.hashes(), set())
r1.md5 = "aabbcc"
self.assertEqual(i.hashes(), set(['md5']))
r2.sha1 = "ddeeff"
self.assertEqual(i.hashes(), set(['md5', 'sha-1']))
def test08_iter(self):
i = ResourceList()
i.add( Resource('a',timestamp=1) )
i.add( Resource('b',timestamp=2) )
i.add( Resource('c',timestamp=3) )
i.add( Resource('d',timestamp=4) )
resources=[]
for r in i:
resources.append(r)
self.assertEqual(len(resources), 4)
self.assertEqual( resources[0].uri, 'a')
self.assertEqual( resources[3].uri, 'd')
def test08_iter(self):
i = ResourceList()
i.add(Resource('a', timestamp=1))
i.add(Resource('b', timestamp=2))
i.add(Resource('c', timestamp=3))
i.add(Resource('d', timestamp=4))
resources = []
for r in i:
resources.append(r)
self.assertEqual(len(resources), 4)
self.assertEqual(resources[0].uri, 'a')
self.assertEqual(resources[3].uri, 'd')
def test06_add_iterable(self):
r1 = Resource(uri='a', length=1)
r2 = Resource(uri='b', length=2)
i = ResourceList()
i.add([r1, r2])
self.assertRaises(ResourceListDupeError, i.add, r1)
self.assertRaises(ResourceListDupeError, i.add, r2)
# allow dupes
r1d = Resource(uri='a', length=10)
i.add([r1d], replace=True)
self.assertEqual(len(i), 2)
self.assertEqual(i.resources['a'].length, 10)
def test06_add_iterable(self):
r1 = Resource(uri='a',length=1)
r2 = Resource(uri='b',length=2)
i = ResourceList()
i.add( [r1,r2] )
self.assertRaises( ResourceListDupeError, i.add, r1)
self.assertRaises( ResourceListDupeError, i.add, r2)
# allow dupes
r1d = Resource(uri='a',length=10)
i.add( [r1d] ,replace=True)
self.assertEqual( len(i), 2 )
self.assertEqual( i.resources['a'].length, 10 )
def test07_hashes(self):
r1 = Resource(uri='a')
r2 = Resource(uri='b')
i = ResourceList()
self.assertEqual(i.hashes(), set())
i.add(r1)
i.add(r2)
self.assertEqual(i.hashes(), set())
r1.md5 = "aabbcc"
self.assertEqual(i.hashes(), set(['md5']))
r2.sha1 = "ddeeff"
self.assertEqual(i.hashes(), set(['md5', 'sha-1']))
def test_11_write_multifile(self):
tempdir = tempfile.mkdtemp(prefix='test_resource_list_multifile_dir')
rl = ResourceList()
rl.mapper = Mapper(['http://localhost/=%s/' % (tempdir)])
rl.add(Resource(uri='http://localhost/a'))
rl.add(Resource(uri='http://localhost/b'))
rl.add(Resource(uri='http://localhost/c'))
rl.add(Resource(uri='http://localhost/d'))
rl.max_sitemap_entries = 2
# first try writing without mutlifile allowed
rl.allow_multifile = False
self.assertRaises(ListBaseIndexError, rl.write,
basename=os.path.join(tempdir, 'sitemap.xml'))
# second actually do it
rl.allow_multifile = True
rl.write(basename=os.path.join(tempdir, 'sitemap.xml'))
# check the two component sitemaps
rl1 = ResourceList()
rl1.read(os.path.join(tempdir, 'sitemap00000.xml'))
self.assertEquals(len(rl1), 2)
self.assertEquals(rl1.capability, 'resourcelist')
self.assertFalse(rl1.sitemapindex)
i = iter(rl1)
self.assertEquals(next(i).uri, 'http://localhost/a')
self.assertEquals(next(i).uri, 'http://localhost/b')
rl2 = ResourceList()
rl2.read(os.path.join(tempdir, 'sitemap00001.xml'))
self.assertEquals(len(rl2), 2)
i = iter(rl2)
self.assertEquals(next(i).uri, 'http://localhost/c')
self.assertEquals(next(i).uri, 'http://localhost/d')
# check the sitemapindex (read just as index)
rli = ResourceList()
rli.read(os.path.join(tempdir, 'sitemap.xml'), index_only=True)
self.assertEquals(len(rli), 2)
i = iter(rli)
self.assertEquals(rli.capability, 'resourcelist')
self.assertTrue(rli.sitemapindex)
self.assertEquals(next(i).uri, 'http://localhost/sitemap00000.xml')
self.assertEquals(next(i).uri, 'http://localhost/sitemap00001.xml')
# check the sitemapindex and components
rli = ResourceList(mapper=rl.mapper)
rli.read(os.path.join(tempdir, 'sitemap.xml'))
self.assertEquals(len(rli), 4)
self.assertEquals(rli.capability, 'resourcelist')
self.assertFalse(rli.sitemapindex)
i = iter(rli)
self.assertEquals(next(i).uri, 'http://localhost/a')
self.assertEquals(next(i).uri, 'http://localhost/b')
self.assertEquals(next(i).uri, 'http://localhost/c')
self.assertEquals(next(i).uri, 'http://localhost/d')
# cleanup tempdir
shutil.rmtree(tempdir)
def test_07_print(self):
r1 = Resource(uri='a', lastmod='2001-01-01', length=1234)
r2 = Resource(uri='b', lastmod='2002-02-02', length=56789)
r3 = Resource(uri='c', lastmod='2003-03-03', length=0)
m = ResourceList(md={'capability': 'resourcelist', 'modified': None})
m.add(r1)
m.add(r2)
m.add(r3)
# print m
self.assertEqual(
Sitemap().resources_as_xml(m),
"<?xml version='1.0' encoding='UTF-8'?>\n<urlset xmlns=\"http://www.sitemaps.org/schemas/sitemap/0.9\" xmlns:rs=\"http://www.openarchives.org/rs/terms/\"><rs:md capability=\"resourcelist\" /><url><loc>a</loc><lastmod>2001-01-01T00:00:00Z</lastmod><rs:md length=\"1234\" /></url><url><loc>b</loc><lastmod>2002-02-02T00:00:00Z</lastmod><rs:md length=\"56789\" /></url><url><loc>c</loc><lastmod>2003-03-03T00:00:00Z</lastmod><rs:md length=\"0\" /></url></urlset>"
)
def test33_write(self):
# ResourceList
rl = ResourceList()
rl.add(Resource(uri='http://example.com/test/a', timestamp=1))
rl.add(Resource(uri='http://example.com/test/b', timestamp=1))
rl.add(Resource(uri='http://example.com/test/c', timestamp=1))
rl_filename = os.path.join(self.tmpdir, 'test33_write_resourcelist.xml')
rl.write(basename=rl_filename)
with open(rl_filename, 'r') as f:
s = Sitemap()
s.parse_xml(fh=f)
self.assertFalse(s.parsed_index)
# ResourceListIndex
rli = ResourceList()
rli.add(Resource(uri='http://example.com/test/resourcelist00000.xml', timestamp=1))
rli.add(Resource(uri='http://example.com/test/resourcelist00001.xml', timestamp=1))
rli.add(Resource(uri='http://example.com/test/resourcelist00002.xml', timestamp=1))
rli.sitemapindex = True
rli_filename = os.path.join(self.tmpdir, 'test33_write_resourcelist-index.xml')
rli.write(basename=rli_filename)
with open(rli_filename, 'r') as f:
s = Sitemap()
s.parse_xml(fh=f)
self.assertTrue(s.parsed_index)
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_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 test02_changed(self):
src = ResourceList()
src.add(Resource('a', timestamp=1))
src.add(Resource('b', timestamp=2))
dst = ResourceList()
dst.add(Resource('a', timestamp=3))
dst.add(Resource('b', timestamp=4))
(same, changed, deleted, added) = dst.compare(src)
self.assertEqual(len(same), 0, "0 things unchanged")
self.assertEqual(len(changed), 2, "2 things changed")
i = iter(changed)
self.assertEqual(next(i).uri, 'a', "first was a")
self.assertEqual(next(i).uri, 'b', "second was b")
self.assertEqual(len(deleted), 0, "nothing deleted")
self.assertEqual(len(added), 0, "nothing added")
def test02_changed(self):
src = ResourceList()
src.add( Resource('a',timestamp=1) )
src.add( Resource('b',timestamp=2) )
dst = ResourceList()
dst.add( Resource('a',timestamp=3) )
dst.add( Resource('b',timestamp=4) )
( same, changed, deleted, added ) = dst.compare(src)
self.assertEqual( len(same), 0, "0 things unchanged" )
self.assertEqual( len(changed), 2, "2 things changed" )
i = iter(changed)
self.assertEqual( next(i).uri, 'a', "first was a" )
self.assertEqual( next(i).uri, 'b', "second was b" )
self.assertEqual( len(deleted), 0, "nothing deleted" )
self.assertEqual( len(added), 0, "nothing added" )
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 test03_dump_multi_file_max_size(self):
rl = ResourceList()
for letter in map(chr, range(ord('a'), ord('l') + 1)):
uri = 'http://ex.org/%s' % (letter)
fname = 'tests/testdata/a_to_z/%s' % (letter)
rl.add(Resource(uri, path=fname))
self.assertEqual(len(rl), 12)
#d=Dump(rl)
#tmpdir=tempfile.mkdtemp()
#tmpbase=os.path.join(tmpdir,'base')
#d.max_size=2000 # start new zip after size exceeds 2000 bytes
#n=d.write(tmpbase)
#self.assertEqual( n, 2, 'expect to write 2 dump files' )
#
# Now repeat with large size limit but small number of files limit
d2 = Dump(rl)
tmpbase = os.path.join(self.tmpdir, 'test03_')
d2.max_files = 4
n = d2.write(tmpbase)
self.assertEqual(n, 3, 'expect to write 3 dump files')
self.assertTrue(os.path.isfile(tmpbase + '00000.zip'))
self.assertTrue(os.path.isfile(tmpbase + '00001.zip'))
self.assertTrue(os.path.isfile(tmpbase + '00002.zip'))
# Look at the first file in detail
zipf = tmpbase + '00000.zip'
zo = zipfile.ZipFile(zipf, 'r')
self.assertEqual(zo.namelist(), ['manifest.xml', 'a', 'b', 'c', 'd'])
#self.assertEqual( zo.getinfo('manifest.xml').file_size, 470 )
self.assertEqual(zo.getinfo('a').file_size, 9)
self.assertEqual(zo.getinfo('b').file_size, 1116)
self.assertEqual(zo.getinfo('c').file_size, 32)
self.assertEqual(zo.getinfo('d').file_size, 13)
zo.close()
os.unlink(zipf)
# Check second and third files have expected contents
zipf = tmpbase + '00001.zip'
zo = zipfile.ZipFile(zipf, 'r')
self.assertEqual(zo.namelist(), ['manifest.xml', 'e', 'f', 'g', 'h'])
zo.close()
os.unlink(zipf)
zipf = tmpbase + '00002.zip'
zo = zipfile.ZipFile(zipf, 'r')
self.assertEqual(zo.namelist(), ['manifest.xml', 'i', 'j', 'k', 'l'])
zo.close()
os.unlink(zipf)
def test03_dump_multi_file_max_size(self):
rl=ResourceList()
for letter in map(chr,xrange(ord('a'),ord('l')+1)):
uri='http://ex.org/%s' % (letter)
fname='resync/test/testdata/a_to_z/%s' % (letter)
rl.add( Resource(uri, path=fname) )
self.assertEqual( len(rl), 12 )
#d=Dump(rl)
#tmpdir=tempfile.mkdtemp()
#tmpbase=os.path.join(tmpdir,'base')
#d.max_size=2000 # start new zip after size exceeds 2000 bytes
#n=d.write(tmpbase)
#self.assertEqual( n, 2, 'expect to write 2 dump files' )
#
# Now repeat with large size limit but small number of files limit
d2=Dump(rl)
tmpbase=os.path.join(self.tmpdir,'test03_')
d2.max_files=4
n=d2.write(tmpbase)
self.assertEqual( n, 3, 'expect to write 3 dump files' )
self.assertTrue( os.path.isfile(tmpbase+'00000.zip') )
self.assertTrue( os.path.isfile(tmpbase+'00001.zip') )
self.assertTrue( os.path.isfile(tmpbase+'00002.zip') )
# Look at the first file in detail
zipf=tmpbase+'00000.zip'
zo=zipfile.ZipFile(zipf,'r')
self.assertEqual( zo.namelist(), ['manifest.xml','a','b','c','d'] )
#self.assertEqual( zo.getinfo('manifest.xml').file_size, 470 )
self.assertEqual( zo.getinfo('a').file_size, 9 )
self.assertEqual( zo.getinfo('b').file_size, 1116 )
self.assertEqual( zo.getinfo('c').file_size, 32 )
self.assertEqual( zo.getinfo('d').file_size, 13 )
zo.close()
os.unlink(zipf)
# Check second and third files have expected contents
zipf=tmpbase+'00001.zip'
zo=zipfile.ZipFile(zipf,'r')
self.assertEqual( zo.namelist(), ['manifest.xml','e','f','g','h'] )
zo.close()
os.unlink(zipf)
zipf=tmpbase+'00002.zip'
zo=zipfile.ZipFile(zipf,'r')
self.assertEqual( zo.namelist(), ['manifest.xml','i','j','k','l'] )
zo.close()
os.unlink(zipf)
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 )
def test06_add_changed_resources(self):
added = ResourceList()
added.add( Resource('a',timestamp=1,change='created') )
added.add( Resource('d',timestamp=4,change='created') )
self.assertEqual(len(added), 2, "2 things in added resource_list")
changes = ChangeList()
changes.add_changed_resources( added, change='created' )
self.assertEqual(len(changes), 2, "2 things added")
i = iter(changes)
first = next(i)
self.assertEqual(first.uri, 'a', "changes[0].uri=a")
self.assertEqual(first.timestamp, 1, "changes[0].timestamp=1")
self.assertEqual(first.change, 'created') #, "changes[0].change=createdd")
second = next(i)
self.assertEqual(second.timestamp, 4, "changes[1].timestamp=4")
self.assertEqual(second.change, 'created', "changes[1].change=createdd")
# Now add some with updated (one same, one diff)
updated = ResourceList()
updated.add( Resource('a',timestamp=5,change='created') )
updated.add( Resource('b',timestamp=6,change='created') )
self.assertEqual(len(updated), 2, "2 things in updated resource_list")
changes.add_changed_resources( updated, change='updated' )
self.assertEqual(len(changes), 4, "4 = 2 old + 2 things updated")
# Make new resource_list from the changes which should not have dupes
dst = ResourceList()
dst.add( changes, replace=True )
self.assertEqual(len(dst), 3, "3 unique resources")
self.assertEqual(dst.resources['a'].timestamp, 5 ) # 5 was later in last the 1
self.assertEqual(dst.resources['a'].change, 'updated')
self.assertEqual(dst.resources['b'].timestamp, 6)
self.assertEqual(dst.resources['b'].change, 'updated')
self.assertEqual(dst.resources['d'].timestamp, 4)
self.assertEqual(dst.resources['d'].change, 'created')
def test33_write(self):
# ResourceList
rl = ResourceList()
rl.add(Resource(uri='http://example.com/test/a', timestamp=1))
rl.add(Resource(uri='http://example.com/test/b', timestamp=1))
rl.add(Resource(uri='http://example.com/test/c', timestamp=1))
rl_filename = os.path.join(self.tmpdir,
'test33_write_resourcelist.xml')
rl.write(basename=rl_filename)
with open(rl_filename, 'r') as f:
s = Sitemap()
s.parse_xml(fh=f)
self.assertFalse(s.parsed_index)
# ResourceListIndex
rli = ResourceList()
rli.add(
Resource(uri='http://example.com/test/resourcelist00000.xml',
timestamp=1))
rli.add(
Resource(uri='http://example.com/test/resourcelist00001.xml',
timestamp=1))
rli.add(
Resource(uri='http://example.com/test/resourcelist00002.xml',
timestamp=1))
rli.sitemapindex = True
rli_filename = os.path.join(self.tmpdir,
'test33_write_resourcelist-index.xml')
rli.write(basename=rli_filename)
with open(rli_filename, 'r') as f:
s = Sitemap()
s.parse_xml(fh=f)
self.assertTrue(s.parsed_index)
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 test03_deleted(self):
src = ResourceList()
src.add( Resource('a',timestamp=1) )
src.add( Resource('b',timestamp=2) )
dst = ResourceList()
dst.add( Resource('a',timestamp=1) )
dst.add( Resource('b',timestamp=2) )
dst.add( Resource('c',timestamp=3) )
dst.add( Resource('d',timestamp=4) )
( same, changed, deleted, added ) = dst.compare(src)
self.assertEqual( len(same), 2, "2 things unchanged" )
self.assertEqual( len(changed), 0, "nothing changed" )
self.assertEqual( len(deleted), 2, "c and d deleted" )
i = iter(deleted)
self.assertEqual( i.next().uri, 'c', "first was c" )
self.assertEqual( i.next().uri, 'd', "second was d" )
self.assertEqual( len(added), 0, "nothing added" )
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)
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"
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)
if args.resource_url[-1] != '/':
args.resource_url += '/'
if not isdir(args.resource_dir):
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"
def test11_bad_size(self):
rl=ResourceList()
rl.add( Resource('http://ex.org/a', length=9999, path='resync/test/testdata/a') )
d=Dump(rl)
self.assertTrue( d.check_files(check_length=False) )
self.assertRaises( DumpError, d.check_files )
def test10_no_path(self):
rl=ResourceList()
rl.add( Resource('http://ex.org/a', length=7, path='resync/test/testdata/a') )
rl.add( Resource('http://ex.org/b', length=21 ) )
d=Dump(rl)
self.assertRaises( DumpError, d.check_files )
