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 test01_no_links(self):
xml = run_resync(
['--resourcelist', 'http://example.org/t', 'tests/testdata/dir1'])
rl = ResourceList()
rl.parse(fh=io.BytesIO(xml))
self.assertEqual(len(rl), 2)
self.assertEqual(rl.link('describedby'), None)
def read_reference_resource_list(self, ref_sitemap, name='reference'):
"""Read reference resource list and return the ResourceList object
name parameter just uses in output messages to say what type
of resource list is being read.
"""
rl = ResourceList()
self.logger.info("Reading reference %s resource list from %s ..." %
(name, ref_sitemap))
rl.mapper = self.mapper
rl.read(uri=ref_sitemap, index_only=(not self.allow_multifile))
num_entries = len(rl.resources)
self.logger.info(
"Read %s resource list with %d entries in %d sitemaps" %
(name, num_entries, rl.num_files))
if (self.verbose):
to_show = 100
override_str = ' (override with --max-sitemap-entries)'
if (self.max_sitemap_entries):
to_show = self.max_sitemap_entries
override_str = ''
if (num_entries > to_show):
print "Showing first %d entries sorted by URI%s..." % (
to_show, override_str)
n = 0
for r in rl.resources:
print r
n += 1
if (n >= to_show):
break
return (rl)
def test01_no_links(self):
xml = run_resync(['--write-resourcelist',
'http://example.org/t', 'tests/testdata/dir1'])
rl = ResourceList()
rl.parse(fh=io.BytesIO(xml))
self.assertEqual(len(rl), 2)
self.assertEqual(rl.link('describedby'), None)
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 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 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 read_reference_resource_list(self,ref_sitemap,name='reference'):
"""Read reference resource list and return the ResourceList object
name parameter just uses in output messages to say what type
of resource list is being read.
"""
rl = ResourceList()
self.logger.info("Reading reference %s resource list from %s ..." % (name,ref_sitemap))
rl.mapper=self.mapper
rl.read(uri=ref_sitemap,index_only=(not self.allow_multifile))
num_entries = len(rl.resources)
self.logger.info("Read %s resource list with %d entries in %d sitemaps" % (name,num_entries,rl.num_files))
if (self.verbose):
to_show = 100
override_str = ' (override with --max-sitemap-entries)'
if (self.max_sitemap_entries):
to_show = self.max_sitemap_entries
override_str = ''
if (num_entries>to_show):
print "Showing first %d entries sorted by URI%s..." % (to_show,override_str)
n=0
for r in rl.resources:
print r
n+=1
if ( n >= to_show ):
break
return(rl)
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_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 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 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_ex_01(self):
"""resourcesync_ex_1 is a simple resource_list with 2 resources, no metadata"""
rl=ResourceList()
rl.parse(uri='tests/testdata/examples_from_spec/resourcesync_ex_1.xml')
self.assertEqual( rl.capability, 'resourcelist' )
self.assertEqual( len(rl.resources), 2, '2 resources')
sms = sorted(rl.uris())
self.assertEqual( sms, ['http://example.com/res1','http://example.com/res2'] )
self.assertEqual( rl.resources['http://example.com/res1'].lastmod, None )
def test31_parse_no_capability(self):
xml='<?xml version=\'1.0\' encoding=\'UTF-8\'?>\n\
<urlset xmlns="http://www.sitemaps.org/schemas/sitemap/0.9">\
<url><loc>http://example.com/res1</loc><lastmod>2012-03-14T18:37:36Z</lastmod></url>\
</urlset>'
rl=ResourceList()
rl.parse(fh=StringIO.StringIO(xml))
self.assertEqual( len(rl.resources), 1, 'got 1 resource')
self.assertEqual( rl.md['capability'], 'resourcelist', 'capability set by reading routine' )
self.assertFalse( 'from' in rl.md )
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 test31_parse_no_capability(self):
xml='<?xml version=\'1.0\' encoding=\'UTF-8\'?>\n\
<urlset xmlns="http://www.sitemaps.org/schemas/sitemap/0.9">\
<url><loc>http://example.com/res1</loc><lastmod>2012-03-14T18:37:36Z</lastmod></url>\
</urlset>'
rl=ResourceList()
rl.parse(fh=io.StringIO(xml))
self.assertEqual( len(rl.resources), 1, 'got 1 resource')
self.assertEqual( rl.md['capability'], 'resourcelist', 'capability set by reading routine' )
self.assertFalse( 'from' in rl.md )
def test_ex_08(self):
"""resourcesync_ex_8 is a simple Resource List Index with 2 Resource Lists"""
rl=ResourceList()
rl.read(uri='tests/testdata/examples_from_spec/resourcesync_ex_8.xml',index_only=True)
self.assertEqual( rl.capability, 'resourcelist' )
self.assertEqual( rl.md_at, '2013-01-03T09:00:00Z' )
self.assertEqual( len(rl.resources), 2, '2 resources')
sms = sorted(rl.uris())
self.assertEqual( sms, ['http://example.com/resourcelist-part1.xml',
'http://example.com/resourcelist-part2.xml'] )
def test_01_read_local_filenames(self):
rl = ResourceList()
rl.read('tests/testdata/sitemapindex2/sitemap.xml')
self.assertEqual( len(rl.resources), 17, '17 resources from 3 sitemaps listed')
sr = sorted(rl.uris())
self.assertEqual( sr[0], 'http://localhost:8888/resources/1' )
self.assertEqual( sr[1], 'http://localhost:8888/resources/10' )
self.assertEqual( sr[2], 'http://localhost:8888/resources/100' )
self.assertEqual( sr[3], 'http://localhost:8888/resources/1000' )
self.assertEqual( sr[16], 'http://localhost:8888/resources/826' )
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 test_ex_02(self):
"""resourcesync_ex_2 is a simple resource_list with 2 resources, some metadata"""
rl=ResourceList()
rl.parse(uri='tests/testdata/examples_from_spec/resourcesync_ex_2.xml')
self.assertEqual( len(rl.resources), 2, '2 resources')
sms = sorted(rl.uris())
self.assertEqual( sms, ['http://example.com/res1','http://example.com/res2'] )
self.assertEqual( rl.resources['http://example.com/res1'].lastmod, '2013-01-02T13:00:00Z' )
self.assertEqual( rl.resources['http://example.com/res2'].lastmod, '2013-01-02T14:00:00Z' )
self.assertEqual( rl.resources['http://example.com/res1'].md5, '1584abdf8ebdc9802ac0c6a7402c03b6' )
self.assertEqual( rl.resources['http://example.com/res2'].md5, '1e0d5cb8ef6ba40c99b14c0237be735e' )
def test_01_read_local_filenames(self):
rl = ResourceList()
rl.read('tests/testdata/sitemapindex2/sitemap.xml')
self.assertEqual(len(rl.resources), 17,
'17 resources from 3 sitemaps listed')
sr = sorted(rl.uris())
self.assertEqual(sr[0], 'http://localhost:8888/resources/1')
self.assertEqual(sr[1], 'http://localhost:8888/resources/10')
self.assertEqual(sr[2], 'http://localhost:8888/resources/100')
self.assertEqual(sr[3], 'http://localhost:8888/resources/1000')
self.assertEqual(sr[16], 'http://localhost:8888/resources/826')
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_02_read_with_mapper(self):
rl = ResourceList()
rl.mapper = Mapper(['http://localhost/=tests/testdata/sitemapindex2/'])
rl.read('tests/testdata/sitemapindex2/sitemap_mapper.xml')
self.assertEqual( len(rl.resources), 17, '17 resources from 3 sitemaps listed')
sr = sorted(rl.uris())
self.assertEqual( sr[0], 'http://localhost:8888/resources/1' )
self.assertEqual( sr[1], 'http://localhost:8888/resources/10' )
self.assertEqual( sr[2], 'http://localhost:8888/resources/100' )
self.assertEqual( sr[3], 'http://localhost:8888/resources/1000' )
self.assertEqual( sr[16], 'http://localhost:8888/resources/826' )
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 test30_parse(self):
xml='<?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" modified="2013-01-01"/>\
<url><loc>/tmp/rs_test/src/file_a</loc><lastmod>2012-03-14T18:37:36Z</lastmod><rs:md change="updated" length="12" /></url>\
<url><loc>/tmp/rs_test/src/file_b</loc><lastmod>2012-03-14T18:37:36Z</lastmod><rs:md length="32" /></url>\
</urlset>'
rl=ResourceList()
rl.parse(fh=StringIO.StringIO(xml))
self.assertEqual( len(rl.resources), 2, 'got 2 resources')
self.assertEqual( rl.md['capability'], 'resourcelist', 'capability set' )
self.assertEqual( rl.md['modified'], '2013-01-01' )
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 test30_parse(self):
xml='<?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 at="2013-08-07" capability="resourcelist" completed="2013-08-08" />\
<url><loc>/tmp/rs_test/src/file_a</loc><lastmod>2012-03-14T18:37:36Z</lastmod><rs:md change="updated" length="12" /></url>\
<url><loc>/tmp/rs_test/src/file_b</loc><lastmod>2012-03-14T18:37:36Z</lastmod><rs:md length="32" /></url>\
</urlset>'
rl=ResourceList()
rl.parse(fh=StringIO.StringIO(xml))
self.assertEqual( len(rl.resources), 2, 'got 2 resources')
self.assertEqual( rl.md['capability'], 'resourcelist', 'capability set' )
self.assertEqual( rl.md_at, '2013-08-07' )
self.assertEqual( rl.md_completed, '2013-08-08' )
def test02_resourcelist(self):
rl = ResourceList()
caps = CapabilityList()
caps.add_capability( rl, "http://example.org/resourcelist.xml" )
caps.md['from'] = "2013-02-07T22:39:00"
self.assertEqual( len(caps), 1 )
self.assertEqual( caps.as_xml(), '<?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="capabilitylist" from="2013-02-07T22:39:00" /><url><loc>http://example.org/resourcelist.xml</loc><rs:md capability="resourcelist" /></url></urlset>' )
def get_state_published(self):
"""
See if publish_dir has a zip end file. If so, return the path of the zip end file and the resourcelist
(with local paths) of resources published in the zip end file.
:return: - the path to the zip end file or None if there is no zip end file.
- the resourcelist of resources published in zip end file or an empty list if there is no zip end file.
"""
path_zip_end_old = None
rl_end_old = ResourceList()
zip_end_files = glob(
os.path.join(self.publish_dir, PREFIX_END_PART + "*.zip"))
if len(zip_end_files) > 1:
raise RuntimeError(
"Found more than one %s*.zip files. Inconsistent structure of %s."
% (PREFIX_END_PART, self.publish_dir))
elif len(zip_end_files) == 1:
path_zip_end_old = zip_end_files[0]
if path_zip_end_old:
rl_file = open(os.path.splitext(path_zip_end_old)[0] + ".xml", "r")
sm = Sitemap()
sm.parse_xml(rl_file, resources=rl_end_old)
rl_file.close()
return path_zip_end_old, rl_end_old
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 generate(self):
"""Generate a resource_list (snapshot from the source)."""
then = time.time()
resource_list = ResourceList(resources=self.source.resources,
count=self.source.resource_count)
now = time.time()
self.logger.info("Generated resource_list: %f" % (now - then))
return resource_list
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 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 test32_parse_bad_capability(self):
# the <rs:md capability="bad_capability".. should give error
xml='<?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="bad_capability" from="2013-01-01"/>\
<url><loc>http://example.com/bad_res_1</loc><lastmod>2012-03-14T18:37:36Z</lastmod></url>\
</urlset>'
rl=ResourceList()
self.assertRaises( SitemapParseError, rl.parse, fh=StringIO.StringIO(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 test03_multiple(self):
caps = CapabilityList()
rl = ResourceList()
caps.add_capability( rl, "rl.xml" )
cl = ChangeList()
caps.add_capability( cl, "cl.xml" )
self.assertEqual( len(caps), 2 )
xml = caps.as_xml()
self.assertTrue( re.search( r'<loc>rl.xml</loc><rs:md capability="resourcelist" />', xml ) )
self.assertTrue( re.search( r'<loc>cl.xml</loc><rs:md capability="changelist" />', xml) )
def list_resources_chunk(self):
"""
Fill a resource list up to max_files_compressed or with as much rdf-files as there are left in resource_dir.
A boolean indicates whether the resource_dir was exhausted.
:return: the ResourceList, exhausted
"""
resourcelist = ResourceList()
exhausted = self.list_patch_files(resourcelist,
max_files=self.max_files_compressed)
return resourcelist, exhausted
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 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_build_ex_13(self):
"""Capability List document with 4 entries"""
cl = CapabilityList()
cl.describedby = 'http://example.com/info_about_set1_of_resources.xml'
cl.up = 'http://example.com/resourcesync_description.xml'
cl.add_capability( capability=ResourceList( uri='http://example.com/dataset1/resourcelist.xml' ) )
cl.add_capability( capability=ResourceDump( uri='http://example.com/dataset1/resourcedump.xml' ) )
cl.add_capability( capability=ChangeList( uri='http://example.com/dataset1/changelist.xml' ) )
cl.add_capability( capability=ChangeDump( uri='http://example.com/dataset1/changedump.xml' ) )
ex_xml = self._open_ex('resourcesync_ex_13').read()
self._assert_xml_equal( cl.as_xml(), ex_xml )
def test05_add(self):
r1 = Resource(uri='a', length=1)
r2 = Resource(uri='b', length=2)
i = ResourceList()
i.add(r1)
self.assertRaises(ResourceListDupeError, i.add, r1)
i.add(r2)
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 test04_added(self):
src = ResourceList()
src.add( Resource('a',timestamp=1) )
src.add( Resource('b',timestamp=2) )
src.add( Resource('c',timestamp=3) )
src.add( Resource('d',timestamp=4) )
dst = ResourceList()
dst.add( Resource('a',timestamp=1) )
dst.add( Resource('c',timestamp=3) )
( 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), 0, "nothing deleted" )
self.assertEqual( len(added), 2, "b and d added" )
i = iter(added)
self.assertEqual( next(i).uri, 'b', "first was b" )
self.assertEqual( next(i).uri, 'd', "second was d" )
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_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_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 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 test02_resource_list_links(self):
xml = run_resync([
'--resourcelist',
'--describedby-link=a',
'--sourcedescription-link=b', #will be ignored
'--capabilitylist-link=c',
'http://example.org/t',
'resync/test/testdata/dir1'
])
rl = ResourceList()
rl.parse(fh=StringIO.StringIO(xml))
self.assertEqual(len(rl), 2)
self.assertNotEqual(rl.link('describedby'), None)
self.assertEqual(rl.link('describedby')['href'], 'a')
self.assertNotEqual(rl.link('up'), None)
self.assertEqual(rl.link('up')['href'], 'c')
def test02_resource_list_links(self):
xml = run_resync(['--write-resourcelist',
'--describedby-link=a',
'--sourcedescription-link=b', # will be ignored
'--capabilitylist-link=c',
'http://example.org/t', 'tests/testdata/dir1'])
rl = ResourceList()
rl.parse(fh=io.BytesIO(xml))
self.assertEqual(len(rl), 2)
self.assertNotEqual(rl.link('describedby'), None)
self.assertEqual(rl.link('describedby')['href'], 'a')
self.assertNotEqual(rl.link('up'), None)
self.assertEqual(rl.link('up')['href'], 'c')
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 test01_same(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) )
( same, changed, deleted, added ) = dst.compare(src)
self.assertEqual( len(same), 2, "2 things unchanged" )
i = iter(same)
self.assertEqual( i.next().uri, 'a', "first was a" )
self.assertEqual( i.next().uri, 'b', "second was b" )
self.assertEqual( len(changed), 0, "nothing changed" )
self.assertEqual( len(deleted), 0, "nothing deleted" )
self.assertEqual( len(added), 0, "nothing added" )
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 )