def test07_explore_show_head(self):
e = Explorer()
# file that exists with matching
with capture_stdout() as capturer:
e.explore_show_head(uri='tests/testdata/dir1/file_a',
check_headers={'content-length': 20,
'unknown': 'abc'})
self.assertTrue(
re.search(r'HEAD tests/testdata/dir1/file_a', capturer.result))
self.assertTrue(
re.search(r'content-length: 20 MATCHES EXPECTED VALUE', capturer.result))
# same file, bad header check
with capture_stdout() as capturer:
e.explore_show_head('tests/testdata/dir1/file_a',
check_headers={'content-length': 99})
self.assertTrue(
re.search(r'HEAD tests/testdata/dir1/file_a', capturer.result))
self.assertTrue(
re.search(r'content-length: 20 EXPECTED 99', capturer.result))
# file that does not exist
with capture_stdout() as capturer:
e.explore_show_head('tests/testdata/does_not_exist')
self.assertTrue(
re.search(r'HEAD tests/testdata/does_not_exist', capturer.result))
self.assertTrue(re.search(r'status: 404', capturer.result))
def test20_parse_document(self):
# Key property of the parse_document() method is that it parses the
# document and identifies its type
c = Client()
with capture_stdout() as capturer:
c.sitemap_name='tests/testdata/examples_from_spec/resourcesync_ex_1.xml'
c.parse_document()
self.assertTrue( re.search(r'Parsed resourcelist document with 2 entries',capturer.result) )
with capture_stdout() as capturer:
c.sitemap_name='tests/testdata/examples_from_spec/resourcesync_ex_17.xml'
c.parse_document()
self.assertTrue( re.search(r'Parsed resourcedump document with 3 entries',capturer.result) )
with capture_stdout() as capturer:
c.sitemap_name='tests/testdata/examples_from_spec/resourcesync_ex_19.xml'
c.parse_document()
self.assertTrue( re.search(r'Parsed changelist document with 4 entries',capturer.result) )
with capture_stdout() as capturer:
c.sitemap_name='tests/testdata/examples_from_spec/resourcesync_ex_22.xml'
c.parse_document()
self.assertTrue( re.search(r'Parsed changedump document with 3 entries',capturer.result) )
# Document that doesn't exist
c.sitemap_name='/does_not_exist'
self.assertRaises( ClientFatalError, c.parse_document )
# and verbose with truncation...
with capture_stdout() as capturer:
c.verbose = True
c.sitemap_name = 'tests/testdata/examples_from_spec/resourcesync_ex_1.xml'
c.max_sitemap_entries = 1
c.parse_document()
self.assertTrue( re.search(r'Showing first 1 entries', capturer.result ) )
self.assertTrue( re.search(r'\[0\] ', capturer.result ) )
self.assertFalse( re.search(r'\[1\] ', capturer.result ) )
def test07_explore_show_head(self):
e = Explorer()
# file that exists with matching
with capture_stdout() as capturer:
e.explore_show_head(uri='tests/testdata/dir1/file_a',
check_headers={
'content-length': 20,
'unknown': 'abc'
})
self.assertTrue(
re.search(r'HEAD tests/testdata/dir1/file_a', capturer.result))
self.assertTrue(
re.search(r'content-length: 20 MATCHES EXPECTED VALUE',
capturer.result))
# same file, bad header check
with capture_stdout() as capturer:
e.explore_show_head('tests/testdata/dir1/file_a',
check_headers={'content-length': 99})
self.assertTrue(
re.search(r'HEAD tests/testdata/dir1/file_a', capturer.result))
self.assertTrue(
re.search(r'content-length: 20 EXPECTED 99', capturer.result))
# file that does not exist
with capture_stdout() as capturer:
e.explore_show_head('tests/testdata/does_not_exist')
self.assertTrue(
re.search(r'HEAD tests/testdata/does_not_exist', capturer.result))
self.assertTrue(re.search(r'status: 404', capturer.result))
def test47_write_source_description(self):
c = Client()
# simple case to STDOUT
with capture_stdout() as capturer:
c.write_source_description(['a', 'b', 'c'])
self.assertTrue(re.search(r'<urlset ', capturer.result))
self.assertTrue(
re.search(r'<rs:md capability="description" />', capturer.result))
self.assertTrue(
re.search(
r'<url><loc>a</loc><rs:md capability="capabilitylist" /></url>',
capturer.result))
self.assertTrue(
re.search(
r'<url><loc>b</loc><rs:md capability="capabilitylist" /></url>',
capturer.result))
# more complex case to STDOUT
with capture_stdout() as capturer:
c.write_source_description(capability_lists=['http://a.b/'],
links=[{
'rel': 'c',
'href': 'd'
}])
self.assertTrue(re.search(r'http://a.b/', capturer.result))
# to file (just check that something is written)
outfile = os.path.join(self.tmpdir, 'sd_out.xml')
c.write_source_description(capability_lists=['http://a.b/'],
outfile=outfile,
links=[{
'rel': 'c',
'href': 'd'
}])
self.assertTrue(os.path.getsize(outfile) > 100)
def test41_write_resource_list_path(self):
c = Client()
c.set_mappings( ['http://example.org/','tests/testdata/'] )
links=[{'rel':'uri_c','href':'uri_d'}]
# with an explicit paths setting only the specified paths will be included
with capture_stdout() as capturer:
c.write_resource_list(paths='tests/testdata/dir1', links=links)
self.assertTrue( re.search(r'<rs:md at="\S+" capability="resourcelist"', capturer.result ) )
self.assertTrue( re.search(r'<url><loc>http://example.org/dir1/file_a</loc>', capturer.result ) )
self.assertTrue( re.search(r'<url><loc>http://example.org/dir1/file_b</loc>', capturer.result ) )
self.assertFalse( re.search(r'<url><loc>http://example.org/dir2/file_x</loc>', capturer.result ) )
# check link present
self.assertTrue( re.search(r'rel="uri_c"', capturer.result ) )
self.assertTrue( re.search(r'href="uri_d"', capturer.result ) )
# Travis CI does not preserve timestamps from github so test here for the file
# size but not the datestamp
#self.assertTrue( re.search(r'<url><loc>http://example.org/dir1/file_a</loc><lastmod>[\w\-:]+</lastmod><rs:md length="20" /></url>', capturer.result ) )
#self.assertTrue( re.search(r'<url><loc>http://example.org/dir1/file_b</loc><lastmod>[\w\-:]+</lastmod><rs:md length="45" /></url>', capturer.result ) )
# to file
outfile = os.path.join(self.tmpdir,'rl_out.xml')
c.write_resource_list(paths='tests/testdata/dir1', outfile=outfile)
self.assertTrue( os.path.getsize(outfile)>100 )
# dump instead (default file)
c.default_resource_dump = os.path.join(self.tmpdir,'rl_out_dump_def')
outfile = c.default_resource_dump+'00000.zip'
self.assertFalse( os.path.exists(outfile) )
c.write_resource_list(paths='tests/testdata/dir1', dump=True)
self.assertTrue( os.path.getsize(outfile)>100 )
# (specific file)
outbase = os.path.join(self.tmpdir,'rl_out_dump')
outfile = outbase+'00000.zip'
self.assertFalse( os.path.exists(outfile) )
c.write_resource_list(paths='tests/testdata/dir1', dump=True, outfile=outbase)
self.assertTrue( os.path.getsize(outfile)>100 )
def test45_write_change_list(self):
c = Client()
ex1 = 'tests/testdata/examples_from_spec/resourcesync_ex_1.xml'
with capture_stdout() as capturer:
c.write_change_list(ref_sitemap=ex1, newref_sitemap=ex1)
self.assertTrue( re.search(r'<rs:md capability="changelist"', capturer.result) )
# compare ex1 with testdata on disk
c.set_mappings( ['http://example.org/','tests/testdata/'] )
with capture_stdout() as capturer:
c.write_change_list(ref_sitemap=ex1, paths='tests/testdata/dir1')
self.assertTrue( re.search(r'<rs:md capability="changelist"', capturer.result) )
self.assertTrue( re.search(r'<url><loc>http://example.com/res1</loc><rs:md change="deleted" /></url>', capturer.result) )
# to file
outfile = os.path.join(self.tmpdir,'cl_out.xml')
c.write_change_list(ref_sitemap=ex1, newref_sitemap=ex1, outfile=outfile)
self.assertTrue( os.path.getsize(outfile)>100 )
def test47_write_source_description(self):
c = Client()
# simple case to STDOUT
with capture_stdout() as capturer:
c.write_source_description( [ 'a','b','c' ] )
self.assertTrue( re.search(r'<urlset ',capturer.result) )
self.assertTrue( re.search(r'<rs:md capability="description" />',capturer.result) )
self.assertTrue( re.search(r'<url><loc>a</loc><rs:md capability="capabilitylist" /></url>',capturer.result) )
self.assertTrue( re.search(r'<url><loc>b</loc><rs:md capability="capabilitylist" /></url>',capturer.result) )
# more complex case to STDOUT
with capture_stdout() as capturer:
c.write_source_description(capability_lists=['http://a.b/'], links=[{'rel':'c','href':'d'}])
self.assertTrue( re.search(r'http://a.b/', capturer.result ) )
# to file (just check that something is written)
outfile = os.path.join(self.tmpdir,'sd_out.xml')
c.write_source_description(capability_lists=['http://a.b/'], outfile=outfile, links=[{'rel':'c','href':'d'}])
self.assertTrue( os.path.getsize(outfile)>100 )
def test48_write_dump_if_requested(self):
c = Client()
# no dump file
self.assertFalse(c.write_dump_if_requested(ChangeList(), None))
# with dump file
with capture_stdout() as capturer:
c.write_dump_if_requested(ChangeList(), '/tmp/a_file')
self.assertTrue(re.search(r'FIXME', capturer.result))
def test04_explore(self):
e = Explorer()
e.sitemap_name = 'tests/testdata/explore1/caps1.xml'
with capture_stdout() as capturer:
# IOError generated from attempt to read stdin
e.fake_input = 'q'
e.explore()
self.assertTrue(re.search(r'resync-explorer done', capturer.result))
def test48_write_dump_if_requested(self):
c = Client()
# no dump file
self.assertFalse( c.write_dump_if_requested( ChangeList(), None ) )
# with dump file
with capture_stdout() as capturer:
c.write_dump_if_requested(ChangeList(),'/tmp/a_file')
self.assertTrue( re.search(r'FIXME', capturer.result) )
def test06_explore_show_summary(self):
e = Explorer()
# file that exists with matching
with capture_stdout() as capturer:
e.explore_show_summary(list=CapabilityList())
self.assertTrue(re.search(r'Parsed \(unknown capability\) document with 0 entries:',
capturer.result))
# dummy capabilities object and display
cl = CapabilityList()
cl.add(Resource('uri:resourcelist'))
cl.add(Resource('uri:changelist'))
with capture_stdout() as capturer:
e.explore_show_summary(cl, False, [])
self.assertTrue(re.search(
r'Parsed \(unknown capability\) document with 2 entries:', capturer.result))
self.assertTrue(re.search(r'\[1\] uri:changelist', capturer.result))
self.assertTrue(re.search(r'\[2\] uri:resourcelist', capturer.result))
def test04_explore(self):
e = Explorer()
e.sitemap_name = 'tests/testdata/explore1/caps1.xml'
with capture_stdout() as capturer:
# IOError generated from attempt to read stdin
e.fake_input = 'q'
e.explore()
self.assertTrue(re.search(r'resync-explorer done', capturer.result))
def test05_explore_uri(self):
e = Explorer()
with capture_stdout() as capturer:
e.fake_input = 'q'
self.assertRaises(ExplorerQuit, e.explore_uri,
XResource('tests/testdata/explore1/caps1.xml'))
self.assertTrue(re.search(r'Reading tests/testdata/explore1/caps1.xml',
capturer.result))
self.assertTrue(re.search(r'Parsed capabilitylist document with 4 entries:',
capturer.result))
def test49_read_reference_resource_list(self):
c = Client()
with capture_stdout() as capturer:
rl = c.read_reference_resource_list('tests/testdata/examples_from_spec/resourcesync_ex_1.xml')
self.assertEqual( len(rl), 2 )
self.assertEqual( '', capturer.result )
c.verbose = True
with capture_stdout() as capturer:
rl = c.read_reference_resource_list('tests/testdata/examples_from_spec/resourcesync_ex_1.xml')
self.assertEqual( len(rl), 2 )
self.assertTrue( re.search(r'http://example.com/res2', capturer.result) )
c.verbose = True
c.max_sitemap_entries = 1
with capture_stdout() as capturer:
rl = c.read_reference_resource_list('tests/testdata/examples_from_spec/resourcesync_ex_1.xml')
self.assertEqual( len(rl), 2 )
self.assertTrue( re.search(r'http://example.com/res1', capturer.result) )
self.assertTrue( re.search(r'Showing first 1 entries', capturer.result) )
self.assertFalse( re.search(r'http://example.com/res2', capturer.result) )
def test40_write_resource_list_mappings(self):
c = Client()
c.set_mappings( ['http://example.org/','tests/testdata/'] )
# with no explicit paths seting the mapping will be used
with capture_stdout() as capturer:
c.write_resource_list()
#sys.stderr.write(capturer.result)
self.assertTrue( re.search(r'<rs:md at="\S+" capability="resourcelist"', capturer.result ) )
self.assertTrue( re.search(r'<url><loc>http://example.org/dir1/file_a</loc>', capturer.result ) )
self.assertTrue( re.search(r'<url><loc>http://example.org/dir1/file_b</loc>', capturer.result ) )
self.assertTrue( re.search(r'<url><loc>http://example.org/dir2/file_x</loc>', capturer.result ) )
def test20_parse_document(self):
# Key property of the parse_document() method is that it parses the
# document and identifies its type
c = Client()
with capture_stdout() as capturer:
c.sitemap_name = 'tests/testdata/examples_from_spec/resourcesync_ex_1.xml'
c.parse_document()
self.assertTrue(
re.search(r'Parsed resourcelist document with 2 entries',
capturer.result))
with capture_stdout() as capturer:
c.sitemap_name = 'tests/testdata/examples_from_spec/resourcesync_ex_17.xml'
c.parse_document()
self.assertTrue(
re.search(r'Parsed resourcedump document with 3 entries',
capturer.result))
with capture_stdout() as capturer:
c.sitemap_name = 'tests/testdata/examples_from_spec/resourcesync_ex_19.xml'
c.parse_document()
self.assertTrue(
re.search(r'Parsed changelist document with 4 entries',
capturer.result))
with capture_stdout() as capturer:
c.sitemap_name = 'tests/testdata/examples_from_spec/resourcesync_ex_22.xml'
c.parse_document()
self.assertTrue(
re.search(r'Parsed changedump document with 3 entries',
capturer.result))
# Document that doesn't exist
c.sitemap_name = '/does_not_exist'
self.assertRaises(ClientFatalError, c.parse_document)
# and verbose with truncation...
with capture_stdout() as capturer:
c.verbose = True
c.sitemap_name = 'tests/testdata/examples_from_spec/resourcesync_ex_1.xml'
c.max_sitemap_entries = 1
c.parse_document()
self.assertTrue(re.search(r'Showing first 1 entries', capturer.result))
self.assertTrue(re.search(r'\[0\] ', capturer.result))
self.assertFalse(re.search(r'\[1\] ', capturer.result))
def test46_write_capability_list(self):
c = Client()
caps = { 'a':'uri_a', 'b':'uri_b' }
# simple case to STDOUT
with capture_stdout() as capturer:
c.write_capability_list( caps )
self.assertTrue( re.search(r'<urlset ',capturer.result) )
self.assertTrue( re.search(r'<rs:md capability="capabilitylist" />',capturer.result) )
self.assertTrue( re.search(r'<url><loc>uri_a</loc><rs:md capability="a"',capturer.result) )
self.assertTrue( re.search(r'<url><loc>uri_b</loc><rs:md capability="b"',capturer.result) )
# to file (just check that something is written)
outfile = os.path.join(self.tmpdir,'caps_out.xml')
c.write_capability_list(capabilities=caps, outfile=outfile)
self.assertTrue( os.path.getsize(outfile)>100 )
def test49_read_reference_resource_list(self):
c = Client()
with capture_stdout() as capturer:
rl = c.read_reference_resource_list(
'tests/testdata/examples_from_spec/resourcesync_ex_1.xml')
self.assertEqual(len(rl), 2)
self.assertEqual('', capturer.result)
c.verbose = True
with capture_stdout() as capturer:
rl = c.read_reference_resource_list(
'tests/testdata/examples_from_spec/resourcesync_ex_1.xml')
self.assertEqual(len(rl), 2)
self.assertTrue(re.search(r'http://example.com/res2', capturer.result))
c.verbose = True
c.max_sitemap_entries = 1
with capture_stdout() as capturer:
rl = c.read_reference_resource_list(
'tests/testdata/examples_from_spec/resourcesync_ex_1.xml')
self.assertEqual(len(rl), 2)
self.assertTrue(re.search(r'http://example.com/res1', capturer.result))
self.assertTrue(re.search(r'Showing first 1 entries', capturer.result))
self.assertFalse(re.search(r'http://example.com/res2',
capturer.result))
def test45_write_change_list(self):
c = Client()
ex1 = 'tests/testdata/examples_from_spec/resourcesync_ex_1.xml'
with capture_stdout() as capturer:
c.write_change_list(ref_sitemap=ex1, newref_sitemap=ex1)
self.assertTrue(
re.search(r'<rs:md capability="changelist"', capturer.result))
# compare ex1 with testdata on disk
c.set_mappings(['http://example.org/', 'tests/testdata/'])
with capture_stdout() as capturer:
c.write_change_list(ref_sitemap=ex1, paths='tests/testdata/dir1')
self.assertTrue(
re.search(r'<rs:md capability="changelist"', capturer.result))
self.assertTrue(
re.search(
r'<url><loc>http://example.com/res1</loc><rs:md change="deleted" /></url>',
capturer.result))
# to file
outfile = os.path.join(self.tmpdir, 'cl_out.xml')
c.write_change_list(ref_sitemap=ex1,
newref_sitemap=ex1,
outfile=outfile)
self.assertTrue(os.path.getsize(outfile) > 100)
def test41_write_resource_list_path(self):
c = Client()
c.set_mappings(['http://example.org/', 'tests/testdata/'])
links = [{'rel': 'uri_c', 'href': 'uri_d'}]
# with an explicit paths setting only the specified paths will be
# included
with capture_stdout() as capturer:
c.write_resource_list(paths='tests/testdata/dir1', links=links)
self.assertTrue(
re.search(r'<rs:md at="\S+" capability="resourcelist"',
capturer.result))
self.assertTrue(
re.search(r'<url><loc>http://example.org/dir1/file_a</loc>',
capturer.result))
self.assertTrue(
re.search(r'<url><loc>http://example.org/dir1/file_b</loc>',
capturer.result))
self.assertFalse(
re.search(r'<url><loc>http://example.org/dir2/file_x</loc>',
capturer.result))
# check link present
self.assertTrue(re.search(r'rel="uri_c"', capturer.result))
self.assertTrue(re.search(r'href="uri_d"', capturer.result))
# Travis CI does not preserve timestamps from github so test here for the file
# size but not the datestamp
# self.assertTrue( re.search(r'<url><loc>http://example.org/dir1/file_a</loc><lastmod>[\w\-:]+</lastmod><rs:md length="20" /></url>', capturer.result ) )
# self.assertTrue( re.search(r'<url><loc>http://example.org/dir1/file_b</loc><lastmod>[\w\-:]+</lastmod><rs:md length="45" /></url>', capturer.result ) )
# to file
outfile = os.path.join(self.tmpdir, 'rl_out.xml')
c.write_resource_list(paths='tests/testdata/dir1', outfile=outfile)
self.assertTrue(os.path.getsize(outfile) > 100)
# dump instead (default file)
c.default_resource_dump = os.path.join(self.tmpdir, 'rl_out_dump_def')
outfile = c.default_resource_dump + '00000.zip'
self.assertFalse(os.path.exists(outfile))
c.write_resource_list(paths='tests/testdata/dir1', dump=True)
self.assertTrue(os.path.getsize(outfile) > 100)
# (specific file)
outbase = os.path.join(self.tmpdir, 'rl_out_dump')
outfile = outbase + '00000.zip'
self.assertFalse(os.path.exists(outfile))
c.write_resource_list(paths='tests/testdata/dir1',
dump=True,
outfile=outbase)
self.assertTrue(os.path.getsize(outfile) > 100)
def test40_write_resource_list_mappings(self):
c = Client()
c.set_mappings(['http://example.org/', 'tests/testdata/'])
# with no explicit paths seting the mapping will be used
with capture_stdout() as capturer:
c.write_resource_list()
#sys.stderr.write(capturer.result)
self.assertTrue(
re.search(r'<rs:md at="\S+" capability="resourcelist"',
capturer.result))
self.assertTrue(
re.search(r'<url><loc>http://example.org/dir1/file_a</loc>',
capturer.result))
self.assertTrue(
re.search(r'<url><loc>http://example.org/dir1/file_b</loc>',
capturer.result))
self.assertTrue(
re.search(r'<url><loc>http://example.org/dir2/file_x</loc>',
capturer.result))
def test46_write_capability_list(self):
c = Client()
caps = {'a': 'uri_a', 'b': 'uri_b'}
# simple case to STDOUT
with capture_stdout() as capturer:
c.write_capability_list(caps)
self.assertTrue(re.search(r'<urlset ', capturer.result))
self.assertTrue(
re.search(r'<rs:md capability="capabilitylist" />',
capturer.result))
self.assertTrue(
re.search(r'<url><loc>uri_a</loc><rs:md capability="a"',
capturer.result))
self.assertTrue(
re.search(r'<url><loc>uri_b</loc><rs:md capability="b"',
capturer.result))
# to file (just check that something is written)
outfile = os.path.join(self.tmpdir, 'caps_out.xml')
c.write_capability_list(capabilities=caps, outfile=outfile)
self.assertTrue(os.path.getsize(outfile) > 100)
def test10_expand_relative_uri(self):
e = Explorer()
with capture_stdout() as capturer:
uri = e.expand_relative_uri('https://example.org/ctx', 'abc')
self.assertEqual(uri, 'https://example.org/abc')
self.assertTrue(re.search(r'expanded relative URI', capturer.result))
def test10_expand_relative_uri(self):
e = Explorer()
with capture_stdout() as capturer:
uri = e.expand_relative_uri('https://example.org/ctx', 'abc')
self.assertEqual(uri, 'https://example.org/abc')
self.assertTrue(re.search(r'expanded relative URI', capturer.result))