def __create_resourcelist__(src, checksum=True):
"""
Create a resourcelist xml for the source denominated by src.
:param src: 's1', 's2' etc.
:param checksum: should checksums be added to the xml.
:return: None
"""
abs_path = os.path.dirname(os.path.abspath(__name__))
data = []
path = os.path.join(abs_path, "rs/source", src, "files")
for root, directories, filenames in os.walk(path):
for filename in filenames:
data.append(os.path.join(root, filename))
paths = ",".join(data)
outfile = os.path.join(abs_path, "rs/source", src, "resourcelist.xml")
# create a resourcelist from the files in test/rs/source/{src}/files
client = Client(checksum=checksum)
prefix = "http://localhost:8000/rs/source/" + src + "/files"
resourcedir = os.path.join(abs_path, "rs/source", src, "files")
args = [prefix, resourcedir]
client.set_mappings(args)
client.write_resource_list(paths, outfile)
def __create_resourcelist__(src, checksum=True):
"""
Create a resourcelist xml for the source denominated by src.
:param src: 's1', 's2' etc.
:param checksum: should checksums be added to the xml.
:return: None
"""
abs_path = os.path.dirname(os.path.abspath(__name__))
data = []
path = os.path.join(abs_path, "rs/source", src, "files")
for root, directories, filenames in os.walk(path):
for filename in filenames:
data.append(os.path.join(root, filename))
paths = ",".join(data)
outfile = os.path.join(abs_path, "rs/source", src, "resourcelist.xml")
# create a resourcelist from the files in test/rs/source/{src}/files
client = Client(checksum=checksum)
prefix = "http://localhost:8000/rs/source/" + src + "/files"
resourcedir = os.path.join(abs_path, "rs/source", src, "files")
args = [prefix, resourcedir]
client.set_mappings(args)
client.write_resource_list(paths, outfile)
def test41_write_resource_list_path(self):
c = Client()
c.set_mappings( ['http://example.org/','resync/test/testdata/'] )
# with an explicit paths setting only the specified paths will be included
with capture_stdout() as capturer:
c.write_resource_list(paths='resync/test/testdata/dir1')
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.assertFalse( re.search(r'<url><loc>http://example.org/dir2/file_x</loc>', capturer.result ) )
def test40_write_resource_list_mappings(self):
c = Client()
c.set_mappings( ['http://example.org/','resync/test/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 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 test41_write_resource_list_path(self):
c = Client()
c.set_mappings(['http://example.org/', 'resync/test/testdata/'])
# with an explicit paths setting only the specified paths will be included
with capture_stdout() as capturer:
c.write_resource_list(paths='resync/test/testdata/dir1')
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.assertFalse(
re.search(r'<url><loc>http://example.org/dir2/file_x</loc>',
capturer.result))
def test40_write_resource_list_mappings(self):
c = Client()
c.set_mappings(['http://example.org/', 'resync/test/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 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)
