def _get_downloaded_file(filename):
""" given a test filename, return the file_meta dictionary needed by
the workflow. Used for tests.
"""
if filename:
from util import get_test_file
csv_file = get_test_file(filename, 'scheduler')
magic_type = util.MS.file(csv_file)
return {
'out_file': csv_file,
'file_name': filename,
'file_size': os.path.getsize(csv_file),
'content_type': 'text/csv',
'md5sum': md5_for_file(csv_file),
'magic_type': util.magic_to_mime(magic_type),
}
print
print '*' * 80
print "WARNING"
print '*' * 80
print "When testing the workflow, you should set what to do with " \
"each source you're dealing with. Check " \
"webui.scheduler.test_helpers.py"
print '*' * 80
print
return {}
def _get_downloaded_file(filename):
""" given a test filename, return the file_meta dictionary needed by
the workflow. Used for tests.
"""
if filename:
from util import get_test_file
csv_file = get_test_file(
filename, 'scheduler'
)
magic_type = util.MS.file(csv_file)
return {
'out_file': csv_file,
'file_name': filename,
'file_size': os.path.getsize(csv_file),
'content_type': 'text/csv',
'md5sum': md5_for_file(csv_file),
'magic_type': util.magic_to_mime(magic_type),
}
print
print '*' * 80
print "WARNING"
print '*' * 80
print "When testing the workflow, you should set what to do with " \
"each source you're dealing with. Check " \
"webui.scheduler.test_helpers.py"
print '*' * 80
print
return {}
def _download_url(url, save_dir):
"""Downloads a URL into a file and save HTTP metadata."""
loggy = local.logger
request = urllib2.Request(url)
opener = urllib2.build_opener(CustomRedirectHandler())
url_handler = opener.open(request)
file_meta = __file_meta_from_headers(
url,
url_handler.headers,
url_handler.redirect_headers
if hasattr(url_handler, 'redirect_headers') else None
)
file_name = file_meta['file_name']
# do not remove directory here, download may be in parallel with other
# tasks using the same URL
# shutil.rmtree(save_dir, True)
__mkdir_p(save_dir)
if file_name[-1] == '/':
file_name = file_name[0:-1]
out_file = save_dir + '/' + file_name
output = open(out_file, 'wb')
file_size = file_meta['file_size']
if file_size == 0:
file_size = 1
loggy.info("Downloading: %s KBytes: %s", file_name, file_size / 1024)
file_size_dl = 0
block_sz = 8192
emit_status_count = 0
while True:
data_buffer = url_handler.read(block_sz)
if not data_buffer:
break
file_size_dl += len(data_buffer)
output.write(data_buffer)
if emit_status_count >= 100:
loggy.info("%10d [%3.2f%%]", file_size_dl,
file_size_dl * 100. / file_size)
emit_status_count = 0
else:
emit_status_count += 1
output.close()
# http://www.gavinj.net/2007/05/python-file-magic.html
magic_type = util.MS.file(out_file)
file_meta.update({
'out_file': out_file,
'magic_type': util.magic_to_mime(magic_type),
'md5sum': md5_for_file(out_file)
})
if file_meta['file_size'] == -1:
file_meta['file_size'] = os.path.getsize(file_meta['out_file'])
return file_meta
def _download_url(url, save_dir):
"""Downloads a URL into a file and save HTTP metadata."""
loggy = local.logger
request = urllib2.Request(url)
opener = urllib2.build_opener(CustomRedirectHandler())
url_handler = opener.open(request)
file_meta = __file_meta_from_headers(
url, url_handler.headers, url_handler.redirect_headers if hasattr(
url_handler, 'redirect_headers') else None)
file_name = file_meta['file_name']
# do not remove directory here, download may be in parallel with other
# tasks using the same URL
# shutil.rmtree(save_dir, True)
__mkdir_p(save_dir)
if file_name[-1] == '/':
file_name = file_name[0:-1]
out_file = save_dir + '/' + file_name
output = open(out_file, 'wb')
file_size = file_meta['file_size']
if file_size == 0:
file_size = 1
loggy.info("Downloading: %s KBytes: %s", file_name, file_size / 1024)
file_size_dl = 0
block_sz = 8192
emit_status_count = 0
while True:
data_buffer = url_handler.read(block_sz)
if not data_buffer:
break
file_size_dl += len(data_buffer)
output.write(data_buffer)
if emit_status_count >= 100:
loggy.info("%10d [%3.2f%%]", file_size_dl,
file_size_dl * 100. / file_size)
emit_status_count = 0
else:
emit_status_count += 1
output.close()
# http://www.gavinj.net/2007/05/python-file-magic.html
magic_type = util.MS.file(out_file)
file_meta.update({
'out_file': out_file,
'magic_type': util.magic_to_mime(magic_type),
'md5sum': md5_for_file(out_file)
})
if file_meta['file_size'] == -1:
file_meta['file_size'] = os.path.getsize(file_meta['out_file'])
return file_meta
def test_magic_to_mime(self):
self.assertEqual("text/plain", util.magic_to_mime('ascii text, with crlf line terminators'))