def get_data_path(self, baseurl, urlpath, entrypath):
"""
Gets directory listing or file description or raw file dump
:param baseurl: base URL of endpoint
:param urlpath: base path of URL
:param entrypath: basepath of the entry selected (equivalent of URL)
:returns: `dict` of catalogs/collections or `dict` of GeoJSON item
"""
thispath = os.path.join(baseurl, urlpath)
resource_type = None
root_link = None
child_links = []
data_path = self.data + entrypath
if '/' not in entrypath: # root
root_link = baseurl
else:
parentpath = urljoin(thispath, '.')
child_links.append({
'rel': 'parent',
'href': '{}?f=json'.format(parentpath),
'type': 'application/json'
})
child_links.append({
'rel': 'parent',
'href': parentpath,
'type': 'text/html'
})
depth = entrypath.count('/')
root_path = '/'.replace('/', '../' * depth, 1)
root_link = urljoin(thispath, root_path)
content = {
'links': [{
'rel': 'root',
'href': '{}?f=json'.format(root_link),
'type': 'application/json'
}, {
'rel': 'root',
'href': root_link,
'type': 'text/html'
}, {
'rel': 'self',
'href': '{}?f=json'.format(thispath),
'type': 'application/json',
}, {
'rel': 'self',
'href': thispath,
'type': 'text/html'
}]
}
LOGGER.debug('Checking if path exists as Catalog, Collection or Asset')
try:
jsondata = _get_json_data('{}/catalog.json'.format(data_path))
resource_type = 'Catalog'
except Exception:
try:
jsondata = _get_json_data(
'{}/collection.json'.format(data_path)) # noqa
resource_type = 'Collection'
except Exception:
try:
filename = os.path.basename(data_path)
jsondata = _get_json_data('{}/{}.json'.format(
data_path, filename)) # noqa
resource_type = 'Assets'
except Exception:
msg = 'Resource does not exist: {}'.format(data_path)
LOGGER.error(msg)
raise ProviderNotFoundError(msg)
if resource_type == 'Catalog' or resource_type == 'Collection':
content['type'] = resource_type
link_href_list = []
for link in jsondata["links"]:
if resource_type in ['Catalog', 'Collection'] \
and link["rel"] in ["child", "item"]:
link_href_list.append(link["href"].replace('\\', '/'))
link_href_list.sort()
for link in link_href_list:
unused, path_ending, entry_type = link.split('/')
newpath = os.path.join(baseurl, urlpath,
path_ending).replace('\\', '/') # noqa
if entry_type == 'catalog.json':
child_links.append({
'rel': 'child',
'href': newpath,
'type': 'text/html',
'created': "-",
'entry:type': 'Catalog'
})
elif entry_type == 'collection.json':
child_links.append({
'rel': 'child',
'href': newpath,
'type': 'text/html',
'created': "-",
'entry:type': 'Collection'
})
else:
child_links.append({
'rel': 'item',
'href': newpath,
'title': path_ending,
'created': "-",
'entry:type': 'Item'
})
elif resource_type == 'Assets':
content = jsondata
content['assets']['default'] = {
'href': os.path.join(baseurl, urlpath).replace('\\', '/'),
}
for key in content['assets']:
content['assets'][key]['file:size'] = 0
content['assets'][key]['created'] = jsondata["properties"][
"datetime"] # noqa
content['links'].extend(child_links)
return content
def get_data_path(self, baseurl, urlpath, dirpath):
"""
Gets directory listing or file description or raw file dump
:param baseurl: base URL of endpoint
:param urlpath: base path of URL
:param dirpath: directory basepath (equivalent of URL)
:returns: `dict` of file listing or `dict` of GeoJSON item or raw file
"""
thispath = os.path.join(baseurl, urlpath)
resource_type = None
root_link = None
child_links = []
data_path = os.path.join(self.data, dirpath)
data_path = self.data + dirpath
if '/' not in dirpath: # root
root_link = baseurl
else:
parentpath = urljoin(thispath, '.')
child_links.append({
'rel': 'parent',
'href': '{}?f=json'.format(parentpath),
'type': 'application/json'
})
child_links.append({
'rel': 'parent',
'href': parentpath,
'type': 'text/html'
})
depth = dirpath.count('/')
root_path = '/'.replace('/', '../' * depth, 1)
root_link = urljoin(thispath, root_path)
content = {
'links': [{
'rel': 'root',
'href': '{}?f=json'.format(root_link),
'type': 'application/json'
}, {
'rel': 'root',
'href': root_link,
'type': 'text/html'
}, {
'rel': 'self',
'href': '{}?f=json'.format(thispath),
'type': 'application/json',
}, {
'rel': 'self',
'href': thispath,
'type': 'text/html'
}]
}
LOGGER.debug('Checking if path exists as raw file or directory')
if data_path.endswith(tuple(self.file_types)):
resource_type = 'raw_file'
elif os.path.exists(data_path):
resource_type = 'directory'
else:
LOGGER.debug('Checking if path exists as file via file_types')
for ft in self.file_types:
tmp_path = '{}{}'.format(data_path, ft)
if os.path.exists(tmp_path):
resource_type = 'file'
data_path = tmp_path
break
if resource_type is None:
msg = 'Resource does not exist: {}'.format(data_path)
LOGGER.error(msg)
raise ProviderNotFoundError(msg)
if resource_type == 'raw_file':
with io.open(data_path, 'rb') as fh:
return fh.read()
elif resource_type == 'directory':
content['type'] = 'Catalog'
dirpath2 = os.listdir(data_path)
dirpath2.sort()
for dc in dirpath2:
# TODO: handle a generic directory for tiles
if dc == "tiles":
continue
fullpath = os.path.join(data_path, dc)
filectime = file_modified_iso8601(fullpath)
filesize = os.path.getsize(fullpath)
if os.path.isdir(fullpath):
newpath = os.path.join(baseurl, urlpath, dc)
# child_links.append({
# 'rel': 'child',
# 'href': '{}?f=json'.format(newpath),
# 'type': 'application/json'
# })
child_links.append({
'rel': 'child',
'href': newpath,
'type': 'text/html',
'created': filectime,
})
elif os.path.isfile(fullpath):
basename, extension = os.path.splitext(dc)
newpath = os.path.join(baseurl, urlpath, basename)
newpath2 = '{}{}'.format(newpath, extension)
if extension in self.file_types:
fullpath = os.path.join(data_path, dc)
child_links.append({
'rel': 'item',
'href': newpath,
'title': get_path_basename(newpath2),
'created': filectime,
'file:size': filesize
})
# child_links.append({
# 'rel': 'item',
# 'title': get_path_basename(newpath2),
# 'href': newpath,
# 'type': 'text/html',
# 'created': filectime,
# 'file:size': filesize
# })
elif resource_type == 'file':
filename = os.path.basename(data_path)
id_ = os.path.splitext(filename)[0]
if urlpath:
filename = filename.replace(id_, '')
url = '{}/{}{}'.format(baseurl, urlpath, filename)
filectime = file_modified_iso8601(data_path)
filesize = os.path.getsize(data_path)
content = {
'id': id_,
'type': 'Feature',
'properties': {},
'links': [],
'assets': {}
}
content.update(_describe_file(data_path))
content['assets']['default'] = {
'href': url,
'created': filectime,
'file:size': filesize
}
content['links'].extend(child_links)
return content