def generator(filenames: iter, count=0) -> [int, Resource]:
passes_gate = self.resource_gate()
for filename in filenames:
if not isinstance(filename, str):
LOG.warning("Not a string: %s" % filename)
filename = str(filename)
file = os.path.abspath(filename)
if not os.path.exists(file):
LOG.warning("File does not exist: %s" % file)
elif os.path.isdir(file):
for cr, rsc in generator(self.walk_directories(file), count=count):
yield cr, rsc
count = cr
elif os.path.isfile(file):
if passes_gate(file):
count += 1
path = os.path.relpath(file, self.para.resource_dir)
uri = self.para.url_prefix + defaults.sanitize_url_path(path)
stat = os.stat(file)
resource = Resource(uri=uri, length=stat.st_size,
lastmod=defaults.w3c_datetime(stat.st_ctime),
md5=defaults.md5_for_file(file),
mime_type=defaults.mime_type(file))
yield count, resource
self.observers_inform(self, ExecutorEvent.created_resource, resource=resource,
count=count, file=file)
else:
self.observers_inform(self, ExecutorEvent.rejected_file, file=file)
else:
LOG.warning("Not a regular file: %s" % file)
def uri_from_path(self, path):
"""
``derived`` :samp:`Calculate the url of a path relative to {resource_dir}`
:param str path: the path to calculate the url from
:return: the url of the path relative to ``resource_dir``
"""
rel_path = os.path.relpath(path, self.resource_dir)
return self.url_prefix + defaults.sanitize_url_path(rel_path)
def capabilitylist_url(self) -> str:
"""
``derived`` :samp:`The current capabilitylist url`
The current capabilitylist url points to 'capabilitylist.xml' in the metadata directory.
:return: current capabilitylist url
"""
path = self.abs_metadata_path("capabilitylist.xml")
rel_path = os.path.relpath(path, self.resource_dir)
return self.url_prefix + defaults.sanitize_url_path(rel_path)
def description_url(self):
"""
``derived`` :samp:`The current description url`
The current description url either points to ``{server root}/.well-known/resourcesync``
or to a file in the metadata directory.
:return: current description url
See also: :func:`has_wellknown_at_root`
"""
if self.has_wellknown_at_root:
r = urllib.parse.urlsplit(self.url_prefix)
return urllib.parse.urlunsplit([r[0], r[1], WELL_KNOWN_URL, "", ""])
else:
path = self.abs_metadata_path(WELL_KNOWN_URL)
rel_path = os.path.relpath(path, self.resource_dir)
return self.url_prefix + defaults.sanitize_url_path(rel_path)
def create_index(self, sitemap_data_iter: iter):
if len(sitemap_data_iter) > 1:
resourcelist_index = ResourceList()
resourcelist_index.sitemapindex = True
resourcelist_index.md_at = self.date_start_processing
resourcelist_index.md_completed = self.date_end_processing
index_path = self.para.abs_metadata_path("resourcelist-index.xml")
rel_index_path = os.path.relpath(index_path,
self.para.resource_dir)
index_url = self.para.url_prefix + defaults.sanitize_url_path(
rel_index_path)
resourcelist_index.link_set(rel="up",
href=self.para.capabilitylist_url())
for sitemap_data in sitemap_data_iter:
resourcelist_index.add(
Resource(uri=sitemap_data.uri,
md_at=sitemap_data.doc_start,
md_completed=sitemap_data.doc_end))
if sitemap_data.document_saved:
self.update_rel_index(index_url, sitemap_data.path)
self.finish_sitemap(-1, resourcelist_index)
def test_sanitize_url_path(self):
self.assertEquals("foo/bar/baz.txt",
defaults.sanitize_url_path("foo/bar/baz.txt"))
self.assertEquals("foo/bar/baz.txt",
defaults.sanitize_url_path("foo\\bar\\baz.txt"))