Fix style issues #515

    * Docstrings should be in the imperative mood
    * Use f strings instead of %

Signed-off-by: Jono Yang <[email protected]>

minecode/management/commands/priority_queue.py

@@ -117,9 +117,6 @@ def process_request(priority_resource_uri, _priority_router=priority_router):
         if priority:
             kwargs["priority"] = priority
         errors = _priority_router.process(purl_to_visit, **kwargs)
-        if TRACE:
-            new_uris_to_visit = list(new_uris_to_visit or [])
-            logger.debug(f"visit_uri: new_uris_to_visit: {new_uris_to_visit}")
 
         return errors
 

minecode/management/commands/run_visit.py

@@ -295,7 +295,7 @@ def visit_uri(
     if visit_error:
         msg = f"Visit error for URI: {uri_to_visit}"
         msg += "\n".format()
-        msg += get_error_message(e)
+        msg += get_error_message(e)  # NOQA
         visit_errors.append(msg)
         logger.error(msg)
 

minecode/management/commands/update_maven_package_data.py

@@ -218,7 +218,7 @@ def update_maven_packages(
         version=version,
         qualifiers=normalized_qualifiers or "",
     )
-    if existing_package.exists():
+    if existing_packages.exists():
         duplicate_packages = []
         for existing_package in existing_packages:
             if existing_package.download_url != maven_package.download_url:

minecode/mappers/__init__.py

@@ -25,8 +25,8 @@ def __call__(self, uri, resource_uri):
 
     def get_packages(self, uri, resource_uri):
         """
-        This method must yield ScannedPackage objects (or return a list) built
-        from a resource_uri ResourceURI object.
+        Yield ScannedPackage objects (or return a list) built from a
+        resource_uri ResourceURI object.
         """
         raise NotImplementedError
 

minecode/mappers/debian.py

@@ -74,9 +74,7 @@ def get_vcs_repo(description):
         repos.append((vcs_tool, vcs_repo))
 
     if len(repos) > 1:
-        raise TypeError(
-            "Debian description with more than one Vcs repos: %(repos)r" % locals()
-        )
+        raise TypeError(f"Debian description with more than one Vcs repos: {repos}")
 
     if repos:
         vcs_tool, vcs_repo = repos[0]

minecode/mappers/repomd.py

@@ -16,7 +16,7 @@
 
 @map_router.route(".+/repomd.xml")
 def map_repomd_data(uris, resource_uri):
-    """Returns a list of RpmPackage objects collected from visitors."""
+    """Return a list of RpmPackage objects collected from visitors."""
     if not resource_uri.data:
         return
     packages = []

minecode/model_utils.py

@@ -458,8 +458,8 @@ def merge_or_create_package(scanned_package, visit_level, override=False):
 
 def update_or_create_resource(package, resource_data):
     """
-    Using Resource data from `resource_data`, create or update the
-    corresponding purldb Resource from `package`.
+    Create or update the corresponding purldb Resource from `package` using
+    `resource_data`.
 
     Return a 3-tuple of the corresponding purldb Resource of `resource_data`,
     `resource`, as well as booleans representing whether the Resource was

minecode/route.py

@@ -119,7 +119,8 @@ def append(self, pattern, endpoint):
 
     def route(self, *patterns):
         """
-        Decorator to make a callable 'endpoint' routed to one or more patterns.
+        Return a decorator to make a callable 'endpoint' routed to one or more
+        patterns.
 
         Example:
         -------
@@ -178,7 +179,7 @@ def resolve(self, string):
             # this can happen when multiple patterns match the same string
             # we raise an exception with enough debugging information
             pats = repr([r.pattern for r in candidates])
-            msg = "%(string)r matches multiple patterns %(pats)r" % locals()
+            msg = f"{string} matches multiple patterns {pats}"
             raise MultipleRoutesDefined(msg)
 
         return candidates[0].endpoint

minecode/rsync.py

@@ -137,7 +137,7 @@ def fetch_directory(uri, recurse=True):
         file_name = tmp.name
         ends = not uri.endswith("/") and "/" or ""
         recursive = recurse and "--recursive" or "--no-recursive"
-        cmd = 'rsync --no-motd %(recursive)s -d "%(uri)s%(ends)s"' % locals()
+        cmd = f'rsync --no-motd {recursive} -d "{uri}{ends}"'
         rsync = command.Command(cmd)
         out, err = rsync.execute()
 

minecode/saneyaml.py

@@ -137,7 +137,7 @@ def ordered_dumper(dumper, data):
 
 
 def null_dumper(dumper, value):
-    """Always dump nulls as empty string."""
+    """Dump nulls as empty string."""
     return dumper.represent_scalar("tag:yaml.org,2002:null", "")
 
 
@@ -149,7 +149,7 @@ def string_dumper(dumper, value, _tag="tag:yaml.org,2002:str"):
     Ensure that all scalars are dumped as UTF-8 unicode, folded and
     quoted in the sanest and most readable way.
     """
-    if not isinstance(value, basestring):
+    if not isinstance(value, str):
         value = repr(value)
 
     if isinstance(value, str):

minecode/tests/test_command.py

@@ -21,7 +21,7 @@ class CommandTest(MiningTestCase):
     def test_listing_command(self):
         td = self.get_test_loc("command")
         osc = "ls" if not ON_WINDOWS else "dir"
-        c = '%(osc)s "%(td)s"' % locals()
+        c = f'{osc} "{td}"'
         cmd = command.Command(c)
         out, err = cmd.execute()
         err = [e for e in err]

minecode/tests/test_debian.py

@@ -37,7 +37,6 @@ def check_objects_expected(self, results, expected_loc, regen=FIXTURES_REGEN):
         result = ""
         for item in results:
             if isinstance(item, str):
-                item = unicode(item, "utf-8")
                 result += item.encode("utf-8")
             else:
                 if isinstance(item, debcon.Debian822):
@@ -66,7 +65,7 @@ def check_expected_deb822(self, deb_object, expected_loc, regen=FIXTURES_REGEN):
             assert expected == result
 
     def get_tmp_gz_file(self, loc):
-        """Creates a .gz file at a temporary location, and returns that location."""
+        """Create a .gz file at a temporary location, and returns that location."""
         temp_gz_location = self.get_temp_file(extension=".gz")
         with open(loc, "rb") as f:
             file_content = f.read()

minecode/tests/test_rsync.py

@@ -279,7 +279,7 @@ def test_fetch_directory_no_recurse(self):
             self.assertTrue("bar/this" not in results)
 
     def get_dirs(self, input_path):
-        """Returns only the type and path from rsync entries."""
+        """Return only the type and path from rsync entries."""
         return [
             (e["type"], e["path"])
             for e in rsync.directory_entries(input_path)

minecode/tests/test_rubygems.py

@@ -50,8 +50,8 @@ def test_check_gem_file_visitor_routes(self):
             "https://rubygems.org/downloads/O365RubyEasy-0.0.1.gem",  # upper
         ]
 
-        for route in routes:
-            self.assertTrue(visit_router.resolve(route))
+        for gem_file_visitor_route in routes:
+            self.assertTrue(visit_router.resolve(gem_file_visitor_route))
 
     def test_RubyGemsIndexVisitor_latest(self):
         uri = "http://rubygems.org/specs.4.8.gz"

minecode/utils.py

@@ -48,14 +48,14 @@ def stringify_null_purl_fields(data):
 
 
 def sha1(content):
-    """Returns the sha1 hash of the given content."""
+    """Return the sha1 hash of the given content."""
     h = hashlib.sha1()
     h.update(content)
     return h.hexdigest()
 
 
 def md5(content):
-    """Returns the md5 hash of the given content."""
+    """Return the md5 hash of the given content."""
     h = hashlib.md5()
     h.update(content)
     return h.hexdigest()
@@ -86,14 +86,14 @@ def __eq__(self, other):
 
 
 def normalize_trailing_slash(uri):
-    """Appends a trailing slash if the URI is not ending with one already."""
+    """Append a trailing slash if the URI is not ending with one already."""
     if not uri.endswith("/"):
         uri += "/"
     return uri
 
 
 def is_ascii(s):
-    """Returns True is the string is ASCII."""
+    """Return True is the string is ASCII."""
     return all(ord(c) < 128 for c in s)
 
 
@@ -109,7 +109,7 @@ def clean_html_entities(text):
 
 
 def clean_description(text):
-    """Cleans the description text from HTML entities and from extra whitespaces."""
+    """Clean the description text from HTML entities and from extra whitespaces."""
     return " ".join(clean_html_entities(text.strip()).split())
 
 
@@ -212,19 +212,18 @@ def get_http_response(uri, timeout=10):
     requests_args["timeout"] = timeout
 
     if not uri.lower().startswith("http"):
-        raise Exception("get_http_response: Not an HTTP URI: %(uri)r" % locals())
+        raise Exception(f"get_http_response: Not an HTTP URI: {uri}")
 
     try:
         response = requests.get(uri, **requests_args)
     except (ConnectionError, InvalidSchema):
-        logger.error("get_http_response: Download failed for %(uri)r" % locals())
+        logger.error(f"get_http_response: Download failed for {uri}")
         raise
 
     status = response.status_code
     if status != 200:
         raise Exception(
-            "get_http_response: Download failed for %(uri)r "
-            "with %(status)r" % locals()
+            f"get_http_response: Download failed for {uri} " f"with {status}"
         )
     return response
 
@@ -249,8 +248,8 @@ def get_package_sha1(package, field="repository_download_url"):
 
 def fetch_and_write_file_from_url(url):
     """
-    Fetches a file from the `url` and returns the location for the
-    temporary file. Return None if the url is not reachable.
+    Fetch a file from the `url` and return the location for the temporary file.
+    Return None if the url is not reachable.
     """
     response = requests.get(url)
     if not response.ok:
@@ -327,7 +326,7 @@ def extract_file(location):
                 target = event.target
                 break
     except Exception as e:
-        logger.error("extract_file: failed for %(location)r" % locals())
+        logger.error(f"extract_file: failed for {location}")
         raise e
     return target
 
@@ -389,7 +388,7 @@ def _setup(self):
             smaller_queryset = copy.deepcopy(self._base_queryset)[
                 i : i + self.max_obj_num
             ]
-            logger.debug("Grabbing next %s objects from DB" % self.max_obj_num)
+            logger.debug(f"Grabbing next {self.max_obj_num} objects from DB")
             yield from smaller_queryset.iterator()
 
     def __iter__(self):

minecode/utils_test.py

@@ -189,16 +189,16 @@ def mocked_requests_get_for_uris(url_to_location, *args, **kwargs):
 
 
 def response_403(url, request):
-    """Returns a HTTP response with status 403."""
+    """Return a HTTP response with status 403."""
     return {"status_code": 403, "content": ""}
 
 
 class JsonBasedTestingMixin(TestCase):
     def _normalize_results(self, data, fields_to_remove=[]):
         """
-        Returns the `data`, where any `package_uid` value has been normalized
-        with `purl_with_fake_uuid()` and fields from `fields_to_remove` have
-        been removed from `data`.
+        Return `data`, where any `package_uid` value has been normalized with
+        `purl_with_fake_uuid()` and fields from `fields_to_remove` have been
+        removed from it.
         """
         if type(data) in (list, ReturnList):
             return [self._normalize_results(entry, fields_to_remove) for entry in data]
@@ -265,9 +265,9 @@ def check_expected_results(
 class JsonBasedTesting(JsonBasedTestingMixin, FileBasedTesting):
     def _normalize_results(self, data, fields_to_remove=[]):
         """
-        Returns the `data`, where any `package_uid` value has been normalized
-        with `purl_with_fake_uuid()` and fields from `fields_to_remove` have
-        been removed from `data`.
+        Return the `data`, where any `package_uid` value has been normalized
+        with `purl_with_fake_uuid()` and fields from `fields_to_remove` that
+        have been removed from `data`.
         """
         if type(data) in (list, ReturnList):
             return [self._normalize_results(entry, fields_to_remove) for entry in data]
@@ -354,10 +354,6 @@ def check_expected_uris(
 
 def model_to_dict(instance, fields=None, exclude=None):
     """
-    Copied from django.forms.models. model_to_dict
-    license: bsd-new
-    see ABOUT file for details
-
     Return a mapping containing the data in ``instance``.
 
     ``fields`` is an optional list of field names. If provided, only the
@@ -369,6 +365,10 @@ def model_to_dict(instance, fields=None, exclude=None):
 
     Note that all field with the word "date" in their name is converted
     to a boolean value to abstract test results from dates.
+
+    Copied from django.forms.models. model_to_dict
+    license: bsd-new
+    see ABOUT file for details
     """
     opts = instance._meta
     data = dict()

minecode/version.py

@@ -136,7 +136,7 @@ def strip_version_tags(path):
 
 
 def strip_extensions(path):
-    """ "Remove well known archive extensions from end of path."""
+    """Remove well known archive extensions from end of path."""
     for rext in ARCHIVE_FILE_EXT_RES:
         path = rext.sub("", path)
     return path

minecode/visitors/bower.py

@@ -22,6 +22,8 @@ class BowerTopJsonVisitor(HttpJsonVisitor):
 
     def get_uris(self, content):
         """
+        Yield Bower URIs from `content`.
+
         The json content is a list with name and url, like the following format:
         ...
           {

minecode/visitors/maven.py

@@ -1410,13 +1410,9 @@ def get_entries(location, fields=frozenset(ENTRY_FIELDS)):
                 except EOFError:
                     if TRACE_DEEP:
                         print(
-                            "Index version: %(_index_version)r last_modified: %(_last_modified)r"
-                            % locals()
-                        )
-                        print(
-                            "Processed %(entries_count)d docs. Last entry: %(entry)r"
-                            % locals()
+                            f"Index version: {_index_version} last_modified: {_last_modified}"
                         )
+                        print(f"Processed {entries_count} docs. Last entry: {entry}")
                         print("Unique keys:")
                         for k in sorted(keys):
                             print(k)

minecode/visitors/pypi.py

@@ -58,7 +58,7 @@ def fetch(self, uri, timeout=None):
         return temp_file
 
     def dumps(self, content):
-        """The content is huge json and should not be dumped."""
+        """Do not dump the content, as it is huge json."""
         return None
 
     def get_uris(self, content):