Format code and other minor cleanups

Signed-off-by: Philippe Ombredanne <[email protected]>

Author: pombredanne

src/attributecode/__init__.py

@@ -24,7 +24,7 @@
 try:
     basestring  # Python 2
 except NameError:
-    basestring = str  # Python 3
+    basestring = str  # Python 3 #NOQA
 
 
 __version__ = '3.2.2'

src/attributecode/api.py

@@ -22,11 +22,11 @@
 
 try:  # Python 2
     from urllib import urlencode, quote
-    from urllib2 import urlopen, Request, HTTPError, URLError
+    from urllib2 import urlopen, Request, HTTPError
 except ImportError:  # Python 3
     from urllib.parse import urlencode, quote
     from urllib.request import urlopen, Request
-    from urllib.error import HTTPError, URLError
+    from urllib.error import HTTPError
 
 from attributecode import ERROR
 from attributecode import Error

src/attributecode/cmd.py

@@ -108,7 +108,7 @@ def cli():
 @click.argument('output', nargs=1, required=True,
     type=click.Path(exists=False, dir_okay=False, resolve_path=True))
 
-@click.option('--filter', nargs=1, multiple=True, 
+@click.option('--filter', nargs=1, multiple=True,
     help='Filter for the output inventory. e.g. "license_expression=gpl-2.0')
 
 @click.option('-f', '--format', is_flag=False, default='csv', show_default=True,
@@ -139,7 +139,7 @@ def cli():
 
 @click.help_option('-h', '--help')
 
-def inventory(location, output, mapping, mapping_file, mapping_output, filter, quiet, format, verbose):
+def inventory(location, output, mapping, mapping_file, mapping_output, filter, quiet, format, verbose):  # NOQA
     """
 Collect a JSON or CSV inventory of components from .ABOUT files.
 
@@ -155,7 +155,7 @@ def inventory(location, output, mapping, mapping_file, mapping_output, filter, q
         # FIXME: return error code?
         return
 
-    click.echo('Collecting inventory from: %(location)s and writing output to: %(output)s' % locals()) #(location, output))
+    click.echo('Collecting inventory from: %(location)s and writing output to: %(output)s' % locals())
 
     # FIXME: do we really want to continue support zip as an input?
     if location.lower().endswith('.zip'):
@@ -320,7 +320,7 @@ def gen(location, output, mapping, mapping_file, license_notice_text_location, f
 @click.option('--template', type=click.Path(exists=True), nargs=1,
     help='Path to an optional custom attribution template used for generation.')
 
-@click.option('--vartext', nargs=1, multiple=True, 
+@click.option('--vartext', nargs=1, multiple=True,
     help='Variable texts to the attribution template.')
 
 @click.option('--verbose', is_flag=True, default=False,
@@ -478,7 +478,7 @@ def log_errors(errors, err_count, quiet, verbose, base_dir=False):
 
 
 def have_problematic_error(errors):
-    for severity, message in errors:
+    for severity, message in errors:  # NOQA
         sever = severities[severity]
         if sever in problematic_errors:
             return True

src/attributecode/gen.py

@@ -24,12 +24,12 @@
 from posixpath import basename, dirname, exists, join, normpath
 import sys
 
-if sys.version_info[0] < 3:
+if sys.version_info[0] < 3: 
     # Python 2
-    import backports.csv as csv
+    import backports.csv as csv #NOQA
 else:
     # Python 3
-    import csv
+    import csv #NOQA
 
 from attributecode import ERROR
 from attributecode import CRITICAL

src/attributecode/model.py

@@ -40,17 +40,17 @@
 import sys
 
 if sys.version_info[0] < 3:  # Python 2
-    import backports.csv as csv
-    from itertools import izip_longest as zip_longest
-    from urlparse import urljoin, urlparse
-    from urllib2 import urlopen, Request, HTTPError
+    import backports.csv as csv  # NOQA
+    from itertools import izip_longest as zip_longest  # NOQA
+    from urlparse import urljoin, urlparse  # NOQA
+    from urllib2 import urlopen, Request, HTTPError  # NOQA
 else:  # Python 3
-    basestring = str
-    import csv
-    from itertools import zip_longest
-    from urllib.parse import urljoin, urlparse
-    from urllib.request import urlopen, Request
-    from urllib.error import HTTPError
+    basestring = str  # NOQA
+    import csv  # NOQA
+    from itertools import zip_longest  # NOQA
+    from urllib.parse import urljoin, urlparse  # NOQA
+    from urllib.request import urlopen, Request  # NOQA
+    from urllib.error import HTTPError  # NOQA
 
 from license_expression import Licensing
 
@@ -67,7 +67,6 @@
 from attributecode.util import on_windows
 from attributecode.util import ungroup_licenses
 from attributecode.util import UNC_PREFIX
-from attributecode.util import UNC_PREFIX_POSIX
 
 
 class Field(object):
@@ -666,7 +665,7 @@ def __eq__(self, other):
                 and self.value == other.value)
 
 
-def validate_fields(fields, about_file_path, running_inventory, base_dir, 
+def validate_fields(fields, about_file_path, running_inventory, base_dir,
                     license_notice_text_location=None):
     """
     Validate a sequence of Field objects. Return a list of errors.
@@ -707,7 +706,7 @@ def create_fields(self):
         is simpler.
         """
         self.fields = OrderedDict([
-            #('about_resource', ListField(required=True)),
+            # ('about_resource', ListField(required=True)),
             # ('about_resource', AboutResourceField(required=True)),
             ('about_resource', AboutResourceField(required=True)),
             ('name', SingleLineField(required=True)),
@@ -874,29 +873,6 @@ def as_dict(self, with_paths=False, with_absent=True, with_empty=True):
         if with_paths:
             afpa = self.about_file_path_attr
             as_dict[afpa] = self.about_file_path
-            arpa = self.about_resource_path_attr
-            """
-            if self.about_resource_path.present:
-                as_dict[arpa] = self.resolved_resources_paths()
-            else:
-                arp = OrderedDict()
-                # Create a relative 'about_resource_path' if user has not defined
-                if self.about_resource.present:
-                    for resource_name in self.about_resource.value:
-                        key = u''
-                        if resource_name == '.':
-                            key = resource_name
-                        else:
-                            key = './' + resource_name
-                        arp[key] = None
-                        as_dict[arpa] = arp
-                # Return an empty 'about_resource_path' if the 'about_resource'
-                # key is not found
-                else:
-                    key = u''
-                    arp[key] = None
-                    as_dict[arpa] = arp
-            """
 
         for field in self.all_fields(with_absent=with_absent,
                                      with_empty=with_empty):
@@ -1050,9 +1026,9 @@ def load(self, location, use_mapping=False, mapping_file=None):
             and then join with the 'about_resource'
             """
             running_inventory = True
-            # wrap the value of the boolean field in quote to avoid 
+            # wrap the value of the boolean field in quote to avoid
             # automatically conversion from yaml.load
-            input = util.wrap_boolean_value(input_text)
+            input = util.wrap_boolean_value(input_text)  # NOQA
             errs = self.load_dict(saneyaml.load(input), base_dir, running_inventory, use_mapping, mapping_file)
             errors.extend(errs)
         except Exception as e:
@@ -1092,7 +1068,7 @@ def load_dict(self, fields_dict, base_dir, running_inventory=False,
                 licenses_field = (key, value)
                 fields.remove(licenses_field)
         errors = self.process(
-            fields, about_file_path, running_inventory, base_dir, 
+            fields, about_file_path, running_inventory, base_dir,
             license_notice_text_location, use_mapping, mapping_file)
         self.errors = errors
         return errors
@@ -1141,7 +1117,7 @@ def dumps(self, use_mapping=False, mapping_file=False, with_absent=False, with_e
             if lic_group[2]:
                 lic_dict['file'] = lic_group[2]
             if lic_group[3]:
-                lic_dict['url'] = lic_group[3] 
+                lic_dict['url'] = lic_group[3]
             about_data.setdefault('licenses', []).append(lic_dict)
         formatted_about_data = util.format_output(about_data, use_mapping, mapping_file)
         return saneyaml.dump(formatted_about_data)
@@ -1210,7 +1186,7 @@ def dump_lic(self, location, license_dict):
 # line in the form of "name: value"
 field_declaration = re.compile(
     r'^'
-    + field_name +
+    +field_name +
     r'\s*:\s*'
     r'(?P<value>.*)'
     r'\s*$'
@@ -1382,7 +1358,7 @@ def about_object_to_list_of_dictionary(abouts, with_absent=False, with_empty=Tru
     return abouts_dictionary_list
 
 
-def write_output(abouts, location, format, mapping_output=None, with_absent=False, with_empty=True):
+def write_output(abouts, location, format, mapping_output=None, with_absent=False, with_empty=True):  # NOQA
     """
     Write a CSV/JSON file at location given a list of About objects
     """

src/attributecode/saneyaml.py

@@ -34,12 +34,12 @@
 try:
     unicode  # Python 2
 except NameError:
-    unicode = str  # Python 3
+    unicode = str  # Python 3 #NOQA
 
 try:
     basestring  # Python 2
 except NameError:
-    basestring = str  # Python 3
+    basestring = str  # Python 3 #NOQA
 
 
 """

src/attributecode/util.py

@@ -34,12 +34,11 @@
 import sys
 
 if sys.version_info[0] < 3:  # Python 2
-    from itertools import izip_longest as zip_longest
+    from itertools import izip_longest as zip_longest  # NOQA
 else:  # Python 3
-    from itertools import zip_longest
+    from itertools import zip_longest  # NOQA
 
 
-import yaml
 from yaml.reader import Reader
 from yaml.scanner import Scanner
 from yaml.parser import Parser
@@ -50,10 +49,10 @@
 
 if sys.version_info[0] < 3:
     # Python 2
-    import backports.csv as csv
+    import backports.csv as csv  # NOQA
 else:
     # Python 3
-    import csv
+    import csv  # NOQA
 
 try:
     # Python 2
@@ -62,7 +61,7 @@
     # Python 3
     import http.client as httplib
 
-from attributecode import CRITICAL, INFO
+from attributecode import CRITICAL
 from attributecode import Error
 
 
@@ -159,7 +158,7 @@ def check_duplicate_keys_about_file(context):
 
 def wrap_boolean_value(context):
     bool_fields = ['redistribute', 'attribute', 'track_changes', 'modified']
-    input = []
+    input = []  # NOQA
     for line in context.splitlines():
         key = line.partition(':')[0]
         if key in bool_fields:
@@ -300,7 +299,7 @@ def __next__(self):
                 self.fieldnames
             row = next(self.reader)
             self.line_num = self.reader.line_num
-    
+
             # unlike the basic reader, we prefer not to return blanks,
             # because we will typically wind up with a dict full of None
             # values
@@ -381,6 +380,7 @@ def get_output_mapping(location):
         sys.exit(errno.EACCES)
     return mapping
 
+
 def apply_mapping(abouts, alternate_mapping=None):
     """
     Given a list of About data dictionaries and a dictionary of
@@ -422,6 +422,7 @@ def get_mapping_key_order(mapping_file):
         mapping = get_mapping()
     return mapping.keys()
 
+
 def format_output(about_data, use_mapping, mapping_file):
     """
     Convert the about_data dictionary to an ordered dictionary for saneyaml.dump()
@@ -459,6 +460,7 @@ def format_output(about_data, use_mapping, mapping_file):
                 order_dict[other_key] = about_data[other_key]
     return order_dict
 
+
 def get_about_file_path(location, use_mapping=False, mapping_file=None):
     """
     Read file at location, return a list of about_file_path.
@@ -497,10 +499,14 @@ def load_csv(location, use_mapping=False, mapping_file=None):
 
 def load_json(location, use_mapping=False, mapping_file=None):
     """
-    Read JSON at location, return a list of ordered mappings, one for each entry.
+    Read JSON file at `location` and return a list of ordered mappings, one for
+    each entry.
     """
+    # FIXME: IMHO we should know where the JSON is from and its shape
+    # TODO use: object_pairs_hook=OrderedDict
     with open(location) as json_file:
         results = json.load(json_file)
+
     # If the loaded JSON is not a list,
     # - JSON output from AboutCode Manager:
     # look for the "components" field as it is the field
@@ -542,20 +548,22 @@ def load_json(location, use_mapping=False, mapping_file=None):
     #    "name": "test",
     #    ...
     # }
-    if not isinstance(results, list):
+    if isinstance(results, list):
+        updated_results = sorted(results)
+    else:
         if u'aboutcode_manager_notice' in results:
             updated_results = results['components']
         elif u'scancode_notice' in results:
             updated_results = results['files']
         else:
             updated_results = [results]
-    else:
-        updated_results = sorted(results)
 
+    about_ordered_list = updated_results
+
+    # FIXME: why this double test? either have a mapping file and we use mapping or we do not.
+    # FIXME: IMHO only one argument is needed
     if use_mapping or mapping_file:
         about_ordered_list = apply_mapping(updated_results, mapping_file)
-    else:
-        about_ordered_list = updated_results
     return about_ordered_list
 
 
@@ -674,11 +682,11 @@ def inventory_filter(abouts, filter_dict):
 
 
 def update_fieldnames(fieldnames, mapping_output):
-    map = get_output_mapping(mapping_output)
+    mapping = get_output_mapping(mapping_output)
     updated_header = []
     for name in fieldnames:
         try:
-            updated_header.append(map[name])
+            updated_header.append(mapping[name])
         except:
             updated_header.append(name)
     return updated_header
@@ -701,6 +709,7 @@ def update_about_dictionary_keys(about_dictionary_list, mapping_output):
         updated_dict_list.append(updated_ordered_dict)
     return updated_dict_list
 
+
 def ungroup_licenses(licenses):
     """
     Ungroup multiple licenses information
@@ -785,7 +794,7 @@ def format_about_dict_for_json_output(about_dictionary_list):
                     lic_dict['file'] = lic_group[2]
                 if lic_group[3]:
                     lic_dict['url'] = lic_group[3]
-                licenses_list.append(lic_dict) 
+                licenses_list.append(lic_dict)
             row_list['licenses'] = licenses_list
         json_formatted_list.append(row_list)
     return json_formatted_list
@@ -837,4 +846,4 @@ def __init__(self, stream):
         Parser.__init__(self)
         Composer.__init__(self)
         NoDuplicateConstructor.__init__(self)
-        Resolver.__init__(self)
+        Resolver.__init__(self)