Replace OrderedDict with plain dict #295

dict is ordered by default in Python 3.6+

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

etc/scripts/genurlrules.py

@@ -24,7 +24,6 @@
 #  Visit https://github.com/nexB/scancode-toolkit/ for support and download.
 
 
-from collections import OrderedDict
 import os
 
 import click
@@ -113,7 +112,7 @@ def combine_expressions(expressions, relation='AND', licensing=Licensing()):
                 type(expressions)))
 
     # Remove duplicate element in the expressions list
-    expressions = OrderedDict((x, True) for x in expressions).keys()
+    expressions = dict((x, True) for x in expressions).keys()
 
     if len(expressions) == 1:
         return expressions[0]

etc/scripts/scancli.py

@@ -12,7 +12,6 @@
 # specific language governing permissions and limitations under the License.
 
 
-from collections import OrderedDict
 import json
 from os.path import abspath
 from os.path import dirname
@@ -59,7 +58,7 @@ def scan(locations, deserialize=False, scancode_root_dir=None):
         channel.send(scan_kwargs)  # execute func-call remotely
         results = channel.receive()
         if deserialize:
-            results = json.loads(results, object_pairs_hook=OrderedDict)
+            results = json.loads(results)
         yield results
 
 

etc/scripts/sch2js/sch2js.py

@@ -39,8 +39,7 @@
 """
 
 if __name__ == '__main__':
-    from collections import OrderedDict
-
+
     from six import iteritems
 
     from schematics.types.base import BaseType
@@ -76,7 +75,7 @@ def jsonschema_for_single_field(field_instance):
         """
         Return a mapping for the schema of a single field.
         """
-        field_schema = OrderedDict()
+        field_schema = {}
 
         field_schema['type'] = SCHEMATIC_TYPE_TO_JSON_TYPE.get(
             field_instance.__class__.__name__, 'string')
@@ -97,7 +96,7 @@ def jsonschema_for_fields(model):
         """
         Return a mapping for the schema of a collection of fields.
         """
-        properties = OrderedDict()
+        properties = {}
         required = []
         for field_name, field_instance in iteritems(model.fields):
             serialized_name = getattr(field_instance, 'serialized_name', None) or field_name
@@ -109,15 +108,15 @@ def jsonschema_for_fields(model):
                 try:
                     node = jsonschema_for_model(field_instance.model_class, 'array')
                     if hasattr(field_instance, 'metadata'):
-                        _node = OrderedDict()
+                        _node = {}
                         _node['type'] = node.pop('type')
                         _node['title'] = field_instance.metadata.get('label', '')
                         _node['description'] = field_instance.metadata.get('description', '')
                         _node.update(node)
                         node = _node
                 except AttributeError:
                     field_schema = jsonschema_for_single_field(field_instance.field)
-                    node = OrderedDict()
+                    node = {}
                     node['type'] = 'array'
                     if hasattr(field_instance, 'metadata'):
                         node['title'] = field_instance.metadata.get('label', '')
@@ -156,23 +155,23 @@ def jsonschema_for_model(model, _type='object'):
             schema_title = ''
             schema_description = ''
 
-        schema = OrderedDict([
-            ('type', 'object'),
-            ('title', schema_title),
-            ('description', schema_description),
-        ])
+        schema = {
+            'type': 'object',
+            'title': schema_title,
+            'description':schema_description,
+        }
 
         if required:
             schema['required'] = required
 
         if hasattr(model, '_schema_order'):
             ordered_properties = [(i, properties.pop(i)) for i in model._schema_order]
-            schema['properties'] = OrderedDict(ordered_properties)
+            schema['properties'] = dict(ordered_properties)
         else:
             schema['properties'] = properties
 
         if _type == 'array':
-            schema = OrderedDict([
+            schema = dict([
                 ('type', 'array'),
                 ('items', schema),
             ])
@@ -185,7 +184,7 @@ def to_jsonschema(model, **kwargs):
         Return a a JSON schema mapping for the `model` class.
         """
         schema_id = kwargs.pop('schema_id', '')
-        jsonschema = OrderedDict([
+        jsonschema = dict([
             ('$schema', 'http://json-schema.org/draft-04/schema#'),
             ('id', schema_id)
         ])

etc/scripts/synclic.py

@@ -24,7 +24,6 @@
 #  Visit https://github.com/nexB/scancode-toolkit/ for support and download.
 
 
-from collections import OrderedDict
 import io
 import json
 import os
@@ -316,7 +315,7 @@ def get_response(url, headers, params):
     status = response.status_code
     if status != requests.codes.ok:  # NOQA
         raise Exception('Failed HTTP request for %(url)r: %(status)r' % locals())
-    return response.json(object_pairs_hook=OrderedDict)
+    return response.json(object_pairs_hook=dict)
 
 
 def clean_text(text):
@@ -381,7 +380,7 @@ def fetch_licenses(self, scancode_licenses, from_repo=SPDX_DEFAULT_REPO):
                     # Skip the old plus licenses. We use them in
                     # ScanCode, but they are deprecated in SPDX.
                     continue
-                details = json.loads(archive.read(path), object_pairs_hook=OrderedDict)
+                details = json.loads(archive.read(path))
                 lic = self.build_license(details, scancode_licenses)
                 if lic:
                     yield lic
@@ -613,7 +612,7 @@ def call_deja_api(api_url, api_key, paginate=0, headers=None, params=None):
     params = params or {}
 
     def _get_results(response):
-        return response.json(object_pairs_hook=OrderedDict)
+        return response.json(object_pairs_hook=dict)
 
     if paginate:
         assert isinstance(paginate, int)
@@ -760,7 +759,7 @@ def get_owner(api_url, api_key, name):
 
 def license_to_dict(lico):
     """
-    Return an OrderedDict of license data with texts for API calls.
+    Return an dict of license data with texts for API calls.
     Fields with empty values are not included.
     """
     licm = dict(

src/cluecode/plugin_copyright.py

@@ -23,7 +23,6 @@
 #  Visit https://github.com/nexB/scancode-toolkit/ for support and download.
 
 
-from collections import OrderedDict
 
 import attr
 
@@ -39,7 +38,7 @@ class CopyrightScanner(ScanPlugin):
     Scan a Resource for copyrights.
     """
 
-    resource_attributes = OrderedDict([
+    resource_attributes = dict([
         ('copyrights',attr.ib(default=attr.Factory(list))),
         ('holders',attr.ib(default=attr.Factory(list))),
         ('authors',attr.ib(default=attr.Factory(list))),

src/formattedcode/output_csv.py

@@ -23,7 +23,6 @@
 #  Visit https://github.com/nexB/scancode-toolkit/ for support and download.
 
 
-from collections import OrderedDict
 
 import saneyaml
 from six import string_types
@@ -81,7 +80,7 @@ def write_csv(results, output_file):
     # FIXMe: this is reading all in memory
     results = list(results)
 
-    headers = OrderedDict([
+    headers = dict([
         ('info', []),
         ('license_expression', []),
         ('license', []),
@@ -132,7 +131,7 @@ def collect_keys(mapping, key_group):
 
         errors = scanned_file.pop('scan_errors', [])
 
-        file_info = OrderedDict(Resource=path)
+        file_info = dict(Resource=path)
         file_info.update(((k, v) for k, v in scanned_file.items()
         # FIXME: info are NOT lists: lists are the actual scans
                           if not isinstance(v, (list, dict))))
@@ -143,12 +142,12 @@ def collect_keys(mapping, key_group):
         yield file_info
 
         for lic_exp in scanned_file.get('license_expressions', []):
-            inf = OrderedDict(Resource=path, license_expression=lic_exp)
+            inf = dict(Resource=path, license_expression=lic_exp)
             collect_keys(inf, 'license_expression')
             yield inf
 
         for licensing in scanned_file.get('licenses', []):
-            lic = OrderedDict(Resource=path)
+            lic = dict(Resource=path)
             for k, val in licensing.items():
                 # do not include matched text for now.
                 if k == 'matched_text':
@@ -178,37 +177,37 @@ def collect_keys(mapping, key_group):
             yield lic
 
         for copyr in scanned_file.get('copyrights', []):
-            inf = OrderedDict(Resource=path)
+            inf = dict(Resource=path)
             inf['copyright'] = copyr['value']
             inf['start_line'] = copyr['start_line']
             inf['end_line'] = copyr['start_line']
             collect_keys(inf, 'copyright')
             yield inf
 
         for copyr in scanned_file.get('holders', []):
-            inf = OrderedDict(Resource=path)
+            inf = dict(Resource=path)
             inf['copyright_holder'] = copyr['value']
             inf['start_line'] = copyr['start_line']
             inf['end_line'] = copyr['start_line']
             collect_keys(inf, 'copyright')
             yield inf
 
         for copyr in scanned_file.get('authors', []):
-            inf = OrderedDict(Resource=path)
+            inf = dict(Resource=path)
             inf['author'] = copyr['value']
             inf['start_line'] = copyr['start_line']
             inf['end_line'] = copyr['start_line']
             collect_keys(inf, 'copyright')
             yield inf
 
         for email in scanned_file.get('emails', []):
-            email_info = OrderedDict(Resource=path)
+            email_info = dict(Resource=path)
             email_info.update(email)
             collect_keys(email_info, 'email')
             yield email_info
 
         for url in scanned_file.get('urls', []):
-            url_info = OrderedDict(Resource=path)
+            url_info = dict(Resource=path)
             url_info.update(url)
             collect_keys(url_info, 'url')
             yield url_info
@@ -227,7 +226,7 @@ def pretty(data):
     if not data:
         return None
     seqtypes = list, tuple
-    maptypes = OrderedDict, dict
+    maptypes = dict, dict
     coltypes = seqtypes + maptypes
     if isinstance(data, seqtypes):
         if len(data) == 1 and isinstance(data[0], string_types):
@@ -281,7 +280,7 @@ def flatten_package(_package, path, prefix='package__'):
 
     package_columns = get_package_columns()
 
-    pack = OrderedDict(Resource=path)
+    pack = dict(Resource=path)
     for k, val in _package.items():
         if k not in package_columns:
             continue

src/formattedcode/output_html.py

@@ -23,7 +23,6 @@
 #  Visit https://github.com/nexB/scancode-toolkit/ for support and download.
 
 
-from collections import OrderedDict
 import io
 from operator import itemgetter
 from os.path import abspath
@@ -162,9 +161,9 @@ def generate_output(results, version, template):
 
     from licensedcode.cache import get_licenses_db
 
-    converted = OrderedDict()
-    converted_infos = OrderedDict()
-    converted_packages = OrderedDict()
+    converted = {}
+    converted_infos = {}
+    converted_packages = {}
     licenses = {}
 
     LICENSES = 'licenses'
@@ -175,7 +174,7 @@ def generate_output(results, version, template):
 
     # Create a flattened data dict keyed by path
     for scanned_file in results:
-        scanned_file = OrderedDict(scanned_file)
+        scanned_file = dict(scanned_file)
         path = scanned_file['path']
         results = []
         if COPYRIGHTS in scanned_file:
@@ -210,7 +209,7 @@ def generate_output(results, version, template):
         # should rather just pass a the list of files from the scan
         # results and let the template handle this rather than
         # denormalizing the list here??
-        converted_infos[path] = OrderedDict()
+        converted_infos[path] = {}
         for name, value in scanned_file.items():
             if name in (LICENSES, PACKAGES, COPYRIGHTS, EMAILS, URLS):
                 continue
@@ -219,7 +218,7 @@ def generate_output(results, version, template):
         if PACKAGES in scanned_file:
             converted_packages[path] = scanned_file[PACKAGES]
 
-        licenses = OrderedDict(sorted(licenses.items()))
+        licenses = dict(sorted(licenses.items()))
 
     files = {
         'license_copyright': converted,

src/formattedcode/output_json.py

@@ -23,7 +23,6 @@
 #  Visit https://github.com/nexB/scancode-toolkit/ for support and download.
 
 
-from collections import OrderedDict
 
 import jsonstreams
 from six import string_types
@@ -144,7 +143,7 @@ def get_results(codebase, as_list=False, **kwargs):
     """
 
     codebase.add_files_count_to_current_header()
-    results = OrderedDict([('headers', codebase.get_headers()), ])
+    results = dict([('headers', codebase.get_headers()), ])
 
     # add codebase toplevel attributes such as summaries
     if codebase.attributes:

src/formattedcode/output_jsonlines.py

@@ -23,7 +23,6 @@
 #  Visit https://github.com/nexB/scancode-toolkit/ for support and download.
 
 
-from collections import OrderedDict
 
 import simplejson
 
@@ -60,7 +59,7 @@ def process_codebase(self, codebase, output_json_lines, **kwargs):
 
         codebase.add_files_count_to_current_header()
 
-        headers = OrderedDict(headers=codebase.get_headers())
+        headers = dict(headers=codebase.get_headers())
 
         simplejson_kwargs = dict(
             iterable_as_array=True,

src/licensedcode/models.py

@@ -25,7 +25,6 @@
 
 from collections import Counter
 from collections import defaultdict
-from collections import OrderedDict
 from functools import partial
 from itertools import chain
 import io
@@ -218,7 +217,7 @@ def text(self):
 
     def to_dict(self):
         """
-        Return an OrderedDict of license data (excluding texts).
+        Return an dict of license data (excluding texts).
         Fields with empty values are not included.
         """
 
@@ -238,7 +237,7 @@ def dict_fields(attr, value):
                 return False
             return True
 
-        data = attr.asdict(self, filter=dict_fields, dict_factory=OrderedDict)
+        data = attr.asdict(self, filter=dict_fields, dict_factory=dict)
         cv = data.get('minimum_coverage')
         if cv and isinstance(cv, float) and int(cv) == cv:
             cv = int(cv)
@@ -934,7 +933,7 @@ def to_dict(self):
         Return an ordered mapping of self, excluding texts. Used for
         serialization. Empty values are not included.
         """
-        data = OrderedDict()
+        data = {}
         if self.license_expression:
             data['license_expression'] = self.license_expression