global: add pre-commit with ruff

.pre-commit-config.yaml

@@ -0,0 +1,17 @@
+repos:
+  - repo: https://github.com/pre-commit/pre-commit-hooks
+    rev: v4.6.0
+    hooks:
+      - id: check-yaml
+      - id: end-of-file-fixer
+      - id: trailing-whitespace
+      - id: fix-byte-order-marker
+      - id: mixed-line-ending
+      - id: name-tests-test
+        args: [ --pytest-test-first ]
+        exclude: '^(?!factories/)'
+  - repo: https://github.com/astral-sh/ruff-pre-commit
+    rev: v0.5.6
+    hooks:
+      - id: ruff
+        args: [ --fix ]

inspire_dojson/__init__.py

@@ -24,8 +24,8 @@
 
 from __future__ import absolute_import, division, print_function
 
-from . import common  # noqa: F401
-from .api import marcxml2record, record2marcxml  # noqa: F401
-from .errors import DoJsonError  # noqa: F401
+from inspire_dojson import common  # noqa: F401
+from inspire_dojson.api import marcxml2record, record2marcxml  # noqa: F401
+from inspire_dojson.errors import DoJsonError  # noqa: F401
 
 __version__ = "63.2.22"

inspire_dojson/api.py

@@ -28,34 +28,34 @@
 import re
 from itertools import chain
 
+from dojson.contrib.marc21.utils import create_record
+from inspire_utils.helpers import force_list
+from inspire_utils.record import get_value
 from lxml.builder import E
 from lxml.etree import tostring
 from six import iteritems, text_type, unichr
 from six.moves import urllib
 
-from dojson.contrib.marc21.utils import create_record
-
+from inspire_dojson.cds import cds2hep_marc
+from inspire_dojson.conferences import conferences
+from inspire_dojson.data import data
+from inspire_dojson.errors import NotSupportedError
+from inspire_dojson.experiments import experiments
+from inspire_dojson.hep import hep, hep2marc
+from inspire_dojson.hepnames import hepnames, hepnames2marc
+from inspire_dojson.institutions import institutions
+from inspire_dojson.journals import journals
 from inspire_dojson.utils import create_record_from_dict, force_single_element
-from inspire_utils.helpers import force_list
-from inspire_utils.record import get_value
-
-from .cds import cds2hep_marc
-from .conferences import conferences
-from .data import data
-from .errors import NotSupportedError
-from .experiments import experiments
-from .hep import hep, hep2marc
-from .hepnames import hepnames, hepnames2marc
-from .institutions import institutions
-from .journals import journals
 
 try:
     unichr(0x100000)
     RE_INVALID_CHARS_FOR_XML = re.compile(
-        u'[^\U00000009\U0000000A\U0000000D\U00000020-\U0000D7FF\U0000E000-\U0000FFFD\U00010000-\U0010FFFF]+')
+        u'[^\U00000009\U0000000A\U0000000D\U00000020-\U0000D7FF\U0000E000-\U0000FFFD\U00010000-\U0010FFFF]+'
+    )
 except ValueError:  # pragma: no cover
     RE_INVALID_CHARS_FOR_XML = re.compile(
-        u'[^\U00000009\U0000000A\U0000000D\U00000020-\U0000D7FF\U0000E000-\U0000FFFD]+')
+        u'[^\U00000009\U0000000A\U0000000D\U00000020-\U0000D7FF\U0000E000-\U0000FFFD]+'
+    )
 
 RECORD = E.record
 CONTROLFIELD = E.controlfield
@@ -107,7 +107,9 @@ def record2marcxml_etree(record):
     elif schema_name == 'authors':
         marcjson = hepnames2marc.do(record)
     else:
-        raise NotSupportedError(u'JSON -> MARC rules missing for "{}"'.format(schema_name))
+        raise NotSupportedError(
+            u'JSON -> MARC rules missing for "{}"'.format(schema_name)
+        )
 
     record = RECORD()
 
@@ -117,15 +119,19 @@ def record2marcxml_etree(record):
             value = force_single_element(values)
             if not isinstance(value, text_type):
                 value = text_type(value)
-            record.append(CONTROLFIELD(_strip_invalid_chars_for_xml(value), {'tag': tag}))
+            record.append(
+                CONTROLFIELD(_strip_invalid_chars_for_xml(value), {'tag': tag})
+            )
         else:
             for value in force_list(values):
                 datafield = DATAFIELD({'tag': tag, 'ind1': ind1, 'ind2': ind2})
                 for code, els in sorted(iteritems(value)):
                     for el in force_list(els):
                         if not isinstance(el, text_type):
                             el = text_type(el)
-                        datafield.append(SUBFIELD(_strip_invalid_chars_for_xml(el), {'code': code}))
+                        datafield.append(
+                            SUBFIELD(_strip_invalid_chars_for_xml(el), {'code': code})
+                        )
                 record.append(datafield)
 
     return record
@@ -155,7 +161,9 @@ def cds_marcxml2record(marcxml):
 
 
 def _get_collections(marcjson):
-    collections = chain.from_iterable([force_list(el) for el in force_list(get_value(marcjson, '980__.a'))])
+    collections = chain.from_iterable(
+        [force_list(el) for el in force_list(get_value(marcjson, '980__.a'))]
+    )
     normalized_collections = [el.lower() for el in collections]
 
     return normalized_collections

inspire_dojson/cds/__init__.py

@@ -24,5 +24,5 @@
 
 from __future__ import absolute_import, division, print_function
 
-from . import rules  # noqa: F401
-from .model import cds2hep_marc  # noqa: F401
+from inspire_dojson.cds import rules  # noqa: F401
+from inspire_dojson.cds.model import cds2hep_marc  # noqa: F401

inspire_dojson/cds/model.py

@@ -25,28 +25,35 @@
 from __future__ import absolute_import, division, print_function
 
 from itertools import chain
-from inspire_utils.record import get_value
+
 from inspire_utils.helpers import force_list
+from inspire_utils.record import get_value
 
-from ..model import FilterOverdo, clean_record
+from inspire_dojson.model import FilterOverdo, clean_record
 
 
 def add_control_number(record, blob):
     if '001' not in blob:
         return record
 
-    collections = (value.lower() for value in chain(force_list(get_value(blob, '980__.a', default=[])),
-                                                    force_list(get_value(blob, '980__.c', default=[]))))
+    collections = (
+        value.lower()
+        for value in chain(
+            force_list(get_value(blob, '980__.a', default=[])),
+            force_list(get_value(blob, '980__.c', default=[])),
+        )
+    )
     if 'hidden' in collections:
-        record.setdefault('595__', []).append({
-            '9': 'CDS',
-            'a': u'CDS-{}'.format(blob['001'])
-        })
+        record.setdefault('595__', []).append(
+            {'9': 'CDS', 'a': u'CDS-{}'.format(blob['001'])}
+        )
     else:
-        record.setdefault('035__', []).append({
-            '9': 'CDS',
-            'a': blob['001'],
-        })
+        record.setdefault('035__', []).append(
+            {
+                '9': 'CDS',
+                'a': blob['001'],
+            }
+        )
 
     return record