From 36c7e2dd9f49b5979c559ad12b72dd29d1bdb064 Mon Sep 17 00:00:00 2001
From: PascalEgn <pascal.egner@googlemail.com>
Date: Mon, 5 Aug 2024 17:57:06 +0200
Subject: [PATCH] global: format to <100 line-width

---
 inspire_utils/config.py             |   6 +-
 inspire_utils/date.py               |  49 ++++---
 inspire_utils/dedupers.py           |  10 +-
 inspire_utils/helpers.py            |  14 +-
 inspire_utils/logging.py            |   6 +-
 inspire_utils/name.py               | 209 ++++++++++++++++++----------
 inspire_utils/parsers/arxiv.py      | 129 ++++++++++-------
 inspire_utils/parsers/author_xml.py |  22 +--
 inspire_utils/parsers/crossref.py   |  13 +-
 inspire_utils/parsers/elsevier.py   |  61 ++++----
 inspire_utils/parsers/jats.py       | 115 ++++++++-------
 inspire_utils/query.py              |  19 +--
 inspire_utils/record.py             |  11 +-
 inspire_utils/urls.py               |   3 +-
 inspire_utils/utils.py              |  18 +--
 ruff.toml                           |   3 +-
 tests/test_config.py                |  15 +-
 tests/test_date.py                  |   4 +-
 tests/test_helpers.py               |   9 +-
 tests/test_name.py                  |  61 ++++----
 tests/test_parsers_arxiv.py         |  16 ++-
 tests/test_parsers_crossref.py      |  33 +++--
 tests/test_parsers_elsevier.py      |  39 +++---
 tests/test_parsers_jats.py          |  25 ++--
 tests/test_record.py                |   4 +-
 tests/test_urls.py                  |   4 +-
 26 files changed, 533 insertions(+), 365 deletions(-)

diff --git a/inspire_utils/config.py b/inspire_utils/config.py
index e323fad..66d162f 100644
--- a/inspire_utils/config.py
+++ b/inspire_utils/config.py
@@ -19,7 +19,6 @@
 # In applying this license, CERN does not waive the privileges and immunities
 # granted to it by virtue of its status as an Intergovernmental Organization
 # or submit itself to any jurisdiction.
-
 """INSPIRE configuration loader.
 
 Inspired by the Flask configuration loader:
@@ -47,10 +46,7 @@ def __init__(self, file_path, cause):
             cause (string): reason of failure, i.e. what exactly was the
                 problem while parsing
         """
-        message = six.text_type("Malformed config at {}: {}").format(
-            file_path,
-            cause
-        )
+        message = six.text_type("Malformed config at {}: {}").format(file_path, cause)
         super(MalformedConfig, self).__init__(message)
 
 
diff --git a/inspire_utils/date.py b/inspire_utils/date.py
index 4216579..70ad648 100644
--- a/inspire_utils/date.py
+++ b/inspire_utils/date.py
@@ -19,7 +19,6 @@
 # In applying this license, CERN does not waive the privileges and immunities
 # granted to it by virtue of its status as an Intergovernmental Organization
 # or submit itself to any jurisdiction.
-
 """Utils to handle dates in INSPIRE."""
 
 from __future__ import absolute_import, division, print_function
@@ -48,13 +47,18 @@ class PartialDate(object):
     Raises:
         TypeError: when the date parts are not `int` s or `None`.
         ValueError: when the date is not valid.
-
     """
+
     def __init__(self, year, month=None, day=None):
-        well_typed = all(isinstance(part, int) or part is None for part in (year, month, day))
+        well_typed = all(
+            isinstance(part, int) or part is None for part in (year, month, day)
+        )
         if not well_typed:
-            raise TypeError(u'arguments to {classname} must be of type int or None'.format(
-                classname=type(self).__name__))
+            raise TypeError(
+                u'arguments to {classname} must be of type int or None'.format(
+                    classname=type(self).__name__
+                )
+            )
         if year is None or year < 1000:
             raise ValueError('year must be an int >= 1000')
         if day and not month:
@@ -68,10 +72,18 @@ def __init__(self, year, month=None, day=None):
         self.day = day
 
     def __repr__(self):
-        return u'PartialDate(year={self.year}, month={self.month}, day={self.day})'.format(self=self)
+        return (
+            u'PartialDate(year={self.year}, month={self.month}, day={self.day})'.format(
+                self=self
+            )
+        )
 
     def __eq__(self, other):
-        return self.year == other.year and self.month == other.month and self.day == other.day
+        return (
+            self.year == other.year
+            and self.month == other.month
+            and self.day == other.day
+        )
 
     def __lt__(self, other):
         self_month = self.month or 99
@@ -97,7 +109,6 @@ def loads(cls, string):
             Traceback (most recent call last):
             ...
             ValueError: month must be in 1..12
-
         """
 
         date_parts = string.split('-')
@@ -116,7 +127,6 @@ def dumps(self):
         Returns:
             str: normalized date, in the form ``YYYY-MM-DD``, ``YYYY-MM`` or
                 ``YYYY`` (depending on the information present in the date)
-
         """
         non_empty = itertools.takewhile(bool, (self.year, self.month, self.day))
         # XXX: this only handles dates after 1000, which should be sufficient
@@ -147,7 +157,6 @@ def parse(cls, date, **kwargs):
         Examples:
             >>> PartialDate.parse('30 Jun 1686')
             PartialDate(year=1686, month=6, day=30)
-
         """
         # In order to detect partial dates, parse twice with different defaults
         # and compare the results.
@@ -180,7 +189,6 @@ def from_parts(cls, year, month=None, day=None):
         Examples:
             >>> PartialDate.from_parts('1686', 'June', '30')
             PartialDate(year=1686, month=6, day=30)
-
         """
         # XXX: 0 is not a valid year/month/day
         non_empty = itertools.takewhile(
@@ -194,13 +202,18 @@ def pprint(self):
         Examples:
             >>> PartialDate(1686, 6, 30).pprint()
             u'Jun 30, 1686'
-
         """
         if not self.month:
-            return dates.format_date(datetime.date(self.year, 1, 1), 'yyyy', locale='en')
+            return dates.format_date(
+                datetime.date(self.year, 1, 1), 'yyyy', locale='en'
+            )
         if not self.day:
-            return dates.format_date(datetime.date(self.year, self.month, 1), 'MMM, yyyy', locale='en')
-        return dates.format_date(datetime.date(self.year, self.month, self.day), 'MMM d, yyyy', locale='en')
+            return dates.format_date(
+                datetime.date(self.year, self.month, 1), 'MMM, yyyy', locale='en'
+            )
+        return dates.format_date(
+            datetime.date(self.year, self.month, self.day), 'MMM d, yyyy', locale='en'
+        )
 
 
 def normalize_date(date, **kwargs):
@@ -232,7 +245,6 @@ def normalize_date(date, **kwargs):
         >>> normalize_date(None)
         >>> normalize_date('30 Jun 1686')
         '1686-06-30'
-
     """
     if date is None:
         return
@@ -265,7 +277,10 @@ def earliest_date(dates):
 
 
 def fill_missing_date_parts(date):
-    """Sets missing day and/or month to 1. Useful to avoid errors when saving to DB."""
+    """Sets missing day and/or month to 1.
+
+    Useful to avoid errors when saving to DB.
+    """
 
     if date is None:
         return
diff --git a/inspire_utils/dedupers.py b/inspire_utils/dedupers.py
index d15edbb..f559a85 100644
--- a/inspire_utils/dedupers.py
+++ b/inspire_utils/dedupers.py
@@ -28,8 +28,8 @@
 def dedupe_list(list_with_duplicates):
     """Remove duplicates from a list preserving the order.
 
-    We might be tempted to use the list(set(l)) idiom, but it doesn't preserve
-    the order, which hinders testability.
+    We might be tempted to use the list(set(l)) idiom, but it doesn't
+    preserve the order, which hinders testability.
     """
     result = []
 
@@ -43,9 +43,11 @@ def dedupe_list(list_with_duplicates):
 def dedupe_list_of_dicts(ld):
     """Remove duplicates from a list of dictionaries preserving the order.
 
-    We can't use the generic list helper because a dictionary isn't hashable.
-    Adapted from http://stackoverflow.com/a/9427216/374865.
+    We can't use the generic list helper because a dictionary isn't
+    hashable. Adapted from
+    http://stackoverflow.com/a/9427216/374865.
     """
+
     def _freeze(o):
         """Recursively freezes a dict into an hashable object.
 
diff --git a/inspire_utils/helpers.py b/inspire_utils/helpers.py
index 36078c7..260caa2 100644
--- a/inspire_utils/helpers.py
+++ b/inspire_utils/helpers.py
@@ -58,7 +58,6 @@ def force_list(data):
         ['foo', 'bar']
         >>> force_list(['foo', 'bar', 'baz'])
         ['foo', 'bar', 'baz']
-
     """
     if data is None:
         return []
@@ -81,7 +80,6 @@ def maybe_float(el):
     Examples:
         >>> maybe_float('35.0499505')
         35.0499505
-
     """
     try:
         return float(el)
@@ -101,7 +99,6 @@ def maybe_int(el):
     Examples:
         >>> maybe_int('10')
         10
-
     """
     try:
         return int(el)
@@ -132,7 +129,8 @@ def remove_tags(dirty, allowed_tags=(), allowed_trees=(), strip=None):
         removed.
 
     Examples:
-        >>> tag = '<p><b><i>Only</i></b> this text remains.<span class="hidden">Not this one.</span></p>'
+        >>> tag = '<p><b><i>Only</i></b> this text remains.
+        <span class="hidden">Not this one.</span></p>'
         >>> remove_tags(tag, allowed_tree=('b',), strip='@class="hidden"')
         u'<b><i>Only</i></b> this text remains.'
         >>> remove_tags(tag, allowed_tags=('b',), strip='@class="hidden"')
@@ -141,7 +139,9 @@ def remove_tags(dirty, allowed_tags=(), allowed_trees=(), strip=None):
         u'<b>Only</b> this text remains.'
     """
     if isinstance(dirty, six.string_types):
-        element = etree.fromstring(u''.join(('<DUMMYROOTTAG>', dirty, '</DUMMYROOTTAG>')))
+        element = etree.fromstring(
+            u''.join(('<DUMMYROOTTAG>', dirty, '</DUMMYROOTTAG>'))
+        )
     elif isinstance(dirty, etree._Element):
         element = dirty
     else:  # assuming scrapy Selector
@@ -156,7 +156,9 @@ def remove_tags(dirty, allowed_tags=(), allowed_trees=(), strip=None):
         return tail
 
     subtext = u''.join(
-        remove_tags(child, allowed_tags=allowed_tags, allowed_trees=allowed_trees, strip=strip)
+        remove_tags(
+            child, allowed_tags=allowed_tags, allowed_trees=allowed_trees, strip=strip
+        )
         for child in element
     )
     text = element.text or u''
diff --git a/inspire_utils/logging.py b/inspire_utils/logging.py
index da252ae..16ef9be 100644
--- a/inspire_utils/logging.py
+++ b/inspire_utils/logging.py
@@ -36,13 +36,15 @@ def __getattr__(self, item):
     def error(self, message, *args, **kwargs):
         """Log error with stack trace and locals information.
 
-        By default, enables stack trace information in logging messages, so that stacktrace and locals appear in Sentry.
+        By default, enables stack trace information in logging messages,
+        so that stacktrace and locals appear in Sentry.
         """
         kwargs.setdefault('extra', {}).setdefault('stack', True)
         return self.logger.error(message, *args, **kwargs)
 
 
 def getStackTraceLogger(*args, **kwargs):
-    """Returns a :class:`StackTrace` logger that wraps a Python logger instance."""
+    """Returns a :class:`StackTrace` logger that wraps a Python logger
+    instance."""
     logger = logging.getLogger(*args, **kwargs)
     return StackTraceLogger(logger)
diff --git a/inspire_utils/name.py b/inspire_utils/name.py
index 9fe5624..b883d08 100644
--- a/inspire_utils/name.py
+++ b/inspire_utils/name.py
@@ -38,20 +38,45 @@
 
 _LASTNAME_NON_LASTNAME_SEPARATORS = [u' ', u', ']
 _NAMES_MAX_NUMBER_THRESHOLD = 5
-"""Threshold for skipping the combinatorial expansion of names (when generating name variations). """
+"""Threshold for skipping the combinatorial expansion of names (when generating
+name variations)."""
 
 
 def _prepare_nameparser_constants():
     """Prepare nameparser Constants.
 
-    Remove nameparser's titles and use our own and add as suffixes the roman numerals.
-    Configuration is the same for all names (i.e. instances).
+    Remove nameparser's titles and use our own and add as suffixes the
+    roman numerals. Configuration is the same for all names (i.e.
+    instances).
     """
     constants = Constants()
-    roman_numeral_suffixes = [u'vi', u'vii', u'viii', u'ix', u'x', u'xi',
-                              u'xii', u'xiii', u'xiv', u'xv']
-    titles = [u'Dr', u'Prof', u'Professor', u'Sir', u'Editor', u'Ed', u'Mr',
-              u'Mrs', u'Ms', u'Chair', u'Co-Chair', u'Chairs', u'co-Chairs']
+    roman_numeral_suffixes = [
+        u'vi',
+        u'vii',
+        u'viii',
+        u'ix',
+        u'x',
+        u'xi',
+        u'xii',
+        u'xiii',
+        u'xiv',
+        u'xv',
+    ]
+    titles = [
+        u'Dr',
+        u'Prof',
+        u'Professor',
+        u'Sir',
+        u'Editor',
+        u'Ed',
+        u'Mr',
+        u'Mrs',
+        u'Ms',
+        u'Chair',
+        u'Co-Chair',
+        u'Chairs',
+        u'co-Chairs',
+    ]
     constants.titles.remove(*constants.titles).add(*titles)
     constants.suffix_not_acronyms.add(*roman_numeral_suffixes)
     constants.suffixes_prefixes_titles.remove(*constants.suffixes_prefixes_titles)
@@ -65,15 +90,18 @@ class ParsedName(object):
     After construction, the instance exposes the fields exposed by `HumanName` instance, i.e.
     `title`, `first`, `middle`, `last`, `suffix`.
     """
+
     constants = _prepare_nameparser_constants()
-    """The default constants configuration for `HumanName` to use for parsing all names."""
+    """The default constants configuration for `HumanName` to use for parsing
+    all names."""
 
     def __init__(self, name, constants=None, without_titles=False):
         """Create a ParsedName instance.
 
         Args:
             name (Union[str, HumanName]): The name to be parsed (must be non empty nor None).
-            constants (:class:`nameparser.config.Constants`): Configuration for `HumanName` instantiation.
+            constants (:class:`nameparser.config.Constants`): Configuration
+                for `HumanName` instantiation.
                 (Can be None, if provided it overwrites the default one generated in
                 :method:`prepare_nameparser_constants`.)
         """
@@ -93,7 +121,9 @@ def __init__(self, name, constants=None, without_titles=False):
 
             self._parsed_name.capitalize()
 
-        if ',' not in name and (not self.first_list or (self.first_list and '.' not in self.first_list[-1])):
+        if ',' not in name and (
+            not self.first_list or (self.first_list and '.' not in self.first_list[-1])
+        ):
             self.maybe_only_last_name = True
         else:
             self.maybe_only_last_name = False
@@ -116,18 +146,26 @@ def first_initials(self):
 
     @property
     def first(self):
-        name = u'{} {}'.format(self._parsed_name.first, self._parsed_name.middle).strip()
+        name = u'{} {}'.format(
+            self._parsed_name.first, self._parsed_name.middle
+        ).strip()
         return name.strip('.')
 
     @property
     def first_initials_list(self):
-        names_no_dash_list = itertools.chain.from_iterable(name.split("-") for name in self.first_list)
-        names_split_on_dot = itertools.chain.from_iterable(name.split('.') for name in names_no_dash_list)
+        names_no_dash_list = itertools.chain.from_iterable(
+            name.split("-") for name in self.first_list
+        )
+        names_split_on_dot = itertools.chain.from_iterable(
+            name.split('.') for name in names_no_dash_list
+        )
         return [(name[0] + u'.') for name in names_split_on_dot if name]
 
     @property
     def first_list(self):
-        first_and_middle_names = self._parsed_name.first_list + self._parsed_name.middle_list
+        first_and_middle_names = (
+            self._parsed_name.first_list + self._parsed_name.middle_list
+        )
         names = [name for name in first_and_middle_names if name and name != '.']
         return names
 
@@ -156,9 +194,11 @@ def loads(cls, name):
             ValueError: when name is empty or None.
         """
         if not isinstance(name, six.string_types):
-            raise TypeError(u'arguments to {classname} must be of type {string_types}'.format(
-                classname=cls.__name__, string_types=repr(six.string_types)
-            ))
+            raise TypeError(
+                u'arguments to {classname} must be of type {string_types}'.format(
+                    classname=cls.__name__, string_types=repr(six.string_types)
+                )
+            )
         if not name or name.isspace():
             raise ValueError('name must not be empty')
 
@@ -166,12 +206,12 @@ def loads(cls, name):
 
     def dumps(self):
         """Dump the name to string, after normalizing it."""
+
         def _is_initial(author_name):
             return len(author_name) == 1 or u'.' in author_name
 
         def _ensure_dotted_initials(author_name):
-            if _is_initial(author_name) \
-                    and u'.' not in author_name:
+            if _is_initial(author_name) and u'.' not in author_name:
                 seq = (author_name, u'.')
                 author_name = u''.join(seq)
             return author_name
@@ -183,20 +223,30 @@ def _ensure_dotted_suffixes(author_suffix):
             return author_suffix
 
         def _is_roman_numeral(suffix):
-            """Controls that the user's input only contains valid roman numerals"""
-            valid_roman_numerals = [u'M', u'D', u'C', u'L', u'X',
-                                    u'V', u'I', u'(', u')']
-            return all(letters in valid_roman_numerals
-                       for letters in suffix.upper())
-
-        first_and_middle_names = iter(_ensure_dotted_initials(name) for name in self.first_list)
+            """Controls that the user's input only contains valid roman
+            numerals."""
+            valid_roman_numerals = [
+                u'M',
+                u'D',
+                u'C',
+                u'L',
+                u'X',
+                u'V',
+                u'I',
+                u'(',
+                u')',
+            ]
+            return all(letters in valid_roman_numerals for letters in suffix.upper())
+
+        first_and_middle_names = iter(
+            _ensure_dotted_initials(name) for name in self.first_list
+        )
 
         try:
             prev = next(first_and_middle_names)
             names_with_spaces = [prev]
         except StopIteration:
-            LOGGER.warning(u"Cannot process %s properly",
-                           self._parsed_name.original)
+            LOGGER.warning(u"Cannot process %s properly", self._parsed_name.original)
             names_with_spaces = []
 
         for name in first_and_middle_names:
@@ -213,8 +263,8 @@ def _is_roman_numeral(suffix):
             suffix = _ensure_dotted_suffixes(self.suffix)
 
         final_name = u', '.join(
-            part for part in (self.last, normalized_names.strip(), suffix)
-            if part)
+            part for part in (self.last, normalized_names.strip(), suffix) if part
+        )
 
         # Replace unicode curly apostrophe to normal apostrophe.
         final_name = final_name.replace(u'’', '\'')
@@ -235,27 +285,16 @@ def pprint(self, initials_only=False):
             u'S. M. Lieber'
             >>> ParsedName('Downey, Robert Jr.').pprint(initials_only=True)
             u'R. Downey Jr.'
-
         """
         last_name = self.last
         suffixes = ', ' + self.suffix if self.suffix else ''
 
-        if initials_only and last_name != u'':
-            first_names = self.first_initials
-        else:
-            first_names = self.first
+        first_names = self.first_initials if initials_only and last_name != u'' else self.first
 
         return u'{} {}{}'.format(first_names, last_name, suffixes).strip()
 
     @classmethod
-    def from_parts(
-        cls,
-        first=None,
-        last=None,
-        middle=None,
-        suffix=None,
-        title=None
-    ):
+    def from_parts(cls, first=None, last=None, middle=None, suffix=None, title=None):
         name = HumanName()
         name.first = first
         name.middle = middle
@@ -266,16 +305,19 @@ def from_parts(
 
     def generate_es_query(self, keyword="authors"):
         """Generates a query handling specifically authors.
+
         Notes:
             There are three main cases:
             1) ``a Smith``
             This will just generate a ``match`` query on ``last_name``
             2) ``a John Smith``
-             This will just generate a ``match`` query on ``last_name`` and  a ``prefix`` query on ``first_name``
-             and a ``match`` query on the initial ``J``. This will return results from ``Smith, John`` and ``Smith, J``
+             This will just generate a ``match`` query on ``last_name`` and  a ``prefix``
+             query on ``first_name`` and a ``match`` query on the initial ``J``.
+             This will return results from ``Smith, John`` and ``Smith, J``
              but not from ``Smith, Jane``.
             3) ``a J Smith``
-            This will just generate a ``match`` query on ``last_name`` and a match query on ``first_name.initials``.
+            This will just generate a ``match`` query on ``last_name`` and a match
+            query on ``first_name.initials``.
             Please note, cases such as ``J.D.`` have been properly handled by the tokenizer.
         """
         nested_query = {
@@ -381,9 +423,8 @@ def normalize_name(name):
 def _generate_non_lastnames_variations(non_lastnames):
     """Generate variations for all non-lastnames.
 
-    E.g. For 'John Richard', this method generates: [
-        'John', 'J', 'Richard', 'R', 'John Richard', 'John R', 'J Richard', 'J R',
-    ]
+    E.g. For 'John Richard', this method generates: [     'John', 'J',
+    'Richard', 'R', 'John Richard', 'John R', 'J Richard', 'J R', ]
     """
     if not non_lastnames:
         return []
@@ -411,12 +452,18 @@ def _generate_lastnames_variations(lastnames):
     if not lastnames:
         return []
 
-    split_lastnames = [split_lastname for lastname in lastnames for split_lastname in lastname.split('-')]
+    split_lastnames = [
+        split_lastname
+        for lastname in lastnames
+        for split_lastname in lastname.split('-')
+    ]
 
     lastnames_variations = split_lastnames
     if len(split_lastnames) > 1:
         # Generate lastnames concatenation if there are more than one lastname after split.
-        lastnames_variations.append(u' '.join([lastname for lastname in split_lastnames]))
+        lastnames_variations.append(
+            u' '.join([lastname for lastname in split_lastnames])
+        )
 
     return lastnames_variations
 
@@ -431,19 +478,23 @@ def generate_name_variations(name):
         list: All the name variations for the given name.
 
     Notes:
-        Uses `unidecode` for doing unicode characters transliteration to ASCII ones. This was chosen so that we can map
-        both full names of authors in HEP records and user's input to the same space and thus make exact queries work.
+        Uses `unidecode` for doing unicode characters transliteration to ASCII ones.
+        This was chosen so that we can map both full names of authors in HEP records
+        and user's input to the same space and thus make exact queries work.
     """
+
     def _update_name_variations_with_product(set_a, set_b):
-        name_variations.update([
-            unidecode((names_variation[0] +
-                       separator +
-                       names_variation[1]).strip(''.join(_LASTNAME_NON_LASTNAME_SEPARATORS))).lower()
-            for names_variation
-            in product(set_a, set_b)
-            for separator
-            in _LASTNAME_NON_LASTNAME_SEPARATORS
-        ])
+        name_variations.update(
+            [
+                unidecode(
+                    (names_variation[0] + separator + names_variation[1]).strip(
+                        ''.join(_LASTNAME_NON_LASTNAME_SEPARATORS)
+                    )
+                ).lower()
+                for names_variation in product(set_a, set_b)
+                for separator in _LASTNAME_NON_LASTNAME_SEPARATORS
+            ]
+        )
 
     parsed_name = ParsedName.loads(name)
 
@@ -453,27 +504,32 @@ def _update_name_variations_with_product(set_a, set_b):
 
     name_variations = set()
 
-    # We need to filter out empty entries, since HumanName for this name `Perelstein,, Maxim` returns a first_list with
-    # an empty string element.
+    # We need to filter out empty entries, since HumanName for this name
+    # `Perelstein,, Maxim` returns a first_list with an empty string element.
     non_lastnames = [
         non_lastname
-        for non_lastname
-        in parsed_name.first_list + parsed_name.suffix_list
+        for non_lastname in parsed_name.first_list + parsed_name.suffix_list
         if non_lastname
     ]
 
-    # This is needed because due to erroneous data (e.g. having many authors in a single authors field) ends up
+    # This is needed because due to erroneous data (e.g. having many
+    # authors in a single authors field) ends up
     # requiring a lot of memory (due to combinatorial expansion of all non lastnames).
     # The policy is to use the input as a name variation, since this data will have to be curated.
-    if len(non_lastnames) > _NAMES_MAX_NUMBER_THRESHOLD or len(parsed_name.last_list) > _NAMES_MAX_NUMBER_THRESHOLD:
-        LOGGER.warning('Skipping name variations generation - too many names in: "%s"', name)
+    if (
+        len(non_lastnames) > _NAMES_MAX_NUMBER_THRESHOLD
+        or len(parsed_name.last_list) > _NAMES_MAX_NUMBER_THRESHOLD
+    ):
+        LOGGER.warning(
+            'Skipping name variations generation - too many names in: "%s"', name
+        )
         return [name]
 
-    non_lastnames_variations = \
-        _generate_non_lastnames_variations(non_lastnames)
+    non_lastnames_variations = _generate_non_lastnames_variations(non_lastnames)
     lastnames_variations = _generate_lastnames_variations(parsed_name.last_list)
 
-    # Create variations where lastnames comes first and is separated from non lastnames either by space or comma.
+    # Create variations where lastnames comes first and is separated
+    # from non lastnames either by space or comma.
     _update_name_variations_with_product(lastnames_variations, non_lastnames_variations)
 
     # Second part of transformations - having the lastnames in the end.
@@ -490,7 +546,8 @@ def format_name(name, initials_only=False, without_titles=False):
 
     Args:
         name (str): The name to format, in pretty much any format.
-        initials_only (bool): ``True`` if we want the first names to be displayed with only the initial followed by a dot. ``False`` otherwise.
+        initials_only (bool): ``True`` if we want the first names to be
+            displayed with only the initial followed by a dot. ``False`` otherwise.
 
     Examples:
     >>> format_name('Lieber, Stanley Martin')
@@ -500,4 +557,8 @@ def format_name(name, initials_only=False, without_titles=False):
     >>> format_name('Downey, Robert Jr.', initials_only=True)
     u'R. Downey Jr.'
     """
-    return ParsedName(name=name, without_titles=without_titles).loads(name).pprint(initials_only)
+    return (
+        ParsedName(name=name, without_titles=without_titles)
+        .loads(name)
+        .pprint(initials_only)
+    )
diff --git a/inspire_utils/parsers/arxiv.py b/inspire_utils/parsers/arxiv.py
index 6c24884..68d630d 100644
--- a/inspire_utils/parsers/arxiv.py
+++ b/inspire_utils/parsers/arxiv.py
@@ -47,15 +47,11 @@
 )
 
 RE_CONFERENCE = re.compile(
-    r'\b(%s)\b' % '|'.join(
-        [re.escape(word) for word in CONFERENCE_WORDS]
-    ),
+    r'\b(%s)\b' % '|'.join([re.escape(word) for word in CONFERENCE_WORDS]),
     re.I | re.U,
 )
 RE_THESIS = re.compile(
-    r'\b(%s)\b' % '|'.join(
-        [re.escape(word) for word in THESIS_WORDS]
-    ),
+    r'\b(%s)\b' % '|'.join([re.escape(word) for word in THESIS_WORDS]),
     re.I | re.U,
 )
 RE_PAGES = re.compile(r'(?i)(\d+)\s*pages?\b')
@@ -71,18 +67,20 @@ def _handle_sqrt(node, l2tobj):
 
 def get_arxiv_latex_context_db():
     default_db = get_default_latex_context_db()
-    arxiv_db = default_db.filter_context(keep_categories=["latex-base", "advanced-symbols"])
+    arxiv_db = default_db.filter_context(
+        keep_categories=["latex-base", "advanced-symbols"]
+    )
     arxiv_db.add_context_category(
-        "overrides",
-        prepend=True,
-        macros=[
-            MacroTextSpec("sqrt", _handle_sqrt)
-        ]
+        "overrides", prepend=True, macros=[MacroTextSpec("sqrt", _handle_sqrt)]
     )
 
     # adapted from https://github.com/phfaist/pylatexenc/issues/32
-    arxiv_db.set_unknown_macro_spec(MacroTextSpec("", lambda node: node.latex_verbatim()))
-    arxiv_db.set_unknown_environment_spec(EnvironmentTextSpec("", lambda node: node.latex_verbatim()))
+    arxiv_db.set_unknown_macro_spec(
+        MacroTextSpec("", lambda node: node.latex_verbatim())
+    )
+    arxiv_db.set_unknown_environment_spec(
+        EnvironmentTextSpec("", lambda node: node.latex_verbatim())
+    )
 
     return arxiv_db
 
@@ -98,6 +96,7 @@ class ArxivParser(object):
         source (Optional[str]): if provided, sets the ``source`` everywhere in
             the record. Otherwise, the source is extracted from the arXiv metadata.
     """
+
     _l2t = LatexNodes2Text(
         latex_context=get_arxiv_latex_context_db(),
         math_mode="verbatim",
@@ -139,8 +138,9 @@ def parse(self):
         self.builder.add_arxiv_eprint(self.arxiv_eprint, self.arxiv_categories)
         self.builder.add_private_note(self.private_note)
         self.builder.add_document_type(self.document_type)
-        normalized_categories = [classify_field(arxiv_cat)
-                                 for arxiv_cat in self.arxiv_categories]
+        normalized_categories = [
+            classify_field(arxiv_cat) for arxiv_cat in self.arxiv_categories
+        ]
         self.builder.add_inspire_categories(dedupe_list(normalized_categories), 'arxiv')
 
         return self.builder.record
@@ -161,8 +161,13 @@ def _get_authors_and_collaborations(self, node):
         # take 'for the' out of the general phrases and dont use it in
         # affiliations
         collab_phrases = [
-            'consortium', ' collab ', 'collaboration', ' team', 'group',
-            ' on behalf of ', ' representing ',
+            'consortium',
+            ' collab ',
+            'collaboration',
+            ' team',
+            'group',
+            ' on behalf of ',
+            ' representing ',
         ]
         inst_phrases = ['institute', 'university', 'department', 'center']
 
@@ -172,16 +177,23 @@ def _get_authors_and_collaborations(self, node):
         some_affiliation_contains_collaboration = False
 
         authors_and_affiliations = (
-            self._get_author_names_and_affiliations(author) for author in author_selectors
+            self._get_author_names_and_affiliations(author)
+            for author in author_selectors
         )
         next_author_and_affiliations = (
-            self._get_author_names_and_affiliations(author) for author in author_selectors
+            self._get_author_names_and_affiliations(author)
+            for author in author_selectors
         )
         next(next_author_and_affiliations)
 
-        for (forenames, keyname, affiliations), (next_forenames, next_keyname, _) in six.moves.zip_longest(
-                authors_and_affiliations, next_author_and_affiliations,
-                fillvalue=('end of author-list', '', None)
+        for (forenames, keyname, affiliations), (
+            next_forenames,
+            next_keyname,
+            _,
+        ) in six.moves.zip_longest(
+            authors_and_affiliations,
+            next_author_and_affiliations,
+            fillvalue=('end of author-list', '', None),
         ):
 
             name_string = " %s %s " % (forenames, keyname)
@@ -193,9 +205,7 @@ def _get_authors_and_collaborations(self, node):
             for aff in affiliations:
                 affiliation_contains_collaboration = any(
                     phrase in aff.lower() for phrase in collab_phrases
-                ) and not any(
-                    phrase in aff.lower() for phrase in inst_phrases
-                )
+                ) and not any(phrase in aff.lower() for phrase in inst_phrases)
                 if affiliation_contains_collaboration:
                     affiliations_with_collaborations.append(aff)
                     some_affiliation_contains_collaboration = True
@@ -214,12 +224,14 @@ def _get_authors_and_collaborations(self, node):
                 coll, author_name = coll_cleanforthe(name_string)
                 if author_name:
                     surname, given_names = split_fullname(author_name)
-                    authors.append({
-                        'full_name': surname + ', ' + given_names,
-                        'surname': surname,
-                        'given_names': given_names,
-                        'affiliations': [],
-                    })
+                    authors.append(
+                        {
+                            'full_name': surname + ', ' + given_names,
+                            'surname': surname,
+                            'given_names': given_names,
+                            'affiliations': [],
+                        }
+                    )
                 if coll and coll not in collaborations:
                     collaborations.append(coll)
             elif name_string.strip() == ':':
@@ -228,30 +240,35 @@ def _get_authors_and_collaborations(self, node):
                 if not some_affiliation_contains_collaboration:
                     # everything up to now seems to be collaboration info
                     for author_info in authors:
-                        name_string = " %s %s " % \
-                            (author_info['given_names'], author_info['surname'])
+                        name_string = " %s %s " % (
+                            author_info['given_names'],
+                            author_info['surname'],
+                        )
                         coll, author_name = coll_cleanforthe(name_string)
                         if coll and coll not in collaborations:
                             collaborations.append(coll)
                     authors = []
             else:
-                authors.append({
-                    'full_name': keyname + ', ' + forenames,
-                    'surname': keyname,
-                    'given_names': forenames,
-                    'affiliations': affiliations_without_collaborations
-                })
+                authors.append(
+                    {
+                        'full_name': keyname + ', ' + forenames,
+                        'surname': keyname,
+                        'given_names': forenames,
+                        'affiliations': affiliations_without_collaborations,
+                    }
+                )
         if warning_tags:
-            warning = 'WARNING: Colon in authors before %s: Check author list for collaboration names!' % ', '.join(warning_tags)
+            warning = (
+                'WARNING: Colon in authors before %s: Check author list for collaboration names!'
+                % ', '.join(warning_tags)
+            )
         else:
             warning = ''
         return authors, collaborations, warning
 
     @staticmethod
     def _get_author_names_and_affiliations(author_node):
-        forenames = u' '.join(
-            author_node.xpath('.//forenames//text()').extract()
-        )
+        forenames = u' '.join(author_node.xpath('.//forenames//text()').extract())
         keyname = u' '.join(author_node.xpath('.//keyname//text()').extract())
         affiliations = author_node.xpath('.//affiliation//text()').extract()
 
@@ -272,8 +289,12 @@ def abstract(self):
     @property
     def authors(self):
         authors, _, _ = self.authors_and_collaborations
-        parsed_authors = [self.builder.make_author(
-            full_name=auth["full_name"], raw_affiliations=auth["affiliations"]) for auth in authors]
+        parsed_authors = [
+            self.builder.make_author(
+                full_name=auth["full_name"], raw_affiliations=auth["affiliations"]
+            )
+            for auth in authors
+        ]
 
         return parsed_authors
 
@@ -286,7 +307,9 @@ def collaborations(self):
     @property
     def dois(self):
         doi_values = self.root.xpath('.//doi/text()').extract()
-        doi_values_splitted = chain.from_iterable([re.split(RE_DOIS, doi) for doi in doi_values])
+        doi_values_splitted = chain.from_iterable(
+            [re.split(RE_DOIS, doi) for doi in doi_values]
+        )
         dois = [
             {'doi': value, 'material': 'publication'} for value in doi_values_splitted
         ]
@@ -328,7 +351,9 @@ def pubinfo_freetext(self):
 
     @property
     def title(self):
-        long_text_fixed = self.fix_long_text(self.root.xpath('.//title/text()').extract_first())
+        long_text_fixed = self.fix_long_text(
+            self.root.xpath('.//title/text()').extract_first()
+        )
         return self.latex_to_unicode(long_text_fixed)
 
     @staticmethod
@@ -386,7 +411,9 @@ def arxiv_eprint(self):
     def arxiv_categories(self):
         categories = self.root.xpath('.//categories/text()').extract_first(default='[]')
         categories = categories.split()
-        categories_without_old = [normalize_arxiv_category(arxiv_cat) for arxiv_cat in categories]
+        categories_without_old = [
+            normalize_arxiv_category(arxiv_cat) for arxiv_cat in categories
+        ]
 
         return dedupe_list(categories_without_old)
 
@@ -409,7 +436,9 @@ def source(self):
     @property
     def authors_and_collaborations(self):
         if not hasattr(self, '_authors_and_collaborations'):
-            self._authors_and_collaborations = self._get_authors_and_collaborations(self.root)
+            self._authors_and_collaborations = self._get_authors_and_collaborations(
+                self.root
+            )
         return self._authors_and_collaborations
 
     @classmethod
diff --git a/inspire_utils/parsers/author_xml.py b/inspire_utils/parsers/author_xml.py
index 9acc26f..4565f52 100644
--- a/inspire_utils/parsers/author_xml.py
+++ b/inspire_utils/parsers/author_xml.py
@@ -55,11 +55,11 @@ def parse(self):
         content.remove_namespaces()
         undefined_or_none_value_regex = re.compile("undefined|none", re.IGNORECASE)
         undefined_or_empty_inspireid_value_regex = re.compile(
-            "undefined|inspire-\s*$", re.IGNORECASE # noqa
+            "undefined|inspire-\s*$", re.IGNORECASE  # noqa
         )
         undefined_value_regex = re.compile("undefined", re.IGNORECASE)
         ror_path_value_regex = re.compile("https://ror.org/*")
-        remove_new_line_regex = re.compile("\s*\n\s*") # noqa
+        remove_new_line_regex = re.compile("\s*\n\s*")  # noqa
 
         # Goes through all the authors in the file
         for author in content.xpath("//Person"):
@@ -71,10 +71,12 @@ def parse(self):
             # Gets all the author ids
             for source, id in zip(
                 author.xpath(
-                    './authorIDs/authorID[@source!="" and text()!=""]/@source | ./authorids/authorid[@source!="" and text()!=""]/@source'
+                    './authorIDs/authorID[@source!="" and text()!=""]/@source'
+                    '| ./authorids/authorid[@source!="" and text()!=""]/@source'
                 ).getall(),
                 author.xpath(
-                    './authorIDs/authorID[@source!="" and text()!=""]/text() | ./authorids/authorid[@source!="" and text()!=""]/text()'
+                    './authorIDs/authorID[@source!="" and text()!=""]/text()'
+                    '| ./authorids/authorid[@source!="" and text()!=""]/text()'
                 ).getall(),
             ):
                 source = re.sub(remove_new_line_regex, "", source)
@@ -94,7 +96,8 @@ def parse(self):
                 "./authorAffiliations/authorAffiliation/@organizationid"
             ).getall():
                 orgName = content.xpath(
-                    'string(//organizations/Organization[@id="{}"]/orgName[@source="spiresICN" or @source="INSPIRE" and text()!="" ]/text())'.format(
+                    'string(//organizations/Organization[@id="{}"]/orgName[@source="spiresICN"'
+                    'or @source="INSPIRE" and text()!="" ]/text())'.format(
                         affiliation
                     )
                 ).get()
@@ -105,15 +108,18 @@ def parse(self):
                 ):
                     affiliations.append(cleaned_org_name)
 
-                # Gets all the affiliations_identifiers for affiliated organizations using the organization ids from author
+                # Gets all the affiliations_identifiers for affiliated organizations
+                # using the organization ids from author
                 for value, source in zip(
                     content.xpath(
-                        '//organizations/Organization[@id="{}"]/orgName[@source="ROR" or @source="GRID" and text()!=""]/text()'.format(
+                        '//organizations/Organization[@id="{}"]/orgName[@source="ROR"'
+                        'or @source="GRID" and text()!=""]/text()'.format(
                             affiliation
                         )
                     ).getall(),
                     content.xpath(
-                        '//organizations/Organization[@id="{}"]/orgName[@source="ROR" or @source="GRID" and text()!=""]/@source'.format(
+                        '//organizations/Organization[@id="{}"]/orgName[@source="ROR"'
+                        'or @source="GRID" and text()!=""]/@source'.format(
                             affiliation
                         )
                     ).getall(),
diff --git a/inspire_utils/parsers/crossref.py b/inspire_utils/parsers/crossref.py
index d732ebe..1c66071 100644
--- a/inspire_utils/parsers/crossref.py
+++ b/inspire_utils/parsers/crossref.py
@@ -66,6 +66,7 @@ class CrossrefParser(object):
         source (Optional[str]): if provided, sets the ``source`` everywhere in
             the record. Otherwise, the source is extracted from the Crossref metadata.
     """
+
     def __init__(self, crossref_record, source=None):
         self.record = crossref_record.get("message")
         if not source:
@@ -115,9 +116,7 @@ def subtitle(self):
     @property
     def dois(self):
         value = self.record.get("DOI")
-        dois = [
-            {'doi': value, 'material': self.material}
-        ]
+        dois = [{'doi': value, 'material': self.material}]
 
         return dois
 
@@ -133,7 +132,9 @@ def material(self):
             material = 'erratum'
         elif title.startswith("Addendum") or subtitle.startswith("Addendum"):
             material = 'addendum'
-        elif title.startswith("Publisher's Note") or subtitle.startswith("Publisher's Note"):
+        elif title.startswith("Publisher's Note") or subtitle.startswith(
+            "Publisher's Note"
+        ):
             material = 'editorial note'
         else:
             material = 'publication'
@@ -238,7 +239,9 @@ def get_author(self, author_key):
         affiliations = self.get_author_affiliations(author_key)
         orcid = self.get_author_orcid(author_key)
 
-        return self.builder.make_author(author_name, raw_affiliations=affiliations, ids=orcid)
+        return self.builder.make_author(
+            author_name, raw_affiliations=affiliations, ids=orcid
+        )
 
     @property
     def authors(self):
diff --git a/inspire_utils/parsers/elsevier.py b/inspire_utils/parsers/elsevier.py
index b6bd862..203fe0f 100644
--- a/inspire_utils/parsers/elsevier.py
+++ b/inspire_utils/parsers/elsevier.py
@@ -107,7 +107,8 @@ class ElsevierParser(object):
     subclassed to customize its behavior.
 
     Args:
-        elsevier_record (Union[str, scrapy.selector.Selector]): the record in Elsevier format to parse.
+        elsevier_record (Union[str, scrapy.selector.Selector]): the record in Elsevier
+            format to parse.
         source (Optional[str]): if provided, sets the ``source`` everywhere in
             the record. Otherwise, the source is extracted from the Elsevier metadata.
     """
@@ -141,9 +142,7 @@ def parse(self):
         if self.imprints_date:
             self.builder.add_imprint_date(self.imprints_date)
         elif self.publication_date:
-            self.builder.add_imprint_date(
-                self.publication_date.dumps()
-            )
+            self.builder.add_imprint_date(self.publication_date.dumps())
         for reference in self.references:
             self.builder.add_reference(reference)
 
@@ -176,14 +175,17 @@ def references(self):
 
     @property
     def abstract(self):
-        abstract_nodes = self.root.xpath(".//head/abstract[not(@graphical)]/abstract-sec/simple-para")
+        abstract_nodes = self.root.xpath(
+            ".//head/abstract[not(@graphical)]/abstract-sec/simple-para"
+        )
 
         if not abstract_nodes:
             return
 
-        abstract_paragraphs = [remove_tags(
-            abstract_node, **self.remove_tags_config_abstract
-        ).strip("/ \n") for abstract_node in abstract_nodes]
+        abstract_paragraphs = [
+            remove_tags(abstract_node, **self.remove_tags_config_abstract).strip("/ \n")
+            for abstract_node in abstract_nodes
+        ]
         abstract = ' '.join(abstract_paragraphs)
         return abstract
 
@@ -270,9 +272,7 @@ def dois(self):
     @property
     def document_type(self):
         doctype = None
-        if self.root.xpath(
-            "./*[contains(name(),'article') or self::book-review]"
-        ):
+        if self.root.xpath("./*[contains(name(),'article') or self::book-review]"):
             doctype = "article"
         elif self.root.xpath("./*[self::book or self::simple-book]"):
             doctype = "book"
@@ -428,9 +428,9 @@ def publication_info(self):
 
     @property
     def publisher(self):
-        publisher = self.root.xpath("string(./RDF/Description/publisher[1])").extract_first(
-            "Elsevier B.V."
-        )
+        publisher = self.root.xpath(
+            "string(./RDF/Description/publisher[1])"
+        ).extract_first("Elsevier B.V.")
 
         return publisher
 
@@ -443,7 +443,11 @@ def subtitle(self):
     @property
     def title(self):
         title = self.root.xpath("./*/head/title[1]").extract_first()
-        return remove_tags(title, **self.remove_tags_config_title).strip("\n") if title else None
+        return (
+            remove_tags(title, **self.remove_tags_config_title).strip("\n")
+            if title
+            else None
+        )
 
     @property
     def year(self):
@@ -544,7 +548,9 @@ def get_reference_authors(ref_node):
         authors = ref_node.xpath("./contribution/authors/author")
         authors_names = []
         for author in authors:
-            given_names = author.xpath("string(./given-name[1])").extract_first(default="")
+            given_names = author.xpath("string(./given-name[1])").extract_first(
+                default=""
+            )
             last_names = author.xpath("string(./surname[1])").extract_first(default="")
             authors_names.append(" ".join([given_names, last_names]).strip())
         return authors_names
@@ -562,7 +568,9 @@ def get_reference_editors(ref_node):
         editors = ref_node.xpath(".//editors/authors/author")
         editors_names = []
         for editor in editors:
-            given_names = editor.xpath("string(./given-name[1])").extract_first(default="")
+            given_names = editor.xpath("string(./given-name[1])").extract_first(
+                default=""
+            )
             last_names = editor.xpath("string(./surname[1])").extract_first(default="")
             editors_names.append(" ".join([given_names, last_names]).strip())
         return editors_names
@@ -580,13 +588,13 @@ def get_reference_pages(ref_node):
     def get_reference_iter(self, ref_node):
         """Extract one reference.
 
-        Args:
-            ref_node(scrapy.selector.Selector): a selector on a single
-                reference, i.e. ``<ref>``.
+         Args:
+             ref_node(scrapy.selector.Selector): a selector on a single
+                 reference, i.e. ``<ref>``.
 
-       Yields:
-            dict: the parsed reference, as generated by
-                :class:`inspire_schemas.api.ReferenceBuilder`
+        Yields:
+             dict: the parsed reference, as generated by
+                 :class:`inspire_schemas.api.ReferenceBuilder`
         """
         # handle also unstructured refs
         for citation_node in ref_node.xpath("./reference|./other-ref"):
@@ -599,7 +607,10 @@ def get_reference_iter(self, ref_node):
             )
 
             fields = [
-                (("string(.//series/title/maintitle[1])"), builder.set_journal_title,),
+                (
+                    ("string(.//series/title/maintitle[1])"),
+                    builder.set_journal_title,
+                ),
                 (
                     "string(.//title[parent::edited-book|parent::book]/maintitle[1])",
                     builder.add_parent_title,
@@ -646,7 +657,7 @@ def get_reference_iter(self, ref_node):
                     "|self::label"
                     "|self::publisher"
                     "|self::doi"
-                    "|self::pages"
+                    "|self::pages",
                 )
                 .strip("\"';,. \t\n\r")
                 .replace("()", "")
diff --git a/inspire_utils/parsers/jats.py b/inspire_utils/parsers/jats.py
index fbe18b6..c723f0e 100644
--- a/inspire_utils/parsers/jats.py
+++ b/inspire_utils/parsers/jats.py
@@ -35,9 +35,7 @@
 from inspire_utils.helpers import maybe_int, remove_tags
 from inspire_utils.utils import get_node
 
-JOURNAL_TITLES_MAPPING = {
-    "Physics": "APS Physics"
-}
+JOURNAL_TITLES_MAPPING = {"Physics": "APS Physics"}
 
 
 class JatsParser(object):
@@ -51,6 +49,7 @@ class JatsParser(object):
         source (Optional[str]): if provided, sets the ``source`` everywhere in
             the record. Otherwise, the source is extracted from the JATS metadata.
     """
+
     def __init__(self, jats_record, source=None):
         self.root = self.get_root_node(jats_record)
         if not source:
@@ -104,7 +103,7 @@ def references(self):
     remove_tags_config_abstract = {
         'allowed_tags': ['sup', 'sub'],
         'allowed_trees': ['math'],
-        'strip': 'self::pub-id|self::issn'
+        'strip': 'self::pub-id|self::issn',
     }
 
     remove_tags_config_title = {
@@ -118,7 +117,9 @@ def abstract(self):
         if not abstract_nodes:
             return
 
-        abstract = remove_tags(abstract_nodes[0], **self.remove_tags_config_abstract).strip()
+        abstract = remove_tags(
+            abstract_nodes[0], **self.remove_tags_config_abstract
+        ).strip()
         return abstract
 
     @property
@@ -129,7 +130,9 @@ def article_type(self):
 
     @property
     def artid(self):
-        artid = self.root.xpath('./front/article-meta//elocation-id//text()').extract_first()
+        artid = self.root.xpath(
+            './front/article-meta//elocation-id//text()'
+        ).extract_first()
 
         return artid
 
@@ -166,28 +169,34 @@ def copyright(self):
 
     @property
     def copyright_holder(self):
-        copyright_holder = self.root.xpath('./front//copyright-holder/text()').extract_first()
+        copyright_holder = self.root.xpath(
+            './front//copyright-holder/text()'
+        ).extract_first()
 
         return copyright_holder
 
     @property
     def copyright_statement(self):
-        copyright_statement = self.root.xpath('./front//copyright-statement/text()').extract_first()
+        copyright_statement = self.root.xpath(
+            './front//copyright-statement/text()'
+        ).extract_first()
 
         return copyright_statement
 
     @property
     def copyright_year(self):
-        copyright_year = self.root.xpath('./front//copyright-year/text()').extract_first()
+        copyright_year = self.root.xpath(
+            './front//copyright-year/text()'
+        ).extract_first()
 
         return maybe_int(copyright_year)
 
     @property
     def dois(self):
-        doi_values = self.root.xpath('./front/article-meta//article-id[@pub-id-type="doi"]/text()').extract()
-        dois = [
-            {'doi': value, 'material': self.material} for value in doi_values
-        ]
+        doi_values = self.root.xpath(
+            './front/article-meta//article-id[@pub-id-type="doi"]/text()'
+        ).extract()
+        dois = [{'doi': value, 'material': self.material} for value in doi_values]
 
         if self.material != 'publication':
             doi_values = self.root.xpath(
@@ -222,20 +231,26 @@ def journal_title(self):
 
     @property
     def journal_issue(self):
-        journal_issue = self.root.xpath('./front/article-meta/issue/text()').extract_first()
+        journal_issue = self.root.xpath(
+            './front/article-meta/issue/text()'
+        ).extract_first()
 
         return journal_issue
 
     @property
     def journal_volume(self):
-        journal_volume = self.root.xpath('./front/article-meta/volume/text()').extract_first()
+        journal_volume = self.root.xpath(
+            './front/article-meta/volume/text()'
+        ).extract_first()
 
         return journal_volume
 
     @property
     def keywords(self):
         keyword_groups = self.root.xpath('./front//kwd-group')
-        keywords = itertools.chain.from_iterable(self.get_keywords(group) for group in keyword_groups)
+        keywords = itertools.chain.from_iterable(
+            self.get_keywords(group) for group in keyword_groups
+        )
 
         return keywords
 
@@ -251,7 +266,11 @@ def license(self):
 
     @property
     def license_statement(self):
-        license_statement = self.root.xpath('string(./front/article-meta//license)').extract_first().strip()
+        license_statement = (
+            self.root.xpath('string(./front/article-meta//license)')
+            .extract_first()
+            .strip()
+        )
 
         return license_statement
 
@@ -279,13 +298,17 @@ def material(self):
 
     @property
     def number_of_pages(self):
-        number_of_pages = maybe_int(self.root.xpath('./front/article-meta//page-count/@count').extract_first())
+        number_of_pages = maybe_int(
+            self.root.xpath('./front/article-meta//page-count/@count').extract_first()
+        )
 
         return number_of_pages
 
     @property
     def page_start(self):
-        page_start = self.root.xpath('./front/article-meta/fpage/text()').extract_first()
+        page_start = self.root.xpath(
+            './front/article-meta/fpage/text()'
+        ).extract_first()
 
         return page_start
 
@@ -305,9 +328,7 @@ def publication_date(self):
         )
 
         if date_nodes:
-            publication_date = min(
-                self.get_date(date_node) for date_node in date_nodes
-            )
+            publication_date = min(self.get_date(date_node) for date_node in date_nodes)
 
             return publication_date
 
@@ -382,13 +403,11 @@ def year(self):
             './front//pub-date[@pub-type="ppub"] |'
             './front//pub-date[starts-with(@date-type,"pub") and $not_online] |'
             './front//date[starts-with(@date-type,"pub") and $not_online]',
-            not_online=not_online
+            not_online=not_online,
         )
 
         if date_nodes:
-            year = min(
-                self.get_date(date_node) for date_node in date_nodes
-            ).year
+            year = min(self.get_date(date_node) for date_node in date_nodes).year
 
             return year
 
@@ -401,7 +420,8 @@ def get_author_affiliations(self, author_node):
             referred_ids.update(set(raw_referred_id.split(' ')))
 
         affiliations = [
-            self.get_affiliation(rid) for rid in referred_ids
+            self.get_affiliation(rid)
+            for rid in referred_ids
             if self.get_affiliation(rid)
         ]
 
@@ -439,11 +459,7 @@ def _get_iso_date(iso_date_string):
 
     @staticmethod
     def _get_date_from_parts(year, month, day):
-        possible_dates = [
-            [year, month, day],
-            [year, month],
-            [year]
-        ]
+        possible_dates = [[year, month, day], [year, month], [year]]
         # we try different date combinations
         # cause even if date part is not None
         # it can raise validation error
@@ -485,10 +501,15 @@ def get_date(self, date_node):
     def get_keywords(group_node):
         """Extract keywords from a keyword group."""
         schema = None
-        if 'pacs' in group_node.xpath('@kwd-group-type').extract_first(default='').lower():
+        if (
+            'pacs'
+            in group_node.xpath('@kwd-group-type').extract_first(default='').lower()
+        ):
             schema = 'PACS'
 
-        keywords = (kwd.xpath('string(.)').extract_first() for kwd in group_node.xpath('.//kwd'))
+        keywords = (
+            kwd.xpath('string(.)').extract_first() for kwd in group_node.xpath('.//kwd')
+        )
         keyword_dicts = ({'keyword': keyword, 'schema': schema} for keyword in keywords)
 
         return keyword_dicts
@@ -507,10 +528,7 @@ def get_root_node(jats_record):
             scrapy.selector.Selector: a selector on the root ``<article>``
                 node.
         """
-        if isinstance(jats_record, six.string_types):
-            root = get_node(jats_record)
-        else:
-            root = jats_record
+        root = get_node(jats_record) if isinstance(jats_record, six.string_types) else jats_record
         root.remove_namespaces()
 
         return root
@@ -531,15 +549,14 @@ def get_author(self, author_node):
         orcid = self.get_orcid(author_node)
         author_ids = [("ORCID", orcid)] if orcid else []
         return self.builder.make_author(
-            author_name,
-            raw_affiliations=affiliations,
-            emails=emails,
-            ids=author_ids
+            author_name, raw_affiliations=affiliations, emails=emails, ids=author_ids
         )
 
     @staticmethod
     def get_orcid(author_node):
-        orcid = author_node.xpath('./contrib-id[@contrib-id-type="orcid"]/text()').extract_first()
+        orcid = author_node.xpath(
+            './contrib-id[@contrib-id-type="orcid"]/text()'
+        ).extract_first()
         if orcid:
             return normalize_orcid(orcid)
 
@@ -555,8 +572,7 @@ def get_reference_authors(ref_node, role):
             List[str]: list of names
         """
         return ref_node.xpath(
-            './person-group[@person-group-type=$role]/string-name/text()',
-            role=role
+            './person-group[@person-group-type=$role]/string-name/text()', role=role
         ).extract()
 
     def get_reference(self, ref_node):
@@ -576,7 +592,7 @@ def get_reference(self, ref_node):
             builder.add_raw_reference(
                 ref_node.extract().strip(),
                 source=self.builder.source,
-                ref_format='JATS'
+                ref_format='JATS',
             )
 
             fields = [
@@ -600,10 +616,13 @@ def get_reference(self, ref_node):
                 (
                     'pub-id[@pub-id-type="other"]'
                     '[contains(preceding-sibling::text(),"Report No")]/text()',
-                    builder.add_report_number
+                    builder.add_report_number,
                 ),
                 ('./article-title/text()', builder.add_title),
-                ('../label/text()', lambda x, builder=builder: builder.set_label(x.strip('[].')))
+                (
+                    '../label/text()',
+                    lambda x, builder=builder: builder.set_label(x.strip('[].')),
+                ),
             ]
 
             for xpath, field_handler in fields:
diff --git a/inspire_utils/query.py b/inspire_utils/query.py
index 75c7996..a1398c6 100644
--- a/inspire_utils/query.py
+++ b/inspire_utils/query.py
@@ -26,15 +26,18 @@ def wrap_queries_in_bool_clauses_if_more_than_one(
     queries, use_must_clause, preserve_bool_semantics_if_one_clause=False
 ):
     """Helper for wrapping a list of queries into a bool.{must, should} clause.
+
     Args:
         queries (list): List of queries to be wrapped in a bool.{must, should} clause.
-        use_must_clause (bool): Flag that signifies whether to use 'must' or 'should' clause.
-        preserve_bool_semantics_if_one_clause (bool): Flag that signifies whether to generate a bool query even if
-            there's only one clause. This happens to generate boolean query semantics. Usually not the case, but
-            useful for boolean queries support.
+        use_must_clause (bool): Flag that signifies whether to use
+        'must' or 'should' clause.
+        preserve_bool_semantics_if_one_clause (bool): Flag that signifies whether to
+        generate a bool query even if there's only one clause. This happens to generate
+        boolean query semantics. Usually not the case, but useful for boolean queries support.
     Returns:
-        (dict): If len(queries) > 1, the bool clause, otherwise if len(queries) == 1, will return the query itself,
-                while finally, if len(queries) == 0, then an empty dictionary is returned.
+        (dict): If len(queries) > 1, the bool clause, otherwise if len(queries) == 1,
+        will return the query itself,while finally, if len(queries) == 0,
+        then an empty dictionary is returned.
     """
     if not queries:
         return {}
@@ -48,9 +51,7 @@ def wrap_queries_in_bool_clauses_if_more_than_one(
 
 
 def ordered(obj):
-    """
-    Helper to order the dictionary
-    """
+    """Helper to order the dictionary."""
     # See https://stackoverflow.com/a/25851972
     if isinstance(obj, dict):
         return sorted((k, ordered(v)) for k, v in obj.items())
diff --git a/inspire_utils/record.py b/inspire_utils/record.py
index 4e25369..f7fe520 100644
--- a/inspire_utils/record.py
+++ b/inspire_utils/record.py
@@ -504,12 +504,11 @@ def get_values_for_schema(elements, schema):
 
 
 def replace_undesirable_characters(line):
-    """
-    Replace certain bad characters in a text line.
-    @param line: (string) the text line in which bad characters are to
-                 be replaced.
-    @return: (string) the text line after the bad characters have been
-                      replaced.
+    """Replace certain bad characters in a text line. @param line: (string) the
+    text line in which bad characters are to.
+
+    be replaced. @return: (string) the text line after the
+    bad characters have been                   replaced.
     """
     # These are separate because we want a particular order
     for bad_string, replacement in UNDESIRABLE_STRING_REPLACEMENTS:
diff --git a/inspire_utils/urls.py b/inspire_utils/urls.py
index ea339d6..efe50bd 100644
--- a/inspire_utils/urls.py
+++ b/inspire_utils/urls.py
@@ -19,7 +19,6 @@
 # In applying this license, CERN does not waive the privileges and immunities
 # granted to it by virtue of its status as an Intergovernmental Organization
 # or submit itself to any jurisdiction.
-
 """URL-related utils."""
 
 from __future__ import absolute_import, division, print_function
@@ -45,7 +44,7 @@ def ensure_scheme(url, default_scheme='http'):
             netloc=parsed.path,
             path='',
             query=parsed.query,
-            fragment=parsed.fragment
+            fragment=parsed.fragment,
         )
 
     return urlunsplit(parsed)
diff --git a/inspire_utils/utils.py b/inspire_utils/utils.py
index 6c6b67d..3a99c7c 100644
--- a/inspire_utils/utils.py
+++ b/inspire_utils/utils.py
@@ -12,7 +12,9 @@
     r'\b(?:for|on behalf of|representing)\b',
     re.IGNORECASE,
 )
-INST_PHRASES = ['for the development', ]
+INST_PHRASES = [
+    'for the development',
+]
 
 
 def get_node(text, namespaces=None):
@@ -25,7 +27,7 @@ def get_node(text, namespaces=None):
 
 
 def coll_cleanforthe(coll):
-    """ Cleanup collaboration, try to find author """
+    """Cleanup collaboration, try to find author."""
     author = None
 
     if any(phrase for phrase in INST_PHRASES if phrase in coll.lower()):
@@ -52,10 +54,10 @@ def coll_cleanforthe(coll):
 def split_fullname(author, switch_name_order=False):
     """Split an author name to surname and given names.
 
-    It accepts author strings with and without comma separation.
-    As default surname is first in case of comma separation, otherwise last.
-    Multi-part surnames are incorrectly detected in strings without comma
-    separation.
+    It accepts author strings with and without comma separation. As
+    default surname is first in case of comma separation, otherwise
+    last. Multi-part surnames are incorrectly detected in strings
+    without comma separation.
     """
     if not author:
         return "", ""
@@ -112,7 +114,7 @@ def split_fullname(author, switch_name_order=False):
     'talk',
     'talks',
     'workshop',
-    'workshops'
+    'workshops',
 ]
 
 THESIS_WORDS = [
@@ -136,5 +138,5 @@ def split_fullname(author, switch_name_order=False):
     'staatsexamensarbeit',
     'tesi',
     'thesis',
-    'travail'
+    'travail',
 ]
diff --git a/ruff.toml b/ruff.toml
index 843a909..8c073e3 100644
--- a/ruff.toml
+++ b/ruff.toml
@@ -1,4 +1,5 @@
 target-version = "py311"
+line-length = 100
 [lint.flake8-tidy-imports]
 ban-relative-imports = "all"
 
@@ -19,7 +20,7 @@ select = [
     # flake8-pytest-style
     "PT",
 ]
-ignore = ["B904", "E501"]
+ignore = ["B904"]
 
 
 [lint.pycodestyle]
diff --git a/tests/test_config.py b/tests/test_config.py
index 525d6e2..ae02fa9 100644
--- a/tests/test_config.py
+++ b/tests/test_config.py
@@ -42,10 +42,12 @@ def test_config(tmpdir):
     mock_config = tmpdir.join("inspirehep.cfg")
     mock_config.write("SERVER_NAME = '0.0.0.0'; OTHER_VARIABLE = 42")
 
-    config = Config(defaults={
-        'SERVER_NAME': '127.0.0.1',
-        'SOME_OTHER_DEFAULT': 1234,
-    })
+    config = Config(
+        defaults={
+            'SERVER_NAME': '127.0.0.1',
+            'SOME_OTHER_DEFAULT': 1234,
+        }
+    )
     config.load_pyfile(mock_config.strpath)
 
     assert config['SERVER_NAME'] == '0.0.0.0'
@@ -84,9 +86,12 @@ def test_config_invalid_file(tmpdir):
     with pytest.raises(MalformedConfig):
         config.load_pyfile(mock_config.strpath)
 
+
 @pytest.mark.usefixtures(name="_restore_cwd")
 def test_load_config(tmpdir):
-    mock_inspirehep_var_cfg = tmpdir.mkdir('var').mkdir('inspirehep-instance').join("inspirehep.cfg")
+    mock_inspirehep_var_cfg = (
+        tmpdir.mkdir('var').mkdir('inspirehep-instance').join("inspirehep.cfg")
+    )
     mock_inspirehep_var_cfg.write("SERVER_NAME = '0.0.0.0'")
 
     mock_inspirehep_cfg = tmpdir.join("inspirehep.cfg")
diff --git a/tests/test_date.py b/tests/test_date.py
index 66b1eff..e66f92e 100644
--- a/tests/test_date.py
+++ b/tests/test_date.py
@@ -68,7 +68,9 @@ def test_partial_date_raises_on_day_with_no_month():
 
 
 def test_partial_date_raises_on_wrong_types():
-    with pytest.raises(TypeError, match='arguments to PartialDate must be of type int or None'):
+    with pytest.raises(
+        TypeError, match='arguments to PartialDate must be of type int or None'
+    ):
         PartialDate('1686', '6', '30')
 
 
diff --git a/tests/test_helpers.py b/tests/test_helpers.py
index c0f0672..e317d1d 100644
--- a/tests/test_helpers.py
+++ b/tests/test_helpers.py
@@ -83,7 +83,8 @@ def test_maybe_int_returns_none_otherwise():
 def test_remove_tags_allowed_trees_strip():
     allowed_trees = ('b',)
     strip = '@class="hidden"'
-    snippet = '<p><b><i>Only</i></b> this text remains.<span class="hidden">Not this one.</span></p>'
+    snippet = ('<p><b><i>Only</i></b> this text remains.'
+               '<span class="hidden">Not this one.</span></p>')
 
     result = remove_tags(snippet, allowed_trees=allowed_trees, strip=strip)
     expected = u'<b><i>Only</i></b> this text remains.'
@@ -94,7 +95,8 @@ def test_remove_tags_allowed_trees_strip():
 def test_remove_tags_allowed_tags_strip():
     allowed_tags = ('b',)
     strip = '@class="hidden"'
-    snippet = '<p><b><i>Only</i></b> this text remains.<span class="hidden">Not this one.</span></p>'
+    snippet = ('<p><b><i>Only</i></b> this text remains.'
+                '<span class="hidden">Not this one.</span></p>')
 
     result = remove_tags(snippet, allowed_tags=allowed_tags, strip=strip)
     expected = u'<b>Only</b> this text remains.'
@@ -105,7 +107,8 @@ def test_remove_tags_allowed_tags_strip():
 def test_remove_tags_allowed_tags_strip_preserves_text():
     allowed_tags = ('i',)
     strip = '@class="hidden"'
-    snippet = '<p><b><i>Only</i></b> this text remains.<span class="hidden">Not this one.</span></p>'
+    snippet = ('<p><b><i>Only</i></b> this text remains.'
+               '<span class="hidden">Not this one.</span></p>')
 
     result = remove_tags(snippet, allowed_tags=allowed_tags, strip=strip)
     expected = u'<i>Only</i> this text remains.'
diff --git a/tests/test_name.py b/tests/test_name.py
index af0a3da..9e108de 100644
--- a/tests/test_name.py
+++ b/tests/test_name.py
@@ -120,8 +120,11 @@ def test_normalize_name_handles_suffixes(input_author_name, expected):
 
 @pytest.mark.parametrize(
     ("input_author_name", "expected"),
-    [("Sir John Smith", "Smith, John"),
-     ("Bao, Hon", "Bao, Hon"), ("ed witten", "Witten, Ed")],
+    [
+        ("Sir John Smith", "Smith, John"),
+        ("Bao, Hon", "Bao, Hon"),
+        ("ed witten", "Witten, Ed"),
+    ],
 )
 def test_normalize_name_handles_titles(input_author_name, expected):
     assert normalize_name(input_author_name) == expected
@@ -416,8 +419,7 @@ def test_format_author_name():
 def test_format_author_name_with_initials():
     expected = "S. M. Lieber"
 
-    assert expected == format_name(
-        "Lieber, Stanley Martin", initials_only=True)
+    assert expected == format_name("Lieber, Stanley Martin", initials_only=True)
 
 
 def test_format_author_name_with_initials_with_all_caps_name():
@@ -439,15 +441,20 @@ def test_parsed_name_initials():
 
 @pytest.mark.parametrize(
     ("input_author_name", "expected"),
-    [("Lieber, Ed", "E. Lieber"),
-     ('Lieber, Ed Viktor', "E. V. Lieber"),
-     ('Lieber, Ed Jr.', "E. Lieber, Jr."),
-     ('Lieber, Ed Victor Jr.', "E. V. Lieber, Jr."),
-     ],
+    [
+        ("Lieber, Ed", "E. Lieber"),
+        ('Lieber, Ed Viktor', "E. V. Lieber"),
+        ('Lieber, Ed Jr.', "E. Lieber, Jr."),
+        ('Lieber, Ed Victor Jr.', "E. V. Lieber, Jr."),
+    ],
 )
-def test_format_author_name_with_initials_when_first_name_is_similar_to_title(input_author_name, expected):
+def test_format_author_name_with_initials_when_first_name_is_similar_to_title(
+    input_author_name, expected
+):
 
-    assert expected == format_name(input_author_name, initials_only=True, without_titles=True)
+    assert expected == format_name(
+        input_author_name, initials_only=True, without_titles=True
+    )
 
 
 def test_parsed_wrong_names_and_not_fail():
@@ -485,9 +492,9 @@ def test_first_name_with_dash_is_printed_with_dash_and_initialized_correctly():
 
 
 def test_first_name_initials_without_whitespace_is_initialized_correctly():
-    assert format_name(
-        "Miguel A-M.G. Garcia", initials_only=True
-    ) == u"M. A. M. G. Garcia"
+    assert (
+        format_name("Miguel A-M.G. Garcia", initials_only=True) == u"M. A. M. G. Garcia"
+    )
 
 
 def test_last_name_recognized_correctly_regression_test():
@@ -1348,48 +1355,52 @@ def test_generate_es_query_title_name():
     name = "ed witten"
     expected_query = {
         'nested': {
-            'path': 'authors', 'query': {
+            'path': 'authors',
+            'query': {
                 'bool': {
                     'must': [
                         {
                             'match': {
                                 u'authors.last_name': {
                                     'operator': 'AND',
-                                    'query': u'Witten'
+                                    'query': u'Witten',
                                 }
                             }
-                        }, {
+                        },
+                        {
                             'bool': {
                                 'should': [
                                     {
                                         'match_phrase_prefix': {
                                             u'authors.first_name': {
                                                 'query': u'Ed',
-                                                'analyzer': 'names_analyzer'
+                                                'analyzer': 'names_analyzer',
                                             }
                                         }
-                                    }, {
+                                    },
+                                    {
                                         'match': {
                                             u'authors.first_name': {
                                                 'operator': 'AND',
                                                 'query': u'Ed',
-                                                'analyzer': 'names_initials_analyzer'
+                                                'analyzer': 'names_initials_analyzer',
                                             }
                                         }
-                                    }, {
+                                    },
+                                    {
                                         'match': {
                                             u'authors.full_name': {
                                                 'operator': 'AND',
-                                                'query': 'Ed Witten'
+                                                'query': 'Ed Witten',
                                             }
                                         }
-                                    }
+                                    },
                                 ]
                             }
-                        }
+                        },
                     ]
                 }
-            }
+            },
         }
     }
     parsed_name = ParsedName(name)
diff --git a/tests/test_parsers_arxiv.py b/tests/test_parsers_arxiv.py
index 5e17a5e..6e1938e 100644
--- a/tests/test_parsers_arxiv.py
+++ b/tests/test_parsers_arxiv.py
@@ -51,15 +51,23 @@ def test_latex_to_unicode_preserves_math():
 
 
 def test_latex_to_unicode_preserves_braces_containing_more_than_one_char():
-    expected = u"On the origin of the Type~{\\sc ii} spicules - dynamic 3D MHD simulations"
-    result = ArxivParser.latex_to_unicode(u"On the origin of the Type~{\\sc ii} spicules - dynamic 3D MHD simulations")
+    expected = (
+        u"On the origin of the Type~{\\sc ii} spicules - dynamic 3D MHD simulations"
+    )
+    result = ArxivParser.latex_to_unicode(
+        u"On the origin of the Type~{\\sc ii} spicules - dynamic 3D MHD simulations"
+    )
 
     assert result == expected
 
 
 def test_latex_to_unicode_preserves_comments():
-    expected = u"A 4% measurement of $H_0$ using the cumulative distribution of strong-lensing time delays in doubly-imaged quasars"
-    result = ArxivParser.latex_to_unicode(u"A 4% measurement of $H_0$ using the cumulative distribution of strong-lensing time delays in doubly-imaged quasars")
+    expected = (u"A 4% measurement of $H_0$ using the cumulative"
+                u"distribution of strong-lensing time delays in doubly-imaged quasars")
+    result = ArxivParser.latex_to_unicode(
+        (u"A 4% measurement of $H_0$ using the cumulative"
+                u"distribution of strong-lensing time delays in doubly-imaged quasars")
+    )
 
     assert result == expected
 
diff --git a/tests/test_parsers_crossref.py b/tests/test_parsers_crossref.py
index 2c12cc5..8fa8303 100644
--- a/tests/test_parsers_crossref.py
+++ b/tests/test_parsers_crossref.py
@@ -54,13 +54,16 @@ def get_parser_by_file(filename):
     return CrossrefParser(aps_crossref)
 
 
-@pytest.fixture(scope='module', params=[
-    ('2018.3804742.json', '2018.3804742_expected.yml'),
-    ('tasc.2017.2776938.json', 'tasc.2017.2776938_expected.yml'),
-    ('9781316535783.011.json', '9781316535783.011_expected.yml'),
-    ('PhysRevB.33.3547.2.json', 'PhysRevB.33.3547.2_expected.yml'),
-    ('s1463-4988(99)00060-3.json', 's1463-4988(99)00060-3_expected.yml'),
-])
+@pytest.fixture(
+    scope='module',
+    params=[
+        ('2018.3804742.json', '2018.3804742_expected.yml'),
+        ('tasc.2017.2776938.json', 'tasc.2017.2776938_expected.yml'),
+        ('9781316535783.011.json', '9781316535783.011_expected.yml'),
+        ('PhysRevB.33.3547.2.json', 'PhysRevB.33.3547.2_expected.yml'),
+        ('s1463-4988(99)00060-3.json', 's1463-4988(99)00060-3_expected.yml'),
+    ],
+)
 def records(request):
     return {
         'crossref': get_parser_by_file(request.param[0]),
@@ -99,24 +102,20 @@ def test_data_completeness(records):
         assert field in all_fields
 
 
-@pytest.mark.parametrize(
-    'field_name',
-    REQUIRED_FIELDS
-)
+@pytest.mark.parametrize('field_name', REQUIRED_FIELDS)
 def test_required_fields(field_name, records):
-    '''Check every field in this list since all of them are required in a Crossref record'''
+    """Check every field in this list since all of them are required in a
+    Crossref record."""
     result = getattr(records['crossref'], field_name)
     expected = records['expected'][field_name]
 
     assert result == expected
 
 
-@pytest.mark.parametrize(
-    'field_name',
-    UNREQUIRED_FIELDS
-)
+@pytest.mark.parametrize('field_name', UNREQUIRED_FIELDS)
 def test_unrequired_fields(field_name, records):
-    '''Check if the field was parsed correctly only if the field exists in this record'''
+    """Check if the field was parsed correctly only if the field exists in this
+    record."""
     if field_name in records['expected']:
         result = getattr(records['crossref'], field_name)
         expected = records['expected'][field_name]
diff --git a/tests/test_parsers_elsevier.py b/tests/test_parsers_elsevier.py
index 234e67e..fb79d0a 100644
--- a/tests/test_parsers_elsevier.py
+++ b/tests/test_parsers_elsevier.py
@@ -55,17 +55,20 @@ def get_parser_by_file(filename):
     return ElsevierParser(aps_elsevier)
 
 
-@pytest.fixture(scope='module', params=[
-    ('j.nima.2019.162787.xml', 'j.nima.2019.162787_expected.yml'),
-    ('j.nuclphysa.2020.121991.xml', 'j.nuclphysa.2020.121991_expected.yml'),
-    ('j.nima.2019.162728.xml', 'j.nima.2019.162728_expected.yml'),
-    ('j.nimb.2019.04.063.xml', 'j.nimb.2019.04.063_expected.yml'),
-    ('j.cpc.2020.107740.xml', 'j.cpc.2020.107740_expected.yml'),
-    ('j.scib.2020.01.008.xml', 'j.scib.2020.01.008_expected.yml'),
-    ('aphy.2001.6176.xml', 'aphy.2001.6176_expected.yml'),
-    ('j.aim.2021.107831.xml', 'j.aim.2021.107831_expected.yml'),
-    ('j.nuclphysa.2020.121992.xml', 'j.nuclphysa.2020.121992_expected.yml'),
-])
+@pytest.fixture(
+    scope='module',
+    params=[
+        ('j.nima.2019.162787.xml', 'j.nima.2019.162787_expected.yml'),
+        ('j.nuclphysa.2020.121991.xml', 'j.nuclphysa.2020.121991_expected.yml'),
+        ('j.nima.2019.162728.xml', 'j.nima.2019.162728_expected.yml'),
+        ('j.nimb.2019.04.063.xml', 'j.nimb.2019.04.063_expected.yml'),
+        ('j.cpc.2020.107740.xml', 'j.cpc.2020.107740_expected.yml'),
+        ('j.scib.2020.01.008.xml', 'j.scib.2020.01.008_expected.yml'),
+        ('aphy.2001.6176.xml', 'aphy.2001.6176_expected.yml'),
+        ('j.aim.2021.107831.xml', 'j.aim.2021.107831_expected.yml'),
+        ('j.nuclphysa.2020.121992.xml', 'j.nuclphysa.2020.121992_expected.yml'),
+    ],
+)
 def records(request):
     return {
         'elsevier': get_parser_by_file(request.param[0]),
@@ -97,11 +100,7 @@ def records(request):
     'journal_issue',
     'is_conference_paper',
 ]
-FIELDS_TO_CHECK_SEPARATELY = [
-    'publication_date',
-    'documents',
-    'collaborations'
-]
+FIELDS_TO_CHECK_SEPARATELY = ['publication_date', 'documents', 'collaborations']
 
 
 def test_data_completeness(records):
@@ -110,10 +109,7 @@ def test_data_completeness(records):
         assert field in tested_fields
 
 
-@pytest.mark.parametrize(
-    'field_name',
-    FIELDS_TO_CHECK
-)
+@pytest.mark.parametrize('field_name', FIELDS_TO_CHECK)
 def test_field(field_name, records):
     result = getattr(records['elsevier'], field_name)
     expected = records['expected'][field_name]
@@ -148,8 +144,7 @@ def test_parse(records):
 def test_attach_fulltext_document(records):
     parser = records['elsevier']
     parser.attach_fulltext_document(
-        records['file_name'],
-        'http://example.org/{}'.format(records['file_name'])
+        records['file_name'], 'http://example.org/{}'.format(records['file_name'])
     )
     result = parser.parse()
     assert result['documents'] == records['expected']['documents']
diff --git a/tests/test_parsers_jats.py b/tests/test_parsers_jats.py
index d222dab..a7c420b 100644
--- a/tests/test_parsers_jats.py
+++ b/tests/test_parsers_jats.py
@@ -55,13 +55,16 @@ def get_parser_by_file(filename):
     return JatsParser(aps_jats)
 
 
-@pytest.fixture(scope='module', params=[
-    ('PhysRevD.102.014505.xml', 'PhysRevD.102.014505_expected.yml'),
-    ('PhysRevX.7.021022.xml', 'PhysRevX.7.021022_expected.yml'),
-    ('PhysRevX.4.021018.xml', 'PhysRevX.4.021018_expected.yml'),
-    ('PhysRevD.96.095036.xml', 'PhysRevD.96.095036_expected.yml'),
-    ('PhysRevX.7.021021.xml', 'PhysRevX.7.021021_expected.yml'),
-])
+@pytest.fixture(
+    scope='module',
+    params=[
+        ('PhysRevD.102.014505.xml', 'PhysRevD.102.014505_expected.yml'),
+        ('PhysRevX.7.021022.xml', 'PhysRevX.7.021022_expected.yml'),
+        ('PhysRevX.4.021018.xml', 'PhysRevX.4.021018_expected.yml'),
+        ('PhysRevD.96.095036.xml', 'PhysRevD.96.095036_expected.yml'),
+        ('PhysRevX.7.021021.xml', 'PhysRevX.7.021021_expected.yml'),
+    ],
+)
 def records(request):
     return {
         'jats': get_parser_by_file(request.param[0]),
@@ -105,10 +108,7 @@ def test_data_completeness(records):
         assert field in tested_fields
 
 
-@pytest.mark.parametrize(
-    'field_name',
-    FIELDS_TO_CHECK
-)
+@pytest.mark.parametrize('field_name', FIELDS_TO_CHECK)
 def test_field(field_name, records):
     result = getattr(records['jats'], field_name)
     expected = records['expected'][field_name]
@@ -145,8 +145,7 @@ def test_parse(records):
 def test_attach_fulltext_document(records):
     parser = records['jats']
     parser.attach_fulltext_document(
-        records['file_name'],
-        'http://example.org/{}'.format(records['file_name'])
+        records['file_name'], 'http://example.org/{}'.format(records['file_name'])
     )
     result = parser.parse()
 
diff --git a/tests/test_record.py b/tests/test_record.py
index 31e65c3..1cdbb68 100644
--- a/tests/test_record.py
+++ b/tests/test_record.py
@@ -74,9 +74,7 @@ def test_get_value_allows_slices_in_paths():
 
 
 def test_get_value_returns_none_if_inner_key_does_not_exist_on_string():
-    record = {
-        'foo': 'bar'
-    }
+    record = {'foo': 'bar'}
 
     result = get_value(record, 'foo.value')
 
diff --git a/tests/test_urls.py b/tests/test_urls.py
index aac1c37..eccc167 100644
--- a/tests/test_urls.py
+++ b/tests/test_urls.py
@@ -54,7 +54,7 @@
         'explicit netloc',
         'with scheme, no netloc',
         'without scheme, no netloc',
-    ]
+    ],
 )
 def test_ensure_scheme(url, scheme, expected):
     if scheme:
@@ -86,7 +86,7 @@ def test_ensure_scheme(url, scheme, expected):
         'integer recid, scheme already present',
         'string recid, no scheme',
         'unicode url',
-    ]
+    ],
 )
 def test_record_url_by_pattern(pattern, recid, expected):
     assert record_url_by_pattern(pattern, recid) == expected