Add pre-commit (scrapy#70)

.git-blame-ignore-revs

@@ -0,0 +1,2 @@
+# Apply black format
+627f3bd9ea5210f40dbd5697eff9351bb5af019c

.github/workflows/main.yml

@@ -3,6 +3,15 @@ on:
 - pull_request
 - push
 jobs:
+  pre-commit:
+    runs-on: ubuntu-latest
+    steps:
+    - uses: actions/checkout@v3
+    - uses: actions/setup-python@v3
+      with:
+        python-version: "3.11"
+    - uses: pre-commit/action@v3.0.0
+
   tests:
     runs-on: ubuntu-latest
     strategy:

.pre-commit-config.yaml

@@ -0,0 +1,24 @@
+default_language_version:
+    python: python3.10
+repos:
+  - hooks:
+      - id: black
+        language_version: python3
+    repo: https://github.com/ambv/black
+    rev: 23.3.0
+  - hooks:
+      - id: isort
+        language_version: python3
+    repo: https://github.com/PyCQA/isort
+    rev: 5.12.0
+  - hooks:
+      - id: flake8
+        language_version: python3
+        additional_dependencies:
+          - flake8-bugbear
+          - flake8-comprehensions
+          - flake8-debugger
+          - flake8-docstrings
+          - flake8-string-format
+    repo: https://github.com/pycqa/flake8
+    rev: 6.0.0

README.rst

@@ -73,4 +73,5 @@ All contributions are welcome!
    * File an `issue here <https://github.com/scrapy/itemloaders/issues>`_, if there isn't one yet
    * Fork this repository
    * Create a branch to work on your changes
+   * Run `pre-commit install` to install pre-commit hooks
    * Push your local branch and submit a Pull Request

docs/_ext/__init__.py

@@ -1 +0,0 @@
-

docs/_ext/github.py

@@ -1,19 +1,31 @@
+from typing import Optional
+
 from docutils import nodes
 from docutils.parsers.rst.roles import set_classes
 
 
 def setup(app):
-    app.add_role('gh', github_role)
+    app.add_role("gh", github_role)
 
 
-def github_role(name, rawtext, text, lineno, inliner, options={}, content=[]):
+def github_role(
+    name,
+    rawtext,
+    text,
+    lineno,
+    inliner,
+    options: Optional[dict] = None,
+    content: Optional[list] = None,
+):
+    options = options or {}
+    content = content or []
     if text.isdigit():
-        display_text = f'#{text}'
-        url = f'https://github.com/scrapy/itemloaders/issues/{text}'
+        display_text = f"#{text}"
+        url = f"https://github.com/scrapy/itemloaders/issues/{text}"
     else:
         short_commit = text[:7]
         display_text = short_commit
-        url = f'https://github.com/scrapy/itemloaders/commit/{short_commit}'
+        url = f"https://github.com/scrapy/itemloaders/commit/{short_commit}"
 
     set_classes(options)
     node = nodes.reference(rawtext, display_text, refuri=url, **options)

docs/conf.py

@@ -15,6 +15,8 @@
 from datetime import datetime
 from os import path
 
+import sphinx_rtd_theme
+
 # If your extensions are in another directory, add it here. If the directory
 # is relative to the documentation root, use os.path.abspath to make it
 # absolute, like shown here.
@@ -27,90 +29,90 @@
 # Add any Sphinx extension module names here, as strings. They can be extensions
 # coming with Sphinx (named 'sphinx.ext.*') or your custom ones.
 extensions = [
-    '_ext.github',
-    'sphinx.ext.autodoc',
-    'sphinx.ext.coverage',
-    'sphinx.ext.intersphinx',
-    'sphinx.ext.viewcode',
+    "_ext.github",
+    "sphinx.ext.autodoc",
+    "sphinx.ext.coverage",
+    "sphinx.ext.intersphinx",
+    "sphinx.ext.viewcode",
 ]
 
 # Add any paths that contain templates here, relative to this directory.
-templates_path = ['_templates']
+templates_path = ["_templates"]
 
 # The suffix of source filenames.
-source_suffix = '.rst'
+source_suffix = ".rst"
 
 # The encoding of source files.
-#source_encoding = 'utf-8'
+# source_encoding = 'utf-8'
 
 # The master toctree document.
-master_doc = 'index'
+master_doc = "index"
 
 # General information about the project.
-project = 'itemloaders'
-copyright = '2020–{}, Zyte Group Ltd'.format(datetime.now().year)
+project = "itemloaders"
+copyright = "2020–{}, Zyte Group Ltd".format(datetime.now().year)
 
 # The version info for the project you're documenting, acts as replacement for
 # |version| and |release|, also used in various other places throughout the
 # built documents.
 #
 # The short X.Y version.
-version = ''
-release = ''
+version = ""
+release = ""
 
 # The language for content autogenerated by Sphinx. Refer to documentation
 # for a list of supported languages.
-language = 'en'
+language = "en"
 
 # There are two options for replacing |today|: either, you set today to some
 # non-false value, then it is used:
-#today = ''
+# today = ''
 # Else, today_fmt is used as the format for a strftime call.
-#today_fmt = '%B %d, %Y'
+# today_fmt = '%B %d, %Y'
 
 # List of documents that shouldn't be included in the build.
-#unused_docs = []
+# unused_docs = []
 
-exclude_patterns = ['build']
+exclude_patterns = ["build"]
 
 # List of directories, relative to source directory, that shouldn't be searched
 # for source files.
-exclude_trees = ['.build']
+exclude_trees = [".build"]
 
 # The reST default role (used for this markup: `text`) to use for all documents.
-#default_role = None
+# default_role = None
 
 # If true, '()' will be appended to :func: etc. cross-reference text.
-#add_function_parentheses = True
+# add_function_parentheses = True
 
 # If true, the current module name will be prepended to all description
 # unit titles (such as .. function::).
-#add_module_names = True
+# add_module_names = True
 
 # If true, sectionauthor and moduleauthor directives will be shown in the
 # output. They are ignored by default.
-#show_authors = False
+# show_authors = False
 
 # The name of the Pygments (syntax highlighting) style to use.
-pygments_style = 'sphinx'
+pygments_style = "sphinx"
 
 
 # Options for HTML output
 # -----------------------
 
 # The theme to use for HTML and HTML Help pages.  See the documentation for
 # a list of builtin themes.
-html_theme = 'sphinx_rtd_theme'
+html_theme = "sphinx_rtd_theme"
 
 # Theme options are theme-specific and customize the look and feel of a theme
 # further.  For a list of options available for each theme, see the
 # documentation.
-#html_theme_options = {}
+# html_theme_options = {}
 
 # Add any paths that contain custom themes here, relative to this directory.
 # Add path to the RTD explicitly to robustify builds (otherwise might
 # fail in a clean Debian build env)
-import sphinx_rtd_theme
+
 html_theme_path = [sphinx_rtd_theme.get_html_theme_path()]
 
 
@@ -121,19 +123,19 @@
 
 # The name for this set of Sphinx documents.  If None, it defaults to
 # "<project> v<release> documentation".
-#html_title = None
+# html_title = None
 
 # A shorter title for the navigation bar.  Default is the same as html_title.
-#html_short_title = None
+# html_short_title = None
 
 # The name of an image file (relative to this directory) to place at the top
 # of the sidebar.
-#html_logo = None
+# html_logo = None
 
 # The name of an image file (within the static path) to use as favicon of the
 # docs.  This file should be a Windows icon file (.ico) being 16x16 or 32x32
 # pixels large.
-#html_favicon = None
+# html_favicon = None
 
 # Add any paths that contain custom static files (such as style sheets) here,
 # relative to this directory. They are copied after the builtin static files,
@@ -142,92 +144,92 @@
 
 # If not '', a 'Last updated on:' timestamp is inserted at every page bottom,
 # using the given strftime format.
-html_last_updated_fmt = '%b %d, %Y'
+html_last_updated_fmt = "%b %d, %Y"
 
 # Custom sidebar templates, maps document names to template names.
-#html_sidebars = {}
+# html_sidebars = {}
 
 # Additional templates that should be rendered to pages, maps page names to
 # template names.
-#html_additional_pages = {}
+# html_additional_pages = {}
 
 # If false, no module index is generated.
-#html_use_modindex = True
+# html_use_modindex = True
 
 # If false, no index is generated.
-#html_use_index = True
+# html_use_index = True
 
 # If true, the index is split into individual pages for each letter.
-#html_split_index = False
+# html_split_index = False
 
 # If true, the reST sources are included in the HTML build as _sources/<name>.
 html_copy_source = True
 
 # If true, an OpenSearch description file will be output, and all pages will
 # contain a <link> tag referring to it.  The value of this option must be the
 # base URL from which the finished HTML is served.
-#html_use_opensearch = ''
+# html_use_opensearch = ''
 
 # If nonempty, this is the file name suffix for HTML files (e.g. ".xhtml").
-#html_file_suffix = ''
+# html_file_suffix = ''
 
 # Output file base name for HTML help builder.
-htmlhelp_basename = 'itemloadersdoc'
+htmlhelp_basename = "itemloadersdoc"
 
 
 # Options for LaTeX output
 # ------------------------
 
 # The paper size ('letter' or 'a4').
-#latex_paper_size = 'letter'
+# latex_paper_size = 'letter'
 
 # The font size ('10pt', '11pt' or '12pt').
-#latex_font_size = '10pt'
+# latex_font_size = '10pt'
 
 # Grouping the document tree into LaTeX files. List of tuples
 # (source start file, target name, title, author, document class [howto/manual]).
 latex_documents = [
-  ('index', 'itemloaders.tex', 'itemloaders Documentation', 'Zyte', 'manual'),
+    ("index", "itemloaders.tex", "itemloaders Documentation", "Zyte", "manual"),
 ]
 
 # The name of an image file (relative to this directory) to place at the top of
 # the title page.
-#latex_logo = None
+# latex_logo = None
 
 # For "manual" documents, if this is true, then toplevel headings are parts,
 # not chapters.
-#latex_use_parts = False
+# latex_use_parts = False
 
 # Additional stuff for the LaTeX preamble.
-#latex_preamble = ''
+# latex_preamble = ''
 
 # Documents to append as an appendix to all manuals.
-#latex_appendices = []
+# latex_appendices = []
 
 # If false, no module index is generated.
-#latex_use_modindex = True
+# latex_use_modindex = True
 
 
 # autodocs
 
 
 def setup(app):
-    app.connect('autodoc-skip-member', maybe_skip_member)
+    app.connect("autodoc-skip-member", maybe_skip_member)
 
 
 def maybe_skip_member(app, what, name, obj, skip, options):
     if not skip:
         # autodocs was generating a text "alias of" for the following members
         # https://github.com/sphinx-doc/sphinx/issues/4422
-        return name in {'default_item_class', 'default_selector_class'}
+        return name in {"default_item_class", "default_selector_class"}
     return skip
 
 
 nitpicky = True
 
 intersphinx_mapping = {
-    'parsel': ('https://parsel.readthedocs.io/en/stable/', None),
-    'python': ('https://docs.python.org/3', None),
-    'scrapy': ('https://docs.scrapy.org/en/latest/', None),
-    'w3lib': ('https://w3lib.readthedocs.io/en/latest', None),
+    "parsel": ("https://parsel.readthedocs.io/en/stable/", None),
+    "python": ("https://docs.python.org/3", None),
+    "scrapy": ("https://docs.scrapy.org/en/latest/", None),
+    "w3lib": ("https://w3lib.readthedocs.io/en/latest", None),
 }

itemloaders/__init__.py

@@ -245,7 +245,7 @@ def get_value(self, value, *processors, re=None, **kw):
                 raise ValueError(
                     "Error with processor %s value=%r error='%s: %s'"
                     % (_proc.__class__.__name__, value, type(e).__name__, str(e))
-                )
+                ) from e
         return value
 
     def load_item(self):
@@ -276,7 +276,7 @@ def get_output_value(self, field_name):
             raise ValueError(
                 "Error with output processor: field=%r value=%r error='%s: %s'"
                 % (field_name, value, type(e).__name__, str(e))
-            )
+            ) from e
 
     def get_collected_values(self, field_name):
         """Return the collected values for the given field."""
@@ -319,7 +319,7 @@ def _process_input_value(self, field_name, value):
                     type(e).__name__,
                     str(e),
                 )
-            )
+            ) from e
 
     def _check_selector_method(self):
         if self.selector is None:

itemloaders/common.py

@@ -1,14 +1,15 @@
 """Common functions used in Item Loaders code"""
 
 from functools import partial
+
 from itemloaders.utils import get_func_args
 
 
 def wrap_loader_context(function, context):
     """Wrap functions that receive loader_context to contain the context
     "pre-loaded" and expose a interface that receives only one argument
     """
-    if 'loader_context' in get_func_args(function):
+    if "loader_context" in get_func_args(function):
         return partial(function, loader_context=context)
     else:
         return function