pre-commit: introduce codespell check

* codespell --ignore-words-list="ba,datas,fo"

* up-to-date -> uptodate

* Add pre-commit hook...

* Pre-commit needs quotes?

* Single quotes?

* Arrrgggsss

* Update .pre-commit-config.yaml

Co-authored-by: Saugat Pachhai <[email protected]>

Co-authored-by: Saugat Pachhai <[email protected]>

.pre-commit-config.yaml

@@ -7,6 +7,13 @@ repos:
         language_version: python3
     repo: https://github.com/ambv/black
     rev: 21.6b0
+  - hooks:
+      - id: codespell
+        args: 
+          - --ignore-words-list
+          - ba,datas,fo,uptodate
+    repo: https://github.com/codespell-project/codespell
+    rev: v2.1.0
   - hooks:
       - id: isort
         language_version: python3

README.rst

@@ -184,7 +184,7 @@ Comparison to related technologies
 
 #. *Data Engineering* tools such as `AirFlow <https://airflow.apache.org/>`_, `Luigi <https://github.com/spotify/luigi>`_ and
    others - in DVC data, model and ML pipelines represent a single ML project and focuses on data scientist' experience while
-   data engineering pipeline orchestrates multiple data projects and focuses on efficent execution. DVC project can be used
+   data engineering pipeline orchestrates multiple data projects and focuses on efficient execution. DVC project can be used
    from data pipeline as a single execution step. `AirFlow DVC <https://github.com/covid-genomics/airflow-dvc>`_ is an example
    of such integration.
 

dvc/dagascii.py

@@ -163,7 +163,7 @@ class AsciiCanvas:
         self.point(x0 + width, y0 + height, "+")
 
 
-def _build_sugiyama_layout(vertexes, edges):
+def _build_sugiyama_layout(vertices, edges):
     #
     # Just a reminder about naming conventions:
     # +------------X
@@ -174,17 +174,17 @@ def _build_sugiyama_layout(vertexes, edges):
     # Y
     #
 
-    vertexes = {v: Vertex(f" {v} ") for v in vertexes}
+    vertices = {v: Vertex(f" {v} ") for v in vertices}
     # NOTE: reverting edges to correctly orientate the graph
-    edges = [Edge(vertexes[e], vertexes[s]) for s, e in edges]
-    vertexes = vertexes.values()
-    graph = Graph(vertexes, edges)
+    edges = [Edge(vertices[e], vertices[s]) for s, e in edges]
+    vertices = vertices.values()
+    graph = Graph(vertices, edges)
 
-    for vertex in vertexes:
+    for vertex in vertices:
         vertex.view = VertexViewer(vertex.data)
 
     # NOTE: determine min box length to create the best layout
-    minw = min(v.view.w for v in vertexes)
+    minw = min(v.view.w for v in vertices)
 
     for edge in edges:
         edge.view = EdgeViewer()
@@ -204,11 +204,11 @@ def _build_sugiyama_layout(vertexes, edges):
     return sug
 
 
-def draw(vertexes, edges):
+def draw(vertices, edges):
     """Build a DAG and draw it in ASCII.
 
     Args:
-        vertexes (list): list of graph vertexes.
+        vertices (list): list of graph vertices.
         edges (list): list of graph edges.
     """
     # pylint: disable=too-many-locals
@@ -217,7 +217,7 @@ def draw(vertexes, edges):
     Xs = []  # pylint: disable=invalid-name
     Ys = []  # pylint: disable=invalid-name
 
-    sug = _build_sugiyama_layout(vertexes, edges)
+    sug = _build_sugiyama_layout(vertices, edges)
 
     for vertex in sug.g.sV:
         # NOTE: moving boxes w/2 to the left

dvc/fs/azure.py

@@ -25,7 +25,7 @@ _DEFAULT_CREDS_STEPS = (
 
 @contextmanager
 def _temp_event_loop():
-    """When trying to initalize azure filesystem instances
+    """When trying to initialize azure filesystem instances
     with DefaultCredentials, the authentication process requires
     to have an access to a separate event loop. The normal calls
     are run in a separate loop managed by the fsspec, but the

dvc/fs/fsspec_wrapper.py

@@ -48,7 +48,7 @@ class FSSpecWrapper(BaseFileSystem):
             yield entry
 
     def _entry_hook(self, entry):
-        """Simple hook method to be overriden when wanted to process
+        """Simple hook method to be overridden when wanted to process
         entries within info() and ls(detail=True) calls"""
         return entry
 

dvc/repo/experiments/__init__.py

@@ -753,7 +753,7 @@ class Experiments:
         assert entry.index == 0
 
         # NOTE: the stash commit to be popped already contains all the current
-        # workspace changes plus CLI modifed --params changes.
+        # workspace changes plus CLI modified --params changes.
         # `checkout --force` here will not lose any data (popping stash commit
         # will result in conflict between workspace params and stashed CLI
         # params, but we always want the stashed version).

dvc/scm/git/backend/base.py

@@ -187,7 +187,7 @@ class BaseGitBackend(ABC):
 
     @abstractmethod
     def get_refs_containing(self, rev: str, pattern: Optional[str] = None):
-        """Iterate over all git refs containing the specfied revision."""
+        """Iterate over all git refs containing the specified revision."""
 
     @abstractmethod
     def push_refspec(

scripts/innosetup/setup.iss

@@ -34,7 +34,7 @@ Source: "{#MyAppDir}\*"; DestDir: "{app}"; Flags: ignoreversion recursesubdirs c
 
 [Tasks]
 Name: modifypath; Description: Adds dvc's application directory to environmental path; Flags: checkablealone;
-Name: modifypath\system; Description: Adds dvc's application directory to enviromental path for all users;
+Name: modifypath\system; Description: Adds dvc's application directory to environmental path for all users;
 Name: addsymlinkpermissions; Description: Add permission for creating symbolic links; Flags: checkablealone;
 Name: addsymlinkpermissions\system; Description: Add permissions for creating symbolic links for all users;
 

tests/func/plots/test_show.py

@@ -571,7 +571,7 @@ def test_raise_on_wrong_field(tmp_dir, scm, dvc, run_copy_metrics):
 
 
 def test_load_metric_from_dict_json(tmp_dir):
-    metric = [{"acccuracy": 1, "loss": 2}, {"accuracy": 3, "loss": 4}]
+    metric = [{"accuracy": 1, "loss": 2}, {"accuracy": 3, "loss": 4}]
     dmetric = {"train": metric}
 
     plot_data = JSONPlotData("-", "revision", json.dumps(dmetric))
@@ -584,7 +584,7 @@ def test_load_metric_from_dict_json(tmp_dir):
 
 
 def test_load_metric_from_dict_yaml(tmp_dir):
-    metric = [{"acccuracy": 1, "loss": 2}, {"accuracy": 3, "loss": 4}]
+    metric = [{"accuracy": 1, "loss": 2}, {"accuracy": 3, "loss": 4}]
     dmetric = {"train": metric}
 
     plot_data = YAMLPlotData("-", "revision", dumps_yaml(dmetric))

tests/func/test_status.py

@@ -49,7 +49,7 @@ def test_status_non_dvc_repo_import(tmp_dir, dvc, git_dir):
 
 
 def test_status_before_and_after_dvc_init(tmp_dir, dvc, git_dir):
-    git_dir.scm_gen("file", "first version", commit="first verison")
+    git_dir.scm_gen("file", "first version", commit="first version")
     old_rev = git_dir.scm.get_rev()
 
     dvc.imp(os.fspath(git_dir), "file", "file")