Merge pull request datajoint#1093 from yarikoptic/enh-codespell

kabilar · web-flow · commit 0392b801011d · 2023-06-27T17:21:11.000-05:00
codespell: workflow, config + typos fixed
diff --git a/.codespellrc b/.codespellrc
@@ -0,0 +1,5 @@
+[codespell]
+skip = .git,*.pdf,*.svg,*.csv,*.ipynb,*.drawio
+# Rever -- nobody knows
+# numer -- numerator variable
+ignore-words-list = rever,numer
diff --git a/.github/workflows/codespell.yml b/.github/workflows/codespell.yml
@@ -0,0 +1,22 @@
+---
+name: Codespell
+
+on:
+  push:
+    branches: [master]
+  pull_request:
+    branches: [master]
+
+permissions:
+  contents: read
+
+jobs:
+  codespell:
+    name: Check for spelling errors
+    runs-on: ubuntu-latest
+
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v3
+      - name: Codespell
+        uses: codespell-project/actions-codespell@v2
diff --git a/CHANGELOG.md b/CHANGELOG.md
@@ -31,7 +31,7 @@
 - Fixed - Fix queries with backslashes ([#999](https://github.com/datajoint/datajoint-python/issues/999)) PR [#1052](https://github.com/datajoint/datajoint-python/pull/1052)
 
 ### 0.13.7 -- Jul 13, 2022
-- Fixed - Fix networkx incompatable change by version pinning to 2.6.3 (#1035) PR #1036
+- Fixed - Fix networkx incompatible change by version pinning to 2.6.3 (#1035) PR #1036
 - Added - Support for serializing numpy datetime64 types (#1022) PR #1036
 - Changed - Add traceback to default logging PR #1036
 
@@ -83,7 +83,7 @@
 - Fixed - `schema.list_tables()` is not topologically sorted (#838) PR #893
 - Fixed - Diagram part tables do not show proper class name (#882) PR #893
 - Fixed - Error in complex restrictions (#892) PR #893
-- Fixed - WHERE and GROUP BY clases are dropped on joins with aggregation (#898, #899) PR #893
+- Fixed - WHERE and GROUP BY classes are dropped on joins with aggregation (#898, #899) PR #893
 
 ### 0.13.0 -- Mar 24, 2021
 - Re-implement query transpilation into SQL, fixing issues (#386, #449, #450, #484, #558). PR #754
diff --git a/LNX-docker-compose.yml b/LNX-docker-compose.yml
@@ -44,7 +44,7 @@ services:
       interval: 15s
   fakeservices.datajoint.io:
     <<: *net
-    image: datajoint/nginx:v0.2.5
+    image: datajoint/nginx:v0.2.6
     environment:
       - ADD_db_TYPE=DATABASE
       - ADD_db_ENDPOINT=db:3306
diff --git a/datajoint/__init__.py b/datajoint/__init__.py
@@ -1,5 +1,5 @@
 """
-DataJoint for Python is a framework for building data piplines using MySQL databases
+DataJoint for Python is a framework for building data pipelines using MySQL databases
 to represent pipeline structure and bulk storage systems for large objects.
 DataJoint is built on the foundation of the relational data model and prescribes a
 consistent method for organizing, populating, and querying data.
diff --git a/datajoint/autopopulate.py b/datajoint/autopopulate.py
@@ -118,7 +118,7 @@ def _job_key(self, key):
 
     def _jobs_to_do(self, restrictions):
         """
-        :return: the query yeilding the keys to be computed (derived from self.key_source)
+        :return: the query yielding the keys to be computed (derived from self.key_source)
         """
         if self.restriction:
             raise DataJointError(
diff --git a/datajoint/blob.py b/datajoint/blob.py
@@ -449,7 +449,7 @@ def pack_dict(self, d):
         )
 
     def read_struct(self):
-        """deserialize matlab stuct"""
+        """deserialize matlab struct"""
         n_dims = self.read_value()
         shape = self.read_value(count=n_dims)
         n_elem = np.prod(shape, dtype=int)
diff --git a/datajoint/connection.py b/datajoint/connection.py
@@ -113,7 +113,7 @@ def conn(
     :param init_fun: initialization function
     :param reset: whether the connection should be reset or not
     :param use_tls: TLS encryption option. Valid options are: True (required), False
-        (required no TLS), None (TLS prefered, default), dict (Manually specify values per
+        (required no TLS), None (TLS preferred, default), dict (Manually specify values per
         https://dev.mysql.com/doc/refman/5.7/en/connection-options.html#encrypted-connection-options).
     """
     if not hasattr(conn, "connection") or reset:
diff --git a/datajoint/schemas.py b/datajoint/schemas.py
@@ -21,7 +21,7 @@
 
 def ordered_dir(class_):
     """
-    List (most) attributes of the class including inherited ones, similar to `dir` build-in function,
+    List (most) attributes of the class including inherited ones, similar to `dir` built-in function,
     but respects order of attribute declaration as much as possible.
 
     :param class_: class to list members for
diff --git a/datajoint/table.py b/datajoint/table.py
@@ -230,7 +230,7 @@ def ancestors(self, as_objects=False):
 
     def parts(self, as_objects=False):
         """
-        return part tables either as entries in a dict with foreign key informaiton or a list of objects
+        return part tables either as entries in a dict with foreign key information or a list of objects
 
         :param as_objects: if False (default), the output is a dict describing the foreign keys. If True, return table objects.
         """
diff --git a/docs/src/design/diagrams.md b/docs/src/design/diagrams.md
@@ -2,7 +2,7 @@
 
 Diagrams are a great way to visualize all or part of a pipeline and understand the flow
 of data. DataJoint diagrams are based on **entity relationship diagram** (ERD), with
-some minor departures fom this standard. 
+some minor departures from this standard. 
 
 Here, tables are depicted as nodes and [dependencies](./tables/dependencies) as directed edges
 between them. The `draw` method plots the graph, with many other methods ([Python](https://datajoint.com/docs/core/datajoint-python/latest/api/datajoint/diagram/)) to
diff --git a/docs/src/develop.md b/docs/src/develop.md
@@ -83,7 +83,7 @@ black tests --check -v
 
 Jupyter notebooks are supported in this environment. This means that when you `import datajoint`, it will use the current state of the source.
 
-Be sure to see the reference documenation if you are new to [running Jupyter notebooks w/ VSCode](https://code.visualstudio.com/docs/datascience/jupyter-notebooks#_create-or-open-a-jupyter-notebook).
+Be sure to see the reference documentation if you are new to [running Jupyter notebooks w/ VSCode](https://code.visualstudio.com/docs/datascience/jupyter-notebooks#_create-or-open-a-jupyter-notebook).
 
 ### Debugger
 
diff --git a/docs/src/existing-pipelines.md b/docs/src/existing-pipelines.md
@@ -58,7 +58,7 @@ schema.spawn_missing_classes()
 
 While `spawn_missing_classes` creates the new classes in the local namespace, it is
 often more convenient to import a schema with its Python module, equivalent to the
-Python command. We can mimmick this import without having access to the schema using
+Python command. We can mimic this import without having access to the schema using
 the `VirtualModule` class object:
 
 ```python
diff --git a/docs/src/faq.md b/docs/src/faq.md
@@ -23,7 +23,7 @@ languages must comply to the same data model and computation approach as defined
 ## Can I use DataJoint with my current database?
 
 Researchers use many different tools to keep records, from simple formalized file
-heirarchies to complete software packages for colony management and standard file types
+hierarchies to complete software packages for colony management and standard file types
 like NWB. Existing projects have built interfaces with many such tools, such as
 [PyRAT](https://github.com/SFB1089/adamacs/blob/main/notebooks/03_pyrat_insert.ipynb).
 The only requirement for interface is that tool has an open API. Contact
diff --git a/docs/src/getting-started/index.md b/docs/src/getting-started/index.md
@@ -225,7 +225,7 @@ dj.Diagram(schema.Rectangle) + dj.Diagram(schema.Area)
 
 ### Customize
 
-Adding or substracting a number to a diagram object adds nodes downstream or upstream,
+Adding or subtracting a number to a diagram object adds nodes downstream or upstream,
 respectively, in the pipeline.
 
 ``` python
diff --git a/local-docker-compose.yml b/local-docker-compose.yml
@@ -46,7 +46,7 @@ services:
       interval: 15s
   fakeservices.datajoint.io:
     <<: *net
-    image: datajoint/nginx:v0.2.5
+    image: datajoint/nginx:v0.2.6
     environment:
       - ADD_db_TYPE=DATABASE
       - ADD_db_ENDPOINT=db:3306
diff --git a/tests_old/test_blob.py b/tests_old/test_blob.py
@@ -100,7 +100,7 @@ def test_pack():
     y = unpack(pack(x))
     assert_dict_equal(x, y, "Dict do not match!")
     assert_false(
-        isinstance(["range"][0], np.ndarray), "Scalar int was coerced into arrray."
+        isinstance(["range"][0], np.ndarray), "Scalar int was coerced into array."
     )
 
     x = uuid.uuid4()
diff --git a/tests_old/test_fetch.py b/tests_old/test_fetch.py
@@ -360,7 +360,7 @@ def test_fetch_group_by(self):
 
     def test_dj_u_distinct(self):
         # Test developed to see if removing DISTINCT from the select statement
-        # generation breakes the dj.U universal set imlementation
+        # generation breaks the dj.U universal set implementation
 
         # Contents to be inserted
         contents = [(1, 2, 3), (2, 2, 3), (3, 3, 2), (4, 5, 5)]
diff --git a/tests_old/test_university.py b/tests_old/test_university.py
@@ -77,10 +77,10 @@ def test_restrict():
     assert_true(len(s1) == 11)
     assert_list_equal(s1, s2)
 
-    millenials = Student & 'date_of_birth between "1981-01-01" and "1996-12-31"'
-    assert_true(len(millenials) == 170)
-    millenials_no_math = millenials - (Enroll & 'dept="MATH"')
-    assert_true(len(millenials_no_math) == 53)
+    millennials = Student & 'date_of_birth between "1981-01-01" and "1996-12-31"'
+    assert_true(len(millennials) == 170)
+    millennials_no_math = millennials - (Enroll & 'dept="MATH"')
+    assert_true(len(millennials_no_math) == 53)
 
     inactive_students = Student - (Enroll & CurrentTerm)
     assert_true(len(inactive_students) == 204)

Original file line number	Diff line number	Diff line change
`@@ -449,7 +449,7 @@ def pack_dict(self, d):`
`449`	`449`	`)`
`450`	`450`
`451`	`451`	`def read_struct(self):`
`452`		`- """deserialize matlab stuct"""`
	`452`	`+ """deserialize matlab struct"""`
`453`	`453`	`n_dims = self.read_value()`
`454`	`454`	`shape = self.read_value(count=n_dims)`
`455`	`455`	`n_elem = np.prod(shape, dtype=int)`