Add codespell config and workflow and fix a few typos (#129)

* Add github action to codespell main on push and PRs

* Add rudimentary codespell config

* ignore all resources and sie variable and OGER name

* [DATALAD RUNCMD] run codespell throughout but ignore fail

=== Do not change lines below ===
{
 "chain": [],
 "cmd": "codespell -w || :",
 "exit": 0,
 "extra_inputs": [],
 "inputs": [],
 "outputs": [],
 "pwd": "."
}
^^^ Do not change lines above ^^^

* [DATALAD RUNCMD] Do interactive fixing of typos

=== Do not change lines below ===
{
 "chain": [],
 "cmd": "codespell -w -i 3 -C 2",
 "exit": 0,
 "extra_inputs": [],
 "inputs": [],
 "outputs": [],
 "pwd": "."
}
^^^ Do not change lines above ^^^

.github/workflows/codespell.yml

@@ -0,0 +1,23 @@
+# Codespell configuration is within pyproject.toml
+---
+name: Codespell
+
+on:
+  push:
+    branches: [main]
+  pull_request:
+    branches: [main]
+
+permissions:
+  contents: read
+
+jobs:
+  codespell:
+    name: Check for spelling errors
+    runs-on: ubuntu-latest
+
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v4
+      - name: Codespell
+        uses: codespell-project/actions-codespell@v2

CONTRIBUTING.md

@@ -78,7 +78,7 @@ that you can use as a starting point.
 
 ## How to Request an Enhancement
 
-We welcome request for enhancements and you can make these requestes via the issue tracker. Please be sure to provide
+We welcome request for enhancements and you can make these requests via the issue tracker. Please be sure to provide
 sufficient context to what the enhancement is trying to address, its utility, and how it's likely to be useful to you
 and the broader community.
 

pyproject.toml

@@ -57,3 +57,10 @@ extract-schema = "schema_automator.utils.schema_extractor:cli"
 [tool.poetry.extras]
 docs = ["Sphinx", "sphinx-pdj-theme", "sphinxcontrib-mermaid"]
 mariadb = ["mariadb"]
+
+[tool.codespell]
+# Ref: https://github.com/codespell-project/codespell#using-a-config-file
+skip = '.git,*.lock,resources'
+check-hidden = true
+ignore-regex = '\bOGER\b'
+ignore-words-list = 'sie'

schema_automator/annotators/enum_annotator.py

@@ -214,7 +214,7 @@ def get_ols_term_annotations(iri_param, ontology_param, session_param, ols_terms
               default=2, show_default=True)
 @click.option('--max_cosine',
               help="""how much of a cosine distance will you tolerate 
-              when comparing an enum name to a term lable or synonym?""",
+              when comparing an enum name to a term label or synonym?""",
               default=0.05, show_default=True)
 @click.option('--query_field_string',
               help="""do you want to define a custom list of fields to search in? 

schema_automator/cli.py

@@ -447,7 +447,7 @@ def import_owl(owlfile, output, **args):
 @click.option('--identifier', '-I', help="Slot to use as identifier")
 @click.option('--model-uri', help="Model URI prefix")
 @click.option('--metamodel-mappings',
-              help="Path to metamodel mappings YAML dicitonary")
+              help="Path to metamodel mappings YAML dictionary")
 @click.option('--output', '-o', help="Path to saved yaml schema")
 def import_rdfs(rdfsfile, output, metamodel_mappings, **args):
     """

schema_automator/generalizers/csv_data_generalizer.py

@@ -86,7 +86,7 @@ class CsvDataGeneralizer(Generalizer):
     """If number if distinct values divided by total number of values is greater than this, then the column is considered an enum"""
 
     enum_strlen_threshold: int = 30
-    """Maximimum length of a string to be considered a permissible enum value"""
+    """Maximum length of a string to be considered a permissible enum value"""
 
     max_enum_size: int = 50
     """Max number of permissible values for a column to be considered an enum"""

schema_automator/metamodels/dosdp/dosdp_linkml.yaml

@@ -117,7 +117,7 @@ classes:
         inlined: true
         range: VarDeclaration
       list_vars:
-        description: A dictionary of variables refering to lists of owl classes. Key
+        description: A dictionary of variables referring to lists of owl classes. Key
           = variable name, value = variable range of items in list specified as a
           valid OWL data-type.
       data_vars:
@@ -522,7 +522,7 @@ slots:
     description: 'A dictionary of OWL annotation properties key : label; value : short
       form id'
   list_vars:
-    description: A dictionary of variables refering to lists of owl classes. Key =
+    description: A dictionary of variables referring to lists of owl classes. Key =
       variable name, value = variable range of items in list specified as a valid
       OWL data-type.
   data_vars: