Implement clean up strategies

Makefile

@@ -307,10 +307,9 @@ docserve: gen-docs
 	$(RUN) mkdocs serve
 
 
-# Regenerate from Google Sheets. Note that this uses a *separate* Pipenv in the
-# generators/google-sheets directory, so we have to run pipenv install on it separately.
+# Generate LinkML schema from Google Sheet data model using sheet2linkml.
 generate-model: install install-dev
-	CDM_GOOGLE_SHEET_ID=$(CDM_GOOGLE_SHEET_ID) $(RUN) python vendor/sheet2linkml/sheet2linkml.py --output model/schema/crdch_model.yaml
+	CDM_GOOGLE_SHEET_ID=$(CDM_GOOGLE_SHEET_ID) $(RUN) sheet2linkml --output linkml_model/schema/crdch_model.yaml --logging-config ./logging.ini
 
 # MAM 20210806 not sure how this fits into the linkml model template's doc building/publsihing approach
 # Deploy changes to the `dev` version on the gh-pages branch.

Pipfile

@@ -7,29 +7,20 @@ name = "pypi"
 # For LinkML, we use the `ccdh-dev` branch, which we manually keep in sync with LinkML's main branch
 # as well as some additional changes required for CRDCH generation.
 linkml = {editable = true, ref = "ccdh-dev", git = "https://github.com/cancerDHC/linkml.git"}
-
 # Since we use the development version of LinkML, we also use the development version of linkml-runtime.
 # This may sometimes cause issues between this and LinkML.
 linkml-runtime = {editable = true, git = "https://github.com/linkml/linkml-runtime.git"}
-
 pyparsing = "<=2.4.7"
 rdflib-pyld-compat = "*" # resinstating after removal by migration to linkml model template
+sheet2linkml = ">=1.1.0"  # used for converting spreadsheet data model to LinkML schema
 
 [dev-packages]
 pyyaml = "*"            # For reading and writing YAML files.
-
 # Packages needed for testing.
 pytest = "~=6.2.4"
 tox = "*"
 typing_extensions = "*" # This is a tox prereq for Python 3.7, but not installed by Pipenv.
 twine = "*" # should this go in make-venv/Pipfile ?
-
-# Packages needed by sheet2linkml.
-black = "==v21.5b1"     # Used for code linting.
-requests = "*"          # For making HTTP requests.
-pygsheets = "*"         # For accessing Google Sheets.
-python-dotenv = "*"     # For reading .env files.
-
 # Packages needed for building and publishing documentation.
 mike = "*"
 mkdocs-material = "*"

README.md

@@ -4,15 +4,14 @@ This repository stores the [LinkML](https://linkml.github.io/) representation of
 
 This repository includes [the LinkML model itself](./model/schema/crdch_model.yaml) (in [YAML](https://en.wikipedia.org/wiki/YAML) format) as well as a number of artifacts produced automatically by LinkML, including a JSON Schema, JSON-LD context, a GraphQL description, a CSV description and ShEx validation shapes.
 
-Model documentation in Markdown can also be generated for this repository, and is currently hosted on GitHub Pages at https://cancerdhc.github.io/ccdhmodel/. A set of Python Data Classes can also be generated and are [available for use](./crdch_model/crdch_model.py). Examples of their use are available in the [Example Data](https://github.com/cancerDHC/example-data/) repository.
+Model documentation in Markdown can also be generated for this repository, and is currently hosted on [GitHub Pages](https://cancerdhc.github.io/ccdhmodel/). A set of Python Data Classes can also be generated and are [available for use](./crdch_model/crdch_model.py). Examples of their use are available in the [Example Data](https://github.com/cancerDHC/example-data/) repository.
 
 ## Setup
 
-### Automated generation of YAML
+### Automated generation of LinkML YAML
 
 The CRDC-H model is currently in development on [a Google Sheet](https://docs.google.com/spreadsheets/d/1oWS7cao-fgz2MKWtyr8h2dEL9unX__0bJrWKv6mQmM4/).
-This repository contains a program in the [`./vendor/sheet2linkml`](./vendor/sheet2linkml) directory
-that can read the Google Sheet using the Google Drive API and generate a LinkML representation of the model.
+The [sheet2linkml](https://github.com/cancerDHC/sheet2linkml/) package can read the Google Sheet and generate a LinkML representation of the model.
 
 In order to run this program, you will need to create and download Google Drive client credentials. First,
 [enable the Google Drive API](https://developers.google.com/drive/api/v3/enable-drive-api). After the API is enabled, 
@@ -22,9 +21,15 @@ the root directory of this project. [Detailed instructions and screenshots](http
 are also available from the [`pygsheets` documentation](https://pygsheets.readthedocs.io/), which is the package we use to
 access Google Sheets.
 
-Once this is setup, run `make generate-model` to update the schema from Google Sheets. The first time you run this script,
+Once this is setup, run from the root of the project:
+
+```
+make generate-model
+```
+
+to create the schema from Google Sheet. The first time you run this script,
 you will see a browser page asking you to log in. Follow the instructions. The script will download a token and store it
-locally. You won't need to log in in the future.
+locally, so you won't need to login again after that.
 
 ### Generation of LinkML artifacts