Merge branch 'dev' into feat/SOF-6914-1

.github/workflows/cicd.yml

@@ -35,7 +35,14 @@ jobs:
     runs-on: ubuntu-20.04
     strategy:
       matrix:
-        python-version: [3.6, 3.7, 3.8]
+        python-version:
+          - 3.8.6
+          - 3.9.x
+          # Enable after resolving Cython/PyYAML issue https://github.com/yaml/pyyaml/issues/724
+          # - 3.10.x
+          # - 3.11.x
+          # Enable after: AttributeError: module 'pkgutil' has no attribute 'ImpImporter'. Did you mean: 'zipimporter'?
+          # - 3.12.x
 
     steps:
       - name: Checkout this repository
@@ -54,13 +61,14 @@ jobs:
         uses: ./actions/py/test
         with:
           python-version: ${{ matrix.python-version }}
-          test-script: src/py/esse/tests/validate.py
 
   run-js-tests:
     runs-on: ubuntu-latest
     strategy:
       matrix:
-        node-version: [14.x, 16.x, 18.x]
+        node-version:
+          - 14.x
+          - 20.x
 
     steps:
       - name: Checkout this repository
@@ -106,13 +114,12 @@ jobs:
       - name: Publish JS release
         uses: ./actions/js/publish
         with:
-          node-version: 12.21.x
           npm-token: ${{ secrets.NPM_TOKEN }}
           github-token: ${{ secrets.BOT_GITHUB_TOKEN }}
 
 
   publish-py-package:
-    needs: publish-js-package
+    needs: [run-py-linter, run-py-tests, run-js-tests]
     runs-on: ubuntu-latest
     if: github.ref_name == 'dev'
 
@@ -137,3 +144,45 @@ jobs:
           pypi-username: ${{ secrets.PYPI_USERNAME }}
           pypi-password: ${{ secrets.PYPI_PASSWORD }}
           publish-tag: 'false'
+
+  deploy-docs:
+    needs: [publish-py-package, publish-js-package]
+    runs-on: ubuntu-latest
+    strategy:
+      matrix:
+        node-version:
+          - 20.x
+    steps:
+      - uses: actions/checkout@v4
+        with:
+          lfs: true
+
+      - name: Setup NodeJS
+        uses: actions/setup-node@v4
+        with:
+          node-version: ${{ matrix.node-version }}
+          registry-url: https://registry.npmjs.org
+
+      - name: Build
+        shell: bash -l {0}
+        run: |
+          npm install
+          echo "Building Schemas and Examples"
+          npm run build:assets-with-docs
+          echo "List build directory ./docs/js"
+          ls -l docs/js
+
+      - name: Generate Directory Listings
+        uses: jayanta525/github-pages-directory-listing@v4.0.0
+        with:
+          FOLDER: docs/js      #directory to generate index
+
+      - name: Deploy
+        uses: peaceiris/actions-gh-pages@v3
+        # If you're changing the branch from main,
+        # also change the `main` in `refs/heads/main`
+        # below accordingly.
+        # if: github.ref == 'refs/heads/main'
+        with:
+          github_token: ${{ secrets.GITHUB_TOKEN }}
+          publish_dir: ./docs/js

.gitignore

@@ -53,7 +53,11 @@ dist/
 .nyc_output
 .eslintcache
 
-.husky
+.husky/*
+!.husky/pre-commit
 
 schemas.js
 schema.js
+
+# Static assets, if any
+site

.husky/pre-commit

@@ -0,0 +1,14 @@
+#!/bin/sh
+. "$(dirname "$0")/_/husky.sh"
+
+SRC_PATTERN="\.json$"
+if git diff --cached --name-only | grep --quiet -E "$SRC_PATTERN"
+then
+  echo "JSON assets changed. Running build scripts."
+  echo "Re-building JS assets."
+  npm run build:assets
+  echo "Re-building Python assets: requires virtual environment and dependencies (pip install .'[tests]')."
+  python build_schemas.py
+fi
+
+npx lint-staged

.pre-commit-config.yaml

@@ -3,4 +3,18 @@ repos:
     rev: 2023.6.13
     hooks:
       - id: ruff
+        exclude: ^src/py/mat3ra/esse/data
       - id: black
+        exclude: ^src/py/mat3ra/esse/data
+  - repo: local
+    hooks:
+      - id: generate-python-modules
+        name: Regenerate data modules classes from static assets
+        # yamllint disable rule:line-length
+        entry: |
+          bash -c 'if ! [ "$(git diff --cached --name-only | grep -e "example|schema")" ]; then echo "Skipping model generation because static files were not changed."; exit 0; fi'
+          bash -c 'python build_schemas.py'
+        # yamllint enable rule:line-length
+        language: system
+        pass_filenames: false
+        verbose: true

README.md

@@ -4,127 +4,154 @@
 
 # ESSE
 
-Essential Source of Schemas and Examples (ESSE) contains data formats and associated examples specifically designed for digital materials science (see refs. [1, 2](#links) below).
+Essential Source of Schemas and Examples (ESSE) contains data formats and examples for common entities used in digital materials science (see refs. [1, 2](#links) below).
 
-## Installation
+Although, the schemas are used to facilitate the operations of [mat3ra.com](https://mat3ra.com), they are designed to be generic and can be used in other applications. The open-source packages developed by Mat3ra.com use the schemas available in this repository.
 
-ESSE can be used as a Node.js or Python package on the server side.
+The latest variants of schemas and examples are available at [schemas.mat3ra.com](https://schemas.mat3ra.com/).
 
-### Python
+ESSE has a dual-nature as both a Python and a Node.js package.
 
-ESSE is compatible with Python 3.6+.  It can be installed as a Python package either via PyPI or the repository as below.
 
-#### PyPI
+## 1. Installation
+
+### 1.1. Python
+
+ESSE is compatible with Python 3.8+.
+
+#### 1.1.1. PyPI
 
 ```bash
-pip install esse
+pip install mat3ra-esse
 ```
 
-#### Repository
+#### 1.1.2. Repository
 
 ```bash
 virtualenv .venv
 source .venv/bin/activate
 pip install -e PATH_TO_ESSE_REPOSITORY
 ```
 
-### Node
+### 1.2. Node
 
-ESSE can be installed as a Node.js package either via NPM or the repository as below.
-
-#### NPM
+#### 1.2.1. NPM
 
 ```bash
 npm install @exabyte-io/esse.js
 ```
 
-#### Repository
-
-Add `"esse-js": "file:PATH_TO_ESSE_REPOSITORY"` to `package.json`.
 
-## Usage
+## 2. Usage
 
 ESSE contains separate but equivalent interfaces for Python and Javascript.
 The package provides `ESSE` class that can be initialized and used as below.
 
-### Python
+### 2.1. Usage in Python
 
 ```python
-from esse import ESSE
+from mat3ra.esse import ESSE
 
-es = ESSE()
-schema = es.get_schema_by_id("material")
+helper = ESSE()
+schema = helper.get_schema_by_id("material")
 ```
 
-### Node
+### 2.2. Usage in Node/JS/TS
 
 ```javascript
 import {ESSE} from "esse-js";
 
-const es = new ESSE();
-const schema = es.getSchemaById("material");
+const helper = new ESSE();
+const schema = helper.getSchemaById("material");
 ```
 
-## Structure
+
+## 3. Directory Structure
 
 ESSE contains 3 main directories, [schema](schema), [example](example) and [src](src) outlined below.
 
-### Schema
+### 3.1. Schema
 
 The schema directory contains the schemas specifying the rules to structure data. A set of core schemas, outlined below, are defined to facilitate the schema modularity.
 
-#### Primitive
-
-[Primitive](schema/core/primitive) directory contains a set of custom primitives that extends default standard primitive types allowed by schema, such as String and Number.
+- [Primitive](schema/core/primitive) directory contains a set of custom primitives that extends default standard primitive types allowed by schema, such as String and Number.
 Primitives are solely defined by the default primitives and can not be re-constructed from each other.
+- [Abstract](schema/core/abstract) directory contains unit-less schemas that are constructed from default and custom primitives.
+- [Reusable](schema/core/reusable) directory contains the schemas that are widely used in other schemas to avoid duplication, constructed from the abstract and primitive schemas.
+- [Reference](schema/core/reference) directory contains the schemas defining the rules to structure the references to data sources.
 
-#### Abstract
+### 3.2. Example
 
-[Abstract](schema/core/abstract) directory contains unit-less schemas that are constructed from default and custom primitives.
+This directory contains the examples formed according to the schemas and implements the same directory structure as the schema directory.
 
-#### Reusable
+### 3.3. src
 
-[Reusable](schema/core/reusable) directory contains the schemas that are widely used in other schemas to avoid duplication, constructed from the abstract and primitive schemas.
+This directory contains Python and Javascript interfaces implementing the functionality to access and validate schemas and examples.
 
-#### Reference
 
-[Reference](schema/core/reference) directory contains the schemas defining the rules to structure the references to data sources.
+## 4. Conventions
 
-### Example
+### 4.1. Generative vs Non-generative keys
+Generative keys are the fields which allow for user input prior to calculation of the final property values. A flag is included in the schema comments on the fields in [property schemas](schema/properties_directory): `isGenerative:true` marks which fields to use as subschemas in the generation of a user input schema. On properties allowing user inputs, additional fields may be tagged, as in [the `file_content` property](schema/properties_directory/non-scalar/file_content.json)
 
-This directory contains the examples formed according to the schemas and implements the same directory structure as the schema directory.
 
-### src
+## 5. Development
 
-This directory contains Python and Javascript interfaces implementing the functionality to access and validate schemas and examples.
+The schemas and examples are stored as JSON assets. The JSON assets are used to generate JS/TS and PY modules that can be used to access the schemas and examples in the corresponding runtimes. The modules are generated using the [build_schemas.py](./build_schemas.py) and [build_schema.js](./build_schema.js) scripts. The JS modules are generated during the transpilation step of the npm. The PY modules are generated during the development and distributed within the pip package.
+
+The following outlines the development process workflow:
+
+1. Setup: clone the repository and install the dependencies for both JS and PY (as explained below).
+2. Edit code and commit changes.
+3. Pre commit is used to regenerate the modules.
+4. Push the changes to GitHub.
+5. GH workflow is used to generate the fully resolved file (without "$ref"s and "$allOf" etc.) and examples and publish them to [schemas.mat3ra.com](http://schemas.mat3ra.com/).
+6. Publish the new version of the package to PyPI and npm.
+
+The [pre-commit](.husky/pre-commit) is using both JS and PY runtime(s) to regenerate the schemas and examples. 
+
+[//]: # (TODO: consider reusing JS runtime and schemas build script for PY modules for consistency)
+NOTE: The PY and JS modules are built from the same JSON sources, but using different runtimes (scripts) and thus may still be different. Only for JS the fully resolved schemas (with merged "$allOf") are created. They are used for the docs website. 
 
-### Generative vs Non-generative keys
-Generative keys are the fields which allow for user input prior to calculation of the final property values. A flag is included in the schema comments on the fields in [property schemas](schema/properties_directory): `isGenerative:true` marks which fields to use as subschemas in the generation of a user input schema.
-- On properties allowing user inputs, additional fields may be tagged, as in [the `file_content` property](schema/properties_directory/non-scalar/file_content.json)
+### 5.1. Development in Python
 
-## Tests
+When developing in python the following should be taken into account:
 
-Execute the following command from the root directory of this repository to run the tests. The script will run both Javascript and Python tests in which examples are validated against the corresponding schemas.
+1. The modules containing the schemas and examples are generated using the [build-schemas.py](./build_schemas.py) script. There is a setup for it to be run automatically on every commit, but it is recommended to run it manually before committing to make sure that the changes are reflected in the modules. This can be done with `pre-commit run --all-files`. The pre-commit package can be installed with `pip install pre-commit`. To rebuild schemas manually, run (note `-e` in install):
+    ```bash
+    virtualenv .venv
+    source .venv/bin/activate
+    pip install -e ."[tests]"
+    python build_schemas.py
+    ```
+2. Tests can be run using the following commands:
+    ```bash
+    virtualenv .venv
+    source .venv/bin/activate
+    pip install ."[tests]"
+    python -m unittest discover --verbose --catch --start-directory tests/py/esse/   
+    ```
 
+### 5.2. Development in Javascript/Typescript
+
+See [package.json](package.json) for the list of available npm commands. The JS modules are generated using the [build_schema.js](./build_schema.js) script. There is a setup for it to be run automatically when the package is installed (see "transpile" directive). To rebuild schemas manually, run:
 ```bash
-bash run-tests.sh
+npm install
+npm run transpile
 ```
-The script has been tested with node.js v12.16.3 and v8.17.0 as well as Python version 2.7 (up to version 2.3.0) and 3.6+ (for version 2020.10.19 and later).
-
-## Contribution
 
-This repository is an [open-source](LICENSE.md) work-in-progress and we welcome contributions. We suggest forking this repository and introducing the adjustments there, the changes in the fork can further be considered for merging into this repository as it is commonly done on Github (see [3](#links) below).
+### 5.3. General Dev Suggestions
 
-## Best Practices
+This repository is an [open-source](LICENSE.md) work-in-progress and we welcome contributions. We suggest forking this repository and introducing the adjustments there, the changes in the fork can further be considered for merging into this repository as it is commonly done on GitHub (see [3](#links) below).
 
-- Use unique IDs for schemas. One can run `sh refactor.sh` to automatically set the IDs and reformat examples.
+Other suggestions:
 
+- Use unique IDs for schemas
 - Do not use circular references in the schemas, instead leave the type as object and add explanation to description.
 
-## Links
 
-1: [Data-centric online ecosystem for digital materials science](https://arxiv.org/pdf/1902.10838.pdf)
+## 6. Links
 
+1: [Data-centric online ecosystem for digital materials science](https://arxiv.org/pdf/1902.10838.pdf)
 2: [CateCom: A Practical Data-Centric Approach to Categorization of Computational Models](https://pubs.acs.org/doi/abs/10.1021/acs.jcim.2c00112)
-
 3: [GitHub Standard Fork & Pull Request Workflow](https://gist.github.com/Chaser324/ce0505fbed06b947d962)

build_schemas.js

@@ -4,10 +4,12 @@
  * downstream consumption to avoid FS calls in the browser.
  */
 const fs = require("fs");
+const path = require("path");
+const mergeAllOf = require("json-schema-merge-allof");
 const { ESSE } = require("./lib/js/esse");
 
 const esse = new ESSE();
-const { schemas } = esse;
+const { schemas, wrappedExamples } = esse;
 const schema = esse.buildGlobalSchema();
 
 fs.writeFileSync(
@@ -17,3 +19,24 @@ fs.writeFileSync(
 );
 
 fs.writeFileSync("./schema.js", "module.exports = " + JSON.stringify(schema), "utf8");
+
+if (process.env.BUILD_ASSETS !== "true") {
+    process.exit(0);
+}
+
+const subfolder = process.env.BUILD_PATH || "./docs/js/";
+schemas.forEach((s) => {
+    if (process.env.SKIP_MERGE_ALLOF !== "true") {
+        s = mergeAllOf(s, { resolvers: { defaultResolver: mergeAllOf.options.resolvers.title } });
+    }
+    const id_as_path = s.$id.replace("-", "_");
+    const full_path = `${subfolder}/schema/${id_as_path}.json`;
+    fs.mkdirSync(path.dirname(full_path), { recursive: true });
+    fs.writeFileSync(full_path, JSON.stringify(s, null, 4), "utf8");
+});
+wrappedExamples.forEach((e) => {
+    const id_as_path = e.path.replace("-", "_");
+    const full_path = `${subfolder}/example/${id_as_path}.json`;
+    fs.mkdirSync(path.dirname(full_path), { recursive: true });
+    fs.writeFileSync(full_path, JSON.stringify(e.data, null, 4), "utf8");
+});