Merge pull request #31 from gskorokhod/main

Add essence-feature-usage-stats tool

.github/dependabot.yml

@@ -20,3 +20,10 @@ updates:
  assignees:
  - "ozgurakgun"
 
+ - package-ecosystem: "pip"
+ directory: "/tools/essence-feature-usage-stats/"
+ schedule:
+ interval: "weekly"
+ assignees:
+ - "ozgurakgun"
+

.github/workflows/essence-feature-stats.yml

@@ -0,0 +1,66 @@
+ name: "tools/essence-feature-stats - Deploy to Github Pages"
+
+ on:
+ push:
+ branches:
+ - main
+
+ env:
+ ESSENCE_DIR: "./EssenceCatalog"
+ CONJURE_DIR: "./conjure"
+ ESSENCE_EXAMPLES_REPO: "https://github.com/conjure-cp/EssenceCatalog.git"
+ CONJURE_REPO: "https://github.com/conjure-cp/conjure"
+ OUTPUT_PATH: "./web/static/index.html"
+ KEYWORD_BLOCKLIST: >
+ mInfo,finds,givens,enumGivens,enumLettings,lettings,
+ unnameds,strategyQ,Auto,Interactive,strategyA,trailCompact,
+ nameGenState,nbExtraGivens,representations,representationsTree,
+ originalDomains,trailGeneralised,trailVerbose,trailRewrites,
+ mLanguage,language,version,mStatements,Name,Declaration,Op
+
+ jobs:
+ build:
+ name: "tools/essence-feature-stats: Build the tool and clone EssenceCatalog repo"
+
+ runs-on: ubuntu-latest
+
+ strategy:
+ matrix:
+ python-version: ["3.11"]
+
+ permissions:
+ contents: write
+
+ steps:
+ - name: Checkout code
+ uses: actions/checkout@v4
+
+ - name: Install Python ${{ matrix.python-version }}
+ uses: actions/setup-python@v4
+ with:
+ python-version: ${{ matrix.python-version }}
+
+ - name: Install python dependencies
+ run: pip install -r requirements.txt
+ working-directory: ./tools/essence-feature-usage-stats
+
+ - name: Run main.py to generate the table
+ run: python main.py
+ working-directory: ./tools/essence-feature-usage-stats
+
+ - name: Fix file permissions
+ run: chmod -v -R +rwx ./web/static/
+ working-directory: ./tools/essence-feature-usage-stats
+
+ - name: Add the .nojekyll file
+ run: touch ./web/static/.nojekyll
+ working-directory: ./tools/essence-feature-usage-stats
+
+ - name: Deploy to GitHub Pages
+ uses: JamesIves/github-pages-deploy-action@v4.4.3
+ with:
+ branch: gh-pages
+ folder: ./tools/essence-feature-usage-stats/web/static
+ target-folder: tools/essence-feature-usage-stats
+ commit-message: "Actions: Deploy the essence features usage table 🚀"
+

.gitignore

@@ -1,3 +1,13 @@
+# rust/c++
 target
-solvers/**/vendor/build
 coverage
+solvers/**/vendor/build
+
+# python
+.env
+venv
+__pycache__
+.ruff_cache
+
+# IDE
+.idea

tools/essence-feature-usage-stats/README.md

@@ -0,0 +1,59 @@
+# essence-feature-usage-stats
+
+## About
+
+This is an internal tool for the [conjure-oxide](https://github.com/conjure-cp/conjure-oxide) project.
+
+It does the following:
+- Given a directory containing Essence files, go through it and count how often every Essence language feature is used
+- Display this data as a simple web page with a table
+
+The purpose of this is to make it easier to find Essence examples to test specific Essence language features, which should be useful over the course of rewriting the conjure tool stack in Rust
+
+
+## Building
+
+The static HTML page is generated by running the main.py script.
+
+The page is placed in the ./web/static directory by default. 
+This can be configured using the OUTPUT_PATH environment variable, but paths to the script and stylesheet
+inside the index.html template will need to be updated. 
+The GitHub action also assumes that path and won't work if it's changed.
+
+It is deployed using GitHub Pages: see https://conjure-cp.github.io/conjure-oxide/tools/essence-feature-usage-stats
+
+
+## Usage
+
+- Essence example files are taken from the [EssenceCatalog](https://github.com/conjure-cp/EssenceCatalog) repo. This can be changed using an environment variable - see bellow.
+- Table headers show Essence keywords
+- Table row headers show paths to Essence example files and the size of the files (in lines of code)
+- Table cells show how often a given keyword is used in a given file
+- Cells are colour coded. Red means a keyword is NOT used in this file, orange means it's used less than average, green means it's used more
+- Columns are sortable. Click on table header cells to sort rows by how often this keyword is used in each file.
+- Sorting by the first column (the one with file names) will sort by file size
+- The section above the table is a list of Essence keywords, sorted by their total usage accross files
+- The "Show" checkboxes in this section show/hide table columns
+- The "Any", "Require", "Exclude" radio button allows you to filter the table by specific keywords:
+ - "Require" means that only files that have one or more usage of this keyword will be shown
+ - "Exclude" means that only files that don't use this keyword will be shown
+ - "Any" means that files will be shown regardless of whether they use this feature
+ - These can be combined to search for exactly the right files to test specific Essence features
+
+## Configuration
+
+- ESSENCE_DIR - local directory to store essence files
+- CONJURE_DIR - local directory to store conjure binaries
+- ESSENCE_EXAMPLES_REPO - repo to download Essence examples from
+- CONJURE_REPO - repo to download the latest release of conjure from
+- OUTPUT_PATH - path to save the generated HTML page. Be careful with changing this (see above).
+- KEYWORD_BLOCKLIST - comma-separated list of Essence keywords to ignore
+
+---
+
+## Authors
+
+- Georgii Skorokhod and Hannah Zheng, 2023
+- University of St Andrews
+- Developed as part of a Vertically Integrated Project by Ozgur Akgun et al
+- (See [main repo](https://github.com/conjure-cp))

tools/essence-feature-usage-stats/main.py

@@ -0,0 +1,51 @@
+import datetime
+import os
+from pathlib import Path
+
+from dotenv import load_dotenv
+from jinja2 import Environment, FileSystemLoader, select_autoescape
+
+from stats.essence_stats import EssenceStats
+
+ENV_PATH = Path("./.env").resolve()
+load_dotenv(dotenv_path=ENV_PATH)
+
+KEYWORD_BLOCKLIST = [x.strip() for x in os.getenv("KEYWORD_BLOCKLIST").split(",")]
+ESSENCE_DIR = Path(os.getenv("ESSENCE_DIR"))
+CONJURE_DIR = Path(os.getenv("CONJURE_DIR"))
+OUTPUT_PATH = Path(os.getenv("OUTPUT_PATH"))
+CONJURE_REPO = os.getenv("CONJURE_REPO")
+ESSENCE_EXAMPLES_REPO = os.getenv("ESSENCE_EXAMPLES_REPO")
+
+jinja_env = Environment(
+ loader=FileSystemLoader(Path("web/templates")),
+ autoescape=select_autoescape(),
+)
+
+if __name__ == "__main__":
+ stats = EssenceStats(
+ CONJURE_DIR,
+ CONJURE_REPO,
+ ESSENCE_DIR,
+ ESSENCE_EXAMPLES_REPO,
+ "master",
+ KEYWORD_BLOCKLIST,
+ )
+
+ timestamp = datetime.datetime.now().strftime("%d.%m.%Y - %H:%M")
+ template = jinja_env.get_template("index.html")
+ html = template.render(
+ data={
+ "essence_stats": stats,
+ "n_keywords": 200,
+ "css_path": "styles.css",
+ "script_path": "script.js",
+ "timestamp": timestamp,
+ },
+ )
+
+ OUTPUT_PATH.parent.mkdir(parents=True, exist_ok=True)
+ with OUTPUT_PATH.open("w") as f:
+ f.write(html)
+ f.close()
+ print(f"Table created: {OUTPUT_PATH.resolve()}")

tools/essence-feature-usage-stats/pyproject.toml

@@ -0,0 +1,23 @@
+[tool.ruff]
+select = ["E", "F", "B", "I", "N", "UP",
+ "A", "COM", "C4", "ISC001", "ISC002",
+ "ICN", "G", "INP", "PIE", "Q", "RSE",
+ "RET", "SIM", "ARG", "D",
+ "FIX", "PL", "TRY", "FLY", "PERF",
+ "RUF", "ERA", "PTH", "SLF"]
+
+# 2. Avoid enforcing line-length violations (`E501`) and module docstrings (D100)
+# Use line breaks at the first line of doc string (D213), so ignore D212
+# Don't use blank lines before class docstring, so ignore D203
+ignore = ["E501", "D100", "D212", "D203"]
+
+# 3. Unfixable rules
+# ERA: Don't autoremove all commented code, I may actually need it
+unfixable = ["ERA"]
+
+exclude = ["EssenceCatalog"]
+
+# 4. Ignore `E402` (import violations) in all `__init__.py` files, and in `path/to/file.py`.
+[tool.ruff.per-file-ignores]
+"web/colour.py" = ["PLR2004"]
+"__init__.py" = ["D"]

tools/essence-feature-usage-stats/requirements.txt

@@ -0,0 +1,19 @@
+black==23.10.1
+certifi==2023.7.22
+charset-normalizer==3.3.2
+click==8.1.7
+gitdb==4.0.11
+GitPython==3.1.40
+idna==3.4
+Jinja2==3.1.2
+MarkupSafe==2.1.3
+mypy-extensions==1.0.0
+packaging==23.2
+pathspec==0.11.2
+platformdirs==3.11.0
+python-dotenv==1.0.0
+requests==2.31.0
+ruff==0.1.3
+smmap==5.0.1
+tqdm==4.66.1
+urllib3==2.0.7