Restructure app: split tests, previews and comparison helpers into modules

.github/workflows/staging-deploy.yml

@@ -31,19 +31,24 @@ jobs:
       - name: Install dependencies
         run: |
           python -m venv .venv
-          .venv/bin/pip install pytest
+          .venv/bin/pip install -r requirements-dev.txt
           .venv/bin/pip install -r app/requirements.txt
 
 
       - name: Lint with flake8
         run: |
           source .venv/bin/activate
-          .venv/bin/pip install flake8
           # stop the build if there are Python syntax errors or undefined names
           flake8 ./app --count --select=E9,F63,F7,F82 --show-source --statistics
           # exit-zero treats all errors as warnings. The GitHub editor is 127 chars wide
           flake8 ./app --count --exit-zero --max-complexity=10 --max-line-length=127 --statistics
 
+      - name: Type check with mypy
+        run: |
+          source .venv/bin/activate
+          # configuration (checked files, strictness, untyped dependencies) is in mypy.ini
+          mypy
+
       - name: Run tests
         if: always()
         run: |

.github/workflows/test-lint.yml

@@ -28,18 +28,23 @@ jobs:
       - name: Install dependencies
         run: |
           python -m venv .venv
-          .venv/bin/pip install pytest
+          .venv/bin/pip install -r requirements-dev.txt
           .venv/bin/pip install -r app/requirements.txt
 
       - name: Lint with flake8
         run: |
           source .venv/bin/activate
-          .venv/bin/pip install flake8
           # stop the build if there are Python syntax errors or undefined names
           flake8 ./app --count --select=E9,F63,F7,F82 --show-source --statistics
           # exit-zero treats all errors as warnings. The GitHub editor is 127 chars wide
           flake8 ./app --count --exit-zero --max-complexity=10 --max-line-length=127 --statistics
 
+      - name: Type check with mypy
+        run: |
+          source .venv/bin/activate
+          # configuration (checked files, strictness, untyped dependencies) is in mypy.ini
+          mypy
+
       - name: Run tests
         if: always()
         run: |

README.md

@@ -25,7 +25,7 @@ This version is specifically for python, however the ultimate goal is to make si
 5. You are now ready to start developing your function:
 
    - Edit the `app/evaluation.py` file, which ultimately gets called when the function is given the `eval` command
-   - Add pytest tests to `app/evaluation_test.py`, `app/preview_test.py` or `app/tests/`. They get run:
+   - Add pytest tests to `app/tests/`. They get run:
        - On every pull request and before the image is built and deployed (`pytest` from the repo root)
        - Whenever the `healthcheck` command is supplied to the deployed function (via `app/evaluation_tests.py`)
    - Edit `app/docs/user.md` and `app/docs/dev.md` to reflect your changes. These files are baked into the function's image, and is made available using the `docs` command. This feature is used to display this function's documentation on our [Documentation](https://lambda-feedback.github.io/Documentation/) website once it's been hooked up!

app/conftest.py

@@ -1,2 +1,5 @@
-def pytest_configure(config):
+import pytest
+
+
+def pytest_configure(config: pytest.Config) -> None:
     config.addinivalue_line("markers", "slow: excluded from the deployed healthcheck (see evaluation_tests.py)")

app/context/defaults.py

@@ -0,0 +1,9 @@
+"""Default evaluation parameters shared by all contexts; each context adds its own on top of these."""
+
+base_default_parameters = {
+    "complexNumbers": False,
+    "convention": "equal_precedence",
+    "elementary_functions": False,
+    "strict_syntax": False,
+    "multiple_answers_criteria": "all",
+}

app/context/graph_helpers.py

@@ -0,0 +1,38 @@
+"""Helpers for building the `CriteriaGraph`s shared by the symbolic and physical quantity contexts."""
+
+from __future__ import annotations
+
+from collections.abc import Mapping
+from typing import Any
+
+from lambdafeedback.criteria import CriteriaGraph, FeedbackStringGenerator, OutputNode, ReachedCriteria
+
+
+def outcome_tag(label: str, result: bool | None, inputs: Mapping[str, Any] | None = None) -> ReachedCriteria:
+    """`{label+"_TRUE": inputs}` if `result` is True, `label+"_FALSE"` if it is False, otherwise `label+"_UNKNOWN"`."""
+    if result is True:
+        return {label+"_TRUE": inputs}
+    elif result is False:
+        return {label+"_FALSE": inputs}
+    else:
+        return {label+"_UNKNOWN": inputs}
+
+
+def attach_terminal_criterion(
+    graph: CriteriaGraph,
+    evaluation_label: str,
+    label: str,
+    end: OutputNode,
+    summary: str,
+    details: str,
+    feedback_string_generator: FeedbackStringGenerator | None = None,
+) -> None:
+    """Attaches a new criterion `label` to `evaluation_label` and connects it to the `end` node."""
+    graph.attach_new_criterion(
+        evaluation_label,
+        label,
+        summary=summary,
+        details=details,
+        feedback_string_generator=feedback_string_generator
+    )
+    graph.attach(label, end.label)

app/context/operators.py

@@ -0,0 +1,11 @@
+"""The comparison operators that criteria can use, by the symbol used in the criteria string."""
+
+import operator
+
+COMPARISON_OPERATORS = {
+    "=": operator.eq,
+    ">": operator.gt,
+    ">=": operator.ge,
+    "<": operator.lt,
+    "<=": operator.le,
+}