Add python tests to CI

Author: luciaquirke

.github/workflows/python-package-conda.yml

@@ -0,0 +1,29 @@
+name: Python Package using Conda
+
+on: [push]
+
+jobs:
+  build-linux:
+    runs-on: ubuntu-latest
+    strategy:
+      max-parallel: 5
+
+    steps:
+      - uses: actions/checkout@v3
+      - name: Set up Conda
+        uses: conda-incubator/setup-miniconda@v3
+        with:
+          python-version: "3.10"
+          miniforge-version: latest
+          use-mamba: true
+          mamba-version: "*"  
+      - name: Test Python
+        env:
+          PYTHONPATH: /home/runner/work/tokengrams/tokengrams
+        shell: bash -l {0}
+        run: |
+          mamba install -c conda-forge numpy pytest hypothesis maturin
+          maturin develop
+          maturin build
+          python -m pip install --user ./target/wheels/tokengrams*.whl
+          pytest

.github/workflows/python.yml

@@ -0,0 +1,10 @@
+name: test
+channels:
+  - conda-forge
+  - defaults
+dependencies:
+  - python=3.10
+  - numpy
+  - pytest
+  - hypothesis
+  - maturin

environment.yml

@@ -1,3 +1,6 @@
+import os
+print(os.getcwd())
+
 from .tokengrams import (
     InMemoryIndex,
     MemmapIndex,

tokengrams/__init__.py

@@ -28,25 +28,25 @@ def check_gram_index(index: InMemoryIndex | MemmapIndex, tokens: list[int]):
 )
 def test_gram_index(tokens: list[int]):
     # Construct index
-    index = InMemoryIndex(tokens)
+    index = InMemoryIndex(tokens, False)
     check_gram_index(index, tokens)
 
     # Save to disk and check that we can load it back
     with NamedTemporaryFile() as f:
         memmap = np.memmap(f, dtype=np.uint16, mode="w+", shape=(len(tokens),))
         memmap[:] = tokens
 
-        index = InMemoryIndex.from_token_file(f.name, None)
+        index = InMemoryIndex.from_token_file(f.name, False, None)
         check_gram_index(index, tokens)
 
         with NamedTemporaryFile() as idx:
-            index = MemmapIndex.build(f.name, idx.name)
+            index = MemmapIndex.build(f.name, idx.name, False)
             check_gram_index(index, tokens)
 
             index = MemmapIndex(f.name, idx.name)
             check_gram_index(index, tokens)
 
         # Now check limited token loading
         for limit in range(1, len(tokens) + 1):
-            index = InMemoryIndex.from_token_file(f.name, limit)
+            index = InMemoryIndex.from_token_file(f.name, False, limit)
             check_gram_index(index, tokens[:limit])

tokengrams/tests/test_gram_index.py

@@ -1,11 +1,11 @@
 class InMemoryIndex:
     """An n-gram index."""
 
-    def __init__(self, tokens: list[int]) -> None:
+    def __init__(self, tokens: list[int], verbose: bool) -> None:
         ...
 
     @staticmethod
-    def from_token_file(path: str, token_limit: int | None, verbose: bool) -> "InMemoryIndex":
+    def from_token_file(path: str, verbose: bool, token_limit: int | None) -> "InMemoryIndex":
         """Construct a `InMemoryIndex` from a file containing raw little-endian tokens."""
 
     def contains(self, query: list[int]) -> bool: