add pytest dev dep, and add CI test workflow

.github/workflows/{tests.yml → benchmark.yml}

@@ -1,6 +1,6 @@
 name: Integration test with benchmark
 
-on: [push]
+on: [] # re-enable after integration
 
 env:
   TORCH_DEVICE: "cpu"

.github/workflows/ci.yml

@@ -0,0 +1,25 @@
+name: CI tests
+
+on: [push]
+
+env:
+  TORCH_DEVICE: "cpu"
+  OCR_ENGINE: "surya"
+
+jobs:
+  tests:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v3
+      - name: Set up Python 3.11
+        uses: actions/setup-python@v4
+        with:
+          python-version: 3.11
+      - name: Install python dependencies
+        run: |
+          pip install poetry
+          poetry install
+      - name: Run tests
+        env:
+          HF_TOKEN: ${{ secrets.HF_TOKEN }}
+        run: poetry run pytest

poetry.lock

@@ -1200,6 +1200,17 @@ files = [
 [package.extras]
 all = ["flake8 (>=7.1.1)", "mypy (>=1.11.2)", "pytest (>=8.3.2)", "ruff (>=0.6.2)"]
 
+[[package]]
+name = "iniconfig"
+version = "2.0.0"
+description = "brain-dead simple config-ini parsing"
+optional = false
+python-versions = ">=3.7"
+files = [
+    {file = "iniconfig-2.0.0-py3-none-any.whl", hash = "sha256:b6a85871a79d2e3b22d2d1b94ac2824226a63c6b741c88f7ae975f18b6778374"},
+    {file = "iniconfig-2.0.0.tar.gz", hash = "sha256:2d91e135bf72d31a410b17c16da610a82cb55f6b0477d1a902134b24a455b8b3"},
+]
+
 [[package]]
 name = "ipykernel"
 version = "6.29.5"
@@ -2401,9 +2412,9 @@ files = [
 [package.dependencies]
 numpy = [
     {version = ">=1.26.0", markers = "python_version >= \"3.12\""},
+    {version = ">=1.23.5", markers = "python_version >= \"3.11\" and python_version < \"3.12\""},
     {version = ">=1.21.4", markers = "python_version >= \"3.10\" and platform_system == \"Darwin\" and python_version < \"3.11\""},
     {version = ">=1.21.2", markers = "platform_system != \"Darwin\" and python_version >= \"3.10\" and python_version < \"3.11\""},
-    {version = ">=1.23.5", markers = "python_version >= \"3.11\" and python_version < \"3.12\""},
 ]
 
 [[package]]
@@ -2482,8 +2493,8 @@ files = [
 [package.dependencies]
 numpy = [
     {version = ">=1.26.0", markers = "python_version >= \"3.12\""},
-    {version = ">=1.22.4", markers = "python_version < \"3.11\""},
     {version = ">=1.23.2", markers = "python_version == \"3.11\""},
+    {version = ">=1.22.4", markers = "python_version < \"3.11\""},
 ]
 python-dateutil = ">=2.8.2"
 pytz = ">=2020.1"
@@ -2684,6 +2695,21 @@ docs = ["furo (>=2024.8.6)", "proselint (>=0.14)", "sphinx (>=8.0.2)", "sphinx-a
 test = ["appdirs (==1.4.4)", "covdefaults (>=2.3)", "pytest (>=8.3.2)", "pytest-cov (>=5)", "pytest-mock (>=3.14)"]
 type = ["mypy (>=1.11.2)"]
 
+[[package]]
+name = "pluggy"
+version = "1.5.0"
+description = "plugin and hook calling mechanisms for python"
+optional = false
+python-versions = ">=3.8"
+files = [
+    {file = "pluggy-1.5.0-py3-none-any.whl", hash = "sha256:44e1ad92c8ca002de6377e165f3e0f1be63266ab4d554740532335b9d75ea669"},
+    {file = "pluggy-1.5.0.tar.gz", hash = "sha256:2cffa88e94fdc978c4c574f15f9e59b7f4201d439195c3715ca9e2486f1d0cf1"},
+]
+
+[package.extras]
+dev = ["pre-commit", "tox"]
+testing = ["pytest", "pytest-benchmark"]
+
 [[package]]
 name = "prometheus-client"
 version = "0.21.0"
@@ -3172,6 +3198,28 @@ files = [
 [package.extras]
 dev = ["build", "flake8", "mypy", "pytest", "twine"]
 
+[[package]]
+name = "pytest"
+version = "8.3.3"
+description = "pytest: simple powerful testing with Python"
+optional = false
+python-versions = ">=3.8"
+files = [
+    {file = "pytest-8.3.3-py3-none-any.whl", hash = "sha256:a6853c7375b2663155079443d2e45de913a911a11d669df02a50814944db57b2"},
+    {file = "pytest-8.3.3.tar.gz", hash = "sha256:70b98107bd648308a7952b06e6ca9a50bc660be218d53c257cc1fc94fda10181"},
+]
+
+[package.dependencies]
+colorama = {version = "*", markers = "sys_platform == \"win32\""}
+exceptiongroup = {version = ">=1.0.0rc8", markers = "python_version < \"3.11\""}
+iniconfig = "*"
+packaging = "*"
+pluggy = ">=1.5,<2"
+tomli = {version = ">=1", markers = "python_version < \"3.11\""}
+
+[package.extras]
+dev = ["argcomplete", "attrs (>=19.2)", "hypothesis (>=3.56)", "mock", "pygments (>=2.7.2)", "requests", "setuptools", "xmlschema"]
+
 [[package]]
 name = "python-dateutil"
 version = "2.9.0.post0"
@@ -5160,4 +5208,4 @@ propcache = ">=0.2.0"
 [metadata]
 lock-version = "2.0"
 python-versions = "^3.10"
-content-hash = "820767eabe5514a23b53137f6c37e9ec69925c70aa5be7b98a4c07a5f8a8c583"
+content-hash = "87f2bf6e84db6c7100db24777a4104096cb963d9bea7380e520dbc1bd8f2feb7"

pyproject.toml

@@ -46,6 +46,7 @@ streamlit = "^1.37.1"
 fastapi = "^0.115.4"
 uvicorn = "^0.32.0"
 python-multipart = "^0.0.16"
+pytest = "^8.3.3"
 
 [tool.poetry.scripts]
 marker = "convert:main"