Revamp CI (#825)

.github/workflows/ci.yml

@@ -7,13 +7,69 @@ on:
     branches: [ master ]
 
 jobs:
-  build:
-
+  type-check:
     runs-on: ubuntu-20.04
+    steps:
+      - uses: actions/checkout@v2
+      - uses: actions/setup-python@v2
+        with:
+          python-version: 3.7
+      - name: Test with mypy
+        run: |
+          pip install mypy
+          mypy haystack --ignore-missing-imports
 
+  build-cache:
+    needs: type-check
+    runs-on: ubuntu-20.04
+    steps:
+      - uses: actions/checkout@v2
+      - uses: actions/setup-python@v2
+        with:
+          python-version: 3.7
+      - run: echo "date=$(date +'%Y-%m-%d')" >> $GITHUB_ENV
+      - name: Cache
+        id: cache-python-env
+        uses: actions/cache@v2
+        with:
+          path: ${{ env.pythonLocation }}
+          key: ${{ env.pythonLocation }}-${{ hashFiles('setup.py') }}-${{ hashFiles('requirements.txt') }}
+      - name: Install dependencies
+        if: steps.cache-python-env.outputs.cache-hit != 'true'
+        run: |
+          python -m pip install --upgrade pip
+          pip install pytest
+          pip install --upgrade --upgrade-strategy eager -r requirements.txt -e .
+
+  prepare-build:
+    needs: build-cache
+    runs-on: ubuntu-20.04
+    steps:
+      - uses: actions/checkout@v2
+      - id: set-matrix
+        run: |
+          echo "::set-output name=matrix::$(cd test && ls -d test_*.py | jq -R . | jq -cs .)"
+    outputs:
+      matrix: ${{ steps.set-matrix.outputs.matrix }}
+  build:
+    needs: prepare-build
+    runs-on: ubuntu-20.04
+    strategy:
+      matrix:
+        test-path: ${{fromJson(needs.prepare-build.outputs.matrix)}}
+      fail-fast: false
     steps:
     - uses: actions/checkout@v2
-      
+    - name: Set up Python 3.7
+      uses: actions/setup-python@v2
+      with:
+        python-version: 3.7
+    - run: echo "date=$(date +'%Y-%m-%d')" >> $GITHUB_ENV
+    - name: Cache
+      uses: actions/cache@v2
+      with:
+        path: ${{ env.pythonLocation }}
+        key: ${{ env.pythonLocation }}-${{ hashFiles('setup.py') }}-${{ hashFiles('requirements.txt') }}
     - name: Run Elasticsearch
       run: docker run -d -p 9200:9200 -e "discovery.type=single-node" -e "ES_JAVA_OPTS=-Xms128m -Xmx128m" elasticsearch:7.9.2
 
@@ -23,33 +79,8 @@ jobs:
     - name: Run Apache Tika
       run: docker run -d -p 9998:9998 -e "TIKA_CHILD_JAVA_OPTS=-JXms128m" -e "TIKA_CHILD_JAVA_OPTS=-JXmx128m" apache/tika:1.24.1
 
-    - name: Set up Python 3.7
-      uses: actions/setup-python@v2
-      with:
-        python-version: 3.7
-      
-    - name: Install dependencies
-      run: |
-        python -m pip install --upgrade pip
-        pip install pytest
-        pip install -r requirements.txt
-        pip install -e .
-        wget --no-check-certificate https://dl.xpdfreader.com/xpdf-tools-linux-4.03.tar.gz && tar -xvf xpdf-tools-linux-4.03.tar.gz && sudo cp xpdf-tools-linux-4.03/bin64/pdftotext /usr/local/bin
-    - name: Test with mypy
-      run: |
-        pip install mypy
-        mypy haystack --ignore-missing-imports
-
-    - name: Run Pytest without generator/pipeline marker
-      run: cd test &&  pytest -m "not pipeline and not generator and not summarizer"
-
-#    - name: Stop Containers
-#      run: docker rm -f `docker ps -a -q`
-
-    - name: Run pytest with generator/pipeline marker
-      run: cd test && pytest -m "pipeline or generator"
-
-    - name: Run pytest with summarizer marker
-      run: cd test && pytest -m "summarizer"
-
+    - name: Install pdftotext
+      run: wget --no-check-certificate https://dl.xpdfreader.com/xpdf-tools-linux-4.03.tar.gz && tar -xvf xpdf-tools-linux-4.03.tar.gz && sudo cp xpdf-tools-linux-4.03/bin64/pdftotext /usr/local/bin
 
+    - name: Run tests
+      run: cd test && pytest ${{ matrix.test-path }}

test/conftest.py

@@ -132,10 +132,9 @@ def xpdf_fixture(tika_fixture):
             raise Exception(
                 """Currently auto installation of pdftotext is not supported on {0} platform """.format(platform)
             )
-
-        commands = """ wget --no-check-certificate https://dl.xpdfreader.com/xpdf-tools-{0}-4.02.tar.gz &&
-                       tar -xvf xpdf-tools-{0}-4.02.tar.gz &&
-                       {1} cp xpdf-tools-{0}-4.02/bin64/pdftotext /usr/local/bin""".format(platform_id, sudo_prefix)
+        commands = """ wget --no-check-certificate https://dl.xpdfreader.com/xpdf-tools-{0}-4.03.tar.gz &&
+                       tar -xvf xpdf-tools-{0}-4.03.tar.gz &&
+                       {1} cp xpdf-tools-{0}-4.03/bin64/pdftotext /usr/local/bin""".format(platform_id, sudo_prefix)
         run([commands], shell=True)
 
         verify_installation = run(["pdftotext -v"], shell=True)

test/test_docx_conversion.py

@@ -1,12 +0,0 @@
-from pathlib import Path
-
-import pytest
-
-from haystack.file_converter.docx import DocxToTextConverter
-
-
-@pytest.mark.tika
-def test_convert():
-    converter = DocxToTextConverter()
-    document = converter.convert(file_path=Path("samples/docx/sample_docx.docx"))
-    assert document["text"].startswith("Sample Docx File")

test/test_file_converter.py

@@ -2,6 +2,7 @@ from pathlib import Path
 
 import pytest
 
+from haystack.file_converter.docx import DocxToTextConverter
 from haystack.file_converter.pdf import PDFToTextConverter
 from haystack.file_converter.tika import TikaConverter
 
@@ -45,3 +46,7 @@ def test_language_validation(Converter, xpdf_fixture, caplog):
     assert "The language for samples/pdf/sample_pdf_1.pdf is not one of ['de']." in caplog.text
 
 
+def test_docx_converter():
+    converter = DocxToTextConverter()
+    document = converter.convert(file_path=Path("samples/docx/sample_docx.docx"))
+    assert document["text"].startswith("Sample Docx File")

test/test_imports.py

@@ -1,27 +0,0 @@
-def test_module_imports():
-    from haystack import Finder
-    from haystack.document_store.sql import SQLDocumentStore
-    from haystack.document_store.elasticsearch import ElasticsearchDocumentStore
-    from haystack.document_store.faiss import FAISSDocumentStore
-    from haystack.document_store.milvus import MilvusDocumentStore
-    from haystack.document_store.base import BaseDocumentStore
-    from haystack.preprocessor.cleaning import clean_wiki_text
-    from haystack.preprocessor.utils import convert_files_to_dicts, fetch_archive_from_http
-    from haystack.reader.farm import FARMReader
-    from haystack.reader.transformers import TransformersReader
-    from haystack.retriever.sparse import TfidfRetriever
-    from haystack.utils import print_answers
-
-    assert Finder is not None
-    assert SQLDocumentStore is not None
-    assert ElasticsearchDocumentStore is not None
-    assert FAISSDocumentStore is not None
-    assert MilvusDocumentStore is not None
-    assert BaseDocumentStore is not None
-    assert clean_wiki_text is not None
-    assert convert_files_to_dicts is not None
-    assert fetch_archive_from_http is not None
-    assert FARMReader is not None
-    assert TransformersReader is not None
-    assert TfidfRetriever is not None
-    assert print_answers is not None