Test: Add code coverage reporting to CI (#12874)

### What problem does this PR solve?

Add code coverage reporting to CI

### Type of change

- [x] Test (please describe): coverage report

---------

Co-authored-by: Liu An <asiro@qq.com>

.github/workflows/tests.yml

@@ -202,8 +202,11 @@ jobs:
           echo -e "RAGFLOW_IMAGE=${RAGFLOW_IMAGE}" >> docker/.env
           echo "HOST_ADDRESS=http://host.docker.internal:${SVR_HTTP_PORT}" >> ${GITHUB_ENV}
 
+          # Patch entrypoint.sh for coverage
+          sed -i '/"\$PY" api\/ragflow_server.py \${INIT_SUPERUSER_ARGS} &/c\   echo "Ensuring coverage is installed..."\n      "$PY" -m pip install coverage\n     export COVERAGE_FILE=/ragflow/logs/.coverage\n        echo "Starting ragflow_server with coverage..."\n        "$PY" -m coverage run --source=./api/apps --omit="*/tests/*,*/migrations/*" -a api/ragflow_server.py ${INIT_SUPERUSER_ARGS} &' docker/entrypoint.sh
+
           sudo docker compose -f docker/docker-compose.yml -p ${GITHUB_RUN_ID} up -d
-          uv sync --python 3.12 --group test --frozen && uv pip install sdk/python
+          uv sync --python 3.12 --group test --frozen && uv pip install -e sdk/python
 
       - name: Run sdk tests against Elasticsearch
         run: |
@@ -212,7 +215,7 @@ jobs:
             echo "Waiting for service to be available..."
             sleep 5
           done
-          source .venv/bin/activate && set -o pipefail; pytest -s --tb=short --level=${HTTP_API_TEST_LEVEL} test/testcases/test_sdk_api 2>&1 | tee es_sdk_test.log
+          source .venv/bin/activate && set -o pipefail; pytest -s --tb=short --level=${HTTP_API_TEST_LEVEL} --junitxml=pytest-infinity-sdk.xml --cov=sdk/python/ragflow_sdk --cov-branch --cov-report=xml:coverage-es-sdk.xml test/testcases/test_sdk_api 2>&1 | tee es_sdk_test.log
 
       - name: Run web api tests against Elasticsearch
         run: |
@@ -221,7 +224,7 @@ jobs:
             echo "Waiting for service to be available..."
             sleep 5
           done
-          source .venv/bin/activate && set -o pipefail; pytest -s --tb=short --level=${HTTP_API_TEST_LEVEL} test/testcases/test_web_api/ 2>&1 | tee es_web_api_test.log
+          source .venv/bin/activate && set -o pipefail; pytest -s --tb=short --level=${HTTP_API_TEST_LEVEL} test/testcases/test_web_api 2>&1 | tee es_web_api_test.log
           
       - name: Run http api tests against Elasticsearch
         run: |
@@ -232,7 +235,7 @@ jobs:
           done
           source .venv/bin/activate && set -o pipefail; pytest -s --tb=short --level=${HTTP_API_TEST_LEVEL} test/testcases/test_http_api 2>&1 | tee es_http_api_test.log
 
-      - name: RAGFlow CLI retrieval test
+      - name: RAGFlow CLI retrieval test Elasticsearch
         env:
           PYTHONPATH: ${{ github.workspace }}
         run: |
@@ -333,7 +336,43 @@ jobs:
           run_cli "${LOG_FILE}" $CLI --type user --host "$USER_HOST" --port "$USER_PORT" --username "$EMAIL" --password "$PASS" command "parse dataset '$DATASET' sync"
           run_cli "${LOG_FILE}" $CLI --type user --host "$USER_HOST" --port "$USER_PORT" --username "$EMAIL" --password "$PASS" command "Benchmark 16 100 search 'what are these documents about' on datasets '$DATASET'"
 
-      - name: Collect ragflow log
+      - name: Stop ragflow to save coverage Elasticsearch
+        if: ${{ !cancelled() }}
+        run: |
+          # Send SIGINT to ragflow_server.py to trigger coverage save
+          PID=$(sudo docker exec ${RAGFLOW_CONTAINER} ps aux | grep "ragflow_server.py" | grep -v grep | awk '{print $2}' | head -n 1)
+          if [ -n "$PID" ]; then
+            echo "Sending SIGINT to ragflow_server.py (PID: $PID)..."
+            sudo docker exec ${RAGFLOW_CONTAINER} kill -INT $PID
+            # Wait for process to exit and coverage file to be written
+            sleep 10
+          else
+            echo "ragflow_server.py not found!"
+          fi
+          sudo docker compose -f docker/docker-compose.yml -p ${GITHUB_RUN_ID} stop
+
+      - name: Generate server coverage report Elasticsearch
+        if: ${{ !cancelled() }}
+        run: |
+          # .coverage file should be in docker/ragflow-logs/.coverage
+          if [ -f docker/ragflow-logs/.coverage ]; then
+            echo "Found .coverage file"
+            cp docker/ragflow-logs/.coverage .coverage
+            source .venv/bin/activate
+            # Create .coveragerc to map container paths to host paths
+            echo "[paths]" > .coveragerc
+            echo "source =" >> .coveragerc
+            echo "    ." >> .coveragerc
+            echo "    /ragflow" >> .coveragerc
+            coverage xml -o coverage-es-server.xml
+            rm .coveragerc
+            # Clean up for next run
+            sudo rm docker/ragflow-logs/.coverage
+          else
+            echo ".coverage file not found!"
+          fi
+          
+      - name: Collect ragflow log Elasticsearch
         if: ${{ !cancelled() }}
         run: |
           if [ -d docker/ragflow-logs ]; then
@@ -362,7 +401,7 @@ jobs:
             echo "Waiting for service to be available..."
             sleep 5
           done
-          source .venv/bin/activate && set -o pipefail; DOC_ENGINE=infinity pytest -s --tb=short --level=${HTTP_API_TEST_LEVEL} test/testcases/test_sdk_api 2>&1 | tee infinity_sdk_test.log
+          source .venv/bin/activate && set -o pipefail; DOC_ENGINE=infinity pytest -s --tb=short --level=${HTTP_API_TEST_LEVEL} --junitxml=pytest-infinity-sdk.xml --cov=sdk/python/ragflow_sdk --cov-branch --cov-report=xml:coverage-infinity-sdk.xml test/testcases/test_sdk_api 2>&1 | tee infinity_sdk_test.log
 
       - name: Run web api tests against Infinity
         run: |
@@ -371,7 +410,7 @@ jobs:
             echo "Waiting for service to be available..."
             sleep 5
           done
-          source .venv/bin/activate && set -o pipefail; DOC_ENGINE=infinity pytest -s --tb=short --level=${HTTP_API_TEST_LEVEL} test/testcases/test_web_api/ 2>&1 | tee infinity_web_api_test.log
+          source .venv/bin/activate && set -o pipefail; DOC_ENGINE=infinity pytest -s --tb=short --level=${HTTP_API_TEST_LEVEL} test/testcases/test_web_api/test_api_app 2>&1 | tee infinity_web_api_test.log
 
       - name: Run http api tests against Infinity
         run: |
@@ -382,7 +421,7 @@ jobs:
           done
           source .venv/bin/activate && set -o pipefail; DOC_ENGINE=infinity pytest -s --tb=short --level=${HTTP_API_TEST_LEVEL} test/testcases/test_http_api 2>&1 | tee infinity_http_api_test.log
 
-      - name: RAGFlow CLI retrieval test (Infinity)
+      - name: RAGFlow CLI retrieval test Infinity
         env:
           PYTHONPATH: ${{ github.workspace }}
         run: |
@@ -483,6 +522,47 @@ jobs:
           run_cli "${LOG_FILE}" $CLI --type user --host "$USER_HOST" --port "$USER_PORT" --username "$EMAIL" --password "$PASS" command "parse dataset '$DATASET' sync"
           run_cli "${LOG_FILE}" $CLI --type user --host "$USER_HOST" --port "$USER_PORT" --username "$EMAIL" --password "$PASS" command "Benchmark 16 100 search 'what are these documents about' on datasets '$DATASET'"
 
+      - name: Stop ragflow to save coverage Infinity
+        if: ${{ !cancelled() }}
+        run: |
+          # Send SIGINT to ragflow_server.py to trigger coverage save
+          PID=$(sudo docker exec ${RAGFLOW_CONTAINER} ps aux | grep "ragflow_server.py" | grep -v grep | awk '{print $2}' | head -n 1)
+          if [ -n "$PID" ]; then
+            echo "Sending SIGINT to ragflow_server.py (PID: $PID)..."
+            sudo docker exec ${RAGFLOW_CONTAINER} kill -INT $PID
+            # Wait for process to exit and coverage file to be written
+            sleep 10
+          else
+            echo "ragflow_server.py not found!"
+          fi
+          sudo docker compose -f docker/docker-compose.yml -p ${GITHUB_RUN_ID} stop
+
+      - name: Generate server coverage report Infinity
+        if: ${{ !cancelled() }}
+        run: |
+          # .coverage file should be in docker/ragflow-logs/.coverage
+          if [ -f docker/ragflow-logs/.coverage ]; then
+            echo "Found .coverage file"
+            cp docker/ragflow-logs/.coverage .coverage
+            source .venv/bin/activate
+            # Create .coveragerc to map container paths to host paths
+            echo "[paths]" > .coveragerc
+            echo "source =" >> .coveragerc
+            echo "    ." >> .coveragerc
+            echo "    /ragflow" >> .coveragerc
+            coverage xml -o coverage-infinity-server.xml
+            rm .coveragerc
+          else
+            echo ".coverage file not found!"
+          fi
+          
+      - name: Upload coverage reports to Codecov
+        uses: codecov/codecov-action@v5
+        if: ${{ !cancelled() }}
+        with:
+          token: ${{ secrets.CODECOV_TOKEN }}
+          fail_ci_if_error: false
+
       - name: Collect ragflow log
         if: ${{ !cancelled() }}
         run: |
@@ -493,6 +573,7 @@ jobs:
             echo "No docker/ragflow-logs directory found; skipping log collection"
           fi
           sudo rm -rf docker/ragflow-logs || true
+
       - name: Stop ragflow:nightly
         if: always()  # always run this step even if previous steps failed
         run: |

pyproject.toml

@@ -172,6 +172,7 @@ test = [
     "requests>=2.32.2",
     "requests-toolbelt>=1.0.0",
     "pycryptodomex==3.20.0",
+    "codecov>=2.1.13",
 ]
 
 [[tool.uv.index]]

uv.lock

@@ -1096,6 +1096,19 @@ wheels = [
     { url = "https://pypi.tuna.tsinghua.edu.cn/packages/d5/e1/3714a2f371985215c219c2a70953d38e3eed81ef165aed061d21de0e998b/cobble-0.1.4-py3-none-any.whl", hash = "sha256:36c91b1655e599fd428e2b95fdd5f0da1ca2e9f1abb0bc871dec21a0e78a2b44", size = 3984, upload-time = "2024-06-01T18:11:07.911Z" },
 ]
 
+[[package]]
+name = "codecov"
+version = "2.1.13"
+source = { registry = "https://pypi.tuna.tsinghua.edu.cn/simple" }
+dependencies = [
+    { name = "coverage" },
+    { name = "requests" },
+]
+sdist = { url = "https://pypi.tuna.tsinghua.edu.cn/packages/2c/bb/594b26d2c85616be6195a64289c578662678afa4910cef2d3ce8417cf73e/codecov-2.1.13.tar.gz", hash = "sha256:2362b685633caeaf45b9951a9b76ce359cd3581dd515b430c6c3f5dfb4d92a8c", size = 21416, upload-time = "2023-04-17T23:11:39.779Z" }
+wheels = [
+    { url = "https://pypi.tuna.tsinghua.edu.cn/packages/af/02/18785edcdf6266cdd6c6dc7635f1cbeefd9a5b4c3bb8aff8bd681e9dd095/codecov-2.1.13-py2.py3-none-any.whl", hash = "sha256:c2ca5e51bba9ebb43644c43d0690148a55086f7f5e6fd36170858fa4206744d5", size = 16512, upload-time = "2023-04-17T23:11:37.344Z" },
+]
+
 [[package]]
 name = "cohere"
 version = "5.6.2"
@@ -6223,6 +6236,7 @@ dependencies = [
 
 [package.dev-dependencies]
 test = [
+    { name = "codecov" },
     { name = "hypothesis" },
     { name = "openpyxl" },
     { name = "pillow" },
@@ -6357,6 +6371,7 @@ requires-dist = [
 
 [package.metadata.requires-dev]
 test = [
+    { name = "codecov", specifier = ">=2.1.13" },
     { name = "hypothesis", specifier = ">=6.132.0" },
     { name = "openpyxl", specifier = ">=3.1.5" },
     { name = "pillow", specifier = ">=10.4.0,<13.0.0" },