Add statistics python project to build pipeline (#10175)

Author: clairernovotny

.pipelines/NuGetGallery-CI.yml

@@ -126,6 +126,40 @@ extends:
                   testResultsFiles: $(NuGetGalleryPath)\Results.*.xml
                   failTaskOnFailedTests: true
 
+      - stage: statslogparser
+        displayName: StatsLogPasrser
+        dependsOn: []
+        jobs:
+          - job: build_and_test
+            displayName: statslogparser build and test
+            cancelTimeoutInMinutes: 1
+            variables:
+              PIPX_HOME: $(Agent.ToolsDirectory)\pipx
+            steps:
+              - checkout: self
+                fetchDepth: 1
+                clean: true
+                fetchTags: false
+                path: $(NuGetGalleryDirectory)
+              - task: UsePythonVersion@0
+                inputs:
+                  versionSpec: '3.10'
+              - script: |
+                  python -m pip install --user pipx
+                  pipx ensurepath
+                displayName: 'Install tools'
+              - script: |
+                  pipx install poetry
+                  poetry install
+                  poetry build
+                  poetry run pytest tests/ --cov loginterpretation --cov-report html
+                workingDirectory: $(NuGetGalleryPath)\python\StatsLogParser
+            templateContext:
+              outputs:
+                - output: pipelineArtifact
+                  path: $(NuGetGalleryPath)\python\StatsLogParser\dist
+                  artifact: StatsLogParser
+
       - stage: jobs
         displayName: NuGet.Jobs.sln
         dependsOn: []

python/.gitignore

@@ -47,6 +47,7 @@ htmlcov/
 .cache
 nosetests.xml
 coverage.xml
+test-output.xml
 *.cover
 *.py,cover
 .hypothesis/

python/StatsLogParser/README.md

@@ -14,6 +14,7 @@ In your CLI, go to the `python/StatsLogParser` directory and then run `poetry in
 
 ### Dev and Test
 VS Code is recommended -- open the `python/StatsLogParser` folder and ensure you have the Python extensions installed. Poetry extensions are recommended too for environment activation. Testing is with pytest.
+To test on the CLI, you can run `poetry run pytest tests/` and to get code coverage, `poetry run pytest tests/ --cov loginterpretation --cov-report html`
 
 ### Dependencies
 Dependencies are in the `pyproject.toml` file. If you add/update dependencies, run `poetry export -f requirements.txt --output requirements.txt` to update the `requirements.txt` as both the that file and the `whl` will be needed for Spark.

python/StatsLogParser/dist/.artifactignore

@@ -0,0 +1,2 @@
+**/*
+!*.whl

python/StatsLogParser/loginterpretation/useragentparser.py

@@ -2,7 +2,7 @@
 from collections import namedtuple
 from typing import Optional
 import re
-import pkg_resources
+import pkgutil
 from ua_parser import user_agent_parser
 from ua_parser._regexes import USER_AGENT_PARSERS
 import yaml
@@ -47,11 +47,8 @@ def _replace_whitespace_with_plus_sign(match):
 
     @staticmethod
     def _read_known_clients_yaml() -> str:
-        file_name = pkg_resources.resource_filename(__name__, 'knownclients.yaml')
-        with open(file_name, 'r', encoding='utf-8-sig') as file:
-            yaml_file = file.read()
-
-        return yaml_file
+        file_data = pkgutil.get_data(__name__, 'knownclients.yaml').decode('utf-8-sig')
+        return file_data
 
     @staticmethod
     def _create_parser_data_from_yaml(yaml_content) -> list[user_agent_parser.UserAgentParser]:

python/StatsLogParser/poetry.lock

@@ -13,6 +13,8 @@ ua-parser = "^0.18.0"
 
 [tool.poetry.group.test.dependencies]
 pytest = "^8.3.2"
+pytest-cov = "^5.0.0"
+pytest-azurepipelines = "^1.0.5"
 
 [build-system]
 requires = ["poetry-core"]