Cleanup collector-sync module (#9631)

Co-authored-by: otelbot <197425009+otelbot@users.noreply.github.com>

Author: jaydeluca

.github/scripts/collector-sync.sh

@@ -43,7 +43,10 @@ if [ ! -d "tmp_repos/opentelemetry-ecosystem-explorer" ]; then
   exit 1
 fi
 
-VERSION=$(ls -1 tmp_repos/opentelemetry-ecosystem-explorer/ecosystem-registry/collector/core 2>/dev/null | grep -v -i 'SNAPSHOT' | sort -V | tail -n 1)
+VERSION=$(find tmp_repos/opentelemetry-ecosystem-explorer/ecosystem-registry/collector/core \
+  -mindepth 1 -maxdepth 1 -type d -printf '%f\n' 2>/dev/null | \
+  grep -v -i 'SNAPSHOT' | sort -V | tail -n 1)
+
 if [ -z "$VERSION" ]; then
   echo "Error: No collector versions found"
   exit 1
@@ -92,7 +95,7 @@ _Last updated: $(date -u '+%Y-%m-%d %H:%M:%S UTC')_"
 fi
 
 echo "Checking for component changes..."
-CHANGED_FILES=$(git diff --name-only data/collector/)
+CHANGED_FILES=$(git diff --name-only data/collector/ data/collector-versions.yml)
 
 if [ -z "$CHANGED_FILES" ]; then
   echo "No component changes detected"

.github/workflows/test-collector-sync.yml

@@ -0,0 +1,45 @@
+name: Test collector-sync
+
+on:
+  pull_request:
+    paths:
+      - 'scripts/collector-sync/**'
+      - '.github/workflows/test-collector-sync.yml'
+
+permissions:
+  contents: read
+
+jobs:
+  test:
+    name: Python tests
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v6
+
+      - name: Set up Python
+        uses: actions/setup-python@a309ff8b426b58ec0e2a45f0f869d46889d02405 # v6.2.0
+
+      - name: Install uv
+        uses: astral-sh/setup-uv@cec208311dfd045dd5311c1add060b2062131d57 # v8.0.0
+        with:
+          enable-cache: true
+
+      - name: Install dependencies
+        run: |
+          cd scripts/collector-sync
+          uv sync --all-extras
+
+      - name: Run pytest
+        run: |
+          cd scripts/collector-sync
+          uv run pytest
+
+      - name: Run mypy type checking
+        run: |
+          cd scripts/collector-sync
+          uv run mypy src/
+
+      - name: Run ruff linting
+        run: |
+          cd scripts/collector-sync
+          uv run ruff check src/

content/ja/docs/collector/components/receiver.md

@@ -5,7 +5,7 @@ default_lang_commit: 1c2b0563e8e66ef0952c442e3662e4bec18a8762 # patched
 drifted_from_default: true
 weight: 310
 # prettier-ignore
-cSpell:ignore: activedirectorydsreceiver aerospikereceiver apachereceiver apachesparkreceiver awscloudwatchreceiver awscontainerinsightreceiver awsecscontainermetricsreceiver awsfirehosereceiver awslambdareceiver awss awsxrayreceiver azureblobreceiver azureeventhubreceiver azuremonitorreceiver carbonreceiver chronyreceiver ciscoosreceiver cloudflarereceiver cloudfoundryreceiver collectdreceiver couchdbreceiver datadogreceiver dockerstatsreceiver elasticsearchreceiver envoyalsreceiver expvarreceiver faroreceiver filelogreceiver filestatsreceiver flinkmetricsreceiver fluentforwardreceiver githubreceiver gitlabreceiver googlecloudmonitoringreceiver googlecloudpubsubpushreceiver googlecloudpubsubreceiver googlecloudspannerreceiver haproxyreceiver hostmetricsreceiver httpcheckreceiver huaweicloudcesreceiver icmpcheckreceiver iisreceiver influxdbreceiver jaegerreceiver jmxreceiver journaldreceiver kafkametricsreceiver kafkareceiver kubeletstatsreceiver libhoneyreceiver lokireceiver memcachedreceiver mongodbatlasreceiver mongodbreceiver mysqlreceiver namedpipereceiver netflowreceiver nginxreceiver nopreceiver nsxtreceiver ntpreceiver oracledbreceiver osqueryreceiver otelarrowreceiver otlpjsonfilereceiver otlpreceiver podmanreceiver postgresqlreceiver pprofreceiver prometheusreceiver prometheusremotewritereceiver pulsarreceiver purefareceiver purefbreceiver rabbitmqreceiver receivercreator redfishreceiver redisreceiver riakreceiver saphanareceiver sclusterreceiver seventsreceiver signalfxreceiver simpleprometheusreceiver skywalkingreceiver slogreceiver snmpreceiver snowflakereceiver sobjectsreceiver solacereceiver splunkenterprisereceiver splunkhecreceiver sqlqueryreceiver sqlserverreceiver sshcheckreceiver statsdreceiver stefreceiver syslogreceiver systemdreceiver tcpcheckreceiver tcplogreceiver tlscheckreceiver udplogreceiver vcenterreceiver wavefrontreceiver webhookeventreceiver windowseventlogreceiver windowsperfcountersreceiver windowsservicereceiver xreceiver yanggrpcreceiver zipkinreceiver zookeeperreceiver
+cSpell:ignore: activedirectorydsreceiver aerospikereceiver apachereceiver apachesparkreceiver awscloudwatchreceiver awscontainerinsightreceiver awsecscontainermetricsreceiver awsfirehosereceiver awslambdareceiver awss awsxrayreceiver azureblobreceiver azureeventhubreceiver azuremonitorreceiver carbonreceiver chronyreceiver ciscoosreceiver cloudflarereceiver cloudfoundryreceiver collectdreceiver couchdbreceiver datadogreceiver dockerstatsreceiver elasticsearchreceiver envoyalsreceiver expvarreceiver faroreceiver filelogreceiver filestatsreceiver flinkmetricsreceiver fluentforwardreceiver githubreceiver gitlabreceiver googlecloudmonitoringreceiver googlecloudpubsubpushreceiver googlecloudpubsubreceiver googlecloudspannerreceiver haproxyreceiver hostmetricsreceiver httpcheckreceiver huaweicloudcesreceiver icmpcheckreceiver iisreceiver influxdbreceiver jaegerreceiver jmxreceiver journaldreceiver kafkametricsreceiver kafkareceiver kubeletstatsreceiver libhoneyreceiver lokireceiver memcachedreceiver mongodbatlasreceiver mongodbreceiver mysqlreceiver namedpipereceiver netflowreceiver nginxreceiver nopreceiver nsxtreceiver ntpreceiver oracledbreceiver osqueryreceiver otelarrowreceiver otlpjsonfilereceiver otlpreceiver podmanreceiver postgresqlreceiver pprofreceiver prometheusreceiver prometheusremotewritereceiver pulsarreceiver purefareceiver purefbreceiver rabbitmqreceiver receivercreator redfishreceiver redisreceiver riakreceiver saphanareceiver sclusterreceiver seventsreceiver signalfxreceiver simpleprometheusreceiver skywalkingreceiver slogreceiver snmpreceiver snowflakereceiver sobjectsreceiver solacereceiver splunkenterprisereceiver splunkhecreceiver sqlqueryreceiver sqlserverreceiver sshcheckreceiver statsdreceiver stefreceiver syslogreceiver systemdreceiver tcpcheckreceiver tcplogreceiver tlscheckreceiver udplogreceiver vcenterreceiver wavefrontreceiver webhookeventreceiver windowseventlogreceiver windowsperfcountersreceiver windowsservicereceiver xreceiver yanggrpcreceiver zookeeperreceiver
 ---
 
 レシーバーは、さまざまなソースとフォーマットからテレメトリーデータを収集します。
@@ -129,7 +129,6 @@ cSpell:ignore: activedirectorydsreceiver aerospikereceiver apachereceiver apache
 | {{< component-link name="windowsperfcountersreceiver" type="receiver" repo="contrib" >}}    | contrib                    | -            | beta           | -           |
 | {{< component-link name="windowsservicereceiver" type="receiver" repo="contrib" >}}         | contrib                    | -            | development    | -           |
 | {{< component-link name="yanggrpcreceiver" type="receiver" repo="contrib" >}}               | contrib                    | -            | alpha          | -           |
-| {{< component-link name="zipkinreceiver" type="receiver" repo="contrib" >}}                 | contrib, core, K8s         | beta         | -              | -           |
 | {{< component-link name="zookeeperreceiver" type="receiver" repo="contrib" >}}              | contrib                    | -            | alpha          | -           |
 
 [^1]: このコンポーネントが含まれている[ディストリビューション](/docs/collector/distributions/)（core、contrib、K8sなど）を示します。

data/collector-versions.yml

@@ -2,4 +2,4 @@
 # This file is automatically updated by scripts/collector-sync
 
 core: v0.149.0
-contrib: v0.148.0
+contrib: v0.149.0

scripts/collector-sync/README.md

@@ -11,11 +11,9 @@ This automation:
    [opentelemetry-ecosystem-explorer](https://github.com/open-telemetry/opentelemetry-ecosystem-explorer)
    repository to access the collector registry
 2. Reads component metadata from `ecosystem-registry/collector/`
-3. Generates markdown tables with component information
-4. Updates documentation pages in `content/en/docs/collector/components/`
-5. Updates version information in `data/collector-versions.yml`
-6. Fixes spelling errors in component names
-7. Creates/updates pull requests with the changes
+3. Updates data registry files in `data/collector/`
+4. Updates version information in `data/collector-versions.yml`
+5. Creates/updates pull requests with the changes
 
 ## Version Management
 
@@ -38,8 +36,6 @@ The automation:
 **To update versions for a new release:**
 
 1. Run the automation script (updates `data/collector-versions.yml`)
-2. Hugo automatically uses new versions in all component links
-3. No need to regenerate markdown tables
 
 ## Local Development
 
@@ -49,9 +45,9 @@ The automation:
 # Install uv
 curl -LsSf https://astral.sh/uv/install.sh | sh
 
-# Install Python dependencies
+# Install Python dependencies (including dev dependencies)
 cd scripts/collector-sync
-uv sync
+uv sync --all-extras
 ```
 
 ### Running Locally
@@ -66,12 +62,16 @@ uv run python -m documentation_sync --no-update
 
 ### Testing
 
+**Prerequisites:** Ensure dev dependencies are installed with
+`uv sync --all-extras`.
+
 ```bash
 # Run all tests
 npm run test:collector-sync
 
 # Or run individually
 npm run check:collector-sync        # pytest
+npm run check:collector-sync:types  # mypy type checking
 npm run check:collector-sync:lint   # ruff linting
 
 # Auto-fix linting issues

scripts/collector-sync/src/documentation_sync/component_data_generator.py

@@ -1,22 +1,20 @@
 """Generate YAML data files for Hugo rendering of component tables."""
 
-import re
+import logging
 from pathlib import Path
 from typing import Any
 
 import yaml
 
-import logging
-
 from documentation_sync import component_utils
 from documentation_sync.metadata_diagnostics import MetadataDiagnostics
 
 logger = logging.getLogger(__name__)
 
 class IndentDumper(yaml.Dumper):
-    def increase_indent(self, flow=False, indentless=False):
+    def increase_indent(self, flow: bool = False, indentless: bool = False) -> Any:
         # Setting indentless=False forces the list items to indent
-        return super(IndentDumper, self).increase_indent(flow, False)
+        return super().increase_indent(flow, False)
 
 class ComponentDataGenerator:
     """Generates component data files."""
@@ -139,9 +137,3 @@ def write_component_data_files(self, inventory: dict[str, Any], output_dir: Path
                 )
 
             logger.info("  ✓ %s", output_file.relative_to(output_dir))
-
-
-class IndentDumper(yaml.Dumper):
-    def increase_indent(self, flow=False, indentless=False):
-        # Setting indentless=False forces the list items to indent
-        return super(IndentDumper, self).increase_indent(flow, False)

scripts/collector-sync/src/documentation_sync/explorer_repository_manager.py

@@ -2,7 +2,6 @@
 
 import logging
 from pathlib import Path
-from typing import Optional
 
 from git import Repo
 from git.exc import GitCommandError
@@ -16,15 +15,15 @@ class ExplorerRepositoryManager:
     EXPLORER_REPO_URL = "https://github.com/open-telemetry/opentelemetry-ecosystem-explorer.git"
     DEFAULT_CLONE_PATH = Path("tmp_repos/opentelemetry-ecosystem-explorer")
 
-    def __init__(self, clone_path: Optional[Path] = None):
+    def __init__(self, clone_path: Path | None = None):
         """Initialize the repository manager.
 
         Args:
             clone_path: Path where the repository should be cloned.
                        Defaults to tmp_repos/opentelemetry-ecosystem-explorer
         """
         self.clone_path = clone_path or self.DEFAULT_CLONE_PATH
-        self._repo: Optional[Repo] = None
+        self._repo: Repo | None = None
 
     def ensure_repository(self) -> Path:
         """Ensure the repository is cloned and up to date.