Merge branch 'development' into alex_devenum_update

Author: alexandraBara

.github/workflows/update-plugin-docs.yml

@@ -0,0 +1,62 @@
+# Workflow to run plugin documentation generation then create a PR with the updated changes
+
+name: Plugin Documentation Generator
+
+permissions:
+  contents: write
+  pull-requests: write
+
+on:
+  workflow_dispatch:
+  schedule:
+    - cron: '0 0 * * *'
+
+jobs:
+  generate_docs:
+    runs-on: [ self-hosted ]
+    # To disable this workflow, set DISABLE_AUTO_DOCS to 'true' in repository variables
+    if: vars.DISABLE_AUTO_DOCS != 'true'
+    env:
+      HOME: /tmp/github-actions-home
+
+    steps:
+    - name: Setup HOME directory
+      run: |
+        mkdir -p /tmp/github-actions-home
+        export HOME=/tmp/github-actions-home
+
+    - name: Checkout repository
+      uses: actions/checkout@v4
+      with:
+        token: ${{ secrets.GITHUB_TOKEN }}
+
+    - name: Install dependencies
+      run: ./dev-setup.sh
+
+    - name: Run plugin documentation generator
+      run: |
+        source venv/bin/activate
+        python docs/generate_plugin_doc_bundle.py \
+          --package nodescraper.plugins.inband \
+          --output docs/PLUGIN_DOC.md
+
+    - name: Format documentation with pre-commit
+      run: |
+        source venv/bin/activate
+        pre-commit run --files docs/PLUGIN_DOC.md || true
+
+    - name: Create Pull Request
+      uses: peter-evans/create-pull-request@v6
+      with:
+        token: ${{ secrets.GITHUB_TOKEN }}
+        commit-message: "docs: Update plugin documentation [automated]"
+        committer: "github-actions[bot] <github-actions[bot]@users.noreply.github.com>"
+        author: "github-actions[bot] <github-actions[bot]@users.noreply.github.com>"
+        branch: automated-plugin-docs-update
+        delete-branch: true
+        title: "docs: Update plugin documentation [automated]"
+        body: |
+          Automated plugin documentation update generated by workflow.
+
+          This PR was automatically created by the Plugin Documentation Generator workflow.
+        labels: documentation,automated

CONTRIBUTING.md

@@ -52,8 +52,41 @@ When creating a PR, use the following process.
 > By creating a PR, you agree to allow your contribution to be licensed under the
 > terms of the LICENSE.txt file.
 
-### Documentation
+### Pre-commit hooks
 
-Submit Node Scraper documentation changes to our
-[documentation](https://github.com/amd/node-scraper/blob/development/README.md). You must update
-documentation related to any new feature or API contribution.
+This repository uses [pre-commit](https://pre-commit.com/) to automatically format code. When you commit changes to plugin files, the hooks will:
+
+1. Run code formatters (ruff, black)
+2. Run type checking (mypy)
+
+#### Setup
+
+Install pre-commit hooks after cloning the repository:
+
+```bash
+# Activate your virtual environment
+source venv/bin/activate
+
+# Install pre-commit hooks
+pre-commit install
+```
+
+#### Usage
+
+The hooks run automatically when you commit.
+
+```bash
+# First commit attempt - hooks run and may modify files
+git commit -m "Add new plugin feature"
+
+# If hooks modified files, stage them and commit again
+git add .
+git commit -m "Add new plugin feature"
+```
+
+You can also run hooks manually:
+
+```bash
+# Run all hooks on all files
+pre-commit run --all-files
+```

docs/PLUGIN_DOC.md

@@ -269,7 +269,7 @@ def extract_regexes_and_args_from_analyzer(
             output.append("**Analyzer Args:**")
             for key, value in anns.items():
                 # Format the type annotation
-                type_str = str(value).replace("typing.", "")
+                type_str = format_type_annotation(value)
                 output.append(f"- `{key}`: {type_str}")
 
     return output
@@ -294,9 +294,23 @@ def bases_list(cls: type) -> List[str]:
         return []
 
 
+def format_type_annotation(type_ann: Any) -> str:
+    """
+    Format a type annotation for documentation, removing non-deterministic content like function memory addresses.
+    """
+    import re
+
+    type_str = str(type_ann)
+    type_str = type_str.replace("typing.", "")
+    type_str = re.sub(r"<function\s+(\w+)\s+at\s+0x[0-9a-fA-F]+>", r"\1", type_str)
+    type_str = re.sub(r"<bound method\s+(\S+)\s+of\s+.+?>", r"\1", type_str)
+    type_str = re.sub(r"<class '([^']+)'>", r"\1", type_str)
+    return type_str
+
+
 def annotations_for_model(model_cls: type) -> List[str]:
     anns = get_attr(model_cls, "__annotations__", {}) or {}
-    return [f"**{k}**: `{v}`" for k, v in anns.items()]
+    return [f"**{k}**: `{format_type_annotation(v)}`" for k, v in anns.items()]
 
 
 def class_vars_dump(cls: type, exclude: set) -> List[str]:
@@ -458,7 +472,7 @@ def render_analyzer_args_section(args_cls: type, link_base: str, rel_root: Optio
 
     anns = get_attr(args_cls, "__annotations__", {}) or {}
     if anns:
-        ann_items = [f"**{k}**: `{v}`" for k, v in anns.items()]
+        ann_items = [f"**{k}**: `{format_type_annotation(v)}`" for k, v in anns.items()]
         s += md_header("Annotations / fields", 3) + md_list(ann_items)
     return s
 

docs/generate_plugin_doc_bundle.py

@@ -334,6 +334,7 @@ def process_args(
         plugin_arg_index = -1
 
     plugin_arg_map = {}
+    invalid_plugins = []
     if plugin_arg_index != -1 and plugin_arg_index != len(raw_arg_input) - 1:
         top_level_args = raw_arg_input[: plugin_arg_index + 1]
         plugin_args = raw_arg_input[plugin_arg_index + 1 :]
@@ -344,12 +345,26 @@ def process_args(
         else:
             cur_plugin = None
             for arg in plugin_args:
-                if arg in plugin_names:
+                # Handle comma-separated plugin names (but not arguments)
+                if not arg.startswith("-") and "," in arg:
+                    # Split comma-separated plugin names
+                    for potential_plugin in arg.split(","):
+                        potential_plugin = potential_plugin.strip()
+                        if potential_plugin in plugin_names:
+                            plugin_arg_map[potential_plugin] = []
+                            cur_plugin = potential_plugin
+                        elif potential_plugin:
+                            # Track invalid plugin names to log event later
+                            invalid_plugins.append(potential_plugin)
+                elif arg in plugin_names:
                     plugin_arg_map[arg] = []
                     cur_plugin = arg
                 elif cur_plugin:
                     plugin_arg_map[cur_plugin].append(arg)
-    return (top_level_args, plugin_arg_map)
+                elif not arg.startswith("-"):
+                    # Track invalid plugin names to log event later
+                    invalid_plugins.append(arg)
+    return (top_level_args, plugin_arg_map, invalid_plugins)
 
 
 def main(arg_input: Optional[list[str]] = None):
@@ -367,7 +382,9 @@ def main(arg_input: Optional[list[str]] = None):
     parser, plugin_subparser_map = build_parser(plugin_reg, config_reg)
 
     try:
-        top_level_args, plugin_arg_map = process_args(arg_input, list(plugin_subparser_map.keys()))
+        top_level_args, plugin_arg_map, invalid_plugins = process_args(
+            arg_input, list(plugin_subparser_map.keys())
+        )
 
         parsed_args = parser.parse_args(top_level_args)
         system_info = get_system_info(parsed_args)
@@ -387,6 +404,13 @@ def main(arg_input: Optional[list[str]] = None):
         if log_path:
             logger.info("Log path: %s", log_path)
 
+        # Log warning if invalid plugin names were provided
+        if invalid_plugins:
+            logger.warning(
+                "Invalid plugin name(s) ignored: %s. Use 'describe plugin' to list available plugins.",
+                ", ".join(invalid_plugins),
+            )
+
         if parsed_args.subcmd == "summary":
             generate_summary(parsed_args.search_path, parsed_args.output_path, logger)
             sys.exit(0)

nodescraper/cli/cli.py

@@ -173,6 +173,12 @@ def run_queue(self) -> list[PluginResult]:
                         global_run_args = self.apply_global_args_to_plugin(
                             plugin_inst, plugin_class, self.plugin_config.global_args
                         )
+                        # Merge analysis_args and collection_args
+                        for args_key in ["analysis_args", "collection_args"]:
+                            if args_key in global_run_args and args_key in run_payload:
+                                # Merge: global args override plugin-specific args keys specified in both global and plugin-specific args
+                                run_payload[args_key].update(global_run_args[args_key])
+                                del global_run_args[args_key]
                         run_payload.update(global_run_args)
                     except ValueError as ve:
                         self.logger.error(