Workplan dependencies and prio for text research lab workplans

src/markitect_tool/cli/main.py

@@ -16,6 +16,7 @@ from markitect_tool.contract import (
     load_contract_file,
     validate_contract,
 )
+from markitect_tool.query import InvalidQueryError, extract_document, query_document
 from markitect_tool.schema import load_schema_file, validate_markdown_file, validate_schema
 
 
@@ -65,6 +66,60 @@ def metrics(file: Path, output_format: str) -> None:
     _emit_metrics(data, output_format)
 
 
+@main.command()
+@click.argument("file", type=click.Path(exists=True, dir_okay=False, path_type=Path))
+@click.argument("selector")
+@click.option(
+    "--format",
+    "output_format",
+    type=click.Choice(["json", "yaml", "text"], case_sensitive=False),
+    default="json",
+    show_default=True,
+)
+def query(file: Path, selector: str, output_format: str) -> None:
+    """Query structured Markdown content with a small selector."""
+
+    document = parse_markdown_file(file)
+    try:
+        matches = query_document(document, selector)
+    except InvalidQueryError as exc:
+        raise click.ClickException(str(exc)) from exc
+    data = {
+        "selector": selector,
+        "document_path": str(file),
+        "count": len(matches),
+        "matches": [match.to_dict() for match in matches],
+    }
+    _emit_query(data, output_format)
+
+
+@main.command()
+@click.argument("file", type=click.Path(exists=True, dir_okay=False, path_type=Path))
+@click.argument("selector")
+@click.option(
+    "--format",
+    "output_format",
+    type=click.Choice(["text", "json", "yaml"], case_sensitive=False),
+    default="text",
+    show_default=True,
+)
+def extract(file: Path, selector: str, output_format: str) -> None:
+    """Extract text or Markdown content from structured Markdown."""
+
+    document = parse_markdown_file(file)
+    try:
+        items = extract_document(document, selector)
+    except InvalidQueryError as exc:
+        raise click.ClickException(str(exc)) from exc
+    data = {
+        "selector": selector,
+        "document_path": str(file),
+        "count": len(items),
+        "items": items,
+    }
+    _emit_extract(data, output_format)
+
+
 @main.command()
 @click.argument("file", type=click.Path(exists=True, dir_okay=False, path_type=Path))
 @click.option(
@@ -214,5 +269,28 @@ def _emit_metrics(data: dict, output_format: str) -> None:
                 )
 
 
+def _emit_query(data: dict, output_format: str) -> None:
+    if output_format == "json":
+        click.echo(json.dumps(data, indent=2, ensure_ascii=False))
+    elif output_format == "yaml":
+        click.echo(yaml.safe_dump(data, sort_keys=False))
+    else:
+        click.echo(f"{data['count']} match(es)")
+        for match in data["matches"]:
+            location = f":{match['line']}" if match.get("line") else ""
+            click.echo(f"- {match['kind']} {match['path']}{location}")
+            if match.get("text"):
+                click.echo(f"  {match['text'].splitlines()[0]}")
+
+
+def _emit_extract(data: dict, output_format: str) -> None:
+    if output_format == "json":
+        click.echo(json.dumps(data, indent=2, ensure_ascii=False))
+    elif output_format == "yaml":
+        click.echo(yaml.safe_dump(data, sort_keys=False))
+    else:
+        click.echo("\n\n".join(data["items"]))
+
+
 if __name__ == "__main__":
     main()