markitect-tool/src/markitect_tool/cli/main.py

"""`mkt` command entry point."""

from __future__ import annotations

import json
from pathlib import Path

import click
import yaml

from markitect_tool.core import parse_markdown_file
from markitect_tool.contract import (
    ContractLoaderError,
    check_markdown_file,
    collect_metrics,
    load_contract_file,
    validate_contract,
)
from markitect_tool.ops import IncludeError, compose_files, resolve_includes, transform_markdown
from markitect_tool.query import InvalidQueryError, extract_document, query_document
from markitect_tool.schema import load_schema_file, validate_markdown_file, validate_schema


@click.group()
@click.version_option()
def main() -> None:
    """Markdown-native toolkit for structured knowledge artifacts."""


@main.command()
@click.argument("file", type=click.Path(exists=True, dir_okay=False, path_type=Path))
@click.option(
    "--format",
    "output_format",
    type=click.Choice(["json", "yaml", "tree"], case_sensitive=False),
    default="json",
    show_default=True,
)
def parse(file: Path, output_format: str) -> None:
    """Parse a Markdown file into a structured representation."""

    document = parse_markdown_file(file)
    data = document.to_dict()
    if output_format == "yaml":
        click.echo(yaml.safe_dump(data, sort_keys=False))
    elif output_format == "tree":
        for heading in document.headings:
            click.echo(f"{'#' * heading.level} {heading.text}")
    else:
        click.echo(json.dumps(data, indent=2, ensure_ascii=False))


@main.command()
@click.argument("file", type=click.Path(exists=True, dir_okay=False, path_type=Path))
@click.option(
    "--format",
    "output_format",
    type=click.Choice(["json", "yaml", "text"], case_sensitive=False),
    default="text",
    show_default=True,
)
def metrics(file: Path, output_format: str) -> None:
    """Report practical size and complexity metrics for a Markdown file."""

    document = parse_markdown_file(file)
    data = collect_metrics(document).to_dict() | {"document_path": str(file)}
    _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("--strip-frontmatter", is_flag=True, help="Remove YAML frontmatter.")
@click.option(
    "--set",
    "set_values",
    multiple=True,
    metavar="KEY=VALUE",
    help="Set a frontmatter value. Dot paths create nested mappings.",
)
@click.option(
    "--heading-delta",
    type=int,
    default=0,
    show_default=True,
    help="Shift ATX heading levels, clamped to 1..6.",
)
@click.option("--extract", "extract_selector", help="Replace content with selector output.")
@click.option(
    "--output",
    type=click.Path(dir_okay=False, path_type=Path),
    help="Write transformed Markdown to a file.",
)
@click.option(
    "--format",
    "output_format",
    type=click.Choice(["markdown", "json", "yaml"], case_sensitive=False),
    default="markdown",
    show_default=True,
)
def transform(
    file: Path,
    strip_frontmatter: bool,
    set_values: tuple[str, ...],
    heading_delta: int,
    extract_selector: str | None,
    output: Path | None,
    output_format: str,
) -> None:
    """Apply deterministic transforms to a Markdown file."""

    try:
        frontmatter_updates = _parse_key_value_options(set_values)
        result = transform_markdown(
            file.read_text(encoding="utf-8"),
            strip_frontmatter=strip_frontmatter,
            set_frontmatter=frontmatter_updates,
            heading_delta=heading_delta,
            extract_selector=extract_selector,
            source_path=str(file),
        )
    except (InvalidQueryError, ValueError) as exc:
        raise click.ClickException(str(exc)) from exc
    _emit_markdown_result(result.to_dict(), output_format, output)


@main.command()
@click.argument(
    "files",
    nargs=-1,
    required=True,
    type=click.Path(exists=True, dir_okay=False, path_type=Path),
)
@click.option("--title", help="Add a top-level title before composed files.")
@click.option(
    "--heading-delta",
    type=int,
    default=0,
    show_default=True,
    help="Shift heading levels in each input before composing.",
)
@click.option(
    "--include-frontmatter",
    is_flag=True,
    help="Keep each input file's frontmatter in the composed body.",
)
@click.option(
    "--output",
    type=click.Path(dir_okay=False, path_type=Path),
    help="Write composed Markdown to a file.",
)
@click.option(
    "--format",
    "output_format",
    type=click.Choice(["markdown", "json", "yaml"], case_sensitive=False),
    default="markdown",
    show_default=True,
)
def compose(
    files: tuple[Path, ...],
    title: str | None,
    heading_delta: int,
    include_frontmatter: bool,
    output: Path | None,
    output_format: str,
) -> None:
    """Compose multiple Markdown files into one document."""

    result = compose_files(
        list(files),
        title=title,
        heading_delta=heading_delta,
        include_frontmatter=include_frontmatter,
    )
    _emit_markdown_result(result.to_dict(), output_format, output)


@main.command()
@click.argument("file", type=click.Path(exists=True, dir_okay=False, path_type=Path))
@click.option(
    "--base-dir",
    type=click.Path(exists=True, file_okay=False, path_type=Path),
    help="Directory includes must stay within. Defaults to the input file directory.",
)
@click.option(
    "--max-depth",
    type=int,
    default=10,
    show_default=True,
    help="Maximum recursive include depth.",
)
@click.option(
    "--output",
    type=click.Path(dir_okay=False, path_type=Path),
    help="Write resolved Markdown to a file.",
)
@click.option(
    "--format",
    "output_format",
    type=click.Choice(["markdown", "json", "yaml"], case_sensitive=False),
    default="markdown",
    show_default=True,
)
def include(
    file: Path,
    base_dir: Path | None,
    max_depth: int,
    output: Path | None,
    output_format: str,
) -> None:
    """Resolve Markdown include markers in a document."""

    try:
        result = resolve_includes(
            file.read_text(encoding="utf-8"),
            base_dir=base_dir or file.parent,
            current_path=file,
            max_depth=max_depth,
        )
    except IncludeError as exc:
        raise click.ClickException(str(exc)) from exc
    _emit_markdown_result(result.to_dict(), output_format, output)


@main.command()
@click.argument("file", type=click.Path(exists=True, dir_okay=False, path_type=Path))
@click.option(
    "--schema",
    "schema_file",
    required=True,
    type=click.Path(exists=True, dir_okay=False, path_type=Path),
)
@click.option(
    "--format",
    "output_format",
    type=click.Choice(["json", "yaml", "text"], case_sensitive=False),
    default="text",
    show_default=True,
)
def validate(file: Path, schema_file: Path, output_format: str) -> None:
    """Validate a Markdown file against a Markdown schema file."""

    result = validate_markdown_file(file, schema_file)
    _emit_result(result.to_dict(), output_format)
    raise click.exceptions.Exit(0 if result.valid else 1)


@main.group()
def schema() -> None:
    """Work with Markdown schema files."""


@schema.command("validate")
@click.argument("schema_file", type=click.Path(exists=True, dir_okay=False, path_type=Path))
@click.option(
    "--format",
    "output_format",
    type=click.Choice(["json", "yaml", "text"], case_sensitive=False),
    default="text",
    show_default=True,
)
def schema_validate(schema_file: Path, output_format: str) -> None:
    """Validate that a Markdown schema contains a well-formed JSON Schema."""

    loaded = load_schema_file(schema_file)
    result = validate_schema(loaded.schema)
    data = result.to_dict() | {"schema_path": str(schema_file)}
    _emit_result(data, output_format)
    raise click.exceptions.Exit(0 if result.valid else 1)


@main.group()
def contract() -> None:
    """Work with Markdown document contracts."""


@contract.command("validate")
@click.argument("contract_file", type=click.Path(exists=True, dir_okay=False, path_type=Path))
@click.option(
    "--format",
    "output_format",
    type=click.Choice(["json", "yaml", "text"], case_sensitive=False),
    default="text",
    show_default=True,
)
def contract_validate(contract_file: Path, output_format: str) -> None:
    """Validate that a Markdown contract file is well formed."""

    result = validate_contract(load_contract_file(contract_file))
    _emit_diagnostic_result(result.to_dict(), output_format)
    raise click.exceptions.Exit(0 if result.valid else 1)


@contract.command("check")
@click.argument("file", type=click.Path(exists=True, dir_okay=False, path_type=Path))
@click.option(
    "--contract",
    "contract_file",
    required=True,
    type=click.Path(exists=True, dir_okay=False, path_type=Path),
)
@click.option(
    "--format",
    "output_format",
    type=click.Choice(["json", "yaml", "text"], case_sensitive=False),
    default="text",
    show_default=True,
)
def contract_check(file: Path, contract_file: Path, output_format: str) -> None:
    """Check a Markdown file against a Markdown document contract."""

    try:
        result = check_markdown_file(file, contract_file)
    except ContractLoaderError as exc:
        raise click.ClickException(str(exc)) from exc
    _emit_diagnostic_result(result.to_dict(), output_format)
    raise click.exceptions.Exit(0 if result.valid else 1)


def _emit_result(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:
        if data.get("valid"):
            click.echo("valid")
        else:
            click.echo("invalid")
            for violation in data.get("violations", []):
                click.echo(f"- {violation['path']}: {violation['message']}")


def _emit_diagnostic_result(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("valid" if data.get("valid") else "invalid")
        for diagnostic in data.get("diagnostics", []):
            click.echo(
                f"- [{diagnostic['severity']}] {diagnostic['code']}: "
                f"{diagnostic['message']}"
            )
            if diagnostic.get("source"):
                source = diagnostic["source"]
                suffix = f":{source['line']}" if source.get("line") else ""
                click.echo(f"  source: {source.get('path', '<document>')}{suffix}")
            if diagnostic.get("guidance"):
                click.echo(f"  guidance: {diagnostic['guidance']}")


def _emit_metrics(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:
        doc = data["document"]
        click.echo("document")
        for metric, value in doc.items():
            click.echo(f"- {metric}: {value}")
        sections = data.get("sections", [])
        if sections:
            click.echo("sections")
            for section in sections:
                click.echo(
                    f"- {section['heading']}: words={section['words']}, "
                    f"paragraphs={section['paragraphs']}, line={section['line']}"
                )


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"]))


def _emit_markdown_result(data: dict, output_format: str, output: Path | None) -> None:
    if output_format == "json":
        click.echo(json.dumps(data, indent=2, ensure_ascii=False))
        return
    if output_format == "yaml":
        click.echo(yaml.safe_dump(data, sort_keys=False))
        return
    markdown = data["markdown"]
    if output:
        output.write_text(markdown, encoding="utf-8")
    else:
        click.echo(markdown, nl=False)


def _parse_key_value_options(items: tuple[str, ...]) -> dict[str, object]:
    values: dict[str, object] = {}
    for item in items:
        if "=" not in item:
            raise ValueError(f"Expected KEY=VALUE, got `{item}`")
        key, raw_value = item.split("=", 1)
        key = key.strip()
        if not key:
            raise ValueError(f"Expected non-empty key in `{item}`")
        _set_path(values, key.split("."), yaml.safe_load(raw_value))
    return values


def _set_path(mapping: dict[str, object], path: list[str], value: object) -> None:
    current = mapping
    for part in path[:-1]:
        next_value = current.setdefault(part, {})
        if not isinstance(next_value, dict):
            raise ValueError(f"Cannot set nested frontmatter path through scalar `{part}`")
        current = next_value
    current[path[-1]] = value


if __name__ == "__main__":
    main()