"""Email message parsing utilities."""

from email.message import Message
from typing import Any

from myclaude.mail.utils import decode_header_value, strip_html_tags


def _extract_payload(part: Message) -> str:
    """Extract text payload from a message part."""
    charset = part.get_content_charset() or "utf-8"
    payload = part.get_payload(decode=True)
    if isinstance(payload, bytes):
        return payload.decode(charset, errors="replace")
    return str(payload or "")


def extract_text(msg: Message) -> tuple[str, str]:
    """Extract plain text and html body from a message.

    Returns (plain_text, html_text). Either may be empty.
    """
    plain_parts: list[str] = []
    html_parts: list[str] = []

    if msg.is_multipart():
        for part in msg.walk():
            ctype = part.get_content_type()
            cdisp = str(part.get("Content-Disposition", ""))
            if "attachment" in cdisp:
                continue
            if ctype == "text/plain":
                plain_parts.append(_extract_payload(part))
            elif ctype == "text/html":
                html_parts.append(_extract_payload(part))
    else:
        ctype = msg.get_content_type()
        payload = _extract_payload(msg)
        if ctype == "text/html":
            html_parts.append(payload)
        else:
            plain_parts.append(payload)

    plain = "\n".join(plain_parts).strip()
    html = "\n".join(html_parts).strip()

    if not plain and html:
        plain = strip_html_tags(html)

    return plain, html


def extract_attachments(msg: Message) -> list[dict[str, Any]]:
    """Return list of attachment metadata dicts."""
    attachments: list[dict[str, Any]] = []
    if not msg.is_multipart():
        return attachments

    for part in msg.walk():
        cdisp = str(part.get("Content-Disposition", ""))
        if "attachment" not in cdisp:
            continue
        filename = decode_header_value(part.get_filename())
        if filename:
            attachments.append(
                {
                    "filename": filename,
                    "content_type": part.get_content_type(),
                    "size": len(part.get_payload(decode=True) or b""),
                }
            )
    return attachments