ForcePilot/backend/package/yuxi/channels/adapters/imessage/formatter.py

from __future__ import annotations

import re

TABLE_ROW_RE = re.compile(r"^\|(.+)\|$")
TABLE_SEP_RE = re.compile(r"^\|[\s\-:\|]+\|$")
DIRECTIVE_RE = re.compile(r"<\s*/?directive[^>]*>", re.IGNORECASE)


def convert_markdown_tables(text: str) -> str:
    """将 Markdown 表格转换为可读的 bullets 格式。

    iMessage 不支持 Markdown 表格渲染，此函数将表格行转为可读的列表。
    """
    lines = text.split("\n")
    result: list[str] = []
    i = 0
    while i < len(lines):
        line = lines[i]
        if i + 2 < len(lines) and TABLE_ROW_RE.match(line) and TABLE_SEP_RE.match(lines[i + 1]):
            header = line
            sep = lines[i + 1]
            body_rows: list[str] = []
            j = i + 2
            while j < len(lines) and TABLE_ROW_RE.match(lines[j]):
                body_rows.append(lines[j])
                j += 1

            converted = _table_to_bullets(header, sep, body_rows)
            result.extend(converted)
            i = j
            continue

        result.append(line)
        i += 1

    return "\n".join(result)


def _table_to_bullets(header: str, sep: str, body_rows: list[str]) -> list[str]:
    header_cells = _parse_cells(header)
    sep_cells = _parse_cells(sep)

    if not header_cells:
        return [header, sep] + body_rows

    alignments = _detect_alignments(sep_cells, len(header_cells))
    body_cells = [_parse_cells(row) for row in body_rows]

    output: list[str] = []
    for row_idx, cells in enumerate([header_cells] + body_cells):
        if row_idx == 0:
            output.append(f"• {', '.join(cells)}")
        elif len(cells) <= 2:
            output.append("  " + ": ".join(cells))
        else:
            parts: list[str] = []
            for ci, (cell, hdr, align) in enumerate(zip(cells, header_cells, alignments)):
                prefix = f"  {hdr}: " if ci == 0 or align != "skip" else f"  {hdr}: "
                parts.append(f"{prefix}{cell}")
            output.append("")
            output.extend(parts)

    return output


def _parse_cells(row: str) -> list[str]:
    return [cell.strip() for cell in row.strip("|").split("|")]


def _detect_alignments(sep_cells: list[str], col_count: int) -> list[str]:
    aligns: list[str] = []
    for i in range(col_count):
        if i < len(sep_cells):
            cell = sep_cells[i]
            left = cell.startswith(":")
            right = cell.endswith(":")
            if left and right:
                aligns.append("center")
            elif right:
                aligns.append("right")
            else:
                aligns.append("left")
        else:
            aligns.append("left")
    return aligns


def sanitize_imessage_text(text: str) -> str:
    """净化出站文本，移除 iMessage 中不支持的格式。

    - 去除 \\r 字符（换行标准化）
    - 去除 <directive> 内联指令标签
    - 去除长度前缀损坏（如 \"123\\nThis is message\"）
    - 过滤控制字符
    - 合并多余空白行
    """
    text = text.replace("\r", "")

    text = DIRECTIVE_RE.sub("", text)

    text = _strip_length_prefix(text)

    text = re.sub(r"[\x00-\x08\x0b\x0c\x0e-\x1f\x7f-\x9f]", "", text)

    text = re.sub(r"\n{3,}", "\n\n", text)
    text = text.strip()

    return text


def _strip_length_prefix(text: str) -> str:
    """去除 iMessage 长度前缀损坏格式。

    BlueBubbles 可能在某些消息前附加长度前缀如 \"42\\nHello world\"，
    去除数字换行前缀。
    """
    match = re.match(r"^(\d+)\n", text)
    if match:
        prefix_len = int(match.group(1))
        remaining = text[match.end() :]
        if abs(len(remaining) - prefix_len) <= 5:
            return remaining
    return text