from __future__ import annotations

import re

_ALLOWED_TAGS = {
    "b",
    "strong",
    "i",
    "em",
    "u",
    "ins",
    "s",
    "strike",
    "del",
    "code",
    "pre",
    "a",
}

_TAG_PATTERN = re.compile(r"</?(\w+)[^>]*>")

_TABLE_ROW_PATTERN = re.compile(r"^\|(.+)\|$", re.MULTILINE)
_TABLE_SEPARATOR_PATTERN = re.compile(r"^\|[\s\-:|]+\|$", re.MULTILINE)


def text_sanitizer(text: str) -> str:
    if not text:
        return ""

    text = text.replace("&nbsp;", " ")

    def _replace_tag(m: re.Match) -> str:
        tag = m.group(1).lower()
        if tag in _ALLOWED_TAGS:
            return m.group(0)
        return ""

    text = _TAG_PATTERN.sub(_replace_tag, text)
    text = text.strip()
    return text


def markdown_to_whatsapp(md_text: str) -> str:
    if not md_text:
        return ""

    text = md_text

    text = re.sub(r"```(\w+)?\n(.*?)```", _code_block, text, flags=re.DOTALL)
    text = re.sub(r"`([^`]+)`", r"```\1```", text)

    text = _convert_tables(text)

    # All formatting -> temp markers to prevent cross-contamination
    text = re.sub(r"\*\*\*(.+?)\*\*\*", r"<BI>\1</BI>", text)
    text = re.sub(r"___(.+?)___", r"<BI>\1</BI>", text)
    text = re.sub(r"\*\*(.+?)\*\*", r"<B>\1</B>", text)
    text = re.sub(r"__(.+?)__", r"<B>\1</B>", text)
    text = re.sub(r"(?<!\*)\*(?!\*)(.+?)(?<!\*)\*(?!\*)", r"<I>\1</I>", text)
    text = re.sub(r"(?<!_)_(?!_)(.+?)(?<!_)_(?!_)", r"<I>\1</I>", text)

    text = text.replace("<BI>", "*_")
    text = text.replace("</BI>", "_*")
    text = text.replace("<B>", "*")
    text = text.replace("</B>", "*")
    text = text.replace("<I>", "_")
    text = text.replace("</I>", "_")

    text = re.sub(r"~~(.+?)~~", r"~\1~", text)

    text = re.sub(r"^### (.+)$", r"*_\1_*", text, flags=re.MULTILINE)
    text = re.sub(r"^## (.+)$", r"*_\1_*", text, flags=re.MULTILINE)
    text = re.sub(r"^# (.+)$", r"*_\1_*", text, flags=re.MULTILINE)

    text = re.sub(r"\[([^\]]+)\]\(([^)]+)\)", _link, text)

    text = re.sub(r"^\- (.+)$", r"• \1", text, flags=re.MULTILINE)
    text = re.sub(r"^\d+\. (.+)$", r"• \1", text, flags=re.MULTILINE)

    text = text.replace("<br>", "\n")
    text = re.sub(r"\n{3,}", "\n\n", text)

    return text.strip()


def _convert_tables(text: str) -> str:

    def _replace_table(m: re.Match) -> str:
        table_block = m.group(0)
        lines = table_block.strip().split("\n")
        if len(lines) < 2:
            return table_block

        data_lines = []
        header = None
        for line in lines:
            stripped = line.strip()
            if not stripped.startswith("|"):
                continue
            if _TABLE_SEPARATOR_PATTERN.match(stripped):
                continue
            cells = [c.strip() for c in stripped[1:-1].split("|")]
            if header is None:
                header = " | ".join(cells)
            else:
                data_lines.append("• " + " | ".join(cells))

        if header is None:
            return table_block

        result = [header]
        result.extend(data_lines)
        return "\n".join(result)

    text = re.sub(
        r"(?:^|\n)(\|.+\|\s*\n){2,}",
        _replace_table,
        text,
        flags=re.MULTILINE,
    )
    return text


def _code_block(m: re.Match) -> str:
    lang = m.group(1) or ""
    code = m.group(2).strip()
    prefix = f"[{lang}]\n" if lang else ""
    return f"```{prefix}{code}```"


def _link(m: re.Match) -> str:
    text = m.group(1)
    url = m.group(2)
    if text == url:
        return url
    if not text.strip():
        return url
    return f"{text}\n({url})"