ForcePilot/backend/package/yuxi/channel/extensions/freshdesk/format.py

import html as html_mod
import re
from time import time as _time

ALLOWED_TAGS = {
    "p",
    "br",
    "b",
    "strong",
    "i",
    "em",
    "u",
    "s",
    "del",
    "ul",
    "ol",
    "li",
    "a",
    "img",
    "table",
    "tr",
    "td",
    "th",
    "h1",
    "h2",
    "h3",
    "h4",
    "h5",
    "h6",
    "hr",
    "blockquote",
    "code",
    "pre",
    "span",
}

ALLOWED_ATTRS = {
    "a": {"href", "rel", "target"},
    "img": {"src", "alt", "width", "height"},
    "td": {"colspan", "rowspan"},
    "th": {"colspan", "rowspan"},
}

FORBIDDEN_TAGS = {"script", "style", "iframe", "object", "embed", "form", "input"}


def sanitize_html(html_body: str) -> str:
    for tag in FORBIDDEN_TAGS:
        html_body = re.sub(
            rf"<\s*{tag}[^>]*>.*?<\s*/\s*{tag}\s*>",
            "",
            html_body,
            flags=re.DOTALL | re.IGNORECASE,
        )
        html_body = re.sub(
            rf"<\s*{tag}[^>]*/?\s*>",
            "",
            html_body,
            flags=re.IGNORECASE,
        )
    return html_body


def markdown_to_html(md_text: str) -> str:
    text = html_mod.escape(md_text)

    text = re.sub(r"```(\w+)?\n?(.*?)```", r"<pre><code>\2</code></pre>", text, flags=re.DOTALL)
    text = re.sub(r"`([^`]+)`", r"<code>\1</code>", text)
    text = re.sub(r"\*\*(.+?)\*\*", r"<strong>\1</strong>", text)
    text = re.sub(r"\*(.+?)\*", r"<em>\1</em>", text)
    text = re.sub(r"~~(.+?)~~", r"<s>\1</s>", text)
    text = re.sub(r"\[([^\]]+)\]\(([^)]+)\)", r'<a href="\2" rel="nofollow">\1</a>', text)

    text = re.sub(r"^[\-\*]\s+(.+)$", r"<li>\1</li>", text, flags=re.MULTILINE)
    text = re.sub(r"(<li>.*?</li>(\n?<li>.*?</li>)*)", r"<ul>\1</ul>", text)

    text = re.sub(r"^\d+\.\s+(.+)$", r"<li>\1</li>", text, flags=re.MULTILINE)
    text = re.sub(r"(<li>.*?</li>(\n?<li>.*?</li>)*)", r"<ol>\1</ol>", text)

    lines = text.split("\n")
    result_lines = []
    in_table = False
    table_rows = []
    for line in lines:
        if line.strip().startswith("|") and line.strip().endswith("|"):
            cells = [c.strip() for c in line.strip().strip("|").split("|")]
            if all(c.startswith("-") and len(c) > 1 for c in cells):
                continue
            table_rows.append("<tr>" + "".join(f"<td>{c}</td>" for c in cells) + "</tr>")
            in_table = True
        else:
            if in_table and table_rows:
                result_lines.append("<table>" + "".join(table_rows) + "</table>")
                table_rows = []
                in_table = False
            result_lines.append(line)
    if in_table and table_rows:
        result_lines.append("<table>" + "".join(table_rows) + "</table>")
    text = "\n".join(result_lines)

    text = re.sub(r"^>\s+(.+)$", r"<blockquote>\1</blockquote>", text, flags=re.MULTILINE)
    text = re.sub(r"^---+$", r"<hr>", text, flags=re.MULTILINE)
    text = re.sub(r"^#{1,2}\s+(.+)$", r"<h3>\1</h3>", text, flags=re.MULTILINE)
    text = re.sub(r"^#{3,6}\s+(.+)$", r"<h4>\1</h4>", text, flags=re.MULTILINE)

    lines = text.split("\n")
    result = []
    for line in lines:
        stripped = line.strip()
        if not stripped:
            result.append("<br>")
        elif stripped.startswith("<") and not stripped.startswith("<br"):
            result.append(stripped)
        else:
            result.append(f"<p>{stripped}</p>")
    return "\n".join(result)


def message_parts_to_text(parts: list[dict]) -> str:
    texts = []
    for part in parts:
        if "text" in part:
            texts.append(part["text"].get("content", ""))
        elif "image" in part:
            img = part["image"]
            texts.append(f"[图片: {img.get('name', img.get('url', ''))}]")
        elif "file" in part:
            f = part["file"]
            texts.append(f"[文件: {f.get('name', f.get('url', ''))}]")
        elif "card" in part:
            card = part["card"]
            texts.append(f"[卡片: {card.get('title', '')}]")
    return "\n".join(texts)


def get_agent_prompt_rules(mode: str = "both") -> list[str]:
    rules = [
        "Your response will be sent to Freshdesk/Freshworks as an AI agent reply.",
    ]

    if mode in ("freshdesk", "both"):
        rules.extend(
            [
                "--- Freshdesk (Ticket System) Format Rules ---",
                "The message body is HTML. Use <strong> for bold, <em> for italic.",
                'Use <a href="URL" rel="nofollow">text</a> for links.',
                "Use <ul><li>item</li></ul> for unordered lists.",
                "Use <ol><li>item</li></ol> for ordered lists.",
                "Use <code> for inline code and <pre><code> for code blocks.",
                "Use <blockquote>text</blockquote> for quotations.",
                "Use <h3> or <h4> for headings.",
                "Use <table><tr><td>...</td></tr></table> for tables.",
                "Do NOT use <script>, <style>, <iframe>, <div> tags.",
                "Do NOT use CSS class or id attributes.",
            ]
        )

    if mode in ("freshchat", "both"):
        rules.extend(
            [
                "--- Freshchat (Messaging Platform) Format Rules ---",
                "The message is plain text. Rich formatting via **bold** and *italic*.",
                "URLs are auto-detected and rendered as clickable links.",
                "Use Quick Reply buttons when asking for user choice (options: 2-5 items).",
                "Keep messages concise and conversational.",
            ]
        )

    rules.extend(
        [
            "--- General Rules ---",
            "Identify yourself as an AI assistant when relevant.",
            "If the issue requires human intervention, suggest escalation.",
        ]
    )

    return rules


def parse_timestamp(ts: str) -> int:
    try:
        from datetime import datetime

        dt = datetime.fromisoformat(ts.replace("Z", "+00:00"))
        return int(dt.timestamp() * 1000)
    except (ValueError, TypeError):
        return int(_time() * 1000)