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

import json
import re
from datetime import datetime


class ADFBuilder:
    PANEL_TYPES = {"info", "note", "success", "warning", "error", "tip"}
    STATUS_COLORS = {"neutral", "purple", "blue", "red", "yellow", "green"}

    @staticmethod
    def doc(blocks: list[dict]) -> str:
        return json.dumps(
            {
                "version": 1,
                "type": "doc",
                "content": blocks,
            },
            ensure_ascii=False,
        )

    @classmethod
    def paragraph(cls, text: str) -> dict:
        return {
            "type": "paragraph",
            "content": cls._parse_inline(text),
        }

    @classmethod
    def heading(cls, text: str, level: int = 3) -> dict:
        return {
            "type": "heading",
            "attrs": {"level": min(max(level, 1), 6)},
            "content": cls._parse_inline(text),
        }

    @staticmethod
    def code_block(code: str, language: str = "python") -> dict:
        return {
            "type": "codeBlock",
            "attrs": {"language": language},
            "content": [{"type": "text", "text": code}],
        }

    @classmethod
    def bullet_list(cls, items: list[str]) -> dict:
        return {
            "type": "bulletList",
            "content": [
                {
                    "type": "listItem",
                    "content": [cls.paragraph(item)],
                }
                for item in items
            ],
        }

    @classmethod
    def ordered_list(cls, items: list[str]) -> dict:
        return {
            "type": "orderedList",
            "content": [
                {
                    "type": "listItem",
                    "content": [cls.paragraph(item)],
                }
                for item in items
            ],
        }

    @staticmethod
    def mention(account_id: str, display_name: str) -> dict:
        return {
            "type": "mention",
            "attrs": {
                "id": account_id,
                "text": f"@{display_name}",
                "accessLevel": "",
                "userType": "DEFAULT",
            },
        }

    @staticmethod
    def link(url: str, text: str | None = None) -> dict:
        return {
            "type": "text",
            "text": text or url,
            "marks": [{"type": "link", "attrs": {"href": url}}],
        }

    @staticmethod
    def text_with_marks(text: str, marks: list[dict] | None = None) -> dict:
        node: dict = {"type": "text", "text": text}
        if marks:
            node["marks"] = marks
        return node

    @staticmethod
    def table(headers: list[str], rows: list[list[str]]) -> dict:
        return {
            "type": "table",
            "attrs": {"isNumberColumnEnabled": False, "layout": "default"},
            "content": [
                {
                    "type": "tableRow",
                    "content": [
                        {
                            "type": "tableHeader",
                            "attrs": {},
                            "content": [{"type": "paragraph", "content": [{"type": "text", "text": h}]}],
                        }
                        for h in headers
                    ],
                }
            ]
            + [
                {
                    "type": "tableRow",
                    "content": [
                        {
                            "type": "tableCell",
                            "attrs": {},
                            "content": [{"type": "paragraph", "content": [{"type": "text", "text": cell}]}],
                        }
                        for cell in row
                    ],
                }
                for row in rows
            ],
        }

    @classmethod
    def panel(cls, content: list[dict], panel_type: str = "info") -> dict:
        return {
            "type": "panel",
            "attrs": {"panelType": panel_type if panel_type in cls.PANEL_TYPES else "info"},
            "content": content,
        }

    @classmethod
    def info_panel(cls, text: str) -> dict:
        return cls.panel(
            [{"type": "paragraph", "content": [{"type": "text", "text": text}]}],
            "info",
        )

    @staticmethod
    def expand(title: str, content: list[dict]) -> dict:
        return {
            "type": "expand",
            "attrs": {"title": title},
            "content": content,
        }

    @staticmethod
    def task_list(tasks: list[dict]) -> dict:
        return {
            "type": "taskList",
            "attrs": {},
            "content": [
                {
                    "type": "taskItem",
                    "attrs": {
                        "localId": task.get("id", f"task-{i}"),
                        "state": task.get("state", "TODO"),
                    },
                    "content": [
                        {"type": "text", "text": task.get("text", "")},
                    ],
                }
                for i, task in enumerate(tasks)
            ],
        }

    @staticmethod
    def blockquote(content: list[dict]) -> dict:
        return {"type": "blockquote", "content": content}

    @staticmethod
    def rule() -> dict:
        return {"type": "rule"}

    @classmethod
    def status(cls, text: str, color: str = "neutral") -> dict:
        return {
            "type": "status",
            "attrs": {
                "text": text,
                "color": color if color in cls.STATUS_COLORS else "neutral",
            },
        }

    @staticmethod
    def date(iso_date: str) -> dict:
        ts = int(datetime.fromisoformat(iso_date).timestamp() * 1000)
        return {
            "type": "date",
            "attrs": {"timestamp": ts},
        }

    @staticmethod
    def media(media_id: str, media_type: str = "file", collection: str = "") -> dict:
        return {
            "type": "mediaSingle",
            "attrs": {"layout": "center"},
            "content": [
                {
                    "type": "media",
                    "attrs": {
                        "type": media_type,
                        "id": media_id,
                        "collection": collection,
                    },
                }
            ],
        }

    @staticmethod
    def emoji(short_name: str, id: str | None = None, text: str | None = None) -> dict:
        attrs: dict = {"shortName": short_name}
        if id:
            attrs["id"] = id
        if text:
            attrs["text"] = text
        return {
            "type": "emoji",
            "attrs": attrs,
        }

    @staticmethod
    def macro(name: str, params: dict | None = None) -> dict:
        macro_params: dict = {}
        if params:
            for key, value in params.items():
                macro_params[key] = {"value": value}
        return {
            "type": "extension",
            "attrs": {
                "extensionType": "com.atlassian.confluence.macro.core",
                "extensionKey": name,
                "parameters": {"macroParams": macro_params},
            },
        }

    @staticmethod
    def layout_section(columns: list[list[dict]], column_widths: list[int] | None = None) -> dict:
        if column_widths is None:
            column_widths = [100 // len(columns)] * len(columns)
        return {
            "type": "layoutSection",
            "attrs": {"layoutType": "two_equal" if len(columns) == 2 else "default"},
            "content": [
                {
                    "type": "layoutColumn",
                    "attrs": {"width": column_widths[i]},
                    "content": col,
                }
                for i, col in enumerate(columns)
            ],
        }

    @staticmethod
    def _parse_inline(text: str) -> list[dict]:
        pattern = re.compile(
            r'(\*\*(.+?)\*\*|\*(.+?)\*|`(.+?)`|\[(.+?)\]\((.+?)\))'
        )
        nodes = []
        last_end = 0
        for m in pattern.finditer(text):
            if m.start() > last_end:
                plain = text[last_end:m.start()]
                if plain:
                    nodes.append({"type": "text", "text": plain})
            last_end = m.end()

            if m.group(2):
                nodes.append({"type": "text", "text": m.group(2), "marks": [{"type": "strong"}]})
            elif m.group(3):
                nodes.append({"type": "text", "text": m.group(3), "marks": [{"type": "em"}]})
            elif m.group(4):
                nodes.append({"type": "text", "text": m.group(4), "marks": [{"type": "code"}]})
            elif m.group(5) and m.group(6):
                nodes.append({
                    "type": "text",
                    "text": m.group(5),
                    "marks": [{"type": "link", "attrs": {"href": m.group(6)}}],
                })

        if last_end < len(text):
            nodes.append({"type": "text", "text": text[last_end:]})

        return nodes or [{"type": "text", "text": text}]

    @classmethod
    def from_markdown(cls, md_text: str) -> str:
        blocks = []
        lines = md_text.split("\n")
        i = 0

        while i < len(lines):
            stripped = lines[i].strip()

            if not stripped:
                i += 1
                continue

            heading_match = re.match(r"^(#{1,6})\s+(.+)", stripped)
            if heading_match:
                level = len(heading_match.group(1))
                blocks.append(cls.heading(heading_match.group(2), level))
                i += 1
                continue

            if stripped.startswith("```"):
                lang = stripped[3:].strip() or "text"
                code_lines = []
                i += 1
                while i < len(lines) and not lines[i].strip().startswith("```"):
                    code_lines.append(lines[i])
                    i += 1
                i += 1
                blocks.append(cls.code_block("\n".join(code_lines), lang))
                continue

            if stripped.startswith("- ") or stripped.startswith("* "):
                items = []
                while i < len(lines) and (lines[i].strip().startswith("- ") or lines[i].strip().startswith("* ")):
                    items.append(lines[i].strip()[2:])
                    i += 1
                blocks.append(cls.bullet_list(items))
                continue

            ordered_match = re.match(r"^(\d+)\.\s+(.+)", stripped)
            if ordered_match:
                items = []
                while i < len(lines):
                    m = re.match(r"^(\d+)\.\s+(.+)", lines[i].strip())
                    if not m:
                        break
                    items.append(m.group(2))
                    i += 1
                blocks.append(cls.ordered_list(items))
                continue

            if stripped.startswith("> "):
                quote_lines = []
                while i < len(lines) and lines[i].strip().startswith("> "):
                    quote_lines.append(lines[i].strip()[2:])
                    i += 1
                blocks.append(cls.blockquote([cls.paragraph("\n".join(quote_lines))]))
                continue

            if stripped.startswith("---") or stripped.startswith("***"):
                blocks.append(cls.rule())
                i += 1
                continue

            table_match = re.match(r"^\|(.+)\|$", stripped)
            if table_match and i + 1 < len(lines) and re.match(r"^\|[\s\-:|]+\|$", lines[i + 1].strip()):
                headers = [h.strip() for h in table_match.group(1).split("|") if h.strip() or h.strip() == ""]
                rows = []
                i += 2
                while i < len(lines):
                    row_match = re.match(r"^\|(.+)\|$", lines[i].strip())
                    if not row_match:
                        break
                    cells = [c.strip() for c in row_match.group(1).split("|")]
                    rows.append(cells)
                    i += 1
                blocks.append(cls.table(headers, rows))
                continue

            blocks.append(cls.paragraph(stripped))
            i += 1

        return cls.doc(blocks)


def extract_text_from_adf(adf_json: str) -> str:
    try:
        doc = json.loads(adf_json) if isinstance(adf_json, str) else adf_json
    except (json.JSONDecodeError, TypeError):
        return ""

    parts = []

    def _walk(node):
        if isinstance(node, dict):
            if node.get("type") == "text":
                parts.append(node.get("text", ""))
            elif node.get("type") == "mention":
                parts.append(node.get("attrs", {}).get("text", "@unknown"))
            elif node.get("type") == "hardBreak":
                parts.append("\n")
            for child in node.get("content", []):
                _walk(child)
        elif isinstance(node, list):
            for item in node:
                _walk(item)

    _walk(doc)
    return "".join(parts)


ADF_REQUIRED_KEYS = {"version", "type", "content"}


def validate_adf(adf_json: str) -> tuple[bool, str]:
    try:
        doc = json.loads(adf_json) if isinstance(adf_json, str) else adf_json
    except (json.JSONDecodeError, TypeError) as e:
        return False, f"Invalid JSON: {e}"

    if not isinstance(doc, dict):
        return False, "ADF root must be a dict"

    missing = ADF_REQUIRED_KEYS - set(doc.keys())
    if missing:
        return False, f"Missing required keys: {missing}"

    if doc.get("type") != "doc":
        return False, f"Root type must be 'doc', got '{doc.get('type')}'"

    if doc.get("version") != 1:
        return False, f"ADF version must be 1, got {doc.get('version')}"

    return True, "OK"