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

from __future__ import annotations

import re


def markdown_to_adf(markdown: str, *, is_final: bool = False) -> dict:
    lines = markdown.split("\n")
    blocks: list[dict] = []
    i = 0
    while i < len(lines):
        line = lines[i]
        if not line.strip():
            i += 1
            continue
        if line.startswith("```"):
            code_lines: list[str] = []
            lang = _extract_lang(line)
            i += 1
            while i < len(lines) and not lines[i].startswith("```"):
                code_lines.append(lines[i])
                i += 1
            i += 1
            blocks.append(_adf_code_block("\n".join(code_lines), lang))
            continue
        img_match = re.match(r"!\[([^\]]*)\]\(([^)]+)\)", line.strip())
        if img_match:
            blocks.append(_adf_media(img_match.group(2), img_match.group(1) or "image"))
            i += 1
            continue
        if line.startswith("> "):
            quote_lines: list[str] = []
            while i < len(lines) and lines[i].startswith("> "):
                quote_lines.append(lines[i][2:])
                i += 1
            blocks.append(_adf_blockquote("\n".join(quote_lines)))
            continue
        if line.startswith("#"):
            level = len(line) - len(line.lstrip("#"))
            heading_text = line.lstrip("#").strip()
            blocks.append(_adf_heading(heading_text, level))
            i += 1
            continue
        if line.strip().startswith("|") and line.strip().endswith("|"):
            table_rows: list[list[str]] = []
            while i < len(lines) and lines[i].strip().startswith("|"):
                cells = [c.strip() for c in lines[i].strip().strip("|").split("|")]
                table_rows.append(cells)
                i += 1
            if len(table_rows) >= 2:
                header = table_rows[0]
                data_start = 2 if _is_table_separator(table_rows[1]) else 1
                blocks.append(_adf_table(header, table_rows[data_start:]))
            continue
        if line.startswith("- ") or line.startswith("* "):
            list_items: list[str] = []
            while i < len(lines) and (lines[i].startswith("- ") or lines[i].startswith("* ")):
                list_items.append(lines[i][2:].strip())
                i += 1
            blocks.append(_adf_bullet_list(list_items))
            continue
        if re.match(r"^\d+\. ", line):
            list_items: list[str] = []
            while i < len(lines) and re.match(r"^\d+\. ", lines[i]):
                list_items.append(re.sub(r"^\d+\. ", "", lines[i]).strip())
                i += 1
            blocks.append(_adf_ordered_list(list_items))
            continue
        if line.strip() == "---":
            blocks.append({"type": "rule"})
            i += 1
            continue
        blocks.append(_adf_paragraph(line))
        i += 1

    return {"type": "doc", "version": 1, "content": blocks}


def _extract_lang(line: str) -> str:
    return line[3:].strip()


def _is_table_separator(cells: list[str]) -> bool:
    return all(re.match(r"^:?-{3,}:?$", c) for c in cells)


def _adf_table(header: list[str], rows: list[list[str]]) -> dict:
    table_rows = [
        {
            "type": "tableRow",
            "content": [
                {
                    "type": "tableHeader",
                    "content": [_adf_simple_paragraph(cell)],
                }
                for cell in header
            ],
        }
    ]
    for row in rows:
        table_rows.append(
            {
                "type": "tableRow",
                "content": [
                    {
                        "type": "tableCell",
                        "content": [_adf_simple_paragraph(cell)],
                    }
                    for cell in row
                ],
            }
        )
    return {
        "type": "table",
        "attrs": {"isNumberColumnEnabled": False, "layout": "default"},
        "content": table_rows,
    }


def _adf_simple_paragraph(text: str) -> dict:
    return {"type": "paragraph", "content": _parse_inline(text)}


def _parse_inline(text: str) -> list[dict]:
    result: list[dict] = []
    pattern = re.compile(
        r"(\*\*(.+?)\*\*|"
        r"~~(.+?)~~|"
        r"`(.+?)`|"
        r"\*(.+?)\*|"
        r"\[([^\]]+)\]\(([^)]+)\)|"
        r"@([\w.-]+))"
    )
    last_end = 0
    for match in pattern.finditer(text):
        if match.start() > last_end:
            result.append({"type": "text", "text": text[last_end : match.start()]})
        if match.group(2):
            result.append({"type": "text", "text": match.group(2), "marks": [{"type": "strong"}]})
        elif match.group(3):
            result.append({"type": "text", "text": match.group(3), "marks": [{"type": "strike"}]})
        elif match.group(4):
            result.append({"type": "text", "text": match.group(4), "marks": [{"type": "code"}]})
        elif match.group(5):
            result.append({"type": "text", "text": match.group(5), "marks": [{"type": "em"}]})
        elif match.group(6):
            result.append(
                {
                    "type": "text",
                    "text": match.group(6),
                    "marks": [{"type": "link", "attrs": {"href": match.group(7)}}],
                }
            )
        elif match.group(8):
            result.append(
                {
                    "type": "mention",
                    "attrs": {
                        "id": match.group(8),
                        "text": match.group(8),
                        "accessLevel": "",
                    },
                }
            )
        last_end = match.end()
    if last_end < len(text):
        result.append({"type": "text", "text": text[last_end:]})
    if not result:
        result.append({"type": "text", "text": text})
    return result


def _adf_paragraph(text: str) -> dict:
    return {"type": "paragraph", "content": _parse_inline(text)}


def _adf_heading(text: str, level: int) -> dict:
    return {
        "type": "heading",
        "attrs": {"level": min(level, 6)},
        "content": _parse_inline(text),
    }


def _adf_code_block(code: str, language: str = "") -> dict:
    attrs = {}
    if language:
        attrs["language"] = language
    return {
        "type": "codeBlock",
        "attrs": attrs,
        "content": [{"type": "text", "text": code}],
    }


def _adf_blockquote(text: str) -> dict:
    return {
        "type": "blockquote",
        "content": [_adf_paragraph(text)],
    }


def _adf_bullet_list(items: list[str]) -> dict:
    return {
        "type": "bulletList",
        "content": [
            {
                "type": "listItem",
                "content": [_adf_paragraph(item)],
            }
            for item in items
        ],
    }


def _adf_ordered_list(items: list[str]) -> dict:
    return {
        "type": "orderedList",
        "content": [
            {
                "type": "listItem",
                "content": [_adf_paragraph(item)],
            }
            for item in items
        ],
    }


def _adf_media(url: str, alt: str = "") -> dict:
    return {
        "type": "mediaSingle",
        "attrs": {"layout": "center"},
        "content": [
            {
                "type": "media",
                "attrs": {
                    "type": "external",
                    "url": url,
                    "alt": alt,
                },
            }
        ],
    }