SpineWallpaper/tools/downloader/jslit.py

"""JS 字面量 → Python 对象。

米哈游活动页把骨架数据与场景树以 **JS 对象字面量** 内联在 bundle 里，不是合法 JSON：

    {skeleton:{hash:"KR8Ibf8DXTI",spine:"4.2.43",x:-110.93},bones:[{name:"root"}],scaleX:.6487}

键不带引号、小数可以省略前导 0、布尔写作 ``!0`` / ``!1``、末尾可以有逗号。
这里只做**词法层**的规范化（把字面量改写成 JSON 文本），再交给 ``json.loads``——
不 ``eval``、不执行页面代码。

唯一被容忍的"语义"是未知裸标识符（例如 ``undefined``）：默认替换为 ``null`` 并计数，
``strict=True`` 时抛错。骨架数据里出现别的裸标识符说明提取边界错了，值得知道。
"""

from __future__ import annotations

import json
import re
from typing import Any

__all__ = ["loads", "match_literal", "first_object_value", "unescape", "JsLitError"]

# 按优先级排列的词法单元。字符串/数字/``!0`` 必须排在 ``other`` 之前。
_TOKEN = re.compile(
    r"""
      (?P<ws>\s+)
    | (?P<dquote>"(?:[^"\\]|\\.)*")
    | (?P<squote>'(?:[^'\\]|\\.)*')
    | (?P<template>`(?:[^`\\]|\\.)*`)
    | (?P<negnot>!0|!1)
    | (?P<num>-?(?:\d+\.\d*|\.\d+|\d+)(?:[eE][+-]?\d+)?)
    | (?P<ident>[A-Za-z_$][\w$]*)
    | (?P<other>.)
    """,
    re.VERBOSE | re.DOTALL,
)

_LITERAL_IDENTS = {"true": "true", "false": "false", "null": "null"}
_NULL_IDENTS = {"undefined", "NaN", "Infinity", "void"}

_ESCAPES = {"n": "\n", "t": "\t", "r": "\r", "b": "\b", "f": "\f", "v": "\v", "0": "\0"}


class JsLitError(ValueError):
    """字面量无法规范化成 JSON。"""


def unescape(body: str) -> str:
    """还原 JS 字符串体里的转义（``\\n`` / ``\\uXXXX`` / ``\\'`` / ``\\\\`` …）。

    Family B 的骨架是 ``e.exports=JSON.parse('…')``：外层是**单引号** JS 字符串，
    必须先按 JS 语义还原，再交给 ``json.loads``。
    """
    return _unescape(body, "'")


def _unescape(body: str, quote: str) -> str:
    """还原 JS 字符串体（不含两端引号）里的转义。"""
    out: list[str] = []
    i = 0
    while i < len(body):
        ch = body[i]
        if ch != "\\":
            out.append(ch)
            i += 1
            continue
        nxt = body[i + 1] if i + 1 < len(body) else ""
        if nxt == "u" and i + 6 <= len(body):
            out.append(chr(int(body[i + 2 : i + 6], 16)))
            i += 6
        elif nxt == "x" and i + 4 <= len(body):
            out.append(chr(int(body[i + 2 : i + 4], 16)))
            i += 4
        elif nxt == "\n":  # 行延续
            i += 2
        else:
            out.append(_ESCAPES.get(nxt, nxt))
            i += 2
    return "".join(out)


def _num_key(value: str) -> str:
    """把数字字面量还原成 JS 当键时用的字符串（``0`` → ``"0"``、``.5`` → ``"0.5"``）。"""
    try:
        as_float = float(value)
    except ValueError:
        return value
    if as_float.is_integer():
        return str(int(as_float))
    return repr(as_float)


def _normalize(text: str, *, strict: bool) -> tuple[str, int]:
    out: list[str] = []
    unknown = 0
    pos = 0
    for m in _TOKEN.finditer(text):
        kind = m.lastgroup
        raw = m.group()
        if kind == "ws" or kind == "other":
            out.append(raw)
            pos = m.end()
            continue
        if kind in ("dquote", "squote", "template"):
            body = raw[1:-1]
            quote = raw[0]
            out.append(json.dumps(_unescape(body, quote), ensure_ascii=False))
        elif kind == "negnot":
            out.append("true" if raw == "!0" else "false")
        elif kind == "num":
            value = raw
            if value.startswith("-."):
                value = "-0" + value[1:]
            elif value.startswith("."):
                value = "0" + value
            if value.endswith("."):
                value += "0"
            # 数字也能当键（动画名就叫 "0" 的骨架真实存在：`animations:{0:{…}}`）。
            # JS 会把数字字面量转成字符串当键，所以这里要按同一语义还原。
            if re.match(r"\s*:", text[m.end() :]):
                out.append(json.dumps(_num_key(value), ensure_ascii=False))
            else:
                out.append(value)
        elif kind == "ident":
            # 后面（跳过空白）跟冒号的标识符是键，否则是值。
            tail = text[m.end() :]
            is_key = bool(re.match(r"\s*:", tail))
            if is_key:
                out.append(json.dumps(raw, ensure_ascii=False))
            elif raw in _LITERAL_IDENTS:
                out.append(_LITERAL_IDENTS[raw])
            elif raw in _NULL_IDENTS:
                out.append("null")
                unknown += 1
                if strict:
                    raise JsLitError(f"未知标识符 {raw!r} @ {m.start()}")
            else:
                out.append("null")
                unknown += 1
                if strict:
                    raise JsLitError(f"未知标识符 {raw!r} @ {m.start()}")
        pos = m.end()
    if pos < len(text):
        out.append(text[pos:])
    normalized = "".join(out)
    # 尾逗号：`,}` / `,]`
    normalized = re.sub(r",(\s*[}\]])", r"\1", normalized)
    return normalized, unknown


def loads(text: str, *, strict: bool = False) -> Any:
    """把 JS 字面量文本解析成 Python 对象。"""
    normalized, _ = _normalize(text, strict=strict)
    try:
        return json.loads(normalized)
    except json.JSONDecodeError as exc:
        head = text[max(0, exc.pos - 120) : exc.pos + 120].replace("\n", " ")
        raise JsLitError(f"字面量规范化后仍不是 JSON：{exc.msg} @ {exc.pos}\n…{head}…") from exc


def match_literal(text: str, start: int) -> int:
    """返回 ``text[start]`` 处那个配平字面量的**闭括号下标**；找不到返回 -1。

    与 JS 侧同名的辅助函数一一对应：跳过字符串/模板串/注释，按开闭括号配平。
    它是所有提取器的地基——正则数不清嵌套括号，只有这个能。
    """
    if start >= len(text):
        return -1
    open_ch = text[start]
    close_ch = {"{": "}", "[": "]", "(": ")"}.get(open_ch)
    if close_ch is None:
        return -1
    depth = 0
    i = start
    while i < len(text):
        ch = text[i]
        if ch in "\"'`":
            quote = ch
            i += 1
            while i < len(text):
                if text[i] == "\\":
                    i += 2
                elif text[i] == quote:
                    break
                else:
                    i += 1
            i += 1
            continue
        if ch == "/" and i + 1 < len(text) and text[i + 1] == "/":
            while i < len(text) and text[i] != "\n":
                i += 1
            continue
        if ch == "/" and i + 1 < len(text) and text[i + 1] == "*":
            i += 2
            while i + 1 < len(text) and not (text[i] == "*" and text[i + 1] == "/"):
                i += 1
            i += 2
            continue
        if ch == open_ch:
            depth += 1
        elif ch == close_ch:
            depth -= 1
            if depth == 0:
                return i
        i += 1
    return -1


def first_object_value(text: str, brace_index: int) -> Any:
    """``Object.values(Object.assign({k: v}))[0]`` 的取值语义：解析 ``{...}`` 并返回第一个值。"""
    end = match_literal(text, brace_index)
    if end < 0:
        raise JsLitError(f"未配平的对象字面量 @ {brace_index}")
    obj = loads(text[brace_index : end + 1])
    if not isinstance(obj, dict) or not obj:
        raise JsLitError(f"期望非空对象字面量 @ {brace_index}")
    return next(iter(obj.values()))