"""Knowledge text chunking helpers.

Parser and markdown conversion logic has been moved to ``yuxi.plugins.parser``.
This module only keeps chunking-related utilities.
"""

from pathlib import Path

from langchain_community.document_loaders import (
    CSVLoader,
    JSONLoader,
    TextLoader,
    UnstructuredHTMLLoader,
    UnstructuredMarkdownLoader,
    UnstructuredWordDocumentLoader,
)
from langchain_text_splitters import RecursiveCharacterTextSplitter


def chunk_with_parser(file_path, params=None):
    """
    使用文件解析器将文件切分成固定大小的块

    Args:
        file_path: 文件路径
        params: 参数
    """
    params = params or {}
    chunk_size = int(params.get("chunk_size", 500))
    chunk_overlap = int(params.get("chunk_overlap", 100))

    file_type = Path(file_path).suffix.lower()

    # 选择合适的加载器
    if file_type in [".txt"]:
        loader = TextLoader(file_path)

    elif file_type in [".md"]:
        loader = UnstructuredMarkdownLoader(file_path)

    elif file_type in [".docx", ".doc"]:
        loader = UnstructuredWordDocumentLoader(file_path)

    elif file_type in [".html", ".htm"]:
        loader = UnstructuredHTMLLoader(file_path)

    elif file_type in [".json"]:
        loader = JSONLoader(file_path, jq_schema=".")

    elif file_type in [".csv"]:
        loader = CSVLoader(file_path)

    else:
        raise ValueError(f"不支持的文件类型: {file_type}")

    # 加载文档
    docs = loader.load()

    # 创建文本分割器
    text_splitter = RecursiveCharacterTextSplitter(
        chunk_size=chunk_size,
        chunk_overlap=chunk_overlap,
        separators=["\n\n", "\n", ".", " ", ""],
    )

    # 分割文档
    nodes = text_splitter.split_documents(docs)

    # 添加序号信息到metadata
    for i, node in enumerate(nodes):
        if node.metadata is None:
            node.metadata = {}
        node.metadata["chunk_idx"] = i

    return nodes


def chunk_text(text, params=None):
    """
    将文本切分成固定大小的块
    """
    params = params or {}
    chunk_size = int(params.get("chunk_size", 500))
    chunk_overlap = int(params.get("chunk_overlap", 100))

    # 创建文本分割器
    text_splitter = RecursiveCharacterTextSplitter(
        chunk_size=chunk_size, chunk_overlap=chunk_overlap, separators=["\n\n", "\n", ".", " ", ""]
    )

    # 分割文档
    nodes = text_splitter.split_text(text)

    # 添加序号信息到metadata
    nodes = [{"text": node, "metadata": {"chunk_idx": i}} for i, node in enumerate(nodes)]
    return nodes


def chunk(text_or_path, params=None):
    raise NotImplementedError("chunk is deprecated, use chunk_with_parser or chunk_text instead")