"""测试所有 PDF Readers 的一致性。"""

import pytest
from readers.pdf import (
    docling,
    docling_ocr,
    markitdown,
    pypdf,
    unstructured,
    unstructured_ocr,
)


class TestPdfReadersConsistency:
    """验证所有 PDF Readers 解析同一文件时核心文字内容一致。"""

    def test_all_readers_parse_same_content(self, temp_pdf):
        """测试所有 Readers 解析同一文件时核心内容一致。"""
        file_path = temp_pdf(text="测试PDF标题\n这是测试段落内容。\n第二段内容。")

        parsers = [
            ("docling", docling.parse),
            ("docling_ocr", docling_ocr.parse),
            ("markitdown", markitdown.parse),
            ("pypdf", pypdf.parse),
            ("unstructured", unstructured.parse),
            ("unstructured_ocr", unstructured_ocr.parse),
        ]

        successful_results = []
        for name, parser in parsers:
            content, error = parser(file_path)
            if content is not None and content.strip():
                successful_results.append((name, content))

        assert len(successful_results) > 0, "没有任何 reader 成功解析文件"

        core_texts = ["测试", "PDF", "标题", "段落", "内容"]
        for name, content in successful_results:
            assert any(text in content for text in core_texts), \
                f"{name} 解析结果不包含核心内容"