import re
from src.format_extractor import FormatExtractor

# 模拟带换行的 HTML
html_with_newlines = """
in the name of
<span id="page_vi"></span>
abundance...
"""

extractor = FormatExtractor()
clean_text, text_with_ph, _, _, _ = extractor.extract(f"<p>{html_with_newlines}</p>")

print(f"Original HTML: {repr(html_with_newlines)}")
print(f"Clean Text: {repr(clean_text)}")
print(f"Text with PH: {repr(text_with_ph)}")
print(f"Has Newline: {'\\n' in text_with_ph}")
print("-" * 20)

# 模拟 Prompt 构建
prompt_line = f"p_00006 [BODY] {text_with_ph}"
print("Prompt Line Preview:")
print(prompt_line)