"""
Module for highlighting text based on keywords.
 
This module provides functionality to highlight specific keywords within text documents.
It handles both single word (one-gram) and multi-word (n-gram) keyword highlighting,
allowing for flexible text markup based on keyword extraction results.
"""
 
import re
import logging
 
DEFAULT_HIGHLIGHT_PRE = "<kw>"
DEFAULT_HIGHLIGHT_POST = "</kw>"

from yake.highlight import TextHighlighter
 
# Sample text to process
text = "Natural language processing is a field of artificial intelligence that focuses on interactions between computers and human language."
 
# Keywords to highlight
keywords = ["natural language processing", "artificial intelligence", "computers"]
 
# Initialize the highlighter with maximum n-gram size of 3
highlighter = TextHighlighter(max_ngram_size=3)
 
# Get highlighted text
highlighted_text = highlighter.highlight(text, keywords)
print(highlighted_text)
# Output: "<kw>Natural language processing</kw> is a field of <kw>artificial intelligence</kw> that focuses on interactions between <kw>computers</kw> and human language."
 
# Custom highlighting markers
custom_highlighter = TextHighlighter(
    max_ngram_size=3,
    highlight_pre="**",
    highlight_post="**"
)
custom_highlighted = custom_highlighter.highlight(text, keywords)
print(custom_highlighted)
# Output: "**Natural language processing** is a field of **artificial intelligence** that focuses on interactions between **computers** and human language."