aiisc-watermarking-model / highlighter.py
jgyasu's picture
Upload folder using huggingface_hub
38c3a0a verified
import re
def highlight_common_words(common_words, sentences, title):
color_map = {}
color_index = 0
highlighted_html = []
for idx, sentence in enumerate(sentences, start=1):
sentence_with_idx = f"{idx}. {sentence}"
highlighted_sentence = sentence_with_idx
for index, word in common_words:
if word not in color_map:
color_map[word] = f'hsl({color_index * 60 % 360}, 70%, 80%)'
color_index += 1
escaped_word = re.escape(word)
pattern = rf'\b{escaped_word}\b'
highlighted_sentence = re.sub(
pattern,
lambda m, idx=index, color=color_map[word]: (
f'<span style="background-color: {color}; font-weight: bold;'
f' padding: 2px 4px; border-radius: 2px; position: relative;">'
f'<span style="background-color: black; color: white; border-radius: 50%;'
f' padding: 2px 5px; margin-right: 5px;">{idx}</span>'
f'{m.group(0)}'
f'</span>'
),
highlighted_sentence,
flags=re.IGNORECASE
)
highlighted_html.append(highlighted_sentence)
final_html = "<br><br>".join(highlighted_html)
return f'''
<div style="border: solid 1px #; padding: 16px; background-color: #FFFFFF; color: #374151; box-shadow: 0 4px 8px rgba(0, 0, 0, 0.1); border-radius: 8px;">
<h3 style="margin-top: 0; font-size: 1em; color: #111827;">{title}</h3>
<div style="background-color: #F5F5F5; line-height: 1.6; padding: 15px; border-radius: 8px;">{final_html}</div>
</div>
'''
import re
# def highlight_common_words_dict(common_words, sentences, title):
# color_map = {}
# color_index = 0
# highlighted_html = []
# # Ensure indices in common_words are integers
# sanitized_common_words = [(int(index), word) for index, word in common_words]
# for idx, (sentence, score) in enumerate(sentences.items(), start=1):
# sentence_with_idx = f"{idx}. {sentence}"
# highlighted_sentence = sentence_with_idx
# for index, word in sanitized_common_words:
# if word not in color_map:
# color_map[word] = f'hsl({color_index * 60 % 360}, 70%, 80%)'
# color_index += 1
# escaped_word = re.escape(word)
# pattern = rf'\b{escaped_word}\b'
# highlighted_sentence = re.sub(
# pattern,
# lambda m, idx=index, color=color_map[word]: (
# f'<span style="background-color: {color}; font-weight: bold;'
# f' padding: 1px 2px; border-radius: 2px; position: relative;">'
# f'<span style="background-color: black; color: white; border-radius: 50%;'
# f' padding: 1px 3px; margin-right: 3px; font-size: 0.8em;">{idx}</span>'
# f'{m.group(0)}'
# f'</span>'
# ),
# highlighted_sentence,
# flags=re.IGNORECASE
# )
# highlighted_html.append(
# f'<div style="margin-bottom: 5px;">'
# f'{highlighted_sentence}'
# f'<div style="display: inline-block; margin-left: 5px; padding: 3px 5px; border-radius: 3px; background-color: white; font-size: 0.9em;">'
# f'Entailment Score: {score}</div></div>'
# )
# final_html = "<br>".join(highlighted_html)
# return f'''
# <div style="background-color: #ffffff; color: #374151;">
# <h3 style="margin-top: 0; font-size: 1em; color: #111827;">{title}</h3>
# <div style="background-color: #F5F5F5; line-height: 1.6; padding: 15px; border-radius: 8px;">{final_html}</div>
# </div>
# '''
def highlight_common_words_dict(common_words, sentences, title):
color_map = {}
color_index = 0
highlighted_html = []
for idx, (sentence, score) in enumerate(sentences.items(), start=1):
sentence_with_idx = f"{idx}. {sentence}"
highlighted_sentence = sentence_with_idx
for index, word in common_words:
if word not in color_map:
color_map[word] = f'hsl({color_index * 60 % 360}, 70%, 80%)'
color_index += 1
escaped_word = re.escape(word)
pattern = rf'\b{escaped_word}\b'
highlighted_sentence = re.sub(
pattern,
lambda m, idx=index, color=color_map[word]: (
f'<span style="background-color: {color}; font-weight: bold;'
f' padding: 2px 4px; border-radius: 2px; position: relative;">'
f'<span style="background-color: black; color: white; border-radius: 50%;'
f' padding: 2px 5px; margin-right: 5px;">{idx}</span>'
f'{m.group(0)}'
f'</span>'
),
highlighted_sentence,
flags=re.IGNORECASE
)
# Append the sentence and entailment score to the HTML
highlighted_html.append(
f'<div style="margin-bottom: 5px;">'
f'{highlighted_sentence}'
f'<div style="display: inline-block; margin-left: 10px; padding: 3px 8px; border-radius: 5px; background-color: #E5E7EB; font-size: 0.9em; color: #374151;">'
f'Entailment Score: {score}</div></div>'
)
final_html = "<br><br>".join(highlighted_html)
return f'''
<div style="border: solid 1px #E5E7EB; padding: 16px; background-color: #FFFFFF; color: #374151; box-shadow: 0 4px 8px rgba(0, 0, 0, 0.1); border-radius: 8px;">
<h3 style="margin-top: 0; font-size: 1em; color: #111827;">{title}</h3>
<div style="background-color: #F5F5F5; line-height: 1.6; padding: 15px; border-radius: 8px;">{final_html}</div>
</div>
'''
def reparaphrased_sentences_html(sentences):
formatted_sentences = []
for idx, sentence in enumerate(sentences, start=1):
# Add index to each sentence
sentence_with_idx = f"{idx}. {sentence}"
formatted_sentences.append(sentence_with_idx)
final_html = "<br><br>".join(formatted_sentences)
return f'''
<div style="border: solid 1px #ccc; padding: 16px; background-color: #FFFFFF; color: #374151;
box-shadow: 0 4px 8px rgba(0, 0, 0, 0.1); border-radius: 8px;">
<div style="background-color: #F5F5F5; line-height: 1.6; padding: 15px; border-radius: 8px;">{final_html}</div>
</div>
'''
# common_words = [(1, "highlight"), (2, "numbering")]
# sentences = ["This is a test to highlight words.", "Numbering is important for clarity."]
# # Test highlight_common_words
# highlighted_html = highlight_common_words(common_words, sentences, "Test Highlighting")
# print(highlighted_html)
# # Test highlight_common_words_dict
# sentences_with_scores = {"Highlight words in this text.": 0.95, "Number sentences for clarity.": 0.8}
# highlighted_html_dict = highlight_common_words_dict(common_words, sentences_with_scores, "Test Dict Highlighting")
# print(highlighted_html_dict)