Spaces:
Sleeping
Sleeping
File size: 4,258 Bytes
0eb97a6 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 | import json
import gradio as gr
def analyze_text(text: str) -> str:
"""Analyze text and return statistics.
Args:
text: The input text to analyze
Returns:
JSON string with analysis results
"""
words = text.split()
chars = len(text)
chars_no_spaces = len(text.replace(" ", ""))
sentences = text.count(".") + text.count("!") + text.count("?")
avg_word_length = round(chars_no_spaces / len(words), 2) if words else 0
avg_sentence_length = round(len(words) / max(sentences, 1), 2)
return json.dumps(
{
"total_characters": chars,
"characters_without_spaces": chars_no_spaces,
"total_words": len(words),
"total_sentences": max(sentences, 1),
"average_word_length": avg_word_length,
"average_sentence_length": avg_sentence_length,
"unique_words": len(set(word.lower() for word in words)),
}
)
def extract_keywords(text: str, count: int = 5) -> str:
"""Extract keywords (most common words) from text.
Args:
text: The input text
count: Number of keywords to return (default 5)
Returns:
JSON string with keywords and frequencies
"""
# Remove common words
stopwords = {
"the",
"a",
"an",
"and",
"or",
"but",
"in",
"on",
"at",
"to",
"for",
"of",
"with",
"is",
"are",
"was",
"were",
"be",
"been",
"by",
"from",
}
words = text.lower().split()
filtered = [w.strip(".,!?;:") for w in words if w.lower() not in stopwords]
from collections import Counter
word_freq = Counter(filtered)
top_words = word_freq.most_common(count)
return json.dumps({"keywords": [{"word": w, "frequency": f} for w, f in top_words]})
def check_reading_level(text: str) -> str:
"""Estimate reading difficulty level.
Args:
text: The input text
Returns:
JSON string with reading level estimate
"""
sentences = max(
text.count(".") + text.count(",") + text.count("!") + text.count("?"), 1
)
words = len(text.split())
syllables = (
text.count("a")
+ text.count("e")
+ text.count("i")
+ text.count("o")
+ text.count("u")
)
if words == 0:
return json.dumps({"error": "No text to analyze"})
# Flesh Kincaid Grade
grade = (0.39 * (words / sentences)) + (11.8 * (syllables / words)) - 15.59
grade = max(0, round(grade, 1))
if grade < 6:
level = "Elementary School"
elif grade < 9:
level = "Middle School"
elif grade < 13:
level = "High School"
else:
level = "College/Academic"
return json.dumps({"grade_level": grade, "reading_level": level})
# Create web UI
with gr.Blocks(title="Text Processor") as demo:
gr.Markdown("# Text Processing Tools")
gr.Markdown(
"Analyze text statistics, extract keywords, and check reading difficulty."
)
with gr.Tab("Text Analysis"):
text_input1 = gr.Textbox(
label="Enter text",
lines=8,
placeholder="Paste your text here...",
)
analysis_output = gr.Textbox(label="Analysis Result", lines=8)
gr.Button("Analyze", size="lg").click(
analyze_text, inputs=text_input1, outputs=analysis_output
)
with gr.Tab("Extract Keywords"):
text_input2 = gr.Textbox(label="Enter text", lines=8)
count_input = gr.Slider(1, 20, value=5, step=1, label="Number of keywords")
keywords_output = gr.Textbox(label="Keywords ", lines=8)
gr.Button("Extract", size="lg").click(
extract_keywords, inputs=[text_input2, count_input], outputs=keywords_output
)
with gr.Tab("Reading Level"):
text_input3 = gr.Textbox(label="Enter text", lines=8)
level_output = gr.Textbox(label="Reading Level Analysis", lines=5)
gr.Button("Check Level", size="lg").click(
check_reading_level, inputs=text_input3, outputs=level_output
)
if __name__ == "__main__":
demo.launch(mcp_server=True)
|