Build a tool to calculate content readability

Creating a tool to calculate content readability typically involves implementing readability formulas such as the Flesch-Kincaid Grade Level, Flesch Reading Ease, Gunning Fog Index, SMOG Index, or Coleman-Liau Index. Here’s a simple Python script that calculates several readability scores for any given text input.

python
CopyEdit
import re
import math

def count_syllables(word):
    word = word.lower()
    vowels = "aeiouy"
    syllables = 0
    if word[0] in vowels:
        syllables +=1
    for index in range(1, len(word)):
        if word[index] in vowels and word[index-1] not in vowels:
            syllables +=1
    if word.endswith("e"):
        syllables -= 1
    if syllables == 0:
        syllables = 1
    return syllables

def count_words(text):
    words = re.findall(r'bw+b', text)
    return len(words)

def count_sentences(text):
    sentences = re.findall(r'[.!?]+', text)
    return len(sentences) if len(sentences) > 0 else 1

def count_syllables_in_text(text):
    words = re.findall(r'bw+b', text)
    syllables = sum(count_syllables(word) for word in words)
    return syllables

def flesch_reading_ease(text):
    words = count_words(text)
    sentences = count_sentences(text)
    syllables = count_syllables_in_text(text)
    # Flesch Reading Ease formula
    score = 206.835 - 1.015 * (words / sentences) - 84.6 * (syllables / words)
    return round(score, 2)

def flesch_kincaid_grade(text):
    words = count_words(text)
    sentences = count_sentences(text)
    syllables = count_syllables_in_text(text)
    # Flesch-Kincaid Grade Level formula
    score = 0.39 * (words / sentences) + 11.8 * (syllables / words) - 15.59
    return round(score, 2)

def gunning_fog_index(text):
    words = count_words(text)
    sentences = count_sentences(text)
    complex_words = count_complex_words(text)
    score = 0.4 * ((words / sentences) + 100 * (complex_words / words))
    return round(score, 2)

def count_complex_words(text):
    words = re.findall(r'bw+b', text)
    complex_words = [word for word in words if count_syllables(word) >= 3]
    return len(complex_words)

def smog_index(text):
    sentences = count_sentences(text)
    complex_words = count_complex_words(text)
    if sentences >= 3:
        score = 1.0430 * math.sqrt(complex_words * (30 / sentences)) + 3.1291
        return round(score, 2)
    else:
        return None  # Not enough sentences for SMOG calculation

def coleman_liau_index(text):
    words = count_words(text)
    sentences = count_sentences(text)
    letters = len(re.findall(r'[A-Za-z]', text))
    L = (letters / words) * 100
    S = (sentences / words) * 100
    score = 0.0588 * L - 0.296 * S - 15.8
    return round(score, 2)

def readability_report(text):
    report = {
        "Flesch Reading Ease": flesch_reading_ease(text),
        "Flesch-Kincaid Grade Level": flesch_kincaid_grade(text),
        "Gunning Fog Index": gunning_fog_index(text),
        "SMOG Index": smog_index(text),
        "Coleman-Liau Index": coleman_liau_index(text)
    }
    return report

# Example usage:
if __name__ == "__main__":
    sample_text = """Your content here. Replace this with the text you want to analyze for readability."""
    results = readability_report(sample_text)
    for metric, score in results.items():
        print(f"{metric}: {score}")

This tool:

• Counts words, sentences, syllables, and complex words.

• Calculates five common readability scores.

• Returns a dictionary of scores for your content.

You can integrate this into a website backend, CLI, or any Python environment to measure readability. Would you like it adapted for a web interface or another language?