Finds the average size in bytes of the content of the column "Body"

column_average_bytes.sh

#!/bin/bash

# Check if a file path is provided
if [ "$#" -ne 1 ]; then
    echo "Usage: $0 <csv_file_path>"
    exit 1
fi

file_path=$1
total_size=0
count=0

# Check if the file exists
if [ ! -f "$file_path" ]; then
    echo "File does not exist: $file_path"
    exit 1
fi

# Read the file line by line, skipping the header
while IFS=, read -r date body message; do
    if [ $count -ne 0 ]; then  # Skip the header row
        # Calculate the size of the Body field in bytes
        size=$(echo -n "$body" | wc -c | awk '{print $1}')
        total_size=$((total_size + size))
    fi
    count=$((count + 1))
done < <(tail -n +2 "$file_path")

# Calculate the average size
if [ $count -gt 1 ]; then  # Adjust for the fact that count includes the header
    avg_size=$(echo "scale=2; $total_size / ($count - 1)" | bc)
    echo "Average size: $avg_size bytes"
else
    echo "No data to process."
fi