compare_tags.sh

compare_tags.sh

#!/bin/bash

# compare_tags.sh - Compare leaf node tags between two Immuta CSV files
# Usage: ./compare_tags.sh file1.csv file2.csv

if [ $# -ne 2 ]; then
    echo "Usage: $0 <file1.csv> <file2.csv>"
    exit 1
fi

FILE1=$1
FILE2=$2
TEMP_DIR=$(mktemp -d)
TAGS1="${TEMP_DIR}/tags1.txt"
TAGS2="${TEMP_DIR}/tags2.txt"
ONLY_IN_1="${TEMP_DIR}/only_in_1.txt"
ONLY_IN_2="${TEMP_DIR}/only_in_2.txt"

echo "Comparing tag leaf nodes between:"
echo "  - $FILE1"
echo "  - $FILE2"
echo ""

# Extract first column (leaf nodes), skip header, remove quotes, and sort
cut -d, -f1 "$FILE1" | tail -n +2 | tr -d '"' | sort > "$TAGS1"
cut -d, -f1 "$FILE2" | tail -n +2 | tr -d '"' | sort > "$TAGS2"

# Find tags unique to each file
comm -23 "$TAGS1" "$TAGS2" > "$ONLY_IN_1"
comm -13 "$TAGS1" "$TAGS2" > "$ONLY_IN_2"

# Count results
COUNT1=$(wc -l < "$ONLY_IN_1")
COUNT2=$(wc -l < "$ONLY_IN_2")
TOTAL1=$(wc -l < "$TAGS1")
TOTAL2=$(wc -l < "$TAGS2")

# Display summary
echo "Summary:"
echo "  - $FILE1: $TOTAL1 total tags"
echo "  - $FILE2: $TOTAL2 total tags"
echo "  - $COUNT1 tags only in $FILE1"
echo "  - $COUNT2 tags only in $FILE2"
echo ""

# Display detailed results if differences exist
if [ $COUNT1 -gt 0 ]; then
    echo "Tags only in $FILE1:"
    cat "$ONLY_IN_1" | sed 's/^/  - /'
    echo ""
fi

if [ $COUNT2 -gt 0 ]; then
    echo "Tags only in $FILE2:"
    cat "$ONLY_IN_2" | sed 's/^/  - /'
    echo ""
fi

# Clean up
rm -rf "$TEMP_DIR"

echo "Comparison complete."