#!/usr/bin/env bash
# Find duplicate files in a directory using checksums

DIR="${1:-$HOME}"
MIN_SIZE="${2:-1M}"  # Only files larger than 1MB

echo "Scanning $DIR for duplicate files (min size: $MIN_SIZE)..."
echo "Skipping: .cache, node_modules, .git, .local, .config, tmp, tmp.*"

# Find files, compute md5sum, group by hash, show duplicates
find "$DIR" \
    -type f \
    -size "+$MIN_SIZE" \
    \( \
        -not -path "*/.cache/*" \
        -not -path "*/node_modules/*" \
        -not -path "*/.git/*" \
        -not -path "*/.local/*" \
        -not -path "*/.config/*" \
        -not -path "*/tmp/*" \
        -not -path "*/tmp.*/*" \
        -not -path "*/.npm/*" \
        -not -path "*/.cargo/*" \
        -not -path "*/.ollama/*" \
        -not -path "*/.config/llama-swap/*" \
        -not -path "*/.cache/*" \
        -not -path "*/.local/share/Steam/*" \
        -not -path "*/.local/share/containers/*" \
        -not -path "*/.local/lib/docker/*" \
    \) \
    -exec md5sum {} + 2>/dev/null | \
    sort | \
    uniq -D -w 32 | \
    cut -c 35-