detailed comparison of files in "a" to files and hardlinks in "b"

arrs_inspector.sh

#!/bin/bash

# What Is This
#   A way to compare downloads in folder A to hardlinks in folder B.  Useful to see if your 
#   "use hardlinks" logic in the ARRS is working
#   
# Separation of Concerns (AI yackin')
#   The logic for calculating the 2TB physical limit is isolated from the descriptive logic 
#   used for the detailed file list.
# 
# Storage Logic (AI yackin')
#   The math specifically accounts for the unique nature of hardlinks, ensuring you know exactly 
#   how much "physical" space is left on your drive versus "apparent" space.
# 
# Usage
#   make this executable
#       chmod +x arrs_inspector.sh
#   arrs_inspector.sh --overview
#   arrs_inspector.sh --detail
# 
# More Terminal Fun! A few helpful one-liners
#   folders that contain more than one video file
#       find ~/files/downloads/movies -type f \( -iname "*.mp4" -o -iname "*.mkv" -o -iname "*.avi" -o -iname "*.m4v" -o -iname "*.mov" \) -printf "%h\n" | sort | uniq -c | awk '$1 > 1 {sub(/^[ \t]*[0-9]+ /, ""); print}' | xargs -I {} ls -lh {}
#   do I maybe need to upgrade soon? (prices and exchange rate hard-coded)
#       echo -e "Plan           | Storage | Monthly (USD) | Visualization\n$(echo -e "Bat Box\nGremlin Box\nVampire Box\nZombie Box\nRed Dragon Box" | awk -v used=$(du -sb ~ 2>/dev/null | cut -f1) 'BEGIN{OFS="|"; eur2usd=1.17; split("2000,3000,4000,6000,12000", s, ","); split("14.35,18.85,27.85,36.85,72.85", p, ",")} {gb=s[NR]; usd=p[NR]*eur2usd; bar_total=40; used_gb=used/(1024^3); used_marks=int((used_gb/gb)*bar_total); if(used_marks<1 && used_gb>0) used_marks=1; printf "%-14s | %4.1f TB | $%7.2f     | [", $0, gb/1000, usd; for(i=0; i<bar_total; i++) printf (i<used_marks ? "#" : "-"); printf "] %s\n", ($0=="Bat Box" ? sprintf("<< USED: %.1f GB (%.1f%%)", used_gb, (used_gb/gb)*100) : "")} END {print "\n* Pricing, exchange rate, and other deets subject to change."}')"

# Configuration - Update these paths if your movie folders change
DL_PATH="$HOME/files/downloads/movies"
MD_PATH="$HOME/files/media/movies"

# Colors for terminal output
GREEN='\033[0;32m'
BLUE='\033[0;34m'
YELLOW='\033[1;33m'
RED='\033[0;31m'
NC='\033[0m'

show_overview() {
    echo -e "${BLUE}--- Arrs Storage Overview ---${NC}"
    (
        find "$DL_PATH" -type f -printf "dl %i %s\n" 2>/dev/null
        find "$MD_PATH" -type f -printf "md %i %s\n" 2>/dev/null
    ) | awk -v yellow="$YELLOW" -v green="$GREEN" -v nc="$NC" '
    {
        type=$1; inode=$2; size=$3;
        
        # Count physical space (only count each unique inode once)
        if (!seen_inode[inode]++) { actual_sz += size }

        if (type == "dl") {
            dl_cnt++; dl_sz += size; dl_inodes[inode]++
        } else if (type == "md") {
            md_cnt++; md_sz += size;
            if (inode in dl_inodes) { hl_cnt++; hl_sz += size }
        }
    }
    END {
        printf "Downloads Total: %d files (%.2f GB)\n", dl_cnt, dl_sz/1024^3;
        printf "Media Total:     %d files (%.2f GB)\n", md_cnt, md_sz/1024^3;
        print "------------------------------------------";
        printf "Actual Physical Space Used: %s%.2f GB%s\n", yellow, actual_sz/1024^3, nc;
        printf "Space Saved by Hardlinks:   %s%.2f GB%s\n", green, (dl_sz+md_sz-actual_sz)/1024^3, nc;
    }'
}

show_detail() {
    echo -e "${BLUE}--- Detailed File Audit ---${NC}"
    find "$DL_PATH" "$MD_PATH" -type f -exec stat -c '%i %n' {} + 2>/dev/null | awk -v dl="$DL_PATH" -v md="$MD_PATH" -v green="$GREEN" -v red="$RED" -v nc="$NC" '
    {
        inode=$1; $1=""; sub(/^ /, "", $0); fullpath=$0;
        filename=fullpath; gsub(/.*\//, "", filename);
        
        if (fullpath ~ dl) { in_dl[filename] = 1; dl_inode[filename] = inode }
        if (fullpath ~ md) { in_md[filename] = 1; md_inode[filename] = inode }
    }
    END {
        for (f in in_dl) all[f]; for (f in in_md) all[f];
        for (f in all) {
            dl_status = (in_dl[f]) ? "exists" : "none  ";
            if (!in_md[f]) {
                md_status = "none";
                color = red;
            } else {
                if (in_dl[f] && dl_inode[f] == md_inode[f]) {
                    md_status = "hardlinked";
                    color = green;
                } else {
                    md_status = "COPY/FILE";
                    color = red;
                }
            }
            printf "[DL: %-7s] [MD: %s%-12s%s] %s\n", dl_status, color, md_status, nc, f;
        }
    }' | sort -k5
}

# Main Execution Logic
case "$1" in
    --overview)
        show_overview
        ;;
    --detail)
        show_detail
        ;;
    *)
        echo "Usage: $0 {--overview|--detail}"
        exit 1
        ;;
esac