dupes

#!/bin/bash

# Check if a search term is provided
if [ -z "$1" ]; then
    echo "Usage: $0 <filename-pattern>"
    exit 1
fi

# Define the search directory (current directory by default)
SEARCH_DIR=${2:-.}

# Find files matching the pattern
echo "Searching for files matching '$1' in '$SEARCH_DIR'..."
FILES=()
while IFS= read -r file; do
    FILES+=("$file")
done < <(find "$SEARCH_DIR" -type f -iname "*$1*" 2>/dev/null)

# If no files found, exit
if [ ${#FILES[@]} -eq 0 ]; then
    echo "No matching files found."
    exit 0
fi

# Display found files
echo -e "\nResults are:"
for file in "${FILES[@]}"; do
    echo "$file"
done

# Function to check if two files are identical
are_files_identical() {
    cmp -s "$1" "$2"
}

# Group identical files
GROUPED_FILES=()  # Holds lists of identical files
UNIQUE_FILES=()    # Holds unique files

for file in "${FILES[@]}"; do
    MATCH_FOUND=false
    for i in "${!GROUPED_FILES[@]}"; do
        ref_file=${GROUPED_FILES[$i]%% *}  # Get the first file in the group
        if are_files_identical "$file" "$ref_file"; then
            GROUPED_FILES[$i]="${GROUPED_FILES[$i]} $file"
            MATCH_FOUND=true
            break
        fi
    done

    if [ "$MATCH_FOUND" = false ]; then
        GROUPED_FILES+=("$file")
        UNIQUE_FILES+=("$file")
    fi
done

# Display grouped files
echo -e "\nIdentical files:"
for group in "${GROUPED_FILES[@]}"; do
    if [[ "$group" == *" "* ]]; then
        echo "$group are all the same file with different names."
    fi
done

# Display unique files
echo -e "\nUnique files:"
for file in "${UNIQUE_FILES[@]}"; do
    if [[ "$file" != *" "* ]]; then
        echo "$file is unique"
    fi
done