added 1080p 2160p filter and removal

compare

@@ -9,8 +9,10 @@
 #      the directory is removed outright.
 #   3. The remaining directories are “cleaned” (converted to lowercase, punctuation removed)
 #      and then grouped by fuzzy similarity using a configurable threshold.
-#   4. If duplicate groups remain, you are prompted to choose which duplicate to remove.
+#   4. Within each group, if at least one directory contains "2160p" and one contains "1080p",
-#   5. A dry-run mode (--dry-run) is available to show what would be removed without deleting.
+#      the 1080p directory(ies) are removed (or flagged in dry-run mode).
+#   5. For any remaining duplicate groups, the user is prompted to select a directory to remove.
+#   6. A --dry-run mode is available to preview removals without actually deleting any directories.
 
 set -euo pipefail
 
@@ -59,14 +61,14 @@ if [ ! -f "$WORDS_FILE" ]; then
     exit 1
 fi
 
-# Read undesirable words (one per line) into an array (ignoring blank lines)
+# Read undesirable words (one per line) into an array, ignoring blank lines.
 mapfile -t words < <(grep -v '^[[:space:]]*$' "$WORDS_FILE")
 
 echo "=== Pre-filtering Directories by Undesirable Words ==="
 # Create an array to hold directories that do NOT match any undesirable word.
 filtered_dirs=()
 
-# Loop over immediate subdirectories in both directories.
+# Loop over immediate subdirectories in both DIR1 and DIR2.
 for d in "$DIR1"/* "$DIR2"/*; do
     if [ -d "$d" ]; then
         base=$(basename "$d")
@@ -96,12 +98,10 @@ done
 clean_name() {
     local name="$1"
     # Normalize: convert to lowercase, remove punctuation, and trim extra whitespace.
-    local normalized
+    echo "$name" | tr '[:upper:]' '[:lower:]' | sed 's/[^a-z0-9 ]//g' | xargs
-    normalized=$(echo "$name" | tr '[:upper:]' '[:lower:]' | sed 's/[^a-z0-9 ]//g' | xargs)
-    echo "$normalized"
 }
 
-# Function: Compute fuzzy similarity between two strings using Python's difflib.
+# Function: Compute fuzzy similarity between two names using Python's difflib.
 compute_similarity() {
     local name1="$1"
     local name2="$2"
@@ -136,8 +136,45 @@ for d in "${filtered_dirs[@]}"; do
     fi
 done
 
+echo "=== Resolution Preference Filtering ==="
+# For each group, if one directory contains "2160p" and another contains "1080p",
+# remove the 1080p directory(ies).
+for key in "${!groups[@]}"; do
+    IFS=$'\n' read -r -a paths <<< "${groups[$key]}" || true
+    has_2160p=false
+    has_1080p=false
+    for path in "${paths[@]}"; do
+        base=$(basename "$path")
+        if echo "$base" | grep -qi "2160p"; then
+            has_2160p=true
+        fi
+        if echo "$base" | grep -qi "1080p"; then
+            has_1080p=true
+        fi
+    done
+    if $has_2160p && $has_1080p; then
+        echo "Group (representative cleaned name: ${group_rep[$key]:-unknown}) has both 1080p and 2160p directories."
+        new_group=()
+        for path in "${paths[@]}"; do
+            base=$(basename "$path")
+            if echo "$base" | grep -qi "1080p"; then
+                echo "Removing '$path' because a 2160p version is present."
+                if $DRY_RUN; then
+                    echo "Dry-run: would remove '$path'"
+                else
+                    rm -rf "$path"
+                    echo "Removed '$path'"
+                fi
+            else
+                new_group+=("$path")
+            fi
+        done
+        groups["$key"]=$(printf "%s\n" "${new_group[@]}")
+    fi
+done
+
 echo "=== Interactive Duplicate Resolution ==="
-# For each group that has more than one directory, prompt the user to select one to remove.
+# For each group that still contains more than one directory, prompt the user to select one to remove.
 for key in "${!groups[@]}"; do
     IFS=$'\n' read -r -a paths <<< "${groups[$key]}" || true
     # Filter out directories that no longer exist.
@@ -148,7 +185,7 @@ for key in "${!groups[@]}"; do
         fi
     done
     if [ "${#existing[@]}" -gt 1 ]; then
-        echo "Duplicate group (cleaned representative: ${group_rep[$key]:-unknown}):"
+        echo "Duplicate group (representative cleaned name: ${group_rep[$key]:-unknown}):"
         i=1
         for p in "${existing[@]}"; do
             echo "  [$i] $p"
@@ -171,4 +208,3 @@ for key in "${!groups[@]}"; do
 done
 
 echo "Script completed."
-