Add exclude option to find_duplicate_pictures.sh

README.md

@@ -32,6 +32,9 @@ three independent checks:
 # Scan specific roots
 ./find_duplicate_pictures.sh /home/user/Pictures /mnt/backup
 
+# Scan a collection while skipping cache and export directories
+./find_duplicate_pictures.sh --exclude ~/Pictures/Cache --exclude ~/Pictures/Exports ~/Pictures
+
 # Scan the whole filesystem (default when no arguments given)
 ./find_duplicate_pictures.sh
 
@@ -50,6 +53,16 @@ chmod +x find_duplicate_pictures.sh
 | `FOLLOW_LINKS` | `0` (off) | Set to `1` to follow symlinks while scanning |
 | `REPORT` | *(none)* | Path to a file where the full report is also saved |
 
+### Directory exclusions
+
+Use `-x DIR` or `--exclude DIR` to skip a directory and all of its contents.
+The option may be repeated and accepts paths containing spaces. Relative paths
+are supported for both scan roots and exclusions.
+
+```bash
+./find_duplicate_pictures.sh -x ~/Pictures/Cache -x ~/Pictures/Exports ~/Pictures
+```
+
 ### Examples
 
 ```bash

find_duplicate_pictures.sh

@@ -14,18 +14,22 @@
 # pre-filter before hashing.
 #
 # Usage:
-#   ./find_duplicate_pictures.sh [DIR ...]
+#   ./find_duplicate_pictures.sh [--exclude DIR ...] [DIR ...]
 #   ./find_duplicate_pictures.sh            # defaults to "/" (whole system)
 #
 # Examples:
 #   ./find_duplicate_pictures.sh / /mnt/c /mnt/d
 #   ./find_duplicate_pictures.sh ~/Pictures
+#   ./find_duplicate_pictures.sh --exclude ~/Pictures/Cache ~/Pictures
 #
 # Options (environment variables):
 #   HASH_CMD=sha256sum   # override hash tool (sha256sum, shasum -a 256, md5sum)
 #   FOLLOW_LINKS=1       # follow symlinks while scanning (default: off)
 #   REPORT=report.txt    # also write the report to a file
 #
+# Options:
+#   -x, --exclude DIR    # skip DIR and everything below it (repeatable)
+#
 
 set -u
 
@@ -82,12 +86,46 @@ build_ext_expr() {
 # Arguments / scan roots
 # ---------------------------------------------------------------------------
 
-if [ "$#" -gt 0 ]; then
-    ROOTS=("$@")
-else
+ROOTS=()
+EXCLUDE_DIRS=()
+while [ "$#" -gt 0 ]; do
+    case "$1" in
+        -x|--exclude)
+            if [ "$#" -lt 2 ]; then
+                echo "ERROR: $1 requires a directory path." >&2
+                exit 1
+            fi
+            EXCLUDE_DIRS+=("$2")
+            shift 2
+            ;;
+        --)
+            shift
+            ROOTS+=("$@")
+            break
+            ;;
+        *)
+            ROOTS+=("$1")
+            shift
+            ;;
+    esac
+done
+
+if [ "${#ROOTS[@]}" -eq 0 ]; then
     ROOTS=("/")
 fi
 
+# Use absolute paths because find emits paths relative to the supplied root.
+for index in "${!ROOTS[@]}"; do
+    if [ -d "${ROOTS[$index]}" ]; then
+        ROOTS[$index]=$(cd "${ROOTS[$index]}" && pwd -P)
+    fi
+done
+for index in "${!EXCLUDE_DIRS[@]}"; do
+    if [ -d "${EXCLUDE_DIRS[$index]}" ]; then
+        EXCLUDE_DIRS[$index]=$(cd "${EXCLUDE_DIRS[$index]}" && pwd -P)
+    fi
+done
+
 FIND_LINK_FLAG=()
 if [ "${FOLLOW_LINKS:-0}" = "1" ]; then
     FIND_LINK_FLAG=(-L)
@@ -98,6 +136,9 @@ PRUNE_EXPR=()
 for d in $PRUNE_DIRS; do
     PRUNE_EXPR+=( -path "$d" -prune -o )
 done
+for d in "${EXCLUDE_DIRS[@]}"; do
+    PRUNE_EXPR+=( -path "$d" -prune -o )
+done
 
 # Extension expression
 mapfile -t EXT_EXPR < <(build_ext_expr)