Skip to content

feat(dupe.sh) - revamp and add summary etc #31

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
bakerboy448 merged 3 commits into from
Apr 15, 2025
Merged

feat(dupe.sh) - revamp and add summary etc #31

Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
46698b3
feat(dupe.sh) - revamp and add summary etc
bakerboy448 Apr 15, 2025
d40facf
codespell
bakerboy448 Apr 15, 2025
ee1961e
fix runtime calc
bakerboy448 Apr 15, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
61 changes: 48 additions & 13 deletions dupe.sh
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -19,24 +19,59 @@ else
echo ".env file not found in script directory ($ENV_PATH)"
fi

# Variables
# Default Variables
JDUPES_OUTPUT_LOG=${JDUPES_OUTPUT_LOG:-"/mnt/data/jdupes.log"}
JDUPES_SOURCE_DIR=${JDUPES_SOURCE_DIR:-"/mnt/data/media/"}
JDUPES_DESTINATION_DIR=${JDUPES_DESTINATION_DIR:-"/mnt/data/torrents/"}
JDUPES_HASH_DB=${JDUPES_HASH_DB:-"/.config/jdupes_hashdb"}
## Secret Variables
JDUPES_COMMAND=${JDUPES_COMMAND:-"/usr/bin/jdupes"}
JDUPES_EXCLUDE_DIRS=${JDUPES_EXCLUDE_DIRS:-"-X nostr:.RecycleBin -X nostr:.trash"}
JDUPES_INCLUDE_EXT=${JDUPES_INCLUDE_EXT:-"mp4,mkv,avi"}
DEBUG=${DEBUG:-"false"}

# Logging the start of the operation
timestamp=$(date +"%Y-%m-%d %H:%M:%S")
echo "[$timestamp] Duplicate search started for $JDUPES_SOURCE_DIR and $JDUPES_DESTINATION_DIR." >>"$JDUPES_OUTPUT_LOG"
echo "command is"
# Running jdupes with the loaded environment variables
echo "$JDUPES_COMMAND" "$JDUPES_EXCLUDE_DIRS" -X onlyext:"$JDUPES_INCLUDE_EXT" -L -r -Z -y "$JDUPES_HASH_DB" "$JDUPES_SOURCE_DIR" "$JDUPES_DESTINATION_DIR"
"$JDUPES_COMMAND" "$JDUPES_EXCLUDE_DIRS" -X onlyext:"$JDUPES_INCLUDE_EXT" -L -r -Z -y "$JDUPES_HASH_DB" "$JDUPES_SOURCE_DIR" "$JDUPES_DESTINATION_DIR" >>"$JDUPES_OUTPUT_LOG"

# Logging the completion of the operation
timestamp=$(date +"%Y-%m-%d %H:%M:%S")
echo "[$timestamp] Duplicate search completed for $JDUPES_SOURCE_DIR and $JDUPES_DESTINATION_DIR." >>"$JDUPES_OUTPUT_LOG"
find_duplicates() {
local log_file="$JDUPES_OUTPUT_LOG"
local start_time=$(date +%s)
echo "[$(date +"%Y-%m-%d %H:%M:%S")] Duplicate search started" | tee -a "$log_file"

if [ "$DEBUG" == "true" ]; then
echo "Running jdupes with:" | tee -a "$log_file"
echo "$JDUPES_COMMAND $JDUPES_EXCLUDE_DIRS -X onlyext:$JDUPES_INCLUDE_EXT -r -M -y $JDUPES_HASH_DB $JDUPES_SOURCE_DIR $JDUPES_DESTINATION_DIR" | tee -a "$log_file"
fi

local results
results=$("$JDUPES_COMMAND" "$JDUPES_EXCLUDE_DIRS" -X onlyext:"$JDUPES_INCLUDE_EXT" -r -M -y "$JDUPES_HASH_DB" "$JDUPES_SOURCE_DIR" "$JDUPES_DESTINATION_DIR")

if [[ $results != *"No duplicates found."* ]]; then
"$JDUPES_COMMAND" "$JDUPES_EXCLUDE_DIRS" -X onlyext:"$JDUPES_INCLUDE_EXT" -r -L -y "$JDUPES_HASH_DB" "$JDUPES_SOURCE_DIR" "$JDUPES_DESTINATION_DIR" >>"$log_file"
fi

if [ "$DEBUG" == "true" ]; then
echo -e "jdupes output: ${results}" | tee -a "$log_file"
fi

parse_jdupes_output "$results" "$log_file"
local finish_time=$(date +%s)
local run_time=$((finish_time - start_time))
echo "[$(date +"%Y-%m-%d %H:%M:%S")] Duplicate search completed in ${run_time}s" | tee -a "$log_file"
}

parse_jdupes_output() {
local results="$1"
local log_file="$2"

if [[ $results != *"No duplicates found."* ]]; then
field_message="❌ Unlinked files discovered..."
parsed_log=$(echo "$results" | awk -F/ '{print $NF}' | sort -u)
else
field_message="✅ No unlinked files discovered..."
parsed_log="No hardlinks created"
fi

if [ "$DEBUG" == "true" ]; then
echo -e "$field_message" | tee -a "$log_file"
echo -e "Parsed log: ${parsed_log}" | tee -a "$log_file"
fi
}

find_duplicates
Loading