diff --git a/.gitignore b/.gitignore index e47805256..5cd8c3040 100644 --- a/.gitignore +++ b/.gitignore @@ -26,4 +26,4 @@ __pycache__/ .mypy_cache/ .ruff_cache/ -newproject/ + diff --git a/02_activities/assignments/assignment_script.sh b/02_activities/assignments/assignment_script.sh index 4b48cec8b..3cce93719 100644 --- a/02_activities/assignments/assignment_script.sh +++ b/02_activities/assignments/assignment_script.sh @@ -18,6 +18,7 @@ cd newproject mkdir analysis output touch README.md +echo "# Project Name: DSI Consulting Inc." > README.md touch analysis/main.py # download client data @@ -25,26 +26,32 @@ curl -Lo rawdata.zip https://github.com/UofT-DSI/shell/raw/refs/heads/main/02_ac unzip -q rawdata.zip ########################################### -# Complete assignment here -# 1. Create a directory named data -# 2. Move the ./rawdata directory to ./data/raw (eg. move it into ./data and rename it to raw) +# Complete assignment here +mkdir data +# 2. Move the ./rawdata directory to ./data/raw (eg. move it into ./data and rename it to raw) +mv rawdata data/raw # 3. List the contents of the ./data/raw directory +ls -la data/raw # 4. Create the directory ./data/processed, # then create the following sub-directories within it: server_logs, user_logs, and event_logs +mkdir -p data/processed/server_logs data/processed/user_logs data/processed/event_logs # 5. Copy all server log files (files with "server" in the name AND a .log extension) from ./data/raw to ./data/processed/server_logs - +cp data/raw/*server*.log data/processed/server_logs/ # 6. Repeat the above step for user logs and event logs - +cp data/raw/*user*.log data/processed/user_logs/ +cp data/raw/*event*.log data/processed/event_logs/ # 7. For user privacy, remove all files containing IP addresses (files with "ipaddr" in the filename) from ./data/raw and ./data/processed/user_logs +rm -f data/raw/*ipaddr*.* +rm -f data/processed/user_logs/*ipaddr*.* # 8. Create a file named ./data/inventory.txt that lists all the files in the subfolders of ./data/processed - +find ./data/processed -type f > data/inventory.txt ########################################### - echo "Project setup is complete!" +echo "Its done!" \ No newline at end of file