From e976b55a5c2a83f4f2ab1221ea228c9b8737db4f Mon Sep 17 00:00:00 2001 From: Simeon Wong Date: Thu, 14 Nov 2024 20:32:09 -0500 Subject: [PATCH 1/4] delete ip logs... WARNING UNTESTED! --- 02_activities/assignments/assignment.sh | 1 + 1 file changed, 1 insertion(+) diff --git a/02_activities/assignments/assignment.sh b/02_activities/assignments/assignment.sh index d81e9a77b..001291867 100644 --- a/02_activities/assignments/assignment.sh +++ b/02_activities/assignments/assignment.sh @@ -33,6 +33,7 @@ unzip rawdata.zip # 6. Repeat the above step for user logs and 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 +rf -rf ./data # 8. Create a file named ./data/inventory.txt that lists all the files in the subfolders of ./data/processed From ea20676d33161a6f4d0fcd3c4f7aa5360f0f4309 Mon Sep 17 00:00:00 2001 From: Simeon Wong Date: Thu, 14 Nov 2024 20:55:44 -0500 Subject: [PATCH 2/4] initialize README file with company name --- 02_activities/assignments/assignment.sh | 1 + 1 file changed, 1 insertion(+) diff --git a/02_activities/assignments/assignment.sh b/02_activities/assignments/assignment.sh index 001291867..f2bfd22bd 100644 --- a/02_activities/assignments/assignment.sh +++ b/02_activities/assignments/assignment.sh @@ -11,6 +11,7 @@ set -x mkdir analysis output touch README.md +echo "# Project Name: DSI Consulting Inc." > README.md touch analysis/main.py # download client data From 191c32095765dd4e4ed01719e7c71d775f7e287b Mon Sep 17 00:00:00 2001 From: tutoringjedi Date: Thu, 9 Apr 2026 22:34:17 -0400 Subject: [PATCH 3/4] Complete assignment.sh --- 02_activities/assignments/assignment.sh | 26 +++++++++++++++---------- 1 file changed, 16 insertions(+), 10 deletions(-) diff --git a/02_activities/assignments/assignment.sh b/02_activities/assignments/assignment.sh index 4b48cec8b..d2d5d5e3f 100644 --- a/02_activities/assignments/assignment.sh +++ b/02_activities/assignments/assignment.sh @@ -25,25 +25,31 @@ 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 +mkdir data -# 2. Move the ./rawdata directory to ./data/raw (eg. move it into ./data and rename it to raw) +# 2. Move the ./rawdata directory to ./data/raw +mv rawdata data/raw # 3. List the contents of the ./data/raw directory +ls data/raw -# 4. Create the directory ./data/processed, -# then create the following sub-directories within it: server_logs, user_logs, and 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 +# 4. Create the directory ./data/processed and sub-directories +mkdir -p data/processed/server_logs data/processed/user_logs data/processed/event_logs -# 6. Repeat the above step for user logs and event logs +# 5. Copy all server log files +cp data/raw/*server*.log data/processed/server_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 +# 6. Repeat for user and event logs +cp data/raw/*user*.log data/processed/user_logs +cp data/raw/*event*.log data/processed/event_logs -# 8. Create a file named ./data/inventory.txt that lists all the files in the subfolders of ./data/processed +# 7. Remove files with ipaddr in the name +rm data/raw/*ipaddr* +rm data/processed/user_logs/*ipaddr* +# 8. Create inventory.txt +find data/processed -type f > data/inventory.txt ########################################### From 4f59ca8dbeea97bb3f3568c69264263edd6de1b6 Mon Sep 17 00:00:00 2001 From: tutoringjedi Date: Fri, 10 Apr 2026 15:54:08 -0400 Subject: [PATCH 4/4] Suppress ipaddr error in user_logs --- 02_activities/assignments/assignment.sh | 13 ++----------- 1 file changed, 2 insertions(+), 11 deletions(-) diff --git a/02_activities/assignments/assignment.sh b/02_activities/assignments/assignment.sh index 32c7a3fce..16ea4c2f5 100644 --- a/02_activities/assignments/assignment.sh +++ b/02_activities/assignments/assignment.sh @@ -41,22 +41,13 @@ mkdir -p data/processed/server_logs data/processed/user_logs data/processed/even # 5. Copy all server log files cp data/raw/*server*.log data/processed/server_logs -<<<<<<< HEAD # 6. Repeat for user and event logs -cp data/raw/*user*.log data/processed/user_logs +cp data/raw/*user_log*.log data/processed/user_logs cp data/raw/*event*.log data/processed/event_logs -======= -# 6. Repeat the above step for user logs and 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 -rf -rf ./data - -# 8. Create a file named ./data/inventory.txt that lists all the files in the subfolders of ./data/processed ->>>>>>> ea20676d33161a6f4d0fcd3c4f7aa5360f0f4309 # 7. Remove files with ipaddr in the name rm data/raw/*ipaddr* -rm data/processed/user_logs/*ipaddr* +rm data/processed/user_logs/*ipaddr* 2>/dev/null || true # 8. Create inventory.txt find data/processed -type f > data/inventory.txt