From 39f02f99ff28c56726361f107e64d4eccaade8b8 Mon Sep 17 00:00:00 2001
From: Wirusik <wirus006@gmail.com>
Date: Fri, 6 May 2022 20:29:31 +0200
Subject: [PATCH] correction for create-dataset Jenkinsfile

---
 .gitignore  |  1 +
 Dockerfile  | 11 ++++++-----
 Jenkinsfile | 34 ++++++++++++----------------------
 init.py     |  6 ------
 4 files changed, 19 insertions(+), 33 deletions(-)

diff --git a/.gitignore b/.gitignore
index 735dca1..9c9209f 100644
--- a/.gitignore
+++ b/.gitignore
@@ -3,3 +3,4 @@ df_wta.csv
 atp-and-wta-tennis-data.zip
 data
 model.zip
+secret.txt
diff --git a/Dockerfile b/Dockerfile
index b44dc48..b7c6426 100644
--- a/Dockerfile
+++ b/Dockerfile
@@ -13,18 +13,19 @@ RUN pip3 install pandas
 RUN pip3 install pillow --global-option="build_ext" --global-option="--disable-zlib" --global-option="--disable-jpeg"
 RUN pip3 install scikit-learn
 RUN pip3 install matplotlib
-RUN mkdir ~/.kaggle/
-RUN echo '{"username":"wirus006","key":"c3323e37d3f91a0914d0172ef3c7c30c"}' > ~/.kaggle/kaggle.json
 
 # Create app directory in image
 WORKDIR /app
 
-# Copy init dataset script to /app directory in image
-COPY ./init.py ./
+COPY . .
+ARG KAGGLE_USERNAME
+ARG KAGGLE_KEY
 
 # Download kaggle dataset
 RUN kaggle datasets download -d hakeem/atp-and-wta-tennis-data
 RUN unzip -o atp-and-wta-tennis-data.zip
 
 # Script executed after docker run
-CMD python3 ./init.py
+RUN python3 ./init.py
+RUN chmod a+rwx -R *
+RUN ls -la
\ No newline at end of file
diff --git a/Jenkinsfile b/Jenkinsfile
index 6aae979..8689984 100644
--- a/Jenkinsfile
+++ b/Jenkinsfile
@@ -1,7 +1,4 @@
-pipeline {
-    agent {
-        dockerfile true 
-    }
+pipeline {    
     parameters {
         string (
             defaultValue: 'wirus006',
@@ -10,35 +7,28 @@ pipeline {
             trim: false
         )
         password (
-            defaultValue: 'c3323e37d3f91a0914d0172ef3c7c30c',
+            defaultValue: '',
             description: 'Kaggle token taken from kaggle.json file, as described in https://github.com/Kaggle/kaggle-api#api-credentials',
             name: 'KAGGLE_KEY'
         )
     }
+    agent {
+        dockerfile {
+            additionalBuildArgs "--build-arg KAGGLE_USERNAME=${params.KAGGLE_USERNAME} --build-arg KAGGLE_KEY=${params.KAGGLE_KEY} -t s444498-create-dataset"
+        }
+    }
     stages {
-        stage('Hello') {
-            steps {
-                echo 'Hello world!' 
-            }
-        }
-        stage('Checkout') {
-            steps {
-                git 'https://git.wmi.amu.edu.pl/s444498/ium_444498.git'
-            }
-        }
-        stage('Shell Script') {
+        stage('Archive dataset') {
             steps {
                 withEnv(["KAGGLE_USERNAME=${params.KAGGLE_USERNAME}",
                 "KAGGLE_KEY=${params.KAGGLE_KEY}"]) {
-                    sh "chmod +x -R ${env.WORKSPACE}"
                     sh 'echo hello world | figlet'
+                    sh 'chmod a+rwx -R *'
+                    sh 'pwd && ls'
+                    sh 'ls /app/data/'
+                    archiveArtifacts artifacts: '/app/data/*', onlyIfSuccessful: true
                 }
             }
         }
     }
-    post {
-        always {
-            archiveArtifacts artifacts: '*atp*.csv', onlyIfSuccessful: true
-        }
-    }
 }
diff --git a/init.py b/init.py
index 97a7019..3f1fe4b 100644
--- a/init.py
+++ b/init.py
@@ -8,12 +8,6 @@ from pathlib import Path
 
 # Inicjalizacja danych
 
-file_exists = exists('./df_atp.csv')
-
-if not file_exists:
-    subprocess.run(["kaggle", "datasets", "download", "-d", "hakeem/atp-and-wta-tennis-data"])
-    subprocess.run(["unzip", "-o", "atp-and-wta-tennis-data.zip"])
-
 atp_data = pd.read_csv('df_atp.csv')
 print(atp_data)