GCI99 AvoidCSVFormat Simplify regex pattern from \.(csv) to \.csv (remove unnecessary capture group) and add IT.

Co-authored-by: DataLabGroupe-CreditAgricole <[email protected]>

Author: cleophass

src/it/java/org/greencodeinitiative/creedengo/python/integration/tests/GCIRulesIT.java

@@ -17,15 +17,15 @@
  */
 package org.greencodeinitiative.creedengo.python.integration.tests;
 
-import org.junit.jupiter.api.Test;
-import org.sonarqube.ws.Issues;
-import org.sonarqube.ws.Measures;
+import static java.util.Optional.ofNullable;
+import static org.assertj.core.api.Assertions.assertThat;
 
 import java.util.List;
 import java.util.Map;
 
-import static java.util.Optional.ofNullable;
-import static org.assertj.core.api.Assertions.assertThat;
+import org.junit.jupiter.api.Test;
+import org.sonarqube.ws.Issues;
+import org.sonarqube.ws.Measures;
 
 class GCIRulesIT extends GCIRulesBase {
 
@@ -303,6 +303,21 @@ void testGCI97(){
         checkIssuesForFile(filePath, ruleId, ruleMsg, startLines, endLines, SEVERITY, TYPE, EFFORT_1MIN);
     }
 
+    @Test
+    void testGCI99(){
+        String filePath = "src/avoidCSVFormat.py";
+        String ruleId = "creedengo-python:GCI99";
+        String ruleMsg = "Use Parquet or Feather format instead of CSV";
+        int[] startLines = new int[]{
+            4, 6, 10, 12, 14, 15, 17, 18, 23, 39, 47, 48
+        };
+        int[] endLines = new int[]{
+            4, 6, 10, 12, 14, 15, 17, 18, 23, 39, 47, 48
+        };
+
+        checkIssuesForFile(filePath, ruleId, ruleMsg, startLines, endLines, SEVERITY, TYPE, EFFORT_50MIN);
+    }
+
     @Test
     void testGCI106() {
         String filePath = "src/avoidSqrtInLoop.py";
@@ -317,4 +332,6 @@ void testGCI106() {
         checkIssuesForFile(filePath, ruleId, ruleMsg, startLines, endLines, SEVERITY, TYPE, EFFORT_5MIN);
     }
 
+
+
 }

src/it/test-projects/creedengo-python-plugin-test-project/src/avoidCSVFormat.py

@@ -0,0 +1,51 @@
+import pandas as pd
+import pandas as pandas_alias
+
+df = pd.read_csv('data.csv') # Noncompliant {{Use Parquet or Feather format instead of CSV}}
+
+df.to_csv('output.csv') # Noncompliant {{Use Parquet or Feather format instead of CSV}}
+
+df = pd.read_parquet('data.parquet')
+
+path_to_file = 'MNIST.csv' # Noncompliant {{Use Parquet or Feather format instead of CSV}}
+
+df2 = pandas_alias.read_csv('another_data.csv') # Noncompliant {{Use Parquet or Feather format instead of CSV}}
+
+with open('data.csv') as f: # Noncompliant {{Use Parquet or Feather format instead of CSV}}
+    df3 = pd.read_csv(f) # Noncompliant {{Use Parquet or Feather format instead of CSV}}
+
+df4 = pd.read_csv( # Noncompliant {{Use Parquet or Feather format instead of CSV}}
+    'complex_data.csv', # Noncompliant {{Use Parquet or Feather format instead of CSV}}
+    sep=',',
+    header=0
+)
+
+df4.to_csv("output.csv") # Noncompliant {{Use Parquet or Feather format instead of CSV}}
+
+df5 = pd.DataFrame({'col1': [1, 2], 'col2': [3, 4]})
+
+other_path = 'data.json'
+
+df6 = pd.read_json(other_path)
+
+df7 = pd.read_feather('features.feather')
+
+df8 = pd.read_parquet("file.parquet")
+
+df9 = pandas_alias.read_feather("something.feather")
+
+df10 = pandas_alias.read_parquet("nested/dir/file.parquet")
+
+result = pd.read_csv("log.csv", encoding='utf-8') # Noncompliant {{Use Parquet or Feather format instead of CSV}}
+
+df11 = pd.DataFrame({'a': [1, 2], 'b': [3, 4]})
+df11.to_parquet("output.parquet")
+
+df12 = pd.DataFrame({'x': [5, 6]})
+df12.to_feather("output.feather")
+
+filename = "report.csv" # Noncompliant {{Use Parquet or Feather format instead of CSV}}
+data = pd.read_csv(filename) # Noncompliant {{Use Parquet or Feather format instead of CSV}}
+
+log_file = "logfile.log"
+df13 = pd.read_table(log_file, delimiter='|')

src/main/java/org/greencodeinitiative/creedengo/python/checks/AvoidCSVFormat.java

@@ -31,13 +31,12 @@
 import java.util.regex.Pattern;
 
 import org.sonar.plugins.python.api.PythonSubscriptionCheck;
-@Rule(key = "GCI99")
 
+@Rule(key = "GCI99")
 public class AvoidCSVFormat extends PythonSubscriptionCheck {
 
     public static final String DESCRIPTION = "Use Parquet or Feather format instead of CSV";
-    protected static final Pattern CSV_EXTENSION = Pattern.compile("\\.(csv)");
-    
+    protected static final Pattern CSV_EXTENSION = Pattern.compile("\\.csv");
     private final Set<Integer> reportedLines = new HashSet<>();
 
     @Override
@@ -48,18 +47,14 @@ public void initialize(Context context) {
 
     public void visitCallExpression(SubscriptionContext ctx) {
         CallExpression callExpression = (CallExpression) ctx.syntaxNode();
-
         Expression callee = callExpression.callee();
 
-        
-
         if (callee.is(Tree.Kind.QUALIFIED_EXPR)) {
             QualifiedExpression qualifiedExpression = (QualifiedExpression) callee;
             String methodName = qualifiedExpression.name().name();
-            
+
             if (methodName.equals("read_csv") || methodName.equals("to_csv")) {
                 int line = callExpression.firstToken().line();
-                
 
                 if (!reportedLines.contains(line)) {
                     reportedLines.add(line);
@@ -73,13 +68,12 @@ public void visitNodeString(SubscriptionContext ctx) {
         StringLiteral stringLiteral = (StringLiteral) ctx.syntaxNode();
         int line = stringLiteral.firstToken().line();
 
-
         if (reportedLines.contains(line)) {
             return;
         }
-        
         String strValue = stringLiteral.trimmedQuotesValue();
         Matcher matcher = CSV_EXTENSION.matcher(strValue);
+
         if (matcher.find()) {
             reportedLines.add(line);
             ctx.addIssue(stringLiteral, DESCRIPTION);

src/main/resources/org/greencodeinitiative/creedengo/python/creedengo_way_profile.json

@@ -12,6 +12,7 @@
 		"GCI89",
 		"GCI96",
 		"GCI97",
+		"GCI99",
 		"GCI106",
 		"GCI203",
 		"GCI404"