feat: Add charSet parameter to FILE macro (#144)

* feat: Add ability to set the character set for reading the file.

Defaults to the default charset for the running JVM

* Fix spotbugs

Author: slide

src/main/java/org/jenkinsci/plugins/tokenmacro/impl/WorkspaceFileMacro.java

@@ -31,12 +31,18 @@
 import hudson.model.TaskListener;
 
 import java.io.BufferedReader;
+import java.io.ByteArrayOutputStream;
 import java.io.IOException;
 import java.io.InputStreamReader;
+import java.io.OutputStreamWriter;
+import java.io.StringWriter;
 import java.nio.charset.Charset;
 import java.util.Collections;
 import java.util.List;
+import java.util.stream.Collectors;
 
+import org.apache.commons.io.IOUtils;
+import org.apache.commons.lang.ObjectUtils;
 import org.jenkinsci.plugins.tokenmacro.DataBoundTokenMacro;
 import org.jenkinsci.plugins.tokenmacro.MacroEvaluationException;
 
@@ -48,6 +54,8 @@ public class WorkspaceFileMacro extends DataBoundTokenMacro  {
     public String fileNotFoundMessage = "ERROR: File '%s' does not exist";
     @Parameter
     public int maxLines = -1;
+    @Parameter
+    public String charSet = Charset.defaultCharset().name();
 
 
     public static final String MACRO_NAME = "FILE";
@@ -83,28 +91,13 @@ public String evaluate(Run<?,?> run, FilePath workspace, TaskListener listener,
         }
 
         try {
-            if(maxLines > 0) {
-                int lines = 0;
-
-                StringBuilder result = new StringBuilder();
-                BufferedReader reader = null;
-                try {
-                    String line;
-                    reader = new BufferedReader(new InputStreamReader(workspace.child(path).read(), Charset.defaultCharset()));
-                    while (lines < maxLines && (line = reader.readLine()) != null) {
-                        result.append(line);
-                        result.append('\n');
-                        lines++;
-                    }
-                } finally {
-                    if(reader != null) {
-                        reader.close();
-                    }
+            Charset charset = Charset.forName(charSet);
+            try (BufferedReader reader = new BufferedReader(new InputStreamReader(workspace.child(path).read(), charset))) {
+                if (maxLines > 0) {
+                    return reader.lines().limit(maxLines).collect(Collectors.joining("\n"));
+                } else {
+                    return reader.lines().collect(Collectors.joining("\n"));
                 }
-
-                return result.toString();
-            } else {
-                return workspace.child(path).readToString();
             }
         } catch (IOException e) {
             return "ERROR: File '" + path + "' could not be read";

src/test/java/org/jenkinsci/plugins/tokenmacro/impl/WorkspaceFileMacroTest.java

@@ -8,17 +8,23 @@
 import hudson.model.FreeStyleProject;
 import hudson.model.TaskListener;
 import hudson.util.StreamTaskListener;
+import org.apache.commons.io.IOUtils;
 import org.jvnet.hudson.test.TestBuilder;
 
+import java.io.BufferedReader;
 import java.io.BufferedWriter;
 import java.io.IOException;
+import java.io.InputStreamReader;
 import java.io.OutputStreamWriter;
+import java.util.HashMap;
+import java.util.Map;
 
 import org.junit.Rule;
 import org.junit.Test;
 import org.jvnet.hudson.test.JenkinsRule;
 
 import static org.junit.Assert.*;
+import static org.mockito.Mockito.when;
 
 /**
  * @author Kohsuke Kawaguchi
@@ -77,4 +83,75 @@ public boolean perform(AbstractBuild<?, ?> build, Launcher launcher, BuildListen
             assertEquals("Hello, world! " + i, lines[i]);
         }
     }
+
+    @Test
+    public void testUtfEncodings() throws Exception {
+        String[] expected = { "première is first",
+                "première is slightly different",
+                "Кириллица is Cyrillic",
+                "\uD801\uDC00 am Deseret" };
+
+        String[] encodings = { "utf8", "utf16" };
+
+        for(String encoding : encodings) {
+            FreeStyleProject project = j.createFreeStyleProject();
+            TaskListener listener = StreamTaskListener.fromStdout();
+            project.getBuildersList().add(new TestBuilder() {
+                @Override
+                public boolean perform(AbstractBuild<?, ?> build, Launcher launcher, BuildListener listener) throws InterruptedException, IOException {
+                    FilePath file = build.getWorkspace().child(encoding + ".txt");
+                    try(BufferedWriter writer = new BufferedWriter(new OutputStreamWriter(file.write(), encoding))) {
+                        try(BufferedReader reader = new BufferedReader(new InputStreamReader(getClass().getResourceAsStream(encoding + ".txt"), encoding))) {
+                            IOUtils.copy(reader, writer);
+                        }
+                    }
+                    return true;
+                }
+            });
+            FreeStyleBuild build = project.scheduleBuild2(0).get();
+
+            WorkspaceFileMacro content = new WorkspaceFileMacro();
+            content.path = encoding + ".txt";
+            content.charSet = encoding;
+
+            String output = content.evaluate(build, listener, WorkspaceFileMacro.MACRO_NAME);
+            String[] lines = output.split("\n");
+            assertEquals(4, lines.length);
+
+            for (int i = 0; i < 4; i++) {
+                assertEquals(expected[i], lines[i]);
+            }
+        }
+    }
+
+    @Test
+    public void testSimpleChinese() throws Exception {
+        FreeStyleProject project = j.createFreeStyleProject();
+        TaskListener listener = StreamTaskListener.fromStdout();
+
+        String expected;
+        try(BufferedReader reader = new BufferedReader(new InputStreamReader(getClass().getResourceAsStream("Chinese-Simplified.txt"), "utf16"))) {
+            expected = IOUtils.toString(reader);
+        }
+        project.getBuildersList().add(new TestBuilder() {
+            @Override
+            public boolean perform(AbstractBuild<?, ?> build, Launcher launcher, BuildListener listener) throws InterruptedException, IOException {
+                FilePath file = build.getWorkspace().child("Chinese-Simplified.txt");
+                try(BufferedWriter writer = new BufferedWriter(new OutputStreamWriter(file.write(), "utf16"))) {
+                    try(BufferedReader reader = new BufferedReader(new InputStreamReader(getClass().getResourceAsStream("Chinese-Simplified.txt"), "utf16"))) {
+                        IOUtils.copy(reader, writer);
+                    }
+                }
+                return true;
+            }
+        });
+        FreeStyleBuild build = project.scheduleBuild2(0).get();
+
+        WorkspaceFileMacro content = new WorkspaceFileMacro();
+        content.path = "Chinese-Simplified.txt";
+        content.charSet = "utf16";
+
+        String output = content.evaluate(build, listener, WorkspaceFileMacro.MACRO_NAME);
+        assertEquals(expected, output);
+    }
 }

src/test/resources/org/jenkinsci/plugins/tokenmacro/impl/Chinese-Simplified.txt

@@ -0,0 +1,4 @@
+première is first
+première is slightly different
+Кириллица is Cyrillic
+𐐀 am Deseret