SONARPLUGINS-2560 Set encoding properly when reading content from Sonar server

diff --git a/src/main/java/org/sonar/runner/Bootstrapper.java b/src/main/java/org/sonar/runner/Bootstrapper.java
index 47c745237f5e29d078189f2f9c62df6e8a125ab8..00d3d8ca0e1430147d0bb8693472ebf17bff3107 100644 (file)
--- a/src/main/java/org/sonar/runner/Bootstrapper.java
+++ b/src/main/java/org/sonar/runner/Bootstrapper.java
@@ -19,7 +19,12 @@
  */
 package org.sonar.runner;
 
-import java.io.*;
+import java.io.File;
+import java.io.FileOutputStream;
+import java.io.IOException;
+import java.io.InputStream;
+import java.io.InputStreamReader;
+import java.io.Reader;
 import java.net.HttpURLConnection;
 import java.net.MalformedURLException;
 import java.net.URL;
@@ -122,7 +127,11 @@ class Bootstrapper {
   String remoteContent(String path) throws IOException {
     String fullUrl = serverUrl + path;
     HttpURLConnection conn = newHttpConnection(new URL(fullUrl));
-    Reader reader = new InputStreamReader((InputStream) conn.getContent());
+    String charset = IOUtils.getCharsetFromContentType(conn.getContentType());
+    if (charset == null || "".equals(charset)) {
+      charset = "UTF-8";
+    }
+    Reader reader = new InputStreamReader((InputStream) conn.getContent(), charset);
     try {
       int statusCode = conn.getResponseCode();
       if (statusCode != HttpURLConnection.HTTP_OK) {

diff --git a/src/main/java/org/sonar/runner/IOUtils.java b/src/main/java/org/sonar/runner/IOUtils.java
index 90448efe5a3a4827df40fff073fb603cf35efca2..9109f3f33743f11cb200d8734c0bf59567a04e9b 100644 (file)
--- a/src/main/java/org/sonar/runner/IOUtils.java
+++ b/src/main/java/org/sonar/runner/IOUtils.java
@@ -19,7 +19,16 @@
  */
 package org.sonar.runner;
 
-import java.io.*;
+import java.io.Closeable;
+import java.io.File;
+import java.io.IOException;
+import java.io.InputStream;
+import java.io.OutputStream;
+import java.io.Reader;
+import java.io.StringWriter;
+import java.io.Writer;
+import java.util.regex.Matcher;
+import java.util.regex.Pattern;
 
 /**
  * Internal class used only by the Runner as we don't want it to depend on third-party libs.
@@ -36,6 +45,8 @@ final class IOUtils {
    */
   private static final int DEFAULT_BUFFER_SIZE = 1024 * 4;
 
+  private static final Pattern CHARSET_PATTERN = Pattern.compile("(?i)\\bcharset=\\s*\"?([^\\s;\"]*)");
+
   /**
    * Unconditionally close a <code>Closeable</code>.
    */
@@ -99,4 +110,22 @@ final class IOUtils {
     }
   }
 
+  /**
+   * Parse out a charset from a content type header.
+   *
+   * @param contentType e.g. "text/html; charset=EUC-JP"
+   * @return "EUC-JP", or null if not found. Charset is trimmed and uppercased.
+   */
+  static String getCharsetFromContentType(String contentType) {
+    if (contentType == null) {
+      return null;
+    }
+
+    Matcher m = CHARSET_PATTERN.matcher(contentType);
+    if (m.find()) {
+      return m.group(1).trim().toUpperCase();
+    }
+    return null;
+  }
+
 }