Fix for issue #48

mojohaus · Mar 15, 2020 · 52017dd · 52017dd
1 parent dea12f4
commit 52017dd
Show file tree

Hide file tree

Showing 7 changed files with 599 additions and 29 deletions.
diff --git a/pom.xml b/pom.xml
@@ -138,12 +138,6 @@
       <artifactId>maven-common-artifact-filters</artifactId>
       <version>3.0.1</version>
     </dependency>
-    <dependency>
-    	<groupId>com.ibm.icu</groupId>
-    	<artifactId>icu4j</artifactId>
-    	<version>56.1</version>
-    </dependency>
-
   </dependencies>
 
   <build>

diff --git a/src/it/require-encoding-iso88591/pom.xml b/src/it/require-encoding-iso88591/pom.xml
@@ -26,6 +26,7 @@
 							<encoding>ISO-8859-1</encoding>
 							<includes>src/main/resources/ascii.txt,src/main/resources/iso88591.txt</includes>
 							<excludes>pom.xml</excludes>
+							<acceptAsciiSubset>true</acceptAsciiSubset>
 						</requireEncoding>
 					</rules>
 				</configuration>

diff --git a/src/it/require-encoding-iso88591/verify.groovy b/src/it/require-encoding-iso88591/verify.groovy
@@ -6,7 +6,7 @@ String text = file.getText("utf-8");
 assert !text.contains( "Encoding US-ASCII is hard to detect." )
 assert !text.contains( "Files not encoded in US-ASCII:" )
 assert !text.contains( "src/main/resources/utf8.txt==>".replace('/', File.separator) )
-assert text.contains( "src/main/resources/ascii.txt==>ISO-8859-1".replace('/', File.separator) )
+assert text.contains( "src/main/resources/ascii.txt==>US-ASCII".replace('/', File.separator) )
 assert text.contains( "src/main/resources/iso88591.txt==>ISO-8859-1".replace('/', File.separator) )
 
 return true;
diff --git a/src/it/require-encoding-usascii/verify.groovy b/src/it/require-encoding-usascii/verify.groovy
@@ -6,7 +6,7 @@ String text = file.getText("utf-8");
 assert text.contains( "Encoding US-ASCII is hard to detect." )
 assert text.contains( "Files not encoded in US-ASCII:" )
 assert text.contains( "src/main/resources/utf8.txt==>UTF-8".replace('/', File.separator) )
-assert text.contains( "src/main/resources/ascii.txt==>ISO-8859-1".replace('/', File.separator) )
+assert text.contains( "src/main/resources/ascii.txt==>US-ASCII".replace('/', File.separator) )
 assert text.contains( "src/main/resources/iso88591.txt==>ISO-8859-1".replace('/', File.separator) )
 
 return true;
diff --git a/src/main/java/org/apache/maven/plugins/enforcer/RequireEncoding.java b/src/main/java/org/apache/maven/plugins/enforcer/RequireEncoding.java
@@ -4,7 +4,12 @@
 import java.io.File;
 import java.io.FileInputStream;
 import java.io.IOException;
+import java.io.InputStreamReader;
 import java.nio.charset.StandardCharsets;
+import java.nio.file.Files;
+import java.util.Arrays;
+import java.util.HashSet;
+import java.util.Set;
 
 import org.apache.maven.enforcer.rule.api.EnforcerRule;
 import org.apache.maven.enforcer.rule.api.EnforcerRuleException;
@@ -14,9 +19,7 @@
 import org.codehaus.plexus.util.DirectoryScanner;
 import org.codehaus.plexus.util.IOUtil;
 import org.codehaus.plexus.util.StringUtils;
-
-import com.ibm.icu.text.CharsetDetector;
-import com.ibm.icu.text.CharsetMatch;
+import org.freebsd.file.FileEncoding;
 
 /**
  * Checks file encodings to see if they match the project.build.sourceEncoding If file encoding can not be determined it
@@ -53,6 +56,11 @@ public class RequireEncoding
      */
     private boolean failFast = true;
 
+    /**
+     * Should the rule accept US-ASCII as an subset of UTF-8 and ISO-8859-1.
+     */
+    private boolean acceptAsciiSubset = false;
+
     public void execute( EnforcerRuleHelper helper )
         throws EnforcerRuleException
     {
@@ -63,10 +71,18 @@ public void execute( EnforcerRuleHelper helper )
                 encoding = (String) helper.evaluate( "${project.build.sourceEncoding}" );
             }
             Log log = helper.getLog();
+
+            Set< String > acceptedEncodings = new HashSet< String >( Arrays.asList( encoding ) );
             if ( encoding.equals( StandardCharsets.US_ASCII.name() ) )
             {
                 log.warn( "Encoding US-ASCII is hard to detect. Use UTF-8 or ISO-8859-1" );
             }
+
+            if ( acceptAsciiSubset && ( encoding.equals( StandardCharsets.ISO_8859_1.name() ) || encoding.equals( StandardCharsets.UTF_8.name() ) ) )
+            {
+                acceptedEncodings.add( StandardCharsets.US_ASCII.name() );
+            }
+
             String basedir = (String) helper.evaluate( "${basedir}" );
             DirectoryScanner ds = new DirectoryScanner();
             ds.setBasedir( basedir );
@@ -91,7 +107,7 @@ public void execute( EnforcerRuleHelper helper )
                 {
                     log.debug( file + "==>" + fileEncoding );
                 }
-                if ( fileEncoding != null && !fileEncoding.equals( encoding ) )
+                if ( fileEncoding != null && !acceptedEncodings.contains( fileEncoding ) )
                 {
                     filesInMsg.append( file );
                     filesInMsg.append( "==>" );
@@ -121,27 +137,18 @@ public void execute( EnforcerRuleHelper helper )
     protected String getEncoding( String requiredEncoding, File file, Log log )
         throws IOException
     {
-        FileInputStream fis = null;
-        try
+        FileEncoding fileEncoding = new FileEncoding();
+        if ( !fileEncoding.guessFileEncoding( Files.readAllBytes( file.toPath() ) ) )
         {
-            fis = new FileInputStream( file );
-            CharsetDetector detector = new CharsetDetector();
-            detector.setDeclaredEncoding( requiredEncoding );
-            detector.setText( new BufferedInputStream( fis ) );
-            CharsetMatch[] charsets = detector.detectAll();
-            if ( charsets == null )
-            {
-                return null;
-            }
-            else
-            {
-                return charsets[0].getName();
-            }
+            return null;
         }
-        finally
+
+        if ( log.isDebugEnabled() )
         {
-            IOUtil.close( fis );
+            log.debug( String.format( "%s: (%s) %s; charset=%s", file, fileEncoding.getCode(), fileEncoding.getType(), fileEncoding.getCodeMime() ) );
         }
+
+        return fileEncoding.getCodeMime().toUpperCase();
     }
 
     /**