Merge pull request #90 from LibraryOfCongress/Internationalize

Internationalize messages

README.md

@@ -50,6 +50,11 @@ this functionality, the
 demonstrates how you can implement this feature with your additional application
 and workflow requirements.
 
+##### Internationalization
+All logging and error messages have been put into a [ResourceBundle](https://docs.oracle.com/javase/7/docs/api/java/util/ResourceBundle.html). 
+This allows for all the messages to be translated to multiple languages and automatically used during runtime. 
+If you would like to contribute to translations please visit https://www.transifex.com/acdha/bagit-java/dashboard/
+
 ##### New Interfaces
 
 The 5.x version is a complete rewrite of the bagit-java library which attempts
@@ -170,3 +175,4 @@ Simply run `gradle eclipse` and it will automatically create a eclipse project f
 ### Roadmap for this library
 * Further refine reading and writing of bags version 0.93-0.97
 * Fix bugs/issues reported with new library (on going)
+* Translate to various languages (on going)

code-quality.gradle

@@ -79,10 +79,10 @@ jacocoTestReport {
 
 cpdCheck {
     source = sourceSets.main.allJava
-//    reports {
-//        text.enabled = true
-//        xml.enabled = false
-//    }
+    reports {
+        text.enabled = true
+        xml.enabled = false
+    }
 }
 
 dependencyCheck {
@@ -97,4 +97,58 @@ dependencyCheck {
 //      xml.enabled = false
 //      html.enabled = true
 //  }
-//}
+//}
+
+import java.util.Map.Entry;
+task checkMessageBundle(){
+  inputs.files(fileTree(dir: "src/main/resources", include: "**/MessageBundle*.properties"))
+  outputs.dir("$buildDir/checkMessageBundle") //hack: define a output dir so gradle will check if up-to-date
+
+  doLast{
+    Set<String> messageKeys = new HashSet<>()
+
+    inputs.getFiles().each{File file -> 
+      file.eachLine {String line -> 
+        if(line && !line.trim().startsWith('#')){
+          String[] keyValue = checkMessageBundleLineIsCorrectlyFormatted(line, file)
+
+          if(messageKeys.contains(keyValue[0])){
+            throw new GradleException("Internationalization message bundle contains duplicate key [${keyValue[0]}]!")
+          }
+          messageKeys.add(keyValue[0])
+        }
+      }
+    }
+
+    checkAllMessageKeysAreUsed(messageKeys)
+  }
+}
+check.dependsOn checkMessageBundle
+
+String[] checkMessageBundleLineIsCorrectlyFormatted(String line, File file){
+  String[] keyValue = line.split("=", 2)
+
+  if(keyValue.size() != 2 || keyValue[1].isEmpty()){
+    throw new GradleException("Line [${line}] in file [${file}] is not a valid entry for the internationalization message bundle!")
+  }
+
+  return keyValue
+}
+
+void checkAllMessageKeysAreUsed(Set<String> messageKeys){
+  sourceSets.main.allJava.each { File file ->
+    file.eachLine{ String line ->
+      for(String key : messageKeys.clone()){
+        if(line.contains(key)){
+          messageKeys.remove(key)
+        }
+      }
+    }
+  }
+
+  if(messageKeys.size() > 0){
+    messageKeys.each{String key ->
+      throw new GradleException("[${key}] is listed in the internationalization message bundle but never actually used!")
+    }  
+  }
+}

src/main/java/gov/loc/repository/bagit/conformance/BagLinter.java

@@ -11,6 +11,7 @@
 import java.util.Collections;
 import java.util.HashSet;
 import java.util.List;
+import java.util.ResourceBundle;
 import java.util.Set;
 
 import org.slf4j.Logger;
@@ -40,6 +41,7 @@
  */
 public final class BagLinter {
   private static final Logger logger = LoggerFactory.getLogger(BagLinter.class);
+  private static final ResourceBundle messages = ResourceBundle.getBundle("MessageBundle");
   private static final Version VERSION_1_0 = new Version(1,0);
 
   private BagLinter(){
@@ -117,38 +119,36 @@ public static Set<BagitWarning> lintBag(final Path rootDir, final Collection<Bag
     checkForExtraLines(bagitFile, warnings, warningsToIgnore);
     final SimpleImmutableEntry<Version, Charset> bagitInfo = BagitTextFileReader.readBagitTextFile(bagitFile);
 
-    logger.debug("Checking encoding problems.");
+    logger.info(messages.getString("checking_encoding_problems"));
     EncodingChecker.checkEncoding(bagitInfo.getValue(), warnings, warningsToIgnore);
 
-    logger.debug("checking for latest version.");
+    logger.info(messages.getString("checking_latest_version"));
     VersionChecker.checkVersion(bagitInfo.getKey(), warnings, warningsToIgnore);
 
-    logger.debug("checking manifests for problems.");
+    logger.info(messages.getString("checking_manifest_problems"));
     ManifestChecker.checkManifests(bagitDir, bagitInfo.getValue(), warnings, warningsToIgnore);
 
-    logger.debug("checking bag metadata for problems.");
+    logger.info(messages.getString("checking_metadata_problems"));
     MetadataChecker.checkBagMetadata(bagitDir, bagitInfo.getValue(), warnings, warningsToIgnore);
 
     return warnings;
   }
 
   private static void checkForExtraLines(final Path bagitFile, final Collection<BagitWarning> warnings, final Collection<BagitWarning> warningsToIgnore) throws InvalidBagMetadataException, IOException, UnparsableVersionException{
     if(warningsToIgnore.contains(BagitWarning.EXTRA_LINES_IN_BAGIT_FILES)){
-      logger.debug("skipping check for extra lines in bagit files");
+      logger.debug(messages.getString("skipping_check_extra_lines"));
       return;
     }
 
-    logger.debug("checking if [{}] contains more than 2 lines");
+    logger.debug(messages.getString("checking_extra_lines"));
     final List<SimpleImmutableEntry<String, String>> pairs = KeyValueReader.readKeyValuesFromFile(bagitFile, ":", StandardCharsets.UTF_8);
 
     for(final SimpleImmutableEntry<String, String> pair : pairs){
       if("BagIt-Version".equals(pair.getKey())){
         final Version version = BagitTextFileReader.parseVersion(pair.getValue());
         //versions before 1.0 specified it must be exactly 2 lines
         if(pairs.size() > 2 && version.isOlder(VERSION_1_0)){
-          logger.warn("The bagit specification states that the bagit.txt file must contain exactly 2 lines. "
-              + "However we found {} lines, some implementations will "
-              + "ignore this but may cause imcompatibility issues with other tools.", pairs.size());
+          logger.warn(messages.getString("extra_lines_warning"), pairs.size());
           warnings.add(BagitWarning.EXTRA_LINES_IN_BAGIT_FILES);
         }
       }

src/main/java/gov/loc/repository/bagit/conformance/BagProfileChecker.java

@@ -8,10 +8,12 @@
 import java.util.List;
 import java.util.Map;
 import java.util.Map.Entry;
+import java.util.ResourceBundle;
 import java.util.Set;
 
 import org.slf4j.Logger;
 import org.slf4j.LoggerFactory;
+import org.slf4j.helpers.MessageFormatter;
 
 import com.fasterxml.jackson.core.JsonParseException;
 import com.fasterxml.jackson.databind.JsonMappingException;
@@ -37,6 +39,7 @@
  */
 public final class BagProfileChecker {
   private static final Logger logger = LoggerFactory.getLogger(BagProfileChecker.class);
+  private static final ResourceBundle messages = ResourceBundle.getBundle("MessageBundle");
 
   private BagProfileChecker(){
     //intentionally left empty
@@ -75,8 +78,7 @@ public static void bagConformsToProfile(final InputStream jsonProfile, final Bag
     requiredManifestsExist(bag.getTagManifests(), profile.getTagManifestTypesRequired(), false);
 
     if(!profile.getAcceptableBagitVersions().contains(bag.getVersion().toString())){
-      throw new BagitVersionIsNotAcceptableException("Version [" + bag.getVersion().toString() + "] is not in the acceptable list of " + 
-          profile.getAcceptableBagitVersions());
+      throw new BagitVersionIsNotAcceptableException(messages.getString("bagit_version_not_acceptable_error"), bag.getVersion(), profile.getAcceptableBagitVersions());
     }
 
     requiredTagFilesExist(bag.getRootDir(), profile.getTagFilesRequired());
@@ -92,9 +94,9 @@ private static BagitProfile parseBagitProfile(final InputStream jsonProfile) thr
   }
 
   private static void checkFetch(final Path rootDir, final boolean allowFetchFile, final List<FetchItem> itemsToFetch) throws FetchFileNotAllowedException{
-    logger.debug("Checking if the fetch file is allowed for bag [{}]", rootDir);
+    logger.debug(messages.getString("checking_fetch_file_allowed"), rootDir);
     if(!allowFetchFile && !itemsToFetch.isEmpty()){
-      throw new FetchFileNotAllowedException("Fetch File was found in bag [" + rootDir + "]");
+      throw new FetchFileNotAllowedException(messages.getString("fetch_file_not_allowed_error"), rootDir);
     }
   }
 
@@ -104,19 +106,19 @@ private static void checkMetadata(final Metadata bagMetadata, final Map<String,
     for(final Entry<String, BagInfoRequirement> bagInfoEntryRequirement : bagInfoEntryRequirements.entrySet()){
       final boolean metadataContainsKey = bagMetadata.contains(bagInfoEntryRequirement.getKey());
 
-      logger.debug("Checking if [{}] is required in the bag metadata", bagInfoEntryRequirement.getKey());
+      logger.debug(messages.getString("checking_metadata_entry_required"), bagInfoEntryRequirement.getKey());
       //is it required and not there?
       if(bagInfoEntryRequirement.getValue().isRequired() && !metadataContainsKey){
-        throw new RequiredMetadataFieldNotPresentException("Profile specifies metadata field [" + bagInfoEntryRequirement.getKey() + "] is required but was not found!");
+        throw new RequiredMetadataFieldNotPresentException(messages.getString("required_metadata_field_not_present_error"), bagInfoEntryRequirement.getKey());
       }
 
       //a size of zero implies that all values are acceptable
       if(!bagInfoEntryRequirement.getValue().getAcceptableValues().isEmpty()){
-        logger.debug("Checking if all the values listed for [{}] are acceptable", bagInfoEntryRequirement.getKey());
+        logger.debug(messages.getString("check_values_acceptable"), bagInfoEntryRequirement.getKey());
         for(final String metadataValue : bagMetadata.get(bagInfoEntryRequirement.getKey())){
           if(!bagInfoEntryRequirement.getValue().getAcceptableValues().contains(metadataValue)){
-            throw new MetatdataValueIsNotAcceptableException("Profile specifies that acceptable values for [" + bagInfoEntryRequirement.getKey() + 
-                "] are " + bagInfoEntryRequirement.getValue().getAcceptableValues() + " but found [" + metadataValue + "]");
+            throw new MetatdataValueIsNotAcceptableException(messages.getString("metadata_value_not_acceptable_error"), 
+                bagInfoEntryRequirement.getKey(), bagInfoEntryRequirement.getValue().getAcceptableValues(), metadataValue);
           }
         }
       }
@@ -126,18 +128,21 @@ private static void checkMetadata(final Metadata bagMetadata, final Map<String,
   @SuppressWarnings("PMD.AvoidInstantiatingObjectsInLoops")
   private static void requiredManifestsExist(final Set<Manifest> manifests, final List<String> requiredManifestTypes, final boolean isPayloadManifest) throws RequiredManifestNotPresentException{
     final Set<String> manifestTypesPresent = new HashSet<>();
-    logger.debug("Checking if all the required manifests are present");
+    logger.debug(messages.getString("check_required_manifests_present"));
 
     for(final Manifest manifest : manifests){
       manifestTypesPresent.add(manifest.getAlgorithm().getBagitName());
     }
 
     for(final String requiredManifestType : requiredManifestTypes){
       if(!manifestTypesPresent.contains(requiredManifestType)){
-        final StringBuilder sb = new StringBuilder(25);
-        sb.append("Required ");
-        if(isPayloadManifest){ sb.append("tag");}
-        sb.append("manifest type [").append(requiredManifestType).append("] was not present");
+        final StringBuilder sb = new StringBuilder();
+        if(isPayloadManifest){ sb.append("tag");
+          sb.append(MessageFormatter.format(messages.getString("required_tag_manifest_type_not_present"), requiredManifestType).getMessage());
+        }
+        else{
+          sb.append(MessageFormatter.format(messages.getString("required_manifest_type_not_present"), requiredManifestType).getMessage());
+        }
 
         throw new RequiredManifestNotPresentException(sb.toString());
       }
@@ -146,12 +151,12 @@ private static void requiredManifestsExist(final Set<Manifest> manifests, final
 
   private static void requiredTagFilesExist(final Path rootDir, final List<String> requiredTagFilePaths) throws RequiredTagFileNotPresentException{
     Path requiredTagFile;
-    logger.debug("Checking if all the required tag files exist");
+    logger.debug(messages.getString("checking_required_tag_file_exists"));
 
     for(final String requiredTagFilePath : requiredTagFilePaths){
       requiredTagFile = rootDir.resolve(requiredTagFilePath);
       if(!Files.exists(requiredTagFile)){
-        throw new RequiredTagFileNotPresentException("Required tag file [" + requiredTagFilePath + "] was not found");
+        throw new RequiredTagFileNotPresentException(messages.getString("required_tag_file_not_found_error"), requiredTagFilePath);
       }
     }
   }

src/main/java/gov/loc/repository/bagit/conformance/BagitWarning.java

@@ -1,42 +1,35 @@
 package gov.loc.repository.bagit.conformance;
 
+import java.util.ResourceBundle;
+
 /**
  * The BagIt specification is very flexible in what it allows. 
  * This leads to situations where something may be technically allowed, but should be discouraged. 
  * This class is for that purpose, to allow reporting of these allowed but discouraged situations to the user.
  */
 public enum BagitWarning {
-  BAG_WITHIN_A_BAG("A data directory can contain anything,"
-      + " including another bag. However it would be better to merge the bags together."),
-  DIFFERENT_CASE("The bag contains two files that differ only in case. "
-      + "This can cause problems on a filesystem like the one used by apple (HFS)."),
-  DIFFERENT_NORMALIZATION("The bag contains two files that differ only in the normalization. "
-      + "This can cause verification to fail on some systems, and general user confusion."),
-  EXTRA_LINES_IN_BAGIT_FILES("The bagit specification says it must only contain 2 lines. "
-      + "However, some implementations have decided to ignore this which may cause compatibility issues"),
-  LEADING_DOT_SLASH("A manifest lists all data files as relative to the bag root directory,"
-      + " it is superfluous to therefore specify it with a dot."),
-  NON_STANDARD_ALGORITHM("The checksum algorithm used does not come standard with the Java runtime. Consider using SHA512 instead."),
-  MD5SUM_TOOL_GENERATED_MANIFEST("The manifest was created using a using checksum utilities such as those\n" + 
-      "contained in the GNU Coreutils package (md5sum, sha1sum, etc.), collectively referred to here as 'md5sum'. "
-      + "This creates slight differences in generated manifests that can cause problems in some implementations."),
-  MISSING_TAG_MANIEST("The tag manifest guards against a truncated payload manifest as well as other potental "
-      + "problems and is always recommened that it be included."),
-  OLD_BAGIT_VERSION("The bagit specification version is not the newest. Consider converting to the latest version."),
-  OS_SPECIFIC_FILES("Files created by the operating system (OS) for its own use. They are non-portable across OS versions "
-      + "and should not be included in any manifest. Examples Thumbs.db on Windows or .DS_Store on OS X"),
-  PAYLOAD_OXUM_MISSING("It is recommended to always include the Payload-Oxum in the bag metadata "
-      + "since it allows for a 'quick verification' of the bag."),
-  TAG_FILES_ENCODING("It is recommended to always use UTF-8"),
-  WEAK_CHECKSUM_ALGORITHM("The checksum algorithm used is known to be weak. We recommend using SHA512 at a minium");
+  BAG_WITHIN_A_BAG("bag_within_a_bag"),
+  DIFFERENT_CASE("different_case"),
+  DIFFERENT_NORMALIZATION("different_normalization"),
+  EXTRA_LINES_IN_BAGIT_FILES("extra_lines_in_bagit_files"),
+  LEADING_DOT_SLASH("leading_dot_slash"),
+  NON_STANDARD_ALGORITHM("non_standard_algorithm"),
+  MD5SUM_TOOL_GENERATED_MANIFEST("md5sum_tool_generated_manifest"),
+  MISSING_TAG_MANIFEST("missing_tag_manifest"),
+  OLD_BAGIT_VERSION("old_bagit_version"),
+  OS_SPECIFIC_FILES("os_specific_files"),
+  PAYLOAD_OXUM_MISSING("payload_oxum_missing"),
+  TAG_FILES_ENCODING("tag_files_encoding"),
+  WEAK_CHECKSUM_ALGORITHM("weak_checksum_algorithm");
 
-  private final String reason;
+  private final String messageBundleKey;
+  private static final ResourceBundle messages = ResourceBundle.getBundle("MessageBundle");
 
   private BagitWarning(final String reason){
-    this.reason = reason;
+    this.messageBundleKey = reason;
   }
 
   public String getReason() {
-    return reason;
+    return messages.getString(messageBundleKey);
   }
 }

src/main/java/gov/loc/repository/bagit/conformance/EncodingChecker.java

@@ -3,6 +3,7 @@
 import java.nio.charset.Charset;
 import java.nio.charset.StandardCharsets;
 import java.util.Collection;
+import java.util.ResourceBundle;
 import java.util.Set;
 
 import org.slf4j.Logger;
@@ -14,13 +15,14 @@
  */
 public interface EncodingChecker {
   Logger logger = LoggerFactory.getLogger(EncodingChecker.class);
+  ResourceBundle messages = ResourceBundle.getBundle("MessageBundle");
 
   /*
    * It is now normal for all files to be UTF-8
    */
   static void checkEncoding(final Charset encoding, final Set<BagitWarning> warnings, final Collection<BagitWarning> warningsToIgnore){
     if(!warningsToIgnore.contains(BagitWarning.TAG_FILES_ENCODING) && !StandardCharsets.UTF_8.equals(encoding)){
-      logger.warn("Tag files are encoded with [{}]. We recommend always using UTF-8 instead.", encoding);
+      logger.warn(messages.getString("tag_files_not_encoded_with_utf8_warning"), encoding);
       warnings.add(BagitWarning.TAG_FILES_ENCODING);
     }
   }