Merge pull request #37 from LibraryOfCongress/rewrite_extension

merge Rewrite extension

Author: johnscancella

README.md

@@ -31,12 +31,14 @@ The "new" bagit interface is very intuitive, but here are some easy to follow ex
 File folder = new File("FolderYouWantToBag");
 StandardSupportedAlgorithms algorithm = StandardSupportedAlgorithms.MD5;
 boolean includeHiddenFiles = false;
-Bag bag = BagCreator.bagInPlace(folder, algorithm, includeHiddenFiles);
+BagCreator creator = new BagCreator();
+Bag bag = creator.bagInPlace(folder, algorithm, includeHiddenFiles);
 ```
 ##### Read an existing bag (version 0.93 and higher)
 ```java
 File rootDir = new File("RootDirectoryOfExistingBag");
-Bag bag = BagReader.read(rootDir);
+BagReader reader = new BagReader();
+Bag bag = reader.read(rootDir);
 ```
 ##### Write a Bag object to disk
 ```java
@@ -46,21 +48,50 @@ BagWriter.write(bag, outputDir); //where bag is a Bag object
 ##### Verify Complete
 ```java
 boolean ignoreHiddenFiles = true;
-BagVerifier.isComplete(bag, ignoreHiddenFiles);
+BagVerifier verifier = new BagVerifier();
+verifier.isComplete(bag, ignoreHiddenFiles);
 ```
 ##### Verify Valid
 ```java
 boolean ignoreHiddenFiles = true;
-BagVerifier.isValid(bag, ignoreHiddenFiles);
+BagVerifier verifier = new BagVerifier();
+verifier.isValid(bag, ignoreHiddenFiles);
 ```
 ##### Quickly verify by payload-oxum
 ```java
 boolean ignoreHiddenFiles = true;
+BagVerifier verifier = new BagVerifier();
 
-if(BagVerifier.canQuickVerify(bag)){
-  BagVerifier.quicklyVerify(bag, ignoreHiddenFiles);
+if(verifier.canQuickVerify(bag)){
+  verifier.quicklyVerify(bag, ignoreHiddenFiles);
 }
 ```
+##### Add other checksum algorithms
+You only need to implement 2 interfaces
+```java
+public class MyNewSupportedAlgorithm implements SupportedAlgorithm {
+  @Override
+  public String getMessageDigestName() {
+    return "SHA3-256";
+  }
+  @Override
+  public String getBagitName() {
+    return "sha3256";
+  }
+}
+
+public class MyNewNameMapping implements BagitAlgorithmNameToSupportedAlgorithmMapping {
+  @Override
+  public SupportedAlgorithm getMessageDigestName(String bagitAlgorithmName) {
+    if("sha3256".equals(bagitAlgorithmName)){
+      return new MyNewSupportedAlgorithm();
+    }
+    
+    return StandardSupportedAlgorithms.valueOf(bagitAlgorithmName.toUpperCase());
+  }
+}
+```
+and then add the implemented BagitAlgorithmNameToSupportedAlgorithmMapping class to your BagReader or bagVerifier object before using their methods
 
 ## Developing Bagit-Java
 Bagit-Java uses [Gradle](https://gradle.org/) for its build system. Check out the great [documentation](https://docs.gradle.org/current/userguide/userguide_single.html) to learn more.
@@ -80,7 +111,6 @@ Simply run `gradle eclipse` and it will automatically create a eclipse project f
 * Further refine reading and writing of bags version 0.93-0.97
 * Integrate new proposed specification we are calling "dot bagit"
 * Fix bugs/issues reported with new library (on going)
-* Add extensions for more than standard supported algorithms
 
 ### Support
 1. The Digital Curation Google Group (https://groups.google.com/d/forum/digital-curation) is an open discussion list that reaches many of the contributors to and users of this open-source project

build.gradle

@@ -19,7 +19,9 @@ repositories {
 dependencies {
   compile 'org.slf4j:slf4j-api:latest.integration'
 
-  testCompile 'junit:junit:4.12', 'org.springframework.boot:spring-boot-starter-logging:1.3.2.RELEASE'
+  testCompile 'junit:junit:latest.integration', 
+    'org.springframework.boot:spring-boot-starter-logging:latest.integration',
+    'org.bouncycastle:bcprov-jdk15on:latest.integration'
 }
 
 test { //show test output

src/main/java/gov/loc/repository/bagit/creator/AddPayloadToBagManifestVistor.java

@@ -56,7 +56,7 @@ public FileVisitResult visitFile(Path path, BasicFileAttributes attrs)throws IOE
       InputStream inputStream = Files.newInputStream(path, StandardOpenOption.READ);
       String hash = Hasher.hash(inputStream, messageDigest);
       logger.debug("Adding [{}] to manifest with hash [{}]", path, hash);
-      manifest.getFileToChecksumMap().put(path.toFile(), hash); 
+      manifest.getFileToChecksumMap().put(path, hash); 
     }
 
     return FileVisitResult.CONTINUE;

src/main/java/gov/loc/repository/bagit/creator/BagCreator.java

@@ -1,10 +1,9 @@
 package gov.loc.repository.bagit.creator;
 
-import java.io.File;
 import java.io.IOException;
+import java.nio.file.DirectoryStream;
 import java.nio.file.Files;
 import java.nio.file.Path;
-import java.nio.file.Paths;
 import java.security.MessageDigest;
 import java.security.NoSuchAlgorithmException;
 
@@ -37,24 +36,26 @@ public class BagCreator {
    * @throws IOException if there is a problem writing or moving file(s)
    * @return a {@link Bag} object representing the newly created bagit bag
    */
-  public static Bag bagInPlace(File root, SupportedAlgorithm algorithm, boolean includeHidden) throws NoSuchAlgorithmException, IOException{
+  public static Bag bagInPlace(Path root, SupportedAlgorithm algorithm, boolean includeHidden) throws NoSuchAlgorithmException, IOException{
     Bag bag = new Bag(new Version(0, 97));
     bag.setRootDir(root);
     logger.info("Creating a bag with version: [{}] in directory: [{}]", bag.getVersion(), root);
 
-    File[] files = root.listFiles();
-    File dataDir = new File(root, "data");
-    if(!dataDir.exists() && !dataDir.mkdir()){
-      throw new IOException("Unable to make " + dataDir);
-    }
 
-    moveFilesToDataDir(files, dataDir);
+    Path dataDir = root.resolve("data");
+    Files.createDirectory(dataDir);
+    DirectoryStream<Path> directoryStream = Files.newDirectoryStream(root);
+    for(Path path : directoryStream){
+      if(!path.equals(dataDir) && !Files.isHidden(path) || includeHidden){
+        Files.move(path, dataDir.resolve(path.getFileName()));
+      }
+    }
 
     logger.info("Creating payload manifest");
     Manifest manifest = new Manifest(algorithm);
     MessageDigest messageDigest = MessageDigest.getInstance(algorithm.getMessageDigestName());
     AddPayloadToBagManifestVistor visitor = new AddPayloadToBagManifestVistor(manifest, messageDigest, includeHidden);
-    Files.walkFileTree(Paths.get(dataDir.toURI()), visitor);
+    Files.walkFileTree(dataDir, visitor);
 
     bag.getPayLoadManifests().add(manifest);
     BagWriter.writeBagitFile(bag.getVersion(), bag.getFileEncoding(), root);
@@ -64,17 +65,6 @@ public static Bag bagInPlace(File root, SupportedAlgorithm algorithm, boolean in
     return bag;
   }
 
-  protected static void moveFilesToDataDir(File[] files, File dataDir) throws IOException{
-    if(files != null){
-      logger.info("Moving files to [{}]", dataDir);
-      for(File file : files){
-        Path dest = Paths.get(dataDir.getPath(), file.getName());
-        logger.debug("Moving [{}] to [{}]", file, dest);
-        Files.move(Paths.get(file.toURI()), dest);
-      }
-    }
-  }
-  
   /**
    * Creates a basic(only required elements) .bagit bag in place.
    * This creates files and directories, thus if an error is thrown during operation it may leave the filesystem 
@@ -87,21 +77,19 @@ protected static void moveFilesToDataDir(File[] files, File dataDir) throws IOEx
    * @throws IOException if there is a problem writing files or .bagit directory
    */
   @Incubating
-  public static Bag createDotBagit(File root, SupportedAlgorithm algorithm, boolean includeHidden) throws NoSuchAlgorithmException, IOException{
+  public static Bag createDotBagit(Path root, SupportedAlgorithm algorithm, boolean includeHidden) throws NoSuchAlgorithmException, IOException{
     Bag bag = new Bag(new Version(0, 98));
     bag.setRootDir(root);
     logger.info("Creating a bag with version: [{}] in directory: [{}]", bag.getVersion(), root);
 
-    File dotbagitDir = new File(root, ".bagit");
-    if(!dotbagitDir.mkdir()){
-      throw new IOException("Was unable to create " + dotbagitDir);
-    }
+    Path dotbagitDir = root.resolve(".bagit");
+    Files.createDirectories(dotbagitDir);
 
     logger.info("Creating payload manifest");
     Manifest manifest = new Manifest(algorithm);
     MessageDigest messageDigest = MessageDigest.getInstance(algorithm.getMessageDigestName());
     AddPayloadToBagManifestVistor visitor = new AddPayloadToBagManifestVistor(manifest, messageDigest, includeHidden);
-    Files.walkFileTree(Paths.get(root.toURI()), visitor);
+    Files.walkFileTree(root, visitor);
 
     bag.getPayLoadManifests().add(manifest);
     BagWriter.writeBagitFile(bag.getVersion(), bag.getFileEncoding(), dotbagitDir);

src/main/java/gov/loc/repository/bagit/domain/Bag.java

@@ -1,7 +1,7 @@
 package gov.loc.repository.bagit.domain;
 
-import java.io.File;
 import java.nio.charset.StandardCharsets;
+import java.nio.file.Path;
 import java.util.ArrayList;
 import java.util.HashSet;
 import java.util.List;
@@ -33,7 +33,7 @@ public class Bag {
   private List<Pair<String, String>> metadata = new ArrayList<>();
 
   //the current location of the bag on the filesystem
-  private File rootDir;
+  private Path rootDir;
 
   public Bag(){
   }
@@ -142,11 +142,11 @@ public boolean equals(Object obj) {
         Objects.equals(this.metadata, other.getMetadata());
   }
 
-  public File getRootDir() {
+  public Path getRootDir() {
     return rootDir;
   }
 
-  public void setRootDir(File rootDir) {
+  public void setRootDir(Path rootDir) {
     this.rootDir = rootDir;
   }
 

src/main/java/gov/loc/repository/bagit/domain/Manifest.java

@@ -1,7 +1,7 @@
 
 package gov.loc.repository.bagit.domain;
 
-import java.io.File;
+import java.nio.file.Path;
 import java.util.HashMap;
 
 import gov.loc.repository.bagit.hash.SupportedAlgorithm;
@@ -11,17 +11,17 @@
  */
 public class Manifest {
   private final SupportedAlgorithm algorithm;
-  private HashMap<File, String> fileToChecksumMap = new HashMap<>();
+  private HashMap<Path, String> fileToChecksumMap = new HashMap<>();
 
   public Manifest(SupportedAlgorithm algorithm){
     this.algorithm = algorithm;
   }
 
-  public HashMap<File, String> getFileToChecksumMap() {
+  public HashMap<Path, String> getFileToChecksumMap() {
     return fileToChecksumMap;
   }
 
-  public void setFileToChecksumMap(HashMap<File, String> fileToChecksumMap) {
+  public void setFileToChecksumMap(HashMap<Path, String> fileToChecksumMap) {
     this.fileToChecksumMap = fileToChecksumMap;
   }
 

src/main/java/gov/loc/repository/bagit/hash/BagitAlgorithmNameToSupportedAlgorithmMapping.java

@@ -0,0 +1,8 @@
+package gov.loc.repository.bagit.hash;
+
+/**
+ * Implement this interface if you need to be able to use other algorithms than the {@link StandardSupportedAlgorithms}
+ */
+public interface BagitAlgorithmNameToSupportedAlgorithmMapping {
+  public SupportedAlgorithm getMessageDigestName(String bagitAlgorithmName);
+}

src/main/java/gov/loc/repository/bagit/hash/StandardBagitAlgorithmNameToSupportedAlgorithmMapping.java

@@ -0,0 +1,14 @@
+package gov.loc.repository.bagit.hash;
+
+/**
+ * Provides a mapping between bagit algorithm names and {@link SupportedAlgorithm} 
+ */
+public class StandardBagitAlgorithmNameToSupportedAlgorithmMapping
+    implements BagitAlgorithmNameToSupportedAlgorithmMapping {
+
+  @Override
+  public SupportedAlgorithm getMessageDigestName(String bagitAlgorithmName) {
+    return StandardSupportedAlgorithms.valueOf(bagitAlgorithmName.toUpperCase());
+  }
+
+}