RAT-98: report skipped files

apache-rat-core/pom.xml

@@ -281,5 +281,10 @@
       <artifactId>groovy-all</artifactId>
       <scope>test</scope>
     </dependency>
+    <dependency>
+      <groupId>com.google.jimfs</groupId>
+      <artifactId>jimfs</artifactId>
+      <scope>test</scope>
+    </dependency>
   </dependencies>
 </project>

apache-rat-core/src/it/java/org/apache/rat/ReportTest.java

@@ -163,7 +163,7 @@ public static Stream<Arguments> args() throws RatException {
             @Override
             public void report(Document document)  {
                 if (!document.isIgnored()) {
-                    String[] tokens = document.getName().tokenize(document.getName().localized());
+                    String[] tokens = DocumentName.FSInfo.getDefault().tokenize(document.getName().localized());
                     results.add(Arguments.of(tokens[1], document));
                 }
             }

apache-rat-core/src/it/resources/ReportTest/RAT_14/verify.groovy

@@ -64,7 +64,7 @@ myArgs[1] = "UNAPPROVED:-1"
 myArgs[2] = "--"
 myArgs[3] = src.getAbsolutePath()
 
-ReportConfiguration configuration = OptionCollection.parseCommands(myArgs, { opts -> })
+ReportConfiguration configuration = OptionCollection.parseCommands(src, myArgs, { opts -> })
 assertNotNull(configuration)
 configuration.validate(DefaultLog.getInstance().&error)
 Reporter reporter = new Reporter(configuration)

apache-rat-core/src/it/resources/ReportTest/RAT_335/ignore.txt → apache-rat-core/src/it/resources/ReportTest/RAT_335/commandLine.txt

@@ -1,7 +1,5 @@
 --output-style
 xml
---input-exclude
-**/.gitignore
 --input-exclude-parsed-scm
 GIT
 --

apache-rat-core/src/it/resources/ReportTest/RAT_335/verify.groovy

@@ -36,48 +36,11 @@ private static Map<String, String> mapOf(String... parts) {
 output = new File(args[0])
 content = output.text
 
-//Map<ClaimStatistic.Counter, String> data = new HashMap<>()
-//data.put(ClaimStatistic.Counter.APPROVED, "2")
-//data.put(ClaimStatistic.Counter.ARCHIVES, "0")
-//data.put(ClaimStatistic.Counter.BINARIES, "0")
-//data.put(ClaimStatistic.Counter.DOCUMENT_TYPES, "3")
-//data.put(ClaimStatistic.Counter.IGNORED, "6")
-//data.put(ClaimStatistic.Counter.LICENSE_CATEGORIES, "2")
-//data.put(ClaimStatistic.Counter.LICENSE_NAMES, "2")
-//data.put(ClaimStatistic.Counter.NOTICES, "1")
-//data.put(ClaimStatistic.Counter.STANDARDS, "6")
-//data.put(ClaimStatistic.Counter.UNAPPROVED, "4")
-//data.put(ClaimStatistic.Counter.UNKNOWN, "4")
-
 Document document = XmlUtils.toDom(new FileInputStream(args[0]))
 XPath xPath = XPathFactory.newInstance().newXPath()
 
-//for (ClaimStatistic.Counter counter : ClaimStatistic.Counter.values()) {
-//    String xpath = String.format("/rat-report/statistics/statistic[@name='%s']", counter.displayName())
-//    Map<String, String> map = mapOf("approval",
-//            counter == ClaimStatistic.Counter.UNAPPROVED ? "false" : "true",
-//            "count", data.get(counter),
-//            "description", counter.getDescription())
-//    XmlUtils.assertAttributes(document, xPath, xpath, map)
-//}
-
-//// license categories
-//XmlUtils.assertAttributes(document, xPath, "/rat-report/statistics/licenseCategory[@name='?????']",
-//        mapOf("count", "4" ))
-//
-//XmlUtils.assertAttributes(document, xPath, "/rat-report/statistics/licenseCategory[@name='AL   ']",
-//        mapOf("count", "2" ))
-//
-//// license names
-//XmlUtils.assertAttributes(document, xPath, "/rat-report/statistics/licenseName[@name='Apache License Version 2.0']",
-//        mapOf("count", "2" ))
-//
-//XmlUtils.assertAttributes(document, xPath, "/rat-report/statistics/licenseName[@name='Unknown license']",
-//        mapOf("count", "4" ))
-
 List<String> ignoredFiles = new ArrayList<>(Arrays.asList(
         "/dir1/dir1.txt",
-        "/dir1/file1.log",
         "/dir1/.gitignore",
         "/dir2/dir2.md",
         "/dir3/dir3.log",
@@ -102,24 +65,4 @@ XmlUtils.assertAttributes(document, xPath, "/rat-report/statistics/documentType[
         mapOf("count", "1" ))
 
 XmlUtils.assertAttributes(document, xPath, "/rat-report/statistics/documentType[@name='STANDARD']",
-        mapOf("count", "6" ))
-
-/*
-TextUtils.assertPatternInTarget("^  Approved:\\s+8 ", content)
-TextUtils.assertPatternInTarget("^  Archives:\\s+1 ", content)
-TextUtils.assertPatternInTarget("^  Binaries:\\s+2 ", content)
-TextUtils.assertPatternInTarget("^  Document types:\\s+5 ", content)
-TextUtils.assertPatternInTarget("^  Ignored:\\s+1 ", content)
-TextUtils.assertPatternInTarget("^  License categories:\\s+4 ", content)
-TextUtils.assertPatternInTarget("^  License names:\\s+5", content)
-TextUtils.assertPatternInTarget("^  Notices:\\s+2 ", content)
-TextUtils.assertPatternInTarget("^  Standards:\\s+8 ", content)
-TextUtils.assertPatternInTarget("^  Unapproved:\\s+2 ", content)
-TextUtils.assertPatternInTarget("^  Unknown:\\s+2 ", content)
-
-logOutput = new File(args[1])
-log = logOutput.text
-
-TextUtils.assertPatternNotInTarget("^ERROR:", log)
-TextUtils.assertPatternNotInTarget("^WARN:", log)
-*/
+        mapOf("count", "4" ))

apache-rat-core/src/main/java/org/apache/rat/OptionCollection.java

@@ -132,25 +132,28 @@ private static String asString(final Object[] args) {
     /**
      * Parses the standard options to create a ReportConfiguration.
      *
+     * @param workingDirectory The directory to resolve relative file names against.
      * @param args the arguments to parse
      * @param helpCmd the help command to run when necessary.
      * @return a ReportConfiguration or null if Help was printed.
      * @throws IOException on error.
      */
-    public static ReportConfiguration parseCommands(final String[] args, final Consumer<Options> helpCmd) throws IOException {
-        return parseCommands(args, helpCmd, false);
+    public static ReportConfiguration parseCommands(final File workingDirectory, final String[] args, final Consumer<Options> helpCmd) throws IOException {
+        return parseCommands(workingDirectory, args, helpCmd, false);
     }
 
     /**
      * Parses the standard options to create a ReportConfiguration.
      *
+     * @param workingDirectory The directory to resolve relative file names against.
      * @param args the arguments to parse
      * @param helpCmd the help command to run when necessary.
      * @param noArgs If true then the commands do not need extra arguments
      * @return a ReportConfiguration or {@code null} if Help was printed.
      * @throws IOException on error.
      */
-    public static ReportConfiguration parseCommands(final String[] args, final Consumer<Options> helpCmd, final boolean noArgs) throws IOException {
+    public static ReportConfiguration parseCommands(final File workingDirectory, final String[] args,
+                                                    final Consumer<Options> helpCmd, final boolean noArgs) throws IOException {
         Options opts = buildOptions();
         CommandLine commandLine;
         try {
@@ -166,27 +169,23 @@ public static ReportConfiguration parseCommands(final String[] args, final Consu
 
         Arg.processLogLevel(commandLine);
 
+        ArgumentContext argumentContext = new ArgumentContext(workingDirectory, commandLine);
         if (commandLine.hasOption(HELP)) {
             helpCmd.accept(opts);
             return null;
         }
 
         if (commandLine.hasOption(HELP_LICENSES)) {
-            new Licenses(createConfiguration(commandLine), new PrintWriter(System.out)).printHelp();
-            return null;
-        }
-
-        if (commandLine.hasOption(HELP_LICENSES)) {
-            new Licenses(createConfiguration(commandLine), new PrintWriter(System.out)).printHelp();
+            new Licenses(createConfiguration(argumentContext), new PrintWriter(System.out)).printHelp();
             return null;
         }
 
         if (commandLine.hasOption(Arg.HELP_LICENSES.option())) {
-            new Licenses(createConfiguration(commandLine), new PrintWriter(System.out)).printHelp();
+            new Licenses(createConfiguration(argumentContext), new PrintWriter(System.out)).printHelp();
             return null;
         }
 
-        ReportConfiguration configuration = createConfiguration(commandLine);
+        ReportConfiguration configuration = createConfiguration(argumentContext);
         if (!noArgs && !configuration.hasSource()) {
             String msg = "No directories or files specified for scanning. Did you forget to close a multi-argument option?";
             DefaultLog.getInstance().error(msg);
@@ -201,14 +200,15 @@ public static ReportConfiguration parseCommands(final String[] args, final Consu
      * Create the report configuration.
      * Note: this method is package private for testing.
      * You probably want one of the {@code ParseCommands} methods.
-     * @param commandLine the parsed command line.
+     * @param argumentContext The context to execute in.
      * @return a ReportConfiguration
-     * @see #parseCommands(String[], Consumer)
-     * @see #parseCommands(String[], Consumer, boolean)
+     * @see #parseCommands(File, String[], Consumer)
+     * @see #parseCommands(File, String[], Consumer, boolean)
      */
-    static ReportConfiguration createConfiguration(final CommandLine commandLine) {
-        final ReportConfiguration configuration = new ReportConfiguration();
-        new ArgumentContext(configuration, commandLine).processArgs();
+    static ReportConfiguration createConfiguration(final ArgumentContext argumentContext) {
+        argumentContext.processArgs();
+        final ReportConfiguration configuration = argumentContext.getConfiguration();
+        final CommandLine commandLine = argumentContext.getCommandLine();
         if (Arg.DIR.isSelected()) {
             try {
                 configuration.addSource(getReportable(commandLine.getParsedOptionValue(Arg.DIR.getSelected()), configuration));
@@ -249,10 +249,10 @@ static IReportable getReportable(final File base, final ReportConfiguration conf
             DefaultLog.getInstance().error("Directory '" + documentName + "' does not exist.");
             return null;
         }
-        DocumentNameMatcher documentNameMatcher = config.getNameMatcher(documentName);
+        DocumentNameMatcher documentExcluder = config.getDocumentExcluder(documentName);
 
-        Document doc = new FileDocument(documentName, absBase, documentNameMatcher);
-        if (!documentNameMatcher.matches(doc.getName())) {
+        Document doc = new FileDocument(documentName, absBase, documentExcluder);
+        if (!documentExcluder.matches(doc.getName())) {
             DefaultLog.getInstance().error("Directory '" + documentName + "' is in excluded list.");
             return null;
         }

apache-rat-core/src/main/java/org/apache/rat/Report.java

@@ -18,6 +18,8 @@
  */
 package org.apache.rat;
 
+import java.io.File;
+
 import org.apache.commons.cli.Options;
 import org.apache.rat.document.RatDocumentAnalysisException;
 import org.apache.rat.help.Help;
@@ -39,7 +41,7 @@ public final class Report {
      */
     public static void main(final String[] args) throws Exception {
         DefaultLog.getInstance().info(new VersionInfo().toString());
-        ReportConfiguration configuration = OptionCollection.parseCommands(args, Report::printUsage);
+        ReportConfiguration configuration = OptionCollection.parseCommands(new File("."), args, Report::printUsage);
         if (configuration != null) {
             configuration.validate(DefaultLog.getInstance()::error);
             Reporter reporter = new Reporter(configuration);

apache-rat-core/src/main/java/org/apache/rat/ReportConfiguration.java

@@ -414,11 +414,11 @@ public void addIncludedPatterns(final Iterable<String> patterns) {
     }
 
     /**
-     * Get the DocumentNameMatcher based on the directory.
+     * Get the DocumentNameMatcher that excludes files found in the directory tree..
      * @param baseDir the DocumentName for the base directory.
      * @return the DocumentNameMatcher for the base directory.
      */
-    public DocumentNameMatcher getNameMatcher(final DocumentName baseDir) {
+    public DocumentNameMatcher getDocumentExcluder(final DocumentName baseDir) {
         return exclusionProcessor.getNameMatcher(baseDir);
     }
 

apache-rat-core/src/main/java/org/apache/rat/analysis/TikaProcessor.java

@@ -129,9 +129,9 @@ public static InputStream markSupportedInputStream(final InputStream stream) {
      * @throws RatDocumentAnalysisException on error.
      */
     public static String process(final Document document) throws RatDocumentAnalysisException {
-        Metadata metadata = new Metadata();
         try (InputStream stream = markSupportedInputStream(document.inputStream())) {
-            metadata.set(TikaCoreProperties.RESOURCE_NAME_KEY, document.getName().getName());
+            Metadata metadata = new Metadata();
+            metadata.set(TikaCoreProperties.RESOURCE_NAME_KEY, document.getName().getShortName());
             String result = TIKA.detect(stream, metadata);
             String[] parts = result.split("/");
             MediaType mediaType = new MediaType(parts[0], parts[1]);
@@ -146,7 +146,6 @@ public static String process(final Document document) throws RatDocumentAnalysis
                     document.getMetaData().setDocumentType(Document.Type.NOTICE);
                 }
             }
-
             return result;
         } catch (IOException e) {
             throw new RatDocumentAnalysisException(e);

apache-rat-core/src/main/java/org/apache/rat/api/Document.java

@@ -52,7 +52,7 @@ public enum Type {
     }
 
     /** The path matcher used by this document */
-    protected final DocumentNameMatcher nameMatcher;
+    protected final DocumentNameMatcher nameExcluder;
     /** The metadata for this document */
     private final MetaData metaData;
     /** The fully qualified name of this document */
@@ -61,11 +61,11 @@ public enum Type {
     /**
      * Creates an instance.
      * @param name the native NameSet of the resource.
-     * @param nameMatcher the document name matcher to filter directories/files.
+     * @param nameExcluder the document name matcher to filter directories/files.
      */
-    protected Document(final DocumentName name, final DocumentNameMatcher nameMatcher) {
+    protected Document(final DocumentName name, final DocumentNameMatcher nameExcluder) {
         this.name = name;
-        this.nameMatcher = nameMatcher;
+        this.nameExcluder = nameExcluder;
         this.metaData = new MetaData();
     }
 
@@ -81,8 +81,8 @@ public final DocumentName getName() {
      * Gets the file filter this document was created with.
      * @return the file filter this document was created with.
      */
-    public final DocumentNameMatcher getNameMatcher() {
-        return nameMatcher;
+    public final DocumentNameMatcher getNameExcluder() {
+        return nameExcluder;
     }
 
     @Override