Fix #770 Fix #1351 : use PathAccepter in FileHistoryCache

- Extract path-based including/ignoring to configuration
- Also, relocate Filter, IgnoredDirs, IgnoredFiles,
  IgnoredNames to configuration

Author: idodeclare

opengrok-indexer/src/main/java/org/opengrok/indexer/configuration/Configuration.java

@@ -59,8 +59,6 @@
 import org.opengrok.indexer.authorization.AuthControlFlag;
 import org.opengrok.indexer.authorization.AuthorizationStack;
 import org.opengrok.indexer.history.RepositoryInfo;
-import org.opengrok.indexer.index.Filter;
-import org.opengrok.indexer.index.IgnoredNames;
 import org.opengrok.indexer.logger.LoggerFactory;
 
 

opengrok-indexer/src/main/java/org/opengrok/indexer/configuration/ConfigurationHelp.java

@@ -18,7 +18,7 @@
  */
 
 /*
- * Copyright (c) 2018-2019, Chris Fraire <cfraire@me.com>.
+ * Copyright (c) 2018-2020, Chris Fraire <cfraire@me.com>.
  */
 
 package org.opengrok.indexer.configuration;
@@ -39,8 +39,6 @@
 import org.opengrok.indexer.authorization.AuthorizationPlugin;
 import org.opengrok.indexer.authorization.AuthorizationStack;
 import org.opengrok.indexer.history.RepositoryInfo;
-import org.opengrok.indexer.index.Filter;
-import org.opengrok.indexer.index.IgnoredNames;
 import org.opengrok.indexer.util.StringUtils;
 
 /**

opengrok-indexer/src/main/java/org/opengrok/indexer/index/Filter.java renamed to opengrok-indexer/src/main/java/org/opengrok/indexer/configuration/Filter.java

@@ -19,9 +19,10 @@
 
 /*
  * Copyright (c) 2010, 2018, Oracle and/or its affiliates. All rights reserved.
+ * Portions Copyright (c) 2020, Chris Fraire <cfraire@me.com>.
  */
 
-package org.opengrok.indexer.index;
+package org.opengrok.indexer.configuration;
 
 import java.io.File;
 import java.io.Serializable;

opengrok-indexer/src/main/java/org/opengrok/indexer/index/IgnoredDirs.java renamed to opengrok-indexer/src/main/java/org/opengrok/indexer/configuration/IgnoredDirs.java

@@ -19,9 +19,9 @@
 
 /*
  * Copyright (c) 2015, 2018, Oracle and/or its affiliates. All rights reserved.
- * Portions Copyright (c) 2019, Chris Fraire <cfraire@me.com>.
+ * Portions Copyright (c) 2019-2020, Chris Fraire <cfraire@me.com>.
  */
-package org.opengrok.indexer.index;
+package org.opengrok.indexer.configuration;
 
 import java.io.File;
 

opengrok-indexer/src/main/java/org/opengrok/indexer/index/IgnoredFiles.java renamed to opengrok-indexer/src/main/java/org/opengrok/indexer/configuration/IgnoredFiles.java

@@ -19,9 +19,9 @@
 
 /*
  * Copyright (c) 2007, 2018, Oracle and/or its affiliates. All rights reserved.
- * Portions Copyright (c) 2019, Chris Fraire <cfraire@me.com>.
+ * Portions Copyright (c) 2019-2020, Chris Fraire <cfraire@me.com>.
  */
-package org.opengrok.indexer.index;
+package org.opengrok.indexer.configuration;
 
 import java.io.File;
 

opengrok-indexer/src/main/java/org/opengrok/indexer/index/IgnoredNames.java renamed to opengrok-indexer/src/main/java/org/opengrok/indexer/configuration/IgnoredNames.java

@@ -19,9 +19,9 @@
 
 /*
  * Copyright (c) 2015, 2018, Oracle and/or its affiliates. All rights reserved.
- * Portions Copyright (c) 2019, Chris Fraire <cfraire@me.com>.
+ * Portions Copyright (c) 2019-2020, Chris Fraire <cfraire@me.com>.
  */
-package org.opengrok.indexer.index;
+package org.opengrok.indexer.configuration;
 
 import java.io.File;
 import java.io.Serializable;
@@ -60,6 +60,12 @@ public void setItems(List<String> item) {
         }
     }
 
+    /**
+     * Adds the specified {@code pattern} if it follows the expected naming
+     * convention (or else ignored).
+     * @param pattern defined pattern starting either with {@code "f:"} for
+     *                ignore-file or with {@code "d:"} for an ignore-directory
+     */
     public void add(String pattern) {
         if (pattern.startsWith(FILE_PREFIX)) {
             ignoredFiles.add(pattern.substring(FILE_PREFIX.length()));

opengrok-indexer/src/main/java/org/opengrok/indexer/configuration/PathAccepter.java

@@ -0,0 +1,74 @@
+/*
+ * CDDL HEADER START
+ *
+ * The contents of this file are subject to the terms of the
+ * Common Development and Distribution License (the "License").
+ * You may not use this file except in compliance with the License.
+ *
+ * See LICENSE.txt included in this distribution for the specific
+ * language governing permissions and limitations under the License.
+ *
+ * When distributing Covered Code, include this CDDL HEADER in each
+ * file and include the License file at LICENSE.txt.
+ * If applicable, add the following below this CDDL HEADER, with the
+ * fields enclosed by brackets "[]" replaced with your own identifying
+ * information: Portions Copyright [yyyy] [name of copyright owner]
+ *
+ * CDDL HEADER END
+ */
+
+/*
+ * Copyright (c) 2008, 2019, Oracle and/or its affiliates. All rights reserved.
+ * Portions Copyright (c) 2017-2020, Chris Fraire <cfraire@me.com>.
+ */
+
+package org.opengrok.indexer.configuration;
+
+import org.opengrok.indexer.logger.LoggerFactory;
+
+import java.io.File;
+import java.util.logging.Level;
+import java.util.logging.Logger;
+
+/**
+ * Represents a gatekeeper that decides whether a particular file or directory
+ * is acceptable for history or code analysis with respect to configuration of
+ * ignored files and directories or of specified inclusive filtering.
+ */
+public class PathAccepter {
+
+    private static final Logger LOGGER = LoggerFactory.getLogger(PathAccepter.class);
+
+    private final IgnoredNames ignoredNames;
+    private final Filter includedNames;
+
+    /**
+     * Package-private to be initialized from the runtime environment.
+     */
+    PathAccepter(IgnoredNames ignoredNames, Filter includedNames) {
+        this.ignoredNames = ignoredNames;
+        this.includedNames = includedNames;
+    }
+
+    /**
+     * Evaluates the specified {@code file} versus the runtime configuration of
+     * ignored files and directories or of specified inclusive filtering, and
+     * returns a value whether the {@code file} is to be accepted.
+     * @param file a defined instance under the source root
+     */
+    public boolean accept(File file) {
+        if (!includedNames.isEmpty()
+                && // the filter should not affect directory names
+                (!(file.isDirectory() || includedNames.match(file)))) {
+            LOGGER.log(Level.FINER, "not including {0}", file.getAbsolutePath());
+            return false;
+        }
+
+        if (ignoredNames.ignore(file)) {
+            LOGGER.log(Level.FINER, "ignoring {0}", file.getAbsolutePath());
+            return false;
+        }
+
+        return true;
+    }
+}

opengrok-indexer/src/main/java/org/opengrok/indexer/configuration/RuntimeEnvironment.java

@@ -62,8 +62,6 @@
 import org.opengrok.indexer.authorization.AuthorizationStack;
 import org.opengrok.indexer.history.HistoryGuru;
 import org.opengrok.indexer.history.RepositoryInfo;
-import org.opengrok.indexer.index.Filter;
-import org.opengrok.indexer.index.IgnoredNames;
 import org.opengrok.indexer.index.IndexDatabase;
 import org.opengrok.indexer.index.IndexerParallelizer;
 import org.opengrok.indexer.logger.LoggerFactory;
@@ -190,6 +188,13 @@ public IndexerParallelizer getIndexerParallelizer() {
         return lzIndexerParallelizer.get();
     }
 
+    /**
+     * Gets an instance associated to this environment.
+     */
+    public PathAccepter getPathAccepter() {
+        return new PathAccepter(getIgnoredNames(), getIncludedNames());
+    }
+
     private String getCanonicalPath(String s) {
         if (s == null) {
             return null;
@@ -704,8 +709,7 @@ public void removeRepositories() {
      */
     public void setRepositories(String... dir) {
         List<RepositoryInfo> repos = new ArrayList<>(HistoryGuru.getInstance().
-                addRepositories(Arrays.stream(dir).map(File::new).toArray(File[]::new),
-                        getIgnoredNames()));
+                addRepositories(Arrays.stream(dir).map(File::new).toArray(File[]::new)));
         setRepositories(repos);
     }