ZipFile!

.gitignore

@@ -0,0 +1,49 @@
+# Covers JetBrains IDEs: IntelliJ, RubyMine, PhpStorm, AppCode, PyCharm, CLion, Android Studio and Webstorm
+# Reference: https://intellij-support.jetbrains.com/hc/en-us/articles/206544839
+
+# User-specific stuff:
+.idea/**/workspace.xml
+.idea/**/tasks.xml
+.idea/dictionaries
+
+# Sensitive or high-churn files:
+.idea/**/dataSources/
+.idea/**/dataSources.ids
+.idea/**/dataSources.xml
+.idea/**/dataSources.local.xml
+.idea/**/sqlDataSources.xml
+.idea/**/dynamic.xml
+.idea/**/uiDesigner.xml
+
+# Gradle:
+.idea/**/gradle.xml
+.idea/**/libraries
+
+# CMake
+cmake-build-debug/
+
+# Mongo Explorer plugin:
+.idea/**/mongoSettings.xml
+
+## File-based project format:
+*.iws
+
+## Plugin-specific files:
+
+# IntelliJ
+out/
+
+# mpeltonen/sbt-idea plugin
+.idea_modules/
+
+# JIRA plugin
+atlassian-ide-plugin.xml
+
+# Cursive Clojure plugin
+.idea/replstate.xml
+
+# Crashlytics plugin (for Android Studio and IntelliJ)
+com_crashlytics_export_strings.xml
+crashlytics.properties
+crashlytics-build.properties
+fabric.properties

ZipFile.iml

@@ -0,0 +1,18 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<module org.jetbrains.idea.maven.project.MavenProjectsManager.isMavenModule="true" type="JAVA_MODULE" version="4">
+  <component name="NewModuleRootManager" LANGUAGE_LEVEL="JDK_1_7">
+    <output url="file://$MODULE_DIR$/target/classes" />
+    <output-test url="file://$MODULE_DIR$/target/test-classes" />
+    <content url="file://$MODULE_DIR$">
+      <sourceFolder url="file://$MODULE_DIR$/src/main/java" isTestSource="false" />
+      <sourceFolder url="file://$MODULE_DIR$/src/test/java" isTestSource="true" />
+      <sourceFolder url="file://$MODULE_DIR$/src/test/resources" type="java-test-resource" />
+      <excludeFolder url="file://$MODULE_DIR$/target" />
+    </content>
+    <orderEntry type="inheritedJdk" />
+    <orderEntry type="sourceFolder" forTests="false" />
+    <orderEntry type="library" name="Maven: junit:junit:4.0" level="project" />
+    <orderEntry type="library" name="Maven: org.jetbrains:annotations:13.0" level="project" />
+    <orderEntry type="library" name="Maven: commons-io:commons-io:2.5" level="project" />
+  </component>
+</module>

pom.xml

@@ -0,0 +1,41 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<project xmlns="http://maven.apache.org/POM/4.0.0"
+         xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
+         xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 http://maven.apache.org/xsd/maven-4.0.0.xsd">
+    <modelVersion>4.0.0</modelVersion>
+
+    <groupId>ru.spbau.mit.kazakov</groupId>
+    <artifactId>ZipFile</artifactId>
+    <version>1.0-SNAPSHOT</version>
+    <build>
+        <plugins>
+            <plugin>
+                <groupId>org.apache.maven.plugins</groupId>
+                <artifactId>maven-compiler-plugin</artifactId>
+                <configuration>
+                    <source>1.7</source>
+                    <target>1.7</target>
+                </configuration>
+            </plugin>
+        </plugins>
+    </build>
+
+    <dependencies>
+        <dependency>
+            <groupId>junit</groupId>
+            <artifactId>junit</artifactId>
+            <version>4.0</version>
+        </dependency>
+        <dependency>
+            <groupId>org.jetbrains</groupId>
+            <artifactId>annotations</artifactId>
+            <version>13.0</version>
+        </dependency>
+        <dependency>
+            <groupId>commons-io</groupId>
+            <artifactId>commons-io</artifactId>
+            <version>2.5</version>
+        </dependency>
+    </dependencies>
+
+</project>

src/main/java/ru/spbau/mit/kazakov/ZipFile/NotExistingDirectoryException.java

@@ -0,0 +1,8 @@
+package ru.spbau.mit.kazakov.ZipFile;
+
+/**
+ * Exception thrown when passed directory doesn't exist.
+ */
+public class NotExistingDirectoryException extends Exception {
+
+}

src/main/java/ru/spbau/mit/kazakov/ZipFile/RegexpUnzip.java

@@ -0,0 +1,105 @@
+package ru.spbau.mit.kazakov.ZipFile;
+
+
+import org.jetbrains.annotations.NotNull;
+
+import java.io.*;
+import java.util.ArrayList;
+import java.util.zip.ZipEntry;
+import java.util.zip.ZipInputStream;
+
+/**
+ * Class for extracting files with names satisfying specified regular expression from archives located in specified directory.
+ * Extracted files with their folders will be located in their archive directory.
+ */
+public class RegexpUnzip {
+    /**
+     * Finds archives in specified directory and extract files that satisfies specified regular expression from them.
+     *
+     * @param path   to directory
+     * @param regexp to satisfy
+     * @throws NotExistingDirectoryException if path doesn't specify a directory
+     */
+    public static void unzipMatchedFilesInPath(@NotNull String path, @NotNull String regexp) throws NotExistingDirectoryException, IOException {
+        File directory = new File(path);
+        if (!directory.isDirectory()) {
+            throw new NotExistingDirectoryException();
+        }
+
+        ArrayList<File> zipFiles = new ArrayList<>();
+        File[] filesInDirectory = directory.listFiles();
+        if (filesInDirectory == null) {
+            return;
+        }
+
+        for (File file : filesInDirectory) {
+            if (isZipFile(file)) {
+                zipFiles.add(file);
+            }
+        }
+
+        for (File zipFile : zipFiles) {
+            unzipMatchedFiles(zipFile.getAbsolutePath(), path, regexp);
+        }
+    }
+
+    /**
+     * Unzips files with names satisfying regular expression from specified archive.
+     *
+     * @param zipFile for files to extract
+     * @param path    to archive
+     * @param regexp  to satisfy
+     */
+    private static void unzipMatchedFiles(String zipFile, String path, String regexp) throws IOException {
+        try (ZipInputStream zipInputStream = new ZipInputStream(new FileInputStream(zipFile))) {
+            ZipEntry zipEntry = zipInputStream.getNextEntry();
+
+            while (zipEntry != null) {
+                String fileNameToExtract = zipEntry.getName();
+
+                if (fileNameToExtract.matches(regexp) && !zipEntry.isDirectory()) {
+                    File fileToExtract = new File(path + File.separator + fileNameToExtract);
+                    new File(fileToExtract.getParent()).mkdirs();
+                    extract(fileToExtract, zipInputStream);
+                }
+
+                zipEntry = zipInputStream.getNextEntry();
+            }
+        }
+    }
+
+    /**
+     * Extracts a zip entry.
+     *
+     * @param fileToExtract  extracting file
+     * @param zipInputStream zip stream to extract from
+     */
+    private static void extract(final File fileToExtract, final ZipInputStream zipInputStream) throws IOException {
+        try (FileOutputStream fileOutputStream = new FileOutputStream(fileToExtract)) {
+            byte[] buffer = new byte[1024];
+            int readBytes;
+
+            while ((readBytes = zipInputStream.read(buffer)) > 0) {
+                fileOutputStream.write(buffer, 0, readBytes);
+            }
+        }
+    }
+
+    /**
+     * Determines whether a file is a zip file.
+     *
+     * @param file to check
+     * @return true if file is a zip file, and false otherwise
+     */
+    private static boolean isZipFile(final File file) throws IOException {
+        if (file.isDirectory()) {
+            return false;
+        }
+
+        try (RandomAccessFile randomAccessFile = new RandomAccessFile(file, "r")) {
+            long n = randomAccessFile.readInt();
+            return n == 0x504B0304;
+        }
+    }
+
+}

src/test/java/ru/spbau/mit/kazakov/ZipFile/RegexpUnzipTest.java

@@ -0,0 +1,90 @@
+package ru.spbau.mit.kazakov.ZipFile;
+
+import org.apache.commons.io.FileUtils;
+import org.junit.Before;
+import org.junit.Test;
+
+import java.io.File;
+import java.io.IOException;
+import java.util.ArrayList;
+import java.util.Collection;
+
+import static org.junit.Assert.*;
+
+public class RegexpUnzipTest {
+    private final static String ABSOLUTE_PATH_TO_RESOURCES
+            = new File("src" + File.separator + "test" + File.separator + "resources").getAbsolutePath();
+    @Before
+    public void clearTestingFolder() throws IOException {
+        File testingFolder = new File(ABSOLUTE_PATH_TO_RESOURCES + File.separator + "testing folder");
+        FileUtils.cleanDirectory(testingFolder);
+
+        File testingFiles = new File(ABSOLUTE_PATH_TO_RESOURCES + File.separator + "testing files");
+        FileUtils.copyDirectory(testingFiles, testingFolder);
+    }
+
+    private ArrayList<String> getTestingFolderFileNames() {
+        ArrayList<String> fileNamesInTestingFolder = new ArrayList<>();
+        File testingFolder = new File(ABSOLUTE_PATH_TO_RESOURCES + File.separator + "testing folder");
+
+        Collection<File> filesInTestingFolder = FileUtils.listFiles(testingFolder, null, true);
+        for (File file : filesInTestingFolder) {
+            fileNamesInTestingFolder.add(file.getName());
+        }
+
+        return fileNamesInTestingFolder;
+    }
+
+    @Test(expected = NotExistingDirectoryException.class)
+    public void testUnzipMatchedFilesInPathNotExistingFileThrowsNotExistingDirectoryException() throws Exception {
+        String wrongDirectory = ABSOLUTE_PATH_TO_RESOURCES + File.separator + "testing folder" + File.separator + "not existing file";
+        RegexpUnzip.unzipMatchedFilesInPath(wrongDirectory, ".*");
+    }
+
+    @Test(expected = NotExistingDirectoryException.class)
+    public void testUnzipMatchedFilesInPathNotDirectoryThrowsNotExistingDirectoryException() throws Exception {
+        String wrongDirectory = ABSOLUTE_PATH_TO_RESOURCES + File.separator + "testing folder" + File.separator + "Some archive.zip";
+        RegexpUnzip.unzipMatchedFilesInPath(wrongDirectory, ".*");
+    }
+
+    @Test
+    public void testUnzipMatchedFilesInPathNoMatchings() throws Exception {
+        RegexpUnzip.unzipMatchedFilesInPath(ABSOLUTE_PATH_TO_RESOURCES + File.separator + "testing folder", "");
+        ArrayList<String> fileNamesInTestingFolder = getTestingFolderFileNames();
+        assertEquals(5, fileNamesInTestingFolder.size());
+    }
+
+    @Test
+    public void testUnzipMatchedFilesInPathOneArchiveMatchings() throws Exception {
+        RegexpUnzip.unzipMatchedFilesInPath(ABSOLUTE_PATH_TO_RESOURCES + File.separator + "testing folder", ".*file.*");
+        ArrayList<String> fileNamesInTestingFolder = getTestingFolderFileNames();
+        assertEquals(8, fileNamesInTestingFolder.size());
+        assertTrue(fileNamesInTestingFolder.contains("Some file.txt"));
+        assertTrue(fileNamesInTestingFolder.contains("Another file"));
+        assertTrue(fileNamesInTestingFolder.contains("Some file in a directory.txt"));
+    }
+
+    @Test
+    public void testUnzipMatchedFilesInPathBothArchiveMatchings() throws Exception {
+        RegexpUnzip.unzipMatchedFilesInPath(ABSOLUTE_PATH_TO_RESOURCES + File.separator + "testing folder", ".*txt.*");
+        ArrayList<String> fileNamesInTestingFolder = getTestingFolderFileNames();
+        assertEquals(9, fileNamesInTestingFolder.size());
+        assertTrue(fileNamesInTestingFolder.contains("Some file.txt"));
+        assertTrue(fileNamesInTestingFolder.contains("Regular.txt"));
+        assertTrue(fileNamesInTestingFolder.contains("Some file in a directory.txt"));
+        assertTrue(fileNamesInTestingFolder.contains("It isn't a folder.txt"));
+    }
+
+    @Test
+    public void testUnzipMatchedFilesInPathAllMatchings() throws Exception {
+        RegexpUnzip.unzipMatchedFilesInPath(ABSOLUTE_PATH_TO_RESOURCES + File.separator + "testing folder", ".*");
+        ArrayList<String> fileNamesInTestingFolder = getTestingFolderFileNames();
+        assertEquals(11, fileNamesInTestingFolder.size());
+        assertTrue(fileNamesInTestingFolder.contains("Some file.txt"));
+        assertTrue(fileNamesInTestingFolder.contains("Another file"));
+        assertTrue(fileNamesInTestingFolder.contains("Regular.txt"));
+        assertTrue(fileNamesInTestingFolder.contains("Some file in a directory.txt"));
+        assertTrue(fileNamesInTestingFolder.contains("It isn't a folder.txt"));
+        assertTrue(fileNamesInTestingFolder.contains("Unknown"));
+    }
+}

src/test/resources/testing files/Not an archive/Some file not inside an archive.txt

@@ -0,0 +1 @@
+Nothing

src/test/resources/testing files/This file isn't an archive

@@ -0,0 +1 @@
+Go away