You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@pdfbox.apache.org by ti...@apache.org on 2016/01/05 08:42:04 UTC
svn commit: r1723009 - in
/pdfbox/trunk/pdfbox/src/main/java/org/apache/pdfbox:
pdmodel/graphics/image/ util/filetypedetector/
Author: tilman
Date: Tue Jan 5 07:42:03 2016
New Revision: 1723009
URL: http://svn.apache.org/viewvc?rev=1723009&view=rev
Log:
PDFBOX-3163: added creating PDImageXObject by content as suggested by Benjamin Gamard and Maciej Wo?niak, with Apache 2 licensed content detection code from Drew Noakes
Added:
pdfbox/trunk/pdfbox/src/main/java/org/apache/pdfbox/util/filetypedetector/
pdfbox/trunk/pdfbox/src/main/java/org/apache/pdfbox/util/filetypedetector/ByteTrie.java (with props)
pdfbox/trunk/pdfbox/src/main/java/org/apache/pdfbox/util/filetypedetector/FileType.java (with props)
pdfbox/trunk/pdfbox/src/main/java/org/apache/pdfbox/util/filetypedetector/FileTypeDetector.java (with props)
Modified:
pdfbox/trunk/pdfbox/src/main/java/org/apache/pdfbox/pdmodel/graphics/image/PDImageXObject.java
Modified: pdfbox/trunk/pdfbox/src/main/java/org/apache/pdfbox/pdmodel/graphics/image/PDImageXObject.java
URL: http://svn.apache.org/viewvc/pdfbox/trunk/pdfbox/src/main/java/org/apache/pdfbox/pdmodel/graphics/image/PDImageXObject.java?rev=1723009&r1=1723008&r2=1723009&view=diff
==============================================================================
--- pdfbox/trunk/pdfbox/src/main/java/org/apache/pdfbox/pdmodel/graphics/image/PDImageXObject.java (original)
+++ pdfbox/trunk/pdfbox/src/main/java/org/apache/pdfbox/pdmodel/graphics/image/PDImageXObject.java Tue Jan 5 07:42:03 2016
@@ -21,6 +21,7 @@ import java.awt.Paint;
import java.awt.RenderingHints;
import java.awt.image.BufferedImage;
import java.awt.image.WritableRaster;
+import java.io.BufferedInputStream;
import java.io.File;
import java.io.FileInputStream;
import java.io.IOException;
@@ -44,6 +45,8 @@ import org.apache.pdfbox.pdmodel.common.
import org.apache.pdfbox.pdmodel.graphics.PDXObject;
import org.apache.pdfbox.pdmodel.graphics.color.PDColorSpace;
import org.apache.pdfbox.pdmodel.graphics.color.PDDeviceGray;
+import org.apache.pdfbox.util.filetypedetector.FileType;
+import org.apache.pdfbox.util.filetypedetector.FileTypeDetector;
/**
* An Image XObject.
@@ -145,7 +148,7 @@ public final class PDImageXObject extend
}
/**
- * Create a PDImageXObject from an image file, see {@link #createFromFile(File, PDDocument)} for
+ * Create a PDImageXObject from an image file, see {@link #createFromFileByExtension(File, PDDocument)} for
* more details.
*
* @param imagePath the image file path.
@@ -156,7 +159,7 @@ public final class PDImageXObject extend
*/
public static PDImageXObject createFromFile(String imagePath, PDDocument doc) throws IOException
{
- return createFromFile(new File(imagePath), doc);
+ return createFromFileByExtension(new File(imagePath), doc);
}
/**
@@ -174,13 +177,13 @@ public final class PDImageXObject extend
* PDImageXObject.
* @throws IllegalArgumentException if the image type is not supported.
*/
- public static PDImageXObject createFromFile(File file, PDDocument doc) throws IOException
+ public static PDImageXObject createFromFileByExtension(File file, PDDocument doc) throws IOException
{
String name = file.getName();
int dot = file.getName().lastIndexOf('.');
if (dot == -1)
{
- throw new IOException("Image type not supported: " + name);
+ throw new IllegalArgumentException("Image type not supported: " + name);
}
String ext = name.substring(dot + 1).toLowerCase();
if ("jpg".equals(ext) || "jpeg".equals(ext))
@@ -196,7 +199,63 @@ public final class PDImageXObject extend
BufferedImage bim = ImageIO.read(file);
return LosslessFactory.createFromImage(doc, bim);
}
- throw new IOException("Image type not supported: " + name);
+ throw new IllegalArgumentException("Image type not supported: " + name);
+ }
+
+ /**
+ * Create a PDImageXObject from an image file. The file format is determined by the file
+ * content. The following file types are supported: jpg, jpeg, tif, tiff, gif, bmp and png. This
+ * is a convenience method that calls {@link JPEGFactory#createFromStream},
+ * {@link CCITTFactory#createFromFile} or {@link ImageIO#read} combined with
+ * {@link LosslessFactory#createFromImage}. (The later can also be used to create a
+ * PDImageXObject from a BufferedImage).
+ *
+ * @param file the image file.
+ * @param doc the document that shall use this PDImageXObject.
+ * @return a PDImageXObject.
+ * @throws IOException if there is an error when reading the file or creating the
+ * PDImageXObject.
+ * @throws IllegalArgumentException if the image type is not supported.
+ */
+ public static PDImageXObject createFromFileByContent(File file, PDDocument doc) throws IOException
+ {
+ FileInputStream fileInputStream = null;
+ BufferedInputStream bufferedInputStream = null;
+ FileType fileType = null;
+ try
+ {
+ fileInputStream = new FileInputStream(file);
+ bufferedInputStream = new BufferedInputStream(fileInputStream);
+ fileType = FileTypeDetector.detectFileType(bufferedInputStream);
+ }
+ catch (IOException e)
+ {
+ throw new IOException("Could not determine file type: " + file.getName(), e);
+ }
+ finally
+ {
+ IOUtils.closeQuietly(fileInputStream);
+ IOUtils.closeQuietly(bufferedInputStream);
+ }
+ if (fileType == null)
+ {
+ throw new IllegalArgumentException("Image type not supported: " + file.getName());
+ }
+
+ if (fileType.equals(FileType.JPEG))
+ {
+ return JPEGFactory.createFromStream(doc, new FileInputStream(file));
+ }
+ if (fileType.equals(FileType.TIFF))
+ {
+ return CCITTFactory.createFromFile(doc, file);
+ }
+ if (fileType.equals(FileType.BMP) || fileType.equals(FileType.GIF) || fileType.equals(FileType.PNG))
+ {
+ BufferedImage bim = ImageIO.read(file);
+ return LosslessFactory.createFromImage(doc, bim);
+ }
+ throw new IllegalArgumentException("Image type not supported: " + file.getName());
}
// repairs parameters using decode result
Added: pdfbox/trunk/pdfbox/src/main/java/org/apache/pdfbox/util/filetypedetector/ByteTrie.java
URL: http://svn.apache.org/viewvc/pdfbox/trunk/pdfbox/src/main/java/org/apache/pdfbox/util/filetypedetector/ByteTrie.java?rev=1723009&view=auto
==============================================================================
--- pdfbox/trunk/pdfbox/src/main/java/org/apache/pdfbox/util/filetypedetector/ByteTrie.java (added)
+++ pdfbox/trunk/pdfbox/src/main/java/org/apache/pdfbox/util/filetypedetector/ByteTrie.java Tue Jan 5 07:42:03 2016
@@ -0,0 +1,134 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one or more
+ * contributor license agreements. See the NOTICE file distributed with
+ * this work for additional information regarding copyright ownership.
+ * The ASF licenses this file to You under the Apache License, Version 2.0
+ * (the "License"); you may not use this file except in compliance with
+ * the License. You may obtain a copy of the License at
+ *
+ * http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+package org.apache.pdfbox.util.filetypedetector;
+
+import java.util.HashMap;
+import java.util.Map;
+
+/**
+ * @author Drew Noakes
+ *
+ * code taken from https://github.com/drewnoakes/metadata-extractor
+ *
+ * 2016-01-04
+ *
+ * latest commit number 73f1a48
+ *
+ * Stores values using a prefix tree (aka 'trie', i.e. reTRIEval data structure).
+ *
+ * @param <T> the type of value to store for byte sequences
+ */
+class ByteTrie<T>
+{
+ /**
+ * A node in the trie. Has children and may have an associated value.
+ */
+ static class ByteTrieNode<T>
+ {
+ private final Map<Byte, ByteTrieNode<T>> children = new HashMap<Byte, ByteTrieNode<T>>();
+ private T value = null;
+
+ public void setValue(T value)
+ {
+ if (this.value != null)
+ {
+ throw new IllegalStateException("Value already set for this trie node");
+ }
+ this.value = value;
+ }
+
+ public T getValue()
+ {
+ return value;
+ }
+ }
+
+ private final ByteTrieNode<T> root = new ByteTrieNode<T>();
+ private int maxDepth;
+
+ /**
+ * Return the most specific value stored for this byte sequence. If not found, returns
+ * <code>null</code> or a default values as specified by calling
+ * {@link ByteTrie#setDefaultValue}.
+ * @param bytes
+ * @return
+ */
+ public T find(byte[] bytes)
+ {
+ ByteTrieNode<T> node = root;
+ T val = node.getValue();
+ for (byte b : bytes)
+ {
+ ByteTrieNode<T> child = node.children.get(b);
+ if (child == null)
+ {
+ break;
+ }
+ node = child;
+ if (node.getValue() != null)
+ {
+ val = node.getValue();
+ }
+ }
+ return val;
+ }
+
+ /**
+ * Store the given value at the specified path.
+ * @param value
+ * @param parts
+ */
+ public void addPath(T value, byte[]... parts)
+ {
+ int depth = 0;
+ ByteTrieNode<T> node = root;
+ for (byte[] part : parts)
+ {
+ for (byte b : part)
+ {
+ ByteTrieNode<T> child = node.children.get(b);
+ if (child == null)
+ {
+ child = new ByteTrieNode<T>();
+ node.children.put(b, child);
+ }
+ node = child;
+ depth++;
+ }
+ }
+ node.setValue(value);
+ maxDepth = Math.max(maxDepth, depth);
+ }
+
+ /**
+ * Sets the default value to use in {@link ByteTrie#find(byte[])} when no path matches.
+ * @param defaultValue
+ */
+ public void setDefaultValue(T defaultValue)
+ {
+ root.setValue(defaultValue);
+ }
+
+ /**
+ * Gets the maximum depth stored in this trie.
+ * @return
+ */
+ public int getMaxDepth()
+ {
+ return maxDepth;
+ }
+}
Propchange: pdfbox/trunk/pdfbox/src/main/java/org/apache/pdfbox/util/filetypedetector/ByteTrie.java
------------------------------------------------------------------------------
svn:eol-style = native
Added: pdfbox/trunk/pdfbox/src/main/java/org/apache/pdfbox/util/filetypedetector/FileType.java
URL: http://svn.apache.org/viewvc/pdfbox/trunk/pdfbox/src/main/java/org/apache/pdfbox/util/filetypedetector/FileType.java?rev=1723009&view=auto
==============================================================================
--- pdfbox/trunk/pdfbox/src/main/java/org/apache/pdfbox/util/filetypedetector/FileType.java (added)
+++ pdfbox/trunk/pdfbox/src/main/java/org/apache/pdfbox/util/filetypedetector/FileType.java Tue Jan 5 07:42:03 2016
@@ -0,0 +1,57 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one or more
+ * contributor license agreements. See the NOTICE file distributed with
+ * this work for additional information regarding copyright ownership.
+ * The ASF licenses this file to You under the Apache License, Version 2.0
+ * (the "License"); you may not use this file except in compliance with
+ * the License. You may obtain a copy of the License at
+ *
+ * http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+package org.apache.pdfbox.util.filetypedetector;
+
+/**
+ * @author Drew Noakes
+ *
+ * code taken from https://github.com/drewnoakes/metadata-extractor
+ *
+ * 2016-01-04
+ *
+ * latest commit number 73f1a48
+ *
+ * Enumeration of supported image file formats.
+ */
+public enum FileType
+{
+ UNKNOWN,
+ JPEG,
+ TIFF,
+ PSD,
+ PNG,
+ BMP,
+ GIF,
+ ICO,
+ PCX,
+ RIFF,
+
+ /** Sony camera raw. */
+ ARW,
+ /** Canon camera raw, version 1. */
+ CRW,
+ /** Canon camera raw, version 2. */
+ CR2,
+ /** Nikon camera raw. */
+ NEF,
+ /** Olympus camera raw. */
+ ORF,
+ /** FujiFilm camera raw. */
+ RAF,
+ /** Panasonic camera raw. */
+ RW2
+}
\ No newline at end of file
Propchange: pdfbox/trunk/pdfbox/src/main/java/org/apache/pdfbox/util/filetypedetector/FileType.java
------------------------------------------------------------------------------
svn:eol-style = native
Added: pdfbox/trunk/pdfbox/src/main/java/org/apache/pdfbox/util/filetypedetector/FileTypeDetector.java
URL: http://svn.apache.org/viewvc/pdfbox/trunk/pdfbox/src/main/java/org/apache/pdfbox/util/filetypedetector/FileTypeDetector.java?rev=1723009&view=auto
==============================================================================
--- pdfbox/trunk/pdfbox/src/main/java/org/apache/pdfbox/util/filetypedetector/FileTypeDetector.java (added)
+++ pdfbox/trunk/pdfbox/src/main/java/org/apache/pdfbox/util/filetypedetector/FileTypeDetector.java Tue Jan 5 07:42:03 2016
@@ -0,0 +1,110 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one or more
+ * contributor license agreements. See the NOTICE file distributed with
+ * this work for additional information regarding copyright ownership.
+ * The ASF licenses this file to You under the Apache License, Version 2.0
+ * (the "License"); you may not use this file except in compliance with
+ * the License. You may obtain a copy of the License at
+ *
+ * http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+package org.apache.pdfbox.util.filetypedetector;
+
+import java.io.BufferedInputStream;
+import java.io.IOException;
+
+/**
+ * @author Drew Noakes
+ *
+ * code taken from https://github.com/drewnoakes/metadata-extractor
+ *
+ * 2016-01-04
+ *
+ * latest commit number 73f1a48
+ *
+ * Examines the a file's first bytes and estimates the file's type.
+ */
+public class FileTypeDetector
+{
+ private final static ByteTrie<FileType> root;
+
+ static
+ {
+ root = new ByteTrie<FileType>();
+ root.setDefaultValue(FileType.UNKNOWN);
+
+ // https://en.wikipedia.org/wiki/List_of_file_signatures
+
+ root.addPath(FileType.JPEG, new byte[]{(byte)0xff, (byte)0xd8});
+ root.addPath(FileType.TIFF, "II".getBytes(), new byte[]{0x2a, 0x00});
+ root.addPath(FileType.TIFF, "MM".getBytes(), new byte[]{0x00, 0x2a});
+ root.addPath(FileType.PSD, "8BPS".getBytes());
+ root.addPath(FileType.PNG, new byte[]{(byte)0x89, 0x50, 0x4E, 0x47, 0x0D, 0x0A, 0x1A, 0x0A, 0x00, 0x00, 0x00, 0x0D, 0x49, 0x48, 0x44, 0x52});
+ // TODO technically there are other very rare magic numbers for OS/2 BMP files...
+ root.addPath(FileType.BMP, "BM".getBytes());
+ root.addPath(FileType.GIF, "GIF87a".getBytes());
+ root.addPath(FileType.GIF, "GIF89a".getBytes());
+ root.addPath(FileType.ICO, new byte[]{0x00, 0x00, 0x01, 0x00});
+ // multiple PCX versions, explicitly listed
+ root.addPath(FileType.PCX, new byte[]{0x0A, 0x00, 0x01});
+ root.addPath(FileType.PCX, new byte[]{0x0A, 0x02, 0x01});
+ root.addPath(FileType.PCX, new byte[]{0x0A, 0x03, 0x01});
+ root.addPath(FileType.PCX, new byte[]{0x0A, 0x05, 0x01});
+ root.addPath(FileType.RIFF, "RIFF".getBytes());
+
+ root.addPath(FileType.ARW, "II".getBytes(), new byte[]{0x2a, 0x00, 0x08, 0x00});
+ root.addPath(FileType.CRW, "II".getBytes(), new byte[]{0x1a, 0x00, 0x00, 0x00}, "HEAPCCDR".getBytes());
+ root.addPath(FileType.CR2, "II".getBytes(), new byte[]{0x2a, 0x00, 0x10, 0x00, 0x00, 0x00, 0x43, 0x52});
+ root.addPath(FileType.NEF, "MM".getBytes(), new byte[]{0x00, 0x2a, 0x00, 0x00, 0x00, (byte)0x80, 0x00});
+ root.addPath(FileType.ORF, "IIRO".getBytes(), new byte[]{(byte)0x08, 0x00});
+ root.addPath(FileType.ORF, "IIRS".getBytes(), new byte[]{(byte)0x08, 0x00});
+ root.addPath(FileType.RAF, "FUJIFILMCCD-RAW".getBytes());
+ root.addPath(FileType.RW2, "II".getBytes(), new byte[]{0x55, 0x00});
+ }
+
+ private FileTypeDetector() throws Exception
+ {
+ throw new Exception("Not intended for instantiation");
+ }
+
+ /**
+ * Examines the a file's first bytes and estimates the file's type.
+ * <p>
+ * Requires a {@link BufferedInputStream} in order to mark and reset the stream to the position
+ * at which it was provided to this method once completed.
+ * <p>
+ * Requires the stream to contain at least eight bytes.
+ *
+ * @throws IOException if an IO error occurred or the input stream ended unexpectedly.
+ */
+ public static FileType detectFileType(final BufferedInputStream inputStream) throws IOException
+ {
+ if (!inputStream.markSupported())
+ {
+ throw new IOException("Stream must support mark/reset");
+ }
+
+ int maxByteCount = root.getMaxDepth();
+
+ inputStream.mark(maxByteCount);
+
+ byte[] bytes = new byte[maxByteCount];
+ int bytesRead = inputStream.read(bytes);
+
+ if (bytesRead == -1)
+ {
+ throw new IOException("Stream ended before file's magic number could be determined.");
+ }
+
+ inputStream.reset();
+
+ //noinspection ConstantConditions
+ return root.find(bytes);
+ }
+}
Propchange: pdfbox/trunk/pdfbox/src/main/java/org/apache/pdfbox/util/filetypedetector/FileTypeDetector.java
------------------------------------------------------------------------------
svn:eol-style = native