Index: tika-parsers/src/test/java/org/apache/tika/parser/swf/SWFParserTest.java =================================================================== --- tika-parsers/src/test/java/org/apache/tika/parser/swf/SWFParserTest.java (revision 0) +++ tika-parsers/src/test/java/org/apache/tika/parser/swf/SWFParserTest.java (revision 0) @@ -0,0 +1,63 @@ +/* + * 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.tika.parser.swf; + +import java.io.InputStream; + +import junit.framework.TestCase; + +import org.apache.tika.metadata.Metadata; +import org.apache.tika.parser.AutoDetectParser; +import org.apache.tika.parser.ParseContext; +import org.apache.tika.parser.Parser; +import org.apache.tika.sax.BodyContentHandler; +import org.xml.sax.ContentHandler; + +/** + * Test case for parsing swf files. + */ +public class SWFParserTest extends TestCase { + + public void testSWFParsing() throws Exception { + Parser parser = new AutoDetectParser(); // Should auto-detect! + ContentHandler handler = new BodyContentHandler(); + Metadata metadata = new Metadata(); + + InputStream stream = SWFParserTest.class + .getResourceAsStream("/test-documents/test.swf"); + try { + parser.parse(stream, handler, metadata,new ParseContext()); + } finally { + stream.close(); + } + + String content = handler.toString(); + assertTrue(content.contains("Mix.")); + assertTrue(content.contains("Edit.")); + assertTrue(content.contains("Master.")); + assertTrue(content.contains("Compose.")); + assertTrue(content.contains("Animate.")); + assertTrue(content.contains("With a single suite of powerful tools")); + assertTrue(content.contains("that work together as one.")); + assertTrue(content.contains("World-class video and audio tools that bring")); + assertTrue(content + .contains("new power and efficiency to your film, video,")); + assertTrue(content.contains("DVD, and web workflows.")); + assertTrue(content.contains("Learn more.")); + } + +} Index: tika-parsers/src/test/resources/test-documents/test.swf =================================================================== Cannot display: file marked as a binary type. svn:mime-type = application/octet-stream Property changes on: tika-parsers/src/test/resources/test-documents/test.swf ___________________________________________________________________ Added: svn:mime-type + application/octet-stream Index: tika-parsers/src/main/java/org/apache/tika/parser/swf/ExtractText.java =================================================================== --- tika-parsers/src/main/java/org/apache/tika/parser/swf/ExtractText.java (revision 0) +++ tika-parsers/src/main/java/org/apache/tika/parser/swf/ExtractText.java (revision 0) @@ -0,0 +1,147 @@ +package org.apache.tika.parser.swf; + +import java.io.IOException; +import java.util.HashMap; + +import com.anotherbigidea.flash.interfaces.SWFText; +import com.anotherbigidea.flash.interfaces.SWFVectors; +import com.anotherbigidea.flash.structs.AlphaColor; +import com.anotherbigidea.flash.structs.Color; +import com.anotherbigidea.flash.structs.Matrix; +import com.anotherbigidea.flash.structs.Rect; +import com.anotherbigidea.flash.writers.SWFTagTypesImpl; + +/** + * Taken from http://www.anotherbigidea.com/javaswf/samples/ExtractText.java + * + * Shows how to parse a Flash movie and extract all the text in Text symbols and + * the initial text in Edit Fields. Output is to System.out. + * + * A "pipeline" is set up in the main method: + * + * SWFReader-->TagParser-->ExtractText + * + * SWFReader reads the input SWF file and separates out the header and the tags. + * The separated contents are passed to TagParser which parses out the + * individual tag types and passes them to ExtractText. + * + * ExtractText extends SWFTagTypesImpl and overrides some methods. + */ +public class ExtractText extends SWFTagTypesImpl { + /** + * Store font info keyed by the font symbol id Each entry is an int[] of + * character codes for the corresponding font glyphs (An empty array denotes a + * System Font) + */ + protected HashMap fontCodes = new HashMap(); + + private StringBuffer textBuffer = new StringBuffer(); + + public ExtractText() { + super(null); + } + + public String getText() { + return textBuffer.toString(); + } + + /** + * SWFTagTypes interface Save the Text Font character code info + */ + public void tagDefineFontInfo(int fontId, String fontName, int flags, + int[] codes) throws IOException { + fontCodes.put(new Integer(fontId), codes); + } + + /** + * SWFTagTypes interface Save the character code info + */ + public SWFVectors tagDefineFont2(int id, int flags, String name, + int numGlyphs, int ascent, int descent, int leading, int[] codes, + int[] advances, Rect[] bounds, int[] kernCodes1, int[] kernCodes2, + int[] kernAdjustments) throws IOException { + fontCodes.put(new Integer(id), (codes != null) ? codes : new int[0]); + + return null; + } + + /** + * SWFTagTypes interface Dump any initial text in the field + */ + public void tagDefineTextField(int fieldId, String fieldName, + String initialText, Rect boundary, int flags, AlphaColor textColor, + int alignment, int fontId, int fontSize, int charLimit, int leftMargin, + int rightMargin, int indentation, int lineSpacing) throws IOException { + if (initialText != null) { + textBuffer.append(initialText); + } + } + + /** + * SWFTagTypes interface + */ + public SWFText tagDefineText(int id, Rect bounds, Matrix matrix) + throws IOException { + return new TextDumper(textBuffer); + } + + /** + * SWFTagTypes interface + */ + public SWFText tagDefineText2(int id, Rect bounds, Matrix matrix) + throws IOException { + return new TextDumper(textBuffer); + } + + public class TextDumper implements SWFText { + protected Integer fontId; + protected boolean firstY = true; + private StringBuffer buffer; + + TextDumper(StringBuffer buff) { + buffer = buff; + } + + public void font(int fontId, int textHeight) { + this.fontId = new Integer(fontId); + } + + public void setY(int y) { + if (firstY) firstY = false; + else buffer.append("\n"); // Change in Y - dump a new line + } + + public void text(int[] glyphIndices, int[] glyphAdvances) { + int[] codes = (int[]) fontCodes.get(fontId); + if (codes == null) { + // System.out.println("\n**** COULD NOT FIND FONT INFO FOR TEXT ****\n"); + return; + } + + // --Translate the glyph indices to character codes + char[] chars = new char[glyphIndices.length]; + + for (int i = 0; i < chars.length; i++) { + int index = glyphIndices[i]; + + if (index >= codes.length) // System Font ? + { + chars[i] = (char) index; + } else { + chars[i] = (char) (codes[index]); + } + } + + buffer.append(chars); + } + + public void color(Color color) {} + + public void setX(int x) {} + + public void done() { + buffer.append("\n"); + } + } + +} Index: tika-parsers/src/main/java/org/apache/tika/parser/swf/SWFParser.java =================================================================== --- tika-parsers/src/main/java/org/apache/tika/parser/swf/SWFParser.java (revision 0) +++ tika-parsers/src/main/java/org/apache/tika/parser/swf/SWFParser.java (revision 0) @@ -0,0 +1,80 @@ +/** + * 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.tika.parser.swf; + +import java.io.IOException; +import java.io.InputStream; + +import org.apache.tika.exception.TikaException; +import org.apache.tika.metadata.Metadata; +import org.apache.tika.parser.ParseContext; +import org.apache.tika.parser.Parser; +import org.apache.tika.sax.XHTMLContentHandler; +import org.xml.sax.ContentHandler; +import org.xml.sax.SAXException; + +import com.anotherbigidea.flash.readers.SWFReader; +import com.anotherbigidea.flash.readers.TagParser; +import com.anotherbigidea.io.InStream; + +/** + * Parser for Flash SWF files. Based on JavaSWF and similar to A. Bialecki's + * implementation for Nutch except that we do not handle text from the actions + * or structured URLS. URLs can be obtained from the text extracted using + * ParserPostProcessor + * + * @author Julien Nioche + */ +public class SWFParser implements Parser { + + /** + * @deprecated This method will be removed in Apache Tika 1.0. + */ + public void parse(InputStream stream, ContentHandler handler, + Metadata metadata) throws IOException, SAXException, TikaException { + parse(stream, handler, metadata, new ParseContext()); + } + + public void parse(InputStream stream, ContentHandler handler, + Metadata metadata, ParseContext context) throws IOException, + SAXException, TikaException { + try { + ExtractText extractor = new ExtractText(); + + // TagParser implements SWFTags and drives a SWFTagTypes interface + TagParser parser = new TagParser(extractor); + + // SWFReader reads an input file and drives a SWFTags interface + SWFReader reader = new SWFReader(parser, new InStream(stream)); + + // read the input SWF file and pass it through the interface pipeline + reader.readFile(); + String text = extractor.getText(); + // we leave the extraction of links from the text to the + // ParserPostProcessor + + XHTMLContentHandler xhtml = new XHTMLContentHandler(handler, metadata); + xhtml.startDocument(); + xhtml.element("p", extractor.getText()); + xhtml.endDocument(); + } catch (Exception e) { + throw new TikaException("Error parsing an SWF document", e); + } + } + +} Index: tika-parsers/pom.xml =================================================================== --- tika-parsers/pom.xml (revision 884183) +++ tika-parsers/pom.xml (working copy) @@ -119,8 +119,11 @@ metadata-extractor 2.4.0-beta-1 - - + + com.anotherbigidea + javaswf + CVS-SNAPSHOT-1 + Index: tika-core/src/main/resources/org/apache/tika/tika-config.xml =================================================================== --- tika-core/src/main/resources/org/apache/tika/tika-config.xml (revision 884183) +++ tika-core/src/main/resources/org/apache/tika/tika-config.xml (working copy) @@ -171,6 +171,10 @@ application/epub+zip + + application/x-shockwave-flash + + - \ No newline at end of file +