The following document contains the results of RAT (Release Audit Tool).
*****************************************************
Summary
-------
Notes: 4
Binaries: 13
Archives: 1
Standards: 118
Apache Licensed: 108
Generated Documents: 0
JavaDocs are generated and so license header is optional
Generated files do not required license headers
10 Unknown Licenses
*******************************
Archives (+ indicates readable, $ unreadable):
+ src/test/resources/test-documents/test-documents.zip
*****************************************************
Files with AL headers will be marked L
Binary files (which do not require AL headers) will be marked B
Compressed archives will be marked A
Notices, licenses etc will be marked N
!????? .checkstyle
!????? .externalToolBuilders/Maven_Ant_Builder.launch
!????? CHANGES.txt
AL HEADER.txt
N KEYS
N LICENSE.txt
!????? maven-eclipse.xml
N NOTICE.txt
AL pom.xml
N README.txt
AL src/main/assembly/standalone.xml
AL src/main/java/org/apache/tika/cli/TikaCLI.java
AL src/main/java/org/apache/tika/config/TikaConfig.java
AL src/main/java/org/apache/tika/exception/TikaException.java
AL src/main/java/org/apache/tika/gui/ParsingTransferHandler.java
AL src/main/java/org/apache/tika/gui/TikaGUI.java
AL src/main/java/org/apache/tika/metadata/CreativeCommons.java
AL src/main/java/org/apache/tika/metadata/DublinCore.java
AL src/main/java/org/apache/tika/metadata/HttpHeaders.java
AL src/main/java/org/apache/tika/metadata/Metadata.java
AL src/main/java/org/apache/tika/metadata/MSOffice.java
AL src/main/java/org/apache/tika/metadata/package.html
AL src/main/java/org/apache/tika/metadata/SpellCheckedMetadata.java
AL src/main/java/org/apache/tika/metadata/TikaMetadataKeys.java
AL src/main/java/org/apache/tika/metadata/TikaMimeKeys.java
AL src/main/java/org/apache/tika/mime/Clause.java
AL src/main/java/org/apache/tika/mime/HexCoDec.java
AL src/main/java/org/apache/tika/mime/Magic.java
AL src/main/java/org/apache/tika/mime/MagicClause.java
AL src/main/java/org/apache/tika/mime/MagicMatch.java
AL src/main/java/org/apache/tika/mime/MediaType.java
AL src/main/java/org/apache/tika/mime/MediaTypeRegistry.java
AL src/main/java/org/apache/tika/mime/MimeType.java
AL src/main/java/org/apache/tika/mime/MimeTypeException.java
AL src/main/java/org/apache/tika/mime/MimeTypes.java
AL src/main/java/org/apache/tika/mime/MimeTypesFactory.java
AL src/main/java/org/apache/tika/mime/MimeTypesReader.java
AL src/main/java/org/apache/tika/mime/Operator.java
AL src/main/java/org/apache/tika/mime/Patterns.java
AL src/main/java/org/apache/tika/parser/AbstractParser.java
AL src/main/java/org/apache/tika/parser/AutoDetectParser.java
AL src/main/java/org/apache/tika/parser/CompositeParser.java
AL src/main/java/org/apache/tika/parser/EmptyParser.java
AL src/main/java/org/apache/tika/parser/ErrorParser.java
AL src/main/java/org/apache/tika/parser/html/HtmlParser.java
!????? src/main/java/org/apache/tika/parser/image/ImageParser.java
AL src/main/java/org/apache/tika/parser/microsoft/Cell.java
AL src/main/java/org/apache/tika/parser/microsoft/CellDecorator.java
AL src/main/java/org/apache/tika/parser/microsoft/ExcelExtractor.java
AL src/main/java/org/apache/tika/parser/microsoft/LinkedCell.java
AL src/main/java/org/apache/tika/parser/microsoft/NumberCell.java
AL src/main/java/org/apache/tika/parser/microsoft/OfficeParser.java
AL src/main/java/org/apache/tika/parser/microsoft/TextCell.java
AL src/main/java/org/apache/tika/parser/opendocument/OpenOfficeContentParser.java
AL src/main/java/org/apache/tika/parser/opendocument/OpenOfficeMetaParser.java
AL src/main/java/org/apache/tika/parser/opendocument/OpenOfficeParser.java
AL src/main/java/org/apache/tika/parser/Parser.java
AL src/main/java/org/apache/tika/parser/ParserDecorator.java
AL src/main/java/org/apache/tika/parser/ParserPostProcessor.java
AL src/main/java/org/apache/tika/parser/ParsingReader.java
AL src/main/java/org/apache/tika/parser/pdf/PDF2XHTML.java
AL src/main/java/org/apache/tika/parser/pdf/PDFParser.java
AL src/main/java/org/apache/tika/parser/rtf/RTFParser.java
AL src/main/java/org/apache/tika/parser/txt/TXTParser.java
AL src/main/java/org/apache/tika/parser/xml/DcXMLParser.java
AL src/main/java/org/apache/tika/parser/xml/MetadataHandler.java
AL src/main/java/org/apache/tika/parser/xml/XMLParser.java
AL src/main/java/org/apache/tika/sax/BodyContentHandler.java
AL src/main/java/org/apache/tika/sax/ContentHandlerDecorator.java
AL src/main/java/org/apache/tika/sax/TeeContentHandler.java
AL src/main/java/org/apache/tika/sax/TextContentHandler.java
AL src/main/java/org/apache/tika/sax/WriteOutContentHandler.java
AL src/main/java/org/apache/tika/sax/XHTMLContentHandler.java
AL src/main/java/org/apache/tika/sax/xpath/AttributeMatcher.java
AL src/main/java/org/apache/tika/sax/xpath/ChildMatcher.java
AL src/main/java/org/apache/tika/sax/xpath/CompositeMatcher.java
AL src/main/java/org/apache/tika/sax/xpath/ElementMatcher.java
AL src/main/java/org/apache/tika/sax/xpath/Matcher.java
AL src/main/java/org/apache/tika/sax/xpath/MatchingContentHandler.java
AL src/main/java/org/apache/tika/sax/xpath/NamedAttributeMatcher.java
AL src/main/java/org/apache/tika/sax/xpath/NamedElementMatcher.java
AL src/main/java/org/apache/tika/sax/xpath/NodeMatcher.java
AL src/main/java/org/apache/tika/sax/xpath/SubtreeMatcher.java
AL src/main/java/org/apache/tika/sax/xpath/TextMatcher.java
AL src/main/java/org/apache/tika/sax/xpath/XPathParser.java
AL src/main/java/org/apache/tika/utils/ParseUtils.java
AL src/main/java/org/apache/tika/utils/RegexUtils.java
AL src/main/java/org/apache/tika/utils/RereadableInputStream.java
AL src/main/java/org/apache/tika/utils/StringUtil.java
AL src/main/java/org/apache/tika/utils/Utils.java
AL src/main/resources/mime/tika-mimetypes.xml
AL src/main/resources/tika-config.xml
AL src/site/apt/download.apt
AL src/site/apt/index.apt
B src/site/resources/tika.png
B src/site/resources/tika.xcf
AL src/site/site.xml
AL src/test/java/org/apache/tika/metadata/TestMetadata.java
AL src/test/java/org/apache/tika/metadata/TestSpellCheckedMetadata.java
AL src/test/java/org/apache/tika/mime/MediaTypeTest.java
AL src/test/java/org/apache/tika/mime/MimeTypesTest.java
AL src/test/java/org/apache/tika/mime/MimeTypeTest.java
AL src/test/java/org/apache/tika/mime/PatternsTest.java
AL src/test/java/org/apache/tika/mime/TestMimeTypes.java
AL src/test/java/org/apache/tika/parser/AutoDetectParserTest.java
AL src/test/java/org/apache/tika/parser/html/HtmlParserTest.java
AL src/test/java/org/apache/tika/parser/image/ImageParserTest.java
AL src/test/java/org/apache/tika/parser/microsoft/ExcelParserTest.java
AL src/test/java/org/apache/tika/parser/microsoft/PowerPointParserTest.java
AL src/test/java/org/apache/tika/parser/microsoft/WordParserTest.java
AL src/test/java/org/apache/tika/parser/opendocument/OpenOfficeParserTest.java
AL src/test/java/org/apache/tika/parser/ParsingReaderTest.java
AL src/test/java/org/apache/tika/parser/txt/TXTParserTest.java
AL src/test/java/org/apache/tika/parser/xml/DcXMLParserTest.java
AL src/test/java/org/apache/tika/sax/xpath/XPathParserTest.java
AL src/test/java/org/apache/tika/TestParsers.java
AL src/test/java/org/apache/tika/TestRereadableInputStream.java
AL src/test/java/org/apache/tika/utils/RegexUtilsTest.java
AL src/test/resources/log4j.properties
A src/test/resources/test-documents/test-documents.zip
B src/test/resources/test-documents/testBMP.bmp
B src/test/resources/test-documents/testEXCEL-formats.xls
B src/test/resources/test-documents/testEXCEL.xls
B src/test/resources/test-documents/testGIF.gif
!????? src/test/resources/test-documents/testHTML.html
!????? src/test/resources/test-documents/testHTML_utf8.html
B src/test/resources/test-documents/testJPEG.jpg
B src/test/resources/test-documents/testOpenOffice2.odt
B src/test/resources/test-documents/testPDF.pdf
B src/test/resources/test-documents/testPNG.png
B src/test/resources/test-documents/testPPT.ppt
!????? src/test/resources/test-documents/testRTF.rtf
B src/test/resources/test-documents/testTIFF.tif
!????? src/test/resources/test-documents/testTXT.txt
B src/test/resources/test-documents/testWORD.doc
!????? src/test/resources/test-documents/testXML.xml
*****************************************************
Printing headers for files without AL header...
=======================================================================
==.checkstyle
=======================================================================
<?xml version="1.0" encoding="UTF-8"?>
<fileset-config file-format-version="1.2.0" simple-config="true">
<fileset name="all" enabled="true" check-config-name="Sun Checks" local="false">
<file-match-pattern match-pattern="." include-pattern="true"/>
</fileset>
</fileset-config>
=======================================================================
==.externalToolBuilders/Maven_Ant_Builder.launch
=======================================================================
<launchConfiguration type="org.eclipse.ant.AntBuilderLaunchConfigurationType">
<booleanAttribute key="org.eclipse.debug.ui.ATTR_LAUNCH_IN_BACKGROUND" value="false"/>
<stringAttribute key="org.eclipse.ui.externaltools.ATTR_RUN_BUILD_KINDS" value="full,incremental,auto,clean"/>
<booleanAttribute key="org.eclipse.ui.externaltools.ATTR_TRIGGERS_CONFIGURED" value="true"/>
<booleanAttribute key="org.eclipse.debug.core.appendEnvironmentVariables" value="true"/>
<stringAttribute key="org.eclipse.jdt.launching.PROJECT_ATTR" value="tika"/>
<booleanAttribute key="org.eclipse.jdt.launching.DEFAULT_CLASSPATH" value="true"/>
<stringAttribute key="org.eclipse.ui.externaltools.ATTR_LOCATION" value="${build_project}/maven-eclipse.xml"/>
<stringAttribute key="org.eclipse.ui.externaltools.ATTR_WORKING_DIRECTORY" value="${build_project}"/>
<stringAttribute key="org.eclipse.debug.core.ATTR_REFRESH_SCOPE" value="${project}"/>
<booleanAttribute key="org.eclipse.debug.core.capture_output" value="false"/>
<stringAttribute key="org.eclipse.ui.externaltools.ATTR_BUILD_SCOPE" value="${working_set:<?xml version='1.0'?><launchConfigurationWorkingSet editPageId='org.eclipse.ui.resourceWorkingSetPage' factoryID='org.eclipse.ui.internal.WorkingSetFactory' label='workingSet' name='workingSet'><item factoryID='org.eclipse.ui.internal.model.ResourceFactory' path='tika' type='4'/></launchConfigurationWorkingSet>}"/>
<stringAttribute key="process_factory_id" value="org.eclipse.ant.ui.remoteAntProcessFactory"/>
<booleanAttribute key="org.eclipse.ant.ui.DEFAULT_VM_INSTALL" value="false"/>
<booleanAttribute key="org.eclipse.debug.ui.ATTR_CONSOLE_OUTPUT_ON" value="false"/>
<booleanAttribute key="org.eclipse.ant.ui.ATTR_TARGETS_UPDATED" value="true"/>
<stringAttribute key="org.eclipse.jdt.launching.CLASSPATH_PROVIDER" value="org.eclipse.ant.ui.AntClasspathProvider"/>
<listAttribute key="org.eclipse.debug.core.MAPPED_RESOURCE_TYPES">
<listEntry value="1"/>
</listAttribute>
<listAttribute key="org.eclipse.debug.core.MAPPED_RESOURCE_PATHS">
<listEntry value="/tika/maven-eclipse.xml"/>
</listAttribute>
</launchConfiguration>
=======================================================================
==CHANGES.txt
=======================================================================
Tika Change Log
Unreleased changes (0.2-incubating)
1. TIKA-109 - WordParser fails on some Word files (Dave Meikle)
2. TIKA-105 - Excel parser implementation based on POI's Event API
(Niall Pemberton)
3. TIKA-116 - Streaming parser for OpenDocument files (Jukka Zitting)
4. TIKA-117 - Drop JDOM and Jaxen dependencies (Jukka Zitting)
5. TIKA-115 - Tika package with all the dependencies (Jukka Zitting)
6. TIKA-97 - Tika GUI (Jukka Zitting)
7. TIKA-96 - Tika CLI (Jukka Zitting)
8. TIKA-112 - Use Commons IO 1.4 (Jukka Zitting)
9. TIKA-126 - Add Parser.parse(InputStream, Metadata) for metadata extraction
(Jukka Zitting)
10. TIKA-127 - Add support for Visio files (Jukka Zitting)
11. TIKA-129 - node() support for the streaming XPath utility (Jukka Zitting)
12. TIKA-130 - self-or-descendant axis does not match self in streaming XPath
(Jukka Zitting)
13. TIKA-131 - Lazy XHTML prefix generation (Jukka Zitting)
14. TIKA-128 - HTML parser should produce XHTML SAX events (Jukka Zitting)
15. TIKA-133 - TeeContentHandler constructor should use varargs (Jukka Zitting)
16. TIKA-132 - Refactor Excel extractor to parse per sheet and add
hyperlink support (Niall Pemberton)
17. TIKA-134 - mvn package does not produce packages for bin/src
(Karl Heinz Marbaise)
18. TIKA-138 - Ignore HTML style and script content (Jukka Zitting)
19. TIKA-113 - Metadata (such as title) should not be part of content
(Jukka Zitting)
20. TIKA-139 - Add a composite parser (Jukka Zitting)
=======================================================================
==maven-eclipse.xml
=======================================================================
<project default="copy-resources">
<target name="init"/>
<target name="copy-resources" depends="init">
<copy todir="target/classes/META-INF" filtering="false">
<fileset dir="." includes="README.txt|NOTICE.txt|LICENSE.txt"/>
</copy>
<copy todir="target/classes/org/apache/tika" filtering="false">
<fileset dir="src/main/resources"/>
</copy>
</target>
</project>
=======================================================================
==src/main/java/org/apache/tika/parser/image/ImageParser.java
=======================================================================
package org.apache.tika.parser.image;
import java.io.IOException;
import java.io.InputStream;
import java.util.Iterator;
import javax.imageio.ImageIO;
import javax.imageio.ImageReader;
import org.apache.commons.io.input.CloseShieldInputStream;
import org.apache.tika.exception.TikaException;
import org.apache.tika.metadata.Metadata;
import org.apache.tika.parser.Parser;
import org.apache.tika.sax.XHTMLContentHandler;
import org.xml.sax.ContentHandler;
import org.xml.sax.SAXException;
public class ImageParser implements Parser {
public void parse(InputStream stream, Metadata metadata)
throws IOException, TikaException {
String type = metadata.get(Metadata.CONTENT_TYPE);
if (type != null) {
Iterator<ImageReader> iterator =
ImageIO.getImageReadersByMIMEType(type);
if (iterator.hasNext()) {
ImageReader reader = iterator.next();
reader.setInput(ImageIO.createImageInputStream(
new CloseShieldInputStream(stream)));
metadata.set("height", Integer.toString(reader.getHeight(0)));
metadata.set("width", Integer.toString(reader.getWidth(0)));
reader.dispose();
}
}
}
public void parse(
InputStream stream, ContentHandler handler, Metadata metadata)
throws IOException, SAXException, TikaException {
parse(stream, metadata);
XHTMLContentHandler xhtml = new XHTMLContentHandler(handler, metadata);
xhtml.startDocument();
xhtml.endDocument();
}
}
=======================================================================
==src/test/resources/test-documents/testHTML.html
=======================================================================
<html>
<head>
<title>Title : Test Indexation Html</title>
</head>
<body>
<h1>Test Indexation Html</h1>
<p><a href="http://www.apache.org/">Indexation</a> du fichier</p>
</body>
</html>
=======================================================================
==src/test/resources/test-documents/testHTML_utf8.html
=======================================================================
<html>
<head>
<title>Title : Tilte with UTF-8 chars öäå</title>
</head>
<body>
<h1>Content with UTF-8 chars</h1>
<p>åäö</p>
</body>
</html>
=======================================================================
==src/test/resources/test-documents/testRTF.rtf
=======================================================================
{\rtf1\ansi\ansicpg1252\uc1\deff0\stshfdbch0\stshfloch0\stshfhich0\stshfbi0\deflang1036\deflangfe1036{\fonttbl{\f0\froman\fcharset0\fprq2{\*\panose 02020603050405020304}Times New Roman;}{\f37\froman\fcharset238\fprq2 Times New Roman CE;}
{\f38\froman\fcharset204\fprq2 Times New Roman Cyr;}{\f40\froman\fcharset161\fprq2 Times New Roman Greek;}{\f41\froman\fcharset162\fprq2 Times New Roman Tur;}{\f42\froman\fcharset177\fprq2 Times New Roman (Hebrew);}
{\f43\froman\fcharset178\fprq2 Times New Roman (Arabic);}{\f44\froman\fcharset186\fprq2 Times New Roman Baltic;}{\f45\froman\fcharset163\fprq2 Times New Roman (Vietnamese);}}{\colortbl;\red0\green0\blue0;\red0\green0\blue255;\red0\green255\blue255;
\red0\green255\blue0;\red255\green0\blue255;\red255\green0\blue0;\red255\green255\blue0;\red255\green255\blue255;\red0\green0\blue128;\red0\green128\blue128;\red0\green128\blue0;\red128\green0\blue128;\red128\green0\blue0;\red128\green128\blue0;
\red128\green128\blue128;\red192\green192\blue192;}{\stylesheet{\ql \li0\ri0\widctlpar\aspalpha\aspnum\faauto\adjustright\rin0\lin0\itap0 \fs24\lang1036\langfe1036\cgrid\langnp1036\langfenp1036 \snext0 Normal;}{\*\cs10 \additive \ssemihidden
Default Paragraph Font;}{\*\ts11\tsrowd\trftsWidthB3\trpaddl108\trpaddr108\trpaddfl3\trpaddft3\trpaddfb3\trpaddfr3\trcbpat1\trcfpat1\tscellwidthfts0\tsvertalt\tsbrdrt\tsbrdrl\tsbrdrb\tsbrdrr\tsbrdrdgl\tsbrdrdgr\tsbrdrh\tsbrdrv
\ql \li0\ri0\widctlpar\aspalpha\aspnum\faauto\adjustright\rin0\lin0\itap0 \fs20\lang1024\langfe1024\cgrid\langnp1024\langfenp1024 \snext11 \ssemihidden Normal Table;}}{\*\latentstyles\lsdstimax156\lsdlockeddef0}{\*\rsidtbl \rsid2954171\rsid10375891}
{\*\generator Microsoft Word 11.0.6568;}{\info{\title Test d\'92indexation Word}{\author Bibliotheque}{\operator Bibliotheque}{\creatim\yr2006\mo5\dy18\hr12\min19}{\revtim\yr2006\mo5\dy18\hr12\min19}{\version2}{\edmins0}{\nofpages1}{\nofwords3}
{\nofchars21}{\*\company Universite Laval}{\nofcharsws23}{\vern24579}}\paperw11906\paperh16838\margl1417\margr1417\margt1417\margb1417
\deftab708\widowctrl\ftnbj\aenddoc\hyphhotz425\noxlattoyen\expshrtn\noultrlspc\dntblnsbdb\nospaceforul\formshade\horzdoc\dgmargin\dghspace180\dgvspace180\dghorigin1417\dgvorigin1417\dghshow1\dgvshow1
\jexpand\viewkind1\viewscale100\pgbrdrhead\pgbrdrfoot\splytwnine\ftnlytwnine\htmautsp\nolnhtadjtbl\useltbaln\alntblind\lytcalctblwd\lyttblrtgr\lnbrkrule\nobrkwrptbl\snaptogridincell\allowfieldendsel\wrppunct\asianbrkrule\nojkernpunct\rsidroot2954171 \fet0
\sectd \linex0\headery708\footery708\colsx708\endnhere\sectlinegrid360\sectdefaultcl\sftnbj {\*\pnseclvl1\pnucrm\pnstart1\pnindent720\pnhang {\pntxta .}}{\*\pnseclvl2\pnucltr\pnstart1\pnindent720\pnhang {\pntxta .}}{\*\pnseclvl3
\pndec\pnstart1\pnindent720\pnhang {\pntxta .}}{\*\pnseclvl4\pnlcltr\pnstart1\pnindent720\pnhang {\pntxta )}}{\*\pnseclvl5\pndec\pnstart1\pnindent720\pnhang {\pntxtb (}{\pntxta )}}{\*\pnseclvl6\pnlcltr\pnstart1\pnindent720\pnhang {\pntxtb (}{\pntxta )}}
{\*\pnseclvl7\pnlcrm\pnstart1\pnindent720\pnhang {\pntxtb (}{\pntxta )}}{\*\pnseclvl8\pnlcltr\pnstart1\pnindent720\pnhang {\pntxtb (}{\pntxta )}}{\*\pnseclvl9\pnlcrm\pnstart1\pnindent720\pnhang {\pntxtb (}{\pntxta )}}\pard\plain
\ql \li0\ri0\widctlpar\aspalpha\aspnum\faauto\adjustright\rin0\lin0\itap0 \fs24\lang1036\langfe1036\cgrid\langnp1036\langfenp1036 {\insrsid2954171 Test d\rquote indexation Word
\par
\par }}
=======================================================================
==src/test/resources/test-documents/testTXT.txt
=======================================================================
Test d'indexation de Txt
http://www.apache.org
=======================================================================
==src/test/resources/test-documents/testXML.xml
=======================================================================
<?xml version="1.0" encoding="UTF-8"?>
<oaidc:dc xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:oaidc="http://www.openarchives.org/OAI/2.0/oai_dc/">
<dc:title>Tika test document</dc:title>
<dc:creator>Rida Benjelloun</dc:creator>
<dc:subject>Java</dc:subject>
<dc:subject>XML</dc:subject>
<dc:subject>XSLT</dc:subject>
<dc:subject>JDOM</dc:subject>
<dc:subject>Indexation</dc:subject>
<dc:description>Framework d'indexation des documents XML, HTML, PDF etc.. </dc:description>
<dc:identifier>http://www.apache.org</dc:identifier>
<dc:date>2000-12</dc:date>
<dc:type>test</dc:type>
<dc:format>application/msword</dc:format>
<dc:language>Fr</dc:language>
<dc:rights>Archimède et Lius à Châteauneuf testing chars en été</dc:rights>
</oaidc:dc>