Index: src/main/java/org/apache/tika/config/Content.java =================================================================== --- src/main/java/org/apache/tika/config/Content.java (revision 582664) +++ src/main/java/org/apache/tika/config/Content.java (working copy) @@ -19,11 +19,13 @@ import org.jdom.Element; /** - * Content object, used to configure and store data populated from XPATH, Regex, - * Document fulltext, document metadata etc. + * Content object, used to configure the metadata to be extracted using + * XPath, Regex, and other means. */ public class Content { + private final String name; + private final String textSelect; private final String xPathSelect; @@ -30,11 +32,10 @@ private final String regexSelect; - private String value; - - private String[] values; - - public Content(String xPathSelect, String textSelect, String regexSelect) { + public Content( + String name, + String xPathSelect, String textSelect, String regexSelect) { + this.name = name; this.xPathSelect = xPathSelect; this.textSelect = textSelect; this.regexSelect = regexSelect; @@ -41,6 +42,7 @@ } public Content(Element element) { + name = element.getAttributeValue("name"); xPathSelect = element.getAttributeValue("xpathSelect"); textSelect = element.getAttributeValue("textSelect"); regexSelect = element.getChildTextTrim("regexSelect"); @@ -46,6 +48,10 @@ regexSelect = element.getChildTextTrim("regexSelect"); } + public String getName() { + return name; + } + public String getRegexSelect() { return regexSelect; } @@ -58,20 +64,4 @@ return xPathSelect; } - public String getValue() { - return value; - } - - public void setValue(String value) { - this.value = value; - } - - public String[] getValues() { - return values; - } - - public void setValues(String[] values) { - this.values = values; - } - } Index: src/main/java/org/apache/tika/config/ParserConfig.java =================================================================== --- src/main/java/org/apache/tika/config/ParserConfig.java (revision 582664) +++ src/main/java/org/apache/tika/config/ParserConfig.java (working copy) @@ -16,9 +16,9 @@ */ package org.apache.tika.config; +import java.util.ArrayList; +import java.util.Collection; import java.util.Collections; -import java.util.HashMap; -import java.util.Map; import org.jdom.Element; @@ -33,8 +33,7 @@ private final String nameSpace; - private final Map contents = - new HashMap(); + private final Collection contents = new ArrayList(); public ParserConfig(Element element) { name = element.getAttributeValue("name"); @@ -43,8 +42,7 @@ Element extract = element.getChild("extract"); if (extract != null) { for (Object child : extract.getChildren()) { - String name = ((Element) child).getAttributeValue("name"); - contents.put(name, new Content((Element) child)); + contents.add(new Content((Element) child)); } } } @@ -61,8 +59,8 @@ return parserClass; } - public Map getContents() { - return Collections.unmodifiableMap(contents); + public Collection getContents() { + return Collections.unmodifiableCollection(contents); } } Index: src/main/java/org/apache/tika/parser/Parser.java =================================================================== --- src/main/java/org/apache/tika/parser/Parser.java (revision 582664) +++ src/main/java/org/apache/tika/parser/Parser.java (working copy) @@ -21,6 +21,7 @@ import org.apache.tika.config.Content; import org.apache.tika.exception.TikaException; +import org.apache.tika.metadata.Metadata; /** * Tika parser interface @@ -36,7 +37,8 @@ * The responsibility to close the stream remains on the caller. * * @param stream the document to be parsed - * @param contents set of metadata information to extract + * @param contents configuration of metadata information to extract + * @param metadata document metadata * @return full text content of the document * @throws IOException if the document could not be read * @throws TikaException if the document could not be parsed @@ -41,7 +43,8 @@ * @throws IOException if the document could not be read * @throws TikaException if the document could not be parsed */ - String parse(InputStream stream, Iterable contents) + String parse( + InputStream stream, Iterable contents, Metadata metadata) throws IOException, TikaException; } Index: src/main/java/org/apache/tika/parser/ParserDecorator.java =================================================================== --- src/main/java/org/apache/tika/parser/ParserDecorator.java (revision 582664) +++ src/main/java/org/apache/tika/parser/ParserDecorator.java (working copy) @@ -21,6 +21,7 @@ import org.apache.tika.config.Content; import org.apache.tika.exception.TikaException; +import org.apache.tika.metadata.Metadata; /** * Decorator base class for the {@link Parser} interface. This class @@ -49,9 +50,10 @@ * override this method (and use super.parse() to invoke * the decorated parser) to implement extra decoration. */ - public String parse(InputStream stream, Iterable contents) + public String parse( + InputStream stream, Iterable contents, Metadata metadata) throws IOException, TikaException { - return parser.parse(stream, contents); + return parser.parse(stream, contents, metadata); } } Index: src/main/java/org/apache/tika/parser/ParserPostProcessor.java =================================================================== --- src/main/java/org/apache/tika/parser/ParserPostProcessor.java (revision 582664) +++ src/main/java/org/apache/tika/parser/ParserPostProcessor.java (working copy) @@ -24,6 +24,7 @@ import org.apache.oro.text.regex.MalformedPatternException; import org.apache.tika.config.Content; import org.apache.tika.exception.TikaException; +import org.apache.tika.metadata.Metadata; import org.apache.tika.utils.RegexUtils; /** @@ -54,18 +55,19 @@ * Forwards the call to the delegated parser and post-processes the * results as described above. */ - public String parse(InputStream stream, Iterable contents) + public String parse( + InputStream stream, Iterable contents, Metadata metadata) throws IOException, TikaException { try { - String contentStr = super.parse(stream, contents); + String contentStr = super.parse(stream, contents, metadata); for (Content content : contents) { if ("fulltext".equalsIgnoreCase(content.getTextSelect())) { - content.setValue(contentStr); + metadata.set(content.getName(), contentStr); } else if ("summary".equalsIgnoreCase(content.getTextSelect())) { int length = Math.min(contentStr.length(), 500); String summary = contentStr.substring(0, length); - content.setValue(summary); + metadata.set(content.getName(), summary); } else if (content.getRegexSelect() != null) { String regex = content.getRegexSelect(); try { @@ -71,10 +73,8 @@ try { List values = RegexUtils.extract(contentStr, regex); - if (values.size() > 0) { - content.setValue(values.get(0)); - content.setValues( - values.toArray(new String[values.size()])); + for (String value : values) { + metadata.add(content.getName(), value); } } catch (MalformedPatternException e) { logger.error( Index: src/main/java/org/apache/tika/parser/html/HtmlParser.java =================================================================== --- src/main/java/org/apache/tika/parser/html/HtmlParser.java (revision 582664) +++ src/main/java/org/apache/tika/parser/html/HtmlParser.java (working copy) @@ -22,6 +22,7 @@ import org.apache.log4j.Logger; import org.apache.tika.config.Content; import org.apache.tika.exception.TikaException; +import org.apache.tika.metadata.Metadata; import org.apache.tika.parser.Parser; import org.w3c.dom.Element; import org.w3c.dom.Node; @@ -37,7 +38,8 @@ static Logger logger = Logger.getRootLogger(); - public String parse(InputStream stream, Iterable contents) + public String parse( + InputStream stream, Iterable contents, Metadata metadata) throws IOException, TikaException { Tidy tidy = new Tidy(); tidy.setQuiet(true); @@ -47,7 +49,7 @@ String text = content.getTextSelect(); if (text != null && !text.equalsIgnoreCase("fulltext") && !text.equalsIgnoreCase("summary")) { - extractElementTxt((Element) root, content); + extractElementTxt((Element) root, content, metadata); } } return getTextContent(root); @@ -53,7 +55,8 @@ return getTextContent(root); } - private void extractElementTxt(Element root, Content content) { + private void extractElementTxt( + Element root, Content content, Metadata metadata) { NodeList children = root.getElementsByTagName(content.getTextSelect()); if (children != null) { if (children.getLength() > 0) { @@ -61,11 +64,9 @@ Element node = (Element) children.item(0); Text txt = (Text) node.getFirstChild(); if (txt != null) { - content.setValue(txt.getData()); - + metadata.set(content.getName(), txt.getData()); } } else { - String[] values = new String[100]; for (int i = 0; i < children.getLength(); i++) { Element node = (Element) children.item(i); Text txt = (Text) node.getFirstChild(); @@ -70,13 +71,9 @@ Element node = (Element) children.item(i); Text txt = (Text) node.getFirstChild(); if (txt != null) { - values[i] = txt.getData(); + metadata.add(content.getName(), txt.getData()); } } - if (values.length > 0) { - content.setValue(values[0]); - content.setValues(values); - } } } } Index: src/main/java/org/apache/tika/parser/msexcel/MsExcelParser.java =================================================================== --- src/main/java/org/apache/tika/parser/msexcel/MsExcelParser.java (revision 582664) +++ src/main/java/org/apache/tika/parser/msexcel/MsExcelParser.java (working copy) @@ -21,6 +21,7 @@ import org.apache.tika.config.Content; import org.apache.tika.exception.TikaException; +import org.apache.tika.metadata.Metadata; import org.apache.tika.parser.Parser; import org.apache.tika.utils.MSExtractor; @@ -29,7 +30,8 @@ */ public class MsExcelParser implements Parser { - public String parse(InputStream stream, Iterable contents) + public String parse( + InputStream stream, Iterable contents, Metadata metadata) throws IOException, TikaException { try { MSExtractor extractor = new ExcelExtractor(); @@ -34,7 +36,7 @@ try { MSExtractor extractor = new ExcelExtractor(); extractor.setContents(contents); - extractor.extract(stream); + extractor.extract(stream, metadata); return extractor.getText(); } catch (IOException e) { throw e; Index: src/main/java/org/apache/tika/parser/mspowerpoint/MsPowerPointParser.java =================================================================== --- src/main/java/org/apache/tika/parser/mspowerpoint/MsPowerPointParser.java (revision 582664) +++ src/main/java/org/apache/tika/parser/mspowerpoint/MsPowerPointParser.java (working copy) @@ -21,6 +21,7 @@ import org.apache.tika.config.Content; import org.apache.tika.exception.TikaException; +import org.apache.tika.metadata.Metadata; import org.apache.tika.parser.Parser; import org.apache.tika.utils.MSExtractor; @@ -29,7 +30,8 @@ */ public class MsPowerPointParser implements Parser { - public String parse(InputStream stream, Iterable contents) + public String parse( + InputStream stream, Iterable contents, Metadata metadata) throws IOException, TikaException { try { MSExtractor extractor = new PPTExtractor(); @@ -34,7 +36,7 @@ try { MSExtractor extractor = new PPTExtractor(); extractor.setContents(contents); - extractor.extract(stream); + extractor.extract(stream, metadata); return extractor.getText(); } catch (IOException e) { throw e; Index: src/main/java/org/apache/tika/parser/msword/MsWordParser.java =================================================================== --- src/main/java/org/apache/tika/parser/msword/MsWordParser.java (revision 582664) +++ src/main/java/org/apache/tika/parser/msword/MsWordParser.java (working copy) @@ -21,6 +21,7 @@ import org.apache.tika.config.Content; import org.apache.tika.exception.TikaException; +import org.apache.tika.metadata.Metadata; import org.apache.tika.parser.Parser; import org.apache.tika.utils.MSExtractor; @@ -29,7 +30,8 @@ */ public class MsWordParser implements Parser { - public String parse(InputStream stream, Iterable contents) + public String parse( + InputStream stream, Iterable contents, Metadata metadata) throws IOException, TikaException { try { MSExtractor extractor = new WordExtractor(); @@ -34,7 +36,7 @@ try { MSExtractor extractor = new WordExtractor(); extractor.setContents(contents); - extractor.extract(stream); + extractor.extract(stream, metadata); return extractor.getText(); } catch (IOException e) { throw e; Index: src/main/java/org/apache/tika/parser/opendocument/OpenOfficeParser.java =================================================================== --- src/main/java/org/apache/tika/parser/opendocument/OpenOfficeParser.java (revision 582664) +++ src/main/java/org/apache/tika/parser/opendocument/OpenOfficeParser.java (working copy) @@ -29,6 +29,7 @@ import org.apache.tika.config.Content; import org.apache.tika.exception.TikaException; +import org.apache.tika.metadata.Metadata; import org.apache.tika.parser.Parser; import org.apache.tika.parser.xml.XMLParser; @@ -75,7 +76,8 @@ return xmlDoc; } - public String parse(InputStream stream, Iterable contents) + public String parse( + InputStream stream, Iterable contents, Metadata metadata) throws IOException, TikaException { Document xmlDoc = parse(stream); XMLParser xp = new XMLParser(); @@ -82,7 +84,7 @@ xp.getAllDocumentNs(xmlDoc); for (Content content : contents) { if (content.getXPathSelect() != null) { - xp.extractContent(xmlDoc, content); + xp.extractContent(xmlDoc, content, metadata); } } return xp.concatOccurrence(xmlDoc, "//*", " "); Index: src/main/java/org/apache/tika/parser/pdf/PDFParser.java =================================================================== --- src/main/java/org/apache/tika/parser/pdf/PDFParser.java (revision 582664) +++ src/main/java/org/apache/tika/parser/pdf/PDFParser.java (working copy) @@ -23,6 +23,7 @@ import org.apache.tika.config.Content; import org.apache.tika.exception.TikaException; +import org.apache.tika.metadata.Metadata; import org.apache.tika.parser.Parser; import org.pdfbox.pdmodel.PDDocument; @@ -34,7 +35,8 @@ */ public class PDFParser implements Parser { - public String parse(InputStream stream, Iterable contents) + public String parse( + InputStream stream, Iterable contents, Metadata metadata) throws IOException, TikaException { try { PDDocument pdfDocument = PDDocument.load(stream); @@ -48,23 +50,24 @@ for (Content content : contents) { String text = content.getTextSelect(); if ("title".equalsIgnoreCase(text)) { - content.setValue(metaData.getTitle()); + metadata.set(content.getName(), metaData.getTitle()); } else if ("author".equalsIgnoreCase(text)) { - content.setValue(metaData.getAuthor()); + metadata.set(content.getName(), metaData.getAuthor()); } else if ("creator".equalsIgnoreCase(text)) { - content.setValue(metaData.getCreator()); + metadata.set(content.getName(), metaData.getCreator()); } else if ("keywords".equalsIgnoreCase(text)) { - content.setValue(metaData.getKeywords()); + metadata.set(content.getName(), metaData.getKeywords()); } else if ("producer".equalsIgnoreCase(text)) { - content.setValue(metaData.getProducer()); + metadata.set(content.getName(), metaData.getProducer()); } else if ("subject".equalsIgnoreCase(text)) { - content.setValue(metaData.getSubject()); + metadata.set(content.getName(), metaData.getSubject()); } else if ("trapped".equalsIgnoreCase(text)) { - content.setValue(metaData.getTrapped()); + metadata.set(content.getName(), metaData.getTrapped()); } else if ("creationDate".equalsIgnoreCase(text)) { Calendar calendar = metaData.getCreationDate(); if (calendar != null) { - content.setValue(calendar.getTime().toString()); + metadata.set(content.getName(), + calendar.getTime().toString()); } } else if ("modificationDate".equalsIgnoreCase(text)) { Calendar calendar = metaData.getModificationDate(); @@ -69,7 +72,8 @@ } else if ("modificationDate".equalsIgnoreCase(text)) { Calendar calendar = metaData.getModificationDate(); if (calendar != null) { - content.setValue(calendar.getTime().toString()); + metadata.set(content.getName(), + calendar.getTime().toString()); } } } Index: src/main/java/org/apache/tika/parser/rtf/RTFParser.java =================================================================== --- src/main/java/org/apache/tika/parser/rtf/RTFParser.java (revision 582664) +++ src/main/java/org/apache/tika/parser/rtf/RTFParser.java (working copy) @@ -24,6 +24,7 @@ import org.apache.tika.config.Content; import org.apache.tika.exception.TikaException; +import org.apache.tika.metadata.Metadata; import org.apache.tika.parser.Parser; /** @@ -31,7 +32,8 @@ */ public class RTFParser implements Parser { - public String parse(InputStream stream, Iterable contents) + public String parse( + InputStream stream, Iterable contents, Metadata metadata) throws IOException, TikaException { try { DefaultStyledDocument sd = new DefaultStyledDocument(); Index: src/main/java/org/apache/tika/parser/txt/TXTParser.java =================================================================== --- src/main/java/org/apache/tika/parser/txt/TXTParser.java (revision 582664) +++ src/main/java/org/apache/tika/parser/txt/TXTParser.java (working copy) @@ -23,6 +23,7 @@ import org.apache.tika.config.Content; import org.apache.tika.exception.TikaException; +import org.apache.tika.metadata.Metadata; import org.apache.tika.parser.Parser; /** @@ -30,7 +31,8 @@ */ public class TXTParser implements Parser { - public String parse(InputStream stream, Iterable contents) + public String parse( + InputStream stream, Iterable contents, Metadata metadata) throws IOException, TikaException { StringBuilder sb = new StringBuilder(); BufferedReader br = new BufferedReader(new InputStreamReader(stream)); Index: src/main/java/org/apache/tika/parser/xml/XMLParser.java =================================================================== --- src/main/java/org/apache/tika/parser/xml/XMLParser.java (revision 582664) +++ src/main/java/org/apache/tika/parser/xml/XMLParser.java (working copy) @@ -24,6 +24,7 @@ import org.apache.tika.config.Content; import org.apache.tika.exception.TikaException; +import org.apache.tika.metadata.Metadata; import org.apache.tika.parser.Parser; import org.apache.tika.utils.Utils; @@ -60,7 +61,8 @@ this.namespace = namespace; } - public String parse(InputStream stream, Iterable contents) + public String parse( + InputStream stream, Iterable contents, Metadata metadata) throws IOException, TikaException { Document xmlDoc = Utils.parse(stream); if (exist(getAllDocumentNs(xmlDoc), getNamespace())) { @@ -66,7 +68,7 @@ if (exist(getAllDocumentNs(xmlDoc), getNamespace())) { for (Content content : contents) { if (content.getXPathSelect() != null) { - extractContent(xmlDoc, content); + extractContent(xmlDoc, content, metadata); } } } @@ -167,7 +169,8 @@ } } - public void extractContent(Document xmlDoc, Content content) { + public void extractContent( + Document xmlDoc, Content content, Metadata metadata) { try { JDOMXPath xp = new JDOMXPath(content.getXPathSelect()); xp.setNamespaceContext(nsc); @@ -173,8 +176,6 @@ xp.setNamespaceContext(nsc); List selectNodes = xp.selectNodes(xmlDoc); Iterator nodes = selectNodes.iterator(); - String[] values = new String[selectNodes.size()]; - int i = 0; while (nodes.hasNext()) { Object node = nodes.next(); if (node instanceof Element) { @@ -180,30 +181,24 @@ if (node instanceof Element) { Element elem = (Element) node; if (StringUtils.isNotBlank(elem.getText())) { - values[i] = elem.getText().trim(); + metadata.add(content.getName(), elem.getText().trim()); } } else if (node instanceof Attribute) { Attribute att = (Attribute) node; - values[i] = att.getValue(); + metadata.add(content.getName(), att.getValue()); } else if (node instanceof Text) { Text text = (Text) node; - values[i] = text.getText(); + metadata.add(content.getName(), text.getText()); } else if (node instanceof Comment) { Comment com = (Comment) node; - values[i] = com.getText(); + metadata.add(content.getName(), com.getText()); } else if (node instanceof ProcessingInstruction) { ProcessingInstruction pi = (ProcessingInstruction) node; - values[i] = pi.getData(); + metadata.add(content.getName(), pi.getData()); } else if (node instanceof EntityRef) { EntityRef er = (EntityRef) node; - values[i] = er.toString(); - + metadata.add(content.getName(), er.toString()); } - i++; - } - if (values.length > 0) { - content.setValue(values[0]); - content.setValues(values); } } catch (JaxenException e) { logger.error(e.getMessage()); Index: src/main/java/org/apache/tika/utils/MSExtractor.java =================================================================== --- src/main/java/org/apache/tika/utils/MSExtractor.java (revision 582664) +++ src/main/java/org/apache/tika/utils/MSExtractor.java (working copy) @@ -26,6 +26,7 @@ import org.apache.poi.poifs.eventfilesystem.POIFSReaderEvent; import org.apache.poi.poifs.eventfilesystem.POIFSReaderListener; import org.apache.tika.config.Content; +import org.apache.tika.metadata.Metadata; /** * Defines a Microsoft document content extractor. @@ -55,7 +56,7 @@ /** * Extracts properties and text from an MS Document input stream */ - public void extract(InputStream input) throws Exception { + public void extract(InputStream input, Metadata metadata) throws Exception { RereadableInputStream ris = new RereadableInputStream(input, MEMORY_THRESHOLD); try { @@ -62,7 +63,8 @@ // First, extract properties this.reader = new POIFSReader(); - this.reader.registerListener(new PropertiesReaderListener(), + this.reader.registerListener( + new PropertiesReaderListener(metadata), SummaryInformation.DEFAULT_STREAM_NAME); if (input.available() > 0) { @@ -94,6 +96,12 @@ private class PropertiesReaderListener implements POIFSReaderListener { + private final Metadata metadata; + + public PropertiesReaderListener(Metadata metadata) { + this.metadata = metadata; + } + public void processPOIFSReaderEvent(POIFSReaderEvent event) { if (!event.getName().startsWith( SummaryInformation.DEFAULT_STREAM_NAME)) { @@ -106,67 +114,67 @@ for (Content content : contents) { if (content.getTextSelect().equalsIgnoreCase("title")) { if (si.getTitle() != null) - content.setValue(si.getTitle()); + metadata.set(content.getName(), si.getTitle()); } else if (content.getTextSelect().equalsIgnoreCase( "author")) { if (si.getAuthor() != null) - content.setValue(si.getAuthor()); + metadata.set(content.getName(), si.getAuthor()); } else if (content.getTextSelect().equalsIgnoreCase( "keywords")) { if (si.getKeywords() != null) - content.setValue(si.getKeywords()); + metadata.set(content.getName(), si.getKeywords()); } else if (content.getTextSelect().equalsIgnoreCase( "subject")) { if (si.getSubject() != null) - content.setValue(si.getSubject()); + metadata.set(content.getName(), si.getSubject()); } else if (content.getTextSelect().equalsIgnoreCase( "lastauthor")) { if (si.getLastAuthor() != null) - content.setValue(si.getLastAuthor()); + metadata.set(content.getName(), si.getLastAuthor()); } else if (content.getTextSelect().equalsIgnoreCase( "comments")) { if (si.getComments() != null) - content.setValue(si.getComments()); + metadata.set(content.getName(), si.getComments()); } else if (content.getTextSelect().equalsIgnoreCase( "template")) { if (si.getTemplate() != null) - content.setValue(si.getTemplate()); + metadata.set(content.getName(), si.getTemplate()); } else if (content.getTextSelect().equalsIgnoreCase( "applicationname")) { if (si.getApplicationName() != null) - content.setValue(si.getApplicationName()); + metadata.set(content.getName(), si.getApplicationName()); } else if (content.getTextSelect().equalsIgnoreCase( "revnumber")) { if (si.getRevNumber() != null) - content.setValue(si.getRevNumber()); + metadata.set(content.getName(), si.getRevNumber()); } else if (content.getTextSelect().equalsIgnoreCase( "creationdate")) { if (si.getCreateDateTime() != null) - content.setValue(si.getCreateDateTime().toString()); + metadata.set(content.getName(), si.getCreateDateTime().toString()); } else if (content.getTextSelect().equalsIgnoreCase( "charcount")) { if (si.getCharCount() > 0) - content.setValue("" + si.getCharCount()); + metadata.set(content.getName(), "" + si.getCharCount()); } else if (content.getTextSelect().equals("edittime")) { if (si.getEditTime() > 0) - content.setValue("" + si.getEditTime()); + metadata.set(content.getName(), "" + si.getEditTime()); } else if (content.getTextSelect().equals( "lastsavedatetime")) { if (si.getLastSaveDateTime() != null) - content.setValue(si.getLastSaveDateTime() - .toString()); + metadata.set(content.getName(), + si.getLastSaveDateTime().toString()); } else if (content.getTextSelect().equals("pagecount")) { if (si.getPageCount() > 0) - content.setValue("" + si.getPageCount()); + metadata.set(content.getName(), "" + si.getPageCount()); } else if (content.getTextSelect().equals("security")) { if (si.getSecurity() > 0) - content.setValue("" + si.getSecurity()); + metadata.set(content.getName(), "" + si.getSecurity()); } else if (content.getTextSelect().equals("wordcount")) { if (si.getWordCount() > 0) - content.setValue("" + si.getWordCount()); + metadata.set(content.getName(), "" + si.getWordCount()); } else if (content.getTextSelect().equals("lastprinted")) { if (si.getLastPrinted() != null) - content.setValue(si.getLastPrinted().toString()); + metadata.set(content.getName(), si.getLastPrinted().toString()); } } Index: src/main/java/org/apache/tika/utils/ParseUtils.java =================================================================== --- src/main/java/org/apache/tika/utils/ParseUtils.java (revision 582664) +++ src/main/java/org/apache/tika/utils/ParseUtils.java (working copy) @@ -30,6 +30,7 @@ import org.apache.tika.config.ParserConfig; import org.apache.tika.config.TikaConfig; import org.apache.tika.exception.TikaException; +import org.apache.tika.metadata.Metadata; import org.apache.tika.metadata.TikaMimeKeys; import org.apache.tika.parser.Parser; import org.apache.tika.parser.ParserFactory; @@ -172,7 +173,7 @@ IOException { ParserConfig pc = config.getParserConfig(mimeType); Parser parser = ParserFactory.getParser(pc); - return parser.parse(inputStream, pc.getContents().values()); + return parser.parse(inputStream, pc.getContents(), new Metadata()); } /** Index: src/main/java/org/apache/tika/utils/Utils.java =================================================================== --- src/main/java/org/apache/tika/utils/Utils.java (revision 582664) +++ src/main/java/org/apache/tika/utils/Utils.java (working copy) @@ -24,13 +24,8 @@ import java.io.IOException; import java.io.InputStream; import java.io.OutputStream; -import java.io.OutputStreamWriter; -import java.io.PrintWriter; -import java.io.StringWriter; -import java.io.Writer; import java.util.ArrayList; import java.util.List; -import java.util.Map; import java.util.zip.ZipEntry; import java.util.zip.ZipInputStream; @@ -35,7 +30,6 @@ import java.util.zip.ZipInputStream; import org.apache.log4j.Logger; -import org.apache.tika.config.Content; import org.jdom.Document; import org.jdom.JDOMException; import org.jdom.input.SAXBuilder; @@ -52,40 +46,6 @@ static Logger logger = Logger.getRootLogger(); - public static String toString(Map structuredContent) { - final StringWriter sw = new StringWriter(); - print(structuredContent, sw); - return sw.toString(); - } - - public static void print(Map structuredContent) { - print(structuredContent, new OutputStreamWriter(System.out)); - } - - public static void print(Map structuredContent, - Writer outputWriter) { - final PrintWriter output = new PrintWriter(outputWriter, true); - for (Map.Entry entry : structuredContent.entrySet()) { - Content ct = entry.getValue(); - if (ct.getValue() != null) { - output.print(entry.getKey() + ": "); - output.println(ct.getValue()); - } else if (ct.getValues() != null) { - output.print(entry.getKey() + ": "); - for (int j = 0; j < ct.getValues().length; j++) { - if (j == 0) - output.println(ct.getValues()[j]); - else { - output.println("\t" + ct.getValues()[j]); - } - } - } else { // there are no values, but there is a Content object - System.out.println("Content '" + entry.getKey() - + "' has no values."); - } - } - } - public static Document parse(InputStream is) { org.jdom.Document xmlDoc = new org.jdom.Document(); try { Index: src/test/java/org/apache/tika/TestParsers.java =================================================================== --- src/test/java/org/apache/tika/TestParsers.java (revision 582664) +++ src/test/java/org/apache/tika/TestParsers.java (working copy) @@ -20,12 +20,11 @@ import java.io.FileInputStream; import java.io.IOException; import java.io.InputStream; +import java.util.Collection; import java.util.List; -import java.util.Map; import junit.framework.TestCase; -import org.apache.log4j.Logger; import org.apache.tika.config.Content; import org.apache.tika.config.ParserConfig; import org.apache.tika.config.TikaConfig; @@ -30,6 +29,7 @@ import org.apache.tika.config.ParserConfig; import org.apache.tika.config.TikaConfig; import org.apache.tika.log.TikaLogger; +import org.apache.tika.metadata.Metadata; import org.apache.tika.parser.Parser; import org.apache.tika.parser.ParserFactory; import org.apache.tika.utils.ParseUtils; @@ -117,16 +117,16 @@ ParserConfig config = tc .getParserConfig("application/vnd.ms-powerpoint"); Parser parser = ParserFactory.getParser(config); - Map contents = config.getContents(); + Collection contents = config.getContents(); assertNotNull(contents); + Metadata metadata = new Metadata(); InputStream stream = new FileInputStream(file); try { - parser.parse(stream, contents.values()); + parser.parse(stream, contents, metadata); } finally { stream.close(); } - assertEquals("Sample Powerpoint Slide", contents.get("title") - .getValue()); + assertEquals("Sample Powerpoint Slide", metadata.get(Metadata.TITLE)); } public void testWORDxtraction() throws Exception { @@ -136,15 +136,16 @@ assertEquals(s1, s2); ParserConfig config = tc.getParserConfig("application/msword"); Parser parser = ParserFactory.getParser(config); - Map contents = config.getContents(); + Collection contents = config.getContents(); assertNotNull(contents); + Metadata metadata = new Metadata();; InputStream stream = new FileInputStream(file); try { - parser.parse(stream, contents.values()); + parser.parse(stream, contents, metadata); } finally { stream.close(); } - assertEquals("Sample Word Document", contents.get("title").getValue()); + assertEquals("Sample Word Document", metadata.get(Metadata.TITLE)); } public void testEXCELExtraction() throws Exception { @@ -162,15 +163,16 @@ .contains(expected)); ParserConfig config = tc.getParserConfig("application/vnd.ms-excel"); Parser parser = ParserFactory.getParser(config); - Map contents = config.getContents(); + Collection contents = config.getContents(); assertNotNull(contents); + Metadata metadata = new Metadata();; InputStream stream = new FileInputStream(file); try { - parser.parse(stream, contents.values()); + parser.parse(stream, contents, metadata); } finally { stream.close(); } - assertEquals("Simple Excel document", contents.get("title").getValue()); + assertEquals("Simple Excel document", metadata.get(Metadata.TITLE)); } public void testOOExtraction() throws Exception { @@ -191,18 +193,18 @@ Parser parser = ParserFactory.getParser(config); assertNotNull(parser); - Map contents = config.getContents(); + Collection contents = config.getContents(); assertNotNull(contents); + Metadata metadata = new Metadata(); InputStream stream = new FileInputStream(file); try { - parser.parse(stream, contents.values()); + parser.parse(stream, contents, metadata); } finally { stream.close(); } - assertEquals("Title : Test Indexation Html", contents.get("title") - .getValue()); + assertEquals("Title : Test Indexation Html", metadata.get(Metadata.TITLE)); - final String text = Utils.toString(contents); + final String text = metadata.toString(); final String expected = "Test Indexation Html"; assertTrue("text contains '" + expected + "'", text.contains(expected)); }