Index: src/test/java/org/apache/tika/TestParsers.java =================================================================== --- src/test/java/org/apache/tika/TestParsers.java (revision 1339249) +++ src/test/java/org/apache/tika/TestParsers.java (working copy) @@ -22,6 +22,7 @@ import org.apache.tika.config.TikaConfig; import org.apache.tika.metadata.Metadata; +import org.apache.tika.metadata.TikaCoreProperties; import org.apache.tika.parser.ParseContext; import org.apache.tika.parser.Parser; import org.xml.sax.helpers.DefaultHandler; @@ -51,7 +52,7 @@ } finally { stream.close(); } - assertEquals("Sample Word Document", metadata.get(Metadata.TITLE)); + assertEquals("Sample Word Document", metadata.get(TikaCoreProperties.TITLE)); } public void testEXCELExtraction() throws Exception { @@ -69,7 +70,7 @@ } finally { stream.close(); } - assertEquals("Simple Excel document", metadata.get(Metadata.TITLE)); + assertEquals("Simple Excel document", metadata.get(TikaCoreProperties.TITLE)); } public void testOptionalHyphen() throws Exception { Index: src/test/java/org/apache/tika/parser/image/ImageMetadataExtractorTest.java =================================================================== --- src/test/java/org/apache/tika/parser/image/ImageMetadataExtractorTest.java (revision 1339328) +++ src/test/java/org/apache/tika/parser/image/ImageMetadataExtractorTest.java (working copy) @@ -20,8 +20,8 @@ import java.util.GregorianCalendar; import java.util.Iterator; -import org.apache.tika.metadata.DublinCore; import org.apache.tika.metadata.Metadata; +import org.apache.tika.metadata.TikaCoreProperties; import com.drew.metadata.Directory; import com.drew.metadata.MetadataException; @@ -66,7 +66,7 @@ Metadata metadata = new Metadata(); new ImageMetadataExtractor.ExifHandler().handle(exif, metadata); - assertEquals("Should be ISO date without time zone", "2000-01-01T00:00:00", metadata.get(Metadata.DATE)); + assertEquals("Should be ISO date without time zone", "2000-01-01T00:00:00", metadata.get(TikaCoreProperties.DATE)); } public void testExifHandlerParseDateFallback() throws MetadataException { @@ -77,7 +77,7 @@ Metadata metadata = new Metadata(); new ImageMetadataExtractor.ExifHandler().handle(exif, metadata); - assertEquals("Should try EXIF Date/Time if Original is not set", "1999-01-01T00:00:00", metadata.get(Metadata.DATE)); + assertEquals("Should try EXIF Date/Time if Original is not set", "1999-01-01T00:00:00", metadata.get(TikaCoreProperties.DATE)); } public void testExifHandlerParseDateError() throws MetadataException { @@ -88,7 +88,7 @@ Metadata metadata = new Metadata(); new ImageMetadataExtractor.ExifHandler().handle(exif, metadata); - assertEquals("Parsing should proceed without date", null, metadata.get(Metadata.DATE)); + assertEquals("Parsing should proceed without date", null, metadata.get(TikaCoreProperties.DATE)); } public void testCopyUnknownFieldsHandler() throws MetadataException { @@ -100,7 +100,7 @@ when(t2.getTagName()).thenReturn(Metadata.KEYWORDS); when(t2.getDescription()).thenReturn("known"); Tag t3 = mock(Tag.class); - when(t3.getTagName()).thenReturn(Metadata.DESCRIPTION); + when(t3.getTagName()).thenReturn(TikaCoreProperties.DESCRIPTION.getName()); when(t3.getDescription()).thenReturn("known"); Iterator tags = Arrays.asList(t1, t2, t3).iterator(); when(d.getTagIterator()).thenReturn(tags); @@ -109,7 +109,7 @@ assertEquals("t1", metadata.get("Image Description")); assertNull("keywords should be excluded from bulk copy because it is a defined field", metadata.get(Metadata.KEYWORDS)); - assertNull(metadata.get(Metadata.DESCRIPTION)); + assertNull(metadata.get(TikaCoreProperties.DESCRIPTION)); } } Index: src/test/java/org/apache/tika/parser/image/xmp/JempboxExtractorTest.java =================================================================== --- src/test/java/org/apache/tika/parser/image/xmp/JempboxExtractorTest.java (revision 1339249) +++ src/test/java/org/apache/tika/parser/image/xmp/JempboxExtractorTest.java (working copy) @@ -23,6 +23,7 @@ import org.apache.tika.exception.TikaException; import org.apache.tika.metadata.Metadata; +import org.apache.tika.metadata.TikaCoreProperties; import org.apache.tika.parser.image.xmp.JempboxExtractor; import junit.framework.TestCase; @@ -33,20 +34,20 @@ Metadata metadata = new Metadata(); InputStream stream = getClass().getResourceAsStream("/test-documents/testJPEG_commented.jpg"); // set some values before extraction to see that they are overridden - metadata.set(Metadata.TITLE, "old title"); - metadata.set(Metadata.DESCRIPTION, "old description"); - metadata.set(Metadata.CREATOR, "previous author"); + metadata.set(TikaCoreProperties.TITLE, "old title"); + metadata.set(TikaCoreProperties.DESCRIPTION, "old description"); + metadata.set(TikaCoreProperties.CREATOR, "previous author"); // ... or kept in case the field is multi-value - metadata.add(Metadata.SUBJECT, "oldkeyword"); + metadata.add(TikaCoreProperties.SUBJECT, "oldkeyword"); JempboxExtractor extractor = new JempboxExtractor(metadata); extractor.parse(stream); // DublinCore fields - assertEquals("Tosteberga \u00C4ngar", metadata.get(Metadata.TITLE)); - assertEquals("Bird site in north eastern Sk\u00E5ne, Sweden.\n(new line)", metadata.get(Metadata.DESCRIPTION)); - assertEquals("Some Tourist", metadata.get(Metadata.CREATOR)); - Collection keywords = Arrays.asList(metadata.getValues(Metadata.SUBJECT)); + assertEquals("Tosteberga \u00C4ngar", metadata.get(TikaCoreProperties.TITLE)); + assertEquals("Bird site in north eastern Sk\u00E5ne, Sweden.\n(new line)", metadata.get(TikaCoreProperties.DESCRIPTION)); + assertEquals("Some Tourist", metadata.get(TikaCoreProperties.CREATOR)); + Collection keywords = Arrays.asList(metadata.getValues(TikaCoreProperties.SUBJECT)); assertTrue(keywords.contains("oldkeyword")); assertTrue(keywords.contains("grazelands")); assertTrue(keywords.contains("nature reserve")); @@ -62,10 +63,10 @@ extractor.parse(stream); // DublinCore fields - assertEquals("Tosteberga \u00C4ngar", metadata.get(Metadata.TITLE)); - assertEquals("Bird site in north eastern Sk\u00E5ne, Sweden.\n(new line)", metadata.get(Metadata.DESCRIPTION)); - assertEquals("Some Tourist", metadata.get(Metadata.CREATOR)); - Collection keywords = Arrays.asList(metadata.getValues(Metadata.SUBJECT)); + assertEquals("Tosteberga \u00C4ngar", metadata.get(TikaCoreProperties.TITLE)); + assertEquals("Bird site in north eastern Sk\u00E5ne, Sweden.\n(new line)", metadata.get(TikaCoreProperties.DESCRIPTION)); + assertEquals("Some Tourist", metadata.get(TikaCoreProperties.CREATOR)); + Collection keywords = Arrays.asList(metadata.getValues(TikaCoreProperties.SUBJECT)); assertTrue(keywords.contains("bird watching")); assertTrue(keywords.contains("coast")); } @@ -78,8 +79,8 @@ extractor.parse(stream); // XnViewMp fields not understood by Jempbox - assertEquals("Bird site in north eastern Sk\u00E5ne, Sweden.\n(new line)", metadata.get(Metadata.DESCRIPTION)); - Collection keywords = Arrays.asList(metadata.getValues(Metadata.SUBJECT)); + assertEquals("Bird site in north eastern Sk\u00E5ne, Sweden.\n(new line)", metadata.get(TikaCoreProperties.DESCRIPTION)); + Collection keywords = Arrays.asList(metadata.getValues(TikaCoreProperties.SUBJECT)); assertTrue(keywords.contains("coast")); assertTrue(keywords.contains("nature reserve")); } Index: src/test/java/org/apache/tika/parser/image/TiffParserTest.java =================================================================== --- src/test/java/org/apache/tika/parser/image/TiffParserTest.java (revision 1339249) +++ src/test/java/org/apache/tika/parser/image/TiffParserTest.java (working copy) @@ -22,6 +22,7 @@ import org.apache.tika.parser.Parser; import org.apache.tika.parser.image.TiffParser; import org.apache.tika.metadata.Metadata; +import org.apache.tika.metadata.TikaCoreProperties; import org.xml.sax.helpers.DefaultHandler; import java.io.InputStream; @@ -41,7 +42,7 @@ assertEquals("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.", metadata.get(Metadata.DESCRIPTION)); + "copyright ownership.", metadata.get(TikaCoreProperties.DESCRIPTION)); // All EXIF/TIFF tags assertEquals("Inch", metadata.get(Metadata.RESOLUTION_UNIT)); @@ -53,7 +54,7 @@ assertEquals("3", metadata.get(Metadata.SAMPLES_PER_PIXEL)); // Embedded XMP - List subject = Arrays.asList(metadata.getValues(Metadata.SUBJECT)); + List subject = Arrays.asList(metadata.getValues(TikaCoreProperties.SUBJECT)); assertTrue("got " + subject, subject.contains("cat")); assertTrue("got " + subject, subject.contains("garden")); } Index: src/test/java/org/apache/tika/parser/image/MetadataFieldsTest.java =================================================================== --- src/test/java/org/apache/tika/parser/image/MetadataFieldsTest.java (revision 1339328) +++ src/test/java/org/apache/tika/parser/image/MetadataFieldsTest.java (working copy) @@ -16,8 +16,8 @@ */ package org.apache.tika.parser.image; -import org.apache.tika.metadata.Metadata; import org.apache.tika.metadata.TIFF; +import org.apache.tika.metadata.TikaCoreProperties; import junit.framework.TestCase; @@ -26,7 +26,7 @@ public void testIsMetadataField() { assertFalse(MetadataFields.isMetadataField("random string that is not a field")); assertFalse(MetadataFields.isMetadataField("xyz")); - assertTrue(MetadataFields.isMetadataField(Metadata.SUBJECT)); + assertTrue(MetadataFields.isMetadataField(TikaCoreProperties.SUBJECT)); assertTrue(MetadataFields.isMetadataField(TIFF.F_NUMBER.getName())); } Index: src/test/java/org/apache/tika/parser/jpeg/JpegParserTest.java =================================================================== --- src/test/java/org/apache/tika/parser/jpeg/JpegParserTest.java (revision 1339249) +++ src/test/java/org/apache/tika/parser/jpeg/JpegParserTest.java (working copy) @@ -24,6 +24,7 @@ import org.apache.tika.metadata.Metadata; import org.apache.tika.metadata.TIFF; +import org.apache.tika.metadata.TikaCoreProperties; import org.apache.tika.parser.ParseContext; import org.apache.tika.parser.Parser; import org.xml.sax.helpers.DefaultHandler; @@ -65,8 +66,8 @@ // Common tags //assertEquals("2009-10-02T23:02:49", metadata.get(Metadata.LAST_MODIFIED)); assertEquals("Date/Time Original for when the photo was taken, unspecified time zone", - "2009-08-11T09:09:45", metadata.get(Metadata.DATE)); - List keywords = Arrays.asList(metadata.getValues(Metadata.SUBJECT)); + "2009-08-11T09:09:45", metadata.get(TikaCoreProperties.DATE)); + List keywords = Arrays.asList(metadata.getValues(TikaCoreProperties.SUBJECT)); assertTrue("'canon-55-250' expected in " + keywords, keywords.contains("canon-55-250")); assertTrue("'moscow-birds' expected in " + keywords, keywords.contains("moscow-birds")); assertTrue("'serbor' expected in " + keywords, keywords.contains("serbor")); @@ -108,7 +109,7 @@ // Common tags assertEquals("Date/Time Original for when the photo was taken, unspecified time zone", - "2009-08-11T09:09:45", metadata.get(Metadata.DATE)); + "2009-08-11T09:09:45", metadata.get(TikaCoreProperties.DATE)); assertEquals("This image has different Date/Time than Date/Time Original, so it is probably modification date", "2009-10-02T23:02:49", metadata.get(Metadata.LAST_MODIFIED)); assertEquals("Date/Time Original should be stored in EXIF field too", @@ -141,17 +142,17 @@ parser.parse(stream, new DefaultHandler(), metadata, new ParseContext()); // embedded comments with non-ascii characters - assertEquals("Tosteberga \u00C4ngar", metadata.get(Metadata.TITLE)); - assertEquals("Bird site in north eastern Sk\u00E5ne, Sweden.\n(new line)", metadata.get(Metadata.DESCRIPTION)); + assertEquals("Tosteberga \u00C4ngar", metadata.get(TikaCoreProperties.TITLE)); + assertEquals("Bird site in north eastern Sk\u00E5ne, Sweden.\n(new line)", metadata.get(TikaCoreProperties.DESCRIPTION)); assertEquals("Some Tourist", metadata.get(Metadata.AUTHOR)); - assertEquals("Some Tourist", metadata.get(Metadata.CREATOR)); // Dublin Core + assertEquals("Some Tourist", metadata.get(TikaCoreProperties.CREATOR)); // Dublin Core // xmp handles spaces in keywords, returns "bird watching, nature reserve, coast, grazelands" // but we have to replace them with underscore List keywords = Arrays.asList(metadata.getValues(Metadata.KEYWORDS)); assertTrue(keywords.contains("coast")); assertTrue(keywords.contains("bird watching")); - assertEquals(keywords, Arrays.asList(metadata.getValues(Metadata.SUBJECT))); + assertEquals(keywords, Arrays.asList(metadata.getValues(TikaCoreProperties.SUBJECT))); // Core EXIF/TIFF tags assertEquals("103", metadata.get(Metadata.IMAGE_WIDTH)); @@ -180,10 +181,10 @@ parser.parse(stream, new DefaultHandler(), metadata, new ParseContext()); // embedded comments with non-ascii characters - assertEquals("Tosteberga \u00C4ngar", metadata.get(Metadata.TITLE)); - assertEquals("Bird site in north eastern Sk\u00E5ne, Sweden.\n(new line)", metadata.get(Metadata.DESCRIPTION)); - assertEquals("Some Tourist", metadata.get(Metadata.CREATOR)); - List subject = Arrays.asList(metadata.getValues(Metadata.SUBJECT)); + assertEquals("Tosteberga \u00C4ngar", metadata.get(TikaCoreProperties.TITLE)); + assertEquals("Bird site in north eastern Sk\u00E5ne, Sweden.\n(new line)", metadata.get(TikaCoreProperties.DESCRIPTION)); + assertEquals("Some Tourist", metadata.get(TikaCoreProperties.CREATOR)); + List subject = Arrays.asList(metadata.getValues(TikaCoreProperties.SUBJECT)); assertTrue("got " + subject, subject.contains("bird watching")); } @@ -196,10 +197,10 @@ // XnViewMp's default comment dialog has only comment, not headline. // Comment is embedded only if "Write comments in XMP" is enabled in settings - assertEquals("Bird site in north eastern Sk\u00E5ne, Sweden.\n(new line)", metadata.get(Metadata.DESCRIPTION)); + assertEquals("Bird site in north eastern Sk\u00E5ne, Sweden.\n(new line)", metadata.get(TikaCoreProperties.DESCRIPTION)); // xmp handles spaces in keywords, returns "bird watching, nature reserve, coast, grazelands" // but we have to replace them with underscore - String[] subject = metadata.getValues(Metadata.SUBJECT); + String[] subject = metadata.getValues(TikaCoreProperties.SUBJECT); List keywords = Arrays.asList(subject); assertTrue("'coast'" + " not in " + keywords, keywords.contains("coast")); assertTrue("'nature reserve'" + " not in " + keywords, keywords.contains("nature reserve")); @@ -212,8 +213,8 @@ getClass().getResourceAsStream("/test-documents/testJPEG_oddTagComponent.jpg"); parser.parse(stream, new DefaultHandler(), metadata, new ParseContext()); - assertEquals(null, metadata.get(Metadata.TITLE)); - assertEquals(null, metadata.get(Metadata.DESCRIPTION)); + assertEquals(null, metadata.get(TikaCoreProperties.TITLE)); + assertEquals(null, metadata.get(TikaCoreProperties.DESCRIPTION)); assertEquals("251", metadata.get(Metadata.IMAGE_WIDTH)); assertEquals("384", metadata.get(Metadata.IMAGE_LENGTH)); } Index: src/test/java/org/apache/tika/parser/rtf/RTFParserTest.java =================================================================== --- src/test/java/org/apache/tika/parser/rtf/RTFParserTest.java (revision 1339249) +++ src/test/java/org/apache/tika/parser/rtf/RTFParserTest.java (working copy) @@ -30,6 +30,7 @@ import org.apache.tika.TikaTest; import org.apache.tika.io.TikaInputStream; import org.apache.tika.metadata.Metadata; +import org.apache.tika.metadata.TikaCoreProperties; import org.apache.tika.parser.ParseContext; import org.apache.tika.sax.WriteOutContentHandler; @@ -132,7 +133,7 @@ // Verify title, since it was also encoded with MS932: Result r = getResult("testRTF-ms932.rtf"); - assertEquals("\u30bf\u30a4\u30c8\u30eb", r.metadata.get(Metadata.TITLE)); + assertEquals("\u30bf\u30a4\u30c8\u30eb", r.metadata.get(TikaCoreProperties.TITLE)); } public void testUmlautSpacesExtraction() throws Exception { @@ -153,7 +154,7 @@ // Verify title -- this title uses upr escape inside // title info field: assertEquals("\u30be\u30eb\u30b2\u3068\u5c3e\u5d0e\u3001\u6de1\u3005\u3068\u6700\u671f\u3000", - r.metadata.get(Metadata.TITLE)); + r.metadata.get(TikaCoreProperties.TITLE)); assertEquals("VMazel", r.metadata.get(Metadata.AUTHOR)); assertEquals("StarWriter", r.metadata.get(Metadata.COMMENT)); assertContains("1.", content); @@ -267,7 +268,7 @@ assertContains("Subject is here", content); assertEquals("Subject is here", - r.metadata.get(Metadata.SUBJECT)); + r.metadata.get(TikaCoreProperties.SUBJECT)); assertContains("Suddenly some Japanese text:", content); // Special version of (GHQ) Index: src/test/java/org/apache/tika/parser/iwork/IWorkParserTest.java =================================================================== --- src/test/java/org/apache/tika/parser/iwork/IWorkParserTest.java (revision 1339249) +++ src/test/java/org/apache/tika/parser/iwork/IWorkParserTest.java (working copy) @@ -21,6 +21,7 @@ import junit.framework.TestCase; import org.apache.tika.metadata.Metadata; +import org.apache.tika.metadata.TikaCoreProperties; import org.apache.tika.parser.AutoDetectParser; import org.apache.tika.parser.ParseContext; import org.apache.tika.parser.Parser; @@ -48,13 +49,13 @@ ContentHandler handler = new BodyContentHandler(); iWorkParser.parse(input, handler, metadata, parseContext); - assertEquals(6, metadata.size()); + assertEquals(7, metadata.size()); assertEquals("application/vnd.apple.keynote", metadata.get(Metadata.CONTENT_TYPE)); assertEquals("3", metadata.get(Metadata.SLIDE_COUNT)); assertEquals("1024", metadata.get(KeynoteContentHandler.PRESENTATION_WIDTH)); assertEquals("768", metadata.get(KeynoteContentHandler.PRESENTATION_HEIGHT)); assertEquals("Tika user", metadata.get(Metadata.AUTHOR)); - assertEquals("Apache tika", metadata.get(Metadata.TITLE)); + assertEquals("Apache tika", metadata.get(TikaCoreProperties.TITLE)); String content = handler.toString(); assertTrue(content.contains("A sample presentation")); @@ -82,13 +83,13 @@ ContentHandler handler = new BodyContentHandler(); iWorkParser.parse(input, handler, metadata, parseContext); - assertEquals(51, metadata.size()); + assertEquals(53, metadata.size()); assertEquals("application/vnd.apple.pages", metadata.get(Metadata.CONTENT_TYPE)); assertEquals("Tika user", metadata.get(Metadata.AUTHOR)); - assertEquals("Apache tika", metadata.get(Metadata.TITLE)); + assertEquals("Apache tika", metadata.get(TikaCoreProperties.TITLE)); assertEquals("2010-05-09T21:34:38+0200", metadata.get(Metadata.CREATION_DATE)); assertEquals("2010-05-09T23:50:36+0200", metadata.get(Metadata.LAST_MODIFIED)); - assertEquals("en", metadata.get(Metadata.LANGUAGE)); + assertEquals("en", metadata.get(TikaCoreProperties.LANGUAGE)); assertEquals("2", metadata.get(Metadata.PAGE_COUNT)); String content = handler.toString(); @@ -123,7 +124,7 @@ assertEquals(9, metadata.size()); assertEquals("2", metadata.get(Metadata.PAGE_COUNT)); assertEquals("Tika User", metadata.get(Metadata.AUTHOR)); - assertEquals("Account checking", metadata.get(Metadata.TITLE)); + assertEquals("Account checking", metadata.get(TikaCoreProperties.TITLE)); assertEquals("a comment", metadata.get(Metadata.COMMENT)); assertTrue(content.contains("Category")); Index: src/test/java/org/apache/tika/parser/mp3/Mp3ParserTest.java =================================================================== --- src/test/java/org/apache/tika/parser/mp3/Mp3ParserTest.java (revision 1339249) +++ src/test/java/org/apache/tika/parser/mp3/Mp3ParserTest.java (working copy) @@ -22,6 +22,7 @@ import junit.framework.TestCase; import org.apache.tika.metadata.Metadata; +import org.apache.tika.metadata.TikaCoreProperties; import org.apache.tika.metadata.XMPDM; import org.apache.tika.parser.AutoDetectParser; import org.apache.tika.parser.ParseContext; @@ -51,7 +52,7 @@ } assertEquals("audio/mpeg", metadata.get(Metadata.CONTENT_TYPE)); - assertEquals("Test Title", metadata.get(Metadata.TITLE)); + assertEquals("Test Title", metadata.get(TikaCoreProperties.TITLE)); assertEquals("Test Artist", metadata.get(Metadata.AUTHOR)); String content = handler.toString(); @@ -86,7 +87,7 @@ // Check core properties assertEquals("audio/mpeg", metadata.get(Metadata.CONTENT_TYPE)); - assertEquals("Test Title", metadata.get(Metadata.TITLE)); + assertEquals("Test Title", metadata.get(TikaCoreProperties.TITLE)); assertEquals("Test Artist", metadata.get(Metadata.AUTHOR)); // Check the textual contents @@ -135,7 +136,7 @@ } assertEquals("audio/mpeg", metadata.get(Metadata.CONTENT_TYPE)); - assertEquals("Test Title", metadata.get(Metadata.TITLE)); + assertEquals("Test Title", metadata.get(TikaCoreProperties.TITLE)); assertEquals("Test Artist", metadata.get(Metadata.AUTHOR)); String content = handler.toString(); @@ -169,7 +170,7 @@ } assertEquals("audio/mpeg", metadata.get(Metadata.CONTENT_TYPE)); - assertEquals("Test Title", metadata.get(Metadata.TITLE)); + assertEquals("Test Title", metadata.get(TikaCoreProperties.TITLE)); assertEquals("Test Artist", metadata.get(Metadata.AUTHOR)); String content = handler.toString(); @@ -203,7 +204,7 @@ } assertEquals("audio/mpeg", metadata.get(Metadata.CONTENT_TYPE)); - assertEquals("Une chason en Fran\u00e7ais", metadata.get(Metadata.TITLE)); + assertEquals("Une chason en Fran\u00e7ais", metadata.get(TikaCoreProperties.TITLE)); assertEquals("Test Artist \u2468\u2460", metadata.get(Metadata.AUTHOR)); assertEquals("Test Artist \u2468\u2460", metadata.get(XMPDM.ARTIST)); assertEquals("Test Album \u2460\u2468", metadata.get(XMPDM.ALBUM)); @@ -241,7 +242,7 @@ } assertEquals("audio/mpeg", metadata.get(Metadata.CONTENT_TYPE)); - assertEquals("Test Title", metadata.get(Metadata.TITLE)); + assertEquals("Test Title", metadata.get(TikaCoreProperties.TITLE)); assertEquals("Test Artist", metadata.get(Metadata.AUTHOR)); String content = handler.toString(); @@ -306,7 +307,7 @@ } assertEquals("audio/mpeg", metadata.get(Metadata.CONTENT_TYPE)); - assertEquals("Plus loin vers l'ouest", metadata.get(Metadata.TITLE)); + assertEquals("Plus loin vers l'ouest", metadata.get(TikaCoreProperties.TITLE)); assertEquals("Merzhin", metadata.get(Metadata.AUTHOR)); String content = handler.toString(); @@ -341,7 +342,7 @@ // Check we coud get the headers from the start assertEquals("audio/mpeg", metadata.get(Metadata.CONTENT_TYPE)); - assertEquals("Girl you have no faith in medicine", metadata.get(Metadata.TITLE)); + assertEquals("Girl you have no faith in medicine", metadata.get(TikaCoreProperties.TITLE)); assertEquals("The White Stripes", metadata.get(Metadata.AUTHOR)); String content = handler.toString(); Index: src/test/java/org/apache/tika/parser/mp4/MP4ParserTest.java =================================================================== --- src/test/java/org/apache/tika/parser/mp4/MP4ParserTest.java (revision 1339249) +++ src/test/java/org/apache/tika/parser/mp4/MP4ParserTest.java (working copy) @@ -22,6 +22,7 @@ import org.apache.tika.io.TikaInputStream; import org.apache.tika.metadata.Metadata; +import org.apache.tika.metadata.TikaCoreProperties; import org.apache.tika.metadata.XMPDM; import org.apache.tika.parser.AutoDetectParser; import org.apache.tika.parser.ParseContext; @@ -52,10 +53,10 @@ // Check core properties assertEquals("audio/mp4", metadata.get(Metadata.CONTENT_TYPE)); - assertEquals("Test Title", metadata.get(Metadata.TITLE)); + assertEquals("Test Title", metadata.get(TikaCoreProperties.TITLE)); assertEquals("Test Artist", metadata.get(Metadata.AUTHOR)); assertEquals("2012-01-28T18:39:18Z", metadata.get(Metadata.CREATION_DATE)); - assertEquals("2012-01-28T18:40:25Z", metadata.get(Metadata.MODIFIED)); + assertEquals("2012-01-28T18:40:25Z", metadata.get(TikaCoreProperties.MODIFIED)); // Check the textual contents String content = handler.toString(); Index: src/test/java/org/apache/tika/parser/html/HtmlParserTest.java =================================================================== --- src/test/java/org/apache/tika/parser/html/HtmlParserTest.java (revision 1339249) +++ src/test/java/org/apache/tika/parser/html/HtmlParserTest.java (working copy) @@ -36,6 +36,7 @@ import org.apache.tika.exception.TikaException; import org.apache.tika.metadata.Geographic; import org.apache.tika.metadata.Metadata; +import org.apache.tika.metadata.TikaCoreProperties; import org.apache.tika.parser.ParseContext; import org.apache.tika.sax.BodyContentHandler; import org.apache.tika.sax.TeeContentHandler; @@ -76,7 +77,7 @@ } assertEquals( - "Title : Test Indexation Html", metadata.get(Metadata.TITLE)); + "Title : Test Indexation Html", metadata.get(TikaCoreProperties.TITLE)); assertEquals("Tika Developers", metadata.get("Author")); assertEquals("5", metadata.get("refresh")); @@ -120,7 +121,7 @@ HtmlParserTest.class.getResourceAsStream(path), metadata); assertEquals("application/xhtml+xml", metadata.get(Metadata.CONTENT_TYPE)); - assertEquals("XHTML test document", metadata.get(Metadata.TITLE)); + assertEquals("XHTML test document", metadata.get(TikaCoreProperties.TITLE)); assertEquals("Tika Developers", metadata.get("Author")); assertEquals("5", metadata.get("refresh")); @@ -258,7 +259,7 @@ new HtmlParser().parse ( new ByteArrayInputStream(test.getBytes("UTF-8")), new BodyContentHandler(), metadata, new ParseContext()); - assertEquals("\u017d", metadata.get(Metadata.TITLE)); + assertEquals("\u017d", metadata.get(TikaCoreProperties.TITLE)); } /** Index: src/test/java/org/apache/tika/parser/prt/PRTParserTest.java =================================================================== --- src/test/java/org/apache/tika/parser/prt/PRTParserTest.java (revision 1339249) +++ src/test/java/org/apache/tika/parser/prt/PRTParserTest.java (working copy) @@ -20,6 +20,7 @@ import org.apache.tika.TikaTest; import org.apache.tika.metadata.Metadata; +import org.apache.tika.metadata.TikaCoreProperties; import org.apache.tika.sax.BodyContentHandler; import org.xml.sax.ContentHandler; @@ -38,11 +39,11 @@ // This file has a date assertEquals("2011-06-20T16:54:00", - metadata.get(Metadata.DATE)); + metadata.get(TikaCoreProperties.DATE)); assertEquals("2011-06-20T16:54:00", metadata.get(Metadata.CREATION_DATE)); // But no description - assertEquals(null, metadata.get(Metadata.DESCRIPTION)); + assertEquals(null, metadata.get(TikaCoreProperties.DESCRIPTION)); String contents = handler.toString(); @@ -80,7 +81,7 @@ assertEquals("1997-04-01T08:59:00", metadata.get(Metadata.CREATION_DATE)); assertEquals("TIKA TEST PART DESCRIPTION INFORMATION\r\n", - metadata.get(Metadata.DESCRIPTION)); + metadata.get(TikaCoreProperties.DESCRIPTION)); String contents = handler.toString(); Index: src/test/java/org/apache/tika/parser/microsoft/PowerPointParserTest.java =================================================================== --- src/test/java/org/apache/tika/parser/microsoft/PowerPointParserTest.java (revision 1339249) +++ src/test/java/org/apache/tika/parser/microsoft/PowerPointParserTest.java (working copy) @@ -21,6 +21,7 @@ import org.apache.tika.TikaTest; import org.apache.tika.metadata.Metadata; +import org.apache.tika.metadata.TikaCoreProperties; import org.apache.tika.parser.ParseContext; import org.apache.tika.sax.BodyContentHandler; import org.xml.sax.ContentHandler; @@ -38,7 +39,7 @@ assertEquals( "application/vnd.ms-powerpoint", metadata.get(Metadata.CONTENT_TYPE)); - assertEquals("Sample Powerpoint Slide", metadata.get(Metadata.TITLE)); + assertEquals("Sample Powerpoint Slide", metadata.get(TikaCoreProperties.TITLE)); assertEquals("Keith Bennett", metadata.get(Metadata.AUTHOR)); String content = handler.toString(); assertTrue(content.contains("Sample Powerpoint Slide")); @@ -104,7 +105,7 @@ assertContains("Subject is here", content); assertEquals("Subject is here", - metadata.get(Metadata.SUBJECT)); + metadata.get(TikaCoreProperties.SUBJECT)); assertContains("Suddenly some Japanese text:", content); // Special version of (GHQ) @@ -203,7 +204,7 @@ assertEquals("2011-08-22T13:30:53Z", metadata.get(Metadata.CREATION_DATE)); assertEquals("1", metadata.get(Metadata.SLIDE_COUNT)); assertEquals("3", metadata.get(Metadata.WORD_COUNT)); - assertEquals("Test extraction properties pptx", metadata.get(Metadata.TITLE)); + assertEquals("Test extraction properties pptx", metadata.get(TikaCoreProperties.TITLE)); assertEquals("true", metadata.get("custom:myCustomBoolean")); assertEquals("3", metadata.get("custom:myCustomNumber")); assertEquals("MyStringValue", metadata.get("custom:MyCustomString")); Index: src/test/java/org/apache/tika/parser/microsoft/ProjectParserTest.java =================================================================== --- src/test/java/org/apache/tika/parser/microsoft/ProjectParserTest.java (revision 1339249) +++ src/test/java/org/apache/tika/parser/microsoft/ProjectParserTest.java (working copy) @@ -19,6 +19,7 @@ import java.io.InputStream; import org.apache.tika.metadata.Metadata; +import org.apache.tika.metadata.TikaCoreProperties; import org.apache.tika.parser.ParseContext; import org.apache.tika.sax.BodyContentHandler; import org.xml.sax.ContentHandler; @@ -61,8 +62,8 @@ "application/vnd.ms-project", metadata.get(Metadata.CONTENT_TYPE)); - assertEquals("The quick brown fox jumps over the lazy dog", metadata.get(Metadata.TITLE)); - assertEquals("Gym class featuring a brown fox and lazy dog", metadata.get(Metadata.SUBJECT)); + assertEquals("The quick brown fox jumps over the lazy dog", metadata.get(TikaCoreProperties.TITLE)); + assertEquals("Gym class featuring a brown fox and lazy dog", metadata.get(TikaCoreProperties.SUBJECT)); assertEquals("Nevin Nollop", metadata.get(Metadata.AUTHOR)); assertEquals("", metadata.get(Metadata.LAST_AUTHOR)); assertEquals("Pangram, fox, dog", metadata.get(Metadata.KEYWORDS)); Index: src/test/java/org/apache/tika/parser/microsoft/VisioParserTest.java =================================================================== --- src/test/java/org/apache/tika/parser/microsoft/VisioParserTest.java (revision 1339249) +++ src/test/java/org/apache/tika/parser/microsoft/VisioParserTest.java (working copy) @@ -19,6 +19,7 @@ import java.io.InputStream; import org.apache.tika.metadata.Metadata; +import org.apache.tika.metadata.TikaCoreProperties; import org.apache.tika.parser.ParseContext; import org.apache.tika.sax.BodyContentHandler; import org.xml.sax.ContentHandler; @@ -38,7 +39,7 @@ assertEquals( "application/vnd.visio", metadata.get(Metadata.CONTENT_TYPE)); - assertEquals("", metadata.get(Metadata.TITLE)); + assertEquals("", metadata.get(TikaCoreProperties.TITLE)); assertEquals("Hogwarts", metadata.get(Metadata.AUTHOR)); String content = handler.toString(); assertTrue(content.contains("Some random text, on a page")); Index: src/test/java/org/apache/tika/parser/microsoft/WordParserTest.java =================================================================== --- src/test/java/org/apache/tika/parser/microsoft/WordParserTest.java (revision 1339249) +++ src/test/java/org/apache/tika/parser/microsoft/WordParserTest.java (working copy) @@ -27,6 +27,7 @@ import org.apache.tika.TikaTest; import org.apache.tika.metadata.Metadata; +import org.apache.tika.metadata.TikaCoreProperties; import org.apache.tika.parser.ParseContext; import org.apache.tika.parser.microsoft.ooxml.OOXMLParserTest; import org.apache.tika.sax.BodyContentHandler; @@ -45,7 +46,7 @@ assertEquals( "application/msword", metadata.get(Metadata.CONTENT_TYPE)); - assertEquals("Sample Word Document", metadata.get(Metadata.TITLE)); + assertEquals("Sample Word Document", metadata.get(TikaCoreProperties.TITLE)); assertEquals("Keith Bennett", metadata.get(Metadata.AUTHOR)); assertTrue(handler.toString().contains("Sample Word Document")); } finally { @@ -114,7 +115,7 @@ assertEquals( "application/msword", metadata.get(Metadata.CONTENT_TYPE)); - assertEquals("Sample Word Document", metadata.get(Metadata.TITLE)); + assertEquals("Sample Word Document", metadata.get(TikaCoreProperties.TITLE)); assertEquals("Keith Bennett", metadata.get(Metadata.AUTHOR)); assertTrue(xml.contains("Sample Word Document")); @@ -176,8 +177,8 @@ assertEquals( "application/msword", metadata.get(Metadata.CONTENT_TYPE)); - assertEquals("The quick brown fox jumps over the lazy dog", metadata.get(Metadata.TITLE)); - assertEquals("Gym class featuring a brown fox and lazy dog", metadata.get(Metadata.SUBJECT)); + assertEquals("The quick brown fox jumps over the lazy dog", metadata.get(TikaCoreProperties.TITLE)); + assertEquals("Gym class featuring a brown fox and lazy dog", metadata.get(TikaCoreProperties.SUBJECT)); assertEquals("Nevin Nollop", metadata.get(Metadata.AUTHOR)); assertTrue(handler.toString().contains("The quick brown fox jumps over the lazy dog")); } finally { @@ -241,7 +242,7 @@ assertContains("Subject is here", content); assertEquals("Subject is here", - metadata.get(Metadata.SUBJECT)); + metadata.get(TikaCoreProperties.SUBJECT)); assertContains("Suddenly some Japanese text:", content); // Special version of (GHQ) @@ -278,11 +279,11 @@ assertEquals("Microsoft Office Word",metadata.get(Metadata.APPLICATION_NAME)); assertEquals("1", metadata.get(Metadata.PAGE_COUNT)); assertEquals("2", metadata.get(Metadata.WORD_COUNT)); - assertEquals("My Title", metadata.get(Metadata.TITLE)); + assertEquals("My Title", metadata.get(TikaCoreProperties.TITLE)); assertEquals("My Keyword", metadata.get(Metadata.KEYWORDS)); assertEquals("Normal.dotm", metadata.get(Metadata.TEMPLATE)); assertEquals("My Comments", metadata.get(Metadata.COMMENTS)); - assertEquals("My subject", metadata.get(Metadata.SUBJECT)); + assertEquals("My subject", metadata.get(TikaCoreProperties.SUBJECT)); assertEquals("EDF-DIT", metadata.get(Metadata.COMPANY)); assertEquals("MyStringValue", metadata.get("custom:MyCustomString")); assertEquals("2010-12-30T23:00:00Z", metadata.get("custom:MyCustomDate")); Index: src/test/java/org/apache/tika/parser/microsoft/OutlookParserTest.java =================================================================== --- src/test/java/org/apache/tika/parser/microsoft/OutlookParserTest.java (revision 1339249) +++ src/test/java/org/apache/tika/parser/microsoft/OutlookParserTest.java (working copy) @@ -29,6 +29,7 @@ import junit.framework.TestCase; import org.apache.tika.metadata.Metadata; +import org.apache.tika.metadata.TikaCoreProperties; import org.apache.tika.parser.AutoDetectParser; import org.apache.tika.parser.ParseContext; import org.apache.tika.parser.Parser; @@ -58,7 +59,7 @@ metadata.get(Metadata.CONTENT_TYPE)); assertEquals( "Microsoft Outlook Express 6", - metadata.get(Metadata.TITLE)); + metadata.get(TikaCoreProperties.TITLE)); assertEquals( "Nouvel utilisateur de Outlook Express", metadata.get(Metadata.MESSAGE_RECIPIENT_ADDRESS)); @@ -69,7 +70,7 @@ // Stored as Thu, 5 Apr 2007 09:26:06 -0700 assertEquals( "2007-04-05T16:26:06Z", - metadata.get(Metadata.DATE)); + metadata.get(TikaCoreProperties.DATE)); String content = handler.toString(); assertTrue(content.contains("")); @@ -131,7 +132,7 @@ metadata.get(Metadata.CONTENT_TYPE)); assertEquals( "Welcome to Microsoft Office Outlook 2003", - metadata.get(Metadata.TITLE)); + metadata.get(TikaCoreProperties.TITLE)); String content = handler.toString(); assertTrue(content.contains("Outlook 2003")); Index: src/test/java/org/apache/tika/parser/microsoft/TNEFParserTest.java =================================================================== --- src/test/java/org/apache/tika/parser/microsoft/TNEFParserTest.java (revision 1339249) +++ src/test/java/org/apache/tika/parser/microsoft/TNEFParserTest.java (working copy) @@ -22,6 +22,7 @@ import org.apache.tika.extractor.ParserContainerExtractor; import org.apache.tika.io.TikaInputStream; import org.apache.tika.metadata.Metadata; +import org.apache.tika.metadata.TikaCoreProperties; import org.apache.tika.mime.MediaType; import org.apache.tika.parser.ParseContext; import org.apache.tika.sax.BodyContentHandler; @@ -54,7 +55,7 @@ TNEFParser tnef = new TNEFParser(); tnef.parse(stream, handler, metadata, new ParseContext()); - assertEquals("This is a test message", metadata.get(Metadata.SUBJECT)); + assertEquals("This is a test message", metadata.get(TikaCoreProperties.SUBJECT)); } /** Index: src/test/java/org/apache/tika/parser/microsoft/PublisherParserTest.java =================================================================== --- src/test/java/org/apache/tika/parser/microsoft/PublisherParserTest.java (revision 1339249) +++ src/test/java/org/apache/tika/parser/microsoft/PublisherParserTest.java (working copy) @@ -19,6 +19,7 @@ import java.io.InputStream; import org.apache.tika.metadata.Metadata; +import org.apache.tika.metadata.TikaCoreProperties; import org.apache.tika.parser.ParseContext; import org.apache.tika.sax.BodyContentHandler; import org.xml.sax.ContentHandler; @@ -38,7 +39,7 @@ assertEquals( "application/x-mspublisher", metadata.get(Metadata.CONTENT_TYPE)); - assertEquals(null, metadata.get(Metadata.TITLE)); + assertEquals(null, metadata.get(TikaCoreProperties.TITLE)); assertEquals("Nick Burch", metadata.get(Metadata.AUTHOR)); String content = handler.toString(); assertTrue(content.contains("0123456789")); Index: src/test/java/org/apache/tika/parser/microsoft/ExcelParserTest.java =================================================================== --- src/test/java/org/apache/tika/parser/microsoft/ExcelParserTest.java (revision 1339249) +++ src/test/java/org/apache/tika/parser/microsoft/ExcelParserTest.java (working copy) @@ -24,6 +24,7 @@ import org.apache.tika.detect.DefaultDetector; import org.apache.tika.detect.Detector; import org.apache.tika.metadata.Metadata; +import org.apache.tika.metadata.TikaCoreProperties; import org.apache.tika.mime.MediaType; import org.apache.tika.parser.AutoDetectParser; import org.apache.tika.parser.ParseContext; @@ -45,7 +46,7 @@ assertEquals( "application/vnd.ms-excel", metadata.get(Metadata.CONTENT_TYPE)); - assertEquals("Simple Excel document", metadata.get(Metadata.TITLE)); + assertEquals("Simple Excel document", metadata.get(TikaCoreProperties.TITLE)); assertEquals("Keith Bennett", metadata.get(Metadata.AUTHOR)); // Mon Oct 01 17:13:56 BST 2007 Index: src/test/java/org/apache/tika/parser/microsoft/ooxml/OOXMLParserTest.java =================================================================== --- src/test/java/org/apache/tika/parser/microsoft/ooxml/OOXMLParserTest.java (revision 1339390) +++ src/test/java/org/apache/tika/parser/microsoft/ooxml/OOXMLParserTest.java (working copy) @@ -28,6 +28,7 @@ import org.apache.tika.TikaTest; import org.apache.tika.io.TikaInputStream; import org.apache.tika.metadata.Metadata; +import org.apache.tika.metadata.TikaCoreProperties; import org.apache.tika.metadata.TikaMetadataKeys; import org.apache.tika.parser.AutoDetectParser; import org.apache.tika.parser.ParseContext; @@ -57,7 +58,7 @@ assertEquals( "application/vnd.openxmlformats-officedocument.spreadsheetml.sheet", metadata.get(Metadata.CONTENT_TYPE)); - assertEquals("Simple Excel document", metadata.get(Metadata.TITLE)); + assertEquals("Simple Excel document", metadata.get(TikaCoreProperties.TITLE)); assertEquals("Keith Bennett", metadata.get(Metadata.AUTHOR)); String content = handler.toString(); assertTrue(content.contains("Sample Excel Worksheet")); @@ -184,7 +185,7 @@ "Mime-type checking for " + filename, mimeTypes[i], metadata.get(Metadata.CONTENT_TYPE)); - assertEquals("Attachment Test", metadata.get(Metadata.TITLE)); + assertEquals("Attachment Test", metadata.get(TikaCoreProperties.TITLE)); assertEquals("Rajiv", metadata.get(Metadata.AUTHOR)); String content = handler.toString(); @@ -273,7 +274,7 @@ assertEquals( "application/vnd.openxmlformats-officedocument.wordprocessingml.document", metadata.get(Metadata.CONTENT_TYPE)); - assertEquals("Sample Word Document", metadata.get(Metadata.TITLE)); + assertEquals("Sample Word Document", metadata.get(TikaCoreProperties.TITLE)); assertEquals("Keith Bennett", metadata.get(Metadata.AUTHOR)); assertTrue(handler.toString().contains("Sample Word Document")); } finally { @@ -344,7 +345,7 @@ assertEquals( "application/vnd.openxmlformats-officedocument.wordprocessingml.document", metadata.get(Metadata.CONTENT_TYPE)); - assertEquals("Sample Word Document", metadata.get(Metadata.TITLE)); + assertEquals("Sample Word Document", metadata.get(TikaCoreProperties.TITLE)); assertEquals("Keith Bennett", metadata.get(Metadata.AUTHOR)); assertTrue(xml.contains("Sample Word Document")); @@ -557,7 +558,7 @@ assertContains("Subject is here", content); assertEquals("Subject is here", - metadata.get(Metadata.SUBJECT)); + metadata.get(TikaCoreProperties.SUBJECT)); assertContains("Suddenly some Japanese text:", content); // Special version of (GHQ) @@ -625,7 +626,7 @@ assertContains("Subject is here", content); assertEquals("Subject is here", - metadata.get(Metadata.SUBJECT)); + metadata.get(TikaCoreProperties.SUBJECT)); assertContains("Suddenly some Japanese text:", content); // Special version of (GHQ) @@ -729,7 +730,7 @@ metadata.get(Metadata.CONTENT_TYPE)); assertEquals(null, metadata.get(Metadata.AUTHOR)); assertEquals(null, metadata.get(Metadata.LAST_AUTHOR)); - assertEquals("2006-09-12T15:06:44Z", metadata.get(Metadata.DATE)); + assertEquals("2006-09-12T15:06:44Z", metadata.get(TikaCoreProperties.DATE)); assertEquals("2006-09-12T15:06:44Z", metadata.get(Metadata.CREATION_DATE)); assertEquals("2011-08-22T14:24:38Z", metadata.get(Metadata.LAST_MODIFIED)); assertEquals("Microsoft Excel", metadata.get(Metadata.APPLICATION_NAME)); @@ -758,17 +759,17 @@ metadata.get(Metadata.CONTENT_TYPE)); assertEquals("EJ04325S", metadata.get(Metadata.AUTHOR)); assertEquals("Etienne Jouvin", metadata.get(Metadata.LAST_AUTHOR)); - assertEquals("2011-07-29T16:52:00Z", metadata.get(Metadata.DATE)); + assertEquals("2011-07-29T16:52:00Z", metadata.get(TikaCoreProperties.DATE)); assertEquals("2011-07-29T16:52:00Z", metadata.get(Metadata.CREATION_DATE)); assertEquals("2012-01-03T22:14:00Z", metadata.get(Metadata.LAST_MODIFIED)); assertEquals("Microsoft Office Word",metadata.get(Metadata.APPLICATION_NAME)); assertEquals("1", metadata.get(Metadata.PAGE_COUNT)); assertEquals("2", metadata.get(Metadata.WORD_COUNT)); - assertEquals("My Title", metadata.get(Metadata.TITLE)); + assertEquals("My Title", metadata.get(TikaCoreProperties.TITLE)); assertEquals("My Keyword", metadata.get(Metadata.KEYWORDS)); assertEquals("Normal.dotm", metadata.get(Metadata.TEMPLATE)); - assertEquals("My subject", metadata.get(Metadata.SUBJECT)); - assertEquals("EDF-DIT", metadata.get(Metadata.PUBLISHER)); + assertEquals("My subject", metadata.get(TikaCoreProperties.SUBJECT)); + assertEquals("EDF-DIT", metadata.get(TikaCoreProperties.PUBLISHER)); assertEquals("true", metadata.get("custom:myCustomBoolean")); assertEquals("3", metadata.get("custom:myCustomNumber")); assertEquals("MyStringValue", metadata.get("custom:MyCustomString")); @@ -794,12 +795,12 @@ metadata.get(Metadata.CONTENT_TYPE)); assertEquals("JOUVIN ETIENNE", metadata.get(Metadata.AUTHOR)); assertEquals("EJ04325S", metadata.get(Metadata.LAST_AUTHOR)); - assertEquals("2011-08-22T13:30:53Z", metadata.get(Metadata.DATE)); + assertEquals("2011-08-22T13:30:53Z", metadata.get(TikaCoreProperties.DATE)); assertEquals("2011-08-22T13:30:53Z", metadata.get(Metadata.CREATION_DATE)); assertEquals("2011-08-22T13:32:49Z", metadata.get(Metadata.LAST_MODIFIED)); assertEquals("1", metadata.get(Metadata.SLIDE_COUNT)); assertEquals("3", metadata.get(Metadata.WORD_COUNT)); - assertEquals("Test extraction properties pptx", metadata.get(Metadata.TITLE)); + assertEquals("Test extraction properties pptx", metadata.get(TikaCoreProperties.TITLE)); assertEquals("true", metadata.get("custom:myCustomBoolean")); assertEquals("3", metadata.get("custom:myCustomNumber")); assertEquals("MyStringValue", metadata.get("custom:MyCustomString")); Index: src/test/java/org/apache/tika/parser/ParsingReaderTest.java =================================================================== --- src/test/java/org/apache/tika/parser/ParsingReaderTest.java (revision 1339249) +++ src/test/java/org/apache/tika/parser/ParsingReaderTest.java (working copy) @@ -21,6 +21,7 @@ import java.io.Reader; import org.apache.tika.metadata.Metadata; +import org.apache.tika.metadata.TikaCoreProperties; import junit.framework.TestCase; @@ -83,7 +84,7 @@ new AutoDetectParser(), stream, metadata, new ParseContext()); try { // Metadata should already be available - assertEquals("Simple Excel document", metadata.get(Metadata.TITLE)); + assertEquals("Simple Excel document", metadata.get(TikaCoreProperties.TITLE)); // Check that the internal buffering isn't broken assertEquals('F', (char) reader.read()); assertEquals('e', (char) reader.read()); Index: src/test/java/org/apache/tika/parser/txt/TXTParserTest.java =================================================================== --- src/test/java/org/apache/tika/parser/txt/TXTParserTest.java (revision 1339249) +++ src/test/java/org/apache/tika/parser/txt/TXTParserTest.java (working copy) @@ -20,6 +20,7 @@ import java.io.StringWriter; import org.apache.tika.metadata.Metadata; +import org.apache.tika.metadata.TikaCoreProperties; import org.apache.tika.parser.ParseContext; import org.apache.tika.parser.Parser; import org.apache.tika.sax.BodyContentHandler; @@ -51,7 +52,7 @@ // TIKA-501: Remove language detection from TXTParser assertNull(metadata.get(Metadata.CONTENT_LANGUAGE)); - assertNull(metadata.get(Metadata.LANGUAGE)); + assertNull(metadata.get(TikaCoreProperties.LANGUAGE)); assertTrue(content.contains("Hello")); assertTrue(content.contains("World")); @@ -169,13 +170,13 @@ final String test = "Simple Content"; Metadata metadata = new Metadata(); - metadata.set(Metadata.LANGUAGE, "en"); + metadata.set(TikaCoreProperties.LANGUAGE, "en"); parser.parse( new ByteArrayInputStream(test.getBytes("UTF-8")), new BodyContentHandler(), metadata, new ParseContext()); - assertEquals("en", metadata.get(Metadata.LANGUAGE)); + assertEquals("en", metadata.get(TikaCoreProperties.LANGUAGE)); } public void testCP866() throws Exception { Index: src/test/java/org/apache/tika/parser/asm/ClassParserTest.java =================================================================== --- src/test/java/org/apache/tika/parser/asm/ClassParserTest.java (revision 1339249) +++ src/test/java/org/apache/tika/parser/asm/ClassParserTest.java (working copy) @@ -20,6 +20,7 @@ import org.apache.tika.Tika; import org.apache.tika.metadata.Metadata; +import org.apache.tika.metadata.TikaCoreProperties; /** * Test case for parsing Java class files. @@ -32,7 +33,7 @@ String content = new Tika().parseToString( ClassParserTest.class.getResourceAsStream(path), metadata); - assertEquals("AutoDetectParser", metadata.get(Metadata.TITLE)); + assertEquals("AutoDetectParser", metadata.get(TikaCoreProperties.TITLE)); assertEquals( "AutoDetectParser.class", metadata.get(Metadata.RESOURCE_NAME_KEY)); Index: src/test/java/org/apache/tika/parser/dwg/DWGParserTest.java =================================================================== --- src/test/java/org/apache/tika/parser/dwg/DWGParserTest.java (revision 1339249) +++ src/test/java/org/apache/tika/parser/dwg/DWGParserTest.java (working copy) @@ -21,6 +21,7 @@ import junit.framework.TestCase; import org.apache.tika.metadata.Metadata; +import org.apache.tika.metadata.TikaCoreProperties; import org.apache.tika.sax.BodyContentHandler; import org.xml.sax.ContentHandler; @@ -76,9 +77,9 @@ assertEquals("image/vnd.dwg", metadata.get(Metadata.CONTENT_TYPE)); assertEquals("The quick brown fox jumps over the lazy dog", - metadata.get(Metadata.TITLE)); + metadata.get(TikaCoreProperties.TITLE)); assertEquals("Gym class featuring a brown fox and lazy dog", - metadata.get(Metadata.SUBJECT)); + metadata.get(TikaCoreProperties.SUBJECT)); assertEquals("Nevin Nollop", metadata.get(Metadata.AUTHOR)); assertEquals("Pangram, fox, dog", @@ -86,7 +87,7 @@ assertEquals("Lorem ipsum", metadata.get(Metadata.COMMENTS).substring(0,11)); assertEquals("http://www.alfresco.com", - metadata.get(Metadata.RELATION)); + metadata.get(TikaCoreProperties.RELATION)); String content = handler.toString(); assertTrue(content.contains("The quick brown fox jumps over the lazy dog")); @@ -105,12 +106,12 @@ assertEquals("image/vnd.dwg", metadata.get(Metadata.CONTENT_TYPE)); - assertNull(metadata.get(Metadata.TITLE)); - assertNull(metadata.get(Metadata.SUBJECT)); + assertNull(metadata.get(TikaCoreProperties.TITLE)); + assertNull(metadata.get(TikaCoreProperties.SUBJECT)); assertNull(metadata.get(Metadata.AUTHOR)); assertNull(metadata.get(Metadata.KEYWORDS)); assertNull(metadata.get(Metadata.COMMENTS)); - assertNull(metadata.get(Metadata.RELATION)); + assertNull(metadata.get(TikaCoreProperties.RELATION)); String content = handler.toString(); assertTrue(content.contains("")); @@ -128,9 +129,9 @@ assertEquals("image/vnd.dwg", metadata.get(Metadata.CONTENT_TYPE)); assertEquals("Test Title", - metadata.get(Metadata.TITLE)); + metadata.get(TikaCoreProperties.TITLE)); assertEquals("Test Subject", - metadata.get(Metadata.SUBJECT)); + metadata.get(TikaCoreProperties.SUBJECT)); assertEquals("My Author", metadata.get(Metadata.AUTHOR)); assertEquals("My keyword1, MyKeyword2", @@ -140,7 +141,7 @@ assertEquals("bejanpol", metadata.get(Metadata.LAST_AUTHOR)); assertEquals("http://mycompany/drawings", - metadata.get(Metadata.RELATION)); + metadata.get(TikaCoreProperties.RELATION)); assertEquals("MyCustomPropertyValue", metadata.get("MyCustomProperty")); Index: src/test/java/org/apache/tika/parser/mail/RFC822ParserTest.java =================================================================== --- src/test/java/org/apache/tika/parser/mail/RFC822ParserTest.java (revision 1339249) +++ src/test/java/org/apache/tika/parser/mail/RFC822ParserTest.java (working copy) @@ -31,6 +31,7 @@ import org.apache.james.mime4j.stream.MimeConfig; import org.apache.tika.exception.TikaException; import org.apache.tika.metadata.Metadata; +import org.apache.tika.metadata.TikaCoreProperties; import org.apache.tika.parser.ParseContext; import org.apache.tika.parser.Parser; import org.apache.tika.sax.BodyContentHandler; @@ -59,7 +60,7 @@ verify(handler).endDocument(); //note no leading spaces, and no quotes assertEquals("Julien Nioche (JIRA) ", metadata.get(Metadata.AUTHOR)); - assertEquals("[jira] Commented: (TIKA-461) RFC822 messages not parsed", metadata.get(Metadata.SUBJECT)); + assertEquals("[jira] Commented: (TIKA-461) RFC822 messages not parsed", metadata.get(TikaCoreProperties.SUBJECT)); } catch (Exception e) { fail("Exception thrown: " + e.getMessage()); } @@ -147,7 +148,7 @@ //tests correct decoding of internationalized headers, both //quoted-printable (Q) and Base64 (B). assertEquals("Keld J\u00F8rn Simonsen ", metadata.get(Metadata.AUTHOR)); - assertEquals("If you can read this you understand the example.", metadata.get(Metadata.SUBJECT)); + assertEquals("If you can read this you understand the example.", metadata.get(TikaCoreProperties.SUBJECT)); } catch (Exception e) { fail("Exception thrown: " + e.getMessage()); } @@ -165,7 +166,7 @@ parser.parse(stream, handler, metadata, new ParseContext()); assertEquals("Saved by Windows Internet Explorer 7", metadata.get(Metadata.AUTHOR)); - assertEquals("Air Permit Programs | Air & Radiation | US EPA", metadata.get(Metadata.SUBJECT)); + assertEquals("Air Permit Programs | Air & Radiation | US EPA", metadata.get(TikaCoreProperties.SUBJECT)); } /** @@ -220,7 +221,7 @@ assertEquals(true, metadata.isMultiValued(Metadata.MESSAGE_TO)); assertEquals("abc", metadata.getValues(Metadata.MESSAGE_TO)[0]); assertEquals("def", metadata.getValues(Metadata.MESSAGE_TO)[1]); - assertEquals("abcd", metadata.get(Metadata.SUBJECT)); + assertEquals("abcd", metadata.get(TikaCoreProperties.SUBJECT)); assertTrue(handler.toString().contains("bar biz bat")); } Index: src/test/java/org/apache/tika/parser/ibooks/iBooksParserTest.java =================================================================== --- src/test/java/org/apache/tika/parser/ibooks/iBooksParserTest.java (revision 1339249) +++ src/test/java/org/apache/tika/parser/ibooks/iBooksParserTest.java (working copy) @@ -21,6 +21,7 @@ import junit.framework.TestCase; import org.apache.tika.metadata.Metadata; +import org.apache.tika.metadata.TikaCoreProperties; import org.apache.tika.parser.ParseContext; import org.apache.tika.parser.epub.EpubParser; import org.apache.tika.sax.BodyContentHandler; @@ -39,11 +40,11 @@ assertEquals("application/x-ibooks+zip", metadata.get(Metadata.CONTENT_TYPE)); assertEquals("en-GB", - metadata.get(Metadata.LANGUAGE)); + metadata.get(TikaCoreProperties.LANGUAGE)); assertEquals("iBooks Author v1.0", - metadata.get(Metadata.CONTRIBUTOR)); + metadata.get(TikaCoreProperties.CONTRIBUTOR)); assertEquals("Apache", - metadata.get(Metadata.CREATOR)); + metadata.get(TikaCoreProperties.CREATOR)); /* TODO For some reason, the xhtml files in iBooks-style ePub are not parsed properly, and the content comes back empty.git che String content = handler.toString(); Index: src/test/java/org/apache/tika/parser/epub/EpubParserTest.java =================================================================== --- src/test/java/org/apache/tika/parser/epub/EpubParserTest.java (revision 1339249) +++ src/test/java/org/apache/tika/parser/epub/EpubParserTest.java (working copy) @@ -21,6 +21,7 @@ import junit.framework.TestCase; import org.apache.tika.metadata.Metadata; +import org.apache.tika.metadata.TikaCoreProperties; import org.apache.tika.parser.ParseContext; import org.apache.tika.sax.BodyContentHandler; import org.xml.sax.ContentHandler; @@ -38,11 +39,11 @@ assertEquals("application/epub+zip", metadata.get(Metadata.CONTENT_TYPE)); assertEquals("en", - metadata.get(Metadata.LANGUAGE)); + metadata.get(TikaCoreProperties.LANGUAGE)); assertEquals("This is an ePub test publication for Tika.", - metadata.get(Metadata.DESCRIPTION)); + metadata.get(TikaCoreProperties.DESCRIPTION)); assertEquals("Apache", - metadata.get(Metadata.PUBLISHER)); + metadata.get(TikaCoreProperties.PUBLISHER)); String content = handler.toString(); assertTrue(content.contains("Plus a simple div")); Index: src/test/java/org/apache/tika/parser/xml/DcXMLParserTest.java =================================================================== --- src/test/java/org/apache/tika/parser/xml/DcXMLParserTest.java (revision 1339249) +++ src/test/java/org/apache/tika/parser/xml/DcXMLParserTest.java (working copy) @@ -21,6 +21,7 @@ import junit.framework.TestCase; import org.apache.tika.metadata.Metadata; +import org.apache.tika.metadata.TikaCoreProperties; import org.apache.tika.sax.BodyContentHandler; import org.xml.sax.ContentHandler; import org.xml.sax.helpers.DefaultHandler; @@ -38,34 +39,34 @@ assertEquals( "application/xml", metadata.get(Metadata.CONTENT_TYPE)); - assertEquals("Tika test document", metadata.get(Metadata.TITLE)); - assertEquals("Rida Benjelloun", metadata.get(Metadata.CREATOR)); + assertEquals("Tika test document", metadata.get(TikaCoreProperties.TITLE)); + assertEquals("Rida Benjelloun", metadata.get(TikaCoreProperties.CREATOR)); // The file contains 5 dc:subject tags, which come through as // a multi-valued Tika Metadata entry in file order - assertEquals(true, metadata.isMultiValued(Metadata.SUBJECT)); - assertEquals(5, metadata.getValues(Metadata.SUBJECT).length); - assertEquals("Java", metadata.getValues(Metadata.SUBJECT)[0]); - assertEquals("XML", metadata.getValues(Metadata.SUBJECT)[1]); - assertEquals("XSLT", metadata.getValues(Metadata.SUBJECT)[2]); - assertEquals("JDOM", metadata.getValues(Metadata.SUBJECT)[3]); - assertEquals("Indexation", metadata.getValues(Metadata.SUBJECT)[4]); + assertEquals(true, metadata.isMultiValued(TikaCoreProperties.SUBJECT)); + assertEquals(5, metadata.getValues(TikaCoreProperties.SUBJECT).length); + assertEquals("Java", metadata.getValues(TikaCoreProperties.SUBJECT)[0]); + assertEquals("XML", metadata.getValues(TikaCoreProperties.SUBJECT)[1]); + assertEquals("XSLT", metadata.getValues(TikaCoreProperties.SUBJECT)[2]); + assertEquals("JDOM", metadata.getValues(TikaCoreProperties.SUBJECT)[3]); + assertEquals("Indexation", metadata.getValues(TikaCoreProperties.SUBJECT)[4]); assertEquals( "Framework d\'indexation des documents XML, HTML, PDF etc..", - metadata.get(Metadata.DESCRIPTION)); + metadata.get(TikaCoreProperties.DESCRIPTION)); assertEquals( "http://www.apache.org", - metadata.get(Metadata.IDENTIFIER)); - assertEquals("test", metadata.get(Metadata.TYPE)); - assertEquals("application/msword", metadata.get(Metadata.FORMAT)); - assertEquals("Fr", metadata.get(Metadata.LANGUAGE)); - assertTrue(metadata.get(Metadata.RIGHTS).contains("testing chars")); + metadata.get(TikaCoreProperties.IDENTIFIER)); + assertEquals("test", metadata.get(TikaCoreProperties.TYPE)); + assertEquals("application/msword", metadata.get(TikaCoreProperties.FORMAT)); + assertEquals("Fr", metadata.get(TikaCoreProperties.LANGUAGE)); + assertTrue(metadata.get(TikaCoreProperties.RIGHTS).contains("testing chars")); String content = handler.toString(); assertTrue(content.contains("Tika test document")); - assertEquals("2000-12-01T00:00:00.000Z", metadata.get(Metadata.DATE)); + assertEquals("2000-12-01T00:00:00.000Z", metadata.get(TikaCoreProperties.DATE)); } finally { input.close(); } @@ -78,7 +79,7 @@ new DcXMLParser().parse(input, new DefaultHandler(), metadata); final String expected = "Archim\u00E8de et Lius \u00E0 Ch\u00E2teauneuf testing chars en \u00E9t\u00E9"; - assertEquals(expected,metadata.get(Metadata.RIGHTS)); + assertEquals(expected,metadata.get(TikaCoreProperties.RIGHTS)); } finally { input.close(); } Index: src/test/java/org/apache/tika/parser/feed/FeedParserTest.java =================================================================== --- src/test/java/org/apache/tika/parser/feed/FeedParserTest.java (revision 1339249) +++ src/test/java/org/apache/tika/parser/feed/FeedParserTest.java (working copy) @@ -21,6 +21,7 @@ import junit.framework.TestCase; import org.apache.tika.metadata.Metadata; +import org.apache.tika.metadata.TikaCoreProperties; import org.apache.tika.parser.ParseContext; import org.apache.tika.sax.BodyContentHandler; import org.xml.sax.ContentHandler; @@ -41,8 +42,8 @@ assertFalse(content == null); assertEquals("Sample RSS File for Junit test", - metadata.get(Metadata.DESCRIPTION)); - assertEquals("TestChannel", metadata.get(Metadata.TITLE)); + metadata.get(TikaCoreProperties.DESCRIPTION)); + assertEquals("TestChannel", metadata.get(TikaCoreProperties.TITLE)); // TODO find a way of testing the paragraphs and anchors Index: src/test/java/org/apache/tika/parser/netcdf/NetCDFParserTest.java =================================================================== --- src/test/java/org/apache/tika/parser/netcdf/NetCDFParserTest.java (revision 1339249) +++ src/test/java/org/apache/tika/parser/netcdf/NetCDFParserTest.java (working copy) @@ -21,6 +21,7 @@ //TIKA imports import org.apache.tika.metadata.Metadata; +import org.apache.tika.metadata.TikaCoreProperties; import org.apache.tika.parser.ParseContext; import org.apache.tika.parser.Parser; import org.apache.tika.sax.BodyContentHandler; @@ -52,7 +53,7 @@ stream.close(); } - assertEquals(metadata.get(Metadata.TITLE), + assertEquals(metadata.get(TikaCoreProperties.TITLE), "model output prepared for IPCC AR4"); assertEquals(metadata.get(Metadata.CONTACT), "ccsm@ucar.edu"); assertEquals(metadata.get(Metadata.PROJECT_ID), Index: src/test/java/org/apache/tika/parser/mbox/MboxParserTest.java =================================================================== --- src/test/java/org/apache/tika/parser/mbox/MboxParserTest.java (revision 1339249) +++ src/test/java/org/apache/tika/parser/mbox/MboxParserTest.java (working copy) @@ -27,6 +27,7 @@ import junit.framework.TestCase; import org.apache.tika.metadata.Metadata; +import org.apache.tika.metadata.TikaCoreProperties; import org.apache.tika.parser.ParseContext; import org.apache.tika.parser.Parser; import org.apache.tika.sax.XHTMLContentHandler; @@ -69,14 +70,14 @@ verify(handler).characters(new String("Test content").toCharArray(), 0, 12); verify(handler).endDocument(); - assertEquals("subject", metadata.get(Metadata.TITLE)); - assertEquals("subject", metadata.get(Metadata.SUBJECT)); + assertEquals("subject", metadata.get(TikaCoreProperties.TITLE)); + assertEquals("subject", metadata.get(TikaCoreProperties.SUBJECT)); assertEquals("", metadata.get(Metadata.AUTHOR)); - assertEquals("", metadata.get(Metadata.CREATOR)); + assertEquals("", metadata.get(TikaCoreProperties.CREATOR)); assertEquals(null, metadata.get(Metadata.MESSAGE_RECIPIENT_ADDRESS)); assertEquals("", metadata.get("MboxParser-return-path")); assertEquals("Should be ISO date in UTC, converted from 'Tue, 9 Jun 2009 23:58:45 -0400'", - "2009-06-10T03:58:45Z", metadata.get(Metadata.DATE)); + "2009-06-10T03:58:45Z", metadata.get(TikaCoreProperties.DATE)); } catch (Exception e) { fail("Exception thrown: " + e.getMessage()); } @@ -133,10 +134,10 @@ try { parser.parse(stream, handler, metadata, new ParseContext()); - assertEquals("Re: question about when shuffle/sort start working", metadata.get(Metadata.TITLE)); - assertEquals("Re: question about when shuffle/sort start working", metadata.get(Metadata.SUBJECT)); + assertEquals("Re: question about when shuffle/sort start working", metadata.get(TikaCoreProperties.TITLE)); + assertEquals("Re: question about when shuffle/sort start working", metadata.get(TikaCoreProperties.SUBJECT)); assertEquals("Jothi Padmanabhan ", metadata.get(Metadata.AUTHOR)); - assertEquals("Jothi Padmanabhan ", metadata.get(Metadata.CREATOR)); + assertEquals("Jothi Padmanabhan ", metadata.get(TikaCoreProperties.CREATOR)); assertEquals("core-user@hadoop.apache.org", metadata.get(Metadata.MESSAGE_RECIPIENT_ADDRESS)); verify(handler).startDocument(); Index: src/test/java/org/apache/tika/parser/font/AdobeFontMetricParserTest.java =================================================================== --- src/test/java/org/apache/tika/parser/font/AdobeFontMetricParserTest.java (revision 1339249) +++ src/test/java/org/apache/tika/parser/font/AdobeFontMetricParserTest.java (working copy) @@ -19,6 +19,7 @@ import junit.framework.TestCase; import org.apache.tika.metadata.Metadata; +import org.apache.tika.metadata.TikaCoreProperties; import org.apache.tika.parser.AutoDetectParser; import org.apache.tika.parser.ParseContext; import org.apache.tika.parser.Parser; @@ -46,7 +47,7 @@ } assertEquals("application/x-font-adobe-metric", metadata.get(Metadata.CONTENT_TYPE)); - assertEquals("TestFullName", metadata.get(Metadata.TITLE)); + assertEquals("TestFullName", metadata.get(TikaCoreProperties.TITLE)); assertEquals("Fri Jul 15 17:50:51 2011", metadata.get(Metadata.CREATION_DATE)); assertEquals("TestFontName", metadata.get("FontName")); Index: src/test/java/org/apache/tika/parser/odf/ODFParserTest.java =================================================================== --- src/test/java/org/apache/tika/parser/odf/ODFParserTest.java (revision 1339249) +++ src/test/java/org/apache/tika/parser/odf/ODFParserTest.java (working copy) @@ -20,6 +20,8 @@ import org.apache.tika.TikaTest; import org.apache.tika.metadata.Metadata; +import org.apache.tika.metadata.TikaCoreProperties; +import org.apache.tika.metadata.Office; import org.apache.tika.parser.AutoDetectParser; import org.apache.tika.parser.ParseContext; import org.apache.tika.parser.Parser; @@ -76,15 +78,24 @@ assertEquals( "application/vnd.oasis.opendocument.text", metadata.get(Metadata.CONTENT_TYPE)); - assertEquals("2007-09-14T11:07:10", metadata.get(Metadata.DATE)); + assertEquals("2007-09-14T11:07:10", metadata.get(TikaCoreProperties.DATE)); assertEquals("2007-09-14T11:06:08", metadata.get(Metadata.CREATION_DATE)); - assertEquals("en-US", metadata.get(Metadata.LANGUAGE)); + assertEquals("en-US", metadata.get(TikaCoreProperties.LANGUAGE)); assertEquals("PT1M7S", metadata.get(Metadata.EDIT_TIME)); assertEquals( "NeoOffice/2.2$Unix OpenOffice.org_project/680m18$Build-9161", metadata.get("generator")); // Check the document statistics + assertEquals("1", metadata.get(Office.PAGE_COUNT)); + assertEquals("1", metadata.get(Office.PARAGRAPH_COUNT)); + assertEquals("14", metadata.get(Office.WORD_COUNT)); + assertEquals("78", metadata.get(Office.CHARACTER_COUNT)); + assertEquals("0", metadata.get(Office.TABLE_COUNT)); + assertEquals("0", metadata.get(Office.OBJECT_COUNT)); + assertEquals("0", metadata.get(Office.IMAGE_COUNT)); + + // Check the Tika-1.0 style document statistics assertEquals("1", metadata.get(Metadata.PAGE_COUNT)); assertEquals("1", metadata.get(Metadata.PARAGRAPH_COUNT)); assertEquals("14", metadata.get(Metadata.WORD_COUNT)); @@ -93,7 +104,7 @@ assertEquals("0", metadata.get(Metadata.OBJECT_COUNT)); assertEquals("0", metadata.get(Metadata.IMAGE_COUNT)); - // Check the old style statistics (these will be removed shortly) + // Check the very old style statistics (these will be removed shortly) assertEquals("0", metadata.get("nbTab")); assertEquals("0", metadata.get("nbObject")); assertEquals("0", metadata.get("nbImg")); @@ -133,10 +144,10 @@ assertEquals( "application/vnd.oasis.opendocument.formula", metadata.get(Metadata.CONTENT_TYPE)); - assertEquals(null, metadata.get(Metadata.DATE)); + assertEquals(null, metadata.get(TikaCoreProperties.DATE)); assertEquals("2006-01-27T11:55:22", metadata.get(Metadata.CREATION_DATE)); - assertEquals("The quick brown fox jumps over the lazy dog", metadata.get(Metadata.TITLE)); - assertEquals("Gym class featuring a brown fox and lazy dog", metadata.get(Metadata.SUBJECT)); + assertEquals("The quick brown fox jumps over the lazy dog", metadata.get(TikaCoreProperties.TITLE)); + assertEquals("Gym class featuring a brown fox and lazy dog", metadata.get(TikaCoreProperties.SUBJECT)); assertEquals("PT0S", metadata.get(Metadata.EDIT_TIME)); assertEquals("1", metadata.get("editing-cycles")); assertEquals( @@ -188,12 +199,12 @@ assertEquals( "application/vnd.oasis.opendocument.text", metadata.get(Metadata.CONTENT_TYPE)); - assertEquals("2009-10-05T21:22:38", metadata.get(Metadata.DATE)); + assertEquals("2009-10-05T21:22:38", metadata.get(TikaCoreProperties.DATE)); assertEquals("2009-10-05T19:04:01", metadata.get(Metadata.CREATION_DATE)); - assertEquals("Apache Tika", metadata.get(Metadata.TITLE)); - assertEquals("Test document", metadata.get(Metadata.SUBJECT)); - assertEquals("A rather complex document", metadata.get(Metadata.DESCRIPTION)); - assertEquals("Bart Hanssens", metadata.get(Metadata.CREATOR)); + assertEquals("Apache Tika", metadata.get(TikaCoreProperties.TITLE)); + assertEquals("Test document", metadata.get(TikaCoreProperties.SUBJECT)); + assertEquals("A rather complex document", metadata.get(TikaCoreProperties.DESCRIPTION)); + assertEquals("Bart Hanssens", metadata.get(TikaCoreProperties.CREATOR)); assertEquals("Bart Hanssens", metadata.get("initial-creator")); assertEquals("2", metadata.get("editing-cycles")); assertEquals("PT02H03M24S", metadata.get(Metadata.EDIT_TIME)); @@ -209,6 +220,15 @@ assertEquals(null, metadata.get("custom:Info 4")); // Check the document statistics + assertEquals("2", metadata.get(Office.PAGE_COUNT)); + assertEquals("13", metadata.get(Office.PARAGRAPH_COUNT)); + assertEquals("54", metadata.get(Office.WORD_COUNT)); + assertEquals("351", metadata.get(Office.CHARACTER_COUNT)); + assertEquals("0", metadata.get(Office.TABLE_COUNT)); + assertEquals("2", metadata.get(Office.OBJECT_COUNT)); + assertEquals("0", metadata.get(Office.IMAGE_COUNT)); + + // Check the Tika-1.0 style document statistics assertEquals("2", metadata.get(Metadata.PAGE_COUNT)); assertEquals("13", metadata.get(Metadata.PARAGRAPH_COUNT)); assertEquals("54", metadata.get(Metadata.WORD_COUNT)); Index: src/test/java/org/apache/tika/parser/pdf/PDFParserTest.java =================================================================== --- src/test/java/org/apache/tika/parser/pdf/PDFParserTest.java (revision 1339249) +++ src/test/java/org/apache/tika/parser/pdf/PDFParserTest.java (working copy) @@ -26,6 +26,7 @@ import org.apache.tika.TikaTest; import org.apache.tika.metadata.Metadata; +import org.apache.tika.metadata.TikaCoreProperties; import org.apache.tika.parser.AutoDetectParser; import org.apache.tika.parser.ParseContext; import org.apache.tika.parser.Parser; @@ -53,7 +54,7 @@ assertEquals("application/pdf", metadata.get(Metadata.CONTENT_TYPE)); assertEquals("Bertrand Delacr\u00e9taz", metadata.get(Metadata.AUTHOR)); - assertEquals("Apache Tika - Apache Tika", metadata.get(Metadata.TITLE)); + assertEquals("Apache Tika - Apache Tika", metadata.get(TikaCoreProperties.TITLE)); // Can't reliably test dates yet - see TIKA-451 // assertEquals("Sat Sep 15 10:02:31 BST 2007", metadata.get(Metadata.CREATION_DATE)); @@ -87,7 +88,7 @@ assertEquals("application/pdf", metadata.get(Metadata.CONTENT_TYPE)); assertEquals("Document author", metadata.get(Metadata.AUTHOR)); - assertEquals("Document title", metadata.get(Metadata.TITLE)); + assertEquals("Document title", metadata.get(TikaCoreProperties.TITLE)); assertEquals("Custom Value", metadata.get("Custom Property")); assertEquals("Array Entry 1", metadata.get("Custom Array")); @@ -120,8 +121,8 @@ assertEquals("application/pdf", metadata.get(Metadata.CONTENT_TYPE)); assertEquals("The Bank of England", metadata.get(Metadata.AUTHOR)); - assertEquals("Speeches by Andrew G Haldane", metadata.get(Metadata.SUBJECT)); - assertEquals("Rethinking the Financial Network, Speech by Andrew G Haldane, Executive Director, Financial Stability delivered at the Financial Student Association, Amsterdam on 28 April 2009", metadata.get(Metadata.TITLE)); + assertEquals("Speeches by Andrew G Haldane", metadata.get(TikaCoreProperties.SUBJECT)); + assertEquals("Rethinking the Financial Network, Speech by Andrew G Haldane, Executive Director, Financial Stability delivered at the Financial Student Association, Amsterdam on 28 April 2009", metadata.get(TikaCoreProperties.TITLE)); String content = handler.toString(); assertTrue(content.contains("RETHINKING THE FINANCIAL NETWORK")); @@ -150,8 +151,8 @@ assertEquals("application/pdf", metadata.get(Metadata.CONTENT_TYPE)); assertEquals("The Bank of England", metadata.get(Metadata.AUTHOR)); - assertEquals("Speeches by Andrew G Haldane", metadata.get(Metadata.SUBJECT)); - assertEquals("Rethinking the Financial Network, Speech by Andrew G Haldane, Executive Director, Financial Stability delivered at the Financial Student Association, Amsterdam on 28 April 2009", metadata.get(Metadata.TITLE)); + assertEquals("Speeches by Andrew G Haldane", metadata.get(TikaCoreProperties.SUBJECT)); + assertEquals("Rethinking the Financial Network, Speech by Andrew G Haldane, Executive Director, Financial Stability delivered at the Financial Student Association, Amsterdam on 28 April 2009", metadata.get(TikaCoreProperties.TITLE)); assertTrue(content.contains("RETHINKING THE FINANCIAL NETWORK")); assertTrue(content.contains("On 16 November 2002")); @@ -233,7 +234,7 @@ assertContains("Subject is here", content); assertEquals("Subject is here", - metadata.get(Metadata.SUBJECT)); + metadata.get(TikaCoreProperties.SUBJECT)); assertContains("Suddenly some Japanese text:", content); // Special version of (GHQ) Index: src/main/java/org/apache/tika/parser/asm/XHTMLClassVisitor.java =================================================================== --- src/main/java/org/apache/tika/parser/asm/XHTMLClassVisitor.java (revision 1339249) +++ src/main/java/org/apache/tika/parser/asm/XHTMLClassVisitor.java (working copy) @@ -21,6 +21,7 @@ import org.apache.tika.exception.TikaException; import org.apache.tika.metadata.Metadata; +import org.apache.tika.metadata.TikaCoreProperties; import org.apache.tika.sax.XHTMLContentHandler; import org.objectweb.asm.AnnotationVisitor; import org.objectweb.asm.Attribute; @@ -78,7 +79,7 @@ className = className.substring(dot + 1); } - metadata.set(Metadata.TITLE, className); + metadata.set(TikaCoreProperties.TITLE, className); metadata.set(Metadata.RESOURCE_NAME_KEY, className + ".class"); try { Index: src/main/java/org/apache/tika/parser/dwg/DWGParser.java =================================================================== --- src/main/java/org/apache/tika/parser/dwg/DWGParser.java (revision 1339249) +++ src/main/java/org/apache/tika/parser/dwg/DWGParser.java (working copy) @@ -26,6 +26,7 @@ import org.apache.tika.exception.TikaException; import org.apache.tika.io.EndianUtils; import org.apache.tika.metadata.Metadata; +import org.apache.tika.metadata.TikaCoreProperties; import org.apache.tika.mime.MediaType; import org.apache.tika.parser.AbstractParser; import org.apache.tika.parser.ParseContext; @@ -52,22 +53,22 @@ /** The order of the fields in the header */ private static final String[] HEADER_PROPERTIES_ENTRIES = { - Metadata.TITLE, - Metadata.SUBJECT, + TikaCoreProperties.TITLE.getName(), + TikaCoreProperties.SUBJECT.getName(), Metadata.AUTHOR, Metadata.KEYWORDS, Metadata.COMMENTS, Metadata.LAST_AUTHOR, null, // Unknown? - Metadata.RELATION, // Hyperlink + TikaCoreProperties.RELATION.getName(), // Hyperlink }; /** For the 2000 file, they're indexed */ private static final String[] HEADER_2000_PROPERTIES_ENTRIES = { null, - Metadata.RELATION, // 0x01 - Metadata.TITLE, // 0x02 - Metadata.SUBJECT, // 0x03 + TikaCoreProperties.RELATION.getName(), // 0x01 + TikaCoreProperties.TITLE.getName(), // 0x02 + TikaCoreProperties.SUBJECT.getName(), // 0x03 Metadata.AUTHOR, // 0x04 null, Metadata.COMMENTS, // 0x06 Index: src/main/java/org/apache/tika/parser/image/ImageMetadataExtractor.java =================================================================== --- src/main/java/org/apache/tika/parser/image/ImageMetadataExtractor.java (revision 1339249) +++ src/main/java/org/apache/tika/parser/image/ImageMetadataExtractor.java (working copy) @@ -33,6 +33,7 @@ import org.apache.tika.metadata.Geographic; import org.apache.tika.metadata.Metadata; import org.apache.tika.metadata.Property; +import org.apache.tika.metadata.TikaCoreProperties; import org.xml.sax.SAXException; import com.drew.imaging.jpeg.JpegProcessingException; @@ -300,9 +301,9 @@ * Use IPTC for other annotation fields, and XMP for unicode support. */ public void handleCommentTags(Directory directory, Metadata metadata) { - if (metadata.get(Metadata.DESCRIPTION) == null && + if (metadata.get(TikaCoreProperties.DESCRIPTION) == null && directory.containsTag(ExifDirectory.TAG_IMAGE_DESCRIPTION)) { - metadata.set(Metadata.DESCRIPTION, directory.getString(ExifDirectory.TAG_IMAGE_DESCRIPTION)); + metadata.set(TikaCoreProperties.DESCRIPTION, directory.getString(ExifDirectory.TAG_IMAGE_DESCRIPTION)); } } /** @@ -415,7 +416,7 @@ // Unless we have GPS time we don't know the time zone so date must be set // as ISO 8601 datetime without timezone suffix (no Z or +/-) String datetimeNoTimeZone = DATE_UNSPECIFIED_TZ.format(original); // Same time zone as Metadata Extractor uses - metadata.set(Metadata.DATE, datetimeNoTimeZone); + metadata.set(TikaCoreProperties.DATE, datetimeNoTimeZone); metadata.set(Metadata.ORIGINAL_DATE, datetimeNoTimeZone); } if (directory.containsTag(ExifDirectory.TAG_DATETIME)) { @@ -424,7 +425,7 @@ metadata.set(Metadata.LAST_MODIFIED, datetimeNoTimeZone); // If Date/Time Original does not exist this might be creation date if (original == null) { - metadata.set(Metadata.DATE, datetimeNoTimeZone); + metadata.set(TikaCoreProperties.DATE, datetimeNoTimeZone); } } } @@ -447,15 +448,15 @@ } } if (directory.containsTag(IptcDirectory.TAG_HEADLINE)) { - metadata.set(Metadata.TITLE, directory.getString(IptcDirectory.TAG_HEADLINE)); + metadata.set(TikaCoreProperties.TITLE, directory.getString(IptcDirectory.TAG_HEADLINE)); } else if (directory.containsTag(IptcDirectory.TAG_OBJECT_NAME)) { - metadata.set(Metadata.TITLE, directory.getString(IptcDirectory.TAG_OBJECT_NAME)); + metadata.set(TikaCoreProperties.TITLE, directory.getString(IptcDirectory.TAG_OBJECT_NAME)); } if (directory.containsTag(IptcDirectory.TAG_BY_LINE)) { metadata.set(Metadata.AUTHOR, directory.getString(IptcDirectory.TAG_BY_LINE)); } if (directory.containsTag(IptcDirectory.TAG_CAPTION)) { - metadata.set(Metadata.DESCRIPTION, + metadata.set(TikaCoreProperties.DESCRIPTION, // Looks like metadata extractor returns IPTC newlines as a single carriage return, // but the exiv2 command does not so we change to line feed here because that is less surprising to users directory.getString(IptcDirectory.TAG_CAPTION).replaceAll("\r\n?", "\n")); Index: src/main/java/org/apache/tika/parser/image/PSDParser.java =================================================================== --- src/main/java/org/apache/tika/parser/image/PSDParser.java (revision 1339249) +++ src/main/java/org/apache/tika/parser/image/PSDParser.java (working copy) @@ -29,6 +29,7 @@ import org.apache.tika.io.EndianUtils; import org.apache.tika.metadata.Metadata; import org.apache.tika.metadata.TIFF; +import org.apache.tika.metadata.TikaCoreProperties; import org.apache.tika.mime.MediaType; import org.apache.tika.parser.AbstractParser; import org.apache.tika.parser.ParseContext; @@ -114,7 +115,7 @@ // Is it one we can do something useful with? if(rb.id == ResourceBlock.ID_CAPTION) { - metadata.add(Metadata.DESCRIPTION, rb.getDataAsString()); + metadata.add(TikaCoreProperties.DESCRIPTION, rb.getDataAsString()); } else if(rb.id == ResourceBlock.ID_EXIF_1) { // TODO Parse the EXIF info } else if(rb.id == ResourceBlock.ID_EXIF_3) { Index: src/main/java/org/apache/tika/parser/image/xmp/JempboxExtractor.java =================================================================== --- src/main/java/org/apache/tika/parser/image/xmp/JempboxExtractor.java (revision 1339328) +++ src/main/java/org/apache/tika/parser/image/xmp/JempboxExtractor.java (working copy) @@ -28,8 +28,8 @@ import org.apache.jempbox.xmp.XMPMetadata; import org.apache.jempbox.xmp.XMPSchemaDublinCore; import org.apache.tika.exception.TikaException; -import org.apache.tika.metadata.DublinCore; import org.apache.tika.metadata.Metadata; +import org.apache.tika.metadata.TikaCoreProperties; import org.xml.sax.InputSource; public class JempboxExtractor { @@ -59,18 +59,18 @@ XMPSchemaDublinCore dc = xmp.getDublinCoreSchema(); if (dc != null) { if (dc.getTitle() != null) { - metadata.set(Metadata.TITLE, dc.getTitle()); + metadata.set(TikaCoreProperties.TITLE, dc.getTitle()); } if (dc.getDescription() != null) { - metadata.set(Metadata.DESCRIPTION, dc.getDescription()); + metadata.set(TikaCoreProperties.DESCRIPTION, dc.getDescription()); } if (dc.getCreators() != null && dc.getCreators().size() > 0) { - metadata.set(Metadata.CREATOR, joinCreators(dc.getCreators())); + metadata.set(TikaCoreProperties.CREATOR, joinCreators(dc.getCreators())); } if (dc.getSubjects() != null && dc.getSubjects().size() > 0) { Iterator keywords = dc.getSubjects().iterator(); while (keywords.hasNext()) { - metadata.add(Metadata.SUBJECT, keywords.next()); + metadata.add(TikaCoreProperties.SUBJECT, keywords.next()); } // TODO should we set KEYWORDS too? // All tested photo managers set the same in Iptc.Application2.Keywords and Xmp.dc.subject Index: src/main/java/org/apache/tika/parser/image/MetadataFields.java =================================================================== --- src/main/java/org/apache/tika/parser/image/MetadataFields.java (revision 1339249) +++ src/main/java/org/apache/tika/parser/image/MetadataFields.java (working copy) @@ -22,6 +22,7 @@ import org.apache.tika.metadata.Metadata; import org.apache.tika.metadata.Property; +import org.apache.tika.metadata.TikaCoreProperties; /** * Knowns about all declared {@link Metadata} fields. @@ -32,9 +33,8 @@ private static HashSet known; - static { - known = new HashSet(); - Field[] fields = Metadata.class.getFields(); + private static void setKnownForClass(Class clazz) { + Field[] fields = clazz.getFields(); for (Field f : fields) { int mod = f.getModifiers(); if (Modifier.isPublic(mod) && Modifier.isStatic(mod) && Modifier.isFinal(mod)) { @@ -67,8 +67,18 @@ } } + static { + known = new HashSet(); + setKnownForClass(TikaCoreProperties.class); + setKnownForClass(Metadata.class); + } + public static boolean isMetadataField(String name) { return known.contains(name); } + public static boolean isMetadataField(Property property) { + return known.contains(property.getName()); + } + } Index: src/main/java/org/apache/tika/parser/mail/MailContentHandler.java =================================================================== --- src/main/java/org/apache/tika/parser/mail/MailContentHandler.java (revision 1339249) +++ src/main/java/org/apache/tika/parser/mail/MailContentHandler.java (working copy) @@ -24,7 +24,6 @@ import org.apache.james.mime4j.codec.DecoderUtil; import org.apache.james.mime4j.dom.address.Address; import org.apache.james.mime4j.dom.address.AddressList; -import org.apache.james.mime4j.dom.address.Group; import org.apache.james.mime4j.dom.address.Mailbox; import org.apache.james.mime4j.dom.address.MailboxList; import org.apache.james.mime4j.dom.field.AddressListField; @@ -38,6 +37,7 @@ import org.apache.james.mime4j.stream.Field; import org.apache.tika.exception.TikaException; import org.apache.tika.metadata.Metadata; +import org.apache.tika.metadata.TikaCoreProperties; import org.apache.tika.parser.AutoDetectParser; import org.apache.tika.sax.BodyContentHandler; import org.apache.tika.sax.EmbeddedContentHandler; @@ -161,7 +161,7 @@ metadata.add(Metadata.AUTHOR, from); } } else if (fieldname.equalsIgnoreCase("Subject")) { - metadata.add(Metadata.SUBJECT, + metadata.add(TikaCoreProperties.SUBJECT, ((UnstructuredField) parsedField).getValue()); } else if (fieldname.equalsIgnoreCase("To")) { processAddressList(parsedField, "To:", Metadata.MESSAGE_TO); @@ -171,7 +171,7 @@ processAddressList(parsedField, "Bcc:", Metadata.MESSAGE_BCC); } else if (fieldname.equalsIgnoreCase("Date")) { DateTimeField dateField = (DateTimeField) parsedField; - metadata.set(Metadata.DATE, dateField.getDate()); + metadata.set(TikaCoreProperties.DATE, dateField.getDate()); metadata.set(Metadata.CREATION_DATE, dateField.getDate()); } } catch (RuntimeException me) { Index: src/main/java/org/apache/tika/parser/rtf/TextExtractor.java =================================================================== --- src/main/java/org/apache/tika/parser/rtf/TextExtractor.java (revision 1339249) +++ src/main/java/org/apache/tika/parser/rtf/TextExtractor.java (working copy) @@ -32,6 +32,7 @@ import org.apache.tika.exception.TikaException; import org.apache.tika.metadata.Metadata; +import org.apache.tika.metadata.TikaCoreProperties; import org.apache.tika.sax.XHTMLContentHandler; import org.apache.tika.utils.CharsetUtils; import org.xml.sax.SAXException; @@ -827,9 +828,9 @@ if (equals("author")) { nextMetaData = Metadata.AUTHOR; } else if (equals("title")) { - nextMetaData = Metadata.TITLE; + nextMetaData = TikaCoreProperties.TITLE.getName(); } else if (equals("subject")) { - nextMetaData = Metadata.SUBJECT; + nextMetaData = TikaCoreProperties.SUBJECT.getName(); } else if (equals("keywords")) { nextMetaData = Metadata.KEYWORDS; } else if (equals("category")) { Index: src/main/java/org/apache/tika/parser/iwork/NumbersContentHandler.java =================================================================== --- src/main/java/org/apache/tika/parser/iwork/NumbersContentHandler.java (revision 1339249) +++ src/main/java/org/apache/tika/parser/iwork/NumbersContentHandler.java (working copy) @@ -17,6 +17,8 @@ package org.apache.tika.parser.iwork; import org.apache.tika.metadata.Metadata; +import org.apache.tika.metadata.Property; +import org.apache.tika.metadata.TikaCoreProperties; import org.apache.tika.sax.XHTMLContentHandler; import org.xml.sax.Attributes; import org.xml.sax.SAXException; @@ -36,7 +38,7 @@ private boolean parseText = false; private boolean inMetadata = false; - private String metadataKey; + private Property metadataKey; private String metadataPropertyQName; private boolean inTable = false; @@ -202,11 +204,13 @@ } } - private String resolveMetadataKey(String localName) { + private Property resolveMetadataKey(String localName) { if ("authors".equals(localName)) { - return Metadata.AUTHOR; + return Property.internalText(Metadata.AUTHOR); } - - return localName; + if ("title".equals(localName)) { + return TikaCoreProperties.TITLE; + } + return Property.internalText(localName); } } \ No newline at end of file Index: src/main/java/org/apache/tika/parser/iwork/KeynoteContentHandler.java =================================================================== --- src/main/java/org/apache/tika/parser/iwork/KeynoteContentHandler.java (revision 1339249) +++ src/main/java/org/apache/tika/parser/iwork/KeynoteContentHandler.java (working copy) @@ -17,6 +17,7 @@ package org.apache.tika.parser.iwork; import org.apache.tika.metadata.Metadata; +import org.apache.tika.metadata.TikaCoreProperties; import org.apache.tika.sax.XHTMLContentHandler; import org.xml.sax.Attributes; import org.xml.sax.SAXException; @@ -90,7 +91,7 @@ } else if (inMetadata && "key:authors".equals(qName)) { inMetaDataAuthors = true; } else if (inMetaDataTitle && "key:string".equals(qName)) { - metadata.set(Metadata.TITLE, attributes.getValue("sfa:string")); + metadata.set(TikaCoreProperties.TITLE, attributes.getValue("sfa:string")); } else if (inMetaDataAuthors && "key:string".equals(qName)) { metadata.add(Metadata.AUTHOR, attributes.getValue("sfa:string")); } else if (inSlide && "sf:tabular-model".equals(qName)) { Index: src/main/java/org/apache/tika/parser/iwork/PagesContentHandler.java =================================================================== --- src/main/java/org/apache/tika/parser/iwork/PagesContentHandler.java (revision 1339249) +++ src/main/java/org/apache/tika/parser/iwork/PagesContentHandler.java (working copy) @@ -18,6 +18,7 @@ import org.apache.tika.metadata.Metadata; import org.apache.tika.metadata.Property; +import org.apache.tika.metadata.TikaCoreProperties; import org.apache.tika.sax.XHTMLContentHandler; import org.xml.sax.Attributes; import org.xml.sax.SAXException; @@ -252,13 +253,13 @@ if ("sf:authors".equals(metaDataQName)) { metaDataKey = Metadata.AUTHOR; } else if ("sf:title".equals(metaDataQName)) { - metaDataKey = Metadata.TITLE; + metaDataKey = TikaCoreProperties.TITLE; } else if ("sl:SLCreationDateProperty".equals(metaDataQName)) { metaDataKey = Metadata.CREATION_DATE; } else if ("sl:SLLastModifiedDateProperty".equals(metaDataQName)) { metaDataKey = Metadata.LAST_MODIFIED; } else if ("sl:language".equals(metaDataQName)) { - metaDataKey = Metadata.LANGUAGE; + metaDataKey = TikaCoreProperties.LANGUAGE; } return metaDataKey; } Index: src/main/java/org/apache/tika/parser/mp3/Mp3Parser.java =================================================================== --- src/main/java/org/apache/tika/parser/mp3/Mp3Parser.java (revision 1339249) +++ src/main/java/org/apache/tika/parser/mp3/Mp3Parser.java (working copy) @@ -25,6 +25,7 @@ import org.apache.tika.exception.TikaException; import org.apache.tika.metadata.Metadata; +import org.apache.tika.metadata.TikaCoreProperties; import org.apache.tika.metadata.XMPDM; import org.apache.tika.mime.MediaType; import org.apache.tika.parser.AbstractParser; @@ -71,7 +72,7 @@ if (audioAndTags.tags.length > 0) { CompositeTagHandler tag = new CompositeTagHandler(audioAndTags.tags); - metadata.set(Metadata.TITLE, tag.getTitle()); + metadata.set(TikaCoreProperties.TITLE, tag.getTitle()); metadata.set(Metadata.AUTHOR, tag.getArtist()); metadata.set(XMPDM.ARTIST, tag.getArtist()); metadata.set(XMPDM.COMPOSER, tag.getComposer()); Index: src/main/java/org/apache/tika/parser/iptc/IptcAnpaParser.java =================================================================== --- src/main/java/org/apache/tika/parser/iptc/IptcAnpaParser.java (revision 1339328) +++ src/main/java/org/apache/tika/parser/iptc/IptcAnpaParser.java (working copy) @@ -18,8 +18,6 @@ import java.io.IOException; import java.io.InputStream; -import java.io.UnsupportedEncodingException; -import java.nio.charset.Charset; import java.text.ParseException; import java.text.SimpleDateFormat; import java.util.Collections; @@ -29,8 +27,8 @@ import java.util.TimeZone; import org.apache.tika.exception.TikaException; -import org.apache.tika.metadata.DublinCore; import org.apache.tika.metadata.Metadata; +import org.apache.tika.metadata.TikaCoreProperties; import org.apache.tika.mime.MediaType; import org.apache.tika.parser.ParseContext; import org.apache.tika.parser.Parser; @@ -772,19 +770,19 @@ // every property that gets set must be non-null, or it will cause NPE // in other consuming applications, like Lucene metadata.set(Metadata.CONTENT_TYPE, clean("text/anpa-1312")); - metadata.set(Metadata.TITLE, clean(properties.get("title"))); - metadata.set(Metadata.SUBJECT, clean(properties.get("subject"))); + metadata.set(TikaCoreProperties.TITLE, clean(properties.get("title"))); + metadata.set(TikaCoreProperties.SUBJECT, clean(properties.get("subject"))); metadata.set(Metadata.AUTHOR, clean(properties.get("author"))); metadata.set(Metadata.CREATION_DATE, clean(properties.get("created"))); - metadata.set(Metadata.MODIFIED, clean(properties.get("modified"))); - metadata.set(Metadata.SOURCE, clean(properties.get("source"))); -// metadata.set(Metadata.PUBLISHER, clean(properties.get("publisher"))); - metadata.set(Metadata.PUBLISHER, clean(this.getFormatName())); + metadata.set(TikaCoreProperties.MODIFIED, clean(properties.get("modified"))); + metadata.set(TikaCoreProperties.SOURCE, clean(properties.get("source"))); +// metadata.set(TikaCoreProperties.PUBLISHER, clean(properties.get("publisher"))); + metadata.set(TikaCoreProperties.PUBLISHER, clean(this.getFormatName())); /* - metadata.set(Metadata.DATE, font.getHeader().getCreated().getTime()); + metadata.set(TikaCoreProperties.DATE, font.getHeader().getCreated().getTime()); metadata.set( - Property.internalDate(Metadata.MODIFIED), + Property.internalDate(TikaCoreProperties.MODIFIED), font.getHeader().getModified().getTime()); */ } Index: src/main/java/org/apache/tika/parser/xml/DcXMLParser.java =================================================================== --- src/main/java/org/apache/tika/parser/xml/DcXMLParser.java (revision 1339328) +++ src/main/java/org/apache/tika/parser/xml/DcXMLParser.java (working copy) @@ -16,8 +16,9 @@ */ package org.apache.tika.parser.xml; -import org.apache.tika.metadata.DublinCore; import org.apache.tika.metadata.Metadata; +import org.apache.tika.metadata.Property; +import org.apache.tika.metadata.TikaCoreProperties; import org.apache.tika.parser.ParseContext; import org.apache.tika.sax.TeeContentHandler; import org.xml.sax.ContentHandler; @@ -31,28 +32,28 @@ private static final long serialVersionUID = 4905318835463880819L; private static ContentHandler getDublinCoreHandler( - Metadata metadata, String name, String element) { + Metadata metadata, Property property, String element) { return new ElementMetadataHandler( "http://purl.org/dc/elements/1.1/", element, - metadata, name); + metadata, property); } protected ContentHandler getContentHandler( ContentHandler handler, Metadata metadata, ParseContext context) { return new TeeContentHandler( super.getContentHandler(handler, metadata, context), - getDublinCoreHandler(metadata, Metadata.TITLE, "title"), - getDublinCoreHandler(metadata, Metadata.SUBJECT, "subject"), - getDublinCoreHandler(metadata, Metadata.CREATOR, "creator"), - getDublinCoreHandler(metadata, Metadata.DESCRIPTION, "description"), - getDublinCoreHandler(metadata, Metadata.PUBLISHER, "publisher"), - getDublinCoreHandler(metadata, Metadata.CONTRIBUTOR, "contributor"), - getDublinCoreHandler(metadata, Metadata.DATE.getName(), "date"), - getDublinCoreHandler(metadata, Metadata.TYPE, "type"), - getDublinCoreHandler(metadata, Metadata.FORMAT, "format"), - getDublinCoreHandler(metadata, Metadata.IDENTIFIER, "identifier"), - getDublinCoreHandler(metadata, Metadata.LANGUAGE, "language"), - getDublinCoreHandler(metadata, Metadata.RIGHTS, "rights")); + getDublinCoreHandler(metadata, TikaCoreProperties.TITLE, "title"), + getDublinCoreHandler(metadata, TikaCoreProperties.SUBJECT, "subject"), + getDublinCoreHandler(metadata, TikaCoreProperties.CREATOR, "creator"), + getDublinCoreHandler(metadata, TikaCoreProperties.DESCRIPTION, "description"), + getDublinCoreHandler(metadata, TikaCoreProperties.PUBLISHER, "publisher"), + getDublinCoreHandler(metadata, TikaCoreProperties.CONTRIBUTOR, "contributor"), + getDublinCoreHandler(metadata, TikaCoreProperties.DATE, "date"), + getDublinCoreHandler(metadata, TikaCoreProperties.TYPE, "type"), + getDublinCoreHandler(metadata, TikaCoreProperties.FORMAT, "format"), + getDublinCoreHandler(metadata, TikaCoreProperties.IDENTIFIER, "identifier"), + getDublinCoreHandler(metadata, TikaCoreProperties.LANGUAGE, "language"), + getDublinCoreHandler(metadata, TikaCoreProperties.RIGHTS, "rights")); } } Index: src/main/java/org/apache/tika/parser/xml/ElementMetadataHandler.java =================================================================== --- src/main/java/org/apache/tika/parser/xml/ElementMetadataHandler.java (revision 1339249) +++ src/main/java/org/apache/tika/parser/xml/ElementMetadataHandler.java (working copy) @@ -164,12 +164,11 @@ if (logger.isTraceEnabled()) { logger.trace("adding " + name + "=" + value); } - if (targetProperty != null && targetProperty.getPropertyType() != null && - targetProperty.getPropertyType() == Property.PropertyType.BAG) { + if (targetProperty != null && targetProperty.isMultiValuePermitted()) { if (value != null && value.length() > 0) { String[] previous = metadata.getValues(name); if (previous == null || !Arrays.asList(previous).contains(value)) { - metadata.add(name, value); + metadata.add(targetProperty, value); } } } else { Index: src/main/java/org/apache/tika/parser/mp4/MP4Parser.java =================================================================== --- src/main/java/org/apache/tika/parser/mp4/MP4Parser.java (revision 1339249) +++ src/main/java/org/apache/tika/parser/mp4/MP4Parser.java (working copy) @@ -30,6 +30,7 @@ import org.apache.tika.io.TikaInputStream; import org.apache.tika.metadata.Metadata; import org.apache.tika.metadata.Property; +import org.apache.tika.metadata.TikaCoreProperties; import org.apache.tika.metadata.XMPDM; import org.apache.tika.mime.MediaType; import org.apache.tika.parser.AbstractParser; @@ -162,7 +163,7 @@ MP4TimeToDate(mHeader.getCreationTime()) ); metadata.set( - Property.externalDate(Metadata.MODIFIED), // TODO Should be a real property + TikaCoreProperties.MODIFIED, MP4TimeToDate(mHeader.getModificationTime()) ); @@ -188,7 +189,7 @@ MP4TimeToDate(header.getCreationTime()) ); metadata.set( - Property.externalDate(Metadata.MODIFIED), // TODO Should be a real property + TikaCoreProperties.MODIFIED, MP4TimeToDate(header.getModificationTime()) ); @@ -224,7 +225,7 @@ if (apple != null) { // Title AppleTrackTitleBox title = getOrNull(apple, AppleTrackTitleBox.class); - addMetadata(Metadata.TITLE, metadata, title); + addMetadata(TikaCoreProperties.TITLE, metadata, title); // Artist AppleArtistBox artist = getOrNull(apple, AppleArtistBox.class); Index: src/main/java/org/apache/tika/parser/feed/FeedParser.java =================================================================== --- src/main/java/org/apache/tika/parser/feed/FeedParser.java (revision 1339249) +++ src/main/java/org/apache/tika/parser/feed/FeedParser.java (working copy) @@ -26,6 +26,7 @@ import org.apache.tika.exception.TikaException; import org.apache.tika.io.CloseShieldInputStream; import org.apache.tika.metadata.Metadata; +import org.apache.tika.metadata.TikaCoreProperties; import org.apache.tika.mime.MediaType; import org.apache.tika.parser.AbstractParser; import org.apache.tika.parser.ParseContext; @@ -72,8 +73,8 @@ String title = stripTags(feed.getTitleEx()); String description = stripTags(feed.getDescriptionEx()); - metadata.set(Metadata.TITLE, title); - metadata.set(Metadata.DESCRIPTION, description); + metadata.set(TikaCoreProperties.TITLE, title); + metadata.set(TikaCoreProperties.DESCRIPTION, description); // store the other fields in the metadata XHTMLContentHandler xhtml = Index: src/main/java/org/apache/tika/parser/netcdf/NetCDFParser.java =================================================================== --- src/main/java/org/apache/tika/parser/netcdf/NetCDFParser.java (revision 1339249) +++ src/main/java/org/apache/tika/parser/netcdf/NetCDFParser.java (working copy) @@ -26,6 +26,8 @@ import org.apache.tika.exception.TikaException; import org.apache.tika.io.IOUtils; import org.apache.tika.metadata.Metadata; +import org.apache.tika.metadata.Property; +import org.apache.tika.metadata.TikaCoreProperties; import org.apache.tika.mime.MediaType; import org.apache.tika.parser.AbstractParser; import org.apache.tika.parser.ParseContext; @@ -86,12 +88,12 @@ // first parse out the set of global attributes for (Attribute attr : ncFile.getGlobalAttributes()) { - String attrName = attr.getName(); + Property property = resolveMetadataKey(attr.getName()); if (attr.getDataType().isString()) { - metadata.add(attrName, attr.getStringValue()); + metadata.add(property, attr.getStringValue()); } else if (attr.getDataType().isNumeric()) { int value = attr.getNumericValue().intValue(); - metadata.add(attrName, String.valueOf(value)); + metadata.add(property, String.valueOf(value)); } } } catch (IOException e) { @@ -102,5 +104,12 @@ xhtml.startDocument(); xhtml.endDocument(); } + + private Property resolveMetadataKey(String localName) { + if ("title".equals(localName)) { + return TikaCoreProperties.TITLE; + } + return Property.internalText(localName); + } } Index: src/main/java/org/apache/tika/parser/html/HtmlParser.java =================================================================== --- src/main/java/org/apache/tika/parser/html/HtmlParser.java (revision 1339249) +++ src/main/java/org/apache/tika/parser/html/HtmlParser.java (working copy) @@ -148,7 +148,7 @@ String language = match.getLanguage(); if (language != null) { metadata.set(Metadata.CONTENT_LANGUAGE, match.getLanguage()); - metadata.set(Metadata.LANGUAGE, match.getLanguage()); + metadata.set(TikaCoreProperties.LANGUAGE, match.getLanguage()); } */ Index: src/main/java/org/apache/tika/parser/html/HtmlHandler.java =================================================================== --- src/main/java/org/apache/tika/parser/html/HtmlHandler.java (revision 1339249) +++ src/main/java/org/apache/tika/parser/html/HtmlHandler.java (working copy) @@ -26,6 +26,7 @@ import java.util.regex.Pattern; import org.apache.tika.metadata.Metadata; +import org.apache.tika.metadata.TikaCoreProperties; import org.apache.tika.mime.MediaType; import org.apache.tika.sax.TextContentHandler; import org.apache.tika.sax.XHTMLContentHandler; @@ -233,7 +234,7 @@ if (titleLevel > 0) { titleLevel--; if (titleLevel == 0) { - metadata.set(Metadata.TITLE, title.toString().trim()); + metadata.set(TikaCoreProperties.TITLE, title.toString().trim()); } } if (bodyLevel > 0) { Index: src/main/java/org/apache/tika/parser/mbox/MboxParser.java =================================================================== --- src/main/java/org/apache/tika/parser/mbox/MboxParser.java (revision 1339249) +++ src/main/java/org/apache/tika/parser/mbox/MboxParser.java (working copy) @@ -32,6 +32,7 @@ import org.apache.tika.exception.TikaException; import org.apache.tika.metadata.Metadata; +import org.apache.tika.metadata.TikaCoreProperties; import org.apache.tika.mime.MediaType; import org.apache.tika.parser.AbstractParser; import org.apache.tika.parser.ParseContext; @@ -198,7 +199,7 @@ if (headerTag.equalsIgnoreCase("From")) { metadata.add(Metadata.AUTHOR, headerContent); - metadata.add(Metadata.CREATOR, headerContent); + metadata.set(TikaCoreProperties.CREATOR, headerContent); } else if (headerTag.equalsIgnoreCase("To") || headerTag.equalsIgnoreCase("Cc") || headerTag.equalsIgnoreCase("Bcc")) { @@ -217,26 +218,26 @@ } metadata.add(property, headerContent); } else if (headerTag.equalsIgnoreCase("Subject")) { - metadata.add(Metadata.SUBJECT, headerContent); - metadata.add(Metadata.TITLE, headerContent); + metadata.add(TikaCoreProperties.SUBJECT, headerContent); + metadata.set(TikaCoreProperties.TITLE, headerContent); } else if (headerTag.equalsIgnoreCase("Date")) { try { Date date = parseDate(headerContent); - metadata.set(Metadata.DATE, date); + metadata.set(TikaCoreProperties.DATE, date); metadata.set(Metadata.CREATION_DATE, date); } catch (ParseException e) { // ignoring date because format was not understood } } else if (headerTag.equalsIgnoreCase("Message-Id")) { - metadata.add(Metadata.IDENTIFIER, headerContent); + metadata.set(TikaCoreProperties.IDENTIFIER, headerContent); } else if (headerTag.equalsIgnoreCase("In-Reply-To")) { - metadata.add(Metadata.RELATION, headerContent); + metadata.set(TikaCoreProperties.RELATION, headerContent); } else if (headerTag.equalsIgnoreCase("Content-Type")) { // TODO - key off content-type in headers to // set mapping to use for content and convert if necessary. metadata.add(Metadata.CONTENT_TYPE, headerContent); - metadata.add(Metadata.FORMAT, headerContent); + metadata.set(TikaCoreProperties.FORMAT, headerContent); } else { metadata.add(EMAIL_HEADER_METADATA_PREFIX + headerTag, headerContent); } Index: src/main/java/org/apache/tika/parser/microsoft/TNEFParser.java =================================================================== --- src/main/java/org/apache/tika/parser/microsoft/TNEFParser.java (revision 1339249) +++ src/main/java/org/apache/tika/parser/microsoft/TNEFParser.java (working copy) @@ -33,6 +33,7 @@ import org.apache.tika.extractor.ParsingEmbeddedDocumentExtractor; import org.apache.tika.io.TikaInputStream; import org.apache.tika.metadata.Metadata; +import org.apache.tika.metadata.TikaCoreProperties; import org.apache.tika.mime.MediaType; import org.apache.tika.parser.AbstractParser; import org.apache.tika.parser.ParseContext; @@ -81,7 +82,7 @@ // Set the message subject if known String subject = msg.getSubject(); if(subject != null && subject.length() > 0) { - metadata.set(Metadata.SUBJECT, subject); + metadata.set(TikaCoreProperties.SUBJECT, subject); } // Recurse into the message body RTF Index: src/main/java/org/apache/tika/parser/microsoft/ooxml/MetadataExtractor.java =================================================================== --- src/main/java/org/apache/tika/parser/microsoft/ooxml/MetadataExtractor.java (revision 1339249) +++ src/main/java/org/apache/tika/parser/microsoft/ooxml/MetadataExtractor.java (working copy) @@ -30,6 +30,7 @@ import org.apache.tika.metadata.Metadata; import org.apache.tika.metadata.PagedText; import org.apache.tika.metadata.Property; +import org.apache.tika.metadata.TikaCoreProperties; import org.openxmlformats.schemas.officeDocument.x2006.customProperties.CTProperty; import org.openxmlformats.schemas.officeDocument.x2006.extendedProperties.CTProperties; @@ -65,21 +66,21 @@ addProperty(metadata, Metadata.CATEGORY, propsHolder.getCategoryProperty()); addProperty(metadata, Metadata.CONTENT_STATUS, propsHolder .getContentStatusProperty()); - addProperty(metadata, Metadata.DATE, propsHolder + addProperty(metadata, TikaCoreProperties.DATE, propsHolder .getCreatedProperty()); addProperty(metadata, Metadata.CREATION_DATE, propsHolder .getCreatedProperty()); - addProperty(metadata, Metadata.CREATOR, propsHolder + addProperty(metadata, TikaCoreProperties.CREATOR, propsHolder .getCreatorProperty()); addProperty(metadata, Metadata.AUTHOR, propsHolder .getCreatorProperty()); - addProperty(metadata, Metadata.DESCRIPTION, propsHolder + addProperty(metadata, TikaCoreProperties.DESCRIPTION, propsHolder .getDescriptionProperty()); - addProperty(metadata, Metadata.IDENTIFIER, propsHolder + addProperty(metadata, TikaCoreProperties.IDENTIFIER, propsHolder .getIdentifierProperty()); addProperty(metadata, Metadata.KEYWORDS, propsHolder .getKeywordsProperty()); - addProperty(metadata, Metadata.LANGUAGE, propsHolder + addProperty(metadata, TikaCoreProperties.LANGUAGE, propsHolder .getLanguageProperty()); addProperty(metadata, Metadata.LAST_AUTHOR, propsHolder .getLastModifiedByProperty()); @@ -89,9 +90,9 @@ .getModifiedProperty()); addProperty(metadata, Metadata.REVISION_NUMBER, propsHolder .getRevisionProperty()); - addProperty(metadata, Metadata.SUBJECT, propsHolder + addProperty(metadata, TikaCoreProperties.SUBJECT, propsHolder .getSubjectProperty()); - addProperty(metadata, Metadata.TITLE, propsHolder.getTitleProperty()); + addProperty(metadata, TikaCoreProperties.TITLE, propsHolder.getTitleProperty()); addProperty(metadata, Metadata.VERSION, propsHolder.getVersionProperty()); } @@ -107,7 +108,7 @@ .getCharacters()); addProperty(metadata, Metadata.CHARACTER_COUNT_WITH_SPACES, propsHolder .getCharactersWithSpaces()); - addProperty(metadata, Metadata.PUBLISHER, propsHolder.getCompany()); + addProperty(metadata, TikaCoreProperties.PUBLISHER, propsHolder.getCompany()); addProperty(metadata, Metadata.LINE_COUNT, propsHolder.getLines()); addProperty(metadata, Metadata.MANAGER, propsHolder.getManager()); addProperty(metadata, Metadata.NOTES, propsHolder.getNotes()); @@ -234,9 +235,18 @@ } } - private void addProperty(Metadata metadata, Property property, Nullable value) { - if (value.getValue() != null) { - metadata.set(property, value.getValue()); + private void addProperty(Metadata metadata, Property property, Nullable nullableValue) { + T value = nullableValue.getValue(); + if (value != null) { + if (value instanceof Date) { + metadata.set(property, (Date) value); + } else if (value instanceof String) { + metadata.set(property, (String) value); + } else if (value instanceof Integer) { + metadata.set(property, (Integer) value); + } else if (value instanceof Double) { + metadata.set(property, (Double) value); + } } } @@ -245,6 +255,12 @@ addProperty(metadata, name, value.getValue().toString()); } } + + private void addProperty(Metadata metadata, Property property, String value) { + if (value != null) { + metadata.set(property, value); + } + } private void addProperty(Metadata metadata, String name, String value) { if (value != null) { Index: src/main/java/org/apache/tika/parser/microsoft/OutlookExtractor.java =================================================================== --- src/main/java/org/apache/tika/parser/microsoft/OutlookExtractor.java (revision 1339249) +++ src/main/java/org/apache/tika/parser/microsoft/OutlookExtractor.java (working copy) @@ -35,6 +35,7 @@ import org.apache.tika.exception.TikaException; import org.apache.tika.io.TikaInputStream; import org.apache.tika.metadata.Metadata; +import org.apache.tika.metadata.TikaCoreProperties; import org.apache.tika.parser.ParseContext; import org.apache.tika.parser.html.HtmlParser; import org.apache.tika.parser.mbox.MboxParser; @@ -102,8 +103,8 @@ metadata.set(Metadata.MESSAGE_CC, msg.getDisplayCC()); metadata.set(Metadata.MESSAGE_BCC, msg.getDisplayBCC()); - metadata.set(Metadata.TITLE, subject); - metadata.set(Metadata.SUBJECT, msg.getConversationTopic()); + metadata.set(TikaCoreProperties.TITLE, subject); + metadata.set(TikaCoreProperties.SUBJECT, msg.getConversationTopic()); try { for(String recipientAddress : msg.getRecipientEmailAddressList()) { @@ -115,7 +116,7 @@ // Date - try two ways to find it // First try via the proper chunk if(msg.getMessageDate() != null) { - metadata.set(Metadata.DATE, msg.getMessageDate().getTime()); + metadata.set(TikaCoreProperties.DATE, msg.getMessageDate().getTime()); metadata.set(Metadata.CREATION_DATE, msg.getMessageDate().getTime()); metadata.set(Metadata.LAST_SAVED, msg.getMessageDate().getTime()); } else { @@ -130,12 +131,12 @@ // See if we can parse it as a normal mail date try { Date d = MboxParser.parseDate(date); - metadata.set(Metadata.DATE, d); + metadata.set(TikaCoreProperties.DATE, d); metadata.set(Metadata.CREATION_DATE, d); metadata.set(Metadata.LAST_SAVED, d); } catch(ParseException e) { // Store it as-is, and hope for the best... - metadata.set(Metadata.DATE, date); + metadata.set(TikaCoreProperties.DATE, date); metadata.set(Metadata.CREATION_DATE, date); metadata.set(Metadata.LAST_SAVED, date); } Index: src/main/java/org/apache/tika/parser/microsoft/SummaryExtractor.java =================================================================== --- src/main/java/org/apache/tika/parser/microsoft/SummaryExtractor.java (revision 1339249) +++ src/main/java/org/apache/tika/parser/microsoft/SummaryExtractor.java (working copy) @@ -35,6 +35,7 @@ import org.apache.tika.metadata.Metadata; import org.apache.tika.metadata.PagedText; import org.apache.tika.metadata.Property; +import org.apache.tika.metadata.TikaCoreProperties; /** * Outlook Message Parser. @@ -90,10 +91,10 @@ } private void parse(SummaryInformation summary) { - set(Metadata.TITLE, summary.getTitle()); + set(TikaCoreProperties.TITLE, summary.getTitle()); set(Metadata.AUTHOR, summary.getAuthor()); set(Metadata.KEYWORDS, summary.getKeywords()); - set(Metadata.SUBJECT, summary.getSubject()); + set(TikaCoreProperties.SUBJECT, summary.getSubject()); set(Metadata.LAST_AUTHOR, summary.getLastAuthor()); set(Metadata.COMMENTS, summary.getComments()); set(Metadata.TEMPLATE, summary.getTemplate()); @@ -115,7 +116,7 @@ private void parse(DocumentSummaryInformation summary) { set(Metadata.COMPANY, summary.getCompany()); set(Metadata.MANAGER, summary.getManager()); - set(Metadata.LANGUAGE, getLanguage(summary)); + set(TikaCoreProperties.LANGUAGE, getLanguage(summary)); set(Metadata.CATEGORY, summary.getCategory()); set(Metadata.SLIDE_COUNT, summary.getSlideCount()); if (summary.getSlideCount() > 0) { @@ -175,6 +176,12 @@ metadata.set(name, value); } } + + private void set(Property property, String value) { + if (value != null) { + metadata.set(property, value); + } + } private void set(Property property, Date value) { if (value != null) { Index: src/main/java/org/apache/tika/parser/prt/PRTParser.java =================================================================== --- src/main/java/org/apache/tika/parser/prt/PRTParser.java (revision 1339249) +++ src/main/java/org/apache/tika/parser/prt/PRTParser.java (working copy) @@ -26,6 +26,7 @@ import org.apache.tika.exception.TikaException; import org.apache.tika.io.EndianUtils; import org.apache.tika.metadata.Metadata; +import org.apache.tika.metadata.TikaCoreProperties; import org.apache.tika.mime.MediaType; import org.apache.tika.parser.AbstractParser; import org.apache.tika.parser.ParseContext; @@ -85,7 +86,7 @@ "-" + dateStr.substring(6,8) + "T" + dateStr.substring(8,10) + ":" + dateStr.substring(10, 12) + ":00"; metadata.set(Metadata.CREATION_DATE, formattedDate); - metadata.set(Metadata.DATE, formattedDate); + metadata.set(TikaCoreProperties.DATE, formattedDate); } metadata.set(Metadata.CONTENT_TYPE, PRT_MIME_TYPE); @@ -94,7 +95,7 @@ IOUtils.readFully(stream, desc); String description = extractText(desc, true); if(description.length() > 0) { - metadata.set(Metadata.DESCRIPTION, description); + metadata.set(TikaCoreProperties.DESCRIPTION, description); } // Now look for text Index: src/main/java/org/apache/tika/parser/font/AdobeFontMetricParser.java =================================================================== --- src/main/java/org/apache/tika/parser/font/AdobeFontMetricParser.java (revision 1339249) +++ src/main/java/org/apache/tika/parser/font/AdobeFontMetricParser.java (working copy) @@ -27,6 +27,7 @@ import org.apache.tika.exception.TikaException; import org.apache.tika.metadata.Metadata; import org.apache.tika.metadata.Property; +import org.apache.tika.metadata.TikaCoreProperties; import org.apache.tika.mime.MediaType; import org.apache.tika.parser.AbstractParser; import org.apache.tika.parser.ParseContext; @@ -67,7 +68,7 @@ extractCreationDate( metadata, comments ); metadata.set( Metadata.CONTENT_TYPE, AFM_TYPE.toString() ); - metadata.set( Metadata.TITLE, fontMetrics.getFullName() ); + metadata.set( TikaCoreProperties.TITLE, fontMetrics.getFullName() ); // Add metadata associated with the font type addMetadataByString( metadata, "AvgCharacterWidth", Float.toString( fontMetrics.getAverageCharacterWidth() ) ); Index: src/main/java/org/apache/tika/parser/font/TrueTypeParser.java =================================================================== --- src/main/java/org/apache/tika/parser/font/TrueTypeParser.java (revision 1339328) +++ src/main/java/org/apache/tika/parser/font/TrueTypeParser.java (working copy) @@ -25,9 +25,8 @@ import org.apache.fontbox.ttf.TrueTypeFont; import org.apache.tika.exception.TikaException; import org.apache.tika.io.TikaInputStream; -import org.apache.tika.metadata.DublinCore; import org.apache.tika.metadata.Metadata; -import org.apache.tika.metadata.Property; +import org.apache.tika.metadata.TikaCoreProperties; import org.apache.tika.mime.MediaType; import org.apache.tika.parser.AbstractParser; import org.apache.tika.parser.ParseContext; @@ -67,9 +66,9 @@ } metadata.set(Metadata.CONTENT_TYPE, TYPE.toString()); - metadata.set(Metadata.DATE, font.getHeader().getCreated().getTime()); + metadata.set(TikaCoreProperties.DATE, font.getHeader().getCreated().getTime()); metadata.set( - Property.internalDate(Metadata.MODIFIED), + TikaCoreProperties.MODIFIED, font.getHeader().getModified().getTime()); XHTMLContentHandler xhtml = new XHTMLContentHandler(handler, metadata); Index: src/main/java/org/apache/tika/parser/pdf/PDFParser.java =================================================================== --- src/main/java/org/apache/tika/parser/pdf/PDFParser.java (revision 1339249) +++ src/main/java/org/apache/tika/parser/pdf/PDFParser.java (working copy) @@ -39,6 +39,7 @@ import org.apache.tika.metadata.Metadata; import org.apache.tika.metadata.PagedText; import org.apache.tika.metadata.Property; +import org.apache.tika.metadata.TikaCoreProperties; import org.apache.tika.mime.MediaType; import org.apache.tika.parser.AbstractParser; import org.apache.tika.parser.ParseContext; @@ -152,12 +153,12 @@ throws TikaException { PDDocumentInformation info = document.getDocumentInformation(); metadata.set(PagedText.N_PAGES, document.getNumberOfPages()); - addMetadata(metadata, Metadata.TITLE, info.getTitle()); + addMetadata(metadata, TikaCoreProperties.TITLE, info.getTitle()); addMetadata(metadata, Metadata.AUTHOR, info.getAuthor()); - addMetadata(metadata, Metadata.CREATOR, info.getCreator()); + addMetadata(metadata, TikaCoreProperties.CREATOR, info.getCreator()); addMetadata(metadata, Metadata.KEYWORDS, info.getKeywords()); addMetadata(metadata, "producer", info.getProducer()); - addMetadata(metadata, Metadata.SUBJECT, info.getSubject()); + addMetadata(metadata, TikaCoreProperties.SUBJECT, info.getSubject()); addMetadata(metadata, "trapped", info.getTrapped()); try { addMetadata(metadata, "created", info.getCreationDate()); @@ -186,6 +187,12 @@ } } + private void addMetadata(Metadata metadata, Property property, String value) { + if (value != null) { + metadata.add(property, value); + } + } + private void addMetadata(Metadata metadata, String name, String value) { if (value != null) { metadata.add(name, value);