You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@tika.apache.org by ta...@apache.org on 2016/06/29 13:28:52 UTC
tika git commit: fix getRecursiveJson -> getRecursiveMetadata in
TikaTest, no json is involved here...
Repository: tika
Updated Branches:
refs/heads/master a57d8364c -> 23a11eff3
fix getRecursiveJson -> getRecursiveMetadata in TikaTest, no json is involved here...
Project: http://git-wip-us.apache.org/repos/asf/tika/repo
Commit: http://git-wip-us.apache.org/repos/asf/tika/commit/23a11eff
Tree: http://git-wip-us.apache.org/repos/asf/tika/tree/23a11eff
Diff: http://git-wip-us.apache.org/repos/asf/tika/diff/23a11eff
Branch: refs/heads/master
Commit: 23a11eff3018977f031cce663bb412678f08ba89
Parents: a57d836
Author: tballison <ta...@mitre.org>
Authored: Wed Jun 29 09:28:44 2016 -0400
Committer: tballison <ta...@mitre.org>
Committed: Wed Jun 29 09:28:44 2016 -0400
----------------------------------------------------------------------
.../src/test/java/org/apache/tika/TikaTest.java | 6 +++---
.../parser/apple/AppleSingleFileParserTest.java | 2 +-
.../tika/parser/microsoft/ExcelParserTest.java | 2 +-
.../microsoft/POIContainerExtractionTest.java | 4 ++--
.../tika/parser/microsoft/PowerPointParserTest.java | 2 +-
.../tika/parser/microsoft/WordParserTest.java | 2 +-
.../ooxml/OOXMLContainerExtractionTest.java | 2 +-
.../parser/microsoft/ooxml/OOXMLParserTest.java | 6 +++---
.../parser/microsoft/xml/XML2003ParserTest.java | 2 +-
.../org/apache/tika/parser/pdf/PDFParserTest.java | 16 ++++++++--------
.../org/apache/tika/parser/rtf/RTFParserTest.java | 2 +-
11 files changed, 23 insertions(+), 23 deletions(-)
----------------------------------------------------------------------
http://git-wip-us.apache.org/repos/asf/tika/blob/23a11eff/tika-core/src/test/java/org/apache/tika/TikaTest.java
----------------------------------------------------------------------
diff --git a/tika-core/src/test/java/org/apache/tika/TikaTest.java b/tika-core/src/test/java/org/apache/tika/TikaTest.java
index c1e7b36b..a699ac8 100644
--- a/tika-core/src/test/java/org/apache/tika/TikaTest.java
+++ b/tika-core/src/test/java/org/apache/tika/TikaTest.java
@@ -152,11 +152,11 @@ public abstract class TikaTest {
}
}
- protected List<Metadata> getRecursiveJson(String filePath) throws Exception {
- return getRecursiveJson(filePath, new ParseContext());
+ protected List<Metadata> getRecursiveMetadata(String filePath) throws Exception {
+ return getRecursiveMetadata(filePath, new ParseContext());
}
- protected List<Metadata> getRecursiveJson(String filePath, ParseContext context) throws Exception {
+ protected List<Metadata> getRecursiveMetadata(String filePath, ParseContext context) throws Exception {
Parser p = new AutoDetectParser();
RecursiveParserWrapper wrapper = new RecursiveParserWrapper(p,
new BasicContentHandlerFactory(BasicContentHandlerFactory.HANDLER_TYPE.XML, -1));
http://git-wip-us.apache.org/repos/asf/tika/blob/23a11eff/tika-parsers/src/test/java/org/apache/tika/parser/apple/AppleSingleFileParserTest.java
----------------------------------------------------------------------
diff --git a/tika-parsers/src/test/java/org/apache/tika/parser/apple/AppleSingleFileParserTest.java b/tika-parsers/src/test/java/org/apache/tika/parser/apple/AppleSingleFileParserTest.java
index f5c8dd1..8a1c831 100644
--- a/tika-parsers/src/test/java/org/apache/tika/parser/apple/AppleSingleFileParserTest.java
+++ b/tika-parsers/src/test/java/org/apache/tika/parser/apple/AppleSingleFileParserTest.java
@@ -34,7 +34,7 @@ public class AppleSingleFileParserTest extends TikaTest {
@Test
public void testBasic() throws Exception {
- List<Metadata> list = getRecursiveJson("testAppleSingleFile.pdf");
+ List<Metadata> list = getRecursiveMetadata("testAppleSingleFile.pdf");
assertEquals(2, list.size());
assertContains(AppleSingleFileParser.class.getName(),
Arrays.asList(list.get(0).getValues("X-Parsed-By")));
http://git-wip-us.apache.org/repos/asf/tika/blob/23a11eff/tika-parsers/src/test/java/org/apache/tika/parser/microsoft/ExcelParserTest.java
----------------------------------------------------------------------
diff --git a/tika-parsers/src/test/java/org/apache/tika/parser/microsoft/ExcelParserTest.java b/tika-parsers/src/test/java/org/apache/tika/parser/microsoft/ExcelParserTest.java
index d2d6f1a..fe8edd2 100644
--- a/tika-parsers/src/test/java/org/apache/tika/parser/microsoft/ExcelParserTest.java
+++ b/tika-parsers/src/test/java/org/apache/tika/parser/microsoft/ExcelParserTest.java
@@ -459,7 +459,7 @@ public class ExcelParserTest extends TikaTest {
@Test
public void testEmbeddedPDF() throws Exception {
- List<Metadata> metadataList = getRecursiveJson("testExcel_embeddedPDF.xls");
+ List<Metadata> metadataList = getRecursiveMetadata("testExcel_embeddedPDF.xls");
assertContains("Hello World!", metadataList.get(2).get(RecursiveParserWrapper.TIKA_CONTENT));
}
}
http://git-wip-us.apache.org/repos/asf/tika/blob/23a11eff/tika-parsers/src/test/java/org/apache/tika/parser/microsoft/POIContainerExtractionTest.java
----------------------------------------------------------------------
diff --git a/tika-parsers/src/test/java/org/apache/tika/parser/microsoft/POIContainerExtractionTest.java b/tika-parsers/src/test/java/org/apache/tika/parser/microsoft/POIContainerExtractionTest.java
index 25e567f..b59bb00 100644
--- a/tika-parsers/src/test/java/org/apache/tika/parser/microsoft/POIContainerExtractionTest.java
+++ b/tika-parsers/src/test/java/org/apache/tika/parser/microsoft/POIContainerExtractionTest.java
@@ -350,7 +350,7 @@ public class POIContainerExtractionTest extends AbstractPOIContainerExtractionTe
@Test
public void testEmbeddedStorageId() throws Exception {
- List<Metadata> list = getRecursiveJson("testWORD_embeded.doc");
+ List<Metadata> list = getRecursiveMetadata("testWORD_embeded.doc");
//.docx
assertEquals("{F4754C9B-64F5-4B40-8AF4-679732AC0607}",
list.get(10).get(TikaMetadataKeys.EMBEDDED_STORAGE_CLASS_ID));
@@ -368,7 +368,7 @@ public class POIContainerExtractionTest extends AbstractPOIContainerExtractionTe
//doc converts a chart to a actual xls file
//so we only need to look in ppt and xls
for (String suffix : new String[]{"ppt", "xls"}) {
- List<Metadata> list = getRecursiveJson("testMSChart-govdocs-428996."+suffix);
+ List<Metadata> list = getRecursiveMetadata("testMSChart-govdocs-428996."+suffix);
boolean found = false;
for (Metadata m : list) {
if (m.get(Metadata.CONTENT_TYPE).equals(POIFSContainerDetector.MS_GRAPH_CHART.toString())) {
http://git-wip-us.apache.org/repos/asf/tika/blob/23a11eff/tika-parsers/src/test/java/org/apache/tika/parser/microsoft/PowerPointParserTest.java
----------------------------------------------------------------------
diff --git a/tika-parsers/src/test/java/org/apache/tika/parser/microsoft/PowerPointParserTest.java b/tika-parsers/src/test/java/org/apache/tika/parser/microsoft/PowerPointParserTest.java
index 478abf0..ca20be7 100644
--- a/tika-parsers/src/test/java/org/apache/tika/parser/microsoft/PowerPointParserTest.java
+++ b/tika-parsers/src/test/java/org/apache/tika/parser/microsoft/PowerPointParserTest.java
@@ -243,7 +243,7 @@ public class PowerPointParserTest extends TikaTest {
@Test
public void testEmbeddedPDF() throws Exception {
- List<Metadata> metadataList = getRecursiveJson("testPPT_EmbeddedPDF.ppt");
+ List<Metadata> metadataList = getRecursiveMetadata("testPPT_EmbeddedPDF.ppt");
assertContains("Apache Tika project", metadataList.get(1).get(RecursiveParserWrapper.TIKA_CONTENT));
assertEquals("3.pdf", metadataList.get(1).get(Metadata.RESOURCE_NAME_KEY));
assertContains("Hello World", metadataList.get(2).get(RecursiveParserWrapper.TIKA_CONTENT));
http://git-wip-us.apache.org/repos/asf/tika/blob/23a11eff/tika-parsers/src/test/java/org/apache/tika/parser/microsoft/WordParserTest.java
----------------------------------------------------------------------
diff --git a/tika-parsers/src/test/java/org/apache/tika/parser/microsoft/WordParserTest.java b/tika-parsers/src/test/java/org/apache/tika/parser/microsoft/WordParserTest.java
index 10e48fd..c1e3909 100644
--- a/tika-parsers/src/test/java/org/apache/tika/parser/microsoft/WordParserTest.java
+++ b/tika-parsers/src/test/java/org/apache/tika/parser/microsoft/WordParserTest.java
@@ -505,7 +505,7 @@ public class WordParserTest extends TikaTest {
@Test
public void testOrigSourcePath() throws Exception {
- Metadata embed1_zip_metadata = getRecursiveJson("test_recursive_embedded.doc").get(11);
+ Metadata embed1_zip_metadata = getRecursiveMetadata("test_recursive_embedded.doc").get(11);
assertContains("C:\\Users\\tallison\\AppData\\Local\\Temp\\embed1.zip",
Arrays.asList(embed1_zip_metadata.getValues(TikaCoreProperties.ORIGINAL_RESOURCE_NAME)));
assertContains("C:\\Users\\tallison\\Desktop\\tmp\\New folder (2)\\embed1.zip",
http://git-wip-us.apache.org/repos/asf/tika/blob/23a11eff/tika-parsers/src/test/java/org/apache/tika/parser/microsoft/ooxml/OOXMLContainerExtractionTest.java
----------------------------------------------------------------------
diff --git a/tika-parsers/src/test/java/org/apache/tika/parser/microsoft/ooxml/OOXMLContainerExtractionTest.java b/tika-parsers/src/test/java/org/apache/tika/parser/microsoft/ooxml/OOXMLContainerExtractionTest.java
index 3d1359f..6c3c8d5 100644
--- a/tika-parsers/src/test/java/org/apache/tika/parser/microsoft/ooxml/OOXMLContainerExtractionTest.java
+++ b/tika-parsers/src/test/java/org/apache/tika/parser/microsoft/ooxml/OOXMLContainerExtractionTest.java
@@ -308,7 +308,7 @@ public class OOXMLContainerExtractionTest extends AbstractPOIContainerExtraction
//docx converts a chart to a actual xlsx file
//so we only need to look in pptx and xlsx
for (String suffix : new String[]{"pptx", "xlsx"}) {
- List<Metadata> list = getRecursiveJson("testMSChart-govdocs-428996."+suffix);
+ List<Metadata> list = getRecursiveMetadata("testMSChart-govdocs-428996."+suffix);
boolean found = false;
for (Metadata m : list) {
if (m.get(Metadata.CONTENT_TYPE).equals(POIFSContainerDetector.MS_GRAPH_CHART.toString())) {
http://git-wip-us.apache.org/repos/asf/tika/blob/23a11eff/tika-parsers/src/test/java/org/apache/tika/parser/microsoft/ooxml/OOXMLParserTest.java
----------------------------------------------------------------------
diff --git a/tika-parsers/src/test/java/org/apache/tika/parser/microsoft/ooxml/OOXMLParserTest.java b/tika-parsers/src/test/java/org/apache/tika/parser/microsoft/ooxml/OOXMLParserTest.java
index 4cb1271..bc2b0ae 100644
--- a/tika-parsers/src/test/java/org/apache/tika/parser/microsoft/ooxml/OOXMLParserTest.java
+++ b/tika-parsers/src/test/java/org/apache/tika/parser/microsoft/ooxml/OOXMLParserTest.java
@@ -1215,7 +1215,7 @@ public class OOXMLParserTest extends TikaTest {
@Test
public void testEmbeddedPDFInPPTX() throws Exception {
- List<Metadata> metadataList = getRecursiveJson("testPPT_EmbeddedPDF.pptx");
+ List<Metadata> metadataList = getRecursiveMetadata("testPPT_EmbeddedPDF.pptx");
Metadata pdfMetadata1 = metadataList.get(2);
assertContains("Apache Tika", pdfMetadata1.get(RecursiveParserWrapper.TIKA_CONTENT));
Metadata pdfMetadata2 = metadataList.get(4);
@@ -1224,14 +1224,14 @@ public class OOXMLParserTest extends TikaTest {
@Test
public void testEmbeddedPDFInXLSX() throws Exception {
- List<Metadata> metadataList = getRecursiveJson("testExcel_embeddedPDF.xlsx");
+ List<Metadata> metadataList = getRecursiveMetadata("testExcel_embeddedPDF.xlsx");
Metadata pdfMetadata = metadataList.get(1);
assertContains("Hello World", pdfMetadata.get(RecursiveParserWrapper.TIKA_CONTENT));
}
@Test
public void testOrigSourcePath() throws Exception {
- Metadata embed1_zip_metadata = getRecursiveJson("test_recursive_embedded.docx").get(11);
+ Metadata embed1_zip_metadata = getRecursiveMetadata("test_recursive_embedded.docx").get(11);
assertContains("C:\\Users\\tallison\\AppData\\Local\\Temp\\embed1.zip",
Arrays.asList(embed1_zip_metadata.getValues(TikaCoreProperties.ORIGINAL_RESOURCE_NAME)));
assertContains("C:\\Users\\tallison\\Desktop\\tmp\\New folder (2)\\embed1.zip",
http://git-wip-us.apache.org/repos/asf/tika/blob/23a11eff/tika-parsers/src/test/java/org/apache/tika/parser/microsoft/xml/XML2003ParserTest.java
----------------------------------------------------------------------
diff --git a/tika-parsers/src/test/java/org/apache/tika/parser/microsoft/xml/XML2003ParserTest.java b/tika-parsers/src/test/java/org/apache/tika/parser/microsoft/xml/XML2003ParserTest.java
index 8df47e9..b60368c 100644
--- a/tika-parsers/src/test/java/org/apache/tika/parser/microsoft/xml/XML2003ParserTest.java
+++ b/tika-parsers/src/test/java/org/apache/tika/parser/microsoft/xml/XML2003ParserTest.java
@@ -34,7 +34,7 @@ public class XML2003ParserTest extends TikaTest {
@Test
public void testBasicWord() throws Exception {
- List<Metadata> list = getRecursiveJson("testWORD2003.xml");
+ List<Metadata> list = getRecursiveMetadata("testWORD2003.xml");
assertEquals(8, list.size());
Metadata m = list.get(0);//container doc
http://git-wip-us.apache.org/repos/asf/tika/blob/23a11eff/tika-parsers/src/test/java/org/apache/tika/parser/pdf/PDFParserTest.java
----------------------------------------------------------------------
diff --git a/tika-parsers/src/test/java/org/apache/tika/parser/pdf/PDFParserTest.java b/tika-parsers/src/test/java/org/apache/tika/parser/pdf/PDFParserTest.java
index 58c23b8..be1f769 100644
--- a/tika-parsers/src/test/java/org/apache/tika/parser/pdf/PDFParserTest.java
+++ b/tika-parsers/src/test/java/org/apache/tika/parser/pdf/PDFParserTest.java
@@ -765,7 +765,7 @@ public class PDFParserTest extends TikaTest {
context.set(org.apache.tika.parser.pdf.PDFParserConfig.class, config);
context.set(org.apache.tika.parser.Parser.class, new AutoDetectParser());
- List<Metadata> metadatas = getRecursiveJson("testPDF_childAttachments.pdf", context);
+ List<Metadata> metadatas = getRecursiveMetadata("testPDF_childAttachments.pdf", context);
int inline = 0;
int attach = 0;
for (Metadata m : metadatas) {
@@ -787,7 +787,7 @@ public class PDFParserTest extends TikaTest {
inline = 0;
attach = 0;
- metadatas = getRecursiveJson("testPDF_childAttachments.pdf", context);
+ metadatas = getRecursiveMetadata("testPDF_childAttachments.pdf", context);
for (Metadata m : metadatas) {
String v = m.get(TikaCoreProperties.EMBEDDED_RESOURCE_TYPE);
if (v != null) {
@@ -807,7 +807,7 @@ public class PDFParserTest extends TikaTest {
@Test
public void testInlineConfig() throws Exception {
- List<Metadata> metadatas = getRecursiveJson("testPDF_childAttachments.pdf");
+ List<Metadata> metadatas = getRecursiveMetadata("testPDF_childAttachments.pdf");
int inline = 0;
int attach = 0;
for (Metadata m : metadatas) {
@@ -834,7 +834,7 @@ public class PDFParserTest extends TikaTest {
inline = 0;
attach = 0;
- metadatas = getRecursiveJson("testPDF_childAttachments.pdf", context);
+ metadatas = getRecursiveMetadata("testPDF_childAttachments.pdf", context);
for (Metadata m : metadatas) {
String v = m.get(TikaCoreProperties.EMBEDDED_RESOURCE_TYPE);
if (v != null) {
@@ -851,7 +851,7 @@ public class PDFParserTest extends TikaTest {
@Test //TIKA-1376
public void testEmbeddedFileNameExtraction() throws Exception {
- List<Metadata> metadatas = getRecursiveJson("testPDF_multiFormatEmbFiles.pdf");
+ List<Metadata> metadatas = getRecursiveMetadata("testPDF_multiFormatEmbFiles.pdf");
assertEquals("metadata size", 5, metadatas.size());
Metadata firstAttachment = metadatas.get(1);
assertEquals("attachment file name", "Test.txt", firstAttachment.get(Metadata.RESOURCE_NAME_KEY));
@@ -859,7 +859,7 @@ public class PDFParserTest extends TikaTest {
@Test //TIKA-1374
public void testOSSpecificEmbeddedFileExtraction() throws Exception {
- List<Metadata> metadatas = getRecursiveJson("testPDF_multiFormatEmbFiles.pdf");
+ List<Metadata> metadatas = getRecursiveMetadata("testPDF_multiFormatEmbFiles.pdf");
assertEquals("metadata size", 5, metadatas.size());
assertEquals("file name", "Test.txt", metadatas.get(1).get(Metadata.RESOURCE_NAME_KEY));
@@ -1177,7 +1177,7 @@ public class PDFParserTest extends TikaTest {
ParseContext context = new ParseContext();
context.set(PDFParserConfig.class, config);
- List<Metadata> metadataList = getRecursiveJson("testPDF_childAttachments.pdf", context);
+ List<Metadata> metadataList = getRecursiveMetadata("testPDF_childAttachments.pdf", context);
//sanity check
assertEquals(5, metadataList.size());
//inlined jpeg metadata
@@ -1213,7 +1213,7 @@ public class PDFParserTest extends TikaTest {
} else {
assertNotContained("<div class=\"ocr\">pdf_haystack", xmlResult.xml);
}
- assertEquals(4, getRecursiveJson("testPDFEmbeddingAndEmbedded.docx", context).size());
+ assertEquals(4, getRecursiveMetadata("testPDFEmbeddingAndEmbedded.docx", context).size());
}
}
http://git-wip-us.apache.org/repos/asf/tika/blob/23a11eff/tika-parsers/src/test/java/org/apache/tika/parser/rtf/RTFParserTest.java
----------------------------------------------------------------------
diff --git a/tika-parsers/src/test/java/org/apache/tika/parser/rtf/RTFParserTest.java b/tika-parsers/src/test/java/org/apache/tika/parser/rtf/RTFParserTest.java
index 43d2fde..8fd27b3 100644
--- a/tika-parsers/src/test/java/org/apache/tika/parser/rtf/RTFParserTest.java
+++ b/tika-parsers/src/test/java/org/apache/tika/parser/rtf/RTFParserTest.java
@@ -433,7 +433,7 @@ public class RTFParserTest extends TikaTest {
expected.put(45, new Pair("testJPEG_\u666E\u6797\u65AF\u987F.jpg", "image/jpeg"));
- List<Metadata> metadataList = getRecursiveJson("testRTFEmbeddedFiles.rtf");
+ List<Metadata> metadataList = getRecursiveMetadata("testRTFEmbeddedFiles.rtf");
assertEquals(48, metadataList.size());
for (Map.Entry<Integer, Pair> e : expected.entrySet()) {
Metadata metadata = metadataList.get(e.getKey());