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 2021/04/09 16:19:16 UTC
[tika] branch main updated: [TIKA-3344] [TIKA-3345] main (#424)
This is an automated email from the ASF dual-hosted git repository.
tallison pushed a commit to branch main
in repository https://gitbox.apache.org/repos/asf/tika.git
The following commit(s) were added to refs/heads/main by this push:
new 6262305 [TIKA-3344] [TIKA-3345] main (#424)
6262305 is described below
commit 6262305632b84cb28a299b9543d2e50876fc9f6a
Author: Subhajit Das <Su...@users.noreply.github.com>
AuthorDate: Fri Apr 9 21:46:54 2021 +0530
[TIKA-3344] [TIKA-3345] main (#424)
* Added case-insensitivity to tika server ocr header names
* Minor restructure and added missing javadoc
* TIKA-3344 and TIKA-3345 for main
* Fixed checkstyle
* Fixed checkstyle
* Fixed checkstyle
* [TIKA-3344] [TIKA-3345] main - checkstyle violation fix
---
.../tika/server/classic/TikaResourceTest.java | 80 ++++++++++++++++++----
.../tika/server/core/resource/TikaResource.java | 58 ++++++++++++----
2 files changed, 111 insertions(+), 27 deletions(-)
diff --git a/tika-server/tika-server-classic/src/test/java/org/apache/tika/server/classic/TikaResourceTest.java b/tika-server/tika-server-classic/src/test/java/org/apache/tika/server/classic/TikaResourceTest.java
index 4dc3b21..54a5909 100644
--- a/tika-server/tika-server-classic/src/test/java/org/apache/tika/server/classic/TikaResourceTest.java
+++ b/tika-server/tika-server-classic/src/test/java/org/apache/tika/server/classic/TikaResourceTest.java
@@ -28,6 +28,7 @@ import java.util.ArrayList;
import java.util.List;
import java.util.Locale;
import javax.ws.rs.ProcessingException;
+import javax.ws.rs.core.MediaType;
import javax.ws.rs.core.Response;
import org.apache.commons.codec.binary.Base64;
@@ -36,6 +37,8 @@ import org.apache.cxf.attachment.AttachmentUtil;
import org.apache.cxf.jaxrs.JAXRSServerFactoryBean;
import org.apache.cxf.jaxrs.client.WebClient;
import org.apache.cxf.jaxrs.ext.multipart.Attachment;
+import org.apache.cxf.jaxrs.ext.multipart.ContentDisposition;
+import org.apache.cxf.jaxrs.ext.multipart.MultipartBody;
import org.apache.cxf.jaxrs.lifecycle.SingletonResourceProvider;
import org.junit.Test;
@@ -57,6 +60,7 @@ public class TikaResourceTest extends CXFTestBase {
private static final String STREAM_CLOSED_FAULT = "java.io.IOException: Stream Closed";
private static final String TIKA_PATH = "/tika";
+ private static final String TIKA_POST_PATH = "/tika/form";
private static final int UNPROCESSEABLE = 422;
@Override
@@ -68,7 +72,7 @@ public class TikaResourceTest extends CXFTestBase {
@Override
protected void setUpProviders(JAXRSServerFactoryBean sf) {
- List<Object> providers = new ArrayList<Object>();
+ List<Object> providers = new ArrayList<>();
providers.add(new TikaServerParseExceptionMapper(false));
sf.setProviders(providers);
}
@@ -158,8 +162,9 @@ public class TikaResourceTest extends CXFTestBase {
@Test
- public void testPasswordXLS() throws Exception {
- Response response = WebClient.create(endPoint + TIKA_PATH).type("application/vnd.ms-excel")
+ public void testPasswordXLS() {
+ Response response = WebClient.create(endPoint + TIKA_PATH)
+ .type("application/vnd.ms-excel")
.accept("text/plain")
.put(ClassLoader.getSystemResourceAsStream("test-documents/password.xls"));
@@ -181,8 +186,9 @@ public class TikaResourceTest extends CXFTestBase {
}
@Test
- public void testPasswordXLSHTML() throws Exception {
- Response response = WebClient.create(endPoint + TIKA_PATH).type("application/vnd.ms-excel")
+ public void testPasswordXLSHTML() {
+ Response response = WebClient.create(endPoint + TIKA_PATH)
+ .type("application/vnd.ms-excel")
.accept("text/html")
.put(ClassLoader.getSystemResourceAsStream("test-documents/password.xls"));
@@ -199,8 +205,9 @@ public class TikaResourceTest extends CXFTestBase {
}
@Test
- public void testPasswordXLSXML() throws Exception {
- Response response = WebClient.create(endPoint + TIKA_PATH).type("application/vnd.ms-excel")
+ public void testPasswordXLSXML() {
+ Response response = WebClient.create(endPoint + TIKA_PATH)
+ .type("application/vnd.ms-excel")
.accept("text/xml")
.put(ClassLoader.getSystemResourceAsStream("test-documents/password.xls"));
@@ -290,7 +297,7 @@ public class TikaResourceTest extends CXFTestBase {
.put(ClassLoader.getSystemResourceAsStream("test-documents/testOCR.pdf"));
String responseMsg = getStringFromInputStream((InputStream) response.getEntity());
- assertTrue(responseMsg.trim().equals(""));
+ assertEquals("", responseMsg.trim());
response =
WebClient.create(endPoint + TIKA_PATH).type("application/pdf").accept("text/plain")
@@ -298,7 +305,7 @@ public class TikaResourceTest extends CXFTestBase {
.put(ClassLoader.getSystemResourceAsStream("test-documents/testOCR.pdf"));
responseMsg = getStringFromInputStream((InputStream) response.getEntity());
- assertTrue(responseMsg.trim().equals(""));
+ assertEquals("", responseMsg.trim());
response =
@@ -332,7 +339,7 @@ public class TikaResourceTest extends CXFTestBase {
.put(ClassLoader.getSystemResourceAsStream("test-documents/testOCR.pdf"));
String responseMsg = getStringFromInputStream((InputStream) response.getEntity());
- assertTrue(responseMsg.trim().equals(""));
+ assertEquals("", responseMsg.trim());
response =
WebClient.create(endPoint + TIKA_PATH).type("application/pdf").accept("text/plain")
@@ -341,7 +348,7 @@ public class TikaResourceTest extends CXFTestBase {
.put(ClassLoader.getSystemResourceAsStream("test-documents/testOCR.pdf"));
responseMsg = getStringFromInputStream((InputStream) response.getEntity());
- assertTrue(responseMsg.trim().equals(""));
+ assertEquals("", responseMsg.trim());
response =
@@ -417,8 +424,8 @@ public class TikaResourceTest extends CXFTestBase {
}
@Test
- public void testDataIntegrityCheck() throws Exception {
- Response response = null;
+ public void testDataIntegrityCheck() {
+ Response response;
try {
response = WebClient.create(endPoint + TIKA_PATH).type("application/pdf")
.accept("text/plain")
@@ -465,7 +472,6 @@ public class TikaResourceTest extends CXFTestBase {
}
-
@Test
public void testUnicodePasswordProtectedSpaces() throws Exception {
//TIKA-2858
@@ -510,4 +516,50 @@ public class TikaResourceTest extends CXFTestBase {
assertNotFound("embed4.txt", responseMsg);
}
+ // TIKA-3344
+ @Test
+ public void testPDFLowerCaseOCRConfigPOST() throws Exception {
+ if (! new TesseractOCRParser().hasTesseract()) {
+ return;
+ }
+
+ Response response = WebClient.create(endPoint + TIKA_POST_PATH)
+ .type("application/pdf")
+ .accept(MediaType.TEXT_PLAIN).type(MediaType.MULTIPART_FORM_DATA)
+ .header(PDFServerConfig.X_TIKA_PDF_HEADER_PREFIX.toLowerCase(Locale.ROOT)
+ + "ocrstrategy", "no_ocr")
+ .post(testPDFLowerCaseOCRConfigPOSTBody());
+ String responseMsg = getStringFromInputStream((InputStream) response
+ .getEntity());
+
+ assertEquals("", responseMsg.trim());
+
+ response = WebClient.create(endPoint + TIKA_POST_PATH)
+ .type("application/pdf")
+ .accept(MediaType.TEXT_PLAIN).type(MediaType.MULTIPART_FORM_DATA)
+ .header(PDFServerConfig.X_TIKA_PDF_HEADER_PREFIX.toLowerCase(Locale.ROOT)
+ + "ocrstrategy", "ocr_only")
+ .post(testPDFLowerCaseOCRConfigPOSTBody());
+ responseMsg = getStringFromInputStream((InputStream) response
+ .getEntity());
+ assertContains("Happy New Year 2003!", responseMsg);
+
+ //now try a bad value
+ response = WebClient.create(endPoint + TIKA_POST_PATH)
+ .type("application/pdf")
+ .accept(MediaType.TEXT_PLAIN).type(MediaType.MULTIPART_FORM_DATA)
+ .header(PDFServerConfig.X_TIKA_PDF_HEADER_PREFIX.toLowerCase(Locale.ROOT)
+ + "ocrstrategy", "non-sense-value")
+ .post(testPDFLowerCaseOCRConfigPOSTBody());
+ assertEquals(400, response.getStatus());
+ }
+
+ private MultipartBody testPDFLowerCaseOCRConfigPOSTBody() {
+ ContentDisposition cd = new ContentDisposition(
+ "form-data; name=\"input\"; filename=\"testOCR.pdf\"");
+ Attachment att = new Attachment("upload", ClassLoader
+ .getSystemResourceAsStream("test-documents/testOCR.pdf"), cd);
+ return new MultipartBody(att);
+ }
+
}
diff --git a/tika-server/tika-server-core/src/main/java/org/apache/tika/server/core/resource/TikaResource.java b/tika-server/tika-server-core/src/main/java/org/apache/tika/server/core/resource/TikaResource.java
index c83b5a2..e129da4 100644
--- a/tika-server/tika-server-core/src/main/java/org/apache/tika/server/core/resource/TikaResource.java
+++ b/tika-server/tika-server-core/src/main/java/org/apache/tika/server/core/resource/TikaResource.java
@@ -53,6 +53,7 @@ import javax.xml.transform.stream.StreamResult;
import org.apache.commons.lang3.StringUtils;
import org.apache.cxf.attachment.ContentDisposition;
import org.apache.cxf.jaxrs.ext.multipart.Attachment;
+import org.apache.cxf.jaxrs.impl.MetadataMap;
import org.slf4j.Logger;
import org.slf4j.LoggerFactory;
import org.xml.sax.ContentHandler;
@@ -231,9 +232,11 @@ public class TikaResource {
}
} catch (Throwable ex) {
- throw new WebApplicationException(String.format(Locale.ROOT,
- "%s is an invalid %s header or has an invalid value: %s", key, prefix, val),
- Response.Status.BAD_REQUEST);
+ // TIKA-3345
+ String error = (!(ex.getCause() instanceof IllegalArgumentException)) ?
+ String.format(Locale.ROOT, "%s is an invalid %s header", key, prefix) :
+ String.format(Locale.ROOT, "%s is an invalid %s header value", val, key);
+ throw new WebApplicationException(error, Response.Status.BAD_REQUEST);
}
}
@@ -375,9 +378,11 @@ public class TikaResource {
@Consumes("multipart/form-data")
@Produces("text/plain")
@Path("form")
- public StreamingOutput getTextFromMultipart(Attachment att, @Context final UriInfo info) {
- return produceText(att.getObject(InputStream.class), new Metadata(), att.getHeaders(),
- info);
+ public StreamingOutput getTextFromMultipart(Attachment att,
+ @Context HttpHeaders httpHeaders,
+ @Context final UriInfo info) {
+ return produceText(att.getObject(InputStream.class), new Metadata(),
+ preparePostHeaderMap(att, httpHeaders), info);
}
//this is equivalent to text-main in tika-app
@@ -396,8 +401,10 @@ public class TikaResource {
@Produces("text/plain")
@Path("form/main")
public StreamingOutput getTextMainFromMultipart(final Attachment att,
+ @Context HttpHeaders httpHeaders,
@Context final UriInfo info) {
- return produceTextMain(att.getObject(InputStream.class), att.getHeaders(), info);
+ return produceTextMain(att.getObject(InputStream.class),
+ preparePostHeaderMap(att, httpHeaders), info);
}
public StreamingOutput produceTextMain(final InputStream is,
@@ -463,9 +470,11 @@ public class TikaResource {
@Consumes("multipart/form-data")
@Produces("text/html")
@Path("form")
- public StreamingOutput getHTMLFromMultipart(Attachment att, @Context final UriInfo info) {
- return produceOutput(att.getObject(InputStream.class), new Metadata(), att.getHeaders(),
- info, "html");
+ public StreamingOutput getHTMLFromMultipart(Attachment att,
+ @Context HttpHeaders httpHeaders,
+ @Context final UriInfo info) {
+ return produceOutput(att.getObject(InputStream.class), new Metadata(),
+ preparePostHeaderMap(att, httpHeaders), info, "html");
}
@PUT
@@ -482,9 +491,11 @@ public class TikaResource {
@Consumes("multipart/form-data")
@Produces("text/xml")
@Path("form")
- public StreamingOutput getXMLFromMultipart(Attachment att, @Context final UriInfo info) {
- return produceOutput(att.getObject(InputStream.class), new Metadata(), att.getHeaders(),
- info, "xml");
+ public StreamingOutput getXMLFromMultipart(Attachment att,
+ @Context HttpHeaders httpHeaders,
+ @Context final UriInfo info) {
+ return produceOutput(att.getObject(InputStream.class),
+ new Metadata(), preparePostHeaderMap(att, httpHeaders), info, "xml");
}
@PUT
@@ -532,4 +543,25 @@ public class TikaResource {
}
};
}
+
+ /**
+ * Prepares a multivalued map, combining attachment headers and request headers.
+ * Gives priority to attachment headers.
+ * @param att the attachment.
+ * @param httpHeaders the http headers, fetched from context.
+ * @return the case insensitive MetadataMap containing combined headers.
+ */
+ private MetadataMap<String, String> preparePostHeaderMap(Attachment att,
+ HttpHeaders httpHeaders) {
+ if (att == null && httpHeaders == null) return null;
+ MetadataMap<String, String> finalHeaders = new MetadataMap<>(false,
+ true);
+ if (httpHeaders != null && httpHeaders.getRequestHeaders() != null) {
+ finalHeaders.putAll(httpHeaders.getRequestHeaders());
+ }
+ if (att != null && att.getHeaders() != null) {
+ finalHeaders.putAll(att.getHeaders());
+ }
+ return finalHeaders;
+ }
}