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 2023/07/26 17:28:00 UTC

[tika] branch main updated (1e359cc5a -> 031b9a630)

This is an automated email from the ASF dual-hosted git repository.

tallison pushed a change to branch main
in repository https://gitbox.apache.org/repos/asf/tika.git


    from 1e359cc5a Merge pull request #1257 from apache/dependabot/maven/aws.version-1.12.514
     new 062e607ee TIKA-4103 -- check for resourceName; unrelated, add resourceName for macros in OfficeParser
     new 422bdef90 Merge remote-tracking branch 'origin/main'
     new af100c474 Merge remote-tracking branch 'origin/main'
     new 031b9a630 Merge remote-tracking branch 'origin/main'

The 4 revisions listed above as "new" are entirely new to this
repository and will be described in separate emails.  The revisions
listed as "add" were already present in the repository and have only
been added to this reference.


Summary of changes:
 .../src/main/java/org/apache/tika/eval/app/ExtractComparer.java  | 9 +++++++--
 .../main/java/org/apache/tika/parser/microsoft/OfficeParser.java | 4 ++++
 2 files changed, 11 insertions(+), 2 deletions(-)


[tika] 02/04: Merge remote-tracking branch 'origin/main'

Posted by ta...@apache.org.
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

commit 422bdef904706b8489844df7e44f2da0896ac531
Merge: 062e607ee 3357e4463
Author: tallison <ta...@apache.org>
AuthorDate: Mon Jul 24 11:40:50 2023 -0400

    Merge remote-tracking branch 'origin/main'

 .../resources/org/apache/tika/mime/tika-mimetypes.xml    |  6 +++++-
 tika-parent/pom.xml                                      |  6 +++---
 tika-parsers/tika-parsers-ml/tika-age-recogniser/pom.xml |  2 +-
 .../tika/detect/microsoft/POIFSContainerDetector.java    |  4 ++--
 .../tika/parser/microsoft/AbstractPOIFSExtractor.java    | 16 ++++++++++++++--
 .../parser/microsoft/ooxml/AbstractOOXMLExtractor.java   | 16 ++++++++++++++++
 .../java/org/apache/tika/parser/pkg/PackageParser.java   |  4 +++-
 .../apache/tika/detect/TestContainerAwareDetector.java   |  7 +++++++
 8 files changed, 51 insertions(+), 10 deletions(-)


[tika] 04/04: Merge remote-tracking branch 'origin/main'

Posted by ta...@apache.org.
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

commit 031b9a630da365de06eac5e94b1696cc43103925
Merge: af100c474 1e359cc5a
Author: tallison <ta...@apache.org>
AuthorDate: Wed Jul 26 13:25:04 2023 -0400

    Merge remote-tracking branch 'origin/main'

 tika-parent/pom.xml | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)


[tika] 03/04: Merge remote-tracking branch 'origin/main'

Posted by ta...@apache.org.
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

commit af100c474c6b05c9bd9649d9c58e4bb36d1caa84
Merge: 422bdef90 a38a2fbbc
Author: tallison <ta...@apache.org>
AuthorDate: Tue Jul 25 15:18:21 2023 -0400

    Merge remote-tracking branch 'origin/main'

 tika-parent/pom.xml | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)


[tika] 01/04: TIKA-4103 -- check for resourceName; unrelated, add resourceName for macros in OfficeParser

Posted by ta...@apache.org.
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

commit 062e607ee72c2a7cead5b5f5d232ee3fbafbbdd8
Author: tallison <ta...@apache.org>
AuthorDate: Fri Jul 21 16:23:43 2023 -0400

    TIKA-4103 -- check for resourceName; unrelated, add resourceName for macros in OfficeParser
---
 .../src/main/java/org/apache/tika/eval/app/ExtractComparer.java  | 9 +++++++--
 .../main/java/org/apache/tika/parser/microsoft/OfficeParser.java | 4 ++++
 2 files changed, 11 insertions(+), 2 deletions(-)

diff --git a/tika-eval/tika-eval-app/src/main/java/org/apache/tika/eval/app/ExtractComparer.java b/tika-eval/tika-eval-app/src/main/java/org/apache/tika/eval/app/ExtractComparer.java
index dbab7d476..62723d7e6 100644
--- a/tika-eval/tika-eval-app/src/main/java/org/apache/tika/eval/app/ExtractComparer.java
+++ b/tika-eval/tika-eval-app/src/main/java/org/apache/tika/eval/app/ExtractComparer.java
@@ -470,7 +470,9 @@ public class ExtractComparer extends AbstractProfiler {
         if (digestA == null) {
             return -1;
         }
+        String resourceName = metadata.get(TikaCoreProperties.RESOURCE_NAME_KEY);
 
+        int cand = -1;
         for (int i = 0; i < metadataListB.size(); i++) {
             if (handledB.contains(i)) {
                 continue;
@@ -478,10 +480,13 @@ public class ExtractComparer extends AbstractProfiler {
             Metadata mB = metadataListB.get(i);
             String digestB = mB.get(sharedDigestKey);
             if (digestA.equalsIgnoreCase(digestB)) {
-                return i;
+                cand = i;
+                if (resourceName != null && resourceName.equals(mB.get(TikaCoreProperties.RESOURCE_NAME_KEY))) {
+                    return i;
+                }
             }
         }
-        return -1;
+        return cand;
     }
 
     private void writeContrasts(Map<Cols, String> data, ContrastStatistics contrastStatistics) {
diff --git a/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/OfficeParser.java b/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/OfficeParser.java
index e862260f6..c3c81e792 100644
--- a/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/OfficeParser.java
+++ b/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/OfficeParser.java
@@ -61,6 +61,7 @@ import org.apache.tika.parser.microsoft.ooxml.OOXMLParser;
 import org.apache.tika.sax.BodyContentHandler;
 import org.apache.tika.sax.EmbeddedContentHandler;
 import org.apache.tika.sax.XHTMLContentHandler;
+import org.apache.tika.utils.StringUtils;
 
 /**
  * Defines a Microsoft document content extractor.
@@ -126,6 +127,9 @@ public class OfficeParser extends AbstractOfficeParser {
             m.set(TikaCoreProperties.EMBEDDED_RESOURCE_TYPE,
                     TikaCoreProperties.EmbeddedResourceType.MACRO.toString());
             m.set(Metadata.CONTENT_TYPE, "text/x-vbasic");
+            if (!StringUtils.isBlank(e.getKey())) {
+                m.set(TikaCoreProperties.RESOURCE_NAME_KEY, e.getKey());
+            }
             if (embeddedDocumentExtractor.shouldParseEmbedded(m)) {
                 embeddedDocumentExtractor.parseEmbedded(
                         new UnsynchronizedByteArrayInputStream(e.getValue().getBytes(StandardCharsets.UTF_8)),