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 2017/01/11 12:06:47 UTC
tika git commit: TIKA-2235 - set default dpi for OCR to 300 via
Matthew Caruana Galizia
Repository: tika
Updated Branches:
refs/heads/master 66f6310ee -> d1b1ad3d9
TIKA-2235 - set default dpi for OCR to 300 via Matthew Caruana Galizia
Project: http://git-wip-us.apache.org/repos/asf/tika/repo
Commit: http://git-wip-us.apache.org/repos/asf/tika/commit/d1b1ad3d
Tree: http://git-wip-us.apache.org/repos/asf/tika/tree/d1b1ad3d
Diff: http://git-wip-us.apache.org/repos/asf/tika/diff/d1b1ad3d
Branch: refs/heads/master
Commit: d1b1ad3d916a413e8fec20b5f68d20fa9b2c4ab6
Parents: 66f6310
Author: tballison <ta...@mitre.org>
Authored: Wed Jan 11 07:06:39 2017 -0500
Committer: tballison <ta...@mitre.org>
Committed: Wed Jan 11 07:06:39 2017 -0500
----------------------------------------------------------------------
.../src/main/java/org/apache/tika/parser/pdf/PDFParserConfig.java | 2 +-
.../main/resources/org/apache/tika/parser/pdf/PDFParser.properties | 2 +-
2 files changed, 2 insertions(+), 2 deletions(-)
----------------------------------------------------------------------
http://git-wip-us.apache.org/repos/asf/tika/blob/d1b1ad3d/tika-parsers/src/main/java/org/apache/tika/parser/pdf/PDFParserConfig.java
----------------------------------------------------------------------
diff --git a/tika-parsers/src/main/java/org/apache/tika/parser/pdf/PDFParserConfig.java b/tika-parsers/src/main/java/org/apache/tika/parser/pdf/PDFParserConfig.java
index ce98e0d..5ffffac 100644
--- a/tika-parsers/src/main/java/org/apache/tika/parser/pdf/PDFParserConfig.java
+++ b/tika-parsers/src/main/java/org/apache/tika/parser/pdf/PDFParserConfig.java
@@ -115,7 +115,7 @@ public class PDFParserConfig implements Serializable {
private OCR_STRATEGY ocrStrategy = OCR_STRATEGY.NO_OCR;
- private int ocrDPI = 200;
+ private int ocrDPI = 300;
private ImageType ocrImageType = ImageType.GRAY;
private String ocrImageFormatName = "png";
http://git-wip-us.apache.org/repos/asf/tika/blob/d1b1ad3d/tika-parsers/src/main/resources/org/apache/tika/parser/pdf/PDFParser.properties
----------------------------------------------------------------------
diff --git a/tika-parsers/src/main/resources/org/apache/tika/parser/pdf/PDFParser.properties b/tika-parsers/src/main/resources/org/apache/tika/parser/pdf/PDFParser.properties
index 319e693..e414610 100644
--- a/tika-parsers/src/main/resources/org/apache/tika/parser/pdf/PDFParser.properties
+++ b/tika-parsers/src/main/resources/org/apache/tika/parser/pdf/PDFParser.properties
@@ -27,7 +27,7 @@ catchIntermediateIOExceptions true
#options: no_ocr, ocr_only, ocr_and_text_extraction
ocrStrategy no_ocr
#dots per inch for the ocr rendering of the page image
-ocrDPI 200
+ocrDPI 300
#if you request tif, make sure you have imageio jars on your classpath!
ocrImageFormatName png
#options: argb, binary, gray, rgb