mirror of
https://github.com/Alfresco/alfresco-community-repo.git
synced 2025-07-31 17:39:05 +00:00
Merged HEAD-BUG-FIX (4.3/Cloud) to HEAD (4.3/Cloud)
68541: Merged V4.2-BUG-FIX (4.2.3) to HEAD-BUG-FIX (4.3/Cloud) 68489: MNT-11225: Problem with pdf-text extraction, spaces between letters in many of the words - Removed debugging sys out git-svn-id: https://svn.alfresco.com/repos/alfresco-enterprise/alfresco/HEAD/root@70424 c4b6b30b-aa2e-2d43-bbcb-ca4b014f7261
This commit is contained in:
@@ -66,7 +66,6 @@ public class PdfBoxContentTransformer extends TikaPoweredContentTransformer
|
|||||||
ParseContext context = super.buildParseContext(metadata, targetMimeType, options);
|
ParseContext context = super.buildParseContext(metadata, targetMimeType, options);
|
||||||
if (pdfParserConfig != null)
|
if (pdfParserConfig != null)
|
||||||
{
|
{
|
||||||
System.out.println("**** spacingTolerance=" + pdfParserConfig.getSpacingTolerance() + ", averageCharTolerance=" + pdfParserConfig.getAverageCharTolerance());
|
|
||||||
context.set(PDFParserConfig.class, pdfParserConfig);
|
context.set(PDFParserConfig.class, pdfParserConfig);
|
||||||
}
|
}
|
||||||
// TODO: Possibly extend TransformationOptions to allow for per-transform PDFParserConfig?
|
// TODO: Possibly extend TransformationOptions to allow for per-transform PDFParserConfig?
|
||||||
|
Reference in New Issue
Block a user