You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@pdfbox.apache.org by ti...@apache.org on 2017/06/21 06:33:12 UTC

svn commit: r1799390 - /pdfbox/trunk/pdfbox/src/main/java/org/apache/pdfbox/text/TextPosition.java

Author: tilman
Date: Wed Jun 21 06:33:12 2017
New Revision: 1799390

URL: http://svn.apache.org/viewvc?rev=1799390&view=rev
Log:
PDFBOX-3833: don't treat prolonged sound mark as a diacritic

Modified:
    pdfbox/trunk/pdfbox/src/main/java/org/apache/pdfbox/text/TextPosition.java

Modified: pdfbox/trunk/pdfbox/src/main/java/org/apache/pdfbox/text/TextPosition.java
URL: http://svn.apache.org/viewvc/pdfbox/trunk/pdfbox/src/main/java/org/apache/pdfbox/text/TextPosition.java?rev=1799390&r1=1799389&r2=1799390&view=diff
==============================================================================
--- pdfbox/trunk/pdfbox/src/main/java/org/apache/pdfbox/text/TextPosition.java (original)
+++ pdfbox/trunk/pdfbox/src/main/java/org/apache/pdfbox/text/TextPosition.java Wed Jun 21 06:33:12 2017
@@ -689,6 +689,14 @@ public final class TextPosition
         {
             return false;
         }
+        if ("ー".equals(text))
+        {
+            // PDFBOX-3833: ー is not a real diacritic like ¨ or ˆ, it just changes the 
+            // pronunciation of the previous sound, and is printed after the previous glyph
+            // http://www.japanesewithanime.com/2017/04/prolonged-sound-mark.html
+            // Ignoring it as diacritic avoids trouble if it slightly overlaps with the next glyph.
+            return false;
+        }
         int type = Character.getType(text.charAt(0));
         return type == Character.NON_SPACING_MARK ||
                type == Character.MODIFIER_SYMBOL ||