add processing of hyphen chars in Word-to-HTML and Word-to-FO converters

git-svn-id: https://svn.apache.org/repos/asf/poi/trunk@1149020 13f79535-47bb-0310-9956-ffa450edef68
This commit is contained in:
Sergey Vladimirov 2011-07-21 03:33:29 +00:00
parent d7e5c4681e
commit 3f0760921f

View File

@ -61,6 +61,10 @@ public abstract class AbstractWordConverter
private static final byte SPECCHAR_AUTONUMBERED_FOOTNOTE_REFERENCE = 2;
private static final char UNICODECHAR_NONBREAKING_HYPHEN = '\u2011';
private static final char UNICODECHAR_ZERO_WIDTH_SPACE = '\u200b';
private final Set<Bookmark> bookmarkStack = new LinkedHashSet<Bookmark>();
private FontReplacer fontReplacer = new DefaultFontReplacer();
@ -225,6 +229,16 @@ public abstract class AbstractWordConverter
}
processLineBreak( block, characterRun );
}
else if ( charChar == 30 )
{
// Non-breaking hyphens are stored as ASCII 30
stringBuilder.append( UNICODECHAR_NONBREAKING_HYPHEN );
}
else if ( charChar == 31 )
{
// Non-required hyphens to zero-width space
stringBuilder.append( UNICODECHAR_ZERO_WIDTH_SPACE );
}
else
{
stringBuilder.append( charChar );