diff software/mpdl-services/mpiwg-mpdl-lt/src/de/mpg/mpiwg/berlin/mpdl/lt/text/norm/lang/MpdlNormalizerLexEL.lex @ 23:e845310098ba

diverse Korrekturen
author Josef Willenborg <jwillenborg@mpiwg-berlin.mpg.de>
date Tue, 27 Nov 2012 12:35:19 +0100
parents 4a3641ae14d2
children
line wrap: on
line diff
--- a/software/mpdl-services/mpiwg-mpdl-lt/src/de/mpg/mpiwg/berlin/mpdl/lt/text/norm/lang/MpdlNormalizerLexEL.lex	Wed Dec 14 13:57:09 2011 +0100
+++ b/software/mpdl-services/mpiwg-mpdl-lt/src/de/mpg/mpiwg/berlin/mpdl/lt/text/norm/lang/MpdlNormalizerLexEL.lex	Tue Nov 27 12:35:19 2012 +0100
@@ -7,7 +7,7 @@
  *
  */
 
-package de.mpg.mpiwg.berlin.mpdl.lt.analyzer.lang;
+package de.mpg.mpiwg.berlin.mpdl.lt.text.norm.lang;
 
 %%
 
@@ -47,6 +47,12 @@
 
 %%
 
+// jump over empty xml elements
+"<"[^><]+"/>" { add(yytext()); }
+"-<"[^><]+"/>" { add(yytext()); }
+"<"[^><]+"></"[^><]+">" { add(yytext()); }
+"-<"[^><]+"></"[^><]+">" { add(yytext()); }
+
 
 // always replace tonos by oxia 
 // (although this should really be corrected in the text rather than normalized)