Add an attribute to the vertical with the decomposed unicode represen…

…tation
acdh-oeaw · Jun 21, 2024 · 6e4be3f · 6e4be3f
1 parent c120958
commit 6e4be3f
Show file tree

Hide file tree

Showing 2 changed files with 6 additions and 3 deletions.
diff --git a/080_scripts_generic/080_01_ELAN2TEI/tokenizer/xsl/vert2txt.xsl b/080_scripts_generic/080_01_ELAN2TEI/tokenizer/xsl/vert2txt.xsl
@@ -78,7 +78,7 @@
     </xsl:template>
     <xsl:template name="noske-token">
         <xsl:value-of
-            select="concat(string-join((normalize-space(.), @xtoks:id[parent::xtoks:w], tei:sort-attrs(.)), '&#x9;'), '&#xA;')"
+            select="concat(string-join((normalize-unicode(normalize-space(.), 'NFC'), @xtoks:id[parent::xtoks:w], normalize-unicode(normalize-space(.), 'NFD'), tei:sort-attrs(.)), '&#x9;'), '&#xA;')"
         />
     </xsl:template>
     <xsl:template match="xtoks:w | xtoks:pc">

diff --git a/nosketchengine/shawi b/nosketchengine/shawi
@@ -21,14 +21,17 @@ TAGSETDOC ""
 ATTRIBUTE "word" {
 	TYPE "MD_MD"
 }
-#	MULTIVALUE y
-#     MULTISEP ","
 
 ## column #2
 ATTRIBUTE "wid" {
 	TYPE "MD_MD"
 }
 
+## column #3 used for the decomposed version of the word
+ATTRIBUTE "decomp" {
+	TYPE "MD_MD"
+}
+
 ## column #3
 ATTRIBUTE "ana" {
 	TYPE "MD_MD"