add alias data from https://unicode.org/charts/charindex.html

Author: davidcarlisle

add-alias.xsl

@@ -0,0 +1,42 @@
+<xsl:stylesheet version="2.0" xmlns:xsl="http://www.w3.org/1999/XSL/Transform">
+
+<xsl:variable name="aliases" select="doc('aliases.xml')"/>
+<xsl:output encoding="US-ASCII" omit-xml-declaration="yes"/>
+
+<xsl:template match="/">
+     <xsl:processing-instruction name="xml-stylesheet">type="text/xsl" href="unicode.xsl"</xsl:processing-instruction>
+    <xsl:text>&#10;</xsl:text>
+    <xsl:copy-of select="comment()"/>
+    <xsl:text>&#10;</xsl:text>
+    <xsl:apply-templates/>
+    <xsl:text>&#10;</xsl:text>
+</xsl:template>
+
+<xsl:template match="processing-instruction()|comment()" priority="2"/>
+
+<xsl:template match="node()|@*">
+ <xsl:copy>
+  <xsl:copy-of select="@*"/>
+  <xsl:apply-templates/>
+ </xsl:copy>
+</xsl:template>
+
+<xsl:key name="alias" match="tr" use="concat(
+   'U',
+   if(string-length(td/a)=4) then '0' else '',
+   td/a)
+   "/>
+<xsl:template match="unicodedata">
+ <xsl:copy>
+  <xsl:copy-of select="@* except @alias"/>
+  <xsl:if test="key('alias',../@id,$aliases)">
+   <xsl:attribute name="alias"
+		  select="string-join(
+			  key('alias',../@id,$aliases)/td[1],';'
+			  )">
+   </xsl:attribute>
+  </xsl:if>
+ </xsl:copy>
+</xsl:template>
+
+</xsl:stylesheet>

charlist.rnc

@@ -67,7 +67,8 @@ unicodedata = element unicodedata {
   attribute upper { text }?,
   attribute lower { text }?,
   attribute title { text }?,
-  attribute mathclass { text }?
+  attribute mathclass { text }?,
+  attribute alias { text }?
 }
 latex = element latex { attribute set { text }?, text }
 varlatex = element varlatex { attribute set { text }?, text }

get-aliases

@@ -0,0 +1,12 @@
+
+# add aliases from charindex.html to unicode.xml
+
+rm charindex.html
+wget https://unicode.org/charts/charindex.html
+
+echo '<table>' > aliases.xml
+grep 'td>[a-z0-9 \-]\+<' charindex.html  >> aliases.xml
+echo '</table>' >> aliases.xml
+
+saxon9 unicode.xml add-alias.xsl >u2.xml
+diff unicode.xml u2.xml