basex-lsp/docs/wordat.xqbk

{"cells":[{"kind":1,"language":"markdown","value":"XPath name charactors"},{"kind":2,"language":"xquery","value":"let $s:=`[A-Z]\r\n           | '_'\r\n           | [a-z]\r\n           | [#xC0-#xD6]\r\n           | [#xD8-#xF6]\r\n           | [#xF8-#x2FF]\r\n           | [#x370-#x37D]\r\n           | [#x37F-#x1FFF]\r\n           | [#x200C-#x200D]\r\n           | [#x2070-#x218F]\r\n           | [#x2C00-#x2FEF]\r\n           | [#x3001-#xD7FF]\r\n           | [#xF900-#xFDCF]\r\n           | [#xFDF0-#xFFFD]\r\n          `\r\nlet $sreg:= normalize-space($s)\r\n       =>tokenize(\"\\|\")\r\n       =!>normalize-space()\r\n       =!>replace(\"(#x[0-9A-F]+)\",fn($s,$m){\r\n                convert:integer-from-base(substring($m,3),16)\r\n                =>codepoints-to-string()\r\n              })\r\n       =!>translate(\"'\",\"\")\r\n       =>string-join(\"|\")\r\nreturn $sreg"}]}