Support Latin-1 supplement a0-ff as DSL string literals (#957)

* Support Latin-1 supplement a0-ff as DSL string literals * build artifacts for previous commit
johnkerl · Feb 21, 2022 · 472b42d · 472b42d
1 parent 0756149
commit 472b42d
Show file tree

Hide file tree

Showing 4 changed files with 20 additions and 9 deletions.
diff --git a/internal/pkg/parsing/lexer/lexer.go b/internal/pkg/parsing/lexer/lexer.go
diff --git a/internal/pkg/parsing/lexer/transitiontable.go b/internal/pkg/parsing/lexer/transitiontable.go
diff --git a/internal/pkg/parsing/mlr.bnf b/internal/pkg/parsing/mlr.bnf
@@ -54,7 +54,7 @@
 // CHARACTER CLASSES
 // ----------------------------------------------------------------
 
-_letter : 'a'-'z' | 'A'-'Z' | '\u00a0'-'\u00ff' | '\u0100'-'\U0010FFFF';
+_letter : 'a'-'z' | 'A'-'Z' | '\u00a0'-'\u00ff' | '\u0100'-'\U0010ffff';
 _decdig : '0'-'9' ;
 _hexdig : '0'-'9' | 'a'-'f' | 'A'-'F';
 _octdig : '0'-'7' ;
@@ -95,7 +95,8 @@ _string_literal_element
   | ( '\\' '*' )
   | ( '\\' '0' ) | ( '\\' '1' ) | ( '\\' '2' ) | ( '\\' '3' ) | ( '\\' '4' )
   | ( '\\' '5' ) | ( '\\' '6' ) | ( '\\' '7' ) | ( '\\' '8' ) | ( '\\' '9' )
-  | '\u0100'-'\U0010FFFF'
+  | '\u00a0'-'\u00ff'
+  | '\u0100'-'\U0010ffff'
 ;
 string_literal : '"' {_string_literal_element} '"' ;
 

diff --git a/todo.txt b/todo.txt
@@ -7,6 +7,7 @@ RELEASES
     https://github.com/johnkerl/miller/issues?q=is%3Aissue+is%3Aopen+label%3Aneeds-documentation
   o fmt/unfmt/regex doc
   o FAQ/examples reorg
+  ? ??? for doc-string contents search -- ? & mlr help namegoeshere foo ...
 
   k strptime/882
   k fmtifnum, & recursive fmtnum/fmtifnum