Lex $foo as a single token, instead of using '$' IDENT

Previously, bindings were parsed as the combination of two tokens: '$' IDENT This meant that using a keyword as variable name (e.g. $then, $label) did not work. Attempts were made to allow $keyword to work by adding some '$' Keyword rules in the parser, but this did not allow $keyword in all places: jq --arg label foo -n '$label' # ok jq -n '"foo" as $label | .' # error Treating $foo as a single token is much simpler, in my opinion. This patch also changes how LOC is lexed: "$__loc__" instead of as "__loc__" that gets combined with '$' in the parser. This patch also disallows having spaces after '$' when recalling a variable `$ foo' since that was probably just an unintentional side effect of the implementation, and it was not documented. Fixes #2675
jqlang · Jul 9, 2023 · 193f432 · 193f432
1 parent c08ecba
commit 193f432
Show file tree

Hide file tree

Showing 7 changed files with 1,583 additions and 1,617 deletions.
diff --git a/src/lexer.c b/src/lexer.c
diff --git a/src/lexer.h b/src/lexer.h
diff --git a/src/lexer.l b/src/lexer.l
@@ -60,7 +60,7 @@ struct lexer_param;
 "catch" { return CATCH; }
 "label" { return LABEL; }
 "break" { return BREAK; }
-"__loc__" { return LOC; }
+"$__loc__" { return LOC; }
 "|=" { return SETPIPE; }
 "+=" { return SETPLUS; }
 "-=" { return SETMINUS; }
@@ -122,6 +122,7 @@ struct lexer_param;
 
 ([a-zA-Z_][a-zA-Z_0-9]*::)*[a-zA-Z_][a-zA-Z_0-9]* { yylval->literal = jv_string(yytext); return IDENT;}
 \.[a-zA-Z_][a-zA-Z_0-9]* { yylval->literal = jv_string(yytext+1); return FIELD;}
+\$([a-zA-Z_][a-zA-Z_0-9]*::)*[a-zA-Z_][a-zA-Z_0-9]* { yylval->literal = jv_string(yytext+1); return BINDING;}
 
 [ \n\t]+ {}