1 files changed, 47 insertions(+), 19 deletions(-)

M doc/grammar.ebnf

@@ 4,24 4,42 @@
 #
 # [0]: https://golang.org/ref/spec#Notation
 
-grammar    = definition { definition } .
-definition = identifier ARROW expression [ EOS ] .
-expression = sequence { SEPARATOR sequence } .
-sequence   = label { label } .
-label      = [ identifier COLON ] prefix .
-prefix     = AND coderef
-           | DOLLAR coderef
-           | AT coderef
-           | [ AND | NOT ] suffix
-           .
-suffix     = primary [ QUESTION | STAR | PLUS ] .
-primary    = identifier
-           | LPAREN expression RPAREN
-           | literal
-           | class
-           | DOT
-           .
-coderef    = LBRACE identifier RBRACE .
+grammar        = definition { definition } .
+definition     = identifier ARROW expression [ EOS ] .
+expression     = sequence { SEPARATOR sequence } .
+sequence       = label { label } .
+label          = [ identifier COLON ] prefix .
+prefix         = AND coderef # TODO: move coderefs before labels, no sense in having id:${code}
+               | DOLLAR coderef
+               | AT coderef
+               | [ AND | NOT ] suffix
+               .
+suffix         = primary [ QUESTION | STAR | PLUS ] .
+primary        = identifier
+               | LPAREN expression RPAREN
+               | literal
+               | class
+               | DOT
+               .
+coderef        = LBRACE identifier RBRACE .
+identifier     = LETTER { LETTER | NUMBER } .
+literal        = dquote_literal | squote_literal .
+dquote_literal = DQUOTE { SAFE_RUNE | SQUOTE | RBRACK | dquote_escape } DQUOTE .
+squote_literal = SQUOTE { SAFE_RUNE | DQUOTE | RBRACK | squote_escape } SQUOTE .
+class          = LBRACK range { range } RBRACK .
+range          = char MINUS char | char .
+char           = SAFE_RUNE | SQUOTE | DQUOTE | class_escape .
+dquote_escape  = common_escape | BACKSLASH DQUOTE .
+squote_escape  = common_escape | BACKSLASH SQUOTE .
+class_escape   = common_escape | BACKSLASH LBRACK | BACKSLASH RBRACK | BACKSLASH MINUS | BACKSLASH CHEVRON .
+common_escape  = hex_escape
+               | unicode_escape
+               | BACKSLASH ( 'a' | 'b' | 'f' | 'n' | 'r' | 't' | 'v' | BACKSLASH )
+               .
+hex_escape     = BACKSLASH 'x' HEX_DIGIT HEX_DIGIT .
+unicode_escape = BACKSLASH 'u' HEX_DIGIT HEX_DIGIT HEX_DIGIT HEX_DIGIT
+               | BACKSLASH 'U' HEX_DIGIT HEX_DIGIT HEX_DIGIT HEX_DIGIT HEX_DIGIT HEX_DIGIT HEX_DIGIT HEX_DIGIT
+               .
 
 # For reference, the terminal productions are loosely defined here.
 # They are handled by the scanner.


@@ 42,4 60,14 @@ RPAREN    = ')' .
 DOT       = '.' .
 LBRACE    = '{' .
 RBRACE    = '}' .
-
+LETTER    = any unicode letter or '_' .
+NUMBER    = any unicode number or '-' .
+LBRACK    = '[' .
+RBRACK    = ']' .
+DQUOTE    = '"' .
+SQUOTE    = '\'' .
+SAFE_RUNE = any unicode code point except '\n', '\\', '"', '\'' and ']' .
+BACKSLASH = '\\' .
+MINUS     = '-' .
+CHEVRON   = '^' .
+HEX_DIGIT = '0' ... '9' | 'a' ... 'f' | 'A' ... 'F' .