new parser

2 files changed, 109 insertions, 0 deletions

diff --git a/spec/parser.ebnf b/spec/parser.ebnf
new file mode 100644
index 0000000..9e02fba
--- /dev/null
+++ b/spec/parser.ebnf
@@ -0,0 +1,75 @@
+unit          : blank* ( datum blank? | EOF ) ;
+
+
+blank         : 9...13 | comment ;
+
+datum         : one_datum ( join_char? one_datum )* ;
+
+join_char     : '.' | ':' | '|' ;
+
+
+comment       : ';' ( skip_unit | skip_line ) ;
+
+skip_unit     : '~' unit ;
+
+skip_line     : ( ~LF )* LF? ;
+
+
+one_datum     : ( bare_str | clad_datum ) ;
+
+bare_str      : bare_str_elt+ ;
+
+clad_datum    : '\' bare_esc_str
+              | '"' quoted_str '"'
+              | '#' hash_expr
+              | '(' blank* list? ')'
+              | '[' blank* list? ']'
+              | '{' blank* list? '}'
+              | quote_expr
+              ;
+
+
+bare_str_elt  : bare_char | '\' bare_esc ;
+
+
+bare_esc_str  : bare_esc bare_str_elt* ;
+
+quoted_str    : ( quoted_char | '\' quoted_esc )* ;
+
+hash_expr     : rune clad_datum?
+              | '%' label ( '%' | '=' unit )
+              | clad_datum
+              ;
+
+list          : unit+ ( '.' blank+ unit )? blank* ;
+
+quote_expr    : ( "'" | "`" | "," ) datum ;
+
+
+bare_char     : letter | digit
+              | '!' | '$' | '%' | '&' | '*' | '+' | '-' | '/'
+              | '<' | '=' | '>' | '?' | '@' | '^' | '_' | '~'
+              ;
+
+bare_esc      : 33...126 ;
+
+
+quoted_char   : ~( '"' | '\' ) ;
+
+quoted_esc    : '\' | '"' | 'a' | 'b' | 'e'
+              | 'f' | 'n' | 'r' | 't' | 'v'
+              | 'x' hex_digit{2}
+              | 'u' '{' hex_digit+ '}'
+              ;
+
+
+rune          : letter ( letter | digit ){0,5} ;
+
+label         : hex_digit{1,12} ;
+
+
+letter        : 'a'...'z' | 'A'...'Z' ;
+
+digit         : '0'...'9' ;
+
+hex_digit     : '0'...'9' | 'a'...'f' | 'A'...'F' ;
diff --git a/spec/syntax.md b/spec/syntax.md
new file mode 100644
index 0000000..b85ed78
--- /dev/null
+++ b/spec/syntax.md
@@ -0,0 +1,34 @@
+# Zisp S-Expression Syntax
+
+We use a BNF notation with the following rules:
+
+* Concatenation of expressions is implicit: `foo bar` means `foo`
+  followed by `bar`.
+
+* Expressions may be followed by `?`, `*`, `+`, `{N}`, or `{N,M}`,
+  which have the meanings they have in regular expressions.
+
+* The syntax is defined in terms of bytes, not characters.  Terminals
+  `'c'` and `"c"` refer to the ASCII value of the given character `c`.
+  Numbers are in decimal and refer to a byte with the given value.
+
+* The `~` prefix means NOT.  It only applies to rules that match one
+  byte, and negates them.  For example, `~( 'a' | 'b' )` matches any
+  byte other than 97 and 98.
+
+* Ranges of terminal values are expressed as `x...y` (inclusive).
+
+* There is no ambiguity, backtracking, or look-ahead beyond the byte
+  currently being matched.  Rules match left to right, depth-first,
+  and greedy.  As soon as the input matches the first terminal of a
+  rule, it must match that rule to the end.
+
+The last rule means that the BNF is very simple to translate to code.
+
+The parser consumes one `unit` from an input stream every time it's
+called; it returns the `datum` therein, or EOF.
+
+```
+
+
+```