diff options
| author | Ruben Beltran del Rio <git@r.bdr.sh> | 2025-07-09 08:34:19 +0200 |
|---|---|---|
| committer | Ruben Beltran del Rio <git@r.bdr.sh> | 2025-07-09 08:34:19 +0200 |
| commit | 1ec7f2c6deb64f5b13b32fae2bf74ae2d8aaaabb (patch) | |
| tree | 47b6addedf0bdb18d35774e9b027d07074929d4a /Documentation/wmap-spec.ebnf | |
| parent | 6926feead1a7fadb7f5f974996bef8c30b3bfdbe (diff) | |
Account for CRLF/CR/LF. Lex note text. Use Wmap Parser for renderer.
Diffstat (limited to 'Documentation/wmap-spec.ebnf')
| -rw-r--r-- | Documentation/wmap-spec.ebnf | 17 |
1 files changed, 11 insertions, 6 deletions
diff --git a/Documentation/wmap-spec.ebnf b/Documentation/wmap-spec.ebnf index d3c5ad7..05eabe5 100644 --- a/Documentation/wmap-spec.ebnf +++ b/Documentation/wmap-spec.ebnf @@ -2,7 +2,7 @@ (* Top-level structure *) program = { line } ; -line = ( entity newline ) | ( ignored_line newline ) | newline ; +line = ( entity line_ending ) | ( ignored_line line_ending ) | line_ending ; entity = vertex | edge | note | stage | group | inertia | evolution ; ignored_line = ? any sequence of tokens that doesn't match entity grammar ? ; @@ -23,8 +23,8 @@ edge_type = "--" | "->" ; sign = "+" | "-" ; (* Terminal symbols *) -vertex_label = preserved_case( { character - ( "-" | "+" | "," | "[" | "]" | "(" | ")" | newline ) } ) ; -text = preserved_case( { character - newline } ) ; +vertex_label = preserved_case( { character - ( "-" | "+" | "," | "[" | "]" | "(" | ")" | line_ending ) } ) ; +text = preserved_case( { character - line_ending } ) ; real_number = [ digit ] { digit } [ "." { digit } ] | "." digit { digit } ; stage_number = case_insensitive( "i" | "ii" | "iii" | "iv" ) ; shape_label = case_insensitive( "x" | "square" | "triangle" | "circle" ) ; @@ -32,7 +32,10 @@ shape_label = case_insensitive( "x" | "square" | "triangle" | "circle" ) ; (* Lexical elements *) character = ? any Unicode character ? ; digit = "0" | "1" | "2" | "3" | "4" | "5" | "6" | "7" | "8" | "9" ; -newline = ? newline character ? ; +line_ending = lf | crlf | cr ; +lf = ? U+000A (Line Feed) ? ; +cr = ? U+000D (Carriage Return) ? ; +crlf = cr lf ; (* Lexical rules *) case_insensitive(x) = ? case-insensitive match of x ? ; @@ -42,6 +45,8 @@ preserved_case(x) = ? case-insensitive match of x, preserving original case for (* - Keywords and shape labels are case-insensitive *) (* - Vertex labels are case-insensitive for matching but preserve original case *) (* - Text content preserves original case *) -(* - Whitespace (except newlines) may appear between any tokens *) +(* - Whitespace (except line endings) may appear between any tokens *) (* - Each line contains exactly one entity *) -(* - Invalid lines should be ignored. *) +(* - Invalid lines should be ignored *) +(* - Line endings support Unix (LF), Windows (CRLF), and classic Mac (CR) formats *) +(* - CRLF is treated as a single line ending, not separate CR and LF *) |