From 05b677f0c484181bcbd7eb86b41a70b8e508644b Mon Sep 17 00:00:00 2001 From: Isaac Freund Date: Fri, 28 May 2021 19:21:14 +0000 Subject: [PATCH] langref: sync grammar with zig-spec repo --- doc/langref.html.in | 146 ++++++++++++++++++++++++++++++-------------- 1 file changed, 99 insertions(+), 47 deletions(-) diff --git a/doc/langref.html.in b/doc/langref.html.in index 9458abfe18..da3c038948 100644 --- a/doc/langref.html.in +++ b/doc/langref.html.in @@ -9748,7 +9748,7 @@ test "expect in release fast mode" { to see a command-line usage help menu. This will include project-specific options that were declared in the build.zig script.

- + {#header_open|Building an Executable#}

This build.zig file is automatically generated by zig init-exe.

@@ -11112,40 +11112,40 @@ fn readU32Be() u32 {} {#header_close#} {#header_open|Grammar#} - 
Root <- skip ContainerMembers eof
+      
Root <- skip container_doc_comment? ContainerMembers eof
 
 # *** Top level ***
-ContainerMembers
-    <- TestDecl ContainerMembers
-     / TopLevelComptime ContainerMembers
-     / KEYWORD_pub? TopLevelDecl ContainerMembers
-     / ContainerField COMMA ContainerMembers
-     / ContainerField
+ContainerMembers <- ContainerDeclarations (ContainerField COMMA)* (ContainerField / ContainerDeclarations)
+
+ContainerDeclarations
+    <- TestDecl ContainerDeclarations
+     / TopLevelComptime ContainerDeclarations
+     / doc_comment? KEYWORD_pub? TopLevelDecl ContainerDeclarations
      /
 
-TestDecl <- KEYWORD_test STRINGLITERALSINGLE Block
+TestDecl <- doc_comment? KEYWORD_test STRINGLITERALSINGLE? Block
 
-TopLevelComptime <- KEYWORD_comptime BlockExpr
+TopLevelComptime <- doc_comment? KEYWORD_comptime BlockExpr
 
 TopLevelDecl
     <- (KEYWORD_export / KEYWORD_extern STRINGLITERALSINGLE? / (KEYWORD_inline / KEYWORD_noinline))? FnProto (SEMICOLON / Block)
      / (KEYWORD_export / KEYWORD_extern STRINGLITERALSINGLE?)? KEYWORD_threadlocal? VarDecl
      / KEYWORD_usingnamespace Expr SEMICOLON
 
-FnProto <- KEYWORD_fn IDENTIFIER? LPAREN ParamDeclList RPAREN ByteAlign? LinkSection? CallConv? EXCLAMATIONMARK? (KEYWORD_anytype / TypeExpr)
+FnProto <- KEYWORD_fn IDENTIFIER? LPAREN ParamDeclList RPAREN ByteAlign? LinkSection? CallConv? EXCLAMATIONMARK? TypeExpr
 
 VarDecl <- (KEYWORD_const / KEYWORD_var) IDENTIFIER (COLON TypeExpr)? ByteAlign? LinkSection? (EQUAL Expr)? SEMICOLON
 
-ContainerField <- KEYWORD_comptime? IDENTIFIER (COLON TypeExpr ByteAlign?)? (EQUAL Expr)?
+ContainerField <- doc_comment? KEYWORD_comptime? IDENTIFIER (COLON (KEYWORD_anytype / TypeExpr) ByteAlign?)? (EQUAL Expr)?
 
 # *** Block Level ***
 Statement
     <- KEYWORD_comptime? VarDecl
      / KEYWORD_comptime BlockExprStatement
      / KEYWORD_nosuspend BlockExprStatement
-     / KEYWORD_suspend (SEMICOLON / BlockExprStatement)
+     / KEYWORD_suspend BlockExprStatement
      / KEYWORD_defer BlockExprStatement
-     / KEYWORD_errdefer BlockExprStatement
+     / KEYWORD_errdefer Payload? BlockExprStatement
      / IfStatement
      / LabeledStatement
      / SwitchExpr
@@ -11278,7 +11278,7 @@ WhileTypeExpr <- WhilePrefix TypeExpr (KEYWORD_else Payload? TypeExpr)?
 SwitchExpr <- KEYWORD_switch LPAREN Expr RPAREN LBRACE SwitchProngList RBRACE
 
 # *** Assembly ***
-AsmExpr <- KEYWORD_asm KEYWORD_volatile? LPAREN STRINGLITERAL AsmOutput? RPAREN
+AsmExpr <- KEYWORD_asm KEYWORD_volatile? LPAREN Expr AsmOutput? RPAREN
 
 AsmOutput <- COLON AsmOutputList AsmInput?
 
@@ -11301,13 +11301,15 @@ WhileContinueExpr <- COLON LPAREN AssignExpr RPAREN
 
 LinkSection <- KEYWORD_linksection LPAREN Expr RPAREN
 
+# Fn specific
 CallConv <- KEYWORD_callconv LPAREN Expr RPAREN
 
-ParamDecl <- (KEYWORD_noalias / KEYWORD_comptime)? (IDENTIFIER COLON)? ParamType
+ParamDecl
+    <- doc_comment? (KEYWORD_noalias / KEYWORD_comptime)? (IDENTIFIER COLON)? ParamType
+     / DOT3
 
 ParamType
     <- KEYWORD_anytype
-     / DOT3
      / TypeExpr
 
 # Control flow prefixes
@@ -11397,11 +11399,12 @@ PrefixOp
 PrefixTypeOp
     <- QUESTIONMARK
      / KEYWORD_anyframe MINUSRARROW
-     / ArrayTypeStart (ByteAlign / KEYWORD_const / KEYWORD_volatile / KEYWORD_allowzero)*
+     / SliceTypeStart (ByteAlign / KEYWORD_const / KEYWORD_volatile / KEYWORD_allowzero)*
      / PtrTypeStart (KEYWORD_align LPAREN Expr (COLON INTEGER COLON INTEGER)? RPAREN / KEYWORD_const / KEYWORD_volatile / KEYWORD_allowzero)*
+     / ArrayTypeStart
 
 SuffixOp
-    <- LBRACKET Expr (DOT2 Expr?)? RBRACKET
+    <- LBRACKET Expr (DOT2 (Expr? (COLON Expr)?)?)? RBRACKET
      / DOT IDENTIFIER
      / DOTASTERISK
      / DOTQUESTIONMARK
@@ -11409,15 +11412,17 @@ SuffixOp
 FnCallArguments <- LPAREN ExprList RPAREN
 
 # Ptr specific
-ArrayTypeStart <- LBRACKET Expr? (COLON Expr)? RBRACKET
+SliceTypeStart <- LBRACKET (COLON Expr)? RBRACKET
 
 PtrTypeStart
     <- ASTERISK
      / ASTERISK2
      / LBRACKET ASTERISK (LETTERC / COLON Expr)? RBRACKET
 
+ArrayTypeStart <- LBRACKET Expr (COLON Expr)? RBRACKET
+
 # ContainerDecl specific
-ContainerDeclAuto <- ContainerDeclType LBRACE ContainerMembers RBRACE
+ContainerDeclAuto <- ContainerDeclType LBRACE container_doc_comment? ContainerMembers RBRACE
 
 ContainerDeclType
     <- KEYWORD_struct
@@ -11429,7 +11434,7 @@ ContainerDeclType
 ByteAlign <- KEYWORD_align LPAREN Expr RPAREN
 
 # Lists
-IdentifierList <- (IDENTIFIER COMMA)* IDENTIFIER?
+IdentifierList <- (doc_comment? IDENTIFIER COMMA)* (doc_comment? IDENTIFIER)?
 
 SwitchProngList <- (SwitchProng COMMA)* SwitchProng?
 
@@ -11445,49 +11450,96 @@ ExprList <- (Expr COMMA)* Expr?
 
 # *** Tokens ***
 eof <- !.
-eol <- ('\r'? '\n') | eof
+bin <- [01]
+bin_ <- '_'? bin
+oct <- [0-7]
+oct_ <- '_'? oct
 hex <- [0-9a-fA-F]
-hex_ <- ('_'/hex)
+hex_ <- '_'? hex
 dec <- [0-9]
-dec_ <- ('_'/dec)
+dec_ <- '_'? dec
 
-dec_int <- dec (dec_* dec)?
-hex_int <- hex (hex_* dec)?
+bin_int <- bin bin_*
+oct_int <- oct oct_*
+dec_int <- dec dec_*
+hex_int <- hex hex_*
+
+ox80_oxBF <- [\200-\277]
+oxF4 <- '\364'
+ox80_ox8F <- [\200-\217]
+oxF1_oxF3 <- [\361-\363]
+oxF0 <- '\360'
+ox90_0xBF <- [\220-\277]
+oxEE_oxEF <- [\356-\357]
+oxED <- '\355'
+ox80_ox9F <- [\200-\237]
+oxE1_oxEC <- [\341-\354]
+oxE0 <- '\340'
+oxA0_oxBF <- [\240-\277]
+oxC2_oxDF <- [\302-\337]
+
+# From https://lemire.me/blog/2018/05/09/how-quickly-can-you-check-that-a-string-is-valid-unicode-utf-8/
+# First Byte      Second Byte     Third Byte      Fourth Byte
+# [0x00,0x7F]
+# [0xC2,0xDF]     [0x80,0xBF]
+#    0xE0         [0xA0,0xBF]     [0x80,0xBF]
+# [0xE1,0xEC]     [0x80,0xBF]     [0x80,0xBF]
+#    0xED         [0x80,0x9F]     [0x80,0xBF]
+# [0xEE,0xEF]     [0x80,0xBF]     [0x80,0xBF]
+#    0xF0         [0x90,0xBF]     [0x80,0xBF]     [0x80,0xBF]
+# [0xF1,0xF3]     [0x80,0xBF]     [0x80,0xBF]     [0x80,0xBF]
+#    0xF4         [0x80,0x8F]     [0x80,0xBF]     [0x80,0xBF]
+
+mb_utf8_literal <-
+       oxF4      ox80_ox8F ox80_oxBF ox80_oxBF
+     / oxF1_oxF3 ox80_oxBF ox80_oxBF ox80_oxBF
+     / oxF0      ox90_0xBF ox80_oxBF ox80_oxBF
+     / oxEE_oxEF ox80_oxBF ox80_oxBF
+     / oxED      ox80_ox9F ox80_oxBF
+     / oxE1_oxEC ox80_oxBF ox80_oxBF
+     / oxE0      oxA0_oxBF ox80_oxBF
+     / oxC2_oxDF ox80_oxBF
+
+ascii_char_not_nl_slash_squote <- [\000-\011\013-\046-\050-\133\135-\177]
 
 char_escape
-    <- '\\x' hex hex
-     / '\\u{' hex+ '}'
-     / '\\' [nr\\t'"]
+    <- "\\x" hex hex
+     / "\\u{" hex+ "}"
+     / "\\" [nr\\t'"]
 char_char
-    <- char_escape
-     / [^\\'\r\n]
+    <- mb_utf8_literal
+     / char_escape
+     / ascii_char_not_nl_slash_squote
+
 string_char
     <- char_escape
-     / [^\\"\r\n]
+     / [^\\"\n]
 
-line_comment <- '//'[^\r\n]* eol
-line_string <- ('\\\\' [^\r\n]* eol skip)+
-skip <- ([ \t] / eol / line_comment)*
+container_doc_comment <- ('//!' [^\n]* [ \n]*)+
+doc_comment <- ('///' [^\n]* [ \n]*)+
+line_comment <- '//' ![!/][^\n]* / '////' [^\n]*
+line_string <- ("\\\\" [^\n]* [ \n]*)+
+skip <- ([ \n] / line_comment)*
 
 CHAR_LITERAL <- "'" char_char "'" skip
 FLOAT
-    <- '0x' hex_* hex '.' hex_int ([pP] [-+]? hex_int)? skip
-     /      dec_int   '.' dec_int ([eE] [-+]? dec_int)? skip
-     / '0x' hex_* hex '.'? [pP] [-+]? hex_int skip
-     /      dec_int   '.'? [eE] [-+]? dec_int skip
+    <- "0x" hex_int "." hex_int ([pP] [-+]? dec_int)? skip
+     /      dec_int "." dec_int ([eE] [-+]? dec_int)? skip
+     / "0x" hex_int "."? [pP] [-+]? dec_int skip
+     /      dec_int "."? [eE] [-+]? dec_int skip
 INTEGER
-    <- '0b' [_01]*  [01]  skip
-     / '0o' [_0-7]* [0-7] skip
-     / '0x' hex_* hex skip
+    <- "0b" bin_int skip
+     / "0o" oct_int skip
+     / "0x" hex_int skip
      /      dec_int   skip
-STRINGLITERALSINGLE <- '"' string_char* '"' skip
+STRINGLITERALSINGLE <- "\"" string_char* "\"" skip
 STRINGLITERAL
     <- STRINGLITERALSINGLE
-     / line_string skip
+     / (line_string                 skip)+
 IDENTIFIER
     <- !keyword [A-Za-z_] [A-Za-z0-9_]* skip
-     / '@"' string_char* '"' skip
-BUILTINIDENTIFIER <- '@'[A-Za-z_][A-Za-z0-9_]* skip
+     / "@\"" string_char* "\""                            skip
+BUILTINIDENTIFIER <- "@"[A-Za-z_][A-Za-z0-9_]* skip
 
 
 AMPERSAND            <- '&'      ![=]      skip