From 3c7271f05710111bb2fc4e393773ab8026ddba26 Mon Sep 17 00:00:00 2001 From: Robert Griesemer Date: Tue, 24 May 2011 14:18:44 -0700 Subject: [PATCH] =?UTF-8?q?go=20spec:=20be=20precise=20with=20the=20use=20?= =?UTF-8?q?of=20the=20informal=20ellipsis=20=20=E2=80=A6=20and=20the=20Go?= =?UTF-8?q?=20token=20...?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Fixes #1867. R=r CC=golang-dev https://golang.org/cl/4538092 --- doc/go_spec.html | 46 +++++++++++++++++++++------------------ src/cmd/godoc/spec.go | 5 +++-- src/pkg/ebnf/ebnf_test.go | 2 +- src/pkg/ebnf/parser.go | 5 +++-- 4 files changed, 32 insertions(+), 26 deletions(-) diff --git a/doc/go_spec.html b/doc/go_spec.html index a561bbdd0df..d71da28decc 100644 --- a/doc/go_spec.html +++ b/doc/go_spec.html @@ -48,7 +48,7 @@ The syntax is specified using Extended Backus-Naur Form (EBNF): Production = production_name "=" [ Expression ] "." . Expression = Alternative { "|" Alternative } . Alternative = Term { Term } . -Term = production_name | token [ "..." token ] | Group | Option | Repetition . +Term = production_name | token [ "…" token ] | Group | Option | Repetition . Group = "(" Expression ")" . Option = "[" Expression "]" . Repetition = "{" Expression "}" . @@ -72,8 +72,12 @@ double quotes "" or back quotes ``.

-The form a ... b represents the set of characters from -a through b as alternatives. +The form a … b represents the set of characters from +a through b as alternatives. The horizontal +ellipis … is also used elsewhere in the spec to informally denote various +enumerations or code snippets that are not further specified. The character … +(as opposed to the three characters ...) is not a token of the Go +language.

Source code representation

@@ -122,9 +126,9 @@ The underscore character _ (U+005F) is considered a letter. 

 letter        = unicode_letter | "_" .
-decimal_digit = "0" ... "9" .
-octal_digit   = "0" ... "7" .
-hex_digit     = "0" ... "9" | "A" ... "F" | "a" ... "f" .
+decimal_digit = "0" … "9" .
+octal_digit   = "0" … "7" .
+hex_digit     = "0" … "9" | "A" … "F" | "a" … "f" .

Lexical elements

@@ -286,7 +290,7 @@ An optional prefix sets a non-decimal base: 0 for octal, 0x 
 int_lit     = decimal_lit | octal_lit | hex_lit .
-decimal_lit = ( "1" ... "9" ) { decimal_digit } .
+decimal_lit = ( "1" … "9" ) { decimal_digit } .
 octal_lit   = "0" { octal_digit } .
 hex_lit     = "0" ( "x" | "X" ) hex_digit { hex_digit } .
@@ -1053,9 +1057,9 @@ have the method set 

-func (p T) Read(b Buffer) bool { return ... }
-func (p T) Write(b Buffer) bool { return ... }
-func (p T) Close() { ... }
+func (p T) Read(b Buffer) bool { return … }
+func (p T) Write(b Buffer) bool { return … }
+func (p T) Close() { … }

@@ -1093,8 +1097,8 @@ If S1 and S2 also implement 

-func (p T) Lock() { ... }
-func (p T) Unlock() { ... }
+func (p T) Lock() { … }
+func (p T) Unlock() { … }

@@ -2099,7 +2103,7 @@ element index plus one. A slice literal has the form 

-[]T{x1, x2, ... xn}
+[]T{x1, x2, … xn}

@@ -2107,7 +2111,7 @@ and is a shortcut for a slice operation applied to an array literal: 

-[n]T{x1, x2, ... xn}[0 : n]
+[n]T{x1, x2, … xn}[0 : n]

@@ -2133,8 +2137,8 @@ parentheses. 

-if x == (T{a,b,c}[i]) { ... }
-if (x == T{a,b,c}[i]) { ... }
+if x == (T{a,b,c}[i]) { … }
+if (x == T{a,b,c}[i]) { … }

@@ -2567,11 +2571,11 @@ Given an expression f of function type 

-f(a1, a2, ... an)
+f(a1, a2, … an)

-calls f with arguments a1, a2, ... an. +calls f with arguments a1, a2, … an. Except for one special case, arguments must be single-valued expressions assignable to the parameter types of F and are evaluated before the function is called. @@ -2650,7 +2654,7 @@ arguments bound to the final parameter and may differ for each call site. Given the function and call 

-func Greeting(prefix string, who ... string)
+func Greeting(prefix string, who ...string)
 Greeting("hello:", "Joe", "Anna", "Eileen")
@@ -4891,7 +4895,7 @@ package main import "fmt" -// Send the sequence 2, 3, 4, ... to channel 'ch'. +// Send the sequence 2, 3, 4, … to channel 'ch'. func generate(ch chan<- int) { for i := 2; ; i++ { ch <- i // Send 'i' to channel 'ch'. @@ -5042,7 +5046,7 @@ arguments and returns no value. 

-func main() { ... }
+func main() { … }

diff --git a/src/cmd/godoc/spec.go b/src/cmd/godoc/spec.go index f8b95e387f6..d863ca0d844 100644 --- a/src/cmd/godoc/spec.go +++ b/src/cmd/godoc/spec.go @@ -99,7 +99,8 @@ func (p *ebnfParser) parseTerm() bool { case token.STRING: p.next() - if p.tok == token.ELLIPSIS { + const ellipsis = "…" // U+2026, the horizontal ellipsis character + if p.tok == token.ILLEGAL && p.lit == ellipsis { p.next() p.expect(token.STRING) } @@ -157,7 +158,7 @@ func (p *ebnfParser) parse(fset *token.FileSet, out io.Writer, src []byte) { p.out = out p.src = src p.file = fset.AddFile("", fset.Base(), len(src)) - p.scanner.Init(p.file, src, p, 0) + p.scanner.Init(p.file, src, p, scanner.AllowIllegalChars) p.next() // initializes pos, tok, lit // process source diff --git a/src/pkg/ebnf/ebnf_test.go b/src/pkg/ebnf/ebnf_test.go index e77cf64adfa..2055f872ac2 100644 --- a/src/pkg/ebnf/ebnf_test.go +++ b/src/pkg/ebnf/ebnf_test.go @@ -22,7 +22,7 @@ var grammars = []string{ `Program = "a" | "b" "c" .`, - `Program = "a" ... "z" .`, + `Program = "a" … "z" .`, `Program = Song . Song = { Note } . diff --git a/src/pkg/ebnf/parser.go b/src/pkg/ebnf/parser.go index 818168e111d..166412f990e 100644 --- a/src/pkg/ebnf/parser.go +++ b/src/pkg/ebnf/parser.go @@ -95,7 +95,8 @@ func (p *parser) parseTerm() (x Expression) { case token.STRING: tok := p.parseToken() x = tok - if p.tok == token.ELLIPSIS { + const ellipsis = "…" // U+2026, the horizontal ellipsis character + if p.tok == token.ILLEGAL && p.lit == ellipsis { p.next() x = &Range{tok, p.parseToken()} } @@ -177,7 +178,7 @@ func (p *parser) parse(fset *token.FileSet, filename string, src []byte) Grammar // initialize parser p.fset = fset p.ErrorVector.Reset() - p.scanner.Init(fset.AddFile(filename, fset.Base(), len(src)), src, p, 0) + p.scanner.Init(fset.AddFile(filename, fset.Base(), len(src)), src, p, scanner.AllowIllegalChars) p.next() // initializes pos, tok, lit grammar := make(Grammar)