joepie91/pegjs
1
0
Fork 0
Code Issues Pull requests Releases Wiki Activity

Added \uFEFF (BOM) to the definition of whitespace in the metagrammar.

Browse source 
The Rhino bug that prevented inclusion of \uFEFF among the whitespace characters
is no longer relevant here because we compile character classes into regexps
now, which avoids the infinite recursion.
This commit is contained in:
David Majda 2010-04-11 11:24:36 +02:00
parent 383c5acaa6
commit 3291c70d97
3 changed files with 5 additions and 7 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

4
lib/metagrammar.js
View file

@ -3212,13 +3212,13 @@ PEG.grammarParser = (function(){
var savedReportMatchFailures = context.reportMatchFailures;
context.reportMatchFailures = false;
if (this._input.substr(this._pos).match(/^[   ᠎ -   　]/) !== null) {
if (this._input.substr(this._pos).match(/^[   ᠎ -   　]/) !== null) {
var result301 = this._input[this._pos];
this._pos++;
} else {
var result301 = null;
if (context.reportMatchFailures) {
this._matchFailed('[' + "   ᠎ -   　" + ']');
this._matchFailed('[' + "   ᠎ -   　" + ']');
}
}
context.reportMatchFailures = savedReportMatchFailures;

7
lib/metagrammar.pegjs
View file

@ -205,8 +205,5 @@ eol "end of line": "\n" / "\r\n" / "\r" / "\u2028" / "\u2029"
eolChar: [\n\r\u2028\u2029]
/*
* Modelled after ECMA-262, 5th ed., 7.2. \uFEFF should be between the
* characters too, but it causes infinite loop in Rhino.
*/
whitespace "whitespace": [ \t\v\f\u00A0\u1680\u180E\u2000-\u200A\u202F\u205F\u3000]
/* Modelled after ECMA-262, 5th ed., 7.2. */
whitespace "whitespace": [ \t\v\f\u00A0\uFEFF\u1680\u180E\u2000-\u200A\u202F\u205F\u3000]

1
test/metagrammar-test.js
View file

@ -434,6 +434,7 @@ with (PEG.Grammar) {
grammarParserParses('start:\f"abcd"', simpleGrammar);
grammarParserParses('start: "abcd"', simpleGrammar);
grammarParserParses('start:\u00A0"abcd"', simpleGrammar);
grammarParserParses('start:\uFEFF"abcd"', simpleGrammar);
grammarParserParses('start:\u1680"abcd"', simpleGrammar);
grammarParserParses('start:\u180E"abcd"', simpleGrammar);
grammarParserParses('start:\u2000"abcd"', simpleGrammar);