summaryrefslogtreecommitdiffstats
path: root/scripts/export-data.js
diff options
context:
space:
mode:
authorMathias Bynens <mathias@qiwi.be>2014-05-24 14:12:00 +0200
committerMathias Bynens <mathias@qiwi.be>2014-05-24 14:12:43 +0200
commitf397e8ffa59e45763dd88cab0f7468ef29ecfdcc (patch)
tree875b2c28cd93c92a38753ad0669ec380010416e6 /scripts/export-data.js
parent9f63ec2d00bcb3ccf79a4780b040652fce7176b7 (diff)
downloadhe-f397e8ffa59e45763dd88cab0f7468ef29ecfdcc.zip
he-f397e8ffa59e45763dd88cab0f7468ef29ecfdcc.tar.gz
he-f397e8ffa59e45763dd88cab0f7468ef29ecfdcc.tar.bz2
Fix off-by-one error in printable ASCII range
Diffstat (limited to 'scripts/export-data.js')
-rw-r--r--scripts/export-data.js12
1 files changed, 6 insertions, 6 deletions
diff --git a/scripts/export-data.js b/scripts/export-data.js
index d7705cc..d9f374a 100644
--- a/scripts/export-data.js
+++ b/scripts/export-data.js
@@ -67,19 +67,19 @@ var overrides = Object.keys(
module.exports = {
'encodeMap': readJSON('encode-map'),
'encodeASCII': encodeASCII, // not used
- 'encodeNonASCII': encodeNonASCII,
+ 'regexEncodeNonASCII': encodeNonASCII,
'decodeOverrides': readJSON('decode-map-overrides'),
'decodeMap': readJSON('decode-map'),
'decodeMapLegacy': readJSON('decode-map-legacy'),
- 'astralSymbol': regenerate().addRange(0x010000, 0x10FFFF).toString(),
'invalidReferenceCodePoints': (function() {
return jsesc(readJSON('invalid-character-reference-code-points'));
}()),
- 'invalidRawCodePoints': regenerate(invalidRawCodePoints).toString(),
'invalidCodePointsString': (function() {
var string = String.fromCodePoint.apply(0, invalidRawCodePoints);
return jsesc(string, { 'wrap': true });
}()),
+ 'regexInvalidRawCodePoints': regenerate(invalidRawCodePoints).toString(),
+ 'regexAstralSymbol': regenerate().addRange(0x010000, 0x10FFFF).toString(),
'regexDecimalEscapeSource': '&#([0-9]+)(;?)',
'regexHexadecimalEscapeSource': '&#[xX]([a-fA-F0-9]+)(;?)',
'regexNamedReferenceSource': '&([0-9a-zA-Z]+);',
@@ -88,7 +88,7 @@ module.exports = {
')([=a-zA-Z0-9])?';
}()),
'regexLoneSurrogate': '[\\uD800-\\uDBFF](?:[^\\uDC00-\\uDFFF]|$)|(?:[^\\uD800-\uDBFF]|^)[\\uDC00-\\uDFFF]',
- 'ascii': (function() {
+ 'regexASCII': (function() {
return regenerate()
// Add all ASCII symbols (not just printable ASCII).
.addRange(0x0, 0x7F)
@@ -97,14 +97,14 @@ module.exports = {
.remove(overrides)
.toString();
}()),
- 'otherBMP': (function() {
+ 'regexOtherBMP': (function() {
return regenerate()
// Add all BMP symbols.
.addRange(0x0, 0xFFFF)
// Remove ASCII newlines.
.remove('\r', '\n')
// Remove printable ASCII symbols.
- .removeRange(0x20, 0x7F)
+ .removeRange(0x20, 0x7E)
// Remove code points listed in the first column of the overrides table.
// http://whatwg.org/html/tokenization.html#table-charref-overrides
.remove(overrides)