mirror of
https://github.com/ezyang/htmlpurifier.git
synced 2025-08-04 21:28:06 +02:00
[1.2.0] Documentation updated
- Moved docs from EntityParser to Encoder - Removed/updated docs in Generator git-svn-id: http://htmlpurifier.org/svnroot/htmlpurifier/trunk@490 48356398-32a2-884e-a903-53898d9a118a
This commit is contained in:
@@ -225,7 +225,30 @@ class HTMLPurifier_Encoder
|
||||
|
||||
/**
|
||||
* Translates a Unicode codepoint into its corresponding UTF-8 character.
|
||||
* @note Based on Feyd's function at
|
||||
* <http://forums.devnetwork.net/viewtopic.php?p=191404#191404>,
|
||||
* which is in public domain.
|
||||
* @note While we're going to do code point parsing anyway, a good
|
||||
* optimization would be to refuse to translate code points that
|
||||
* are non-SGML characters. However, this could lead to duplication.
|
||||
* @note This is very similar to the unichr function in
|
||||
* maintenance/generate-entity-file.php (although this is superior,
|
||||
* due to its sanity checks).
|
||||
*/
|
||||
|
||||
// +----------+----------+----------+----------+
|
||||
// | 33222222 | 22221111 | 111111 | |
|
||||
// | 10987654 | 32109876 | 54321098 | 76543210 | bit
|
||||
// +----------+----------+----------+----------+
|
||||
// | | | | 0xxxxxxx | 1 byte 0x00000000..0x0000007F
|
||||
// | | | 110yyyyy | 10xxxxxx | 2 byte 0x00000080..0x000007FF
|
||||
// | | 1110zzzz | 10yyyyyy | 10xxxxxx | 3 byte 0x00000800..0x0000FFFF
|
||||
// | 11110www | 10wwzzzz | 10yyyyyy | 10xxxxxx | 4 byte 0x00010000..0x0010FFFF
|
||||
// +----------+----------+----------+----------+
|
||||
// | 00000000 | 00011111 | 11111111 | 11111111 | Theoretical upper limit of legal scalars: 2097151 (0x001FFFFF)
|
||||
// | 00000000 | 00010000 | 11111111 | 11111111 | Defined upper limit of legal scalar codes
|
||||
// +----------+----------+----------+----------+
|
||||
|
||||
function unichr($code) {
|
||||
if($code > 1114111 or $code < 0 or
|
||||
($code >= 55296 and $code <= 57343) ) {
|
||||
|
Reference in New Issue
Block a user