hg/stx-libbasic2: comparison HTMLUtilities.st

equal deleted inserted replaced

-:0972b064ccee
+:f50a1263f3ce
+"{ Encoding: utf8 }"
 "
 COPYRIGHT (c) 2007 by eXept Software AG
 All Rights Reserved
 This software is furnished under a license and may be used
 ^self escapeCharacterEntities:aString andControlCharacters:self controlCharacters
 "
 self escapeCharacterEntities:'a<b'
-self escapeCharacterEntities:'a�b'
+self escapeCharacterEntities:'aöb'
 "
 "Modified: / 06-05-2015 / 16:30:13 / sr"
 !
 self escapeCharacterEntities:aString andControlCharacters:controlCharacters on:ws.
 ]
 "
 self escapeCharacterEntities:'a<b'
-self escapeCharacterEntities:'a�b'
+self escapeCharacterEntities:'aöb'
 "
 "Created: / 06-05-2015 / 16:29:51 / sr"
 "Modified (format): / 05-02-2017 / 17:59:32 / cg"
 !
 ]
 ].
 "
 self escapeCharacterEntities:'a<b'
-self escapeCharacterEntities:'a�b'
+self escapeCharacterEntities:'aöb'
 "
 "Created: / 05-02-2017 / 17:58:34 / cg"
 !
 ^self escapeCharacterEntities:aString andControlCharacters:self controlCharacters on:aStream
 "
 self escapeCharacterEntities:'a<b'
-self escapeCharacterEntities:'a�b'
+self escapeCharacterEntities:'aöb'
 "
 "Created: / 05-02-2017 / 18:00:56 / cg"
 !
 "
 !
 unEscape:aString
 "Convert escaped characters in an urls arguments or post fields back to their proper characters.
-Undoes the effect of urlEncode and urlEncode2.
+Undoes the effect of #urlEncoded: and #urlEncoded2:.
 These are:
 + -> space
 %XX ascii as hex digits
-%uXXXX unicode as hex digits
+%uXXXX unicode as hex digits   NOTE: %u is non-standard bit implemented in MS IIS
 %% -> %
 "
 |rs ws c peekC isUnicodeEscaped|
 self unEscape:'/Home/a%C3%A4%C3%B6%C3%BCa'
 "
 "Modified: / 09-01-2011 / 10:44:50 / cg"
 "Modified (comment): / 06-05-2015 / 15:40:04 / sr"
+"Modified (comment): / 03-02-2017 / 17:06:32 / stefan"
 !
 unescapeCharacterEntities:aString
 "helper to unescape character entities in a string.
 Normally, this is done by the HTMLParser when it scans text,
 "Created: / 06-05-2015 / 16:56:14 / sr"
 "Modified: / 18-05-2015 / 12:13:35 / sr"
 !
 urlEncode2:aStringOrStream on:ws
+<resource: #obsolete>
 "helper to escape invalid/dangerous characters in an urls arguments.
 Similar to urlEncode, but treats '*','~' and spaces differently.
 (some clients, such as bitTorrent seem to require this - time will tell...)
 Any byte not in the set 0-9, a-z, A-Z, '.', '-', '_', is encoded using
 the '%nn' format, where nn is the hexadecimal value of the byte.
 "Modified: / 06-05-2015 / 15:43:39 / sr"
 !
 urlEncode:aStringOrStream on:ws
 "helper to escape invalid/dangerous characters in an urls arguments or post-fields.
-Similar to urlEncode2, but treats '*','~' and spaces differently.
-(some clients, such as bitTorrent seem to require urlEncode2 - time will tell...)
+Any byte not in the set 0-9, a-z, A-Z, '.', '-', '_' and '~', is encoded using
-Any byte not in the set 0-9, a-z, A-Z, '.', '-', '_' and '*', is encoded using
 the '%nn' format, where nn is the hexadecimal value of the byte.
+Characters outside the ASCII range are encoded into utf8 first.
 Spaces are encoded as '+'.
 see: application/x-www-form-urlencoded
-see: RFC1738"
+see: https://tools.ietf.org/html/rfc3986 (obsoletes RFC1738)"
-|rs c cp space|
+|rs c|
-space := Character space.
 rs := aStringOrStream readStream.
-[rs atEnd] whileFalse: [
+[(c := rs nextOrNil) notNil] whileTrue: [
-c := rs next.
+|cp|
-(c isLetterOrDigit or:[ '-_.*' includes:c ]) ifTrue:[
+(c isLetterOrDigit or:['-_.~' includes:c]) ifTrue:[
 ws nextPut:c.
 ] ifFalse:[
-c == space ifTrue:[
+c == Character space ifTrue:[
 ws nextPut:$+.
 ] ifFalse:[
-ws nextPut: $%.
+cp := c codePoint.
-(cp := c codePoint) > 16rFF ifTrue:[
+cp > 16r7F ifTrue:[
-ws nextPut: $u.
+c utf8Encoded do:[:eachUtf8Char|
-cp printOn:ws base:16 size:4 fill:$0.
+ws nextPut: $%.
+eachUtf8Char codePoint printOn:ws base:16 size:2 fill:$0.
+].
 ] ifFalse:[
+ws nextPut: $%.
 cp printOn:ws base:16 size:2 fill:$0.
 ].
 ].
 ].
 ].
+"
+self urlEncoded:'hokus pokus fidibus*-/~'
+self urlEncoded:'Ützel Brötzel*-/~'
+self urlEncoded:'χαιρε'
+"
 "Modified: / 09-01-2011 / 10:43:30 / cg"
 "Modified: / 06-05-2015 / 16:06:52 / sr"
+"Modified (comment): / 07-02-2017 / 14:51:42 / stefan"
 !
 urlEncoded2: aString
+<resource: #obsolete>
 "helper to escape invalid/dangerous characters in an urls arguments or post-fields.
 Similar to urlEncoded, but treats '*','~' and spaces differently.
 (some clients, such as bitTorrent seem to require this - time will tell...)
 Any byte not in the set 0-9, a-z, A-Z, '.', '-', '_' and '~', is encoded using
 the '%nn' format, where nn is the hexadecimal value of the byte.
 "Created: / 09-01-2011 / 10:34:50 / cg"
 !
 urlEncoded: aString
 "helper to escape invalid/dangerous characters in an urls arguments or post-fields.
-Similar to urlEncoded2, but treats '*','~' and spaces differently.
-(some clients, such as bitTorrent seem to require urlEncoded2 - time will tell...)
+Any byte not in the set 0-9, a-z, A-Z, '.', '-', '_' and '~', is encoded using
-Any byte not in the set 0-9, a-z, A-Z, '.', '-', '_' and '*', is encoded using
 the '%nn' format, where nn is the hexadecimal value of the byte.
+Characters outside the ASCII range are encoded into utf8 first.
 Spaces are encoded as '+'.
 see: application/x-www-form-urlencoded
-see: RFC1738"
+see: https://tools.ietf.org/html/rfc3986 (obsoletes RFC1738)"
 |ws|
-ws := String writeStreamWithInitialSize:aString size.
+ws := WriteStream on:(String new:aString size + 20).
 self urlEncode:aString on:ws.
 ^ ws contents
 "
 self unEscape:(self urlEncoded:'-_.*%exept;')
 self urlEncoded:'-_.*%exept;'
 "
 "Modified: / 09-01-2011 / 10:43:37 / cg"
+"Modified: / 07-02-2017 / 14:54:12 / stefan"
 !
 withAllSpecialHTMLCharactersEscaped:aStringOrCharacter
 "replace ampersand, less, greater and quotes by html-character escapes"
 "
 self escape:'a b'
 self escape:'a%b'
 self escape:'a b'
 self escape:'a+b'
-self escape:'a���b'
+self escape:'aäüöb'
 "
 "Modified: / 06-05-2015 / 16:07:18 / sr"
 "Modified: / 25-11-2016 / 16:37:53 / cg"
 ! !

changeset 4302	f50a1263f3ce
parent 4297	0908351381fd
child 4333	2e428045cb82