"
COPYRIGHT (c) 2007 by eXept Software AG
All Rights Reserved
This software is furnished under a license and may be used
only in accordance with the terms of that license and with the
inclusion of the above copyright notice. This software may not
be provided or otherwise made available to, or used by, any
other person. No title to or ownership of the software is
hereby transferred.
"
"{ Package: 'stx:libbasic2' }"
Object subclass:#HTMLUtilities
instanceVariableNames:''
classVariableNames:'EscapeControlCharacters'
poolDictionaries:''
category:'Net-Communication-Support'
!
!HTMLUtilities class methodsFor:'documentation'!
copyright
"
COPYRIGHT (c) 2007 by eXept Software AG
All Rights Reserved
This software is furnished under a license and may be used
only in accordance with the terms of that license and with the
inclusion of the above copyright notice. This software may not
be provided or otherwise made available to, or used by, any
other person. No title to or ownership of the software is
hereby transferred.
"
!
documentation
"
Collected support functions to deal with HTML.
Used both by HTML generators (DocGenerator), HTMLParsers and the webServer.
Therefore, it has been put into libbasic2.
"
! !
!HTMLUtilities class methodsFor:'helpers'!
controlCharacters
EscapeControlCharacters isNil ifTrue:[
EscapeControlCharacters := Dictionary new.
"/ EscapeControlCharacters at:Character space put:' '.
EscapeControlCharacters at:$< put:'<'.
EscapeControlCharacters at:$> put:'>'.
EscapeControlCharacters at:$& put:'&'.
EscapeControlCharacters at:$" put:'"'.
].
^ EscapeControlCharacters.
!
escapeCharacterEntities:aString
"helper to escape invalid/dangerous characters in html strings.
These are:
control characters, '<', '>', '&' and space -> %XX ascii as hex digits
% -> %%
"
"/ TODO: this is similar to withSpecialHTMLCharactersEscaped.
"/ we should refactor this into one method only (can we do hex escapes always ?).
"/ Notice, that these two methods came into existance due to historic reasons
"/ and were developed independent of each other, but later moved to this common place.
|rs ws c controlCharacters controlString|
controlCharacters := self controlCharacters.
rs := ReadStream on: aString.
ws := WriteStream on: ''.
[ rs atEnd ] whileFalse: [
c := rs next.
controlString := controlCharacters at:c ifAbsent:nil.
controlString notNil ifTrue:[
ws nextPutAll:controlString.
] ifFalse:[
c codePoint > 16r7F ifTrue:[
ws
nextPutAll:'&#';
nextPutAll:(c codePoint printString);
nextPutAll:';'.
] ifFalse:[
ws nextPut:c.
]
]
].
^ ws contents
"
self escapeCharacterEntities:'a<b'
self escapeCharacterEntities:'aöb'
"
!
extractCharSetEncodingFromContentType:contentTypeLine
|idx rest encoding|
idx := contentTypeLine findString:'charset='.
idx == 0 ifTrue:[
^ nil
].
rest := (contentTypeLine copyFrom:idx+'charset=' size) withoutSeparators.
idx := (rest indexOfSeparator) min:(rest indexOf:$;).
idx == 0 ifTrue:[
encoding := rest
] ifFalse:[
encoding := rest copyTo:idx-1.
].
(encoding startsWith:$") ifTrue:[
encoding := encoding copyFrom:2 to:(encoding indexOf:$" startingAt:3)-1.
].
^ encoding.
"
self extractCharSetEncodingFromContentType:'text/html; charset=ascii'
self extractCharSetEncodingFromContentType:'text/html; charset='
self extractCharSetEncodingFromContentType:'text/html; fooBar=bla'
self extractCharSetEncodingFromContentType:'text/xml; charset=utf-8'
self extractCharSetEncodingFromContentType:'text/xml; charset=utf-8; bla=fasel'
"
!
extractMimeTypeFromContentType:contentTypeLine
|idx mimeAndEncoding|
idx := contentTypeLine indexOf:$:.
mimeAndEncoding := (contentTypeLine copyFrom:idx+1) withoutSeparators.
(mimeAndEncoding includes:$;) ifFalse:[
^ mimeAndEncoding
].
idx := mimeAndEncoding indexOf:$;.
^ mimeAndEncoding copyTo:idx-1
"
self extractMimeTypeFromContentType:'text/html; charset=ascii'
self extractMimeTypeFromContentType:'text/html; '
self extractMimeTypeFromContentType:'text/html'
self extractMimeTypeFromContentType:'text/xml; charset=utf-8'
"
!
unEscape:aString
"Convert escaped characters in an urls arguments or post fields to their proper characters.
These are:
+ -> space
%XX ascii as hex digits
%% -> %
"
|rs ws c peekC|
(aString indexOfAny:'+%') == 0 ifTrue:[
^ aString
].
rs := ReadStream on: aString.
ws := WriteStream on: ''.
[rs atEnd] whileFalse:[
c := rs next.
c == $+
ifTrue:[ c := Character space ]
ifFalse:[
c == $%
ifTrue: [
peekC := rs peek.
(peekC notNil and:[peekC isHexDigit]) ifTrue:[
c := (Integer readFrom:(rs next:2) radix:16) asCharacter
] ifFalse:[
c := rs next.
]
]
].
ws nextPut: c.
].
^ ws contents
"
self new unEscape:'a%20b'
self new unEscape:'a%%b'
self new unEscape:'a+b'
self new unEscape:'a%+b'
"
!
urlEncoded: aString
"helper to escape invalid/dangerous characters in an urls arguments or post-fields.
see: application/x-www-form-urlencoded
"
"
self unEscape:(self urlEncoded:'_-.*Frankfurt(Main) Hbf')
self urlEncoded:'_-.*Frankfurt(Main) Hbf') unescape
self unEscape:(self urlEncoded:'-_.*%exept;')
self urlEncoded:'-_.*%exept;'
"
| rs ws c space|
space := Character space.
rs := ReadStream on: aString.
ws := WriteStream on: ''.
[ rs atEnd ] whileFalse: [
c := rs next.
c isLetterOrDigit ifTrue:[
ws nextPut:c.
] ifFalse:[
c == space ifTrue:[
ws nextPut:$+.
] ifFalse:[
('-_.*' includes:c) ifTrue:[
ws nextPut:c.
] ifFalse:[
ws nextPut: $%.
c codePoint printOn:ws base:16.
].
].
].
].
^ ws contents
"
self new escape:'a b'
self new escape:'a%b'
self new escape:'a b'
self new escape:'a+b'
"
!
withSpecialHTMLCharactersEscaped:aStringOrCharacter
"replace ampersand, less and greater by html-character escapes"
"/ TODO: this is similar to escapeCharacterEntities.
"/ we should refactor this into one method only (can we do hex escapes always ?).
"/ Notice, that these two methods came into existance due to historic reasons
"/ and were developed independent of each other, but later moved to this common place.
|resultStream orgs repls|
"/ orgs := #( $& $< $> ).
"/ repls := #( '&' '<' '>' ).
(aStringOrCharacter isString
and:[ (aStringOrCharacter includesAny:'&<>') not ]) ifTrue:[^ aStringOrCharacter].
resultStream := WriteStream on:''.
aStringOrCharacter asString do:[:eachCharacter |
"/ huh - a switch. Sorry, but this method is used heavily.
eachCharacter == $&
ifTrue:[ resultStream nextPutAll:'&' ]
ifFalse:[
eachCharacter == $<
ifTrue:[ resultStream nextPutAll:'<' ]
ifFalse:[
eachCharacter == $>
ifTrue:[ resultStream nextPutAll:'>' ]
ifFalse:[
resultStream nextPut:eachCharacter
]]].
].
^ resultStream contents
"
self withSpecialHTMLCharactersEscaped:'<>#&'
self withSpecialHTMLCharactersEscaped:$<
self withSpecialHTMLCharactersEscaped:$#
"
"Modified: / 05-12-2006 / 13:48:59 / cg"
! !
!HTMLUtilities class methodsFor:'serving-helpers'!
escape:aString
"helper to escape invalid/dangerous characters in an urls arguments or post-fields.
These are:
control characters, '+', ';', '?', '&' and space -> %XX ascii as hex digits
% -> %%
"
| rs ws c |
rs := ReadStream on: aString.
ws := WriteStream on: ''.
[ rs atEnd ] whileFalse: [
c := rs next.
c == $% ifTrue:[
ws nextPutAll: '%%'.
] ifFalse:[
((c codePoint < 16r7F)
and:[ ('+;?& ' includes:c) not ]) ifTrue: [
ws nextPut: c.
] ifFalse:[
ws nextPut: $%.
c codePoint printOn:ws base:16.
]
]
].
^ ws contents
"
self escape:'a b'
self escape:'a%b'
self escape:'a b'
self escape:'a+b'
self escape:'aäüöb'
"
! !
!HTMLUtilities class methodsFor:'documentation'!
version
^ '$Header: /cvs/stx/stx/libbasic2/HTMLUtilities.st,v 1.3 2008-12-03 19:41:11 cg Exp $'
! !