| ||||||||
| ||||||||
| ||||||||
Description | ||||||||
Version : $Id$ Unicode and UTF-8 Conversion Functions | ||||||||
Synopsis | ||||||||
Unicode Type declarations | ||||||||
type Unicode = Char | ||||||||
Unicode is represented as the Char type Precondition for this is the support of Unicode character range in the compiler (e.g. ghc but not hugs) | ||||||||
type UString = [Unicode] | ||||||||
the type for Unicode strings | ||||||||
type UTF8Char = Char | ||||||||
UTF-8 charachters are represented by the Char type | ||||||||
type UTF8String = String | ||||||||
UTF-8 strings are implemented as Haskell strings | ||||||||
type UStringWithErrors = [Either String Char] | ||||||||
type DecodingFct = String -> (UString, [String]) | ||||||||
Decoding function with a pair containing the result string and a list of decoding errors as result | ||||||||
type DecodingFctEmbedErrors = String -> UStringWithErrors | ||||||||
Decoding function where decoding errors are interleaved with decoded characters | ||||||||
XML char predicates | ||||||||
isXmlChar :: Unicode -> Bool | ||||||||
checking for valid XML characters | ||||||||
isXmlLatin1Char :: Unicode -> Bool | ||||||||
test for a legal latin1 XML char | ||||||||
isXmlSpaceChar :: Unicode -> Bool | ||||||||
checking for XML space character: \n, \r, \t and " " | ||||||||
isXml11SpaceChar :: Unicode -> Bool | ||||||||
checking for XML1.1 space character: additional space 0x85 and 0x2028 see also : isXmlSpaceChar | ||||||||
isXmlNameChar :: Unicode -> Bool | ||||||||
checking for XML name character | ||||||||
isXmlNameStartChar :: Unicode -> Bool | ||||||||
checking for XML name start character see also : isXmlNameChar | ||||||||
isXmlNCNameChar :: Unicode -> Bool | ||||||||
checking for XML NCName character: no ":" allowed see also : isXmlNameChar | ||||||||
isXmlNCNameStartChar :: Unicode -> Bool | ||||||||
checking for XML NCName start character: no ":" allowed see also : isXmlNameChar, isXmlNCNameChar | ||||||||
isXmlPubidChar :: Unicode -> Bool | ||||||||
checking for XML public id character | ||||||||
isXmlLetter :: Unicode -> Bool | ||||||||
checking for XML letter | ||||||||
isXmlBaseChar :: Unicode -> Bool | ||||||||
checking for XML base charater | ||||||||
isXmlIdeographicChar :: Unicode -> Bool | ||||||||
checking for XML ideographic charater | ||||||||
isXmlCombiningChar :: Unicode -> Bool | ||||||||
checking for XML combining charater | ||||||||
isXmlDigit :: Unicode -> Bool | ||||||||
checking for XML digit | ||||||||
isXmlExtender :: Unicode -> Bool | ||||||||
checking for XML extender | ||||||||
isXmlControlOrPermanentlyUndefined :: Unicode -> Bool | ||||||||
checking for XML control or permanently discouraged char see Errata to XML1.0 (http://www.w3.org/XML/xml-V10-2e-errata) No 46 Document authors are encouraged to avoid compatibility characters, as defined in section 6.8 of [Unicode] (see also D21 in section 3.6 of [Unicode3]). The characters defined in the following ranges are also discouraged. They are either control characters or permanently undefined Unicode characters: | ||||||||
UTF-8 and Unicode conversion functions | ||||||||
utf8ToUnicode :: DecodingFct | ||||||||
UTF-8 to Unicode conversion with deletion of leading byte order mark, as described in XML standard F.1 | ||||||||
utf8ToUnicodeEmbedErrors :: DecodingFctEmbedErrors | ||||||||
latin1ToUnicode :: String -> UString | ||||||||
code conversion from latin1 to Unicode | ||||||||
ucs2ToUnicode :: String -> UString | ||||||||
UCS-2 to UTF-8 conversion with byte order mark analysis | ||||||||
ucs2BigEndianToUnicode :: String -> UString | ||||||||
UCS-2 big endian to Unicode conversion | ||||||||
ucs2LittleEndianToUnicode :: String -> UString | ||||||||
UCS-2 little endian to Unicode conversion | ||||||||
utf16beToUnicode :: String -> UString | ||||||||
UTF-16 big endian to UTF-8 conversion with removal of byte order mark | ||||||||
utf16leToUnicode :: String -> UString | ||||||||
UTF-16 little endian to UTF-8 conversion with removal of byte order mark | ||||||||
unicodeCharToUtf8 :: Unicode -> UTF8String | ||||||||
conversion from Unicode (Char) to a UTF8 encoded string. | ||||||||
unicodeToUtf8 :: UString -> UTF8String | ||||||||
conversion from Unicode strings (UString) to UTF8 encoded strings. | ||||||||
unicodeToXmlEntity :: UString -> String | ||||||||
substitute all Unicode characters, that are not legal 1-byte UTF-8 XML characters by a character reference. This function can be used to translate all text nodes and attribute values into pure ascii. see also : unicodeToLatin1 | ||||||||
unicodeToLatin1 :: UString -> String | ||||||||
substitute all Unicode characters, that are not legal latin1 UTF-8 XML characters by a character reference. This function can be used to translate all text nodes and attribute values into ISO latin1. see also : unicodeToXmlEntity | ||||||||
unicodeRemoveNoneAscii :: UString -> String | ||||||||
removes all non ascii chars, may be used to transform a document into a pure ascii representation by removing all non ascii chars from tag and attibute names see also : unicodeRemoveNoneLatin1, unicodeToXmlEntity | ||||||||
unicodeRemoveNoneLatin1 :: UString -> String | ||||||||
removes all non latin1 chars, may be used to transform a document into a pure ascii representation by removing all non ascii chars from tag and attibute names see also : unicodeRemoveNoneAscii, unicodeToLatin1 | ||||||||
intToCharRef :: Int -> String | ||||||||
convert an Unicode into a XML character reference. see also : intToCharRefHex | ||||||||
intToCharRefHex :: Int -> String | ||||||||
convert an Unicode into a XML hexadecimal character reference. see also: intToCharRef | ||||||||
getDecodingFct :: String -> Maybe DecodingFct | ||||||||
the lookup function for selecting the decoding function | ||||||||
getDecodingFctEmbedErrors :: String -> Maybe DecodingFctEmbedErrors | ||||||||
the lookup function for selecting the decoding function | ||||||||
getOutputEncodingFct :: String -> Maybe (String -> UString) | ||||||||
the lookup function for selecting the encoding function | ||||||||
normalizeNL :: String -> String | ||||||||
White Space (XML Standard 2.3) and end of line handling (2.11) #x0D and #x0D#x0A are mapped to #x0A | ||||||||
guessEncoding :: String -> String | ||||||||
Produced by Haddock version 0.8 |