1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283
|
(* $Id: netencoding.mli,v 1.5 2001/08/30 19:45:43 gerd Exp $
* ----------------------------------------------------------------------
*
*)
(**********************************************************************)
(* Several encodings important for the net *)
(**********************************************************************)
(**********************************************************************)
(* Base 64 encoding *)
(**********************************************************************)
(* See RFC 2045 for a description of Base 64 encoding. *)
(* THREAD-SAFETY:
* All Base64 functions are reentrant and thus thread-safe.
*)
module Base64 : sig
val encode : ?pos:int -> ?len:int -> ?linelength:int -> ?crlf:bool ->
string -> string
(* Compute the "base 64" encoding of the given string argument.
* Note that the result is a string that only contains the characters
* a-z, A-Z, 0-9, +, /, =, and optionally spaces, CR and LF characters.
*
* If pos and/or len are passed, only the substring starting at
* pos (default: 0) with length len (default: rest of the string)
* is encoded.
*
* The result is divided up into lines not longer than 'linelength'
* (without counting the line separator); default: do not divide lines.
* If 'linelength' is smaller than 4, no line division is performed.
* If 'linelength' is not divisible by 4, the produced lines are a
* bit shorter than 'linelength'.
*
* If 'crlf' (default: false) the lines are ended by CRLF; otherwise
* they are only ended by LF.
* (You need the crlf option to produce correct MIME messages.)
*
*)
val url_encode : ?pos:int -> ?len:int -> ?linelength:int -> ?crlf:bool ->
string -> string
(* Same as 'encode' but use slightly different characters that can be
* part of URLs without additional encodings.
* The encoded string consists only of the characters a-z, A-Z, 0-9,
* -, /, .
* 'url_encode' does NOT implement the Base 64 encoding as described
* in the standard!
*)
val encode_substring : string -> pos:int -> len:int -> linelength:int ->
crlf:bool -> string
(* *** DEPRECATED FUNCTION *** Use 'encode' instead! ***
*
* encode_substring s pos len linelen crlf:
* Encodes the substring at position 'pos' in 's' with length 'len'.
* The result is divided up into lines not longer than 'linelen' (without
* counting the line separator).
* If 'linelen' is smaller than 4, no line division is performed.
* If 'linelen' is not divisible by 4, the produced lines are a
* bit shorter than 'linelen'.
* If 'crlf' the lines are ended by CRLF; otherwise they are only
* ended by LF.
* (You need the crlf option to produce correct MIME messages.)
*)
val decode : ?pos:int -> ?len:int -> ?url_variant:bool ->
?accept_spaces:bool -> string -> string
(* Decodes the given string argument.
*
* If pos and/or len are passed, only the substring starting at
* pos (default: 0) with length len (default: rest of the string)
* is decoded.
*
* If url_variant (default: true) is set, the functions also
* accepts the characters '-' and '.' as produced by 'url_encode'.
*
* If accept_spaces (default: false) is set, the function ignores
* white space contained in the string to decode (otherwise the
* function fails if it finds white space).
*)
val decode_ignore_spaces : string -> string
(* *** DEPRECATED FUNCTION *** Use 'decode' instead! ***
*
* Decodes the string, too, but it is allowed that the string contains
* whitespace characters.
* This function is slower than 'decode'.
*)
val decode_substring : string -> pos:int -> len:int -> url_variant:bool ->
accept_spaces:bool -> string
(* *** DEPRECATED FUNCTION *** Use 'decode' instead! ***
*
* decode_substring s pos len url spaces:
* Decodes the substring of 's' beginning at 'pos' with length 'len'.
* If 'url', strings created by 'url_encode' are accepted, too.
* If 'spaces', whitespace characters are allowed in the string.
*)
end
(**********************************************************************)
(* Quoted printable encoding *)
(**********************************************************************)
(* See RFC 2045.
* This implementation assumes that the encoded string has a text MIME
* type. Because of this, the characters CR and LF are never protected
* by hex tokens; they are copied literally to the output string.
*)
(* THREAD-SAFETY:
* All QuotedPrintable functions are reentrant and thus thread-safe.
*)
module QuotedPrintable :
sig
val encode : ?pos:int -> ?len:int -> string -> string
(* Encodes the string and returns it.
* Note line breaks:
* No additional soft line breaks are added. The characters CR
* and LF are not represented as =0D resp. =0A. (But other control
* characters ARE encoded.)
* Note unsafe characters:
* As recommended by RFC 2045, the characters !\"#$@[]^`{|}~
* are additionally represented as hex tokens. -- "
*
* If pos and/or len are passed, only the substring starting at
* pos (default: 0) with length len (default: rest of the string)
* is encoded.
*)
val encode_substring : string -> pos:int -> len:int -> string
(* *** DEPRECATED FUNCTION *** Use 'encode' instead! ***
* encode_substring s pos len:
* Encodes the substring of 's' beginning at 'pos' with length 'len'.
*)
val decode : ?pos:int -> ?len:int -> string -> string
(* Decodes the string and returns it.
* Most format errors cause an Invalid_argument exception.
* Note that soft line breaks can be properly decoded although
* 'encode' will never produce them.
*
* If pos and/or len are passed, only the substring starting at
* pos (default: 0) with length len (default: rest of the string)
* is decoded.
*)
val decode_substring : string -> pos:int -> len:int -> string
(* *** DEPRECATED FUNCTION *** Use 'decode' instead! ***
* decode_substring s pos len:
* Decodes the substring of 's' beginning at 'pos' with length 'len'.
*)
end
(**********************************************************************)
(* Q encoding *)
(**********************************************************************)
(* See RFC 2047.
* The functions behave similar to those of QuotedPrintable.
*)
(* THREAD-SAFETY:
* All Q functions are reentrant and thus thread-safe.
*)
module Q :
sig
val encode : ?pos:int -> ?len:int -> string -> string
(* Note:
* All characters except alphanumeric characters are protected by
* hex tokens.
* In particular, spaces are represented as "=20", not as "_".
*)
val decode : ?pos:int -> ?len:int -> string -> string
val encode_substring : string -> pos:int -> len:int -> string
(* *** DEPRECATED FUNCTION *** Use 'encode' instead! *** *)
val decode_substring : string -> pos:int -> len:int -> string
(* *** DEPRECATED FUNCTION *** Use 'decode' instead! *** *)
end
(**********************************************************************)
(* B encoding *)
(**********************************************************************)
(* The B encoding of RFC 2047 is the same as Base64. *)
(**********************************************************************)
(* URL-encoding *)
(**********************************************************************)
(* Encoding/Decoding within URLs:
*
* The following two functions perform the '%'-substitution for
* characters that may otherwise be interpreted as metacharacters.
*
* According to: RFC 1738, RFC 1630
*
* Option ~plus: This option has been added because there are some
* implementations that do not map ' ' to '+', for example Javascript's
* escape function. The default is "true" because this is the RFC-
* compliant definition.
*)
(* THREAD-SAFETY:
* The Url functions are thread-safe.
*)
module Url :
sig
val decode : ?plus:bool -> string -> string
(* Option ~plus: Whether '+' is converted to space. The default
* is true. If false, '+' is returned as it is.
*)
val encode : ?plus:bool -> string -> string
(* Option ~plus: Whether spaces are converted to '+'. The default
* is true. If false, spaces are converted to "%20", and
* only %xx sequences are produced.
*)
end
(**********************************************************************)
(* HTMLization *)
(**********************************************************************)
(* Encodes characters that need protection by converting them to
* entity references. E.g. "<" is converted to "<".
* As the entities may be named, there is a dependency on the character
* set. Currently, there are only functions for the Latin 1 alphabet.
*)
(* THREAD-SAFETY:
* The Html functions are thread-safe.
*)
module Html :
sig
val encode_from_latin1 : string -> string
(* Encodes the characters 0-8, 11-12, 14-31, '<', '>', '"', '&',
* 127-255. If the characters have a name, a named entity is
* preferred over a numeric entity.
*)
val decode_to_latin1 : string -> string
(* Decodes the string. Unknown named entities are left as they
* are (i.e. decode_to_latin1 "&nonsense;" = "&nonsense;").
* The same applies to numeric entities greater than 255.
*)
end
(* ======================================================================
* History:
*
* $Log: netencoding.mli,v $
* Revision 1.5 2001/08/30 19:45:43 gerd
* Module Url: added the option ~plus
*
* Revision 1.4 2000/06/25 22:34:43 gerd
* Added labels to arguments.
*
* Revision 1.3 2000/06/25 21:15:48 gerd
* Checked thread-safety.
*
* Revision 1.2 2000/03/03 01:08:29 gerd
* Added Netencoding.Html functions.
*
* Revision 1.1 2000/03/02 01:14:48 gerd
* Initial revision.
*
*
*)
|