1/* Part of SWI-Prolog 2 3 Author: Jan Wielemaker 4 E-mail: J.Wielemaker@vu.nl 5 WWW: http://www.swi-prolog.org 6 Copyright (c) 2002-2018, University of Amsterdam 7 VU University Amsterdam 8 All rights reserved. 9 10 Redistribution and use in source and binary forms, with or without 11 modification, are permitted provided that the following conditions 12 are met: 13 14 1. Redistributions of source code must retain the above copyright 15 notice, this list of conditions and the following disclaimer. 16 17 2. Redistributions in binary form must reproduce the above copyright 18 notice, this list of conditions and the following disclaimer in 19 the documentation and/or other materials provided with the 20 distribution. 21 22 THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS 23 "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT 24 LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS 25 FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE 26 COPYRIGHT OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, 27 INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, 28 BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; 29 LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER 30 CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT 31 LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN 32 ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE 33 POSSIBILITY OF SUCH DAMAGE. 34*/ 35 36:- module(mimetype, 37 [ file_mime_type/2, % +Path, -Type 38 file_content_type/2, % +Path, -Type 39 file_content_type/3 % +Path, ?MediaType, -Type 40 ]). 41 42/** <module> Determine mime-type for a file 43 44Simple library to guess the mime-type from the extension of a file. As 45various applications need to do this type of inferencing it seems 46worthwhile to place this functionality in an extensible library. 47 48@tbd Consider content handling (using the Unix file command) 49@tbd Allow parameters? (e.g. text/html; charset=UTF-8) 50*/ 51 52:- multifile 53 mime:mime_extension/2, 54 mime:text_mimetype/1, 55 mime:charset/3. 56 57%! file_mime_type(+FileName, -MimeType) is semidet. 58% 59% True when MimeType is the mime-type to be used for sending 60% FileName. The default rules can be overridden and extended using 61% the hook mime:mime_extension/2. 62% 63% @param MimeType is a compound term of the form Type/SubType. 64 65file_mime_type(File, MimeType) :- 66 file_name_extension(_, Ext, File), 67 ( current_prolog_flag(windows, true) 68 -> downcase_atom(Ext, Lower), 69 mime_extension(Lower, MimeType) 70 ; mime_extension(Ext, M0) 71 -> MimeType = M0 72 ; downcase_atom(Ext, Lower), 73 mime_extension(Lower, MimeType) 74 ), 75 !. 76file_mime_type(File, MimeType) :- 77 file_base_name(File, Base), 78 downcase_atom(Base, Lower), 79 name_mimetype(Lower, Mime), 80 !, 81 MimeType = Mime. 82file_mime_type(_, MimeType) :- 83 default_mimetype(MimeType). 84 85%! mime:mime_extension(+Ext, -MimeType) is semidet. 86% 87% Hook that is called by file_mime_type/2 before the default table 88% is examined. 89 90mime_extension(Ext, MimeType) :- 91 ( mime:mime_extension(Ext, Mime) 92 -> MimeType = Mime 93 ; ext_mimetype(Ext, Mime) 94 -> MimeType = Mime 95 ). 96 97%! default_mimetype(-MimeType) is semidet. 98% 99% If the mime-type cannot be determined from the file extension, 100% this predicate is used as fallback. It takes the value from the 101% Prolog flag =default_mimetype=. To change the default, use e.g., 102% 103% == 104% :- set_prolog_flag(default_mimetype, text/plain). 105% == 106% 107% The initial default mime-type is =|application/unknown|=. Use 108% the value =|-|= to denote there is no default. 109 110:- create_prolog_flag(default_mimetype, application/unknown, [keep(true)]). 111 112default_mimetype(MimeType) :- 113 current_prolog_flag(default_mimetype, MimeType), 114 MimeType = _/_. 115 116 117%! ext_mimetype(+Extension, -MimeType) is semidet. 118% 119% Built-in table of file-name extension to mime-type mappings. 120% 121% @tbd Update this list, e.g., from 122% http://www.webmaster-toolkit.com/mime-types.shtml 123 124 % plain text 125ext_mimetype(txt, text/plain). 126 % markup 127ext_mimetype(htm, text/html). 128ext_mimetype(html, text/html). 129ext_mimetype(xhtml, application/'xhtml+xml'). 130ext_mimetype(sgml, text/'x-sgml'). 131ext_mimetype(sgm, text/'x-sgml'). 132ext_mimetype(xml, text/xml). 133ext_mimetype(css, text/css). 134ext_mimetype(xsl, text/xml). % Unclear what this should be. 135ext_mimetype(md, text/markdown). 136 % Other data markup 137ext_mimetype(json, application/json). 138ext_mimetype(yaml, application/yaml). % Not official 139 % semantic web stuff 140ext_mimetype(rdf, application/'rdf+xml'). 141ext_mimetype(rdfs, application/'rdf+xml'). 142ext_mimetype(owl, application/'rdf+xml'). 143ext_mimetype(ttl, application/turtle). 144ext_mimetype(nt, application/'n-triples'). 145ext_mimetype(nq, application/'n-quads'). 146 % Prolog source 147ext_mimetype(pl, text/plain). 148 % Other languages 149ext_mimetype(c, text/'x-c'). 150ext_mimetype(h, text/'x-c'). 151ext_mimetype(cc, text/'x-c'). 152ext_mimetype(py, text/'x-python'). 153ext_mimetype(java, text/'x-java'). 154ext_mimetype(sh, text/plain). 155 % Packaged formats 156ext_mimetype(gz, application/'x-gzip'). 157ext_mimetype(zip, application/zip). 158ext_mimetype(tgz, application/'x-gtar'). 159 % Some document formats 160ext_mimetype(pdf, application/pdf). 161ext_mimetype(doc, application/msword). 162 % Java classes 163ext_mimetype(class, application/'octet-stream'). 164ext_mimetype(jar, application/'x-java-archive'). 165 % JavaScript and WASM 166ext_mimetype(js, text/javascript). 167ext_mimetype(wasm, application/wasm). 168ext_mimetype(data, application/'octet-stream'). 169 % Visual Basic Script :-( 170ext_mimetype(vbs, text/vbscript). 171 % Some image formats 172ext_mimetype(jpg, image/jpeg). 173ext_mimetype(jpeg, image/jpeg). 174ext_mimetype(gif, image/gif). 175ext_mimetype(png, image/png). 176ext_mimetype(tif, image/tiff). 177ext_mimetype(tiff, image/tiff). 178ext_mimetype(xpm, image/'x-xpixmap'). 179ext_mimetype(ico, image/'x-ico'). 180ext_mimetype(svg, image/'svg+xml'). 181 % Google earth 182ext_mimetype(kml, application/'vnd.google-earth.kml+xml'). 183ext_mimetype(kmz, application/'vnd.google-earth.kmz'). 184 185 % Flash 186ext_mimetype(swf, application/'x-shockwave-flash'). 187ext_mimetype(flv, video/'x-flv'). 188 % MP3 189ext_mimetype(mp3, audio/mpeg). 190 % Downloads 191ext_mimetype(rpm, application/'x-rpm'). 192ext_mimetype(exe, application/'x-executable'). 193 194%! name_mimetype(+DownCaseFileName, -MimeType) is semidet. 195% 196% Determine the mime-type of files based on the entire filename. 197 198name_mimetype(makefile, text/plain). 199name_mimetype(configure, text/plain). 200name_mimetype('configure.in', text/plain). 201name_mimetype('configure.ac', text/plain). 202name_mimetype('makefile.in', text/plain). 203name_mimetype('makefile.am', text/plain). 204name_mimetype('readme.in', text/plain). 205name_mimetype('license', text/plain). 206 207%! text_mimetype(+MimeType) is semidet. 208% 209% True when documents of MimeType are text documents and thus may need 210% a charset specification. 211 212text_mimetype(MimeType) :- 213 mime:text_mimetype(MimeType), 214 !. 215text_mimetype(text/_). 216 217%! file_content_type(+File:atom, -ContentType:atom) is det. 218%! file_content_type(+File:atom, ?MediaType, -ContentType:atom) is det. 219% 220% True if File should be served using =|ContentType:|= ContentType. It 221% takes the following steps: 222% 223% 1. Determine the media type using file_mime_type/2, unless 224% already specified using file_content_type/3. 225% 2. Determine it is a text file using text_mimetype/1 226% 3. Use the charset from the Prolog flag `default_charset` 227% 228% The behavior is controlled by several hooks and a flag. 229% 230% - mime:mime_extension/2 defines the media type 231% - mime:text_mimetype/1 defines the media type is text 232% - mime:charset/3 derives the charset for a file with a given 233% media type, if the media type is text according to 234% mime:text_mimetype/1. 235% - If mime:text_mimetype/1 succeeds and mime:charset/3 fails, the 236% flag `default_charset` defines the charset unless it is set 237% to `-`. The flag set by default to =UTF-8= if the Prolog 238% flag `encoding` is set to `utf8`. 239 240file_content_type(File, ContentType) :- 241 file_content_type(File, _, ContentType). 242file_content_type(File, MediaType, ContentType) :- 243 ( ground(MediaType) 244 -> true 245 ; file_mime_type(File, MediaType) 246 ), 247 ( text_mimetype(MediaType), 248 ( mime:charset(File, MediaType, Charset0) 249 -> Charset = Charset0 250 ; default_charset(Charset) 251 ) 252 -> format(atom(ContentType), '~w; charset=~w', [MediaType, Charset]) 253 ; format(atom(ContentType), '~w', [MediaType]) 254 ). 255 256%! mime:charset(+File, +MediaType, -Charset) is semidet. 257% 258% Hook that determines the Charset for File that has media type 259% MediaType. This hook allows overruling file_content_type/2. 260% 261% @see mime:text_mimetype/1. 262 263default_charset(Charset) :- 264 current_prolog_flag(default_charset, Charset), 265 Charset \== (-). 266 267set_default_charset :- 268 current_prolog_flag(default_charset, _), 269 !. 270set_default_charset :- 271 current_prolog_flag(encoding, utf8), 272 !, 273 set_prolog_flag(default_charset, 'UTF-8'). 274set_default_charset. 275 276:- initialization(set_default_charset).