View source with raw comments or as raw
    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          ]).

Determine mime-type for a file

Simple library to guess the mime-type from the extension of a file. As various applications need to do this type ofinferencing it seems worthwhile to place this functionality in an extensible library.

To be done
- Consider content handling (using the Unix file command)
- Allow parameters? (e.g. text/html; charset=UTF-8) */
   52:- multifile
   53    mime:mime_extension/2,
   54    mime:text_mimetype/1,
   55    mime:charset/3.
 file_mime_type(+FileName, -MimeType) is semidet
True when MimeType is the mime-type to be used for sending FileName. The default rules can be overridden and extended using the hook mime:mime_extension/2.
Arguments:
MimeType- is a compound term of the form Type/SubType.
   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).
 mime:mime_extension(+Ext, -MimeType) is semidet
Hook that is called by file_mime_type/2 before the default table is examined.
   90mime_extension(Ext, MimeType) :-
   91    (   mime:mime_extension(Ext, Mime)
   92    ->  MimeType = Mime
   93    ;   ext_mimetype(Ext, Mime)
   94    ->  MimeType = Mime
   95    ).
 default_mimetype(-MimeType) is semidet
If the mime-type cannot be determined from the file extension, this predicate is used as fallback. It takes the value from the Prolog flag default_mimetype. To change the default, use e.g.,
:- set_prolog_flag(default_mimetype, text/plain).

The initial default mime-type is application/unknown. Use the value - to denote there is no default.

  110:- create_prolog_flag(default_mimetype, application/unknown, [keep(true)]).  111
  112default_mimetype(MimeType) :-
  113    current_prolog_flag(default_mimetype, MimeType),
  114    MimeType = _/_.
 ext_mimetype(+Extension, -MimeType) is semidet
Built-in table of file-name extension to mime-type mappings.
To be done
- Update this list, e.g., from http://www.webmaster-toolkit.com/mime-types.shtml
  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').
 name_mimetype(+DownCaseFileName, -MimeType) is semidet
Determine the mime-type of files based on the entire filename.
  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).
 text_mimetype(+MimeType) is semidet
True when documents of MimeType are text documents and thus may need a charset specification.
  211text_mimetype(MimeType) :-
  212    mime:text_mimetype(MimeType),
  213    !.
  214text_mimetype(text/_).
 file_content_type(+File:atom, -ContentType:atom) is det
 file_content_type(+File:atom, ?MediaType, -ContentType:atom) is det
True if File should be served using ContentType: ContentType. It takes the following steps:
  1. Determine the media type using file_mime_type/2, unless already specified using file_content_type/3.
  2. Determine it is a text file using text_mimetype/1
  3. Use the charset from the Prolog flag default_charset

The behavior is controlled by several hooks and a flag.

  239file_content_type(File, ContentType) :-
  240    file_content_type(File, _, ContentType).
  241file_content_type(File, MediaType, ContentType) :-
  242    (   ground(MediaType)
  243    ->  true
  244    ;   file_mime_type(File, MediaType)
  245    ),
  246    (   text_mimetype(MediaType),
  247        (   mime:charset(File, MediaType, Charset0)
  248        ->  Charset = Charset0
  249        ;   default_charset(Charset)
  250        )
  251    ->  format(atom(ContentType), '~w; charset=~w', [MediaType, Charset])
  252    ;   format(atom(ContentType), '~w', [MediaType])
  253    ).
 mime:charset(+File, +MediaType, -Charset) is semidet
Hook that determines the Charset for File that has media type MediaType. This hook allows overruling file_content_type/2.
See also
- text_mimetype/1.
  262default_charset(Charset) :-
  263    current_prolog_flag(default_charset, Charset),
  264    Charset \== (-).
  265
  266set_default_charset :-
  267    current_prolog_flag(default_charset, _),
  268    !.
  269set_default_charset :-
  270    current_prolog_flag(encoding, utf8),
  271    !,
  272    set_prolog_flag(default_charset, 'UTF-8').
  273set_default_charset.
  274
  275:- initialization(set_default_charset).