Annotation of libwww/Library/src/HTFormat.html, revision 2.51

2.10      timbl       1: <HTML>
                      2: <HEAD>
2.45      frystyk     3: <TITLE>Format Negotiation Manager</TITLE>
2.51    ! frystyk     4: <!-- Changed by: Henrik Frystyk Nielsen, 31-Oct-1995 -->
2.15      timbl       5: <NEXTID N="z18">
2.10      timbl       6: </HEAD>
2.1       timbl       7: <BODY>
2.27      frystyk     8: 
2.31      frystyk     9: <H1>The Format Manager</H1>
2.33      frystyk    10: 
                     11: <PRE>
                     12: /*
2.41      frystyk    13: **     (c) COPYRIGHT MIT 1995.
2.33      frystyk    14: **     Please first read the full copyright statement in the file COPYRIGH.
                     15: */
                     16: </PRE>
2.31      frystyk    17: 
                     18: Here we describe the functions of the HTFormat module which handles
                     19: conversion between different data representations. (In MIME parlance,
                     20: a representation is known as a content-type. In <A
2.46      frystyk    21: HREF="http://www.w3.org/pub/WWW/TheProject.html">WWW</A> the
2.31      frystyk    22: term <EM>format</EM> is often used as it is shorter). The content of
                     23: this module is:
                     24: 
                     25: <UL>
2.42      frystyk    26: <LI><A HREF="#converter">Converters</A>
2.50      frystyk    27: <LI><A HREF="#user">Generic preferences (media type, language, charset etc.)</A>
                     28: <LI><A HREF="#global">Global Preferences</A>
2.42      frystyk    29: <LI><A HREF="#Rank">Content Negotiation</A>
2.31      frystyk    30: <LI><A HREF="#z3">The Stream Stack</A>
                     31: </UL>
                     32: 
                     33: This module is implemented by <A HREF="HTFormat.c">HTFormat.c</A>, and
2.49      frystyk    34: it is a part of the <A HREF="http://www.w3.org/pub/WWW/Library/"> W3C
                     35: Reference Library</A>.
2.27      frystyk    36: 
2.31      frystyk    37: <PRE>
                     38: #ifndef HTFORMAT_H
2.1       timbl      39: #define HTFORMAT_H
                     40: 
2.31      frystyk    41: #include <A HREF="HTUtils.html">"HTUtils.h"</A>
                     42: #include <A HREF="HTStream.html">"HTStream.h"</A>
                     43: #include <A HREF="HTAtom.html">"HTAtom.h"</A>
                     44: #include <A HREF="HTList.html">"HTList.h"</A>
2.42      frystyk    45: #include <A HREF="HTAnchor.html">"HTAnchor.h"</A>
2.47      frystyk    46: #include <A HREF="HTReq.html">"HTReq.h"</A>
2.31      frystyk    47: </PRE>
2.1       timbl      48: 
2.42      frystyk    49: <A NAME="converter"><H2>Stream Converters</H2></A>
2.18      luotonen   50: 
2.42      frystyk    51: A <CODE><A NAME="z12">converter</A></CODE> is a stream with a special
                     52: set of parameters and which is registered as capable of converting
                     53: from a MIME type to something else (maybe another MIME-type). A
                     54: converter is defined to be a function returning a stream and accepting
                     55: the following parameters. The content type elements are atoms for
                     56: which we have defined a prototype.
2.18      luotonen   57: 
2.31      frystyk    58: <PRE>
2.42      frystyk    59: typedef HTStream * HTConverter PARAMS((HTRequest *     request,
                     60:                                        void *          param,
                     61:                                        HTFormat        input_format,
                     62:                                        HTFormat        output_format,
                     63:                                        HTStream *      output_stream));
                     64: </PRE>
2.18      luotonen   65: 
2.50      frystyk    66: <A NAME="user"><H2>Generic Preferences</H2></A>
2.31      frystyk    67: 
2.42      frystyk    68: The Library contains functionality for letting the application (or
                     69: user) express the preferences for the rendition of a given data object
                     70: when issuing a request. The categories supported are:
                     71: 
                     72: <UL>
                     73: <LI>Content type (media type)
                     74: <LI>Encoding
                     75: <LI>Language
                     76: <LI>Charset
                     77: </UL>
2.17      luotonen   78: 
2.42      frystyk    79: <A NAME="FormatTypes"><H3>Registration of Accepted Content Types</H3></A>
2.17      luotonen   80: 
2.42      frystyk    81: A <CODE>presenter</CODE> is a module (possibly an external program)
                     82: which can present a graphic object of a certain MIME type to the
                     83: user. That is, <CODE>presenters</CODE> are normally used to present
                     84: objects that the <CODE>converters</CODE> are not able to handle. Data
                     85: is transferred to the external program using for example the <A
                     86: HREF="HTFWrite.html">HTSaveAndExecute</A> stream which writes to a
                     87: local file. Both presenters and converters are of the type <A
                     88: HREF="#converter">HTConverter</A>.
2.31      frystyk    89: 
                     90: <PRE>
2.42      frystyk    91: typedef struct _HTPresentation {
                     92:     HTFormat   rep;                         /* representation name atomized */
                     93:     HTFormat   rep_out;                         /* resulting representation */
                     94:     HTConverter *converter;          /* The routine to gen the stream stack */
                     95:     char *     command;                               /* MIME-format string */
                     96:     char *     test_command;                          /* MIME-format string */
                     97:     double     quality;                     /* Between 0 (bad) and 1 (good) */
                     98:     double     secs;
                     99:     double     secs_per_byte;
                    100: } HTPresentation;
2.28      frystyk   101: </PRE>
                    102: 
2.42      frystyk   103: <H4>Predefined Content Types</H4>
2.28      frystyk   104: 
2.42      frystyk   105: These macros (which used to be constants) define some basic internally
                    106: referenced representations. The <CODE>www/xxx</CODE> ones are of
                    107: course not MIME standard. <CODE>star/star</CODE> is an output format
                    108: which leaves the input untouched. It is useful for diagnostics, and
                    109: for users who want to see the original, whatever it is.
2.28      frystyk   110: 
                    111: <PRE>
                    112: #define WWW_SOURCE     HTAtom_for("*/*")      /* Whatever it was originally */
                    113: </PRE>
                    114: 
2.31      frystyk   115: <CODE>www/present</CODE> represents the user's perception of the
                    116: document.  If you convert to www/present, you present the material to
                    117: the user.
2.10      timbl     118: 
2.28      frystyk   119: <PRE>
                    120: #define WWW_PRESENT    HTAtom_for("www/present")   /* The user's perception */
                    121: </PRE>
                    122: 
                    123: The message/rfc822 format means a MIME message or a plain text message
                    124: with no MIME header. This is what is returned by an HTTP server.
                    125: 
                    126: <PRE>
                    127: #define WWW_MIME       HTAtom_for("www/mime")             /* A MIME message */
                    128: </PRE>
                    129: 
2.31      frystyk   130: <CODE>www/unknown</CODE> is a really unknown type.  Some default
                    131: action is appropriate.
2.13      timbl     132: 
2.28      frystyk   133: <PRE>
                    134: #define WWW_UNKNOWN     HTAtom_for("www/unknown")
2.13      timbl     135: </PRE>
2.28      frystyk   136: 
2.31      frystyk   137: These are regular MIME types defined. Others can be added!
2.28      frystyk   138: 
                    139: <PRE>
                    140: #define WWW_PLAINTEXT  HTAtom_for("text/plain")
2.1       timbl     141: #define WWW_POSTSCRIPT         HTAtom_for("application/postscript")
                    142: #define WWW_RICHTEXT   HTAtom_for("application/rtf")
2.10      timbl     143: #define WWW_AUDIO       HTAtom_for("audio/basic")
2.1       timbl     144: #define WWW_HTML       HTAtom_for("text/html")
2.11      timbl     145: #define WWW_BINARY     HTAtom_for("application/octet-stream")
2.26      frystyk   146: #define WWW_VIDEO      HTAtom_for("video/mpeg")
2.38      frystyk   147: #define WWW_GIF        HTAtom_for("image/gif")
2.44      frystyk   148: #define WWW_PNG        HTAtom_for("image/x-png")  /* @@@ soon image/png @@@ */
2.48      frystyk   149: </PRE>
                    150: 
                    151: We also have some that come from the various protocols
                    152: 
                    153: <PRE>
                    154: #define WWW_GOPHER_MENU HTAtom_for("text/x-gopher")
                    155: 
                    156: #define WWW_FTP_LNST   HTAtom_for("text/x-ftp-lnst")
                    157: #define WWW_FTP_LIST   HTAtom_for("text/x-ftp-list")
                    158: 
                    159: #define WWW_NNTP_LIST   HTAtom_for("text/x-nntp-list")
                    160: #define WWW_NNTP_OVER  HTAtom_for("text/x-nntp-over")
                    161: #define WWW_NNTP_HEAD  HTAtom_for("text/x-nntp-head")
2.28      frystyk   162: </PRE>
                    163: 
2.50      frystyk   164: <H4>Add a Presenter</H4>
                    165: 
                    166: This function creates a presenter object and adds to the list of
                    167: conversions.
2.31      frystyk   168: 
2.1       timbl     169: <DL>
2.31      frystyk   170: <DT>conversions
                    171: <DD>The list of <CODE>conveters</CODE> and <CODE>presenters</CODE>
2.50      frystyk   172: <DT>rep_in
2.42      frystyk   173: <DD>the MIME-style format name
2.50      frystyk   174: <DT>rep_out
                    175: <DD>is the resulting content-type after the conversion
                    176: <DT>converter
                    177: <DD>is the routine to call which actually does the conversion
2.1       timbl     178: <DT>quality
2.31      frystyk   179: <DD>A degradation faction [0..1]
2.1       timbl     180: <DT>maxbytes
2.31      frystyk   181: <DD>A limit on the length acceptable as input (0 infinite)
2.1       timbl     182: <DT>maxsecs
2.31      frystyk   183: <DD>A limit on the time user will wait (0 for infinity)
2.1       timbl     184: </DL>
                    185: 
2.31      frystyk   186: <PRE>
2.49      frystyk   187: extern void HTPresentation_add (HTList *       conversions,
                    188:                                CONST char *    representation,
                    189:                                CONST char *    command,
                    190:                                CONST char *    test_command,
                    191:                                double          quality,
                    192:                                double          secs, 
                    193:                                double          secs_per_byte);
2.31      frystyk   194: </PRE>
2.1       timbl     195: 
2.50      frystyk   196: <H4>Delete a list of Presenters</H4>
                    197: 
                    198: <PRE>
                    199: extern void HTPresentation_deleteAll   (HTList * list);
                    200: </PRE>
                    201: 
                    202: <H4>Add a Converter</H4>
                    203: 
                    204: This function creates a presenter object and adds to the list of
                    205: conversions.
2.1       timbl     206: 
                    207: <DL>
2.31      frystyk   208: <DT>conversions
                    209: <DD>The list of <CODE>conveters</CODE> and <CODE>presenters</CODE>
2.1       timbl     210: <DT>rep_in
2.42      frystyk   211: <DD>the MIME-style format name
2.1       timbl     212: <DT>rep_out
2.31      frystyk   213: <DD>is the resulting content-type after the conversion
2.1       timbl     214: <DT>converter
2.31      frystyk   215: <DD>is the routine to call which actually does the conversion
                    216: <DT>quality
                    217: <DD>A degradation faction [0..1]
                    218: <DT>maxbytes
                    219: <DD>A limit on the length acceptable as input (0 infinite)
                    220: <DT>maxsecs
                    221: <DD>A limit on the time user will wait (0 for infinity)
2.1       timbl     222: </DL>
                    223: 
                    224: <PRE>
2.49      frystyk   225: extern void HTConversion_add   (HTList *       conversions,
                    226:                                CONST char *    rep_in,
                    227:                                CONST char *    rep_out,
                    228:                                HTConverter *   converter,
                    229:                                double          quality,
                    230:                                double          secs, 
                    231:                                double          secs_per_byte);
2.42      frystyk   232: </PRE>
                    233: 
2.50      frystyk   234: <H4>Delete a list of Converters</H4>
                    235: 
                    236: <PRE>
                    237: extern void HTConversion_deleteAll     (HTList * list);
                    238: </PRE>
                    239: 
2.42      frystyk   240: <A NAME="Encoding"><H3>Registration of Accepted Content Encodings</H3></A>
                    241: 
                    242: Encodings are the HTTP extension of transfer encodings. Encodings
2.50      frystyk   243: include compress, gzip etc.
2.42      frystyk   244: 
                    245: <PRE>
                    246: typedef struct _HTAcceptNode {
                    247:     HTAtom *   atom;
                    248:     double     quality;
                    249: } HTAcceptNode;
                    250: </PRE>
                    251: 
                    252: <H4>Predefined Encoding Types</H4>
                    253: 
                    254: <PRE>
                    255: #define WWW_ENC_7BIT           HTAtom_for("7bit")
                    256: #define WWW_ENC_8BIT           HTAtom_for("8bit")
                    257: #define WWW_ENC_BINARY         HTAtom_for("binary")
                    258: #define WWW_ENC_BASE64         HTAtom_for("base64")
                    259: #define WWW_ENC_COMPRESS       HTAtom_for("compress")
                    260: #define WWW_ENC_GZIP           HTAtom_for("gzip")
                    261: </PRE>
                    262: 
                    263: <H4>Register an Encoding</H4>
                    264: 
                    265: <PRE>
2.50      frystyk   266: extern void HTEncoding_add (HTList *           list,
                    267:                            CONST char *        enc,
                    268:                            double              quality);
2.42      frystyk   269: </PRE>
2.31      frystyk   270: 
2.50      frystyk   271: <H4>Delete a list of Encoders</H4>
2.31      frystyk   272: 
2.50      frystyk   273: <PRE>
2.51    ! frystyk   274: extern void HTEncoding_deleteAll (HTList * list);
2.50      frystyk   275: </PRE>
                    276: 
                    277: <H3><A NAME="charset">Accepted Charsets</A></H3>
2.31      frystyk   278: 
2.42      frystyk   279: <H4>Register a Charset</H4>
                    280: 
                    281: <PRE>
2.50      frystyk   282: extern void HTCharset_add (HTList *            list,
                    283:                           CONST char *         charset,
                    284:                           double               quality);
2.42      frystyk   285: </PRE>
                    286: 
2.50      frystyk   287: <H4>Delete a list of Charsets</H4>
2.42      frystyk   288: 
2.50      frystyk   289: <PRE>
                    290: extern void HTCharset_deleteAll        (HTList * list);
                    291: </PRE>
                    292: 
                    293: <A NAME="Language"><H3>Accepted Content Languages</H3></A>
2.31      frystyk   294: 
2.42      frystyk   295: <H4>Register a Language</H4>
2.31      frystyk   296: 
                    297: <PRE>
2.50      frystyk   298: extern void HTLanguage_add (HTList *           list,
                    299:                            CONST char *        lang,
                    300:                            double              quality);
                    301: </PRE>
                    302: 
                    303: <H4>Delete a list of Languages</H4>
                    304: 
                    305: <PRE>
2.51    ! frystyk   306: extern void HTLanguage_deleteAll (HTList * list);
2.50      frystyk   307: </PRE>
                    308: 
                    309: <A NAME="global"><H2>Global Registrations</H2></A>
                    310: 
                    311: There are two places where these preferences can be registered: in a
                    312: <EM>global</EM> list valid for <B>all</B> requests and a
                    313: <EM>local</EM> list valid for a particular request only. These are
                    314: valid for <EM>all</EM> requests. See the <A HREF="HTReq.html">Request
                    315: Manager</A> fro local sets.
                    316: 
2.51    ! frystyk   317: <H3>Converters and Presenters</H3>
2.50      frystyk   318: 
                    319: The <EM>global</EM> list of specific conversions which the format
                    320: manager can do in order to fulfill the request.  There is also a <A
                    321: HREF="HTReq.html"><EM>local</EM></A> list of conversions which
                    322: contains a generic set of possible conversions.
                    323: 
                    324: <PRE>
                    325: extern void HTFormat_setConversion     (HTList *list);
                    326: extern HTList * HTFormat_conversion    (void);
2.31      frystyk   327: </PRE>
                    328: 
2.50      frystyk   329: <H3>Content Encodings</H3>
2.42      frystyk   330: 
2.50      frystyk   331: <PRE>
                    332: extern void HTFormat_setEncoding       (HTList *list);
                    333: extern HTList * HTFormat_encoding      (void);
                    334: </PRE>
2.1       timbl     335: 
2.51    ! frystyk   336: <H3>Content Languages</H3>
2.50      frystyk   337: 
                    338: <PRE>
                    339: extern void HTFormat_setLanguage       (HTList *list);
                    340: extern HTList * HTFormat_language      (void);
                    341: </PRE>
2.42      frystyk   342: 
2.51    ! frystyk   343: <H3>Content Charsets</H3>
2.1       timbl     344: 
2.31      frystyk   345: <PRE>
2.50      frystyk   346: extern void HTFormat_setCharset                (HTList *list);
                    347: extern HTList * HTFormat_charset       (void);
2.31      frystyk   348: </PRE>
                    349: 
2.50      frystyk   350: <H3>Delete All Global Lists</H3>
2.42      frystyk   351: 
2.50      frystyk   352: This is a convenience function that might make life easier.
2.34      frystyk   353: 
                    354: <PRE>
2.50      frystyk   355: extern void HTFormat_deleteAll (void);
2.34      frystyk   356: </PRE>
2.31      frystyk   357: 
                    358: <A NAME="Rank"><H2>Ranking of Accepted Formats</H2></A>
                    359: 
2.36      frystyk   360: This function is used when the best match among several possible
                    361: documents is to be found as a function of the accept headers sent in
                    362: the client request.
2.31      frystyk   363: 
                    364: <PRE>
2.42      frystyk   365: typedef struct _HTContentDescription {
                    366:     char *     filename;
                    367:     HTAtom *   content_type;
                    368:     HTAtom *   content_language;
                    369:     HTAtom *   content_encoding;
                    370:     int                content_length;
                    371:     double     quality;
                    372: } HTContentDescription;
                    373: 
2.32      frystyk   374: extern BOOL HTRank PARAMS((HTList * possibilities,
2.31      frystyk   375:                           HTList * accepted_content_types,
                    376:                           HTList * accepted_content_languages,
                    377:                           HTList * accepted_content_encodings));
2.1       timbl     378: </PRE>
2.31      frystyk   379: 
2.42      frystyk   380: <H2><A NAME="z3">The Stream Stack</A></H2>
2.31      frystyk   381: 
                    382: This is the routine which actually sets up the conversion. It
                    383: currently checks only for direct conversions, but multi-stage
                    384: conversions are forseen.  It takes a stream into which the output
                    385: should be sent in the final format, builds the conversion stack, and
                    386: returns a stream into which the data in the input format should be
2.42      frystyk   387: fed. If <CODE>guess</CODE> is true and input format is
2.31      frystyk   388: <CODE>www/unknown</CODE>, try to guess the format by looking at the
                    389: first few bytes of the stream. <P>
2.1       timbl     390: 
2.31      frystyk   391: <PRE>
2.32      frystyk   392: extern HTStream * HTStreamStack PARAMS((HTFormat       rep_in,
2.31      frystyk   393:                                        HTFormat        rep_out,
                    394:                                        HTStream *      output_stream,
                    395:                                        HTRequest *     request,
                    396:                                        BOOL            guess));
2.1       timbl     397: </PRE>
2.31      frystyk   398: 
2.42      frystyk   399: <H2>Cost of a Stream Stack</H2>
2.31      frystyk   400: 
                    401: Must return the cost of the same stack which HTStreamStack would set
2.1       timbl     402: up.
                    403: 
2.31      frystyk   404: <PRE>
2.37      frystyk   405: extern double HTStackValue     PARAMS((HTList *        conversions,
2.31      frystyk   406:                                        HTFormat        format_in,
                    407:                                        HTFormat        format_out,
2.37      frystyk   408:                                        double          initial_value,
2.31      frystyk   409:                                        long int        length));
                    410: 
2.42      frystyk   411: #endif /* HTFORMAT */
2.38      frystyk   412: </PRE>
                    413: 
2.42      frystyk   414: End of declaration module
2.31      frystyk   415: 
                    416: </BODY>
2.10      timbl     417: </HTML>

Webmaster