source: draft-ietf-httpbis/latest/p3-payload.xml @ 94

Last change on this file since 94 was 94, checked in by ylafon@…, 12 years ago

added Yves Lafon in authors section

  • Property svn:eol-style set to native
File size: 106.0 KB
Line 
1<?xml version="1.0" encoding="utf-8"?>
2<!DOCTYPE rfc [
3  <!ENTITY MAY "<bcp14 xmlns='http://purl.org/net/xml2rfc/ext'>MAY</bcp14>">
4  <!ENTITY MUST "<bcp14 xmlns='http://purl.org/net/xml2rfc/ext'>MUST</bcp14>">
5  <!ENTITY MUST-NOT "<bcp14 xmlns='http://purl.org/net/xml2rfc/ext'>MUST NOT</bcp14>">
6  <!ENTITY OPTIONAL "<bcp14 xmlns='http://purl.org/net/xml2rfc/ext'>OPTIONAL</bcp14>">
7  <!ENTITY RECOMMENDED "<bcp14 xmlns='http://purl.org/net/xml2rfc/ext'>RECOMMENDED</bcp14>">
8  <!ENTITY REQUIRED "<bcp14 xmlns='http://purl.org/net/xml2rfc/ext'>REQUIRED</bcp14>">
9  <!ENTITY SHALL "<bcp14 xmlns='http://purl.org/net/xml2rfc/ext'>SHALL</bcp14>">
10  <!ENTITY SHALL-NOT "<bcp14 xmlns='http://purl.org/net/xml2rfc/ext'>SHALL NOT</bcp14>">
11  <!ENTITY SHOULD "<bcp14 xmlns='http://purl.org/net/xml2rfc/ext'>SHOULD</bcp14>">
12  <!ENTITY SHOULD-NOT "<bcp14 xmlns='http://purl.org/net/xml2rfc/ext'>SHOULD NOT</bcp14>">
13  <!ENTITY ID-VERSION "latest">
14  <!ENTITY ID-MONTH "December">
15  <!ENTITY ID-YEAR "2007">
16  <!ENTITY caching                  "<xref target='Part6' xmlns:x='http://purl.org/net/xml2rfc/ext'/>">
17  <!ENTITY header-transfer-encoding "<xref target='Part1' x:rel='#header.transfer-encoding' xmlns:x='http://purl.org/net/xml2rfc/ext'/>">
18  <!ENTITY header-allow             "<xref target='Part2' x:rel='#header.allow' xmlns:x='http://purl.org/net/xml2rfc/ext'/>">
19  <!ENTITY header-content-length    "<xref target='Part1' x:rel='#header.content-length' xmlns:x='http://purl.org/net/xml2rfc/ext'/>">
20  <!ENTITY header-content-range     "<xref target='Part5' x:rel='#header.content-range' xmlns:x='http://purl.org/net/xml2rfc/ext'/>">
21  <!ENTITY header-expires           "<xref target='Part6' x:rel='#header.expires' xmlns:x='http://purl.org/net/xml2rfc/ext'/>">
22  <!ENTITY header-last-modified     "<xref target='Part4' x:rel='#header.last-modified' xmlns:x='http://purl.org/net/xml2rfc/ext'/>">
23  <!ENTITY header-user-agent        "<xref target='Part2' x:rel='#header.user-agent' xmlns:x='http://purl.org/net/xml2rfc/ext'/>">
24  <!ENTITY message-body             "<xref target='Part1' x:rel='#message.body' xmlns:x='http://purl.org/net/xml2rfc/ext'/>">
25  <!ENTITY message-length           "<xref target='Part1' x:rel='#message.length' xmlns:x='http://purl.org/net/xml2rfc/ext'/>">
26  <!ENTITY multipart-byteranges     "<xref target='Part5' x:rel='#internet.media.type.multipart.byteranges' xmlns:x='http://purl.org/net/xml2rfc/ext'/>">
27]>
28<?rfc toc="yes" ?>
29<?rfc symrefs="yes" ?>
30<?rfc sortrefs="yes" ?>
31<?rfc compact="yes"?>
32<?rfc subcompact="no" ?>
33<?rfc linkmailto="no" ?>
34<?rfc editing="no" ?>
35<?rfc-ext allow-markup-in-artwork="yes" ?>
36<?rfc-ext include-references-in-index="yes" ?>
37<rfc obsoletes="2068, 2616" category="std"
38     ipr="full3978" docName="draft-ietf-httpbis-p3-payload-&ID-VERSION;"
39     xmlns:x='http://purl.org/net/xml2rfc/ext' xmlns:ed="http://greenbytes.de/2002/rfcedit">
40<front>
41
42  <title abbrev="HTTP/1.1">HTTP/1.1, part 3: Message Payload and Content Negotiation</title>
43
44  <author initials="R." surname="Fielding" fullname="Roy T. Fielding" role="editor">
45    <organization abbrev="Day Software">Day Software</organization>
46    <address>
47      <postal>
48        <street>23 Corporate Plaza DR, Suite 280</street>
49        <city>Newport Beach</city>
50        <region>CA</region>
51        <code>92660</code>
52        <country>USA</country>
53      </postal>
54      <phone>+1-949-706-5300</phone>
55      <facsimile>+1-949-706-5305</facsimile>
56      <email>fielding@gbiv.com</email>
57      <uri>http://roy.gbiv.com/</uri>
58    </address>
59  </author>
60
61  <author initials="J." surname="Gettys" fullname="Jim Gettys">
62    <organization>One Laptop per Child</organization>
63    <address>
64      <postal>
65        <street>21 Oak Knoll Road</street>
66        <city>Carlisle</city>
67        <region>MA</region>
68        <code>01741</code>
69        <country>USA</country>
70      </postal>
71      <email>jg@laptop.org</email>
72      <uri>http://www.laptop.org/</uri>
73    </address>
74  </author>
75 
76  <author initials="J." surname="Mogul" fullname="Jeffrey C. Mogul">
77    <organization abbrev="HP">Hewlett-Packard Company</organization>
78    <address>
79      <postal>
80        <street>HP Labs, Large Scale Systems Group</street>
81        <street>1501 Page Mill Road, MS 1177</street>
82        <city>Palo Alto</city>
83        <region>CA</region>
84        <code>94304</code>
85        <country>USA</country>
86      </postal>
87      <email>JeffMogul@acm.org</email>
88    </address>
89  </author>
90
91  <author initials="H." surname="Frystyk" fullname="Henrik Frystyk Nielsen">
92    <organization abbrev="Microsoft">Microsoft Corporation</organization>
93    <address>
94      <postal>
95        <street>1 Microsoft Way</street>
96        <city>Redmond</city>
97        <region>WA</region>
98        <code>98052</code>
99        <country>USA</country>
100      </postal>
101      <email>henrikn@microsoft.com</email>
102    </address>
103  </author>
104
105  <author initials="L." surname="Masinter" fullname="Larry Masinter">
106    <organization abbrev="Adobe Systems">Adobe Systems, Incorporated</organization>
107    <address>
108      <postal>
109        <street>345 Park Ave</street>
110        <city>San Jose</city>
111        <region>CA</region>
112        <code>95110</code>
113        <country>USA</country>
114      </postal>
115      <email>LMM@acm.org</email>
116      <uri>http://larry.masinter.net/</uri>
117    </address>
118  </author>
119 
120  <author initials="P." surname="Leach" fullname="Paul J. Leach">
121    <organization abbrev="Microsoft">Microsoft Corporation</organization>
122    <address>
123      <postal>
124        <street>1 Microsoft Way</street>
125        <city>Redmond</city>
126        <region>WA</region>
127        <code>98052</code>
128      </postal>
129      <email>paulle@microsoft.com</email>
130    </address>
131  </author>
132   
133  <author initials="T." surname="Berners-Lee" fullname="Tim Berners-Lee">
134    <organization abbrev="W3C/MIT">World Wide Web Consortium</organization>
135    <address>
136      <postal>
137        <street>MIT Computer Science and Artificial Intelligence Laboratory</street>
138        <street>The Stata Center, Building 32</street>
139        <street>32 Vassar Street</street>
140        <city>Cambridge</city>
141        <region>MA</region>
142        <code>02139</code>
143        <country>USA</country>
144      </postal>
145      <email>timbl@w3.org</email>
146      <uri>http://www.w3.org/People/Berners-Lee/</uri>
147    </address>
148  </author>
149
150  <author initials="Y." surname="Lafon" fullname="Yves Lafon">
151    <organization abbrev="W3C">World Wide Web Consortium</organization>
152    <address>
153      <postal>
154        <street>W3C / ERCIM</street>
155        <street>2004, rte des Lucioles</street>
156        <city>Sophia-Antipolis</city>
157        <region>AM</region>
158        <code>06902</code>
159        <country>France</country>
160      </postal>
161      <email>ylafon@w3.org</email>
162      <uri>http://www.raubacapeu.net/people/yves/</uri>
163    </address>
164  </author>
165
166  <date month="&ID-MONTH;" year="&ID-YEAR;"/>
167
168<abstract>
169<t>
170   The Hypertext Transfer Protocol (HTTP) is an application-level
171   protocol for distributed, collaborative, hypermedia information
172   systems. HTTP has been in use by the World Wide Web global information
173   initiative since 1990. This document is Part 3 of the seven-part specification
174   that defines the protocol referred to as "HTTP/1.1" and, taken together,
175   obsoletes RFC 2616.  Part 3 defines HTTP message content,
176   metadata, and content negotiation.
177</t>
178</abstract>
179
180<note title="Editorial Note (To be removed by RFC Editor)">
181  <t>
182    This version of the HTTP specification contains only minimal editorial
183    changes from <xref target="RFC2616"/> (abstract, introductory paragraph,
184    and authors' addresses).  All other changes are due to partitioning the
185    original into seven mostly independent parts.  The intent is for readers
186    of future drafts to able to use draft 00 as the basis for comparison
187    when the WG makes later changes to the specification text.  This draft
188    will shortly be followed by draft 01 (containing the first round of changes
189    that have already been agreed to on the mailing list). There is no point in
190    reviewing this draft other than to verify that the partitioning has been
191    done correctly.  Roy T. Fielding, Yves Lafon, and Julian Reschke
192    will be the editors after draft 00 is submitted.
193  </t>
194  <t>
195    Discussion of this draft should take place on the HTTPBIS working group
196    mailing list (ietf-http-wg@w3.org). The current issues list is
197    at <eref target="http://www3.tools.ietf.org/wg/httpbis/trac/report/11"/>
198    and related documents (including fancy diffs) can be found at
199    <eref target="http://www3.tools.ietf.org/wg/httpbis/"/>.
200  </t>
201</note>
202</front>
203<middle>
204<section title="Introduction" anchor="introduction">
205<t>
206   This document will define aspects of HTTP related to the payload of
207   messages (message content), including metadata and media types, along
208   with HTTP content negotiation.  Right now it only includes the extracted
209   relevant sections of RFC 2616 without edit.
210</t>
211</section>
212
213<section title="Protocol Parameters" anchor="protocol.parameters">
214
215<section title="Character Sets" anchor="character.sets">
216<t>
217   HTTP uses the same definition of the term "character set" as that
218   described for MIME:
219</t>
220<t>
221   The term "character set" is used in this document to refer to a
222   method used with one or more tables to convert a sequence of octets
223   into a sequence of characters. Note that unconditional conversion in
224   the other direction is not required, in that not all characters may
225   be available in a given character set and a character set may provide
226   more than one sequence of octets to represent a particular character.
227   This definition is intended to allow various kinds of character
228   encoding, from simple single-table mappings such as US-ASCII to
229   complex table switching methods such as those that use ISO-2022's
230   techniques. However, the definition associated with a MIME character
231   set name &MUST; fully specify the mapping to be performed from octets
232   to characters. In particular, use of external profiling information
233   to determine the exact mapping is not permitted.
234</t>
235<t><list><t>
236      <x:h>Note:</x:h> This use of the term "character set" is more commonly
237      referred to as a "character encoding." However, since HTTP and
238      MIME share the same registry, it is important that the terminology
239      also be shared.
240</t></list></t>
241<t>
242   HTTP character sets are identified by case-insensitive tokens. The
243   complete set of tokens is defined by the IANA Character Set registry
244   (<eref target="http://www.iana.org/assignments/character-sets"/>).
245</t>
246<figure><artwork type="abnf2616"><iref primary="true" item="Grammar" subitem="charset"/>
247    charset = token
248</artwork></figure>
249<t>
250   Although HTTP allows an arbitrary token to be used as a charset
251   value, any token that has a predefined value within the IANA
252   Character Set registry &MUST; represent the character set defined
253   by that registry. Applications &SHOULD; limit their use of character
254   sets to those defined by the IANA registry.
255</t>
256<t>
257   HTTP uses charset in two contexts: within an Accept-Charset request
258   header (in which the charset value is an unquoted token) and as the
259   value of a parameter in a Content-type header (within a request or
260   response), in which case the parameter value of the charset parameter
261   may be quoted.
262</t>
263<t>
264   Implementors should be aware of IETF character set requirements <xref target="RFC2279"/>
265   <xref target="RFC2277"/>.
266</t>
267
268<section title="Missing Charset" anchor="missing.charset">
269<t>
270   Some HTTP/1.0 software has interpreted a Content-Type header without
271   charset parameter incorrectly to mean "recipient should guess."
272   Senders wishing to defeat this behavior &MAY; include a charset
273   parameter even when the charset is ISO-8859-1 and &SHOULD; do so when
274   it is known that it will not confuse the recipient.
275</t>
276<t>
277   Unfortunately, some older HTTP/1.0 clients did not deal properly with
278   an explicit charset parameter. HTTP/1.1 recipients &MUST; respect the
279   charset label provided by the sender; and those user agents that have
280   a provision to "guess" a charset &MUST; use the charset from the
281   content-type field if they support that charset, rather than the
282   recipient's preference, when initially displaying a document. See
283   <xref target="canonicalization.and.text.defaults"/>.
284</t>
285</section>
286</section>
287
288<section title="Content Codings" anchor="content.codings">
289<t>
290   Content coding values indicate an encoding transformation that has
291   been or can be applied to an entity. Content codings are primarily
292   used to allow a document to be compressed or otherwise usefully
293   transformed without losing the identity of its underlying media type
294   and without loss of information. Frequently, the entity is stored in
295   coded form, transmitted directly, and only decoded by the recipient.
296</t>
297<figure><artwork type="abnf2616"><iref primary="true" item="Grammar" subitem="content-coding"/>
298    content-coding   = token
299</artwork></figure>
300<t>
301   All content-coding values are case-insensitive. HTTP/1.1 uses
302   content-coding values in the Accept-Encoding (<xref target="header.accept-encoding"/>) and
303   Content-Encoding (<xref target="header.content-encoding"/>) header fields. Although the value
304   describes the content-coding, what is more important is that it
305   indicates what decoding mechanism will be required to remove the
306   encoding.
307</t>
308<t>
309   The Internet Assigned Numbers Authority (IANA) acts as a registry for
310   content-coding value tokens. Initially, the registry contains the
311   following tokens:
312</t>
313<t>
314   gzip<iref item="gzip"/>
315  <list>
316    <t>
317        An encoding format produced by the file compression program
318        "gzip" (GNU zip) as described in RFC 1952 <xref target="RFC1952"/>. This format is a
319        Lempel-Ziv coding (LZ77) with a 32 bit CRC.
320    </t>
321  </list>
322</t>
323<t>
324   compress<iref item="compress"/>
325  <list><t>
326        The encoding format produced by the common UNIX file compression
327        program "compress". This format is an adaptive Lempel-Ziv-Welch
328        coding (LZW).
329</t><t>
330        Use of program names for the identification of encoding formats
331        is not desirable and is discouraged for future encodings. Their
332        use here is representative of historical practice, not good
333        design. For compatibility with previous implementations of HTTP,
334        applications &SHOULD; consider "x-gzip" and "x-compress" to be
335        equivalent to "gzip" and "compress" respectively.
336  </t></list>
337</t>
338<t>
339   deflate<iref item="deflate"/>
340  <list><t>
341        The "zlib" format defined in RFC 1950 <xref target="RFC1950"/> in combination with
342        the "deflate" compression mechanism described in RFC 1951 <xref target="RFC1951"/>.
343  </t></list>
344</t>
345<t>
346   identity<iref item="identity"/>
347  <list><t>
348        The default (identity) encoding; the use of no transformation
349        whatsoever. This content-coding is used only in the Accept-Encoding
350        header, and &SHOULD-NOT;  be used in the Content-Encoding
351        header.
352  </t></list>
353</t>
354<t>
355   New content-coding value tokens &SHOULD; be registered; to allow
356   interoperability between clients and servers, specifications of the
357   content coding algorithms needed to implement a new value &SHOULD; be
358   publicly available and adequate for independent implementation, and
359   conform to the purpose of content coding defined in this section.
360</t>
361</section>
362
363<section title="Media Types" anchor="media.types">
364<t>
365   HTTP uses Internet Media Types <xref target="RFC4288"/> in the Content-Type (<xref target="header.content-type"/>)
366   and Accept (<xref target="header.accept"/>) header fields in order to provide
367   open and extensible data typing and type negotiation.
368</t>
369<figure><artwork type="abnf2616"><iref primary="true" item="Grammar" subitem="media-type"/><iref primary="true" item="Grammar" subitem="type"/><iref primary="true" item="Grammar" subitem="subtype"/>
370    media-type     = type "/" subtype *( ";" parameter )
371    type           = token
372    subtype        = token
373</artwork></figure>
374<t>
375   Parameters &MAY; follow the type/subtype in the form of attribute/value
376   pairs.
377</t>
378<figure><artwork type="abnf2616"><iref primary="true" item="Grammar" subitem="parameter"/><iref primary="true" item="Grammar" subitem="attribute"/><iref primary="true" item="Grammar" subitem="value"/>
379    parameter               = attribute "=" value
380    attribute               = token
381    value                   = token | quoted-string
382</artwork></figure>
383<t>
384   The type, subtype, and parameter attribute names are case-insensitive.
385   Parameter values might or might not be case-sensitive,
386   depending on the semantics of the parameter name. Linear white space
387   (LWS) &MUST-NOT; be used between the type and subtype, nor between an
388   attribute and its value. The presence or absence of a parameter might
389   be significant to the processing of a media-type, depending on its
390   definition within the media type registry.
391</t>
392<t>
393   Note that some older HTTP applications do not recognize media type
394   parameters. When sending data to older HTTP applications,
395   implementations &SHOULD; only use media type parameters when they are
396   required by that type/subtype definition.
397</t>
398<t>
399   Media-type values are registered with the Internet Assigned Number
400   Authority (IANA). The media type registration process is
401   outlined in RFC 4288 <xref target="RFC4288"/>. Use of non-registered media types is
402   discouraged.
403</t>
404
405<section title="Canonicalization and Text Defaults" anchor="canonicalization.and.text.defaults">
406<t>
407   Internet media types are registered with a canonical form. An
408   entity-body transferred via HTTP messages &MUST; be represented in the
409   appropriate canonical form prior to its transmission except for
410   "text" types, as defined in the next paragraph.
411</t>
412<t>
413   When in canonical form, media subtypes of the "text" type use CRLF as
414   the text line break. HTTP relaxes this requirement and allows the
415   transport of text media with plain CR or LF alone representing a line
416   break when it is done consistently for an entire entity-body. HTTP
417   applications &MUST; accept CRLF, bare CR, and bare LF as being
418   representative of a line break in text media received via HTTP. In
419   addition, if the text is represented in a character set that does not
420   use octets 13 and 10 for CR and LF respectively, as is the case for
421   some multi-byte character sets, HTTP allows the use of whatever octet
422   sequences are defined by that character set to represent the
423   equivalent of CR and LF for line breaks. This flexibility regarding
424   line breaks applies only to text media in the entity-body; a bare CR
425   or LF &MUST-NOT; be substituted for CRLF within any of the HTTP control
426   structures (such as header fields and multipart boundaries).
427</t>
428<t>
429   If an entity-body is encoded with a content-coding, the underlying
430   data &MUST; be in a form defined above prior to being encoded.
431</t>
432<t>
433   The "charset" parameter is used with some media types to define the
434   character set (<xref target="character.sets"/>) of the data. When no explicit charset
435   parameter is provided by the sender, media subtypes of the "text"
436   type are defined to have a default charset value of "ISO-8859-1" when
437   received via HTTP. Data in character sets other than "ISO-8859-1" or
438   its subsets &MUST; be labeled with an appropriate charset value. See
439   <xref target="missing.charset"/> for compatibility problems.
440</t>
441</section>
442
443<section title="Multipart Types" anchor="multipart.types">
444<t>
445   MIME provides for a number of "multipart" types -- encapsulations of
446   one or more entities within a single message-body. All multipart
447   types share a common syntax, as defined in section <xref target="RFC2046" x:sec="5.1.1" x:fmt="number"/> of RFC 2046
448   <xref target="RFC2046"/>, and &MUST; include a boundary parameter as part of the media type
449   value. The message body is itself a protocol element and &MUST;
450   therefore use only CRLF to represent line breaks between body-parts.
451   Unlike in RFC 2046, the epilogue of any multipart message &MUST; be
452   empty; HTTP applications &MUST-NOT; transmit the epilogue (even if the
453   original multipart contains an epilogue). These restrictions exist in
454   order to preserve the self-delimiting nature of a multipart message-body,
455   wherein the "end" of the message-body is indicated by the
456   ending multipart boundary.
457</t>
458<t>
459   In general, HTTP treats a multipart message-body no differently than
460   any other media type: strictly as payload. The one exception is the
461   "multipart/byteranges" type (&multipart-byteranges;) when it appears in a 206
462   (Partial Content) response. In all
463   other cases, an HTTP user agent &SHOULD; follow the same or similar
464   behavior as a MIME user agent would upon receipt of a multipart type.
465   The MIME header fields within each body-part of a multipart message-body
466   do not have any significance to HTTP beyond that defined by
467   their MIME semantics.
468</t>
469<t>
470   In general, an HTTP user agent &SHOULD; follow the same or similar
471   behavior as a MIME user agent would upon receipt of a multipart type.
472   If an application receives an unrecognized multipart subtype, the
473   application &MUST; treat it as being equivalent to "multipart/mixed".
474</t>
475<t><list><t>
476      <x:h>Note:</x:h> The "multipart/form-data" type has been specifically defined
477      for carrying form data suitable for processing via the POST
478      request method, as described in RFC 1867 <xref target="RFC1867"/>.
479</t></list></t>
480</section>
481</section>
482
483<section title="Quality Values" anchor="quality.values">
484<t>
485   HTTP content negotiation (<xref target="content.negotiation"/>) uses short "floating point"
486   numbers to indicate the relative importance ("weight") of various
487   negotiable parameters.  A weight is normalized to a real number in
488   the range 0 through 1, where 0 is the minimum and 1 the maximum
489   value. If a parameter has a quality value of 0, then content with
490   this parameter is `not acceptable' for the client. HTTP/1.1
491   applications &MUST-NOT; generate more than three digits after the
492   decimal point. User configuration of these values &SHOULD; also be
493   limited in this fashion.
494</t>
495<figure><artwork type="abnf2616"><iref primary="true" item="Grammar" subitem="qvalue"/>
496    qvalue         = ( "0" [ "." 0*3DIGIT ] )
497                   | ( "1" [ "." 0*3("0") ] )
498</artwork></figure>
499<t>
500   "Quality values" is a misnomer, since these values merely represent
501   relative degradation in desired quality.
502</t>
503</section>
504
505<section title="Language Tags" anchor="language.tags">
506<t>
507   A language tag identifies a natural language spoken, written, or
508   otherwise conveyed by human beings for communication of information
509   to other human beings. Computer languages are explicitly excluded.
510   HTTP uses language tags within the Accept-Language and Content-Language
511   fields.
512</t>
513<t>
514   The syntax and registry of HTTP language tags is the same as that
515   defined by RFC 1766 <xref target="RFC1766"/>. In summary, a language tag is composed of 1
516   or more parts: A primary language tag and a possibly empty series of
517   subtags:
518</t>
519<figure><artwork type="abnf2616"><iref primary="true" item="Grammar" subitem="language-tag"/><iref primary="true" item="Grammar" subitem="primary-tag"/><iref primary="true" item="Grammar" subitem="subtag"/>
520     language-tag  = primary-tag *( "-" subtag )
521     primary-tag   = 1*8ALPHA
522     subtag        = 1*8ALPHA
523</artwork></figure>
524<t>
525   White space is not allowed within the tag and all tags are case-insensitive.
526   The name space of language tags is administered by the
527   IANA. Example tags include:
528</t>
529<figure><artwork type="example">
530    en, en-US, en-cockney, i-cherokee, x-pig-latin
531</artwork></figure>
532<t>
533   where any two-letter primary-tag is an ISO-639 language abbreviation
534   and any two-letter initial subtag is an ISO-3166 country code. (The
535   last three tags above are not registered tags; all but the last are
536   examples of tags which could be registered in future.)
537</t>
538</section>
539</section>
540
541<section title="Entity" anchor="entity">
542<t>
543   Request and Response messages &MAY; transfer an entity if not otherwise
544   restricted by the request method or response status code. An entity
545   consists of entity-header fields and an entity-body, although some
546   responses will only include the entity-headers.
547</t>
548<t>
549   In this section, both sender and recipient refer to either the client
550   or the server, depending on who sends and who receives the entity.
551</t>
552
553<section title="Entity Header Fields" anchor="entity.header.fields">
554<t>
555   Entity-header fields define metainformation about the entity-body or,
556   if no body is present, about the resource identified by the request.
557   Some of this metainformation is &OPTIONAL;; some might be &REQUIRED; by
558   portions of this specification.
559</t>
560<figure><artwork type="abnf2616"><iref primary="true" item="Grammar" subitem="entity-header"/><iref primary="true" item="Grammar" subitem="extension-header"/>
561    entity-header  = Allow                    ; &header-allow;
562                   | Content-Encoding         ; <xref target="header.content-encoding"/>
563                   | Content-Language         ; <xref target="header.content-language"/>
564                   | Content-Length           ; &header-content-length;
565                   | Content-Location         ; <xref target="header.content-location"/>
566                   | Content-MD5              ; <xref target="header.content-md5"/>
567                   | Content-Range            ; &header-content-range;
568                   | Content-Type             ; <xref target="header.content-type"/>
569                   | Expires                  ; &header-expires;
570                   | Last-Modified            ; &header-last-modified;
571                   | extension-header
572
573    extension-header = message-header
574</artwork></figure>
575<t>
576   The extension-header mechanism allows additional entity-header fields
577   to be defined without changing the protocol, but these fields cannot
578   be assumed to be recognizable by the recipient. Unrecognized header
579   fields &SHOULD; be ignored by the recipient and &MUST; be forwarded by
580   transparent proxies.
581</t>
582</section>
583
584<section title="Entity Body" anchor="entity.body">
585<t>
586   The entity-body (if any) sent with an HTTP request or response is in
587   a format and encoding defined by the entity-header fields.
588</t>
589<figure><artwork type="abnf2616"><iref primary="true" item="Grammar" subitem="entity-body"/>
590    entity-body    = *OCTET
591</artwork></figure>
592<t>
593   An entity-body is only present in a message when a message-body is
594   present, as described in &message-body;. The entity-body is obtained
595   from the message-body by decoding any Transfer-Encoding that might
596   have been applied to ensure safe and proper transfer of the message.
597</t>
598
599<section title="Type" anchor="type">
600<t>
601   When an entity-body is included with a message, the data type of that
602   body is determined via the header fields Content-Type and Content-Encoding.
603   These define a two-layer, ordered encoding model:
604</t>
605<figure><artwork type="example">
606    entity-body := Content-Encoding( Content-Type( data ) )
607</artwork></figure>
608<t>
609   Content-Type specifies the media type of the underlying data.
610   Content-Encoding may be used to indicate any additional content
611   codings applied to the data, usually for the purpose of data
612   compression, that are a property of the requested resource. There is
613   no default encoding.
614</t>
615<t>
616   Any HTTP/1.1 message containing an entity-body &SHOULD; include a
617   Content-Type header field defining the media type of that body. If
618   and only if the media type is not given by a Content-Type field, the
619   recipient &MAY; attempt to guess the media type via inspection of its
620   content and/or the name extension(s) of the URI used to identify the
621   resource. If the media type remains unknown, the recipient &SHOULD;
622   treat it as type "application/octet-stream".
623</t>
624</section>
625   
626<section title="Entity Length" anchor="entity.length">
627<t>
628   The entity-length of a message is the length of the message-body
629   before any transfer-codings have been applied. &message-length; defines
630   how the transfer-length of a message-body is determined.
631</t>
632</section>
633</section>
634</section>
635
636<section title="Content Negotiation" anchor="content.negotiation">
637<t>
638   Most HTTP responses include an entity which contains information for
639   interpretation by a human user. Naturally, it is desirable to supply
640   the user with the "best available" entity corresponding to the
641   request. Unfortunately for servers and caches, not all users have the
642   same preferences for what is "best," and not all user agents are
643   equally capable of rendering all entity types. For that reason, HTTP
644   has provisions for several mechanisms for "content negotiation" --
645   the process of selecting the best representation for a given response
646   when there are multiple representations available.
647  <list><t>
648      <x:h>Note:</x:h> This is not called "format negotiation" because the
649      alternate representations may be of the same media type, but use
650      different capabilities of that type, be in different languages,
651      etc.
652  </t></list>
653</t>
654<t>
655   Any response containing an entity-body &MAY; be subject to negotiation,
656   including error responses.
657</t>
658<t>
659   There are two kinds of content negotiation which are possible in
660   HTTP: server-driven and agent-driven negotiation. These two kinds of
661   negotiation are orthogonal and thus may be used separately or in
662   combination. One method of combination, referred to as transparent
663   negotiation, occurs when a cache uses the agent-driven negotiation
664   information provided by the origin server in order to provide
665   server-driven negotiation for subsequent requests.
666</t>
667
668<section title="Server-driven Negotiation" anchor="server-driven.negotiation">
669<t>
670   If the selection of the best representation for a response is made by
671   an algorithm located at the server, it is called server-driven
672   negotiation. Selection is based on the available representations of
673   the response (the dimensions over which it can vary; e.g. language,
674   content-coding, etc.) and the contents of particular header fields in
675   the request message or on other information pertaining to the request
676   (such as the network address of the client).
677</t>
678<t>
679   Server-driven negotiation is advantageous when the algorithm for
680   selecting from among the available representations is difficult to
681   describe to the user agent, or when the server desires to send its
682   "best guess" to the client along with the first response (hoping to
683   avoid the round-trip delay of a subsequent request if the "best
684   guess" is good enough for the user). In order to improve the server's
685   guess, the user agent &MAY; include request header fields (Accept,
686   Accept-Language, Accept-Encoding, etc.) which describe its
687   preferences for such a response.
688</t>
689<t>
690   Server-driven negotiation has disadvantages:
691  <list style="numbers">
692    <t>
693         It is impossible for the server to accurately determine what
694         might be "best" for any given user, since that would require
695         complete knowledge of both the capabilities of the user agent
696         and the intended use for the response (e.g., does the user want
697         to view it on screen or print it on paper?).
698    </t>
699    <t>
700         Having the user agent describe its capabilities in every
701         request can be both very inefficient (given that only a small
702         percentage of responses have multiple representations) and a
703         potential violation of the user's privacy.
704    </t>
705    <t>
706         It complicates the implementation of an origin server and the
707         algorithms for generating responses to a request.
708    </t>
709    <t>
710         It may limit a public cache's ability to use the same response
711         for multiple user's requests.
712    </t>
713  </list>
714</t>
715<t>
716   HTTP/1.1 includes the following request-header fields for enabling
717   server-driven negotiation through description of user agent
718   capabilities and user preferences: Accept (<xref target="header.accept"/>), Accept-Charset
719   (<xref target="header.accept-charset"/>), Accept-Encoding (<xref target="header.accept-encoding"/>), Accept-Language
720   (<xref target="header.accept-language"/>), and User-Agent (&header-user-agent;). However, an
721   origin server is not limited to these dimensions and &MAY; vary the
722   response based on any aspect of the request, including information
723   outside the request-header fields or within extension header fields
724   not defined by this specification.
725</t>
726<t>
727   The Vary header field &caching; can be used to express the parameters the
728   server uses to select a representation that is subject to server-driven
729   negotiation.
730</t>
731</section>
732
733<section title="Agent-driven Negotiation" anchor="agent-driven.negotiation">
734<t>
735   With agent-driven negotiation, selection of the best representation
736   for a response is performed by the user agent after receiving an
737   initial response from the origin server. Selection is based on a list
738   of the available representations of the response included within the
739   header fields or entity-body of the initial response, with each
740   representation identified by its own URI. Selection from among the
741   representations may be performed automatically (if the user agent is
742   capable of doing so) or manually by the user selecting from a
743   generated (possibly hypertext) menu.
744</t>
745<t>
746   Agent-driven negotiation is advantageous when the response would vary
747   over commonly-used dimensions (such as type, language, or encoding),
748   when the origin server is unable to determine a user agent's
749   capabilities from examining the request, and generally when public
750   caches are used to distribute server load and reduce network usage.
751</t>
752<t>
753   Agent-driven negotiation suffers from the disadvantage of needing a
754   second request to obtain the best alternate representation. This
755   second request is only efficient when caching is used. In addition,
756   this specification does not define any mechanism for supporting
757   automatic selection, though it also does not prevent any such
758   mechanism from being developed as an extension and used within
759   HTTP/1.1.
760</t>
761<t>
762   HTTP/1.1 defines the 300 (Multiple Choices) and 406 (Not Acceptable)
763   status codes for enabling agent-driven negotiation when the server is
764   unwilling or unable to provide a varying response using server-driven
765   negotiation.
766</t>
767</section>
768
769<section title="Transparent Negotiation" anchor="transparent.negotiation">
770<t>
771   Transparent negotiation is a combination of both server-driven and
772   agent-driven negotiation. When a cache is supplied with a form of the
773   list of available representations of the response (as in agent-driven
774   negotiation) and the dimensions of variance are completely understood
775   by the cache, then the cache becomes capable of performing server-driven
776   negotiation on behalf of the origin server for subsequent
777   requests on that resource.
778</t>
779<t>
780   Transparent negotiation has the advantage of distributing the
781   negotiation work that would otherwise be required of the origin
782   server and also removing the second request delay of agent-driven
783   negotiation when the cache is able to correctly guess the right
784   response.
785</t>
786<t>
787   This specification does not define any mechanism for transparent
788   negotiation, though it also does not prevent any such mechanism from
789   being developed as an extension that could be used within HTTP/1.1.
790</t>
791</section>
792</section>
793<section title="Header Field Definitions" anchor="header.fields">
794<t>
795   This section defines the syntax and semantics of all standard
796   HTTP/1.1 header fields. For entity-header fields, both sender and
797   recipient refer to either the client or the server, depending on who
798   sends and who receives the entity.
799</t>
800<section title="Accept" anchor="header.accept">
801  <iref primary="true" item="Accept header" x:for-anchor=""/>
802  <iref primary="true" item="Headers" subitem="Accept" x:for-anchor=""/>
803<t>
804   The Accept request-header field can be used to specify certain media
805   types which are acceptable for the response. Accept headers can be
806   used to indicate that the request is specifically limited to a small
807   set of desired types, as in the case of a request for an in-line
808   image.
809</t>
810<figure><artwork type="abnf2616"><iref primary="true" item="Grammar" subitem="Accept"/><iref primary="true" item="Grammar" subitem="media-range"/><iref primary="true" item="Grammar" subitem="accept-params"/><iref primary="true" item="Grammar" subitem="accept-extension"/>
811    Accept         = "Accept" ":"
812                     #( media-range [ accept-params ] )
813
814    media-range    = ( "*/*"
815                     | ( type "/" "*" )
816                     | ( type "/" subtype )
817                     ) *( ";" parameter )
818    accept-params  = ";" "q" "=" qvalue *( accept-extension )
819    accept-extension = ";" token [ "=" ( token | quoted-string ) ]
820</artwork></figure>
821<t>
822   The asterisk "*" character is used to group media types into ranges,
823   with "*/*" indicating all media types and "type/*" indicating all
824   subtypes of that type. The media-range &MAY; include media type
825   parameters that are applicable to that range.
826</t>
827<t>
828   Each media-range &MAY; be followed by one or more accept-params,
829   beginning with the "q" parameter for indicating a relative quality
830   factor. The first "q" parameter (if any) separates the media-range
831   parameter(s) from the accept-params. Quality factors allow the user
832   or user agent to indicate the relative degree of preference for that
833   media-range, using the qvalue scale from 0 to 1 (<xref target="quality.values"/>). The
834   default value is q=1.
835  <list><t>
836      <x:h>Note:</x:h> Use of the "q" parameter name to separate media type
837      parameters from Accept extension parameters is due to historical
838      practice. Although this prevents any media type parameter named
839      "q" from being used with a media range, such an event is believed
840      to be unlikely given the lack of any "q" parameters in the IANA
841      media type registry and the rare usage of any media type
842      parameters in Accept. Future media types are discouraged from
843      registering any parameter named "q".
844  </t></list>
845</t>
846<t>
847   The example
848</t>
849<figure><artwork type="example">
850    Accept: audio/*; q=0.2, audio/basic
851</artwork></figure>
852<t>
853   &SHOULD; be interpreted as "I prefer audio/basic, but send me any audio
854   type if it is the best available after an 80% mark-down in quality."
855</t>
856<t>
857   If no Accept header field is present, then it is assumed that the
858   client accepts all media types. If an Accept header field is present,
859   and if the server cannot send a response which is acceptable
860   according to the combined Accept field value, then the server &SHOULD;
861   send a 406 (not acceptable) response.
862</t>
863<t>
864   A more elaborate example is
865</t>
866<figure><artwork type="example">
867    Accept: text/plain; q=0.5, text/html,
868            text/x-dvi; q=0.8, text/x-c
869</artwork></figure>
870<t>
871   Verbally, this would be interpreted as "text/html and text/x-c are
872   the preferred media types, but if they do not exist, then send the
873   text/x-dvi entity, and if that does not exist, send the text/plain
874   entity."
875</t>
876<t>
877   Media ranges can be overridden by more specific media ranges or
878   specific media types. If more than one media range applies to a given
879   type, the most specific reference has precedence. For example,
880</t>
881<figure><artwork type="example">
882    Accept: text/*, text/html, text/html;level=1, */*
883</artwork></figure>
884<t>
885   have the following precedence:
886</t>
887<figure><artwork type="example">
888    1) text/html;level=1
889    2) text/html
890    3) text/*
891    4) */*
892</artwork></figure>
893<t>
894   The media type quality factor associated with a given type is
895   determined by finding the media range with the highest precedence
896   which matches that type. For example,
897</t>
898<figure><artwork type="example">
899    Accept: text/*;q=0.3, text/html;q=0.7, text/html;level=1,
900            text/html;level=2;q=0.4, */*;q=0.5
901</artwork></figure>
902<t>
903   would cause the following values to be associated:
904</t>
905<figure><artwork type="example">
906    text/html;level=1         = 1
907    text/html                 = 0.7
908    text/plain                = 0.3
909    image/jpeg                = 0.5
910    text/html;level=2         = 0.4
911    text/html;level=3         = 0.7
912</artwork></figure>
913<t>
914      <x:h>Note:</x:h> A user agent might be provided with a default set of quality
915      values for certain media ranges. However, unless the user agent is
916      a closed system which cannot interact with other rendering agents,
917      this default set ought to be configurable by the user.
918</t>
919</section>
920
921<section title="Accept-Charset" anchor="header.accept-charset">
922  <iref primary="true" item="Accept-Charset header" x:for-anchor=""/>
923  <iref primary="true" item="Headers" subitem="Accept-Charset" x:for-anchor=""/>
924<t>
925   The Accept-Charset request-header field can be used to indicate what
926   character sets are acceptable for the response. This field allows
927   clients capable of understanding more comprehensive or special-purpose
928   character sets to signal that capability to a server which is
929   capable of representing documents in those character sets.
930</t>
931<figure><artwork type="abnf2616"><iref primary="true" item="Grammar" subitem="Accept-Charset"/>
932   Accept-Charset = "Accept-Charset" ":"
933           1#( ( charset | "*" )[ ";" "q" "=" qvalue ] )
934</artwork></figure>
935<t>
936   Character set values are described in <xref target="character.sets"/>. Each charset &MAY;
937   be given an associated quality value which represents the user's
938   preference for that charset. The default value is q=1. An example is
939</t>
940<figure><artwork type="example">
941   Accept-Charset: iso-8859-5, unicode-1-1;q=0.8
942</artwork></figure>
943<t>
944   The special value "*", if present in the Accept-Charset field,
945   matches every character set (including ISO-8859-1) which is not
946   mentioned elsewhere in the Accept-Charset field. If no "*" is present
947   in an Accept-Charset field, then all character sets not explicitly
948   mentioned get a quality value of 0, except for ISO-8859-1, which gets
949   a quality value of 1 if not explicitly mentioned.
950</t>
951<t>
952   If no Accept-Charset header is present, the default is that any
953   character set is acceptable. If an Accept-Charset header is present,
954   and if the server cannot send a response which is acceptable
955   according to the Accept-Charset header, then the server &SHOULD; send
956   an error response with the 406 (not acceptable) status code, though
957   the sending of an unacceptable response is also allowed.
958</t>
959</section>
960
961<section title="Accept-Encoding" anchor="header.accept-encoding">
962  <iref primary="true" item="Accept-Encoding header" x:for-anchor=""/>
963  <iref primary="true" item="Headers" subitem="Accept-Encoding" x:for-anchor=""/>
964<t>
965   The Accept-Encoding request-header field is similar to Accept, but
966   restricts the content-codings (<xref target="content.codings"/>) that are acceptable in
967   the response.
968</t>
969<figure><artwork type="abnf2616"><iref primary="true" item="Grammar" subitem="Accept-Encoding"/><iref primary="true" item="Grammar" subitem="codings"/>
970    Accept-Encoding  = "Accept-Encoding" ":"
971                       1#( codings [ ";" "q" "=" qvalue ] )
972    codings          = ( content-coding | "*" )
973</artwork></figure>
974<t>
975   Examples of its use are:
976</t>
977<figure><artwork type="example">
978    Accept-Encoding: compress, gzip
979    Accept-Encoding:
980    Accept-Encoding: *
981    Accept-Encoding: compress;q=0.5, gzip;q=1.0
982    Accept-Encoding: gzip;q=1.0, identity; q=0.5, *;q=0
983</artwork></figure>
984<t>
985   A server tests whether a content-coding is acceptable, according to
986   an Accept-Encoding field, using these rules:
987  <list style="numbers">
988      <t>If the content-coding is one of the content-codings listed in
989         the Accept-Encoding field, then it is acceptable, unless it is
990         accompanied by a qvalue of 0. (As defined in <xref target="quality.values"/>, a
991         qvalue of 0 means "not acceptable.")</t>
992
993      <t>The special "*" symbol in an Accept-Encoding field matches any
994         available content-coding not explicitly listed in the header
995         field.</t>
996
997      <t>If multiple content-codings are acceptable, then the acceptable
998         content-coding with the highest non-zero qvalue is preferred.</t>
999
1000      <t>The "identity" content-coding is always acceptable, unless
1001         specifically refused because the Accept-Encoding field includes
1002         "identity;q=0", or because the field includes "*;q=0" and does
1003         not explicitly include the "identity" content-coding. If the
1004         Accept-Encoding field-value is empty, then only the "identity"
1005         encoding is acceptable.</t>
1006  </list>
1007</t>
1008<t>
1009   If an Accept-Encoding field is present in a request, and if the
1010   server cannot send a response which is acceptable according to the
1011   Accept-Encoding header, then the server &SHOULD; send an error response
1012   with the 406 (Not Acceptable) status code.
1013</t>
1014<t>
1015   If no Accept-Encoding field is present in a request, the server &MAY;
1016   assume that the client will accept any content coding. In this case,
1017   if "identity" is one of the available content-codings, then the
1018   server &SHOULD; use the "identity" content-coding, unless it has
1019   additional information that a different content-coding is meaningful
1020   to the client.
1021  <list><t>
1022      <x:h>Note:</x:h> If the request does not include an Accept-Encoding field,
1023      and if the "identity" content-coding is unavailable, then
1024      content-codings commonly understood by HTTP/1.0 clients (i.e.,
1025      "gzip" and "compress") are preferred; some older clients
1026      improperly display messages sent with other content-codings.  The
1027      server might also make this decision based on information about
1028      the particular user-agent or client.
1029    </t><t>
1030      <x:h>Note:</x:h> Most HTTP/1.0 applications do not recognize or obey qvalues
1031      associated with content-codings. This means that qvalues will not
1032      work and are not permitted with x-gzip or x-compress.
1033    </t></list>
1034</t>
1035</section>
1036
1037<section title="Accept-Language" anchor="header.accept-language">
1038  <iref primary="true" item="Accept-Language header" x:for-anchor=""/>
1039  <iref primary="true" item="Headers" subitem="Accept-Language" x:for-anchor=""/>
1040<t>
1041   The Accept-Language request-header field is similar to Accept, but
1042   restricts the set of natural languages that are preferred as a
1043   response to the request. Language tags are defined in <xref target="language.tags"/>.
1044</t>
1045<figure><artwork type="abnf2616"><iref primary="true" item="Grammar" subitem="Accept-Language"/><iref primary="true" item="Grammar" subitem="language-range"/>
1046    Accept-Language = "Accept-Language" ":"
1047                      1#( language-range [ ";" "q" "=" qvalue ] )
1048    language-range  = ( ( 1*8ALPHA *( "-" 1*8ALPHA ) ) | "*" )
1049</artwork></figure>
1050<t>
1051   Each language-range &MAY; be given an associated quality value which
1052   represents an estimate of the user's preference for the languages
1053   specified by that range. The quality value defaults to "q=1". For
1054   example,
1055</t>
1056<figure><artwork type="example">
1057    Accept-Language: da, en-gb;q=0.8, en;q=0.7
1058</artwork></figure>
1059<t>
1060   would mean: "I prefer Danish, but will accept British English and
1061   other types of English." A language-range matches a language-tag if
1062   it exactly equals the tag, or if it exactly equals a prefix of the
1063   tag such that the first tag character following the prefix is "-".
1064   The special range "*", if present in the Accept-Language field,
1065   matches every tag not matched by any other range present in the
1066   Accept-Language field.
1067  <list><t>
1068      <x:h>Note:</x:h> This use of a prefix matching rule does not imply that
1069      language tags are assigned to languages in such a way that it is
1070      always true that if a user understands a language with a certain
1071      tag, then this user will also understand all languages with tags
1072      for which this tag is a prefix. The prefix rule simply allows the
1073      use of prefix tags if this is the case.
1074  </t></list>
1075</t>
1076<t>
1077   The language quality factor assigned to a language-tag by the
1078   Accept-Language field is the quality value of the longest language-range
1079   in the field that matches the language-tag. If no language-range
1080   in the field matches the tag, the language quality factor
1081   assigned is 0. If no Accept-Language header is present in the
1082   request, the server
1083   &SHOULD; assume that all languages are equally acceptable. If an
1084   Accept-Language header is present, then all languages which are
1085   assigned a quality factor greater than 0 are acceptable.
1086</t>
1087<t>
1088   It might be contrary to the privacy expectations of the user to send
1089   an Accept-Language header with the complete linguistic preferences of
1090   the user in every request. For a discussion of this issue, see
1091   <xref target="privacy.issues.connected.to.accept.headers"/>.
1092</t>
1093<t>
1094   As intelligibility is highly dependent on the individual user, it is
1095   recommended that client applications make the choice of linguistic
1096   preference available to the user. If the choice is not made
1097   available, then the Accept-Language header field &MUST-NOT; be given in
1098   the request.
1099  <list><t>
1100      <x:h>Note:</x:h> When making the choice of linguistic preference available to
1101      the user, we remind implementors of  the fact that users are not
1102      familiar with the details of language matching as described above,
1103      and should provide appropriate guidance. As an example, users
1104      might assume that on selecting "en-gb", they will be served any
1105      kind of English document if British English is not available. A
1106      user agent might suggest in such a case to add "en" to get the
1107      best matching behavior.
1108  </t></list>
1109</t>
1110</section>
1111
1112<section title="Content-Encoding" anchor="header.content-encoding">
1113  <iref primary="true" item="Content-Encoding header" x:for-anchor=""/>
1114  <iref primary="true" item="Headers" subitem="Content-Encoding" x:for-anchor=""/>
1115<t>
1116   The Content-Encoding entity-header field is used as a modifier to the
1117   media-type. When present, its value indicates what additional content
1118   codings have been applied to the entity-body, and thus what decoding
1119   mechanisms must be applied in order to obtain the media-type
1120   referenced by the Content-Type header field. Content-Encoding is
1121   primarily used to allow a document to be compressed without losing
1122   the identity of its underlying media type.
1123</t>
1124<figure><artwork type="abnf2616"><iref primary="true" item="Grammar" subitem="Content-Encoding"/>
1125    Content-Encoding  = "Content-Encoding" ":" 1#content-coding
1126</artwork></figure>
1127<t>
1128   Content codings are defined in <xref target="content.codings"/>. An example of its use is
1129</t>
1130<figure><artwork type="example">
1131    Content-Encoding: gzip
1132</artwork></figure>
1133<t>
1134   The content-coding is a characteristic of the entity identified by
1135   the Request-URI. Typically, the entity-body is stored with this
1136   encoding and is only decoded before rendering or analogous usage.
1137   However, a non-transparent proxy &MAY; modify the content-coding if the
1138   new coding is known to be acceptable to the recipient, unless the
1139   "no-transform" cache-control directive is present in the message.
1140</t>
1141<t>
1142   If the content-coding of an entity is not "identity", then the
1143   response &MUST; include a Content-Encoding entity-header (<xref target="header.content-encoding"/>)
1144   that lists the non-identity content-coding(s) used.
1145</t>
1146<t>
1147   If the content-coding of an entity in a request message is not
1148   acceptable to the origin server, the server &SHOULD; respond with a
1149   status code of 415 (Unsupported Media Type).
1150</t>
1151<t>
1152   If multiple encodings have been applied to an entity, the content
1153   codings &MUST; be listed in the order in which they were applied.
1154   Additional information about the encoding parameters &MAY; be provided
1155   by other entity-header fields not defined by this specification.
1156</t>
1157</section>
1158
1159<section title="Content-Language" anchor="header.content-language">
1160  <iref primary="true" item="Content-Language header" x:for-anchor=""/>
1161  <iref primary="true" item="Headers" subitem="Content-Language" x:for-anchor=""/>
1162<t>
1163   The Content-Language entity-header field describes the natural
1164   language(s) of the intended audience for the enclosed entity. Note
1165   that this might not be equivalent to all the languages used within
1166   the entity-body.
1167</t>
1168<figure><artwork type="abnf2616"><iref primary="true" item="Grammar" subitem="Content-Language"/>
1169    Content-Language  = "Content-Language" ":" 1#language-tag
1170</artwork></figure>
1171<t>
1172   Language tags are defined in <xref target="language.tags"/>. The primary purpose of
1173   Content-Language is to allow a user to identify and differentiate
1174   entities according to the user's own preferred language. Thus, if the
1175   body content is intended only for a Danish-literate audience, the
1176   appropriate field is
1177</t>
1178<figure><artwork type="example">
1179    Content-Language: da
1180</artwork></figure>
1181<t>
1182   If no Content-Language is specified, the default is that the content
1183   is intended for all language audiences. This might mean that the
1184   sender does not consider it to be specific to any natural language,
1185   or that the sender does not know for which language it is intended.
1186</t>
1187<t>
1188   Multiple languages &MAY; be listed for content that is intended for
1189   multiple audiences. For example, a rendition of the "Treaty of
1190   Waitangi," presented simultaneously in the original Maori and English
1191   versions, would call for
1192</t>
1193<figure><artwork type="example">
1194    Content-Language: mi, en
1195</artwork></figure>
1196<t>
1197   However, just because multiple languages are present within an entity
1198   does not mean that it is intended for multiple linguistic audiences.
1199   An example would be a beginner's language primer, such as "A First
1200   Lesson in Latin," which is clearly intended to be used by an
1201   English-literate audience. In this case, the Content-Language would
1202   properly only include "en".
1203</t>
1204<t>
1205   Content-Language &MAY; be applied to any media type -- it is not
1206   limited to textual documents.
1207</t>
1208</section>
1209
1210<section title="Content-Location" anchor="header.content-location">
1211  <iref primary="true" item="Content-Location header" x:for-anchor=""/>
1212  <iref primary="true" item="Headers" subitem="Content-Location" x:for-anchor=""/>
1213<t>
1214   The Content-Location entity-header field &MAY; be used to supply the
1215   resource location for the entity enclosed in the message when that
1216   entity is accessible from a location separate from the requested
1217   resource's URI. A server &SHOULD; provide a Content-Location for the
1218   variant corresponding to the response entity; especially in the case
1219   where a resource has multiple entities associated with it, and those
1220   entities actually have separate locations by which they might be
1221   individually accessed, the server &SHOULD; provide a Content-Location
1222   for the particular variant which is returned.
1223</t>
1224<figure><artwork type="abnf2616"><iref primary="true" item="Grammar" subitem="Content-Location"/>
1225    Content-Location = "Content-Location" ":"
1226                      ( absoluteURI | relativeURI )
1227</artwork></figure>
1228<t>
1229   The value of Content-Location also defines the base URI for the
1230   entity.
1231</t>
1232<t>
1233   The Content-Location value is not a replacement for the original
1234   requested URI; it is only a statement of the location of the resource
1235   corresponding to this particular entity at the time of the request.
1236   Future requests &MAY; specify the Content-Location URI as the request-URI
1237   if the desire is to identify the source of that particular
1238   entity.
1239</t>
1240<t>
1241   A cache cannot assume that an entity with a Content-Location
1242   different from the URI used to retrieve it can be used to respond to
1243   later requests on that Content-Location URI. However, the Content-Location
1244   can be used to differentiate between multiple entities
1245   retrieved from a single requested resource, as described in &caching;.
1246</t>
1247<t>
1248   If the Content-Location is a relative URI, the relative URI is
1249   interpreted relative to the Request-URI.
1250</t>
1251<t>
1252   The meaning of the Content-Location header in PUT or POST requests is
1253   undefined; servers are free to ignore it in those cases.
1254</t>
1255</section>
1256
1257<section title="Content-MD5" anchor="header.content-md5">
1258  <iref primary="true" item="Content-MD5 header" x:for-anchor=""/>
1259  <iref primary="true" item="Headers" subitem="Content-MD5" x:for-anchor=""/>
1260<t>
1261   The Content-MD5 entity-header field, as defined in RFC 1864 <xref target="RFC1864"/>, is
1262   an MD5 digest of the entity-body for the purpose of providing an
1263   end-to-end message integrity check (MIC) of the entity-body. (Note: a
1264   MIC is good for detecting accidental modification of the entity-body
1265   in transit, but is not proof against malicious attacks.)
1266</t>
1267<figure><artwork type="abnf2616"><iref primary="true" item="Grammar" subitem="Content-MD5"/><iref primary="true" item="Grammar" subitem="md5-digest"/>
1268     Content-MD5   = "Content-MD5" ":" md5-digest
1269     md5-digest   = &lt;base64 of 128 bit MD5 digest as per RFC 1864&gt;
1270</artwork></figure>
1271<t>
1272   The Content-MD5 header field &MAY; be generated by an origin server or
1273   client to function as an integrity check of the entity-body. Only
1274   origin servers or clients &MAY; generate the Content-MD5 header field;
1275   proxies and gateways &MUST-NOT; generate it, as this would defeat its
1276   value as an end-to-end integrity check. Any recipient of the entity-body,
1277   including gateways and proxies, &MAY; check that the digest value
1278   in this header field matches that of the entity-body as received.
1279</t>
1280<t>
1281   The MD5 digest is computed based on the content of the entity-body,
1282   including any content-coding that has been applied, but not including
1283   any transfer-encoding applied to the message-body. If the message is
1284   received with a transfer-encoding, that encoding &MUST; be removed
1285   prior to checking the Content-MD5 value against the received entity.
1286</t>
1287<t>
1288   This has the result that the digest is computed on the octets of the
1289   entity-body exactly as, and in the order that, they would be sent if
1290   no transfer-encoding were being applied.
1291</t>
1292<t>
1293   HTTP extends RFC 1864 to permit the digest to be computed for MIME
1294   composite media-types (e.g., multipart/* and message/rfc822), but
1295   this does not change how the digest is computed as defined in the
1296   preceding paragraph.
1297</t>
1298<t>
1299   There are several consequences of this. The entity-body for composite
1300   types &MAY; contain many body-parts, each with its own MIME and HTTP
1301   headers (including Content-MD5, Content-Transfer-Encoding, and
1302   Content-Encoding headers). If a body-part has a Content-Transfer-Encoding
1303   or Content-Encoding header, it is assumed that the content
1304   of the body-part has had the encoding applied, and the body-part is
1305   included in the Content-MD5 digest as is -- i.e., after the
1306   application. The Transfer-Encoding header field is not allowed within
1307   body-parts.
1308</t>
1309<t>
1310   Conversion of all line breaks to CRLF &MUST-NOT; be done before
1311   computing or checking the digest: the line break convention used in
1312   the text actually transmitted &MUST; be left unaltered when computing
1313   the digest.
1314  <list><t>
1315      <x:h>Note:</x:h> while the definition of Content-MD5 is exactly the same for
1316      HTTP as in RFC 1864 for MIME entity-bodies, there are several ways
1317      in which the application of Content-MD5 to HTTP entity-bodies
1318      differs from its application to MIME entity-bodies. One is that
1319      HTTP, unlike MIME, does not use Content-Transfer-Encoding, and
1320      does use Transfer-Encoding and Content-Encoding. Another is that
1321      HTTP more frequently uses binary content types than MIME, so it is
1322      worth noting that, in such cases, the byte order used to compute
1323      the digest is the transmission byte order defined for the type.
1324      Lastly, HTTP allows transmission of text types with any of several
1325      line break conventions and not just the canonical form using CRLF.
1326  </t></list>
1327</t>
1328</section>
1329
1330<section title="Content-Type" anchor="header.content-type">
1331  <iref primary="true" item="Content-Type header" x:for-anchor=""/>
1332  <iref primary="true" item="Headers" subitem="Content-Type" x:for-anchor=""/>
1333<t>
1334   The Content-Type entity-header field indicates the media type of the
1335   entity-body sent to the recipient or, in the case of the HEAD method,
1336   the media type that would have been sent had the request been a GET.
1337</t>
1338<figure><artwork type="abnf2616"><iref primary="true" item="Grammar" subitem="Content-Type"/>
1339    Content-Type   = "Content-Type" ":" media-type
1340</artwork></figure>
1341<t>
1342   Media types are defined in <xref target="media.types"/>. An example of the field is
1343</t>
1344<figure><artwork type="example">
1345    Content-Type: text/html; charset=ISO-8859-4
1346</artwork></figure>
1347<t>
1348   Further discussion of methods for identifying the media type of an
1349   entity is provided in <xref target="type"/>.
1350</t>
1351</section>
1352
1353</section>
1354
1355<section title="IANA Considerations" anchor="IANA.considerations">
1356<t>
1357   TBD.
1358</t>
1359</section>
1360
1361<section title="Security Considerations" anchor="security.considerations">
1362<t>
1363   This section is meant to inform application developers, information
1364   providers, and users of the security limitations in HTTP/1.1 as
1365   described by this document. The discussion does not include
1366   definitive solutions to the problems revealed, though it does make
1367   some suggestions for reducing security risks.
1368</t>
1369
1370<section title="Privacy Issues Connected to Accept Headers" anchor="privacy.issues.connected.to.accept.headers">
1371<t>
1372   Accept request-headers can reveal information about the user to all
1373   servers which are accessed. The Accept-Language header in particular
1374   can reveal information the user would consider to be of a private
1375   nature, because the understanding of particular languages is often
1376   strongly correlated to the membership of a particular ethnic group.
1377   User agents which offer the option to configure the contents of an
1378   Accept-Language header to be sent in every request are strongly
1379   encouraged to let the configuration process include a message which
1380   makes the user aware of the loss of privacy involved.
1381</t>
1382<t>
1383   An approach that limits the loss of privacy would be for a user agent
1384   to omit the sending of Accept-Language headers by default, and to ask
1385   the user whether or not to start sending Accept-Language headers to a
1386   server if it detects, by looking for any Vary response-header fields
1387   generated by the server, that such sending could improve the quality
1388   of service.
1389</t>
1390<t>
1391   Elaborate user-customized accept header fields sent in every request,
1392   in particular if these include quality values, can be used by servers
1393   as relatively reliable and long-lived user identifiers. Such user
1394   identifiers would allow content providers to do click-trail tracking,
1395   and would allow collaborating content providers to match cross-server
1396   click-trails or form submissions of individual users. Note that for
1397   many users not behind a proxy, the network address of the host
1398   running the user agent will also serve as a long-lived user
1399   identifier. In environments where proxies are used to enhance
1400   privacy, user agents ought to be conservative in offering accept
1401   header configuration options to end users. As an extreme privacy
1402   measure, proxies could filter the accept headers in relayed requests.
1403   General purpose user agents which provide a high degree of header
1404   configurability &SHOULD; warn users about the loss of privacy which can
1405   be involved.
1406</t>
1407</section>
1408
1409<section title="Content-Disposition Issues" anchor="content-disposition.issues">
1410<t>
1411   RFC 1806 <xref target="RFC1806"/>, from which the often implemented Content-Disposition
1412   (see <xref target="content-disposition"/>) header in HTTP is derived, has a number of very
1413   serious security considerations. Content-Disposition is not part of
1414   the HTTP standard, but since it is widely implemented, we are
1415   documenting its use and risks for implementors. See RFC 2183 <xref target="RFC2183"/>
1416   (which updates RFC 1806) for details.
1417</t>
1418</section>
1419
1420</section>
1421
1422<section title="Acknowledgments" anchor="ack">
1423<t>
1424   Based on an XML translation of RFC 2616 by Julian Reschke.
1425</t>
1426</section>
1427</middle>
1428<back>
1429<references>
1430
1431<reference anchor="Part1">
1432   <front>
1433      <title abbrev="HTTP/1.1">HTTP/1.1, part 1: URIs, Connections, and Message Parsing</title>
1434      <author initials="R." surname="Fielding" fullname="Roy T. Fielding" role="editor">
1435         <organization abbrev="Day Software">Day Software</organization>
1436         <address><email>fielding@gbiv.com</email></address>
1437      </author>
1438      <author initials="J." surname="Gettys" fullname="Jim Gettys">
1439         <organization>One Laptop per Child</organization>
1440         <address><email>jg@laptop.org</email></address>
1441      </author>
1442      <author initials="J." surname="Mogul" fullname="Jeffrey C. Mogul">
1443         <organization abbrev="HP">Hewlett-Packard Company</organization>
1444         <address><email>JeffMogul@acm.org</email></address>
1445      </author>
1446      <author initials="H." surname="Frystyk" fullname="Henrik Frystyk Nielsen">
1447         <organization abbrev="Microsoft">Microsoft Corporation</organization>
1448         <address><email>henrikn@microsoft.com</email></address>
1449      </author>
1450      <author initials="L." surname="Masinter" fullname="Larry Masinter">
1451         <organization abbrev="Adobe Systems">Adobe Systems, Incorporated</organization>
1452         <address><email>LMM@acm.org</email></address>
1453      </author>
1454      <author initials="P." surname="Leach" fullname="Paul J. Leach">
1455         <organization abbrev="Microsoft">Microsoft Corporation</organization>
1456         <address><email>paulle@microsoft.com</email></address>
1457      </author>
1458      <author initials="T." surname="Berners-Lee" fullname="Tim Berners-Lee">
1459         <organization abbrev="W3C/MIT">World Wide Web Consortium</organization>
1460         <address><email>timbl@w3.org</email></address>
1461      </author>
1462      <date month="&ID-MONTH;" year="&ID-YEAR;"/>
1463   </front>
1464   <seriesInfo name="Internet-Draft" value="draft-ietf-httpbis-p1-messaging-&ID-VERSION;"/>
1465   <x:source href="p1-messaging.xml" basename="p1-messaging"/>
1466</reference>
1467
1468<reference anchor="Part2">
1469   <front>
1470      <title abbrev="HTTP/1.1">HTTP/1.1, part 2: Message Semantics</title>
1471      <author initials="R." surname="Fielding" fullname="Roy T. Fielding" role="editor">
1472         <organization abbrev="Day Software">Day Software</organization>
1473         <address><email>fielding@gbiv.com</email></address>
1474      </author>
1475      <author initials="J." surname="Gettys" fullname="Jim Gettys">
1476         <organization>One Laptop per Child</organization>
1477         <address><email>jg@laptop.org</email></address>
1478      </author>
1479      <author initials="J." surname="Mogul" fullname="Jeffrey C. Mogul">
1480         <organization abbrev="HP">Hewlett-Packard Company</organization>
1481         <address><email>JeffMogul@acm.org</email></address>
1482      </author>
1483      <author initials="H." surname="Frystyk" fullname="Henrik Frystyk Nielsen">
1484         <organization abbrev="Microsoft">Microsoft Corporation</organization>
1485         <address><email>henrikn@microsoft.com</email></address>
1486      </author>
1487      <author initials="L." surname="Masinter" fullname="Larry Masinter">
1488         <organization abbrev="Adobe Systems">Adobe Systems, Incorporated</organization>
1489         <address><email>LMM@acm.org</email></address>
1490      </author>
1491      <author initials="P." surname="Leach" fullname="Paul J. Leach">
1492         <organization abbrev="Microsoft">Microsoft Corporation</organization>
1493         <address><email>paulle@microsoft.com</email></address>
1494      </author>
1495      <author initials="T." surname="Berners-Lee" fullname="Tim Berners-Lee">
1496         <organization abbrev="W3C/MIT">World Wide Web Consortium</organization>
1497         <address><email>timbl@w3.org</email></address>
1498      </author>
1499      <date month="&ID-MONTH;" year="&ID-YEAR;"/>
1500   </front>
1501   <seriesInfo name="Internet-Draft" value="draft-ietf-httpbis-p2-semantics-&ID-VERSION;"/>
1502   <x:source href="p2-semantics.xml" basename="p2-semantics"/>
1503</reference>
1504
1505<reference anchor="Part4">
1506   <front>
1507      <title abbrev="HTTP/1.1">HTTP/1.1, part 4: Conditional Requests</title>
1508      <author initials="R." surname="Fielding" fullname="Roy T. Fielding" role="editor">
1509         <organization abbrev="Day Software">Day Software</organization>
1510         <address><email>fielding@gbiv.com</email></address>
1511      </author>
1512      <author initials="J." surname="Gettys" fullname="Jim Gettys">
1513         <organization>One Laptop per Child</organization>
1514         <address><email>jg@laptop.org</email></address>
1515      </author>
1516      <author initials="J." surname="Mogul" fullname="Jeffrey C. Mogul">
1517         <organization abbrev="HP">Hewlett-Packard Company</organization>
1518         <address><email>JeffMogul@acm.org</email></address>
1519      </author>
1520      <author initials="H." surname="Frystyk" fullname="Henrik Frystyk Nielsen">
1521         <organization abbrev="Microsoft">Microsoft Corporation</organization>
1522         <address><email>henrikn@microsoft.com</email></address>
1523      </author>
1524      <author initials="L." surname="Masinter" fullname="Larry Masinter">
1525         <organization abbrev="Adobe Systems">Adobe Systems, Incorporated</organization>
1526         <address><email>LMM@acm.org</email></address>
1527      </author>
1528      <author initials="P." surname="Leach" fullname="Paul J. Leach">
1529         <organization abbrev="Microsoft">Microsoft Corporation</organization>
1530         <address><email>paulle@microsoft.com</email></address>
1531      </author>
1532      <author initials="T." surname="Berners-Lee" fullname="Tim Berners-Lee">
1533         <organization abbrev="W3C/MIT">World Wide Web Consortium</organization>
1534         <address><email>timbl@w3.org</email></address>
1535      </author>
1536      <date month="&ID-MONTH;" year="&ID-YEAR;"/>
1537   </front>
1538   <seriesInfo name="Internet-Draft" value="draft-ietf-httpbis-p4-conditional-&ID-VERSION;"/>
1539   <x:source href="p4-conditional.xml" basename="p4-conditional"/>
1540</reference>
1541
1542<reference anchor="Part5">
1543   <front>
1544      <title abbrev="HTTP/1.1">HTTP/1.1, part 5: Range Requests and Partial Responses</title>
1545      <author initials="R." surname="Fielding" fullname="Roy T. Fielding" role="editor">
1546         <organization abbrev="Day Software">Day Software</organization>
1547         <address><email>fielding@gbiv.com</email></address>
1548      </author>
1549      <author initials="J." surname="Gettys" fullname="Jim Gettys">
1550         <organization>One Laptop per Child</organization>
1551         <address><email>jg@laptop.org</email></address>
1552      </author>
1553      <author initials="J." surname="Mogul" fullname="Jeffrey C. Mogul">
1554         <organization abbrev="HP">Hewlett-Packard Company</organization>
1555         <address><email>JeffMogul@acm.org</email></address>
1556      </author>
1557      <author initials="H." surname="Frystyk" fullname="Henrik Frystyk Nielsen">
1558         <organization abbrev="Microsoft">Microsoft Corporation</organization>
1559         <address><email>henrikn@microsoft.com</email></address>
1560      </author>
1561      <author initials="L." surname="Masinter" fullname="Larry Masinter">
1562         <organization abbrev="Adobe Systems">Adobe Systems, Incorporated</organization>
1563         <address><email>LMM@acm.org</email></address>
1564      </author>
1565      <author initials="P." surname="Leach" fullname="Paul J. Leach">
1566         <organization abbrev="Microsoft">Microsoft Corporation</organization>
1567         <address><email>paulle@microsoft.com</email></address>
1568      </author>
1569      <author initials="T." surname="Berners-Lee" fullname="Tim Berners-Lee">
1570         <organization abbrev="W3C/MIT">World Wide Web Consortium</organization>
1571         <address><email>timbl@w3.org</email></address>
1572      </author>
1573      <date month="&ID-MONTH;" year="&ID-YEAR;"/>
1574   </front>
1575   <seriesInfo name="Internet-Draft" value="draft-ietf-httpbis-p5-range-&ID-VERSION;"/>
1576   <x:source href="p5-range.xml" basename="p5-range"/>
1577</reference>
1578
1579<reference anchor="Part6">
1580   <front>
1581      <title abbrev="HTTP/1.1">HTTP/1.1, part 6: Caching</title>
1582      <author initials="R." surname="Fielding" fullname="Roy T. Fielding" role="editor">
1583         <organization abbrev="Day Software">Day Software</organization>
1584         <address><email>fielding@gbiv.com</email></address>
1585      </author>
1586      <author initials="J." surname="Gettys" fullname="Jim Gettys">
1587         <organization>One Laptop per Child</organization>
1588         <address><email>jg@laptop.org</email></address>
1589      </author>
1590      <author initials="J." surname="Mogul" fullname="Jeffrey C. Mogul">
1591         <organization abbrev="HP">Hewlett-Packard Company</organization>
1592         <address><email>JeffMogul@acm.org</email></address>
1593      </author>
1594      <author initials="H." surname="Frystyk" fullname="Henrik Frystyk Nielsen">
1595         <organization abbrev="Microsoft">Microsoft Corporation</organization>
1596         <address><email>henrikn@microsoft.com</email></address>
1597      </author>
1598      <author initials="L." surname="Masinter" fullname="Larry Masinter">
1599         <organization abbrev="Adobe Systems">Adobe Systems, Incorporated</organization>
1600         <address><email>LMM@acm.org</email></address>
1601      </author>
1602      <author initials="P." surname="Leach" fullname="Paul J. Leach">
1603         <organization abbrev="Microsoft">Microsoft Corporation</organization>
1604         <address><email>paulle@microsoft.com</email></address>
1605      </author>
1606      <author initials="T." surname="Berners-Lee" fullname="Tim Berners-Lee">
1607         <organization abbrev="W3C/MIT">World Wide Web Consortium</organization>
1608         <address><email>timbl@w3.org</email></address>
1609      </author>
1610      <date month="&ID-MONTH;" year="&ID-YEAR;"/>
1611   </front>
1612   <seriesInfo name="Internet-Draft" value="draft-ietf-httpbis-p6-cache-&ID-VERSION;"/>
1613   <x:source href="p6-cache.xml" basename="p6-cache"/>
1614</reference>
1615
1616<reference anchor="RFC2616">
1617   <front>
1618      <title>Hypertext Transfer Protocol -- HTTP/1.1</title>
1619      <author initials="R." surname="Fielding" fullname="R. Fielding">
1620         <organization>University of California, Irvine</organization>
1621         <address><email>fielding@ics.uci.edu</email></address>
1622      </author>
1623      <author initials="J." surname="Gettys" fullname="J. Gettys">
1624         <organization>W3C</organization>
1625         <address><email>jg@w3.org</email></address>
1626      </author>
1627      <author initials="J." surname="Mogul" fullname="J. Mogul">
1628         <organization>Compaq Computer Corporation</organization>
1629         <address><email>mogul@wrl.dec.com</email></address>
1630      </author>
1631      <author initials="H." surname="Frystyk" fullname="H. Frystyk">
1632         <organization>MIT Laboratory for Computer Science</organization>
1633         <address><email>frystyk@w3.org</email></address>
1634      </author>
1635      <author initials="L." surname="Masinter" fullname="L. Masinter">
1636         <organization>Xerox Corporation</organization>
1637         <address><email>masinter@parc.xerox.com</email></address>
1638      </author>
1639      <author initials="P." surname="Leach" fullname="P. Leach">
1640         <organization>Microsoft Corporation</organization>
1641         <address><email>paulle@microsoft.com</email></address>
1642      </author>
1643      <author initials="T." surname="Berners-Lee" fullname="T. Berners-Lee">
1644         <organization>W3C</organization>
1645         <address><email>timbl@w3.org</email></address>
1646      </author>
1647      <date month="June" year="1999"/>
1648   </front>
1649   <seriesInfo name="RFC" value="2616"/>
1650</reference>
1651
1652<reference anchor="RFC1766">
1653<front>
1654<title abbrev="Language Tag">Tags for the Identification of Languages</title>
1655<author initials="H." surname="Alvestrand" fullname="Harald Tveit Alvestrand">
1656<organization>UNINETT</organization>
1657<address>
1658<postal>
1659<street>Pb. 6883 Elgeseter</street>
1660<city>Trondheim</city>
1661<region/>
1662<code>N-7002</code>
1663<country>NO</country></postal>
1664<phone>+47 73 597094</phone>
1665<email>Harald.T.Alvestrand@uninett.no</email></address></author>
1666<date month="March" year="1995"/>
1667</front>
1668<seriesInfo name="RFC" value="1766"/>
1669</reference>
1670
1671<reference anchor="RFC2045">
1672<front>
1673<title abbrev="Internet Message Bodies">Multipurpose Internet Mail Extensions (MIME) Part One: Format of Internet Message Bodies</title>
1674<author initials="N." surname="Freed" fullname="Ned Freed">
1675<organization>Innosoft International, Inc.</organization>
1676<address>
1677<postal>
1678<street>1050 East Garvey Avenue South</street>
1679<city>West Covina</city>
1680<region>CA</region>
1681<code>91790</code>
1682<country>US</country></postal>
1683<phone>+1 818 919 3600</phone>
1684<facsimile>+1 818 919 3614</facsimile>
1685<email>ned@innosoft.com</email></address></author>
1686<author initials="N.S." surname="Borenstein" fullname="Nathaniel S. Borenstein">
1687<organization>First Virtual Holdings</organization>
1688<address>
1689<postal>
1690<street>25 Washington Avenue</street>
1691<city>Morristown</city>
1692<region>NJ</region>
1693<code>07960</code>
1694<country>US</country></postal>
1695<phone>+1 201 540 8967</phone>
1696<facsimile>+1 201 993 3032</facsimile>
1697<email>nsb@nsb.fv.com</email></address></author>
1698<date month="November" year="1996"/>
1699</front>
1700<seriesInfo name="RFC" value="2045"/>
1701</reference>
1702
1703<reference anchor="RFC822">
1704<front>
1705<title abbrev="Standard for ARPA Internet Text Messages">Standard for the format of ARPA Internet text messages</title>
1706<author initials="D.H." surname="Crocker" fullname="David H. Crocker">
1707<organization>University of Delaware, Dept. of Electrical Engineering</organization>
1708<address>
1709<postal>
1710<street/>
1711<city>Newark</city>
1712<region>DE</region>
1713<code>19711</code>
1714<country>US</country></postal>
1715<email>DCrocker@UDel-Relay</email></address></author>
1716<date month="August" day="13" year="1982"/></front>
1717<seriesInfo name="STD" value="11"/>
1718<seriesInfo name="RFC" value="822"/>
1719</reference>
1720
1721<reference anchor="RFC1867">
1722<front>
1723<title>Form-based File Upload in HTML</title>
1724<author initials="L." surname="Masinter" fullname="Larry Masinter">
1725<organization>Xerox Palo Alto Research Center</organization>
1726<address>
1727<postal>
1728<street>3333 Coyote Hill Road</street>
1729<city>Palo Alto</city>
1730<region>CA</region>
1731<code>94304</code>
1732<country>US</country></postal>
1733<phone>+1 415 812 4365</phone>
1734<facsimile>+1 415 812 4333</facsimile>
1735<email>masinter@parc.xerox.com</email></address></author>
1736<author initials="E." surname="Nebel" fullname="Ernesto Nebel">
1737<organization>XSoft, Xerox Corporation</organization>
1738<address>
1739<postal>
1740<street>10875 Rancho Bernardo Road</street>
1741<street>Suite 200</street>
1742<city>San Diego</city>
1743<region>CA</region>
1744<code>92127-2116</code>
1745<country>US</country></postal>
1746<phone>+1 619 676 7817</phone>
1747<facsimile>+1 619 676 7865</facsimile>
1748<email>nebel@xsoft.sd.xerox.com</email></address></author>
1749<date month="November" year="1995"/>
1750</front>
1751<seriesInfo name="RFC" value="1867"/>
1752</reference>
1753
1754<reference anchor="RFC4288">
1755  <front>
1756    <title>Media Type Specifications and Registration Procedures</title>
1757    <author initials="N." surname="Freed" fullname="N. Freed">
1758      <organization>Sun Microsystems</organization>
1759      <address>
1760        <email>ned.freed@mrochek.com</email>
1761      </address>
1762    </author>
1763    <author initials="J." surname="Klensin" fullname="J. Klensin">
1764      <organization/>
1765      <address>
1766        <email>klensin+ietf@jck.com</email>
1767      </address>
1768    </author>
1769    <date year="2005" month="December"/>
1770  </front>
1771  <seriesInfo name="BCP" value="13"/>
1772  <seriesInfo name="RFC" value="4288"/>
1773</reference>
1774
1775<reference anchor="RFC1864">
1776<front>
1777<title abbrev="Content-MD5 Header Field">The Content-MD5 Header Field</title>
1778<author initials="J." surname="Myers" fullname="John G. Myers">
1779<organization>Carnegie Mellon University</organization>
1780<address>
1781<phone/>
1782<email>jgm+@cmu.edu</email></address></author>
1783<author initials="M." surname="Rose" fullname="Marshall T. Rose">
1784<organization>Dover Beach Consulting, Inc.</organization>
1785<address>
1786<phone/>
1787<email>mrose@dbc.mtview.ca.us</email></address></author>
1788<date month="October" year="1995"/>
1789</front>
1790<seriesInfo name="RFC" value="1864"/>
1791</reference>
1792
1793
1794<reference anchor="RFC1952">
1795<front>
1796<title>GZIP file format specification version 4.3</title>
1797<author initials="P." surname="Deutsch" fullname="L. Peter Deutsch">
1798<organization>Aladdin Enterprises</organization>
1799<address>
1800<postal>
1801<street>203 Santa Margarita Ave.</street>
1802<city>Menlo Park</city>
1803<region>CA</region>
1804<code>94025</code>
1805<country>US</country></postal>
1806<phone>+1 415 322 0103</phone>
1807<facsimile>+1 415 322 1734</facsimile>
1808<email>ghost@aladdin.com</email></address></author>
1809<author initials="J-L." surname="Gailly" fullname="Jean-Loup Gailly">
1810<organization/>
1811<address>
1812<postal>
1813<street/>
1814<city/>
1815<region/>
1816<code/>
1817<country/></postal>
1818<phone/>
1819<email>gzip@prep.ai.mit.edu</email></address></author>
1820<author initials="M." surname="Adler" fullname="Mark Adler">
1821<organization/>
1822<address>
1823<postal>
1824<street/>
1825<city/>
1826<region/>
1827<code/>
1828<country/></postal>
1829<phone/>
1830<email>madler@alumni.caltech.edu</email></address></author>
1831<author initials="L.P." surname="Deutsch" fullname="L. Peter Deutsch">
1832<organization/>
1833<address>
1834<postal>
1835<street/>
1836<city/>
1837<region/>
1838<code/>
1839<country/></postal>
1840<phone/>
1841<email>ghost@aladdin.com</email></address></author>
1842<author initials="G." surname="Randers-Pehrson" fullname="Glenn Randers-Pehrson">
1843<organization/>
1844<address>
1845<postal>
1846<street/>
1847<city/>
1848<region/>
1849<code/>
1850<country/></postal>
1851<phone/>
1852<email>randeg@alumni.rpi.edu</email></address></author>
1853<date month="May" year="1996"/>
1854</front>
1855<seriesInfo name="RFC" value="1952"/>
1856</reference>
1857
1858<reference anchor="RFC1951">
1859<front>
1860<title>DEFLATE Compressed Data Format Specification version 1.3</title>
1861<author initials="P." surname="Deutsch" fullname="L. Peter Deutsch">
1862<organization>Aladdin Enterprises</organization>
1863<address>
1864<postal>
1865<street>203 Santa Margarita Ave.</street>
1866<city>Menlo Park</city>
1867<region>CA</region>
1868<code>94025</code>
1869<country>US</country></postal>
1870<phone>+1 415 322 0103</phone>
1871<facsimile>+1 415 322 1734</facsimile>
1872<email>ghost@aladdin.com</email></address></author>
1873<date month="May" year="1996"/>
1874<abstract>
1875<t>This specification defines a lossless compressed data format that compresses data using a combination of the LZ77 algorithm and Huffman coding, with efficiency comparable to the best currently available general-purpose compression methods.  The data can be produced or consumed, even for an arbitrarily long sequentially presented input data stream, using only an a priori bounded amount of intermediate storage.  The format can be implemented readily in a manner not covered by patents.</t></abstract></front>
1876<seriesInfo name="RFC" value="1951"/>
1877</reference>
1878
1879<reference anchor="RFC1950">
1880<front>
1881<title>ZLIB Compressed Data Format Specification version 3.3</title>
1882<author initials="L.P." surname="Deutsch" fullname="L. Peter Deutsch">
1883<organization>Aladdin Enterprises</organization>
1884<address>
1885<postal>
1886<street>203 Santa Margarita Ave.</street>
1887<city>Menlo Park</city>
1888<region>CA</region>
1889<code>94025</code>
1890<country>US</country></postal>
1891<phone>+1 415 322 0103</phone>
1892<facsimile>+1 415 322 1734</facsimile>
1893<email>ghost@aladdin.com</email></address></author>
1894<author initials="J-L." surname="Gailly" fullname="Jean-Loup Gailly">
1895<organization/></author>
1896<date month="May" year="1996"/>
1897<abstract>
1898<t>This specification defines a lossless compressed data format.  The data can be produced or consumed, even for an arbitrarily long sequentially presented input data stream, using only an a priori bounded amount of intermediate storage.  The format presently uses the DEFLATE compression method but can be easily extended to use
1899   other compression methods.  It can be implemented readily in a manner not covered by patents.  This specification also defines the ADLER-32 checksum (an extension and improvement of the Fletcher checksum), used for detection of data corruption, and provides an algorithm for computing it.</t></abstract></front>
1900<seriesInfo name="RFC" value="1950"/>
1901</reference>
1902
1903<reference anchor="RFC2068">
1904<front>
1905<title abbrev="HTTP/1.1">Hypertext Transfer Protocol -- HTTP/1.1</title>
1906<author initials="R." surname="Fielding" fullname="Roy T. Fielding">
1907<organization>University of California, Irvine, Department of Information and Computer Science</organization>
1908<address>
1909<postal>
1910<street/>
1911<city>Irvine</city>
1912<region>CA</region>
1913<code>92717-3425</code>
1914<country>US</country></postal>
1915<facsimile>+1 714 824 4056</facsimile>
1916<email>fielding@ics.uci.edu</email></address></author>
1917<author initials="J." surname="Gettys" fullname="Jim Gettys">
1918<organization>MIT Laboratory for Computer Science</organization>
1919<address>
1920<postal>
1921<street>545 Technology Square</street>
1922<city>Cambridge</city>
1923<region>MA</region>
1924<code>02139</code>
1925<country>US</country></postal>
1926<facsimile>+1 617 258 8682</facsimile>
1927<email>jg@w3.org</email></address></author>
1928<author initials="J." surname="Mogul" fullname="Jeffrey C. Mogul">
1929<organization>Digital Equipment Corporation, Western Research Laboratory</organization>
1930<address>
1931<postal>
1932<street>250 University Avenue</street>
1933<city>Palo Alto</city>
1934<region>CA</region>
1935<code>94301</code>
1936<country>US</country></postal>
1937<email>mogul@wrl.dec.com</email></address></author>
1938<author initials="H." surname="Nielsen" fullname="Henrik Frystyk Nielsen">
1939<organization>MIT Laboratory for Computer Science</organization>
1940<address>
1941<postal>
1942<street>545 Technology Square</street>
1943<city>Cambridge</city>
1944<region>MA</region>
1945<code>02139</code>
1946<country>US</country></postal>
1947<facsimile>+1 617 258 8682</facsimile>
1948<email>frystyk@w3.org</email></address></author>
1949<author initials="T." surname="Berners-Lee" fullname="Tim Berners-Lee">
1950<organization>MIT Laboratory for Computer Science</organization>
1951<address>
1952<postal>
1953<street>545 Technology Square</street>
1954<city>Cambridge</city>
1955<region>MA</region>
1956<code>02139</code>
1957<country>US</country></postal>
1958<facsimile>+1 617 258 8682</facsimile>
1959<email>timbl@w3.org</email></address></author>
1960<date month="January" year="1997"/>
1961<abstract>
1962<t>The Hypertext Transfer Protocol (HTTP) is an application-level protocol for distributed, collaborative, hypermedia information systems. It is a generic, stateless, object-oriented protocol which can be used for many tasks, such as name servers and distributed object management systems, through extension of its request methods. A feature of HTTP is the typing and negotiation of data representation, allowing systems to be built independently of the data being transferred.</t>
1963<t>HTTP has been in use by the World-Wide Web global information initiative since 1990. This specification defines the protocol referred to as "HTTP/1.1".</t></abstract></front>
1964<seriesInfo name="RFC" value="2068"/>
1965</reference>
1966
1967<reference anchor="RFC1806">
1968<front>
1969<title abbrev="Content-Disposition">Communicating Presentation Information in Internet Messages: The Content-Disposition Header</title>
1970<author initials="R." surname="Troost" fullname="Rens Troost">
1971<organization>New Century Systems</organization>
1972<address>
1973<postal>
1974<street>324 East 41st Street #804</street>
1975<city>New York</city>
1976<region>NY</region>
1977<code>10017</code>
1978<country>US</country></postal>
1979<phone>+1 212 557 2050</phone>
1980<facsimile>+1 212 557 2049</facsimile>
1981<email>rens@century.com</email></address></author>
1982<author initials="S." surname="Dorner" fullname="Steve Dorner">
1983<organization>QUALCOMM Incorporated</organization>
1984<address>
1985<postal>
1986<street>6455 Lusk Boulevard</street>
1987<city>San Diego</city>
1988<region>CA</region>
1989<code>92121</code>
1990<country>US</country></postal>
1991<email>sdorner@qualcomm.com</email></address></author>
1992<date month="June" year="1995"/>
1993<abstract>
1994<t>This memo provides a mechanism whereby messages conforming to the("MIME") specification can convey presentational information.  It specifies a new "Content-Disposition" header, optional and valid for anyentity ("message" or "body part"). Two values for this header are described in this memo; one for the ordinary linear presentation of the body part, and another to facilitate the use of mail to transfer files. It is expected that more values will be defined in the future, and procedures are defined for extending this set of values.</t>
1995<t>This document is intended as an extension to. As such, the reader is assumed to be familiar with, and. The information presented herein supplements but does not replace that found in those documents.</t></abstract></front>
1996<seriesInfo name="RFC" value="1806"/>
1997</reference>
1998
1999<reference anchor="RFC2076">
2000<front>
2001<title abbrev="Internet Message Headers">Common Internet Message Headers</title>
2002<author initials="J." surname="Palme" fullname="Jacob Palme">
2003<organization>Stockholm University/KTH</organization>
2004<address>
2005<postal>
2006<street>Electrum 230</street>
2007<street>S-164 40 Kista</street>
2008<country>SE</country></postal>
2009<phone>+46 8 161667</phone>
2010<facsimile>+46 8 7830829</facsimile>
2011<email>jpalme@dsv.su.se</email></address></author>
2012<date month="February" year="1997"/>
2013<abstract>
2014<t>This memo contains a table of commonly occurring headers in headings of e-mail messages. The document compiles information from other RFCs such as RFC 822, RFC 1036, RFC 1123, RFC 1327, RFC 1496, RFC 1521, RFC 1766, RFC 1806, RFC 1864 and RFC 1911. A few commonly occurring headers which are not defined in RFCs are also included. For each header, the memo gives a short description and a reference to the RFC in which the header is defined.</t></abstract></front>
2015<seriesInfo name="RFC" value="2076"/>
2016</reference>
2017
2018<reference anchor="RFC2279">
2019<front>
2020<title abbrev="UTF-8">UTF-8, a transformation format of ISO 10646</title>
2021<author initials="F." surname="Yergeau" fullname="Francois Yergeau">
2022<organization>Alis Technologies</organization>
2023<address>
2024<postal>
2025<street>100, boul. Alexis-Nihon</street>
2026<street>Suite 600</street>
2027<city>Montreal</city>
2028<region>Quebec</region>
2029<code>H4M 2P2</code>
2030<country>CA</country></postal>
2031<phone>+1 514 747 2547</phone>
2032<facsimile>+1 514 747 2561</facsimile>
2033<email>fyergeau@alis.com</email></address></author>
2034<date month="January" year="1998"/>
2035<abstract>
2036<t>ISO/IEC 10646-1 defines a multi-octet character set called the Universal Character Set (UCS) which encompasses most of the world's writing systems. Multi-octet characters, however, are not compatible with many current applications and protocols, and this has led to the development of a few so-called UCS transformation formats (UTF), each with different characteristics.  UTF-8, the object of this memo, has the characteristic of preserving the full US-ASCII range, providing compatibility with file systems, parsers and other software that rely on US-ASCII values but are transparent to other values. This memo updates and replaces RFC 2044, in particular addressing the question of versions of the relevant standards.</t></abstract></front>
2037<seriesInfo name="RFC" value="2279"/>
2038</reference>
2039
2040<reference anchor="RFC2046">
2041<front>
2042<title abbrev="Media Types">Multipurpose Internet Mail Extensions (MIME) Part Two: Media Types</title>
2043<author initials="N." surname="Freed" fullname="Ned Freed">
2044<organization>Innosoft International, Inc.</organization>
2045<address>
2046<postal>
2047<street>1050 East Garvey Avenue South</street>
2048<city>West Covina</city>
2049<region>CA</region>
2050<code>91790</code>
2051<country>US</country></postal>
2052<phone>+1 818 919 3600</phone>
2053<facsimile>+1 818 919 3614</facsimile>
2054<email>ned@innosoft.com</email></address></author>
2055<author initials="N." surname="Borenstein" fullname="Nathaniel S. Borenstein">
2056<organization>First Virtual Holdings</organization>
2057<address>
2058<postal>
2059<street>25 Washington Avenue</street>
2060<city>Morristown</city>
2061<region>NJ</region>
2062<code>07960</code>
2063<country>US</country></postal>
2064<phone>+1 201 540 8967</phone>
2065<facsimile>+1 201 993 3032</facsimile>
2066<email>nsb@nsb.fv.com</email></address></author>
2067<date month="November" year="1996"/>
2068</front>
2069<seriesInfo name="RFC" value="2046"/>
2070</reference>
2071
2072<reference anchor="RFC2277">
2073<front>
2074<title abbrev="Charset Policy">IETF Policy on Character Sets and Languages</title>
2075<author initials="H.T." surname="Alvestrand" fullname="Harald Tveit Alvestrand">
2076<organization>UNINETT</organization>
2077<address>
2078<postal>
2079<street>P.O.Box 6883 Elgeseter</street>
2080<street>N-7002 TRONDHEIM</street>
2081<country>NORWAY</country></postal>
2082<phone>+47 73 59 70 94</phone>
2083<email>Harald.T.Alvestrand@uninett.no</email></address></author>
2084<date month="January" year="1998"/>
2085<area>Applications</area>
2086<keyword>Internet Engineering Task Force</keyword>
2087<keyword>character encoding</keyword></front>
2088<seriesInfo name="BCP" value="18"/>
2089<seriesInfo name="RFC" value="2277"/>
2090</reference>
2091
2092<reference anchor="RFC2110">
2093<front>
2094<title abbrev="MHTML">MIME E-mail Encapsulation of Aggregate Documents, such as HTML (MHTML)</title>
2095<author initials="J." surname="Palme" fullname="Jacob Palme">
2096<organization>Stockholm University and KTH</organization>
2097<address>
2098<postal>
2099<street>Electrum 230</street>
2100<street>S-164 40 Kista</street>
2101<country>Sweden</country></postal>
2102<phone>+46-8-16 16 67</phone>
2103<facsimile>+46-8-783 08 29</facsimile>
2104<email>jpalme@dsv.su.se</email></address></author>
2105<author initials="A." surname="Hopmann" fullname="Alex Hopmann">
2106<organization>Microsoft Corporation</organization>
2107<address>
2108<postal>
2109<street>3590 North First Street</street>
2110<street>Suite 300</street>
2111<street>San Jose</street>
2112<street>CA 95134</street>
2113<street>Working group chairman:</street></postal>
2114<email>alexhop@microsoft.com</email></address></author>
2115<date month="March" year="1997"/>
2116<area>Applications</area>
2117<keyword>encapsulate</keyword>
2118<keyword>hypertext markup language</keyword>
2119<keyword>mail</keyword>
2120<keyword>multipurpose internet mail extensions</keyword>
2121</front>
2122<seriesInfo name="RFC" value="2110"/>
2123</reference>
2124
2125<reference anchor="RFC2049">
2126<front>
2127<title abbrev="MIME Conformance">Multipurpose Internet Mail Extensions (MIME) Part Five: Conformance Criteria and Examples</title>
2128<author initials="N." surname="Freed" fullname="Ned Freed">
2129<organization>Innosoft International, Inc.</organization>
2130<address>
2131<postal>
2132<street>1050 East Garvey Avenue South</street>
2133<street>West Covina</street>
2134<street>CA 91790</street>
2135<country>USA</country></postal>
2136<phone>+1 818 919 3600</phone>
2137<facsimile>+1 818 919 3614</facsimile>
2138<email>ned@innosoft.com</email></address></author>
2139<author initials="N.S." surname="Borenstein" fullname="Nathaniel S. Borenstein">
2140<organization>First Virtual Holdings</organization>
2141<address>
2142<postal>
2143<street>25 Washington Avenue</street>
2144<street>Morristown</street>
2145<street>NJ 07960</street>
2146<country>USA</country></postal>
2147<phone>+1 201 540 8967</phone>
2148<facsimile>+1 201 993 3032</facsimile>
2149<email>nsb@nsb.fv.com</email></address></author>
2150<date month="November" year="1996"/>
2151<area>Applications</area>
2152<keyword>mail</keyword>
2153<keyword>multipurpose internet mail extensions</keyword>
2154</front>
2155<seriesInfo name="RFC" value="2049"/>
2156</reference>
2157
2158<reference anchor="RFC2183">
2159<front>
2160<title abbrev="Content-Disposition">Communicating Presentation Information in Internet Messages: The Content-Disposition Header Field</title>
2161<author initials="R." surname="Troost" fullname="Rens Troost">
2162<organization>New Century Systems</organization>
2163<address>
2164<postal>
2165<street>324 East 41st Street #804</street>
2166<street>New York</street>
2167<street>NY</street>
2168<street>10017</street>
2169<country>USA</country></postal>
2170<phone>+1 (212) 557-2050</phone>
2171<facsimile>+1 (212) 557-2049</facsimile>
2172<email>rens@century.com</email></address></author>
2173<author initials="S." surname="Dorner" fullname="Steve Dorner">
2174<organization>QUALCOMM Incorporated</organization>
2175<address>
2176<postal>
2177<street>6455 Lusk Boulevard</street>
2178<street>San Diego</street>
2179<street>CA 92121</street>
2180<country>USA</country></postal>
2181<email>sdorner@qualcomm.com</email></address></author>
2182<author initials="K." surname="Moore" fullname="Keith Moore">
2183<organization>Department of Computer Science</organization>
2184<address>
2185<postal>
2186<street>University of Tennessee</street>
2187<street>Knoxville</street>
2188<street>107 Ayres Hall</street>
2189<street>Knoxville TN  37996-1301</street>
2190<country>USA</country></postal>
2191<phone>+1 (423) 974-5067</phone>
2192<facsimile>+1 (423) 974-8296</facsimile>
2193<email>moore@cs.utk.edu</email></address></author>
2194<date month="August" year="1997"/>
2195<area>Applications</area>
2196<keyword>MIME</keyword>
2197<keyword>internet message</keyword>
2198<keyword>multipurpose internet mail extensions</keyword>
2199</front>
2200<seriesInfo name="RFC" value="2183"/>
2201</reference>
2202
2203</references>
2204
2205<section title="Differences Between HTTP Entities and RFC 2045 Entities" anchor="differences.between.http.entities.and.rfc.2045.entities">
2206<t>
2207   HTTP/1.1 uses many of the constructs defined for Internet Mail (RFC
2208   822 <xref target="RFC822"/>) and the Multipurpose Internet Mail Extensions (MIME <xref target="RFC2045"/>) to
2209   allow entities to be transmitted in an open variety of
2210   representations and with extensible mechanisms. However, RFC 2045
2211   discusses mail, and HTTP has a few features that are different from
2212   those described in RFC 2045. These differences were carefully chosen
2213   to optimize performance over binary connections, to allow greater
2214   freedom in the use of new media types, to make date comparisons
2215   easier, and to acknowledge the practice of some early HTTP servers
2216   and clients.
2217</t>
2218<t>
2219   This appendix describes specific areas where HTTP differs from RFC
2220   2045. Proxies and gateways to strict MIME environments &SHOULD; be
2221   aware of these differences and provide the appropriate conversions
2222   where necessary. Proxies and gateways from MIME environments to HTTP
2223   also need to be aware of the differences because some conversions
2224   might be required.
2225</t>
2226<section title="MIME-Version" anchor="mime-version">
2227<t>
2228   HTTP is not a MIME-compliant protocol. However, HTTP/1.1 messages &MAY;
2229   include a single MIME-Version general-header field to indicate what
2230   version of the MIME protocol was used to construct the message. Use
2231   of the MIME-Version header field indicates that the message is in
2232   full compliance with the MIME protocol (as defined in RFC 2045<xref target="RFC2045"/>).
2233   Proxies/gateways are responsible for ensuring full compliance (where
2234   possible) when exporting HTTP messages to strict MIME environments.
2235</t>
2236<figure><artwork type="abnf2616"><iref primary="true" item="Grammar" subitem="MIME-Version"/>
2237    MIME-Version   = "MIME-Version" ":" 1*DIGIT "." 1*DIGIT
2238</artwork></figure>
2239<t>
2240   MIME version "1.0" is the default for use in HTTP/1.1. However,
2241   HTTP/1.1 message parsing and semantics are defined by this document
2242   and not the MIME specification.
2243</t>
2244</section>
2245
2246<section title="Conversion to Canonical Form" anchor="conversion.to.canonical.form">
2247<t>
2248   RFC 2045 <xref target="RFC2045"/> requires that an Internet mail entity be converted to
2249   canonical form prior to being transferred, as described in section <xref target="RFC2049" x:fmt="number" x:sec="4"/>
2250   of RFC 2049 <xref target="RFC2049"/>. <xref target="canonicalization.and.text.defaults"/> of this document describes the forms
2251   allowed for subtypes of the "text" media type when transmitted over
2252   HTTP. RFC 2046 requires that content with a type of "text" represent
2253   line breaks as CRLF and forbids the use of CR or LF outside of line
2254   break sequences. HTTP allows CRLF, bare CR, and bare LF to indicate a
2255   line break within text content when a message is transmitted over
2256   HTTP.
2257</t>
2258<t>
2259   Where it is possible, a proxy or gateway from HTTP to a strict MIME
2260   environment &SHOULD; translate all line breaks within the text media
2261   types described in <xref target="canonicalization.and.text.defaults"/> of this document to the RFC 2049
2262   canonical form of CRLF. Note, however, that this might be complicated
2263   by the presence of a Content-Encoding and by the fact that HTTP
2264   allows the use of some character sets which do not use octets 13 and
2265   10 to represent CR and LF, as is the case for some multi-byte
2266   character sets.
2267</t>
2268<t>
2269   Implementors should note that conversion will break any cryptographic
2270   checksums applied to the original content unless the original content
2271   is already in canonical form. Therefore, the canonical form is
2272   recommended for any content that uses such checksums in HTTP.
2273</t>
2274</section>
2275
2276<section title="Introduction of Content-Encoding" anchor="introduction.of.content-encoding">
2277<t>
2278   RFC 2045 does not include any concept equivalent to HTTP/1.1's
2279   Content-Encoding header field. Since this acts as a modifier on the
2280   media type, proxies and gateways from HTTP to MIME-compliant
2281   protocols &MUST; either change the value of the Content-Type header
2282   field or decode the entity-body before forwarding the message. (Some
2283   experimental applications of Content-Type for Internet mail have used
2284   a media-type parameter of ";conversions=&lt;content-coding&gt;" to perform
2285   a function equivalent to Content-Encoding. However, this parameter is
2286   not part of RFC 2045).
2287</t>
2288</section>
2289
2290<section title="No Content-Transfer-Encoding" anchor="no.content-transfer-encoding">
2291<t>
2292   HTTP does not use the Content-Transfer-Encoding field of RFC
2293   2045. Proxies and gateways from MIME-compliant protocols to HTTP &MUST;
2294   remove any Content-Transfer-Encoding
2295   prior to delivering the response message to an HTTP client.
2296</t>
2297<t>
2298   Proxies and gateways from HTTP to MIME-compliant protocols are
2299   responsible for ensuring that the message is in the correct format
2300   and encoding for safe transport on that protocol, where "safe
2301   transport" is defined by the limitations of the protocol being used.
2302   Such a proxy or gateway &SHOULD; label the data with an appropriate
2303   Content-Transfer-Encoding if doing so will improve the likelihood of
2304   safe transport over the destination protocol.
2305</t>
2306</section>
2307
2308<section title="Introduction of Transfer-Encoding" anchor="introduction.of.transfer-encoding">
2309<t>
2310   HTTP/1.1 introduces the Transfer-Encoding header field (&header-transfer-encoding;).
2311   Proxies/gateways &MUST; remove any transfer-coding prior to
2312   forwarding a message via a MIME-compliant protocol.
2313</t>
2314</section>
2315
2316<section title="MHTML and Line Length Limitations" anchor="mhtml.line.length">
2317<t>
2318   HTTP implementations which share code with MHTML <xref target="RFC2110"/> implementations
2319   need to be aware of MIME line length limitations. Since HTTP does not
2320   have this limitation, HTTP does not fold long lines. MHTML messages
2321   being transported by HTTP follow all conventions of MHTML, including
2322   line length limitations and folding, canonicalization, etc., since
2323   HTTP transports all message-bodies as payload (see <xref target="multipart.types"/>) and
2324   does not interpret the content or any MIME header lines that might be
2325   contained therein.
2326</t>
2327</section>
2328</section>
2329
2330<section title="Additional Features" anchor="additional.features">
2331<t>
2332   RFC 1945 and RFC 2068 document protocol elements used by some
2333   existing HTTP implementations, but not consistently and correctly
2334   across most HTTP/1.1 applications. Implementors are advised to be
2335   aware of these features, but cannot rely upon their presence in, or
2336   interoperability with, other HTTP/1.1 applications. Some of these
2337   describe proposed experimental features, and some describe features
2338   that experimental deployment found lacking that are now addressed in
2339   the base HTTP/1.1 specification.
2340</t>
2341<t>
2342   A number of other headers, such as Content-Disposition and Title,
2343   from SMTP and MIME are also often implemented (see RFC 2076 <xref target="RFC2076"/>).
2344</t>
2345
2346<section title="Content-Disposition" anchor="content-disposition">
2347<iref item="Headers" subitem="Content-Disposition" primary="true" x:for-anchor=""/>
2348<iref item="Content-Disposition header" primary="true" x:for-anchor=""/>
2349<t>
2350   The Content-Disposition response-header field has been proposed as a
2351   means for the origin server to suggest a default filename if the user
2352   requests that the content is saved to a file. This usage is derived
2353   from the definition of Content-Disposition in RFC 1806 <xref target="RFC1806"/>.
2354</t>
2355<figure><artwork type="abnf2616"><iref primary="true" item="Grammar" subitem="content-disposition"/><iref primary="true" item="Grammar" subitem="disposition-type"/><iref primary="true" item="Grammar" subitem="disposition-parm"/><iref primary="true" item="Grammar" subitem="filename-parm"/><iref primary="true" item="Grammar" subitem="disp-extension-token"/><iref primary="true" item="Grammar" subitem="disp-extension-parm"/>
2356     content-disposition = "Content-Disposition" ":"
2357                           disposition-type *( ";" disposition-parm )
2358     disposition-type = "attachment" | disp-extension-token
2359     disposition-parm = filename-parm | disp-extension-parm
2360     filename-parm = "filename" "=" quoted-string
2361     disp-extension-token = token
2362     disp-extension-parm = token "=" ( token | quoted-string )
2363</artwork></figure>
2364<t>
2365   An example is
2366</t>
2367<figure><artwork type="example">
2368     Content-Disposition: attachment; filename="fname.ext"
2369</artwork></figure>
2370<t>
2371   The receiving user agent &SHOULD-NOT;  respect any directory path
2372   information present in the filename-parm parameter, which is the only
2373   parameter believed to apply to HTTP implementations at this time. The
2374   filename &SHOULD; be treated as a terminal component only.
2375</t>
2376<t>
2377   If this header is used in a response with the application/octet-stream
2378   content-type, the implied suggestion is that the user agent
2379   should not display the response, but directly enter a `save response
2380   as...' dialog.
2381</t>
2382<t>
2383   See <xref target="content-disposition.issues"/> for Content-Disposition security issues.
2384</t>
2385</section>
2386</section>
2387
2388<section title="Changes from RFC 2068" anchor="changes.from.rfc.2068">
2389<t>
2390   Charset wildcarding is introduced to avoid explosion of character set
2391   names in accept headers. (<xref target="header.accept-charset"/>)
2392</t>
2393<t>
2394   Content-Base was deleted from the specification: it was not
2395   implemented widely, and there is no simple, safe way to introduce it
2396   without a robust extension mechanism. In addition, it is used in a
2397   similar, but not identical fashion in MHTML <xref target="RFC2110"/>.
2398</t>
2399<t>
2400   A content-coding of "identity" was introduced, to solve problems
2401   discovered in caching. (<xref target="content.codings"/>)
2402</t>
2403<t>
2404   Quality Values of zero should indicate that "I don't want something"
2405   to allow clients to refuse a representation. (<xref target="quality.values"/>)
2406</t>
2407<t>
2408   The Alternates<iref item="Alternates header" primary="true"/><iref item="Headers" subitem="Alternate" primary="true"/>, Content-Version<iref item="Content-Version header" primary="true"/><iref item="Headers" subitem="Content-Version" primary="true"/>, Derived-From<iref item="Derived-From header" primary="true"/><iref item="Headers" subitem="Derived-From" primary="true"/>, Link<iref item="Link header" primary="true"/><iref item="Headers" subitem="Link" primary="true"/>, URI<iref item="URI header" primary="true"/><iref item="Headers" subitem="URI" primary="true"/>, Public<iref item="Public header" primary="true"/><iref item="Headers" subitem="Public" primary="true"/> and
2409   Content-Base<iref item="Content-Base header" primary="true"/><iref item="Headers" subitem="Content-Base" primary="true"/> header fields were defined in previous versions of this
2410   specification, but not commonly implemented. See RFC 2068 <xref target="RFC2068"/>.
2411</t>
2412</section>
2413</back>
2414</rfc>
Note: See TracBrowser for help on using the repository browser.