source: draft-ietf-httpbis/latest/p3-payload.xml @ 95

Last change on this file since 95 was 95, checked in by julian.reschke@…, 12 years ago

List Yves Lafon & Julian Reschke as Editors everywhere, remove specific ack for Julian.

  • Property svn:eol-style set to native
File size: 108.8 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" role="editor">
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  <author initials="J. F." surname="Reschke" fullname="Julian F. Reschke" role="editor">
167    <organization abbrev="greenbytes">greenbytes GmbH</organization>
168    <address>
169      <postal>
170        <street>Hafenweg 16</street>
171        <city>Muenster</city><region>NW</region><code>48155</code>
172        <country>Germany</country>
173      </postal>
174      <phone>+49 251 2807760</phone>   
175      <facsimile>+49 251 2807761</facsimile>   
176      <email>julian.reschke@greenbytes.de</email>       
177      <uri>http://greenbytes.de/tech/webdav/</uri>     
178    </address>
179  </author>
180
181  <date month="&ID-MONTH;" year="&ID-YEAR;"/>
182
183<abstract>
184<t>
185   The Hypertext Transfer Protocol (HTTP) is an application-level
186   protocol for distributed, collaborative, hypermedia information
187   systems. HTTP has been in use by the World Wide Web global information
188   initiative since 1990. This document is Part 3 of the seven-part specification
189   that defines the protocol referred to as "HTTP/1.1" and, taken together,
190   obsoletes RFC 2616.  Part 3 defines HTTP message content,
191   metadata, and content negotiation.
192</t>
193</abstract>
194
195<note title="Editorial Note (To be removed by RFC Editor)">
196  <t>
197    This version of the HTTP specification contains only minimal editorial
198    changes from <xref target="RFC2616"/> (abstract, introductory paragraph,
199    and authors' addresses).  All other changes are due to partitioning the
200    original into seven mostly independent parts.  The intent is for readers
201    of future drafts to able to use draft 00 as the basis for comparison
202    when the WG makes later changes to the specification text.  This draft
203    will shortly be followed by draft 01 (containing the first round of changes
204    that have already been agreed to on the mailing list). There is no point in
205    reviewing this draft other than to verify that the partitioning has been
206    done correctly.  Roy T. Fielding, Yves Lafon, and Julian Reschke
207    will be the editors after draft 00 is submitted.
208  </t>
209  <t>
210    Discussion of this draft should take place on the HTTPBIS working group
211    mailing list (ietf-http-wg@w3.org). The current issues list is
212    at <eref target="http://www3.tools.ietf.org/wg/httpbis/trac/report/11"/>
213    and related documents (including fancy diffs) can be found at
214    <eref target="http://www3.tools.ietf.org/wg/httpbis/"/>.
215  </t>
216</note>
217</front>
218<middle>
219<section title="Introduction" anchor="introduction">
220<t>
221   This document will define aspects of HTTP related to the payload of
222   messages (message content), including metadata and media types, along
223   with HTTP content negotiation.  Right now it only includes the extracted
224   relevant sections of RFC 2616 without edit.
225</t>
226</section>
227
228<section title="Protocol Parameters" anchor="protocol.parameters">
229
230<section title="Character Sets" anchor="character.sets">
231<t>
232   HTTP uses the same definition of the term "character set" as that
233   described for MIME:
234</t>
235<t>
236   The term "character set" is used in this document to refer to a
237   method used with one or more tables to convert a sequence of octets
238   into a sequence of characters. Note that unconditional conversion in
239   the other direction is not required, in that not all characters may
240   be available in a given character set and a character set may provide
241   more than one sequence of octets to represent a particular character.
242   This definition is intended to allow various kinds of character
243   encoding, from simple single-table mappings such as US-ASCII to
244   complex table switching methods such as those that use ISO-2022's
245   techniques. However, the definition associated with a MIME character
246   set name &MUST; fully specify the mapping to be performed from octets
247   to characters. In particular, use of external profiling information
248   to determine the exact mapping is not permitted.
249</t>
250<t><list><t>
251      <x:h>Note:</x:h> This use of the term "character set" is more commonly
252      referred to as a "character encoding." However, since HTTP and
253      MIME share the same registry, it is important that the terminology
254      also be shared.
255</t></list></t>
256<t>
257   HTTP character sets are identified by case-insensitive tokens. The
258   complete set of tokens is defined by the IANA Character Set registry
259   (<eref target="http://www.iana.org/assignments/character-sets"/>).
260</t>
261<figure><artwork type="abnf2616"><iref primary="true" item="Grammar" subitem="charset"/>
262    charset = token
263</artwork></figure>
264<t>
265   Although HTTP allows an arbitrary token to be used as a charset
266   value, any token that has a predefined value within the IANA
267   Character Set registry &MUST; represent the character set defined
268   by that registry. Applications &SHOULD; limit their use of character
269   sets to those defined by the IANA registry.
270</t>
271<t>
272   HTTP uses charset in two contexts: within an Accept-Charset request
273   header (in which the charset value is an unquoted token) and as the
274   value of a parameter in a Content-type header (within a request or
275   response), in which case the parameter value of the charset parameter
276   may be quoted.
277</t>
278<t>
279   Implementors should be aware of IETF character set requirements <xref target="RFC2279"/>
280   <xref target="RFC2277"/>.
281</t>
282
283<section title="Missing Charset" anchor="missing.charset">
284<t>
285   Some HTTP/1.0 software has interpreted a Content-Type header without
286   charset parameter incorrectly to mean "recipient should guess."
287   Senders wishing to defeat this behavior &MAY; include a charset
288   parameter even when the charset is ISO-8859-1 and &SHOULD; do so when
289   it is known that it will not confuse the recipient.
290</t>
291<t>
292   Unfortunately, some older HTTP/1.0 clients did not deal properly with
293   an explicit charset parameter. HTTP/1.1 recipients &MUST; respect the
294   charset label provided by the sender; and those user agents that have
295   a provision to "guess" a charset &MUST; use the charset from the
296   content-type field if they support that charset, rather than the
297   recipient's preference, when initially displaying a document. See
298   <xref target="canonicalization.and.text.defaults"/>.
299</t>
300</section>
301</section>
302
303<section title="Content Codings" anchor="content.codings">
304<t>
305   Content coding values indicate an encoding transformation that has
306   been or can be applied to an entity. Content codings are primarily
307   used to allow a document to be compressed or otherwise usefully
308   transformed without losing the identity of its underlying media type
309   and without loss of information. Frequently, the entity is stored in
310   coded form, transmitted directly, and only decoded by the recipient.
311</t>
312<figure><artwork type="abnf2616"><iref primary="true" item="Grammar" subitem="content-coding"/>
313    content-coding   = token
314</artwork></figure>
315<t>
316   All content-coding values are case-insensitive. HTTP/1.1 uses
317   content-coding values in the Accept-Encoding (<xref target="header.accept-encoding"/>) and
318   Content-Encoding (<xref target="header.content-encoding"/>) header fields. Although the value
319   describes the content-coding, what is more important is that it
320   indicates what decoding mechanism will be required to remove the
321   encoding.
322</t>
323<t>
324   The Internet Assigned Numbers Authority (IANA) acts as a registry for
325   content-coding value tokens. Initially, the registry contains the
326   following tokens:
327</t>
328<t>
329   gzip<iref item="gzip"/>
330  <list>
331    <t>
332        An encoding format produced by the file compression program
333        "gzip" (GNU zip) as described in RFC 1952 <xref target="RFC1952"/>. This format is a
334        Lempel-Ziv coding (LZ77) with a 32 bit CRC.
335    </t>
336  </list>
337</t>
338<t>
339   compress<iref item="compress"/>
340  <list><t>
341        The encoding format produced by the common UNIX file compression
342        program "compress". This format is an adaptive Lempel-Ziv-Welch
343        coding (LZW).
344</t><t>
345        Use of program names for the identification of encoding formats
346        is not desirable and is discouraged for future encodings. Their
347        use here is representative of historical practice, not good
348        design. For compatibility with previous implementations of HTTP,
349        applications &SHOULD; consider "x-gzip" and "x-compress" to be
350        equivalent to "gzip" and "compress" respectively.
351  </t></list>
352</t>
353<t>
354   deflate<iref item="deflate"/>
355  <list><t>
356        The "zlib" format defined in RFC 1950 <xref target="RFC1950"/> in combination with
357        the "deflate" compression mechanism described in RFC 1951 <xref target="RFC1951"/>.
358  </t></list>
359</t>
360<t>
361   identity<iref item="identity"/>
362  <list><t>
363        The default (identity) encoding; the use of no transformation
364        whatsoever. This content-coding is used only in the Accept-Encoding
365        header, and &SHOULD-NOT;  be used in the Content-Encoding
366        header.
367  </t></list>
368</t>
369<t>
370   New content-coding value tokens &SHOULD; be registered; to allow
371   interoperability between clients and servers, specifications of the
372   content coding algorithms needed to implement a new value &SHOULD; be
373   publicly available and adequate for independent implementation, and
374   conform to the purpose of content coding defined in this section.
375</t>
376</section>
377
378<section title="Media Types" anchor="media.types">
379<t>
380   HTTP uses Internet Media Types <xref target="RFC4288"/> in the Content-Type (<xref target="header.content-type"/>)
381   and Accept (<xref target="header.accept"/>) header fields in order to provide
382   open and extensible data typing and type negotiation.
383</t>
384<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"/>
385    media-type     = type "/" subtype *( ";" parameter )
386    type           = token
387    subtype        = token
388</artwork></figure>
389<t>
390   Parameters &MAY; follow the type/subtype in the form of attribute/value
391   pairs.
392</t>
393<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"/>
394    parameter               = attribute "=" value
395    attribute               = token
396    value                   = token | quoted-string
397</artwork></figure>
398<t>
399   The type, subtype, and parameter attribute names are case-insensitive.
400   Parameter values might or might not be case-sensitive,
401   depending on the semantics of the parameter name. Linear white space
402   (LWS) &MUST-NOT; be used between the type and subtype, nor between an
403   attribute and its value. The presence or absence of a parameter might
404   be significant to the processing of a media-type, depending on its
405   definition within the media type registry.
406</t>
407<t>
408   Note that some older HTTP applications do not recognize media type
409   parameters. When sending data to older HTTP applications,
410   implementations &SHOULD; only use media type parameters when they are
411   required by that type/subtype definition.
412</t>
413<t>
414   Media-type values are registered with the Internet Assigned Number
415   Authority (IANA). The media type registration process is
416   outlined in RFC 4288 <xref target="RFC4288"/>. Use of non-registered media types is
417   discouraged.
418</t>
419
420<section title="Canonicalization and Text Defaults" anchor="canonicalization.and.text.defaults">
421<t>
422   Internet media types are registered with a canonical form. An
423   entity-body transferred via HTTP messages &MUST; be represented in the
424   appropriate canonical form prior to its transmission except for
425   "text" types, as defined in the next paragraph.
426</t>
427<t>
428   When in canonical form, media subtypes of the "text" type use CRLF as
429   the text line break. HTTP relaxes this requirement and allows the
430   transport of text media with plain CR or LF alone representing a line
431   break when it is done consistently for an entire entity-body. HTTP
432   applications &MUST; accept CRLF, bare CR, and bare LF as being
433   representative of a line break in text media received via HTTP. In
434   addition, if the text is represented in a character set that does not
435   use octets 13 and 10 for CR and LF respectively, as is the case for
436   some multi-byte character sets, HTTP allows the use of whatever octet
437   sequences are defined by that character set to represent the
438   equivalent of CR and LF for line breaks. This flexibility regarding
439   line breaks applies only to text media in the entity-body; a bare CR
440   or LF &MUST-NOT; be substituted for CRLF within any of the HTTP control
441   structures (such as header fields and multipart boundaries).
442</t>
443<t>
444   If an entity-body is encoded with a content-coding, the underlying
445   data &MUST; be in a form defined above prior to being encoded.
446</t>
447<t>
448   The "charset" parameter is used with some media types to define the
449   character set (<xref target="character.sets"/>) of the data. When no explicit charset
450   parameter is provided by the sender, media subtypes of the "text"
451   type are defined to have a default charset value of "ISO-8859-1" when
452   received via HTTP. Data in character sets other than "ISO-8859-1" or
453   its subsets &MUST; be labeled with an appropriate charset value. See
454   <xref target="missing.charset"/> for compatibility problems.
455</t>
456</section>
457
458<section title="Multipart Types" anchor="multipart.types">
459<t>
460   MIME provides for a number of "multipart" types -- encapsulations of
461   one or more entities within a single message-body. All multipart
462   types share a common syntax, as defined in section <xref target="RFC2046" x:sec="5.1.1" x:fmt="number"/> of RFC 2046
463   <xref target="RFC2046"/>, and &MUST; include a boundary parameter as part of the media type
464   value. The message body is itself a protocol element and &MUST;
465   therefore use only CRLF to represent line breaks between body-parts.
466   Unlike in RFC 2046, the epilogue of any multipart message &MUST; be
467   empty; HTTP applications &MUST-NOT; transmit the epilogue (even if the
468   original multipart contains an epilogue). These restrictions exist in
469   order to preserve the self-delimiting nature of a multipart message-body,
470   wherein the "end" of the message-body is indicated by the
471   ending multipart boundary.
472</t>
473<t>
474   In general, HTTP treats a multipart message-body no differently than
475   any other media type: strictly as payload. The one exception is the
476   "multipart/byteranges" type (&multipart-byteranges;) when it appears in a 206
477   (Partial Content) response. In all
478   other cases, an HTTP user agent &SHOULD; follow the same or similar
479   behavior as a MIME user agent would upon receipt of a multipart type.
480   The MIME header fields within each body-part of a multipart message-body
481   do not have any significance to HTTP beyond that defined by
482   their MIME semantics.
483</t>
484<t>
485   In general, an HTTP user agent &SHOULD; follow the same or similar
486   behavior as a MIME user agent would upon receipt of a multipart type.
487   If an application receives an unrecognized multipart subtype, the
488   application &MUST; treat it as being equivalent to "multipart/mixed".
489</t>
490<t><list><t>
491      <x:h>Note:</x:h> The "multipart/form-data" type has been specifically defined
492      for carrying form data suitable for processing via the POST
493      request method, as described in RFC 1867 <xref target="RFC1867"/>.
494</t></list></t>
495</section>
496</section>
497
498<section title="Quality Values" anchor="quality.values">
499<t>
500   HTTP content negotiation (<xref target="content.negotiation"/>) uses short "floating point"
501   numbers to indicate the relative importance ("weight") of various
502   negotiable parameters.  A weight is normalized to a real number in
503   the range 0 through 1, where 0 is the minimum and 1 the maximum
504   value. If a parameter has a quality value of 0, then content with
505   this parameter is `not acceptable' for the client. HTTP/1.1
506   applications &MUST-NOT; generate more than three digits after the
507   decimal point. User configuration of these values &SHOULD; also be
508   limited in this fashion.
509</t>
510<figure><artwork type="abnf2616"><iref primary="true" item="Grammar" subitem="qvalue"/>
511    qvalue         = ( "0" [ "." 0*3DIGIT ] )
512                   | ( "1" [ "." 0*3("0") ] )
513</artwork></figure>
514<t>
515   "Quality values" is a misnomer, since these values merely represent
516   relative degradation in desired quality.
517</t>
518</section>
519
520<section title="Language Tags" anchor="language.tags">
521<t>
522   A language tag identifies a natural language spoken, written, or
523   otherwise conveyed by human beings for communication of information
524   to other human beings. Computer languages are explicitly excluded.
525   HTTP uses language tags within the Accept-Language and Content-Language
526   fields.
527</t>
528<t>
529   The syntax and registry of HTTP language tags is the same as that
530   defined by RFC 1766 <xref target="RFC1766"/>. In summary, a language tag is composed of 1
531   or more parts: A primary language tag and a possibly empty series of
532   subtags:
533</t>
534<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"/>
535     language-tag  = primary-tag *( "-" subtag )
536     primary-tag   = 1*8ALPHA
537     subtag        = 1*8ALPHA
538</artwork></figure>
539<t>
540   White space is not allowed within the tag and all tags are case-insensitive.
541   The name space of language tags is administered by the
542   IANA. Example tags include:
543</t>
544<figure><artwork type="example">
545    en, en-US, en-cockney, i-cherokee, x-pig-latin
546</artwork></figure>
547<t>
548   where any two-letter primary-tag is an ISO-639 language abbreviation
549   and any two-letter initial subtag is an ISO-3166 country code. (The
550   last three tags above are not registered tags; all but the last are
551   examples of tags which could be registered in future.)
552</t>
553</section>
554</section>
555
556<section title="Entity" anchor="entity">
557<t>
558   Request and Response messages &MAY; transfer an entity if not otherwise
559   restricted by the request method or response status code. An entity
560   consists of entity-header fields and an entity-body, although some
561   responses will only include the entity-headers.
562</t>
563<t>
564   In this section, both sender and recipient refer to either the client
565   or the server, depending on who sends and who receives the entity.
566</t>
567
568<section title="Entity Header Fields" anchor="entity.header.fields">
569<t>
570   Entity-header fields define metainformation about the entity-body or,
571   if no body is present, about the resource identified by the request.
572   Some of this metainformation is &OPTIONAL;; some might be &REQUIRED; by
573   portions of this specification.
574</t>
575<figure><artwork type="abnf2616"><iref primary="true" item="Grammar" subitem="entity-header"/><iref primary="true" item="Grammar" subitem="extension-header"/>
576    entity-header  = Allow                    ; &header-allow;
577                   | Content-Encoding         ; <xref target="header.content-encoding"/>
578                   | Content-Language         ; <xref target="header.content-language"/>
579                   | Content-Length           ; &header-content-length;
580                   | Content-Location         ; <xref target="header.content-location"/>
581                   | Content-MD5              ; <xref target="header.content-md5"/>
582                   | Content-Range            ; &header-content-range;
583                   | Content-Type             ; <xref target="header.content-type"/>
584                   | Expires                  ; &header-expires;
585                   | Last-Modified            ; &header-last-modified;
586                   | extension-header
587
588    extension-header = message-header
589</artwork></figure>
590<t>
591   The extension-header mechanism allows additional entity-header fields
592   to be defined without changing the protocol, but these fields cannot
593   be assumed to be recognizable by the recipient. Unrecognized header
594   fields &SHOULD; be ignored by the recipient and &MUST; be forwarded by
595   transparent proxies.
596</t>
597</section>
598
599<section title="Entity Body" anchor="entity.body">
600<t>
601   The entity-body (if any) sent with an HTTP request or response is in
602   a format and encoding defined by the entity-header fields.
603</t>
604<figure><artwork type="abnf2616"><iref primary="true" item="Grammar" subitem="entity-body"/>
605    entity-body    = *OCTET
606</artwork></figure>
607<t>
608   An entity-body is only present in a message when a message-body is
609   present, as described in &message-body;. The entity-body is obtained
610   from the message-body by decoding any Transfer-Encoding that might
611   have been applied to ensure safe and proper transfer of the message.
612</t>
613
614<section title="Type" anchor="type">
615<t>
616   When an entity-body is included with a message, the data type of that
617   body is determined via the header fields Content-Type and Content-Encoding.
618   These define a two-layer, ordered encoding model:
619</t>
620<figure><artwork type="example">
621    entity-body := Content-Encoding( Content-Type( data ) )
622</artwork></figure>
623<t>
624   Content-Type specifies the media type of the underlying data.
625   Content-Encoding may be used to indicate any additional content
626   codings applied to the data, usually for the purpose of data
627   compression, that are a property of the requested resource. There is
628   no default encoding.
629</t>
630<t>
631   Any HTTP/1.1 message containing an entity-body &SHOULD; include a
632   Content-Type header field defining the media type of that body. If
633   and only if the media type is not given by a Content-Type field, the
634   recipient &MAY; attempt to guess the media type via inspection of its
635   content and/or the name extension(s) of the URI used to identify the
636   resource. If the media type remains unknown, the recipient &SHOULD;
637   treat it as type "application/octet-stream".
638</t>
639</section>
640   
641<section title="Entity Length" anchor="entity.length">
642<t>
643   The entity-length of a message is the length of the message-body
644   before any transfer-codings have been applied. &message-length; defines
645   how the transfer-length of a message-body is determined.
646</t>
647</section>
648</section>
649</section>
650
651<section title="Content Negotiation" anchor="content.negotiation">
652<t>
653   Most HTTP responses include an entity which contains information for
654   interpretation by a human user. Naturally, it is desirable to supply
655   the user with the "best available" entity corresponding to the
656   request. Unfortunately for servers and caches, not all users have the
657   same preferences for what is "best," and not all user agents are
658   equally capable of rendering all entity types. For that reason, HTTP
659   has provisions for several mechanisms for "content negotiation" --
660   the process of selecting the best representation for a given response
661   when there are multiple representations available.
662  <list><t>
663      <x:h>Note:</x:h> This is not called "format negotiation" because the
664      alternate representations may be of the same media type, but use
665      different capabilities of that type, be in different languages,
666      etc.
667  </t></list>
668</t>
669<t>
670   Any response containing an entity-body &MAY; be subject to negotiation,
671   including error responses.
672</t>
673<t>
674   There are two kinds of content negotiation which are possible in
675   HTTP: server-driven and agent-driven negotiation. These two kinds of
676   negotiation are orthogonal and thus may be used separately or in
677   combination. One method of combination, referred to as transparent
678   negotiation, occurs when a cache uses the agent-driven negotiation
679   information provided by the origin server in order to provide
680   server-driven negotiation for subsequent requests.
681</t>
682
683<section title="Server-driven Negotiation" anchor="server-driven.negotiation">
684<t>
685   If the selection of the best representation for a response is made by
686   an algorithm located at the server, it is called server-driven
687   negotiation. Selection is based on the available representations of
688   the response (the dimensions over which it can vary; e.g. language,
689   content-coding, etc.) and the contents of particular header fields in
690   the request message or on other information pertaining to the request
691   (such as the network address of the client).
692</t>
693<t>
694   Server-driven negotiation is advantageous when the algorithm for
695   selecting from among the available representations is difficult to
696   describe to the user agent, or when the server desires to send its
697   "best guess" to the client along with the first response (hoping to
698   avoid the round-trip delay of a subsequent request if the "best
699   guess" is good enough for the user). In order to improve the server's
700   guess, the user agent &MAY; include request header fields (Accept,
701   Accept-Language, Accept-Encoding, etc.) which describe its
702   preferences for such a response.
703</t>
704<t>
705   Server-driven negotiation has disadvantages:
706  <list style="numbers">
707    <t>
708         It is impossible for the server to accurately determine what
709         might be "best" for any given user, since that would require
710         complete knowledge of both the capabilities of the user agent
711         and the intended use for the response (e.g., does the user want
712         to view it on screen or print it on paper?).
713    </t>
714    <t>
715         Having the user agent describe its capabilities in every
716         request can be both very inefficient (given that only a small
717         percentage of responses have multiple representations) and a
718         potential violation of the user's privacy.
719    </t>
720    <t>
721         It complicates the implementation of an origin server and the
722         algorithms for generating responses to a request.
723    </t>
724    <t>
725         It may limit a public cache's ability to use the same response
726         for multiple user's requests.
727    </t>
728  </list>
729</t>
730<t>
731   HTTP/1.1 includes the following request-header fields for enabling
732   server-driven negotiation through description of user agent
733   capabilities and user preferences: Accept (<xref target="header.accept"/>), Accept-Charset
734   (<xref target="header.accept-charset"/>), Accept-Encoding (<xref target="header.accept-encoding"/>), Accept-Language
735   (<xref target="header.accept-language"/>), and User-Agent (&header-user-agent;). However, an
736   origin server is not limited to these dimensions and &MAY; vary the
737   response based on any aspect of the request, including information
738   outside the request-header fields or within extension header fields
739   not defined by this specification.
740</t>
741<t>
742   The Vary header field &caching; can be used to express the parameters the
743   server uses to select a representation that is subject to server-driven
744   negotiation.
745</t>
746</section>
747
748<section title="Agent-driven Negotiation" anchor="agent-driven.negotiation">
749<t>
750   With agent-driven negotiation, selection of the best representation
751   for a response is performed by the user agent after receiving an
752   initial response from the origin server. Selection is based on a list
753   of the available representations of the response included within the
754   header fields or entity-body of the initial response, with each
755   representation identified by its own URI. Selection from among the
756   representations may be performed automatically (if the user agent is
757   capable of doing so) or manually by the user selecting from a
758   generated (possibly hypertext) menu.
759</t>
760<t>
761   Agent-driven negotiation is advantageous when the response would vary
762   over commonly-used dimensions (such as type, language, or encoding),
763   when the origin server is unable to determine a user agent's
764   capabilities from examining the request, and generally when public
765   caches are used to distribute server load and reduce network usage.
766</t>
767<t>
768   Agent-driven negotiation suffers from the disadvantage of needing a
769   second request to obtain the best alternate representation. This
770   second request is only efficient when caching is used. In addition,
771   this specification does not define any mechanism for supporting
772   automatic selection, though it also does not prevent any such
773   mechanism from being developed as an extension and used within
774   HTTP/1.1.
775</t>
776<t>
777   HTTP/1.1 defines the 300 (Multiple Choices) and 406 (Not Acceptable)
778   status codes for enabling agent-driven negotiation when the server is
779   unwilling or unable to provide a varying response using server-driven
780   negotiation.
781</t>
782</section>
783
784<section title="Transparent Negotiation" anchor="transparent.negotiation">
785<t>
786   Transparent negotiation is a combination of both server-driven and
787   agent-driven negotiation. When a cache is supplied with a form of the
788   list of available representations of the response (as in agent-driven
789   negotiation) and the dimensions of variance are completely understood
790   by the cache, then the cache becomes capable of performing server-driven
791   negotiation on behalf of the origin server for subsequent
792   requests on that resource.
793</t>
794<t>
795   Transparent negotiation has the advantage of distributing the
796   negotiation work that would otherwise be required of the origin
797   server and also removing the second request delay of agent-driven
798   negotiation when the cache is able to correctly guess the right
799   response.
800</t>
801<t>
802   This specification does not define any mechanism for transparent
803   negotiation, though it also does not prevent any such mechanism from
804   being developed as an extension that could be used within HTTP/1.1.
805</t>
806</section>
807</section>
808<section title="Header Field Definitions" anchor="header.fields">
809<t>
810   This section defines the syntax and semantics of all standard
811   HTTP/1.1 header fields. For entity-header fields, both sender and
812   recipient refer to either the client or the server, depending on who
813   sends and who receives the entity.
814</t>
815<section title="Accept" anchor="header.accept">
816  <iref primary="true" item="Accept header" x:for-anchor=""/>
817  <iref primary="true" item="Headers" subitem="Accept" x:for-anchor=""/>
818<t>
819   The Accept request-header field can be used to specify certain media
820   types which are acceptable for the response. Accept headers can be
821   used to indicate that the request is specifically limited to a small
822   set of desired types, as in the case of a request for an in-line
823   image.
824</t>
825<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"/>
826    Accept         = "Accept" ":"
827                     #( media-range [ accept-params ] )
828
829    media-range    = ( "*/*"
830                     | ( type "/" "*" )
831                     | ( type "/" subtype )
832                     ) *( ";" parameter )
833    accept-params  = ";" "q" "=" qvalue *( accept-extension )
834    accept-extension = ";" token [ "=" ( token | quoted-string ) ]
835</artwork></figure>
836<t>
837   The asterisk "*" character is used to group media types into ranges,
838   with "*/*" indicating all media types and "type/*" indicating all
839   subtypes of that type. The media-range &MAY; include media type
840   parameters that are applicable to that range.
841</t>
842<t>
843   Each media-range &MAY; be followed by one or more accept-params,
844   beginning with the "q" parameter for indicating a relative quality
845   factor. The first "q" parameter (if any) separates the media-range
846   parameter(s) from the accept-params. Quality factors allow the user
847   or user agent to indicate the relative degree of preference for that
848   media-range, using the qvalue scale from 0 to 1 (<xref target="quality.values"/>). The
849   default value is q=1.
850  <list><t>
851      <x:h>Note:</x:h> Use of the "q" parameter name to separate media type
852      parameters from Accept extension parameters is due to historical
853      practice. Although this prevents any media type parameter named
854      "q" from being used with a media range, such an event is believed
855      to be unlikely given the lack of any "q" parameters in the IANA
856      media type registry and the rare usage of any media type
857      parameters in Accept. Future media types are discouraged from
858      registering any parameter named "q".
859  </t></list>
860</t>
861<t>
862   The example
863</t>
864<figure><artwork type="example">
865    Accept: audio/*; q=0.2, audio/basic
866</artwork></figure>
867<t>
868   &SHOULD; be interpreted as "I prefer audio/basic, but send me any audio
869   type if it is the best available after an 80% mark-down in quality."
870</t>
871<t>
872   If no Accept header field is present, then it is assumed that the
873   client accepts all media types. If an Accept header field is present,
874   and if the server cannot send a response which is acceptable
875   according to the combined Accept field value, then the server &SHOULD;
876   send a 406 (not acceptable) response.
877</t>
878<t>
879   A more elaborate example is
880</t>
881<figure><artwork type="example">
882    Accept: text/plain; q=0.5, text/html,
883            text/x-dvi; q=0.8, text/x-c
884</artwork></figure>
885<t>
886   Verbally, this would be interpreted as "text/html and text/x-c are
887   the preferred media types, but if they do not exist, then send the
888   text/x-dvi entity, and if that does not exist, send the text/plain
889   entity."
890</t>
891<t>
892   Media ranges can be overridden by more specific media ranges or
893   specific media types. If more than one media range applies to a given
894   type, the most specific reference has precedence. For example,
895</t>
896<figure><artwork type="example">
897    Accept: text/*, text/html, text/html;level=1, */*
898</artwork></figure>
899<t>
900   have the following precedence:
901</t>
902<figure><artwork type="example">
903    1) text/html;level=1
904    2) text/html
905    3) text/*
906    4) */*
907</artwork></figure>
908<t>
909   The media type quality factor associated with a given type is
910   determined by finding the media range with the highest precedence
911   which matches that type. For example,
912</t>
913<figure><artwork type="example">
914    Accept: text/*;q=0.3, text/html;q=0.7, text/html;level=1,
915            text/html;level=2;q=0.4, */*;q=0.5
916</artwork></figure>
917<t>
918   would cause the following values to be associated:
919</t>
920<figure><artwork type="example">
921    text/html;level=1         = 1
922    text/html                 = 0.7
923    text/plain                = 0.3
924    image/jpeg                = 0.5
925    text/html;level=2         = 0.4
926    text/html;level=3         = 0.7
927</artwork></figure>
928<t>
929      <x:h>Note:</x:h> A user agent might be provided with a default set of quality
930      values for certain media ranges. However, unless the user agent is
931      a closed system which cannot interact with other rendering agents,
932      this default set ought to be configurable by the user.
933</t>
934</section>
935
936<section title="Accept-Charset" anchor="header.accept-charset">
937  <iref primary="true" item="Accept-Charset header" x:for-anchor=""/>
938  <iref primary="true" item="Headers" subitem="Accept-Charset" x:for-anchor=""/>
939<t>
940   The Accept-Charset request-header field can be used to indicate what
941   character sets are acceptable for the response. This field allows
942   clients capable of understanding more comprehensive or special-purpose
943   character sets to signal that capability to a server which is
944   capable of representing documents in those character sets.
945</t>
946<figure><artwork type="abnf2616"><iref primary="true" item="Grammar" subitem="Accept-Charset"/>
947   Accept-Charset = "Accept-Charset" ":"
948           1#( ( charset | "*" )[ ";" "q" "=" qvalue ] )
949</artwork></figure>
950<t>
951   Character set values are described in <xref target="character.sets"/>. Each charset &MAY;
952   be given an associated quality value which represents the user's
953   preference for that charset. The default value is q=1. An example is
954</t>
955<figure><artwork type="example">
956   Accept-Charset: iso-8859-5, unicode-1-1;q=0.8
957</artwork></figure>
958<t>
959   The special value "*", if present in the Accept-Charset field,
960   matches every character set (including ISO-8859-1) which is not
961   mentioned elsewhere in the Accept-Charset field. If no "*" is present
962   in an Accept-Charset field, then all character sets not explicitly
963   mentioned get a quality value of 0, except for ISO-8859-1, which gets
964   a quality value of 1 if not explicitly mentioned.
965</t>
966<t>
967   If no Accept-Charset header is present, the default is that any
968   character set is acceptable. If an Accept-Charset header is present,
969   and if the server cannot send a response which is acceptable
970   according to the Accept-Charset header, then the server &SHOULD; send
971   an error response with the 406 (not acceptable) status code, though
972   the sending of an unacceptable response is also allowed.
973</t>
974</section>
975
976<section title="Accept-Encoding" anchor="header.accept-encoding">
977  <iref primary="true" item="Accept-Encoding header" x:for-anchor=""/>
978  <iref primary="true" item="Headers" subitem="Accept-Encoding" x:for-anchor=""/>
979<t>
980   The Accept-Encoding request-header field is similar to Accept, but
981   restricts the content-codings (<xref target="content.codings"/>) that are acceptable in
982   the response.
983</t>
984<figure><artwork type="abnf2616"><iref primary="true" item="Grammar" subitem="Accept-Encoding"/><iref primary="true" item="Grammar" subitem="codings"/>
985    Accept-Encoding  = "Accept-Encoding" ":"
986                       1#( codings [ ";" "q" "=" qvalue ] )
987    codings          = ( content-coding | "*" )
988</artwork></figure>
989<t>
990   Examples of its use are:
991</t>
992<figure><artwork type="example">
993    Accept-Encoding: compress, gzip
994    Accept-Encoding:
995    Accept-Encoding: *
996    Accept-Encoding: compress;q=0.5, gzip;q=1.0
997    Accept-Encoding: gzip;q=1.0, identity; q=0.5, *;q=0
998</artwork></figure>
999<t>
1000   A server tests whether a content-coding is acceptable, according to
1001   an Accept-Encoding field, using these rules:
1002  <list style="numbers">
1003      <t>If the content-coding is one of the content-codings listed in
1004         the Accept-Encoding field, then it is acceptable, unless it is
1005         accompanied by a qvalue of 0. (As defined in <xref target="quality.values"/>, a
1006         qvalue of 0 means "not acceptable.")</t>
1007
1008      <t>The special "*" symbol in an Accept-Encoding field matches any
1009         available content-coding not explicitly listed in the header
1010         field.</t>
1011
1012      <t>If multiple content-codings are acceptable, then the acceptable
1013         content-coding with the highest non-zero qvalue is preferred.</t>
1014
1015      <t>The "identity" content-coding is always acceptable, unless
1016         specifically refused because the Accept-Encoding field includes
1017         "identity;q=0", or because the field includes "*;q=0" and does
1018         not explicitly include the "identity" content-coding. If the
1019         Accept-Encoding field-value is empty, then only the "identity"
1020         encoding is acceptable.</t>
1021  </list>
1022</t>
1023<t>
1024   If an Accept-Encoding field is present in a request, and if the
1025   server cannot send a response which is acceptable according to the
1026   Accept-Encoding header, then the server &SHOULD; send an error response
1027   with the 406 (Not Acceptable) status code.
1028</t>
1029<t>
1030   If no Accept-Encoding field is present in a request, the server &MAY;
1031   assume that the client will accept any content coding. In this case,
1032   if "identity" is one of the available content-codings, then the
1033   server &SHOULD; use the "identity" content-coding, unless it has
1034   additional information that a different content-coding is meaningful
1035   to the client.
1036  <list><t>
1037      <x:h>Note:</x:h> If the request does not include an Accept-Encoding field,
1038      and if the "identity" content-coding is unavailable, then
1039      content-codings commonly understood by HTTP/1.0 clients (i.e.,
1040      "gzip" and "compress") are preferred; some older clients
1041      improperly display messages sent with other content-codings.  The
1042      server might also make this decision based on information about
1043      the particular user-agent or client.
1044    </t><t>
1045      <x:h>Note:</x:h> Most HTTP/1.0 applications do not recognize or obey qvalues
1046      associated with content-codings. This means that qvalues will not
1047      work and are not permitted with x-gzip or x-compress.
1048    </t></list>
1049</t>
1050</section>
1051
1052<section title="Accept-Language" anchor="header.accept-language">
1053  <iref primary="true" item="Accept-Language header" x:for-anchor=""/>
1054  <iref primary="true" item="Headers" subitem="Accept-Language" x:for-anchor=""/>
1055<t>
1056   The Accept-Language request-header field is similar to Accept, but
1057   restricts the set of natural languages that are preferred as a
1058   response to the request. Language tags are defined in <xref target="language.tags"/>.
1059</t>
1060<figure><artwork type="abnf2616"><iref primary="true" item="Grammar" subitem="Accept-Language"/><iref primary="true" item="Grammar" subitem="language-range"/>
1061    Accept-Language = "Accept-Language" ":"
1062                      1#( language-range [ ";" "q" "=" qvalue ] )
1063    language-range  = ( ( 1*8ALPHA *( "-" 1*8ALPHA ) ) | "*" )
1064</artwork></figure>
1065<t>
1066   Each language-range &MAY; be given an associated quality value which
1067   represents an estimate of the user's preference for the languages
1068   specified by that range. The quality value defaults to "q=1". For
1069   example,
1070</t>
1071<figure><artwork type="example">
1072    Accept-Language: da, en-gb;q=0.8, en;q=0.7
1073</artwork></figure>
1074<t>
1075   would mean: "I prefer Danish, but will accept British English and
1076   other types of English." A language-range matches a language-tag if
1077   it exactly equals the tag, or if it exactly equals a prefix of the
1078   tag such that the first tag character following the prefix is "-".
1079   The special range "*", if present in the Accept-Language field,
1080   matches every tag not matched by any other range present in the
1081   Accept-Language field.
1082  <list><t>
1083      <x:h>Note:</x:h> This use of a prefix matching rule does not imply that
1084      language tags are assigned to languages in such a way that it is
1085      always true that if a user understands a language with a certain
1086      tag, then this user will also understand all languages with tags
1087      for which this tag is a prefix. The prefix rule simply allows the
1088      use of prefix tags if this is the case.
1089  </t></list>
1090</t>
1091<t>
1092   The language quality factor assigned to a language-tag by the
1093   Accept-Language field is the quality value of the longest language-range
1094   in the field that matches the language-tag. If no language-range
1095   in the field matches the tag, the language quality factor
1096   assigned is 0. If no Accept-Language header is present in the
1097   request, the server
1098   &SHOULD; assume that all languages are equally acceptable. If an
1099   Accept-Language header is present, then all languages which are
1100   assigned a quality factor greater than 0 are acceptable.
1101</t>
1102<t>
1103   It might be contrary to the privacy expectations of the user to send
1104   an Accept-Language header with the complete linguistic preferences of
1105   the user in every request. For a discussion of this issue, see
1106   <xref target="privacy.issues.connected.to.accept.headers"/>.
1107</t>
1108<t>
1109   As intelligibility is highly dependent on the individual user, it is
1110   recommended that client applications make the choice of linguistic
1111   preference available to the user. If the choice is not made
1112   available, then the Accept-Language header field &MUST-NOT; be given in
1113   the request.
1114  <list><t>
1115      <x:h>Note:</x:h> When making the choice of linguistic preference available to
1116      the user, we remind implementors of  the fact that users are not
1117      familiar with the details of language matching as described above,
1118      and should provide appropriate guidance. As an example, users
1119      might assume that on selecting "en-gb", they will be served any
1120      kind of English document if British English is not available. A
1121      user agent might suggest in such a case to add "en" to get the
1122      best matching behavior.
1123  </t></list>
1124</t>
1125</section>
1126
1127<section title="Content-Encoding" anchor="header.content-encoding">
1128  <iref primary="true" item="Content-Encoding header" x:for-anchor=""/>
1129  <iref primary="true" item="Headers" subitem="Content-Encoding" x:for-anchor=""/>
1130<t>
1131   The Content-Encoding entity-header field is used as a modifier to the
1132   media-type. When present, its value indicates what additional content
1133   codings have been applied to the entity-body, and thus what decoding
1134   mechanisms must be applied in order to obtain the media-type
1135   referenced by the Content-Type header field. Content-Encoding is
1136   primarily used to allow a document to be compressed without losing
1137   the identity of its underlying media type.
1138</t>
1139<figure><artwork type="abnf2616"><iref primary="true" item="Grammar" subitem="Content-Encoding"/>
1140    Content-Encoding  = "Content-Encoding" ":" 1#content-coding
1141</artwork></figure>
1142<t>
1143   Content codings are defined in <xref target="content.codings"/>. An example of its use is
1144</t>
1145<figure><artwork type="example">
1146    Content-Encoding: gzip
1147</artwork></figure>
1148<t>
1149   The content-coding is a characteristic of the entity identified by
1150   the Request-URI. Typically, the entity-body is stored with this
1151   encoding and is only decoded before rendering or analogous usage.
1152   However, a non-transparent proxy &MAY; modify the content-coding if the
1153   new coding is known to be acceptable to the recipient, unless the
1154   "no-transform" cache-control directive is present in the message.
1155</t>
1156<t>
1157   If the content-coding of an entity is not "identity", then the
1158   response &MUST; include a Content-Encoding entity-header (<xref target="header.content-encoding"/>)
1159   that lists the non-identity content-coding(s) used.
1160</t>
1161<t>
1162   If the content-coding of an entity in a request message is not
1163   acceptable to the origin server, the server &SHOULD; respond with a
1164   status code of 415 (Unsupported Media Type).
1165</t>
1166<t>
1167   If multiple encodings have been applied to an entity, the content
1168   codings &MUST; be listed in the order in which they were applied.
1169   Additional information about the encoding parameters &MAY; be provided
1170   by other entity-header fields not defined by this specification.
1171</t>
1172</section>
1173
1174<section title="Content-Language" anchor="header.content-language">
1175  <iref primary="true" item="Content-Language header" x:for-anchor=""/>
1176  <iref primary="true" item="Headers" subitem="Content-Language" x:for-anchor=""/>
1177<t>
1178   The Content-Language entity-header field describes the natural
1179   language(s) of the intended audience for the enclosed entity. Note
1180   that this might not be equivalent to all the languages used within
1181   the entity-body.
1182</t>
1183<figure><artwork type="abnf2616"><iref primary="true" item="Grammar" subitem="Content-Language"/>
1184    Content-Language  = "Content-Language" ":" 1#language-tag
1185</artwork></figure>
1186<t>
1187   Language tags are defined in <xref target="language.tags"/>. The primary purpose of
1188   Content-Language is to allow a user to identify and differentiate
1189   entities according to the user's own preferred language. Thus, if the
1190   body content is intended only for a Danish-literate audience, the
1191   appropriate field is
1192</t>
1193<figure><artwork type="example">
1194    Content-Language: da
1195</artwork></figure>
1196<t>
1197   If no Content-Language is specified, the default is that the content
1198   is intended for all language audiences. This might mean that the
1199   sender does not consider it to be specific to any natural language,
1200   or that the sender does not know for which language it is intended.
1201</t>
1202<t>
1203   Multiple languages &MAY; be listed for content that is intended for
1204   multiple audiences. For example, a rendition of the "Treaty of
1205   Waitangi," presented simultaneously in the original Maori and English
1206   versions, would call for
1207</t>
1208<figure><artwork type="example">
1209    Content-Language: mi, en
1210</artwork></figure>
1211<t>
1212   However, just because multiple languages are present within an entity
1213   does not mean that it is intended for multiple linguistic audiences.
1214   An example would be a beginner's language primer, such as "A First
1215   Lesson in Latin," which is clearly intended to be used by an
1216   English-literate audience. In this case, the Content-Language would
1217   properly only include "en".
1218</t>
1219<t>
1220   Content-Language &MAY; be applied to any media type -- it is not
1221   limited to textual documents.
1222</t>
1223</section>
1224
1225<section title="Content-Location" anchor="header.content-location">
1226  <iref primary="true" item="Content-Location header" x:for-anchor=""/>
1227  <iref primary="true" item="Headers" subitem="Content-Location" x:for-anchor=""/>
1228<t>
1229   The Content-Location entity-header field &MAY; be used to supply the
1230   resource location for the entity enclosed in the message when that
1231   entity is accessible from a location separate from the requested
1232   resource's URI. A server &SHOULD; provide a Content-Location for the
1233   variant corresponding to the response entity; especially in the case
1234   where a resource has multiple entities associated with it, and those
1235   entities actually have separate locations by which they might be
1236   individually accessed, the server &SHOULD; provide a Content-Location
1237   for the particular variant which is returned.
1238</t>
1239<figure><artwork type="abnf2616"><iref primary="true" item="Grammar" subitem="Content-Location"/>
1240    Content-Location = "Content-Location" ":"
1241                      ( absoluteURI | relativeURI )
1242</artwork></figure>
1243<t>
1244   The value of Content-Location also defines the base URI for the
1245   entity.
1246</t>
1247<t>
1248   The Content-Location value is not a replacement for the original
1249   requested URI; it is only a statement of the location of the resource
1250   corresponding to this particular entity at the time of the request.
1251   Future requests &MAY; specify the Content-Location URI as the request-URI
1252   if the desire is to identify the source of that particular
1253   entity.
1254</t>
1255<t>
1256   A cache cannot assume that an entity with a Content-Location
1257   different from the URI used to retrieve it can be used to respond to
1258   later requests on that Content-Location URI. However, the Content-Location
1259   can be used to differentiate between multiple entities
1260   retrieved from a single requested resource, as described in &caching;.
1261</t>
1262<t>
1263   If the Content-Location is a relative URI, the relative URI is
1264   interpreted relative to the Request-URI.
1265</t>
1266<t>
1267   The meaning of the Content-Location header in PUT or POST requests is
1268   undefined; servers are free to ignore it in those cases.
1269</t>
1270</section>
1271
1272<section title="Content-MD5" anchor="header.content-md5">
1273  <iref primary="true" item="Content-MD5 header" x:for-anchor=""/>
1274  <iref primary="true" item="Headers" subitem="Content-MD5" x:for-anchor=""/>
1275<t>
1276   The Content-MD5 entity-header field, as defined in RFC 1864 <xref target="RFC1864"/>, is
1277   an MD5 digest of the entity-body for the purpose of providing an
1278   end-to-end message integrity check (MIC) of the entity-body. (Note: a
1279   MIC is good for detecting accidental modification of the entity-body
1280   in transit, but is not proof against malicious attacks.)
1281</t>
1282<figure><artwork type="abnf2616"><iref primary="true" item="Grammar" subitem="Content-MD5"/><iref primary="true" item="Grammar" subitem="md5-digest"/>
1283     Content-MD5   = "Content-MD5" ":" md5-digest
1284     md5-digest   = &lt;base64 of 128 bit MD5 digest as per RFC 1864&gt;
1285</artwork></figure>
1286<t>
1287   The Content-MD5 header field &MAY; be generated by an origin server or
1288   client to function as an integrity check of the entity-body. Only
1289   origin servers or clients &MAY; generate the Content-MD5 header field;
1290   proxies and gateways &MUST-NOT; generate it, as this would defeat its
1291   value as an end-to-end integrity check. Any recipient of the entity-body,
1292   including gateways and proxies, &MAY; check that the digest value
1293   in this header field matches that of the entity-body as received.
1294</t>
1295<t>
1296   The MD5 digest is computed based on the content of the entity-body,
1297   including any content-coding that has been applied, but not including
1298   any transfer-encoding applied to the message-body. If the message is
1299   received with a transfer-encoding, that encoding &MUST; be removed
1300   prior to checking the Content-MD5 value against the received entity.
1301</t>
1302<t>
1303   This has the result that the digest is computed on the octets of the
1304   entity-body exactly as, and in the order that, they would be sent if
1305   no transfer-encoding were being applied.
1306</t>
1307<t>
1308   HTTP extends RFC 1864 to permit the digest to be computed for MIME
1309   composite media-types (e.g., multipart/* and message/rfc822), but
1310   this does not change how the digest is computed as defined in the
1311   preceding paragraph.
1312</t>
1313<t>
1314   There are several consequences of this. The entity-body for composite
1315   types &MAY; contain many body-parts, each with its own MIME and HTTP
1316   headers (including Content-MD5, Content-Transfer-Encoding, and
1317   Content-Encoding headers). If a body-part has a Content-Transfer-Encoding
1318   or Content-Encoding header, it is assumed that the content
1319   of the body-part has had the encoding applied, and the body-part is
1320   included in the Content-MD5 digest as is -- i.e., after the
1321   application. The Transfer-Encoding header field is not allowed within
1322   body-parts.
1323</t>
1324<t>
1325   Conversion of all line breaks to CRLF &MUST-NOT; be done before
1326   computing or checking the digest: the line break convention used in
1327   the text actually transmitted &MUST; be left unaltered when computing
1328   the digest.
1329  <list><t>
1330      <x:h>Note:</x:h> while the definition of Content-MD5 is exactly the same for
1331      HTTP as in RFC 1864 for MIME entity-bodies, there are several ways
1332      in which the application of Content-MD5 to HTTP entity-bodies
1333      differs from its application to MIME entity-bodies. One is that
1334      HTTP, unlike MIME, does not use Content-Transfer-Encoding, and
1335      does use Transfer-Encoding and Content-Encoding. Another is that
1336      HTTP more frequently uses binary content types than MIME, so it is
1337      worth noting that, in such cases, the byte order used to compute
1338      the digest is the transmission byte order defined for the type.
1339      Lastly, HTTP allows transmission of text types with any of several
1340      line break conventions and not just the canonical form using CRLF.
1341  </t></list>
1342</t>
1343</section>
1344
1345<section title="Content-Type" anchor="header.content-type">
1346  <iref primary="true" item="Content-Type header" x:for-anchor=""/>
1347  <iref primary="true" item="Headers" subitem="Content-Type" x:for-anchor=""/>
1348<t>
1349   The Content-Type entity-header field indicates the media type of the
1350   entity-body sent to the recipient or, in the case of the HEAD method,
1351   the media type that would have been sent had the request been a GET.
1352</t>
1353<figure><artwork type="abnf2616"><iref primary="true" item="Grammar" subitem="Content-Type"/>
1354    Content-Type   = "Content-Type" ":" media-type
1355</artwork></figure>
1356<t>
1357   Media types are defined in <xref target="media.types"/>. An example of the field is
1358</t>
1359<figure><artwork type="example">
1360    Content-Type: text/html; charset=ISO-8859-4
1361</artwork></figure>
1362<t>
1363   Further discussion of methods for identifying the media type of an
1364   entity is provided in <xref target="type"/>.
1365</t>
1366</section>
1367
1368</section>
1369
1370<section title="IANA Considerations" anchor="IANA.considerations">
1371<t>
1372   TBD.
1373</t>
1374</section>
1375
1376<section title="Security Considerations" anchor="security.considerations">
1377<t>
1378   This section is meant to inform application developers, information
1379   providers, and users of the security limitations in HTTP/1.1 as
1380   described by this document. The discussion does not include
1381   definitive solutions to the problems revealed, though it does make
1382   some suggestions for reducing security risks.
1383</t>
1384
1385<section title="Privacy Issues Connected to Accept Headers" anchor="privacy.issues.connected.to.accept.headers">
1386<t>
1387   Accept request-headers can reveal information about the user to all
1388   servers which are accessed. The Accept-Language header in particular
1389   can reveal information the user would consider to be of a private
1390   nature, because the understanding of particular languages is often
1391   strongly correlated to the membership of a particular ethnic group.
1392   User agents which offer the option to configure the contents of an
1393   Accept-Language header to be sent in every request are strongly
1394   encouraged to let the configuration process include a message which
1395   makes the user aware of the loss of privacy involved.
1396</t>
1397<t>
1398   An approach that limits the loss of privacy would be for a user agent
1399   to omit the sending of Accept-Language headers by default, and to ask
1400   the user whether or not to start sending Accept-Language headers to a
1401   server if it detects, by looking for any Vary response-header fields
1402   generated by the server, that such sending could improve the quality
1403   of service.
1404</t>
1405<t>
1406   Elaborate user-customized accept header fields sent in every request,
1407   in particular if these include quality values, can be used by servers
1408   as relatively reliable and long-lived user identifiers. Such user
1409   identifiers would allow content providers to do click-trail tracking,
1410   and would allow collaborating content providers to match cross-server
1411   click-trails or form submissions of individual users. Note that for
1412   many users not behind a proxy, the network address of the host
1413   running the user agent will also serve as a long-lived user
1414   identifier. In environments where proxies are used to enhance
1415   privacy, user agents ought to be conservative in offering accept
1416   header configuration options to end users. As an extreme privacy
1417   measure, proxies could filter the accept headers in relayed requests.
1418   General purpose user agents which provide a high degree of header
1419   configurability &SHOULD; warn users about the loss of privacy which can
1420   be involved.
1421</t>
1422</section>
1423
1424<section title="Content-Disposition Issues" anchor="content-disposition.issues">
1425<t>
1426   RFC 1806 <xref target="RFC1806"/>, from which the often implemented Content-Disposition
1427   (see <xref target="content-disposition"/>) header in HTTP is derived, has a number of very
1428   serious security considerations. Content-Disposition is not part of
1429   the HTTP standard, but since it is widely implemented, we are
1430   documenting its use and risks for implementors. See RFC 2183 <xref target="RFC2183"/>
1431   (which updates RFC 1806) for details.
1432</t>
1433</section>
1434
1435</section>
1436
1437<section title="Acknowledgments" anchor="ack">
1438</section>
1439</middle>
1440<back>
1441<references>
1442
1443<reference anchor="Part1">
1444   <front>
1445      <title abbrev="HTTP/1.1">HTTP/1.1, part 1: URIs, Connections, and Message Parsing</title>
1446      <author initials="R." surname="Fielding" fullname="Roy T. Fielding" role="editor">
1447         <organization abbrev="Day Software">Day Software</organization>
1448         <address><email>fielding@gbiv.com</email></address>
1449      </author>
1450      <author initials="J." surname="Gettys" fullname="Jim Gettys">
1451         <organization>One Laptop per Child</organization>
1452         <address><email>jg@laptop.org</email></address>
1453      </author>
1454      <author initials="J." surname="Mogul" fullname="Jeffrey C. Mogul">
1455         <organization abbrev="HP">Hewlett-Packard Company</organization>
1456         <address><email>JeffMogul@acm.org</email></address>
1457      </author>
1458      <author initials="H." surname="Frystyk" fullname="Henrik Frystyk Nielsen">
1459         <organization abbrev="Microsoft">Microsoft Corporation</organization>
1460         <address><email>henrikn@microsoft.com</email></address>
1461      </author>
1462      <author initials="L." surname="Masinter" fullname="Larry Masinter">
1463         <organization abbrev="Adobe Systems">Adobe Systems, Incorporated</organization>
1464         <address><email>LMM@acm.org</email></address>
1465      </author>
1466      <author initials="P." surname="Leach" fullname="Paul J. Leach">
1467         <organization abbrev="Microsoft">Microsoft Corporation</organization>
1468         <address><email>paulle@microsoft.com</email></address>
1469      </author>
1470      <author initials="T." surname="Berners-Lee" fullname="Tim Berners-Lee">
1471         <organization abbrev="W3C/MIT">World Wide Web Consortium</organization>
1472         <address><email>timbl@w3.org</email></address>
1473      </author>
1474      <author initials="Y." surname="Lafon" fullname="Yves Lafon" role="editor">
1475         <organization abbrev="W3C">World Wide Web Consortium</organization>
1476         <address><email>ylafon@w3.org</email></address>
1477      </author>
1478      <author initials="J. F." surname="Reschke" fullname="Julian F. Reschke" role="editor">
1479         <organization abbrev="greenbytes">greenbytes GmbH</organization>
1480         <address><email>julian.reschke@greenbytes.de</email></address>
1481      </author>
1482      <date month="&ID-MONTH;" year="&ID-YEAR;"/>
1483   </front>
1484   <seriesInfo name="Internet-Draft" value="draft-ietf-httpbis-p1-messaging-&ID-VERSION;"/>
1485   <x:source href="p1-messaging.xml" basename="p1-messaging"/>
1486</reference>
1487
1488<reference anchor="Part2">
1489   <front>
1490      <title abbrev="HTTP/1.1">HTTP/1.1, part 2: Message Semantics</title>
1491      <author initials="R." surname="Fielding" fullname="Roy T. Fielding" role="editor">
1492         <organization abbrev="Day Software">Day Software</organization>
1493         <address><email>fielding@gbiv.com</email></address>
1494      </author>
1495      <author initials="J." surname="Gettys" fullname="Jim Gettys">
1496         <organization>One Laptop per Child</organization>
1497         <address><email>jg@laptop.org</email></address>
1498      </author>
1499      <author initials="J." surname="Mogul" fullname="Jeffrey C. Mogul">
1500         <organization abbrev="HP">Hewlett-Packard Company</organization>
1501         <address><email>JeffMogul@acm.org</email></address>
1502      </author>
1503      <author initials="H." surname="Frystyk" fullname="Henrik Frystyk Nielsen">
1504         <organization abbrev="Microsoft">Microsoft Corporation</organization>
1505         <address><email>henrikn@microsoft.com</email></address>
1506      </author>
1507      <author initials="L." surname="Masinter" fullname="Larry Masinter">
1508         <organization abbrev="Adobe Systems">Adobe Systems, Incorporated</organization>
1509         <address><email>LMM@acm.org</email></address>
1510      </author>
1511      <author initials="P." surname="Leach" fullname="Paul J. Leach">
1512         <organization abbrev="Microsoft">Microsoft Corporation</organization>
1513         <address><email>paulle@microsoft.com</email></address>
1514      </author>
1515      <author initials="T." surname="Berners-Lee" fullname="Tim Berners-Lee">
1516         <organization abbrev="W3C/MIT">World Wide Web Consortium</organization>
1517         <address><email>timbl@w3.org</email></address>
1518      </author>
1519      <author initials="Y." surname="Lafon" fullname="Yves Lafon" role="editor">
1520         <organization abbrev="W3C">World Wide Web Consortium</organization>
1521         <address><email>ylafon@w3.org</email></address>
1522      </author>
1523      <author initials="J. F." surname="Reschke" fullname="Julian F. Reschke" role="editor">
1524         <organization abbrev="greenbytes">greenbytes GmbH</organization>
1525         <address><email>julian.reschke@greenbytes.de</email></address>
1526      </author>
1527      <date month="&ID-MONTH;" year="&ID-YEAR;"/>
1528   </front>
1529   <seriesInfo name="Internet-Draft" value="draft-ietf-httpbis-p2-semantics-&ID-VERSION;"/>
1530   <x:source href="p2-semantics.xml" basename="p2-semantics"/>
1531</reference>
1532
1533<reference anchor="Part4">
1534   <front>
1535      <title abbrev="HTTP/1.1">HTTP/1.1, part 4: Conditional Requests</title>
1536      <author initials="R." surname="Fielding" fullname="Roy T. Fielding" role="editor">
1537         <organization abbrev="Day Software">Day Software</organization>
1538         <address><email>fielding@gbiv.com</email></address>
1539      </author>
1540      <author initials="J." surname="Gettys" fullname="Jim Gettys">
1541         <organization>One Laptop per Child</organization>
1542         <address><email>jg@laptop.org</email></address>
1543      </author>
1544      <author initials="J." surname="Mogul" fullname="Jeffrey C. Mogul">
1545         <organization abbrev="HP">Hewlett-Packard Company</organization>
1546         <address><email>JeffMogul@acm.org</email></address>
1547      </author>
1548      <author initials="H." surname="Frystyk" fullname="Henrik Frystyk Nielsen">
1549         <organization abbrev="Microsoft">Microsoft Corporation</organization>
1550         <address><email>henrikn@microsoft.com</email></address>
1551      </author>
1552      <author initials="L." surname="Masinter" fullname="Larry Masinter">
1553         <organization abbrev="Adobe Systems">Adobe Systems, Incorporated</organization>
1554         <address><email>LMM@acm.org</email></address>
1555      </author>
1556      <author initials="P." surname="Leach" fullname="Paul J. Leach">
1557         <organization abbrev="Microsoft">Microsoft Corporation</organization>
1558         <address><email>paulle@microsoft.com</email></address>
1559      </author>
1560      <author initials="T." surname="Berners-Lee" fullname="Tim Berners-Lee">
1561         <organization abbrev="W3C/MIT">World Wide Web Consortium</organization>
1562         <address><email>timbl@w3.org</email></address>
1563      </author>
1564      <author initials="Y." surname="Lafon" fullname="Yves Lafon" role="editor">
1565         <organization abbrev="W3C">World Wide Web Consortium</organization>
1566         <address><email>ylafon@w3.org</email></address>
1567      </author>
1568      <author initials="J. F." surname="Reschke" fullname="Julian F. Reschke" role="editor">
1569         <organization abbrev="greenbytes">greenbytes GmbH</organization>
1570         <address><email>julian.reschke@greenbytes.de</email></address>
1571      </author>
1572      <date month="&ID-MONTH;" year="&ID-YEAR;"/>
1573   </front>
1574   <seriesInfo name="Internet-Draft" value="draft-ietf-httpbis-p4-conditional-&ID-VERSION;"/>
1575   <x:source href="p4-conditional.xml" basename="p4-conditional"/>
1576</reference>
1577
1578<reference anchor="Part5">
1579   <front>
1580      <title abbrev="HTTP/1.1">HTTP/1.1, part 5: Range Requests and Partial Responses</title>
1581      <author initials="R." surname="Fielding" fullname="Roy T. Fielding" role="editor">
1582         <organization abbrev="Day Software">Day Software</organization>
1583         <address><email>fielding@gbiv.com</email></address>
1584      </author>
1585      <author initials="J." surname="Gettys" fullname="Jim Gettys">
1586         <organization>One Laptop per Child</organization>
1587         <address><email>jg@laptop.org</email></address>
1588      </author>
1589      <author initials="J." surname="Mogul" fullname="Jeffrey C. Mogul">
1590         <organization abbrev="HP">Hewlett-Packard Company</organization>
1591         <address><email>JeffMogul@acm.org</email></address>
1592      </author>
1593      <author initials="H." surname="Frystyk" fullname="Henrik Frystyk Nielsen">
1594         <organization abbrev="Microsoft">Microsoft Corporation</organization>
1595         <address><email>henrikn@microsoft.com</email></address>
1596      </author>
1597      <author initials="L." surname="Masinter" fullname="Larry Masinter">
1598         <organization abbrev="Adobe Systems">Adobe Systems, Incorporated</organization>
1599         <address><email>LMM@acm.org</email></address>
1600      </author>
1601      <author initials="P." surname="Leach" fullname="Paul J. Leach">
1602         <organization abbrev="Microsoft">Microsoft Corporation</organization>
1603         <address><email>paulle@microsoft.com</email></address>
1604      </author>
1605      <author initials="T." surname="Berners-Lee" fullname="Tim Berners-Lee">
1606         <organization abbrev="W3C/MIT">World Wide Web Consortium</organization>
1607         <address><email>timbl@w3.org</email></address>
1608      </author>
1609      <author initials="Y." surname="Lafon" fullname="Yves Lafon" role="editor">
1610         <organization abbrev="W3C">World Wide Web Consortium</organization>
1611         <address><email>ylafon@w3.org</email></address>
1612      </author>
1613      <author initials="J. F." surname="Reschke" fullname="Julian F. Reschke" role="editor">
1614         <organization abbrev="greenbytes">greenbytes GmbH</organization>
1615         <address><email>julian.reschke@greenbytes.de</email></address>
1616      </author>
1617      <date month="&ID-MONTH;" year="&ID-YEAR;"/>
1618   </front>
1619   <seriesInfo name="Internet-Draft" value="draft-ietf-httpbis-p5-range-&ID-VERSION;"/>
1620   <x:source href="p5-range.xml" basename="p5-range"/>
1621</reference>
1622
1623<reference anchor="Part6">
1624   <front>
1625      <title abbrev="HTTP/1.1">HTTP/1.1, part 6: Caching</title>
1626      <author initials="R." surname="Fielding" fullname="Roy T. Fielding" role="editor">
1627         <organization abbrev="Day Software">Day Software</organization>
1628         <address><email>fielding@gbiv.com</email></address>
1629      </author>
1630      <author initials="J." surname="Gettys" fullname="Jim Gettys">
1631         <organization>One Laptop per Child</organization>
1632         <address><email>jg@laptop.org</email></address>
1633      </author>
1634      <author initials="J." surname="Mogul" fullname="Jeffrey C. Mogul">
1635         <organization abbrev="HP">Hewlett-Packard Company</organization>
1636         <address><email>JeffMogul@acm.org</email></address>
1637      </author>
1638      <author initials="H." surname="Frystyk" fullname="Henrik Frystyk Nielsen">
1639         <organization abbrev="Microsoft">Microsoft Corporation</organization>
1640         <address><email>henrikn@microsoft.com</email></address>
1641      </author>
1642      <author initials="L." surname="Masinter" fullname="Larry Masinter">
1643         <organization abbrev="Adobe Systems">Adobe Systems, Incorporated</organization>
1644         <address><email>LMM@acm.org</email></address>
1645      </author>
1646      <author initials="P." surname="Leach" fullname="Paul J. Leach">
1647         <organization abbrev="Microsoft">Microsoft Corporation</organization>
1648         <address><email>paulle@microsoft.com</email></address>
1649      </author>
1650      <author initials="T." surname="Berners-Lee" fullname="Tim Berners-Lee">
1651         <organization abbrev="W3C/MIT">World Wide Web Consortium</organization>
1652         <address><email>timbl@w3.org</email></address>
1653      </author>
1654      <author initials="Y." surname="Lafon" fullname="Yves Lafon" role="editor">
1655         <organization abbrev="W3C">World Wide Web Consortium</organization>
1656         <address><email>ylafon@w3.org</email></address>
1657      </author>
1658      <author initials="J. F." surname="Reschke" fullname="Julian F. Reschke" role="editor">
1659         <organization abbrev="greenbytes">greenbytes GmbH</organization>
1660         <address><email>julian.reschke@greenbytes.de</email></address>
1661      </author>
1662      <date month="&ID-MONTH;" year="&ID-YEAR;"/>
1663   </front>
1664   <seriesInfo name="Internet-Draft" value="draft-ietf-httpbis-p6-cache-&ID-VERSION;"/>
1665   <x:source href="p6-cache.xml" basename="p6-cache"/>
1666</reference>
1667
1668<reference anchor="RFC2616">
1669   <front>
1670      <title>Hypertext Transfer Protocol -- HTTP/1.1</title>
1671      <author initials="R." surname="Fielding" fullname="R. Fielding">
1672         <organization>University of California, Irvine</organization>
1673         <address><email>fielding@ics.uci.edu</email></address>
1674      </author>
1675      <author initials="J." surname="Gettys" fullname="J. Gettys">
1676         <organization>W3C</organization>
1677         <address><email>jg@w3.org</email></address>
1678      </author>
1679      <author initials="J." surname="Mogul" fullname="J. Mogul">
1680         <organization>Compaq Computer Corporation</organization>
1681         <address><email>mogul@wrl.dec.com</email></address>
1682      </author>
1683      <author initials="H." surname="Frystyk" fullname="H. Frystyk">
1684         <organization>MIT Laboratory for Computer Science</organization>
1685         <address><email>frystyk@w3.org</email></address>
1686      </author>
1687      <author initials="L." surname="Masinter" fullname="L. Masinter">
1688         <organization>Xerox Corporation</organization>
1689         <address><email>masinter@parc.xerox.com</email></address>
1690      </author>
1691      <author initials="P." surname="Leach" fullname="P. Leach">
1692         <organization>Microsoft Corporation</organization>
1693         <address><email>paulle@microsoft.com</email></address>
1694      </author>
1695      <author initials="T." surname="Berners-Lee" fullname="T. Berners-Lee">
1696         <organization>W3C</organization>
1697         <address><email>timbl@w3.org</email></address>
1698      </author>
1699      <date month="June" year="1999"/>
1700   </front>
1701   <seriesInfo name="RFC" value="2616"/>
1702</reference>
1703
1704<reference anchor="RFC1766">
1705<front>
1706<title abbrev="Language Tag">Tags for the Identification of Languages</title>
1707<author initials="H." surname="Alvestrand" fullname="Harald Tveit Alvestrand">
1708<organization>UNINETT</organization>
1709<address>
1710<postal>
1711<street>Pb. 6883 Elgeseter</street>
1712<city>Trondheim</city>
1713<region/>
1714<code>N-7002</code>
1715<country>NO</country></postal>
1716<phone>+47 73 597094</phone>
1717<email>Harald.T.Alvestrand@uninett.no</email></address></author>
1718<date month="March" year="1995"/>
1719</front>
1720<seriesInfo name="RFC" value="1766"/>
1721</reference>
1722
1723<reference anchor="RFC2045">
1724<front>
1725<title abbrev="Internet Message Bodies">Multipurpose Internet Mail Extensions (MIME) Part One: Format of Internet Message Bodies</title>
1726<author initials="N." surname="Freed" fullname="Ned Freed">
1727<organization>Innosoft International, Inc.</organization>
1728<address>
1729<postal>
1730<street>1050 East Garvey Avenue South</street>
1731<city>West Covina</city>
1732<region>CA</region>
1733<code>91790</code>
1734<country>US</country></postal>
1735<phone>+1 818 919 3600</phone>
1736<facsimile>+1 818 919 3614</facsimile>
1737<email>ned@innosoft.com</email></address></author>
1738<author initials="N.S." surname="Borenstein" fullname="Nathaniel S. Borenstein">
1739<organization>First Virtual Holdings</organization>
1740<address>
1741<postal>
1742<street>25 Washington Avenue</street>
1743<city>Morristown</city>
1744<region>NJ</region>
1745<code>07960</code>
1746<country>US</country></postal>
1747<phone>+1 201 540 8967</phone>
1748<facsimile>+1 201 993 3032</facsimile>
1749<email>nsb@nsb.fv.com</email></address></author>
1750<date month="November" year="1996"/>
1751</front>
1752<seriesInfo name="RFC" value="2045"/>
1753</reference>
1754
1755<reference anchor="RFC822">
1756<front>
1757<title abbrev="Standard for ARPA Internet Text Messages">Standard for the format of ARPA Internet text messages</title>
1758<author initials="D.H." surname="Crocker" fullname="David H. Crocker">
1759<organization>University of Delaware, Dept. of Electrical Engineering</organization>
1760<address>
1761<postal>
1762<street/>
1763<city>Newark</city>
1764<region>DE</region>
1765<code>19711</code>
1766<country>US</country></postal>
1767<email>DCrocker@UDel-Relay</email></address></author>
1768<date month="August" day="13" year="1982"/></front>
1769<seriesInfo name="STD" value="11"/>
1770<seriesInfo name="RFC" value="822"/>
1771</reference>
1772
1773<reference anchor="RFC1867">
1774<front>
1775<title>Form-based File Upload in HTML</title>
1776<author initials="L." surname="Masinter" fullname="Larry Masinter">
1777<organization>Xerox Palo Alto Research Center</organization>
1778<address>
1779<postal>
1780<street>3333 Coyote Hill Road</street>
1781<city>Palo Alto</city>
1782<region>CA</region>
1783<code>94304</code>
1784<country>US</country></postal>
1785<phone>+1 415 812 4365</phone>
1786<facsimile>+1 415 812 4333</facsimile>
1787<email>masinter@parc.xerox.com</email></address></author>
1788<author initials="E." surname="Nebel" fullname="Ernesto Nebel">
1789<organization>XSoft, Xerox Corporation</organization>
1790<address>
1791<postal>
1792<street>10875 Rancho Bernardo Road</street>
1793<street>Suite 200</street>
1794<city>San Diego</city>
1795<region>CA</region>
1796<code>92127-2116</code>
1797<country>US</country></postal>
1798<phone>+1 619 676 7817</phone>
1799<facsimile>+1 619 676 7865</facsimile>
1800<email>nebel@xsoft.sd.xerox.com</email></address></author>
1801<date month="November" year="1995"/>
1802</front>
1803<seriesInfo name="RFC" value="1867"/>
1804</reference>
1805
1806<reference anchor="RFC4288">
1807  <front>
1808    <title>Media Type Specifications and Registration Procedures</title>
1809    <author initials="N." surname="Freed" fullname="N. Freed">
1810      <organization>Sun Microsystems</organization>
1811      <address>
1812        <email>ned.freed@mrochek.com</email>
1813      </address>
1814    </author>
1815    <author initials="J." surname="Klensin" fullname="J. Klensin">
1816      <organization/>
1817      <address>
1818        <email>klensin+ietf@jck.com</email>
1819      </address>
1820    </author>
1821    <date year="2005" month="December"/>
1822  </front>
1823  <seriesInfo name="BCP" value="13"/>
1824  <seriesInfo name="RFC" value="4288"/>
1825</reference>
1826
1827<reference anchor="RFC1864">
1828<front>
1829<title abbrev="Content-MD5 Header Field">The Content-MD5 Header Field</title>
1830<author initials="J." surname="Myers" fullname="John G. Myers">
1831<organization>Carnegie Mellon University</organization>
1832<address>
1833<phone/>
1834<email>jgm+@cmu.edu</email></address></author>
1835<author initials="M." surname="Rose" fullname="Marshall T. Rose">
1836<organization>Dover Beach Consulting, Inc.</organization>
1837<address>
1838<phone/>
1839<email>mrose@dbc.mtview.ca.us</email></address></author>
1840<date month="October" year="1995"/>
1841</front>
1842<seriesInfo name="RFC" value="1864"/>
1843</reference>
1844
1845
1846<reference anchor="RFC1952">
1847<front>
1848<title>GZIP file format specification version 4.3</title>
1849<author initials="P." surname="Deutsch" fullname="L. Peter Deutsch">
1850<organization>Aladdin Enterprises</organization>
1851<address>
1852<postal>
1853<street>203 Santa Margarita Ave.</street>
1854<city>Menlo Park</city>
1855<region>CA</region>
1856<code>94025</code>
1857<country>US</country></postal>
1858<phone>+1 415 322 0103</phone>
1859<facsimile>+1 415 322 1734</facsimile>
1860<email>ghost@aladdin.com</email></address></author>
1861<author initials="J-L." surname="Gailly" fullname="Jean-Loup Gailly">
1862<organization/>
1863<address>
1864<postal>
1865<street/>
1866<city/>
1867<region/>
1868<code/>
1869<country/></postal>
1870<phone/>
1871<email>gzip@prep.ai.mit.edu</email></address></author>
1872<author initials="M." surname="Adler" fullname="Mark Adler">
1873<organization/>
1874<address>
1875<postal>
1876<street/>
1877<city/>
1878<region/>
1879<code/>
1880<country/></postal>
1881<phone/>
1882<email>madler@alumni.caltech.edu</email></address></author>
1883<author initials="L.P." surname="Deutsch" fullname="L. Peter Deutsch">
1884<organization/>
1885<address>
1886<postal>
1887<street/>
1888<city/>
1889<region/>
1890<code/>
1891<country/></postal>
1892<phone/>
1893<email>ghost@aladdin.com</email></address></author>
1894<author initials="G." surname="Randers-Pehrson" fullname="Glenn Randers-Pehrson">
1895<organization/>
1896<address>
1897<postal>
1898<street/>
1899<city/>
1900<region/>
1901<code/>
1902<country/></postal>
1903<phone/>
1904<email>randeg@alumni.rpi.edu</email></address></author>
1905<date month="May" year="1996"/>
1906</front>
1907<seriesInfo name="RFC" value="1952"/>
1908</reference>
1909
1910<reference anchor="RFC1951">
1911<front>
1912<title>DEFLATE Compressed Data Format Specification version 1.3</title>
1913<author initials="P." surname="Deutsch" fullname="L. Peter Deutsch">
1914<organization>Aladdin Enterprises</organization>
1915<address>
1916<postal>
1917<street>203 Santa Margarita Ave.</street>
1918<city>Menlo Park</city>
1919<region>CA</region>
1920<code>94025</code>
1921<country>US</country></postal>
1922<phone>+1 415 322 0103</phone>
1923<facsimile>+1 415 322 1734</facsimile>
1924<email>ghost@aladdin.com</email></address></author>
1925<date month="May" year="1996"/>
1926<abstract>
1927<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>
1928<seriesInfo name="RFC" value="1951"/>
1929</reference>
1930
1931<reference anchor="RFC1950">
1932<front>
1933<title>ZLIB Compressed Data Format Specification version 3.3</title>
1934<author initials="L.P." surname="Deutsch" fullname="L. Peter Deutsch">
1935<organization>Aladdin Enterprises</organization>
1936<address>
1937<postal>
1938<street>203 Santa Margarita Ave.</street>
1939<city>Menlo Park</city>
1940<region>CA</region>
1941<code>94025</code>
1942<country>US</country></postal>
1943<phone>+1 415 322 0103</phone>
1944<facsimile>+1 415 322 1734</facsimile>
1945<email>ghost@aladdin.com</email></address></author>
1946<author initials="J-L." surname="Gailly" fullname="Jean-Loup Gailly">
1947<organization/></author>
1948<date month="May" year="1996"/>
1949<abstract>
1950<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
1951   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>
1952<seriesInfo name="RFC" value="1950"/>
1953</reference>
1954
1955<reference anchor="RFC2068">
1956<front>
1957<title abbrev="HTTP/1.1">Hypertext Transfer Protocol -- HTTP/1.1</title>
1958<author initials="R." surname="Fielding" fullname="Roy T. Fielding">
1959<organization>University of California, Irvine, Department of Information and Computer Science</organization>
1960<address>
1961<postal>
1962<street/>
1963<city>Irvine</city>
1964<region>CA</region>
1965<code>92717-3425</code>
1966<country>US</country></postal>
1967<facsimile>+1 714 824 4056</facsimile>
1968<email>fielding@ics.uci.edu</email></address></author>
1969<author initials="J." surname="Gettys" fullname="Jim Gettys">
1970<organization>MIT Laboratory for Computer Science</organization>
1971<address>
1972<postal>
1973<street>545 Technology Square</street>
1974<city>Cambridge</city>
1975<region>MA</region>
1976<code>02139</code>
1977<country>US</country></postal>
1978<facsimile>+1 617 258 8682</facsimile>
1979<email>jg@w3.org</email></address></author>
1980<author initials="J." surname="Mogul" fullname="Jeffrey C. Mogul">
1981<organization>Digital Equipment Corporation, Western Research Laboratory</organization>
1982<address>
1983<postal>
1984<street>250 University Avenue</street>
1985<city>Palo Alto</city>
1986<region>CA</region>
1987<code>94301</code>
1988<country>US</country></postal>
1989<email>mogul@wrl.dec.com</email></address></author>
1990<author initials="H." surname="Nielsen" fullname="Henrik Frystyk Nielsen">
1991<organization>MIT Laboratory for Computer Science</organization>
1992<address>
1993<postal>
1994<street>545 Technology Square</street>
1995<city>Cambridge</city>
1996<region>MA</region>
1997<code>02139</code>
1998<country>US</country></postal>
1999<facsimile>+1 617 258 8682</facsimile>
2000<email>frystyk@w3.org</email></address></author>
2001<author initials="T." surname="Berners-Lee" fullname="Tim Berners-Lee">
2002<organization>MIT Laboratory for Computer Science</organization>
2003<address>
2004<postal>
2005<street>545 Technology Square</street>
2006<city>Cambridge</city>
2007<region>MA</region>
2008<code>02139</code>
2009<country>US</country></postal>
2010<facsimile>+1 617 258 8682</facsimile>
2011<email>timbl@w3.org</email></address></author>
2012<date month="January" year="1997"/>
2013<abstract>
2014<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>
2015<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>
2016<seriesInfo name="RFC" value="2068"/>
2017</reference>
2018
2019<reference anchor="RFC1806">
2020<front>
2021<title abbrev="Content-Disposition">Communicating Presentation Information in Internet Messages: The Content-Disposition Header</title>
2022<author initials="R." surname="Troost" fullname="Rens Troost">
2023<organization>New Century Systems</organization>
2024<address>
2025<postal>
2026<street>324 East 41st Street #804</street>
2027<city>New York</city>
2028<region>NY</region>
2029<code>10017</code>
2030<country>US</country></postal>
2031<phone>+1 212 557 2050</phone>
2032<facsimile>+1 212 557 2049</facsimile>
2033<email>rens@century.com</email></address></author>
2034<author initials="S." surname="Dorner" fullname="Steve Dorner">
2035<organization>QUALCOMM Incorporated</organization>
2036<address>
2037<postal>
2038<street>6455 Lusk Boulevard</street>
2039<city>San Diego</city>
2040<region>CA</region>
2041<code>92121</code>
2042<country>US</country></postal>
2043<email>sdorner@qualcomm.com</email></address></author>
2044<date month="June" year="1995"/>
2045<abstract>
2046<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>
2047<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>
2048<seriesInfo name="RFC" value="1806"/>
2049</reference>
2050
2051<reference anchor="RFC2076">
2052<front>
2053<title abbrev="Internet Message Headers">Common Internet Message Headers</title>
2054<author initials="J." surname="Palme" fullname="Jacob Palme">
2055<organization>Stockholm University/KTH</organization>
2056<address>
2057<postal>
2058<street>Electrum 230</street>
2059<street>S-164 40 Kista</street>
2060<country>SE</country></postal>
2061<phone>+46 8 161667</phone>
2062<facsimile>+46 8 7830829</facsimile>
2063<email>jpalme@dsv.su.se</email></address></author>
2064<date month="February" year="1997"/>
2065<abstract>
2066<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>
2067<seriesInfo name="RFC" value="2076"/>
2068</reference>
2069
2070<reference anchor="RFC2279">
2071<front>
2072<title abbrev="UTF-8">UTF-8, a transformation format of ISO 10646</title>
2073<author initials="F." surname="Yergeau" fullname="Francois Yergeau">
2074<organization>Alis Technologies</organization>
2075<address>
2076<postal>
2077<street>100, boul. Alexis-Nihon</street>
2078<street>Suite 600</street>
2079<city>Montreal</city>
2080<region>Quebec</region>
2081<code>H4M 2P2</code>
2082<country>CA</country></postal>
2083<phone>+1 514 747 2547</phone>
2084<facsimile>+1 514 747 2561</facsimile>
2085<email>fyergeau@alis.com</email></address></author>
2086<date month="January" year="1998"/>
2087<abstract>
2088<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>
2089<seriesInfo name="RFC" value="2279"/>
2090</reference>
2091
2092<reference anchor="RFC2046">
2093<front>
2094<title abbrev="Media Types">Multipurpose Internet Mail Extensions (MIME) Part Two: Media Types</title>
2095<author initials="N." surname="Freed" fullname="Ned Freed">
2096<organization>Innosoft International, Inc.</organization>
2097<address>
2098<postal>
2099<street>1050 East Garvey Avenue South</street>
2100<city>West Covina</city>
2101<region>CA</region>
2102<code>91790</code>
2103<country>US</country></postal>
2104<phone>+1 818 919 3600</phone>
2105<facsimile>+1 818 919 3614</facsimile>
2106<email>ned@innosoft.com</email></address></author>
2107<author initials="N." surname="Borenstein" fullname="Nathaniel S. Borenstein">
2108<organization>First Virtual Holdings</organization>
2109<address>
2110<postal>
2111<street>25 Washington Avenue</street>
2112<city>Morristown</city>
2113<region>NJ</region>
2114<code>07960</code>
2115<country>US</country></postal>
2116<phone>+1 201 540 8967</phone>
2117<facsimile>+1 201 993 3032</facsimile>
2118<email>nsb@nsb.fv.com</email></address></author>
2119<date month="November" year="1996"/>
2120</front>
2121<seriesInfo name="RFC" value="2046"/>
2122</reference>
2123
2124<reference anchor="RFC2277">
2125<front>
2126<title abbrev="Charset Policy">IETF Policy on Character Sets and Languages</title>
2127<author initials="H.T." surname="Alvestrand" fullname="Harald Tveit Alvestrand">
2128<organization>UNINETT</organization>
2129<address>
2130<postal>
2131<street>P.O.Box 6883 Elgeseter</street>
2132<street>N-7002 TRONDHEIM</street>
2133<country>NORWAY</country></postal>
2134<phone>+47 73 59 70 94</phone>
2135<email>Harald.T.Alvestrand@uninett.no</email></address></author>
2136<date month="January" year="1998"/>
2137<area>Applications</area>
2138<keyword>Internet Engineering Task Force</keyword>
2139<keyword>character encoding</keyword></front>
2140<seriesInfo name="BCP" value="18"/>
2141<seriesInfo name="RFC" value="2277"/>
2142</reference>
2143
2144<reference anchor="RFC2110">
2145<front>
2146<title abbrev="MHTML">MIME E-mail Encapsulation of Aggregate Documents, such as HTML (MHTML)</title>
2147<author initials="J." surname="Palme" fullname="Jacob Palme">
2148<organization>Stockholm University and KTH</organization>
2149<address>
2150<postal>
2151<street>Electrum 230</street>
2152<street>S-164 40 Kista</street>
2153<country>Sweden</country></postal>
2154<phone>+46-8-16 16 67</phone>
2155<facsimile>+46-8-783 08 29</facsimile>
2156<email>jpalme@dsv.su.se</email></address></author>
2157<author initials="A." surname="Hopmann" fullname="Alex Hopmann">
2158<organization>Microsoft Corporation</organization>
2159<address>
2160<postal>
2161<street>3590 North First Street</street>
2162<street>Suite 300</street>
2163<street>San Jose</street>
2164<street>CA 95134</street>
2165<street>Working group chairman:</street></postal>
2166<email>alexhop@microsoft.com</email></address></author>
2167<date month="March" year="1997"/>
2168<area>Applications</area>
2169<keyword>encapsulate</keyword>
2170<keyword>hypertext markup language</keyword>
2171<keyword>mail</keyword>
2172<keyword>multipurpose internet mail extensions</keyword>
2173</front>
2174<seriesInfo name="RFC" value="2110"/>
2175</reference>
2176
2177<reference anchor="RFC2049">
2178<front>
2179<title abbrev="MIME Conformance">Multipurpose Internet Mail Extensions (MIME) Part Five: Conformance Criteria and Examples</title>
2180<author initials="N." surname="Freed" fullname="Ned Freed">
2181<organization>Innosoft International, Inc.</organization>
2182<address>
2183<postal>
2184<street>1050 East Garvey Avenue South</street>
2185<street>West Covina</street>
2186<street>CA 91790</street>
2187<country>USA</country></postal>
2188<phone>+1 818 919 3600</phone>
2189<facsimile>+1 818 919 3614</facsimile>
2190<email>ned@innosoft.com</email></address></author>
2191<author initials="N.S." surname="Borenstein" fullname="Nathaniel S. Borenstein">
2192<organization>First Virtual Holdings</organization>
2193<address>
2194<postal>
2195<street>25 Washington Avenue</street>
2196<street>Morristown</street>
2197<street>NJ 07960</street>
2198<country>USA</country></postal>
2199<phone>+1 201 540 8967</phone>
2200<facsimile>+1 201 993 3032</facsimile>
2201<email>nsb@nsb.fv.com</email></address></author>
2202<date month="November" year="1996"/>
2203<area>Applications</area>
2204<keyword>mail</keyword>
2205<keyword>multipurpose internet mail extensions</keyword>
2206</front>
2207<seriesInfo name="RFC" value="2049"/>
2208</reference>
2209
2210<reference anchor="RFC2183">
2211<front>
2212<title abbrev="Content-Disposition">Communicating Presentation Information in Internet Messages: The Content-Disposition Header Field</title>
2213<author initials="R." surname="Troost" fullname="Rens Troost">
2214<organization>New Century Systems</organization>
2215<address>
2216<postal>
2217<street>324 East 41st Street #804</street>
2218<street>New York</street>
2219<street>NY</street>
2220<street>10017</street>
2221<country>USA</country></postal>
2222<phone>+1 (212) 557-2050</phone>
2223<facsimile>+1 (212) 557-2049</facsimile>
2224<email>rens@century.com</email></address></author>
2225<author initials="S." surname="Dorner" fullname="Steve Dorner">
2226<organization>QUALCOMM Incorporated</organization>
2227<address>
2228<postal>
2229<street>6455 Lusk Boulevard</street>
2230<street>San Diego</street>
2231<street>CA 92121</street>
2232<country>USA</country></postal>
2233<email>sdorner@qualcomm.com</email></address></author>
2234<author initials="K." surname="Moore" fullname="Keith Moore">
2235<organization>Department of Computer Science</organization>
2236<address>
2237<postal>
2238<street>University of Tennessee</street>
2239<street>Knoxville</street>
2240<street>107 Ayres Hall</street>
2241<street>Knoxville TN  37996-1301</street>
2242<country>USA</country></postal>
2243<phone>+1 (423) 974-5067</phone>
2244<facsimile>+1 (423) 974-8296</facsimile>
2245<email>moore@cs.utk.edu</email></address></author>
2246<date month="August" year="1997"/>
2247<area>Applications</area>
2248<keyword>MIME</keyword>
2249<keyword>internet message</keyword>
2250<keyword>multipurpose internet mail extensions</keyword>
2251</front>
2252<seriesInfo name="RFC" value="2183"/>
2253</reference>
2254
2255</references>
2256
2257<section title="Differences Between HTTP Entities and RFC 2045 Entities" anchor="differences.between.http.entities.and.rfc.2045.entities">
2258<t>
2259   HTTP/1.1 uses many of the constructs defined for Internet Mail (RFC
2260   822 <xref target="RFC822"/>) and the Multipurpose Internet Mail Extensions (MIME <xref target="RFC2045"/>) to
2261   allow entities to be transmitted in an open variety of
2262   representations and with extensible mechanisms. However, RFC 2045
2263   discusses mail, and HTTP has a few features that are different from
2264   those described in RFC 2045. These differences were carefully chosen
2265   to optimize performance over binary connections, to allow greater
2266   freedom in the use of new media types, to make date comparisons
2267   easier, and to acknowledge the practice of some early HTTP servers
2268   and clients.
2269</t>
2270<t>
2271   This appendix describes specific areas where HTTP differs from RFC
2272   2045. Proxies and gateways to strict MIME environments &SHOULD; be
2273   aware of these differences and provide the appropriate conversions
2274   where necessary. Proxies and gateways from MIME environments to HTTP
2275   also need to be aware of the differences because some conversions
2276   might be required.
2277</t>
2278<section title="MIME-Version" anchor="mime-version">
2279<t>
2280   HTTP is not a MIME-compliant protocol. However, HTTP/1.1 messages &MAY;
2281   include a single MIME-Version general-header field to indicate what
2282   version of the MIME protocol was used to construct the message. Use
2283   of the MIME-Version header field indicates that the message is in
2284   full compliance with the MIME protocol (as defined in RFC 2045<xref target="RFC2045"/>).
2285   Proxies/gateways are responsible for ensuring full compliance (where
2286   possible) when exporting HTTP messages to strict MIME environments.
2287</t>
2288<figure><artwork type="abnf2616"><iref primary="true" item="Grammar" subitem="MIME-Version"/>
2289    MIME-Version   = "MIME-Version" ":" 1*DIGIT "." 1*DIGIT
2290</artwork></figure>
2291<t>
2292   MIME version "1.0" is the default for use in HTTP/1.1. However,
2293   HTTP/1.1 message parsing and semantics are defined by this document
2294   and not the MIME specification.
2295</t>
2296</section>
2297
2298<section title="Conversion to Canonical Form" anchor="conversion.to.canonical.form">
2299<t>
2300   RFC 2045 <xref target="RFC2045"/> requires that an Internet mail entity be converted to
2301   canonical form prior to being transferred, as described in section <xref target="RFC2049" x:fmt="number" x:sec="4"/>
2302   of RFC 2049 <xref target="RFC2049"/>. <xref target="canonicalization.and.text.defaults"/> of this document describes the forms
2303   allowed for subtypes of the "text" media type when transmitted over
2304   HTTP. RFC 2046 requires that content with a type of "text" represent
2305   line breaks as CRLF and forbids the use of CR or LF outside of line
2306   break sequences. HTTP allows CRLF, bare CR, and bare LF to indicate a
2307   line break within text content when a message is transmitted over
2308   HTTP.
2309</t>
2310<t>
2311   Where it is possible, a proxy or gateway from HTTP to a strict MIME
2312   environment &SHOULD; translate all line breaks within the text media
2313   types described in <xref target="canonicalization.and.text.defaults"/> of this document to the RFC 2049
2314   canonical form of CRLF. Note, however, that this might be complicated
2315   by the presence of a Content-Encoding and by the fact that HTTP
2316   allows the use of some character sets which do not use octets 13 and
2317   10 to represent CR and LF, as is the case for some multi-byte
2318   character sets.
2319</t>
2320<t>
2321   Implementors should note that conversion will break any cryptographic
2322   checksums applied to the original content unless the original content
2323   is already in canonical form. Therefore, the canonical form is
2324   recommended for any content that uses such checksums in HTTP.
2325</t>
2326</section>
2327
2328<section title="Introduction of Content-Encoding" anchor="introduction.of.content-encoding">
2329<t>
2330   RFC 2045 does not include any concept equivalent to HTTP/1.1's
2331   Content-Encoding header field. Since this acts as a modifier on the
2332   media type, proxies and gateways from HTTP to MIME-compliant
2333   protocols &MUST; either change the value of the Content-Type header
2334   field or decode the entity-body before forwarding the message. (Some
2335   experimental applications of Content-Type for Internet mail have used
2336   a media-type parameter of ";conversions=&lt;content-coding&gt;" to perform
2337   a function equivalent to Content-Encoding. However, this parameter is
2338   not part of RFC 2045).
2339</t>
2340</section>
2341
2342<section title="No Content-Transfer-Encoding" anchor="no.content-transfer-encoding">
2343<t>
2344   HTTP does not use the Content-Transfer-Encoding field of RFC
2345   2045. Proxies and gateways from MIME-compliant protocols to HTTP &MUST;
2346   remove any Content-Transfer-Encoding
2347   prior to delivering the response message to an HTTP client.
2348</t>
2349<t>
2350   Proxies and gateways from HTTP to MIME-compliant protocols are
2351   responsible for ensuring that the message is in the correct format
2352   and encoding for safe transport on that protocol, where "safe
2353   transport" is defined by the limitations of the protocol being used.
2354   Such a proxy or gateway &SHOULD; label the data with an appropriate
2355   Content-Transfer-Encoding if doing so will improve the likelihood of
2356   safe transport over the destination protocol.
2357</t>
2358</section>
2359
2360<section title="Introduction of Transfer-Encoding" anchor="introduction.of.transfer-encoding">
2361<t>
2362   HTTP/1.1 introduces the Transfer-Encoding header field (&header-transfer-encoding;).
2363   Proxies/gateways &MUST; remove any transfer-coding prior to
2364   forwarding a message via a MIME-compliant protocol.
2365</t>
2366</section>
2367
2368<section title="MHTML and Line Length Limitations" anchor="mhtml.line.length">
2369<t>
2370   HTTP implementations which share code with MHTML <xref target="RFC2110"/> implementations
2371   need to be aware of MIME line length limitations. Since HTTP does not
2372   have this limitation, HTTP does not fold long lines. MHTML messages
2373   being transported by HTTP follow all conventions of MHTML, including
2374   line length limitations and folding, canonicalization, etc., since
2375   HTTP transports all message-bodies as payload (see <xref target="multipart.types"/>) and
2376   does not interpret the content or any MIME header lines that might be
2377   contained therein.
2378</t>
2379</section>
2380</section>
2381
2382<section title="Additional Features" anchor="additional.features">
2383<t>
2384   RFC 1945 and RFC 2068 document protocol elements used by some
2385   existing HTTP implementations, but not consistently and correctly
2386   across most HTTP/1.1 applications. Implementors are advised to be
2387   aware of these features, but cannot rely upon their presence in, or
2388   interoperability with, other HTTP/1.1 applications. Some of these
2389   describe proposed experimental features, and some describe features
2390   that experimental deployment found lacking that are now addressed in
2391   the base HTTP/1.1 specification.
2392</t>
2393<t>
2394   A number of other headers, such as Content-Disposition and Title,
2395   from SMTP and MIME are also often implemented (see RFC 2076 <xref target="RFC2076"/>).
2396</t>
2397
2398<section title="Content-Disposition" anchor="content-disposition">
2399<iref item="Headers" subitem="Content-Disposition" primary="true" x:for-anchor=""/>
2400<iref item="Content-Disposition header" primary="true" x:for-anchor=""/>
2401<t>
2402   The Content-Disposition response-header field has been proposed as a
2403   means for the origin server to suggest a default filename if the user
2404   requests that the content is saved to a file. This usage is derived
2405   from the definition of Content-Disposition in RFC 1806 <xref target="RFC1806"/>.
2406</t>
2407<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"/>
2408     content-disposition = "Content-Disposition" ":"
2409                           disposition-type *( ";" disposition-parm )
2410     disposition-type = "attachment" | disp-extension-token
2411     disposition-parm = filename-parm | disp-extension-parm
2412     filename-parm = "filename" "=" quoted-string
2413     disp-extension-token = token
2414     disp-extension-parm = token "=" ( token | quoted-string )
2415</artwork></figure>
2416<t>
2417   An example is
2418</t>
2419<figure><artwork type="example">
2420     Content-Disposition: attachment; filename="fname.ext"
2421</artwork></figure>
2422<t>
2423   The receiving user agent &SHOULD-NOT;  respect any directory path
2424   information present in the filename-parm parameter, which is the only
2425   parameter believed to apply to HTTP implementations at this time. The
2426   filename &SHOULD; be treated as a terminal component only.
2427</t>
2428<t>
2429   If this header is used in a response with the application/octet-stream
2430   content-type, the implied suggestion is that the user agent
2431   should not display the response, but directly enter a `save response
2432   as...' dialog.
2433</t>
2434<t>
2435   See <xref target="content-disposition.issues"/> for Content-Disposition security issues.
2436</t>
2437</section>
2438</section>
2439
2440<section title="Changes from RFC 2068" anchor="changes.from.rfc.2068">
2441<t>
2442   Charset wildcarding is introduced to avoid explosion of character set
2443   names in accept headers. (<xref target="header.accept-charset"/>)
2444</t>
2445<t>
2446   Content-Base was deleted from the specification: it was not
2447   implemented widely, and there is no simple, safe way to introduce it
2448   without a robust extension mechanism. In addition, it is used in a
2449   similar, but not identical fashion in MHTML <xref target="RFC2110"/>.
2450</t>
2451<t>
2452   A content-coding of "identity" was introduced, to solve problems
2453   discovered in caching. (<xref target="content.codings"/>)
2454</t>
2455<t>
2456   Quality Values of zero should indicate that "I don't want something"
2457   to allow clients to refuse a representation. (<xref target="quality.values"/>)
2458</t>
2459<t>
2460   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
2461   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
2462   specification, but not commonly implemented. See RFC 2068 <xref target="RFC2068"/>.
2463</t>
2464</section>
2465</back>
2466</rfc>
Note: See TracBrowser for help on using the repository browser.