source: draft-ietf-httpbis/latest/p3-payload.xml @ 116

Last change on this file since 116 was 116, checked in by julian.reschke@…, 12 years ago

Add information about changes since -00.

  • Property svn:eol-style set to native
File size: 104.5 KB
Line 
1<?xml version="1.0" encoding="utf-8"?>
2<?xml-stylesheet type='text/xsl' href='../myxml2rfc.xslt'?>
3<!DOCTYPE rfc [
4  <!ENTITY MAY "<bcp14 xmlns='http://purl.org/net/xml2rfc/ext'>MAY</bcp14>">
5  <!ENTITY MUST "<bcp14 xmlns='http://purl.org/net/xml2rfc/ext'>MUST</bcp14>">
6  <!ENTITY MUST-NOT "<bcp14 xmlns='http://purl.org/net/xml2rfc/ext'>MUST NOT</bcp14>">
7  <!ENTITY OPTIONAL "<bcp14 xmlns='http://purl.org/net/xml2rfc/ext'>OPTIONAL</bcp14>">
8  <!ENTITY RECOMMENDED "<bcp14 xmlns='http://purl.org/net/xml2rfc/ext'>RECOMMENDED</bcp14>">
9  <!ENTITY REQUIRED "<bcp14 xmlns='http://purl.org/net/xml2rfc/ext'>REQUIRED</bcp14>">
10  <!ENTITY SHALL "<bcp14 xmlns='http://purl.org/net/xml2rfc/ext'>SHALL</bcp14>">
11  <!ENTITY SHALL-NOT "<bcp14 xmlns='http://purl.org/net/xml2rfc/ext'>SHALL NOT</bcp14>">
12  <!ENTITY SHOULD "<bcp14 xmlns='http://purl.org/net/xml2rfc/ext'>SHOULD</bcp14>">
13  <!ENTITY SHOULD-NOT "<bcp14 xmlns='http://purl.org/net/xml2rfc/ext'>SHOULD NOT</bcp14>">
14  <!ENTITY ID-VERSION "latest">
15  <!ENTITY ID-MONTH "December">
16  <!ENTITY ID-YEAR "2007">
17  <!ENTITY caching-neg-resp         "<xref target='Part6' x:rel='#caching.negotiated.responses' xmlns:x='http://purl.org/net/xml2rfc/ext'/>">
18  <!ENTITY header-transfer-encoding "<xref target='Part1' x:rel='#header.transfer-encoding' xmlns:x='http://purl.org/net/xml2rfc/ext'/>">
19  <!ENTITY header-allow             "<xref target='Part2' x:rel='#header.allow' xmlns:x='http://purl.org/net/xml2rfc/ext'/>">
20  <!ENTITY header-content-length    "<xref target='Part1' x:rel='#header.content-length' xmlns:x='http://purl.org/net/xml2rfc/ext'/>">
21  <!ENTITY header-content-range     "<xref target='Part5' x:rel='#header.content-range' xmlns:x='http://purl.org/net/xml2rfc/ext'/>">
22  <!ENTITY header-expires           "<xref target='Part6' x:rel='#header.expires' xmlns:x='http://purl.org/net/xml2rfc/ext'/>">
23  <!ENTITY header-last-modified     "<xref target='Part4' x:rel='#header.last-modified' xmlns:x='http://purl.org/net/xml2rfc/ext'/>">
24  <!ENTITY header-user-agent        "<xref target='Part2' x:rel='#header.user-agent' xmlns:x='http://purl.org/net/xml2rfc/ext'/>">
25  <!ENTITY header-vary              "<xref target='Part6' x:rel='#header.vary' xmlns:x='http://purl.org/net/xml2rfc/ext'/>">
26  <!ENTITY message-body             "<xref target='Part1' x:rel='#message.body' xmlns:x='http://purl.org/net/xml2rfc/ext'/>">
27  <!ENTITY message-length           "<xref target='Part1' x:rel='#message.length' xmlns:x='http://purl.org/net/xml2rfc/ext'/>">
28  <!ENTITY multipart-byteranges     "<xref target='Part5' x:rel='#internet.media.type.multipart.byteranges' xmlns:x='http://purl.org/net/xml2rfc/ext'/>">
29]>
30<?rfc toc="yes" ?>
31<?rfc symrefs="yes" ?>
32<?rfc sortrefs="yes" ?>
33<?rfc compact="yes"?>
34<?rfc subcompact="no" ?>
35<?rfc linkmailto="no" ?>
36<?rfc editing="no" ?>
37<?rfc-ext allow-markup-in-artwork="yes" ?>
38<?rfc-ext include-references-in-index="yes" ?>
39<rfc obsoletes="2068, 2616" category="std"
40     ipr="full3978" docName="draft-ietf-httpbis-p3-payload-&ID-VERSION;"
41     xmlns:x='http://purl.org/net/xml2rfc/ext' xmlns:ed="http://greenbytes.de/2002/rfcedit">
42<front>
43
44  <title abbrev="HTTP/1.1">HTTP/1.1, part 3: Message Payload and Content Negotiation</title>
45
46  <author initials="R." surname="Fielding" fullname="Roy T. Fielding" role="editor">
47    <organization abbrev="Day Software">Day Software</organization>
48    <address>
49      <postal>
50        <street>23 Corporate Plaza DR, Suite 280</street>
51        <city>Newport Beach</city>
52        <region>CA</region>
53        <code>92660</code>
54        <country>USA</country>
55      </postal>
56      <phone>+1-949-706-5300</phone>
57      <facsimile>+1-949-706-5305</facsimile>
58      <email>fielding@gbiv.com</email>
59      <uri>http://roy.gbiv.com/</uri>
60    </address>
61  </author>
62
63  <author initials="J." surname="Gettys" fullname="Jim Gettys">
64    <organization>One Laptop per Child</organization>
65    <address>
66      <postal>
67        <street>21 Oak Knoll Road</street>
68        <city>Carlisle</city>
69        <region>MA</region>
70        <code>01741</code>
71        <country>USA</country>
72      </postal>
73      <email>jg@laptop.org</email>
74      <uri>http://www.laptop.org/</uri>
75    </address>
76  </author>
77 
78  <author initials="J." surname="Mogul" fullname="Jeffrey C. Mogul">
79    <organization abbrev="HP">Hewlett-Packard Company</organization>
80    <address>
81      <postal>
82        <street>HP Labs, Large Scale Systems Group</street>
83        <street>1501 Page Mill Road, MS 1177</street>
84        <city>Palo Alto</city>
85        <region>CA</region>
86        <code>94304</code>
87        <country>USA</country>
88      </postal>
89      <email>JeffMogul@acm.org</email>
90    </address>
91  </author>
92
93  <author initials="H." surname="Frystyk" fullname="Henrik Frystyk Nielsen">
94    <organization abbrev="Microsoft">Microsoft Corporation</organization>
95    <address>
96      <postal>
97        <street>1 Microsoft Way</street>
98        <city>Redmond</city>
99        <region>WA</region>
100        <code>98052</code>
101        <country>USA</country>
102      </postal>
103      <email>henrikn@microsoft.com</email>
104    </address>
105  </author>
106
107  <author initials="L." surname="Masinter" fullname="Larry Masinter">
108    <organization abbrev="Adobe Systems">Adobe Systems, Incorporated</organization>
109    <address>
110      <postal>
111        <street>345 Park Ave</street>
112        <city>San Jose</city>
113        <region>CA</region>
114        <code>95110</code>
115        <country>USA</country>
116      </postal>
117      <email>LMM@acm.org</email>
118      <uri>http://larry.masinter.net/</uri>
119    </address>
120  </author>
121 
122  <author initials="P." surname="Leach" fullname="Paul J. Leach">
123    <organization abbrev="Microsoft">Microsoft Corporation</organization>
124    <address>
125      <postal>
126        <street>1 Microsoft Way</street>
127        <city>Redmond</city>
128        <region>WA</region>
129        <code>98052</code>
130      </postal>
131      <email>paulle@microsoft.com</email>
132    </address>
133  </author>
134   
135  <author initials="T." surname="Berners-Lee" fullname="Tim Berners-Lee">
136    <organization abbrev="W3C/MIT">World Wide Web Consortium</organization>
137    <address>
138      <postal>
139        <street>MIT Computer Science and Artificial Intelligence Laboratory</street>
140        <street>The Stata Center, Building 32</street>
141        <street>32 Vassar Street</street>
142        <city>Cambridge</city>
143        <region>MA</region>
144        <code>02139</code>
145        <country>USA</country>
146      </postal>
147      <email>timbl@w3.org</email>
148      <uri>http://www.w3.org/People/Berners-Lee/</uri>
149    </address>
150  </author>
151
152  <author initials="Y." surname="Lafon" fullname="Yves Lafon" role="editor">
153    <organization abbrev="W3C">World Wide Web Consortium</organization>
154    <address>
155      <postal>
156        <street>W3C / ERCIM</street>
157        <street>2004, rte des Lucioles</street>
158        <city>Sophia-Antipolis</city>
159        <region>AM</region>
160        <code>06902</code>
161        <country>France</country>
162      </postal>
163      <email>ylafon@w3.org</email>
164      <uri>http://www.raubacapeu.net/people/yves/</uri>
165    </address>
166  </author>
167
168  <author initials="J. F." surname="Reschke" fullname="Julian F. Reschke" role="editor">
169    <organization abbrev="greenbytes">greenbytes GmbH</organization>
170    <address>
171      <postal>
172        <street>Hafenweg 16</street>
173        <city>Muenster</city><region>NW</region><code>48155</code>
174        <country>Germany</country>
175      </postal>
176      <phone>+49 251 2807760</phone>   
177      <facsimile>+49 251 2807761</facsimile>   
178      <email>julian.reschke@greenbytes.de</email>       
179      <uri>http://greenbytes.de/tech/webdav/</uri>     
180    </address>
181  </author>
182
183  <date month="&ID-MONTH;" year="&ID-YEAR;"/>
184
185<abstract>
186<t>
187   The Hypertext Transfer Protocol (HTTP) is an application-level
188   protocol for distributed, collaborative, hypermedia information
189   systems. HTTP has been in use by the World Wide Web global information
190   initiative since 1990. This document is Part 3 of the seven-part specification
191   that defines the protocol referred to as "HTTP/1.1" and, taken together,
192   obsoletes RFC 2616.  Part 3 defines HTTP message content,
193   metadata, and content negotiation.
194</t>
195</abstract>
196
197<note title="Editorial Note (To be removed by RFC Editor)">
198  <t>
199    Discussion of this draft should take place on the HTTPBIS working group
200    mailing list (ietf-http-wg@w3.org). The current issues list is
201    at <eref target="http://www.tools.ietf.org/wg/httpbis/trac/report/11"/>
202    and related documents (including fancy diffs) can be found at
203    <eref target="http://www.tools.ietf.org/wg/httpbis/"/>.
204  </t>
205</note>
206</front>
207<middle>
208<section title="Introduction" anchor="introduction">
209<t>
210   This document will define aspects of HTTP related to the payload of
211   messages (message content), including metadata and media types, along
212   with HTTP content negotiation.  Right now it only includes the extracted
213   relevant sections of RFC 2616 without edit.
214</t>
215
216<section title="Requirements" anchor="intro.requirements">
217<t>
218   The key words "MUST", "MUST NOT", "REQUIRED", "SHALL", "SHALL NOT",
219   "SHOULD", "SHOULD NOT", "RECOMMENDED", "MAY", and "OPTIONAL" in this
220   document are to be interpreted as described in <xref target="RFC2119"/>.
221</t>
222<t>
223   An implementation is not compliant if it fails to satisfy one or more
224   of the &MUST; or &REQUIRED; level requirements for the protocols it
225   implements. An implementation that satisfies all the &MUST; or &REQUIRED;
226   level and all the &SHOULD; level requirements for its protocols is said
227   to be "unconditionally compliant"; one that satisfies all the &MUST;
228   level requirements but not all the &SHOULD; level requirements for its
229   protocols is said to be "conditionally compliant."
230</t>
231</section>
232</section>
233
234<section title="Protocol Parameters" anchor="protocol.parameters">
235
236<section title="Character Sets" anchor="character.sets">
237<t>
238   HTTP uses the same definition of the term "character set" as that
239   described for MIME:
240</t>
241<t>
242   The term "character set" is used in this document to refer to a
243   method used with one or more tables to convert a sequence of octets
244   into a sequence of characters. Note that unconditional conversion in
245   the other direction is not required, in that not all characters may
246   be available in a given character set and a character set may provide
247   more than one sequence of octets to represent a particular character.
248   This definition is intended to allow various kinds of character
249   encoding, from simple single-table mappings such as US-ASCII to
250   complex table switching methods such as those that use ISO-2022's
251   techniques. However, the definition associated with a MIME character
252   set name &MUST; fully specify the mapping to be performed from octets
253   to characters. In particular, use of external profiling information
254   to determine the exact mapping is not permitted.
255</t>
256<t><list><t>
257      <x:h>Note:</x:h> This use of the term "character set" is more commonly
258      referred to as a "character encoding." However, since HTTP and
259      MIME share the same registry, it is important that the terminology
260      also be shared.
261</t></list></t>
262<t>
263   HTTP character sets are identified by case-insensitive tokens. The
264   complete set of tokens is defined by the IANA Character Set registry
265   (<eref target="http://www.iana.org/assignments/character-sets"/>).
266</t>
267<figure><artwork type="abnf2616"><iref primary="true" item="Grammar" subitem="charset"/>
268    charset = token
269</artwork></figure>
270<t>
271   Although HTTP allows an arbitrary token to be used as a charset
272   value, any token that has a predefined value within the IANA
273   Character Set registry &MUST; represent the character set defined
274   by that registry. Applications &SHOULD; limit their use of character
275   sets to those defined by the IANA registry.
276</t>
277<t>
278   HTTP uses charset in two contexts: within an Accept-Charset request
279   header (in which the charset value is an unquoted token) and as the
280   value of a parameter in a Content-Type header (within a request or
281   response), in which case the parameter value of the charset parameter
282   may be quoted.
283</t>
284<t>
285   Implementors should be aware of IETF character set requirements <xref target="RFC2279"/>
286   <xref target="RFC2277"/>.
287</t>
288
289<section title="Missing Charset" anchor="missing.charset">
290<t>
291   Some HTTP/1.0 software has interpreted a Content-Type header without
292   charset parameter incorrectly to mean "recipient should guess."
293   Senders wishing to defeat this behavior &MAY; include a charset
294   parameter even when the charset is ISO-8859-1 and &SHOULD; do so when
295   it is known that it will not confuse the recipient.
296</t>
297<t>
298   Unfortunately, some older HTTP/1.0 clients did not deal properly with
299   an explicit charset parameter. HTTP/1.1 recipients &MUST; respect the
300   charset label provided by the sender; and those user agents that have
301   a provision to "guess" a charset &MUST; use the charset from the
302   content-type field if they support that charset, rather than the
303   recipient's preference, when initially displaying a document. See
304   <xref target="canonicalization.and.text.defaults"/>.
305</t>
306</section>
307</section>
308
309<section title="Content Codings" anchor="content.codings">
310<t>
311   Content coding values indicate an encoding transformation that has
312   been or can be applied to an entity. Content codings are primarily
313   used to allow a document to be compressed or otherwise usefully
314   transformed without losing the identity of its underlying media type
315   and without loss of information. Frequently, the entity is stored in
316   coded form, transmitted directly, and only decoded by the recipient.
317</t>
318<figure><artwork type="abnf2616"><iref primary="true" item="Grammar" subitem="content-coding"/>
319    content-coding   = token
320</artwork></figure>
321<t>
322   All content-coding values are case-insensitive. HTTP/1.1 uses
323   content-coding values in the Accept-Encoding (<xref target="header.accept-encoding"/>) and
324   Content-Encoding (<xref target="header.content-encoding"/>) header fields. Although the value
325   describes the content-coding, what is more important is that it
326   indicates what decoding mechanism will be required to remove the
327   encoding.
328</t>
329<t>
330   The Internet Assigned Numbers Authority (IANA) acts as a registry for
331   content-coding value tokens. Initially, the registry contains the
332   following tokens:
333</t>
334<t>
335   gzip<iref item="gzip"/>
336  <list>
337    <t>
338        An encoding format produced by the file compression program
339        "gzip" (GNU zip) as described in <xref target="RFC1952"/>. This format is a
340        Lempel-Ziv coding (LZ77) with a 32 bit CRC.
341    </t>
342  </list>
343</t>
344<t>
345   compress<iref item="compress"/>
346  <list><t>
347        The encoding format produced by the common UNIX file compression
348        program "compress". This format is an adaptive Lempel-Ziv-Welch
349        coding (LZW).
350</t><t>
351        Use of program names for the identification of encoding formats
352        is not desirable and is discouraged for future encodings. Their
353        use here is representative of historical practice, not good
354        design. For compatibility with previous implementations of HTTP,
355        applications &SHOULD; consider "x-gzip" and "x-compress" to be
356        equivalent to "gzip" and "compress" respectively.
357  </t></list>
358</t>
359<t>
360   deflate<iref item="deflate"/>
361  <list><t>
362        The "zlib" format defined in <xref target="RFC1950"/> in combination with
363        the "deflate" compression mechanism described in <xref target="RFC1951"/>.
364  </t></list>
365</t>
366<t>
367   identity<iref item="identity"/>
368  <list><t>
369        The default (identity) encoding; the use of no transformation
370        whatsoever. This content-coding is used only in the Accept-Encoding
371        header, and &SHOULD-NOT;  be used in the Content-Encoding
372        header.
373  </t></list>
374</t>
375<t>
376   New content-coding value tokens &SHOULD; be registered; to allow
377   interoperability between clients and servers, specifications of the
378   content coding algorithms needed to implement a new value &SHOULD; be
379   publicly available and adequate for independent implementation, and
380   conform to the purpose of content coding defined in this section.
381</t>
382</section>
383
384<section title="Media Types" anchor="media.types">
385<t>
386   HTTP uses Internet Media Types <xref target="RFC4288"/> in the Content-Type (<xref target="header.content-type"/>)
387   and Accept (<xref target="header.accept"/>) header fields in order to provide
388   open and extensible data typing and type negotiation.
389</t>
390<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"/>
391    media-type     = type "/" subtype *( ";" parameter )
392    type           = token
393    subtype        = token
394</artwork></figure>
395<t>
396   Parameters &MAY; follow the type/subtype in the form of attribute/value
397   pairs.
398</t>
399<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"/>
400    parameter               = attribute "=" value
401    attribute               = token
402    value                   = token | quoted-string
403</artwork></figure>
404<t>
405   The type, subtype, and parameter attribute names are case-insensitive.
406   Parameter values might or might not be case-sensitive,
407   depending on the semantics of the parameter name. Linear white space
408   (LWS) &MUST-NOT; be used between the type and subtype, nor between an
409   attribute and its value. The presence or absence of a parameter might
410   be significant to the processing of a media-type, depending on its
411   definition within the media type registry.
412</t>
413<t>
414   Note that some older HTTP applications do not recognize media type
415   parameters. When sending data to older HTTP applications,
416   implementations &SHOULD; only use media type parameters when they are
417   required by that type/subtype definition.
418</t>
419<t>
420   Media-type values are registered with the Internet Assigned Number
421   Authority (IANA). The media type registration process is
422   outlined in <xref target="RFC4288"/>. Use of non-registered media types is
423   discouraged.
424</t>
425
426<section title="Canonicalization and Text Defaults" anchor="canonicalization.and.text.defaults">
427<t>
428   Internet media types are registered with a canonical form. An
429   entity-body transferred via HTTP messages &MUST; be represented in the
430   appropriate canonical form prior to its transmission except for
431   "text" types, as defined in the next paragraph.
432</t>
433<t>
434   When in canonical form, media subtypes of the "text" type use CRLF as
435   the text line break. HTTP relaxes this requirement and allows the
436   transport of text media with plain CR or LF alone representing a line
437   break when it is done consistently for an entire entity-body. HTTP
438   applications &MUST; accept CRLF, bare CR, and bare LF as being
439   representative of a line break in text media received via HTTP. In
440   addition, if the text is represented in a character set that does not
441   use octets 13 and 10 for CR and LF respectively, as is the case for
442   some multi-byte character sets, HTTP allows the use of whatever octet
443   sequences are defined by that character set to represent the
444   equivalent of CR and LF for line breaks. This flexibility regarding
445   line breaks applies only to text media in the entity-body; a bare CR
446   or LF &MUST-NOT; be substituted for CRLF within any of the HTTP control
447   structures (such as header fields and multipart boundaries).
448</t>
449<t>
450   If an entity-body is encoded with a content-coding, the underlying
451   data &MUST; be in a form defined above prior to being encoded.
452</t>
453<t>
454   The "charset" parameter is used with some media types to define the
455   character set (<xref target="character.sets"/>) of the data. When no explicit charset
456   parameter is provided by the sender, media subtypes of the "text"
457   type are defined to have a default charset value of "ISO-8859-1" when
458   received via HTTP. Data in character sets other than "ISO-8859-1" or
459   its subsets &MUST; be labeled with an appropriate charset value. See
460   <xref target="missing.charset"/> for compatibility problems.
461</t>
462</section>
463
464<section title="Multipart Types" anchor="multipart.types">
465<t>
466   MIME provides for a number of "multipart" types -- encapsulations of
467   one or more entities within a single message-body. All multipart
468   types share a common syntax, as defined in <xref target="RFC2046" x:sec="5.1.1" x:fmt="of"/>,
469   and &MUST; include a boundary parameter as part of the media type
470   value. The message body is itself a protocol element and &MUST;
471   therefore use only CRLF to represent line breaks between body-parts.
472   Unlike in RFC 2046, the epilogue of any multipart message &MUST; be
473   empty; HTTP applications &MUST-NOT; transmit the epilogue (even if the
474   original multipart contains an epilogue). These restrictions exist in
475   order to preserve the self-delimiting nature of a multipart message-body,
476   wherein the "end" of the message-body is indicated by the
477   ending multipart boundary.
478</t>
479<t>
480   In general, HTTP treats a multipart message-body no differently than
481   any other media type: strictly as payload. The one exception is the
482   "multipart/byteranges" type (&multipart-byteranges;) when it appears in a 206
483   (Partial Content) response.
484   <!-- jre: re-insert removed text pointing to caching? -->
485   In all
486   other cases, an HTTP user agent &SHOULD; follow the same or similar
487   behavior as a MIME user agent would upon receipt of a multipart type.
488   The MIME header fields within each body-part of a multipart message-body
489   do not have any significance to HTTP beyond that defined by
490   their MIME semantics.
491</t>
492<t>
493   In general, an HTTP user agent &SHOULD; follow the same or similar
494   behavior as a MIME user agent would upon receipt of a multipart type.
495   If an application receives an unrecognized multipart subtype, the
496   application &MUST; treat it as being equivalent to "multipart/mixed".
497</t>
498<t><list><t>
499      <x:h>Note:</x:h> The "multipart/form-data" type has been specifically defined
500      for carrying form data suitable for processing via the POST
501      request method, as described in <xref target="RFC1867"/>.
502</t></list></t>
503</section>
504</section>
505
506<section title="Quality Values" anchor="quality.values">
507<t>
508   HTTP content negotiation (<xref target="content.negotiation"/>) uses short "floating point"
509   numbers to indicate the relative importance ("weight") of various
510   negotiable parameters.  A weight is normalized to a real number in
511   the range 0 through 1, where 0 is the minimum and 1 the maximum
512   value. If a parameter has a quality value of 0, then content with
513   this parameter is `not acceptable' for the client. HTTP/1.1
514   applications &MUST-NOT; generate more than three digits after the
515   decimal point. User configuration of these values &SHOULD; also be
516   limited in this fashion.
517</t>
518<figure><artwork type="abnf2616"><iref primary="true" item="Grammar" subitem="qvalue"/>
519    qvalue         = ( "0" [ "." 0*3DIGIT ] )
520                   | ( "1" [ "." 0*3("0") ] )
521</artwork></figure>
522<t>
523   "Quality values" is a misnomer, since these values merely represent
524   relative degradation in desired quality.
525</t>
526</section>
527
528<section title="Language Tags" anchor="language.tags">
529<t>
530   A language tag identifies a natural language spoken, written, or
531   otherwise conveyed by human beings for communication of information
532   to other human beings. Computer languages are explicitly excluded.
533   HTTP uses language tags within the Accept-Language and Content-Language
534   fields.
535</t>
536<t>
537   The syntax and registry of HTTP language tags is the same as that
538   defined by <xref target="RFC1766"/>. In summary, a language tag is composed of 1
539   or more parts: A primary language tag and a possibly empty series of
540   subtags:
541</t>
542<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"/>
543     language-tag  = primary-tag *( "-" subtag )
544     primary-tag   = 1*8ALPHA
545     subtag        = 1*8ALPHA
546</artwork></figure>
547<t>
548   White space is not allowed within the tag and all tags are case-insensitive.
549   The name space of language tags is administered by the
550   IANA. Example tags include:
551</t>
552<figure><artwork type="example">
553    en, en-US, en-cockney, i-cherokee, x-pig-latin
554</artwork></figure>
555<t>
556   where any two-letter primary-tag is an ISO-639 language abbreviation
557   and any two-letter initial subtag is an ISO-3166 country code. (The
558   last three tags above are not registered tags; all but the last are
559   examples of tags which could be registered in future.)
560</t>
561</section>
562</section>
563
564<section title="Entity" anchor="entity">
565<t>
566   Request and Response messages &MAY; transfer an entity if not otherwise
567   restricted by the request method or response status code. An entity
568   consists of entity-header fields and an entity-body, although some
569   responses will only include the entity-headers.
570</t>
571<t>
572   In this section, both sender and recipient refer to either the client
573   or the server, depending on who sends and who receives the entity.
574</t>
575
576<section title="Entity Header Fields" anchor="entity.header.fields">
577<t>
578   Entity-header fields define metainformation about the entity-body or,
579   if no body is present, about the resource identified by the request.
580   Some of this metainformation is &OPTIONAL;; some might be &REQUIRED; by
581   portions of this specification.
582</t>
583<figure><artwork type="abnf2616"><iref primary="true" item="Grammar" subitem="entity-header"/><iref primary="true" item="Grammar" subitem="extension-header"/>
584    entity-header  = Allow                    ; &header-allow;
585                   | Content-Encoding         ; <xref target="header.content-encoding"/>
586                   | Content-Language         ; <xref target="header.content-language"/>
587                   | Content-Length           ; &header-content-length;
588                   | Content-Location         ; <xref target="header.content-location"/>
589                   | Content-MD5              ; <xref target="header.content-md5"/>
590                   | Content-Range            ; &header-content-range;
591                   | Content-Type             ; <xref target="header.content-type"/>
592                   | Expires                  ; &header-expires;
593                   | Last-Modified            ; &header-last-modified;
594                   | extension-header
595
596    extension-header = message-header
597</artwork></figure>
598<t>
599   The extension-header mechanism allows additional entity-header fields
600   to be defined without changing the protocol, but these fields cannot
601   be assumed to be recognizable by the recipient. Unrecognized header
602   fields &SHOULD; be ignored by the recipient and &MUST; be forwarded by
603   transparent proxies.
604</t>
605</section>
606
607<section title="Entity Body" anchor="entity.body">
608<t>
609   The entity-body (if any) sent with an HTTP request or response is in
610   a format and encoding defined by the entity-header fields.
611</t>
612<figure><artwork type="abnf2616"><iref primary="true" item="Grammar" subitem="entity-body"/>
613    entity-body    = *OCTET
614</artwork></figure>
615<t>
616   An entity-body is only present in a message when a message-body is
617   present, as described in &message-body;. The entity-body is obtained
618   from the message-body by decoding any Transfer-Encoding that might
619   have been applied to ensure safe and proper transfer of the message.
620</t>
621
622<section title="Type" anchor="type">
623<t>
624   When an entity-body is included with a message, the data type of that
625   body is determined via the header fields Content-Type and Content-Encoding.
626   These define a two-layer, ordered encoding model:
627</t>
628<figure><artwork type="example">
629    entity-body := Content-Encoding( Content-Type( data ) )
630</artwork></figure>
631<t>
632   Content-Type specifies the media type of the underlying data.
633   Content-Encoding may be used to indicate any additional content
634   codings applied to the data, usually for the purpose of data
635   compression, that are a property of the requested resource. There is
636   no default encoding.
637</t>
638<t>
639   Any HTTP/1.1 message containing an entity-body &SHOULD; include a
640   Content-Type header field defining the media type of that body. If
641   and only if the media type is not given by a Content-Type field, the
642   recipient &MAY; attempt to guess the media type via inspection of its
643   content and/or the name extension(s) of the URI used to identify the
644   resource. If the media type remains unknown, the recipient &SHOULD;
645   treat it as type "application/octet-stream".
646</t>
647</section>
648   
649<section title="Entity Length" anchor="entity.length">
650<t>
651   The entity-length of a message is the length of the message-body
652   before any transfer-codings have been applied. &message-length; defines
653   how the transfer-length of a message-body is determined.
654</t>
655</section>
656</section>
657</section>
658
659<section title="Content Negotiation" anchor="content.negotiation">
660<t>
661   Most HTTP responses include an entity which contains information for
662   interpretation by a human user. Naturally, it is desirable to supply
663   the user with the "best available" entity corresponding to the
664   request. Unfortunately for servers and caches, not all users have the
665   same preferences for what is "best," and not all user agents are
666   equally capable of rendering all entity types. For that reason, HTTP
667   has provisions for several mechanisms for "content negotiation" --
668   the process of selecting the best representation for a given response
669   when there are multiple representations available.
670  <list><t>
671      <x:h>Note:</x:h> This is not called "format negotiation" because the
672      alternate representations may be of the same media type, but use
673      different capabilities of that type, be in different languages,
674      etc.
675  </t></list>
676</t>
677<t>
678   Any response containing an entity-body &MAY; be subject to negotiation,
679   including error responses.
680</t>
681<t>
682   There are two kinds of content negotiation which are possible in
683   HTTP: server-driven and agent-driven negotiation. These two kinds of
684   negotiation are orthogonal and thus may be used separately or in
685   combination. One method of combination, referred to as transparent
686   negotiation, occurs when a cache uses the agent-driven negotiation
687   information provided by the origin server in order to provide
688   server-driven negotiation for subsequent requests.
689</t>
690
691<section title="Server-driven Negotiation" anchor="server-driven.negotiation">
692<t>
693   If the selection of the best representation for a response is made by
694   an algorithm located at the server, it is called server-driven
695   negotiation. Selection is based on the available representations of
696   the response (the dimensions over which it can vary; e.g. language,
697   content-coding, etc.) and the contents of particular header fields in
698   the request message or on other information pertaining to the request
699   (such as the network address of the client).
700</t>
701<t>
702   Server-driven negotiation is advantageous when the algorithm for
703   selecting from among the available representations is difficult to
704   describe to the user agent, or when the server desires to send its
705   "best guess" to the client along with the first response (hoping to
706   avoid the round-trip delay of a subsequent request if the "best
707   guess" is good enough for the user). In order to improve the server's
708   guess, the user agent &MAY; include request header fields (Accept,
709   Accept-Language, Accept-Encoding, etc.) which describe its
710   preferences for such a response.
711</t>
712<t>
713   Server-driven negotiation has disadvantages:
714  <list style="numbers">
715    <t>
716         It is impossible for the server to accurately determine what
717         might be "best" for any given user, since that would require
718         complete knowledge of both the capabilities of the user agent
719         and the intended use for the response (e.g., does the user want
720         to view it on screen or print it on paper?).
721    </t>
722    <t>
723         Having the user agent describe its capabilities in every
724         request can be both very inefficient (given that only a small
725         percentage of responses have multiple representations) and a
726         potential violation of the user's privacy.
727    </t>
728    <t>
729         It complicates the implementation of an origin server and the
730         algorithms for generating responses to a request.
731    </t>
732    <t>
733         It may limit a public cache's ability to use the same response
734         for multiple user's requests.
735    </t>
736  </list>
737</t>
738<t>
739   HTTP/1.1 includes the following request-header fields for enabling
740   server-driven negotiation through description of user agent
741   capabilities and user preferences: Accept (<xref target="header.accept"/>), Accept-Charset
742   (<xref target="header.accept-charset"/>), Accept-Encoding (<xref target="header.accept-encoding"/>), Accept-Language
743   (<xref target="header.accept-language"/>), and User-Agent (&header-user-agent;). However, an
744   origin server is not limited to these dimensions and &MAY; vary the
745   response based on any aspect of the request, including information
746   outside the request-header fields or within extension header fields
747   not defined by this specification.
748</t>
749<t>
750   The Vary header field (&header-vary;) can be used to express the parameters the
751   server uses to select a representation that is subject to server-driven
752   negotiation.
753</t>
754</section>
755
756<section title="Agent-driven Negotiation" anchor="agent-driven.negotiation">
757<t>
758   With agent-driven negotiation, selection of the best representation
759   for a response is performed by the user agent after receiving an
760   initial response from the origin server. Selection is based on a list
761   of the available representations of the response included within the
762   header fields or entity-body of the initial response, with each
763   representation identified by its own URI. Selection from among the
764   representations may be performed automatically (if the user agent is
765   capable of doing so) or manually by the user selecting from a
766   generated (possibly hypertext) menu.
767</t>
768<t>
769   Agent-driven negotiation is advantageous when the response would vary
770   over commonly-used dimensions (such as type, language, or encoding),
771   when the origin server is unable to determine a user agent's
772   capabilities from examining the request, and generally when public
773   caches are used to distribute server load and reduce network usage.
774</t>
775<t>
776   Agent-driven negotiation suffers from the disadvantage of needing a
777   second request to obtain the best alternate representation. This
778   second request is only efficient when caching is used. In addition,
779   this specification does not define any mechanism for supporting
780   automatic selection, though it also does not prevent any such
781   mechanism from being developed as an extension and used within
782   HTTP/1.1.
783</t>
784<t>
785   HTTP/1.1 defines the 300 (Multiple Choices) and 406 (Not Acceptable)
786   status codes for enabling agent-driven negotiation when the server is
787   unwilling or unable to provide a varying response using server-driven
788   negotiation.
789</t>
790</section>
791
792<section title="Transparent Negotiation" anchor="transparent.negotiation">
793<t>
794   Transparent negotiation is a combination of both server-driven and
795   agent-driven negotiation. When a cache is supplied with a form of the
796   list of available representations of the response (as in agent-driven
797   negotiation) and the dimensions of variance are completely understood
798   by the cache, then the cache becomes capable of performing server-driven
799   negotiation on behalf of the origin server for subsequent
800   requests on that resource.
801</t>
802<t>
803   Transparent negotiation has the advantage of distributing the
804   negotiation work that would otherwise be required of the origin
805   server and also removing the second request delay of agent-driven
806   negotiation when the cache is able to correctly guess the right
807   response.
808</t>
809<t>
810   This specification does not define any mechanism for transparent
811   negotiation, though it also does not prevent any such mechanism from
812   being developed as an extension that could be used within HTTP/1.1.
813</t>
814</section>
815</section>
816<section title="Header Field Definitions" anchor="header.fields">
817<t>
818   This section defines the syntax and semantics of all standard
819   HTTP/1.1 header fields. For entity-header fields, both sender and
820   recipient refer to either the client or the server, depending on who
821   sends and who receives the entity.
822</t>
823<section title="Accept" anchor="header.accept">
824  <iref primary="true" item="Accept header" x:for-anchor=""/>
825  <iref primary="true" item="Headers" subitem="Accept" x:for-anchor=""/>
826<t>
827   The Accept request-header field can be used to specify certain media
828   types which are acceptable for the response. Accept headers can be
829   used to indicate that the request is specifically limited to a small
830   set of desired types, as in the case of a request for an in-line
831   image.
832</t>
833<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"/>
834    Accept         = "Accept" ":"
835                     #( media-range [ accept-params ] )
836
837    media-range    = ( "*/*"
838                     | ( type "/" "*" )
839                     | ( type "/" subtype )
840                     ) *( ";" parameter )
841    accept-params  = ";" "q" "=" qvalue *( accept-extension )
842    accept-extension = ";" token [ "=" ( token | quoted-string ) ]
843</artwork></figure>
844<t>
845   The asterisk "*" character is used to group media types into ranges,
846   with "*/*" indicating all media types and "type/*" indicating all
847   subtypes of that type. The media-range &MAY; include media type
848   parameters that are applicable to that range.
849</t>
850<t>
851   Each media-range &MAY; be followed by one or more accept-params,
852   beginning with the "q" parameter for indicating a relative quality
853   factor. The first "q" parameter (if any) separates the media-range
854   parameter(s) from the accept-params. Quality factors allow the user
855   or user agent to indicate the relative degree of preference for that
856   media-range, using the qvalue scale from 0 to 1 (<xref target="quality.values"/>). The
857   default value is q=1.
858  <list><t>
859      <x:h>Note:</x:h> Use of the "q" parameter name to separate media type
860      parameters from Accept extension parameters is due to historical
861      practice. Although this prevents any media type parameter named
862      "q" from being used with a media range, such an event is believed
863      to be unlikely given the lack of any "q" parameters in the IANA
864      media type registry and the rare usage of any media type
865      parameters in Accept. Future media types are discouraged from
866      registering any parameter named "q".
867  </t></list>
868</t>
869<t>
870   The example
871</t>
872<figure><artwork type="example">
873    Accept: audio/*; q=0.2, audio/basic
874</artwork></figure>
875<t>
876   &SHOULD; be interpreted as "I prefer audio/basic, but send me any audio
877   type if it is the best available after an 80% mark-down in quality."
878</t>
879<t>
880   If no Accept header field is present, then it is assumed that the
881   client accepts all media types. If an Accept header field is present,
882   and if the server cannot send a response which is acceptable
883   according to the combined Accept field value, then the server &SHOULD;
884   send a 406 (not acceptable) response.
885</t>
886<t>
887   A more elaborate example is
888</t>
889<figure><artwork type="example">
890    Accept: text/plain; q=0.5, text/html,
891            text/x-dvi; q=0.8, text/x-c
892</artwork></figure>
893<t>
894   Verbally, this would be interpreted as "text/html and text/x-c are
895   the preferred media types, but if they do not exist, then send the
896   text/x-dvi entity, and if that does not exist, send the text/plain
897   entity."
898</t>
899<t>
900   Media ranges can be overridden by more specific media ranges or
901   specific media types. If more than one media range applies to a given
902   type, the most specific reference has precedence. For example,
903</t>
904<figure><artwork type="example">
905    Accept: text/*, text/html, text/html;level=1, */*
906</artwork></figure>
907<t>
908   have the following precedence:
909</t>
910<figure><artwork type="example">
911    1) text/html;level=1
912    2) text/html
913    3) text/*
914    4) */*
915</artwork></figure>
916<t>
917   The media type quality factor associated with a given type is
918   determined by finding the media range with the highest precedence
919   which matches that type. For example,
920</t>
921<figure><artwork type="example">
922    Accept: text/*;q=0.3, text/html;q=0.7, text/html;level=1,
923            text/html;level=2;q=0.4, */*;q=0.5
924</artwork></figure>
925<t>
926   would cause the following values to be associated:
927</t>
928<figure><artwork type="example">
929    text/html;level=1         = 1
930    text/html                 = 0.7
931    text/plain                = 0.3
932    image/jpeg                = 0.5
933    text/html;level=2         = 0.4
934    text/html;level=3         = 0.7
935</artwork></figure>
936<t>
937      <x:h>Note:</x:h> A user agent might be provided with a default set of quality
938      values for certain media ranges. However, unless the user agent is
939      a closed system which cannot interact with other rendering agents,
940      this default set ought to be configurable by the user.
941</t>
942</section>
943
944<section title="Accept-Charset" anchor="header.accept-charset">
945  <iref primary="true" item="Accept-Charset header" x:for-anchor=""/>
946  <iref primary="true" item="Headers" subitem="Accept-Charset" x:for-anchor=""/>
947<t>
948   The Accept-Charset request-header field can be used to indicate what
949   character sets are acceptable for the response. This field allows
950   clients capable of understanding more comprehensive or special-purpose
951   character sets to signal that capability to a server which is
952   capable of representing documents in those character sets.
953</t>
954<figure><artwork type="abnf2616"><iref primary="true" item="Grammar" subitem="Accept-Charset"/>
955   Accept-Charset = "Accept-Charset" ":"
956           1#( ( charset | "*" )[ ";" "q" "=" qvalue ] )
957</artwork></figure>
958<t>
959   Character set values are described in <xref target="character.sets"/>. Each charset &MAY;
960   be given an associated quality value which represents the user's
961   preference for that charset. The default value is q=1. An example is
962</t>
963<figure><artwork type="example">
964   Accept-Charset: iso-8859-5, unicode-1-1;q=0.8
965</artwork></figure>
966<t>
967   The special value "*", if present in the Accept-Charset field,
968   matches every character set (including ISO-8859-1) which is not
969   mentioned elsewhere in the Accept-Charset field. If no "*" is present
970   in an Accept-Charset field, then all character sets not explicitly
971   mentioned get a quality value of 0, except for ISO-8859-1, which gets
972   a quality value of 1 if not explicitly mentioned.
973</t>
974<t>
975   If no Accept-Charset header is present, the default is that any
976   character set is acceptable. If an Accept-Charset header is present,
977   and if the server cannot send a response which is acceptable
978   according to the Accept-Charset header, then the server &SHOULD; send
979   an error response with the 406 (not acceptable) status code, though
980   the sending of an unacceptable response is also allowed.
981</t>
982</section>
983
984<section title="Accept-Encoding" anchor="header.accept-encoding">
985  <iref primary="true" item="Accept-Encoding header" x:for-anchor=""/>
986  <iref primary="true" item="Headers" subitem="Accept-Encoding" x:for-anchor=""/>
987<t>
988   The Accept-Encoding request-header field is similar to Accept, but
989   restricts the content-codings (<xref target="content.codings"/>) that are acceptable in
990   the response.
991</t>
992<figure><artwork type="abnf2616"><iref primary="true" item="Grammar" subitem="Accept-Encoding"/><iref primary="true" item="Grammar" subitem="codings"/>
993    Accept-Encoding  = "Accept-Encoding" ":"
994                       1#( codings [ ";" "q" "=" qvalue ] )
995    codings          = ( content-coding | "*" )
996</artwork></figure>
997<t>
998   Examples of its use are:
999</t>
1000<figure><artwork type="example">
1001    Accept-Encoding: compress, gzip
1002    Accept-Encoding:
1003    Accept-Encoding: *
1004    Accept-Encoding: compress;q=0.5, gzip;q=1.0
1005    Accept-Encoding: gzip;q=1.0, identity; q=0.5, *;q=0
1006</artwork></figure>
1007<t>
1008   A server tests whether a content-coding is acceptable, according to
1009   an Accept-Encoding field, using these rules:
1010  <list style="numbers">
1011      <t>If the content-coding is one of the content-codings listed in
1012         the Accept-Encoding field, then it is acceptable, unless it is
1013         accompanied by a qvalue of 0. (As defined in <xref target="quality.values"/>, a
1014         qvalue of 0 means "not acceptable.")</t>
1015
1016      <t>The special "*" symbol in an Accept-Encoding field matches any
1017         available content-coding not explicitly listed in the header
1018         field.</t>
1019
1020      <t>If multiple content-codings are acceptable, then the acceptable
1021         content-coding with the highest non-zero qvalue is preferred.</t>
1022
1023      <t>The "identity" content-coding is always acceptable, unless
1024         specifically refused because the Accept-Encoding field includes
1025         "identity;q=0", or because the field includes "*;q=0" and does
1026         not explicitly include the "identity" content-coding. If the
1027         Accept-Encoding field-value is empty, then only the "identity"
1028         encoding is acceptable.</t>
1029  </list>
1030</t>
1031<t>
1032   If an Accept-Encoding field is present in a request, and if the
1033   server cannot send a response which is acceptable according to the
1034   Accept-Encoding header, then the server &SHOULD; send an error response
1035   with the 406 (Not Acceptable) status code.
1036</t>
1037<t>
1038   If no Accept-Encoding field is present in a request, the server &MAY;
1039   assume that the client will accept any content coding. In this case,
1040   if "identity" is one of the available content-codings, then the
1041   server &SHOULD; use the "identity" content-coding, unless it has
1042   additional information that a different content-coding is meaningful
1043   to the client.
1044  <list><t>
1045      <x:h>Note:</x:h> If the request does not include an Accept-Encoding field,
1046      and if the "identity" content-coding is unavailable, then
1047      content-codings commonly understood by HTTP/1.0 clients (i.e.,
1048      "gzip" and "compress") are preferred; some older clients
1049      improperly display messages sent with other content-codings.  The
1050      server might also make this decision based on information about
1051      the particular user-agent or client.
1052    </t><t>
1053      <x:h>Note:</x:h> Most HTTP/1.0 applications do not recognize or obey qvalues
1054      associated with content-codings. This means that qvalues will not
1055      work and are not permitted with x-gzip or x-compress.
1056    </t></list>
1057</t>
1058</section>
1059
1060<section title="Accept-Language" anchor="header.accept-language">
1061  <iref primary="true" item="Accept-Language header" x:for-anchor=""/>
1062  <iref primary="true" item="Headers" subitem="Accept-Language" x:for-anchor=""/>
1063<t>
1064   The Accept-Language request-header field is similar to Accept, but
1065   restricts the set of natural languages that are preferred as a
1066   response to the request. Language tags are defined in <xref target="language.tags"/>.
1067</t>
1068<figure><artwork type="abnf2616"><iref primary="true" item="Grammar" subitem="Accept-Language"/><iref primary="true" item="Grammar" subitem="language-range"/>
1069    Accept-Language = "Accept-Language" ":"
1070                      1#( language-range [ ";" "q" "=" qvalue ] )
1071    language-range  = ( ( 1*8ALPHA *( "-" 1*8ALPHA ) ) | "*" )
1072</artwork></figure>
1073<t>
1074   Each language-range &MAY; be given an associated quality value which
1075   represents an estimate of the user's preference for the languages
1076   specified by that range. The quality value defaults to "q=1". For
1077   example,
1078</t>
1079<figure><artwork type="example">
1080    Accept-Language: da, en-gb;q=0.8, en;q=0.7
1081</artwork></figure>
1082<t>
1083   would mean: "I prefer Danish, but will accept British English and
1084   other types of English." A language-range matches a language-tag if
1085   it exactly equals the tag, or if it exactly equals a prefix of the
1086   tag such that the first tag character following the prefix is "-".
1087   The special range "*", if present in the Accept-Language field,
1088   matches every tag not matched by any other range present in the
1089   Accept-Language field.
1090  <list><t>
1091      <x:h>Note:</x:h> This use of a prefix matching rule does not imply that
1092      language tags are assigned to languages in such a way that it is
1093      always true that if a user understands a language with a certain
1094      tag, then this user will also understand all languages with tags
1095      for which this tag is a prefix. The prefix rule simply allows the
1096      use of prefix tags if this is the case.
1097  </t></list>
1098</t>
1099<t>
1100   The language quality factor assigned to a language-tag by the
1101   Accept-Language field is the quality value of the longest language-range
1102   in the field that matches the language-tag. If no language-range
1103   in the field matches the tag, the language quality factor
1104   assigned is 0. If no Accept-Language header is present in the
1105   request, the server
1106   &SHOULD; assume that all languages are equally acceptable. If an
1107   Accept-Language header is present, then all languages which are
1108   assigned a quality factor greater than 0 are acceptable.
1109</t>
1110<t>
1111   It might be contrary to the privacy expectations of the user to send
1112   an Accept-Language header with the complete linguistic preferences of
1113   the user in every request. For a discussion of this issue, see
1114   <xref target="privacy.issues.connected.to.accept.headers"/>.
1115</t>
1116<t>
1117   As intelligibility is highly dependent on the individual user, it is
1118   recommended that client applications make the choice of linguistic
1119   preference available to the user. If the choice is not made
1120   available, then the Accept-Language header field &MUST-NOT; be given in
1121   the request.
1122  <list><t>
1123      <x:h>Note:</x:h> When making the choice of linguistic preference available to
1124      the user, we remind implementors of  the fact that users are not
1125      familiar with the details of language matching as described above,
1126      and should provide appropriate guidance. As an example, users
1127      might assume that on selecting "en-gb", they will be served any
1128      kind of English document if British English is not available. A
1129      user agent might suggest in such a case to add "en" to get the
1130      best matching behavior.
1131  </t></list>
1132</t>
1133</section>
1134
1135<section title="Content-Encoding" anchor="header.content-encoding">
1136  <iref primary="true" item="Content-Encoding header" x:for-anchor=""/>
1137  <iref primary="true" item="Headers" subitem="Content-Encoding" x:for-anchor=""/>
1138<t>
1139   The Content-Encoding entity-header field is used as a modifier to the
1140   media-type. When present, its value indicates what additional content
1141   codings have been applied to the entity-body, and thus what decoding
1142   mechanisms must be applied in order to obtain the media-type
1143   referenced by the Content-Type header field. Content-Encoding is
1144   primarily used to allow a document to be compressed without losing
1145   the identity of its underlying media type.
1146</t>
1147<figure><artwork type="abnf2616"><iref primary="true" item="Grammar" subitem="Content-Encoding"/>
1148    Content-Encoding  = "Content-Encoding" ":" 1#content-coding
1149</artwork></figure>
1150<t>
1151   Content codings are defined in <xref target="content.codings"/>. An example of its use is
1152</t>
1153<figure><artwork type="example">
1154    Content-Encoding: gzip
1155</artwork></figure>
1156<t>
1157   The content-coding is a characteristic of the entity identified by
1158   the Request-URI. Typically, the entity-body is stored with this
1159   encoding and is only decoded before rendering or analogous usage.
1160   However, a non-transparent proxy &MAY; modify the content-coding if the
1161   new coding is known to be acceptable to the recipient, unless the
1162   "no-transform" cache-control directive is present in the message.
1163</t>
1164<t>
1165   If the content-coding of an entity is not "identity", then the
1166   response &MUST; include a Content-Encoding entity-header (<xref target="header.content-encoding"/>)
1167   that lists the non-identity content-coding(s) used.
1168</t>
1169<t>
1170   If the content-coding of an entity in a request message is not
1171   acceptable to the origin server, the server &SHOULD; respond with a
1172   status code of 415 (Unsupported Media Type).
1173</t>
1174<t>
1175   If multiple encodings have been applied to an entity, the content
1176   codings &MUST; be listed in the order in which they were applied.
1177   Additional information about the encoding parameters &MAY; be provided
1178   by other entity-header fields not defined by this specification.
1179</t>
1180</section>
1181
1182<section title="Content-Language" anchor="header.content-language">
1183  <iref primary="true" item="Content-Language header" x:for-anchor=""/>
1184  <iref primary="true" item="Headers" subitem="Content-Language" x:for-anchor=""/>
1185<t>
1186   The Content-Language entity-header field describes the natural
1187   language(s) of the intended audience for the enclosed entity. Note
1188   that this might not be equivalent to all the languages used within
1189   the entity-body.
1190</t>
1191<figure><artwork type="abnf2616"><iref primary="true" item="Grammar" subitem="Content-Language"/>
1192    Content-Language  = "Content-Language" ":" 1#language-tag
1193</artwork></figure>
1194<t>
1195   Language tags are defined in <xref target="language.tags"/>. The primary purpose of
1196   Content-Language is to allow a user to identify and differentiate
1197   entities according to the user's own preferred language. Thus, if the
1198   body content is intended only for a Danish-literate audience, the
1199   appropriate field is
1200</t>
1201<figure><artwork type="example">
1202    Content-Language: da
1203</artwork></figure>
1204<t>
1205   If no Content-Language is specified, the default is that the content
1206   is intended for all language audiences. This might mean that the
1207   sender does not consider it to be specific to any natural language,
1208   or that the sender does not know for which language it is intended.
1209</t>
1210<t>
1211   Multiple languages &MAY; be listed for content that is intended for
1212   multiple audiences. For example, a rendition of the "Treaty of
1213   Waitangi," presented simultaneously in the original Maori and English
1214   versions, would call for
1215</t>
1216<figure><artwork type="example">
1217    Content-Language: mi, en
1218</artwork></figure>
1219<t>
1220   However, just because multiple languages are present within an entity
1221   does not mean that it is intended for multiple linguistic audiences.
1222   An example would be a beginner's language primer, such as "A First
1223   Lesson in Latin," which is clearly intended to be used by an
1224   English-literate audience. In this case, the Content-Language would
1225   properly only include "en".
1226</t>
1227<t>
1228   Content-Language &MAY; be applied to any media type -- it is not
1229   limited to textual documents.
1230</t>
1231</section>
1232
1233<section title="Content-Location" anchor="header.content-location">
1234  <iref primary="true" item="Content-Location header" x:for-anchor=""/>
1235  <iref primary="true" item="Headers" subitem="Content-Location" x:for-anchor=""/>
1236<t>
1237   The Content-Location entity-header field &MAY; be used to supply the
1238   resource location for the entity enclosed in the message when that
1239   entity is accessible from a location separate from the requested
1240   resource's URI. A server &SHOULD; provide a Content-Location for the
1241   variant corresponding to the response entity; especially in the case
1242   where a resource has multiple entities associated with it, and those
1243   entities actually have separate locations by which they might be
1244   individually accessed, the server &SHOULD; provide a Content-Location
1245   for the particular variant which is returned.
1246</t>
1247<figure><artwork type="abnf2616"><iref primary="true" item="Grammar" subitem="Content-Location"/>
1248    Content-Location = "Content-Location" ":"
1249                      ( absoluteURI | relativeURI )
1250</artwork></figure>
1251<t>
1252   The value of Content-Location also defines the base URI for the
1253   entity.
1254</t>
1255<t>
1256   The Content-Location value is not a replacement for the original
1257   requested URI; it is only a statement of the location of the resource
1258   corresponding to this particular entity at the time of the request.
1259   Future requests &MAY; specify the Content-Location URI as the request-URI
1260   if the desire is to identify the source of that particular
1261   entity.
1262</t>
1263<t>
1264   A cache cannot assume that an entity with a Content-Location
1265   different from the URI used to retrieve it can be used to respond to
1266   later requests on that Content-Location URI. However, the Content-Location
1267   can be used to differentiate between multiple entities
1268   retrieved from a single requested resource, as described in &caching-neg-resp;.
1269</t>
1270<t>
1271   If the Content-Location is a relative URI, the relative URI is
1272   interpreted relative to the Request-URI.
1273</t>
1274<t>
1275   The meaning of the Content-Location header in PUT or POST requests is
1276   undefined; servers are free to ignore it in those cases.
1277</t>
1278</section>
1279
1280<section title="Content-MD5" anchor="header.content-md5">
1281  <iref primary="true" item="Content-MD5 header" x:for-anchor=""/>
1282  <iref primary="true" item="Headers" subitem="Content-MD5" x:for-anchor=""/>
1283<t>
1284   The Content-MD5 entity-header field, as defined in <xref target="RFC1864"/>, is
1285   an MD5 digest of the entity-body for the purpose of providing an
1286   end-to-end message integrity check (MIC) of the entity-body. (Note: a
1287   MIC is good for detecting accidental modification of the entity-body
1288   in transit, but is not proof against malicious attacks.)
1289</t>
1290<figure><artwork type="abnf2616"><iref primary="true" item="Grammar" subitem="Content-MD5"/><iref primary="true" item="Grammar" subitem="md5-digest"/>
1291     Content-MD5   = "Content-MD5" ":" md5-digest
1292     md5-digest   = &lt;base64 of 128 bit MD5 digest as per <xref target="RFC1864"/>&gt;
1293</artwork></figure>
1294<t>
1295   The Content-MD5 header field &MAY; be generated by an origin server or
1296   client to function as an integrity check of the entity-body. Only
1297   origin servers or clients &MAY; generate the Content-MD5 header field;
1298   proxies and gateways &MUST-NOT; generate it, as this would defeat its
1299   value as an end-to-end integrity check. Any recipient of the entity-body,
1300   including gateways and proxies, &MAY; check that the digest value
1301   in this header field matches that of the entity-body as received.
1302</t>
1303<t>
1304   The MD5 digest is computed based on the content of the entity-body,
1305   including any content-coding that has been applied, but not including
1306   any transfer-encoding applied to the message-body. If the message is
1307   received with a transfer-encoding, that encoding &MUST; be removed
1308   prior to checking the Content-MD5 value against the received entity.
1309</t>
1310<t>
1311   This has the result that the digest is computed on the octets of the
1312   entity-body exactly as, and in the order that, they would be sent if
1313   no transfer-encoding were being applied.
1314</t>
1315<t>
1316   HTTP extends RFC 1864 to permit the digest to be computed for MIME
1317   composite media-types (e.g., multipart/* and message/rfc822), but
1318   this does not change how the digest is computed as defined in the
1319   preceding paragraph.
1320</t>
1321<t>
1322   There are several consequences of this. The entity-body for composite
1323   types &MAY; contain many body-parts, each with its own MIME and HTTP
1324   headers (including Content-MD5, Content-Transfer-Encoding, and
1325   Content-Encoding headers). If a body-part has a Content-Transfer-Encoding
1326   or Content-Encoding header, it is assumed that the content
1327   of the body-part has had the encoding applied, and the body-part is
1328   included in the Content-MD5 digest as is -- i.e., after the
1329   application. The Transfer-Encoding header field is not allowed within
1330   body-parts.
1331</t>
1332<t>
1333   Conversion of all line breaks to CRLF &MUST-NOT; be done before
1334   computing or checking the digest: the line break convention used in
1335   the text actually transmitted &MUST; be left unaltered when computing
1336   the digest.
1337  <list><t>
1338      <x:h>Note:</x:h> while the definition of Content-MD5 is exactly the same for
1339      HTTP as in RFC 1864 for MIME entity-bodies, there are several ways
1340      in which the application of Content-MD5 to HTTP entity-bodies
1341      differs from its application to MIME entity-bodies. One is that
1342      HTTP, unlike MIME, does not use Content-Transfer-Encoding, and
1343      does use Transfer-Encoding and Content-Encoding. Another is that
1344      HTTP more frequently uses binary content types than MIME, so it is
1345      worth noting that, in such cases, the byte order used to compute
1346      the digest is the transmission byte order defined for the type.
1347      Lastly, HTTP allows transmission of text types with any of several
1348      line break conventions and not just the canonical form using CRLF.
1349  </t></list>
1350</t>
1351</section>
1352
1353<section title="Content-Type" anchor="header.content-type">
1354  <iref primary="true" item="Content-Type header" x:for-anchor=""/>
1355  <iref primary="true" item="Headers" subitem="Content-Type" x:for-anchor=""/>
1356<t>
1357   The Content-Type entity-header field indicates the media type of the
1358   entity-body sent to the recipient or, in the case of the HEAD method,
1359   the media type that would have been sent had the request been a GET.
1360</t>
1361<figure><artwork type="abnf2616"><iref primary="true" item="Grammar" subitem="Content-Type"/>
1362    Content-Type   = "Content-Type" ":" media-type
1363</artwork></figure>
1364<t>
1365   Media types are defined in <xref target="media.types"/>. An example of the field is
1366</t>
1367<figure><artwork type="example">
1368    Content-Type: text/html; charset=ISO-8859-4
1369</artwork></figure>
1370<t>
1371   Further discussion of methods for identifying the media type of an
1372   entity is provided in <xref target="type"/>.
1373</t>
1374</section>
1375
1376</section>
1377
1378<section title="IANA Considerations" anchor="IANA.considerations">
1379<t>
1380   TBD.
1381</t>
1382</section>
1383
1384<section title="Security Considerations" anchor="security.considerations">
1385<t>
1386   This section is meant to inform application developers, information
1387   providers, and users of the security limitations in HTTP/1.1 as
1388   described by this document. The discussion does not include
1389   definitive solutions to the problems revealed, though it does make
1390   some suggestions for reducing security risks.
1391</t>
1392
1393<section title="Privacy Issues Connected to Accept Headers" anchor="privacy.issues.connected.to.accept.headers">
1394<t>
1395   Accept request-headers can reveal information about the user to all
1396   servers which are accessed. The Accept-Language header in particular
1397   can reveal information the user would consider to be of a private
1398   nature, because the understanding of particular languages is often
1399   strongly correlated to the membership of a particular ethnic group.
1400   User agents which offer the option to configure the contents of an
1401   Accept-Language header to be sent in every request are strongly
1402   encouraged to let the configuration process include a message which
1403   makes the user aware of the loss of privacy involved.
1404</t>
1405<t>
1406   An approach that limits the loss of privacy would be for a user agent
1407   to omit the sending of Accept-Language headers by default, and to ask
1408   the user whether or not to start sending Accept-Language headers to a
1409   server if it detects, by looking for any Vary response-header fields
1410   generated by the server, that such sending could improve the quality
1411   of service.
1412</t>
1413<t>
1414   Elaborate user-customized accept header fields sent in every request,
1415   in particular if these include quality values, can be used by servers
1416   as relatively reliable and long-lived user identifiers. Such user
1417   identifiers would allow content providers to do click-trail tracking,
1418   and would allow collaborating content providers to match cross-server
1419   click-trails or form submissions of individual users. Note that for
1420   many users not behind a proxy, the network address of the host
1421   running the user agent will also serve as a long-lived user
1422   identifier. In environments where proxies are used to enhance
1423   privacy, user agents ought to be conservative in offering accept
1424   header configuration options to end users. As an extreme privacy
1425   measure, proxies could filter the accept headers in relayed requests.
1426   General purpose user agents which provide a high degree of header
1427   configurability &SHOULD; warn users about the loss of privacy which can
1428   be involved.
1429</t>
1430</section>
1431
1432<section title="Content-Disposition Issues" anchor="content-disposition.issues">
1433<t>
1434   <xref target="RFC1806"/>, from which the often implemented Content-Disposition
1435   (see <xref target="content-disposition"/>) header in HTTP is derived, has a number of very
1436   serious security considerations. Content-Disposition is not part of
1437   the HTTP standard, but since it is widely implemented, we are
1438   documenting its use and risks for implementors. See <xref target="RFC2183"/>
1439   (which updates <xref target="RFC1806"/>) for details.
1440</t>
1441</section>
1442
1443</section>
1444
1445<section title="Acknowledgments" anchor="ack">
1446</section>
1447</middle>
1448<back>
1449<references>
1450
1451<reference anchor="Part1">
1452   <front>
1453      <title abbrev="HTTP/1.1">HTTP/1.1, part 1: URIs, Connections, and Message Parsing</title>
1454      <author initials="R." surname="Fielding" fullname="Roy T. Fielding" role="editor">
1455         <organization abbrev="Day Software">Day Software</organization>
1456         <address><email>fielding@gbiv.com</email></address>
1457      </author>
1458      <author initials="J." surname="Gettys" fullname="Jim Gettys">
1459         <organization>One Laptop per Child</organization>
1460         <address><email>jg@laptop.org</email></address>
1461      </author>
1462      <author initials="J." surname="Mogul" fullname="Jeffrey C. Mogul">
1463         <organization abbrev="HP">Hewlett-Packard Company</organization>
1464         <address><email>JeffMogul@acm.org</email></address>
1465      </author>
1466      <author initials="H." surname="Frystyk" fullname="Henrik Frystyk Nielsen">
1467         <organization abbrev="Microsoft">Microsoft Corporation</organization>
1468         <address><email>henrikn@microsoft.com</email></address>
1469      </author>
1470      <author initials="L." surname="Masinter" fullname="Larry Masinter">
1471         <organization abbrev="Adobe Systems">Adobe Systems, Incorporated</organization>
1472         <address><email>LMM@acm.org</email></address>
1473      </author>
1474      <author initials="P." surname="Leach" fullname="Paul J. Leach">
1475         <organization abbrev="Microsoft">Microsoft Corporation</organization>
1476         <address><email>paulle@microsoft.com</email></address>
1477      </author>
1478      <author initials="T." surname="Berners-Lee" fullname="Tim Berners-Lee">
1479         <organization abbrev="W3C/MIT">World Wide Web Consortium</organization>
1480         <address><email>timbl@w3.org</email></address>
1481      </author>
1482      <author initials="Y." surname="Lafon" fullname="Yves Lafon" role="editor">
1483         <organization abbrev="W3C">World Wide Web Consortium</organization>
1484         <address><email>ylafon@w3.org</email></address>
1485      </author>
1486      <author initials="J. F." surname="Reschke" fullname="Julian F. Reschke" role="editor">
1487         <organization abbrev="greenbytes">greenbytes GmbH</organization>
1488         <address><email>julian.reschke@greenbytes.de</email></address>
1489      </author>
1490      <date month="&ID-MONTH;" year="&ID-YEAR;"/>
1491   </front>
1492   <seriesInfo name="Internet-Draft" value="draft-ietf-httpbis-p1-messaging-&ID-VERSION;"/>
1493   <x:source href="p1-messaging.xml" basename="p1-messaging"/>
1494</reference>
1495
1496<reference anchor="Part2">
1497   <front>
1498      <title abbrev="HTTP/1.1">HTTP/1.1, part 2: Message Semantics</title>
1499      <author initials="R." surname="Fielding" fullname="Roy T. Fielding" role="editor">
1500         <organization abbrev="Day Software">Day Software</organization>
1501         <address><email>fielding@gbiv.com</email></address>
1502      </author>
1503      <author initials="J." surname="Gettys" fullname="Jim Gettys">
1504         <organization>One Laptop per Child</organization>
1505         <address><email>jg@laptop.org</email></address>
1506      </author>
1507      <author initials="J." surname="Mogul" fullname="Jeffrey C. Mogul">
1508         <organization abbrev="HP">Hewlett-Packard Company</organization>
1509         <address><email>JeffMogul@acm.org</email></address>
1510      </author>
1511      <author initials="H." surname="Frystyk" fullname="Henrik Frystyk Nielsen">
1512         <organization abbrev="Microsoft">Microsoft Corporation</organization>
1513         <address><email>henrikn@microsoft.com</email></address>
1514      </author>
1515      <author initials="L." surname="Masinter" fullname="Larry Masinter">
1516         <organization abbrev="Adobe Systems">Adobe Systems, Incorporated</organization>
1517         <address><email>LMM@acm.org</email></address>
1518      </author>
1519      <author initials="P." surname="Leach" fullname="Paul J. Leach">
1520         <organization abbrev="Microsoft">Microsoft Corporation</organization>
1521         <address><email>paulle@microsoft.com</email></address>
1522      </author>
1523      <author initials="T." surname="Berners-Lee" fullname="Tim Berners-Lee">
1524         <organization abbrev="W3C/MIT">World Wide Web Consortium</organization>
1525         <address><email>timbl@w3.org</email></address>
1526      </author>
1527      <author initials="Y." surname="Lafon" fullname="Yves Lafon" role="editor">
1528         <organization abbrev="W3C">World Wide Web Consortium</organization>
1529         <address><email>ylafon@w3.org</email></address>
1530      </author>
1531      <author initials="J. F." surname="Reschke" fullname="Julian F. Reschke" role="editor">
1532         <organization abbrev="greenbytes">greenbytes GmbH</organization>
1533         <address><email>julian.reschke@greenbytes.de</email></address>
1534      </author>
1535      <date month="&ID-MONTH;" year="&ID-YEAR;"/>
1536   </front>
1537   <seriesInfo name="Internet-Draft" value="draft-ietf-httpbis-p2-semantics-&ID-VERSION;"/>
1538   <x:source href="p2-semantics.xml" basename="p2-semantics"/>
1539</reference>
1540
1541<reference anchor="Part4">
1542   <front>
1543      <title abbrev="HTTP/1.1">HTTP/1.1, part 4: Conditional Requests</title>
1544      <author initials="R." surname="Fielding" fullname="Roy T. Fielding" role="editor">
1545         <organization abbrev="Day Software">Day Software</organization>
1546         <address><email>fielding@gbiv.com</email></address>
1547      </author>
1548      <author initials="J." surname="Gettys" fullname="Jim Gettys">
1549         <organization>One Laptop per Child</organization>
1550         <address><email>jg@laptop.org</email></address>
1551      </author>
1552      <author initials="J." surname="Mogul" fullname="Jeffrey C. Mogul">
1553         <organization abbrev="HP">Hewlett-Packard Company</organization>
1554         <address><email>JeffMogul@acm.org</email></address>
1555      </author>
1556      <author initials="H." surname="Frystyk" fullname="Henrik Frystyk Nielsen">
1557         <organization abbrev="Microsoft">Microsoft Corporation</organization>
1558         <address><email>henrikn@microsoft.com</email></address>
1559      </author>
1560      <author initials="L." surname="Masinter" fullname="Larry Masinter">
1561         <organization abbrev="Adobe Systems">Adobe Systems, Incorporated</organization>
1562         <address><email>LMM@acm.org</email></address>
1563      </author>
1564      <author initials="P." surname="Leach" fullname="Paul J. Leach">
1565         <organization abbrev="Microsoft">Microsoft Corporation</organization>
1566         <address><email>paulle@microsoft.com</email></address>
1567      </author>
1568      <author initials="T." surname="Berners-Lee" fullname="Tim Berners-Lee">
1569         <organization abbrev="W3C/MIT">World Wide Web Consortium</organization>
1570         <address><email>timbl@w3.org</email></address>
1571      </author>
1572      <author initials="Y." surname="Lafon" fullname="Yves Lafon" role="editor">
1573         <organization abbrev="W3C">World Wide Web Consortium</organization>
1574         <address><email>ylafon@w3.org</email></address>
1575      </author>
1576      <author initials="J. F." surname="Reschke" fullname="Julian F. Reschke" role="editor">
1577         <organization abbrev="greenbytes">greenbytes GmbH</organization>
1578         <address><email>julian.reschke@greenbytes.de</email></address>
1579      </author>
1580      <date month="&ID-MONTH;" year="&ID-YEAR;"/>
1581   </front>
1582   <seriesInfo name="Internet-Draft" value="draft-ietf-httpbis-p4-conditional-&ID-VERSION;"/>
1583   <x:source href="p4-conditional.xml" basename="p4-conditional"/>
1584</reference>
1585
1586<reference anchor="Part5">
1587   <front>
1588      <title abbrev="HTTP/1.1">HTTP/1.1, part 5: Range Requests and Partial Responses</title>
1589      <author initials="R." surname="Fielding" fullname="Roy T. Fielding" role="editor">
1590         <organization abbrev="Day Software">Day Software</organization>
1591         <address><email>fielding@gbiv.com</email></address>
1592      </author>
1593      <author initials="J." surname="Gettys" fullname="Jim Gettys">
1594         <organization>One Laptop per Child</organization>
1595         <address><email>jg@laptop.org</email></address>
1596      </author>
1597      <author initials="J." surname="Mogul" fullname="Jeffrey C. Mogul">
1598         <organization abbrev="HP">Hewlett-Packard Company</organization>
1599         <address><email>JeffMogul@acm.org</email></address>
1600      </author>
1601      <author initials="H." surname="Frystyk" fullname="Henrik Frystyk Nielsen">
1602         <organization abbrev="Microsoft">Microsoft Corporation</organization>
1603         <address><email>henrikn@microsoft.com</email></address>
1604      </author>
1605      <author initials="L." surname="Masinter" fullname="Larry Masinter">
1606         <organization abbrev="Adobe Systems">Adobe Systems, Incorporated</organization>
1607         <address><email>LMM@acm.org</email></address>
1608      </author>
1609      <author initials="P." surname="Leach" fullname="Paul J. Leach">
1610         <organization abbrev="Microsoft">Microsoft Corporation</organization>
1611         <address><email>paulle@microsoft.com</email></address>
1612      </author>
1613      <author initials="T." surname="Berners-Lee" fullname="Tim Berners-Lee">
1614         <organization abbrev="W3C/MIT">World Wide Web Consortium</organization>
1615         <address><email>timbl@w3.org</email></address>
1616      </author>
1617      <author initials="Y." surname="Lafon" fullname="Yves Lafon" role="editor">
1618         <organization abbrev="W3C">World Wide Web Consortium</organization>
1619         <address><email>ylafon@w3.org</email></address>
1620      </author>
1621      <author initials="J. F." surname="Reschke" fullname="Julian F. Reschke" role="editor">
1622         <organization abbrev="greenbytes">greenbytes GmbH</organization>
1623         <address><email>julian.reschke@greenbytes.de</email></address>
1624      </author>
1625      <date month="&ID-MONTH;" year="&ID-YEAR;"/>
1626   </front>
1627   <seriesInfo name="Internet-Draft" value="draft-ietf-httpbis-p5-range-&ID-VERSION;"/>
1628   <x:source href="p5-range.xml" basename="p5-range"/>
1629</reference>
1630
1631<reference anchor="Part6">
1632   <front>
1633      <title abbrev="HTTP/1.1">HTTP/1.1, part 6: Caching</title>
1634      <author initials="R." surname="Fielding" fullname="Roy T. Fielding" role="editor">
1635         <organization abbrev="Day Software">Day Software</organization>
1636         <address><email>fielding@gbiv.com</email></address>
1637      </author>
1638      <author initials="J." surname="Gettys" fullname="Jim Gettys">
1639         <organization>One Laptop per Child</organization>
1640         <address><email>jg@laptop.org</email></address>
1641      </author>
1642      <author initials="J." surname="Mogul" fullname="Jeffrey C. Mogul">
1643         <organization abbrev="HP">Hewlett-Packard Company</organization>
1644         <address><email>JeffMogul@acm.org</email></address>
1645      </author>
1646      <author initials="H." surname="Frystyk" fullname="Henrik Frystyk Nielsen">
1647         <organization abbrev="Microsoft">Microsoft Corporation</organization>
1648         <address><email>henrikn@microsoft.com</email></address>
1649      </author>
1650      <author initials="L." surname="Masinter" fullname="Larry Masinter">
1651         <organization abbrev="Adobe Systems">Adobe Systems, Incorporated</organization>
1652         <address><email>LMM@acm.org</email></address>
1653      </author>
1654      <author initials="P." surname="Leach" fullname="Paul J. Leach">
1655         <organization abbrev="Microsoft">Microsoft Corporation</organization>
1656         <address><email>paulle@microsoft.com</email></address>
1657      </author>
1658      <author initials="T." surname="Berners-Lee" fullname="Tim Berners-Lee">
1659         <organization abbrev="W3C/MIT">World Wide Web Consortium</organization>
1660         <address><email>timbl@w3.org</email></address>
1661      </author>
1662      <author initials="Y." surname="Lafon" fullname="Yves Lafon" role="editor">
1663         <organization abbrev="W3C">World Wide Web Consortium</organization>
1664         <address><email>ylafon@w3.org</email></address>
1665      </author>
1666      <author initials="J. F." surname="Reschke" fullname="Julian F. Reschke" role="editor">
1667         <organization abbrev="greenbytes">greenbytes GmbH</organization>
1668         <address><email>julian.reschke@greenbytes.de</email></address>
1669      </author>
1670      <date month="&ID-MONTH;" year="&ID-YEAR;"/>
1671   </front>
1672   <seriesInfo name="Internet-Draft" value="draft-ietf-httpbis-p6-cache-&ID-VERSION;"/>
1673   <x:source href="p6-cache.xml" basename="p6-cache"/>
1674</reference>
1675
1676<reference anchor="RFC2616">
1677   <front>
1678      <title>Hypertext Transfer Protocol -- HTTP/1.1</title>
1679      <author initials="R." surname="Fielding" fullname="R. Fielding">
1680         <organization>University of California, Irvine</organization>
1681         <address><email>fielding@ics.uci.edu</email></address>
1682      </author>
1683      <author initials="J." surname="Gettys" fullname="J. Gettys">
1684         <organization>W3C</organization>
1685         <address><email>jg@w3.org</email></address>
1686      </author>
1687      <author initials="J." surname="Mogul" fullname="J. Mogul">
1688         <organization>Compaq Computer Corporation</organization>
1689         <address><email>mogul@wrl.dec.com</email></address>
1690      </author>
1691      <author initials="H." surname="Frystyk" fullname="H. Frystyk">
1692         <organization>MIT Laboratory for Computer Science</organization>
1693         <address><email>frystyk@w3.org</email></address>
1694      </author>
1695      <author initials="L." surname="Masinter" fullname="L. Masinter">
1696         <organization>Xerox Corporation</organization>
1697         <address><email>masinter@parc.xerox.com</email></address>
1698      </author>
1699      <author initials="P." surname="Leach" fullname="P. Leach">
1700         <organization>Microsoft Corporation</organization>
1701         <address><email>paulle@microsoft.com</email></address>
1702      </author>
1703      <author initials="T." surname="Berners-Lee" fullname="T. Berners-Lee">
1704         <organization>W3C</organization>
1705         <address><email>timbl@w3.org</email></address>
1706      </author>
1707      <date month="June" year="1999"/>
1708   </front>
1709   <seriesInfo name="RFC" value="2616"/>
1710</reference>
1711
1712<reference anchor="RFC1766">
1713  <front>
1714    <title abbrev="Language Tag">Tags for the Identification of Languages</title>
1715    <author initials="H." surname="Alvestrand" fullname="Harald Tveit Alvestrand">
1716      <organization>UNINETT</organization>
1717      <address><email>Harald.T.Alvestrand@uninett.no</email></address>
1718    </author>
1719    <date month="March" year="1995"/>
1720  </front>
1721  <seriesInfo name="RFC" value="1766"/>
1722</reference>
1723
1724<reference anchor="RFC2045">
1725  <front>
1726    <title abbrev="Internet Message Bodies">Multipurpose Internet Mail Extensions (MIME) Part One: Format of Internet Message Bodies</title>
1727    <author initials="N." surname="Freed" fullname="Ned Freed">
1728      <organization>Innosoft International, Inc.</organization>
1729      <address><email>ned@innosoft.com</email></address>
1730    </author>
1731    <author initials="N.S." surname="Borenstein" fullname="Nathaniel S. Borenstein">
1732      <organization>First Virtual Holdings</organization>
1733      <address><email>nsb@nsb.fv.com</email></address>
1734    </author>
1735    <date month="November" year="1996"/>
1736  </front>
1737  <seriesInfo name="RFC" value="2045"/>
1738</reference>
1739
1740<reference anchor="RFC822">
1741  <front>
1742    <title abbrev="Standard for ARPA Internet Text Messages">Standard for the format of ARPA Internet text messages</title>
1743    <author initials="D.H." surname="Crocker" fullname="David H. Crocker">
1744      <organization>University of Delaware, Dept. of Electrical Engineering</organization>
1745      <address><email>DCrocker@UDel-Relay</email></address>
1746    </author>
1747    <date month="August" day="13" year="1982"/>
1748  </front>
1749  <seriesInfo name="STD" value="11"/>
1750  <seriesInfo name="RFC" value="822"/>
1751</reference>
1752
1753<reference anchor="RFC1867">
1754  <front>
1755    <title>Form-based File Upload in HTML</title>
1756    <author initials="L." surname="Masinter" fullname="Larry Masinter">
1757      <organization>Xerox Palo Alto Research Center</organization>
1758      <address><email>masinter@parc.xerox.com</email></address>
1759    </author>
1760    <author initials="E." surname="Nebel" fullname="Ernesto Nebel">
1761      <organization>XSoft, Xerox Corporation</organization>
1762      <address><email>nebel@xsoft.sd.xerox.com</email></address>
1763    </author>
1764    <date month="November" year="1995"/>
1765  </front>
1766  <seriesInfo name="RFC" value="1867"/>
1767</reference>
1768
1769<reference anchor="RFC4288">
1770  <front>
1771    <title>Media Type Specifications and Registration Procedures</title>
1772    <author initials="N." surname="Freed" fullname="N. Freed">
1773      <organization>Sun Microsystems</organization>
1774      <address>
1775        <email>ned.freed@mrochek.com</email>
1776      </address>
1777    </author>
1778    <author initials="J." surname="Klensin" fullname="J. Klensin">
1779      <organization/>
1780      <address>
1781        <email>klensin+ietf@jck.com</email>
1782      </address>
1783    </author>
1784    <date year="2005" month="December"/>
1785  </front>
1786  <seriesInfo name="BCP" value="13"/>
1787  <seriesInfo name="RFC" value="4288"/>
1788</reference>
1789
1790<reference anchor="RFC1864">
1791  <front>
1792    <title abbrev="Content-MD5 Header Field">The Content-MD5 Header Field</title>
1793    <author initials="J." surname="Myers" fullname="John G. Myers">
1794      <organization>Carnegie Mellon University</organization>
1795      <address><email>jgm+@cmu.edu</email></address>
1796    </author>
1797    <author initials="M." surname="Rose" fullname="Marshall T. Rose">
1798      <organization>Dover Beach Consulting, Inc.</organization>
1799      <address><email>mrose@dbc.mtview.ca.us</email></address>
1800    </author>
1801    <date month="October" year="1995"/>
1802  </front>
1803  <seriesInfo name="RFC" value="1864"/>
1804</reference>
1805
1806<reference anchor="RFC1952">
1807  <front>
1808    <title>GZIP file format specification version 4.3</title>
1809    <author initials="P." surname="Deutsch" fullname="L. Peter Deutsch">
1810      <organization>Aladdin Enterprises</organization>
1811      <address><email>ghost@aladdin.com</email></address>
1812    </author>
1813    <author initials="J-L." surname="Gailly" fullname="Jean-Loup Gailly">
1814      <organization/>
1815      <address><email>gzip@prep.ai.mit.edu</email></address></author>
1816    <author initials="M." surname="Adler" fullname="Mark Adler">
1817      <organization/>
1818      <address><email>madler@alumni.caltech.edu</email></address></author>
1819    <author initials="L.P." surname="Deutsch" fullname="L. Peter Deutsch">
1820      <organization/>
1821      <address><email>ghost@aladdin.com</email></address>
1822    </author>
1823    <author initials="G." surname="Randers-Pehrson" fullname="Glenn Randers-Pehrson">
1824      <organization/>
1825      <address><email>randeg@alumni.rpi.edu</email></address>
1826    </author>
1827    <date month="May" year="1996"/>
1828  </front>
1829  <seriesInfo name="RFC" value="1952"/>
1830</reference>
1831
1832<reference anchor="RFC1951">
1833  <front>
1834    <title>DEFLATE Compressed Data Format Specification version 1.3</title>
1835    <author initials="P." surname="Deutsch" fullname="L. Peter Deutsch">
1836      <organization>Aladdin Enterprises</organization>
1837      <address><email>ghost@aladdin.com</email></address>
1838    </author>
1839    <date month="May" year="1996"/>
1840  </front>
1841  <seriesInfo name="RFC" value="1951"/>
1842</reference>
1843
1844<reference anchor="RFC1950">
1845  <front>
1846    <title>ZLIB Compressed Data Format Specification version 3.3</title>
1847    <author initials="L.P." surname="Deutsch" fullname="L. Peter Deutsch">
1848      <organization>Aladdin Enterprises</organization>
1849      <address><email>ghost@aladdin.com</email></address>
1850    </author>
1851    <author initials="J-L." surname="Gailly" fullname="Jean-Loup Gailly">
1852      <organization/>
1853    </author>
1854    <date month="May" year="1996"/>
1855  </front>
1856  <seriesInfo name="RFC" value="1950"/>
1857</reference>
1858
1859<reference anchor="RFC2068">
1860  <front>
1861    <title abbrev="HTTP/1.1">Hypertext Transfer Protocol -- HTTP/1.1</title>
1862    <author initials="R." surname="Fielding" fullname="Roy T. Fielding">
1863      <organization>University of California, Irvine, Department of Information and Computer Science</organization>
1864      <address><email>fielding@ics.uci.edu</email></address>
1865    </author>
1866    <author initials="J." surname="Gettys" fullname="Jim Gettys">
1867      <organization>MIT Laboratory for Computer Science</organization>
1868      <address><email>jg@w3.org</email></address>
1869    </author>
1870    <author initials="J." surname="Mogul" fullname="Jeffrey C. Mogul">
1871      <organization>Digital Equipment Corporation, Western Research Laboratory</organization>
1872      <address><email>mogul@wrl.dec.com</email></address>
1873    </author>
1874    <author initials="H." surname="Nielsen" fullname="Henrik Frystyk Nielsen">
1875      <organization>MIT Laboratory for Computer Science</organization>
1876      <address><email>frystyk@w3.org</email></address>
1877    </author>
1878    <author initials="T." surname="Berners-Lee" fullname="Tim Berners-Lee">
1879      <organization>MIT Laboratory for Computer Science</organization>
1880      <address><email>timbl@w3.org</email></address>
1881    </author>
1882    <date month="January" year="1997"/>
1883  </front>
1884  <seriesInfo name="RFC" value="2068"/>
1885</reference>
1886
1887<reference anchor="RFC1806">
1888  <front>
1889    <title abbrev="Content-Disposition">Communicating Presentation Information in Internet Messages: The Content-Disposition Header</title>
1890    <author initials="R." surname="Troost" fullname="Rens Troost">
1891      <organization>New Century Systems</organization>
1892      <address><email>rens@century.com</email></address>
1893    </author>
1894    <author initials="S." surname="Dorner" fullname="Steve Dorner">
1895      <organization>QUALCOMM Incorporated</organization>
1896      <address><email>sdorner@qualcomm.com</email></address>
1897    </author>
1898    <date month="June" year="1995"/>
1899  </front>
1900  <seriesInfo name="RFC" value="1806"/>
1901</reference>
1902
1903<reference anchor="RFC1945">
1904  <front>
1905    <title abbrev="HTTP/1.0">Hypertext Transfer Protocol -- HTTP/1.0</title>
1906    <author initials="T." surname="Berners-Lee" fullname="Tim Berners-Lee">
1907      <organization>MIT, Laboratory for Computer Science</organization>
1908      <address><email>timbl@w3.org</email></address>
1909    </author>
1910    <author initials="R.T." surname="Fielding" fullname="Roy T. Fielding">
1911      <organization>University of California, Irvine, Department of Information and Computer Science</organization>
1912      <address><email>fielding@ics.uci.edu</email></address>
1913    </author>
1914    <author initials="H.F." surname="Nielsen" fullname="Henrik Frystyk Nielsen">
1915      <organization>W3 Consortium, MIT Laboratory for Computer Science</organization>
1916      <address><email>frystyk@w3.org</email></address>
1917    </author>
1918    <date month="May" year="1996"/>
1919  </front>
1920  <seriesInfo name="RFC" value="1945"/>
1921</reference>
1922
1923<reference anchor="RFC2076">
1924  <front>
1925    <title abbrev="Internet Message Headers">Common Internet Message Headers</title>
1926    <author initials="J." surname="Palme" fullname="Jacob Palme">
1927      <organization>Stockholm University/KTH</organization>
1928      <address><email>jpalme@dsv.su.se</email></address>
1929    </author>
1930    <date month="February" year="1997"/>
1931  </front>
1932  <seriesInfo name="RFC" value="2076"/>
1933</reference>
1934
1935<reference anchor="RFC2119">
1936  <front>
1937    <title>Key words for use in RFCs to Indicate Requirement Levels</title>
1938    <author initials="S." surname="Bradner" fullname="Scott Bradner">
1939      <organization>Harvard University</organization>
1940      <address><email>sob@harvard.edu</email></address>
1941    </author>
1942    <date month="March" year="1997"/>
1943  </front>
1944  <seriesInfo name="BCP" value="14"/>
1945  <seriesInfo name="RFC" value="2119"/>
1946</reference>
1947
1948<reference anchor="RFC2279">
1949<front>
1950<title abbrev="UTF-8">UTF-8, a transformation format of ISO 10646</title>
1951<author initials="F." surname="Yergeau" fullname="Francois Yergeau">
1952<organization>Alis Technologies</organization>
1953<address>
1954<postal>
1955<street>100, boul. Alexis-Nihon</street>
1956<street>Suite 600</street>
1957<city>Montreal</city>
1958<region>Quebec</region>
1959<code>H4M 2P2</code>
1960<country>CA</country></postal>
1961<phone>+1 514 747 2547</phone>
1962<facsimile>+1 514 747 2561</facsimile>
1963<email>fyergeau@alis.com</email></address></author>
1964<date month="January" year="1998"/>
1965<abstract>
1966<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>
1967<seriesInfo name="RFC" value="2279"/>
1968</reference>
1969
1970<reference anchor="RFC2046">
1971  <front>
1972    <title abbrev="Media Types">Multipurpose Internet Mail Extensions (MIME) Part Two: Media Types</title>
1973    <author initials="N." surname="Freed" fullname="Ned Freed">
1974      <organization>Innosoft International, Inc.</organization>
1975      <address><email>ned@innosoft.com</email></address>
1976    </author>
1977    <author initials="N." surname="Borenstein" fullname="Nathaniel S. Borenstein">
1978      <organization>First Virtual Holdings</organization>
1979      <address><email>nsb@nsb.fv.com</email></address>
1980    </author>
1981    <date month="November" year="1996"/>
1982  </front>
1983  <seriesInfo name="RFC" value="2046"/>
1984</reference>
1985
1986<reference anchor="RFC2277">
1987<front>
1988<title abbrev="Charset Policy">IETF Policy on Character Sets and Languages</title>
1989<author initials="H.T." surname="Alvestrand" fullname="Harald Tveit Alvestrand">
1990<organization>UNINETT</organization>
1991<address>
1992<postal>
1993<street>P.O.Box 6883 Elgeseter</street>
1994<street>N-7002 TRONDHEIM</street>
1995<country>NORWAY</country></postal>
1996<phone>+47 73 59 70 94</phone>
1997<email>Harald.T.Alvestrand@uninett.no</email></address></author>
1998<date month="January" year="1998"/>
1999<area>Applications</area>
2000<keyword>Internet Engineering Task Force</keyword>
2001<keyword>character encoding</keyword></front>
2002<seriesInfo name="BCP" value="18"/>
2003<seriesInfo name="RFC" value="2277"/>
2004</reference>
2005
2006<reference anchor="RFC2110">
2007<front>
2008<title abbrev="MHTML">MIME E-mail Encapsulation of Aggregate Documents, such as HTML (MHTML)</title>
2009<author initials="J." surname="Palme" fullname="Jacob Palme">
2010<organization>Stockholm University and KTH</organization>
2011<address>
2012<postal>
2013<street>Electrum 230</street>
2014<street>S-164 40 Kista</street>
2015<country>Sweden</country></postal>
2016<phone>+46-8-16 16 67</phone>
2017<facsimile>+46-8-783 08 29</facsimile>
2018<email>jpalme@dsv.su.se</email></address></author>
2019<author initials="A." surname="Hopmann" fullname="Alex Hopmann">
2020<organization>Microsoft Corporation</organization>
2021<address>
2022<postal>
2023<street>3590 North First Street</street>
2024<street>Suite 300</street>
2025<street>San Jose</street>
2026<street>CA 95134</street>
2027<street>Working group chairman:</street></postal>
2028<email>alexhop@microsoft.com</email></address></author>
2029<date month="March" year="1997"/>
2030<area>Applications</area>
2031<keyword>encapsulate</keyword>
2032<keyword>hypertext markup language</keyword>
2033<keyword>mail</keyword>
2034<keyword>multipurpose internet mail extensions</keyword>
2035</front>
2036<seriesInfo name="RFC" value="2110"/>
2037</reference>
2038
2039<reference anchor="RFC2049">
2040  <front>
2041    <title abbrev="MIME Conformance">Multipurpose Internet Mail Extensions (MIME) Part Five: Conformance Criteria and Examples</title>
2042    <author initials="N." surname="Freed" fullname="Ned Freed">
2043      <organization>Innosoft International, Inc.</organization>
2044      <address><email>ned@innosoft.com</email></address>
2045    </author>
2046    <author initials="N.S." surname="Borenstein" fullname="Nathaniel S. Borenstein">
2047      <organization>First Virtual Holdings</organization>
2048      <address><email>nsb@nsb.fv.com</email></address>
2049    </author>
2050    <date month="November" year="1996"/>
2051  </front>
2052  <seriesInfo name="RFC" value="2049"/>
2053</reference>
2054
2055<reference anchor="RFC2183">
2056  <front>
2057    <title abbrev="Content-Disposition">Communicating Presentation Information in Internet Messages: The Content-Disposition Header Field</title>
2058    <author initials="R." surname="Troost" fullname="Rens Troost">
2059      <organization>New Century Systems</organization>
2060      <address><email>rens@century.com</email></address>
2061    </author>
2062    <author initials="S." surname="Dorner" fullname="Steve Dorner">
2063      <organization>QUALCOMM Incorporated</organization>
2064      <address><email>sdorner@qualcomm.com</email></address>
2065    </author>
2066    <author initials="K." surname="Moore" fullname="Keith Moore">
2067      <organization>Department of Computer Science</organization>
2068      <address><email>moore@cs.utk.edu</email></address>
2069    </author>
2070    <date month="August" year="1997"/>
2071  </front>
2072  <seriesInfo name="RFC" value="2183"/>
2073</reference>
2074
2075</references>
2076
2077<section title="Differences Between HTTP Entities and RFC 2045 Entities" anchor="differences.between.http.entities.and.rfc.2045.entities">
2078<t>
2079   HTTP/1.1 uses many of the constructs defined for Internet Mail (<xref target="RFC822"/>) and the Multipurpose Internet Mail Extensions (MIME <xref target="RFC2045"/>) to
2080   allow entities to be transmitted in an open variety of
2081   representations and with extensible mechanisms. However, RFC 2045
2082   discusses mail, and HTTP has a few features that are different from
2083   those described in RFC 2045. These differences were carefully chosen
2084   to optimize performance over binary connections, to allow greater
2085   freedom in the use of new media types, to make date comparisons
2086   easier, and to acknowledge the practice of some early HTTP servers
2087   and clients.
2088</t>
2089<t>
2090   This appendix describes specific areas where HTTP differs from RFC
2091   2045. Proxies and gateways to strict MIME environments &SHOULD; be
2092   aware of these differences and provide the appropriate conversions
2093   where necessary. Proxies and gateways from MIME environments to HTTP
2094   also need to be aware of the differences because some conversions
2095   might be required.
2096</t>
2097<section title="MIME-Version" anchor="mime-version">
2098<t>
2099   HTTP is not a MIME-compliant protocol. However, HTTP/1.1 messages &MAY;
2100   include a single MIME-Version general-header field to indicate what
2101   version of the MIME protocol was used to construct the message. Use
2102   of the MIME-Version header field indicates that the message is in
2103   full compliance with the MIME protocol (as defined in <xref target="RFC2045"/>).
2104   Proxies/gateways are responsible for ensuring full compliance (where
2105   possible) when exporting HTTP messages to strict MIME environments.
2106</t>
2107<figure><artwork type="abnf2616"><iref primary="true" item="Grammar" subitem="MIME-Version"/>
2108    MIME-Version   = "MIME-Version" ":" 1*DIGIT "." 1*DIGIT
2109</artwork></figure>
2110<t>
2111   MIME version "1.0" is the default for use in HTTP/1.1. However,
2112   HTTP/1.1 message parsing and semantics are defined by this document
2113   and not the MIME specification.
2114</t>
2115</section>
2116
2117<section title="Conversion to Canonical Form" anchor="conversion.to.canonical.form">
2118<t>
2119   <xref target="RFC2045"/> requires that an Internet mail entity be converted to
2120   canonical form prior to being transferred, as described in <xref target="RFC2049" x:fmt="of" x:sec="4"/>.
2121   <xref target="canonicalization.and.text.defaults"/> of this document describes the forms
2122   allowed for subtypes of the "text" media type when transmitted over
2123   HTTP. <xref target="RFC2046"/> requires that content with a type of "text" represent
2124   line breaks as CRLF and forbids the use of CR or LF outside of line
2125   break sequences. HTTP allows CRLF, bare CR, and bare LF to indicate a
2126   line break within text content when a message is transmitted over
2127   HTTP.
2128</t>
2129<t>
2130   Where it is possible, a proxy or gateway from HTTP to a strict MIME
2131   environment &SHOULD; translate all line breaks within the text media
2132   types described in <xref target="canonicalization.and.text.defaults"/> of this document to the RFC 2049
2133   canonical form of CRLF. Note, however, that this might be complicated
2134   by the presence of a Content-Encoding and by the fact that HTTP
2135   allows the use of some character sets which do not use octets 13 and
2136   10 to represent CR and LF, as is the case for some multi-byte
2137   character sets.
2138</t>
2139<t>
2140   Implementors should note that conversion will break any cryptographic
2141   checksums applied to the original content unless the original content
2142   is already in canonical form. Therefore, the canonical form is
2143   recommended for any content that uses such checksums in HTTP.
2144</t>
2145</section>
2146
2147<section title="Introduction of Content-Encoding" anchor="introduction.of.content-encoding">
2148<t>
2149   RFC 2045 does not include any concept equivalent to HTTP/1.1's
2150   Content-Encoding header field. Since this acts as a modifier on the
2151   media type, proxies and gateways from HTTP to MIME-compliant
2152   protocols &MUST; either change the value of the Content-Type header
2153   field or decode the entity-body before forwarding the message. (Some
2154   experimental applications of Content-Type for Internet mail have used
2155   a media-type parameter of ";conversions=&lt;content-coding&gt;" to perform
2156   a function equivalent to Content-Encoding. However, this parameter is
2157   not part of RFC 2045).
2158</t>
2159</section>
2160
2161<section title="No Content-Transfer-Encoding" anchor="no.content-transfer-encoding">
2162<t>
2163   HTTP does not use the Content-Transfer-Encoding field of RFC
2164   2045. Proxies and gateways from MIME-compliant protocols to HTTP &MUST;
2165   remove any Content-Transfer-Encoding
2166   prior to delivering the response message to an HTTP client.
2167</t>
2168<t>
2169   Proxies and gateways from HTTP to MIME-compliant protocols are
2170   responsible for ensuring that the message is in the correct format
2171   and encoding for safe transport on that protocol, where "safe
2172   transport" is defined by the limitations of the protocol being used.
2173   Such a proxy or gateway &SHOULD; label the data with an appropriate
2174   Content-Transfer-Encoding if doing so will improve the likelihood of
2175   safe transport over the destination protocol.
2176</t>
2177</section>
2178
2179<section title="Introduction of Transfer-Encoding" anchor="introduction.of.transfer-encoding">
2180<t>
2181   HTTP/1.1 introduces the Transfer-Encoding header field (&header-transfer-encoding;).
2182   Proxies/gateways &MUST; remove any transfer-coding prior to
2183   forwarding a message via a MIME-compliant protocol.
2184</t>
2185</section>
2186
2187<section title="MHTML and Line Length Limitations" anchor="mhtml.line.length">
2188<t>
2189   HTTP implementations which share code with MHTML <xref target="RFC2110"/> implementations
2190   need to be aware of MIME line length limitations. Since HTTP does not
2191   have this limitation, HTTP does not fold long lines. MHTML messages
2192   being transported by HTTP follow all conventions of MHTML, including
2193   line length limitations and folding, canonicalization, etc., since
2194   HTTP transports all message-bodies as payload (see <xref target="multipart.types"/>) and
2195   does not interpret the content or any MIME header lines that might be
2196   contained therein.
2197</t>
2198</section>
2199</section>
2200
2201<section title="Additional Features" anchor="additional.features">
2202<t>
2203   <xref target="RFC1945"/> and <xref target="RFC2068"/> document protocol elements used by some
2204   existing HTTP implementations, but not consistently and correctly
2205   across most HTTP/1.1 applications. Implementors are advised to be
2206   aware of these features, but cannot rely upon their presence in, or
2207   interoperability with, other HTTP/1.1 applications. Some of these
2208   describe proposed experimental features, and some describe features
2209   that experimental deployment found lacking that are now addressed in
2210   the base HTTP/1.1 specification.
2211</t>
2212<t>
2213   A number of other headers, such as Content-Disposition and Title,
2214   from SMTP and MIME are also often implemented (see <xref target="RFC2076"/>).
2215</t>
2216
2217<section title="Content-Disposition" anchor="content-disposition">
2218<iref item="Headers" subitem="Content-Disposition" primary="true" x:for-anchor=""/>
2219<iref item="Content-Disposition header" primary="true" x:for-anchor=""/>
2220<t>
2221   The Content-Disposition response-header field has been proposed as a
2222   means for the origin server to suggest a default filename if the user
2223   requests that the content is saved to a file. This usage is derived
2224   from the definition of Content-Disposition in <xref target="RFC1806"/>.
2225</t>
2226<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"/>
2227     content-disposition = "Content-Disposition" ":"
2228                           disposition-type *( ";" disposition-parm )
2229     disposition-type = "attachment" | disp-extension-token
2230     disposition-parm = filename-parm | disp-extension-parm
2231     filename-parm = "filename" "=" quoted-string
2232     disp-extension-token = token
2233     disp-extension-parm = token "=" ( token | quoted-string )
2234</artwork></figure>
2235<t>
2236   An example is
2237</t>
2238<figure><artwork type="example">
2239     Content-Disposition: attachment; filename="fname.ext"
2240</artwork></figure>
2241<t>
2242   The receiving user agent &SHOULD-NOT;  respect any directory path
2243   information present in the filename-parm parameter, which is the only
2244   parameter believed to apply to HTTP implementations at this time. The
2245   filename &SHOULD; be treated as a terminal component only.
2246</t>
2247<t>
2248   If this header is used in a response with the application/octet-stream
2249   content-type, the implied suggestion is that the user agent
2250   should not display the response, but directly enter a `save response
2251   as...' dialog.
2252</t>
2253<t>
2254   See <xref target="content-disposition.issues"/> for Content-Disposition security issues.
2255</t>
2256</section>
2257</section>
2258
2259<section title="Compatibility with Previous Versions" anchor="compatibility">
2260<section title="Changes from RFC 2068" anchor="changes.from.rfc.2068">
2261<t>
2262   Charset wildcarding is introduced to avoid explosion of character set
2263   names in accept headers. (<xref target="header.accept-charset"/>)
2264</t>
2265<t>
2266   Content-Base was deleted from the specification: it was not
2267   implemented widely, and there is no simple, safe way to introduce it
2268   without a robust extension mechanism. In addition, it is used in a
2269   similar, but not identical fashion in MHTML <xref target="RFC2110"/>.
2270</t>
2271<t>
2272   A content-coding of "identity" was introduced, to solve problems
2273   discovered in caching. (<xref target="content.codings"/>)
2274</t>
2275<t>
2276   Quality Values of zero should indicate that "I don't want something"
2277   to allow clients to refuse a representation. (<xref target="quality.values"/>)
2278</t>
2279<t>
2280   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
2281   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
2282   specification, but not commonly implemented. See <xref target="RFC2068"/>.
2283</t>
2284</section>
2285
2286<section title="Changes from RFC 2616" anchor="changes.from.rfc.2616">
2287<t>
2288  Clarify contexts that charset is used in.
2289  (<xref target="character.sets"/>)
2290</t>
2291<t>
2292  Remove reference to non-existant identity transfer-coding value tokens.
2293  (<xref target="no.content-transfer-encoding"/>)
2294</t>
2295</section>
2296
2297</section>
2298
2299<section title="Change Log (to be removed by RFC Editor before publication)">
2300
2301<section title="Since RFC2616">
2302<t>
2303  Extracted relevant partitions from <xref target="RFC2616"/>.
2304</t>
2305</section>
2306
2307<section title="Since draft-ietf-httpbis-p3-payload-00">
2308<t>
2309  Closed issues:
2310  <list style="symbols"> 
2311    <t>
2312      <eref target="http://www3.tools.ietf.org/wg/httpbis/trac/ticket/8"/>:
2313      "Media Type Registrations"
2314      (<eref target="http://purl.org/NET/http-errata#media-reg"/>)
2315    </t>
2316    <t>
2317      <eref target="http://www3.tools.ietf.org/wg/httpbis/trac/ticket/14"/>:
2318      "Clarification regarding quoting of charset values"
2319      (<eref target="http://purl.org/NET/http-errata#charactersets"/>)
2320    </t>
2321    <t>
2322      <eref target="http://www3.tools.ietf.org/wg/httpbis/trac/ticket/16"/>:
2323      "Remove 'identity' token references"
2324      (<eref target="http://purl.org/NET/http-errata#identity"/>)
2325    </t>
2326    <t>
2327      <eref target="http://www3.tools.ietf.org/wg/httpbis/trac/ticket/46"/>:
2328      "RFC1700 references"
2329    </t>
2330  </list>
2331</t>
2332</section>
2333
2334</section>
2335
2336</back>
2337</rfc>
Note: See TracBrowser for help on using the repository browser.