source: draft-ietf-httpbis/latest/p3-payload.xml @ 96

Last change on this file since 96 was 96, checked in by julian.reschke@…, 12 years ago

Add "Requirements" subsection everywhere (including reference to RFC2119), add missing bcp14 markup.

  • Property svn:eol-style set to native
File size: 110.1 KB
Line 
1<?xml version="1.0" encoding="utf-8"?>
2<!DOCTYPE rfc [
3  <!ENTITY MAY "<bcp14 xmlns='http://purl.org/net/xml2rfc/ext'>MAY</bcp14>">
4  <!ENTITY MUST "<bcp14 xmlns='http://purl.org/net/xml2rfc/ext'>MUST</bcp14>">
5  <!ENTITY MUST-NOT "<bcp14 xmlns='http://purl.org/net/xml2rfc/ext'>MUST NOT</bcp14>">
6  <!ENTITY OPTIONAL "<bcp14 xmlns='http://purl.org/net/xml2rfc/ext'>OPTIONAL</bcp14>">
7  <!ENTITY RECOMMENDED "<bcp14 xmlns='http://purl.org/net/xml2rfc/ext'>RECOMMENDED</bcp14>">
8  <!ENTITY REQUIRED "<bcp14 xmlns='http://purl.org/net/xml2rfc/ext'>REQUIRED</bcp14>">
9  <!ENTITY SHALL "<bcp14 xmlns='http://purl.org/net/xml2rfc/ext'>SHALL</bcp14>">
10  <!ENTITY SHALL-NOT "<bcp14 xmlns='http://purl.org/net/xml2rfc/ext'>SHALL NOT</bcp14>">
11  <!ENTITY SHOULD "<bcp14 xmlns='http://purl.org/net/xml2rfc/ext'>SHOULD</bcp14>">
12  <!ENTITY SHOULD-NOT "<bcp14 xmlns='http://purl.org/net/xml2rfc/ext'>SHOULD NOT</bcp14>">
13  <!ENTITY ID-VERSION "latest">
14  <!ENTITY ID-MONTH "December">
15  <!ENTITY ID-YEAR "2007">
16  <!ENTITY caching                  "<xref target='Part6' xmlns:x='http://purl.org/net/xml2rfc/ext'/>">
17  <!ENTITY header-transfer-encoding "<xref target='Part1' x:rel='#header.transfer-encoding' xmlns:x='http://purl.org/net/xml2rfc/ext'/>">
18  <!ENTITY header-allow             "<xref target='Part2' x:rel='#header.allow' xmlns:x='http://purl.org/net/xml2rfc/ext'/>">
19  <!ENTITY header-content-length    "<xref target='Part1' x:rel='#header.content-length' xmlns:x='http://purl.org/net/xml2rfc/ext'/>">
20  <!ENTITY header-content-range     "<xref target='Part5' x:rel='#header.content-range' xmlns:x='http://purl.org/net/xml2rfc/ext'/>">
21  <!ENTITY header-expires           "<xref target='Part6' x:rel='#header.expires' xmlns:x='http://purl.org/net/xml2rfc/ext'/>">
22  <!ENTITY header-last-modified     "<xref target='Part4' x:rel='#header.last-modified' xmlns:x='http://purl.org/net/xml2rfc/ext'/>">
23  <!ENTITY header-user-agent        "<xref target='Part2' x:rel='#header.user-agent' xmlns:x='http://purl.org/net/xml2rfc/ext'/>">
24  <!ENTITY message-body             "<xref target='Part1' x:rel='#message.body' xmlns:x='http://purl.org/net/xml2rfc/ext'/>">
25  <!ENTITY message-length           "<xref target='Part1' x:rel='#message.length' xmlns:x='http://purl.org/net/xml2rfc/ext'/>">
26  <!ENTITY multipart-byteranges     "<xref target='Part5' x:rel='#internet.media.type.multipart.byteranges' xmlns:x='http://purl.org/net/xml2rfc/ext'/>">
27]>
28<?rfc toc="yes" ?>
29<?rfc symrefs="yes" ?>
30<?rfc sortrefs="yes" ?>
31<?rfc compact="yes"?>
32<?rfc subcompact="no" ?>
33<?rfc linkmailto="no" ?>
34<?rfc editing="no" ?>
35<?rfc-ext allow-markup-in-artwork="yes" ?>
36<?rfc-ext include-references-in-index="yes" ?>
37<rfc obsoletes="2068, 2616" category="std"
38     ipr="full3978" docName="draft-ietf-httpbis-p3-payload-&ID-VERSION;"
39     xmlns:x='http://purl.org/net/xml2rfc/ext' xmlns:ed="http://greenbytes.de/2002/rfcedit">
40<front>
41
42  <title abbrev="HTTP/1.1">HTTP/1.1, part 3: Message Payload and Content Negotiation</title>
43
44  <author initials="R." surname="Fielding" fullname="Roy T. Fielding" role="editor">
45    <organization abbrev="Day Software">Day Software</organization>
46    <address>
47      <postal>
48        <street>23 Corporate Plaza DR, Suite 280</street>
49        <city>Newport Beach</city>
50        <region>CA</region>
51        <code>92660</code>
52        <country>USA</country>
53      </postal>
54      <phone>+1-949-706-5300</phone>
55      <facsimile>+1-949-706-5305</facsimile>
56      <email>fielding@gbiv.com</email>
57      <uri>http://roy.gbiv.com/</uri>
58    </address>
59  </author>
60
61  <author initials="J." surname="Gettys" fullname="Jim Gettys">
62    <organization>One Laptop per Child</organization>
63    <address>
64      <postal>
65        <street>21 Oak Knoll Road</street>
66        <city>Carlisle</city>
67        <region>MA</region>
68        <code>01741</code>
69        <country>USA</country>
70      </postal>
71      <email>jg@laptop.org</email>
72      <uri>http://www.laptop.org/</uri>
73    </address>
74  </author>
75 
76  <author initials="J." surname="Mogul" fullname="Jeffrey C. Mogul">
77    <organization abbrev="HP">Hewlett-Packard Company</organization>
78    <address>
79      <postal>
80        <street>HP Labs, Large Scale Systems Group</street>
81        <street>1501 Page Mill Road, MS 1177</street>
82        <city>Palo Alto</city>
83        <region>CA</region>
84        <code>94304</code>
85        <country>USA</country>
86      </postal>
87      <email>JeffMogul@acm.org</email>
88    </address>
89  </author>
90
91  <author initials="H." surname="Frystyk" fullname="Henrik Frystyk Nielsen">
92    <organization abbrev="Microsoft">Microsoft Corporation</organization>
93    <address>
94      <postal>
95        <street>1 Microsoft Way</street>
96        <city>Redmond</city>
97        <region>WA</region>
98        <code>98052</code>
99        <country>USA</country>
100      </postal>
101      <email>henrikn@microsoft.com</email>
102    </address>
103  </author>
104
105  <author initials="L." surname="Masinter" fullname="Larry Masinter">
106    <organization abbrev="Adobe Systems">Adobe Systems, Incorporated</organization>
107    <address>
108      <postal>
109        <street>345 Park Ave</street>
110        <city>San Jose</city>
111        <region>CA</region>
112        <code>95110</code>
113        <country>USA</country>
114      </postal>
115      <email>LMM@acm.org</email>
116      <uri>http://larry.masinter.net/</uri>
117    </address>
118  </author>
119 
120  <author initials="P." surname="Leach" fullname="Paul J. Leach">
121    <organization abbrev="Microsoft">Microsoft Corporation</organization>
122    <address>
123      <postal>
124        <street>1 Microsoft Way</street>
125        <city>Redmond</city>
126        <region>WA</region>
127        <code>98052</code>
128      </postal>
129      <email>paulle@microsoft.com</email>
130    </address>
131  </author>
132   
133  <author initials="T." surname="Berners-Lee" fullname="Tim Berners-Lee">
134    <organization abbrev="W3C/MIT">World Wide Web Consortium</organization>
135    <address>
136      <postal>
137        <street>MIT Computer Science and Artificial Intelligence Laboratory</street>
138        <street>The Stata Center, Building 32</street>
139        <street>32 Vassar Street</street>
140        <city>Cambridge</city>
141        <region>MA</region>
142        <code>02139</code>
143        <country>USA</country>
144      </postal>
145      <email>timbl@w3.org</email>
146      <uri>http://www.w3.org/People/Berners-Lee/</uri>
147    </address>
148  </author>
149
150  <author initials="Y." surname="Lafon" fullname="Yves Lafon" role="editor">
151    <organization abbrev="W3C">World Wide Web Consortium</organization>
152    <address>
153      <postal>
154        <street>W3C / ERCIM</street>
155        <street>2004, rte des Lucioles</street>
156        <city>Sophia-Antipolis</city>
157        <region>AM</region>
158        <code>06902</code>
159        <country>France</country>
160      </postal>
161      <email>ylafon@w3.org</email>
162      <uri>http://www.raubacapeu.net/people/yves/</uri>
163    </address>
164  </author>
165
166  <author initials="J. F." surname="Reschke" fullname="Julian F. Reschke" role="editor">
167    <organization abbrev="greenbytes">greenbytes GmbH</organization>
168    <address>
169      <postal>
170        <street>Hafenweg 16</street>
171        <city>Muenster</city><region>NW</region><code>48155</code>
172        <country>Germany</country>
173      </postal>
174      <phone>+49 251 2807760</phone>   
175      <facsimile>+49 251 2807761</facsimile>   
176      <email>julian.reschke@greenbytes.de</email>       
177      <uri>http://greenbytes.de/tech/webdav/</uri>     
178    </address>
179  </author>
180
181  <date month="&ID-MONTH;" year="&ID-YEAR;"/>
182
183<abstract>
184<t>
185   The Hypertext Transfer Protocol (HTTP) is an application-level
186   protocol for distributed, collaborative, hypermedia information
187   systems. HTTP has been in use by the World Wide Web global information
188   initiative since 1990. This document is Part 3 of the seven-part specification
189   that defines the protocol referred to as "HTTP/1.1" and, taken together,
190   obsoletes RFC 2616.  Part 3 defines HTTP message content,
191   metadata, and content negotiation.
192</t>
193</abstract>
194
195<note title="Editorial Note (To be removed by RFC Editor)">
196  <t>
197    This version of the HTTP specification contains only minimal editorial
198    changes from <xref target="RFC2616"/> (abstract, introductory paragraph,
199    and authors' addresses).  All other changes are due to partitioning the
200    original into seven mostly independent parts.  The intent is for readers
201    of future drafts to able to use draft 00 as the basis for comparison
202    when the WG makes later changes to the specification text.  This draft
203    will shortly be followed by draft 01 (containing the first round of changes
204    that have already been agreed to on the mailing list). There is no point in
205    reviewing this draft other than to verify that the partitioning has been
206    done correctly.  Roy T. Fielding, Yves Lafon, and Julian Reschke
207    will be the editors after draft 00 is submitted.
208  </t>
209  <t>
210    Discussion of this draft should take place on the HTTPBIS working group
211    mailing list (ietf-http-wg@w3.org). The current issues list is
212    at <eref target="http://www3.tools.ietf.org/wg/httpbis/trac/report/11"/>
213    and related documents (including fancy diffs) can be found at
214    <eref target="http://www3.tools.ietf.org/wg/httpbis/"/>.
215  </t>
216</note>
217</front>
218<middle>
219<section title="Introduction" anchor="introduction">
220<t>
221   This document will define aspects of HTTP related to the payload of
222   messages (message content), including metadata and media types, along
223   with HTTP content negotiation.  Right now it only includes the extracted
224   relevant sections of RFC 2616 without edit.
225</t>
226
227<section title="Requirements" anchor="intro.requirements">
228<t>
229   The key words "MUST", "MUST NOT", "REQUIRED", "SHALL", "SHALL NOT",
230   "SHOULD", "SHOULD NOT", "RECOMMENDED", "MAY", and "OPTIONAL" in this
231   document are to be interpreted as described in <xref target="RFC2119"/>.
232</t>
233<t>
234   An implementation is not compliant if it fails to satisfy one or more
235   of the &MUST; or &REQUIRED; level requirements for the protocols it
236   implements. An implementation that satisfies all the &MUST; or &REQUIRED;
237   level and all the &SHOULD; level requirements for its protocols is said
238   to be "unconditionally compliant"; one that satisfies all the &MUST;
239   level requirements but not all the &SHOULD; level requirements for its
240   protocols is said to be "conditionally compliant."
241</t>
242</section>
243</section>
244
245<section title="Protocol Parameters" anchor="protocol.parameters">
246
247<section title="Character Sets" anchor="character.sets">
248<t>
249   HTTP uses the same definition of the term "character set" as that
250   described for MIME:
251</t>
252<t>
253   The term "character set" is used in this document to refer to a
254   method used with one or more tables to convert a sequence of octets
255   into a sequence of characters. Note that unconditional conversion in
256   the other direction is not required, in that not all characters may
257   be available in a given character set and a character set may provide
258   more than one sequence of octets to represent a particular character.
259   This definition is intended to allow various kinds of character
260   encoding, from simple single-table mappings such as US-ASCII to
261   complex table switching methods such as those that use ISO-2022's
262   techniques. However, the definition associated with a MIME character
263   set name &MUST; fully specify the mapping to be performed from octets
264   to characters. In particular, use of external profiling information
265   to determine the exact mapping is not permitted.
266</t>
267<t><list><t>
268      <x:h>Note:</x:h> This use of the term "character set" is more commonly
269      referred to as a "character encoding." However, since HTTP and
270      MIME share the same registry, it is important that the terminology
271      also be shared.
272</t></list></t>
273<t>
274   HTTP character sets are identified by case-insensitive tokens. The
275   complete set of tokens is defined by the IANA Character Set registry
276   (<eref target="http://www.iana.org/assignments/character-sets"/>).
277</t>
278<figure><artwork type="abnf2616"><iref primary="true" item="Grammar" subitem="charset"/>
279    charset = token
280</artwork></figure>
281<t>
282   Although HTTP allows an arbitrary token to be used as a charset
283   value, any token that has a predefined value within the IANA
284   Character Set registry &MUST; represent the character set defined
285   by that registry. Applications &SHOULD; limit their use of character
286   sets to those defined by the IANA registry.
287</t>
288<t>
289   HTTP uses charset in two contexts: within an Accept-Charset request
290   header (in which the charset value is an unquoted token) and as the
291   value of a parameter in a Content-type header (within a request or
292   response), in which case the parameter value of the charset parameter
293   may be quoted.
294</t>
295<t>
296   Implementors should be aware of IETF character set requirements <xref target="RFC2279"/>
297   <xref target="RFC2277"/>.
298</t>
299
300<section title="Missing Charset" anchor="missing.charset">
301<t>
302   Some HTTP/1.0 software has interpreted a Content-Type header without
303   charset parameter incorrectly to mean "recipient should guess."
304   Senders wishing to defeat this behavior &MAY; include a charset
305   parameter even when the charset is ISO-8859-1 and &SHOULD; do so when
306   it is known that it will not confuse the recipient.
307</t>
308<t>
309   Unfortunately, some older HTTP/1.0 clients did not deal properly with
310   an explicit charset parameter. HTTP/1.1 recipients &MUST; respect the
311   charset label provided by the sender; and those user agents that have
312   a provision to "guess" a charset &MUST; use the charset from the
313   content-type field if they support that charset, rather than the
314   recipient's preference, when initially displaying a document. See
315   <xref target="canonicalization.and.text.defaults"/>.
316</t>
317</section>
318</section>
319
320<section title="Content Codings" anchor="content.codings">
321<t>
322   Content coding values indicate an encoding transformation that has
323   been or can be applied to an entity. Content codings are primarily
324   used to allow a document to be compressed or otherwise usefully
325   transformed without losing the identity of its underlying media type
326   and without loss of information. Frequently, the entity is stored in
327   coded form, transmitted directly, and only decoded by the recipient.
328</t>
329<figure><artwork type="abnf2616"><iref primary="true" item="Grammar" subitem="content-coding"/>
330    content-coding   = token
331</artwork></figure>
332<t>
333   All content-coding values are case-insensitive. HTTP/1.1 uses
334   content-coding values in the Accept-Encoding (<xref target="header.accept-encoding"/>) and
335   Content-Encoding (<xref target="header.content-encoding"/>) header fields. Although the value
336   describes the content-coding, what is more important is that it
337   indicates what decoding mechanism will be required to remove the
338   encoding.
339</t>
340<t>
341   The Internet Assigned Numbers Authority (IANA) acts as a registry for
342   content-coding value tokens. Initially, the registry contains the
343   following tokens:
344</t>
345<t>
346   gzip<iref item="gzip"/>
347  <list>
348    <t>
349        An encoding format produced by the file compression program
350        "gzip" (GNU zip) as described in RFC 1952 <xref target="RFC1952"/>. This format is a
351        Lempel-Ziv coding (LZ77) with a 32 bit CRC.
352    </t>
353  </list>
354</t>
355<t>
356   compress<iref item="compress"/>
357  <list><t>
358        The encoding format produced by the common UNIX file compression
359        program "compress". This format is an adaptive Lempel-Ziv-Welch
360        coding (LZW).
361</t><t>
362        Use of program names for the identification of encoding formats
363        is not desirable and is discouraged for future encodings. Their
364        use here is representative of historical practice, not good
365        design. For compatibility with previous implementations of HTTP,
366        applications &SHOULD; consider "x-gzip" and "x-compress" to be
367        equivalent to "gzip" and "compress" respectively.
368  </t></list>
369</t>
370<t>
371   deflate<iref item="deflate"/>
372  <list><t>
373        The "zlib" format defined in RFC 1950 <xref target="RFC1950"/> in combination with
374        the "deflate" compression mechanism described in RFC 1951 <xref target="RFC1951"/>.
375  </t></list>
376</t>
377<t>
378   identity<iref item="identity"/>
379  <list><t>
380        The default (identity) encoding; the use of no transformation
381        whatsoever. This content-coding is used only in the Accept-Encoding
382        header, and &SHOULD-NOT;  be used in the Content-Encoding
383        header.
384  </t></list>
385</t>
386<t>
387   New content-coding value tokens &SHOULD; be registered; to allow
388   interoperability between clients and servers, specifications of the
389   content coding algorithms needed to implement a new value &SHOULD; be
390   publicly available and adequate for independent implementation, and
391   conform to the purpose of content coding defined in this section.
392</t>
393</section>
394
395<section title="Media Types" anchor="media.types">
396<t>
397   HTTP uses Internet Media Types <xref target="RFC4288"/> in the Content-Type (<xref target="header.content-type"/>)
398   and Accept (<xref target="header.accept"/>) header fields in order to provide
399   open and extensible data typing and type negotiation.
400</t>
401<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"/>
402    media-type     = type "/" subtype *( ";" parameter )
403    type           = token
404    subtype        = token
405</artwork></figure>
406<t>
407   Parameters &MAY; follow the type/subtype in the form of attribute/value
408   pairs.
409</t>
410<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"/>
411    parameter               = attribute "=" value
412    attribute               = token
413    value                   = token | quoted-string
414</artwork></figure>
415<t>
416   The type, subtype, and parameter attribute names are case-insensitive.
417   Parameter values might or might not be case-sensitive,
418   depending on the semantics of the parameter name. Linear white space
419   (LWS) &MUST-NOT; be used between the type and subtype, nor between an
420   attribute and its value. The presence or absence of a parameter might
421   be significant to the processing of a media-type, depending on its
422   definition within the media type registry.
423</t>
424<t>
425   Note that some older HTTP applications do not recognize media type
426   parameters. When sending data to older HTTP applications,
427   implementations &SHOULD; only use media type parameters when they are
428   required by that type/subtype definition.
429</t>
430<t>
431   Media-type values are registered with the Internet Assigned Number
432   Authority (IANA). The media type registration process is
433   outlined in RFC 4288 <xref target="RFC4288"/>. Use of non-registered media types is
434   discouraged.
435</t>
436
437<section title="Canonicalization and Text Defaults" anchor="canonicalization.and.text.defaults">
438<t>
439   Internet media types are registered with a canonical form. An
440   entity-body transferred via HTTP messages &MUST; be represented in the
441   appropriate canonical form prior to its transmission except for
442   "text" types, as defined in the next paragraph.
443</t>
444<t>
445   When in canonical form, media subtypes of the "text" type use CRLF as
446   the text line break. HTTP relaxes this requirement and allows the
447   transport of text media with plain CR or LF alone representing a line
448   break when it is done consistently for an entire entity-body. HTTP
449   applications &MUST; accept CRLF, bare CR, and bare LF as being
450   representative of a line break in text media received via HTTP. In
451   addition, if the text is represented in a character set that does not
452   use octets 13 and 10 for CR and LF respectively, as is the case for
453   some multi-byte character sets, HTTP allows the use of whatever octet
454   sequences are defined by that character set to represent the
455   equivalent of CR and LF for line breaks. This flexibility regarding
456   line breaks applies only to text media in the entity-body; a bare CR
457   or LF &MUST-NOT; be substituted for CRLF within any of the HTTP control
458   structures (such as header fields and multipart boundaries).
459</t>
460<t>
461   If an entity-body is encoded with a content-coding, the underlying
462   data &MUST; be in a form defined above prior to being encoded.
463</t>
464<t>
465   The "charset" parameter is used with some media types to define the
466   character set (<xref target="character.sets"/>) of the data. When no explicit charset
467   parameter is provided by the sender, media subtypes of the "text"
468   type are defined to have a default charset value of "ISO-8859-1" when
469   received via HTTP. Data in character sets other than "ISO-8859-1" or
470   its subsets &MUST; be labeled with an appropriate charset value. See
471   <xref target="missing.charset"/> for compatibility problems.
472</t>
473</section>
474
475<section title="Multipart Types" anchor="multipart.types">
476<t>
477   MIME provides for a number of "multipart" types -- encapsulations of
478   one or more entities within a single message-body. All multipart
479   types share a common syntax, as defined in section <xref target="RFC2046" x:sec="5.1.1" x:fmt="number"/> of RFC 2046
480   <xref target="RFC2046"/>, and &MUST; include a boundary parameter as part of the media type
481   value. The message body is itself a protocol element and &MUST;
482   therefore use only CRLF to represent line breaks between body-parts.
483   Unlike in RFC 2046, the epilogue of any multipart message &MUST; be
484   empty; HTTP applications &MUST-NOT; transmit the epilogue (even if the
485   original multipart contains an epilogue). These restrictions exist in
486   order to preserve the self-delimiting nature of a multipart message-body,
487   wherein the "end" of the message-body is indicated by the
488   ending multipart boundary.
489</t>
490<t>
491   In general, HTTP treats a multipart message-body no differently than
492   any other media type: strictly as payload. The one exception is the
493   "multipart/byteranges" type (&multipart-byteranges;) when it appears in a 206
494   (Partial Content) response. In all
495   other cases, an HTTP user agent &SHOULD; follow the same or similar
496   behavior as a MIME user agent would upon receipt of a multipart type.
497   The MIME header fields within each body-part of a multipart message-body
498   do not have any significance to HTTP beyond that defined by
499   their MIME semantics.
500</t>
501<t>
502   In general, an HTTP user agent &SHOULD; follow the same or similar
503   behavior as a MIME user agent would upon receipt of a multipart type.
504   If an application receives an unrecognized multipart subtype, the
505   application &MUST; treat it as being equivalent to "multipart/mixed".
506</t>
507<t><list><t>
508      <x:h>Note:</x:h> The "multipart/form-data" type has been specifically defined
509      for carrying form data suitable for processing via the POST
510      request method, as described in RFC 1867 <xref target="RFC1867"/>.
511</t></list></t>
512</section>
513</section>
514
515<section title="Quality Values" anchor="quality.values">
516<t>
517   HTTP content negotiation (<xref target="content.negotiation"/>) uses short "floating point"
518   numbers to indicate the relative importance ("weight") of various
519   negotiable parameters.  A weight is normalized to a real number in
520   the range 0 through 1, where 0 is the minimum and 1 the maximum
521   value. If a parameter has a quality value of 0, then content with
522   this parameter is `not acceptable' for the client. HTTP/1.1
523   applications &MUST-NOT; generate more than three digits after the
524   decimal point. User configuration of these values &SHOULD; also be
525   limited in this fashion.
526</t>
527<figure><artwork type="abnf2616"><iref primary="true" item="Grammar" subitem="qvalue"/>
528    qvalue         = ( "0" [ "." 0*3DIGIT ] )
529                   | ( "1" [ "." 0*3("0") ] )
530</artwork></figure>
531<t>
532   "Quality values" is a misnomer, since these values merely represent
533   relative degradation in desired quality.
534</t>
535</section>
536
537<section title="Language Tags" anchor="language.tags">
538<t>
539   A language tag identifies a natural language spoken, written, or
540   otherwise conveyed by human beings for communication of information
541   to other human beings. Computer languages are explicitly excluded.
542   HTTP uses language tags within the Accept-Language and Content-Language
543   fields.
544</t>
545<t>
546   The syntax and registry of HTTP language tags is the same as that
547   defined by RFC 1766 <xref target="RFC1766"/>. In summary, a language tag is composed of 1
548   or more parts: A primary language tag and a possibly empty series of
549   subtags:
550</t>
551<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"/>
552     language-tag  = primary-tag *( "-" subtag )
553     primary-tag   = 1*8ALPHA
554     subtag        = 1*8ALPHA
555</artwork></figure>
556<t>
557   White space is not allowed within the tag and all tags are case-insensitive.
558   The name space of language tags is administered by the
559   IANA. Example tags include:
560</t>
561<figure><artwork type="example">
562    en, en-US, en-cockney, i-cherokee, x-pig-latin
563</artwork></figure>
564<t>
565   where any two-letter primary-tag is an ISO-639 language abbreviation
566   and any two-letter initial subtag is an ISO-3166 country code. (The
567   last three tags above are not registered tags; all but the last are
568   examples of tags which could be registered in future.)
569</t>
570</section>
571</section>
572
573<section title="Entity" anchor="entity">
574<t>
575   Request and Response messages &MAY; transfer an entity if not otherwise
576   restricted by the request method or response status code. An entity
577   consists of entity-header fields and an entity-body, although some
578   responses will only include the entity-headers.
579</t>
580<t>
581   In this section, both sender and recipient refer to either the client
582   or the server, depending on who sends and who receives the entity.
583</t>
584
585<section title="Entity Header Fields" anchor="entity.header.fields">
586<t>
587   Entity-header fields define metainformation about the entity-body or,
588   if no body is present, about the resource identified by the request.
589   Some of this metainformation is &OPTIONAL;; some might be &REQUIRED; by
590   portions of this specification.
591</t>
592<figure><artwork type="abnf2616"><iref primary="true" item="Grammar" subitem="entity-header"/><iref primary="true" item="Grammar" subitem="extension-header"/>
593    entity-header  = Allow                    ; &header-allow;
594                   | Content-Encoding         ; <xref target="header.content-encoding"/>
595                   | Content-Language         ; <xref target="header.content-language"/>
596                   | Content-Length           ; &header-content-length;
597                   | Content-Location         ; <xref target="header.content-location"/>
598                   | Content-MD5              ; <xref target="header.content-md5"/>
599                   | Content-Range            ; &header-content-range;
600                   | Content-Type             ; <xref target="header.content-type"/>
601                   | Expires                  ; &header-expires;
602                   | Last-Modified            ; &header-last-modified;
603                   | extension-header
604
605    extension-header = message-header
606</artwork></figure>
607<t>
608   The extension-header mechanism allows additional entity-header fields
609   to be defined without changing the protocol, but these fields cannot
610   be assumed to be recognizable by the recipient. Unrecognized header
611   fields &SHOULD; be ignored by the recipient and &MUST; be forwarded by
612   transparent proxies.
613</t>
614</section>
615
616<section title="Entity Body" anchor="entity.body">
617<t>
618   The entity-body (if any) sent with an HTTP request or response is in
619   a format and encoding defined by the entity-header fields.
620</t>
621<figure><artwork type="abnf2616"><iref primary="true" item="Grammar" subitem="entity-body"/>
622    entity-body    = *OCTET
623</artwork></figure>
624<t>
625   An entity-body is only present in a message when a message-body is
626   present, as described in &message-body;. The entity-body is obtained
627   from the message-body by decoding any Transfer-Encoding that might
628   have been applied to ensure safe and proper transfer of the message.
629</t>
630
631<section title="Type" anchor="type">
632<t>
633   When an entity-body is included with a message, the data type of that
634   body is determined via the header fields Content-Type and Content-Encoding.
635   These define a two-layer, ordered encoding model:
636</t>
637<figure><artwork type="example">
638    entity-body := Content-Encoding( Content-Type( data ) )
639</artwork></figure>
640<t>
641   Content-Type specifies the media type of the underlying data.
642   Content-Encoding may be used to indicate any additional content
643   codings applied to the data, usually for the purpose of data
644   compression, that are a property of the requested resource. There is
645   no default encoding.
646</t>
647<t>
648   Any HTTP/1.1 message containing an entity-body &SHOULD; include a
649   Content-Type header field defining the media type of that body. If
650   and only if the media type is not given by a Content-Type field, the
651   recipient &MAY; attempt to guess the media type via inspection of its
652   content and/or the name extension(s) of the URI used to identify the
653   resource. If the media type remains unknown, the recipient &SHOULD;
654   treat it as type "application/octet-stream".
655</t>
656</section>
657   
658<section title="Entity Length" anchor="entity.length">
659<t>
660   The entity-length of a message is the length of the message-body
661   before any transfer-codings have been applied. &message-length; defines
662   how the transfer-length of a message-body is determined.
663</t>
664</section>
665</section>
666</section>
667
668<section title="Content Negotiation" anchor="content.negotiation">
669<t>
670   Most HTTP responses include an entity which contains information for
671   interpretation by a human user. Naturally, it is desirable to supply
672   the user with the "best available" entity corresponding to the
673   request. Unfortunately for servers and caches, not all users have the
674   same preferences for what is "best," and not all user agents are
675   equally capable of rendering all entity types. For that reason, HTTP
676   has provisions for several mechanisms for "content negotiation" --
677   the process of selecting the best representation for a given response
678   when there are multiple representations available.
679  <list><t>
680      <x:h>Note:</x:h> This is not called "format negotiation" because the
681      alternate representations may be of the same media type, but use
682      different capabilities of that type, be in different languages,
683      etc.
684  </t></list>
685</t>
686<t>
687   Any response containing an entity-body &MAY; be subject to negotiation,
688   including error responses.
689</t>
690<t>
691   There are two kinds of content negotiation which are possible in
692   HTTP: server-driven and agent-driven negotiation. These two kinds of
693   negotiation are orthogonal and thus may be used separately or in
694   combination. One method of combination, referred to as transparent
695   negotiation, occurs when a cache uses the agent-driven negotiation
696   information provided by the origin server in order to provide
697   server-driven negotiation for subsequent requests.
698</t>
699
700<section title="Server-driven Negotiation" anchor="server-driven.negotiation">
701<t>
702   If the selection of the best representation for a response is made by
703   an algorithm located at the server, it is called server-driven
704   negotiation. Selection is based on the available representations of
705   the response (the dimensions over which it can vary; e.g. language,
706   content-coding, etc.) and the contents of particular header fields in
707   the request message or on other information pertaining to the request
708   (such as the network address of the client).
709</t>
710<t>
711   Server-driven negotiation is advantageous when the algorithm for
712   selecting from among the available representations is difficult to
713   describe to the user agent, or when the server desires to send its
714   "best guess" to the client along with the first response (hoping to
715   avoid the round-trip delay of a subsequent request if the "best
716   guess" is good enough for the user). In order to improve the server's
717   guess, the user agent &MAY; include request header fields (Accept,
718   Accept-Language, Accept-Encoding, etc.) which describe its
719   preferences for such a response.
720</t>
721<t>
722   Server-driven negotiation has disadvantages:
723  <list style="numbers">
724    <t>
725         It is impossible for the server to accurately determine what
726         might be "best" for any given user, since that would require
727         complete knowledge of both the capabilities of the user agent
728         and the intended use for the response (e.g., does the user want
729         to view it on screen or print it on paper?).
730    </t>
731    <t>
732         Having the user agent describe its capabilities in every
733         request can be both very inefficient (given that only a small
734         percentage of responses have multiple representations) and a
735         potential violation of the user's privacy.
736    </t>
737    <t>
738         It complicates the implementation of an origin server and the
739         algorithms for generating responses to a request.
740    </t>
741    <t>
742         It may limit a public cache's ability to use the same response
743         for multiple user's requests.
744    </t>
745  </list>
746</t>
747<t>
748   HTTP/1.1 includes the following request-header fields for enabling
749   server-driven negotiation through description of user agent
750   capabilities and user preferences: Accept (<xref target="header.accept"/>), Accept-Charset
751   (<xref target="header.accept-charset"/>), Accept-Encoding (<xref target="header.accept-encoding"/>), Accept-Language
752   (<xref target="header.accept-language"/>), and User-Agent (&header-user-agent;). However, an
753   origin server is not limited to these dimensions and &MAY; vary the
754   response based on any aspect of the request, including information
755   outside the request-header fields or within extension header fields
756   not defined by this specification.
757</t>
758<t>
759   The Vary header field &caching; can be used to express the parameters the
760   server uses to select a representation that is subject to server-driven
761   negotiation.
762</t>
763</section>
764
765<section title="Agent-driven Negotiation" anchor="agent-driven.negotiation">
766<t>
767   With agent-driven negotiation, selection of the best representation
768   for a response is performed by the user agent after receiving an
769   initial response from the origin server. Selection is based on a list
770   of the available representations of the response included within the
771   header fields or entity-body of the initial response, with each
772   representation identified by its own URI. Selection from among the
773   representations may be performed automatically (if the user agent is
774   capable of doing so) or manually by the user selecting from a
775   generated (possibly hypertext) menu.
776</t>
777<t>
778   Agent-driven negotiation is advantageous when the response would vary
779   over commonly-used dimensions (such as type, language, or encoding),
780   when the origin server is unable to determine a user agent's
781   capabilities from examining the request, and generally when public
782   caches are used to distribute server load and reduce network usage.
783</t>
784<t>
785   Agent-driven negotiation suffers from the disadvantage of needing a
786   second request to obtain the best alternate representation. This
787   second request is only efficient when caching is used. In addition,
788   this specification does not define any mechanism for supporting
789   automatic selection, though it also does not prevent any such
790   mechanism from being developed as an extension and used within
791   HTTP/1.1.
792</t>
793<t>
794   HTTP/1.1 defines the 300 (Multiple Choices) and 406 (Not Acceptable)
795   status codes for enabling agent-driven negotiation when the server is
796   unwilling or unable to provide a varying response using server-driven
797   negotiation.
798</t>
799</section>
800
801<section title="Transparent Negotiation" anchor="transparent.negotiation">
802<t>
803   Transparent negotiation is a combination of both server-driven and
804   agent-driven negotiation. When a cache is supplied with a form of the
805   list of available representations of the response (as in agent-driven
806   negotiation) and the dimensions of variance are completely understood
807   by the cache, then the cache becomes capable of performing server-driven
808   negotiation on behalf of the origin server for subsequent
809   requests on that resource.
810</t>
811<t>
812   Transparent negotiation has the advantage of distributing the
813   negotiation work that would otherwise be required of the origin
814   server and also removing the second request delay of agent-driven
815   negotiation when the cache is able to correctly guess the right
816   response.
817</t>
818<t>
819   This specification does not define any mechanism for transparent
820   negotiation, though it also does not prevent any such mechanism from
821   being developed as an extension that could be used within HTTP/1.1.
822</t>
823</section>
824</section>
825<section title="Header Field Definitions" anchor="header.fields">
826<t>
827   This section defines the syntax and semantics of all standard
828   HTTP/1.1 header fields. For entity-header fields, both sender and
829   recipient refer to either the client or the server, depending on who
830   sends and who receives the entity.
831</t>
832<section title="Accept" anchor="header.accept">
833  <iref primary="true" item="Accept header" x:for-anchor=""/>
834  <iref primary="true" item="Headers" subitem="Accept" x:for-anchor=""/>
835<t>
836   The Accept request-header field can be used to specify certain media
837   types which are acceptable for the response. Accept headers can be
838   used to indicate that the request is specifically limited to a small
839   set of desired types, as in the case of a request for an in-line
840   image.
841</t>
842<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"/>
843    Accept         = "Accept" ":"
844                     #( media-range [ accept-params ] )
845
846    media-range    = ( "*/*"
847                     | ( type "/" "*" )
848                     | ( type "/" subtype )
849                     ) *( ";" parameter )
850    accept-params  = ";" "q" "=" qvalue *( accept-extension )
851    accept-extension = ";" token [ "=" ( token | quoted-string ) ]
852</artwork></figure>
853<t>
854   The asterisk "*" character is used to group media types into ranges,
855   with "*/*" indicating all media types and "type/*" indicating all
856   subtypes of that type. The media-range &MAY; include media type
857   parameters that are applicable to that range.
858</t>
859<t>
860   Each media-range &MAY; be followed by one or more accept-params,
861   beginning with the "q" parameter for indicating a relative quality
862   factor. The first "q" parameter (if any) separates the media-range
863   parameter(s) from the accept-params. Quality factors allow the user
864   or user agent to indicate the relative degree of preference for that
865   media-range, using the qvalue scale from 0 to 1 (<xref target="quality.values"/>). The
866   default value is q=1.
867  <list><t>
868      <x:h>Note:</x:h> Use of the "q" parameter name to separate media type
869      parameters from Accept extension parameters is due to historical
870      practice. Although this prevents any media type parameter named
871      "q" from being used with a media range, such an event is believed
872      to be unlikely given the lack of any "q" parameters in the IANA
873      media type registry and the rare usage of any media type
874      parameters in Accept. Future media types are discouraged from
875      registering any parameter named "q".
876  </t></list>
877</t>
878<t>
879   The example
880</t>
881<figure><artwork type="example">
882    Accept: audio/*; q=0.2, audio/basic
883</artwork></figure>
884<t>
885   &SHOULD; be interpreted as "I prefer audio/basic, but send me any audio
886   type if it is the best available after an 80% mark-down in quality."
887</t>
888<t>
889   If no Accept header field is present, then it is assumed that the
890   client accepts all media types. If an Accept header field is present,
891   and if the server cannot send a response which is acceptable
892   according to the combined Accept field value, then the server &SHOULD;
893   send a 406 (not acceptable) response.
894</t>
895<t>
896   A more elaborate example is
897</t>
898<figure><artwork type="example">
899    Accept: text/plain; q=0.5, text/html,
900            text/x-dvi; q=0.8, text/x-c
901</artwork></figure>
902<t>
903   Verbally, this would be interpreted as "text/html and text/x-c are
904   the preferred media types, but if they do not exist, then send the
905   text/x-dvi entity, and if that does not exist, send the text/plain
906   entity."
907</t>
908<t>
909   Media ranges can be overridden by more specific media ranges or
910   specific media types. If more than one media range applies to a given
911   type, the most specific reference has precedence. For example,
912</t>
913<figure><artwork type="example">
914    Accept: text/*, text/html, text/html;level=1, */*
915</artwork></figure>
916<t>
917   have the following precedence:
918</t>
919<figure><artwork type="example">
920    1) text/html;level=1
921    2) text/html
922    3) text/*
923    4) */*
924</artwork></figure>
925<t>
926   The media type quality factor associated with a given type is
927   determined by finding the media range with the highest precedence
928   which matches that type. For example,
929</t>
930<figure><artwork type="example">
931    Accept: text/*;q=0.3, text/html;q=0.7, text/html;level=1,
932            text/html;level=2;q=0.4, */*;q=0.5
933</artwork></figure>
934<t>
935   would cause the following values to be associated:
936</t>
937<figure><artwork type="example">
938    text/html;level=1         = 1
939    text/html                 = 0.7
940    text/plain                = 0.3
941    image/jpeg                = 0.5
942    text/html;level=2         = 0.4
943    text/html;level=3         = 0.7
944</artwork></figure>
945<t>
946      <x:h>Note:</x:h> A user agent might be provided with a default set of quality
947      values for certain media ranges. However, unless the user agent is
948      a closed system which cannot interact with other rendering agents,
949      this default set ought to be configurable by the user.
950</t>
951</section>
952
953<section title="Accept-Charset" anchor="header.accept-charset">
954  <iref primary="true" item="Accept-Charset header" x:for-anchor=""/>
955  <iref primary="true" item="Headers" subitem="Accept-Charset" x:for-anchor=""/>
956<t>
957   The Accept-Charset request-header field can be used to indicate what
958   character sets are acceptable for the response. This field allows
959   clients capable of understanding more comprehensive or special-purpose
960   character sets to signal that capability to a server which is
961   capable of representing documents in those character sets.
962</t>
963<figure><artwork type="abnf2616"><iref primary="true" item="Grammar" subitem="Accept-Charset"/>
964   Accept-Charset = "Accept-Charset" ":"
965           1#( ( charset | "*" )[ ";" "q" "=" qvalue ] )
966</artwork></figure>
967<t>
968   Character set values are described in <xref target="character.sets"/>. Each charset &MAY;
969   be given an associated quality value which represents the user's
970   preference for that charset. The default value is q=1. An example is
971</t>
972<figure><artwork type="example">
973   Accept-Charset: iso-8859-5, unicode-1-1;q=0.8
974</artwork></figure>
975<t>
976   The special value "*", if present in the Accept-Charset field,
977   matches every character set (including ISO-8859-1) which is not
978   mentioned elsewhere in the Accept-Charset field. If no "*" is present
979   in an Accept-Charset field, then all character sets not explicitly
980   mentioned get a quality value of 0, except for ISO-8859-1, which gets
981   a quality value of 1 if not explicitly mentioned.
982</t>
983<t>
984   If no Accept-Charset header is present, the default is that any
985   character set is acceptable. If an Accept-Charset header is present,
986   and if the server cannot send a response which is acceptable
987   according to the Accept-Charset header, then the server &SHOULD; send
988   an error response with the 406 (not acceptable) status code, though
989   the sending of an unacceptable response is also allowed.
990</t>
991</section>
992
993<section title="Accept-Encoding" anchor="header.accept-encoding">
994  <iref primary="true" item="Accept-Encoding header" x:for-anchor=""/>
995  <iref primary="true" item="Headers" subitem="Accept-Encoding" x:for-anchor=""/>
996<t>
997   The Accept-Encoding request-header field is similar to Accept, but
998   restricts the content-codings (<xref target="content.codings"/>) that are acceptable in
999   the response.
1000</t>
1001<figure><artwork type="abnf2616"><iref primary="true" item="Grammar" subitem="Accept-Encoding"/><iref primary="true" item="Grammar" subitem="codings"/>
1002    Accept-Encoding  = "Accept-Encoding" ":"
1003                       1#( codings [ ";" "q" "=" qvalue ] )
1004    codings          = ( content-coding | "*" )
1005</artwork></figure>
1006<t>
1007   Examples of its use are:
1008</t>
1009<figure><artwork type="example">
1010    Accept-Encoding: compress, gzip
1011    Accept-Encoding:
1012    Accept-Encoding: *
1013    Accept-Encoding: compress;q=0.5, gzip;q=1.0
1014    Accept-Encoding: gzip;q=1.0, identity; q=0.5, *;q=0
1015</artwork></figure>
1016<t>
1017   A server tests whether a content-coding is acceptable, according to
1018   an Accept-Encoding field, using these rules:
1019  <list style="numbers">
1020      <t>If the content-coding is one of the content-codings listed in
1021         the Accept-Encoding field, then it is acceptable, unless it is
1022         accompanied by a qvalue of 0. (As defined in <xref target="quality.values"/>, a
1023         qvalue of 0 means "not acceptable.")</t>
1024
1025      <t>The special "*" symbol in an Accept-Encoding field matches any
1026         available content-coding not explicitly listed in the header
1027         field.</t>
1028
1029      <t>If multiple content-codings are acceptable, then the acceptable
1030         content-coding with the highest non-zero qvalue is preferred.</t>
1031
1032      <t>The "identity" content-coding is always acceptable, unless
1033         specifically refused because the Accept-Encoding field includes
1034         "identity;q=0", or because the field includes "*;q=0" and does
1035         not explicitly include the "identity" content-coding. If the
1036         Accept-Encoding field-value is empty, then only the "identity"
1037         encoding is acceptable.</t>
1038  </list>
1039</t>
1040<t>
1041   If an Accept-Encoding field is present in a request, and if the
1042   server cannot send a response which is acceptable according to the
1043   Accept-Encoding header, then the server &SHOULD; send an error response
1044   with the 406 (Not Acceptable) status code.
1045</t>
1046<t>
1047   If no Accept-Encoding field is present in a request, the server &MAY;
1048   assume that the client will accept any content coding. In this case,
1049   if "identity" is one of the available content-codings, then the
1050   server &SHOULD; use the "identity" content-coding, unless it has
1051   additional information that a different content-coding is meaningful
1052   to the client.
1053  <list><t>
1054      <x:h>Note:</x:h> If the request does not include an Accept-Encoding field,
1055      and if the "identity" content-coding is unavailable, then
1056      content-codings commonly understood by HTTP/1.0 clients (i.e.,
1057      "gzip" and "compress") are preferred; some older clients
1058      improperly display messages sent with other content-codings.  The
1059      server might also make this decision based on information about
1060      the particular user-agent or client.
1061    </t><t>
1062      <x:h>Note:</x:h> Most HTTP/1.0 applications do not recognize or obey qvalues
1063      associated with content-codings. This means that qvalues will not
1064      work and are not permitted with x-gzip or x-compress.
1065    </t></list>
1066</t>
1067</section>
1068
1069<section title="Accept-Language" anchor="header.accept-language">
1070  <iref primary="true" item="Accept-Language header" x:for-anchor=""/>
1071  <iref primary="true" item="Headers" subitem="Accept-Language" x:for-anchor=""/>
1072<t>
1073   The Accept-Language request-header field is similar to Accept, but
1074   restricts the set of natural languages that are preferred as a
1075   response to the request. Language tags are defined in <xref target="language.tags"/>.
1076</t>
1077<figure><artwork type="abnf2616"><iref primary="true" item="Grammar" subitem="Accept-Language"/><iref primary="true" item="Grammar" subitem="language-range"/>
1078    Accept-Language = "Accept-Language" ":"
1079                      1#( language-range [ ";" "q" "=" qvalue ] )
1080    language-range  = ( ( 1*8ALPHA *( "-" 1*8ALPHA ) ) | "*" )
1081</artwork></figure>
1082<t>
1083   Each language-range &MAY; be given an associated quality value which
1084   represents an estimate of the user's preference for the languages
1085   specified by that range. The quality value defaults to "q=1". For
1086   example,
1087</t>
1088<figure><artwork type="example">
1089    Accept-Language: da, en-gb;q=0.8, en;q=0.7
1090</artwork></figure>
1091<t>
1092   would mean: "I prefer Danish, but will accept British English and
1093   other types of English." A language-range matches a language-tag if
1094   it exactly equals the tag, or if it exactly equals a prefix of the
1095   tag such that the first tag character following the prefix is "-".
1096   The special range "*", if present in the Accept-Language field,
1097   matches every tag not matched by any other range present in the
1098   Accept-Language field.
1099  <list><t>
1100      <x:h>Note:</x:h> This use of a prefix matching rule does not imply that
1101      language tags are assigned to languages in such a way that it is
1102      always true that if a user understands a language with a certain
1103      tag, then this user will also understand all languages with tags
1104      for which this tag is a prefix. The prefix rule simply allows the
1105      use of prefix tags if this is the case.
1106  </t></list>
1107</t>
1108<t>
1109   The language quality factor assigned to a language-tag by the
1110   Accept-Language field is the quality value of the longest language-range
1111   in the field that matches the language-tag. If no language-range
1112   in the field matches the tag, the language quality factor
1113   assigned is 0. If no Accept-Language header is present in the
1114   request, the server
1115   &SHOULD; assume that all languages are equally acceptable. If an
1116   Accept-Language header is present, then all languages which are
1117   assigned a quality factor greater than 0 are acceptable.
1118</t>
1119<t>
1120   It might be contrary to the privacy expectations of the user to send
1121   an Accept-Language header with the complete linguistic preferences of
1122   the user in every request. For a discussion of this issue, see
1123   <xref target="privacy.issues.connected.to.accept.headers"/>.
1124</t>
1125<t>
1126   As intelligibility is highly dependent on the individual user, it is
1127   recommended that client applications make the choice of linguistic
1128   preference available to the user. If the choice is not made
1129   available, then the Accept-Language header field &MUST-NOT; be given in
1130   the request.
1131  <list><t>
1132      <x:h>Note:</x:h> When making the choice of linguistic preference available to
1133      the user, we remind implementors of  the fact that users are not
1134      familiar with the details of language matching as described above,
1135      and should provide appropriate guidance. As an example, users
1136      might assume that on selecting "en-gb", they will be served any
1137      kind of English document if British English is not available. A
1138      user agent might suggest in such a case to add "en" to get the
1139      best matching behavior.
1140  </t></list>
1141</t>
1142</section>
1143
1144<section title="Content-Encoding" anchor="header.content-encoding">
1145  <iref primary="true" item="Content-Encoding header" x:for-anchor=""/>
1146  <iref primary="true" item="Headers" subitem="Content-Encoding" x:for-anchor=""/>
1147<t>
1148   The Content-Encoding entity-header field is used as a modifier to the
1149   media-type. When present, its value indicates what additional content
1150   codings have been applied to the entity-body, and thus what decoding
1151   mechanisms must be applied in order to obtain the media-type
1152   referenced by the Content-Type header field. Content-Encoding is
1153   primarily used to allow a document to be compressed without losing
1154   the identity of its underlying media type.
1155</t>
1156<figure><artwork type="abnf2616"><iref primary="true" item="Grammar" subitem="Content-Encoding"/>
1157    Content-Encoding  = "Content-Encoding" ":" 1#content-coding
1158</artwork></figure>
1159<t>
1160   Content codings are defined in <xref target="content.codings"/>. An example of its use is
1161</t>
1162<figure><artwork type="example">
1163    Content-Encoding: gzip
1164</artwork></figure>
1165<t>
1166   The content-coding is a characteristic of the entity identified by
1167   the Request-URI. Typically, the entity-body is stored with this
1168   encoding and is only decoded before rendering or analogous usage.
1169   However, a non-transparent proxy &MAY; modify the content-coding if the
1170   new coding is known to be acceptable to the recipient, unless the
1171   "no-transform" cache-control directive is present in the message.
1172</t>
1173<t>
1174   If the content-coding of an entity is not "identity", then the
1175   response &MUST; include a Content-Encoding entity-header (<xref target="header.content-encoding"/>)
1176   that lists the non-identity content-coding(s) used.
1177</t>
1178<t>
1179   If the content-coding of an entity in a request message is not
1180   acceptable to the origin server, the server &SHOULD; respond with a
1181   status code of 415 (Unsupported Media Type).
1182</t>
1183<t>
1184   If multiple encodings have been applied to an entity, the content
1185   codings &MUST; be listed in the order in which they were applied.
1186   Additional information about the encoding parameters &MAY; be provided
1187   by other entity-header fields not defined by this specification.
1188</t>
1189</section>
1190
1191<section title="Content-Language" anchor="header.content-language">
1192  <iref primary="true" item="Content-Language header" x:for-anchor=""/>
1193  <iref primary="true" item="Headers" subitem="Content-Language" x:for-anchor=""/>
1194<t>
1195   The Content-Language entity-header field describes the natural
1196   language(s) of the intended audience for the enclosed entity. Note
1197   that this might not be equivalent to all the languages used within
1198   the entity-body.
1199</t>
1200<figure><artwork type="abnf2616"><iref primary="true" item="Grammar" subitem="Content-Language"/>
1201    Content-Language  = "Content-Language" ":" 1#language-tag
1202</artwork></figure>
1203<t>
1204   Language tags are defined in <xref target="language.tags"/>. The primary purpose of
1205   Content-Language is to allow a user to identify and differentiate
1206   entities according to the user's own preferred language. Thus, if the
1207   body content is intended only for a Danish-literate audience, the
1208   appropriate field is
1209</t>
1210<figure><artwork type="example">
1211    Content-Language: da
1212</artwork></figure>
1213<t>
1214   If no Content-Language is specified, the default is that the content
1215   is intended for all language audiences. This might mean that the
1216   sender does not consider it to be specific to any natural language,
1217   or that the sender does not know for which language it is intended.
1218</t>
1219<t>
1220   Multiple languages &MAY; be listed for content that is intended for
1221   multiple audiences. For example, a rendition of the "Treaty of
1222   Waitangi," presented simultaneously in the original Maori and English
1223   versions, would call for
1224</t>
1225<figure><artwork type="example">
1226    Content-Language: mi, en
1227</artwork></figure>
1228<t>
1229   However, just because multiple languages are present within an entity
1230   does not mean that it is intended for multiple linguistic audiences.
1231   An example would be a beginner's language primer, such as "A First
1232   Lesson in Latin," which is clearly intended to be used by an
1233   English-literate audience. In this case, the Content-Language would
1234   properly only include "en".
1235</t>
1236<t>
1237   Content-Language &MAY; be applied to any media type -- it is not
1238   limited to textual documents.
1239</t>
1240</section>
1241
1242<section title="Content-Location" anchor="header.content-location">
1243  <iref primary="true" item="Content-Location header" x:for-anchor=""/>
1244  <iref primary="true" item="Headers" subitem="Content-Location" x:for-anchor=""/>
1245<t>
1246   The Content-Location entity-header field &MAY; be used to supply the
1247   resource location for the entity enclosed in the message when that
1248   entity is accessible from a location separate from the requested
1249   resource's URI. A server &SHOULD; provide a Content-Location for the
1250   variant corresponding to the response entity; especially in the case
1251   where a resource has multiple entities associated with it, and those
1252   entities actually have separate locations by which they might be
1253   individually accessed, the server &SHOULD; provide a Content-Location
1254   for the particular variant which is returned.
1255</t>
1256<figure><artwork type="abnf2616"><iref primary="true" item="Grammar" subitem="Content-Location"/>
1257    Content-Location = "Content-Location" ":"
1258                      ( absoluteURI | relativeURI )
1259</artwork></figure>
1260<t>
1261   The value of Content-Location also defines the base URI for the
1262   entity.
1263</t>
1264<t>
1265   The Content-Location value is not a replacement for the original
1266   requested URI; it is only a statement of the location of the resource
1267   corresponding to this particular entity at the time of the request.
1268   Future requests &MAY; specify the Content-Location URI as the request-URI
1269   if the desire is to identify the source of that particular
1270   entity.
1271</t>
1272<t>
1273   A cache cannot assume that an entity with a Content-Location
1274   different from the URI used to retrieve it can be used to respond to
1275   later requests on that Content-Location URI. However, the Content-Location
1276   can be used to differentiate between multiple entities
1277   retrieved from a single requested resource, as described in &caching;.
1278</t>
1279<t>
1280   If the Content-Location is a relative URI, the relative URI is
1281   interpreted relative to the Request-URI.
1282</t>
1283<t>
1284   The meaning of the Content-Location header in PUT or POST requests is
1285   undefined; servers are free to ignore it in those cases.
1286</t>
1287</section>
1288
1289<section title="Content-MD5" anchor="header.content-md5">
1290  <iref primary="true" item="Content-MD5 header" x:for-anchor=""/>
1291  <iref primary="true" item="Headers" subitem="Content-MD5" x:for-anchor=""/>
1292<t>
1293   The Content-MD5 entity-header field, as defined in RFC 1864 <xref target="RFC1864"/>, is
1294   an MD5 digest of the entity-body for the purpose of providing an
1295   end-to-end message integrity check (MIC) of the entity-body. (Note: a
1296   MIC is good for detecting accidental modification of the entity-body
1297   in transit, but is not proof against malicious attacks.)
1298</t>
1299<figure><artwork type="abnf2616"><iref primary="true" item="Grammar" subitem="Content-MD5"/><iref primary="true" item="Grammar" subitem="md5-digest"/>
1300     Content-MD5   = "Content-MD5" ":" md5-digest
1301     md5-digest   = &lt;base64 of 128 bit MD5 digest as per RFC 1864&gt;
1302</artwork></figure>
1303<t>
1304   The Content-MD5 header field &MAY; be generated by an origin server or
1305   client to function as an integrity check of the entity-body. Only
1306   origin servers or clients &MAY; generate the Content-MD5 header field;
1307   proxies and gateways &MUST-NOT; generate it, as this would defeat its
1308   value as an end-to-end integrity check. Any recipient of the entity-body,
1309   including gateways and proxies, &MAY; check that the digest value
1310   in this header field matches that of the entity-body as received.
1311</t>
1312<t>
1313   The MD5 digest is computed based on the content of the entity-body,
1314   including any content-coding that has been applied, but not including
1315   any transfer-encoding applied to the message-body. If the message is
1316   received with a transfer-encoding, that encoding &MUST; be removed
1317   prior to checking the Content-MD5 value against the received entity.
1318</t>
1319<t>
1320   This has the result that the digest is computed on the octets of the
1321   entity-body exactly as, and in the order that, they would be sent if
1322   no transfer-encoding were being applied.
1323</t>
1324<t>
1325   HTTP extends RFC 1864 to permit the digest to be computed for MIME
1326   composite media-types (e.g., multipart/* and message/rfc822), but
1327   this does not change how the digest is computed as defined in the
1328   preceding paragraph.
1329</t>
1330<t>
1331   There are several consequences of this. The entity-body for composite
1332   types &MAY; contain many body-parts, each with its own MIME and HTTP
1333   headers (including Content-MD5, Content-Transfer-Encoding, and
1334   Content-Encoding headers). If a body-part has a Content-Transfer-Encoding
1335   or Content-Encoding header, it is assumed that the content
1336   of the body-part has had the encoding applied, and the body-part is
1337   included in the Content-MD5 digest as is -- i.e., after the
1338   application. The Transfer-Encoding header field is not allowed within
1339   body-parts.
1340</t>
1341<t>
1342   Conversion of all line breaks to CRLF &MUST-NOT; be done before
1343   computing or checking the digest: the line break convention used in
1344   the text actually transmitted &MUST; be left unaltered when computing
1345   the digest.
1346  <list><t>
1347      <x:h>Note:</x:h> while the definition of Content-MD5 is exactly the same for
1348      HTTP as in RFC 1864 for MIME entity-bodies, there are several ways
1349      in which the application of Content-MD5 to HTTP entity-bodies
1350      differs from its application to MIME entity-bodies. One is that
1351      HTTP, unlike MIME, does not use Content-Transfer-Encoding, and
1352      does use Transfer-Encoding and Content-Encoding. Another is that
1353      HTTP more frequently uses binary content types than MIME, so it is
1354      worth noting that, in such cases, the byte order used to compute
1355      the digest is the transmission byte order defined for the type.
1356      Lastly, HTTP allows transmission of text types with any of several
1357      line break conventions and not just the canonical form using CRLF.
1358  </t></list>
1359</t>
1360</section>
1361
1362<section title="Content-Type" anchor="header.content-type">
1363  <iref primary="true" item="Content-Type header" x:for-anchor=""/>
1364  <iref primary="true" item="Headers" subitem="Content-Type" x:for-anchor=""/>
1365<t>
1366   The Content-Type entity-header field indicates the media type of the
1367   entity-body sent to the recipient or, in the case of the HEAD method,
1368   the media type that would have been sent had the request been a GET.
1369</t>
1370<figure><artwork type="abnf2616"><iref primary="true" item="Grammar" subitem="Content-Type"/>
1371    Content-Type   = "Content-Type" ":" media-type
1372</artwork></figure>
1373<t>
1374   Media types are defined in <xref target="media.types"/>. An example of the field is
1375</t>
1376<figure><artwork type="example">
1377    Content-Type: text/html; charset=ISO-8859-4
1378</artwork></figure>
1379<t>
1380   Further discussion of methods for identifying the media type of an
1381   entity is provided in <xref target="type"/>.
1382</t>
1383</section>
1384
1385</section>
1386
1387<section title="IANA Considerations" anchor="IANA.considerations">
1388<t>
1389   TBD.
1390</t>
1391</section>
1392
1393<section title="Security Considerations" anchor="security.considerations">
1394<t>
1395   This section is meant to inform application developers, information
1396   providers, and users of the security limitations in HTTP/1.1 as
1397   described by this document. The discussion does not include
1398   definitive solutions to the problems revealed, though it does make
1399   some suggestions for reducing security risks.
1400</t>
1401
1402<section title="Privacy Issues Connected to Accept Headers" anchor="privacy.issues.connected.to.accept.headers">
1403<t>
1404   Accept request-headers can reveal information about the user to all
1405   servers which are accessed. The Accept-Language header in particular
1406   can reveal information the user would consider to be of a private
1407   nature, because the understanding of particular languages is often
1408   strongly correlated to the membership of a particular ethnic group.
1409   User agents which offer the option to configure the contents of an
1410   Accept-Language header to be sent in every request are strongly
1411   encouraged to let the configuration process include a message which
1412   makes the user aware of the loss of privacy involved.
1413</t>
1414<t>
1415   An approach that limits the loss of privacy would be for a user agent
1416   to omit the sending of Accept-Language headers by default, and to ask
1417   the user whether or not to start sending Accept-Language headers to a
1418   server if it detects, by looking for any Vary response-header fields
1419   generated by the server, that such sending could improve the quality
1420   of service.
1421</t>
1422<t>
1423   Elaborate user-customized accept header fields sent in every request,
1424   in particular if these include quality values, can be used by servers
1425   as relatively reliable and long-lived user identifiers. Such user
1426   identifiers would allow content providers to do click-trail tracking,
1427   and would allow collaborating content providers to match cross-server
1428   click-trails or form submissions of individual users. Note that for
1429   many users not behind a proxy, the network address of the host
1430   running the user agent will also serve as a long-lived user
1431   identifier. In environments where proxies are used to enhance
1432   privacy, user agents ought to be conservative in offering accept
1433   header configuration options to end users. As an extreme privacy
1434   measure, proxies could filter the accept headers in relayed requests.
1435   General purpose user agents which provide a high degree of header
1436   configurability &SHOULD; warn users about the loss of privacy which can
1437   be involved.
1438</t>
1439</section>
1440
1441<section title="Content-Disposition Issues" anchor="content-disposition.issues">
1442<t>
1443   RFC 1806 <xref target="RFC1806"/>, from which the often implemented Content-Disposition
1444   (see <xref target="content-disposition"/>) header in HTTP is derived, has a number of very
1445   serious security considerations. Content-Disposition is not part of
1446   the HTTP standard, but since it is widely implemented, we are
1447   documenting its use and risks for implementors. See RFC 2183 <xref target="RFC2183"/>
1448   (which updates RFC 1806) for details.
1449</t>
1450</section>
1451
1452</section>
1453
1454<section title="Acknowledgments" anchor="ack">
1455</section>
1456</middle>
1457<back>
1458<references>
1459
1460<reference anchor="Part1">
1461   <front>
1462      <title abbrev="HTTP/1.1">HTTP/1.1, part 1: URIs, Connections, and Message Parsing</title>
1463      <author initials="R." surname="Fielding" fullname="Roy T. Fielding" role="editor">
1464         <organization abbrev="Day Software">Day Software</organization>
1465         <address><email>fielding@gbiv.com</email></address>
1466      </author>
1467      <author initials="J." surname="Gettys" fullname="Jim Gettys">
1468         <organization>One Laptop per Child</organization>
1469         <address><email>jg@laptop.org</email></address>
1470      </author>
1471      <author initials="J." surname="Mogul" fullname="Jeffrey C. Mogul">
1472         <organization abbrev="HP">Hewlett-Packard Company</organization>
1473         <address><email>JeffMogul@acm.org</email></address>
1474      </author>
1475      <author initials="H." surname="Frystyk" fullname="Henrik Frystyk Nielsen">
1476         <organization abbrev="Microsoft">Microsoft Corporation</organization>
1477         <address><email>henrikn@microsoft.com</email></address>
1478      </author>
1479      <author initials="L." surname="Masinter" fullname="Larry Masinter">
1480         <organization abbrev="Adobe Systems">Adobe Systems, Incorporated</organization>
1481         <address><email>LMM@acm.org</email></address>
1482      </author>
1483      <author initials="P." surname="Leach" fullname="Paul J. Leach">
1484         <organization abbrev="Microsoft">Microsoft Corporation</organization>
1485         <address><email>paulle@microsoft.com</email></address>
1486      </author>
1487      <author initials="T." surname="Berners-Lee" fullname="Tim Berners-Lee">
1488         <organization abbrev="W3C/MIT">World Wide Web Consortium</organization>
1489         <address><email>timbl@w3.org</email></address>
1490      </author>
1491      <author initials="Y." surname="Lafon" fullname="Yves Lafon" role="editor">
1492         <organization abbrev="W3C">World Wide Web Consortium</organization>
1493         <address><email>ylafon@w3.org</email></address>
1494      </author>
1495      <author initials="J. F." surname="Reschke" fullname="Julian F. Reschke" role="editor">
1496         <organization abbrev="greenbytes">greenbytes GmbH</organization>
1497         <address><email>julian.reschke@greenbytes.de</email></address>
1498      </author>
1499      <date month="&ID-MONTH;" year="&ID-YEAR;"/>
1500   </front>
1501   <seriesInfo name="Internet-Draft" value="draft-ietf-httpbis-p1-messaging-&ID-VERSION;"/>
1502   <x:source href="p1-messaging.xml" basename="p1-messaging"/>
1503</reference>
1504
1505<reference anchor="Part2">
1506   <front>
1507      <title abbrev="HTTP/1.1">HTTP/1.1, part 2: Message Semantics</title>
1508      <author initials="R." surname="Fielding" fullname="Roy T. Fielding" role="editor">
1509         <organization abbrev="Day Software">Day Software</organization>
1510         <address><email>fielding@gbiv.com</email></address>
1511      </author>
1512      <author initials="J." surname="Gettys" fullname="Jim Gettys">
1513         <organization>One Laptop per Child</organization>
1514         <address><email>jg@laptop.org</email></address>
1515      </author>
1516      <author initials="J." surname="Mogul" fullname="Jeffrey C. Mogul">
1517         <organization abbrev="HP">Hewlett-Packard Company</organization>
1518         <address><email>JeffMogul@acm.org</email></address>
1519      </author>
1520      <author initials="H." surname="Frystyk" fullname="Henrik Frystyk Nielsen">
1521         <organization abbrev="Microsoft">Microsoft Corporation</organization>
1522         <address><email>henrikn@microsoft.com</email></address>
1523      </author>
1524      <author initials="L." surname="Masinter" fullname="Larry Masinter">
1525         <organization abbrev="Adobe Systems">Adobe Systems, Incorporated</organization>
1526         <address><email>LMM@acm.org</email></address>
1527      </author>
1528      <author initials="P." surname="Leach" fullname="Paul J. Leach">
1529         <organization abbrev="Microsoft">Microsoft Corporation</organization>
1530         <address><email>paulle@microsoft.com</email></address>
1531      </author>
1532      <author initials="T." surname="Berners-Lee" fullname="Tim Berners-Lee">
1533         <organization abbrev="W3C/MIT">World Wide Web Consortium</organization>
1534         <address><email>timbl@w3.org</email></address>
1535      </author>
1536      <author initials="Y." surname="Lafon" fullname="Yves Lafon" role="editor">
1537         <organization abbrev="W3C">World Wide Web Consortium</organization>
1538         <address><email>ylafon@w3.org</email></address>
1539      </author>
1540      <author initials="J. F." surname="Reschke" fullname="Julian F. Reschke" role="editor">
1541         <organization abbrev="greenbytes">greenbytes GmbH</organization>
1542         <address><email>julian.reschke@greenbytes.de</email></address>
1543      </author>
1544      <date month="&ID-MONTH;" year="&ID-YEAR;"/>
1545   </front>
1546   <seriesInfo name="Internet-Draft" value="draft-ietf-httpbis-p2-semantics-&ID-VERSION;"/>
1547   <x:source href="p2-semantics.xml" basename="p2-semantics"/>
1548</reference>
1549
1550<reference anchor="Part4">
1551   <front>
1552      <title abbrev="HTTP/1.1">HTTP/1.1, part 4: Conditional Requests</title>
1553      <author initials="R." surname="Fielding" fullname="Roy T. Fielding" role="editor">
1554         <organization abbrev="Day Software">Day Software</organization>
1555         <address><email>fielding@gbiv.com</email></address>
1556      </author>
1557      <author initials="J." surname="Gettys" fullname="Jim Gettys">
1558         <organization>One Laptop per Child</organization>
1559         <address><email>jg@laptop.org</email></address>
1560      </author>
1561      <author initials="J." surname="Mogul" fullname="Jeffrey C. Mogul">
1562         <organization abbrev="HP">Hewlett-Packard Company</organization>
1563         <address><email>JeffMogul@acm.org</email></address>
1564      </author>
1565      <author initials="H." surname="Frystyk" fullname="Henrik Frystyk Nielsen">
1566         <organization abbrev="Microsoft">Microsoft Corporation</organization>
1567         <address><email>henrikn@microsoft.com</email></address>
1568      </author>
1569      <author initials="L." surname="Masinter" fullname="Larry Masinter">
1570         <organization abbrev="Adobe Systems">Adobe Systems, Incorporated</organization>
1571         <address><email>LMM@acm.org</email></address>
1572      </author>
1573      <author initials="P." surname="Leach" fullname="Paul J. Leach">
1574         <organization abbrev="Microsoft">Microsoft Corporation</organization>
1575         <address><email>paulle@microsoft.com</email></address>
1576      </author>
1577      <author initials="T." surname="Berners-Lee" fullname="Tim Berners-Lee">
1578         <organization abbrev="W3C/MIT">World Wide Web Consortium</organization>
1579         <address><email>timbl@w3.org</email></address>
1580      </author>
1581      <author initials="Y." surname="Lafon" fullname="Yves Lafon" role="editor">
1582         <organization abbrev="W3C">World Wide Web Consortium</organization>
1583         <address><email>ylafon@w3.org</email></address>
1584      </author>
1585      <author initials="J. F." surname="Reschke" fullname="Julian F. Reschke" role="editor">
1586         <organization abbrev="greenbytes">greenbytes GmbH</organization>
1587         <address><email>julian.reschke@greenbytes.de</email></address>
1588      </author>
1589      <date month="&ID-MONTH;" year="&ID-YEAR;"/>
1590   </front>
1591   <seriesInfo name="Internet-Draft" value="draft-ietf-httpbis-p4-conditional-&ID-VERSION;"/>
1592   <x:source href="p4-conditional.xml" basename="p4-conditional"/>
1593</reference>
1594
1595<reference anchor="Part5">
1596   <front>
1597      <title abbrev="HTTP/1.1">HTTP/1.1, part 5: Range Requests and Partial Responses</title>
1598      <author initials="R." surname="Fielding" fullname="Roy T. Fielding" role="editor">
1599         <organization abbrev="Day Software">Day Software</organization>
1600         <address><email>fielding@gbiv.com</email></address>
1601      </author>
1602      <author initials="J." surname="Gettys" fullname="Jim Gettys">
1603         <organization>One Laptop per Child</organization>
1604         <address><email>jg@laptop.org</email></address>
1605      </author>
1606      <author initials="J." surname="Mogul" fullname="Jeffrey C. Mogul">
1607         <organization abbrev="HP">Hewlett-Packard Company</organization>
1608         <address><email>JeffMogul@acm.org</email></address>
1609      </author>
1610      <author initials="H." surname="Frystyk" fullname="Henrik Frystyk Nielsen">
1611         <organization abbrev="Microsoft">Microsoft Corporation</organization>
1612         <address><email>henrikn@microsoft.com</email></address>
1613      </author>
1614      <author initials="L." surname="Masinter" fullname="Larry Masinter">
1615         <organization abbrev="Adobe Systems">Adobe Systems, Incorporated</organization>
1616         <address><email>LMM@acm.org</email></address>
1617      </author>
1618      <author initials="P." surname="Leach" fullname="Paul J. Leach">
1619         <organization abbrev="Microsoft">Microsoft Corporation</organization>
1620         <address><email>paulle@microsoft.com</email></address>
1621      </author>
1622      <author initials="T." surname="Berners-Lee" fullname="Tim Berners-Lee">
1623         <organization abbrev="W3C/MIT">World Wide Web Consortium</organization>
1624         <address><email>timbl@w3.org</email></address>
1625      </author>
1626      <author initials="Y." surname="Lafon" fullname="Yves Lafon" role="editor">
1627         <organization abbrev="W3C">World Wide Web Consortium</organization>
1628         <address><email>ylafon@w3.org</email></address>
1629      </author>
1630      <author initials="J. F." surname="Reschke" fullname="Julian F. Reschke" role="editor">
1631         <organization abbrev="greenbytes">greenbytes GmbH</organization>
1632         <address><email>julian.reschke@greenbytes.de</email></address>
1633      </author>
1634      <date month="&ID-MONTH;" year="&ID-YEAR;"/>
1635   </front>
1636   <seriesInfo name="Internet-Draft" value="draft-ietf-httpbis-p5-range-&ID-VERSION;"/>
1637   <x:source href="p5-range.xml" basename="p5-range"/>
1638</reference>
1639
1640<reference anchor="Part6">
1641   <front>
1642      <title abbrev="HTTP/1.1">HTTP/1.1, part 6: Caching</title>
1643      <author initials="R." surname="Fielding" fullname="Roy T. Fielding" role="editor">
1644         <organization abbrev="Day Software">Day Software</organization>
1645         <address><email>fielding@gbiv.com</email></address>
1646      </author>
1647      <author initials="J." surname="Gettys" fullname="Jim Gettys">
1648         <organization>One Laptop per Child</organization>
1649         <address><email>jg@laptop.org</email></address>
1650      </author>
1651      <author initials="J." surname="Mogul" fullname="Jeffrey C. Mogul">
1652         <organization abbrev="HP">Hewlett-Packard Company</organization>
1653         <address><email>JeffMogul@acm.org</email></address>
1654      </author>
1655      <author initials="H." surname="Frystyk" fullname="Henrik Frystyk Nielsen">
1656         <organization abbrev="Microsoft">Microsoft Corporation</organization>
1657         <address><email>henrikn@microsoft.com</email></address>
1658      </author>
1659      <author initials="L." surname="Masinter" fullname="Larry Masinter">
1660         <organization abbrev="Adobe Systems">Adobe Systems, Incorporated</organization>
1661         <address><email>LMM@acm.org</email></address>
1662      </author>
1663      <author initials="P." surname="Leach" fullname="Paul J. Leach">
1664         <organization abbrev="Microsoft">Microsoft Corporation</organization>
1665         <address><email>paulle@microsoft.com</email></address>
1666      </author>
1667      <author initials="T." surname="Berners-Lee" fullname="Tim Berners-Lee">
1668         <organization abbrev="W3C/MIT">World Wide Web Consortium</organization>
1669         <address><email>timbl@w3.org</email></address>
1670      </author>
1671      <author initials="Y." surname="Lafon" fullname="Yves Lafon" role="editor">
1672         <organization abbrev="W3C">World Wide Web Consortium</organization>
1673         <address><email>ylafon@w3.org</email></address>
1674      </author>
1675      <author initials="J. F." surname="Reschke" fullname="Julian F. Reschke" role="editor">
1676         <organization abbrev="greenbytes">greenbytes GmbH</organization>
1677         <address><email>julian.reschke@greenbytes.de</email></address>
1678      </author>
1679      <date month="&ID-MONTH;" year="&ID-YEAR;"/>
1680   </front>
1681   <seriesInfo name="Internet-Draft" value="draft-ietf-httpbis-p6-cache-&ID-VERSION;"/>
1682   <x:source href="p6-cache.xml" basename="p6-cache"/>
1683</reference>
1684
1685<reference anchor="RFC2616">
1686   <front>
1687      <title>Hypertext Transfer Protocol -- HTTP/1.1</title>
1688      <author initials="R." surname="Fielding" fullname="R. Fielding">
1689         <organization>University of California, Irvine</organization>
1690         <address><email>fielding@ics.uci.edu</email></address>
1691      </author>
1692      <author initials="J." surname="Gettys" fullname="J. Gettys">
1693         <organization>W3C</organization>
1694         <address><email>jg@w3.org</email></address>
1695      </author>
1696      <author initials="J." surname="Mogul" fullname="J. Mogul">
1697         <organization>Compaq Computer Corporation</organization>
1698         <address><email>mogul@wrl.dec.com</email></address>
1699      </author>
1700      <author initials="H." surname="Frystyk" fullname="H. Frystyk">
1701         <organization>MIT Laboratory for Computer Science</organization>
1702         <address><email>frystyk@w3.org</email></address>
1703      </author>
1704      <author initials="L." surname="Masinter" fullname="L. Masinter">
1705         <organization>Xerox Corporation</organization>
1706         <address><email>masinter@parc.xerox.com</email></address>
1707      </author>
1708      <author initials="P." surname="Leach" fullname="P. Leach">
1709         <organization>Microsoft Corporation</organization>
1710         <address><email>paulle@microsoft.com</email></address>
1711      </author>
1712      <author initials="T." surname="Berners-Lee" fullname="T. Berners-Lee">
1713         <organization>W3C</organization>
1714         <address><email>timbl@w3.org</email></address>
1715      </author>
1716      <date month="June" year="1999"/>
1717   </front>
1718   <seriesInfo name="RFC" value="2616"/>
1719</reference>
1720
1721<reference anchor="RFC1766">
1722<front>
1723<title abbrev="Language Tag">Tags for the Identification of Languages</title>
1724<author initials="H." surname="Alvestrand" fullname="Harald Tveit Alvestrand">
1725<organization>UNINETT</organization>
1726<address>
1727<postal>
1728<street>Pb. 6883 Elgeseter</street>
1729<city>Trondheim</city>
1730<region/>
1731<code>N-7002</code>
1732<country>NO</country></postal>
1733<phone>+47 73 597094</phone>
1734<email>Harald.T.Alvestrand@uninett.no</email></address></author>
1735<date month="March" year="1995"/>
1736</front>
1737<seriesInfo name="RFC" value="1766"/>
1738</reference>
1739
1740<reference anchor="RFC2045">
1741<front>
1742<title abbrev="Internet Message Bodies">Multipurpose Internet Mail Extensions (MIME) Part One: Format of Internet Message Bodies</title>
1743<author initials="N." surname="Freed" fullname="Ned Freed">
1744<organization>Innosoft International, Inc.</organization>
1745<address>
1746<postal>
1747<street>1050 East Garvey Avenue South</street>
1748<city>West Covina</city>
1749<region>CA</region>
1750<code>91790</code>
1751<country>US</country></postal>
1752<phone>+1 818 919 3600</phone>
1753<facsimile>+1 818 919 3614</facsimile>
1754<email>ned@innosoft.com</email></address></author>
1755<author initials="N.S." surname="Borenstein" fullname="Nathaniel S. Borenstein">
1756<organization>First Virtual Holdings</organization>
1757<address>
1758<postal>
1759<street>25 Washington Avenue</street>
1760<city>Morristown</city>
1761<region>NJ</region>
1762<code>07960</code>
1763<country>US</country></postal>
1764<phone>+1 201 540 8967</phone>
1765<facsimile>+1 201 993 3032</facsimile>
1766<email>nsb@nsb.fv.com</email></address></author>
1767<date month="November" year="1996"/>
1768</front>
1769<seriesInfo name="RFC" value="2045"/>
1770</reference>
1771
1772<reference anchor="RFC822">
1773<front>
1774<title abbrev="Standard for ARPA Internet Text Messages">Standard for the format of ARPA Internet text messages</title>
1775<author initials="D.H." surname="Crocker" fullname="David H. Crocker">
1776<organization>University of Delaware, Dept. of Electrical Engineering</organization>
1777<address>
1778<postal>
1779<street/>
1780<city>Newark</city>
1781<region>DE</region>
1782<code>19711</code>
1783<country>US</country></postal>
1784<email>DCrocker@UDel-Relay</email></address></author>
1785<date month="August" day="13" year="1982"/></front>
1786<seriesInfo name="STD" value="11"/>
1787<seriesInfo name="RFC" value="822"/>
1788</reference>
1789
1790<reference anchor="RFC1867">
1791<front>
1792<title>Form-based File Upload in HTML</title>
1793<author initials="L." surname="Masinter" fullname="Larry Masinter">
1794<organization>Xerox Palo Alto Research Center</organization>
1795<address>
1796<postal>
1797<street>3333 Coyote Hill Road</street>
1798<city>Palo Alto</city>
1799<region>CA</region>
1800<code>94304</code>
1801<country>US</country></postal>
1802<phone>+1 415 812 4365</phone>
1803<facsimile>+1 415 812 4333</facsimile>
1804<email>masinter@parc.xerox.com</email></address></author>
1805<author initials="E." surname="Nebel" fullname="Ernesto Nebel">
1806<organization>XSoft, Xerox Corporation</organization>
1807<address>
1808<postal>
1809<street>10875 Rancho Bernardo Road</street>
1810<street>Suite 200</street>
1811<city>San Diego</city>
1812<region>CA</region>
1813<code>92127-2116</code>
1814<country>US</country></postal>
1815<phone>+1 619 676 7817</phone>
1816<facsimile>+1 619 676 7865</facsimile>
1817<email>nebel@xsoft.sd.xerox.com</email></address></author>
1818<date month="November" year="1995"/>
1819</front>
1820<seriesInfo name="RFC" value="1867"/>
1821</reference>
1822
1823<reference anchor="RFC4288">
1824  <front>
1825    <title>Media Type Specifications and Registration Procedures</title>
1826    <author initials="N." surname="Freed" fullname="N. Freed">
1827      <organization>Sun Microsystems</organization>
1828      <address>
1829        <email>ned.freed@mrochek.com</email>
1830      </address>
1831    </author>
1832    <author initials="J." surname="Klensin" fullname="J. Klensin">
1833      <organization/>
1834      <address>
1835        <email>klensin+ietf@jck.com</email>
1836      </address>
1837    </author>
1838    <date year="2005" month="December"/>
1839  </front>
1840  <seriesInfo name="BCP" value="13"/>
1841  <seriesInfo name="RFC" value="4288"/>
1842</reference>
1843
1844<reference anchor="RFC1864">
1845<front>
1846<title abbrev="Content-MD5 Header Field">The Content-MD5 Header Field</title>
1847<author initials="J." surname="Myers" fullname="John G. Myers">
1848<organization>Carnegie Mellon University</organization>
1849<address>
1850<phone/>
1851<email>jgm+@cmu.edu</email></address></author>
1852<author initials="M." surname="Rose" fullname="Marshall T. Rose">
1853<organization>Dover Beach Consulting, Inc.</organization>
1854<address>
1855<phone/>
1856<email>mrose@dbc.mtview.ca.us</email></address></author>
1857<date month="October" year="1995"/>
1858</front>
1859<seriesInfo name="RFC" value="1864"/>
1860</reference>
1861
1862
1863<reference anchor="RFC1952">
1864<front>
1865<title>GZIP file format specification version 4.3</title>
1866<author initials="P." surname="Deutsch" fullname="L. Peter Deutsch">
1867<organization>Aladdin Enterprises</organization>
1868<address>
1869<postal>
1870<street>203 Santa Margarita Ave.</street>
1871<city>Menlo Park</city>
1872<region>CA</region>
1873<code>94025</code>
1874<country>US</country></postal>
1875<phone>+1 415 322 0103</phone>
1876<facsimile>+1 415 322 1734</facsimile>
1877<email>ghost@aladdin.com</email></address></author>
1878<author initials="J-L." surname="Gailly" fullname="Jean-Loup Gailly">
1879<organization/>
1880<address>
1881<postal>
1882<street/>
1883<city/>
1884<region/>
1885<code/>
1886<country/></postal>
1887<phone/>
1888<email>gzip@prep.ai.mit.edu</email></address></author>
1889<author initials="M." surname="Adler" fullname="Mark Adler">
1890<organization/>
1891<address>
1892<postal>
1893<street/>
1894<city/>
1895<region/>
1896<code/>
1897<country/></postal>
1898<phone/>
1899<email>madler@alumni.caltech.edu</email></address></author>
1900<author initials="L.P." surname="Deutsch" fullname="L. Peter Deutsch">
1901<organization/>
1902<address>
1903<postal>
1904<street/>
1905<city/>
1906<region/>
1907<code/>
1908<country/></postal>
1909<phone/>
1910<email>ghost@aladdin.com</email></address></author>
1911<author initials="G." surname="Randers-Pehrson" fullname="Glenn Randers-Pehrson">
1912<organization/>
1913<address>
1914<postal>
1915<street/>
1916<city/>
1917<region/>
1918<code/>
1919<country/></postal>
1920<phone/>
1921<email>randeg@alumni.rpi.edu</email></address></author>
1922<date month="May" year="1996"/>
1923</front>
1924<seriesInfo name="RFC" value="1952"/>
1925</reference>
1926
1927<reference anchor="RFC1951">
1928<front>
1929<title>DEFLATE Compressed Data Format Specification version 1.3</title>
1930<author initials="P." surname="Deutsch" fullname="L. Peter Deutsch">
1931<organization>Aladdin Enterprises</organization>
1932<address>
1933<postal>
1934<street>203 Santa Margarita Ave.</street>
1935<city>Menlo Park</city>
1936<region>CA</region>
1937<code>94025</code>
1938<country>US</country></postal>
1939<phone>+1 415 322 0103</phone>
1940<facsimile>+1 415 322 1734</facsimile>
1941<email>ghost@aladdin.com</email></address></author>
1942<date month="May" year="1996"/>
1943<abstract>
1944<t>This specification defines a lossless compressed data format that compresses data using a combination of the LZ77 algorithm and Huffman coding, with efficiency comparable to the best currently available general-purpose compression methods.  The data can be produced or consumed, even for an arbitrarily long sequentially presented input data stream, using only an a priori bounded amount of intermediate storage.  The format can be implemented readily in a manner not covered by patents.</t></abstract></front>
1945<seriesInfo name="RFC" value="1951"/>
1946</reference>
1947
1948<reference anchor="RFC1950">
1949<front>
1950<title>ZLIB Compressed Data Format Specification version 3.3</title>
1951<author initials="L.P." surname="Deutsch" fullname="L. Peter Deutsch">
1952<organization>Aladdin Enterprises</organization>
1953<address>
1954<postal>
1955<street>203 Santa Margarita Ave.</street>
1956<city>Menlo Park</city>
1957<region>CA</region>
1958<code>94025</code>
1959<country>US</country></postal>
1960<phone>+1 415 322 0103</phone>
1961<facsimile>+1 415 322 1734</facsimile>
1962<email>ghost@aladdin.com</email></address></author>
1963<author initials="J-L." surname="Gailly" fullname="Jean-Loup Gailly">
1964<organization/></author>
1965<date month="May" year="1996"/>
1966<abstract>
1967<t>This specification defines a lossless compressed data format.  The data can be produced or consumed, even for an arbitrarily long sequentially presented input data stream, using only an a priori bounded amount of intermediate storage.  The format presently uses the DEFLATE compression method but can be easily extended to use
1968   other compression methods.  It can be implemented readily in a manner not covered by patents.  This specification also defines the ADLER-32 checksum (an extension and improvement of the Fletcher checksum), used for detection of data corruption, and provides an algorithm for computing it.</t></abstract></front>
1969<seriesInfo name="RFC" value="1950"/>
1970</reference>
1971
1972<reference anchor="RFC2068">
1973<front>
1974<title abbrev="HTTP/1.1">Hypertext Transfer Protocol -- HTTP/1.1</title>
1975<author initials="R." surname="Fielding" fullname="Roy T. Fielding">
1976<organization>University of California, Irvine, Department of Information and Computer Science</organization>
1977<address>
1978<postal>
1979<street/>
1980<city>Irvine</city>
1981<region>CA</region>
1982<code>92717-3425</code>
1983<country>US</country></postal>
1984<facsimile>+1 714 824 4056</facsimile>
1985<email>fielding@ics.uci.edu</email></address></author>
1986<author initials="J." surname="Gettys" fullname="Jim Gettys">
1987<organization>MIT Laboratory for Computer Science</organization>
1988<address>
1989<postal>
1990<street>545 Technology Square</street>
1991<city>Cambridge</city>
1992<region>MA</region>
1993<code>02139</code>
1994<country>US</country></postal>
1995<facsimile>+1 617 258 8682</facsimile>
1996<email>jg@w3.org</email></address></author>
1997<author initials="J." surname="Mogul" fullname="Jeffrey C. Mogul">
1998<organization>Digital Equipment Corporation, Western Research Laboratory</organization>
1999<address>
2000<postal>
2001<street>250 University Avenue</street>
2002<city>Palo Alto</city>
2003<region>CA</region>
2004<code>94301</code>
2005<country>US</country></postal>
2006<email>mogul@wrl.dec.com</email></address></author>
2007<author initials="H." surname="Nielsen" fullname="Henrik Frystyk Nielsen">
2008<organization>MIT Laboratory for Computer Science</organization>
2009<address>
2010<postal>
2011<street>545 Technology Square</street>
2012<city>Cambridge</city>
2013<region>MA</region>
2014<code>02139</code>
2015<country>US</country></postal>
2016<facsimile>+1 617 258 8682</facsimile>
2017<email>frystyk@w3.org</email></address></author>
2018<author initials="T." surname="Berners-Lee" fullname="Tim Berners-Lee">
2019<organization>MIT Laboratory for Computer Science</organization>
2020<address>
2021<postal>
2022<street>545 Technology Square</street>
2023<city>Cambridge</city>
2024<region>MA</region>
2025<code>02139</code>
2026<country>US</country></postal>
2027<facsimile>+1 617 258 8682</facsimile>
2028<email>timbl@w3.org</email></address></author>
2029<date month="January" year="1997"/>
2030<abstract>
2031<t>The Hypertext Transfer Protocol (HTTP) is an application-level protocol for distributed, collaborative, hypermedia information systems. It is a generic, stateless, object-oriented protocol which can be used for many tasks, such as name servers and distributed object management systems, through extension of its request methods. A feature of HTTP is the typing and negotiation of data representation, allowing systems to be built independently of the data being transferred.</t>
2032<t>HTTP has been in use by the World-Wide Web global information initiative since 1990. This specification defines the protocol referred to as "HTTP/1.1".</t></abstract></front>
2033<seriesInfo name="RFC" value="2068"/>
2034</reference>
2035
2036<reference anchor="RFC1806">
2037<front>
2038<title abbrev="Content-Disposition">Communicating Presentation Information in Internet Messages: The Content-Disposition Header</title>
2039<author initials="R." surname="Troost" fullname="Rens Troost">
2040<organization>New Century Systems</organization>
2041<address>
2042<postal>
2043<street>324 East 41st Street #804</street>
2044<city>New York</city>
2045<region>NY</region>
2046<code>10017</code>
2047<country>US</country></postal>
2048<phone>+1 212 557 2050</phone>
2049<facsimile>+1 212 557 2049</facsimile>
2050<email>rens@century.com</email></address></author>
2051<author initials="S." surname="Dorner" fullname="Steve Dorner">
2052<organization>QUALCOMM Incorporated</organization>
2053<address>
2054<postal>
2055<street>6455 Lusk Boulevard</street>
2056<city>San Diego</city>
2057<region>CA</region>
2058<code>92121</code>
2059<country>US</country></postal>
2060<email>sdorner@qualcomm.com</email></address></author>
2061<date month="June" year="1995"/>
2062<abstract>
2063<t>This memo provides a mechanism whereby messages conforming to the("MIME") specification can convey presentational information.  It specifies a new "Content-Disposition" header, optional and valid for anyentity ("message" or "body part"). Two values for this header are described in this memo; one for the ordinary linear presentation of the body part, and another to facilitate the use of mail to transfer files. It is expected that more values will be defined in the future, and procedures are defined for extending this set of values.</t>
2064<t>This document is intended as an extension to. As such, the reader is assumed to be familiar with, and. The information presented herein supplements but does not replace that found in those documents.</t></abstract></front>
2065<seriesInfo name="RFC" value="1806"/>
2066</reference>
2067
2068<reference anchor="RFC2076">
2069<front>
2070<title abbrev="Internet Message Headers">Common Internet Message Headers</title>
2071<author initials="J." surname="Palme" fullname="Jacob Palme">
2072<organization>Stockholm University/KTH</organization>
2073<address>
2074<postal>
2075<street>Electrum 230</street>
2076<street>S-164 40 Kista</street>
2077<country>SE</country></postal>
2078<phone>+46 8 161667</phone>
2079<facsimile>+46 8 7830829</facsimile>
2080<email>jpalme@dsv.su.se</email></address></author>
2081<date month="February" year="1997"/>
2082<abstract>
2083<t>This memo contains a table of commonly occurring headers in headings of e-mail messages. The document compiles information from other RFCs such as RFC 822, RFC 1036, RFC 1123, RFC 1327, RFC 1496, RFC 1521, RFC 1766, RFC 1806, RFC 1864 and RFC 1911. A few commonly occurring headers which are not defined in RFCs are also included. For each header, the memo gives a short description and a reference to the RFC in which the header is defined.</t></abstract></front>
2084<seriesInfo name="RFC" value="2076"/>
2085</reference>
2086
2087<reference anchor="RFC2119">
2088  <front>
2089    <title>Key words for use in RFCs to Indicate Requirement Levels</title>
2090    <author initials="S." surname="Bradner" fullname="Scott Bradner">
2091      <organization>Harvard University</organization>
2092      <address><email>sob@harvard.edu</email></address>
2093    </author>
2094    <date month="March" year="1997"/>
2095  </front>
2096  <seriesInfo name="BCP" value="14"/>
2097  <seriesInfo name="RFC" value="2119"/>
2098</reference>
2099
2100<reference anchor="RFC2279">
2101<front>
2102<title abbrev="UTF-8">UTF-8, a transformation format of ISO 10646</title>
2103<author initials="F." surname="Yergeau" fullname="Francois Yergeau">
2104<organization>Alis Technologies</organization>
2105<address>
2106<postal>
2107<street>100, boul. Alexis-Nihon</street>
2108<street>Suite 600</street>
2109<city>Montreal</city>
2110<region>Quebec</region>
2111<code>H4M 2P2</code>
2112<country>CA</country></postal>
2113<phone>+1 514 747 2547</phone>
2114<facsimile>+1 514 747 2561</facsimile>
2115<email>fyergeau@alis.com</email></address></author>
2116<date month="January" year="1998"/>
2117<abstract>
2118<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>
2119<seriesInfo name="RFC" value="2279"/>
2120</reference>
2121
2122<reference anchor="RFC2046">
2123<front>
2124<title abbrev="Media Types">Multipurpose Internet Mail Extensions (MIME) Part Two: Media Types</title>
2125<author initials="N." surname="Freed" fullname="Ned Freed">
2126<organization>Innosoft International, Inc.</organization>
2127<address>
2128<postal>
2129<street>1050 East Garvey Avenue South</street>
2130<city>West Covina</city>
2131<region>CA</region>
2132<code>91790</code>
2133<country>US</country></postal>
2134<phone>+1 818 919 3600</phone>
2135<facsimile>+1 818 919 3614</facsimile>
2136<email>ned@innosoft.com</email></address></author>
2137<author initials="N." surname="Borenstein" fullname="Nathaniel S. Borenstein">
2138<organization>First Virtual Holdings</organization>
2139<address>
2140<postal>
2141<street>25 Washington Avenue</street>
2142<city>Morristown</city>
2143<region>NJ</region>
2144<code>07960</code>
2145<country>US</country></postal>
2146<phone>+1 201 540 8967</phone>
2147<facsimile>+1 201 993 3032</facsimile>
2148<email>nsb@nsb.fv.com</email></address></author>
2149<date month="November" year="1996"/>
2150</front>
2151<seriesInfo name="RFC" value="2046"/>
2152</reference>
2153
2154<reference anchor="RFC2277">
2155<front>
2156<title abbrev="Charset Policy">IETF Policy on Character Sets and Languages</title>
2157<author initials="H.T." surname="Alvestrand" fullname="Harald Tveit Alvestrand">
2158<organization>UNINETT</organization>
2159<address>
2160<postal>
2161<street>P.O.Box 6883 Elgeseter</street>
2162<street>N-7002 TRONDHEIM</street>
2163<country>NORWAY</country></postal>
2164<phone>+47 73 59 70 94</phone>
2165<email>Harald.T.Alvestrand@uninett.no</email></address></author>
2166<date month="January" year="1998"/>
2167<area>Applications</area>
2168<keyword>Internet Engineering Task Force</keyword>
2169<keyword>character encoding</keyword></front>
2170<seriesInfo name="BCP" value="18"/>
2171<seriesInfo name="RFC" value="2277"/>
2172</reference>
2173
2174<reference anchor="RFC2110">
2175<front>
2176<title abbrev="MHTML">MIME E-mail Encapsulation of Aggregate Documents, such as HTML (MHTML)</title>
2177<author initials="J." surname="Palme" fullname="Jacob Palme">
2178<organization>Stockholm University and KTH</organization>
2179<address>
2180<postal>
2181<street>Electrum 230</street>
2182<street>S-164 40 Kista</street>
2183<country>Sweden</country></postal>
2184<phone>+46-8-16 16 67</phone>
2185<facsimile>+46-8-783 08 29</facsimile>
2186<email>jpalme@dsv.su.se</email></address></author>
2187<author initials="A." surname="Hopmann" fullname="Alex Hopmann">
2188<organization>Microsoft Corporation</organization>
2189<address>
2190<postal>
2191<street>3590 North First Street</street>
2192<street>Suite 300</street>
2193<street>San Jose</street>
2194<street>CA 95134</street>
2195<street>Working group chairman:</street></postal>
2196<email>alexhop@microsoft.com</email></address></author>
2197<date month="March" year="1997"/>
2198<area>Applications</area>
2199<keyword>encapsulate</keyword>
2200<keyword>hypertext markup language</keyword>
2201<keyword>mail</keyword>
2202<keyword>multipurpose internet mail extensions</keyword>
2203</front>
2204<seriesInfo name="RFC" value="2110"/>
2205</reference>
2206
2207<reference anchor="RFC2049">
2208<front>
2209<title abbrev="MIME Conformance">Multipurpose Internet Mail Extensions (MIME) Part Five: Conformance Criteria and Examples</title>
2210<author initials="N." surname="Freed" fullname="Ned Freed">
2211<organization>Innosoft International, Inc.</organization>
2212<address>
2213<postal>
2214<street>1050 East Garvey Avenue South</street>
2215<street>West Covina</street>
2216<street>CA 91790</street>
2217<country>USA</country></postal>
2218<phone>+1 818 919 3600</phone>
2219<facsimile>+1 818 919 3614</facsimile>
2220<email>ned@innosoft.com</email></address></author>
2221<author initials="N.S." surname="Borenstein" fullname="Nathaniel S. Borenstein">
2222<organization>First Virtual Holdings</organization>
2223<address>
2224<postal>
2225<street>25 Washington Avenue</street>
2226<street>Morristown</street>
2227<street>NJ 07960</street>
2228<country>USA</country></postal>
2229<phone>+1 201 540 8967</phone>
2230<facsimile>+1 201 993 3032</facsimile>
2231<email>nsb@nsb.fv.com</email></address></author>
2232<date month="November" year="1996"/>
2233<area>Applications</area>
2234<keyword>mail</keyword>
2235<keyword>multipurpose internet mail extensions</keyword>
2236</front>
2237<seriesInfo name="RFC" value="2049"/>
2238</reference>
2239
2240<reference anchor="RFC2183">
2241<front>
2242<title abbrev="Content-Disposition">Communicating Presentation Information in Internet Messages: The Content-Disposition Header Field</title>
2243<author initials="R." surname="Troost" fullname="Rens Troost">
2244<organization>New Century Systems</organization>
2245<address>
2246<postal>
2247<street>324 East 41st Street #804</street>
2248<street>New York</street>
2249<street>NY</street>
2250<street>10017</street>
2251<country>USA</country></postal>
2252<phone>+1 (212) 557-2050</phone>
2253<facsimile>+1 (212) 557-2049</facsimile>
2254<email>rens@century.com</email></address></author>
2255<author initials="S." surname="Dorner" fullname="Steve Dorner">
2256<organization>QUALCOMM Incorporated</organization>
2257<address>
2258<postal>
2259<street>6455 Lusk Boulevard</street>
2260<street>San Diego</street>
2261<street>CA 92121</street>
2262<country>USA</country></postal>
2263<email>sdorner@qualcomm.com</email></address></author>
2264<author initials="K." surname="Moore" fullname="Keith Moore">
2265<organization>Department of Computer Science</organization>
2266<address>
2267<postal>
2268<street>University of Tennessee</street>
2269<street>Knoxville</street>
2270<street>107 Ayres Hall</street>
2271<street>Knoxville TN  37996-1301</street>
2272<country>USA</country></postal>
2273<phone>+1 (423) 974-5067</phone>
2274<facsimile>+1 (423) 974-8296</facsimile>
2275<email>moore@cs.utk.edu</email></address></author>
2276<date month="August" year="1997"/>
2277<area>Applications</area>
2278<keyword>MIME</keyword>
2279<keyword>internet message</keyword>
2280<keyword>multipurpose internet mail extensions</keyword>
2281</front>
2282<seriesInfo name="RFC" value="2183"/>
2283</reference>
2284
2285</references>
2286
2287<section title="Differences Between HTTP Entities and RFC 2045 Entities" anchor="differences.between.http.entities.and.rfc.2045.entities">
2288<t>
2289   HTTP/1.1 uses many of the constructs defined for Internet Mail (RFC
2290   822 <xref target="RFC822"/>) and the Multipurpose Internet Mail Extensions (MIME <xref target="RFC2045"/>) to
2291   allow entities to be transmitted in an open variety of
2292   representations and with extensible mechanisms. However, RFC 2045
2293   discusses mail, and HTTP has a few features that are different from
2294   those described in RFC 2045. These differences were carefully chosen
2295   to optimize performance over binary connections, to allow greater
2296   freedom in the use of new media types, to make date comparisons
2297   easier, and to acknowledge the practice of some early HTTP servers
2298   and clients.
2299</t>
2300<t>
2301   This appendix describes specific areas where HTTP differs from RFC
2302   2045. Proxies and gateways to strict MIME environments &SHOULD; be
2303   aware of these differences and provide the appropriate conversions
2304   where necessary. Proxies and gateways from MIME environments to HTTP
2305   also need to be aware of the differences because some conversions
2306   might be required.
2307</t>
2308<section title="MIME-Version" anchor="mime-version">
2309<t>
2310   HTTP is not a MIME-compliant protocol. However, HTTP/1.1 messages &MAY;
2311   include a single MIME-Version general-header field to indicate what
2312   version of the MIME protocol was used to construct the message. Use
2313   of the MIME-Version header field indicates that the message is in
2314   full compliance with the MIME protocol (as defined in RFC 2045<xref target="RFC2045"/>).
2315   Proxies/gateways are responsible for ensuring full compliance (where
2316   possible) when exporting HTTP messages to strict MIME environments.
2317</t>
2318<figure><artwork type="abnf2616"><iref primary="true" item="Grammar" subitem="MIME-Version"/>
2319    MIME-Version   = "MIME-Version" ":" 1*DIGIT "." 1*DIGIT
2320</artwork></figure>
2321<t>
2322   MIME version "1.0" is the default for use in HTTP/1.1. However,
2323   HTTP/1.1 message parsing and semantics are defined by this document
2324   and not the MIME specification.
2325</t>
2326</section>
2327
2328<section title="Conversion to Canonical Form" anchor="conversion.to.canonical.form">
2329<t>
2330   RFC 2045 <xref target="RFC2045"/> requires that an Internet mail entity be converted to
2331   canonical form prior to being transferred, as described in section <xref target="RFC2049" x:fmt="number" x:sec="4"/>
2332   of RFC 2049 <xref target="RFC2049"/>. <xref target="canonicalization.and.text.defaults"/> of this document describes the forms
2333   allowed for subtypes of the "text" media type when transmitted over
2334   HTTP. RFC 2046 requires that content with a type of "text" represent
2335   line breaks as CRLF and forbids the use of CR or LF outside of line
2336   break sequences. HTTP allows CRLF, bare CR, and bare LF to indicate a
2337   line break within text content when a message is transmitted over
2338   HTTP.
2339</t>
2340<t>
2341   Where it is possible, a proxy or gateway from HTTP to a strict MIME
2342   environment &SHOULD; translate all line breaks within the text media
2343   types described in <xref target="canonicalization.and.text.defaults"/> of this document to the RFC 2049
2344   canonical form of CRLF. Note, however, that this might be complicated
2345   by the presence of a Content-Encoding and by the fact that HTTP
2346   allows the use of some character sets which do not use octets 13 and
2347   10 to represent CR and LF, as is the case for some multi-byte
2348   character sets.
2349</t>
2350<t>
2351   Implementors should note that conversion will break any cryptographic
2352   checksums applied to the original content unless the original content
2353   is already in canonical form. Therefore, the canonical form is
2354   recommended for any content that uses such checksums in HTTP.
2355</t>
2356</section>
2357
2358<section title="Introduction of Content-Encoding" anchor="introduction.of.content-encoding">
2359<t>
2360   RFC 2045 does not include any concept equivalent to HTTP/1.1's
2361   Content-Encoding header field. Since this acts as a modifier on the
2362   media type, proxies and gateways from HTTP to MIME-compliant
2363   protocols &MUST; either change the value of the Content-Type header
2364   field or decode the entity-body before forwarding the message. (Some
2365   experimental applications of Content-Type for Internet mail have used
2366   a media-type parameter of ";conversions=&lt;content-coding&gt;" to perform
2367   a function equivalent to Content-Encoding. However, this parameter is
2368   not part of RFC 2045).
2369</t>
2370</section>
2371
2372<section title="No Content-Transfer-Encoding" anchor="no.content-transfer-encoding">
2373<t>
2374   HTTP does not use the Content-Transfer-Encoding field of RFC
2375   2045. Proxies and gateways from MIME-compliant protocols to HTTP &MUST;
2376   remove any Content-Transfer-Encoding
2377   prior to delivering the response message to an HTTP client.
2378</t>
2379<t>
2380   Proxies and gateways from HTTP to MIME-compliant protocols are
2381   responsible for ensuring that the message is in the correct format
2382   and encoding for safe transport on that protocol, where "safe
2383   transport" is defined by the limitations of the protocol being used.
2384   Such a proxy or gateway &SHOULD; label the data with an appropriate
2385   Content-Transfer-Encoding if doing so will improve the likelihood of
2386   safe transport over the destination protocol.
2387</t>
2388</section>
2389
2390<section title="Introduction of Transfer-Encoding" anchor="introduction.of.transfer-encoding">
2391<t>
2392   HTTP/1.1 introduces the Transfer-Encoding header field (&header-transfer-encoding;).
2393   Proxies/gateways &MUST; remove any transfer-coding prior to
2394   forwarding a message via a MIME-compliant protocol.
2395</t>
2396</section>
2397
2398<section title="MHTML and Line Length Limitations" anchor="mhtml.line.length">
2399<t>
2400   HTTP implementations which share code with MHTML <xref target="RFC2110"/> implementations
2401   need to be aware of MIME line length limitations. Since HTTP does not
2402   have this limitation, HTTP does not fold long lines. MHTML messages
2403   being transported by HTTP follow all conventions of MHTML, including
2404   line length limitations and folding, canonicalization, etc., since
2405   HTTP transports all message-bodies as payload (see <xref target="multipart.types"/>) and
2406   does not interpret the content or any MIME header lines that might be
2407   contained therein.
2408</t>
2409</section>
2410</section>
2411
2412<section title="Additional Features" anchor="additional.features">
2413<t>
2414   RFC 1945 and RFC 2068 document protocol elements used by some
2415   existing HTTP implementations, but not consistently and correctly
2416   across most HTTP/1.1 applications. Implementors are advised to be
2417   aware of these features, but cannot rely upon their presence in, or
2418   interoperability with, other HTTP/1.1 applications. Some of these
2419   describe proposed experimental features, and some describe features
2420   that experimental deployment found lacking that are now addressed in
2421   the base HTTP/1.1 specification.
2422</t>
2423<t>
2424   A number of other headers, such as Content-Disposition and Title,
2425   from SMTP and MIME are also often implemented (see RFC 2076 <xref target="RFC2076"/>).
2426</t>
2427
2428<section title="Content-Disposition" anchor="content-disposition">
2429<iref item="Headers" subitem="Content-Disposition" primary="true" x:for-anchor=""/>
2430<iref item="Content-Disposition header" primary="true" x:for-anchor=""/>
2431<t>
2432   The Content-Disposition response-header field has been proposed as a
2433   means for the origin server to suggest a default filename if the user
2434   requests that the content is saved to a file. This usage is derived
2435   from the definition of Content-Disposition in RFC 1806 <xref target="RFC1806"/>.
2436</t>
2437<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"/>
2438     content-disposition = "Content-Disposition" ":"
2439                           disposition-type *( ";" disposition-parm )
2440     disposition-type = "attachment" | disp-extension-token
2441     disposition-parm = filename-parm | disp-extension-parm
2442     filename-parm = "filename" "=" quoted-string
2443     disp-extension-token = token
2444     disp-extension-parm = token "=" ( token | quoted-string )
2445</artwork></figure>
2446<t>
2447   An example is
2448</t>
2449<figure><artwork type="example">
2450     Content-Disposition: attachment; filename="fname.ext"
2451</artwork></figure>
2452<t>
2453   The receiving user agent &SHOULD-NOT;  respect any directory path
2454   information present in the filename-parm parameter, which is the only
2455   parameter believed to apply to HTTP implementations at this time. The
2456   filename &SHOULD; be treated as a terminal component only.
2457</t>
2458<t>
2459   If this header is used in a response with the application/octet-stream
2460   content-type, the implied suggestion is that the user agent
2461   should not display the response, but directly enter a `save response
2462   as...' dialog.
2463</t>
2464<t>
2465   See <xref target="content-disposition.issues"/> for Content-Disposition security issues.
2466</t>
2467</section>
2468</section>
2469
2470<section title="Changes from RFC 2068" anchor="changes.from.rfc.2068">
2471<t>
2472   Charset wildcarding is introduced to avoid explosion of character set
2473   names in accept headers. (<xref target="header.accept-charset"/>)
2474</t>
2475<t>
2476   Content-Base was deleted from the specification: it was not
2477   implemented widely, and there is no simple, safe way to introduce it
2478   without a robust extension mechanism. In addition, it is used in a
2479   similar, but not identical fashion in MHTML <xref target="RFC2110"/>.
2480</t>
2481<t>
2482   A content-coding of "identity" was introduced, to solve problems
2483   discovered in caching. (<xref target="content.codings"/>)
2484</t>
2485<t>
2486   Quality Values of zero should indicate that "I don't want something"
2487   to allow clients to refuse a representation. (<xref target="quality.values"/>)
2488</t>
2489<t>
2490   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
2491   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
2492   specification, but not commonly implemented. See RFC 2068 <xref target="RFC2068"/>.
2493</t>
2494</section>
2495</back>
2496</rfc>
Note: See TracBrowser for help on using the repository browser.