diff options
| author | Daniel Veillard <veillard@src.gnome.org> | 1999-10-11 15:09:51 +0000 |
|---|---|---|
| committer | Daniel Veillard <veillard@src.gnome.org> | 1999-10-11 15:09:51 +0000 |
| commit | 7d2c276a65a077932bbe2ae5a1b3af304175f995 (patch) | |
| tree | 6e4edb956a66bdbefea24d7d0f0740dc33ed6395 /result | |
| parent | 6077d03d0ee4774446e30a1b4017e9fffa020923 (diff) | |
| download | android_external_libxml2-7d2c276a65a077932bbe2ae5a1b3af304175f995.tar.gz android_external_libxml2-7d2c276a65a077932bbe2ae5a1b3af304175f995.tar.bz2 android_external_libxml2-7d2c276a65a077932bbe2ae5a1b3af304175f995.zip | |
Fixed probles in some HTML tag autoclose, XML output bug on mixed-content
and fixed the related output for tests, Daniel.
Diffstat (limited to 'result')
35 files changed, 1377 insertions, 4135 deletions
diff --git a/result/SVG/a-wf.xml b/result/SVG/a-wf.xml index c4301bb5..7facfd5c 100644 --- a/result/SVG/a-wf.xml +++ b/result/SVG/a-wf.xml @@ -2,7 +2,7 @@ <svg xmlns="http://www.w3.org/Graphics/SVG/svg-19990412.dtd" width="4in" height="3in"> <desc>This well formed svg document draws a triangle which is a hyperlink
</desc> - <a link="simple" show="replace" actuate="user" href="http://www.w3.org"> + <a xml:link="simple" show="replace" actuate="user" href="http://www.w3.org"> <p d="M 0 0 L 200 0 L 100 200 Z"/> </a> </svg> diff --git a/result/SVG/bike.xml b/result/SVG/bike.xml index 9c5e0c6a..c702188d 100644 --- a/result/SVG/bike.xml +++ b/result/SVG/bike.xml @@ -1,5 +1,6 @@ <?xml version="1.0"?> <!DOCTYPE svg PUBLIC "-//W3C//DTD SVG April 1999//EN" "http://www.w3.org/Graphics/SVG/svg-19990412.dtd"> +<!--DOCTYPE svg SYSTEM "svg-19990412.dtd"--> <svg width="4in" height="3in"> <title>Kona Lavadome mountain bike
</title> @@ -12,27 +13,33 @@ <defs> <symbol id="spoke"> <desc>14/12 gauge double butted spoke</desc> -<!-- the path data goes here --> </symbol> +<!-- the path data goes here --> + </symbol> <symbol id="hub"> <desc>black anodised low torsion hub</desc> -<!--the path data goes here --> </symbol> +<!--the path data goes here --> + </symbol> <symbol id="rim"> <desc>twin wall, eyeletted rim</desc> -<!-- the path data goes here--> </symbol> +<!-- the path data goes here--> + </symbol> <symbol id="cogs"> <desc>8 speed, wide ratio gearing</desc> -<!--the path data goes here --> </symbol> +<!--the path data goes here --> + </symbol> <symbol id="lacing"> <desc>double cross lacing of 32 spokes</desc> </symbol> </defs> -<!-- the overall bike drawing goes here --> <g id="frontwheel"> +<!-- the overall bike drawing goes here --> + <g id="frontwheel"> <title>Front wheel</title> <desc>The front wheel provides grip, steering and some shock absorption</desc> <use href="id(lacing)" style="rotation: 20deg; fillcolor: black"/> </g> <g id="backwheel"/> <g id="frame"> -<!-- and so on --> </g> +<!-- and so on --> + </g> </g> </svg> diff --git a/result/SVG/defs.xml b/result/SVG/defs.xml index 0ceee0bd..78c6beb6 100644 --- a/result/SVG/defs.xml +++ b/result/SVG/defs.xml @@ -10,4 +10,5 @@ <desc>Defining things for later use
</desc> <!-- SVG elements in here would reference/use
- the elements defined in the <defs> --></svg> + the elements defined in the <defs> --> +</svg> diff --git a/result/SVG/desc.xml b/result/SVG/desc.xml index 7f65d2ae..6fde9660 100644 --- a/result/SVG/desc.xml +++ b/result/SVG/desc.xml @@ -9,5 +9,6 @@ This is a bar chart which shows
company sales by region.
</desc> -<!-- Bar chart defined as vector data --> </g> +<!-- Bar chart defined as vector data --> + </g> </svg> diff --git a/result/SVG/gradient.xml b/result/SVG/gradient.xml index 63f97f7c..4570b76d 100644 --- a/result/SVG/gradient.xml +++ b/result/SVG/gradient.xml @@ -6,7 +6,8 @@ <g> <defs> <lineargradient id="MyGradient"> -<!-- Define linear gradient here --> <gradientstop offset="0%" color="#F60"/> +<!-- Define linear gradient here --> + <gradientstop offset="0%" color="#F60"/> <gradientstop offset="70%" color="#FF6"/> </lineargradient> </defs> diff --git a/result/SVG/image-wf.xml b/result/SVG/image-wf.xml index 54c8df1a..e11a12f4 100644 --- a/result/SVG/image-wf.xml +++ b/result/SVG/image-wf.xml @@ -2,7 +2,7 @@ <svg xmlns="http://www.w3.org/Graphics/SVG/svg-19990412.dtd" width="4in" height="3in"> <desc>This links to an external image
</desc> - <image x="200" y="200" style="width: 100px; height: 100px" link="simple" show="embed" actuate="auto" href="myimage.png"> + <image xml:link="simple" x="200" y="200" style="width: 100px; height: 100px" show="embed" actuate="auto" href="myimage.png"> <title>My image</title> </image> </svg> diff --git a/result/SVG/marker.xml b/result/SVG/marker.xml index f99b977f..1b41714c 100644 --- a/result/SVG/marker.xml +++ b/result/SVG/marker.xml @@ -10,11 +10,14 @@ </desc> <path d="M0 0"> <!-- Place an arrowhead rotated 180 degrees at the
- beginning of the path --> <marker href="#Triangle" width="200" height="200" style="text-transform: rotate(180)"/> + beginning of the path --> + <marker href="#Triangle" width="200" height="200" style="text-transform: rotate(180)"/> <data d="M 2000 2000"/> -<!-- Turn off markers in the middle of the path --> <marker href=""/> +<!-- Turn off markers in the middle of the path --> + <marker href=""/> <data d="L 4000 2000 L 4000 4000"/> -<!-- Place an arrowhead at the end of the path--> <marker href="#Triangle" width="200" height="200"/> +<!-- Place an arrowhead at the end of the path--> + <marker href="#Triangle" width="200" height="200"/> <data d="L 6000 4000"/> </path> </svg> diff --git a/result/SVG/mathswitch.xml b/result/SVG/mathswitch.xml index f7a95ebc..b2913840 100644 --- a/result/SVG/mathswitch.xml +++ b/result/SVG/mathswitch.xml @@ -5,16 +5,21 @@ MathML is not supported.
</desc> <!-- The <switch> element will process the first child element
- whose testing attributes evaluate to true.--> <switch> + whose testing attributes evaluate to true.--> + <switch> <!-- Process the MathML if the system-required attribute
evaluates to true (i.e., the user agent supports MathML
- embedded within SVG). --> <foreignobject system-required="http://www.w3.org/TR/REC-MathML-19980407" width="100" height="50"> -<!-- MathML content goes here --> </foreignobject> + embedded within SVG). --> + <foreignobject system-required="http://www.w3.org/TR/REC-MathML-19980407" width="100" height="50"> +<!-- MathML content goes here --> + </foreignobject> <!-- Else, process the following alternate SVG.
Note that there are no testing attributes on the <g> element.
If no testing attributes are provided, it is as if there
- were testing attributes and they evaluated to true.--> <g> -<!-- Draw a red rectangle with a text string on top. --> <rect style="fill: red"/> + were testing attributes and they evaluated to true.--> + <g> +<!-- Draw a red rectangle with a text string on top. --> + <rect style="fill: red"/> <text>Formula goes here</text> </g> </switch> diff --git a/result/SVG/parentns.xml b/result/SVG/parentns.xml index 0b8ecdcd..5b2ed463 100644 --- a/result/SVG/parentns.xml +++ b/result/SVG/parentns.xml @@ -1,6 +1,9 @@ <?xml version="1.0"?> <ABC xmlns="http://parent.name.space" xmlns:svg="http://www.w3.org/Graphics/SVG/1.0"> -<!-- document in the parent namespace --> <svg:svg width="40%" height="40%"> +<!-- document in the parent namespace --> + <svg:svg width="40%" height="40%"> <svg:rectangle width="43.6" height="31.5"/> -<!-- svg graphic continues --> </svg:svg> -<!-- document in parent namespace continues --></ABC> +<!-- svg graphic continues --> + </svg:svg> +<!-- document in parent namespace continues --> +</ABC> diff --git a/result/SVG/patternfill.xml b/result/SVG/patternfill.xml index 0a425fd7..c520ae81 100644 --- a/result/SVG/patternfill.xml +++ b/result/SVG/patternfill.xml @@ -4,7 +4,8 @@ <defs> <symbol id="fourstar"> <!-- Define the pattern using standard graphics elements
- such as paths, images, text and shapes --> </symbol> + such as paths, images, text and shapes --> + </symbol> </defs> <ellipse style="fill: url(#fourstar)" major="40" minor="27"/> </svg> diff --git a/result/SVG/private.xml b/result/SVG/private.xml index e492a25d..edfe3663 100644 --- a/result/SVG/private.xml +++ b/result/SVG/private.xml @@ -7,10 +7,12 @@ <myapp:piece label="Eastern Region" value="2.53"/> <myapp:piece label="Southern Region" value="3.89"/> <myapp:piece label="Western Region" value="2.04"/> -<!-- Other private data goes here --> </myapp:piechart> +<!-- Other private data goes here --> + </myapp:piechart> </private> </defs> <desc>This chart includes private data in another namespace
</desc> <!-- In here would be the actual graphics elements which
- draw the pie chart --></svg> + draw the pie chart --> +</svg> diff --git a/result/SVG/richdesc.xml b/result/SVG/richdesc.xml index eee8fa33..eba1f058 100644 --- a/result/SVG/richdesc.xml +++ b/result/SVG/richdesc.xml @@ -3,10 +3,9 @@ <desc xmlns:mydoc="http://foo.org/mydoc"> <mydoc:title>This is an example SVG file</mydoc:title> <mydoc:para>The global description uses markup from the
- - <mydoc:emph>mydoc</mydoc:emph> - namespace. </mydoc:para> + <mydoc:emph>mydoc</mydoc:emph> namespace.</mydoc:para> </desc> <g> -<!-- the picture goes here --> </g> +<!-- the picture goes here --> + </g> </svg> diff --git a/result/SVG/script.xml b/result/SVG/script.xml index 133c0a0c..c98af0f7 100644 --- a/result/SVG/script.xml +++ b/result/SVG/script.xml @@ -2,10 +2,11 @@ <!DOCTYPE svg PUBLIC "-//W3C//DTD SVG April 1999//EN" "http://www.w3.org/Graphics/SVG/svg-19990412.dtd"> <svg width="4in" height="3in"> <defs> - <script>
+ <script> +<![CDATA[
/* Beep on mouseclick */
MouseClickHandler() { beep(); }
- >
+ ]]> </script> </defs> <circle onclick="MouseClickHandler()" r="85"/> diff --git a/result/SVG/structure01.xml b/result/SVG/structure01.xml index bdac7423..46af5e80 100644 --- a/result/SVG/structure01.xml +++ b/result/SVG/structure01.xml @@ -1,6 +1,8 @@ <?xml version="1.0" standalone="yes"?> <parent xmlns="http://someplace.org" xmlns:svg="http://www.w3.org/Graphics/SVG/svg-19990412.dtd"> -<!-- parent stuff here --> <svg:svg width="5cm" height="8cm"> +<!-- parent stuff here --> + <svg:svg width="5cm" height="8cm"> <svg:ellipse major="200" minor="130"/> </svg:svg> -<!-- ... --></parent> +<!-- ... --> +</parent> diff --git a/result/SVG/style.xml b/result/SVG/style.xml index 80dfa422..7176912a 100644 --- a/result/SVG/style.xml +++ b/result/SVG/style.xml @@ -2,8 +2,9 @@ <!DOCTYPE svg PUBLIC "-//W3C//DTD SVG April 1999//EN" "http://www.w3.org/Graphics/SVG/svg-19990412.dtd"> <svg width="4in" height="3in"> <defs> - <style>
- .TitleText { font-size: 16; font-family: Helvetica } >
+ <style> +<![CDATA[
+ .TitleText { font-size: 16; font-family: Helvetica } ]]> </style> </defs> <text class="TitleText">Here is my title</text> diff --git a/result/SVG/switch.xml b/result/SVG/switch.xml index 124e6139..87eb3646 100644 --- a/result/SVG/switch.xml +++ b/result/SVG/switch.xml @@ -3,11 +3,14 @@ <body> <!-- The SMIL <switch> element will process the
first child element which tests true and skip
- past all others. --> <switch> + past all others. --> + <switch> <!-- The system-required attribute tests to see if
the user agent supports SVG. If true, then
- render the file drawing.svg. --> <ref system-required="http://www.w3.org/Graphics/SVG/svg-19990412.dtd" type="image/svg" src="drawing.svg"/> -<!-- Else, render the alternate image. --> <img src="alternate_image.jpg"/> + render the file drawing.svg. --> + <ref system-required="http://www.w3.org/Graphics/SVG/svg-19990412.dtd" type="image/svg" src="drawing.svg"/> +<!-- Else, render the alternate image. --> + <img src="alternate_image.jpg"/> </switch> </body> </smil> diff --git a/result/SVG/symbol-use.xml b/result/SVG/symbol-use.xml index f6e97a7b..a9b395c2 100644 --- a/result/SVG/symbol-use.xml +++ b/result/SVG/symbol-use.xml @@ -3,14 +3,20 @@ <svg width="4in" height="3in"> <defs> <symbol id="TemplateObject01"> -<!-- symbol definition here --> </symbol> +<!-- symbol definition here --> + </symbol> </defs> <desc>Examples of inline and referenced content
</desc> -<!-- <g> with inline content --> <g> -<!-- Inline content goes here --> </g> -<!-- referenced content --> <use href="#TemplateObject01"/> -<!-- <g> with both referenced and inline content --> <g> +<!-- <g> with inline content --> + <g> +<!-- Inline content goes here --> + </g> +<!-- referenced content --> + <use href="#TemplateObject01"/> +<!-- <g> with both referenced and inline content --> + <g> <use href="#TemplateObject01"/> -<!-- Inline content goes here --> </g> +<!-- Inline content goes here --> + </g> </svg> diff --git a/result/SVG/template.xml b/result/SVG/template.xml index f844b482..607cd91f 100644 --- a/result/SVG/template.xml +++ b/result/SVG/template.xml @@ -2,7 +2,7 @@ <svg xmlns="http://www.w3.org/Graphics/SVG/svg-19990412.dtd" width="4in" height="3in"> <desc>This well formed svg document contains a hyperlink
</desc> - <a link="simple" show="replace" actuate="user" href="http://www.w3.org"> + <a xml:link="simple" show="replace" actuate="user" href="http://www.w3.org"> <p d="M 0 0 L 200 0 L 100 200 Z"/> </a> </svg> diff --git a/result/SVG/toap01.xml b/result/SVG/toap01.xml index 778d92f5..fac024c0 100644 --- a/result/SVG/toap01.xml +++ b/result/SVG/toap01.xml @@ -4,7 +4,5 @@ <desc>Simple text on a path
</desc> <path id="MyPath" style="visibility: hidden" d="M 100 100 C 125 125 175 125 200 100"/> - <text> - <textpath href="#MyPath"/> -Text on path </text> + <text><textpath href="#MyPath"/>Text on path</text> </svg> diff --git a/result/SVG/transform.xml b/result/SVG/transform.xml index 0f456429..db00dbde 100644 --- a/result/SVG/transform.xml +++ b/result/SVG/transform.xml @@ -4,13 +4,17 @@ <desc>Demonstration of coordinate transforms
</desc> <!-- The following two text elements will both draw with a
- font height of 12 pixels --> <text style="font-size: 12">This prints 12 pixels high.</text> + font height of 12 pixels --> + <text style="font-size: 12">This prints 12 pixels high.</text> <text style="font-size: 12px">This prints 12 pixels high.</text> -<!-- Now scale the coordinate system by 2. --> <g style="transform: scale(2)"> +<!-- Now scale the coordinate system by 2. --> + <g style="transform: scale(2)"> <!-- The following text will actually draw 24 pixels high
because each unit in the new coordinate system equals
- 2 units in the previous coordinate system. --> <text style="font-size: 12">This prints 24 pixels high.</text> + 2 units in the previous coordinate system. --> + <text style="font-size: 12">This prints 24 pixels high.</text> <!-- The following text will actually still draw 12 pixels high
- because the CSS unit specifier has been provided. --> <text style="font-size: 12px">This prints 12 pixels high.</text> + because the CSS unit specifier has been provided. --> + <text style="font-size: 12px">This prints 12 pixels high.</text> </g> </svg> diff --git a/result/SVG/trivial.xml b/result/SVG/trivial.xml index 558c7bf2..db125834 100644 --- a/result/SVG/trivial.xml +++ b/result/SVG/trivial.xml @@ -1,3 +1,4 @@ <?xml version="1.0" standalone="yes"?> <svg xmlns="http://www.w3.org/Graphics/SVG/svg-19990412.dtd" width="4in" height="3in"> -<!-- Insert drawing elements here --></svg> +<!-- Insert drawing elements here --> +</svg> diff --git a/result/SVG/viewport-nest.xml b/result/SVG/viewport-nest.xml index 7ce61a97..b6a19a7d 100644 --- a/result/SVG/viewport-nest.xml +++ b/result/SVG/viewport-nest.xml @@ -5,6 +5,8 @@ thus establishing a new viewport
</desc> <!-- The following statement establishing a new viewport
- and renders SVG drawing B into that viewport --> <svg style="left: 25%; top: 25%" width="50%" height="50%"> -<!-- drawing B goes here --> </svg> + and renders SVG drawing B into that viewport --> + <svg style="left: 25%; top: 25%" width="50%" height="50%"> +<!-- drawing B goes here --> + </svg> </svg> diff --git a/result/SVG/viewport-transform.xml b/result/SVG/viewport-transform.xml index f1c14658..3a95fbdc 100644 --- a/result/SVG/viewport-transform.xml +++ b/result/SVG/viewport-transform.xml @@ -4,25 +4,32 @@ <desc>Transformation with establishment of a new viewport
</desc> <!-- The following two text elements will both draw with a
- font height of 12 pixels --> <text style="font-size: 12">This prints 12 pixels high.</text> + font height of 12 pixels --> + <text style="font-size: 12">This prints 12 pixels high.</text> <text style="font-size: 12px">This prints 12 pixels high.</text> -<!-- Now scale the coordinate system by 2. --> <g style="transform: scale(2)"> +<!-- Now scale the coordinate system by 2. --> + <g style="transform: scale(2)"> <!-- The following text will actually draw 24 pixels high
because each unit in the new coordinate system equals
- 2 units in the previous coordinate system. --> <text style="font-size: 12">This prints 24 pixels high.</text> + 2 units in the previous coordinate system. --> + <text style="font-size: 12">This prints 24 pixels high.</text> <!-- The following text will actually still draw 12 pixels high
- because the CSS unit specifier has been provided. --> <text style="font-size: 12px">This prints 12 pixels high.</text> + because the CSS unit specifier has been provided. --> + <text style="font-size: 12px">This prints 12 pixels high.</text> </g> -<!-- This time, scale the coordinate system by 3. --> <g style="transform: scale(3)"> +<!-- This time, scale the coordinate system by 3. --> + <g style="transform: scale(3)"> <!-- Establish a new viewport and thus change the meaning of
- some CSS unit specifiers. --> <svg style="left:0; top:0; right:100; bottom:100" width="100%" height="100%"> + some CSS unit specifiers. --> + <svg style="left:0; top:0; right:100; bottom:100" width="100%" height="100%"> <!-- The following two text elements will both draw with a
font height of 36 screen pixels. The first text element
defines its height in user coordinates, which have been
scaled by 3. The second text element defines its height
in CSS px units, which have been redefined to be three times
as big as screen pixels due the <svg> element establishing
- a new viewport. --> <text style="font-size: 12">This prints 36 pixels high.</text> + a new viewport. --> + <text style="font-size: 12">This prints 36 pixels high.</text> <text style="font-size: 12px">This prints 36 pixels high.</text> </svg> </g> diff --git a/result/SVG/viewport.xml b/result/SVG/viewport.xml index 2847a2fb..22d1ad3b 100644 --- a/result/SVG/viewport.xml +++ b/result/SVG/viewport.xml @@ -1,6 +1,8 @@ <?xml version="1.0" standalone="yes"?> <parent xmlns="http://some.url"> -<!-- SVG graphic --> <svg xmlns="http://www.w3.org/Graphics/SVG/svg-19990412.dtd" width="100px" height="200px"> +<!-- SVG graphic --> + <svg xmlns="http://www.w3.org/Graphics/SVG/svg-19990412.dtd" width="100px" height="200px"> <path d="M100,100 Q200,400,300,100"/> -<!-- rest of SVG graphic would go here --> </svg> +<!-- rest of SVG graphic would go here --> + </svg> </parent> diff --git a/result/VC/ElementValid b/result/VC/ElementValid index fb23d3a6..f9372b39 100644 --- a/result/VC/ElementValid +++ b/result/VC/ElementValid @@ -1,3 +1,3 @@ -./test/VC/ElementValid:3: validity error: No declaration for element doc +./test/VC/ElementValid:3: validity error: Validation failed: no DTD found ! <doc/> - ^ + ^ diff --git a/result/cdata b/result/cdata index 065f7a31..180ea467 100644 --- a/result/cdata +++ b/result/cdata @@ -1,3 +1,4 @@ <?xml version="1.0"?> <doc> -<![CDATA[<greeting>Hello, world!</greeting>]]></doc> +<![CDATA[<greeting>Hello, world!</greeting>]]> +</doc> diff --git a/result/dtd5 b/result/dtd5 index 4c0a0c5a..5409d51c 100644 --- a/result/dtd5 +++ b/result/dtd5 @@ -4,7 +4,4 @@ <!ELEMENT a (#PCDATA)> <!ELEMENT b (#PCDATA)> ]> -<doc> - <a>This</a> - is a <b>valid</b> - document</doc> +<doc><a>This</a> is a <b>valid</b> document</doc> diff --git a/result/ent1 b/result/ent1 index 04e280ec..3e24756f 100644 --- a/result/ent1 +++ b/result/ent1 @@ -3,4 +3,5 @@ <!ENTITY xml "Extensible Markup Language"> ]> <EXAMPLE> - &xml;</EXAMPLE> + &xml; +</EXAMPLE> diff --git a/result/ent2 b/result/ent2 index 52e92f9d..2b4137ca 100644 --- a/result/ent2 +++ b/result/ent2 @@ -6,6 +6,5 @@ ]> <EXAMPLE> &title; - This text is about XML, the &xml; and this is an embedded - <IMG src="image"/> + This text is about XML, the &xml; and this is an embedded <IMG src="image"/> </EXAMPLE> diff --git a/result/noent/cdata b/result/noent/cdata index 065f7a31..180ea467 100644 --- a/result/noent/cdata +++ b/result/noent/cdata @@ -1,3 +1,4 @@ <?xml version="1.0"?> <doc> -<![CDATA[<greeting>Hello, world!</greeting>]]></doc> +<![CDATA[<greeting>Hello, world!</greeting>]]> +</doc> diff --git a/result/noent/dtd11 b/result/noent/dtd11 index 64c8e04e..e0df8af5 100644 --- a/result/noent/dtd11 +++ b/result/noent/dtd11 @@ -3,4 +3,4 @@ <!ELEMENT doc (#PCDATA)> <!ATTLIST doc val CDATA #IMPLIED> ]> -<doc val=""/> +<doc val="v1"/> diff --git a/result/noent/dtd5 b/result/noent/dtd5 index 4c0a0c5a..5409d51c 100644 --- a/result/noent/dtd5 +++ b/result/noent/dtd5 @@ -4,7 +4,4 @@ <!ELEMENT a (#PCDATA)> <!ELEMENT b (#PCDATA)> ]> -<doc> - <a>This</a> - is a <b>valid</b> - document</doc> +<doc><a>This</a> is a <b>valid</b> document</doc> diff --git a/result/noent/ent2 b/result/noent/ent2 index 83d8f0f5..b0c49a62 100644 --- a/result/noent/ent2 +++ b/result/noent/ent2 @@ -6,7 +6,5 @@ ]> <EXAMPLE> - This text is about XML, the Extensible Markup Language and this is an embedded - <IMG src="image"/> - + This text is about XML, the Extensible Markup Language and this is an embedded <IMG src="image"/> </EXAMPLE> diff --git a/result/valid/REC-xml-19980210.xml b/result/valid/REC-xml-19980210.xml index a232b882..2ff55122 100644 --- a/result/valid/REC-xml-19980210.xml +++ b/result/valid/REC-xml-19980210.xml @@ -120,29 +120,18 @@ This document specifies a syntax created by subsetting an existing, widely used international text processing standard (Standard Generalized Markup Language, ISO 8879:1986(E) as amended and corrected) for use on the World Wide Web. It is a product of the W3C -XML Activity, details of which can be found at - <loc href="http://www.w3.org/XML">http://www.w3.org/XML</loc> -. A list of +XML Activity, details of which can be found at <loc href="http://www.w3.org/XML">http://www.w3.org/XML</loc>. A list of current W3C Recommendations and other technical documents can be found -at <loc href="http://www.w3.org/TR">http://www.w3.org/TR</loc> -. - </p> - <p>This specification uses the term URI, which is defined by - <bibref ref="Berners-Lee"/> -, a work in progress expected to update <bibref ref="RFC1738"/> - and <bibref ref="RFC1808"/> -. - </p> +at <loc href="http://www.w3.org/TR">http://www.w3.org/TR</loc>. +</p> + <p>This specification uses the term URI, which is defined by <bibref ref="Berners-Lee"/>, a work in progress expected to update <bibref ref="RFC1738"/> and <bibref ref="RFC1808"/>. +</p> <p>The list of known errors in this specification is available at - - <loc href="http://www.w3.org/XML/xml-19980210-errata">http://www.w3.org/XML/xml-19980210-errata</loc> -. </p> +<loc href="http://www.w3.org/XML/xml-19980210-errata">http://www.w3.org/XML/xml-19980210-errata</loc>.</p> <p>Please report errors in this document to - - <loc href="mailto:xml-editor@w3.org">xml-editor@w3.org</loc> -. - </p> +<loc href="mailto:xml-editor@w3.org">xml-editor@w3.org</loc>. +</p> </status> <pubstmt> <p>Chicago, Vancouver, Mountain View, et al.: @@ -275,11 +264,9 @@ Terry Allen, Norbert Mikula, James Clark, Jon Bosak, Henry Thompson, Paul Grosso, and self. Among other things: give in on "well formed" (Terry is right), tentatively rename QuotedCData as AttValue and Literal as EntityValue to be more informative, since attribute -values are the - <emph>only</emph> - place QuotedCData was used, and +values are the <emph>only</emph> place QuotedCData was used, and vice versa for entity text and Literal. (I'd call it Entity Text, -but 8879 uses that name for both internal and external entities.) </sitem> +but 8879 uses that name for both internal and external entities.)</sitem> <sitem>1997-03-26 : CMSMcQ : resynch the two forks of this draft, reapply my changes dated 03-20 and 03-21. Normalize old 'may not' to 'must not' except in the one case where it meant 'may or may not'.</sitem> @@ -333,13 +320,11 @@ Lots more cleanup.</sitem> <sitem>1996-10-24 : CMSMcQ : quick tweaks, implement some ERB decisions. Characters are not integers. Comments are /* */ not //. Add bibliographic refs to 10646, HyTime, Unicode. -Rename old Cdata as MsData since it's - <emph>only</emph> - seen +Rename old Cdata as MsData since it's <emph>only</emph> seen in marked sections. Call them attribute-value pairs not name-value pairs, except once. Internal subset is optional, needs '?'. Implied attributes should be signaled to the app, not -have values supplied by processor. </sitem> +have values supplied by processor.</sitem> <sitem>1996-10-16 : TB : track down & excise all DSD references; introduce some EBNF for entity declarations.</sitem> <sitem>1996-10-?? : TB : consistency check, fix up scraps so @@ -382,45 +367,30 @@ do some housekeeping</sitem> <div1 id="sec-intro"> <head>Introduction</head> <p>Extensible Markup Language, abbreviated XML, describes a class of -data objects called - <termref def="dt-xml-doc">XML documents</termref> - and +data objects called <termref def="dt-xml-doc">XML documents</termref> and partially describes the behavior of computer programs which process them. XML is an application profile or restricted form of SGML, the Standard Generalized Markup -Language <bibref ref="ISO8879"/> -. +Language <bibref ref="ISO8879"/>. By construction, XML documents are conforming SGML documents. - </p> - <p>XML documents are made up of storage units called - <termref def="dt-entity">entities</termref> -, which contain either parsed +</p> + <p>XML documents are made up of storage units called <termref def="dt-entity">entities</termref>, which contain either parsed or unparsed data. -Parsed data is made up of <termref def="dt-character">characters</termref> -, +Parsed data is made up of <termref def="dt-character">characters</termref>, some -of which form <termref def="dt-chardata">character data</termref> -, -and some of which form <termref def="dt-markup">markup</termref> -. +of which form <termref def="dt-chardata">character data</termref>, +and some of which form <termref def="dt-markup">markup</termref>. Markup encodes a description of the document's storage layout and logical structure. XML provides a mechanism to impose constraints on -the storage layout and logical structure. </p> - <p> - <termdef id="dt-xml-proc" term="XML Processor">A software module -called an - <term>XML processor</term> - is used to read XML documents -and provide access to their content and structure. </termdef> - <termdef id="dt-app" term="Application">It is assumed that an XML processor is +the storage layout and logical structure.</p> + <p><termdef id="dt-xml-proc" term="XML Processor">A software module +called an <term>XML processor</term> is used to read XML documents +and provide access to their content and structure.</termdef> <termdef id="dt-app" term="Application">It is assumed that an XML processor is doing its work on behalf of another module, called the - - <term>application</term> -. </termdef> - This specification describes the +<term>application</term>.</termdef> This specification describes the required behavior of an XML processor in terms of how it must read XML -data and the information it must provide to the application. </p> +data and the information it must provide to the application.</p> <div2 id="sec-origin-goals"> <head>Origin and Goals</head> <p>XML was developed by an XML Working Group (originally known as the @@ -432,45 +402,12 @@ Interest Group (previously known as the SGML Working Group) also organized by the W3C. The membership of the XML Working Group is given in an appendix. Dan Connolly served as the WG's contact with the W3C. </p> - <p>The design goals for XML are: - <olist> - <item> - <p>XML shall be straightforwardly usable over the -Internet.</p> - </item> - <item> - <p>XML shall support a wide variety of applications.</p> - </item> - <item> - <p>XML shall be compatible with SGML.</p> - </item> - <item> - <p>It shall be easy to write programs which process XML -documents.</p> - </item> - <item> - <p>The number of optional features in XML is to be kept to the -absolute minimum, ideally zero.</p> - </item> - <item> - <p>XML documents should be human-legible and reasonably -clear.</p> - </item> - <item> - <p>The XML design should be prepared quickly.</p> - </item> - <item> - <p>The design of XML shall be formal and concise.</p> - </item> - <item> - <p>XML documents shall be easy to create.</p> - </item> - <item> - <p>Terseness in XML markup is of minimal importance.</p> - </item> - </olist> - - </p> + <p>The design goals for XML are:<olist><item><p>XML shall be straightforwardly usable over the +Internet.</p></item><item><p>XML shall support a wide variety of applications.</p></item><item><p>XML shall be compatible with SGML.</p></item><item><p>It shall be easy to write programs which process XML +documents.</p></item><item><p>The number of optional features in XML is to be kept to the +absolute minimum, ideally zero.</p></item><item><p>XML documents should be human-legible and reasonably +clear.</p></item><item><p>The XML design should be prepared quickly.</p></item><item><p>The design of XML shall be formal and concise.</p></item><item><p>XML documents shall be easy to create.</p></item><item><p>Terseness in XML markup is of minimal importance.</p></item></olist> +</p> <p>This specification, together with associated standards (Unicode and ISO/IEC 10646 for characters, @@ -481,10 +418,8 @@ provides all the information necessary to understand XML Version &XML.version; and construct computer programs to process it.</p> <p>This version of the XML specification - <!-- is for &doc.audience;.--> - -&doc.distribution;. </p> +&doc.distribution;.</p> </div2> <div2 id="sec-terminology"> <head>Terminology</head> @@ -492,49 +427,17 @@ and construct computer programs to process it.</p> this specification. The terms defined in the following list are used in building those definitions and in describing the actions of an XML processor: - - <glist> - <gitem> - <label>may</label> - <def> - <p> - <termdef id="dt-may" term="May">Conforming documents and XML +<glist><gitem><label>may</label><def><p><termdef id="dt-may" term="May">Conforming documents and XML processors are permitted to but need not behave as -described.</termdef> - </p> - </def> - </gitem> - <gitem> - <label>must</label> - <def> - <p>Conforming documents and XML processors +described.</termdef></p></def></gitem><gitem><label>must</label><def><p>Conforming documents and XML processors are required to behave as described; otherwise they are in error. - <!-- do NOT change this! this is what defines a violation of a 'must' clause as 'an error'. -MSM --> - - </p> - </def> - </gitem> - <gitem> - <label>error</label> - <def> - <p> - <termdef id="dt-error" term="Error">A violation of the rules of this +</p></def></gitem><gitem><label>error</label><def><p><termdef id="dt-error" term="Error">A violation of the rules of this specification; results are undefined. Conforming software may detect and report an error and may -recover from it.</termdef> - </p> - </def> - </gitem> - <gitem> - <label>fatal error</label> - <def> - <p> - <termdef id="dt-fatal" term="Fatal Error">An error -which a conforming - <termref def="dt-xml-proc">XML processor</termref> - +recover from it.</termdef></p></def></gitem><gitem><label>fatal error</label><def><p><termdef id="dt-fatal" term="Fatal Error">An error +which a conforming <termref def="dt-xml-proc">XML processor</termref> must detect and report to the application. After encountering a fatal error, the processor may continue @@ -546,48 +449,16 @@ Once a fatal error is detected, however, the processor must not continue normal processing (i.e., it must not continue to pass character data and information about the document's logical structure to the application in the normal way). - </termdef> - </p> - </def> - </gitem> - <gitem> - <label>at user option</label> - <def> - <p>Conforming software may or must (depending on the modal verb in the +</termdef></p></def></gitem><gitem><label>at user option</label><def><p>Conforming software may or must (depending on the modal verb in the sentence) behave as described; if it does, it must provide users a means to enable or disable the behavior -described.</p> - </def> - </gitem> - <gitem> - <label>validity constraint</label> - <def> - <p>A rule which applies to all - - <termref def="dt-valid">valid</termref> - XML documents. +described.</p></def></gitem><gitem><label>validity constraint</label><def><p>A rule which applies to all +<termref def="dt-valid">valid</termref> XML documents. Violations of validity constraints are errors; they must, at user option, be reported by - <termref def="dt-validating">validating XML processors</termref> -. </p> - </def> - </gitem> - <gitem> - <label>well-formedness constraint</label> - <def> - <p>A rule which applies to all - <termref def="dt-wellformed">well-formed</termref> - XML documents. +<termref def="dt-validating">validating XML processors</termref>.</p></def></gitem><gitem><label>well-formedness constraint</label><def><p>A rule which applies to all <termref def="dt-wellformed">well-formed</termref> XML documents. Violations of well-formedness constraints are - <termref def="dt-fatal">fatal errors</termref> -. </p> - </def> - </gitem> - <gitem> - <label>match</label> - <def> - <p> - <termdef id="dt-match" term="match">(Of strings or names:) +<termref def="dt-fatal">fatal errors</termref>.</p></def></gitem><gitem><label>match</label><def><p><termdef id="dt-match" term="match">(Of strings or names:) Two strings or names being compared must be identical. Characters with multiple possible representations in ISO/IEC 10646 (e.g. characters with @@ -602,39 +473,16 @@ language generated by that production. (Of content and content models:) An element matches its declaration when it conforms in the fashion described in the constraint - - <specref ref="elementvalid"/> -. - </termdef> - - </p> - </def> - </gitem> - <gitem> - <label>for compatibility</label> - <def> - <p> - <termdef id="dt-compat" term="For Compatibility">A feature of -XML included solely to ensure that XML remains compatible with SGML. +<specref ref="elementvalid"/>. </termdef> - </p> - </def> - </gitem> - <gitem> - <label>for interoperability</label> - <def> - <p> - <termdef id="dt-interop" term="For interoperability">A +</p></def></gitem><gitem><label>for compatibility</label><def><p><termdef id="dt-compat" term="For Compatibility">A feature of +XML included solely to ensure that XML remains compatible with SGML. +</termdef></p></def></gitem><gitem><label>for interoperability</label><def><p><termdef id="dt-interop" term="For interoperability">A non-binding recommendation included to increase the chances that XML documents can be processed by the existing installed base of SGML processors which predate the -&WebSGML;.</termdef> - </p> - </def> - </gitem> - </glist> - - </p> +&WebSGML;.</termdef></p></def></gitem></glist> +</p> </div2> </div1> <!-- &Docs; --> @@ -643,24 +491,16 @@ processors which predate the <p> <termdef id="dt-xml-doc" term="XML Document"> A data object is an - - <term>XML document</term> - if it is - <termref def="dt-wellformed">well-formed</termref> -, as +<term>XML document</term> if it is +<termref def="dt-wellformed">well-formed</termref>, as defined in this specification. A well-formed XML document may in addition be - <termref def="dt-valid">valid</termref> - if it meets certain further -constraints. </termdef> +<termref def="dt-valid">valid</termref> if it meets certain further +constraints.</termdef> </p> <p>Each XML document has both a logical and a physical structure. -Physically, the document is composed of units called - <termref def="dt-entity">entities</termref> -. An entity may <termref def="dt-entref">refer</termref> - to other entities to cause their -inclusion in the document. A document begins in a "root" or <termref def="dt-docent">document entity</termref> -. +Physically, the document is composed of units called <termref def="dt-entity">entities</termref>. An entity may <termref def="dt-entref">refer</termref> to other entities to cause their +inclusion in the document. A document begins in a "root" or <termref def="dt-docent">document entity</termref>. Logically, the document is composed of declarations, elements, comments, character references, and @@ -668,163 +508,80 @@ processing instructions, all of which are indicated in the document by explicit markup. The logical and physical structures must nest properly, as described -in <specref ref="wf-entities"/> -. - </p> +in <specref ref="wf-entities"/>. +</p> <div2 id="sec-well-formed"> <head>Well-Formed XML Documents</head> - <p> - <termdef id="dt-wellformed" term="Well-Formed"> + <p><termdef id="dt-wellformed" term="Well-Formed"> A textual object is a well-formed XML document if:</termdef> - - <olist> - <item> - <p>Taken as a whole, it -matches the production labeled - <nt def="NT-document">document</nt> -. </p> - </item> - <item> - <p>It -meets all the well-formedness constraints given in this specification.</p> - </item> - <item> - <p>Each of the - <termref def="dt-parsedent">parsed entities</termref> - +<olist><item><p>Taken as a whole, it +matches the production labeled <nt def="NT-document">document</nt>.</p></item><item><p>It +meets all the well-formedness constraints given in this specification.</p></item><item><p>Each of the <termref def="dt-parsedent">parsed entities</termref> which is referenced directly or indirectly within the document is - <titleref href="wf-entities">well-formed</titleref> -. </p> - </item> - </olist> - </p> +<titleref href="wf-entities">well-formed</titleref>.</p></item></olist></p> <p> - - <scrap lang="ebnf" id="document"> - <head>Document</head> - <prod id="NT-document"> - <lhs>document</lhs> - <rhs> - <nt def="NT-prolog">prolog</nt> - - <nt def="NT-element">element</nt> - - <nt def="NT-Misc">Misc</nt> -* </rhs> - </prod> - </scrap> - - </p> - <p>Matching the - <nt def="NT-document">document</nt> - production +<scrap lang="ebnf" id="document"><head>Document</head><prod id="NT-document"><lhs>document</lhs><rhs><nt def="NT-prolog">prolog</nt> +<nt def="NT-element">element</nt> +<nt def="NT-Misc">Misc</nt>*</rhs></prod></scrap> +</p> + <p>Matching the <nt def="NT-document">document</nt> production implies that: - <olist> - <item> - <p>It contains one or more - - <termref def="dt-element">elements</termref> -. </p> - </item> -<!--* N.B. some readers (notably JC) find the following +<olist><item><p>It contains one or more +<termref def="dt-element">elements</termref>.</p></item><!--* N.B. some readers (notably JC) find the following paragraph awkward and redundant. I agree it's logically redundant: it *says* it is summarizing the logical implications of matching the grammar, and that means by definition it's logically redundant. I don't think it's rhetorically redundant or unnecessary, though, so I'm keeping it. It could however use some recasting when the editors are feeling -stronger. -MSM *--> - <item> - <p> - <termdef id="dt-root" term="Root Element">There is exactly -one element, called the - <term>root</term> -, or document element, no -part of which appears in the <termref def="dt-content">content</termref> - of any other element. </termdef> - +stronger. -MSM *--><item><p><termdef id="dt-root" term="Root Element">There is exactly +one element, called the <term>root</term>, or document element, no +part of which appears in the <termref def="dt-content">content</termref> of any other element.</termdef> For all other elements, if the start-tag is in the content of another element, the end-tag is in the content of the same element. More simply stated, the elements, delimited by start- and end-tags, nest properly within each other. - </p> - </item> - </olist> - - </p> +</p></item></olist> +</p> <p> <termdef id="dt-parentchild" term="Parent/Child">As a consequence of this, for each non-root element - - <code>C</code> - in the document, there is one other element <code>P</code> - +<code>C</code> in the document, there is one other element <code>P</code> in the document such that - <code>C</code> - is in the content of <code>P</code> -, but is not in +<code>C</code> is in the content of <code>P</code>, but is not in the content of any other element that is in the content of - <code>P</code> -. - <code>P</code> - is referred to as the - <term>parent</term> - of <code>C</code> -, and <code>C</code> - as a - <term>child</term> - of <code>P</code> -. </termdef> +<code>P</code>. +<code>P</code> is referred to as the +<term>parent</term> of <code>C</code>, and <code>C</code> as a +<term>child</term> of <code>P</code>.</termdef> </p> </div2> <div2 id="charsets"> <head>Characters</head> - <p> - <termdef id="dt-text" term="Text">A parsed entity contains - - <term>text</term> -, a sequence of - <termref def="dt-character">characters</termref> -, -which may represent markup or character data. </termdef> - - <termdef id="dt-character" term="Character">A - <term>character</term> - + <p><termdef id="dt-text" term="Text">A parsed entity contains +<term>text</term>, a sequence of +<termref def="dt-character">characters</termref>, +which may represent markup or character data.</termdef> +<termdef id="dt-character" term="Character">A <term>character</term> is an atomic unit of text as specified by -ISO/IEC 10646 <bibref ref="ISO10646"/> -. +ISO/IEC 10646 <bibref ref="ISO10646"/>. Legal characters are tab, carriage return, line feed, and the legal graphic characters of Unicode and ISO/IEC 10646. The use of "compatibility characters", as defined in section 6.8 -of <bibref ref="Unicode"/> -, is discouraged. - </termdef> - - <scrap lang="ebnf" id="char32"> - <head>Character Range</head> - <prodgroup pcw2="4" pcw4="17.5" pcw5="11"> - <prod id="NT-Char"> - <lhs>Char</lhs> - <rhs>#x9 | #xA | #xD | [#x20-#xD7FF] | [#xE000-#xFFFD] -| [#x10000-#x10FFFF]</rhs> - <com>any Unicode character, excluding the -surrogate blocks, FFFE, and FFFF.</com> - </prod> - </prodgroup> - </scrap> - - </p> +of <bibref ref="Unicode"/>, is discouraged. +</termdef> +<scrap lang="ebnf" id="char32"><head>Character Range</head><prodgroup pcw2="4" pcw4="17.5" pcw5="11"><prod id="NT-Char"><lhs>Char</lhs><rhs>#x9 | #xA | #xD | [#x20-#xD7FF] | [#xE000-#xFFFD] +| [#x10000-#x10FFFF]</rhs><com>any Unicode character, excluding the +surrogate blocks, FFFE, and FFFF.</com></prod></prodgroup></scrap> +</p> <p>The mechanism for encoding character code points into bit patterns may vary from entity to entity. All XML processors must accept the UTF-8 and UTF-16 encodings of 10646; the mechanisms for signaling which of the two is in use, or for bringing other encodings into play, are -discussed later, in - <specref ref="charencoding"/> -. - </p> +discussed later, in <specref ref="charencoding"/>. +</p> <!-- <p>Regardless of the specific encoding used, any character in the ISO/IEC 10646 character set may be referred to by the decimal or hexadecimal @@ -835,45 +592,26 @@ UCS-4 code value. <div2 id="sec-common-syn"> <head>Common Syntactic Constructs</head> <p>This section defines some symbols used widely in the grammar.</p> - <p> - <nt def="NT-S">S</nt> - (white space) consists of one or more space (#x20) + <p><nt def="NT-S">S</nt> (white space) consists of one or more space (#x20) characters, carriage returns, line feeds, or tabs. - <scrap lang="ebnf" id="white"> - <head>White Space</head> - <prodgroup pcw2="4" pcw4="17.5" pcw5="11"> - <prod id="NT-S"> - <lhs>S</lhs> - <rhs>(#x20 | #x9 | #xD | #xA)+</rhs> - </prod> - </prodgroup> - </scrap> - </p> +<scrap lang="ebnf" id="white"><head>White Space</head><prodgroup pcw2="4" pcw4="17.5" pcw5="11"><prod id="NT-S"><lhs>S</lhs><rhs>(#x20 | #x9 | #xD | #xA)+</rhs></prod></prodgroup></scrap></p> <p>Characters are classified for convenience as letters, digits, or other characters. Letters consist of an alphabetic or syllabic base character possibly followed by one or more combining characters, or of an ideographic character. Full definitions of the specific characters in each class -are given in - <specref ref="CharClasses"/> -. </p> - <p> - <termdef id="dt-name" term="Name">A - <term>Name</term> - is a token +are given in <specref ref="CharClasses"/>.</p> + <p><termdef id="dt-name" term="Name">A <term>Name</term> is a token beginning with a letter or one of a few punctuation characters, and continuing with letters, digits, hyphens, underscores, colons, or full stops, together -known as name characters. </termdef> - -Names beginning with the string " <code>xml</code> -", or any string -which would match <code>(('X'|'x') ('M'|'m') ('L'|'l'))</code> -, are +known as name characters.</termdef> +Names beginning with the string "<code>xml</code>", or any string +which would match <code>(('X'|'x') ('M'|'m') ('L'|'l'))</code>, are reserved for standardization in this or future versions of this specification. - </p> +</p> <note> <p>The colon character within XML names is reserved for experimentation with name spaces. @@ -887,451 +625,217 @@ names except as part of name-space experiments, but that XML processors should accept the colon as a name character.</p> </note> <p>An - - <nt def="NT-Nmtoken">Nmtoken</nt> - (name token) is any mixture of +<nt def="NT-Nmtoken">Nmtoken</nt> (name token) is any mixture of name characters. - <scrap lang="ebnf"> - <head>Names and Tokens</head> - <prod id="NT-NameChar"> - <lhs>NameChar</lhs> - <rhs> - <nt def="NT-Letter">Letter</nt> - -| <nt def="NT-Digit">Digit</nt> - +<scrap lang="ebnf"><head>Names and Tokens</head><prod id="NT-NameChar"><lhs>NameChar</lhs><rhs><nt def="NT-Letter">Letter</nt> +| <nt def="NT-Digit">Digit</nt> | '.' | '-' | '_' | ':' -| <nt def="NT-CombiningChar">CombiningChar</nt> - -| <nt def="NT-Extender">Extender</nt> - </rhs> - </prod> - <prod id="NT-Name"> - <lhs>Name</lhs> - <rhs>( - <nt def="NT-Letter">Letter</nt> - | '_' | ':') -( <nt def="NT-NameChar">NameChar</nt> -)* </rhs> - </prod> - <prod id="NT-Names"> - <lhs>Names</lhs> - <rhs> - <nt def="NT-Name">Name</nt> - -( <nt def="NT-S">S</nt> - <nt def="NT-Name">Name</nt> -)* </rhs> - </prod> - <prod id="NT-Nmtoken"> - <lhs>Nmtoken</lhs> - <rhs>( - <nt def="NT-NameChar">NameChar</nt> -)+ </rhs> - </prod> - <prod id="NT-Nmtokens"> - <lhs>Nmtokens</lhs> - <rhs> - <nt def="NT-Nmtoken">Nmtoken</nt> - ( <nt def="NT-S">S</nt> - <nt def="NT-Nmtoken">Nmtoken</nt> -)* </rhs> - </prod> - </scrap> - - </p> +| <nt def="NT-CombiningChar">CombiningChar</nt> +| <nt def="NT-Extender">Extender</nt></rhs></prod><prod id="NT-Name"><lhs>Name</lhs><rhs>(<nt def="NT-Letter">Letter</nt> | '_' | ':') +(<nt def="NT-NameChar">NameChar</nt>)*</rhs></prod><prod id="NT-Names"><lhs>Names</lhs><rhs><nt def="NT-Name">Name</nt> +(<nt def="NT-S">S</nt> <nt def="NT-Name">Name</nt>)*</rhs></prod><prod id="NT-Nmtoken"><lhs>Nmtoken</lhs><rhs>(<nt def="NT-NameChar">NameChar</nt>)+</rhs></prod><prod id="NT-Nmtokens"><lhs>Nmtokens</lhs><rhs><nt def="NT-Nmtoken">Nmtoken</nt> (<nt def="NT-S">S</nt> <nt def="NT-Nmtoken">Nmtoken</nt>)*</rhs></prod></scrap> +</p> <p>Literal data is any quoted string not containing the quotation mark used as a delimiter for that string. Literals are used for specifying the content of internal entities -( - <nt def="NT-EntityValue">EntityValue</nt> -), -the values of attributes ( <nt def="NT-AttValue">AttValue</nt> -), +(<nt def="NT-EntityValue">EntityValue</nt>), +the values of attributes (<nt def="NT-AttValue">AttValue</nt>), and external identifiers -( <nt def="NT-SystemLiteral">SystemLiteral</nt> -). -Note that a <nt def="NT-SystemLiteral">SystemLiteral</nt> - +(<nt def="NT-SystemLiteral">SystemLiteral</nt>). +Note that a <nt def="NT-SystemLiteral">SystemLiteral</nt> can be parsed without scanning for markup. - <scrap lang="ebnf"> - <head>Literals</head> - <prod id="NT-EntityValue"> - <lhs>EntityValue</lhs> - <rhs>'"' +<scrap lang="ebnf"><head>Literals</head><prod id="NT-EntityValue"><lhs>EntityValue</lhs><rhs>'"' ([^%&"] -| - <nt def="NT-PEReference">PEReference</nt> - -| <nt def="NT-Reference">Reference</nt> -)* +| <nt def="NT-PEReference">PEReference</nt> +| <nt def="NT-Reference">Reference</nt>)* '"' - </rhs> - <rhs>| +</rhs><rhs>| "'" ([^%&'] -| - <nt def="NT-PEReference">PEReference</nt> - -| <nt def="NT-Reference">Reference</nt> -)* -"'" </rhs> - </prod> - <prod id="NT-AttValue"> - <lhs>AttValue</lhs> - <rhs>'"' +| <nt def="NT-PEReference">PEReference</nt> +| <nt def="NT-Reference">Reference</nt>)* +"'"</rhs></prod><prod id="NT-AttValue"><lhs>AttValue</lhs><rhs>'"' ([^<&"] -| - <nt def="NT-Reference">Reference</nt> -)* +| <nt def="NT-Reference">Reference</nt>)* '"' - </rhs> - <rhs>| +</rhs><rhs>| "'" ([^<&'] -| - <nt def="NT-Reference">Reference</nt> -)* -"'" </rhs> - </prod> - <prod id="NT-SystemLiteral"> - <lhs>SystemLiteral</lhs> - <rhs>('"' [^"]* '"') | ("'" [^']* "'") -</rhs> - </prod> - <prod id="NT-PubidLiteral"> - <lhs>PubidLiteral</lhs> - <rhs>'"' - <nt def="NT-PubidChar">PubidChar</nt> -* +| <nt def="NT-Reference">Reference</nt>)* +"'"</rhs></prod><prod id="NT-SystemLiteral"><lhs>SystemLiteral</lhs><rhs>('"' [^"]* '"') | ("'" [^']* "'") +</rhs></prod><prod id="NT-PubidLiteral"><lhs>PubidLiteral</lhs><rhs>'"' <nt def="NT-PubidChar">PubidChar</nt>* '"' -| "'" ( <nt def="NT-PubidChar">PubidChar</nt> - - "'")* "'" </rhs> - </prod> - <prod id="NT-PubidChar"> - <lhs>PubidChar</lhs> - <rhs>#x20 | #xD | #xA +| "'" (<nt def="NT-PubidChar">PubidChar</nt> - "'")* "'"</rhs></prod><prod id="NT-PubidChar"><lhs>PubidChar</lhs><rhs>#x20 | #xD | #xA | [a-zA-Z0-9] -| [-'()+,./:=?;!*#@$_%]</rhs> - </prod> - </scrap> - - </p> +| [-'()+,./:=?;!*#@$_%]</rhs></prod></scrap> +</p> </div2> <div2 id="syntax"> <head>Character Data and Markup</head> - <p> - <termref def="dt-text">Text</termref> - consists of intermingled - <termref def="dt-chardata">character -data</termref> - and markup. - <termdef id="dt-markup" term="Markup"> - <term>Markup</term> - takes the form of - <termref def="dt-stag">start-tags</termref> -, - <termref def="dt-etag">end-tags</termref> -, - <termref def="dt-empty">empty-element tags</termref> -, - <termref def="dt-entref">entity references</termref> -, - <termref def="dt-charref">character references</termref> -, - <termref def="dt-comment">comments</termref> -, - <termref def="dt-cdsection">CDATA section</termref> - delimiters, - <termref def="dt-doctype">document type declarations</termref> -, and - <termref def="dt-pi">processing instructions</termref> -. - </termdef> - - </p> + <p><termref def="dt-text">Text</termref> consists of intermingled +<termref def="dt-chardata">character +data</termref> and markup. +<termdef id="dt-markup" term="Markup"><term>Markup</term> takes the form of +<termref def="dt-stag">start-tags</termref>, +<termref def="dt-etag">end-tags</termref>, +<termref def="dt-empty">empty-element tags</termref>, +<termref def="dt-entref">entity references</termref>, +<termref def="dt-charref">character references</termref>, +<termref def="dt-comment">comments</termref>, +<termref def="dt-cdsection">CDATA section</termref> delimiters, +<termref def="dt-doctype">document type declarations</termref>, and +<termref def="dt-pi">processing instructions</termref>. +</termdef> +</p> <p> <termdef id="dt-chardata" term="Character Data">All text that is not markup -constitutes the - <term>character data</term> - of -the document. </termdef> +constitutes the <term>character data</term> of +the document.</termdef> </p> <p>The ampersand character (&) and the left angle bracket (<) -may appear in their literal form - <emph>only</emph> - when used as markup -delimiters, or within a <termref def="dt-comment">comment</termref> -, a - <termref def="dt-pi">processing instruction</termref> -, -or a <termref def="dt-cdsection">CDATA section</termref> -. - -They are also legal within the <termref def="dt-litentval">literal entity -value</termref> - of an internal entity declaration; see - <specref ref="wf-entities"/> -. +may appear in their literal form <emph>only</emph> when used as markup +delimiters, or within a <termref def="dt-comment">comment</termref>, a +<termref def="dt-pi">processing instruction</termref>, +or a <termref def="dt-cdsection">CDATA section</termref>. + +They are also legal within the <termref def="dt-litentval">literal entity +value</termref> of an internal entity declaration; see +<specref ref="wf-entities"/>. <!-- FINAL EDIT: restore internal entity decl or leave it out. --> - If they are needed elsewhere, -they must be <termref def="dt-escape">escaped</termref> - -using either <termref def="dt-charref">numeric character references</termref> - +they must be <termref def="dt-escape">escaped</termref> +using either <termref def="dt-charref">numeric character references</termref> or the strings -" <code>&amp;</code> -" and " <code>&lt;</code> -" respectively. +"<code>&amp;</code>" and "<code>&lt;</code>" respectively. The right angle bracket (>) may be represented using the string -" <code>&gt;</code> -", and must, <termref def="dt-compat">for -compatibility</termref> -, +"<code>&gt;</code>", and must, <termref def="dt-compat">for +compatibility</termref>, be escaped using -" <code>&gt;</code> -" or a character reference +"<code>&gt;</code>" or a character reference when it appears in the string -" <code>]]></code> -" +"<code>]]></code>" in content, when that string is not marking the end of -a <termref def="dt-cdsection">CDATA section</termref> -. - </p> +a <termref def="dt-cdsection">CDATA section</termref>. +</p> <p> In the content of elements, character data is any string of characters which does not contain the start-delimiter of any markup. In a CDATA section, character data is any string of characters not including the CDATA-section-close -delimiter, " - <code>]]></code> -". </p> +delimiter, "<code>]]></code>".</p> <p> To allow attribute values to contain both single and double quotes, the apostrophe or single-quote character (') may be represented as -" - <code>&apos;</code> -", and the double-quote character (") as -" <code>&quot;</code> -". - <scrap lang="ebnf"> - <head>Character Data</head> - <prod id="NT-CharData"> - <lhs>CharData</lhs> - <rhs>[^<&]* - ([^<&]* ']]>' [^<&]*)</rhs> - </prod> - </scrap> - - </p> +"<code>&apos;</code>", and the double-quote character (") as +"<code>&quot;</code>". +<scrap lang="ebnf"><head>Character Data</head><prod id="NT-CharData"><lhs>CharData</lhs><rhs>[^<&]* - ([^<&]* ']]>' [^<&]*)</rhs></prod></scrap> +</p> </div2> <div2 id="sec-comments"> <head>Comments</head> <p> - <termdef id="dt-comment" term="Comment"> - <term>Comments</term> - may + <termdef id="dt-comment" term="Comment"><term>Comments</term> may appear anywhere in a document outside other - <termref def="dt-markup">markup</termref> -; in addition, +<termref def="dt-markup">markup</termref>; in addition, they may appear within the document type declaration at places allowed by the grammar. -They are not part of the document's <termref def="dt-chardata">character -data</termref> -; an XML +They are not part of the document's <termref def="dt-chardata">character +data</termref>; an XML processor may, but need not, make it possible for an application to retrieve the text of comments. - <termref def="dt-compat">For compatibility</termref> -, the string -" <code>--</code> -" (double-hyphen) must not occur within +<termref def="dt-compat">For compatibility</termref>, the string +"<code>--</code>" (double-hyphen) must not occur within comments. - <scrap lang="ebnf"> - <head>Comments</head> - <prod id="NT-Comment"> - <lhs>Comment</lhs> - <rhs>'<!--' -(( - <nt def="NT-Char">Char</nt> - - '-') -| ('-' ( <nt def="NT-Char">Char</nt> - - '-')))* -'-->' </rhs> - </prod> - </scrap> - - </termdef> +<scrap lang="ebnf"><head>Comments</head><prod id="NT-Comment"><lhs>Comment</lhs><rhs>'<!--' +((<nt def="NT-Char">Char</nt> - '-') +| ('-' (<nt def="NT-Char">Char</nt> - '-')))* +'-->'</rhs></prod></scrap> +</termdef> </p> <p>An example of a comment: - - <eg><!&como; declarations for <head> & <body> &comc;></eg> - - </p> +<eg><!&como; declarations for <head> & <body> &comc;></eg> +</p> </div2> <div2 id="sec-pi"> <head>Processing Instructions</head> - <p> - <termdef id="dt-pi" term="Processing instruction"> - <term>Processing -instructions</term> - (PIs) allow documents to contain instructions + <p><termdef id="dt-pi" term="Processing instruction"><term>Processing +instructions</term> (PIs) allow documents to contain instructions for applications. - <scrap lang="ebnf"> - <head>Processing Instructions</head> - <prod id="NT-PI"> - <lhs>PI</lhs> - <rhs>'<?' - <nt def="NT-PITarget">PITarget</nt> - -( <nt def="NT-S">S</nt> - -( <nt def="NT-Char">Char</nt> -* - -( <nt def="NT-Char">Char</nt> -* &pic; <nt def="NT-Char">Char</nt> -*)))? -&pic; </rhs> - </prod> - <prod id="NT-PITarget"> - <lhs>PITarget</lhs> - <rhs> - <nt def="NT-Name">Name</nt> - - -(('X' | 'x') ('M' | 'm') ('L' | 'l')) </rhs> - </prod> - </scrap> - </termdef> - -PIs are not part of the document's <termref def="dt-chardata">character -data</termref> -, but must be passed through to the application. The -PI begins with a target ( <nt def="NT-PITarget">PITarget</nt> -) used +<scrap lang="ebnf"><head>Processing Instructions</head><prod id="NT-PI"><lhs>PI</lhs><rhs>'<?' <nt def="NT-PITarget">PITarget</nt> +(<nt def="NT-S">S</nt> +(<nt def="NT-Char">Char</nt>* - +(<nt def="NT-Char">Char</nt>* &pic; <nt def="NT-Char">Char</nt>*)))? +&pic;</rhs></prod><prod id="NT-PITarget"><lhs>PITarget</lhs><rhs><nt def="NT-Name">Name</nt> - +(('X' | 'x') ('M' | 'm') ('L' | 'l'))</rhs></prod></scrap></termdef> +PIs are not part of the document's <termref def="dt-chardata">character +data</termref>, but must be passed through to the application. The +PI begins with a target (<nt def="NT-PITarget">PITarget</nt>) used to identify the application to which the instruction is directed. -The target names " <code>XML</code> -", " <code>xml</code> -", and so on are +The target names "<code>XML</code>", "<code>xml</code>", and so on are reserved for standardization in this or future versions of this specification. The -XML <termref def="dt-notation">Notation</termref> - mechanism +XML <termref def="dt-notation">Notation</termref> mechanism may be used for formal declaration of PI targets. - </p> +</p> </div2> <div2 id="sec-cdata-sect"> <head>CDATA Sections</head> - <p> - <termdef id="dt-cdsection" term="CDATA Section"> - <term>CDATA sections</term> - + <p><termdef id="dt-cdsection" term="CDATA Section"><term>CDATA sections</term> may occur anywhere character data may occur; they are used to escape blocks of text containing characters which would otherwise be recognized as markup. CDATA sections begin with the -string " <code><![CDATA[</code> -" and end with the string -" <code>]]></code> -": - <scrap lang="ebnf"> - <head>CDATA Sections</head> - <prod id="NT-CDSect"> - <lhs>CDSect</lhs> - <rhs> - <nt def="NT-CDStart">CDStart</nt> - - <nt def="NT-CData">CData</nt> - - <nt def="NT-CDEnd">CDEnd</nt> - </rhs> - </prod> - <prod id="NT-CDStart"> - <lhs>CDStart</lhs> - <rhs>'<![CDATA['</rhs> - </prod> - <prod id="NT-CData"> - <lhs>CData</lhs> - <rhs>( - <nt def="NT-Char">Char</nt> -* - -( <nt def="NT-Char">Char</nt> -* ']]>' <nt def="NT-Char">Char</nt> -*)) - </rhs> - </prod> - <prod id="NT-CDEnd"> - <lhs>CDEnd</lhs> - <rhs>']]>'</rhs> - </prod> - </scrap> - - -Within a CDATA section, only the <nt def="NT-CDEnd">CDEnd</nt> - string is +string "<code><![CDATA[</code>" and end with the string +"<code>]]></code>": +<scrap lang="ebnf"><head>CDATA Sections</head><prod id="NT-CDSect"><lhs>CDSect</lhs><rhs><nt def="NT-CDStart">CDStart</nt> +<nt def="NT-CData">CData</nt> +<nt def="NT-CDEnd">CDEnd</nt></rhs></prod><prod id="NT-CDStart"><lhs>CDStart</lhs><rhs>'<![CDATA['</rhs></prod><prod id="NT-CData"><lhs>CData</lhs><rhs>(<nt def="NT-Char">Char</nt>* - +(<nt def="NT-Char">Char</nt>* ']]>' <nt def="NT-Char">Char</nt>*)) +</rhs></prod><prod id="NT-CDEnd"><lhs>CDEnd</lhs><rhs>']]>'</rhs></prod></scrap> + +Within a CDATA section, only the <nt def="NT-CDEnd">CDEnd</nt> string is recognized as markup, so that left angle brackets and ampersands may occur in their literal form; they need not (and cannot) be escaped using -" <code>&lt;</code> -" and " <code>&amp;</code> -". CDATA sections -cannot nest. </termdef> - - </p> - <p>An example of a CDATA section, in which " - <code><greeting></code> -" and -" <code></greeting></code> -" -are recognized as <termref def="dt-chardata">character data</termref> -, not - <termref def="dt-markup">markup</termref> -: - <eg><![CDATA[<greeting>Hello, world!</greeting>]]></eg> - - </p> +"<code>&lt;</code>" and "<code>&amp;</code>". CDATA sections +cannot nest.</termdef> +</p> + <p>An example of a CDATA section, in which "<code><greeting></code>" and +"<code></greeting></code>" +are recognized as <termref def="dt-chardata">character data</termref>, not +<termref def="dt-markup">markup</termref>: +<eg><![CDATA[<greeting>Hello, world!</greeting>]]></eg> +</p> </div2> <div2 id="sec-prolog-dtd"> <head>Prolog and Document Type Declaration</head> - <p> - <termdef id="dt-xmldecl" term="XML Declaration">XML documents + <p><termdef id="dt-xmldecl" term="XML Declaration">XML documents may, and should, -begin with an - <term>XML declaration</term> - which specifies +begin with an <term>XML declaration</term> which specifies the version of -XML being used. </termdef> - -For example, the following is a complete XML document, <termref def="dt-wellformed">well-formed</termref> - but not - <termref def="dt-valid">valid</termref> -: - <eg> -<![CDATA[<?xml version="1.0"?> +XML being used.</termdef> +For example, the following is a complete XML document, <termref def="dt-wellformed">well-formed</termref> but not +<termref def="dt-valid">valid</termref>: +<eg><![CDATA[<?xml version="1.0"?> <greeting>Hello, world!</greeting> -]]> </eg> - +]]></eg> and so is this: - <eg> -<![CDATA[<greeting>Hello, world!</greeting> -]]> </eg> - - </p> - <p>The version number " - <code>1.0</code> -" should be used to indicate +<eg><![CDATA[<greeting>Hello, world!</greeting> +]]></eg> +</p> + <p>The version number "<code>1.0</code>" should be used to indicate conformance to this version of this specification; it is an error -for a document to use the value " <code>1.0</code> -" +for a document to use the value "<code>1.0</code>" if it does not conform to this version of this specification. It is the intent of the XML working group to give later versions of this specification -numbers other than " <code>1.0</code> -", but this intent does not +numbers other than "<code>1.0</code>", but this intent does not indicate a commitment to produce any future versions of XML, nor if any are produced, to use any particular numbering scheme. @@ -1340,513 +844,303 @@ as a means to allow the possibility of automatic version recognition, should it become necessary. Processors may signal an error if they receive documents labeled with versions they do not support. - </p> +</p> <p>The function of the markup in an XML document is to describe its storage and logical structure and to associate attribute-value pairs -with its logical structures. XML provides a mechanism, the - <termref def="dt-doctype">document type declaration</termref> -, to define +with its logical structures. XML provides a mechanism, the <termref def="dt-doctype">document type declaration</termref>, to define constraints on the logical structure and to support the use of predefined storage units. - <termdef id="dt-valid" term="Validity">An XML document is - - <term>valid</term> - if it has an associated document type +<termdef id="dt-valid" term="Validity">An XML document is +<term>valid</term> if it has an associated document type declaration and if the document -complies with the constraints expressed in it. </termdef> - </p> +complies with the constraints expressed in it.</termdef></p> <p>The document type declaration must appear before -the first - <termref def="dt-element">element</termref> - in the document. - <scrap lang="ebnf" id="xmldoc"> - <head>Prolog</head> - <prodgroup pcw2="6" pcw4="17.5" pcw5="9"> - <prod id="NT-prolog"> - <lhs>prolog</lhs> - <rhs> - <nt def="NT-XMLDecl">XMLDecl</nt> -? - <nt def="NT-Misc">Misc</nt> -* -( <nt def="NT-doctypedecl">doctypedecl</nt> - - <nt def="NT-Misc">Misc</nt> -*)? </rhs> - </prod> - <prod id="NT-XMLDecl"> - <lhs>XMLDecl</lhs> - <rhs>&xmlpio; - - <nt def="NT-VersionInfo">VersionInfo</nt> - - <nt def="NT-EncodingDecl">EncodingDecl</nt> -? - <nt def="NT-SDDecl">SDDecl</nt> -? - <nt def="NT-S">S</nt> -? -&pic; </rhs> - </prod> - <prod id="NT-VersionInfo"> - <lhs>VersionInfo</lhs> - <rhs> - <nt def="NT-S">S</nt> - 'version' <nt def="NT-Eq">Eq</nt> - -(' <nt def="NT-VersionNum">VersionNum</nt> - ' -| " <nt def="NT-VersionNum">VersionNum</nt> - ") </rhs> - </prod> - <prod id="NT-Eq"> - <lhs>Eq</lhs> - <rhs> - <nt def="NT-S">S</nt> -? '=' <nt def="NT-S">S</nt> -? </rhs> - </prod> - <prod id="NT-VersionNum"> - <lhs>VersionNum</lhs> - <rhs>([a-zA-Z0-9_.:] | '-')+</rhs> - </prod> - <prod id="NT-Misc"> - <lhs>Misc</lhs> - <rhs> - <nt def="NT-Comment">Comment</nt> - | <nt def="NT-PI">PI</nt> - | - <nt def="NT-S">S</nt> - </rhs> - </prod> - </prodgroup> - </scrap> - </p> - <p> - <termdef id="dt-doctype" term="Document Type Declaration">The XML - - <term>document type declaration</term> - +the first <termref def="dt-element">element</termref> in the document. +<scrap lang="ebnf" id="xmldoc"><head>Prolog</head><prodgroup pcw2="6" pcw4="17.5" pcw5="9"><prod id="NT-prolog"><lhs>prolog</lhs><rhs><nt def="NT-XMLDecl">XMLDecl</nt>? +<nt def="NT-Misc">Misc</nt>* +(<nt def="NT-doctypedecl">doctypedecl</nt> +<nt def="NT-Misc">Misc</nt>*)?</rhs></prod><prod id="NT-XMLDecl"><lhs>XMLDecl</lhs><rhs>&xmlpio; +<nt def="NT-VersionInfo">VersionInfo</nt> +<nt def="NT-EncodingDecl">EncodingDecl</nt>? +<nt def="NT-SDDecl">SDDecl</nt>? +<nt def="NT-S">S</nt>? +&pic;</rhs></prod><prod id="NT-VersionInfo"><lhs>VersionInfo</lhs><rhs><nt def="NT-S">S</nt> 'version' <nt def="NT-Eq">Eq</nt> +(' <nt def="NT-VersionNum">VersionNum</nt> ' +| " <nt def="NT-VersionNum">VersionNum</nt> ")</rhs></prod><prod id="NT-Eq"><lhs>Eq</lhs><rhs><nt def="NT-S">S</nt>? '=' <nt def="NT-S">S</nt>?</rhs></prod><prod id="NT-VersionNum"><lhs>VersionNum</lhs><rhs>([a-zA-Z0-9_.:] | '-')+</rhs></prod><prod id="NT-Misc"><lhs>Misc</lhs><rhs><nt def="NT-Comment">Comment</nt> | <nt def="NT-PI">PI</nt> | +<nt def="NT-S">S</nt></rhs></prod></prodgroup></scrap></p> + <p><termdef id="dt-doctype" term="Document Type Declaration">The XML +<term>document type declaration</term> contains or points to - <termref def="dt-markupdecl">markup declarations</termref> - +<termref def="dt-markupdecl">markup declarations</termref> that provide a grammar for a class of documents. This grammar is known as a document type definition, -or <term>DTD</term> -. +or <term>DTD</term>. The document type declaration can point to an external subset (a special kind of - <termref def="dt-extent">external entity</termref> -) containing markup +<termref def="dt-extent">external entity</termref>) containing markup declarations, or can contain the markup declarations directly in an internal subset, or can do both. The DTD for a document consists of both subsets taken -together. </termdef> - - </p> - <p> - <termdef id="dt-markupdecl" term="markup declaration"> -A - <term>markup declaration</term> - is -an <termref def="dt-eldecl">element type declaration</termref> -, -an <termref def="dt-attdecl">attribute-list declaration</termref> -, -an <termref def="dt-entdecl">entity declaration</termref> -, or -a <termref def="dt-notdecl">notation declaration</termref> -. - </termdef> - +together.</termdef> +</p> + <p><termdef id="dt-markupdecl" term="markup declaration"> +A <term>markup declaration</term> is +an <termref def="dt-eldecl">element type declaration</termref>, +an <termref def="dt-attdecl">attribute-list declaration</termref>, +an <termref def="dt-entdecl">entity declaration</termref>, or +a <termref def="dt-notdecl">notation declaration</termref>. +</termdef> These declarations may be contained in whole or in part -within <termref def="dt-PE">parameter entities</termref> -, +within <termref def="dt-PE">parameter entities</termref>, as described in the well-formedness and validity constraints below. For fuller information, see - <specref ref="sec-physical-struct"/> -. </p> +<specref ref="sec-physical-struct"/>.</p> <scrap lang="ebnf" id="dtd"> <head>Document Type Definition</head> <prodgroup pcw2="6" pcw4="17.5" pcw5="9"> <prod id="NT-doctypedecl"> <lhs>doctypedecl</lhs> - <rhs>'<!DOCTYPE' - <nt def="NT-S">S</nt> - - <nt def="NT-Name">Name</nt> - ( <nt def="NT-S">S</nt> - - <nt def="NT-ExternalID">ExternalID</nt> -)? - <nt def="NT-S">S</nt> -? ('[' -( <nt def="NT-markupdecl">markupdecl</nt> - -| <nt def="NT-PEReference">PEReference</nt> - -| <nt def="NT-S">S</nt> -)* + <rhs>'<!DOCTYPE' <nt def="NT-S">S</nt> +<nt def="NT-Name">Name</nt> (<nt def="NT-S">S</nt> +<nt def="NT-ExternalID">ExternalID</nt>)? +<nt def="NT-S">S</nt>? ('[' +(<nt def="NT-markupdecl">markupdecl</nt> +| <nt def="NT-PEReference">PEReference</nt> +| <nt def="NT-S">S</nt>)* ']' - <nt def="NT-S">S</nt> -?)? '>' </rhs> +<nt def="NT-S">S</nt>?)? '>'</rhs> <vc def="vc-roottype"/> </prod> <prod id="NT-markupdecl"> <lhs>markupdecl</lhs> - <rhs> - <nt def="NT-elementdecl">elementdecl</nt> - -| <nt def="NT-AttlistDecl">AttlistDecl</nt> - -| <nt def="NT-EntityDecl">EntityDecl</nt> - -| <nt def="NT-NotationDecl">NotationDecl</nt> - -| <nt def="NT-PI">PI</nt> - -| <nt def="NT-Comment">Comment</nt> - - </rhs> + <rhs><nt def="NT-elementdecl">elementdecl</nt> +| <nt def="NT-AttlistDecl">AttlistDecl</nt> +| <nt def="NT-EntityDecl">EntityDecl</nt> +| <nt def="NT-NotationDecl">NotationDecl</nt> +| <nt def="NT-PI">PI</nt> +| <nt def="NT-Comment">Comment</nt> +</rhs> <vc def="vc-PEinMarkupDecl"/> <wfc def="wfc-PEinInternalSubset"/> </prod> </prodgroup> </scrap> <p>The markup declarations may be made up in whole or in part of -the - <termref def="dt-repltext">replacement text</termref> - of - <termref def="dt-PE">parameter entities</termref> -. +the <termref def="dt-repltext">replacement text</termref> of +<termref def="dt-PE">parameter entities</termref>. The productions later in this specification for -individual nonterminals ( <nt def="NT-elementdecl">elementdecl</nt> -, - <nt def="NT-AttlistDecl">AttlistDecl</nt> -, and so on) describe -the declarations <emph>after</emph> - all the parameter entities have been - <termref def="dt-include">included</termref> -. </p> +individual nonterminals (<nt def="NT-elementdecl">elementdecl</nt>, +<nt def="NT-AttlistDecl">AttlistDecl</nt>, and so on) describe +the declarations <emph>after</emph> all the parameter entities have been +<termref def="dt-include">included</termref>.</p> <vcnote id="vc-roottype"> <head>Root Element Type</head> <p> -The - <nt def="NT-Name">Name</nt> - in the document type declaration must -match the element type of the <termref def="dt-root">root element</termref> -. - </p> +The <nt def="NT-Name">Name</nt> in the document type declaration must +match the element type of the <termref def="dt-root">root element</termref>. +</p> </vcnote> <vcnote id="vc-PEinMarkupDecl"> <head>Proper Declaration/PE Nesting</head> <p>Parameter-entity - - <termref def="dt-repltext">replacement text</termref> - must be properly nested +<termref def="dt-repltext">replacement text</termref> must be properly nested with markup declarations. That is to say, if either the first character or the last character of a markup -declaration ( <nt def="NT-markupdecl">markupdecl</nt> - above) +declaration (<nt def="NT-markupdecl">markupdecl</nt> above) is contained in the replacement text for a - <termref def="dt-PERef">parameter-entity reference</termref> -, -both must be contained in the same replacement text. </p> +<termref def="dt-PERef">parameter-entity reference</termref>, +both must be contained in the same replacement text.</p> </vcnote> <wfcnote id="wfc-PEinInternalSubset"> <head>PEs in Internal Subset</head> <p>In the internal DTD subset, - - <termref def="dt-PERef">parameter-entity references</termref> - +<termref def="dt-PERef">parameter-entity references</termref> can occur only where markup declarations can occur, not within markup declarations. (This does not apply to references that occur in external parameter entities or to the external subset.) - </p> +</p> </wfcnote> <p> Like the internal subset, the external subset and any external parameter entities referred to in the DTD must consist of a series of complete markup declarations of the types allowed by the non-terminal symbol - - <nt def="NT-markupdecl">markupdecl</nt> -, interspersed with white space -or <termref def="dt-PERef">parameter-entity references</termref> -. +<nt def="NT-markupdecl">markupdecl</nt>, interspersed with white space +or <termref def="dt-PERef">parameter-entity references</termref>. However, portions of the contents of the external subset or of external parameter entities may conditionally be ignored by using -the <termref def="dt-cond-section">conditional section</termref> - +the <termref def="dt-cond-section">conditional section</termref> construct; this is not allowed in the internal subset. - <scrap id="ext-Subset"> - <head>External Subset</head> - <prodgroup pcw2="6" pcw4="17.5" pcw5="9"> - <prod id="NT-extSubset"> - <lhs>extSubset</lhs> - <rhs> - <nt def="NT-TextDecl">TextDecl</nt> -? - <nt def="NT-extSubsetDecl">extSubsetDecl</nt> - </rhs> - </prod> - <prod id="NT-extSubsetDecl"> - <lhs>extSubsetDecl</lhs> - <rhs>( - - <nt def="NT-markupdecl">markupdecl</nt> - -| <nt def="NT-conditionalSect">conditionalSect</nt> - -| <nt def="NT-PEReference">PEReference</nt> - -| <nt def="NT-S">S</nt> - -)* </rhs> - </prod> - </prodgroup> - </scrap> - </p> +<scrap id="ext-Subset"><head>External Subset</head><prodgroup pcw2="6" pcw4="17.5" pcw5="9"><prod id="NT-extSubset"><lhs>extSubset</lhs><rhs><nt def="NT-TextDecl">TextDecl</nt>? +<nt def="NT-extSubsetDecl">extSubsetDecl</nt></rhs></prod><prod id="NT-extSubsetDecl"><lhs>extSubsetDecl</lhs><rhs>( +<nt def="NT-markupdecl">markupdecl</nt> +| <nt def="NT-conditionalSect">conditionalSect</nt> +| <nt def="NT-PEReference">PEReference</nt> +| <nt def="NT-S">S</nt> +)*</rhs></prod></prodgroup></scrap></p> <p>The external subset and external parameter entities also differ from the internal subset in that in them, - - <termref def="dt-PERef">parameter-entity references</termref> - -are permitted <emph>within</emph> - markup declarations, -not only <emph>between</emph> - markup declarations. </p> +<termref def="dt-PERef">parameter-entity references</termref> +are permitted <emph>within</emph> markup declarations, +not only <emph>between</emph> markup declarations.</p> <p>An example of an XML document with a document type declaration: - - <eg> -<![CDATA[<?xml version="1.0"?> +<eg><![CDATA[<?xml version="1.0"?> <!DOCTYPE greeting SYSTEM "hello.dtd"> <greeting>Hello, world!</greeting> -]]> </eg> - -The <termref def="dt-sysid">system identifier</termref> - -" <code>hello.dtd</code> -" gives the URI of a DTD for the document. </p> +]]></eg> +The <termref def="dt-sysid">system identifier</termref> +"<code>hello.dtd</code>" gives the URI of a DTD for the document.</p> <p>The declarations can also be given locally, as in this example: - - <eg> -<![CDATA[<?xml version="1.0" encoding="UTF-8" ?> +<eg><![CDATA[<?xml version="1.0" encoding="UTF-8" ?> <!DOCTYPE greeting [ <!ELEMENT greeting (#PCDATA)> ]> <greeting>Hello, world!</greeting> -]]> </eg> - +]]></eg> If both the external and internal subsets are used, the internal subset is considered to occur before the external subset. <!-- 'is considered to'? boo. whazzat mean? --> - This has the effect that entity and attribute-list declarations in the internal subset take precedence over those in the external subset. - </p> +</p> </div2> <div2 id="sec-rmd"> <head>Standalone Document Declaration</head> <p>Markup declarations can affect the content of the document, -as passed from an - <termref def="dt-xml-proc">XML processor</termref> - +as passed from an <termref def="dt-xml-proc">XML processor</termref> to an application; examples are attribute defaults and entity declarations. The standalone document declaration, which may appear as a component of the XML declaration, signals whether or not there are such declarations which appear external to -the <termref def="dt-docent">document entity</termref> -. - <scrap lang="ebnf" id="fulldtd"> - <head>Standalone Document Declaration</head> - <prodgroup pcw2="4" pcw4="19.5" pcw5="9"> - <prod id="NT-SDDecl"> - <lhs>SDDecl</lhs> - <rhs> - - <nt def="NT-S">S</nt> - -'standalone' <nt def="NT-Eq">Eq</nt> - +the <termref def="dt-docent">document entity</termref>. +<scrap lang="ebnf" id="fulldtd"><head>Standalone Document Declaration</head><prodgroup pcw2="4" pcw4="19.5" pcw5="9"><prod id="NT-SDDecl"><lhs>SDDecl</lhs><rhs> +<nt def="NT-S">S</nt> +'standalone' <nt def="NT-Eq">Eq</nt> (("'" ('yes' | 'no') "'") | ('"' ('yes' | 'no') '"')) - </rhs> - <vc def="vc-check-rmd"/> - </prod> - </prodgroup> - </scrap> - </p> +</rhs><vc def="vc-check-rmd"/></prod></prodgroup></scrap></p> <p> -In a standalone document declaration, the value " - <code>yes</code> -" indicates +In a standalone document declaration, the value "<code>yes</code>" indicates that there -are no markup declarations external to the <termref def="dt-docent">document -entity</termref> - (either in the DTD external subset, or in an +are no markup declarations external to the <termref def="dt-docent">document +entity</termref> (either in the DTD external subset, or in an external parameter entity referenced from the internal subset) which affect the information passed from the XML processor to the application. -The value " <code>no</code> -" indicates that there are or may be such +The value "<code>no</code>" indicates that there are or may be such external markup declarations. Note that the standalone document declaration only -denotes the presence of external <emph>declarations</emph> -; the presence, in a +denotes the presence of external <emph>declarations</emph>; the presence, in a document, of -references to external <emph>entities</emph> -, when those entities are +references to external <emph>entities</emph>, when those entities are internally declared, -does not change its standalone status. </p> +does not change its standalone status.</p> <p>If there are no external markup declarations, the standalone document declaration has no meaning. If there are external markup declarations but there is no standalone -document declaration, the value " - <code>no</code> -" is assumed. </p> - <p>Any XML document for which - <code>standalone="no"</code> - holds can +document declaration, the value "<code>no</code>" is assumed.</p> + <p>Any XML document for which <code>standalone="no"</code> holds can be converted algorithmically to a standalone document, -which may be desirable for some network delivery applications. </p> +which may be desirable for some network delivery applications.</p> <vcnote id="vc-check-rmd"> <head>Standalone Document Declaration</head> <p>The standalone document declaration must have -the value " - <code>no</code> -" if any external markup declarations -contain declarations of: </p> +the value "<code>no</code>" if any external markup declarations +contain declarations of:</p> <ulist> <item> - <p>attributes with - <termref def="dt-default">default</termref> - values, if + <p>attributes with <termref def="dt-default">default</termref> values, if elements to which these attributes apply appear in the document without -specifications of values for these attributes, or </p> +specifications of values for these attributes, or</p> </item> <item> <p>entities (other than &magicents;), -if - <termref def="dt-entref">references</termref> - to those -entities appear in the document, or </p> +if <termref def="dt-entref">references</termref> to those +entities appear in the document, or</p> </item> <item> <p>attributes with values subject to - - <titleref href="AVNormalize">normalization</titleref> -, where the +<titleref href="AVNormalize">normalization</titleref>, where the attribute appears in the document with a value which will -change as a result of normalization, or </p> +change as a result of normalization, or</p> </item> <item> - <p>element types with - <termref def="dt-elemcontent">element content</termref> -, + <p>element types with <termref def="dt-elemcontent">element content</termref>, if white space occurs directly within any instance of those types. - </p> +</p> </item> </ulist> </vcnote> - <p>An example XML declaration with a standalone document declaration: - <eg><?xml version="&XML.version;" standalone='yes'?></eg> - </p> + <p>An example XML declaration with a standalone document declaration:<eg><?xml version="&XML.version;" standalone='yes'?></eg></p> </div2> <div2 id="sec-white-space"> <head>White Space Handling</head> <p>In editing XML documents, it is often convenient to use "white space" (spaces, tabs, and blank lines, denoted by the nonterminal - - <nt def="NT-S">S</nt> - in this specification) to +<nt def="NT-S">S</nt> in this specification) to set apart the markup for greater readability. Such white space is typically not intended for inclusion in the delivered version of the document. On the other hand, "significant" white space that should be preserved in the delivered version is common, for example in poetry and -source code. </p> - <p>An - <termref def="dt-xml-proc">XML processor</termref> - +source code.</p> + <p>An <termref def="dt-xml-proc">XML processor</termref> must always pass all characters in a document that are not -markup through to the application. A <termref def="dt-validating"> -validating XML processor</termref> - must also inform the application +markup through to the application. A <termref def="dt-validating"> +validating XML processor</termref> must also inform the application which of these characters constitute white space appearing -in <termref def="dt-elemcontent">element content</termref> -. - </p> - <p>A special - <termref def="dt-attr">attribute</termref> - -named <kw>xml:space</kw> - may be attached to an element +in <termref def="dt-elemcontent">element content</termref>. +</p> + <p>A special <termref def="dt-attr">attribute</termref> +named <kw>xml:space</kw> may be attached to an element to signal an intention that in that element, white space should be preserved by applications. In valid documents, this attribute, like any other, must be - <termref def="dt-attdecl">declared</termref> - if it is used. +<termref def="dt-attdecl">declared</termref> if it is used. When declared, it must be given as an - <termref def="dt-enumerated">enumerated type</termref> - whose only -possible values are " <code>default</code> -" and " <code>preserve</code> -". -For example: <eg> -<![CDATA[ <!ATTLIST poem xml:space (default|preserve) 'preserve'>]]> </eg> - </p> - <p>The value " - <code>default</code> -" signals that applications' +<termref def="dt-enumerated">enumerated type</termref> whose only +possible values are "<code>default</code>" and "<code>preserve</code>". +For example:<eg><![CDATA[ <!ATTLIST poem xml:space (default|preserve) 'preserve'>]]></eg></p> + <p>The value "<code>default</code>" signals that applications' default white-space processing modes are acceptable for this element; the -value " <code>preserve</code> -" indicates the intent that applications preserve +value "<code>preserve</code>" indicates the intent that applications preserve all the white space. This declared intent is considered to apply to all elements within the content of the element where it is specified, unless overriden with another instance -of the <kw>xml:space</kw> - attribute. - </p> - <p>The - <termref def="dt-root">root element</termref> - of any document +of the <kw>xml:space</kw> attribute. +</p> + <p>The <termref def="dt-root">root element</termref> of any document is considered to have signaled no intentions as regards application space handling, unless it provides a value for this attribute or the attribute is declared with a default value. - </p> +</p> </div2> <div2 id="sec-line-ends"> <head>End-of-Line Handling</head> - <p>XML - <termref def="dt-parsedent">parsed entities</termref> - are often stored in + <p>XML <termref def="dt-parsedent">parsed entities</termref> are often stored in computer files which, for editing convenience, are organized into lines. These lines are typically separated by some combination of the characters -carriage-return (#xD) and line-feed (#xA). </p> - <p>To simplify the tasks of - <termref def="dt-app">applications</termref> -, +carriage-return (#xD) and line-feed (#xA).</p> + <p>To simplify the tasks of <termref def="dt-app">applications</termref>, wherever an external parsed entity or the literal entity value of an internal parsed entity contains either the literal two-character sequence "#xD#xA" or a standalone literal -#xD, an <termref def="dt-xml-proc">XML processor</termref> - must +#xD, an <termref def="dt-xml-proc">XML processor</termref> must pass to the application the single character #xA. (This behavior can conveniently be produced by normalizing all line breaks to #xA on input, before parsing.) - </p> +</p> </div2> <div2 id="sec-lang-tag"> <head>Language Identification</head> @@ -1854,114 +1148,46 @@ line breaks to #xA on input, before parsing.) identify the natural or formal language in which the content is written. -A special - <termref def="dt-attr">attribute</termref> - named - <kw>xml:lang</kw> - may be inserted in +A special <termref def="dt-attr">attribute</termref> named +<kw>xml:lang</kw> may be inserted in documents to specify the language used in the contents and attribute values of any element in an XML document. In valid documents, this attribute, like any other, must be - <termref def="dt-attdecl">declared</termref> - if it is used. +<termref def="dt-attdecl">declared</termref> if it is used. The values of the attribute are language identifiers as defined -by <bibref ref="RFC1766"/> -, "Tags for the Identification of Languages": - <scrap lang="ebnf"> - <head>Language Identification</head> - <prod id="NT-LanguageID"> - <lhs>LanguageID</lhs> - <rhs> - <nt def="NT-Langcode">Langcode</nt> - -('-' <nt def="NT-Subcode">Subcode</nt> -)* </rhs> - </prod> - <prod id="NT-Langcode"> - <lhs>Langcode</lhs> - <rhs> - <nt def="NT-ISO639Code">ISO639Code</nt> - | - <nt def="NT-IanaCode">IanaCode</nt> - | - <nt def="NT-UserCode">UserCode</nt> - </rhs> - </prod> - <prod id="NT-ISO639Code"> - <lhs>ISO639Code</lhs> - <rhs>([a-z] | [A-Z]) ([a-z] | [A-Z])</rhs> - </prod> - <prod id="NT-IanaCode"> - <lhs>IanaCode</lhs> - <rhs>('i' | 'I') '-' ([a-z] | [A-Z])+</rhs> - </prod> - <prod id="NT-UserCode"> - <lhs>UserCode</lhs> - <rhs>('x' | 'X') '-' ([a-z] | [A-Z])+</rhs> - </prod> - <prod id="NT-Subcode"> - <lhs>Subcode</lhs> - <rhs>([a-z] | [A-Z])+</rhs> - </prod> - </scrap> - -The <nt def="NT-Langcode">Langcode</nt> - may be any of the following: - <ulist> - <item> - <p>a two-letter language code as defined by - - <bibref ref="ISO639"/> -, "Codes -for the representation of names of languages" </p> - </item> - <item> - <p>a language identifier registered with the Internet -Assigned Numbers Authority - <bibref ref="IANA"/> -; these begin with the -prefix " <code>i-</code> -" (or " <code>I-</code> -") </p> - </item> - <item> - <p>a language identifier assigned by the user, or agreed on +by <bibref ref="RFC1766"/>, "Tags for the Identification of Languages": +<scrap lang="ebnf"><head>Language Identification</head><prod id="NT-LanguageID"><lhs>LanguageID</lhs><rhs><nt def="NT-Langcode">Langcode</nt> +('-' <nt def="NT-Subcode">Subcode</nt>)*</rhs></prod><prod id="NT-Langcode"><lhs>Langcode</lhs><rhs><nt def="NT-ISO639Code">ISO639Code</nt> | +<nt def="NT-IanaCode">IanaCode</nt> | +<nt def="NT-UserCode">UserCode</nt></rhs></prod><prod id="NT-ISO639Code"><lhs>ISO639Code</lhs><rhs>([a-z] | [A-Z]) ([a-z] | [A-Z])</rhs></prod><prod id="NT-IanaCode"><lhs>IanaCode</lhs><rhs>('i' | 'I') '-' ([a-z] | [A-Z])+</rhs></prod><prod id="NT-UserCode"><lhs>UserCode</lhs><rhs>('x' | 'X') '-' ([a-z] | [A-Z])+</rhs></prod><prod id="NT-Subcode"><lhs>Subcode</lhs><rhs>([a-z] | [A-Z])+</rhs></prod></scrap> +The <nt def="NT-Langcode">Langcode</nt> may be any of the following: +<ulist><item><p>a two-letter language code as defined by +<bibref ref="ISO639"/>, "Codes +for the representation of names of languages"</p></item><item><p>a language identifier registered with the Internet +Assigned Numbers Authority <bibref ref="IANA"/>; these begin with the +prefix "<code>i-</code>" (or "<code>I-</code>")</p></item><item><p>a language identifier assigned by the user, or agreed on between parties in private use; these must begin with the -prefix " - <code>x-</code> -" or " <code>X-</code> -" in order to ensure that they do not conflict -with names later standardized or registered with IANA </p> - </item> - </ulist> - </p> - <p>There may be any number of - <nt def="NT-Subcode">Subcode</nt> - segments; if +prefix "<code>x-</code>" or "<code>X-</code>" in order to ensure that they do not conflict +with names later standardized or registered with IANA</p></item></ulist></p> + <p>There may be any number of <nt def="NT-Subcode">Subcode</nt> segments; if the first subcode segment exists and the Subcode consists of two letters, then it must be a country code from - <bibref ref="ISO3166"/> -, "Codes +<bibref ref="ISO3166"/>, "Codes for the representation of names of countries." If the first subcode consists of more than two letters, it must be a subcode for the language in question registered with IANA, -unless the <nt def="NT-Langcode">Langcode</nt> - begins with the prefix -" <code>x-</code> -" or -" <code>X-</code> -". </p> +unless the <nt def="NT-Langcode">Langcode</nt> begins with the prefix +"<code>x-</code>" or +"<code>X-</code>". </p> <p>It is customary to give the language code in lower case, and the country code (if any) in upper case. Note that these values, unlike other names in XML documents, are case insensitive.</p> <p>For example: - - <eg> -<![CDATA[<p xml:lang="en">The quick brown fox jumps over the lazy dog.</p> +<eg><![CDATA[<p xml:lang="en">The quick brown fox jumps over the lazy dog.</p> <p xml:lang="en-GB">What colour is it?</p> <p xml:lang="en-US">What color is it?</p> <sp who="Faust" desc='leise' xml:lang="de"> @@ -1969,19 +1195,15 @@ are case insensitive.</p> <l>Juristerei, und Medizin</l> <l>und leider auch Theologie</l> <l>durchaus studiert mit heißem Bemüh'n.</l> - </sp>]]> </eg> - </p> + </sp>]]></eg></p> <!--<p>The xml:lang value is considered to apply both to the contents of an element and (unless otherwise via attribute default values) to the values of all of its attributes with free-text (CDATA) values. --> - <p>The intent declared with - <kw>xml:lang</kw> - is considered to apply to + <p>The intent declared with <kw>xml:lang</kw> is considered to apply to all attributes and content of the element where it is specified, -unless overridden with an instance of <kw>xml:lang</kw> - -on another element within that content. </p> +unless overridden with an instance of <kw>xml:lang</kw> +on another element within that content.</p> <!-- If no value is specified for xml:lang on an element, and no default value is @@ -1997,46 +1219,30 @@ value for xml:lang: The application, not the XML processor, is responsible for this ' inheritance' of attribute values. --> - <p>A simple declaration for - <kw>xml:lang</kw> - might take + <p>A simple declaration for <kw>xml:lang</kw> might take the form - <eg>xml:lang NMTOKEN #IMPLIED</eg> - +<eg>xml:lang NMTOKEN #IMPLIED</eg> but specific default values may also be given, if appropriate. In a collection of French poems for English students, with glosses and notes in English, the xml:lang attribute might be declared this way: - <eg> -<![CDATA[ <!ATTLIST poem xml:lang NMTOKEN 'fr'> +<eg><![CDATA[ <!ATTLIST poem xml:lang NMTOKEN 'fr'> <!ATTLIST gloss xml:lang NMTOKEN 'en'> - <!ATTLIST note xml:lang NMTOKEN 'en'>]]> </eg> - - </p> + <!ATTLIST note xml:lang NMTOKEN 'en'>]]></eg> +</p> </div2> </div1> <!-- &Elements; --> <div1 id="sec-logical-struct"> <head>Logical Structures</head> - <p> - <termdef id="dt-element" term="Element">Each - <termref def="dt-xml-doc">XML document</termref> - contains one or more - <term>elements</term> -, the boundaries of which are -either delimited by <termref def="dt-stag">start-tags</termref> - -and <termref def="dt-etag">end-tags</termref> -, or, for <termref def="dt-empty">empty</termref> - elements, by an <termref def="dt-eetag">empty-element tag</termref> -. Each element has a type, + <p><termdef id="dt-element" term="Element">Each <termref def="dt-xml-doc">XML document</termref> contains one or more +<term>elements</term>, the boundaries of which are +either delimited by <termref def="dt-stag">start-tags</termref> +and <termref def="dt-etag">end-tags</termref>, or, for <termref def="dt-empty">empty</termref> elements, by an <termref def="dt-eetag">empty-element tag</termref>. Each element has a type, identified by name, sometimes called its "generic identifier" (GI), and may have a set of -attribute specifications. </termdef> - Each attribute specification -has a <termref def="dt-attrname">name</termref> - and a <termref def="dt-attrval">value</termref> -. - </p> +attribute specifications.</termdef> Each attribute specification +has a <termref def="dt-attrname">name</termref> and a <termref def="dt-attrval">value</termref>. +</p> <scrap lang="ebnf"> <head>Element</head> <prod id="NT-element"> @@ -2044,156 +1250,84 @@ has a <termref def="dt-attrname">name</termref> <rhs> <nt def="NT-EmptyElemTag">EmptyElemTag</nt> </rhs> - <rhs>| - <nt def="NT-STag">STag</nt> - <nt def="NT-content">content</nt> - - <nt def="NT-ETag">ETag</nt> - </rhs> + <rhs>| <nt def="NT-STag">STag</nt> <nt def="NT-content">content</nt> +<nt def="NT-ETag">ETag</nt></rhs> <wfc def="GIMatch"/> <vc def="elementvalid"/> </prod> </scrap> <p>This specification does not constrain the semantics, use, or (beyond syntax) names of the element types and attributes, except that names -beginning with a match to - <code>(('X'|'x')('M'|'m')('L'|'l'))</code> - +beginning with a match to <code>(('X'|'x')('M'|'m')('L'|'l'))</code> are reserved for standardization in this or future versions of this specification. - </p> +</p> <wfcnote id="GIMatch"> <head>Element Type Match</head> <p> -The - <nt def="NT-Name">Name</nt> - in an element's end-tag must match +The <nt def="NT-Name">Name</nt> in an element's end-tag must match the element type in the start-tag. - </p> +</p> </wfcnote> <vcnote id="elementvalid"> <head>Element Valid</head> <p>An element is valid if there is a declaration matching - - <nt def="NT-elementdecl">elementdecl</nt> - where the - <nt def="NT-Name">Name</nt> - matches the element type, and -one of the following holds: </p> +<nt def="NT-elementdecl">elementdecl</nt> where the +<nt def="NT-Name">Name</nt> matches the element type, and +one of the following holds:</p> <olist> <item> - <p>The declaration matches - <kw>EMPTY</kw> - and the element has no - <termref def="dt-content">content</termref> -. </p> + <p>The declaration matches <kw>EMPTY</kw> and the element has no +<termref def="dt-content">content</termref>.</p> </item> <item> - <p>The declaration matches - <nt def="NT-children">children</nt> - and + <p>The declaration matches <nt def="NT-children">children</nt> and the sequence of - <termref def="dt-parentchild">child elements</termref> - +<termref def="dt-parentchild">child elements</termref> belongs to the language generated by the regular expression in the content model, with optional white space (characters -matching the nonterminal <nt def="NT-S">S</nt> -) between each pair -of child elements. </p> +matching the nonterminal <nt def="NT-S">S</nt>) between each pair +of child elements.</p> </item> <item> - <p>The declaration matches - <nt def="NT-Mixed">Mixed</nt> - and -the content consists of <termref def="dt-chardata">character -data</termref> - and <termref def="dt-parentchild">child elements</termref> - -whose types match names in the content model. </p> + <p>The declaration matches <nt def="NT-Mixed">Mixed</nt> and +the content consists of <termref def="dt-chardata">character +data</termref> and <termref def="dt-parentchild">child elements</termref> +whose types match names in the content model.</p> </item> <item> - <p>The declaration matches - <kw>ANY</kw> -, and the types -of any <termref def="dt-parentchild">child elements</termref> - have -been declared. </p> + <p>The declaration matches <kw>ANY</kw>, and the types +of any <termref def="dt-parentchild">child elements</termref> have +been declared.</p> </item> </olist> </vcnote> <div2 id="sec-starttags"> <head>Start-Tags, End-Tags, and Empty-Element Tags</head> - <p> - <termdef id="dt-stag" term="Start-Tag">The beginning of every -non-empty XML element is marked by a - <term>start-tag</term> -. - <scrap lang="ebnf"> - <head>Start-tag</head> - <prodgroup pcw2="6" pcw4="15" pcw5="11.5"> - <prod id="NT-STag"> - <lhs>STag</lhs> - <rhs>'<' - <nt def="NT-Name">Name</nt> - -( <nt def="NT-S">S</nt> - <nt def="NT-Attribute">Attribute</nt> -)* - <nt def="NT-S">S</nt> -? '>' </rhs> - <wfc def="uniqattspec"/> - </prod> - <prod id="NT-Attribute"> - <lhs>Attribute</lhs> - <rhs> - <nt def="NT-Name">Name</nt> - <nt def="NT-Eq">Eq</nt> - - <nt def="NT-AttValue">AttValue</nt> - </rhs> - <vc def="ValueType"/> - <wfc def="NoExternalRefs"/> - <wfc def="CleanAttrVals"/> - </prod> - </prodgroup> - </scrap> - -The <nt def="NT-Name">Name</nt> - in + <p><termdef id="dt-stag" term="Start-Tag">The beginning of every +non-empty XML element is marked by a <term>start-tag</term>. +<scrap lang="ebnf"><head>Start-tag</head><prodgroup pcw2="6" pcw4="15" pcw5="11.5"><prod id="NT-STag"><lhs>STag</lhs><rhs>'<' <nt def="NT-Name">Name</nt> +(<nt def="NT-S">S</nt> <nt def="NT-Attribute">Attribute</nt>)* +<nt def="NT-S">S</nt>? '>'</rhs><wfc def="uniqattspec"/></prod><prod id="NT-Attribute"><lhs>Attribute</lhs><rhs><nt def="NT-Name">Name</nt> <nt def="NT-Eq">Eq</nt> +<nt def="NT-AttValue">AttValue</nt></rhs><vc def="ValueType"/><wfc def="NoExternalRefs"/><wfc def="CleanAttrVals"/></prod></prodgroup></scrap> +The <nt def="NT-Name">Name</nt> in the start- and end-tags gives the -element's <term>type</term> -. </termdef> - - <termdef id="dt-attr" term="Attribute"> -The - <nt def="NT-Name">Name</nt> -- <nt def="NT-AttValue">AttValue</nt> - pairs are +element's <term>type</term>.</termdef> +<termdef id="dt-attr" term="Attribute"> +The <nt def="NT-Name">Name</nt>-<nt def="NT-AttValue">AttValue</nt> pairs are referred to as -the <term>attribute specifications</term> - of the element </termdef> -, - <termdef id="dt-attrname" term="Attribute Name">with the - - <nt def="NT-Name">Name</nt> - in each pair -referred to as the <term>attribute name</term> - </termdef> - and - <termdef id="dt-attrval" term="Attribute Value">the content of the - - <nt def="NT-AttValue">AttValue</nt> - (the text between the - <code>'</code> - or <code>"</code> - delimiters) -as the <term>attribute value</term> -. </termdef> - - </p> +the <term>attribute specifications</term> of the element</termdef>, +<termdef id="dt-attrname" term="Attribute Name">with the +<nt def="NT-Name">Name</nt> in each pair +referred to as the <term>attribute name</term></termdef> and +<termdef id="dt-attrval" term="Attribute Value">the content of the +<nt def="NT-AttValue">AttValue</nt> (the text between the +<code>'</code> or <code>"</code> delimiters) +as the <term>attribute value</term>.</termdef> +</p> <wfcnote id="uniqattspec"> <head>Unique Att Spec</head> <p> @@ -2206,10 +1340,8 @@ or empty-element tag. <p> The attribute must have been declared; the value must be of the type declared for it. -(For attribute types, see - <specref ref="attdecls"/> -.) - </p> +(For attribute types, see <specref ref="attdecls"/>.) +</p> </vcnote> <wfcnote id="NoExternalRefs"> <head>No External Entity References</head> @@ -2219,193 +1351,86 @@ to external entities. </p> </wfcnote> <wfcnote id="CleanAttrVals"> - <head>No - <code><</code> - in Attribute Values </head> - <p>The - <termref def="dt-repltext">replacement text</termref> - of any entity + <head>No <code><</code> in Attribute Values</head> + <p>The <termref def="dt-repltext">replacement text</termref> of any entity referred to directly or indirectly in an attribute -value (other than " <code>&lt;</code> -") must not contain -a <code><</code> -. - </p> +value (other than "<code>&lt;</code>") must not contain +a <code><</code>. +</p> </wfcnote> <p>An example of a start-tag: - - <eg><termdef id="dt-dog" term="dog"></eg> - </p> +<eg><termdef id="dt-dog" term="dog"></eg></p> <p> <termdef id="dt-etag" term="End Tag">The end of every element that begins with a start-tag must -be marked by an - <term>end-tag</term> - +be marked by an <term>end-tag</term> containing a name that echoes the element's type as given in the start-tag: - <scrap lang="ebnf"> - <head>End-tag</head> - <prodgroup pcw2="6" pcw4="15" pcw5="11.5"> - <prod id="NT-ETag"> - <lhs>ETag</lhs> - <rhs>'</' - <nt def="NT-Name">Name</nt> - - <nt def="NT-S">S</nt> -? '>' </rhs> - </prod> - </prodgroup> - </scrap> - - </termdef> - </p> - <p>An example of an end-tag: - <eg></termdef></eg> +<scrap lang="ebnf"><head>End-tag</head><prodgroup pcw2="6" pcw4="15" pcw5="11.5"><prod id="NT-ETag"><lhs>ETag</lhs><rhs>'</' <nt def="NT-Name">Name</nt> +<nt def="NT-S">S</nt>? '>'</rhs></prod></prodgroup></scrap> +</termdef> </p> + <p>An example of an end-tag:<eg></termdef></eg></p> <p> <termdef id="dt-content" term="Content">The - - <termref def="dt-text">text</termref> - between the start-tag and +<termref def="dt-text">text</termref> between the start-tag and end-tag is called the element's - <term>content</term> -: - <scrap lang="ebnf"> - <head>Content of Elements</head> - <prodgroup pcw2="6" pcw4="15" pcw5="11.5"> - <prod id="NT-content"> - <lhs>content</lhs> - <rhs>( - <nt def="NT-element">element</nt> - | <nt def="NT-CharData">CharData</nt> - -| <nt def="NT-Reference">Reference</nt> - | <nt def="NT-CDSect">CDSect</nt> - -| <nt def="NT-PI">PI</nt> - | <nt def="NT-Comment">Comment</nt> -)* </rhs> - </prod> - </prodgroup> - </scrap> - - </termdef> +<term>content</term>: +<scrap lang="ebnf"><head>Content of Elements</head><prodgroup pcw2="6" pcw4="15" pcw5="11.5"><prod id="NT-content"><lhs>content</lhs><rhs>(<nt def="NT-element">element</nt> | <nt def="NT-CharData">CharData</nt> +| <nt def="NT-Reference">Reference</nt> | <nt def="NT-CDSect">CDSect</nt> +| <nt def="NT-PI">PI</nt> | <nt def="NT-Comment">Comment</nt>)*</rhs></prod></prodgroup></scrap> +</termdef> </p> - <p> - <termdef id="dt-empty" term="Empty">If an element is - <term>empty</term> -, + <p><termdef id="dt-empty" term="Empty">If an element is <term>empty</term>, it must be represented either by a start-tag immediately followed -by an end-tag or by an empty-element tag. </termdef> - - <termdef id="dt-eetag" term="empty-element tag">An - - <term>empty-element tag</term> - takes a special form: - <scrap lang="ebnf"> - <head>Tags for Empty Elements</head> - <prodgroup pcw2="6" pcw4="15" pcw5="11.5"> - <prod id="NT-EmptyElemTag"> - <lhs>EmptyElemTag</lhs> - <rhs>'<' - <nt def="NT-Name">Name</nt> - ( <nt def="NT-S">S</nt> - - <nt def="NT-Attribute">Attribute</nt> -)* <nt def="NT-S">S</nt> -? -'/>' </rhs> - <wfc def="uniqattspec"/> - </prod> - </prodgroup> - </scrap> - - </termdef> - </p> +by an end-tag or by an empty-element tag.</termdef> +<termdef id="dt-eetag" term="empty-element tag">An +<term>empty-element tag</term> takes a special form: +<scrap lang="ebnf"><head>Tags for Empty Elements</head><prodgroup pcw2="6" pcw4="15" pcw5="11.5"><prod id="NT-EmptyElemTag"><lhs>EmptyElemTag</lhs><rhs>'<' <nt def="NT-Name">Name</nt> (<nt def="NT-S">S</nt> +<nt def="NT-Attribute">Attribute</nt>)* <nt def="NT-S">S</nt>? +'/>'</rhs><wfc def="uniqattspec"/></prod></prodgroup></scrap> +</termdef></p> <p>Empty-element tags may be used for any element which has no content, whether or not it is declared using the keyword - - <kw>EMPTY</kw> -. - <termref def="dt-interop">For interoperability</termref> -, the empty-element +<kw>EMPTY</kw>. +<termref def="dt-interop">For interoperability</termref>, the empty-element tag must be used, and can only be used, for elements which are - <termref def="dt-eldecl">declared</termref> - <kw>EMPTY</kw> -. </p> +<termref def="dt-eldecl">declared</termref> <kw>EMPTY</kw>.</p> <p>Examples of empty elements: - - <eg><IMG align="left" +<eg><IMG align="left" src="http://www.w3.org/Icons/WWW/w3c_home" /> <br></br> -<br/></eg> - </p> +<br/></eg></p> </div2> <div2 id="elemdecls"> <head>Element Type Declarations</head> - <p>The - <termref def="dt-element">element</termref> - structure of an - <termref def="dt-xml-doc">XML document</termref> - may, for - <termref def="dt-valid">validation</termref> - purposes, + <p>The <termref def="dt-element">element</termref> structure of an +<termref def="dt-xml-doc">XML document</termref> may, for +<termref def="dt-valid">validation</termref> purposes, be constrained using element type and attribute-list declarations. An element type declaration constrains the element's - <termref def="dt-content">content</termref> -. - </p> +<termref def="dt-content">content</termref>. +</p> <p>Element type declarations often constrain which element types can -appear as - <termref def="dt-parentchild">children</termref> - of the element. +appear as <termref def="dt-parentchild">children</termref> of the element. At user option, an XML processor may issue a warning when a declaration mentions an element type for which no declaration -is provided, but this is not an error. </p> - <p> - <termdef id="dt-eldecl" term="Element Type declaration">An - <term>element -type declaration</term> - takes the form: - <scrap lang="ebnf"> - <head>Element Type Declaration</head> - <prodgroup pcw2="5.5" pcw4="18" pcw5="9"> - <prod id="NT-elementdecl"> - <lhs>elementdecl</lhs> - <rhs>'<!ELEMENT' - <nt def="NT-S">S</nt> - - <nt def="NT-Name">Name</nt> - - <nt def="NT-S">S</nt> - - <nt def="NT-contentspec">contentspec</nt> - - <nt def="NT-S">S</nt> -? '>' </rhs> - <vc def="EDUnique"/> - </prod> - <prod id="NT-contentspec"> - <lhs>contentspec</lhs> - <rhs>'EMPTY' +is provided, but this is not an error.</p> + <p><termdef id="dt-eldecl" term="Element Type declaration">An <term>element +type declaration</term> takes the form: +<scrap lang="ebnf"><head>Element Type Declaration</head><prodgroup pcw2="5.5" pcw4="18" pcw5="9"><prod id="NT-elementdecl"><lhs>elementdecl</lhs><rhs>'<!ELEMENT' <nt def="NT-S">S</nt> +<nt def="NT-Name">Name</nt> +<nt def="NT-S">S</nt> +<nt def="NT-contentspec">contentspec</nt> +<nt def="NT-S">S</nt>? '>'</rhs><vc def="EDUnique"/></prod><prod id="NT-contentspec"><lhs>contentspec</lhs><rhs>'EMPTY' | 'ANY' -| - <nt def="NT-Mixed">Mixed</nt> - -| <nt def="NT-children">children</nt> - - </rhs> - </prod> - </prodgroup> - </scrap> - -where the <nt def="NT-Name">Name</nt> - gives the element type -being declared. </termdef> - - </p> +| <nt def="NT-Mixed">Mixed</nt> +| <nt def="NT-children">children</nt> +</rhs></prod></prodgroup></scrap> +where the <nt def="NT-Name">Name</nt> gives the element type +being declared.</termdef> +</p> <vcnote id="EDUnique"> <head>Unique Element Type Declaration</head> <p> @@ -2413,219 +1438,112 @@ No element type may be declared more than once. </p> </vcnote> <p>Examples of element type declarations: - - <eg><!ELEMENT br EMPTY> +<eg><!ELEMENT br EMPTY> <!ELEMENT p (#PCDATA|emph)* > <!ELEMENT %name.para; %content.para; > -<!ELEMENT container ANY></eg> - </p> +<!ELEMENT container ANY></eg></p> <div3 id="sec-element-content"> <head>Element Content</head> - <p> - <termdef id="dt-elemcontent" term="Element content">An element - <termref def="dt-stag">type</termref> - has - <term>element content</term> - when elements of that -type must contain only <termref def="dt-parentchild">child</termref> - + <p><termdef id="dt-elemcontent" term="Element content">An element <termref def="dt-stag">type</termref> has +<term>element content</term> when elements of that +type must contain only <termref def="dt-parentchild">child</termref> elements (no character data), optionally separated by white space (characters matching the nonterminal - <nt def="NT-S">S</nt> -). - </termdef> - +<nt def="NT-S">S</nt>). +</termdef> In this case, the constraint includes a content model, a simple grammar governing the allowed types of the child elements and the order in which they are allowed to appear. The grammar is built on -content particles ( <nt def="NT-cp">cp</nt> -s), which consist of names, +content particles (<nt def="NT-cp">cp</nt>s), which consist of names, choice lists of content particles, or sequence lists of content particles: - <scrap lang="ebnf"> - <head>Element-content Models</head> - <prodgroup pcw2="5.5" pcw4="16" pcw5="11"> - <prod id="NT-children"> - <lhs>children</lhs> - <rhs>( - <nt def="NT-choice">choice</nt> - -| <nt def="NT-seq">seq</nt> -) -('?' | '*' | '+')? </rhs> - </prod> - <prod id="NT-cp"> - <lhs>cp</lhs> - <rhs>( - <nt def="NT-Name">Name</nt> - -| <nt def="NT-choice">choice</nt> - -| <nt def="NT-seq">seq</nt> -) -('?' | '*' | '+')? </rhs> - </prod> - <prod id="NT-choice"> - <lhs>choice</lhs> - <rhs>'(' - <nt def="NT-S">S</nt> -? cp -( <nt def="NT-S">S</nt> -? '|' <nt def="NT-S">S</nt> -? <nt def="NT-cp">cp</nt> - )* - <nt def="NT-S">S</nt> -? ')' </rhs> - <vc def="vc-PEinGroup"/> - </prod> - <prod id="NT-seq"> - <lhs>seq</lhs> - <rhs>'(' - <nt def="NT-S">S</nt> -? cp -( <nt def="NT-S">S</nt> -? ',' <nt def="NT-S">S</nt> -? <nt def="NT-cp">cp</nt> - )* - <nt def="NT-S">S</nt> -? ')' </rhs> - <vc def="vc-PEinGroup"/> - </prod> - </prodgroup> - </scrap> - -where each <nt def="NT-Name">Name</nt> - is the type of an element which may -appear as a <termref def="dt-parentchild">child</termref> -. +<scrap lang="ebnf"><head>Element-content Models</head><prodgroup pcw2="5.5" pcw4="16" pcw5="11"><prod id="NT-children"><lhs>children</lhs><rhs>(<nt def="NT-choice">choice</nt> +| <nt def="NT-seq">seq</nt>) +('?' | '*' | '+')?</rhs></prod><prod id="NT-cp"><lhs>cp</lhs><rhs>(<nt def="NT-Name">Name</nt> +| <nt def="NT-choice">choice</nt> +| <nt def="NT-seq">seq</nt>) +('?' | '*' | '+')?</rhs></prod><prod id="NT-choice"><lhs>choice</lhs><rhs>'(' <nt def="NT-S">S</nt>? cp +( <nt def="NT-S">S</nt>? '|' <nt def="NT-S">S</nt>? <nt def="NT-cp">cp</nt> )* +<nt def="NT-S">S</nt>? ')'</rhs><vc def="vc-PEinGroup"/></prod><prod id="NT-seq"><lhs>seq</lhs><rhs>'(' <nt def="NT-S">S</nt>? cp +( <nt def="NT-S">S</nt>? ',' <nt def="NT-S">S</nt>? <nt def="NT-cp">cp</nt> )* +<nt def="NT-S">S</nt>? ')'</rhs><vc def="vc-PEinGroup"/></prod></prodgroup></scrap> +where each <nt def="NT-Name">Name</nt> is the type of an element which may +appear as a <termref def="dt-parentchild">child</termref>. Any content -particle in a choice list may appear in the <termref def="dt-elemcontent">element content</termref> - at the location where +particle in a choice list may appear in the <termref def="dt-elemcontent">element content</termref> at the location where the choice list appears in the grammar; content particles occurring in a sequence list must each -appear in the <termref def="dt-elemcontent">element content</termref> - in the +appear in the <termref def="dt-elemcontent">element content</termref> in the order given in the list. The optional character following a name or list governs whether the element or the content particles in the list may occur one -or more ( <code>+</code> -), zero or more ( <code>*</code> -), or zero or -one times ( <code>?</code> -). +or more (<code>+</code>), zero or more (<code>*</code>), or zero or +one times (<code>?</code>). The absence of such an operator means that the element or content particle must appear exactly once. This syntax and meaning are identical to those used in the productions in this -specification. </p> +specification.</p> <p> The content of an element matches a content model if and only if it is possible to trace out a path through the content model, obeying the sequence, choice, and repetition operators and matching each element in -the content against an element type in the content model. - <termref def="dt-compat">For compatibility</termref> -, it is an error +the content against an element type in the content model. <termref def="dt-compat">For compatibility</termref>, it is an error if an element in the document can match more than one occurrence of an element type in the content model. -For more information, see <specref ref="determinism"/> -. +For more information, see <specref ref="determinism"/>. <!-- appendix <specref ref="determinism"/>. --> - <!-- appendix on deterministic content models. --> - - </p> +</p> <vcnote id="vc-PEinGroup"> <head>Proper Group/PE Nesting</head> <p>Parameter-entity - - <termref def="dt-repltext">replacement text</termref> - must be properly nested +<termref def="dt-repltext">replacement text</termref> must be properly nested with parenthetized groups. That is to say, if either of the opening or closing parentheses -in a <nt def="NT-choice">choice</nt> -, <nt def="NT-seq">seq</nt> -, or - <nt def="NT-Mixed">Mixed</nt> - construct +in a <nt def="NT-choice">choice</nt>, <nt def="NT-seq">seq</nt>, or +<nt def="NT-Mixed">Mixed</nt> construct is contained in the replacement text for a - <termref def="dt-PERef">parameter entity</termref> -, -both must be contained in the same replacement text. </p> - <p> - <termref def="dt-interop">For interoperability</termref> -, +<termref def="dt-PERef">parameter entity</termref>, +both must be contained in the same replacement text.</p> + <p><termref def="dt-interop">For interoperability</termref>, if a parameter-entity reference appears in a - <nt def="NT-choice">choice</nt> -, <nt def="NT-seq">seq</nt> -, or - <nt def="NT-Mixed">Mixed</nt> - construct, its replacement text +<nt def="NT-choice">choice</nt>, <nt def="NT-seq">seq</nt>, or +<nt def="NT-Mixed">Mixed</nt> construct, its replacement text should not be empty, and neither the first nor last non-blank character of the replacement text should be a connector -( <code>|</code> - or <code>,</code> -). - </p> +(<code>|</code> or <code>,</code>). +</p> </vcnote> <p>Examples of element-content models: - - <eg><!ELEMENT spec (front, body, back?)> +<eg><!ELEMENT spec (front, body, back?)> <!ELEMENT div1 (head, (p | list | note)*, div2*)> -<!ELEMENT dictionary-body (%div.mix; | %dict.mix;)*></eg> - </p> +<!ELEMENT dictionary-body (%div.mix; | %dict.mix;)*></eg></p> </div3> <div3 id="sec-mixed-content"> <head>Mixed Content</head> - <p> - <termdef id="dt-mixed" term="Mixed Content">An element - - <termref def="dt-stag">type</termref> - has - <term>mixed content</term> - when elements of that type may contain + <p><termdef id="dt-mixed" term="Mixed Content">An element +<termref def="dt-stag">type</termref> has +<term>mixed content</term> when elements of that type may contain character data, optionally interspersed with - <termref def="dt-parentchild">child</termref> - elements. </termdef> - +<termref def="dt-parentchild">child</termref> elements.</termdef> In this case, the types of the child elements may be constrained, but not their order or their number of occurrences: - <scrap lang="ebnf"> - <head>Mixed-content Declaration</head> - <prodgroup pcw2="5.5" pcw4="16" pcw5="11"> - <prod id="NT-Mixed"> - <lhs>Mixed</lhs> - <rhs>'(' - <nt def="NT-S">S</nt> -? +<scrap lang="ebnf"><head>Mixed-content Declaration</head><prodgroup pcw2="5.5" pcw4="16" pcw5="11"><prod id="NT-Mixed"><lhs>Mixed</lhs><rhs>'(' <nt def="NT-S">S</nt>? '#PCDATA' -( <nt def="NT-S">S</nt> -? +(<nt def="NT-S">S</nt>? '|' - <nt def="NT-S">S</nt> -? - <nt def="NT-Name">Name</nt> -)* - <nt def="NT-S">S</nt> -? -')*' </rhs> - <rhs>| '(' - <nt def="NT-S">S</nt> -? '#PCDATA' <nt def="NT-S">S</nt> -? ')' - </rhs> - <vc def="vc-PEinGroup"/> - <vc def="vc-MixedChildrenUnique"/> - </prod> - </prodgroup> - </scrap> - -where the <nt def="NT-Name">Name</nt> -s give the types of elements +<nt def="NT-S">S</nt>? +<nt def="NT-Name">Name</nt>)* +<nt def="NT-S">S</nt>? +')*' </rhs><rhs>| '(' <nt def="NT-S">S</nt>? '#PCDATA' <nt def="NT-S">S</nt>? ')' +</rhs><vc def="vc-PEinGroup"/><vc def="vc-MixedChildrenUnique"/></prod></prodgroup></scrap> +where the <nt def="NT-Name">Name</nt>s give the types of elements that may appear as children. - </p> +</p> <vcnote id="vc-MixedChildrenUnique"> <head>No Duplicate Types</head> <p>The same name must not appear more than once in a single mixed-content @@ -2633,104 +1551,51 @@ declaration. </p> </vcnote> <p>Examples of mixed content declarations: - - <eg><!ELEMENT p (#PCDATA|a|ul|b|i|em)*> +<eg><!ELEMENT p (#PCDATA|a|ul|b|i|em)*> <!ELEMENT p (#PCDATA | %font; | %phrase; | %special; | %form;)* > -<!ELEMENT b (#PCDATA)></eg> - </p> +<!ELEMENT b (#PCDATA)></eg></p> </div3> </div2> <div2 id="attdecls"> <head>Attribute-List Declarations</head> - <p> - <termref def="dt-attr">Attributes</termref> - are used to associate -name-value pairs with <termref def="dt-element">elements</termref> -. -Attribute specifications may appear only within <termref def="dt-stag">start-tags</termref> - -and <termref def="dt-eetag">empty-element tags</termref> -; + <p><termref def="dt-attr">Attributes</termref> are used to associate +name-value pairs with <termref def="dt-element">elements</termref>. +Attribute specifications may appear only within <termref def="dt-stag">start-tags</termref> +and <termref def="dt-eetag">empty-element tags</termref>; thus, the productions used to -recognize them appear in <specref ref="sec-starttags"/> -. +recognize them appear in <specref ref="sec-starttags"/>. Attribute-list declarations may be used: - <ulist> - <item> - <p>To define the set of attributes pertaining to a given -element type.</p> - </item> - <item> - <p>To establish type constraints for these -attributes.</p> - </item> - <item> - <p>To provide - <termref def="dt-default">default values</termref> - -for attributes. </p> - </item> - </ulist> - - </p> +<ulist><item><p>To define the set of attributes pertaining to a given +element type.</p></item><item><p>To establish type constraints for these +attributes.</p></item><item><p>To provide <termref def="dt-default">default values</termref> +for attributes.</p></item></ulist> +</p> <p> <termdef id="dt-attdecl" term="Attribute-List Declaration"> - - <term>Attribute-list declarations</term> - specify the name, data type, and default +<term>Attribute-list declarations</term> specify the name, data type, and default value (if any) of each attribute associated with a given element type: - <scrap lang="ebnf"> - <head>Attribute-list Declaration</head> - <prod id="NT-AttlistDecl"> - <lhs>AttlistDecl</lhs> - <rhs>'<!ATTLIST' - <nt def="NT-S">S</nt> - - <nt def="NT-Name">Name</nt> - - <nt def="NT-AttDef">AttDef</nt> -* - <nt def="NT-S">S</nt> -? '>' </rhs> - </prod> - <prod id="NT-AttDef"> - <lhs>AttDef</lhs> - <rhs> - <nt def="NT-S">S</nt> - <nt def="NT-Name">Name</nt> - - <nt def="NT-S">S</nt> - <nt def="NT-AttType">AttType</nt> - - <nt def="NT-S">S</nt> - <nt def="NT-DefaultDecl">DefaultDecl</nt> - </rhs> - </prod> - </scrap> - -The <nt def="NT-Name">Name</nt> - in the - <nt def="NT-AttlistDecl">AttlistDecl</nt> - rule is the type of an element. At +<scrap lang="ebnf"><head>Attribute-list Declaration</head><prod id="NT-AttlistDecl"><lhs>AttlistDecl</lhs><rhs>'<!ATTLIST' <nt def="NT-S">S</nt> +<nt def="NT-Name">Name</nt> +<nt def="NT-AttDef">AttDef</nt>* +<nt def="NT-S">S</nt>? '>'</rhs></prod><prod id="NT-AttDef"><lhs>AttDef</lhs><rhs><nt def="NT-S">S</nt> <nt def="NT-Name">Name</nt> +<nt def="NT-S">S</nt> <nt def="NT-AttType">AttType</nt> +<nt def="NT-S">S</nt> <nt def="NT-DefaultDecl">DefaultDecl</nt></rhs></prod></scrap> +The <nt def="NT-Name">Name</nt> in the +<nt def="NT-AttlistDecl">AttlistDecl</nt> rule is the type of an element. At user option, an XML processor may issue a warning if attributes are declared for an element type not itself declared, but this is not an -error. The <nt def="NT-Name">Name</nt> - in the - <nt def="NT-AttDef">AttDef</nt> - rule is -the name of the attribute. </termdef> +error. The <nt def="NT-Name">Name</nt> in the +<nt def="NT-AttDef">AttDef</nt> rule is +the name of the attribute.</termdef> </p> <p> -When more than one - <nt def="NT-AttlistDecl">AttlistDecl</nt> - is provided for a +When more than one <nt def="NT-AttlistDecl">AttlistDecl</nt> is provided for a given element type, the contents of all those provided are merged. When more than one definition is provided for the same attribute of a given element type, the first declaration is binding and later declarations are ignored. - <termref def="dt-interop">For interoperability,</termref> - writers of DTDs +<termref def="dt-interop">For interoperability,</termref> writers of DTDs may choose to provide at most one attribute-list declaration for a given element type, at most one attribute definition for a given attribute name, and at least one attribute definition @@ -2740,67 +1605,27 @@ issue a warning when more than one attribute-list declaration is provided for a given element type, or more than one attribute definition is provided for a given attribute, but this is not an error. - </p> +</p> <div3 id="sec-attribute-types"> <head>Attribute Types</head> <p>XML attribute types are of three kinds: a string type, a set of tokenized types, and enumerated types. The string type may take any literal string as a value; the tokenized types have varying lexical and semantic constraints, as noted: - - <scrap lang="ebnf"> - <head>Attribute Types</head> - <prodgroup pcw4="14" pcw5="11.5"> - <prod id="NT-AttType"> - <lhs>AttType</lhs> - <rhs> - <nt def="NT-StringType">StringType</nt> - -| <nt def="NT-TokenizedType">TokenizedType</nt> - -| <nt def="NT-EnumeratedType">EnumeratedType</nt> - - </rhs> - </prod> - <prod id="NT-StringType"> - <lhs>StringType</lhs> - <rhs>'CDATA'</rhs> - </prod> - <prod id="NT-TokenizedType"> - <lhs>TokenizedType</lhs> - <rhs>'ID'</rhs> - <vc def="id"/> - <vc def="one-id-per-el"/> - <vc def="id-default"/> - <rhs>| 'IDREF'</rhs> - <vc def="idref"/> - <rhs>| 'IDREFS'</rhs> - <vc def="idref"/> - <rhs>| 'ENTITY'</rhs> - <vc def="entname"/> - <rhs>| 'ENTITIES'</rhs> - <vc def="entname"/> - <rhs>| 'NMTOKEN'</rhs> - <vc def="nmtok"/> - <rhs>| 'NMTOKENS'</rhs> - <vc def="nmtok"/> - </prod> - </prodgroup> - </scrap> - - </p> +<scrap lang="ebnf"><head>Attribute Types</head><prodgroup pcw4="14" pcw5="11.5"><prod id="NT-AttType"><lhs>AttType</lhs><rhs><nt def="NT-StringType">StringType</nt> +| <nt def="NT-TokenizedType">TokenizedType</nt> +| <nt def="NT-EnumeratedType">EnumeratedType</nt> +</rhs></prod><prod id="NT-StringType"><lhs>StringType</lhs><rhs>'CDATA'</rhs></prod><prod id="NT-TokenizedType"><lhs>TokenizedType</lhs><rhs>'ID'</rhs><vc def="id"/><vc def="one-id-per-el"/><vc def="id-default"/><rhs>| 'IDREF'</rhs><vc def="idref"/><rhs>| 'IDREFS'</rhs><vc def="idref"/><rhs>| 'ENTITY'</rhs><vc def="entname"/><rhs>| 'ENTITIES'</rhs><vc def="entname"/><rhs>| 'NMTOKEN'</rhs><vc def="nmtok"/><rhs>| 'NMTOKENS'</rhs><vc def="nmtok"/></prod></prodgroup></scrap> +</p> <vcnote id="id"> <head>ID</head> <p> -Values of type - <kw>ID</kw> - must match the - <nt def="NT-Name">Name</nt> - production. +Values of type <kw>ID</kw> must match the +<nt def="NT-Name">Name</nt> production. A name must not appear more than once in an XML document as a value of this type; i.e., ID values must uniquely identify the elements which bear them. - </p> +</p> </vcnote> <vcnote id="one-id-per-el"> <head>One ID per Element Type</head> @@ -2808,200 +1633,108 @@ identify the elements which bear them. </vcnote> <vcnote id="id-default"> <head>ID Attribute Default</head> - <p>An ID attribute must have a declared default of - <kw>#IMPLIED</kw> - or - <kw>#REQUIRED</kw> -. </p> + <p>An ID attribute must have a declared default of <kw>#IMPLIED</kw> or +<kw>#REQUIRED</kw>.</p> </vcnote> <vcnote id="idref"> <head>IDREF</head> <p> -Values of type - <kw>IDREF</kw> - must match -the <nt def="NT-Name">Name</nt> - production, and -values of type <kw>IDREFS</kw> - must match - <nt def="NT-Names">Names</nt> -; -each <nt def="NT-Name">Name</nt> - must match the value of an ID attribute on -some element in the XML document; i.e. <kw>IDREF</kw> - values must +Values of type <kw>IDREF</kw> must match +the <nt def="NT-Name">Name</nt> production, and +values of type <kw>IDREFS</kw> must match +<nt def="NT-Names">Names</nt>; +each <nt def="NT-Name">Name</nt> must match the value of an ID attribute on +some element in the XML document; i.e. <kw>IDREF</kw> values must match the value of some ID attribute. - </p> +</p> </vcnote> <vcnote id="entname"> <head>Entity Name</head> <p> -Values of type - <kw>ENTITY</kw> - -must match the <nt def="NT-Name">Name</nt> - production, -values of type <kw>ENTITIES</kw> - must match - <nt def="NT-Names">Names</nt> -; -each <nt def="NT-Name">Name</nt> - must +Values of type <kw>ENTITY</kw> +must match the <nt def="NT-Name">Name</nt> production, +values of type <kw>ENTITIES</kw> must match +<nt def="NT-Names">Names</nt>; +each <nt def="NT-Name">Name</nt> must match the -name of an <termref def="dt-unparsed">unparsed entity</termref> - declared in the - <termref def="dt-doctype">DTD</termref> -. - </p> +name of an <termref def="dt-unparsed">unparsed entity</termref> declared in the +<termref def="dt-doctype">DTD</termref>. +</p> </vcnote> <vcnote id="nmtok"> <head>Name Token</head> <p> -Values of type - <kw>NMTOKEN</kw> - must match the - <nt def="NT-Nmtoken">Nmtoken</nt> - production; -values of type <kw>NMTOKENS</kw> - must -match <termref def="NT-Nmtokens">Nmtokens</termref> -. - </p> +Values of type <kw>NMTOKEN</kw> must match the +<nt def="NT-Nmtoken">Nmtoken</nt> production; +values of type <kw>NMTOKENS</kw> must +match <termref def="NT-Nmtokens">Nmtokens</termref>. +</p> </vcnote> <!-- why? <p>The XML processor must normalize attribute values before passing them to the application, as described in <specref ref="AVNormalize"/>.</p>--> - <p> - <termdef id="dt-enumerated" term="Enumerated Attribute -Values"> - <term>Enumerated attributes</term> - can take one -of a list of values provided in the declaration </termdef> -. There are two + <p><termdef id="dt-enumerated" term="Enumerated Attribute +Values"><term>Enumerated attributes</term> can take one +of a list of values provided in the declaration</termdef>. There are two kinds of enumerated types: - <scrap lang="ebnf"> - <head>Enumerated Attribute Types</head> - <prod id="NT-EnumeratedType"> - <lhs>EnumeratedType</lhs> - <rhs> - <nt def="NT-NotationType">NotationType</nt> - -| <nt def="NT-Enumeration">Enumeration</nt> - - </rhs> - </prod> - <prod id="NT-NotationType"> - <lhs>NotationType</lhs> - <rhs>'NOTATION' - - <nt def="NT-S">S</nt> - +<scrap lang="ebnf"><head>Enumerated Attribute Types</head><prod id="NT-EnumeratedType"><lhs>EnumeratedType</lhs><rhs><nt def="NT-NotationType">NotationType</nt> +| <nt def="NT-Enumeration">Enumeration</nt> +</rhs></prod><prod id="NT-NotationType"><lhs>NotationType</lhs><rhs>'NOTATION' +<nt def="NT-S">S</nt> '(' - <nt def="NT-S">S</nt> -? - <nt def="NT-Name">Name</nt> - -( <nt def="NT-S">S</nt> -? '|' <nt def="NT-S">S</nt> -? - <nt def="NT-Name">Name</nt> -)* - <nt def="NT-S">S</nt> -? ')' - </rhs> - <vc def="notatn"/> - </prod> - <prod id="NT-Enumeration"> - <lhs>Enumeration</lhs> - <rhs>'(' - <nt def="NT-S">S</nt> -? - <nt def="NT-Nmtoken">Nmtoken</nt> - -( <nt def="NT-S">S</nt> -? '|' - <nt def="NT-S">S</nt> -? - <nt def="NT-Nmtoken">Nmtoken</nt> -)* - <nt def="NT-S">S</nt> -? -')' </rhs> - <vc def="enum"/> - </prod> - </scrap> - -A <kw>NOTATION</kw> - attribute identifies a - <termref def="dt-notation">notation</termref> -, declared in the +<nt def="NT-S">S</nt>? +<nt def="NT-Name">Name</nt> +(<nt def="NT-S">S</nt>? '|' <nt def="NT-S">S</nt>? +<nt def="NT-Name">Name</nt>)* +<nt def="NT-S">S</nt>? ')' +</rhs><vc def="notatn"/></prod><prod id="NT-Enumeration"><lhs>Enumeration</lhs><rhs>'(' <nt def="NT-S">S</nt>? +<nt def="NT-Nmtoken">Nmtoken</nt> +(<nt def="NT-S">S</nt>? '|' +<nt def="NT-S">S</nt>? +<nt def="NT-Nmtoken">Nmtoken</nt>)* +<nt def="NT-S">S</nt>? +')'</rhs><vc def="enum"/></prod></scrap> +A <kw>NOTATION</kw> attribute identifies a +<termref def="dt-notation">notation</termref>, declared in the DTD with associated system and/or public identifiers, to be used in interpreting the element to which the attribute is attached. - </p> +</p> <vcnote id="notatn"> <head>Notation Attributes</head> <p> Values of this type must match -one of the - <titleref href="Notations">notation</titleref> - names included in +one of the <titleref href="Notations">notation</titleref> names included in the declaration; all notation names in the declaration must be declared. - </p> +</p> </vcnote> <vcnote id="enum"> <head>Enumeration</head> <p> Values of this type -must match one of the - <nt def="NT-Nmtoken">Nmtoken</nt> - tokens in the +must match one of the <nt def="NT-Nmtoken">Nmtoken</nt> tokens in the declaration. - </p> +</p> </vcnote> - <p> - <termref def="dt-interop">For interoperability,</termref> - the same - <nt def="NT-Nmtoken">Nmtoken</nt> - should not occur more than once in the + <p><termref def="dt-interop">For interoperability,</termref> the same +<nt def="NT-Nmtoken">Nmtoken</nt> should not occur more than once in the enumerated attribute types of a single element type. - </p> +</p> </div3> <div3 id="sec-attr-defaults"> <head>Attribute Defaults</head> - <p>An - <termref def="dt-attdecl">attribute declaration</termref> - provides + <p>An <termref def="dt-attdecl">attribute declaration</termref> provides information on whether the attribute's presence is required, and if not, how an XML processor should react if a declared attribute is absent in a document. - <scrap lang="ebnf"> - <head>Attribute Defaults</head> - <prodgroup pcw4="14" pcw5="11.5"> - <prod id="NT-DefaultDecl"> - <lhs>DefaultDecl</lhs> - <rhs>'#REQUIRED' -| '#IMPLIED' </rhs> - <rhs>| (('#FIXED' S)? - <nt def="NT-AttValue">AttValue</nt> -) </rhs> - <vc def="RequiredAttr"/> - <vc def="defattrvalid"/> - <wfc def="CleanAttrVals"/> - <vc def="FixedAttr"/> - </prod> - </prodgroup> - </scrap> - +<scrap lang="ebnf"><head>Attribute Defaults</head><prodgroup pcw4="14" pcw5="11.5"><prod id="NT-DefaultDecl"><lhs>DefaultDecl</lhs><rhs>'#REQUIRED' +| '#IMPLIED' </rhs><rhs>| (('#FIXED' S)? <nt def="NT-AttValue">AttValue</nt>)</rhs><vc def="RequiredAttr"/><vc def="defattrvalid"/><wfc def="CleanAttrVals"/><vc def="FixedAttr"/></prod></prodgroup></scrap> - </p> - <p>In an attribute declaration, - <kw>#REQUIRED</kw> - means that the -attribute must always be provided, <kw>#IMPLIED</kw> - that no default +</p> + <p>In an attribute declaration, <kw>#REQUIRED</kw> means that the +attribute must always be provided, <kw>#IMPLIED</kw> that no default value is provided. <!-- not any more!! <kw>#IMPLIED</kw> means that if the attribute is omitted @@ -3009,32 +1742,22 @@ from an element of this type, the XML processor must inform the application that no value was specified; no constraint is placed on the behavior of the application. --> - - <termdef id="dt-default" term="Attribute Default">If the +<termdef id="dt-default" term="Attribute Default">If the declaration -is neither - <kw>#REQUIRED</kw> - nor <kw>#IMPLIED</kw> -, then the - <nt def="NT-AttValue">AttValue</nt> - value contains the declared - <term>default</term> - value; the <kw>#FIXED</kw> - keyword states that +is neither <kw>#REQUIRED</kw> nor <kw>#IMPLIED</kw>, then the +<nt def="NT-AttValue">AttValue</nt> value contains the declared +<term>default</term> value; the <kw>#FIXED</kw> keyword states that the attribute must always have the default value. If a default value is declared, when an XML processor encounters an omitted attribute, it is to behave as though the attribute were present with -the declared default value. </termdef> - </p> +the declared default value.</termdef></p> <vcnote id="RequiredAttr"> <head>Required Attribute</head> - <p>If the default declaration is the keyword - <kw>#REQUIRED</kw> -, then + <p>If the default declaration is the keyword <kw>#REQUIRED</kw>, then the attribute must be specified for all elements of the type in the attribute-list declaration. - </p> +</p> </vcnote> <vcnote id="defattrvalid"> <head>Attribute Default Legal</head> @@ -3046,52 +1769,33 @@ default value must meet the lexical constraints of the declared attribute type. <vcnote id="FixedAttr"> <head>Fixed Attribute Default</head> <p>If an attribute has a default value declared with the - - <kw>#FIXED</kw> - keyword, instances of that attribute must +<kw>#FIXED</kw> keyword, instances of that attribute must match the default value. - </p> +</p> </vcnote> <p>Examples of attribute-list declarations: - - <eg><!ATTLIST termdef +<eg><!ATTLIST termdef id ID #REQUIRED name CDATA #IMPLIED> <!ATTLIST list type (bullets|ordered|glossary) "ordered"> <!ATTLIST form - method CDATA #FIXED "POST"></eg> - </p> + method CDATA #FIXED "POST"></eg></p> </div3> <div3 id="AVNormalize"> <head>Attribute-Value Normalization</head> <p>Before the value of an attribute is passed to the application or checked for validity, the XML processor must normalize it as follows: - - <ulist> - <item> - <p>a character reference is processed by appending the referenced -character to the attribute value</p> - </item> - <item> - <p>an entity reference is processed by recursively processing the -replacement text of the entity</p> - </item> - <item> - <p>a whitespace character (#x20, #xD, #xA, #x9) is processed by +<ulist><item><p>a character reference is processed by appending the referenced +character to the attribute value</p></item><item><p>an entity reference is processed by recursively processing the +replacement text of the entity</p></item><item><p>a whitespace character (#x20, #xD, #xA, #x9) is processed by appending #x20 to the normalized value, except that only a single #x20 is appended for a "#xD#xA" sequence that is part of an external parsed entity or the literal entity value of an internal parsed -entity</p> - </item> - <item> - <p>other characters are processed by appending them to the normalized -value</p> - </item> - </ulist> - - </p> +entity</p></item><item><p>other characters are processed by appending them to the normalized +value</p></item></ulist> +</p> <p>If the declared value is not CDATA, then the XML processor must further process the normalized attribute value by discarding any leading and trailing space (#x20) characters, and by replacing @@ -3100,111 +1804,58 @@ character.</p> <p> All attributes for which no declaration has been read should be treated by a non-validating parser as if declared - - <kw>CDATA</kw> -. - </p> +<kw>CDATA</kw>. +</p> </div3> </div2> <div2 id="sec-condition-sect"> <head>Conditional Sections</head> - <p> - <termdef id="dt-cond-section" term="conditional section"> - - <term>Conditional sections</term> - are portions of the - <termref def="dt-doctype">document type declaration external subset</termref> - + <p><termdef id="dt-cond-section" term="conditional section"> +<term>Conditional sections</term> are portions of the +<termref def="dt-doctype">document type declaration external subset</termref> which are included in, or excluded from, the logical structure of the DTD based on -the keyword which governs them. </termdef> - - <scrap lang="ebnf"> - <head>Conditional Section</head> - <prodgroup pcw2="9" pcw4="14.5"> - <prod id="NT-conditionalSect"> - <lhs>conditionalSect</lhs> - <rhs> - <nt def="NT-includeSect">includeSect</nt> - -| <nt def="NT-ignoreSect">ignoreSect</nt> - - </rhs> - </prod> - <prod id="NT-includeSect"> - <lhs>includeSect</lhs> - <rhs>'<![' S? 'INCLUDE' S? '[' - - - <nt def="NT-extSubsetDecl">extSubsetDecl</nt> +the keyword which governs them.</termdef> +<scrap lang="ebnf"><head>Conditional Section</head><prodgroup pcw2="9" pcw4="14.5"><prod id="NT-conditionalSect"><lhs>conditionalSect</lhs><rhs><nt def="NT-includeSect">includeSect</nt> +| <nt def="NT-ignoreSect">ignoreSect</nt> +</rhs></prod><prod id="NT-includeSect"><lhs>includeSect</lhs><rhs>'<![' S? 'INCLUDE' S? '[' +<nt def="NT-extSubsetDecl">extSubsetDecl</nt> ']]>' - </rhs> - </prod> - <prod id="NT-ignoreSect"> - <lhs>ignoreSect</lhs> - <rhs>'<![' S? 'IGNORE' S? '[' - - <nt def="NT-ignoreSectContents">ignoreSectContents</nt> -* -']]>' </rhs> - </prod> - <prod id="NT-ignoreSectContents"> - <lhs>ignoreSectContents</lhs> - <rhs> - <nt def="NT-Ignore">Ignore</nt> - -('<![' <nt def="NT-ignoreSectContents">ignoreSectContents</nt> - ']]>' - <nt def="NT-Ignore">Ignore</nt> -)* </rhs> - </prod> - <prod id="NT-Ignore"> - <lhs>Ignore</lhs> - <rhs> - <nt def="NT-Char">Char</nt> -* - -( <nt def="NT-Char">Char</nt> -* ('<![' | ']]>') - <nt def="NT-Char">Char</nt> -*) - </rhs> - </prod> - </prodgroup> - </scrap> - - </p> +</rhs></prod><prod id="NT-ignoreSect"><lhs>ignoreSect</lhs><rhs>'<![' S? 'IGNORE' S? '[' +<nt def="NT-ignoreSectContents">ignoreSectContents</nt>* +']]>'</rhs></prod><prod id="NT-ignoreSectContents"><lhs>ignoreSectContents</lhs><rhs><nt def="NT-Ignore">Ignore</nt> +('<![' <nt def="NT-ignoreSectContents">ignoreSectContents</nt> ']]>' +<nt def="NT-Ignore">Ignore</nt>)*</rhs></prod><prod id="NT-Ignore"><lhs>Ignore</lhs><rhs><nt def="NT-Char">Char</nt>* - +(<nt def="NT-Char">Char</nt>* ('<![' | ']]>') +<nt def="NT-Char">Char</nt>*) +</rhs></prod></prodgroup></scrap> +</p> <p>Like the internal and external DTD subsets, a conditional section may contain one or more complete declarations, comments, processing instructions, or nested conditional sections, intermingled with white space. </p> <p>If the keyword of the -conditional section is - <kw>INCLUDE</kw> -, then the contents of the conditional +conditional section is <kw>INCLUDE</kw>, then the contents of the conditional section are part of the DTD. If the keyword of the conditional -section is <kw>IGNORE</kw> -, then the contents of the conditional section are +section is <kw>IGNORE</kw>, then the contents of the conditional section are not logically part of the DTD. Note that for reliable parsing, the contents of even ignored conditional sections must be read in order to detect nested conditional sections and ensure that the end of the outermost (ignored) conditional section is properly detected. If a conditional section with a -keyword of <kw>INCLUDE</kw> - occurs within a larger conditional -section with a keyword of <kw>IGNORE</kw> -, both the outer and the -inner conditional sections are ignored. </p> +keyword of <kw>INCLUDE</kw> occurs within a larger conditional +section with a keyword of <kw>IGNORE</kw>, both the outer and the +inner conditional sections are ignored.</p> <p>If the keyword of the conditional section is a parameter-entity reference, the parameter entity must be replaced by its content before the processor decides whether to include or ignore the conditional section.</p> <p>An example: - - <eg><!ENTITY % draft 'INCLUDE' > +<eg><!ENTITY % draft 'INCLUDE' > <!ENTITY % final 'IGNORE' > <![%draft;[ @@ -3214,8 +1865,7 @@ include or ignore the conditional section.</p> <!ELEMENT book (title, body, supplements?)> ]]> </eg> - - </p> +</p> </div2> <!-- <div2 id='sec-pass-to-app'> @@ -3242,161 +1892,90 @@ values are specified. <!-- &Entities; --> <div1 id="sec-physical-struct"> <head>Physical Structures</head> - <p> - <termdef id="dt-entity" term="Entity">An XML document may consist + <p><termdef id="dt-entity" term="Entity">An XML document may consist of one or many storage units. These are called - - <term>entities</term> -; they all have <term>content</term> - and are all +<term>entities</term>; they all have <term>content</term> and are all (except for the document entity, see below, and -the <termref def="dt-doctype">external DTD subset</termref> -) -identified by <term>name</term> -. - </termdef> - +the <termref def="dt-doctype">external DTD subset</termref>) +identified by <term>name</term>. +</termdef> Each XML document has one entity -called the <termref def="dt-docent">document entity</termref> -, which serves -as the starting point for the <termref def="dt-xml-proc">XML -processor</termref> - and may contain the whole document. </p> +called the <termref def="dt-docent">document entity</termref>, which serves +as the starting point for the <termref def="dt-xml-proc">XML +processor</termref> and may contain the whole document.</p> <p>Entities may be either parsed or unparsed. - - <termdef id="dt-parsedent" term="Text Entity">A - <term>parsed entity's</term> - +<termdef id="dt-parsedent" term="Text Entity">A <term>parsed entity's</term> contents are referred to as its - <termref def="dt-repltext">replacement text</termref> -; -this <termref def="dt-text">text</termref> - is considered an -integral part of the document. </termdef> - </p> - <p> - <termdef id="dt-unparsed" term="Unparsed Entity">An - - <term>unparsed entity</term> - +<termref def="dt-repltext">replacement text</termref>; +this <termref def="dt-text">text</termref> is considered an +integral part of the document.</termdef></p> + <p><termdef id="dt-unparsed" term="Unparsed Entity">An +<term>unparsed entity</term> is a resource whose contents may or may not be - <termref def="dt-text">text</termref> -, and if text, may not be XML. +<termref def="dt-text">text</termref>, and if text, may not be XML. Each unparsed entity -has an associated <termref def="dt-notation">notation</termref> -, identified by name. +has an associated <termref def="dt-notation">notation</termref>, identified by name. Beyond a requirement that an XML processor make the identifiers for the entity and notation available to the application, -XML places no constraints on the contents of unparsed entities. </termdef> - - </p> +XML places no constraints on the contents of unparsed entities.</termdef> +</p> <p> Parsed entities are invoked by name using entity references; -unparsed entities by name, given in the value of - <kw>ENTITY</kw> - -or <kw>ENTITIES</kw> - -attributes. </p> - <p> - <termdef id="gen-entity" term="general entity"> - <term>General entities</term> - +unparsed entities by name, given in the value of <kw>ENTITY</kw> +or <kw>ENTITIES</kw> +attributes.</p> + <p><termdef id="gen-entity" term="general entity"><term>General entities</term> are entities for use within the document content. In this specification, general entities are sometimes referred -to with the unqualified term <emph>entity</emph> - when this leads -to no ambiguity. </termdef> - - <termdef id="dt-PE" term="Parameter entity">Parameter entities +to with the unqualified term <emph>entity</emph> when this leads +to no ambiguity.</termdef> +<termdef id="dt-PE" term="Parameter entity">Parameter entities are parsed entities for use within the DTD.</termdef> - These two types of entities use different forms of reference and are recognized in different contexts. Furthermore, they occupy different namespaces; a parameter entity and a general entity with the same name are two distinct entities. - </p> +</p> <div2 id="sec-references"> <head>Character and Entity References</head> - <p> - <termdef id="dt-charref" term="Character Reference"> -A - <term>character reference</term> - refers to a specific character in the + <p><termdef id="dt-charref" term="Character Reference"> +A <term>character reference</term> refers to a specific character in the ISO/IEC 10646 character set, for example one not directly accessible from available input devices. - <scrap lang="ebnf"> - <head>Character Reference</head> - <prod id="NT-CharRef"> - <lhs>CharRef</lhs> - <rhs>'&#' [0-9]+ ';' </rhs> - <rhs>| '&hcro;' [0-9a-fA-F]+ ';'</rhs> - <wfc def="wf-Legalchar"/> - </prod> - </scrap> - - <wfcnote id="wf-Legalchar"> - <head>Legal Character</head> - <p>Characters referred to using character references must +<scrap lang="ebnf"><head>Character Reference</head><prod id="NT-CharRef"><lhs>CharRef</lhs><rhs>'&#' [0-9]+ ';' </rhs><rhs>| '&hcro;' [0-9a-fA-F]+ ';'</rhs><wfc def="wf-Legalchar"/></prod></scrap> +<wfcnote id="wf-Legalchar"><head>Legal Character</head><p>Characters referred to using character references must match the production for - - <termref def="NT-Char">Char</termref> -. </p> - </wfcnote> - -If the character reference begins with " <code>&#x</code> -", the digits and -letters up to the terminating <code>;</code> - provide a hexadecimal +<termref def="NT-Char">Char</termref>.</p></wfcnote> +If the character reference begins with "<code>&#x</code>", the digits and +letters up to the terminating <code>;</code> provide a hexadecimal representation of the character's code point in ISO/IEC 10646. -If it begins just with " <code>&#</code> -", the digits up to the terminating - <code>;</code> - provide a decimal representation of the character's +If it begins just with "<code>&#</code>", the digits up to the terminating +<code>;</code> provide a decimal representation of the character's code point. - </termdef> - - </p> - <p> - <termdef id="dt-entref" term="Entity Reference">An - <term>entity -reference</term> - refers to the content of a named entity. </termdef> - - <termdef id="dt-GERef" term="General Entity Reference">References to +</termdef> +</p> + <p><termdef id="dt-entref" term="Entity Reference">An <term>entity +reference</term> refers to the content of a named entity.</termdef> +<termdef id="dt-GERef" term="General Entity Reference">References to parsed general entities -use ampersand ( - <code>&</code> -) and semicolon ( <code>;</code> -) as -delimiters. </termdef> - - <termdef id="dt-PERef" term="Parameter-entity reference"> - - <term>Parameter-entity references</term> - use percent-sign ( <code>%</code> -) and +use ampersand (<code>&</code>) and semicolon (<code>;</code>) as +delimiters.</termdef> +<termdef id="dt-PERef" term="Parameter-entity reference"> +<term>Parameter-entity references</term> use percent-sign (<code>%</code>) and semicolon -( <code>;</code> -) as delimiters. </termdef> - - </p> +(<code>;</code>) as delimiters.</termdef> +</p> <scrap lang="ebnf"> <head>Entity Reference</head> <prod id="NT-Reference"> <lhs>Reference</lhs> - <rhs> - <nt def="NT-EntityRef">EntityRef</nt> - -| <nt def="NT-CharRef">CharRef</nt> - </rhs> + <rhs><nt def="NT-EntityRef">EntityRef</nt> +| <nt def="NT-CharRef">CharRef</nt></rhs> </prod> <prod id="NT-EntityRef"> <lhs>EntityRef</lhs> - <rhs>'&' - <nt def="NT-Name">Name</nt> - ';' </rhs> + <rhs>'&' <nt def="NT-Name">Name</nt> ';'</rhs> <wfc def="wf-entdeclared"/> <vc def="vc-entdeclared"/> <wfc def="textent"/> @@ -3404,9 +1983,7 @@ semicolon </prod> <prod id="NT-PEReference"> <lhs>PEReference</lhs> - <rhs>'%' - <nt def="NT-Name">Name</nt> - ';' </rhs> + <rhs>'%' <nt def="NT-Name">Name</nt> ';'</rhs> <vc def="vc-entdeclared"/> <wfc def="norecursion"/> <wfc def="indtd"/> @@ -3416,64 +1993,45 @@ semicolon <head>Entity Declared</head> <p>In a document without any DTD, a document with only an internal DTD subset which contains no parameter entity references, or a document with -" - <code>standalone='yes'</code> -", -the <nt def="NT-Name">Name</nt> - given in the entity reference must - <termref def="dt-match">match</termref> - that in an - <titleref href="sec-entity-decl">entity declaration</titleref> -, except that +"<code>standalone='yes'</code>", +the <nt def="NT-Name">Name</nt> given in the entity reference must +<termref def="dt-match">match</termref> that in an +<titleref href="sec-entity-decl">entity declaration</titleref>, except that well-formed documents need not declare any of the following entities: &magicents;. The declaration of a parameter entity must precede any reference to it. Similarly, the declaration of a general entity must precede any reference to it which appears in a default value in an attribute-list -declaration. </p> +declaration.</p> <p>Note that if entities are declared in the external subset or in external parameter entities, a non-validating processor is - - <titleref href="include-if-valid">not obligated to</titleref> - read +<titleref href="include-if-valid">not obligated to</titleref> read and process their declarations; for such documents, the rule that an entity must be declared is a well-formedness constraint only -if <titleref href="sec-rmd">standalone='yes'</titleref> -. </p> +if <titleref href="sec-rmd">standalone='yes'</titleref>.</p> </wfcnote> <vcnote id="vc-entdeclared"> <head>Entity Declared</head> <p>In a document with an external subset or external parameter -entities with " - <code>standalone='no'</code> -", -the <nt def="NT-Name">Name</nt> - given in the entity reference must <termref def="dt-match">match</termref> - that in an - <titleref href="sec-entity-decl">entity declaration</titleref> -. +entities with "<code>standalone='no'</code>", +the <nt def="NT-Name">Name</nt> given in the entity reference must <termref def="dt-match">match</termref> that in an +<titleref href="sec-entity-decl">entity declaration</titleref>. For interoperability, valid documents should declare the entities &magicents;, in the form -specified in <specref ref="sec-predefined-ent"/> -. +specified in <specref ref="sec-predefined-ent"/>. The declaration of a parameter entity must precede any reference to it. Similarly, the declaration of a general entity must precede any reference to it which appears in a default value in an attribute-list -declaration. </p> +declaration.</p> </vcnote> <!-- FINAL EDIT: is this duplication too clumsy? --> <wfcnote id="textent"> <head>Parsed Entity</head> <p> -An entity reference must not contain the name of an - <termref def="dt-unparsed">unparsed entity</termref> -. Unparsed entities may be referred -to only in <termref def="dt-attrval">attribute values</termref> - declared to -be of type <kw>ENTITY</kw> - or <kw>ENTITIES</kw> -. - </p> +An entity reference must not contain the name of an <termref def="dt-unparsed">unparsed entity</termref>. Unparsed entities may be referred +to only in <termref def="dt-attrval">attribute values</termref> declared to +be of type <kw>ENTITY</kw> or <kw>ENTITIES</kw>. +</p> </wfcnote> <wfcnote id="norecursion"> <head>No Recursion</head> @@ -3486,212 +2044,93 @@ either directly or indirectly. <head>In DTD</head> <p> Parameter-entity references may only appear in the - - <termref def="dt-doctype">DTD</termref> -. - </p> +<termref def="dt-doctype">DTD</termref>. +</p> </wfcnote> <p>Examples of character and entity references: - - <eg>Type <key>less-than</key> (&hcro;3C;) to save options. +<eg>Type <key>less-than</key> (&hcro;3C;) to save options. This document was prepared on &docdate; and -is classified &security-level;.</eg> - </p> +is classified &security-level;.</eg></p> <p>Example of a parameter-entity reference: - - <eg> -<![CDATA[<!-- declare the parameter entity "ISOLat2"... --> +<eg><![CDATA[<!-- declare the parameter entity "ISOLat2"... --> <!ENTITY % ISOLat2 SYSTEM "http://www.xml.com/iso/isolat2-xml.entities" > <!-- ... now reference it. --> -%ISOLat2;]]> </eg> - </p> +%ISOLat2;]]></eg></p> </div2> <div2 id="sec-entity-decl"> <head>Entity Declarations</head> - <p> - <termdef id="dt-entdecl" term="entity declaration"> + <p><termdef id="dt-entdecl" term="entity declaration"> Entities are declared thus: - - <scrap lang="ebnf"> - <head>Entity Declaration</head> - <prodgroup pcw2="5" pcw4="18.5"> - <prod id="NT-EntityDecl"> - <lhs>EntityDecl</lhs> - <rhs> - <nt def="NT-GEDecl">GEDecl</nt> -<!--</rhs><com>General entities</com> -<rhs>--> - | <nt def="NT-PEDecl">PEDecl</nt> - </rhs> -<!--<com>Parameter entities</com>--> - </prod> - <prod id="NT-GEDecl"> - <lhs>GEDecl</lhs> - <rhs>'<!ENTITY' - <nt def="NT-S">S</nt> - <nt def="NT-Name">Name</nt> - - <nt def="NT-S">S</nt> - <nt def="NT-EntityDef">EntityDef</nt> - - <nt def="NT-S">S</nt> -? '>' </rhs> - </prod> - <prod id="NT-PEDecl"> - <lhs>PEDecl</lhs> - <rhs>'<!ENTITY' - <nt def="NT-S">S</nt> - '%' <nt def="NT-S">S</nt> - - <nt def="NT-Name">Name</nt> - <nt def="NT-S">S</nt> - - <nt def="NT-PEDef">PEDef</nt> - <nt def="NT-S">S</nt> -? '>' </rhs> -<!--<com>Parameter entities</com>--> - </prod> - <prod id="NT-EntityDef"> - <lhs>EntityDef</lhs> - <rhs> - <nt def="NT-EntityValue">EntityValue</nt> - +<scrap lang="ebnf"><head>Entity Declaration</head><prodgroup pcw2="5" pcw4="18.5"><prod id="NT-EntityDecl"><lhs>EntityDecl</lhs><rhs><nt def="NT-GEDecl">GEDecl</nt><!--</rhs><com>General entities</com> +<rhs>--> | <nt def="NT-PEDecl">PEDecl</nt></rhs><!--<com>Parameter entities</com>--></prod><prod id="NT-GEDecl"><lhs>GEDecl</lhs><rhs>'<!ENTITY' <nt def="NT-S">S</nt> <nt def="NT-Name">Name</nt> +<nt def="NT-S">S</nt> <nt def="NT-EntityDef">EntityDef</nt> +<nt def="NT-S">S</nt>? '>'</rhs></prod><prod id="NT-PEDecl"><lhs>PEDecl</lhs><rhs>'<!ENTITY' <nt def="NT-S">S</nt> '%' <nt def="NT-S">S</nt> +<nt def="NT-Name">Name</nt> <nt def="NT-S">S</nt> +<nt def="NT-PEDef">PEDef</nt> <nt def="NT-S">S</nt>? '>'</rhs><!--<com>Parameter entities</com>--></prod><prod id="NT-EntityDef"><lhs>EntityDef</lhs><rhs><nt def="NT-EntityValue">EntityValue</nt> <!--</rhs> -<rhs>--> -| ( <nt def="NT-ExternalID">ExternalID</nt> - - <nt def="NT-NDataDecl">NDataDecl</nt> -?) </rhs> -<!-- <nt def='NT-ExternalDef'>ExternalDef</nt></rhs> --> - </prod> -<!-- FINAL EDIT: what happened to WFs here? --> - <prod id="NT-PEDef"> - <lhs>PEDef</lhs> - <rhs> - <nt def="NT-EntityValue">EntityValue</nt> - -| <nt def="NT-ExternalID">ExternalID</nt> - </rhs> - </prod> - </prodgroup> - </scrap> - -The <nt def="NT-Name">Name</nt> - identifies the entity in an - <termref def="dt-entref">entity reference</termref> - or, in the case of an -unparsed entity, in the value of an <kw>ENTITY</kw> - or <kw>ENTITIES</kw> - +<rhs>-->| (<nt def="NT-ExternalID">ExternalID</nt> +<nt def="NT-NDataDecl">NDataDecl</nt>?)</rhs><!-- <nt def='NT-ExternalDef'>ExternalDef</nt></rhs> --></prod><!-- FINAL EDIT: what happened to WFs here? --><prod id="NT-PEDef"><lhs>PEDef</lhs><rhs><nt def="NT-EntityValue">EntityValue</nt> +| <nt def="NT-ExternalID">ExternalID</nt></rhs></prod></prodgroup></scrap> +The <nt def="NT-Name">Name</nt> identifies the entity in an +<termref def="dt-entref">entity reference</termref> or, in the case of an +unparsed entity, in the value of an <kw>ENTITY</kw> or <kw>ENTITIES</kw> attribute. If the same entity is declared more than once, the first declaration encountered is binding; at user option, an XML processor may issue a -warning if entities are declared multiple times. </termdef> - - </p> +warning if entities are declared multiple times.</termdef> +</p> <div3 id="sec-internal-ent"> <head>Internal Entities</head> - <p> - <termdef id="dt-internent" term="Internal Entity Replacement Text">If + <p><termdef id="dt-internent" term="Internal Entity Replacement Text">If the entity definition is an - - <nt def="NT-EntityValue">EntityValue</nt> -, -the defined entity is called an <term>internal entity</term> -. +<nt def="NT-EntityValue">EntityValue</nt>, +the defined entity is called an <term>internal entity</term>. There is no separate physical storage object, and the content of the entity is given in the -declaration. </termdef> - +declaration. </termdef> Note that some processing of entity and character references in the - <termref def="dt-litentval">literal entity value</termref> - may be required to -produce the correct <termref def="dt-repltext">replacement -text</termref> -: see <specref ref="intern-replacement"/> -. - </p> - <p>An internal entity is a - <termref def="dt-parsedent">parsed -entity</termref> -. </p> +<termref def="dt-litentval">literal entity value</termref> may be required to +produce the correct <termref def="dt-repltext">replacement +text</termref>: see <specref ref="intern-replacement"/>. +</p> + <p>An internal entity is a <termref def="dt-parsedent">parsed +entity</termref>.</p> <p>Example of an internal entity declaration: - - <eg><!ENTITY Pub-Status "This is a pre-release of the - specification."></eg> - </p> +<eg><!ENTITY Pub-Status "This is a pre-release of the + specification."></eg></p> </div3> <div3 id="sec-external-ent"> <head>External Entities</head> <p> <termdef id="dt-extent" term="External Entity">If the entity is not -internal, it is an - <term>external -entity</term> -, declared as follows: - <scrap lang="ebnf"> - <head>External Entity Declaration</head> -<!-- +internal, it is an <term>external +entity</term>, declared as follows: +<scrap lang="ebnf"><head>External Entity Declaration</head><!-- <prod id='NT-ExternalDef'><lhs>ExternalDef</lhs> -<rhs></prod> --> - <prod id="NT-ExternalID"> - <lhs>ExternalID</lhs> - <rhs>'SYSTEM' - <nt def="NT-S">S</nt> - - <nt def="NT-SystemLiteral">SystemLiteral</nt> - </rhs> - <rhs>| 'PUBLIC' - <nt def="NT-S">S</nt> - - <nt def="NT-PubidLiteral">PubidLiteral</nt> - - <nt def="NT-S">S</nt> - - <nt def="NT-SystemLiteral">SystemLiteral</nt> - - </rhs> - </prod> - <prod id="NT-NDataDecl"> - <lhs>NDataDecl</lhs> - <rhs> - <nt def="NT-S">S</nt> - 'NDATA' <nt def="NT-S">S</nt> - - <nt def="NT-Name">Name</nt> - </rhs> - <vc def="not-declared"/> - </prod> - </scrap> - -If the <nt def="NT-NDataDecl">NDataDecl</nt> - is present, this is a -general <termref def="dt-unparsed">unparsed -entity</termref> -; otherwise it is a parsed entity. </termdef> +<rhs></prod> --><prod id="NT-ExternalID"><lhs>ExternalID</lhs><rhs>'SYSTEM' <nt def="NT-S">S</nt> +<nt def="NT-SystemLiteral">SystemLiteral</nt></rhs><rhs>| 'PUBLIC' <nt def="NT-S">S</nt> +<nt def="NT-PubidLiteral">PubidLiteral</nt> +<nt def="NT-S">S</nt> +<nt def="NT-SystemLiteral">SystemLiteral</nt> +</rhs></prod><prod id="NT-NDataDecl"><lhs>NDataDecl</lhs><rhs><nt def="NT-S">S</nt> 'NDATA' <nt def="NT-S">S</nt> +<nt def="NT-Name">Name</nt></rhs><vc def="not-declared"/></prod></scrap> +If the <nt def="NT-NDataDecl">NDataDecl</nt> is present, this is a +general <termref def="dt-unparsed">unparsed +entity</termref>; otherwise it is a parsed entity.</termdef> </p> <vcnote id="not-declared"> <head>Notation Declared</head> <p> -The - <nt def="NT-Name">Name</nt> - must match the declared name of a - <termref def="dt-notation">notation</termref> -. - </p> +The <nt def="NT-Name">Name</nt> must match the declared name of a +<termref def="dt-notation">notation</termref>. +</p> </vcnote> - <p> - <termdef id="dt-sysid" term="System Identifier">The - - <nt def="NT-SystemLiteral">SystemLiteral</nt> - -is called the entity's <term>system identifier</term> -. It is a URI, -which may be used to retrieve the entity. </termdef> - -Note that the hash mark ( <code>#</code> -) and fragment identifier + <p><termdef id="dt-sysid" term="System Identifier">The +<nt def="NT-SystemLiteral">SystemLiteral</nt> +is called the entity's <term>system identifier</term>. It is a URI, +which may be used to retrieve the entity.</termdef> +Note that the hash mark (<code>#</code>) and fragment identifier frequently used with URIs are not, formally, part of the URI itself; an XML processor may signal an error if a fragment identifier is given as part of a system identifier. @@ -3701,70 +2140,46 @@ DTD, or a processing instruction defined by a particular application specification), relative URIs are relative to the location of the resource within which the entity declaration occurs. A URI might thus be relative to the - <termref def="dt-docent">document entity</termref> -, to the entity -containing the <termref def="dt-doctype">external DTD subset</termref> -, -or to some other <termref def="dt-extent">external parameter entity</termref> -. - </p> +<termref def="dt-docent">document entity</termref>, to the entity +containing the <termref def="dt-doctype">external DTD subset</termref>, +or to some other <termref def="dt-extent">external parameter entity</termref>. +</p> <p>An XML processor should handle a non-ASCII character in a URI by representing the character in UTF-8 as one or more bytes, and then escaping these bytes with the URI escaping mechanism (i.e., by converting each byte to %HH, where HH is the hexadecimal notation of the byte value).</p> - <p> - <termdef id="dt-pubid" term="Public identifier"> + <p><termdef id="dt-pubid" term="Public identifier"> In addition to a system identifier, an external identifier may -include a - <term>public identifier</term> -. </termdef> - +include a <term>public identifier</term>.</termdef> An XML processor attempting to retrieve the entity's content may use the public identifier to try to generate an alternative URI. If the processor is unable to do so, it must use the URI specified in the system literal. Before a match is attempted, all strings of white space in the public identifier must be normalized to single space characters (#x20), -and leading and trailing white space must be removed. </p> +and leading and trailing white space must be removed.</p> <p>Examples of external entity declarations: - - <eg><!ENTITY open-hatch +<eg><!ENTITY open-hatch SYSTEM "http://www.textuality.com/boilerplate/OpenHatch.xml"> <!ENTITY open-hatch PUBLIC "-//Textuality//TEXT Standard open-hatch boilerplate//EN" "http://www.textuality.com/boilerplate/OpenHatch.xml"> <!ENTITY hatch-pic SYSTEM "../grafix/OpenHatch.gif" - NDATA gif ></eg> - </p> + NDATA gif ></eg></p> </div3> </div2> <div2 id="TextEntities"> <head>Parsed Entities</head> <div3 id="sec-TextDecl"> <head>The Text Declaration</head> - <p>External parsed entities may each begin with a - <term>text -declaration</term> -. - <scrap lang="ebnf"> - <head>Text Declaration</head> - <prodgroup pcw4="12.5" pcw5="13"> - <prod id="NT-TextDecl"> - <lhs>TextDecl</lhs> - <rhs>&xmlpio; - - <nt def="NT-VersionInfo">VersionInfo</nt> -? - <nt def="NT-EncodingDecl">EncodingDecl</nt> - - <nt def="NT-S">S</nt> -? &pic; </rhs> - </prod> - </prodgroup> - </scrap> - - </p> + <p>External parsed entities may each begin with a <term>text +declaration</term>. +<scrap lang="ebnf"><head>Text Declaration</head><prodgroup pcw4="12.5" pcw5="13"><prod id="NT-TextDecl"><lhs>TextDecl</lhs><rhs>&xmlpio; +<nt def="NT-VersionInfo">VersionInfo</nt>? +<nt def="NT-EncodingDecl">EncodingDecl</nt> +<nt def="NT-S">S</nt>? &pic;</rhs></prod></prodgroup></scrap> +</p> <p>The text declaration must be provided literally, not by reference to a parsed entity. No text declaration may appear at any position other than the beginning of @@ -3773,64 +2188,33 @@ an external parsed entity.</p> <div3 id="wf-entities"> <head>Well-Formed Parsed Entities</head> <p>The document entity is well-formed if it matches the production labeled - - <nt def="NT-document">document</nt> -. +<nt def="NT-document">document</nt>. An external general parsed entity is well-formed if it matches the production labeled - <nt def="NT-extParsedEnt">extParsedEnt</nt> -. +<nt def="NT-extParsedEnt">extParsedEnt</nt>. An external parameter entity is well-formed if it matches the production labeled - <nt def="NT-extPE">extPE</nt> -. - <scrap lang="ebnf"> - <head>Well-Formed External Parsed Entity</head> - <prod id="NT-extParsedEnt"> - <lhs>extParsedEnt</lhs> - <rhs> - <nt def="NT-TextDecl">TextDecl</nt> -? - <nt def="NT-content">content</nt> - </rhs> - </prod> - <prod id="NT-extPE"> - <lhs>extPE</lhs> - <rhs> - <nt def="NT-TextDecl">TextDecl</nt> -? - <nt def="NT-extSubsetDecl">extSubsetDecl</nt> - </rhs> - </prod> - </scrap> - +<nt def="NT-extPE">extPE</nt>. +<scrap lang="ebnf"><head>Well-Formed External Parsed Entity</head><prod id="NT-extParsedEnt"><lhs>extParsedEnt</lhs><rhs><nt def="NT-TextDecl">TextDecl</nt>? +<nt def="NT-content">content</nt></rhs></prod><prod id="NT-extPE"><lhs>extPE</lhs><rhs><nt def="NT-TextDecl">TextDecl</nt>? +<nt def="NT-extSubsetDecl">extSubsetDecl</nt></rhs></prod></scrap> An internal general parsed entity is well-formed if its replacement text matches the production labeled - <nt def="NT-content">content</nt> -. +<nt def="NT-content">content</nt>. All internal parameter entities are well-formed by definition. - </p> +</p> <p>A consequence of well-formedness in entities is that the logical and physical structures in an XML document are properly nested; no - - <termref def="dt-stag">start-tag</termref> -, - <termref def="dt-etag">end-tag</termref> -, - <termref def="dt-empty">empty-element tag</termref> -, - <termref def="dt-element">element</termref> -, - <termref def="dt-comment">comment</termref> -, - <termref def="dt-pi">processing instruction</termref> -, - <termref def="dt-charref">character -reference</termref> -, or - <termref def="dt-entref">entity reference</termref> - -can begin in one entity and end in another. </p> +<termref def="dt-stag">start-tag</termref>, +<termref def="dt-etag">end-tag</termref>, +<termref def="dt-empty">empty-element tag</termref>, +<termref def="dt-element">element</termref>, +<termref def="dt-comment">comment</termref>, +<termref def="dt-pi">processing instruction</termref>, +<termref def="dt-charref">character +reference</termref>, or +<termref def="dt-entref">entity reference</termref> +can begin in one entity and end in another.</p> </div3> <div3 id="charencoding"> <head>Character Encoding in Entities</head> @@ -3851,83 +2235,46 @@ the UTF-8 and UTF-16 encodings, it is recognized that other encodings are used around the world, and it may be desired for XML processors to read entities that use them. Parsed entities which are stored in an encoding other than -UTF-8 or UTF-16 must begin with a - <titleref href="TextDecl">text -declaration</titleref> - containing an encoding declaration: - <scrap lang="ebnf"> - <head>Encoding Declaration</head> - <prod id="NT-EncodingDecl"> - <lhs>EncodingDecl</lhs> - <rhs> - <nt def="NT-S">S</nt> - -'encoding' <nt def="NT-Eq">Eq</nt> - -('"' <nt def="NT-EncName">EncName</nt> - '"' | -"'" <nt def="NT-EncName">EncName</nt> - "'" ) - </rhs> - </prod> - <prod id="NT-EncName"> - <lhs>EncName</lhs> - <rhs>[A-Za-z] ([A-Za-z0-9._] | '-')*</rhs> - <com>Encoding name contains only Latin characters</com> - </prod> - </scrap> - -In the <termref def="dt-docent">document entity</termref> -, the encoding -declaration is part of the <termref def="dt-xmldecl">XML declaration</termref> -. -The <nt def="NT-EncName">EncName</nt> - is the name of the encoding used. - </p> +UTF-8 or UTF-16 must begin with a <titleref href="TextDecl">text +declaration</titleref> containing an encoding declaration: +<scrap lang="ebnf"><head>Encoding Declaration</head><prod id="NT-EncodingDecl"><lhs>EncodingDecl</lhs><rhs><nt def="NT-S">S</nt> +'encoding' <nt def="NT-Eq">Eq</nt> +('"' <nt def="NT-EncName">EncName</nt> '"' | +"'" <nt def="NT-EncName">EncName</nt> "'" ) +</rhs></prod><prod id="NT-EncName"><lhs>EncName</lhs><rhs>[A-Za-z] ([A-Za-z0-9._] | '-')*</rhs><com>Encoding name contains only Latin characters</com></prod></scrap> +In the <termref def="dt-docent">document entity</termref>, the encoding +declaration is part of the <termref def="dt-xmldecl">XML declaration</termref>. +The <nt def="NT-EncName">EncName</nt> is the name of the encoding used. +</p> <!-- FINAL EDIT: check name of IANA and charset names --> <p>In an encoding declaration, the values -" - <code>UTF-8</code> -", -" <code>UTF-16</code> -", -" <code>ISO-10646-UCS-2</code> -", and -" <code>ISO-10646-UCS-4</code> -" should be +"<code>UTF-8</code>", +"<code>UTF-16</code>", +"<code>ISO-10646-UCS-2</code>", and +"<code>ISO-10646-UCS-4</code>" should be used for the various encodings and transformations of Unicode / ISO/IEC 10646, the values -" <code>ISO-8859-1</code> -", -" <code>ISO-8859-2</code> -", ... -" <code>ISO-8859-9</code> -" should be used for the parts of ISO 8859, and +"<code>ISO-8859-1</code>", +"<code>ISO-8859-2</code>", ... +"<code>ISO-8859-9</code>" should be used for the parts of ISO 8859, and the values -" <code>ISO-2022-JP</code> -", -" <code>Shift_JIS</code> -", and -" <code>EUC-JP</code> -" +"<code>ISO-2022-JP</code>", +"<code>Shift_JIS</code>", and +"<code>EUC-JP</code>" should be used for the various encoded forms of JIS X-0208-1997. XML processors may recognize other encodings; it is recommended that -character encodings registered (as <emph>charset</emph> -s) +character encodings registered (as <emph>charset</emph>s) with the Internet Assigned Numbers -Authority <bibref ref="IANA"/> -, other than those just listed, should be +Authority <bibref ref="IANA"/>, other than those just listed, should be referred to using their registered names. Note that these registered names are defined to be case-insensitive, so processors wishing to match against them should do so in a case-insensitive -way. </p> +way.</p> <p>In the absence of information provided by an external transport protocol (e.g. HTTP or MIME), -it is an - <termref def="dt-error">error</termref> - for an entity including +it is an <termref def="dt-error">error</termref> for an entity including an encoding declaration to be presented to the XML processor in an encoding other than that named in the declaration, for an encoding declaration to occur other than at the beginning @@ -3936,97 +2283,40 @@ an entity which begins with neither a Byte Order Mark nor an encoding declaration to use an encoding other than UTF-8. Note that since ASCII is a subset of UTF-8, ordinary ASCII entities do not strictly need -an encoding declaration. </p> - <p>It is a - <termref def="dt-fatal">fatal error</termref> - when an XML processor -encounters an entity with an encoding that it is unable to process. </p> +an encoding declaration.</p> + <p>It is a <termref def="dt-fatal">fatal error</termref> when an XML processor +encounters an entity with an encoding that it is unable to process.</p> <p>Examples of encoding declarations: - - <eg><?xml encoding='UTF-8'?> -<?xml encoding='EUC-JP'?></eg> - </p> +<eg><?xml encoding='UTF-8'?> +<?xml encoding='EUC-JP'?></eg></p> </div3> </div2> <div2 id="entproc"> <head>XML Processor Treatment of Entities and References</head> <p>The table below summarizes the contexts in which character references, entity references, and invocations of unparsed entities might appear and the -required behavior of an - <termref def="dt-xml-proc">XML processor</termref> - in +required behavior of an <termref def="dt-xml-proc">XML processor</termref> in each case. The labels in the leftmost column describe the recognition context: - <glist> - <gitem> - <label>Reference in Content</label> - <def> - <p>as a reference -anywhere after the - <termref def="dt-stag">start-tag</termref> - and -before the <termref def="dt-etag">end-tag</termref> - of an element; corresponds -to the nonterminal <nt def="NT-content">content</nt> -. </p> - </def> - </gitem> - <gitem> - <label>Reference in Attribute Value</label> - <def> - <p>as a reference within either the value of an attribute in a - - <termref def="dt-stag">start-tag</termref> -, or a default -value in an <termref def="dt-attdecl">attribute declaration</termref> -; +<glist><gitem><label>Reference in Content</label><def><p>as a reference +anywhere after the <termref def="dt-stag">start-tag</termref> and +before the <termref def="dt-etag">end-tag</termref> of an element; corresponds +to the nonterminal <nt def="NT-content">content</nt>.</p></def></gitem><gitem><label>Reference in Attribute Value</label><def><p>as a reference within either the value of an attribute in a +<termref def="dt-stag">start-tag</termref>, or a default +value in an <termref def="dt-attdecl">attribute declaration</termref>; corresponds to the nonterminal - <nt def="NT-AttValue">AttValue</nt> -. </p> - </def> - </gitem> - <gitem> - <label>Occurs as Attribute Value</label> - <def> - <p>as a - <nt def="NT-Name">Name</nt> -, not a reference, appearing either as +<nt def="NT-AttValue">AttValue</nt>.</p></def></gitem><gitem><label>Occurs as Attribute Value</label><def><p>as a <nt def="NT-Name">Name</nt>, not a reference, appearing either as the value of an -attribute which has been declared as type <kw>ENTITY</kw> -, or as one of +attribute which has been declared as type <kw>ENTITY</kw>, or as one of the space-separated tokens in the value of an attribute which has been -declared as type <kw>ENTITIES</kw> -. </p> - </def> - </gitem> - <gitem> - <label>Reference in Entity Value</label> - <def> - <p>as a reference +declared as type <kw>ENTITIES</kw>.</p></def></gitem><gitem><label>Reference in Entity Value</label><def><p>as a reference within a parameter or internal entity's - - <termref def="dt-litentval">literal entity value</termref> - in +<termref def="dt-litentval">literal entity value</termref> in the entity's declaration; corresponds to the nonterminal - <nt def="NT-EntityValue">EntityValue</nt> -. </p> - </def> - </gitem> - <gitem> - <label>Reference in DTD</label> - <def> - <p>as a reference within either the internal or external subsets of the - - <termref def="dt-doctype">DTD</termref> -, but outside -of an <nt def="NT-EntityValue">EntityValue</nt> - or - <nt def="NT-AttValue">AttValue</nt> -. </p> - </def> - </gitem> - </glist> - </p> +<nt def="NT-EntityValue">EntityValue</nt>.</p></def></gitem><gitem><label>Reference in DTD</label><def><p>as a reference within either the internal or external subsets of the +<termref def="dt-doctype">DTD</termref>, but outside +of an <nt def="NT-EntityValue">EntityValue</nt> or +<nt def="NT-AttValue">AttValue</nt>.</p></def></gitem></glist></p> <htable border="1" cellpadding="7" align="center"> <htbody> <tr> @@ -4141,65 +2431,50 @@ in DTD</td> </htable> <div3 id="not-recognized"> <head>Not Recognized</head> - <p>Outside the DTD, the - <code>%</code> - character has no + <p>Outside the DTD, the <code>%</code> character has no special significance; thus, what would be parameter entity references in the -DTD are not recognized as markup in <nt def="NT-content">content</nt> -. +DTD are not recognized as markup in <nt def="NT-content">content</nt>. Similarly, the names of unparsed entities are not recognized except when they appear in the value of an appropriately declared attribute. - </p> +</p> </div3> <div3 id="included"> <head>Included</head> <p> <termdef id="dt-include" term="Include">An entity is - - <term>included</term> - when its - <termref def="dt-repltext">replacement text</termref> - is retrieved +<term>included</term> when its +<termref def="dt-repltext">replacement text</termref> is retrieved and processed, in place of the reference itself, as though it were part of the document at the location the reference was recognized. The replacement text may contain both - <termref def="dt-chardata">character data</termref> - -and (except for parameter entities) <termref def="dt-markup">markup</termref> -, +<termref def="dt-chardata">character data</termref> +and (except for parameter entities) <termref def="dt-markup">markup</termref>, which must be recognized in the usual way, except that the replacement text of entities used to escape markup delimiters (the entities &magicents;) is always treated as -data. (The string " <code>AT&amp;T;</code> -" expands to -" <code>AT&T;</code> -" and the remaining ampersand is not recognized +data. (The string "<code>AT&amp;T;</code>" expands to +"<code>AT&T;</code>" and the remaining ampersand is not recognized as an entity-reference delimiter.) -A character reference is <term>included</term> - when the indicated +A character reference is <term>included</term> when the indicated character is processed in place of the reference itself. - </termdef> +</termdef> </p> </div3> <div3 id="include-if-valid"> <head>Included If Validating</head> <p>When an XML processor recognizes a reference to a parsed entity, in order -to - <termref def="dt-valid">validate</termref> - +to <termref def="dt-valid">validate</termref> the document, the processor must - <termref def="dt-include">include</termref> - its +<termref def="dt-include">include</termref> its replacement text. If the entity is external, and the processor is not attempting to validate the XML document, the -processor <termref def="dt-may">may</termref> -, but need not, +processor <termref def="dt-may">may</termref>, but need not, include the entity's replacement text. If a non-validating parser does not include the replacement text, it must inform the application that it recognized, but did not -read, the entity. </p> +read, the entity.</p> <p>This rule is based on the recognition that the automatic inclusion provided by the SGML and XML entity mechanism, primarily designed to support modularity in authoring, is not necessarily @@ -4212,98 +2487,62 @@ presence and retrieve it for display only on demand. <div3 id="forbidden"> <head>Forbidden</head> <p>The following are forbidden, and constitute - - <termref def="dt-fatal">fatal</termref> - errors: - <ulist> - <item> - <p>the appearance of a reference to an - - <termref def="dt-unparsed">unparsed entity</termref> -. - </p> - </item> - <item> - <p>the appearance of any character or general-entity reference in the -DTD except within an - <nt def="NT-EntityValue">EntityValue</nt> - or - <nt def="NT-AttValue">AttValue</nt> -. </p> - </item> - <item> - <p>a reference to an external entity in an attribute value.</p> - </item> - </ulist> - - </p> +<termref def="dt-fatal">fatal</termref> errors: +<ulist><item><p>the appearance of a reference to an +<termref def="dt-unparsed">unparsed entity</termref>. +</p></item><item><p>the appearance of any character or general-entity reference in the +DTD except within an <nt def="NT-EntityValue">EntityValue</nt> or +<nt def="NT-AttValue">AttValue</nt>.</p></item><item><p>a reference to an external entity in an attribute value.</p></item></ulist> +</p> </div3> <div3 id="inliteral"> <head>Included in Literal</head> - <p>When an - <termref def="dt-entref">entity reference</termref> - appears in an + <p>When an <termref def="dt-entref">entity reference</termref> appears in an attribute value, or a parameter entity reference appears in a literal entity -value, its <termref def="dt-repltext">replacement text</termref> - is +value, its <termref def="dt-repltext">replacement text</termref> is processed in place of the reference itself as though it were part of the document at the location the reference was recognized, except that a single or double quote character in the replacement text is always treated as a normal data character and will not terminate the literal. For example, this is well-formed: - <eg> -<![CDATA[<!ENTITY % YN '"Yes"' > -<!ENTITY WhatHeSaid "He said &YN;" >]]> </eg> - +<eg><![CDATA[<!ENTITY % YN '"Yes"' > +<!ENTITY WhatHeSaid "He said &YN;" >]]></eg> while this is not: - <eg><!ENTITY EndAttr "27'" > +<eg><!ENTITY EndAttr "27'" > <element attribute='a-&EndAttr;></eg> - - </p> +</p> </div3> <div3 id="notify"> <head>Notify</head> - <p>When the name of an - <termref def="dt-unparsed">unparsed -entity</termref> - appears as a token in the -value of an attribute of declared type <kw>ENTITY</kw> - or <kw>ENTITIES</kw> -, + <p>When the name of an <termref def="dt-unparsed">unparsed +entity</termref> appears as a token in the +value of an attribute of declared type <kw>ENTITY</kw> or <kw>ENTITIES</kw>, a validating processor must inform the -application of the <termref def="dt-sysid">system</termref> - -and <termref def="dt-pubid">public</termref> - (if any) +application of the <termref def="dt-sysid">system</termref> +and <termref def="dt-pubid">public</termref> (if any) identifiers for both the entity and its associated - <termref def="dt-notation">notation</termref> -. </p> +<termref def="dt-notation">notation</termref>.</p> </div3> <div3 id="bypass"> <head>Bypassed</head> <p>When a general entity reference appears in the - - <nt def="NT-EntityValue">EntityValue</nt> - in an entity declaration, -it is bypassed and left as is. </p> +<nt def="NT-EntityValue">EntityValue</nt> in an entity declaration, +it is bypassed and left as is.</p> </div3> <div3 id="as-PE"> <head>Included as PE</head> <p>Just as with external parsed entities, parameter entities -need only be - <titleref href="include-if-valid">included if -validating</titleref> -. +need only be <titleref href="include-if-valid">included if +validating</titleref>. When a parameter-entity reference is recognized in the DTD and included, its - <termref def="dt-repltext">replacement -text</termref> - is enlarged by the attachment of one leading and one following +<termref def="dt-repltext">replacement +text</termref> is enlarged by the attachment of one leading and one following space (#x20) character; the intent is to constrain the replacement text of parameter entities to contain an integral number of grammatical tokens in the DTD. - </p> +</p> </div3> </div2> <div2 id="intern-replacement"> @@ -4311,198 +2550,130 @@ entities to contain an integral number of grammatical tokens in the DTD. <p>In discussing the treatment of internal entities, it is useful to distinguish two forms of the entity's value. - - <termdef id="dt-litentval" term="Literal Entity Value">The - <term>literal -entity value</term> - is the quoted string actually +<termdef id="dt-litentval" term="Literal Entity Value">The <term>literal +entity value</term> is the quoted string actually present in the entity declaration, corresponding to the -non-terminal <nt def="NT-EntityValue">EntityValue</nt> -. </termdef> - - <termdef id="dt-repltext" term="Replacement Text">The - <term>replacement -text</term> - is the content of the entity, after +non-terminal <nt def="NT-EntityValue">EntityValue</nt>.</termdef> +<termdef id="dt-repltext" term="Replacement Text">The <term>replacement +text</term> is the content of the entity, after replacement of character references and parameter-entity references. - </termdef> - </p> +</termdef></p> <p>The literal entity value as given in an internal entity declaration -( - <nt def="NT-EntityValue">EntityValue</nt> -) may contain character, +(<nt def="NT-EntityValue">EntityValue</nt>) may contain character, parameter-entity, and general-entity references. Such references must be contained entirely within the literal entity value. The actual replacement text that is - <termref def="dt-include">included</termref> - as described above -must contain the <emph>replacement text</emph> - of any +<termref def="dt-include">included</termref> as described above +must contain the <emph>replacement text</emph> of any parameter entities referred to, and must contain the character referred to, in place of any character references in the literal entity value; however, general-entity references must be left as-is, unexpanded. For example, given the following declarations: - <eg> -<![CDATA[<!ENTITY % pub "Éditions Gallimard" > +<eg><![CDATA[<!ENTITY % pub "Éditions Gallimard" > <!ENTITY rights "All rights reserved" > <!ENTITY book "La Peste: Albert Camus, -© 1947 %pub;. &rights;" >]]> </eg> - -then the replacement text for the entity " <code>book</code> -" is: - <eg>La Peste: Albert Camus, +© 1947 %pub;. &rights;" >]]></eg> +then the replacement text for the entity "<code>book</code>" is: +<eg>La Peste: Albert Camus, © 1947 Éditions Gallimard. &rights;</eg> - -The general-entity reference " <code>&rights;</code> -" would be expanded -should the reference " <code>&book;</code> -" appear in the document's -content or an attribute value. </p> +The general-entity reference "<code>&rights;</code>" would be expanded +should the reference "<code>&book;</code>" appear in the document's +content or an attribute value.</p> <p>These simple rules may have complex interactions; for a detailed discussion of a difficult example, see - - <specref ref="sec-entexpand"/> -. - </p> +<specref ref="sec-entexpand"/>. +</p> </div2> <div2 id="sec-predefined-ent"> <head>Predefined Entities</head> <p> <termdef id="dt-escape" term="escape">Entity and character -references can both be used to - <term>escape</term> - the left angle bracket, +references can both be used to <term>escape</term> the left angle bracket, ampersand, and other delimiters. A set of general entities (&magicents;) is specified for this purpose. Numeric character references may also be used; they are expanded immediately when recognized and must be treated as character data, so the numeric character references -" <code>&#60;</code> -" and " <code>&#38;</code> -" may be used to -escape <code><</code> - and <code>&</code> - when they occur -in character data. </termdef> +"<code>&#60;</code>" and "<code>&#38;</code>" may be used to +escape <code><</code> and <code>&</code> when they occur +in character data.</termdef> </p> <p>All XML processors must recognize these entities whether they are declared or not. - - <termref def="dt-interop">For interoperability</termref> -, +<termref def="dt-interop">For interoperability</termref>, valid XML documents should declare these entities, like any others, before using them. If the entities in question are declared, they must be declared as internal entities whose replacement text is the single character being escaped or a character reference to that character, as shown below. - <eg> -<![CDATA[<!ENTITY lt "&#60;"> +<eg><![CDATA[<!ENTITY lt "&#60;"> <!ENTITY gt ">"> <!ENTITY amp "&#38;"> <!ENTITY apos "'"> <!ENTITY quot """> -]]> </eg> - -Note that the <code><</code> - and <code>&</code> - characters -in the declarations of " <code>lt</code> -" and " <code>amp</code> -" +]]></eg> +Note that the <code><</code> and <code>&</code> characters +in the declarations of "<code>lt</code>" and "<code>amp</code>" are doubly escaped to meet the requirement that entity replacement be well-formed. - </p> +</p> </div2> <div2 id="Notations"> <head>Notation Declarations</head> <p> - <termdef id="dt-notation" term="Notation"> - <term>Notations</term> - identify by -name the format of <termref def="dt-extent">unparsed -entities</termref> -, the + <termdef id="dt-notation" term="Notation"><term>Notations</term> identify by +name the format of <termref def="dt-extent">unparsed +entities</termref>, the format of elements which bear a notation attribute, or the application to which -a <termref def="dt-pi">processing instruction</termref> - is -addressed. </termdef> +a <termref def="dt-pi">processing instruction</termref> is +addressed.</termdef> </p> <p> <termdef id="dt-notdecl" term="Notation Declaration"> - - <term>Notation declarations</term> - +<term>Notation declarations</term> provide a name for the notation, for use in entity and attribute-list declarations and in attribute specifications, and an external identifier for the notation which may allow an XML processor or its client application to locate a helper application capable of processing data in the given notation. - <scrap lang="ebnf"> - <head>Notation Declarations</head> - <prod id="NT-NotationDecl"> - <lhs>NotationDecl</lhs> - <rhs>'<!NOTATION' - <nt def="NT-S">S</nt> - <nt def="NT-Name">Name</nt> - - <nt def="NT-S">S</nt> - -( <nt def="NT-ExternalID">ExternalID</nt> - | - <nt def="NT-PublicID">PublicID</nt> -) - <nt def="NT-S">S</nt> -? '>' </rhs> - </prod> - <prod id="NT-PublicID"> - <lhs>PublicID</lhs> - <rhs>'PUBLIC' - <nt def="NT-S">S</nt> - - <nt def="NT-PubidLiteral">PubidLiteral</nt> - - </rhs> - </prod> - </scrap> - - </termdef> +<scrap lang="ebnf"><head>Notation Declarations</head><prod id="NT-NotationDecl"><lhs>NotationDecl</lhs><rhs>'<!NOTATION' <nt def="NT-S">S</nt> <nt def="NT-Name">Name</nt> +<nt def="NT-S">S</nt> +(<nt def="NT-ExternalID">ExternalID</nt> | +<nt def="NT-PublicID">PublicID</nt>) +<nt def="NT-S">S</nt>? '>'</rhs></prod><prod id="NT-PublicID"><lhs>PublicID</lhs><rhs>'PUBLIC' <nt def="NT-S">S</nt> +<nt def="NT-PubidLiteral">PubidLiteral</nt> +</rhs></prod></scrap> +</termdef> </p> <p>XML processors must provide applications with the name and external identifier(s) of any notation declared and referred to in an attribute value, attribute definition, or entity declaration. They may additionally resolve the external identifier into the - - <termref def="dt-sysid">system identifier</termref> -, +<termref def="dt-sysid">system identifier</termref>, file name, or other information needed to allow the application to call a processor for data in the notation described. (It is not an error, however, for XML documents to declare and refer to notations for which notation-specific applications are not available on -the system where the XML processor or application is running.) </p> +the system where the XML processor or application is running.)</p> </div2> <div2 id="sec-doc-entity"> <head>Document Entity</head> - <p> - <termdef id="dt-docent" term="Document Entity">The - <term>document -entity</term> - serves as the root of the entity -tree and a starting-point for an <termref def="dt-xml-proc">XML -processor</termref> -. </termdef> - + <p><termdef id="dt-docent" term="Document Entity">The <term>document +entity</term> serves as the root of the entity +tree and a starting-point for an <termref def="dt-xml-proc">XML +processor</termref>.</termdef> This specification does not specify how the document entity is to be located by an XML processor; unlike other entities, the document entity has no name and might well appear on a processor input stream -without any identification at all. </p> +without any identification at all.</p> </div2> </div1> <!-- &Conformance; --> @@ -4510,69 +2681,47 @@ without any identification at all. </p> <head>Conformance</head> <div2 id="proc-types"> <head>Validating and Non-Validating Processors</head> - <p>Conforming - <termref def="dt-xml-proc">XML processors</termref> - fall into two -classes: validating and non-validating. </p> + <p>Conforming <termref def="dt-xml-proc">XML processors</termref> fall into two +classes: validating and non-validating.</p> <p>Validating and non-validating processors alike must report violations of this specification's well-formedness constraints in the content of the - - <termref def="dt-docent">document entity</termref> - and any -other <termref def="dt-parsedent">parsed entities</termref> - that -they read. </p> - <p> - <termdef id="dt-validating" term="Validating Processor"> - - <term>Validating processors</term> - must report +<termref def="dt-docent">document entity</termref> and any +other <termref def="dt-parsedent">parsed entities</termref> that +they read.</p> + <p><termdef id="dt-validating" term="Validating Processor"> +<term>Validating processors</term> must report violations of the constraints expressed by the declarations in the - <termref def="dt-doctype">DTD</termref> -, and +<termref def="dt-doctype">DTD</termref>, and failures to fulfill the validity constraints given in this specification. - </termdef> - +</termdef> To accomplish this, validating XML processors must read and process the entire DTD and all external parsed entities referenced in the document. - </p> +</p> <p>Non-validating processors are required to check only the - - <termref def="dt-docent">document entity</termref> -, including +<termref def="dt-docent">document entity</termref>, including the entire internal DTD subset, for well-formedness. - <termdef id="dt-use-mdecl" term="Process Declarations"> +<termdef id="dt-use-mdecl" term="Process Declarations"> While they are not required to check the document for validity, they are required to - - <term>process</term> - all the declarations they read in the +<term>process</term> all the declarations they read in the internal DTD subset and in any parameter entity that they read, up to the first reference -to a parameter entity that they do <emph>not</emph> - read; that is to +to a parameter entity that they do <emph>not</emph> read; that is to say, they must use the information in those declarations to - <titleref href="AVNormalize">normalize</titleref> - attribute values, - <titleref href="included">include</titleref> - the replacement text of +<titleref href="AVNormalize">normalize</titleref> attribute values, +<titleref href="included">include</titleref> the replacement text of internal entities, and supply - <titleref href="sec-attr-defaults">default attribute values</titleref> -. - </termdef> - -They must not <termref def="dt-use-mdecl">process</termref> - - <termref def="dt-entdecl">entity declarations</termref> - or - <termref def="dt-attdecl">attribute-list declarations</termref> - +<titleref href="sec-attr-defaults">default attribute values</titleref>. +</termdef> +They must not <termref def="dt-use-mdecl">process</termref> +<termref def="dt-entdecl">entity declarations</termref> or +<termref def="dt-attdecl">attribute-list declarations</termref> encountered after a reference to a parameter entity that is not read, since the entity may have contained overriding declarations. - </p> +</p> </div2> <div2 id="safe-behavior"> <head>Using XML Processors</head> @@ -4582,44 +2731,25 @@ validity violations. Less is required of a non-validating processor; it need not read any part of the document other than the document entity. This has two effects that may be important to users of XML processors: - - <ulist> - <item> - <p>Certain well-formedness errors, specifically those that require +<ulist><item><p>Certain well-formedness errors, specifically those that require reading external entities, may not be detected by a non-validating processor. Examples include the constraints entitled - - <titleref href="wf-entdeclared">Entity Declared</titleref> -, - <titleref href="wf-textent">Parsed Entity</titleref> -, and - <titleref href="wf-norecursion">No Recursion</titleref> -, as well +<titleref href="wf-entdeclared">Entity Declared</titleref>, +<titleref href="wf-textent">Parsed Entity</titleref>, and +<titleref href="wf-norecursion">No Recursion</titleref>, as well as some of the cases described as - <titleref href="forbidden">forbidden</titleref> - in - <specref ref="entproc"/> -. </p> - </item> - <item> - <p>The information passed from the processor to the application may +<titleref href="forbidden">forbidden</titleref> in +<specref ref="entproc"/>.</p></item><item><p>The information passed from the processor to the application may vary, depending on whether the processor reads parameter and external entities. For example, a non-validating processor may not - - <titleref href="AVNormalize">normalize</titleref> - attribute values, - <titleref href="included">include</titleref> - the replacement text of +<titleref href="AVNormalize">normalize</titleref> attribute values, +<titleref href="included">include</titleref> the replacement text of internal entities, or supply - <titleref href="sec-attr-defaults">default attribute values</titleref> -, +<titleref href="sec-attr-defaults">default attribute values</titleref>, where doing so depends on having read declarations in -external or parameter entities. </p> - </item> - </ulist> - - </p> +external or parameter entities.</p></item></ulist> +</p> <p>For maximum reliability in interoperating between different XML processors, applications which use non-validating processors should not rely on any behaviors not required of such processors. @@ -4633,9 +2763,7 @@ entities should use validating XML processors.</p> <p>The formal grammar of XML is given in this specification using a simple Extended Backus-Naur Form (EBNF) notation. Each rule in the grammar defines one symbol, in the form - - <eg>symbol ::= expression</eg> - </p> +<eg>symbol ::= expression</eg></p> <p>Symbols are written with an initial capital letter if they are defined by a regular expression, or with an initial lower case letter otherwise. @@ -4644,211 +2772,35 @@ Literal strings are quoted. </p> <p>Within the expression on the right-hand side of a rule, the following expressions are used to match strings of one or more characters: - - <glist> - <gitem> - <label> - <code>#xN</code> - </label> - <def> - <p>where - <code>N</code> - is a hexadecimal integer, the +<glist><gitem><label><code>#xN</code></label><def><p>where <code>N</code> is a hexadecimal integer, the expression matches the character in ISO/IEC 10646 whose canonical (UCS-4) code value, when interpreted as an unsigned binary number, has the value indicated. The number of leading zeros in the - <code>#xN</code> - form is insignificant; the number of leading +<code>#xN</code> form is insignificant; the number of leading zeros in the corresponding code value is governed by the character -encoding in use and is not significant for XML. </p> - </def> - </gitem> - <gitem> - <label> - <code>[a-zA-Z]</code> -, <code>[#xN-#xN]</code> - </label> - <def> - <p>matches any - <termref def="dt-character">character</termref> - -with a value in the range(s) indicated (inclusive). </p> - </def> - </gitem> - <gitem> - <label> - <code>[^a-z]</code> -, <code>[^#xN-#xN]</code> - </label> - <def> - <p>matches any - <termref def="dt-character">character</termref> - -with a value <emph>outside</emph> - the -range indicated. </p> - </def> - </gitem> - <gitem> - <label> - <code>[^abc]</code> -, <code>[^#xN#xN#xN]</code> - </label> - <def> - <p>matches any - <termref def="dt-character">character</termref> - -with a value not among the characters given. </p> - </def> - </gitem> - <gitem> - <label> - <code>"string"</code> - </label> - <def> - <p>matches a literal string - <termref def="dt-match">matching</termref> - -that given inside the double quotes. </p> - </def> - </gitem> - <gitem> - <label> - <code>'string'</code> - </label> - <def> - <p>matches a literal string - <termref def="dt-match">matching</termref> - -that given inside the single quotes. </p> - </def> - </gitem> - </glist> - +encoding in use and is not significant for XML.</p></def></gitem><gitem><label><code>[a-zA-Z]</code>, <code>[#xN-#xN]</code></label><def><p>matches any <termref def="dt-character">character</termref> +with a value in the range(s) indicated (inclusive).</p></def></gitem><gitem><label><code>[^a-z]</code>, <code>[^#xN-#xN]</code></label><def><p>matches any <termref def="dt-character">character</termref> +with a value <emph>outside</emph> the +range indicated.</p></def></gitem><gitem><label><code>[^abc]</code>, <code>[^#xN#xN#xN]</code></label><def><p>matches any <termref def="dt-character">character</termref> +with a value not among the characters given.</p></def></gitem><gitem><label><code>"string"</code></label><def><p>matches a literal string <termref def="dt-match">matching</termref> +that given inside the double quotes.</p></def></gitem><gitem><label><code>'string'</code></label><def><p>matches a literal string <termref def="dt-match">matching</termref> +that given inside the single quotes.</p></def></gitem></glist> These symbols may be combined to match more complex patterns as follows, -where <code>A</code> - and <code>B</code> - represent simple expressions: - <glist> - <gitem> - <label>( - <code>expression</code> -) </label> - <def> - <p> - <code>expression</code> - is treated as a unit -and may be combined as described in this list. </p> - </def> - </gitem> - <gitem> - <label> - <code>A?</code> - </label> - <def> - <p>matches - <code>A</code> - or nothing; optional <code>A</code> -. </p> - </def> - </gitem> - <gitem> - <label> - <code>A B</code> - </label> - <def> - <p>matches - <code>A</code> - followed by <code>B</code> -. </p> - </def> - </gitem> - <gitem> - <label> - <code>A | B</code> - </label> - <def> - <p>matches - <code>A</code> - or <code>B</code> - but not both. </p> - </def> - </gitem> - <gitem> - <label> - <code>A - B</code> - </label> - <def> - <p>matches any string that matches - <code>A</code> - but does not match - <code>B</code> -. - </p> - </def> - </gitem> - <gitem> - <label> - <code>A+</code> - </label> - <def> - <p>matches one or more occurrences of - <code>A</code> -. </p> - </def> - </gitem> - <gitem> - <label> - <code>A*</code> - </label> - <def> - <p>matches zero or more occurrences of - <code>A</code> -. </p> - </def> - </gitem> - </glist> - +where <code>A</code> and <code>B</code> represent simple expressions: +<glist><gitem><label>(<code>expression</code>)</label><def><p><code>expression</code> is treated as a unit +and may be combined as described in this list.</p></def></gitem><gitem><label><code>A?</code></label><def><p>matches <code>A</code> or nothing; optional <code>A</code>.</p></def></gitem><gitem><label><code>A B</code></label><def><p>matches <code>A</code> followed by <code>B</code>.</p></def></gitem><gitem><label><code>A | B</code></label><def><p>matches <code>A</code> or <code>B</code> but not both.</p></def></gitem><gitem><label><code>A - B</code></label><def><p>matches any string that matches <code>A</code> but does not match +<code>B</code>. +</p></def></gitem><gitem><label><code>A+</code></label><def><p>matches one or more occurrences of <code>A</code>.</p></def></gitem><gitem><label><code>A*</code></label><def><p>matches zero or more occurrences of <code>A</code>.</p></def></gitem></glist> Other notations used in the productions are: - <glist> - <gitem> - <label> - <code>/* ... */</code> - </label> - <def> - <p>comment.</p> - </def> - </gitem> - <gitem> - <label> - <code>[ wfc: ... ]</code> - </label> - <def> - <p>well-formedness constraint; this identifies by name a +<glist><gitem><label><code>/* ... */</code></label><def><p>comment.</p></def></gitem><gitem><label><code>[ wfc: ... ]</code></label><def><p>well-formedness constraint; this identifies by name a constraint on - - <termref def="dt-wellformed">well-formed</termref> - documents -associated with a production. </p> - </def> - </gitem> - <gitem> - <label> - <code>[ vc: ... ]</code> - </label> - <def> - <p>validity constraint; this identifies by name a constraint on - - <termref def="dt-valid">valid</termref> - documents associated with -a production. </p> - </def> - </gitem> - </glist> - - </p> +<termref def="dt-wellformed">well-formed</termref> documents +associated with a production.</p></def></gitem><gitem><label><code>[ vc: ... ]</code></label><def><p>validity constraint; this identifies by name a constraint on +<termref def="dt-valid">valid</termref> documents associated with +a production.</p></def></gitem></glist> +</p> </div1> </body> <back> @@ -4860,54 +2812,41 @@ a production. </p> <head>Normative References</head> <blist> <bibl id="IANA" key="IANA"> -(Internet Assigned Numbers Authority) - <emph>Official Names for -Character Sets</emph> -, +(Internet Assigned Numbers Authority) <emph>Official Names for +Character Sets</emph>, ed. Keld Simonsen et al. -See <loc href="ftp://ftp.isi.edu/in-notes/iana/assignments/character-sets">ftp://ftp.isi.edu/in-notes/iana/assignments/character-sets</loc> -. - </bibl> +See <loc href="ftp://ftp.isi.edu/in-notes/iana/assignments/character-sets">ftp://ftp.isi.edu/in-notes/iana/assignments/character-sets</loc>. +</bibl> <bibl id="RFC1766" key="IETF RFC 1766"> IETF (Internet Engineering Task Force). - - <emph>RFC 1766: Tags for the Identification of Languages</emph> -, +<emph>RFC 1766: Tags for the Identification of Languages</emph>, ed. H. Alvestrand. 1995. - </bibl> +</bibl> <bibl id="ISO639" key="ISO 639"> (International Organization for Standardization). - - <emph>ISO 639:1988 (E). +<emph>ISO 639:1988 (E). Code for the representation of names of languages.</emph> - [Geneva]: International Organization for -Standardization, 1988. </bibl> +Standardization, 1988.</bibl> <bibl id="ISO3166" key="ISO 3166"> (International Organization for Standardization). - - <emph>ISO 3166-1:1997 (E). +<emph>ISO 3166-1:1997 (E). Codes for the representation of names of countries and their subdivisions — Part 1: Country codes</emph> - [Geneva]: International Organization for -Standardization, 1997. </bibl> +Standardization, 1997.</bibl> <bibl id="ISO10646" key="ISO/IEC 10646">ISO (International Organization for Standardization). - - <emph>ISO/IEC 10646-1993 (E). Information technology — Universal +<emph>ISO/IEC 10646-1993 (E). Information technology — Universal Multiple-Octet Coded Character Set (UCS) — Part 1: Architecture and Basic Multilingual Plane.</emph> - [Geneva]: International Organization for Standardization, 1993 (plus amendments AM 1 through AM 7). - </bibl> +</bibl> <bibl id="Unicode" key="Unicode">The Unicode Consortium. - - <emph>The Unicode Standard, Version 2.0.</emph> - -Reading, Mass.: Addison-Wesley Developers Press, 1996. </bibl> +<emph>The Unicode Standard, Version 2.0.</emph> +Reading, Mass.: Addison-Wesley Developers Press, 1996.</bibl> </blist> </div2> <div2> @@ -4915,88 +2854,67 @@ Reading, Mass.: Addison-Wesley Developers Press, 1996. </bibl> <blist> <bibl id="Aho" key="Aho/Ullman">Aho, Alfred V., Ravi Sethi, and Jeffrey D. Ullman. - - <emph>Compilers: Principles, Techniques, and Tools</emph> -. -Reading: Addison-Wesley, 1986, rpt. corr. 1988. </bibl> +<emph>Compilers: Principles, Techniques, and Tools</emph>. +Reading: Addison-Wesley, 1986, rpt. corr. 1988.</bibl> <bibl xml-link="simple" id="Berners-Lee" key="Berners-Lee et al."> Berners-Lee, T., R. Fielding, and L. Masinter. - - <emph>Uniform Resource Identifiers (URI): Generic Syntax and -Semantics</emph> -. +<emph>Uniform Resource Identifiers (URI): Generic Syntax and +Semantics</emph>. 1997. -(Work in progress; see updates to RFC1738.) </bibl> +(Work in progress; see updates to RFC1738.)</bibl> <bibl id="ABK" key="Brüggemann-Klein">Brüggemann-Klein, Anne. - - <emph>Regular Expressions into Finite Automata</emph> -. +<emph>Regular Expressions into Finite Automata</emph>. Extended abstract in I. Simon, Hrsg., LATIN 1992, S. 97-98. Springer-Verlag, Berlin 1992. Full Version in Theoretical Computer Science 120: 197-213, 1993. - </bibl> +</bibl> <bibl id="ABKDW" key="Brüggemann-Klein and Wood">Brüggemann-Klein, Anne, and Derick Wood. - - <emph>Deterministic Regular Languages</emph> -. +<emph>Deterministic Regular Languages</emph>. Universität Freiburg, Institut für Informatik, Bericht 38, Oktober 1991. - </bibl> +</bibl> <bibl id="Clark" key="Clark">James Clark. Comparison of SGML and XML. See - - <loc href="http://www.w3.org/TR/NOTE-sgml-xml-971215">http://www.w3.org/TR/NOTE-sgml-xml-971215</loc> -. - </bibl> +<loc href="http://www.w3.org/TR/NOTE-sgml-xml-971215">http://www.w3.org/TR/NOTE-sgml-xml-971215</loc>. +</bibl> <bibl xml-link="simple" id="RFC1738" key="IETF RFC1738"> IETF (Internet Engineering Task Force). - - <emph>RFC 1738: Uniform Resource Locators (URL)</emph> -, +<emph>RFC 1738: Uniform Resource Locators (URL)</emph>, ed. T. Berners-Lee, L. Masinter, M. McCahill. 1994. - </bibl> +</bibl> <bibl xml-link="simple" id="RFC1808" key="IETF RFC1808"> IETF (Internet Engineering Task Force). - - <emph>RFC 1808: Relative Uniform Resource Locators</emph> -, +<emph>RFC 1808: Relative Uniform Resource Locators</emph>, ed. R. Fielding. 1995. - </bibl> +</bibl> <bibl xml-link="simple" id="RFC2141" key="IETF RFC2141"> IETF (Internet Engineering Task Force). - - <emph>RFC 2141: URN Syntax</emph> -, +<emph>RFC 2141: URN Syntax</emph>, ed. R. Moats. 1997. - </bibl> +</bibl> <bibl id="ISO8879" key="ISO 8879">ISO (International Organization for Standardization). - - <emph>ISO 8879:1986(E). Information processing — Text and Office -Systems — Standard Generalized Markup Language (SGML).</emph> - First +<emph>ISO 8879:1986(E). Information processing — Text and Office +Systems — Standard Generalized Markup Language (SGML).</emph> First edition — 1986-10-15. [Geneva]: International Organization for Standardization, 1986. - </bibl> +</bibl> <bibl id="ISO10744" key="ISO/IEC 10744">ISO (International Organization for Standardization). - - <emph>ISO/IEC 10744-1992 (E). Information technology — +<emph>ISO/IEC 10744-1992 (E). Information technology — Hypermedia/Time-based Structuring Language (HyTime). </emph> - [Geneva]: International Organization for Standardization, 1992. - <emph>Extended Facilities Annexe.</emph> - +<emph>Extended Facilities Annexe.</emph> [Geneva]: International Organization for Standardization, 1996. - </bibl> +</bibl> </blist> </div2> </div1> @@ -5009,21 +2927,8 @@ diacritics), ideographic characters, and combining characters (among others, this class contains most diacritics); these classes combine to form the class of letters. Digits and extenders are also distinguished. - - <scrap lang="ebnf" id="CHARACTERS"> - <head>Characters</head> - <prodgroup pcw3="3" pcw4="15"> - <prod id="NT-Letter"> - <lhs>Letter</lhs> - <rhs> - <nt def="NT-BaseChar">BaseChar</nt> - -| <nt def="NT-Ideographic">Ideographic</nt> - </rhs> - </prod> - <prod id="NT-BaseChar"> - <lhs>BaseChar</lhs> - <rhs>[#x0041-#x005A] +<scrap lang="ebnf" id="CHARACTERS"><head>Characters</head><prodgroup pcw3="3" pcw4="15"><prod id="NT-Letter"><lhs>Letter</lhs><rhs><nt def="NT-BaseChar">BaseChar</nt> +| <nt def="NT-Ideographic">Ideographic</nt></rhs></prod><prod id="NT-BaseChar"><lhs>BaseChar</lhs><rhs>[#x0041-#x005A] | [#x0061-#x007A] | [#x00C0-#x00D6] | [#x00D8-#x00F6] @@ -5225,18 +3130,10 @@ also distinguished. | [#x30A1-#x30FA] | [#x3105-#x312C] | [#xAC00-#xD7A3] -</rhs> - </prod> - <prod id="NT-Ideographic"> - <lhs>Ideographic</lhs> - <rhs>[#x4E00-#x9FA5] +</rhs></prod><prod id="NT-Ideographic"><lhs>Ideographic</lhs><rhs>[#x4E00-#x9FA5] | #x3007 | [#x3021-#x3029] -</rhs> - </prod> - <prod id="NT-CombiningChar"> - <lhs>CombiningChar</lhs> - <rhs>[#x0300-#x0345] +</rhs></prod><prod id="NT-CombiningChar"><lhs>CombiningChar</lhs><rhs>[#x0300-#x0345] | [#x0360-#x0361] | [#x0483-#x0486] | [#x0591-#x05A1] @@ -5331,11 +3228,7 @@ also distinguished. | [#x302A-#x302F] | #x3099 | #x309A -</rhs> - </prod> - <prod id="NT-Digit"> - <lhs>Digit</lhs> - <rhs>[#x0030-#x0039] +</rhs></prod><prod id="NT-Digit"><lhs>Digit</lhs><rhs>[#x0030-#x0039] | [#x0660-#x0669] | [#x06F0-#x06F9] | [#x0966-#x096F] @@ -5350,11 +3243,7 @@ also distinguished. | [#x0E50-#x0E59] | [#x0ED0-#x0ED9] | [#x0F20-#x0F29] -</rhs> - </prod> - <prod id="NT-Extender"> - <lhs>Extender</lhs> - <rhs>#x00B7 +</rhs></prod><prod id="NT-Extender"><lhs>Extender</lhs><rhs>#x00B7 | #x02D0 | #x02D1 | #x0387 @@ -5365,122 +3254,67 @@ also distinguished. | [#x3031-#x3035] | [#x309D-#x309E] | [#x30FC-#x30FE] -</rhs> - </prod> - </prodgroup> - </scrap> - - </p> +</rhs></prod></prodgroup></scrap> +</p> <p>The character classes defined here can be derived from the Unicode character database as follows: - - <ulist> - <item> - <p>Name start characters must have one of the categories Ll, Lu, -Lo, Lt, Nl.</p> - </item> - <item> - <p>Name characters other than Name-start characters -must have one of the categories Mc, Me, Mn, Lm, or Nd.</p> - </item> - <item> - <p>Characters in the compatibility area (i.e. with character code +<ulist><item><p>Name start characters must have one of the categories Ll, Lu, +Lo, Lt, Nl.</p></item><item><p>Name characters other than Name-start characters +must have one of the categories Mc, Me, Mn, Lm, or Nd.</p></item><item><p>Characters in the compatibility area (i.e. with character code greater than #xF900 and less than #xFFFE) are not allowed in XML -names.</p> - </item> - <item> - <p>Characters which have a font or compatibility decomposition (i.e. those +names.</p></item><item><p>Characters which have a font or compatibility decomposition (i.e. those with a "compatibility formatting tag" in field 5 of the database -- -marked by field 5 beginning with a "<") are not allowed.</p> - </item> - <item> - <p>The following characters are treated as name-start characters +marked by field 5 beginning with a "<") are not allowed.</p></item><item><p>The following characters are treated as name-start characters rather than name characters, because the property file classifies -them as Alphabetic: [#x02BB-#x02C1], #x0559, #x06E5, #x06E6.</p> - </item> - <item> - <p>Characters #x20DD-#x20E0 are excluded (in accordance with -Unicode, section 5.14).</p> - </item> - <item> - <p>Character #x00B7 is classified as an extender, because the -property list so identifies it.</p> - </item> - <item> - <p>Character #x0387 is added as a name character, because #x00B7 -is its canonical equivalent.</p> - </item> - <item> - <p>Characters ':' and '_' are allowed as name-start characters.</p> - </item> - <item> - <p>Characters '-' and '.' are allowed as name characters.</p> - </item> - </ulist> - - </p> +them as Alphabetic: [#x02BB-#x02C1], #x0559, #x06E5, #x06E6.</p></item><item><p>Characters #x20DD-#x20E0 are excluded (in accordance with +Unicode, section 5.14).</p></item><item><p>Character #x00B7 is classified as an extender, because the +property list so identifies it.</p></item><item><p>Character #x0387 is added as a name character, because #x00B7 +is its canonical equivalent.</p></item><item><p>Characters ':' and '_' are allowed as name-start characters.</p></item><item><p>Characters '-' and '.' are allowed as name characters.</p></item></ulist> +</p> </div1> <inform-div1 id="sec-xml-and-sgml"> <head>XML and SGML</head> <p>XML is designed to be a subset of SGML, in that every - - <termref def="dt-valid">valid</termref> - XML document should also be a +<termref def="dt-valid">valid</termref> XML document should also be a conformant SGML document. For a detailed comparison of the additional restrictions that XML places on -documents beyond those of SGML, see <bibref ref="Clark"/> -. - </p> +documents beyond those of SGML, see <bibref ref="Clark"/>. +</p> </inform-div1> <inform-div1 id="sec-entexpand"> <head>Expansion of Entity and Character References</head> <p>This appendix contains some examples illustrating the sequence of entity- and character-reference recognition and -expansion, as specified in - <specref ref="entproc"/> -. </p> +expansion, as specified in <specref ref="entproc"/>.</p> <p> If the DTD contains the declaration - - <eg> -<![CDATA[<!ENTITY example "<p>An ampersand (&#38;) may be escaped +<eg><![CDATA[<!ENTITY example "<p>An ampersand (&#38;) may be escaped numerically (&#38;#38;) or with a general entity (&amp;).</p>" > -]]> </eg> - +]]></eg> then the XML processor will recognize the character references when it parses the entity declaration, and resolve them before storing the following string as the -value of the entity " <code>example</code> -": - <eg> -<![CDATA[<p>An ampersand (&) may be escaped +value of the entity "<code>example</code>": +<eg><![CDATA[<p>An ampersand (&) may be escaped numerically (&#38;) or with a general entity (&amp;).</p> -]]> </eg> - -A reference in the document to " <code>&example;</code> -" +]]></eg> +A reference in the document to "<code>&example;</code>" will cause the text to be reparsed, at which time the -start- and end-tags of the " <code>p</code> -" element will be recognized +start- and end-tags of the "<code>p</code>" element will be recognized and the three references will be recognized and expanded, -resulting in a " <code>p</code> -" element with the following content +resulting in a "<code>p</code>" element with the following content (all data, no delimiters or markup): - <eg> -<![CDATA[An ampersand (&) may be escaped +<eg><![CDATA[An ampersand (&) may be escaped numerically (&) or with a general entity (&). -]]> </eg> - - </p> +]]></eg> +</p> <p>A more complex example will illustrate the rules and their effects fully. In the following example, the line numbers are solely for reference. - - <eg> -<![CDATA[1 <?xml version='1.0'?> +<eg><![CDATA[1 <?xml version='1.0'?> 2 <!DOCTYPE test [ 3 <!ELEMENT test (#PCDATA) > 4 <!ENTITY % xx '%zz;'> @@ -5488,107 +3322,57 @@ solely for reference. 6 %xx; 7 ]> 8 <test>This sample shows a &tricky; method.</test> -]]> </eg> - +]]></eg> This produces the following: - <ulist spacing="compact"> - <item> - <p>in line 4, the reference to character 37 is expanded immediately, -and the parameter entity " - <code>xx</code> -" is stored in the symbol -table with the value " <code>%zz;</code> -". Since the replacement text -is not rescanned, the reference to parameter entity " <code>zz</code> -" +<ulist spacing="compact"><item><p>in line 4, the reference to character 37 is expanded immediately, +and the parameter entity "<code>xx</code>" is stored in the symbol +table with the value "<code>%zz;</code>". Since the replacement text +is not rescanned, the reference to parameter entity "<code>zz</code>" is not recognized. (And it would be an error if it were, since -" <code>zz</code> -" is not yet declared.) </p> - </item> - <item> - <p>in line 5, the character reference " - <code>&#60;</code> -" is -expanded immediately and the parameter entity " <code>zz</code> -" is +"<code>zz</code>" is not yet declared.)</p></item><item><p>in line 5, the character reference "<code>&#60;</code>" is +expanded immediately and the parameter entity "<code>zz</code>" is stored with the replacement text -" <code><!ENTITY tricky "error-prone" ></code> -", -which is a well-formed entity declaration. </p> - </item> - <item> - <p>in line 6, the reference to " - <code>xx</code> -" is recognized, -and the replacement text of " <code>xx</code> -" (namely -" <code>%zz;</code> -") is parsed. The reference to " <code>zz</code> -" +"<code><!ENTITY tricky "error-prone" ></code>", +which is a well-formed entity declaration.</p></item><item><p>in line 6, the reference to "<code>xx</code>" is recognized, +and the replacement text of "<code>xx</code>" (namely +"<code>%zz;</code>") is parsed. The reference to "<code>zz</code>" is recognized in its turn, and its replacement text -(" <code><!ENTITY tricky "error-prone" ></code> -") is parsed. -The general entity " <code>tricky</code> -" has now been -declared, with the replacement text " <code>error-prone</code> -". </p> - </item> - <item> - <p> -in line 8, the reference to the general entity " - <code>tricky</code> -" is +("<code><!ENTITY tricky "error-prone" ></code>") is parsed. +The general entity "<code>tricky</code>" has now been +declared, with the replacement text "<code>error-prone</code>".</p></item><item><p> +in line 8, the reference to the general entity "<code>tricky</code>" is recognized, and it is expanded, so the full content of the -" <code>test</code> -" element is the self-describing (and ungrammatical) string - <emph>This sample shows a error-prone method.</emph> - - </p> - </item> - </ulist> - - </p> +"<code>test</code>" element is the self-describing (and ungrammatical) string +<emph>This sample shows a error-prone method.</emph> +</p></item></ulist> +</p> </inform-div1> <inform-div1 id="determinism"> <head>Deterministic Content Models</head> - <p> - <termref def="dt-compat">For compatibility</termref> -, it is + <p><termref def="dt-compat">For compatibility</termref>, it is required that content models in element type declarations be deterministic. - </p> +</p> <!-- FINAL EDIT: WebSGML allows ambiguity? --> <p>SGML requires deterministic content models (it calls them "unambiguous"); XML processors built using SGML systems may flag non-deterministic content models as errors.</p> - <p>For example, the content model - <code>((b, c) | (b, d))</code> - is -non-deterministic, because given an initial <code>b</code> - the parser -cannot know which <code>b</code> - in the model is being matched without -looking ahead to see which element follows the <code>b</code> -. + <p>For example, the content model <code>((b, c) | (b, d))</code> is +non-deterministic, because given an initial <code>b</code> the parser +cannot know which <code>b</code> in the model is being matched without +looking ahead to see which element follows the <code>b</code>. In this case, the two references to - <code>b</code> - can be collapsed +<code>b</code> can be collapsed into a single reference, making the model read - <code>(b, (c | d))</code> -. An initial <code>b</code> - now clearly +<code>(b, (c | d))</code>. An initial <code>b</code> now clearly matches only a single name in the content model. The parser doesn't -need to look ahead to see what follows; either <code>c</code> - or - <code>d</code> - would be accepted. </p> +need to look ahead to see what follows; either <code>c</code> or +<code>d</code> would be accepted.</p> <p>More formally: a finite state automaton may be constructed from the content model using the standard algorithms, e.g. algorithm 3.5 in section 3.9 -of Aho, Sethi, and Ullman - <bibref ref="Aho"/> -. +of Aho, Sethi, and Ullman <bibref ref="Aho"/>. In many such algorithms, a follow set is constructed for each position in the regular expression (i.e., each leaf node in the @@ -5598,12 +3382,10 @@ more than one following position is labeled with the same element type name, then the content model is in error and may be reported as an error. - </p> +</p> <p>Algorithms exist which allow many but not all non-deterministic content models to be reduced automatically to equivalent deterministic -models; see Brüggemann-Klein 1991 - <bibref ref="ABK"/> -. </p> +models; see Brüggemann-Klein 1991 <bibref ref="ABK"/>.</p> </inform-div1> <inform-div1 id="sec-guessing"> <head>Autodetection of Character Encodings</head> @@ -5625,68 +3407,17 @@ processor without, or with, any accompanying (external) information. We consider the first case first. </p> <p> -Because each XML entity not in UTF-8 or UTF-16 format - <emph>must</emph> - +Because each XML entity not in UTF-8 or UTF-16 format <emph>must</emph> begin with an XML encoding declaration, in which the first characters -must be ' <code><?xml</code> -', any conforming processor can detect, +must be '<code><?xml</code>', any conforming processor can detect, after two to four octets of input, which of the following cases apply. In reading this list, it may help to know that in UCS-4, '<' is -" <code>#x0000003C</code> -" and '?' is " <code>#x0000003F</code> -", and the Byte -Order Mark required of UTF-16 data streams is " <code>#xFEFF</code> -". </p> +"<code>#x0000003C</code>" and '?' is "<code>#x0000003F</code>", and the Byte +Order Mark required of UTF-16 data streams is "<code>#xFEFF</code>".</p> <p> - - <ulist> - <item> - <p> - <code>00 00 00 3C</code> -: UCS-4, big-endian machine (1234 order) </p> - </item> - <item> - <p> - <code>3C 00 00 00</code> -: UCS-4, little-endian machine (4321 order) </p> - </item> - <item> - <p> - <code>00 00 3C 00</code> -: UCS-4, unusual octet order (2143) </p> - </item> - <item> - <p> - <code>00 3C 00 00</code> -: UCS-4, unusual octet order (3412) </p> - </item> - <item> - <p> - <code>FE FF</code> -: UTF-16, big-endian </p> - </item> - <item> - <p> - <code>FF FE</code> -: UTF-16, little-endian </p> - </item> - <item> - <p> - <code>00 3C 00 3F</code> -: UTF-16, big-endian, no Byte Order Mark -(and thus, strictly speaking, in error) </p> - </item> - <item> - <p> - <code>3C 00 3F 00</code> -: UTF-16, little-endian, no Byte Order Mark -(and thus, strictly speaking, in error) </p> - </item> - <item> - <p> - <code>3C 3F 78 6D</code> -: UTF-8, ISO 646, ASCII, some part of ISO 8859, +<ulist><item><p><code>00 00 00 3C</code>: UCS-4, big-endian machine (1234 order)</p></item><item><p><code>3C 00 00 00</code>: UCS-4, little-endian machine (4321 order)</p></item><item><p><code>00 00 3C 00</code>: UCS-4, unusual octet order (2143)</p></item><item><p><code>00 3C 00 00</code>: UCS-4, unusual octet order (3412)</p></item><item><p><code>FE FF</code>: UTF-16, big-endian</p></item><item><p><code>FF FE</code>: UTF-16, little-endian</p></item><item><p><code>00 3C 00 3F</code>: UTF-16, big-endian, no Byte Order Mark +(and thus, strictly speaking, in error)</p></item><item><p><code>3C 00 3F 00</code>: UTF-16, little-endian, no Byte Order Mark +(and thus, strictly speaking, in error)</p></item><item><p><code>3C 3F 78 6D</code>: UTF-8, ISO 646, ASCII, some part of ISO 8859, Shift-JIS, EUC, or any other 7-bit, 8-bit, or mixed-width encoding which ensures that the characters of ASCII have their normal positions, width, @@ -5694,23 +3425,12 @@ and values; the actual encoding declaration must be read to detect which of these applies, but since all of these encodings use the same bit patterns for the ASCII characters, the encoding declaration itself may be read reliably - </p> - </item> - <item> - <p> - <code>4C 6F A7 94</code> -: EBCDIC (in some flavor; the full +</p></item><item><p><code>4C 6F A7 94</code>: EBCDIC (in some flavor; the full encoding declaration must be read to tell which code page is in -use) </p> - </item> - <item> - <p>other: UTF-8 without an encoding declaration, or else +use)</p></item><item><p>other: UTF-8 without an encoding declaration, or else the data stream is corrupt, fragmentary, or enclosed in -a wrapper of some kind</p> - </item> - </ulist> - - </p> +a wrapper of some kind</p></item></ulist> +</p> <p> This level of autodetection is enough to read the XML encoding declaration and parse the character-encoding identifier, which is @@ -5755,41 +3475,27 @@ MIME-type label in an external header, for example, should be part of the RFC document defining the text/xml and application/xml MIME types. In the interests of interoperability, however, the following rules are recommended. - - <ulist> - <item> - <p>If an XML entity is in a file, the Byte-Order Mark +<ulist><item><p>If an XML entity is in a file, the Byte-Order Mark and encoding-declaration PI are used (if present) to determine the character encoding. All other heuristics and sources of information are solely for error recovery. -</p> - </item> - <item> - <p>If an XML entity is delivered with a -MIME type of text/xml, then the - <code>charset</code> - parameter +</p></item><item><p>If an XML entity is delivered with a +MIME type of text/xml, then the <code>charset</code> parameter on the MIME type determines the character encoding method; all other heuristics and sources of information are solely for error recovery. - </p> - </item> - <item> - <p>If an XML entity is delivered +</p></item><item><p>If an XML entity is delivered with a MIME type of application/xml, then the Byte-Order Mark and encoding-declaration PI are used (if present) to determine the character encoding. All other heuristics and sources of information are solely for error recovery. -</p> - </item> - </ulist> - +</p></item></ulist> These rules apply only in the absence of protocol-level documentation; in particular, when the MIME types text/xml and application/xml are defined, the recommendations of the relevant RFC will supersede these rules. - </p> +</p> </inform-div1> <inform-div1 id="sec-xml-wg"> <head>W3C XML Working Group</head> diff --git a/result/valid/xlink.xml b/result/valid/xlink.xml index 80ec5ffe..79197898 100644 --- a/result/valid/xlink.xml +++ b/result/valid/xlink.xml @@ -14,9 +14,7 @@ type="text/css"?> <?Pub Dtl?> <title>XML Linking Language (XLink)</title> <version>Version 1.0</version> - <w3c-designation> -<!-- &doc-type;-&iso6.doc.date; --> - WD-xlink-19990527 </w3c-designation> + <w3c-designation><!-- &doc-type;-&iso6.doc.date; --> WD-xlink-19990527</w3c-designation> <w3c-doctype>World Wide Web Consortium Working Draft</w3c-doctype> <pubdate> <day>29</day> @@ -61,24 +59,12 @@ type="text/css"?> <EMAIL>tbray@textuality.com</EMAIL> </AUTHOR>--> </authlist> <status> - <p>This is a W3C Working Draft for review by W3C members and other interested parties. It is a draft document and may be updated, replaced, or obsoleted by other documents at any time. It is inappropriate to use W3C Working Drafts as reference material or to cite them as other than "work in progress". A list of current W3C working drafts can be found at - <loc href="http://www.w3.org/TR">http://www.w3.org/TR</loc> -. </p> - <p> - <emph>Note:</emph> - Since working drafts are subject to frequent change, you are advised to reference the above URI, rather than the URIs for working drafts themselves. Some of the work remaining is described in <specref ref="unfinished"/> -. </p> - <p>This work is part of the W3C XML Activity (for current status, see - <loc href="http://www.w3.org/MarkUp/SGML/Activity">http://www.w3.org/XML/Activity </loc> -). For information about the XPointer language which is expected to be used with XLink, see <loc href="http://www.w3.org/MarkUp/SGML/Activity">http://www.w3.org/TR/WD-xptr</loc> -. - </p> - <p>See - <loc href="http://www.w3.org/TR/NOTE-xlink-principles">http://www.w3.org/TR/NOTE-xlink-principles </loc> - for additional background on the design principles informing XLink. </p> - <p>Also see - <loc href="http://www.w3.org/TR/NOTE-xlink-req/">http://www.w3.org/TR/NOTE-xlink-req/</loc> - for the XLink requirements that this document attempts to satisfy. </p> + <p>This is a W3C Working Draft for review by W3C members and other interested parties. It is a draft document and may be updated, replaced, or obsoleted by other documents at any time. It is inappropriate to use W3C Working Drafts as reference material or to cite them as other than "work in progress". A list of current W3C working drafts can be found at <loc href="http://www.w3.org/TR">http://www.w3.org/TR</loc>.</p> + <p><emph>Note:</emph> Since working drafts are subject to frequent change, you are advised to reference the above URI, rather than the URIs for working drafts themselves. Some of the work remaining is described in <specref ref="unfinished"/>. </p> + <p>This work is part of the W3C XML Activity (for current status, see <loc href="http://www.w3.org/MarkUp/SGML/Activity">http://www.w3.org/XML/Activity </loc>). For information about the XPointer language which is expected to be used with XLink, see <loc href="http://www.w3.org/MarkUp/SGML/Activity">http://www.w3.org/TR/WD-xptr</loc>. + </p> + <p>See <loc href="http://www.w3.org/TR/NOTE-xlink-principles">http://www.w3.org/TR/NOTE-xlink-principles </loc> for additional background on the design principles informing XLink.</p> + <p>Also see <loc href="http://www.w3.org/TR/NOTE-xlink-req/">http://www.w3.org/TR/NOTE-xlink-req/</loc> for the XLink requirements that this document attempts to satisfy.</p> </status> <abstract> <!-- edited the abstract for further clarity - bent --> @@ -121,533 +107,120 @@ type="text/css"?> <div1> <?Pub Dtl?> <head>Introduction</head> - <p>This specification defines constructs that may be inserted into XML DTDs, schemas, and document instances to describe links between objects. A - <termref def="dt-link">link</termref> -, as the term is used here, is an explicit relationship between two or more data objects or portions of data objects. This specification is concerned with the syntax used to assert link existence and describe link characteristics. Implicit (unasserted) relationships, for example that of one word to the next or that of a word in a text to its entry in an on-line dictionary are obviously important, but outside its scope. </p> - <p>Links are asserted by - <xtermref href="WD-xml-lang.html#dt-element">elements </xtermref> - contained in <xtermref href="WD-xml-lang.html#dt-xml-doc">XML document instances</xtermref> -. The simplest case is very like an HTML <code>A</code> - link, and has these characteristics: - <ulist> - <item> - <p>The link is expressed at one of its ends (similar to the - <code>A</code> - element in some document) </p> - </item> - <item> - <p>Users can only initiate travel from that end to the other</p> - </item> - <item> - <p>The link's effect on windows, frames, go-back lists, stylesheets in use, and so on is mainly determined by browsers, not by the link itself. For example, traveral of - <code>A</code> - links normally replaces the current view, perhaps with a user option to open a new window. </p> - </item> - <item> - <p>The link goes to only one destination (although a server may have great freedom in finding or dynamically creating that destination).</p> - </item> - </ulist> - - </p> + <p>This specification defines constructs that may be inserted into XML DTDs, schemas, and document instances to describe links between objects. A <termref def="dt-link">link</termref>, as the term is used here, is an explicit relationship between two or more data objects or portions of data objects. This specification is concerned with the syntax used to assert link existence and describe link characteristics. Implicit (unasserted) relationships, for example that of one word to the next or that of a word in a text to its entry in an on-line dictionary are obviously important, but outside its scope.</p> + <p>Links are asserted by <xtermref href="WD-xml-lang.html#dt-element">elements </xtermref> contained in <xtermref href="WD-xml-lang.html#dt-xml-doc">XML document instances</xtermref>. The simplest case is very like an HTML <code>A</code> link, and has these characteristics: + <ulist><item><p>The link is expressed at one of its ends (similar to the <code>A</code> element in some document)</p></item><item><p>Users can only initiate travel from that end to the other</p></item><item><p>The link's effect on windows, frames, go-back lists, stylesheets in use, and so on is mainly determined by browsers, not by the link itself. For example, traveral of <code>A</code> links normally replaces the current view, perhaps with a user option to open a new window.</p></item><item><p>The link goes to only one destination (although a server may have great freedom in finding or dynamically creating that destination).</p></item></ulist> + </p> <p>While this set of characteristics is already very powerful and obviously has proven itself highly useful and effective, each of these assumptions also limits the range of hypertext functionality. The linking model defined here provides ways to create links that go beyond each of these specific characteristics, thus providing features previously available mostly in dedicated hypermedia systems. </p> <div2> <head>Origin and Goals</head> <p>Following is a summary of the design principles governing XLink: - - <olist> - <item> - <p>XLink must be straightforwardly usable over the Internet. </p> - </item> - <item> - <p>XLink must be usable by a wide variety of link usage domains and classes of linking application software.</p> - </item> - <item> - <p>XLink must support HTML 4.0 linking constructs.</p> - </item> - <item> - <p>The XLink expression language must be XML.</p> - </item> - <item> - <p>The XLink design must be formal, concise, and illustrative.</p> - </item> - <item> - <p>XLinks must be human-readable and human-writable.</p> - </item> - <item> - <p>XLinks may reside within or outside the documents in which the - participating resources reside. </p> - </item> - <item> - <p>XLink must represent the abstract structure and significance of links.</p> - </item> - <item> - <p>XLink must be feasible to implement.</p> - </item> - <item> - <p>XLink must be informed by knowledge of established hypermedia systems and standards.</p> - </item> - </olist> - - </p> + <olist><item><p>XLink must be straightforwardly usable over the Internet. </p></item><item><p>XLink must be usable by a wide variety of link usage domains and classes of linking application software.</p></item><item><p>XLink must support HTML 4.0 linking constructs.</p></item><item><p>The XLink expression language must be XML.</p></item><item><p>The XLink design must be formal, concise, and illustrative.</p></item><item><p>XLinks must be human-readable and human-writable.</p></item><item><p>XLinks may reside within or outside the documents in which the + participating resources reside. </p></item><item><p>XLink must represent the abstract structure and significance of links.</p></item><item><p>XLink must be feasible to implement.</p></item><item><p>XLink must be informed by knowledge of established hypermedia systems and standards.</p></item></olist> + </p> </div2> <!--Changed the list of requirements to reflect current XLink requirements document. bent--> <div2> <head>Relationship to Existing Standards</head> <p>Three standards have been especially influential: - - <ulist> - <item> - <p> - <emph>HTML:</emph> - Defines several SGML element types that represent links. </p> - </item> - <item> - <p> - <emph>HyTime:</emph> - Defines inline and out-of-line link structures and some semantic features, including traversal control and presentation of objects. <!--Changed from "placement of objects into a display or other space" -elm--> - - </p> - </item> - <item> - <p> - <emph>Text Encoding Initiative Guidelines (TEI P3):</emph> - Provides structures for creating links, aggregate objects, and link collections out of them. </p> - </item> - </ulist> - - </p> + <ulist><item><p><emph>HTML:</emph> Defines several SGML element types that represent links.</p></item><item><p><emph>HyTime:</emph> Defines inline and out-of-line link structures and some semantic features, including traversal control and presentation of objects. <!--Changed from "placement of objects into a display or other space" -elm--> + </p></item><item><p><emph>Text Encoding Initiative Guidelines (TEI P3):</emph> Provides structures for creating links, aggregate objects, and link collections out of them.</p></item></ulist> + </p> <p>Many other linking systems have also informed this design, especially Dexter, FRESS, MicroCosm, and InterMedia.</p> </div2> <div2> <head>Terminology</head> - <p>The following basic terms apply in this document. -<!--<IMG + <p>The following basic terms apply in this document. <!--<IMG SRC="local://./linkdiag.gif">(figure to be inserted)--> - - <glist> - <gitem> - <label> - <termdef id="dt-arc" term="Arc">arc</termdef> - </label> - <def> - <p>A symbolic representation of traversal behavior in links, especially the direction, context and timing of traversal.</p> - </def> - </gitem> - <gitem> - <label> - <termdef id="dt-eltree" term="Element Tree">element tree</termdef> - </label> - <def> - <p>A representation of the relevant structure specified by the tags and attributes in an XML document, based on "groves" as defined in the ISO DSSSL standard. </p> - </def> - </gitem> - <gitem> - <label> - <termdef id="dt-inline" term="In-Line Link">inline link</termdef> - </label> - <def> - <p>Abstractly, a - <termref def="dt-link">link</termref> - which serves as one of its own <termref def="dt-resource">resources</termref> -. Concretely, a link where the content of the <termref def="dt-linkel">linking element</termref> - serves as a <termref def="dt-particip-resource">participating resource</termref> -. - HTML <code>A</code> -, HyTime <code>clink</code> -, and TEI <code>XREF</code> - - are all inline links. </p> - </def> - </gitem> - <gitem> - <label> - <termdef id="dt-link" term="Link">link</termdef> - </label> - <def> - <p>An explicit relationship between two or more data objects or portions of data objects.</p> - </def> - </gitem> - <gitem> - <label> - <termdef id="dt-linkel" term="Linking Element">linking element </termdef> - </label> - <def> - <p>An - <xtermref href="WD-xml-lang.html#dt-element">element</xtermref> - that asserts the existence and describes the characteristics of a <termref def="dt-link"> link</termref> -. </p> - </def> - </gitem> - <gitem> - <label> - <termdef id="dt-local-resource" term="Local Resource">local resource</termdef> - </label> - <def> - <p>The content of an - <termref def="dt-inline">inline</termref> -linking element. Note that the content of the linking element could be explicitly pointed to by means of a regular <termref def="dt-locator">locator</termref> - in the same linking element, in which case the resource is considered <termref def="dt-remote-resource"> remote</termref> -, not local. </p> - </def> - </gitem> - <gitem> - <label> - <termdef id="dt-locator" term="Locator">locator</termdef> - </label> - <def> - <p>Data, provided as part of a link, which identifies a - - <termref def="dt-resource">resource</termref> -. </p> - </def> - </gitem> - <gitem> - <label> - <termdef id="dt-multidir" term="Multi-Directional Link">multidirectional link</termdef> - </label> - <def> - <p>A - <termref def="dt-link">link</termref> - whose <termref def="dt-traversal"> traversal</termref> - can be initiated from more than one of its <termref def="dt-particip-resource"> participating resources</termref> -. Note that being able to "go back" after following a one-directional link does not make the link multidirectional. </p> - </def> - </gitem> - <gitem> - <label> - <termdef id="dt-outofline" term="Out-of-line Link">out-of-line link</termdef> - </label> - <def> - <p>A - <termref def="dt-link">link</termref> - whose content does not serve as one of the link's <termref def="dt-particip-resource">participating resources </termref> -. Such links presuppose a notion like <termref def="dt-xlg">extended link groups</termref> -, which instruct application software where to look for links. Out-of-line links are generally required for supporting multidirectional <termref def="dt-traversal">traversal</termref> - and for allowing read-only resources to have outgoing links. </p> - </def> - </gitem> - <gitem> - <label> - <termdef id="dt-parsedq" term="Parsed">parsed</termdef> - </label> - <def> - <p>In the context of link behavior, a parsed link is any link whose content is transcluded into the document where the link originated. The use of the term "parsed" directly refers to the concept in XML of a - parsed entity.</p> - </def> - </gitem> - <gitem> - <label> - <termdef id="dt-particip-resource" term="Participating Resource"> participating resource</termdef> - </label> - <def> - <p>A - <termref def="dt-resource">resource</termref> - that belongs to a link. All resources are potential contributors to a link; participating resources are the actual contributors to a particular link. </p> - </def> - </gitem> - <gitem> - <label> - <termdef id="dt-remote-resource" term="Remote Resource">remote resource</termdef> - </label> - <def> - <p>Any participating resource of a link that is pointed to with a locator. </p> - </def> - </gitem> - <gitem> - <label> - <termdef id="dt-resource" term="Resource">resource</termdef> - </label> - <def> - <p>In the abstract sense, an addressable unit of information or service that is participating in a - <termref def="dt-link">link</termref> -. Examples include files, images, documents, programs, and query results. Concretely, anything reachable by the use of a <termref def="dt-locator">locator</termref> - in some <termref def="dt-linkel">linking element</termref> -. Note that this term and its definition are taken from the basic specifications governing the World Wide Web. <!--Joel notes: need link here. bent asks: A link?--> - - </p> - </def> - </gitem> - <gitem> - <label> - <termdef id="dt-subresource" term="sub-Resource">sub-resource</termdef> - </label> - <def> - <p>A portion of a resource, pointed to as the precise destination of a link. As one example, a link might specify that an entire document be retrieved and displayed, but that some specific part(s) of it is the specific linked data, to be treated in an application-appropriate manner such as indication by highlighting, scrolling, etc.</p> - </def> - </gitem> - <gitem> - <label> - <termdef id="dt-traversal" term="Traversal">traversal</termdef> - </label> - <def> - <p>The action of using a - <termref def="dt-link">link</termref> -; that is, of accessing a <termref def="dt-resource">resource</termref> -. Traversal may be initiated by a user action (for example, clicking on the displayed content of a <termref def="dt-linkel">linking element</termref> -) or occur under program control. </p> - </def> - </gitem> - </glist> - - </p> + <glist><gitem><label><termdef id="dt-arc" term="Arc">arc</termdef></label><def><p>A symbolic representation of traversal behavior in links, especially the direction, context and timing of traversal.</p></def></gitem><gitem><label><termdef id="dt-eltree" term="Element Tree">element tree</termdef></label><def><p>A representation of the relevant structure specified by the tags and attributes in an XML document, based on "groves" as defined in the ISO DSSSL standard. </p></def></gitem><gitem><label><termdef id="dt-inline" term="In-Line Link">inline link</termdef></label><def><p>Abstractly, a <termref def="dt-link">link</termref> which serves as one of its own <termref def="dt-resource">resources</termref>. Concretely, a link where the content of the <termref def="dt-linkel">linking element</termref> serves as a <termref def="dt-particip-resource">participating resource</termref>. + HTML <code>A</code>, HyTime <code>clink</code>, and TEI <code>XREF</code> + are all inline links.</p></def></gitem><gitem><label><termdef id="dt-link" term="Link">link</termdef></label><def><p>An explicit relationship between two or more data objects or portions of data objects.</p></def></gitem><gitem><label><termdef id="dt-linkel" term="Linking Element">linking element </termdef></label><def><p>An <xtermref href="WD-xml-lang.html#dt-element">element</xtermref> that asserts the existence and describes the characteristics of a <termref def="dt-link"> link</termref>.</p></def></gitem><gitem><label><termdef id="dt-local-resource" term="Local Resource">local resource</termdef></label><def><p>The content of an <termref def="dt-inline">inline</termref>linking element. Note that the content of the linking element could be explicitly pointed to by means of a regular <termref def="dt-locator">locator</termref> in the same linking element, in which case the resource is considered <termref def="dt-remote-resource"> remote</termref>, not local.</p></def></gitem><gitem><label><termdef id="dt-locator" term="Locator">locator</termdef> </label><def><p>Data, provided as part of a link, which identifies a + <termref def="dt-resource">resource</termref>.</p></def></gitem><gitem><label><termdef id="dt-multidir" term="Multi-Directional Link">multidirectional link</termdef></label><def><p>A <termref def="dt-link">link</termref> whose <termref def="dt-traversal"> traversal</termref> can be initiated from more than one of its <termref def="dt-particip-resource"> participating resources</termref>. Note that being able to "go back" after following a one-directional link does not make the link multidirectional.</p></def></gitem><gitem><label><termdef id="dt-outofline" term="Out-of-line Link">out-of-line link</termdef></label><def><p>A <termref def="dt-link">link</termref> whose content does not serve as one of the link's <termref def="dt-particip-resource">participating resources </termref>. Such links presuppose a notion like <termref def="dt-xlg">extended link groups</termref>, which instruct application software where to look for links. Out-of-line links are generally required for supporting multidirectional <termref def="dt-traversal">traversal</termref> and for allowing read-only resources to have outgoing links.</p></def></gitem><gitem><label><termdef id="dt-parsedq" term="Parsed">parsed</termdef></label><def><p>In the context of link behavior, a parsed link is any link whose content is transcluded into the document where the link originated. The use of the term "parsed" directly refers to the concept in XML of a + parsed entity.</p></def></gitem><gitem><label><termdef id="dt-particip-resource" term="Participating Resource"> participating resource</termdef></label><def><p>A <termref def="dt-resource">resource</termref> that belongs to a link. All resources are potential contributors to a link; participating resources are the actual contributors to a particular link.</p></def></gitem><gitem><label><termdef id="dt-remote-resource" term="Remote Resource">remote resource</termdef></label><def><p>Any participating resource of a link that is pointed to with a locator. </p></def></gitem><gitem><label><termdef id="dt-resource" term="Resource">resource</termdef></label><def><p>In the abstract sense, an addressable unit of information or service that is participating in a <termref def="dt-link">link</termref>. Examples include files, images, documents, programs, and query results. Concretely, anything reachable by the use of a <termref def="dt-locator">locator</termref> in some <termref def="dt-linkel">linking element</termref>. Note that this term and its definition are taken from the basic specifications governing the World Wide Web. <!--Joel notes: need link here. bent asks: A link?--> + </p></def></gitem><gitem><label><termdef id="dt-subresource" term="sub-Resource">sub-resource</termdef></label><def><p>A portion of a resource, pointed to as the precise destination of a link. As one example, a link might specify that an entire document be retrieved and displayed, but that some specific part(s) of it is the specific linked data, to be treated in an application-appropriate manner such as indication by highlighting, scrolling, etc.</p></def></gitem><gitem><label><termdef id="dt-traversal" term="Traversal">traversal</termdef></label><def><p>The action of using a <termref def="dt-link">link</termref>; that is, of accessing a <termref def="dt-resource">resource</termref>. Traversal may be initiated by a user action (for example, clicking on the displayed content of a <termref def="dt-linkel">linking element</termref>) or occur under program control.</p></def></gitem></glist> + </p> </div2> <div2> <head>Notation</head> - <p>The formal grammar for - <termref def="dt-locator">locators</termref> - is given using a simple Extended Backus-Naur Form (EBNF) location, as described in <xspecref href="http://www.w3.org/TR/REC-xml#sec-notation">the XML specification</xspecref> -. </p> + <p>The formal grammar for <termref def="dt-locator">locators</termref> is given using a simple Extended Backus-Naur Form (EBNF) location, as described in <xspecref href="http://www.w3.org/TR/REC-xml#sec-notation">the XML specification</xspecref>.</p> <!-- fixed link to XML spec - bent --> </div2> </div1> <div1 id="addressing"> <?Pub Dtl?> <head>Locator Syntax</head> - <p>The locator for a - <termref def="dt-resource">resource</termref> - is typically provided by means of a Uniform Resource Identifier, or URI. XPointers can be used in conjunction with the URI structure, as fragment identifiers, to specify a more precise sub-resource. </p> + <p>The locator for a <termref def="dt-resource">resource</termref> is typically provided by means of a Uniform Resource Identifier, or URI. XPointers can be used in conjunction with the URI structure, as fragment identifiers, to specify a more precise sub-resource. </p> <!-- Removed the discussion of queries from the previous paragraph, due to contention within the WG. bent --> - <p>A locator generally contains a URI, as described in IETF RFCs - <bibref ref="rfc1738"/> - and <bibref ref="rfc1808"/> -. As these RFCs state, the URI may include a trailing <emph>query</emph> - (marked by a leading " <code>?</code> -"), and be followed by a " <code>#</code> -" and a <emph>fragment identifier</emph> -, with the query interpreted by the host providing the indicated resource, and the interpretation of the fragment identifier dependent on the data type of the indicated resource. </p> + <p>A locator generally contains a URI, as described in IETF RFCs <bibref ref="rfc1738"/> and <bibref ref="rfc1808"/>. As these RFCs state, the URI may include a trailing <emph>query</emph> (marked by a leading "<code>?</code>"), and be followed by a "<code>#</code>" and a <emph>fragment identifier</emph>, with the query interpreted by the host providing the indicated resource, and the interpretation of the fragment identifier dependent on the data type of the indicated resource.</p> <!--Is there some restriction on URNs having queries and/or fragment identifiers? Since these RFCs don't mention URIs explicitly, should the wording here lead from URLs to URIs more explicitly? -elm--> - <p>In order to locate XML documents and portions of documents, a locator value may contain either a - <xtermref href="http://www.w3.org/Addressing/rfc1738.txt"> URI</xtermref> - or a fragment identifier, or both. Any fragment identifier for pointing into XML must be an <xtermref href="http://www.w3.org/TR/WD-xptr#dt-xpointer"> XPointer</xtermref> -. </p> + <p>In order to locate XML documents and portions of documents, a locator value may contain either a <xtermref href="http://www.w3.org/Addressing/rfc1738.txt"> URI</xtermref> or a fragment identifier, or both. Any fragment identifier for pointing into XML must be an <xtermref href="http://www.w3.org/TR/WD-xptr#dt-xpointer"> XPointer</xtermref>.</p> <p>Special syntax may be used to request the use of particular processing models in accessing the locator's resource. This is designed to reflect the realities of network operation, where it may or may not be desirable to exercise fine control over the distribution of work between local and remote processors. - - <scrap id="locator" lang="ebnf"> - <head>Locator</head> - <prod id="nt-locator"> - <lhs>Locator</lhs> - <rhs> - <nt def="nt-uri">URI</nt> - </rhs> - <rhs>| - <nt def="nt-connector">Connector</nt> - ( <xnt href="http://www.w3.org/TR/WD-xptr">XPointer</xnt> - | <xnt href="WD-xml-lang.html#NT-Name">Name</xnt> -) </rhs> - <rhs>| - <nt def="nt-uri">URI</nt> - <nt def="nt-connector">Connector</nt> - ( <xnt href="http://www.w3.org/TR/WD-xptr">XPointer</xnt> - | <xnt href="WD-xml-lang.html#NT-Name">Name</xnt> -) </rhs> - </prod> - <prod id="nt-connector"> - <lhs>Connector</lhs> - <rhs>'#' | '|'</rhs> - </prod> - <prod id="nt-uri"> - <lhs>URI</lhs> - <rhs> - <xnt href="WD-xml-lang.html#NT-URLchar">URIchar*</xnt> - </rhs> - </prod> - </scrap> - - </p> - <p> - <termdef id="dt-designated" term="Designated Resource">In this discussion, the term - <term>designated resource</term> - refers to the resource which an entire locator serves to locate. </termdef> - The following rules apply: - <ulist> - <item> - <p> - <termdef id="dt-containing-resource" term="Containing Resource"> The URI, if provided, locates a resource called the - <term>containing resource</term> -. </termdef> - </p> - </item> - <item> - <p>If the URI is not provided, the containing resource is considered to be the document in which the linking element is contained. - </p> - </item> - <item> - <p> - <termdef id="dt-sub-resource" term="Sub-Resource">If an XPointer is provided, the designated resource is a - <term>sub-resource</term> - + <scrap id="locator" lang="ebnf"><head>Locator</head><prod id="nt-locator"><lhs>Locator</lhs><rhs><nt def="nt-uri">URI</nt></rhs><rhs>| <nt def="nt-connector">Connector</nt> (<xnt href="http://www.w3.org/TR/WD-xptr">XPointer</xnt> | <xnt href="WD-xml-lang.html#NT-Name">Name</xnt>)</rhs><rhs>| <nt def="nt-uri">URI</nt> <nt def="nt-connector">Connector</nt> (<xnt href="http://www.w3.org/TR/WD-xptr">XPointer</xnt> | <xnt href="WD-xml-lang.html#NT-Name">Name</xnt>)</rhs></prod><prod id="nt-connector"><lhs>Connector</lhs><rhs>'#' | '|'</rhs></prod><prod id="nt-uri"><lhs>URI</lhs><rhs><xnt href="WD-xml-lang.html#NT-URLchar">URIchar*</xnt></rhs></prod></scrap> + </p> + <p><termdef id="dt-designated" term="Designated Resource">In this discussion, the term <term>designated resource</term> refers to the resource which an entire locator serves to locate.</termdef> The following rules apply: + <ulist><item><p><termdef id="dt-containing-resource" term="Containing Resource"> The URI, if provided, locates a resource called the <term>containing resource</term>.</termdef></p></item><item><p>If the URI is not provided, the containing resource is considered to be the document in which the linking element is contained. + </p></item><item><p><termdef id="dt-sub-resource" term="Sub-Resource">If an XPointer is provided, the designated resource is a <term>sub-resource</term> of the containing resource; otherwise the designated resource is the - containing resource. </termdef> - </p> - </item> -<!--Is this now incorrect, given the nature of the switch from here() to origin()? -elm - Oy, yes, i think so. it will require some fun wording, though, so i haven't fixed it yet here -sjd--> - <item> - <p>If the - <nt def="nt-connector">Connector</nt> - is followed directly by a <xnt href="http://www.w3.org/TR/REC-xml#NT-Name">Name</xnt> -, the <xnt href="http://www.w3.org/TR/REC-xml#NT-Name">Name</xnt> - is shorthand for the XPointer" <code>id(Name)</code> -"; that is, the sub-resource is the element in the containing resource that has an XML <xtermref href="http://www.w3.org/TR/REC-xml#sec-attrtypes">ID attribute</xtermref> - whose value <xtermref href="http://www.w3.org/TR/REC-xml#dt-match">matches</xtermref> - the <xnt href="http://www.w3.org/TR/REC-xml#NT-Name">Name</xnt> -. This shorthand is to encourage use of the robust <code>id</code> - addressing mode. </p> - </item> -<!-- fixed links to the XML recommendation - bent --> - <item> - <p>If the connector is " - <code>#</code> -", this signals an intent that the containing resource is to be fetched as a whole from the host that provides it, and that the XPointer processing to extract the sub-resource - is to be performed on the client, that is to say on the same system where the linking element is recognized and processed. </p> - </item> - <item> - <p>If the connector is " - <code>|</code> -", no intent is signaled as to what processing model is to be used to go about accessing the designated resource. </p> - </item> - </ulist> - - </p> + containing resource.</termdef></p></item><!--Is this now incorrect, given the nature of the switch from here() to origin()? -elm + Oy, yes, i think so. it will require some fun wording, though, so i haven't fixed it yet here -sjd--><item><p>If the <nt def="nt-connector">Connector</nt> is followed directly by a <xnt href="http://www.w3.org/TR/REC-xml#NT-Name">Name</xnt>, the <xnt href="http://www.w3.org/TR/REC-xml#NT-Name">Name</xnt> is shorthand for the XPointer"<code>id(Name)</code>"; that is, the sub-resource is the element in the containing resource that has an XML <xtermref href="http://www.w3.org/TR/REC-xml#sec-attrtypes">ID attribute</xtermref> whose value <xtermref href="http://www.w3.org/TR/REC-xml#dt-match">matches</xtermref> the <xnt href="http://www.w3.org/TR/REC-xml#NT-Name">Name</xnt>. This shorthand is to encourage use of the robust <code>id</code> addressing mode.</p></item><!-- fixed links to the XML recommendation - bent --><item><p>If the connector is "<code>#</code>", this signals an intent that the containing resource is to be fetched as a whole from the host that provides it, and that the XPointer processing to extract the sub-resource + is to be performed on the client, that is to say on the same system where the linking element is recognized and processed.</p></item><item><p>If the connector is "<code>|</code>", no intent is signaled as to what processing model is to be used to go about accessing the designated resource.</p></item></ulist> + </p> <p>Note that the definition of a URI includes an optional query component. </p> <p>In the case where the URI contains a query (to be interpreted by the server), information providers and authors of server software are urged to use queries as follows: - - <scrap id="querysyntax" lang="ebnf"> - <head>Query</head> - <prod id="nt-query"> - <lhs>Query</lhs> - <rhs>'XML-XPTR=' ( - <xnt href="http://www.w3.org/TR/WD-xptr"> XPointer</xnt> - | <xnt href="http://www.w3.org/TR/REC-xml#NT-Name">Name</xnt> -) </rhs> - </prod> - </scrap> - - </p> + <scrap id="querysyntax" lang="ebnf"><head>Query</head><prod id="nt-query"><lhs>Query</lhs><rhs>'XML-XPTR=' (<xnt href="http://www.w3.org/TR/WD-xptr"> XPointer</xnt> | <xnt href="http://www.w3.org/TR/REC-xml#NT-Name">Name</xnt>)</rhs></prod></scrap> + </p> <!-- fixed link to XML recommendation - bent --> </div1> <div1> <?Pub Dtl?> <head>Link Recognition</head> - <p>The existence of a - <termref def="dt-link">link</termref> - is asserted by a <termref def="dt-linkel">linking element</termref> -. Linking elements must be recognized reliably by application software in order to provide appropriate display and behavior. There are several ways link recognition could be accomplished: for example, reserving element type names, reserving attributes names, leaving the matter of recognition entirely up to stylesheets and application software, or using the XLink <xtermref href="http://www.w3.org/TR/REC-xml-names/">namespace</xtermref> - to specify element names and attribute names that would be recognized by namespace and XLink-aware processors. Using element and attribute names within the XLink namespace provides a balance between giving users control of their own markup language design and keeping the identification of linking elements simple and unambiguous. </p> - <p>The two approaches to identifying linking elements are relatively simple to implement. For example, here's how the HTML - <code>A</code> - element would be declared using attributes within the XLink namespace, and then how an element within the XLink namespace might do the same: - <eg><A xlink:type="simple" xlink:href="http://www.w3.org/TR/wd-xlink/" + <p>The existence of a <termref def="dt-link">link</termref> is asserted by a <termref def="dt-linkel">linking element</termref>. Linking elements must be recognized reliably by application software in order to provide appropriate display and behavior. There are several ways link recognition could be accomplished: for example, reserving element type names, reserving attributes names, leaving the matter of recognition entirely up to stylesheets and application software, or using the XLink <xtermref href="http://www.w3.org/TR/REC-xml-names/">namespace</xtermref> to specify element names and attribute names that would be recognized by namespace and XLink-aware processors. Using element and attribute names within the XLink namespace provides a balance between giving users control of their own markup language design and keeping the identification of linking elements simple and unambiguous.</p> + <p>The two approaches to identifying linking elements are relatively simple to implement. For example, here's how the HTML <code>A</code> element would be declared using attributes within the XLink namespace, and then how an element within the XLink namespace might do the same: + <eg><A xlink:type="simple" xlink:href="http://www.w3.org/TR/wd-xlink/" xlink:title="The Xlink Working Draft">The XLink Working Draft.</A></eg> - - <eg><xlink:simple href="http://www.w3.org/TR/wd-xlink/" + <eg><xlink:simple href="http://www.w3.org/TR/wd-xlink/" title="The XLink Working Draft">The XLink Working Draft</xlink:simple></eg> - - Any arbitrary element can be made into an XLink by using the <code>xlink:type</code> - attribute. And, of course, the explicit XLink elements may be used, as well. This document will go on to describe the linking attributes that are associated with linking elements. It may be assumed by the reader that these attributes would require the <code>xlink</code> - namespace prefix if they existed within an arbitrary element, or that they may be used directly if they exist within an explicit Xlink element. </p> + Any arbitrary element can be made into an XLink by using the <code>xlink:type</code> attribute. And, of course, the explicit XLink elements may be used, as well. This document will go on to describe the linking attributes that are associated with linking elements. It may be assumed by the reader that these attributes would require the <code>xlink</code> namespace prefix if they existed within an arbitrary element, or that they may be used directly if they exist within an explicit Xlink element.</p> <!-- heavily modified this section to accomodate namespace-aware link recognition - bent --> </div1> <!-- Rewrote this entire section. - bent --> <div1> <head>Linking Attributes</head> - <p>XLink has several attributes associated with the variety of links it may represent. These attributes define four main concepts: locators, arcs, behaviors, and semantics. - <emph>Locators</emph> - define where the actual resource is located. <emph>Arcs</emph> - define the traversal of links. Where does the link come from? Where does it go to? All this information can be stored in the arc attributes. <emph>Behaviors</emph> - define how the link is activated, and what the application should do with the resource being linked to. <emph>Semantics</emph> - define useful information that the application may use, and enables the link for such specalized targets as constricted devices and accessibility software. </p> + <p>XLink has several attributes associated with the variety of links it may represent. These attributes define four main concepts: locators, arcs, behaviors, and semantics. <emph>Locators</emph> define where the actual resource is located. <emph>Arcs</emph> define the traversal of links. Where does the link come from? Where does it go to? All this information can be stored in the arc attributes. <emph>Behaviors</emph> define how the link is activated, and what the application should do with the resource being linked to. <emph>Semantics</emph> define useful information that the application may use, and enables the link for such specalized targets as constricted devices and accessibility software.</p> <div2 id="link-locators"> <head>Locator Attributes</head> - <p>The only locator attribute at this time is - <code>href</code> -. This attribute must contain either a string in the form of a URI that defines the remote resource being linked to, a string containing a fragment identifier that links to a local resource, or a string containing a URI with a fragment identifier concacenated onto it. </p> + <p>The only locator attribute at this time is <code>href</code>. This attribute must contain either a string in the form of a URI that defines the remote resource being linked to, a string containing a fragment identifier that links to a local resource, or a string containing a URI with a fragment identifier concacenated onto it.</p> </div2> <div2 id="link-arcs"> <head>Arc Attributes</head> - <p>Arcs contain two attributes, - <code>from</code> - and <code>to</code> -. The <code>from</code> - attribute may contain a string containing the content of a <code>role</code> - attribute from the resource being linked from. The purpose of the <code>from</code> - attribute is to define where this link is being actuated from. </p> - <p>The - <code>to</code> - attribute may contain a string containing the content of a <code>role</code> - attribute from the resource being linked to. The purpose of the <code>to</code> - attribute is to define where this link traverses to. </p> + <p>Arcs contain two attributes, <code>from</code> and <code>to</code>. The <code>from</code> attribute may contain a string containing the content of a <code>role</code> attribute from the resource being linked from. The purpose of the <code>from</code> attribute is to define where this link is being actuated from.</p> + <p>The <code>to</code> attribute may contain a string containing the content of a <code>role</code> attribute from the resource being linked to. The purpose of the <code>to</code> attribute is to define where this link traverses to.</p> <p>The application may use this information in a number of ways, especially in a complex hypertext system, but it is mainly useful in providing context for application behavior.</p> <!-- I'm at a loss as to how to describe arcs more clearly than this. I don't want to devolve into discussions of directed graphs and n-ary links. -bent --> </div2> <div2 id="link-behaviors"> <head>Behavior Attributes</head> - <p>There are two attributes associated with behavior: - <code>show</code> - and <code>actuate</code> -. The <code>show</code> - attribute defines how the remote resource is to be revealed to the user. It has three options: <code>new</code> -, <code>parsed</code> -, and <code>replace</code> -. The <code>new</code> - option indicates that the remote resource should be shown in a new window (or other device context) without replacing the previous content. The <code>parsed</code> - option, relating directly to the XML concept of a parsed entity, indicates that the content should be integrated into the document from which the link was actuated. The <code>replace</code> - option is the one most commonly seen on the World Wide Web, where the document being linked from is entirely replaced by the object being linked to. </p> - <p>The - <code>actuate</code> - attribute defines how the link is initiated. It has two options: <code>user</code> - and <code>auto</code> -. The <code>user</code> - option indicates that the link must be initiated by some sort of human-initiated selection, such as clicking on an HTML anchor. The <code>auto</code> - option indicates that the link is automatically initiated when the application deems that the user has reached the link. It then follows the behavior set out in the <code>show</code> - option. </p> + <p>There are two attributes associated with behavior: <code>show</code> and <code>actuate</code>. The <code>show</code> attribute defines how the remote resource is to be revealed to the user. It has three options: <code>new</code>, <code>parsed</code>, and <code>replace</code>. The <code>new</code> option indicates that the remote resource should be shown in a new window (or other device context) without replacing the previous content. The <code>parsed</code> option, relating directly to the XML concept of a parsed entity, indicates that the content should be integrated into the document from which the link was actuated. The <code>replace</code> option is the one most commonly seen on the World Wide Web, where the document being linked from is entirely replaced by the object being linked to.</p> + <p>The <code>actuate</code> attribute defines how the link is initiated. It has two options: <code>user</code> and <code>auto</code>. The <code>user</code> option indicates that the link must be initiated by some sort of human-initiated selection, such as clicking on an HTML anchor. The <code>auto</code> option indicates that the link is automatically initiated when the application deems that the user has reached the link. It then follows the behavior set out in the <code>show</code> option.</p> <!-- Something should be put here in terms of an example. Idea: "A" link versus automatically updating encyclopedia. -bent --> </div2> <div2 id="link-semantics"> <head>Semantic Attributes</head> - <p>There are two attributes associated with semantics, - <code>role</code> - and <code>title</code> -. The <code>role</code> - attribute is a generic string used to describe the function of the link's content. For example, a poem might have a link with a <code>role="stanza"</code> -. The <code>role</code> - is also used as an identifier for the <code>from</code> - and <code>to</code> - attributes of arcs. </p> - <p>The - <code>title</code> - attribute is designed to provide human-readable text describing the link. It is very useful for those who have text-based applications, whether that be due to a constricted device that cannot display the link's content, or if it's being read by an application to a visually-impaired user, or if it's being used to create a table of links. The <code>title</code> - attribute contains a simple, descriptive string. </p> + <p>There are two attributes associated with semantics, <code>role</code> and <code>title</code>. The <code>role</code> attribute is a generic string used to describe the function of the link's content. For example, a poem might have a link with a <code>role="stanza"</code>. The <code>role</code> is also used as an identifier for the <code>from</code> and <code>to</code> attributes of arcs.</p> + <p>The <code>title</code> attribute is designed to provide human-readable text describing the link. It is very useful for those who have text-based applications, whether that be due to a constricted device that cannot display the link's content, or if it's being read by an application to a visually-impaired user, or if it's being used to create a table of links. The <code>title</code> attribute contains a simple, descriptive string.</p> </div2> </div1> <div1 id="linking-elements"> <head>Linking Elements</head> - <p>There are several kinds of linking elements in XLink: - <code>simple</code> - links, <code>locators</code> -, <code>arcs</code> -, and <code>extended</code> - links. These elements may be instantiated via element declarations from the XLink namespace, or they may be instantiated via attribute declarations from the XLink namespace. Both kinds of instantiation are described in the definition of each linking element. </p> - <p>The - <code>simple</code> - link is used to declare a link that approximates the functionality of the HTML <code>A</code> - element. It has, however, a few added features to increase its value, including the potential declaration of semantics and behavior. The <code>locator</code> - elements are used to define the resource being linked to. Some links may contain multiple locators, representing a choice of potential links to be traversed. The <code>arcs</code> - are used to define the traversal semantics of the link. Finally, an <code>extended</code> - linking element differs from a simple link in that it can connect any number of resources, not just one local resource (optionally) and one remote resource, and in that extended links are more often out-of-line than simple links. </p> + <p>There are several kinds of linking elements in XLink: <code>simple</code> links, <code>locators</code>, <code>arcs</code>, and <code>extended</code> links. These elements may be instantiated via element declarations from the XLink namespace, or they may be instantiated via attribute declarations from the XLink namespace. Both kinds of instantiation are described in the definition of each linking element.</p> + <p>The <code>simple</code> link is used to declare a link that approximates the functionality of the HTML <code>A</code> element. It has, however, a few added features to increase its value, including the potential declaration of semantics and behavior. The <code>locator</code> elements are used to define the resource being linked to. Some links may contain multiple locators, representing a choice of potential links to be traversed. The <code>arcs</code> are used to define the traversal semantics of the link. Finally, an <code>extended</code> linking element differs from a simple link in that it can connect any number of resources, not just one local resource (optionally) and one remote resource, and in that extended links are more often out-of-line than simple links.</p> <div2 id="simple-links"> <head>Simple Links</head> - <p id="dt-simplelink"> - <termdef id="dt-simpleline" term="Simple Link"> - <term>Simple links</term> - can be used for purposes that approximate the functionality of a basic HTML <code>A</code> - link, but they can also support a limited amount of additional functionality. Simple links have only one locator and thus, for convenience, combine the functions of a linking element and a locator into a single element. </termdef> - As a result of this combination, the simple linking element offers both a locator attribute and all the behavior and semantic attributes. </p> + <p id="dt-simplelink"><termdef id="dt-simpleline" term="Simple Link"><term>Simple links</term> can be used for purposes that approximate the functionality of a basic HTML <code>A</code> link, but they can also support a limited amount of additional functionality. Simple links have only one locator and thus, for convenience, combine the functions of a linking element and a locator into a single element.</termdef> As a result of this combination, the simple linking element offers both a locator attribute and all the behavior and semantic attributes.</p> <p>The following are two examples of linking elements, each showing all the possible attributes that can be associated with a simple link. Here is the explicit XLink simple linking element. - - <eg><!ELEMENT xlink:simple ANY> + <eg><!ELEMENT xlink:simple ANY> <!ATTLIST xlink:slink href CDATA #REQUIRED role CDATA #IMPLIED @@ -655,9 +228,8 @@ title="The XLink Working Draft">The XLink Working Draft</xlink:s show (new|parsed|replace) "replace" actuate (user|auto) "user" ></eg> - And here is how to make an arbitrary element into a simple link. - <eg><!ELEMENT xlink:simple ANY> + <eg><!ELEMENT xlink:simple ANY> <!ATTLIST foo xlink:type (simple|extended|locator|arc) #FIXED "simple" xlink:href CDATA #REQUIRED @@ -666,28 +238,22 @@ title="The XLink Working Draft">The XLink Working Draft</xlink:s xlink:show (new|parsed|replace) "replace" xlink:actuate (user|auto) "user" ></eg> - Here is how the first example might look in a document: - <eg><xlink:simple href="http://www.w3.org/TR/wd-xlink" role="working draft" +<eg><xlink:simple href="http://www.w3.org/TR/wd-xlink" role="working draft" title="The XLink Working Draft" show="replace" actuate="user"> The XLink Working Draft.</xlink:simple></eg> - - <eg><foo xlink:href="http://www.w3.org/TR/wd-xlink" xlink:role="working draft" +<eg><foo xlink:href="http://www.w3.org/TR/wd-xlink" xlink:role="working draft" xlink:title="The XLink Working Draft" xlink:show="new" xlink:actuate="user"> The XLink Working Draft.</foo></eg> - Alternately, a simple link could be as terse as this: - <eg><foo xlink:href="#stanza1">The First Stanza.</foo></eg> - - </p> +<eg><foo xlink:href="#stanza1">The First Stanza.</foo></eg> + </p> <p> There are no constraints on the contents of a simple linking element. In - the sample declaration above, it is given a content model of - <code>ANY</code> - + the sample declaration above, it is given a content model of <code>ANY</code> to illustrate that any content model or declared content is acceptable. In a valid document, every element that is significant to XLink must still conform - to the constraints expressed in its governing DTD. </p> + to the constraints expressed in its governing DTD.</p> <p>Note that it is meaningful to have an out-of-line simple link, although such links are uncommon. They are called "one-ended" and are typically used to associate discrete semantic properties with locations. The properties might @@ -699,58 +265,27 @@ The XLink Working Draft.</foo></eg> <div2 id="extended-link"> <head>Extended Links</head> <p> - <termdef id="dt-extendedlink" term="Extended Link">An - <term>extended link</term> - differs from a simple link in that it can connect any number of resources, not just one local resource (optionally) and one remote resource, and in that extended links are more often out-of-line than simple links. </termdef> + <termdef id="dt-extendedlink" term="Extended Link">An <term>extended link</term> differs from a simple link in that it can connect any number of resources, not just one local resource (optionally) and one remote resource, and in that extended links are more often out-of-line than simple links.</termdef> </p> <p>These additional capabilities of extended links are required for: - - <ulist> - <item> - <p>Enabling outgoing links in documents that cannot be modified to add an inline link</p> - </item> - <item> - <p>Creating links to and from resources in formats with no native support for embedded links (such as most multimedia formats)</p> - </item> - <item> - <p>Applying and filtering sets of relevant links on demand</p> - </item> - <item> - <p>Enabling other advanced hypermedia capabilities</p> - </item> - </ulist> - - </p> + <ulist><item><p>Enabling outgoing links in documents that cannot be modified to add an inline link</p></item><item><p>Creating links to and from resources in formats with no native support for embedded links (such as most multimedia formats)</p></item><item><p>Applying and filtering sets of relevant links on demand</p></item><item><p>Enabling other advanced hypermedia capabilities</p></item></ulist> + </p> <p>Application software might be expected to provide traversal among all of a link's participating resources (subject to semantic constraints outside the scope of this specification) and to signal the fact that a given resource or sub-resource participates in one or more links when it is displayed (even though there is no markup at exactly that point to signal it).</p> - <p>A linking element for an extended link contains a series of - <xtermref href="http://www.w3.org/TR/REC-xml/#dt-parentchild">child elements</xtermref> - that serve as locators and arcs. Because an extended link can have more than one remote resource, it separates out linking itself from the mechanisms used to locate each resource (whereas a simple link combines the two). </p> - <p>The - <code>xlink:type</code> - attribute value for an extended link must be <code> extended</code> -, if the link is being instantiated on an arbitrary element. Note that extended links introduce variants of the <code>show</code> - and <code>actuate</code> - behavior attributes. These attributes, the <code>showdefault</code> - and <code>actuatedefault</code> - define the same behavior as their counterparts. However, in this case, they are considered to define the default behavior for all the linking elements that they contain. </p> - <p>However, when a linking element within an extended link has a - <code>show</code> - or <code>actuate</code> - attribute of its own, that attribute overrides the defaults set on the extended linking element. </p> + <p>A linking element for an extended link contains a series of <xtermref href="http://www.w3.org/TR/REC-xml/#dt-parentchild">child elements</xtermref> that serve as locators and arcs. Because an extended link can have more than one remote resource, it separates out linking itself from the mechanisms used to locate each resource (whereas a simple link combines the two).</p> + <p>The <code>xlink:type</code> attribute value for an extended link must be <code> extended</code>, if the link is being instantiated on an arbitrary element. Note that extended links introduce variants of the <code>show</code> and <code>actuate</code> behavior attributes. These attributes, the <code>showdefault</code> and <code>actuatedefault</code> define the same behavior as their counterparts. However, in this case, they are considered to define the default behavior for all the linking elements that they contain.</p> + <p>However, when a linking element within an extended link has a <code>show</code> or <code>actuate</code> attribute of its own, that attribute overrides the defaults set on the extended linking element.</p> <p>The extended linking element itself retains those attributes relevant to the link as a whole, and to its local resource if any. Following are two sample declaration for an extended link. The first is an example of the explicit XLink extended link: - - <eg><!ELEMENT xlink:extended ((xlink:arc | xlink:locator)*)> +<eg><!ELEMENT xlink:extended ((xlink:arc | xlink:locator)*)> <!ATTLIST xlink:extended role CDATA #IMPLIED title CDATA #IMPLIED showdefault (new|parsed|replace) #IMPLIED actuatedefault (user|auto) #IMPLIED ></eg> - The second is an example of an arbitrary element being used an extended link: - <eg><!ELEMENT foo ((xlink:arc | xlink:locator)*)> +<eg><!ELEMENT foo ((xlink:arc | xlink:locator)*)> <!ATTLIST foo xlink:type (simple|extended|locator|arc) #FIXED "extended" xlink:role CDATA #IMPLIED @@ -758,60 +293,38 @@ The XLink Working Draft.</foo></eg> xlink:showdefault (new|parsed|replace) #IMPLIED xlink:actuatedefault (user|auto) #IMPLIED ></eg> - The following two examples demonstrate how each of the above might appear within a document instance. Note that the content of these examples would be other elements. For brevity's sake, they've been left blank. The first example shows how the link might appear, using an explicit XLink extended link: - <eg><xlink:extended role="address book" title="Ben's Address Book" showdefault="replace" actuatedefault="user"> ... </xlink:extended></eg> - +<eg><xlink:extended role="address book" title="Ben's Address Book" showdefault="replace" actuatedefault="user"> ... </xlink:extended></eg> And the second shows how the link might appear, using an arbitrary element: - <eg><foo xlink:type="extended" xlink:role="address book" xlink:title="Ben's Address Book" xlink:showdefault="replace" xlink:actuatedefault="user"> ... </foo></eg> - - </p> +<eg><foo xlink:type="extended" xlink:role="address book" xlink:title="Ben's Address Book" xlink:showdefault="replace" xlink:actuatedefault="user"> ... </foo></eg> + </p> </div2> <div2 id="xlink-arcs"> <head>Arc Elements</head> - <p> - <termdef id="dt-arc" term="Arc">An - <term>arc</term> - is contained within an extended link for the purpose of defining traversal behavior. </termdef> - More than one arc may be associated with a link. Otherwise, arc elements function exactly as the arc attributes might lead on to expect. </p> + <p><termdef id="dt-arc" term="Arc">An <term>arc</term> is contained within an extended link for the purpose of defining traversal behavior.</termdef> More than one arc may be associated with a link. Otherwise, arc elements function exactly as the arc attributes might lead on to expect.</p> <!-- More here? -bent --> </div2> </div1> <div1> <head>Conformance</head> - <p>An element conforms to XLink if: - <olist> - <item> - <p>The element has an - <code>xml:link</code> - attribute whose value is -one of the attribute values prescribed by this specification, and </p> - </item> - <item> - <p>the element and all of its attributes and content adhere to the + <p>An element conforms to XLink if: <olist><item><p>The element has an <code>xml:link</code> attribute whose value is +one of the attribute values prescribed by this specification, and</p></item><item><p>the element and all of its attributes and content adhere to the syntactic -requirements imposed by the chosen - <code>xml:link</code> - attribute value, -as prescribed in this specification. </p> - </item> - </olist> - </p> +requirements imposed by the chosen <code>xml:link</code> attribute value, +as prescribed in this specification.</p></item></olist></p> <p>Note that conformance is assessed at the level of individual elements, rather than whole XML documents, because XLink and non-XLink linking mechanisms may be used side by side in any one document.</p> <p>An application conforms to XLink if it interprets XLink-conforming elements according to all required semantics prescribed by this specification and, for any optional semantics it chooses to support, supports them in the way -prescribed. -<!--If/when we split out the XLinkfunctionality +prescribed. <!--If/when we split out the XLinkfunctionality (e.g. inline links and out-of-line links), the conformance language will have to address the different -levels of support. -elm--> - </p> +levels of support. -elm--> </p> </div1> </body> <back> @@ -827,62 +340,41 @@ version will provide a mechanism for the use of structured link titles.</p> <div1> <head>References</head> <blist> - <bibl id="xptr" key="XPTR">Eve Maler and Steve DeRose, editors. - <titleref> -XML Pointer Language (XPointer) V1.0</titleref> -. ArborText, Inso, and Brown + <bibl id="xptr" key="XPTR">Eve Maler and Steve DeRose, editors. <titleref> +XML Pointer Language (XPointer) V1.0</titleref>. ArborText, Inso, and Brown University. Burlington, Seekonk, et al.: World Wide Web Consortium, 1998. -(See <loc href="http://www.w3.org/TR/WD-xptr">http://www.w3.org/TR/WD-xptr - </loc> -.) </bibl> +(See <loc href="http://www.w3.org/TR/WD-xptr">http://www.w3.org/TR/WD-xptr + </loc>.)</bibl> <bibl id="iso10744" key="ISO/IEC 10744">ISO (International Organization for -Standardization). - <titleref>ISO/IEC 10744-1992 (E). Information technology -- Hypermedia/Time-based Structuring Language (HyTime).</titleref> - [Geneva]: -International Organization for Standardization, 1992. <titleref>Extended +Standardization). <titleref>ISO/IEC 10744-1992 (E). Information technology +- Hypermedia/Time-based Structuring Language (HyTime).</titleref> [Geneva]: +International Organization for Standardization, 1992. <titleref>Extended Facilities -Annex.</titleref> - [Geneva]: International Organization for Standardization, -1996. (See <loc href="http://www.ornl.gov/sgml/wg8/hytime/html/is10744r.html">http://www.ornl.go -v/sgml/wg8/hytime/html/is10744r.html </loc> - <!--p m-r says this link is -broken. elm --> - ). </bibl> +Annex.</titleref> [Geneva]: International Organization for Standardization, +1996. (See <loc href="http://www.ornl.gov/sgml/wg8/hytime/html/is10744r.html">http://www.ornl.go +v/sgml/wg8/hytime/html/is10744r.html </loc> <!--p m-r says this link is +broken. elm --> ).</bibl> <bibl id="rfc1738" key="IETF RFC 1738">IETF (Internet Engineering Task -Force). - <titleref> -RFC 1738: Uniform Resource Locators</titleref> -. 1991. (See <loc href="http://www.w3.org/Addressing/rfc1738.txt"> -http://www.w3.org/Addressing/rfc1738.txt</loc> -). </bibl> +Force). <titleref> +RFC 1738: Uniform Resource Locators</titleref>. 1991. (See <loc href="http://www.w3.org/Addressing/rfc1738.txt"> +http://www.w3.org/Addressing/rfc1738.txt</loc>).</bibl> <bibl id="rfc1808" key="IETF RFC 1808">IETF (Internet Engineering Task -Force). - <titleref> -RFC 1808: Relative Uniform Resource Locators</titleref> -. 1995. (See <loc href="http://www.w3.org/Addressing/rfc1808.txt">http://www.w3.org/Addressing/rfc -1808.txt </loc> -). </bibl> +Force). <titleref> +RFC 1808: Relative Uniform Resource Locators</titleref>. 1995. (See <loc href="http://www.w3.org/Addressing/rfc1808.txt">http://www.w3.org/Addressing/rfc +1808.txt </loc>).</bibl> <bibl id="tei" key="TEI">C. M. Sperberg-McQueen and Lou Burnard, editors. - - <titleref> -Guidelines for Electronic Text Encoding and Interchange</titleref> -. Association +<titleref> +Guidelines for Electronic Text Encoding and Interchange</titleref>. Association for Computers and the Humanities (ACH), Association for Computational Linguistics (ACL), and Association for Literary and Linguistic Computing (ALLC). Chicago, -Oxford: Text Encoding Initiative, 1994. <!-- add cite to DOM work --> - </bibl> +Oxford: Text Encoding Initiative, 1994. <!-- add cite to DOM work --> </bibl> <bibl id="chum" key="CHUM">]Steven J. DeRose and David G. Durand. 1995. "The -TEI Hypertext Guidelines." In - <titleref>Computing and the Humanities -</titleref> -29(3). -Reprinted in <titleref>Text Encoding Initiative: Background and -Context</titleref> -, -ed. Nancy Ide and Jean ronis <!-- fix this name --> -, ISBN 0-7923-3704-2. </bibl> +TEI Hypertext Guidelines." In <titleref>Computing and the Humanities +</titleref>29(3). +Reprinted in <titleref>Text Encoding Initiative: Background and +Context</titleref>, +ed. Nancy Ide and Jean ronis <!-- fix this name -->, ISBN 0-7923-3704-2. </bibl> </blist> </div1> </back> |