mirrors/htmlpurifier
0
0
Fork 0
mirror of https://github.com/ezyang/htmlpurifier.git synced 2024-11-09 23:28:42 +00:00
Code Releases Activity

Commit updated spec files in preparation for attributes.

Browse Source 
git-svn-id: http://htmlpurifier.org/svnroot/htmlpurifier/trunk@126 48356398-32a2-884e-a903-53898d9a118a
This commit is contained in:
Edward Z. Yang 2006-07-30 00:29:26 +00:00
parent f881061d5f
commit 4c737ab430
3 changed files with 1511 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

271
docs/dtd/xhtml1-purified.dtd Normal file
View File

@ -0,0 +1,271 @@
<!-- Transform %TextAlign to align:value in style -->
<!-- text alignment for p, div, h1-h6. The default is
align="left" for ltr headings, "right" for rtl
Move to style! -->
<!ENTITY % TextAlign "DEPRECATED align (left|center|right|justify) #IMPLIED">
<!-- type and start should have CSS equivalents -->
<!ENTITY % ULStyle "(disc|square|circle)">
<!-- Ordered list numbering style
1 arabic numbers 1, 2, 3, ...
a lower alpha a, b, c, ...
A upper alpha A, B, C, ...
i lower roman i, ii, iii, ...
I upper roman I, II, III, ...
The style is applied to the sequence number which by default
is reset to 1 for the first list item in an ordered list.
-->
<!ENTITY % OLStyle "CDATA">
<!-- LIStyle is constrained to: "(%ULStyle;|%OLStyle;)" -->
<!ENTITY % LIStyle "CDATA">
<!ATTLIST ol
%attrs;
DEPRECATED type %OLStyle; #IMPLIED
DEPRECATED start %Number; #IMPLIED
>
<!ATTLIST li
%attrs;
DEPRECATED type %LIStyle; #IMPLIED
DEPRECATED value %Number; #IMPLIED
>
<!ATTLIST hr
%attrs;
DEPRECATED align (left|center|right) #IMPLIED
DEPRECATED size %Pixels; #IMPLIED
DEPRECATED width %Length; #IMPLIED
>
<!ATTLIST pre
%attrs;
DEPRECATED width %Number; #IMPLIED
>
<!ATTLIST blockquote
%attrs;
cite %URI; #IMPLIED
>
<!ATTLIST ins
%attrs;
cite %URI; #IMPLIED
datetime %Datetime; #IMPLIED
>
<!ATTLIST del
%attrs;
cite %URI; #IMPLIED
datetime %Datetime; #IMPLIED
>
<!ATTLIST a
%attrs;
name NMTOKEN #IMPLIED // ID
href %URI; #IMPLIED
rel %LinkTypes; #IMPLIED // needs policing
rev %LinkTypes; #IMPLIED // see rel
target %FrameTarget; #IMPLIED // usually not used, but might be
>
<!ATTLIST bdo
%coreattrs;
lang %LanguageCode; #IMPLIED
xml:lang %LanguageCode; #IMPLIED
dir (ltr|rtl) #REQUIRED
>
<!ATTLIST br
%coreattrs;
DEPRECATED clear (left|all|right|none) "none"
>
<!ELEMENT q %Inline;> <!-- inlined quote -->
<!ATTLIST q
%attrs;
cite %URI; #IMPLIED
>
<!ATTLIST img
%attrs;
src %URI; #REQUIRED
alt %Text; #REQUIRED
DEPRECATED name NMTOKEN #IMPLIED // ID
longdesc %URI; #IMPLIED
height %Length; #IMPLIED // dubious, but we'll allow
width %Length; #IMPLIED //
DEPRECATED align %ImgAlign; #IMPLIED
DEPRECATED border %Length; #IMPLIED
DEPRECATED hspace %Pixels; #IMPLIED // left/right margin
DEPRECATED vspace %Pixels; #IMPLIED // up/down margin
>
<!--
The border attribute sets the thickness of the frame around the
table. The default units are screen pixels.
The frame attribute specifies which parts of the frame around
the table should be rendered. The values are not the same as
CALS to avoid a name clash with the valign attribute.
-->
<!ENTITY % TFrame "(void|above|below|hsides|lhs|rhs|vsides|box|border)">
<!--
The rules attribute defines which rules to draw between cells:
If rules is absent then assume:
"none" if border is absent or border="0" otherwise "all"
-->
<!ENTITY % TRules "(none | groups | rows | cols | all)">
<!-- horizontal placement of table relative to document -->
<!ENTITY % TAlign "(left|center|right)">
<!-- horizontal alignment attributes for cell contents
char alignment char, e.g. char=':'
charoff offset for alignment char
-->
<!ENTITY % cellhalign
"align (left|center|right|justify|char) #IMPLIED
char %Character; #IMPLIED
charoff %Length; #IMPLIED"
>
<!-- vertical alignment attributes for cell contents -->
<!ENTITY % cellvalign
"valign (top|middle|bottom|baseline) #IMPLIED"
>
<!-- we may want to convert some of these nonetheless -->
<!ATTLIST table
%attrs;
summary %Text; #IMPLIED
width %Length; #IMPLIED
border %Pixels; #IMPLIED
frame %TFrame; #IMPLIED
rules %TRules; #IMPLIED
cellspacing %Length; #IMPLIED
cellpadding %Length; #IMPLIED
DEPRECATED align %TAlign; #IMPLIED
DEPRECATED bgcolor %Color; #IMPLIED
>
<!ENTITY % CAlign "(top|bottom|left|right)">
<!ATTLIST caption
%attrs;
DEPRECATED align %CAlign; #IMPLIED // watch, it's a special set
>
<!--
colgroup groups a set of col elements. It allows you to group
several semantically related columns together.
-->
<!ATTLIST colgroup
%attrs;
span %Number; "1"
width %MultiLength; #IMPLIED
%cellhalign; // very interesting
%cellvalign;
>
<!--
col elements define the alignment properties for cells in
one or more columns.
The width attribute specifies the width of the columns, e.g.
width=64 width in screen pixels
width=0.5* relative width of 0.5
The span attribute causes the attributes of one
col element to apply to more than one column.
-->
<!ATTLIST col
%attrs;
span %Number; "1"
width %MultiLength; #IMPLIED
%cellhalign;
%cellvalign;
>
<!--
Use thead to duplicate headers when breaking table
across page boundaries, or for static headers when
tbody sections are rendered in scrolling panel.
Use tfoot to duplicate footers when breaking table
across page boundaries, or for static footers when
tbody sections are rendered in scrolling panel.
Use multiple tbody sections when rules are needed
between groups of table rows.
-->
<!ATTLIST thead
%attrs;
%cellhalign;
%cellvalign;
>
<!ATTLIST tfoot
%attrs;
%cellhalign;
%cellvalign;
>
<!ATTLIST tbody
%attrs;
%cellhalign;
%cellvalign;
>
<!ATTLIST tr
%attrs;
%cellhalign;
%cellvalign;
DEPRECATED bgcolor %Color; #IMPLIED
>
<!-- Scope is simpler than headers attribute for common tables -->
<!ENTITY % Scope "(row|col|rowgroup|colgroup)">
<!-- th is for headers, td for data and for cells acting as both -->
<!ATTLIST th
%attrs;
abbr %Text; #IMPLIED
axis CDATA #IMPLIED
headers IDREFS #IMPLIED
scope %Scope; #IMPLIED
rowspan %Number; "1"
colspan %Number; "1"
%cellhalign;
%cellvalign;
DEPRECATED nowrap (nowrap) #IMPLIED
DEPRECATED bgcolor %Color; #IMPLIED
DEPRECATED width %Length; #IMPLIED
DEPRECATED height %Length; #IMPLIED
>
<!ATTLIST td
%attrs;
abbr %Text; #IMPLIED
axis CDATA #IMPLIED
headers IDREFS #IMPLIED
scope %Scope; #IMPLIED
rowspan %Number; "1"
colspan %Number; "1"
%cellhalign;
%cellvalign;
DEPRECATED nowrap (nowrap) #IMPLIED
DEPRECATED bgcolor %Color; #IMPLIED
DEPRECATED width %Length; #IMPLIED
DEPRECATED height %Length; #IMPLIED
>

1201
docs/dtd/xhtml1-transitional.dtd Normal file
View File

File diff suppressed because it is too large Load Diff

40
docs/spec.txt
View File

@ -95,6 +95,10 @@ into Data (although I don't see why we can't do that at the start).
One last thing: the remove foreign elements has to do the element One last thing: the remove foreign elements has to do the element
transformations, from FONT to SPAN, etc. transformations, from FONT to SPAN, etc.
font -> span
size CDATA #IMPLIED
color %Color; #IMPLIED
face CDATA #IMPLIED
== STAGE 3 - make well formed == == STAGE 3 - make well formed ==
@ -276,6 +280,14 @@ to text when PCDATA is allowed.
Note that generic child definitions are not usually desirable: we should Note that generic child definitions are not usually desirable: we should
implement custom handlers for each one that specify the stuff correctly. implement custom handlers for each one that specify the stuff correctly.
--
<!--
ins/del are allowed in block and inline content, but it is
inappropriate to include block content within an ins element
occurring in inline content.
-->
== STAGE 4 - check attributes == == STAGE 4 - check attributes ==
STATUS: N (not started) STATUS: N (not started)
@ -332,7 +344,7 @@ Color #NNNNNN, #NNN or color name (translate it
Red = #FF0000 Blue = #0000FF Red = #FF0000 Blue = #0000FF
Purple = #800080 Teal = #008080 Purple = #800080 Teal = #008080
Fuchsia= #FF00FF Aqua = #00FFFF Fuchsia= #FF00FF Aqua = #00FFFF
// plus some directly defined in the spec // plus some directly in the spec
Everything else is either ID, or defined as a certain set of values. Everything else is either ID, or defined as a certain set of values.
@ -347,6 +359,32 @@ The final problem is CSS. Get intimate with the syntax here:
http://www.w3.org/TR/CSS21/syndata.html and also note the "bad" CSS elements http://www.w3.org/TR/CSS21/syndata.html and also note the "bad" CSS elements
that HTML_Safe defines to help determine a whitelist. that HTML_Safe defines to help determine a whitelist.
----
<!ENTITY % coreattrs
"id ID #IMPLIED
class CDATA #IMPLIED
style %StyleSheet; #IMPLIED
title %Text; #IMPLIED"
>
<!ENTITY % i18n
"lang %LanguageCode; #IMPLIED
xml:lang %LanguageCode; #IMPLIED
dir (ltr|rtl) #IMPLIED"
>
<!ENTITY % attrs "%coreattrs; %i18n;">
----
These are the elements that only have %attrs:
ul, dl, dt, dd, address, span, em, strong, dfn, code, samp, kbd, var,
cite, abbr, acronym, sub, sup, tt, i, b, big, small, u, s, strike
These are the elements that only have %attrs and need an alignment transform
div, p, h1, h2, h3, h4, h5, h6
== PART 5 - stringify == == PART 5 - stringify ==
Status: A+ (done completely!) Status: A+ (done completely!)