Take into account r1178 of HTML5's draft in the Python implementation (note that previous changes to the spec aren't yet implemented, this changeset doesn't thus make the implementation conforming to r1178, just to r1177-r1178 changes).

tbroyer · tbroyer · commit 54bb5ecc1da8 · 2008-06-19T13:51:20.000Z
Adds tests for the "p" optional end tag, but not for the 'rt' and 'rp', neither for the parser changes (at least, they don't break existing tests)

--HG--
extra : convert_revision : svn%3Aacbfec75-9323-0410-a652-858a13e371e0/trunk%401182
diff --git a/src/html5lib/constants.py b/src/html5lib/constants.py
@@ -292,6 +292,8 @@
 specialElements = frozenset((
     "address",
     "area",
+    "article",
+    "aside",
     "base",
     "basefont",
     "bgsound",
@@ -301,13 +303,20 @@
     "center",
     "col",
     "colgroup",
+    "command",
+    "datagrid",
     "dd",
+    "details",
+    "dialog",
     "dir",
     "div",
     "dl",
     "dt",
     "embed",
+    "event-source",
     "fieldset",
+    "figure",
+    "footer",
     "form",
     "frame",
     "frameset",
@@ -318,9 +327,12 @@
     "h5",
     "h6",
     "head",
+    "header",
     "hr",
     "iframe",
-    "image",
+    # Note that image is commented out in the spec as "this isn't an
+    # element that can end up on the stack, so it doesn't matter"
+    "image", 
     "img",
     "input",
     "isindex",
@@ -329,6 +341,7 @@
     "listing",
     "menu",
     "meta",
+    "nav",
     "noembed",
     "noframes",
     "noscript",
@@ -340,6 +353,7 @@
     "plaintext",
     "pre",
     "script",
+    "section",
     "select",
     "spacer",
     "style",
@@ -389,9 +403,10 @@
     "h6"
 )
 
-# XXX What about event-source and command?
 voidElements = frozenset((
     "base",
+    "command",
+    "event-source",
     "link",
     "meta",
     "hr",
@@ -401,7 +416,8 @@
     "param",
     "area",
     "col",
-    "input"
+    "input",
+    "source"
 ))
 
 cdataElements = frozenset(('title', 'textarea'))
diff --git a/src/html5lib/filters/optionaltags.py b/src/html5lib/filters/optionaltags.py
@@ -112,14 +112,28 @@ def is_optional_end(self, tagname, next):
                 return False
         elif tagname == 'p':
             # A p element's end tag may be omitted if the p element is
-            # immediately followed by an address, blockquote, dl, fieldset,
-            # form, h1, h2, h3, h4, h5, h6, hr, menu, ol, p, pre, table,
-            # or ul  element, or if there is no more content in the parent
-            # element.
+            # immediately followed by an address, article, aside,
+            # blockquote, datagrid, dialog, dir, div, dl, fieldset,
+            # footer, form, h1, h2, h3, h4, h5, h6, header, hr, menu,
+            # nav, ol, p, pre, section, table, or ul, element, or if
+            # there is no more content in the parent element.
+            if type == "StartTag":
+                return next["name"] in ('address', 'article', 'aside',     \
+                    'blockquote', 'datagrid', 'dialog', 'dir', 'div',      \
+                    'dl', 'fieldset', 'footer', 'form', 'h1', 'h2', 'h3',  \
+                    'h4', 'h5', 'h6', 'header', 'hr', 'menu', 'nav', 'ol', \
+                    'p', 'pre', 'section', 'table', 'ul')
+            else:
+                return type == "EndTag" or type is None
+        elif tagname in ('rt', 'rp'):
+            # An rt element's end tag may be omitted if the rt element is
+            # immediately followed by an rt or rp element, or if there is
+            # no more content in the parent element.
+            # An rp element's end tag may be omitted if the rp element is
+            # immediately followed by an rt or rp element, or if there is
+            # no more content in the parent element.
             if type == "StartTag":
-                return next["name"] in ('address', 'blockquote', \
-                    'dl', 'fieldset', 'form', 'h1', 'h2', 'h3', 'h4', 'h5', \
-                    'h6', 'hr', 'menu', 'ol', 'p', 'pre', 'table', 'ul')
+                return next["name"] in ('rt', 'rp')
             else:
                 return type == "EndTag" or type is None
         elif tagname == 'colgroup':
diff --git a/src/html5lib/html5parser.py b/src/html5lib/html5parser.py
@@ -709,8 +709,10 @@ def __init__(self, parser, tree):
             (("base", "link", "meta", "script", "style", "title"),
               self.startTagProcessInHead),
             ("body", self.startTagBody),
-            (("address", "blockquote", "center", "dir", "div", "dl",
-              "fieldset", "listing", "menu", "ol", "p", "pre", "ul"),
+            (("address", "article", "aside", "blockquote", "center", "datagrid",
+              "details", "dialog", "dir", "div", "dl", "fieldset", "figure",
+              "footer", "h1", "h2", "h3", "h4", "h5", "h6", "header", "listing",
+              "menu", "nav", "ol", "p", "pre", "section", "ul"),
               self.startTagCloseP),
             ("form", self.startTagForm),
             (("li", "dd", "dt"), self.startTagListItem),
@@ -736,17 +738,18 @@ def __init__(self, parser, tree):
             (("caption", "col", "colgroup", "frame", "frameset", "head",
               "option", "optgroup", "tbody", "td", "tfoot", "th", "thead",
               "tr"), self.startTagMisplaced),
-            (("event-source", "section", "nav", "article", "aside", "header",
-              "footer", "datagrid", "command"), self.startTagNew)
+            (("event-source", "command"), self.startTagNew)
         ])
         self.startTagHandler.default = self.startTagOther
 
         self.endTagHandler = utils.MethodDispatcher([
             ("p",self.endTagP),
             ("body",self.endTagBody),
             ("html",self.endTagHtml),
-            (("address", "blockquote", "center", "div", "dl", "fieldset",
-              "listing", "menu", "ol", "pre", "ul"), self.endTagBlock),
+            (("address", "article", "aside", "blockquote", "center", "datagrid",
+              "details", "dialog", "dir", "div", "dl", "fieldset", "figure",
+              "footer", "header", "listing", "menu", "nav", "ol", "pre", "section",
+              "ul"), self.endTagBlock),
             ("form", self.endTagForm),
             (("dd", "dt", "li"), self.endTagListItem),
             (headingElements, self.endTagHeading),
@@ -762,8 +765,7 @@ def __init__(self, parser, tree):
               self.endTagNone),
             (("noframes", "noscript", "noembed", "textarea", "xmp", "iframe"),
               self.endTagCdataTextAreaXmp),
-            (("event-source", "section", "nav", "article", "aside", "header",
-              "footer", "datagrid", "command"), self.endTagNew)
+            (("event-source", "command"), self.endTagNew)
             ])
         self.endTagHandler.default = self.endTagOther
 
