added support for validating a whole bunch of stuff that I can't remember right at the moment

Mark Pilgrim · Mark Pilgrim · commit a83fbe4f2bb7 · 2007-08-31T13:22:40.000Z
--HG--
extra : convert_revision : svn%3Aacbfec75-9323-0410-a652-858a13e371e0/trunk%40990
diff --git a/src/html5lib/filters/rfc2046.py b/src/html5lib/filters/rfc2046.py
@@ -0,0 +1,29 @@
+# adapted from feedvalidator, original copyright license is
+#
+# Copyright (c) 2002-2006, Sam Ruby, Mark Pilgrim, Joseph Walton, and Phil Ringnalda
+#
+# Permission is hereby granted, free of charge, to any person obtaining a copy
+# of this software and associated documentation files (the "Software"), to deal
+# in the Software without restriction, including without limitation the rights
+# to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+# copies of the Software, and to permit persons to whom the Software is
+# furnished to do so, subject to the following conditions:
+#
+# The above copyright notice and this permission notice shall be included in all
+# copies or substantial portions of the Software.
+#
+# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+# IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+# FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+# AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+# LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+# OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+# SOFTWARE.
+
+import re
+
+mime_re = re.compile('[^\s()<>,;:\\"/[\]?=]+/[^\s()<>,;:\\"/[\]?=]+(\s*;\s*[^\s()<>,;:\\"/[\]?=]+=("(\\"|[^"])*"|[^\s()<>,;:\\"/[\]?=]+))*$')
+
+def isValidMIMEType(value):
+    return not not mime_re.match(value)
+    
diff --git a/src/html5lib/filters/rfc3987.py b/src/html5lib/filters/rfc3987.py
@@ -31,6 +31,7 @@
   "urn", "go", "h323", "ipp", "tftp", "mupdate", "pres", "im", "mtqp",
   "iris.beep", "dict", "snmp", "crid", "tag", "dns", "info"
 ]
+allowed_schemes = iana_schemes + ['javascript']
 
 rfc2396_re = re.compile("([a-zA-Z][0-9a-zA-Z+\\-\\.]*:)?/{0,2}" +
                         "[0-9a-zA-Z;/?:@&=+$\\.\\-_!~*'()%,#]*$")
@@ -62,8 +63,8 @@ def isValidURI(value, uriPattern=rfc2396_re):
     elif scheme in ['http','ftp']:
         if not re.match('^\w+://[^/].*',value):
             return False, "invalid-http-or-ftp-uri"
-    elif value.find(':')>=0 and scheme.isalpha() and scheme not in iana_schemes:
-        return False, "unregistered-scheme"
+    elif value.find(':')>=0 and scheme.isalpha() and scheme not in allowed_schemes:
+        return False, "invalid-scheme"
     return True, ""
 
 def isValidIRI(value):
diff --git a/src/html5lib/filters/validator.py b/src/html5lib/filters/validator.py
@@ -21,6 +21,7 @@
 import _base
 import iso639codes
 import rfc3987
+import rfc2046
 from html5lib.constants import E, spaceCharacters, digits
 from html5lib import tokenizer
 import gettext
@@ -65,6 +66,24 @@
         _(u"Root namespace must be 'http://www.w3.org/1999/xhtml', or omitted."),
     "invalid-browsing-context":
         _(u"Value must be one of ('_self', '_parent', '_top'), or a name that does not start with '_': '%(attributeName)s' attribute on <%(tagName)s>."),
+    "invalid-tag-uri":
+        _(u"Invalid URI: '%(attributeName)s' attribute on <%(tagName)s>."),
+    "invalid-urn":
+        _(u"Invalid URN: '%(attributeName)s' attribute on <%(tagName)s>."),
+    "invalid-uri-char":
+        _(u"Illegal character in URI: '%(attributeName)s' attribute on <%(tagName)s>."),
+    "uri-not-iri":
+        _(u"Expected a URI but found an IRI: '%(attributeName)s' attribute on <%(tagName)s>."),
+    "invalid-uri":
+        _(u"Invalid URI: '%(attributeName)s' attribute on <%(tagName)s>."),
+    "invalid-http-or-ftp-uri":
+        _(u"Invalid URI: '%(attributeName)s' attribute on <%(tagName)s>."),
+    "invalid-scheme":
+        _(u"Unregistered URI scheme: '%(attributeName)s' attribute on <%(tagName)s>."),
+    "invalid-rel":
+        _(u"Invalid link relation: '%(attributeName)s' attribute on <%(tagName)s>."),
+    "invalid-mime-type":
+        _(u"Invalid MIME type: '%(attributeName)s' attribute on <%(tagName)s>."),
 })
 
 globalAttributes = frozenset(('class', 'contenteditable', 'contextmenu', 'dir',
@@ -236,6 +255,9 @@
     'password': frozenset(('size',))
 }
 
+linkRelValues = frozenset(('alternate', 'archive', 'archives', 'author', 'contact', 'feed', 'first', 'begin', 'start', 'help', 'icon', 'index', 'top', 'contents', 'toc', 'last', 'end', 'license', 'copyright', 'next', 'pingback', 'prefetch', 'prev', 'previous', 'search', 'stylesheet', 'sidebar', 'tag', 'up'))
+aRelValues = frozenset(('alternate', 'archive', 'archives', 'author', 'contact', 'feed', 'first', 'begin', 'start', 'help', 'index', 'top', 'contents', 'toc', 'last', 'end', 'license', 'copyright', 'next', 'prev', 'previous', 'search', 'sidebar', 'tag', 'up', 'bookmark', 'external', 'nofollow'))
+
 class HTMLConformanceChecker(_base.Filter):
     def __init__(self, stream, encoding, parseMeta, **kwargs):
         _base.Filter.__init__(self, tokenizer.HTMLTokenizer(
@@ -340,17 +362,17 @@ def checkStartTagUnknownAttributes(self, token):
     # Attribute validation helpers
     ##########################################################################
 
-    def checkURI(self, token, tagName, attrName, attrValue):
-        isValid, errorCode = rfc3987.isValidURI(attrValue)
-        if not isValid:
-            yield {"type": "ParseError",
-                   "data": errorCode,
-                   "datavars": {"tagName": tagName,
-                                "attributeName": attrName}}
-            yield {"type": "ParseError",
-                   "data": "invalid-attribute-value",
-                   "datavars": {"tagName": tagName,
-                                "attributeName": attrName}}
+#    def checkURI(self, token, tagName, attrName, attrValue):
+#        isValid, errorCode = rfc3987.isValidURI(attrValue)
+#        if not isValid:
+#            yield {"type": "ParseError",
+#                   "data": errorCode,
+#                   "datavars": {"tagName": tagName,
+#                                "attributeName": attrName}}
+#            yield {"type": "ParseError",
+#                   "data": "invalid-attribute-value",
+#                   "datavars": {"tagName": tagName,
+#                                "attributeName": attrName}}
 
     def checkIRI(self, token, tagName, attrName, attrValue):
         isValid, errorCode = rfc3987.isValidIRI(attrValue)
@@ -382,26 +404,36 @@ def checkID(self, token, tagName, attrName, attrValue):
                                     "attributeName": attrName}}
                 break
         
-    def checkTokenList(self, tagName, attrName, attrValue):
-        # The "token" in the method name refers to tokens in an attribute value
-        # i.e. http://www.whatwg.org/specs/web-apps/current-work/#set-of
-        # but the "token" parameter refers to the token generated from
-        # HTMLTokenizer.  Sorry for the confusion.
+    def parseTokenList(self, value):
         valueList = []
         currentValue = ''
-        for c in attrValue + ' ':
+        for c in value + ' ':
             if c in spaceCharacters:
                 if currentValue:
-                    if currentValue in valueList:
-                        yield {"type": "ParseError",
-                               "data": "duplicate-value-in-token-list",
-                               "datavars": {"tagName": tagName,
-                                            "attributeName": attrName,
-                                            "attributeValue": currentValue}}
                     valueList.append(currentValue)
                     currentValue = ''
             else:
                 currentValue += c
+        if currentValue:
+            valueList.append(currentValue)
+        return valueList
+        
+    def checkTokenList(self, tagName, attrName, attrValue):
+        # The "token" in the method name refers to tokens in an attribute value
+        # i.e. http://www.whatwg.org/specs/web-apps/current-work/#set-of
+        # but the "token" parameter refers to the token generated from
+        # HTMLTokenizer.  Sorry for the confusion.
+        valueList = self.parseTokenList(attrValue)
+        valueDict = {}
+        for currentValue in valueList:
+            if valueDict.has_key(currentValue):
+                yield {"type": "ParseError",
+                       "data": "duplicate-value-in-token-list",
+                       "datavars": {"tagName": tagName,
+                                    "attributeName": attrName,
+                                    "attributeValue": currentValue}}
+                break
+            valueDict[currentValue] = 1
 
     def checkEnumeratedValue(self, token, tagName, attrName, attrValue, enumeratedValues):
         if not attrValue and ('' not in enumeratedValues):
@@ -422,7 +454,7 @@ def checkEnumeratedValue(self, token, tagName, attrName, attrValue, enumeratedVa
                    "datavars": {"tagName": tagName,
                                 "attributeName": attrName}}
         
-    def checkBooleanValue(self, token, tagName, attrName, attrValue):
+    def checkBoolean(self, token, tagName, attrName, attrValue):
         enumeratedValues = frozenset((attrName, ''))
         if attrValue not in enumeratedValues:
             yield {"type": "ParseError",
@@ -435,7 +467,7 @@ def checkBooleanValue(self, token, tagName, attrName, attrValue):
                    "datavars": {"tagName": tagName,
                                 "attributeName": attrName}}
 
-    def checkIntegerValue(self, token, tagName, attrName, attrValue):
+    def checkInteger(self, token, tagName, attrName, attrValue):
         sign = 1
         numberString = ''
         state = 'begin' # ('begin', 'initial-number', 'number', 'trailing-junk')
@@ -476,6 +508,10 @@ def checkIntegerValue(self, token, tagName, attrName, attrValue):
                    "datavars": {"tagName": tagName,
                                 "attributeName": attrName}}
 
+    def checkFloatingPointNumber(self, token, tagName, attrName, attrValue):
+        # XXX
+        pass
+
     def checkBrowsingContext(self, token, tagName, attrName, attrValue):
         if not attrValue: return
         if attrValue[0] != '_': return
@@ -486,6 +522,56 @@ def checkBrowsingContext(self, token, tagName, attrName, attrValue):
                "datavars": {"tagName": tagName,
                             "attributeName": attrName}}
 
+    def checkLangCode(self, token, tagName, attrName, attrValue):
+        if not attrValue: return # blank is OK
+        if not iso639codes.isValidLangCode(attrValue):
+            yield {"type": "ParseError",
+                   "data": "invalid-lang-code",
+                   "datavars": {"tagName": tagName,
+                                "attributeName": attrName,
+                                "attributeValue": attrValue}}
+
+    def checkMIMEType(self, token, tagName, attrName, attrValue):
+        # XXX needs tests
+        if not attrValue:
+            yield {"type": "ParseError",
+                   "data": "attribute-value-can-not-be-blank",
+                   "datavars": {"tagName": tagName,
+                                "attributeName": attrName}}
+
+        if not rfc2046.isValidMIMEType(attrValue):
+            yield {"type": "ParseError",
+                   "data": "invalid-mime-type",
+                   "datavars": {"tagName": tagName,
+                                "attributeName": attrName,
+                                "attributeValue": attrValue}}
+
+    def checkMediaQuery(self, token, tagName, attrName, attrValue):
+        # XXX
+        pass
+
+    def checkLinkRelation(self, token, tagName, attrName, attrValue):
+        for t in self.checkTokenList(tagName, attrName, attrValue) or []: yield t
+        valueList = self.parseTokenList(attrValue)
+        allowedValues = (tagName == 'link') and linkRelValues or aRelValues
+        for currentValue in valueList:
+            if currentValue not in allowedValues:
+                yield {"type": "ParseError",
+                       "data": "invalid-rel",
+                       "datavars": {"tagName": tagName,
+                                    "attributeName": attrName}}
+
+    def checkDateTime(self, token, tagName, attrName, attrValue):
+        # XXX
+        state = 'begin' # ('begin', '...
+#        for c in attrValue:
+#            if state == 'begin':
+#                if c in spaceCharacters:
+#                    continue
+#                elif c in digits:
+#                    state = ...
+                    
+
     ##########################################################################
     # Attribute validation
     ##########################################################################
@@ -521,17 +607,8 @@ def validateAttributeValueDir(self, token, tagName, attrName, attrValue):
     def validateAttributeValueDraggable(self, token, tagName, attrName, attrValue):
         for t in self.checkEnumeratedValue(token, tagName, attrName, attrValue, frozenset(('true', 'false'))) or []: yield t
 
-    def validateAttributeValueIrrelevant(self, token, tagName, attrName, attrValue):
-        for t in self.checkBooleanValue(token, tagName, attrName, attrValue) or []: yield t
-
-    def validateAttributeValueLang(self, token, tagName, attrName, attrValue):
-        if not attrValue: return # blank is OK
-        if not iso639codes.isValidLangCode(attrValue):
-            yield {"type": "ParseError",
-                   "data": "invalid-lang-code",
-                   "datavars": {"tagName": tagName,
-                                "attributeName": attrName,
-                                "attributeValue": attrValue}}
+    validateAttributeValueIrrelevant = checkBoolean
+    validateAttributeValueLang = checkLangCode
 
     def validateAttributeValueContextmenu(self, token, tagName, attrName, attrValue):
         for t in self.checkID(token, tagName, attrName, attrValue) or []: yield t
@@ -552,7 +629,7 @@ def validateAttributeValueId(self, token, tagName, attrName, attrValue):
         self.IDsWeHaveKnownAndLoved.append(attrValue)
         self.thingsThatDefineAnID.append(token)
 
-    validateAttributeValueTabindex = checkIntegerValue
+    validateAttributeValueTabindex = checkInteger
 
     def validateAttributeValueRef(self, token, tagName, attrName, attrValue):
         # XXX
@@ -569,13 +646,47 @@ def validateAttributeValueHtmlXmlns(self, token, tagName, attrName, attrValue):
                    "datavars": {"tagName": tagName,
                                 "attributeName": attrName}}
 
-    def validateAttributeValueBaseHref(self, token, tagName, attrName, attrValue):
-        # XXX
-        pass
-
     validateAttributeValueBaseHref = checkIRI
     validateAttributeValueBaseTarget = checkBrowsingContext
     validateAttributeValueLinkHref = checkIRI
+    validateAttributeValueLinkRel = checkLinkRelation
+    validateAttributeValueLinkMedia = checkMediaQuery
+    validateAttributeValueLinkHreflang = checkLangCode
+    validateAttributeValueLinkType = checkMIMEType
+    # XXX <meta> attributes
+    validateAttributeValueStyleMedia = checkMediaQuery
+    validateAttributeValueStyleType = checkMIMEType
+    validateAttributeValueStyleScoped = checkBoolean
+    validateAttributeValueBlockquoteCite = checkIRI
+    validateAttributeValueOlStart = checkInteger
+    validateAttributeValueLiValue = checkInteger
+    # XXX need tests from here on
+    validateAttributeValueAHref = checkIRI
+    validateAttributeValueATarget = checkBrowsingContext
+
+    def validateAttributeValueAPing(self, token, tagName, attrName, attrValue):
+        valueList = self.parseTokenList(attrValue)
+        for currentValue in valueList:
+            for t in self.checkIRI(token, tagName, attrName, attrValue) or []: yield t
+
+    validateAttributeValueARel = checkLinkRelation
+    validateAttributeValueAMedia = checkMediaQuery
+    validateAttributeValueAHreflang = checkLangCode
+    validateAttributeValueAType = checkMIMEType
+    validateAttributeValueQCite = checkIRI
+    validateAttributeValueTimeDatetime = checkDateTime
+    validateAttributeValueMeterValue = checkFloatingPointNumber
+    validateAttributeValueMeterMin = checkFloatingPointNumber
+    validateAttributeValueMeterLow = checkFloatingPointNumber
+    validateAttributeValueMeterHigh = checkFloatingPointNumber
+    validateAttributeValueMeterMax = checkFloatingPointNumber
+    validateAttributeValueMeterOptimum = checkFloatingPointNumber
+    validateAttributeValueProgressValue = checkFloatingPointNumber
+    validateAttributeValueProgressMax = checkFloatingPointNumber
+    validateAttributeValueInsCite = checkIRI
+    validateAttributeValueInsDatetime = checkDateTime
+    validateAttributeValueDelCite = checkIRI
+    validateAttributeValueDelDatetime = checkDateTime
 
     ##########################################################################
     # Whole document validation (IDs, etc.)
