Merge remote-tracking branch 'upstream/master' into update-docs

AUTHORS.rst

@@ -32,6 +32,7 @@ Patches and suggestions
 - Andreas Madsack
 - Karim Valiev
 - Marc DM
+- Ritwik Gupta
 - Tony Lopes
 - lilbludevil
 - Simon Sapin
@@ -42,4 +43,6 @@ Patches and suggestions
 - Michael[tm] Smith
 - Marc Abramowitz
 - Jon Dufresne
+- Ville Skyttä
+- Jonathan Vanasco
 - Tom Most

CHANGES.rst

@@ -1,6 +1,13 @@
 Change Log
 ----------
 
+unreleased
+~~~~~~~~~~~~~~~~~~
+
+* Added the seamless attribute for iframes.
+* Added `itemscope` as boolean attribute 
+ https://github.com/html5lib/html5lib-python/issues/194
+
 0.999999999/1.0b10
 ~~~~~~~~~~~~~~~~~~
 

html5lib/_ihatexml.py

@@ -180,7 +180,7 @@ def escapeRegexp(string):
 nonXmlNameFirstBMPRegexp = re.compile('[\x00-@\\[-\\^`\\{-\xbf\xd7\xf7\u0132-\u0133\u013f-\u0140\u0149\u017f\u01c4-\u01cc\u01f1-\u01f3\u01f6-\u01f9\u0218-\u024f\u02a9-\u02ba\u02c2-\u0385\u0387\u038b\u038d\u03a2\u03cf\u03d7-\u03d9\u03db\u03dd\u03df\u03e1\u03f4-\u0400\u040d\u0450\u045d\u0482-\u048f\u04c5-\u04c6\u04c9-\u04ca\u04cd-\u04cf\u04ec-\u04ed\u04f6-\u04f7\u04fa-\u0530\u0557-\u0558\u055a-\u0560\u0587-\u05cf\u05eb-\u05ef\u05f3-\u0620\u063b-\u0640\u064b-\u0670\u06b8-\u06b9\u06bf\u06cf\u06d4\u06d6-\u06e4\u06e7-\u0904\u093a-\u093c\u093e-\u0957\u0962-\u0984\u098d-\u098e\u0991-\u0992\u09a9\u09b1\u09b3-\u09b5\u09ba-\u09db\u09de\u09e2-\u09ef\u09f2-\u0a04\u0a0b-\u0a0e\u0a11-\u0a12\u0a29\u0a31\u0a34\u0a37\u0a3a-\u0a58\u0a5d\u0a5f-\u0a71\u0a75-\u0a84\u0a8c\u0a8e\u0a92\u0aa9\u0ab1\u0ab4\u0aba-\u0abc\u0abe-\u0adf\u0ae1-\u0b04\u0b0d-\u0b0e\u0b11-\u0b12\u0b29\u0b31\u0b34-\u0b35\u0b3a-\u0b3c\u0b3e-\u0b5b\u0b5e\u0b62-\u0b84\u0b8b-\u0b8d\u0b91\u0b96-\u0b98\u0b9b\u0b9d\u0ba0-\u0ba2\u0ba5-\u0ba7\u0bab-\u0bad\u0bb6\u0bba-\u0c04\u0c0d\u0c11\u0c29\u0c34\u0c3a-\u0c5f\u0c62-\u0c84\u0c8d\u0c91\u0ca9\u0cb4\u0cba-\u0cdd\u0cdf\u0ce2-\u0d04\u0d0d\u0d11\u0d29\u0d3a-\u0d5f\u0d62-\u0e00\u0e2f\u0e31\u0e34-\u0e3f\u0e46-\u0e80\u0e83\u0e85-\u0e86\u0e89\u0e8b-\u0e8c\u0e8e-\u0e93\u0e98\u0ea0\u0ea4\u0ea6\u0ea8-\u0ea9\u0eac\u0eaf\u0eb1\u0eb4-\u0ebc\u0ebe-\u0ebf\u0ec5-\u0f3f\u0f48\u0f6a-\u109f\u10c6-\u10cf\u10f7-\u10ff\u1101\u1104\u1108\u110a\u110d\u1113-\u113b\u113d\u113f\u1141-\u114b\u114d\u114f\u1151-\u1153\u1156-\u1158\u115a-\u115e\u1162\u1164\u1166\u1168\u116a-\u116c\u116f-\u1171\u1174\u1176-\u119d\u119f-\u11a7\u11a9-\u11aa\u11ac-\u11ad\u11b0-\u11b6\u11b9\u11bb\u11c3-\u11ea\u11ec-\u11ef\u11f1-\u11f8\u11fa-\u1dff\u1e9c-\u1e9f\u1efa-\u1eff\u1f16-\u1f17\u1f1e-\u1f1f\u1f46-\u1f47\u1f4e-\u1f4f\u1f58\u1f5a\u1f5c\u1f5e\u1f7e-\u1f7f\u1fb5\u1fbd\u1fbf-\u1fc1\u1fc5\u1fcd-\u1fcf\u1fd4-\u1fd5\u1fdc-\u1fdf\u1fed-\u1ff1\u1ff5\u1ffd-\u2125\u2127-\u2129\u212c-\u212d\u212f-\u217f\u2183-\u3006\u3008-\u3020\u302a-\u3040\u3095-\u30a0\u30fb-\u3104\u312d-\u4dff\u9fa6-\uabff\ud7a4-\uffff]') # noqa
 
 # Simpler things
-nonPubidCharRegexp = re.compile("[^\x20\x0D\x0Aa-zA-Z0-9\-\'()+,./:=?;!*#@$_%]")
+nonPubidCharRegexp = re.compile("[^\x20\x0D\x0Aa-zA-Z0-9\\-'()+,./:=?;!*#@$_%]")
 
 
 class InfosetFilter(object):

html5lib/constants.py

@@ -588,7 +588,7 @@
 ])
 
 booleanAttributes = {
- "": frozenset(["irrelevant"]),
+ "": frozenset(["irrelevant", "itemscope"]),
  "style": frozenset(["scoped"]),
  "img": frozenset(["ismap"]),
  "audio": frozenset(["autoplay", "controls"]),
@@ -606,6 +606,7 @@
  "input": frozenset(["disabled", "readonly", "required", "autofocus", "checked", "ismap"]),
  "select": frozenset(["disabled", "readonly", "autofocus", "multiple"]),
  "output": frozenset(["disabled", "readonly"]),
+ "iframe": frozenset(["seamless"]),
 }
 
 # entitiesWindows1252 has to be _ordered_ and needs to have an index. It

html5lib/tests/serializer-testdata/options.test

@@ -46,6 +46,29 @@
  "quote_attr_values": "always"
  }
  },
+ {
+ "expected": [
+ "<div itemscope>"
+ ],
+ "input": [
+ [
+ "StartTag",
+ "http:https://www.w3.org/1999/xhtml",
+ "div",
+ [
+ {
+ "namespace": null,
+ "name": "itemscope",
+ "value": "itemscope"
+ }
+ ]
+ ]
+ ],
+ "description": "quote_attr_values='always' with itemscope",
+ "options": {
+ "quote_attr_values": "always"
+ }
+ },
  {
  "expected": [
  "<div irrelevant>"
@@ -171,6 +194,29 @@
  "use_trailing_solidus": true
  }
  },
+ {
+ "expected": [
+ "<div itemscope=itemscope>"
+ ],
+ "input": [
+ [
+ "StartTag",
+ "http:https://www.w3.org/1999/xhtml",
+ "div",
+ [
+ {
+ "namespace": null,
+ "name": "itemscope",
+ "value": "itemscope"
+ }
+ ]
+ ]
+ ],
+ "description": "minimize_boolean_attributes=false",
+ "options": {
+ "minimize_boolean_attributes": false
+ }
+ },
  {
  "expected": [
  "<div irrelevant=irrelevant>"
@@ -194,6 +240,29 @@
  "minimize_boolean_attributes": false
  }
  },
+ {
+ "expected": [
+ "<div itemscope=\"\">"
+ ],
+ "input": [
+ [
+ "StartTag",
+ "http:https://www.w3.org/1999/xhtml",
+ "div",
+ [
+ {
+ "namespace": null,
+ "name": "itemscope",
+ "value": ""
+ }
+ ]
+ ]
+ ],
+ "description": "minimize_boolean_attributes=false with empty value",
+ "options": {
+ "minimize_boolean_attributes": false
+ }
+ },
  {
  "expected": [
  "<div irrelevant=\"\">"