Add html5lib to the list of modules in webkitpy/thirdparty/wpt/wpt/tools.

third_party/WebKit/Tools/Scripts/webkitpy/thirdparty/wpt/wpt/tools/html5lib/html5lib/filters/whitespace.py

Index: third_party/WebKit/Tools/Scripts/webkitpy/thirdparty/wpt/wpt/tools/html5lib/html5lib/filters/whitespace.py
diff --git a/third_party/WebKit/Tools/Scripts/webkitpy/thirdparty/wpt/wpt/tools/html5lib/html5lib/filters/whitespace.py b/third_party/WebKit/Tools/Scripts/webkitpy/thirdparty/wpt/wpt/tools/html5lib/html5lib/filters/whitespace.py
new file mode 100644
index 0000000000000000000000000000000000000000..dfc60eebd35bd6450d82cf65abcbedca8f8fb9da
--- /dev/null
+++ b/third_party/WebKit/Tools/Scripts/webkitpy/thirdparty/wpt/wpt/tools/html5lib/html5lib/filters/whitespace.py
@@ -0,0 +1,38 @@
+from __future__ import absolute_import, division, unicode_literals
+
+import re
+
+from . import _base
+from ..constants import rcdataElements, spaceCharacters
+spaceCharacters = "".join(spaceCharacters)
+
+SPACES_REGEX = re.compile("[%s]+" % spaceCharacters)
+
+
+class Filter(_base.Filter):
+
+    spacePreserveElements = frozenset(["pre", "textarea"] + list(rcdataElements))
+
+    def __iter__(self):
+        preserve = 0
+        for token in _base.Filter.__iter__(self):
+            type = token["type"]
+            if type == "StartTag" \
+                    and (preserve or token["name"] in self.spacePreserveElements):
+                preserve += 1
+
+            elif type == "EndTag" and preserve:
+                preserve -= 1
+
+            elif not preserve and type == "SpaceCharacters" and token["data"]:
+                # Test on token["data"] above to not introduce spaces where there were not
+                token["data"] = " "
+
+            elif not preserve and type == "Characters":
+                token["data"] = collapse_spaces(token["data"])
+
+            yield token
+
+
+def collapse_spaces(text):
+    return SPACES_REGEX.sub(' ', text)