Factor out HtmlTreeBranch and related code from template parser.

This code is not directly related to the template parser, so it
can safely live in its own file.

The only significant change to the code is to the signature of
`html_branches` so that it can be called without requiring a file.
Since it's only used in html_grep, that has been updated to reflect
this change.

Fixes: #1774.

tools/lib/html_grep.py

@@ -3,14 +3,14 @@ from __future__ import print_function
 from collections import defaultdict
 from six.moves import range
 
-from .template_parser import html_branches, Token, HtmlTreeBranch
+from .html_branches import html_branches, HtmlTreeBranch
 
 def show_all_branches(fns):
     # type: (List[str]) -> None
     for fn in fns:
         print(fn)
         text = open(fn).read()
-        branches = html_branches(text)
+        branches = html_branches(text, fn=fn)
         for branch in branches:
             print(branch.text())
         print('---')
@@ -27,7 +27,8 @@ class Grepper(object):
         all_branches = [] # type: List[HtmlTreeBranch]
 
         for fn in fns:
-            branches = html_branches(fn)
+            text = open(fn).read()
+            branches = html_branches(text, fn=fn)
             all_branches += branches
 
         self.word_dict = defaultdict(set) # type: Dict[str, Set[HtmlTreeBranch]]