mirror of
https://github.com/zulip/zulip.git
synced 2025-11-05 14:35:27 +00:00
0f8d014096
This tools greps for HTML nodes that have relevants words pertaining to classes, ids, or tags in themselves or their parents.
64 lines
1.8 KiB
Python
64 lines
1.8 KiB
Python
from __future__ import absolute_import
|
|
from __future__ import print_function
|
|
from collections import defaultdict
|
|
from six.moves import range
|
|
|
|
from .template_parser import html_branches, Token, HtmlTreeBranch
|
|
|
|
def show_all_branches(fns):
|
|
# type: (List[str]) -> None
|
|
for fn in fns:
|
|
print(fn)
|
|
text = open(fn).read()
|
|
branches = html_branches(text)
|
|
for branch in branches:
|
|
print(branch.text())
|
|
print('---')
|
|
|
|
class Grepper(object):
|
|
'''
|
|
A Grepper object is optimized to do repeated
|
|
searches of words that can be found in our
|
|
HtmlTreeBranch objects.
|
|
'''
|
|
|
|
def __init__(self, fns):
|
|
# type: (List[str]) -> None
|
|
all_branches = [] # type: List[HtmlTreeBranch]
|
|
|
|
for fn in fns:
|
|
branches = html_branches(fn)
|
|
all_branches += branches
|
|
|
|
self.word_dict = defaultdict(set) # type: Dict[str, Set[HtmlTreeBranch]]
|
|
for b in all_branches:
|
|
for word in b.words:
|
|
self.word_dict[word].add(b)
|
|
|
|
self.all_branches = set(all_branches)
|
|
|
|
def grep(self, word_set):
|
|
# type: (Set[str]) -> None
|
|
|
|
words = list(word_set) # type: List[str]
|
|
|
|
if len(words) == 0:
|
|
matches = self.all_branches
|
|
else:
|
|
matches = self.word_dict[words[0]]
|
|
for i in range(1, len(words)):
|
|
matches = matches & self.word_dict[words[i]]
|
|
|
|
branches = list(matches)
|
|
branches.sort(key=lambda branch: (branch.fn, branch.line))
|
|
for branch in branches:
|
|
print('%s %d' % (branch.fn, branch.line))
|
|
print(branch.staircase_text())
|
|
print('')
|
|
|
|
def grep(fns, words):
|
|
# type: (List[str], Set[str]) -> None
|
|
grepper = Grepper(fns)
|
|
grepper.grep(words)
|
|
|