Created
August 13, 2023 21:41
-
-
Save daisycamber/39ca63c8950ec9fbd9a647647aad8ba4 to your computer and use it in GitHub Desktop.
Full text search using Python, with autocorrection
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
from feed.models import Post | |
import regex, datetime | |
from autocorrect import Speller | |
SEARCH_REGEX = r'\s({})[\s.,!?:)\-&*\"\';]' | |
ESCAPED_QUERIES = ['a', 'and', 'the', 'is', 'i'] | |
def get_posts_for_query(request, qs): | |
now = datetime.datetime.fromtimestamp(int(request.GET.get('time')) / 1000) | |
spell = Speller() | |
qs = spell(qs) | |
qsplit = qs.split(' ') | |
posts = Post.objects.filter(content__icontains=qs, private=False, published=True, date_posted__lte=now) | |
for q in qsplit: | |
posts = posts.union(Post.objects.filter(content__icontains=q, private=False, published=True, date_posted__lte=now)) | |
posts = posts.order_by('-date_posted') | |
pos = [] | |
for post in posts: | |
count = 0 | |
matches = regex.findall(SEARCH_REGEX.format(qs), post.content, flags=regex.IGNORECASE | regex.BESTMATCH) | |
count = count + len(matches) | |
for q in qsplit: | |
matches = regex.findall(SEARCH_REGEX.format(q), post.content, flags=regex.IGNORECASE | regex.BESTMATCH) | |
for match in matches: | |
if not match in ESCAPED_QUERIES: | |
count = count + 1 | |
if count > 0: | |
pos = pos + [(post.id, count)] | |
pos = sorted(pos, key = lambda x: x[1], reverse=True) | |
posts = [] | |
for post, count in pos: | |
post = Post.objects.get(id=post) | |
posts = posts + ([post] if post.public or request.user.is_authenticated and post.author in request.user.profile.subscriptions.all() or request.user.is_authenticated and request.user.profile.vendor else []) | |
return posts |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment