Skip to content

solr search tweaks (#2005) #2006

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Closed
bolyachevets wants to merge 1 commit into from
Closed

solr search tweaks (#2005) #2006

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
61 changes: 23 additions & 38 deletions api/namex/services/solr/solr_helpers.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,3 +1,4 @@
import re
import string

from namex.constants import Designations
Expand All @@ -8,45 +9,29 @@
class SolrHlpers:
@classmethod
def _name_pre_processing(cls, name):
if not name:
return ''

# Replace ampersands and pluses with space (e.g. H&H -> H H)
processed_name = re.sub(r'([&+])', ' ', name.lower())

# Currency symbol replacements
processed_name = (
(' ' + name.lower() + ' ')
.replace('!', '')
.replace('@', '')
.replace('#', '')
.replace('%', '')
.replace('&', '')
.replace('\\', '')
.replace('/', '')
.replace('{', '')
.replace('}', '')
.replace('[', '')
.replace(']', '')
.replace(')', '')
.replace('(', '')
.replace('+', '')
.replace('-', '')
.replace('|', '')
.replace('?', '')
.replace('.', '')
.replace(',', '')
.replace('_', '')
.replace("'n", '')
.replace("'", '')
.replace('"', '')
.replace(' $ ', 'dollar')
processed_name
.replace(' $ ', ' dollar ')
.replace('$', 's')
.replace(' ¢ ', 'cent')
.replace(' ¢ ', ' cent ')
.replace('¢', 'c')
.replace('britishcolumbia', 'bc')
.replace('britishcolumbias', 'bc')
.replace('britishcolumbian', 'bc')
.replace('britishcolumbians', 'bc')
.replace('british columbia', 'bc')
.replace('british columbias', 'bc')
.replace('british columbian', 'bc')
.replace('british columbians', 'bc')
)
return processed_name.strip()

# Region standardization (british columbia / britishcolumbian(s) -> bc)
processed_name = re.sub(r'\bbritish\s*columbia(ns|n|s)?\b|\bbritishcolumbia(ns|n|s)?\b', 'bc', processed_name)

# Regex removal of punctuation & Solr special characters
rmv_spec_chars_rgx = r"([\[\]!()\"~*?:/\\={}^%`#|<>,.@$;_\-])"
processed_name = re.sub(rmv_spec_chars_rgx, ' ', processed_name)

return ' '.join(processed_name.split())

@classmethod
def _conflicts_post_process(cls, q_data, query_name):
Expand All @@ -65,7 +50,8 @@ def _conflicts_post_process(cls, q_data, query_name):
histories = []

for rcd in q_data.get('searchResults', {}).get('results', []):
nm = cls._get_name_without_designation(rcd.get('name'))
rcd_name = cls._name_pre_processing(rcd.get('name', ''))
nm = cls._get_name_without_designation(rcd_name)
if nm == query_name:
rcd['type'] = 'exact'
exact_matches.append(rcd)
Expand Down Expand Up @@ -140,8 +126,7 @@ def _get_name_without_designation(cls, name):

@classmethod
def get_possible_conflicts(cls, name, start=0, rows=100):
# q_name = cls._name_pre_processing(name)
q_name = name.lower().strip()
q_name = cls._name_pre_processing(name)
q_name = cls._get_name_without_designation(q_name)

candidates = SolrClient.get_possible_conflicts(q_name, start, rows)
Expand Down
21 changes: 21 additions & 0 deletions api/tests/python/unit/test_solr_helpers.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,21 @@
import pytest
from namex.services.solr.solr_helpers import SolrHlpers
from namex.services.solr import words_to_filter_from_name


def test_name_pre_processing_ampersand_and_punctuation():
"""Verify ampersands and punctuation are normalized cleanly."""
result = SolrHlpers._name_pre_processing("H. & H. INVESTMENTS LTD.")
assert result == "h h investments ltd"


def test_name_pre_processing_ampersand_unspaced():
"""Verify unspaced ampersands 'H&H' normalize to 'h h'."""
result = SolrHlpers._name_pre_processing("H&H DHILLON INVESTMENT")
assert result == "h h dhillon investment"


def test_name_pre_processing_preserves_2letter_words():
"""Verify 2-letter words like 'AI', 'EV', 'LI' are preserved intact."""
result = SolrHlpers._name_pre_processing("AI SOLUTIONS EV CHARGING")
assert result == "ai solutions ev charging"