mirror of
https://github.com/rommapp/romm.git
synced 2026-02-18 00:27:41 +01:00
feat: integrate Levenshtein distance for improved fuzzy matching in SGDBBaseHandler
This commit is contained in:
@@ -4,6 +4,7 @@ from typing import Final, NotRequired, TypedDict
|
||||
from adapters.services.steamgriddb import SteamGridDBService
|
||||
from adapters.services.steamgriddb_types import SGDBDimension, SGDBType
|
||||
from config import STEAMGRIDDB_API_KEY
|
||||
from Levenshtein import distance as levenshtein_distance
|
||||
from logger.logger import log
|
||||
|
||||
from .base_hander import MetadataHandler
|
||||
@@ -31,7 +32,7 @@ class SGDBRom(TypedDict):
|
||||
class SGDBBaseHandler(MetadataHandler):
|
||||
def __init__(self) -> None:
|
||||
self.sgdb_service = SteamGridDBService()
|
||||
self.fuzzy_match_threshold: Final = 4
|
||||
self.max_levenshtein_distance: Final = 4
|
||||
|
||||
async def get_details(self, search_term: str) -> list[SGDBResult]:
|
||||
games = await self.sgdb_service.search_games(term=search_term)
|
||||
@@ -64,13 +65,9 @@ class SGDBBaseHandler(MetadataHandler):
|
||||
search_term, remove_articles=False
|
||||
)
|
||||
|
||||
# Check if normalized search term is contained in normalized game name
|
||||
# or if they're very similar (allowing for small character differences)
|
||||
if (
|
||||
search_term_normalized in game_name_normalized
|
||||
or game_name_normalized in search_term_normalized
|
||||
or abs(len(game_name_normalized) - len(search_term_normalized))
|
||||
<= self.fuzzy_match_threshold
|
||||
levenshtein_distance(game_name_normalized, search_term_normalized)
|
||||
<= self.max_levenshtein_distance
|
||||
):
|
||||
game_details = await self._get_game_covers(
|
||||
game_id=game["id"],
|
||||
|
||||
@@ -26,6 +26,7 @@ dependencies = [
|
||||
"gunicorn == 23.0.0",
|
||||
"httpx ~= 0.27",
|
||||
"joserfc ~= 0.9",
|
||||
"levenshtein>=0.27.1",
|
||||
"passlib[bcrypt] ~= 1.7",
|
||||
"pillow ~= 10.3",
|
||||
"psycopg[c] ~= 3.2",
|
||||
|
||||
51
uv.lock
generated
51
uv.lock
generated
@@ -838,6 +838,32 @@ wheels = [
|
||||
{ url = "https://files.pythonhosted.org/packages/2f/57/6bffd4b20b88da3800c5d691e0337761576ee688eb01299eae865689d2df/jupyter_core-5.8.1-py3-none-any.whl", hash = "sha256:c28d268fc90fb53f1338ded2eb410704c5449a358406e8a948b75706e24863d0", size = 28880, upload-time = "2025-05-27T07:38:15.137Z" },
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "levenshtein"
|
||||
version = "0.27.1"
|
||||
source = { registry = "https://pypi.org/simple" }
|
||||
dependencies = [
|
||||
{ name = "rapidfuzz" },
|
||||
]
|
||||
sdist = { url = "https://files.pythonhosted.org/packages/7e/b3/b5f8011483ba9083a0bc74c4d58705e9cf465fbe55c948a1b1357d0a2aa8/levenshtein-0.27.1.tar.gz", hash = "sha256:3e18b73564cfc846eec94dd13fab6cb006b5d2e0cc56bad1fd7d5585881302e3", size = 382571, upload-time = "2025-03-02T19:44:56.148Z" }
|
||||
wheels = [
|
||||
{ url = "https://files.pythonhosted.org/packages/c6/d3/30485fb9aee848542ee2d01aba85106a7f5da982ebeeffc619f70ea593c7/levenshtein-0.27.1-cp313-cp313-macosx_10_13_x86_64.whl", hash = "sha256:ab00c2cae2889166afb7e1af64af2d4e8c1b126f3902d13ef3740df00e54032d", size = 173397, upload-time = "2025-03-02T19:43:42.553Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/df/9f/40a81c54cfe74b22737710e654bd25ad934a675f737b60b24f84099540e0/levenshtein-0.27.1-cp313-cp313-macosx_11_0_arm64.whl", hash = "sha256:c27e00bc7527e282f7c437817081df8da4eb7054e7ef9055b851fa3947896560", size = 155787, upload-time = "2025-03-02T19:43:43.864Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/df/98/915f4e24e21982b6eca2c0203546c160f4a83853fa6a2ac6e2b208a54afc/levenshtein-0.27.1-cp313-cp313-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:a5b07de42bfc051136cc8e7f1e7ba2cb73666aa0429930f4218efabfdc5837ad", size = 150013, upload-time = "2025-03-02T19:43:45.134Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/80/93/9b0773107580416b9de14bf6a12bd1dd2b2964f7a9f6fb0e40723e1f0572/levenshtein-0.27.1-cp313-cp313-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:fb11ad3c9dae3063405aa50d9c96923722ab17bb606c776b6817d70b51fd7e07", size = 181234, upload-time = "2025-03-02T19:43:47.125Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/91/b1/3cd4f69af32d40de14808142cc743af3a1b737b25571bd5e8d2f46b885e0/levenshtein-0.27.1-cp313-cp313-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:5c5986fb46cb0c063305fd45b0a79924abf2959a6d984bbac2b511d3ab259f3f", size = 183697, upload-time = "2025-03-02T19:43:48.412Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/bb/65/b691e502c6463f6965b7e0d8d84224c188aa35b53fbc85853c72a0e436c9/levenshtein-0.27.1-cp313-cp313-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:75191e469269ddef2859bc64c4a8cfd6c9e063302766b5cb7e1e67f38cc7051a", size = 159964, upload-time = "2025-03-02T19:43:49.704Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/0f/c0/89a922a47306a475fb6d8f2ab08668f143d3dc7dea4c39d09e46746e031c/levenshtein-0.27.1-cp313-cp313-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:51b3a7b2266933babc04e4d9821a495142eebd6ef709f90e24bc532b52b81385", size = 244759, upload-time = "2025-03-02T19:43:51.733Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/b4/93/30283c6e69a6556b02e0507c88535df9613179f7b44bc49cdb4bc5e889a3/levenshtein-0.27.1-cp313-cp313-musllinux_1_2_aarch64.whl", hash = "sha256:bbac509794afc3e2a9e73284c9e3d0aab5b1d928643f42b172969c3eefa1f2a3", size = 1115955, upload-time = "2025-03-02T19:43:53.739Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/0b/cf/7e19ea2c23671db02fbbe5a5a4aeafd1d471ee573a6251ae17008458c434/levenshtein-0.27.1-cp313-cp313-musllinux_1_2_i686.whl", hash = "sha256:8d68714785178347ecb272b94e85cbf7e638165895c4dd17ab57e7742d8872ec", size = 1400921, upload-time = "2025-03-02T19:43:55.146Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/e3/f7/fb42bfe2f3b46ef91f0fc6fa217b44dbeb4ef8c72a9c1917bbbe1cafc0f8/levenshtein-0.27.1-cp313-cp313-musllinux_1_2_ppc64le.whl", hash = "sha256:8ee74ee31a5ab8f61cd6c6c6e9ade4488dde1285f3c12207afc018393c9b8d14", size = 1225037, upload-time = "2025-03-02T19:43:56.7Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/74/25/c86f8874ac7b0632b172d0d1622ed3ab9608a7f8fe85d41d632b16f5948e/levenshtein-0.27.1-cp313-cp313-musllinux_1_2_s390x.whl", hash = "sha256:f2441b6365453ec89640b85344afd3d602b0d9972840b693508074c613486ce7", size = 1420601, upload-time = "2025-03-02T19:43:58.383Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/20/fe/ebfbaadcd90ea7dfde987ae95b5c11dc27c2c5d55a2c4ccbbe4e18a8af7b/levenshtein-0.27.1-cp313-cp313-musllinux_1_2_x86_64.whl", hash = "sha256:a9be39640a46d8a0f9be729e641651d16a62b2c07d3f4468c36e1cc66b0183b9", size = 1188241, upload-time = "2025-03-02T19:44:00.976Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/2e/1a/aa6b07316e10781a6c5a5a8308f9bdc22213dc3911b959daa6d7ff654fc6/levenshtein-0.27.1-cp313-cp313-win32.whl", hash = "sha256:a520af67d976761eb6580e7c026a07eb8f74f910f17ce60e98d6e492a1f126c7", size = 88103, upload-time = "2025-03-02T19:44:02.42Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/9d/7b/9bbfd417f80f1047a28d0ea56a9b38b9853ba913b84dd5998785c5f98541/levenshtein-0.27.1-cp313-cp313-win_amd64.whl", hash = "sha256:7dd60aa49c2d8d23e0ef6452c8329029f5d092f386a177e3385d315cabb78f2a", size = 100579, upload-time = "2025-03-02T19:44:04.142Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/8b/01/5f3ff775db7340aa378b250e2a31e6b4b038809a24ff0a3636ef20c7ca31/levenshtein-0.27.1-cp313-cp313-win_arm64.whl", hash = "sha256:149cd4f0baf5884ac5df625b7b0d281721b15de00f447080e38f5188106e1167", size = 87933, upload-time = "2025-03-02T19:44:05.364Z" },
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "linkify-it-py"
|
||||
version = "2.0.3"
|
||||
@@ -1656,6 +1682,29 @@ wheels = [
|
||||
{ url = "https://files.pythonhosted.org/packages/ad/ef/5ae5445d5f675e9e8c868b2326597c5b396e41c5c9645daa45e8c1cd3d5c/pyzstd-0.17.0-cp313-cp313-win_arm64.whl", hash = "sha256:ce6d5fd908fd3ddec32d1c1a5a7a15b9d7737d0ef2ab20fe1e8261da61395017", size = 222966, upload-time = "2025-05-10T14:13:59.881Z" },
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "rapidfuzz"
|
||||
version = "3.13.0"
|
||||
source = { registry = "https://pypi.org/simple" }
|
||||
sdist = { url = "https://files.pythonhosted.org/packages/ed/f6/6895abc3a3d056b9698da3199b04c0e56226d530ae44a470edabf8b664f0/rapidfuzz-3.13.0.tar.gz", hash = "sha256:d2eaf3839e52cbcc0accbe9817a67b4b0fcf70aaeb229cfddc1c28061f9ce5d8", size = 57904226, upload-time = "2025-04-03T20:38:51.226Z" }
|
||||
wheels = [
|
||||
{ url = "https://files.pythonhosted.org/packages/0a/76/606e71e4227790750f1646f3c5c873e18d6cfeb6f9a77b2b8c4dec8f0f66/rapidfuzz-3.13.0-cp313-cp313-macosx_10_13_x86_64.whl", hash = "sha256:09e908064d3684c541d312bd4c7b05acb99a2c764f6231bd507d4b4b65226c23", size = 1982282, upload-time = "2025-04-03T20:36:46.149Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/0a/f5/d0b48c6b902607a59fd5932a54e3518dae8223814db8349b0176e6e9444b/rapidfuzz-3.13.0-cp313-cp313-macosx_11_0_arm64.whl", hash = "sha256:57c390336cb50d5d3bfb0cfe1467478a15733703af61f6dffb14b1cd312a6fae", size = 1439274, upload-time = "2025-04-03T20:36:48.323Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/59/cf/c3ac8c80d8ced6c1f99b5d9674d397ce5d0e9d0939d788d67c010e19c65f/rapidfuzz-3.13.0-cp313-cp313-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:0da54aa8547b3c2c188db3d1c7eb4d1bb6dd80baa8cdaeaec3d1da3346ec9caa", size = 1399854, upload-time = "2025-04-03T20:36:50.294Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/09/5d/ca8698e452b349c8313faf07bfa84e7d1c2d2edf7ccc67bcfc49bee1259a/rapidfuzz-3.13.0-cp313-cp313-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:df8e8c21e67afb9d7fbe18f42c6111fe155e801ab103c81109a61312927cc611", size = 5308962, upload-time = "2025-04-03T20:36:52.421Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/66/0a/bebada332854e78e68f3d6c05226b23faca79d71362509dbcf7b002e33b7/rapidfuzz-3.13.0-cp313-cp313-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:461fd13250a2adf8e90ca9a0e1e166515cbcaa5e9c3b1f37545cbbeff9e77f6b", size = 1625016, upload-time = "2025-04-03T20:36:54.639Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/de/0c/9e58d4887b86d7121d1c519f7050d1be5eb189d8a8075f5417df6492b4f5/rapidfuzz-3.13.0-cp313-cp313-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:c2b3dd5d206a12deca16870acc0d6e5036abeb70e3cad6549c294eff15591527", size = 1600414, upload-time = "2025-04-03T20:36:56.669Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/9b/df/6096bc669c1311568840bdcbb5a893edc972d1c8d2b4b4325c21d54da5b1/rapidfuzz-3.13.0-cp313-cp313-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:1343d745fbf4688e412d8f398c6e6d6f269db99a54456873f232ba2e7aeb4939", size = 3053179, upload-time = "2025-04-03T20:36:59.366Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/f9/46/5179c583b75fce3e65a5cd79a3561bd19abd54518cb7c483a89b284bf2b9/rapidfuzz-3.13.0-cp313-cp313-musllinux_1_2_aarch64.whl", hash = "sha256:b1b065f370d54551dcc785c6f9eeb5bd517ae14c983d2784c064b3aa525896df", size = 2456856, upload-time = "2025-04-03T20:37:01.708Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/6b/64/e9804212e3286d027ac35bbb66603c9456c2bce23f823b67d2f5cabc05c1/rapidfuzz-3.13.0-cp313-cp313-musllinux_1_2_i686.whl", hash = "sha256:11b125d8edd67e767b2295eac6eb9afe0b1cdc82ea3d4b9257da4b8e06077798", size = 7567107, upload-time = "2025-04-03T20:37:04.521Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/8a/f2/7d69e7bf4daec62769b11757ffc31f69afb3ce248947aadbb109fefd9f65/rapidfuzz-3.13.0-cp313-cp313-musllinux_1_2_ppc64le.whl", hash = "sha256:c33f9c841630b2bb7e69a3fb5c84a854075bb812c47620978bddc591f764da3d", size = 2854192, upload-time = "2025-04-03T20:37:06.905Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/05/21/ab4ad7d7d0f653e6fe2e4ccf11d0245092bef94cdff587a21e534e57bda8/rapidfuzz-3.13.0-cp313-cp313-musllinux_1_2_s390x.whl", hash = "sha256:ae4574cb66cf1e85d32bb7e9ec45af5409c5b3970b7ceb8dea90168024127566", size = 3398876, upload-time = "2025-04-03T20:37:09.692Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/0f/a8/45bba94c2489cb1ee0130dcb46e1df4fa2c2b25269e21ffd15240a80322b/rapidfuzz-3.13.0-cp313-cp313-musllinux_1_2_x86_64.whl", hash = "sha256:e05752418b24bbd411841b256344c26f57da1148c5509e34ea39c7eb5099ab72", size = 4377077, upload-time = "2025-04-03T20:37:11.929Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/0c/f3/5e0c6ae452cbb74e5436d3445467447e8c32f3021f48f93f15934b8cffc2/rapidfuzz-3.13.0-cp313-cp313-win32.whl", hash = "sha256:0e1d08cb884805a543f2de1f6744069495ef527e279e05370dd7c83416af83f8", size = 1822066, upload-time = "2025-04-03T20:37:14.425Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/96/e3/a98c25c4f74051df4dcf2f393176b8663bfd93c7afc6692c84e96de147a2/rapidfuzz-3.13.0-cp313-cp313-win_amd64.whl", hash = "sha256:9a7c6232be5f809cd39da30ee5d24e6cadd919831e6020ec6c2391f4c3bc9264", size = 1615100, upload-time = "2025-04-03T20:37:16.611Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/60/b1/05cd5e697c00cd46d7791915f571b38c8531f714832eff2c5e34537c49ee/rapidfuzz-3.13.0-cp313-cp313-win_arm64.whl", hash = "sha256:3f32f15bacd1838c929b35c84b43618481e1b3d7a61b5ed2db0291b70ae88b53", size = 858976, upload-time = "2025-04-03T20:37:19.336Z" },
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "redis"
|
||||
version = "6.2.0"
|
||||
@@ -1709,6 +1758,7 @@ dependencies = [
|
||||
{ name = "gunicorn" },
|
||||
{ name = "httpx" },
|
||||
{ name = "joserfc" },
|
||||
{ name = "levenshtein" },
|
||||
{ name = "passlib", extra = ["bcrypt"] },
|
||||
{ name = "pillow" },
|
||||
{ name = "psycopg", extra = ["c"] },
|
||||
@@ -1773,6 +1823,7 @@ requires-dist = [
|
||||
{ name = "ipdb", marker = "extra == 'dev'", specifier = "~=0.13" },
|
||||
{ name = "ipykernel", marker = "extra == 'dev'", specifier = "~=6.29" },
|
||||
{ name = "joserfc", specifier = "~=0.9" },
|
||||
{ name = "levenshtein", specifier = ">=0.27.1" },
|
||||
{ name = "memray", marker = "extra == 'dev'", specifier = "~=1.15" },
|
||||
{ name = "mypy", marker = "extra == 'dev'", specifier = "~=1.13" },
|
||||
{ name = "passlib", extras = ["bcrypt"], specifier = "~=1.7" },
|
||||
|
||||
Reference in New Issue
Block a user