paradizelost/paperless-ngx
1
0
Fork 0
mirror of https://github.com/paperless-ngx/paperless-ngx.git synced 2025-12-22 01:55:49 -06:00
Code Issues Packages Projects Releases Wiki Activity

Updates the pre-processing of document content to be much more robust, with tokenization, stemming and stop word removal

Browse Source
This commit is contained in:
Trenton Holmes
2022-09-15 08:39:47 -07:00
committed by Trenton H
parent 14d82bd8ff
commit d856e48045
4 changed files with 76 additions and 19 deletions
Download Patch File Download Diff File Expand all files Collapse all files

8
Pipfile.lock generated
View File

@@ -889,6 +889,14 @@
"index": "pypi",
"version": "==2.1.1"
},
"nltk": {
"hashes": [
"sha256:ba3de02490308b248f9b94c8bc1ac0683e9aa2ec49ee78536d8667afb5e3eec8",
"sha256:d6507d6460cec76d70afea4242a226a7542f85c669177b9c7f562b7cf1b05502"
],
"index": "pypi",
"version": "==3.7"
},
"numpy": {
"hashes": [
"sha256:07a8c89a04997625236c5ecb7afe35a02af3896c8aa01890a849913a2309c676",