paradizelost/paperless-ngx
1
0
Fork 0
mirror of https://github.com/paperless-ngx/paperless-ngx.git synced 2025-04-02 13:45:10 -05:00
Code Issues Packages Projects Releases Wiki Activity

add: migration for fuzzy matching

Browse Source
This commit is contained in:
Daniel Quinn 2017-05-11 22:09:30 -07:00
parent 058dad7ba7
commit 731942d855
1 changed files with 25 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

25
src/documents/migrations/0017_auto_20170512_0507.py Normal file
View File

@ -0,0 +1,25 @@
# -*- coding: utf-8 -*-
# Generated by Django 1.10.5 on 2017-05-12 05:07
from __future__ import unicode_literals
from django.db import migrations, models
class Migration(migrations.Migration):
dependencies = [
('documents', '0016_auto_20170325_1558'),
]
operations = [
migrations.AlterField(
model_name='correspondent',
name='matching_algorithm',
field=models.PositiveIntegerField(choices=[(1, 'Any'), (2, 'All'), (3, 'Literal'), (4, 'Regular Expression'), (5, 'Fuzzy Match')], default=1, help_text='Which algorithm you want to use when matching text to the OCR\'d PDF. Here, "any" looks for any occurrence of any word provided in the PDF, while "all" requires that every word provided appear in the PDF, albeit not in the order provided. A "literal" match means that the text you enter must appear in the PDF exactly as you\'ve entered it, and "regular expression" uses a regex to match the PDF. (If you don\'t know what a regex is, you probably don\'t want this option.) Finally, a "fuzzy match" looks for words or phrases that are mostly—but not exactly—the same, which can be useful for matching against documents containg imperfections that foil accurate OCR.'),
),
migrations.AlterField(
model_name='tag',
name='matching_algorithm',
field=models.PositiveIntegerField(choices=[(1, 'Any'), (2, 'All'), (3, 'Literal'), (4, 'Regular Expression'), (5, 'Fuzzy Match')], default=1, help_text='Which algorithm you want to use when matching text to the OCR\'d PDF. Here, "any" looks for any occurrence of any word provided in the PDF, while "all" requires that every word provided appear in the PDF, albeit not in the order provided. A "literal" match means that the text you enter must appear in the PDF exactly as you\'ve entered it, and "regular expression" uses a regex to match the PDF. (If you don\'t know what a regex is, you probably don\'t want this option.) Finally, a "fuzzy match" looks for words or phrases that are mostly—but not exactly—the same, which can be useful for matching against documents containg imperfections that foil accurate OCR.'),
),
]