paradizelost/paperless-ngx
1
0
Fork 0
mirror of https://github.com/paperless-ngx/paperless-ngx.git synced 2025-04-25 10:49:30 -05:00
Code Issues Packages Projects Releases Wiki Activity

Merge pull request #2727 from bdr99/disable-matching

Browse Source 
Feature: Add an option to disable matching
This commit is contained in:
shamoon 2023-02-22 07:13:27 -08:00 committed by GitHub
commit 782db3f324
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
9 changed files with 170 additions and 37 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5
docs/advanced_usage.md
View File

@ -9,7 +9,7 @@ Paperless will compare the matching algorithms defined by every tag,
correspondent, document type, and storage path in your database to see
if they apply to the text in a document. In other words, if you define a
tag called `Home Utility` that had a `match` property of `bc hydro` and
a `matching_algorithm` of `literal`, Paperless will automatically tag
a `matching_algorithm` of `Exact`, Paperless will automatically tag
your newly-consumed document with your `Home Utility` tag so long as the
text `bc hydro` appears in the body of the document somewhere.
@ -25,12 +25,13 @@ documents.
The following algorithms are available:
- **None:** No matching will be performed.
- **Any:** Looks for any occurrence of any word provided in match in
the PDF. If you define the match as `Bank1 Bank2`, it will match
documents containing either of these terms.
- **All:** Requires that every word provided appears in the PDF,
albeit not in the order provided.
- **Literal:** Matches only if the match appears exactly as provided
- **Exact:** Matches only if the match appears exactly as provided
(i.e. preserve ordering) in the PDF.
- **Regular expression:** Parses the match as a regular expression and
tries to find a match within the document.

72
src-ui/messages.xlf
View File

@ -1109,21 +1109,21 @@
<source>Create new item</source>
<context-group purpose="location">
<context context-type="sourcefile">src/app/components/common/edit-dialog/edit-dialog.component.ts</context>
<context context-type="linenumber">67</context>
<context context-type="linenumber">71</context>
</context-group>
</trans-unit>
<trans-unit id="5324147361912094446" datatype="html">
<source>Edit item</source>
<context-group purpose="location">
<context context-type="sourcefile">src/app/components/common/edit-dialog/edit-dialog.component.ts</context>
<context context-type="linenumber">71</context>
<context context-type="linenumber">75</context>
</context-group>
</trans-unit>
<trans-unit id="1699589597032579396" datatype="html">
<source>Could not save element: <x id="PH" equiv-text="error"/></source>
<context-group purpose="location">
<context context-type="sourcefile">src/app/components/common/edit-dialog/edit-dialog.component.ts</context>
<context context-type="linenumber">75</context>
<context context-type="linenumber">79</context>
</context-group>
</trans-unit>
<trans-unit id="7314814725704332646" datatype="html">
@ -1498,7 +1498,7 @@
</context-group>
<context-group purpose="location">
<context context-type="sourcefile">src/app/components/manage/management-list/management-list.component.ts</context>
<context context-type="linenumber">192</context>
<context context-type="linenumber">195</context>
</context-group>
<context-group purpose="location">
<context context-type="sourcefile">src/app/components/manage/settings/settings.component.html</context>
@ -2671,7 +2671,7 @@
</context-group>
<context-group purpose="location">
<context context-type="sourcefile">src/app/components/manage/management-list/management-list.component.ts</context>
<context context-type="linenumber">188</context>
<context context-type="linenumber">191</context>
</context-group>
</trans-unit>
<trans-unit id="5382975254277698192" datatype="html">
@ -3677,53 +3677,64 @@
<source>Automatic</source>
<context-group purpose="location">
<context context-type="sourcefile">src/app/components/manage/management-list/management-list.component.ts</context>
<context context-type="linenumber">98</context>
<context context-type="linenumber">99</context>
</context-group>
<context-group purpose="location">
<context context-type="sourcefile">src/app/data/matching-model.ts</context>
<context context-type="linenumber">39</context>
<context context-type="linenumber">15</context>
</context-group>
</trans-unit>
<trans-unit id="6252070156626006029" datatype="html">
<source>None</source>
<context-group purpose="location">
<context context-type="sourcefile">src/app/components/manage/management-list/management-list.component.ts</context>
<context context-type="linenumber">101</context>
</context-group>
<context-group purpose="location">
<context context-type="sourcefile">src/app/data/matching-model.ts</context>
<context context-type="linenumber">45</context>
</context-group>
</trans-unit>
<trans-unit id="211408744872436427" datatype="html">
<source>Successfully created <x id="PH" equiv-text="this.typeName"/>.</source>
<context-group purpose="location">
<context context-type="sourcefile">src/app/components/manage/management-list/management-list.component.ts</context>
<context context-type="linenumber">138</context>
<context context-type="linenumber">141</context>
</context-group>
</trans-unit>
<trans-unit id="6328828522970676938" datatype="html">
<source>Error occurred while creating <x id="PH" equiv-text="this.typeName"/> : <x id="PH_1" equiv-text="e.toString()"/>.</source>
<context-group purpose="location">
<context context-type="sourcefile">src/app/components/manage/management-list/management-list.component.ts</context>
<context context-type="linenumber">143,145</context>
<context context-type="linenumber">146,148</context>
</context-group>
</trans-unit>
<trans-unit id="2541368547549828690" datatype="html">
<source>Successfully updated <x id="PH" equiv-text="this.typeName"/>.</source>
<context-group purpose="location">
<context context-type="sourcefile">src/app/components/manage/management-list/management-list.component.ts</context>
<context context-type="linenumber">161</context>
<context context-type="linenumber">164</context>
</context-group>
</trans-unit>
<trans-unit id="6151710751857751783" datatype="html">
<source>Error occurred while saving <x id="PH" equiv-text="this.typeName"/> : <x id="PH_1" equiv-text="e.toString()"/>.</source>
<context-group purpose="location">
<context context-type="sourcefile">src/app/components/manage/management-list/management-list.component.ts</context>
<context context-type="linenumber">166,168</context>
<context context-type="linenumber">169,171</context>
</context-group>
</trans-unit>
<trans-unit id="4012132330507560812" datatype="html">
<source>Do you really want to delete the <x id="PH" equiv-text="this.typeName"/>?</source>
<context-group purpose="location">
<context context-type="sourcefile">src/app/components/manage/management-list/management-list.component.ts</context>
<context context-type="linenumber">175</context>
<context context-type="linenumber">178</context>
</context-group>
</trans-unit>
<trans-unit id="8371896857609524947" datatype="html">
<source>Associated documents will not be deleted.</source>
<context-group purpose="location">
<context context-type="sourcefile">src/app/components/manage/management-list/management-list.component.ts</context>
<context context-type="linenumber">190</context>
<context context-type="linenumber">193</context>
</context-group>
</trans-unit>
<trans-unit id="5467489005440577210" datatype="html">
@ -3732,7 +3743,7 @@
)"/></source>
<context-group purpose="location">
<context context-type="sourcefile">src/app/components/manage/management-list/management-list.component.ts</context>
<context context-type="linenumber">203,205</context>
<context context-type="linenumber">206,208</context>
</context-group>
</trans-unit>
<trans-unit id="1685061484835793745" datatype="html">
@ -4501,81 +4512,88 @@
<context context-type="linenumber">7</context>
</context-group>
</trans-unit>
<trans-unit id="2167862279705099846" datatype="html">
<source>Auto: Learn matching automatically</source>
<context-group purpose="location">
<context context-type="sourcefile">src/app/data/matching-model.ts</context>
<context context-type="linenumber">16</context>
</context-group>
</trans-unit>
<trans-unit id="5851669019930456395" datatype="html">
<source>Any word</source>
<context-group purpose="location">
<context context-type="sourcefile">src/app/data/matching-model.ts</context>
<context context-type="linenumber">14</context>
<context context-type="linenumber">20</context>
</context-group>
</trans-unit>
<trans-unit id="7517655726614958140" datatype="html">
<source>Any: Document contains any of these words (space separated)</source>
<context-group purpose="location">
<context context-type="sourcefile">src/app/data/matching-model.ts</context>
<context context-type="linenumber">15</context>
<context context-type="linenumber">21</context>
</context-group>
</trans-unit>
<trans-unit id="700315718208181326" datatype="html">
<source>All words</source>
<context-group purpose="location">
<context context-type="sourcefile">src/app/data/matching-model.ts</context>
<context context-type="linenumber">19</context>
<context context-type="linenumber">25</context>
</context-group>
</trans-unit>
<trans-unit id="111914402588955480" datatype="html">
<source>All: Document contains all of these words (space separated)</source>
<context-group purpose="location">
<context context-type="sourcefile">src/app/data/matching-model.ts</context>
<context context-type="linenumber">20</context>
<context context-type="linenumber">26</context>
</context-group>
</trans-unit>
<trans-unit id="9180173992399180575" datatype="html">
<source>Exact match</source>
<context-group purpose="location">
<context context-type="sourcefile">src/app/data/matching-model.ts</context>
<context context-type="linenumber">24</context>
<context context-type="linenumber">30</context>
</context-group>
</trans-unit>
<trans-unit id="7109184332944610787" datatype="html">
<source>Exact: Document contains this string</source>
<context-group purpose="location">
<context context-type="sourcefile">src/app/data/matching-model.ts</context>
<context context-type="linenumber">25</context>
<context context-type="linenumber">31</context>
</context-group>
</trans-unit>
<trans-unit id="1338733395833138319" datatype="html">
<source>Regular expression</source>
<context-group purpose="location">
<context context-type="sourcefile">src/app/data/matching-model.ts</context>
<context context-type="linenumber">29</context>
<context context-type="linenumber">35</context>
</context-group>
</trans-unit>
<trans-unit id="7548151332424148033" datatype="html">
<source>Regular expression: Document matches this regular expression</source>
<context-group purpose="location">
<context context-type="sourcefile">src/app/data/matching-model.ts</context>
<context context-type="linenumber">30</context>
<context context-type="linenumber">36</context>
</context-group>
</trans-unit>
<trans-unit id="1856513373880048959" datatype="html">
<source>Fuzzy word</source>
<context-group purpose="location">
<context context-type="sourcefile">src/app/data/matching-model.ts</context>
<context context-type="linenumber">34</context>
<context context-type="linenumber">40</context>
</context-group>
</trans-unit>
<trans-unit id="8419167206585286450" datatype="html">
<source>Fuzzy: Document contains a word similar to this word</source>
<context-group purpose="location">
<context context-type="sourcefile">src/app/data/matching-model.ts</context>
<context context-type="linenumber">35</context>
<context context-type="linenumber">41</context>
</context-group>
</trans-unit>
<trans-unit id="2167862279705099846" datatype="html">
<source>Auto: Learn matching automatically</source>
<trans-unit id="8233576851457338601" datatype="html">
<source>None: Disable matching</source>
<context-group purpose="location">
<context context-type="sourcefile">src/app/data/matching-model.ts</context>
<context context-type="linenumber">40</context>
<context context-type="linenumber">46</context>
</context-group>
</trans-unit>
<trans-unit id="5948496158474272829" datatype="html">

11
src-ui/src/app/components/common/edit-dialog/edit-dialog.component.ts
View File

@ -2,7 +2,11 @@ import { Directive, EventEmitter, Input, OnInit, Output } from '@angular/core'
import { FormGroup } from '@angular/forms'
import { NgbActiveModal } from '@ng-bootstrap/ng-bootstrap'
import { Observable } from 'rxjs'
import { MATCHING_ALGORITHMS, MATCH_AUTO } from 'src/app/data/matching-model'
import {
MATCHING_ALGORITHMS,
MATCH_AUTO,
MATCH_NONE,
} from 'src/app/data/matching-model'
import { ObjectWithId } from 'src/app/data/object-with-id'
import { ObjectWithPermissions } from 'src/app/data/object-with-permissions'
import { PaperlessUser } from 'src/app/data/paperless-user'
@ -91,7 +95,10 @@ export abstract class EditDialogComponent<
}
get patternRequired(): boolean {
return this.objectForm?.value.matching_algorithm !== MATCH_AUTO
return (
this.objectForm?.value.matching_algorithm !== MATCH_AUTO &&
this.objectForm?.value.matching_algorithm !== MATCH_NONE
)
}
save() {

3
src-ui/src/app/components/manage/management-list/management-list.component.ts
View File

@ -12,6 +12,7 @@ import {
MatchingModel,
MATCHING_ALGORITHMS,
MATCH_AUTO,
MATCH_NONE,
} from 'src/app/data/matching-model'
import { ObjectWithId } from 'src/app/data/object-with-id'
import { ObjectWithPermissions } from 'src/app/data/object-with-permissions'
@ -96,6 +97,8 @@ export abstract class ManagementListComponent<T extends ObjectWithId>
getMatching(o: MatchingModel) {
if (o.matching_algorithm == MATCH_AUTO) {
return $localize`Automatic`
} else if (o.matching_algorithm == MATCH_NONE) {
return $localize`None`
} else if (o.match && o.match.length > 0) {
return `${
MATCHING_ALGORITHMS.find((a) => a.id == o.matching_algorithm).shortName

16
src-ui/src/app/data/matching-model.ts
View File

@ -1,5 +1,6 @@
import { ObjectWithPermissions } from './object-with-permissions'
import { ObjectWithId } from './object-with-id'
export const MATCH_NONE = 0
export const MATCH_ANY = 1
export const MATCH_ALL = 2
export const MATCH_LITERAL = 3
@ -9,6 +10,11 @@ export const MATCH_AUTO = 6
export const DEFAULT_MATCHING_ALGORITHM = MATCH_AUTO
export const MATCHING_ALGORITHMS = [
{
id: MATCH_AUTO,
shortName: $localize`Automatic`,
name: $localize`Auto: Learn matching automatically`,
},
{
id: MATCH_ANY,
shortName: $localize`Any word`,
@ -35,13 +41,13 @@ export const MATCHING_ALGORITHMS = [
name: $localize`Fuzzy: Document contains a word similar to this word`,
},
{
id: MATCH_AUTO,
shortName: $localize`Automatic`,
name: $localize`Auto: Learn matching automatically`,
id: MATCH_NONE,
shortName: $localize`None`,
name: $localize`None: Disable matching`,
},
]
export interface MatchingModel extends ObjectWithPermissions {
export interface MatchingModel extends ObjectWithId {
name?: string
slug?: string

5
src/documents/matching.py
View File

@ -86,7 +86,10 @@ def matches(matching_model, document):
if matching_model.is_insensitive:
search_kwargs = {"flags": re.IGNORECASE}
if matching_model.matching_algorithm == MatchingModel.MATCH_ALL:
if matching_model.matching_algorithm == MatchingModel.MATCH_NONE:
return False
elif matching_model.matching_algorithm == MatchingModel.MATCH_ALL:
for word in _split_match(matching_model):
search_result = re.search(rf"\b{word}\b", document_content, **search_kwargs)
if not search_result:

81
src/documents/migrations/1032_alter_correspondent_matching_algorithm_and_more.py Normal file
View File

@ -0,0 +1,81 @@
# Generated by Django 4.1.7 on 2023-02-22 00:45
from django.db import migrations, models
class Migration(migrations.Migration):
dependencies = [
("documents", "1031_remove_savedview_user_correspondent_owner_and_more"),
]
operations = [
migrations.AlterField(
model_name="correspondent",
name="matching_algorithm",
field=models.PositiveIntegerField(
choices=[
(0, "None"),
(1, "Any word"),
(2, "All words"),
(3, "Exact match"),
(4, "Regular expression"),
(5, "Fuzzy word"),
(6, "Automatic"),
],
default=1,
verbose_name="matching algorithm",
),
),
migrations.AlterField(
model_name="documenttype",
name="matching_algorithm",
field=models.PositiveIntegerField(
choices=[
(0, "None"),
(1, "Any word"),
(2, "All words"),
(3, "Exact match"),
(4, "Regular expression"),
(5, "Fuzzy word"),
(6, "Automatic"),
],
default=1,
verbose_name="matching algorithm",
),
),
migrations.AlterField(
model_name="storagepath",
name="matching_algorithm",
field=models.PositiveIntegerField(
choices=[
(0, "None"),
(1, "Any word"),
(2, "All words"),
(3, "Exact match"),
(4, "Regular expression"),
(5, "Fuzzy word"),
(6, "Automatic"),
],
default=1,
verbose_name="matching algorithm",
),
),
migrations.AlterField(
model_name="tag",
name="matching_algorithm",
field=models.PositiveIntegerField(
choices=[
(0, "None"),
(1, "Any word"),
(2, "All words"),
(3, "Exact match"),
(4, "Regular expression"),
(5, "Fuzzy word"),
(6, "Automatic"),
],
default=1,
verbose_name="matching algorithm",
),
),
]

2
src/documents/models.py
View File

@ -24,6 +24,7 @@ TASK_STATE_CHOICES = sorted(zip(ALL_STATES, ALL_STATES))
class MatchingModel(models.Model):
MATCH_NONE = 0
MATCH_ANY = 1
MATCH_ALL = 2
MATCH_LITERAL = 3
@ -32,6 +33,7 @@ class MatchingModel(models.Model):
MATCH_AUTO = 6
MATCHING_ALGORITHMS = (
(MATCH_NONE, _("None")),
(MATCH_ANY, _("Any word")),
(MATCH_ALL, _("All words")),
(MATCH_LITERAL, _("Exact match")),

12
src/documents/tests/test_matchables.py
View File

@ -47,6 +47,18 @@ class _TestMatchingBase(TestCase):
class TestMatching(_TestMatchingBase):
def test_match_none(self):
self._test_matching(
"",
"MATCH_NONE",
(),
(
"no",
"match",
),
)
def test_match_all(self):
self._test_matching(