TheAnachronism/docspell
1
0
Fork 0
mirror of https://github.com/TheAnachronism/docspell.git synced 2025-06-21 18:08:25 +00:00
Code Issues Packages Projects Releases Wiki Activity

Reorganize processing code

Browse Source 
Use separate modules for

- text extraction
- conversion to pdf
- text analysis
This commit is contained in:
Eike Kettner
2020-02-15 16:40:50 +01:00
parent 919381be1e
commit 851ee7ef0f
24 changed files with 103 additions and 60 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
modules/joex/src/main/scala/docspell/joex/Config.scala
View File

@ -3,7 +3,7 @@ package docspell.joex
import docspell.common.{Ident, LenientUri}
import docspell.joex.scheduler.SchedulerConfig
import docspell.store.JdbcConfig
import docspell.text.ocr.{Config => OcrConfig}
import docspell.extract.ocr.{Config => OcrConfig}
import docspell.convert.ConvertConfig
case class Config(

4
modules/joex/src/main/scala/docspell/joex/process/FindProposal.scala
View File

@ -5,11 +5,11 @@ import java.time.ZoneId
import cats.{Applicative, FlatMap}
import cats.implicits._
import cats.effect.Sync
import docspell.analysis.contact._
import docspell.common.MetaProposal.Candidate
import docspell.common._
import docspell.joex.scheduler.{Context, Task}
import docspell.store.records.{RAttachmentMeta, REquipment, ROrganization, RPerson}
import docspell.text.contact.Domain
import docspell.store.records._
/** Super simple approach to find corresponding meta data to an item
* by looking up values from NER in the users address book.

8
modules/joex/src/main/scala/docspell/joex/process/TextAnalysis.scala
View File

@ -2,13 +2,13 @@ package docspell.joex.process
import cats.implicits._
import cats.effect.Sync
import docspell.common.{Duration, Language, NerLabel, ProcessItemArgs}
import docspell.analysis.nlp._
import docspell.analysis.contact._
import docspell.analysis.date._
import docspell.common._
import docspell.joex.process.ItemData.AttachmentDates
import docspell.joex.scheduler.Task
import docspell.store.records.RAttachmentMeta
import docspell.text.contact.Contact
import docspell.text.date.DateFind
import docspell.text.nlp.StanfordNerClassifier
object TextAnalysis {

2
modules/joex/src/main/scala/docspell/joex/process/TextExtraction.scala
View File

@ -7,7 +7,7 @@ import docspell.common._
import docspell.joex.scheduler.{Context, Task}
import docspell.store.Store
import docspell.store.records.{RAttachment, RAttachmentMeta}
import docspell.text.ocr.{TextExtract, Config => OcrConfig}
import docspell.extract.ocr.{TextExtract, Config => OcrConfig}
object TextExtraction {