TheAnachronism/docspell
1
0
Fork 0
mirror of https://github.com/TheAnachronism/docspell.git synced 2025-06-22 02:18:26 +00:00
Code Issues Packages Projects Releases Wiki Activity

Merge pull request #2380 from eikek/custom-processing-data

Browse Source 
Custom processing data
This commit is contained in:
mergify[bot]
2023-11-15 19:28:03 +00:00
committed by GitHub
parent 4454d9ec63 175ae02996
commit c4a595d788
16 changed files with 62 additions and 25 deletions
Download Patch File Download Diff File Expand all files Collapse all files

10
modules/addonlib/src/main/scala/docspell/addons/out/NewFile.scala
View File

@ -15,10 +15,10 @@ import docspell.common.ProcessItemArgs.ProcessMeta
import docspell.common.{CollectiveId, Ident, Language}
import docspell.logging.Logger
import io.circe.Codec
import io.circe.generic.extras.Configuration
import io.circe.generic.extras.semiauto.deriveConfiguredCodec
import io.circe.generic.semiauto.deriveCodec
import io.circe.{Codec, Json}
case class NewFile(metadata: Meta = Meta.empty, file: String) {
@ -41,7 +41,8 @@ object NewFile {
case class Meta(
language: Option[Language],
skipDuplicate: Option[Boolean],
attachmentsOnly: Option[Boolean]
attachmentsOnly: Option[Boolean],
customData: Option[Json]
) {
def toProcessMeta(
@ -62,12 +63,13 @@ object NewFile {
fileFilter = None,
tags = None,
reprocess = false,
attachmentsOnly = attachmentsOnly
attachmentsOnly = attachmentsOnly,
customData = customData
)
}
object Meta {
val empty = Meta(None, None, None)
val empty = Meta(None, None, None, None)
implicit val jsonCodec: Codec[Meta] = deriveCodec
}

12
modules/addonlib/src/main/scala/docspell/addons/out/NewItem.scala
View File

@ -15,7 +15,7 @@ import docspell.common._
import docspell.logging.Logger
import io.circe.generic.semiauto.{deriveDecoder, deriveEncoder}
import io.circe.{Decoder, Encoder}
import io.circe.{Decoder, Encoder, Json}
case class NewItem(metadata: Option[Meta], files: List[String]) {
@ -25,7 +25,7 @@ case class NewItem(metadata: Option[Meta], files: List[String]) {
sourceAbbrev: String
): ProcessItemArgs.ProcessMeta =
metadata
.getOrElse(Meta(None, None, None, None, None, None, None))
.getOrElse(Meta.empty)
.toProcessArgs(cid, collLang, sourceAbbrev)
def resolveFiles[F[_]: Files: Monad](
@ -58,7 +58,8 @@ object NewItem {
source: Option[String],
skipDuplicate: Option[Boolean],
tags: Option[List[String]],
attachmentsOnly: Option[Boolean]
attachmentsOnly: Option[Boolean],
customData: Option[Json]
) {
def toProcessArgs(
@ -78,11 +79,14 @@ object NewItem {
fileFilter = None,
tags = tags,
reprocess = false,
attachmentsOnly = attachmentsOnly
attachmentsOnly = attachmentsOnly,
customData = customData
)
}
object Meta {
val empty: Meta = Meta(None, None, None, None, None, None, None, None)
implicit val jsonEncoder: Encoder[Meta] = deriveEncoder
implicit val jsonDecoder: Decoder[Meta] = deriveDecoder
}

8
modules/backend/src/main/scala/docspell/backend/ops/OUpload.scala
View File

@ -19,6 +19,8 @@ import docspell.scheduler.{Job, JobStore}
import docspell.store.Store
import docspell.store.records._
import io.circe.Json
trait OUpload[F[_]] {
def submit(
@ -69,7 +71,8 @@ object OUpload {
tags: List[String],
language: Option[Language],
attachmentsOnly: Option[Boolean],
flattenArchives: Option[Boolean]
flattenArchives: Option[Boolean],
customData: Option[Json]
)
case class UploadData[F[_]](
@ -157,7 +160,8 @@ object OUpload {
data.meta.fileFilter.some,
data.meta.tags.some,
false,
data.meta.attachmentsOnly
data.meta.attachmentsOnly,
data.meta.customData
)
args = ProcessItemArgs(meta, files.toList)
jobs <- right(

3
modules/common/src/main/scala/docspell/common/ProcessItemArgs.scala
View File

@ -54,7 +54,8 @@ object ProcessItemArgs {
fileFilter: Option[Glob],
tags: Option[List[String]],
reprocess: Boolean,
attachmentsOnly: Option[Boolean]
attachmentsOnly: Option[Boolean],
customData: Option[Json]
)
object ProcessMeta {

3
modules/joex/src/main/scala/docspell/joex/addon/ItemAddonTask.scala
View File

@ -75,6 +75,7 @@ object ItemAddonTask extends AddonTaskExtension {
givenMeta = proposals,
tags = tags.map(_.name).toList,
classifyProposals = MetaProposalList.empty,
classifyTags = Nil
classifyTags = Nil,
customData = None // can't retain this information from a final item. TODO
)
}

6
modules/joex/src/main/scala/docspell/joex/process/CreateItem.scala
View File

@ -112,7 +112,8 @@ object CreateItem {
MetaProposalList.empty,
Nil,
MetaProposalList.empty,
Nil
Nil,
ctx.args.meta.customData
)
}
@ -175,7 +176,8 @@ object CreateItem {
MetaProposalList.empty,
Nil,
MetaProposalList.empty,
Nil
Nil,
ctx.args.meta.customData
)
)
}

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

@ -46,7 +46,8 @@ case class ItemData(
tags: List[String],
// proposals obtained from the classifier
classifyProposals: MetaProposalList,
classifyTags: List[String]
classifyTags: List[String],
customData: Option[Json]
) {
/** sort by weight; order of equal weights is not important, just choose one others are
@ -121,6 +122,7 @@ object ItemData {
)
)
.asJson,
"customData" -> data.customData.asJson,
"tags" -> data.tags.asJson,
"assumedTags" -> data.classifyTags.asJson,
"assumedCorrOrg" -> data.finalProposals

6
modules/joex/src/main/scala/docspell/joex/process/ReProcessItem.scala
View File

@ -101,7 +101,8 @@ object ReProcessItem {
MetaProposalList.empty,
Nil,
MetaProposalList.empty,
Nil
Nil,
None // cannot retain customData from an already existing item
)).getOrElseF(
Sync[F].raiseError(new Exception(s"Item not found: ${ctx.args.itemId.id}"))
)
@ -134,7 +135,8 @@ object ReProcessItem {
None,
None,
true,
None // attachOnly (not used when reprocessing attachments)
None, // attachOnly (not used when reprocessing attachments)
None // cannot retain customData from an already existing item
),
Nil
).pure[F]

1
modules/joex/src/main/scala/docspell/joex/scanmailbox/ScanMailboxTask.scala
View File

@ -328,6 +328,7 @@ object ScanMailboxTask {
args.tags.getOrElse(Nil),
args.language,
args.attachmentsOnly,
None,
None
)
data = OUpload.UploadData(

7
modules/restapi/src/main/resources/docspell-openapi.yml
View File

@ -8250,6 +8250,13 @@ components:
attachments of the e-mail are imported and the e-mail body
is discarded. E-mails that don't have any attachments are
skipped.
customData:
type: object
format: json
description: |
Custom user data that gets threaded through the processing. Docspell
ignores it completely, but will pass it to the outcome of processing
to be able to react on it in addons or other ways.
Collective:
description: |

4
modules/restserver/src/main/scala/docspell/restserver/conv/Conversions.scala
View File

@ -315,7 +315,8 @@ trait Conversions {
m.tags.map(_.items).getOrElse(Nil),
m.language,
m.attachmentsOnly,
m.flattenArchives
m.flattenArchives,
m.customData
)
)
)
@ -333,6 +334,7 @@ trait Conversions {
Nil,
None,
None,
None,
None
)
)

3
modules/store/src/main/scala/db/migration/common/MigrateCollectiveIdTaskArgs.scala
View File

@ -348,7 +348,8 @@ object MigrateCollectiveIdTaskArgs extends TransactorSupport {
fileFilter = oldArgs.meta.fileFilter,
tags = oldArgs.meta.tags,
reprocess = oldArgs.meta.reprocess,
attachmentsOnly = oldArgs.meta.attachmentsOnly
attachmentsOnly = oldArgs.meta.attachmentsOnly,
customData = None
),
oldArgs.files.map(f =>
ProcessItemArgs