96 receiving potentially large uploads

backend/build.gradle

@@ -42,10 +42,14 @@ dependencies {
     implementation "org.jetbrains.exposed:exposed-kotlin-datetime:$exposedVersion"
     implementation "org.jetbrains.kotlinx:kotlinx-datetime:0.5.0"
     implementation "org.hibernate.validator:hibernate-validator:8.0.1.Final"
-    
+
     implementation "org.springframework.boot:spring-boot-starter-oauth2-resource-server"
     implementation "org.springframework.boot:spring-boot-starter-security"
-
+
+    implementation 'org.apache.commons:commons-compress:1.25.0'
+    implementation 'com.github.luben:zstd-jni:1.5.2-4'
+    implementation 'org.tukaani:xz:1.8'
+
     testImplementation("org.springframework.boot:spring-boot-starter-test") {
         exclude group: "org.mockito"
     }

backend/docs/runtime_view.md

@@ -11,7 +11,8 @@
 
 ## Initial submission
 
-To submit new sequences, the user calls the `/submit` endpoint and sends unpreprocessed data.
+To submit new sequences, the user calls the `/submit` endpoint and sends unpreprocessed data. 
+Data may be compressed using zstd, gzip, bzip2, xz, lzma or zip.
 For each sequence, Pathoplexus creates a new row in the "sequenceEntries" table.
 It generates a new accession. The version number of the sequence entries is 1.
 

backend/src/main/kotlin/org/pathoplexus/backend/api/SubmissionTypes.kt

@@ -8,8 +8,8 @@ import com.fasterxml.jackson.databind.JsonDeserializer
 import com.fasterxml.jackson.databind.JsonNode
 import com.fasterxml.jackson.databind.annotation.JsonDeserialize
 import io.swagger.v3.oas.annotations.media.Schema
-import org.pathoplexus.backend.service.Accession
-import org.pathoplexus.backend.service.Version
+import org.pathoplexus.backend.utils.Accession
+import org.pathoplexus.backend.utils.Version
 
 interface AccessionVersionInterface {
     val accession: Accession
@@ -154,11 +154,6 @@ data class RevisedData(
     val originalData: OriginalData,
 )
 
-data class SubmittedData(
-    val submissionId: String,
-    val originalData: OriginalData,
-)
-
 data class UnprocessedData(
     @Schema(example = "123") override val accession: Accession,
     @Schema(example = "1") override val version: Version,
@@ -175,7 +170,7 @@ data class OriginalData(
         example = "{\"segment1\": \"ACTG\", \"segment2\": \"GTCA\"}",
         description = "The key is the segment name, the value is the nucleotide sequence",
     )
-    val unalignedNucleotideSequences: Map<String, String>,
+    val unalignedNucleotideSequences: Map<SegmentName, NucleotideSequence>,
 )
 
 enum class Status {

backend/src/main/kotlin/org/pathoplexus/backend/config/Config.kt

@@ -1,8 +1,15 @@
 package org.pathoplexus.backend.config
 
+import org.pathoplexus.backend.api.Organism
+
 data class BackendConfig(
     val instances: Map<String, InstanceConfig>,
-)
+) {
+    fun getInstanceConfig(organism: Organism) =
+        instances[organism.name] ?: throw IllegalArgumentException(
+            "Organism: ${organism.name} not found in backend config. Available organisms: ${instances.keys}",
+        )
+}
 
 data class InstanceConfig(
     val schema: Schema,

backend/src/main/kotlin/org/pathoplexus/backend/config/ReferenceGenome.kt

@@ -11,6 +11,10 @@ data class ReferenceGenome(
             throw IllegalArgumentException("If there is only one nucleotide sequence, it must be named 'main'")
         }
     }
+
+    fun getNucleotideSegmentReference(segmentName: String): NucleotideSequence? = nucleotideSequences.find {
+        it.name == segmentName
+    }?.sequence
 }
 
 data class ReferenceSequence(

backend/src/main/kotlin/org/pathoplexus/backend/controller/ExceptionHandler.kt

@@ -62,7 +62,11 @@ class ExceptionHandler : ResponseEntityExceptionHandler() {
         return ResponseEntity.status(HttpStatus.UNAUTHORIZED).build()
     }
 
-    @ExceptionHandler(UnprocessableEntityException::class, ProcessingValidationException::class)
+    @ExceptionHandler(
+        UnprocessableEntityException::class,
+        ProcessingValidationException::class,
+        DuplicateKeyException::class,
+    )
     @ResponseStatus(HttpStatus.UNPROCESSABLE_ENTITY)
     fun handleUnprocessableEntityException(e: Exception): ResponseEntity<ProblemDetail> {
         log.warn(e) { "Caught unprocessable entity exception: ${e.message}" }
@@ -144,5 +148,6 @@ class ForbiddenException(message: String) : RuntimeException(message)
 class UnprocessableEntityException(message: String) : RuntimeException(message)
 class NotFoundException(message: String) : RuntimeException(message)
 class ProcessingValidationException(message: String) : RuntimeException(message)
+class DuplicateKeyException(message: String) : RuntimeException(message)
 
 class DummyUnauthorizedExceptionToMakeItAppearInSwaggerUi : RuntimeException()

backend/src/main/kotlin/org/pathoplexus/backend/controller/SubmissionController.kt

@@ -19,8 +19,8 @@ import org.pathoplexus.backend.api.SubmittedProcessedData
 import org.pathoplexus.backend.api.UnprocessedData
 import org.pathoplexus.backend.model.ReleasedDataModel
 import org.pathoplexus.backend.model.SubmitModel
-import org.pathoplexus.backend.service.Accession
 import org.pathoplexus.backend.service.DatabaseService
+import org.pathoplexus.backend.utils.Accession
 import org.pathoplexus.backend.utils.IteratorStreamer
 import org.springframework.http.HttpHeaders
 import org.springframework.http.HttpStatus
@@ -39,6 +39,7 @@ import org.springframework.web.bind.annotation.ResponseStatus
 import org.springframework.web.bind.annotation.RestController
 import org.springframework.web.multipart.MultipartFile
 import org.springframework.web.servlet.mvc.method.annotation.StreamingResponseBody
+import java.util.UUID
 import io.swagger.v3.oas.annotations.parameters.RequestBody as SwaggerRequestBody
 
 @RestController
@@ -61,9 +62,13 @@ class SubmissionController(
         @UsernameFromJwt username: String,
         @Parameter(description = METADATA_FILE_DESCRIPTION) @RequestParam metadataFile: MultipartFile,
         @Parameter(description = SEQUENCE_FILE_DESCRIPTION) @RequestParam sequenceFile: MultipartFile,
-    ): List<SubmissionIdMapping> {
-        return submitModel.processSubmission(username, metadataFile, sequenceFile, organism)
-    }
+    ): List<SubmissionIdMapping> = submitModel.processSubmission(
+        UUID.randomUUID().toString(),
+        metadataFile,
+        sequenceFile,
+        username,
+        organism,
+    )
 
     @Operation(description = EXTRACT_UNPROCESSED_DATA_DESCRIPTION)
     @ApiResponse(

backend/src/main/kotlin/org/pathoplexus/backend/controller/SubmissionControllerDescriptions.kt

@@ -9,13 +9,15 @@ You can use this response to associate the user provided submissionId with the s
 """
 
 const val METADATA_FILE_DESCRIPTION = """    
-A TSV (tab separated values) file containing the metadata of the submitted sequence entries.
+A TSV (tab separated values) file containing the metadata of the submitted sequence entries. 
+The file may be compressed with zstd, xz, zip, gzip, lzma, bzip2 (with common extensions).
 It must contain the column names.
 The field 'submissionId' is required and must be unique within the provided dataset.
 It is used to associate metadata to the sequences in the sequences fasta file.
 """
 const val SEQUENCE_FILE_DESCRIPTION = """
 A fasta file containing the unaligned nucleotide sequences of the submitted sequences.
+The file may be compressed with zstd, xz, zip, gzip, lzma, bzip2 (with common extensions).
 If the underlying organism has a single segment,
 the headers of the fasta file must match the 'submissionId' field in the metadata file.
 If the underlying organism has multiple segments,

backend/src/main/kotlin/org/pathoplexus/backend/model/ReleasedDataModel.kt

@@ -6,10 +6,10 @@ import mu.KotlinLogging
 import org.pathoplexus.backend.api.Organism
 import org.pathoplexus.backend.api.ProcessedData
 import org.pathoplexus.backend.api.SiloVersionStatus
-import org.pathoplexus.backend.service.Accession
 import org.pathoplexus.backend.service.DatabaseService
 import org.pathoplexus.backend.service.RawProcessedData
-import org.pathoplexus.backend.service.Version
+import org.pathoplexus.backend.utils.Accession
+import org.pathoplexus.backend.utils.Version
 import org.springframework.stereotype.Service
 import org.springframework.transaction.annotation.Transactional