Switch to using camelCase for metadata fields

backend/src/test/kotlin/org/loculus/backend/controller/submission/PreparedExternalData.kt

@@ -9,7 +9,7 @@ val defaultExternalMetadata =
         accession = "If a test result shows this, processed data was not prepared correctly.",
         version = 1,
         externalMetadata = mapOf(
-            "insdc_accession_full" to TextNode("GENBANK1000.1"),
+            "insdcAccessionFull" to TextNode("GENBANK1000.1"),
         ),
     )
 

backend/src/test/kotlin/org/loculus/backend/controller/submission/SubmitExternalMetadataEndpointTest.kt

@@ -60,7 +60,7 @@ class SubmitExternalMetadataEndpointTest(
         val releasedSequenceEntry = convenienceClient.getReleasedData()
             .find { it.metadata["accession"]?.textValue() == accessions.first() }
 
-        assertThat(releasedSequenceEntry?.metadata, hasEntry("insdc_accession_full", TextNode("GENBANK1000.1")))
+        assertThat(releasedSequenceEntry?.metadata, hasEntry("insdcAccessionFull", TextNode("GENBANK1000.1")))
     }
 
     @Test
@@ -86,7 +86,7 @@ class SubmitExternalMetadataEndpointTest(
         val releasedSequenceEntry = convenienceClient.getReleasedData()
             .find { it.metadata["accession"]?.textValue() == accessions.first() }
 
-        assertThat(releasedSequenceEntry?.metadata, hasEntry("insdc_accession_full", TextNode("GENBANK1000.1")))
+        assertThat(releasedSequenceEntry?.metadata, hasEntry("insdcAccessionFull", TextNode("GENBANK1000.1")))
         assertThat(releasedSequenceEntry?.metadata, hasEntry("other_db_accession", TextNode("DB1.1")))
     }
 
@@ -105,12 +105,12 @@ class SubmitExternalMetadataEndpointTest(
             .andExpect(content().contentType(MediaType.APPLICATION_JSON_VALUE))
             .andExpect(
                 jsonPath("\$.detail")
-                    .value(containsString("Unknown fields in metadata: insdc_accession_full")),
+                    .value(containsString("Unknown fields in metadata: insdcAccessionFull")),
             )
         val releasedSequenceEntry = convenienceClient.getReleasedData()
             .find { it.metadata["accession"]?.textValue() == accessions.first() }
 
-        assertThat(releasedSequenceEntry?.metadata, not(hasKey("insdc_accession_full")))
+        assertThat(releasedSequenceEntry?.metadata, not(hasKey("insdcAccessionFull")))
     }
 
     @Test
@@ -137,7 +137,7 @@ class SubmitExternalMetadataEndpointTest(
         val releasedSequenceEntry = convenienceClient.getReleasedData()
             .find { it.metadata["accession"]?.textValue() == accessions.first().accession }
 
-        assertThat(releasedSequenceEntry?.metadata, not(hasKey("insdc_accession_full")))
+        assertThat(releasedSequenceEntry?.metadata, not(hasKey("insdcAccessionFull")))
     }
 
     @Test
@@ -161,6 +161,6 @@ class SubmitExternalMetadataEndpointTest(
         val releasedSequenceEntry = convenienceClient.getReleasedData()
             .find { it.metadata["accession"]?.textValue() == accession }
 
-        assertThat(releasedSequenceEntry?.metadata, not(hasKey("insdc_accession_full")))
+        assertThat(releasedSequenceEntry?.metadata, not(hasKey("insdcAccessionFull")))
     }
 }

backend/src/test/resources/backend_config.json

@@ -79,7 +79,7 @@
                 ],
                 "externalMetadata": [
                     {
-                        "name": "insdc_accession_full",
+                        "name": "insdcAccessionFull",
                         "type": "string",
                         "externalMetadataUpdater": "ena",
                         "required": true
@@ -176,4 +176,4 @@
             }
         }
     }
-}
+}

backend/src/test/resources/backend_config_single_segment.json

@@ -1,5 +1,5 @@
 {
-    "accessionPrefix" : "LOC_",
+    "accessionPrefix": "LOC_",
     "organisms": {
         "dummyOrganism": {
             "referenceGenomes": {
@@ -76,4 +76,4 @@
             }
         }
     }
-}
+}

docs/src/content/docs/for-administrators/existing-preprocessing-pipelines.md

@@ -29,7 +29,7 @@ Additionally the pipeline performs checks on the metadata fields. The checks are
 In the default configuration the pipeline performs: 
  * **type checks**: Checks that the type of each metadata field corresponds to the expected `type` value seen in the config (default is string).
  * **required value checks**: Checks that if a field is required, e.g. `required` field in config is true, that that field is not None.
- * **INSDC-accepted country checks**: Using the `process_options` preprocessing function checks that the `geo_loc_country` field is set to an [INSDC-accepted country](https://www.ebi.ac.uk/ena/browser/api/xml/ERC000011) option. 
+ * **INSDC-accepted country checks**: Using the `process_options` preprocessing function checks that the `geoLocCountry` field is set to an [INSDC-accepted country](https://www.ebi.ac.uk/ena/browser/api/xml/ERC000011) option. 
 
 The pipeline also formats metadata fields:
  * **process date**: Takes a date string and returns a date field in the "%Y-%m-%d" format.

docs/src/content/docs/for-administrators/setup-with-kubernetes.md

@@ -97,11 +97,11 @@ organisms:
                 - name: host
                   type: string
                   autocomplete: true
-                - name: pango_lineage
+                - name: pangoLineage
                   type: pango_lineage
                   autocomplete: true
                   required: true
-                - name: insdc_accession_full
+                - name: insdcAccessionFull
                   type: string
                   displayName: INSDC accession
                   customDisplay:
@@ -112,12 +112,12 @@ organisms:
                     - country
                     - division
                     - date
-                    - pango_lineage
+                    - pangoLineage
                 defaultOrder: descending
                 defaultOrderBy: date
             silo:
                 dateToSortBy: date
-                partitionBy: pango_lineage
+                partitionBy: pangoLineage
         preprocessing:
             image: ghcr.io/loculus-project/preprocessing-dummy
             args:

ena-submission/ENA_submission.md

@@ -59,14 +59,14 @@ The following could be implement as post-MVP features:
    <!--filename: project.xml-->
    <PROJECT_SET>
    <PROJECT alias={group_accession}:{organism}>
-        <NAME>{ncbi_virus_name}</NAME>
-        <TITLE>{ncbi_virus_name} Genome sequencing</TITLE>
-        <DESCRIPTION>Automated upload of {ncbi_virus_name} sequences submitted by {Institution} from {db}.</DESCRIPTION>
+        <NAME>{ncbiVirusName}</NAME>
+        <TITLE>{ncbiVirusName} Genome sequencing</TITLE>
+        <DESCRIPTION>Automated upload of {ncbiVirusName} sequences submitted by {Institution} from {db}.</DESCRIPTION>
         <SUBMISSION_PROJECT>
             <SEQUENCING_PROJECT/>
             <ORGANISM>
             <TAXON_ID>{taxon_id}</TAXON_ID>
-            <SCIENTIFIC_NAME>{ncbi_virus_name}</SCIENTIFIC_NAME>
+            <SCIENTIFIC_NAME>{ncbiVirusName}</SCIENTIFIC_NAME>
             </ORGANISM>
         </SUBMISSION_PROJECT>
         <PROJECT_LINKS>

ena-submission/config/config.yaml

@@ -16,103 +16,103 @@ organisms:
     organismName: "Crimean-Congo Hemorrhagic Fever Virus"
     externalMetadata:
       - externalMetadataUpdater: ena
-        name: ncbi_release_date
+        name: ncbiReleaseDate
         type: date
       - externalMetadataUpdater: ena
-        name: ncbi_update_date_L
+        name: ncbiUpdateDate_L
         type: date
       - externalMetadataUpdater: ena
-        name: ncbi_update_date_M
+        name: ncbiUpdateDate_M
         type: date
       - externalMetadataUpdater: ena
-        name: ncbi_update_date_S
+        name: ncbiUpdateDate_S
         type: date
       - externalMetadataUpdater: ena
-        name: ncbi_submitter_country
+        name: ncbiSubmitterCountry
         type: string
       - externalMetadataUpdater: ena
-        name: insdc_accession_base_L
+        name: insdcAccessionBase_L
         type: string
       - externalMetadataUpdater: ena
-        name: insdc_accession_base_M
+        name: insdcAccessionBase_M
         type: string
       - externalMetadataUpdater: ena
-        name: insdc_accession_base_S
+        name: insdcAccessionBase_S
         type: string
       - externalMetadataUpdater: ena
-        name: insdc_version_L
+        name: insdcVersion_L
         type: int
       - externalMetadataUpdater: ena
-        name: insdc_version_M
+        name: insdcVersion_M
         type: int
       - externalMetadataUpdater: ena
-        name: insdc_version_S
+        name: insdcVersion_S
         type: int
       - externalMetadataUpdater: ena
-        name: insdc_accession_full_L
+        name: insdcAccessionFull_L
         type: string
       - externalMetadataUpdater: ena
-        name: insdc_accession_full_M
+        name: insdcAccessionFull_M
         type: string
       - externalMetadataUpdater: ena
-        name: insdc_accession_full_S
+        name: insdcAccessionFull_S
         type: string
       - externalMetadataUpdater: ena
-        name: bioproject_accession
+        name: bioprojectAccession
         type: string
       - externalMetadataUpdater: ena
-        name: biosample_accession
+        name: biosampleAccession
         type: string
       - externalMetadataUpdater: ena
-        name: ncbi_sourcedb
+        name: ncbiSourceDb
         type: string
       - externalMetadataUpdater: ena
-        name: ncbi_virus_name
+        name: ncbiVirusName
         type: string
       - externalMetadataUpdater: ena
-        name: ncbi_virus_tax_id
+        name: ncbiVirusTaxId
         type: int
       - externalMetadataUpdater: ena
-        name: sra_run_accession
+        name: sraRunAccession
         type: string
   ebola-sudan:
     ingest:
       taxon_id: 3052460
     organismName: "Ebola Sudan"
     externalMetadata:
       - externalMetadataUpdater: ena
-        name: ncbi_release_date
+        name: ncbiReleaseDate
         type: date
       - externalMetadataUpdater: ena
-        name: ncbi_update_date
+        name: ncbiUpdateDate
         type: date
       - externalMetadataUpdater: ena
-        name: ncbi_submitter_country
+        name: ncbiSubmitterCountry
         type: string
       - externalMetadataUpdater: ena
-        name: insdc_accession_base
+        name: insdcAccessionBase
         type: string
       - externalMetadataUpdater: ena
-        name: insdc_version
+        name: insdcVersion
         type: int
       - externalMetadataUpdater: ena
-        name: insdc_accession_full
+        name: insdcAccessionFull
         type: string
       - externalMetadataUpdater: ena
-        name: bioproject_accession
+        name: bioprojectAccession
         type: string
       - externalMetadataUpdater: ena
-        name: biosample_accession
+        name: biosampleAccession
         type: string
       - externalMetadataUpdater: ena
-        name: ncbi_sourcedb
+        name: ncbiSourceDb
         type: string
       - externalMetadataUpdater: ena
-        name: ncbi_virus_name
+        name: ncbiVirusName
         type: string
       - externalMetadataUpdater: ena
-        name: ncbi_virus_tax_id
+        name: ncbiVirusTaxId
         type: int
       - externalMetadataUpdater: ena
-        name: sra_run_accession
+        name: sraRunAccession
         type: string