update BDC Prod etlMapping + guppy config

bdcatprod/gen3.biodatacatalyst.nhlbi.nih.gov/values/values.yaml

@@ -54,46 +54,57 @@ etl:
   esEndpoint: elasticsearch
   etlMapping:
     mappings:
-      - aggregated_props:
-          - fn: set
-            name: annotated_sex
+      - name: gen3.biodatacatalyst.nhlbi.nih.gov_subject
+        doc_type: subject
+        type: aggregator
+        root: subject
+        props:
+          - name: submitter_id
+          - name: project_id
+          - name: consent_codes
+          - name: geographic_site
+        aggregated_props:
+          - name: annotated_sex
             path: demographics
             src: annotated_sex
-          - fn: set
-            name: race
+            fn: set
+          - name: race
             path: demographics
             src: race
-          - fn: set
-            name: ethnicity
+            fn: set
+          - name: ethnicity
             path: demographics
             src: ethnicity
-          - fn: count
-            name: _samples_count
+            fn: set
+          - name: _samples_count
             path: samples
-          - fn: count
-            name: _aliquots_count
+            fn: count
+          - name: _aliquots_count
             path: samples.aliquots
-          - fn: count
-            name: _read_groups_count
+            fn: count
+          - name: _read_groups_count
             path: samples.aliquots.read_groups
-          - fn: count
-            name: _submitted_unaligned_reads_files_count
+            fn: count
+          - name: _submitted_unaligned_reads_files_count
             path: samples.aliquots.read_groups.submitted_unaligned_reads_files
-          - fn: count
-            name: _submitted_aligned_reads_files_count
+            fn: count
+          - name: _submitted_aligned_reads_files_count
             path: samples.aliquots.read_groups.submitted_aligned_reads_files
-          - fn: count
-            name: _simple_germline_variations_count
+            fn: count
+          - name: _simple_germline_variations_count
             path: samples.aliquots.read_groups.simple_germline_variations
-          - fn: set
-            name: current_smoker_baseline
+            fn: count
+          - name: current_smoker_baseline
             path: exposures
             src: current_smoker_baseline
-          - fn: set
-            name: ever_smoker_baseline
+            fn: set
+          - name: ever_smoker_baseline
             path: exposures
             src: ever_smoker_baseline
-        doc_type: subject
+            fn: set
+        parent_props:
+          - path: studies[studies_submitter_id:submitter_id].projects[code]
+          - path: studies[studies_submitter_id:submitter_id].projects[code].programs[programs_name:name]
         flatten_props:
           - path: demographics
             props:
@@ -158,47 +169,40 @@ etl:
           - index: file
             join_on: _subject_id
             props:
-              - fn: set
-                name: data_format
+              - name: file_object_id
+                src: object_id
+                fn: set
+              - name: file_data_format
                 src: data_format
-              - fn: set
-                name: data_type
+                fn: set
+              - name: file_data_type
                 src: data_type
-              - fn: count
-                name: file_count
+                fn: set
+              - name: file_count
                 src: _file_id
-        name: gen3.biodatacatalyst.nhlbi.nih.gov_subject
-        parent_props:
-          - path: studies[studies_submitter_id:submitter_id].projects[code]
-          - path: studies[studies_submitter_id:submitter_id].projects[code].programs[programs_name:name]
-        props:
-          - name: submitter_id
-          - name: project_id
-          - name: consent_codes
-          - name: geographic_site
-        root: subject
-        type: aggregator
-      - category: data_file
-        doc_type: file
-        injecting_props:
-          program:
-            props:
-              - fn: set
-                name: programs_name
-                src: name
-          project:
-            props:
-              - fn: set
-                name: dbgap_accession_number
-                src: dbgap_accession_number
-          subject:
+                fn: count
+          - index: index_file
+            join_on: _subject_id
             props:
-              - fn: set
-                name: _subject_id
-                src: id
-              - name: project_id
-        name: gen3.biodatacatalyst.nhlbi.nih.gov_file
+              - name: index_file_object_id
+                src: object_id
+                fn: set
+              - name: index_file_data_format
+                src: data_format
+                fn: set
+              - name: index_file_data_type
+                src: data_type
+                fn: set
+              - name: index_file_count
+                src: _index_file_id
+                fn: count
+      - name: gen3.biodatacatalyst.nhlbi.nih.gov_file
+        doc_type: file
+        type: collector
+        root: None
+        category: data_file
         props:
+          - name: project_id
           - name: object_id
           - name: md5sum
           - name: file_name
@@ -210,29 +214,29 @@ etl:
           - name: callset
           - name: bucket_path
           - name: source_node
-        root: None
-        type: collector
-      - category: index_file
-        doc_type: index_file
         injecting_props:
           program:
             props:
-              - fn: set
-                name: programs_name
+              - name: programs_name
                 src: name
+                fn: set
           project:
             props:
-              - fn: set
-                name: dbgap_accession_number
+              - name: dbgap_accession_number
                 src: dbgap_accession_number
+                fn: set
           subject:
             props:
-              - fn: set
-                name: _subject_id
+              - name: _subject_id
                 src: id
-              - name: project_id
-        name: gen3.biodatacatalyst.nhlbi.nih.gov_index_file
+                fn: set
+      - name: gen3.biodatacatalyst.nhlbi.nih.gov_index_file
+        doc_type: index_file
+        type: collector
+        root: None
+        category: index_file
         props:
+          - name: project_id
           - name: object_id
           - name: md5sum
           - name: file_name
@@ -244,8 +248,22 @@ etl:
           - name: callset
           - name: bucket_path
           - name: source_node
-        root: None
-        type: collector
+        injecting_props:
+          program:
+            props:
+              - name: programs_name
+                src: name
+                fn: set
+          project:
+            props:
+              - name: dbgap_accession_number
+                src: dbgap_accession_number
+                fn: set
+          subject:
+            props:
+              - name: _subject_id
+                src: id
+                fn: set
   image:
     tube:
       tag: '2026.04'
@@ -3213,7 +3231,7 @@ fence:
         region: us-east-1
       nih-nhlbi-topmed-sumstats-phs001974-r1-v9-c1:
         cred: fence-bot
-        region: us-east-1  
+        region: us-east-1
     ENABLE_VISA_UPDATE_CRON: true
 fluentd:
   enabled: true
@@ -3285,6 +3303,8 @@ guppy:
       type: subject
     - index: gen3.biodatacatalyst.nhlbi.nih.gov_file
       type: file
+    - index: gen3.biodatacatalyst.nhlbi.nih.gov_index_file
+      type: index_file
 hatchery:
   enabled: false
 indexd: