ENH: update to IDC v22

Author: fedorov

assets/clinical_index.sql

@@ -6,6 +6,6 @@ SELECT
   column_label,
   `values`
 FROM
-  `bigquery-public-data.idc_v21_clinical.column_metadata`
+  `bigquery-public-data.idc_v22_clinical.column_metadata`
 ORDER BY
   collection_id, table_name

assets/sm_index.sql

@@ -31,7 +31,7 @@ WITH
 
 
   FROM
-    `bigquery-public-data.idc_v21.dicom_all` AS dicom_all
+    `bigquery-public-data.idc_v22.dicom_all` AS dicom_all
   GROUP BY
     SeriesInstanceUID
   ),
@@ -45,7 +45,7 @@ SpecimenPreparationSequence_unnested AS (
         concept_code_sequence.CodeMeaning AS ccs_cm,
         concept_code_sequence.CodingSchemeDesignator AS ccs_csd,
         concept_code_sequence.CodeValue AS ccs_val,
-      FROM `bigquery-public-data.idc_v21.dicom_all`,
+      FROM `bigquery-public-data.idc_v22.dicom_all`,
       UNNEST(SpecimenDescriptionSequence[SAFE_OFFSET(0)].SpecimenPreparationSequence) as preparation_unnest_step1,
       UNNEST(preparation_unnest_step1.SpecimenPreparationStepContentItemSequence) as preparation_unnest_step2,
       UNNEST(preparation_unnest_step2.ConceptNameCodeSequence) as concept_name_code_sequence,

assets/sm_instance_index.sql

@@ -9,7 +9,7 @@ WITH
     concept_code_sequence.CodingSchemeDesignator AS ccs_csd,
     concept_code_sequence.CodeValue AS ccs_val,
   FROM
-    `bigquery-public-data.idc_v21.dicom_all`,
+    `bigquery-public-data.idc_v22.dicom_all`,
     UNNEST(SpecimenDescriptionSequence[SAFE_OFFSET(0)].SpecimenPreparationSequence) AS preparation_unnest_step1,
     UNNEST(preparation_unnest_step1.SpecimenPreparationStepContentItemSequence) AS preparation_unnest_step2,
     UNNEST(preparation_unnest_step2.ConceptNameCodeSequence) AS concept_name_code_sequence,
@@ -107,7 +107,7 @@ SELECT
   -- attributes needed to retrieve the selected instances/files
   dicom_all.crdc_instance_uuid
 FROM
-  `bigquery-public-data.idc_v21.dicom_all` AS dicom_all
+  `bigquery-public-data.idc_v22.dicom_all` AS dicom_all
 LEFT JOIN
   slide_embedding
 ON

pyproject.toml

@@ -13,7 +13,7 @@ build-backend = "scikit_build_core.build"
 
 [project]
 name = "idc-index-data"
-version = "21.0.0"
+version = "22.0.0"
 authors = [
   { name = "Andrey Fedorov", email = "[email protected]" },
   { name = "Vamsi Thiriveedhi", email = "[email protected]" },

scripts/sql/idc_index.sql

@@ -29,9 +29,9 @@ SELECT
   ANY_VALUE(CONCAT(series_aws_url,"*")) AS series_aws_url,
   ROUND(SUM(SAFE_CAST(instance_size AS float64))/1000000, 2) AS series_size_MB,
 FROM
-  `bigquery-public-data.idc_v21.dicom_all` AS dicom_all
+  `bigquery-public-data.idc_v22.dicom_all` AS dicom_all
 JOIN
-  `bigquery-public-data.idc_v21.dicom_metadata_curated` AS dicom_curated
+  `bigquery-public-data.idc_v22.dicom_metadata_curated` AS dicom_curated
 ON
   dicom_all.SOPInstanceUID = dicom_curated.SOPInstanceUID
 GROUP BY

scripts/sql/prior_versions_index.sql

@@ -3,7 +3,7 @@
 --
 -- Step 1: Declare variables
 DECLARE idc_versions ARRAY<INT64>;
-DECLARE latest_idc_version INT64 DEFAULT 21;
+DECLARE latest_idc_version INT64 DEFAULT 22;
 DECLARE union_all_query STRING;
 
 --Step 2

tests/test_package.py

@@ -7,7 +7,7 @@
 
 import idc_index_data as m
 
-EXPECTED_IDC_INDEX_VERSION = 21
+EXPECTED_IDC_INDEX_VERSION = 22
 
 
 def test_version():