enh: update to IDC v23

Author: fedorov

assets/clinical_index.sql

@@ -25,6 +25,6 @@ SELECT
   # values encountered in the column
   `values`
 FROM
-  `bigquery-public-data.idc_v22_clinical.column_metadata`
+  `bigquery-public-data.idc_v23_clinical.column_metadata`
 ORDER BY
   collection_id, table_name

assets/sm_index.sql

@@ -37,7 +37,7 @@ WITH
 
 
   FROM
-    `bigquery-public-data.idc_v22.dicom_all` AS dicom_all
+    `bigquery-public-data.idc_v23.dicom_all` AS dicom_all
   GROUP BY
     SeriesInstanceUID
   ),
@@ -51,7 +51,7 @@ 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_v22.dicom_all`,
+      FROM `bigquery-public-data.idc_v23.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

@@ -16,7 +16,7 @@ WITH
     concept_code_sequence.CodingSchemeDesignator AS ccs_csd,
     concept_code_sequence.CodeValue AS ccs_val,
   FROM
-    `bigquery-public-data.idc_v22.dicom_all`,
+    `bigquery-public-data.idc_v23.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,
@@ -144,7 +144,7 @@ SELECT
   # unique identifier of the instance within the IDC
   dicom_all.crdc_instance_uuid AS crdc_instance_uuid
 FROM
-  `bigquery-public-data.idc_v22.dicom_all` AS dicom_all
+  `bigquery-public-data.idc_v23.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 = "22.1.5"
+version = "23.0.1"
 authors = [
   { name = "Andrey Fedorov", email = "andrey.fedorov@gmail.com" },
   { name = "Vamsi Thiriveedhi", email = "vthiriveedhi@mgh.harvard.edu" },

scripts/python/idc_index_data_manager.py

@@ -423,7 +423,7 @@ def retrieve_latest_idc_release_version(self) -> int:
         SELECT
             MAX(idc_version) AS latest_idc_release_version
         FROM
-            `bigquery-public-data.idc_current.version_metadata`
+            `bigquery-public-data.idc_v23.version_metadata`
         """
         query_job = self.client.query(query)
         result = query_job.result()

scripts/sql/analysis_results_index.sql

@@ -43,4 +43,4 @@ SELECT
   # citation for the analysis results collection that should be used for acknowledgment
   Citation
 FROM
-  `bigquery-public-data.idc_v22.analysis_results_metadata`
+  `bigquery-public-data.idc_v23.analysis_results_metadata`

scripts/sql/collections_index.sql

@@ -40,4 +40,4 @@ SELECT
   # detailed information about the collection
   Description
 FROM
-  `bigquery-public-data.idc_v22.original_collections_metadata`
+  `bigquery-public-data.idc_v23.original_collections_metadata`

scripts/sql/idc_index.sql

@@ -83,9 +83,9 @@ SELECT
   # total size of the series in megabytes
   ROUND(SUM(SAFE_CAST(instance_size AS float64))/1000000, 2) AS series_size_MB,
 FROM
-  `bigquery-public-data.idc_v22.dicom_all` AS dicom_all
+  `bigquery-public-data.idc_v23.dicom_all` AS dicom_all
 JOIN
-  `bigquery-public-data.idc_v22.dicom_metadata_curated` AS dicom_curated
+  `bigquery-public-data.idc_v23.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 22;
+DECLARE latest_idc_version INT64 DEFAULT 23;
 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 = 22
+EXPECTED_IDC_INDEX_VERSION = 23
 
 
 def test_version():