From 12d145485b90e944bb9e215a148e72d4d67b6761 Mon Sep 17 00:00:00 2001
From: Charles Haynes <haynescd@chop.edu>
Date: Mon, 7 Oct 2024 14:12:22 -0400
Subject: [PATCH] Add Categorical Clinical Attribute NA filtering

---
 .../StudyViewFilterMapper.xml                 | 75 ++++++++++++++++---
 1 file changed, 63 insertions(+), 12 deletions(-)

diff --git a/src/main/resources/org/cbioportal/persistence/mybatisclickhouse/StudyViewFilterMapper.xml b/src/main/resources/org/cbioportal/persistence/mybatisclickhouse/StudyViewFilterMapper.xml
index 468731e9bc1..6ae7aa8fd6f 100644
--- a/src/main/resources/org/cbioportal/persistence/mybatisclickhouse/StudyViewFilterMapper.xml
+++ b/src/main/resources/org/cbioportal/persistence/mybatisclickhouse/StudyViewFilterMapper.xml
@@ -370,20 +370,71 @@
         </foreach>
     </sql>
 
+    <sql id="selectAllCategoricalClinicalDataByAttribute">
+        SELECT sample_unique_id, patient_unique_id, attribute_value
+        FROM clinical_data_derived
+        WHERE attribute_name = '${clinicalDataFilter.attributeId}' AND type='${type}'
+        AND cancer_study_identifier IN
+        <foreach item="studyId" collection="studyViewFilterHelper.studyViewFilter.studyIds" open="(" separator="," close=")">
+            #{studyId}
+        </foreach>
+    </sql>
     <sql id="categoricalClinicalDataCountFilter">
-        SELECT ${unique_id}
-        FROM ${table_name}
-        WHERE attribute_name = '${clinicalDataFilter.attributeId}' AND
-        type='${type}'
-        <foreach item="dataFilterValue" collection="clinicalDataFilter.values" open=" AND ((" separator=") OR (" close="))">
-            <trim prefix="" prefixOverrides="AND">
-                AND (
-                    <include refid="normalizeAttributeValue">
-                        <property name="attribute_value" value="attribute_value"/>
-                    </include>
-                ) = '${dataFilterValue.value}'
-            </trim>
+        <!-- check if 'NA' is selected -->
+        <bind name="userSelectsNA" value="false" />
+        <bind name="userSelectsNumericalValue" value="false" />
+        <foreach item="dataFilterValue" collection="clinicalDataFilter.values">
+            <choose>
+                <when test="dataFilterValue.value == 'NA'">
+                    <bind name="userSelectsNA" value="true" />
+                </when>
+                <otherwise>
+                    <bind name="userSelectsNumericalValue" value="true" />
+                </otherwise>
+            </choose>
         </foreach>
+        (
+        <!-- if 'NA' is selected, prepare NA samples -->
+        <if test="userSelectsNA">
+            SELECT DISTINCT ${unique_id}
+            FROM sample_derived sd
+            LEFT JOIN (<include refid="selectAllCategoricalClinicalDataByAttribute"/>) AS categorical_clinical_data
+            ON
+            <choose>
+                <when test="'${type}' == 'sample'">
+                    sd.sample_unique_id = categorical_clinical_data.sample_unique_id
+                </when>
+                <otherwise>
+                    sd.patient_unique_id = categorical_clinical_data.patient_unique_id
+                </otherwise>
+            </choose>
+            WHERE empty(attribute_value)
+            AND EXISTS (<include refid="selectAllCategoricalClinicalDataByAttribute"/>)
+        </if>
+
+        <!-- if both 'NA' and non-NA are selected, union them together -->
+        <if test="userSelectsNA and userSelectsNumericalValue">
+            UNION ALL
+        </if>
+
+        <!-- if non-NA is selected, prepare non-NA samples -->
+        <if test="userSelectsNumericalValue">
+            SELECT ${unique_id}
+            FROM ${table_name}
+            WHERE attribute_name = '${clinicalDataFilter.attributeId}' AND
+            type='${type}'
+            <foreach item="dataFilterValue" collection="clinicalDataFilter.values" open=" AND ((" separator=") OR ("
+                     close="))">
+                <trim prefix="" prefixOverrides="AND">
+                    AND (
+                        <include refid="normalizeAttributeValue">
+                            <property name="attribute_value" value="attribute_value"/>
+                        </include>
+                    ) = '${dataFilterValue.value}'
+                </trim>
+            </foreach>
+        </if>
+        )
     </sql>
 
     <sql id="numericalGenomicDataFilter">