Multiple goal search on XML nodes in SQL Server

Question

I have a Process table in SQL Server like this:

workflowXML column has values like this:

sample1 (ProcessID=1)

Answer 1

I was curious to solve this with a set-based recursive approach as I do not like procedural coding in T-SQL. Hope you like it :-)

DECLARE @process TABLE(ID INT IDENTITY, workflowXML XML);
INSERT INTO @process(workflowXML) VALUES
('<process>
    <Event type="start" id="StartEvent_1" name="Start">
      <outgoing>SequenceFlow_0z7u86p</outgoing>
      <outgoing>SequenceFlow_1onkt3z</outgoing>
    </Event>
    <task type="" id="Task_0a7vu1x" name="D">
      <incoming>SequenceFlow_108ajnm</incoming>
      <incoming>SequenceFlow_1onkt3z</incoming>
      <outgoing>SequenceFlow_01clcmz</outgoing>
    </task>
    <task type="goal" id="Task_00ijt4n" name="B">
      <incoming>SequenceFlow_17q1ecq</incoming>
      <incoming>SequenceFlow_0q9j3et</incoming>
      <outgoing>SequenceFlow_1ygvv8b</outgoing>
      <outgoing>SequenceFlow_02glv1g</outgoing>
    </task>
    <task type="" id="Task_1rnuz4y" name="A">
      <incoming>SequenceFlow_1ygvv8b</incoming>
      <incoming>SequenceFlow_0z7u86p</incoming>
      <outgoing>SequenceFlow_108ajnm</outgoing>
      <outgoing>SequenceFlow_17q1ecq</outgoing>
      <outgoing>SequenceFlow_075iuj9</outgoing>
    </task>                
    <task type="goal" id="Task_1d4ykor" name="E">
      <incoming>SequenceFlow_01clcmz</incoming>
      <incoming>SequenceFlow_075iuj9</incoming>
      <incoming>SequenceFlow_1djp3tu</incoming>
      <outgoing>SequenceFlow_0q9j3et</outgoing>
    </task>        
    <task type="goal" id="Task_1sembw4" name="C">
      <incoming>SequenceFlow_02glv1g</incoming>
      <outgoing>SequenceFlow_1djp3tu</outgoing>
    </task>    
</process>')
,('<process id="Process_1" isExecutable="false">
    <Event type="start" id="StartEvent_0bivq0x" name="Start">
      <outgoing>SequenceFlow_0q5ik20</outgoing>
      <outgoing>SequenceFlow_147xk2x</outgoing>
    </Event>
    <task type="" id="Task_141buye" name="A">
      <incoming>SequenceFlow_0q5ik20</incoming>
      <incoming>SequenceFlow_0wg37hn</incoming>
      <outgoing>SequenceFlow_1pvpyhe</outgoing>
      <outgoing>SequenceFlow_10is4pe</outgoing>
    </task>
    <task type="" id="Task_1n3p00i" name="C">
      <incoming>SequenceFlow_147xk2x</incoming>
      <incoming>SequenceFlow_10is4pe</incoming>
      <outgoing>SequenceFlow_18ks1jr</outgoing>
      <outgoing>SequenceFlow_08gxini</outgoing>
    </task>
    <task type="goal" id="Task_0olxqpp" name="B">
      <incoming>SequenceFlow_1pvpyhe</incoming>
      <outgoing>SequenceFlow_03eekq0</outgoing>
    </task>
    <task type="goal" id="Task_0zjgfkf" name="D">
      <incoming>SequenceFlow_18ks1jr</incoming>
      <incoming>SequenceFlow_03eekq0</incoming>
      <outgoing>SequenceFlow_0wg37hn</outgoing>
    </task>
    <task type="" id="Task_1q71efy" name="E">
      <incoming>SequenceFlow_08gxini</incoming>
    </task>
</process>');

--the query

WITH DerivedTable AS
(
    SELECT prTbl.ID AS tblID
          ,nd.value('local-name(.)','nvarchar(max)') AS NodeName
          ,nd.value('@type','nvarchar(max)') AS [Type]
          ,nd.value('@id','nvarchar(max)') AS Id
          ,nd.value('@name','nvarchar(max)') AS [Name]
          ,nd.query('.') AS Task
    FROM @process AS prTbl
    CROSS APPLY prTbl.workflowXML.nodes('process') AS A(pr)
    CROSS APPLY pr.nodes('*') AS B(nd)
)
,AllIncoming AS
(
    SELECT tblId
          ,NodeName 
          ,[Type]
          ,Id 
          ,[Name]
          ,i.value('.','nvarchar(max)') AS [Target] 
    FROM DerivedTable
    CROSS APPLY Task.nodes('task/incoming') AS A(i)
    WHERE NodeName='task'
)
,recCTE AS
(
    SELECT tblID,NodeName,[Type],Id,[Name],Task,1 AS Step,' | ' +CAST(Id AS NVARCHAR(MAX)) AS NodePath
    FROM DerivedTable 
    WHERE [Type]='start'

    UNION ALL

    SELECT nxt.tblID,nxt.NodeName,nxt.[Type],nxt.Id,nxt.[Name],nxt.Task,r.Step+1,r.NodePath + ' | ' + nxt.Id
    FROM recCTE AS r
    INNER JOIN DerivedTable AS nxt ON nxt.Id IN(SELECT x.Id 
                                                FROM AllIncoming AS x 
                                                WHERE x.[Target] IN (SELECT o.value('.','nvarchar(max)')
                                                                     FROM r.Task.nodes('*/outgoing') AS A(o)
                                                                    )
                                                )
    WHERE r.[Type]<>'goal' 
      AND r.NodePath NOT LIKE '%| ' + nxt.Id + '%' 
      AND r.Step<=10 --add an appropriate depth limit to avoid recusion-depth error
)
SELECT t.tblID 
      ,t.[Name] 
      ,t.NodePath
      ,t.Step
      ,t.Id
FROM recCTE AS t
WHERE t.[Type]='goal'
  AND t.Step<=ISNULL((SELECT MIN(x.Step) FROM recCTE AS x WHERE x.tblID=t.tblID AND x.[Type]='goal' AND x.NodeName='task'),999)
ORDER BY t.tblID,t.Step

The result

tblID   Name    NodePath                                          Step  Id
  1     B      | StartEvent_1 | Task_1rnuz4y | Task_00ijt4n        3    Task_00ijt4n
  1     E      | StartEvent_1 | Task_1rnuz4y | Task_1d4ykor        3    Task_1d4ykor
  1     E      | StartEvent_1 | Task_0a7vu1x | Task_1d4ykor        3    Task_1d4ykor
  2     D      | StartEvent_0bivq0x | Task_1n3p00i | Task_0zjgfkf  3    Task_0zjgfkf
  2     B      | StartEvent_0bivq0x | Task_141buye | Task_0olxqpp  3    Task_0olxqpp

You find more than two results for tblID=1 as there are differing paths leading to the same goal node.

UPDATE Your example 3

My first attempt finds the shortest path to a goal. Any goal, which is reached with a longer path, was filtered. This is easy to change:

Let the final WHERE find the shortest path to a specific node by adding the Id:

WHERE t.[Type]='goal'
  AND t.Step<=ISNULL((SELECT MIN(x.Step) 
                      FROM recCTE AS x 
                      WHERE x.tblID=t.tblID
                        AND x.Id=t.Id 
                        AND x.[Type]='goal' AND x.NodeName='task'),999)

This returns for all three examples:

+-------+------+----------------------------------------------------------------------------+------+--------------+
| tblID | Name | NodePath                                                                   | Step | Id           |
+-------+------+----------------------------------------------------------------------------+------+--------------+
| 1     | B    | | StartEvent_1 | Task_1rnuz4y | Task_00ijt4n                               | 3    | Task_00ijt4n |
+-------+------+----------------------------------------------------------------------------+------+--------------+
| 1     | E    | | StartEvent_1 | Task_1rnuz4y | Task_1d4ykor                               | 3    | Task_1d4ykor |
+-------+------+----------------------------------------------------------------------------+------+--------------+
| 1     | E    | | StartEvent_1 | Task_0a7vu1x | Task_1d4ykor                               | 3    | Task_1d4ykor |
+-------+------+----------------------------------------------------------------------------+------+--------------+
| 2     | B    | | StartEvent_0bivq0x | Task_141buye | Task_0olxqpp                         | 3    | Task_0olxqpp |
+-------+------+----------------------------------------------------------------------------+------+--------------+
| 2     | D    | | StartEvent_0bivq0x | Task_1n3p00i | Task_0zjgfkf                         | 3    | Task_0zjgfkf |
+-------+------+----------------------------------------------------------------------------+------+--------------+
| 3     | E    | | StartEvent_1 | Task_1jixk79 | Task_0wtjftd                               | 3    | Task_0wtjftd |
+-------+------+----------------------------------------------------------------------------+------+--------------+
| 3     | C    | | StartEvent_1 | Task_1jixk79 | Task_0xwvhuo | Task_032o8jx                | 4    | Task_032o8jx |
+-------+------+----------------------------------------------------------------------------+------+--------------+
| 3     | H    | | StartEvent_1 | Task_1jixk79 | Task_0xwvhuo | Task_0fsibap                | 4    | Task_0fsibap |
+-------+------+----------------------------------------------------------------------------+------+--------------+
| 3     | G    | | StartEvent_1 | Task_1jixk79 | Task_0xwvhuo | Task_0c85e6p | Task_0qsvlob | 5    | Task_0qsvlob |
+-------+------+----------------------------------------------------------------------------+------+--------------+
| 3     | G    | | StartEvent_1 | Task_1jixk79 | Task_164ihwt | Task_0c85e6p | Task_0qsvlob | 5    | Task_0qsvlob |
+-------+------+----------------------------------------------------------------------------+------+--------------+