TAMULib · wwelling · Sep 26, 2024 · Sep 16, 2024
diff --git a/README.md b/README.md
@@ -796,3 +796,49 @@ Either wait for scheduled event to occur or manually execute via:
 ```shell
 fw run evans-pres-repr
 ```
+
+## duplicate-instance-report
+
+### Instance Duplication Report Workflow (Scheduled)
+
+This workflow emails a CSV report for Call Number, ISBN, LCCN, ISSN, and OCLC matches as well as a full instance duplication CSV report compressed with ZIP format.
+
+The full instance duplication CSV has the following columns. The title and author columns are wrapped in double quotes.
+
+```
+HRID, HRID2, OCLC, ISBN, ISSN, CALL_NUMBER, LCCN, TITLE, TITLE2, AUTHOR, AUTHOR2
+```
+
+Requires following path `/mnt/workflows/${tenantId}/duplicate-instance-report`.
+
+
+These variables are required when building and running the workflow:
+
+| Variable Name                  | Allowed Values | Brief Description |
+| ------------------------------ | -------------- | ----------------- |
+| ldp-url                        | URL            | LDP URL. |
+| ldp-user                       | string         | LDP login username. |
+| ldp-password                   | string         | LDP login password. |
+| duplicate-instance-report-from | e-mail address | The e-mail address of the report sender. |
+| duplicate-instance-report-to   | e-mail address | The e-mail address of the report recipient. |
+
+The scheduled event is for **12:00 AM UTC**, on the first of the month, only in January, April, July, and October.
+
+```shell
+fw config set ldp-url ***
+fw config set ldp-user ***
+fw config set ldp-password ***
+fw config set duplicate-instance-report-from ***
+fw config set duplicate-instance-report-to ***
+```
+
+To build and activate:
+```shell
+fw build duplicate-instance-report
+fw activate duplicate-instance-report
+```
+
+Either wait for scheduled event to occur or manually execute via:
+```shell
+fw run duplicate-instance-report
+```
diff --git a/duplicate-instance-report/nodes/callNumberEmail.json b/duplicate-instance-report/nodes/callNumberEmail.json
@@ -0,0 +1,29 @@
+{
+  "id": "b5dca523-4a24-4d02-a122-6ea8c9f34ac4",
+  "name": "Email Call Number Matches",
+  "description": "Email CSV with instances with matching call numbers",
+  "deserializeAs": "EmailTask",
+  "inputVariables": [
+    {
+      "key": "timestamp",
+      "type": "PROCESS"
+    },
+    {
+      "key": "tenantId",
+      "type": "PROCESS"
+    },
+    {
+      "key": "callNumberCount",
+      "type": "PROCESS"
+    }
+  ],
+  "outputVariable": {},
+  "mailFrom": "{{{duplicate-instance-report-from}}}",
+  "mailTo": "{{{duplicate-instance-report-to}}}",
+  "mailText": "The instances with matching Call Number report has completed, see the results attached.\n${callNumberCount} instance matches found.",
+  "mailMarkup": "<p>The instances with matching Call Number report has completed, see the results attached.</p><br/>${callNumberCount} instance matches found.",
+  "mailSubject": "Matching Call Number Instances Report - LDP {{{ldp-url}}}",
+  "attachmentPath": "/mnt/workflows/${tenantId}/duplicate-instance-report/call-number-${timestamp}.csv",
+  "includeAttachment": "${callNumberCount}",
+  "asyncBefore": true
+}
diff --git a/duplicate-instance-report/nodes/callNumberMoveToNode.json b/duplicate-instance-report/nodes/callNumberMoveToNode.json
@@ -0,0 +1,12 @@
+{
+  "id": "42c50baa-7d73-48ad-bd9b-53ffd6cd6eda",
+  "name": "CALL NUMBER",
+  "description": "",
+  "deserializeAs": "MoveToNode",
+  "gatewayId": "parallel_gateway_aea23b81_06b1_4795_8bab_ea562a854c83",
+  "nodes": [
+    "{{{mod-workflow}}}/databaseQueryTask/7a20c05e-2a58-42f2-9769-42e5b7045343",
+    "{{{mod-workflow}}}/emailTask/b5dca523-4a24-4d02-a122-6ea8c9f34ac4",
+    "{{{mod-workflow}}}/connectTo/53c5ca0f-9116-4bcf-86ba-ad4b4770aaaf"
+  ]
+}
diff --git a/duplicate-instance-report/nodes/callNumberQuery.json b/duplicate-instance-report/nodes/callNumberQuery.json
@@ -0,0 +1,27 @@
+{
+  "id": "7a20c05e-2a58-42f2-9769-42e5b7045343",
+  "name": "Call Number Match Query",
+  "description": "Query to find instances with matching call number",
+  "deserializeAs": "DatabaseQueryTask",
+  "inputVariables": [
+    {
+      "key": "timestamp",
+      "type": "PROCESS"
+    },
+    {
+      "key": "tenantId",
+      "type": "PROCESS"
+    }
+  ],
+  "outputVariable": {
+    "key": "callNumberCount",
+    "type": "PROCESS",
+    "spin": false
+  },
+  "designation": "ldp",
+  "outputPath": "/mnt/workflows/${tenantId}/duplicate-instance-report/call-number-${timestamp}.csv",
+  "resultType": "CSV",
+  "includeHeader": true,
+  "query": "WITH call_number AS (SELECT ie.instance_hrid, he.call_number_type_id, he.call_number_type_name, he.call_number, TRIM(CONCAT_WS(' ', he.call_number_prefix, he.call_number, he.call_number_suffix)) AS full_call_number, ie.title, sm.content AS author FROM folio_reporting.instance_ext ie JOIN folio_reporting.holdings_ext he ON ie.instance_id = he.instance_id JOIN public.srs_marctab sm ON ie.instance_hrid = sm.instance_hrid WHERE he.call_number IS NOT NULL AND he.call_number !~ '^\\s*$' AND he.call_number_type_id IS NOT NULL AND sm.field = '100' AND sm.ord = 1 AND sm.sf = 'a') SELECT l.instance_hrid AS hrid, r.instance_hrid AS hrid2, l.call_number AS call_number, r.call_number AS call_number2, l.full_call_number, '\"' || REPLACE(l.title, '\"', '\"\"') || '\"' AS title, '\"' || REPLACE(r.title, '\"', '\"\"') || '\"' AS title2, '\"' || REPLACE(l.author, '\"', '\"\"') || '\"' AS author, '\"' || REPLACE(r.author, '\"', '\"\"') || '\"' AS author2 FROM call_number l JOIN call_number r ON l.full_call_number = r.full_call_number AND l.instance_hrid < r.instance_hrid",
+  "asyncBefore": true
+}
diff --git a/duplicate-instance-report/nodes/connectToLdp.json b/duplicate-instance-report/nodes/connectToLdp.json
@@ -0,0 +1,13 @@
+{
+  "id": "11f065f0-f1ea-47ed-abc9-146099572e7b",
+  "name": "Connect LDP",
+  "description": "Connect to the LDP",
+  "deserializeAs": "DatabaseConnectionTask",
+  "inputVariables": [],
+  "outputVariable": {},
+  "designation": "ldp",
+  "url": "{{{ldp-url}}}",
+  "username": "{{{ldp-user}}}",
+  "password": "{{{ldp-password}}}",
+  "asyncBefore": true
+}
diff --git a/duplicate-instance-report/nodes/disconnectFromLDP.json b/duplicate-instance-report/nodes/disconnectFromLDP.json
@@ -0,0 +1,10 @@
+{
+  "id": "db806bf5-49b8-4f8a-bf96-fc0258d3c31e",
+  "name": "Disconnect LDP",
+  "description": "Disconnect from the LDP",
+  "deserializeAs": "DatabaseDisconnectTask",
+  "inputVariables": [],
+  "outputVariable": {},
+  "designation": "ldp",
+  "asyncBefore": true
+}
diff --git a/duplicate-instance-report/nodes/end.json b/duplicate-instance-report/nodes/end.json
@@ -0,0 +1,6 @@
+{
+  "id": "3c9848b3-f5a4-4753-b916-2b73c88d9409",
+  "name": "End",
+  "description": "End of duplicate instance report workflow",
+  "deserializeAs": "EndEvent"
+}
diff --git a/duplicate-instance-report/nodes/isbnConnectTo.json b/duplicate-instance-report/nodes/isbnConnectTo.json
@@ -0,0 +1,7 @@
+{
+  "id": "c36f8e08-7e43-49b3-923f-ebb8629617c8",
+  "name": "ISBN Complete",
+  "description": "",
+  "deserializeAs": "ConnectTo",
+  "nodeId": "parallel_gateway_af9d6b6c_6d59_4735_9a7c_2314a68e0985"
+}
diff --git a/duplicate-instance-report/nodes/isbnEmail.json b/duplicate-instance-report/nodes/isbnEmail.json
@@ -0,0 +1,29 @@
+{
+  "id": "66356870-9e8a-406b-ae3d-5fcffef0c556",
+  "name": "Email ISBN Matches",
+  "description": "Email CSV with instances with matching ISBN",
+  "deserializeAs": "EmailTask",
+  "inputVariables": [
+    {
+      "key": "timestamp",
+      "type": "PROCESS"
+    },
+    {
+      "key": "tenantId",
+      "type": "PROCESS"
+    },
+    {
+      "key": "isbnCount",
+      "type": "PROCESS"
+    }
+  ],
+  "outputVariable": {},
+  "mailFrom": "{{{duplicate-instance-report-from}}}",
+  "mailTo": "{{{duplicate-instance-report-to}}}",
+  "mailText": "The instances with matching ISBN report has completed, see the results attached.\n${isbnCount} instance matches found.",
+  "mailMarkup": "<p>The instances with matching ISBN report has completed, see the results attached.</p><br/>${isbnCount} instance matches found.",
+  "mailSubject": "Matching ISBN Instances Report - LDP {{{ldp-url}}}",
+  "attachmentPath": "/mnt/workflows/${tenantId}/duplicate-instance-report/isbn-${timestamp}.csv",
+  "includeAttachment": "${isbnCount}",
+  "asyncBefore": true
+}
diff --git a/duplicate-instance-report/nodes/isbnMoveToNode.json b/duplicate-instance-report/nodes/isbnMoveToNode.json
@@ -0,0 +1,12 @@
+{
+  "id": "408a6624-8be4-4bdf-8688-75c23a730187",
+  "name": "ISBN",
+  "description": "",
+  "deserializeAs": "MoveToNode",
+  "gatewayId": "parallel_gateway_aea23b81_06b1_4795_8bab_ea562a854c83",
+  "nodes": [
+    "{{{mod-workflow}}}/databaseQueryTask/84b7be20-ce1f-45f4-ad2e-7dff0c131e42",
+    "{{{mod-workflow}}}/emailTask/66356870-9e8a-406b-ae3d-5fcffef0c556",
+    "{{{mod-workflow}}}/connectTo/c36f8e08-7e43-49b3-923f-ebb8629617c8"
+  ]
+}
diff --git a/duplicate-instance-report/nodes/isbnQuery.json b/duplicate-instance-report/nodes/isbnQuery.json
@@ -0,0 +1,27 @@
+{
+  "id": "84b7be20-ce1f-45f4-ad2e-7dff0c131e42",
+  "name": "ISBN Match Query",
+  "description": "Query to find instances with matching ISBN",
+  "deserializeAs": "DatabaseQueryTask",
+  "inputVariables": [
+    {
+      "key": "timestamp",
+      "type": "PROCESS"
+    },
+    {
+      "key": "tenantId",
+      "type": "PROCESS"
+    }
+  ],
+  "outputVariable": {
+    "key": "isbnCount",
+    "type": "PROCESS",
+    "spin": false
+  },
+  "designation": "ldp",
+  "outputPath": "/mnt/workflows/${tenantId}/duplicate-instance-report/isbn-${timestamp}.csv",
+  "resultType": "CSV",
+  "includeHeader": true,
+  "query": "WITH isbn AS (SELECT ie.instance_hrid, ii.identifier, NULLIF(LEFT(RIGHT(REGEXP_REPLACE(ii.identifier, ' .*', ''), 10), 9), ':') AS isbn, ie.title, sm.content AS author FROM folio_reporting.instance_ext ie JOIN folio_reporting.instance_identifiers ii ON ie.instance_hrid = ii.instance_hrid JOIN public.srs_marctab sm ON ie.instance_hrid = sm.instance_hrid WHERE ii.identifier_type_name = 'ISBN' AND ii.identifier NOT SIMILAR TO '(:|$)%' AND sm.field = '100' AND sm.ord = 1 AND sm.sf = 'a') SELECT l.instance_hrid AS hrid, r.instance_hrid AS hrid2, l.identifier, l.isbn, '\"' || REPLACE(l.title, '\"', '\"\"') || '\"' AS title, '\"' || REPLACE(r.title, '\"', '\"\"') || '\"' AS title2, '\"' || REPLACE(l.author, '\"', '\"\"') || '\"' AS author, '\"' || REPLACE(r.author, '\"', '\"\"') || '\"' AS author2 FROM isbn l JOIN isbn r ON l.isbn = r.isbn AND l.instance_hrid < r.instance_hrid",
+  "asyncBefore": true
+}
diff --git a/duplicate-instance-report/nodes/issnConnectTo.json b/duplicate-instance-report/nodes/issnConnectTo.json
@@ -0,0 +1,7 @@
+{
+  "id": "01c05fa9-6897-4e1c-b0bc-c56b187173e2",
+  "name": "ISSN Complete",
+  "description": "",
+  "deserializeAs": "ConnectTo",
+  "nodeId": "parallel_gateway_af9d6b6c_6d59_4735_9a7c_2314a68e0985"
+}
diff --git a/duplicate-instance-report/nodes/issnEmail.json b/duplicate-instance-report/nodes/issnEmail.json
@@ -0,0 +1,29 @@
+{
+  "id": "f2cd0c7a-0dbe-4daa-b1ea-29455044a505",
+  "name": "Email ISSN Matches",
+  "description": "Email CSV with instances with matching ISSN",
+  "deserializeAs": "EmailTask",
+  "inputVariables": [
+    {
+      "key": "timestamp",
+      "type": "PROCESS"
+    },
+    {
+      "key": "tenantId",
+      "type": "PROCESS"
+    },
+    {
+      "key": "issnCount",
+      "type": "PROCESS"
+    }
+  ],
+  "outputVariable": {},
+  "mailFrom": "{{{duplicate-instance-report-from}}}",
+  "mailTo": "{{{duplicate-instance-report-to}}}",
+  "mailText": "The instances with matching ISSN report has completed, see the results attached.\n${issnCount} instance matches found.",
+  "mailMarkup": "<p>The instances with matching ISSN report has completed, see the results attached.</p><br/>${issnCount} instance matches found.",
+  "mailSubject": "Matching ISSN Instances Report - LDP {{{ldp-url}}}",
+  "attachmentPath": "/mnt/workflows/${tenantId}/duplicate-instance-report/issn-${timestamp}.csv",
+  "includeAttachment": "${issnCount}",
+  "asyncBefore": true
+}
diff --git a/duplicate-instance-report/nodes/issnMoveToNode.json b/duplicate-instance-report/nodes/issnMoveToNode.json
@@ -0,0 +1,12 @@
+{
+  "id": "3b2668b9-58aa-447e-b907-40cee663a3ea",
+  "name": "ISSN",
+  "description": "",
+  "deserializeAs": "MoveToNode",
+  "gatewayId": "parallel_gateway_aea23b81_06b1_4795_8bab_ea562a854c83",
+  "nodes": [
+    "{{{mod-workflow}}}/databaseQueryTask/403c8b97-2901-494a-bcdd-bfbbe23a1aa8",
+    "{{{mod-workflow}}}/emailTask/f2cd0c7a-0dbe-4daa-b1ea-29455044a505",
+    "{{{mod-workflow}}}/connectTo/01c05fa9-6897-4e1c-b0bc-c56b187173e2"
+  ]
+}
diff --git a/duplicate-instance-report/nodes/issnQuery.json b/duplicate-instance-report/nodes/issnQuery.json
@@ -0,0 +1,27 @@
+{
+  "id": "403c8b97-2901-494a-bcdd-bfbbe23a1aa8",
+  "name": "ISSN Match Query",
+  "description": "Query to find instances with matching ISSN",
+  "deserializeAs": "DatabaseQueryTask",
+  "inputVariables": [
+    {
+      "key": "timestamp",
+      "type": "PROCESS"
+    },
+    {
+      "key": "tenantId",
+      "type": "PROCESS"
+    }
+  ],
+  "outputVariable": {
+    "key": "issnCount",
+    "type": "PROCESS",
+    "spin": false
+  },
+  "designation": "ldp",
+  "outputPath": "/mnt/workflows/${tenantId}/duplicate-instance-report/issn-${timestamp}.csv",
+  "resultType": "CSV",
+  "includeHeader": true,
+  "query": "WITH issn_with_title AS (SELECT ie.instance_hrid, sm.content AS issn, ie.title FROM folio_reporting.instance_ext ie JOIN public.srs_marctab sm ON ie.instance_hrid = sm.instance_hrid WHERE field = '022' AND ord = 1 AND sf = 'a'), issn AS (SELECT issnwt.instance_hrid, issnwt.issn, issnwt.title, sm.content AS author FROM issn_with_title issnwt JOIN public.srs_marctab sm ON issnwt.instance_hrid = sm.instance_hrid WHERE sm.field = '100' AND sm.ord = 1 AND sm.sf = 'a') SELECT l.instance_hrid AS hrid, r.instance_hrid AS hrid2, l.issn, '\"' || REPLACE(l.title, '\"', '\"\"') || '\"' AS title, '\"' || REPLACE(r.title, '\"', '\"\"') || '\"' AS title2, '\"' || REPLACE(l.author, '\"', '\"\"') || '\"' AS author, '\"' || REPLACE(r.author, '\"', '\"\"') || '\"' AS author2 FROM issn l JOIN issn r ON l.issn = r.issn AND l.instance_hrid < r.instance_hrid",
+  "asyncBefore": true
+}
diff --git a/duplicate-instance-report/nodes/join.json b/duplicate-instance-report/nodes/join.json
@@ -0,0 +1,7 @@
+{
+  "id": "af9d6b6c-6d59-4735-9a7c-2314a68e0985",
+  "name": "Join",
+  "description": "",
+  "deserializeAs": "ParallelGateway",
+  "nodes": []
+}
diff --git a/duplicate-instance-report/nodes/lccnConnectTo.json b/duplicate-instance-report/nodes/lccnConnectTo.json
@@ -0,0 +1,7 @@
+{
+  "id": "35bb9b1d-ffa5-4d20-b3c9-afd71ff3990e",
+  "name": "LCCN Complete",
+  "description": "",
+  "deserializeAs": "ConnectTo",
+  "nodeId": "parallel_gateway_af9d6b6c_6d59_4735_9a7c_2314a68e0985"
+}
diff --git a/duplicate-instance-report/nodes/lccnEmail.json b/duplicate-instance-report/nodes/lccnEmail.json
@@ -0,0 +1,29 @@
+{
+  "id": "a32eae62-d2f3-4b7b-bbd4-275ba140555e",
+  "name": "Email LCCN Matches",
+  "description": "Email CSV with instances with matching LCCN",
+  "deserializeAs": "EmailTask",
+  "inputVariables": [
+    {
+      "key": "timestamp",
+      "type": "PROCESS"
+    },
+    {
+      "key": "tenantId",
+      "type": "PROCESS"
+    },
+    {
+      "key": "lccnCount",
+      "type": "PROCESS"
+    }
+  ],
+  "outputVariable": {},
+  "mailFrom": "{{{duplicate-instance-report-from}}}",
+  "mailTo": "{{{duplicate-instance-report-to}}}",
+  "mailText": "The instances with matching LCCN report has completed, see the results attached.\n${lccnCount} instance matches found.",
+  "mailMarkup": "<p>The instances with matching LCCN report has completed, see the results attached.</p><br/>${lccnCount} instance matches found.",
+  "mailSubject": "Matching LCCN Instances Report - LDP {{{ldp-url}}}",
+  "attachmentPath": "/mnt/workflows/${tenantId}/duplicate-instance-report/lccn-${timestamp}.csv",
+  "includeAttachment": "${lccnCount}",
+  "asyncBefore": true
+}
diff --git a/duplicate-instance-report/nodes/lccnMoveToNode.json b/duplicate-instance-report/nodes/lccnMoveToNode.json
@@ -0,0 +1,12 @@
+{
+  "id": "b4e72925-19a4-47ed-8f31-e32cf8905123",
+  "name": "LCCN",
+  "description": "",
+  "deserializeAs": "MoveToNode",
+  "gatewayId": "parallel_gateway_aea23b81_06b1_4795_8bab_ea562a854c83",
+  "nodes": [
+    "{{{mod-workflow}}}/databaseQueryTask/9d943d76-ab21-4ca6-9eae-8df6e962c037",
+    "{{{mod-workflow}}}/emailTask/a32eae62-d2f3-4b7b-bbd4-275ba140555e",
+    "{{{mod-workflow}}}/connectTo/35bb9b1d-ffa5-4d20-b3c9-afd71ff3990e"
+  ]
+}
diff --git a/duplicate-instance-report/nodes/lccnQuery.json b/duplicate-instance-report/nodes/lccnQuery.json
@@ -0,0 +1,27 @@
+{
+  "id": "9d943d76-ab21-4ca6-9eae-8df6e962c037",
+  "name": "LCCN Match Query",
+  "description": "Query to find instances with matching LCCN",
+  "deserializeAs": "DatabaseQueryTask",
+  "inputVariables": [
+    {
+      "key": "timestamp",
+      "type": "PROCESS"
+    },
+    {
+      "key": "tenantId",
+      "type": "PROCESS"
+    }
+  ],
+  "outputVariable": {
+    "key": "lccnCount",
+    "type": "PROCESS",
+    "spin": false
+  },
+  "designation": "ldp",
+  "outputPath": "/mnt/workflows/${tenantId}/duplicate-instance-report/lccn-${timestamp}.csv",
+  "resultType": "CSV",
+  "includeHeader": true,
+  "query": "WITH lccn AS (SELECT ie.instance_hrid, ii.identifier AS lccn, ie.title, sm.content AS author FROM folio_reporting.instance_ext ie JOIN folio_reporting.instance_identifiers ii ON ie.instance_hrid = ii.instance_hrid JOIN public.srs_marctab sm ON ie.instance_hrid = sm.instance_hrid WHERE ii.identifier_type_name = 'LCCN' AND sm.field = '100' AND sm.ord = 1 AND sm.sf = 'a') SELECT l.instance_hrid AS hrid, r.instance_hrid AS hrid2, l.lccn, '\"' || REPLACE(l.title, '\"', '\"\"') || '\"' AS title, '\"' || REPLACE(r.title, '\"', '\"\"') || '\"' AS title2, '\"' || REPLACE(l.author, '\"', '\"\"') || '\"' AS author, '\"' || REPLACE(r.author, '\"', '\"\"') || '\"' AS author2 FROM lccn l JOIN lccn r ON l.lccn = r.lccn AND l.instance_hrid < r.instance_hrid",
+  "asyncBefore": true
+}