From 1c17ce33354a31b182f1b1393dbfe2693bc33065 Mon Sep 17 00:00:00 2001
From: David Cook <dcook@prosentient.com.au>
Date: Thu, 8 Sep 2022 05:06:38 +0000
Subject: [PATCH] Bug 31532: Add preprocessor to Zebra indexing pipeline to
 index 880 as linked field

This patch adds a preprocessor XSLT to the Zebra indexing pipeline,
so that 880 fields get indexed as the fields they're linked to. For example,
a "880 $6 245" field would be indexed as a "245" field.

However, because the preprocessor only occurs in the indexing part of the pipeline,
it does not affect the retrieval of MARCXML from Zebra. That MARCXML will be
the same MARCXML that was sent to Zebra from Koha.

Test plan:

0. Revert bug 15187, and apply patch for 31532
1. cp ./etc/zebradb/biblios/etc/dom-config.xml /etc/koha/zebradb/biblios/etc/dom-config.xml
2a. cp etc/zebradb/marc_defs/marc21/biblios/preprocess_marcxml.xsl /etc/koha/zebradb/marc_defs/marc21/biblios/.
2b. cp etc/zebradb/marc_defs/normarc/biblios/preprocess_marcxml.xsl /etc/koha/zebradb/marc_defs/normarc/biblios/.
2c. cp etc/zebradb/marc_defs/unimarc/biblios/preprocess_marcxml.xsl /etc/koha/zebradb/marc_defs/unimarc/biblios/.
3. koha-rebuild-zebra -b -f -v kohadev
4. Note that in search results the 880$6245$a data appears before the 245$a data
5. Note that you can do a title index search on the 880$6245$a data

Signed-off-by: Katrin Fischer <katrin.fischer.83@web.de>
Signed-off-by: Martin Renvoize <martin.renvoize@ptfs-europe.com>
Signed-off-by: Tomas Cohen Arazi <tomascohen@theke.io>
(cherry picked from commit 2c673944ba8a5f2b785836dab562acdbb026ccee)

Signed-off-by: Lucas Gass <lucas@bywatersolutions.com>
---
 etc/zebradb/biblios/etc/dom-config.xml        |  1 +
 .../marc21/biblios/preprocess_marcxml.xsl     | 23 +++++++++++++++++++
 .../normarc/biblios/preprocess_marcxml.xsl    | 23 +++++++++++++++++++
 .../unimarc/biblios/preprocess_marcxml.xsl    | 16 +++++++++++++
 4 files changed, 63 insertions(+)
 create mode 100644 etc/zebradb/marc_defs/marc21/biblios/preprocess_marcxml.xsl
 create mode 100644 etc/zebradb/marc_defs/normarc/biblios/preprocess_marcxml.xsl
 create mode 100644 etc/zebradb/marc_defs/unimarc/biblios/preprocess_marcxml.xsl

diff --git a/etc/zebradb/biblios/etc/dom-config.xml b/etc/zebradb/biblios/etc/dom-config.xml
index e6eb89fdf2..47ae7289e0 100644
--- a/etc/zebradb/biblios/etc/dom-config.xml
+++ b/etc/zebradb/biblios/etc/dom-config.xml
@@ -28,6 +28,7 @@ Bibliographic DOM config for MARC XML input
 -->
 <dom>
   <extract name="index">
+    <xslt stylesheet="preprocess_marcxml.xsl"/>
     <xslt stylesheet="biblio-zebra-indexdefs.xsl"/>
   </extract>
   <retrieve name="marc">
diff --git a/etc/zebradb/marc_defs/marc21/biblios/preprocess_marcxml.xsl b/etc/zebradb/marc_defs/marc21/biblios/preprocess_marcxml.xsl
new file mode 100644
index 0000000000..8140c0af59
--- /dev/null
+++ b/etc/zebradb/marc_defs/marc21/biblios/preprocess_marcxml.xsl
@@ -0,0 +1,23 @@
+<xsl:stylesheet xmlns:xsl="http://www.w3.org/1999/XSL/Transform" xmlns:marc="http://www.loc.gov/MARC21/slim"
+ version="1.0">
+<xsl:output indent="yes"
+      method="xml"
+      version="1.0"
+      encoding="UTF-8"/>
+
+ <xsl:template name="identity" match="node()|@*">
+   <xsl:copy>
+     <xsl:apply-templates select="@*|node()"/>
+   </xsl:copy>
+ </xsl:template>
+
+ <xsl:template match="marc:datafield[@tag=880]">
+    <xsl:element name="datafield" namespace="http://www.loc.gov/MARC21/slim">
+        <xsl:attribute name="tag"><xsl:value-of select="substring(marc:subfield[@code=6],1,3)"/></xsl:attribute>
+        <xsl:attribute name="ind1"><xsl:value-of select="@ind1"/></xsl:attribute>
+        <xsl:attribute name="ind2"><xsl:value-of select="@ind2"/></xsl:attribute>
+        <xsl:apply-templates select="marc:subfield[@code != '6']"/>
+    </xsl:element>
+</xsl:template>
+
+</xsl:stylesheet>
diff --git a/etc/zebradb/marc_defs/normarc/biblios/preprocess_marcxml.xsl b/etc/zebradb/marc_defs/normarc/biblios/preprocess_marcxml.xsl
new file mode 100644
index 0000000000..8140c0af59
--- /dev/null
+++ b/etc/zebradb/marc_defs/normarc/biblios/preprocess_marcxml.xsl
@@ -0,0 +1,23 @@
+<xsl:stylesheet xmlns:xsl="http://www.w3.org/1999/XSL/Transform" xmlns:marc="http://www.loc.gov/MARC21/slim"
+ version="1.0">
+<xsl:output indent="yes"
+      method="xml"
+      version="1.0"
+      encoding="UTF-8"/>
+
+ <xsl:template name="identity" match="node()|@*">
+   <xsl:copy>
+     <xsl:apply-templates select="@*|node()"/>
+   </xsl:copy>
+ </xsl:template>
+
+ <xsl:template match="marc:datafield[@tag=880]">
+    <xsl:element name="datafield" namespace="http://www.loc.gov/MARC21/slim">
+        <xsl:attribute name="tag"><xsl:value-of select="substring(marc:subfield[@code=6],1,3)"/></xsl:attribute>
+        <xsl:attribute name="ind1"><xsl:value-of select="@ind1"/></xsl:attribute>
+        <xsl:attribute name="ind2"><xsl:value-of select="@ind2"/></xsl:attribute>
+        <xsl:apply-templates select="marc:subfield[@code != '6']"/>
+    </xsl:element>
+</xsl:template>
+
+</xsl:stylesheet>
diff --git a/etc/zebradb/marc_defs/unimarc/biblios/preprocess_marcxml.xsl b/etc/zebradb/marc_defs/unimarc/biblios/preprocess_marcxml.xsl
new file mode 100644
index 0000000000..f2f8134767
--- /dev/null
+++ b/etc/zebradb/marc_defs/unimarc/biblios/preprocess_marcxml.xsl
@@ -0,0 +1,16 @@
+<xsl:stylesheet xmlns:xsl="http://www.w3.org/1999/XSL/Transform" xmlns:marc="http://www.loc.gov/MARC21/slim"
+ version="1.0">
+<xsl:output indent="yes"
+      method="xml"
+      version="1.0"
+      encoding="UTF-8"/>
+
+ <xsl:template name="identity" match="node()|@*">
+   <xsl:copy>
+     <xsl:apply-templates select="@*|node()"/>
+   </xsl:copy>
+ </xsl:template>
+
+<!-- There's nothing to do here for UNIMARC but we need this file since the dom-config.xml file is cross-format -->
+
+</xsl:stylesheet>
-- 
2.20.1