From 95d23a7bf0facdbc424617852ba995d46a2cd4b5 Mon Sep 17 00:00:00 2001
From: Demian Katz <demian.katz@villanova.edu>
Date: Fri, 24 May 2013 13:21:39 -0400
Subject: [PATCH] Progress on VUFIND-749 (index RDA 264 field).
---
import/index_scripts/getdate.bsh | 67 ++++++++++++++++++++++++++
import/index_scripts/getpublishers.bsh | 60 +++++++++++++++++++++++
import/marc.properties | 8 +--
3 files changed, 131 insertions(+), 4 deletions(-)
create mode 100644 import/index_scripts/getpublishers.bsh
diff --git a/import/index_scripts/getdate.bsh b/import/index_scripts/getdate.bsh
index 55102a2d755..5d615c15f74 100644
--- a/import/index_scripts/getdate.bsh
+++ b/import/index_scripts/getdate.bsh
@@ -126,3 +126,70 @@ public String getDate(Record record)
return (null);
return cleanDate(date);
}
+
+/**
+ * Get all available dates from the record.
+ *
+ * @param Record record
+ * @return Set dates
+ */
+public Set getDates(Record record) {
+ Set dates = new LinkedHashSet();
+
+ // First check old-style 260c date:
+ String oldStyle = getDate(record);
+ if (oldStyle != null && oldStyle.length() > 0) {
+ dates.add(oldStyle);
+ }
+
+ // Now track down relevant RDA-style 264c dates; we only care about
+ // copyright and publication dates (and ignore copyright dates if
+ // publication dates are present).
+ Set pubDates = new LinkedHashSet();
+ Set copyDates = new LinkedHashSet();
+ List list264 = record.getVariableFields("264");
+ for (VariableField vf : list264)
+ {
+ DataField df = (DataField) vf;
+ Subfield currentDate = df.getSubfield('c');
+ if (currentDate != null) {
+ String currentDateStr = cleanDate(currentDate.getData());
+ char ind2 = df.getIndicator2();
+ switch (ind2)
+ {
+ case '1':
+ pubDates.add(currentDateStr);
+ break;
+ case '4':
+ copyDates.add(currentDateStr);
+ break;
+ }
+ }
+ }
+ if (pubDates.size() > 0) {
+ dates.addAll(pubDates);
+ } else if (copyDates.size() > 0) {
+ dates.addAll(copyDates);
+ }
+
+ return dates;
+}
+
+/**
+ * Get the earliest publication date from the record.
+ *
+ * @param Record record
+ * @return String earliest date
+ */
+public String getFirstDate(Record record) {
+ String result = null;
+ Set dates = getDates(record);
+ Iterator datesIter = dates.iterator();
+ while (datesIter.hasNext()) {
+ String current = datesIter.next();
+ if (result == null || Integer.parseInt(current) < Integer.parseInt(result)) {
+ result = current;
+ }
+ }
+ return result;
+}
\ No newline at end of file
diff --git a/import/index_scripts/getpublishers.bsh b/import/index_scripts/getpublishers.bsh
new file mode 100644
index 00000000000..aa5a6e5034a
--- /dev/null
+++ b/import/index_scripts/getpublishers.bsh
@@ -0,0 +1,60 @@
+/**
+ * Custom date script.
+ *
+ * This can be used to override built-in SolrMarc custom functions. If you change
+ * this script, you will need to activate it in import/marc_local.properties before
+ * it will be applied during indexing.
+ */
+import org.marc4j.marc.*;
+
+/**
+ * Get all available publishers from the record.
+ *
+ * @param Record record
+ * @return Set publishers
+ */
+public Set getPublishers(Record record) {
+ Set publishers = new LinkedHashSet();
+
+ // First check old-style 260b name:
+ List list260 = record.getVariableFields("260");
+ for (VariableField vf : list260)
+ {
+ DataField df = (DataField) vf;
+ Subfield current = df.getSubfield('b');
+ if (current != null) {
+ publishers.add(current.getData());
+ }
+ }
+
+ // Now track down relevant RDA-style 264b names; we only care about
+ // copyright and publication names (and ignore copyright names if
+ // publication names are present).
+ Set pubNames = new LinkedHashSet();
+ Set copyNames = new LinkedHashSet();
+ List list264 = record.getVariableFields("264");
+ for (VariableField vf : list264)
+ {
+ DataField df = (DataField) vf;
+ Subfield currentName = df.getSubfield('b');
+ if (currentName != null) {
+ char ind2 = df.getIndicator2();
+ switch (ind2)
+ {
+ case '1':
+ pubNames.add(currentName.getData());
+ break;
+ case '4':
+ copyNames.add(currentName.getData());
+ break;
+ }
+ }
+ }
+ if (pubNames.size() > 0) {
+ publishers.addAll(pubNames);
+ } else if (copyNames.size() > 0) {
+ publishers.addAll(copyNames);
+ }
+
+ return publishers;
+}
\ No newline at end of file
diff --git a/import/marc.properties b/import/marc.properties
index ede9390da16..570b21c708c 100644
--- a/import/marc.properties
+++ b/import/marc.properties
@@ -36,9 +36,9 @@ title_sort = custom, getSortableTitle
series = 440ap:800abcdfpqt:830ap
series2 = 490a
-publisher = 260b
-publishDate = custom, getDate
-publishDateSort = custom, getDate
+publisher = script(getpublishers.bsh), getPublishers
+publishDate = script(getdate.bsh), getDates
+publishDateSort = script(getdate.bsh), getFirstDate
physical = 300abcefg:530abcd
dateSpan = 362a
@@ -83,4 +83,4 @@ oclc_num = 035a, (pattern_map.oclc_num)
pattern_map.oclc_num.pattern_0 = \\(OCoLC\\)[^0-9]*[0]*([0-9]+)=>$1
pattern_map.oclc_num.pattern_1 = ocm[0]*([0-9]+)[ ]*[0-9]*=>$1
pattern_map.oclc_num.pattern_2 = ocn[0]*([0-9]+).*=>$1
-pattern_map.oclc_num.pattern_3 = on[0]*([0-9]+).*=>$1
+pattern_map.oclc_num.pattern_3 = on[0]*([0-9]+).*=>$1
\ No newline at end of file
--
GitLab