More precise deduping for insert_tags

[migration-tools.git] / sql / base / base.sql

diff --git a/sql/base/base.sql b/sql/base/base.sql
index 59eec2f..569dd07 100644 (file)
--- a/sql/base/base.sql
+++ b/sql/base/base.sql
@@ -697,16 +697,118 @@ CREATE OR REPLACE FUNCTION migration_tools.attempt_phone (TEXT,TEXT) RETURNS TEX
   DECLARE
     phone TEXT := $1;
     areacode TEXT := $2;
+    temp TEXT := '';
     output TEXT := '';
     n_digits INTEGER := 0;
   BEGIN
-    output := REGEXP_REPLACE(phone, '[^0-9]*([0-9]{3})[^0-9]*([0-9]{3})[^0-9]*([0-9]{4})', E'\\1-\\2-\\3');
-    n_digits := LENGTH(REGEXP_REPLACE(output, '[^0-9]', '', 'g'));
-    IF n_digits = 7 THEN
-      RETURN (areacode || '-' || output);
+    temp := phone;
+    temp := REGEXP_REPLACE(temp, '^1*[^0-9]*(?=[0-9])', '');
+    temp := REGEXP_REPLACE(temp, '[^0-9]*([0-9]{3})[^0-9]*([0-9]{3})[^0-9]*([0-9]{4})', E'\\1-\\2-\\3');
+    n_digits := LENGTH(REGEXP_REPLACE(REGEXP_REPLACE(temp, '(.*)?[a-zA-Z].*', E'\\1') , '[^0-9]', '', 'g'));
+    IF n_digits = 7 AND areacode <> '' THEN
+      temp := REGEXP_REPLACE(temp, '[^0-9]*([0-9]{3})[^0-9]*([0-9]{4})', E'\\1-\\2');
+      output := (areacode || '-' || temp);
     ELSE
-      RETURN output;
+      output := temp;
     END IF;
+    RETURN output;
   END;
 
 $$ LANGUAGE PLPGSQL STRICT VOLATILE;
+
+CREATE OR REPLACE FUNCTION migration_tools.set_leader (TEXT, INT, TEXT) RETURNS TEXT AS $$
+  my ($marcxml, $pos, $value) = @_;
+
+  use MARC::Record;
+  use MARC::File::XML;
+
+  my $xml = $marcxml;
+  eval {
+    my $marc = MARC::Record->new_from_xml($marcxml, 'UTF-8');
+    my $leader = $marc->leader();
+    substr($leader, $pos, 1) = $value;
+    $marc->leader($leader);
+    $xml = $marc->as_xml_record;
+    $xml =~ s/^<\?.+?\?>$//mo;
+    $xml =~ s/\n//sgo;
+    $xml =~ s/>\s+</></sgo;
+  };
+  return $xml;
+$$ LANGUAGE PLPERLU STABLE;
+
+CREATE OR REPLACE FUNCTION migration_tools.set_008 (TEXT, INT, TEXT) RETURNS TEXT AS $$
+  my ($marcxml, $pos, $value) = @_;
+
+  use MARC::Record;
+  use MARC::File::XML;
+
+  my $xml = $marcxml;
+  eval {
+    my $marc = MARC::Record->new_from_xml($marcxml, 'UTF-8');
+    my $f008 = $marc->field('008');
+
+    if ($f008) {
+       my $field = $f008->data();
+       substr($field, $pos, 1) = $value;
+       $f008->update($field);
+       $xml = $marc->as_xml_record;
+       $xml =~ s/^<\?.+?\?>$//mo;
+       $xml =~ s/\n//sgo;
+       $xml =~ s/>\s+</></sgo;
+    }
+  };
+  return $xml;
+$$ LANGUAGE PLPERLU STABLE;
+
+
+CREATE OR REPLACE FUNCTION migration_tools.is_staff_profile (INT) RETURNS BOOLEAN AS $$
+  DECLARE
+    profile ALIAS FOR $1;
+  BEGIN
+    RETURN CASE WHEN 'Staff' IN (select (permission.grp_ancestors(profile)).name) THEN TRUE ELSE FALSE END;
+  END;
+$$ LANGUAGE PLPGSQL STRICT STABLE;
+
+
+CREATE OR REPLACE FUNCTION migration_tools.is_blank (TEXT) RETURNS BOOLEAN AS $$
+  BEGIN
+    RETURN CASE WHEN $1 = '' THEN TRUE ELSE FALSE END;
+  END;
+$$ LANGUAGE PLPGSQL STRICT STABLE;
+
+
+CREATE OR REPLACE FUNCTION migration_tools.insert_tags (TEXT, TEXT) RETURNS TEXT AS $$
+
+  my ($marcxml, $tags) = @_;
+
+  use MARC::Record;
+  use MARC::File::XML;
+
+  my $xml = $marcxml;
+
+  eval {
+    my $marc = MARC::Record->new_from_xml($marcxml, 'UTF-8');
+    my $to_insert = MARC::Record->new_from_xml("<record>$tags</record>", 'UTF-8');
+
+    my @incumbents = ();
+
+    foreach my $field ( $marc->fields() ) {
+      push @incumbents, $field->as_formatted();
+    }
+
+    foreach $field ( $to_insert->fields() ) {
+      if (!grep {$_ eq $field->as_formatted()} @incumbents) {
+        $marc->insert_fields_ordered( ($field) );
+      }
+    }
+
+    $xml = $marc->as_xml_record;
+    $xml =~ s/^<\?.+?\?>$//mo;
+    $xml =~ s/\n//sgo;
+    $xml =~ s/>\s+</></sgo;
+  };
+
+  return $xml;
+
+$$ LANGUAGE PLPERLU STABLE;
+