From c377a9eae5aa1c25d267ed1ace11e31ac6d4feef Mon Sep 17 00:00:00 2001 From: Galen Charlton Date: Wed, 15 Mar 2017 16:18:50 -0400 Subject: [PATCH] update monolithic schema upgrade script for 2.12-rc Signed-off-by: Galen Charlton --- ...pgrade-db.sql => 2.11.3-2.12-rc-upgrade-db.sql} | 201 ++++++++++++++++++++- 1 file changed, 199 insertions(+), 2 deletions(-) rename Open-ILS/src/sql/Pg/version-upgrade/{2.11.3-2.12-beta-upgrade-db.sql => 2.11.3-2.12-rc-upgrade-db.sql} (76%) diff --git a/Open-ILS/src/sql/Pg/version-upgrade/2.11.3-2.12-beta-upgrade-db.sql b/Open-ILS/src/sql/Pg/version-upgrade/2.11.3-2.12-rc-upgrade-db.sql similarity index 76% rename from Open-ILS/src/sql/Pg/version-upgrade/2.11.3-2.12-beta-upgrade-db.sql rename to Open-ILS/src/sql/Pg/version-upgrade/2.11.3-2.12-rc-upgrade-db.sql index 92aff0b5b2..a64af64eb9 100644 --- a/Open-ILS/src/sql/Pg/version-upgrade/2.11.3-2.12-beta-upgrade-db.sql +++ b/Open-ILS/src/sql/Pg/version-upgrade/2.11.3-2.12-rc-upgrade-db.sql @@ -1,5 +1,5 @@ ---Upgrade Script for 2.11.3 to 2.12-beta -\set eg_version '''2.12-beta''' +--Upgrade Script for 2.11.3 to 2.12-rc +\set eg_version '''2.12-rc''' BEGIN; SELECT evergreen.upgrade_deps_block_check('1006', :eg_version); @@ -749,6 +749,203 @@ VALUES ( 'bool' ); +SELECT evergreen.upgrade_deps_block_check('1029', :eg_version); -- csharp/gmcharlt + +UPDATE config.index_normalizer SET description = 'Apply NACO normalization rules to the extracted text. See https://www.loc.gov/aba/pcc/naco/normrule-2.html for details.' WHERE func = 'naco_normalize'; +UPDATE config.index_normalizer SET description = 'Apply NACO normalization rules to the extracted text, retaining the first comma. See https://www.loc.gov/aba/pcc/naco/normrule-2.html for details.' WHERE func = 'naco_normalize_keep_comma'; + +CREATE OR REPLACE FUNCTION public.naco_normalize( TEXT, TEXT ) RETURNS TEXT AS $func$ + + use strict; + use Unicode::Normalize; + use Encode; + + my $str = shift; + my $sf = shift; + + # Apply NACO normalization to input string; based on + # https://www.loc.gov/aba/pcc/naco/documents/SCA_PccNormalization_Final_revised.pdf + # + # Note that unlike a strict reading of the NACO normalization rules, + # output is returned as lowercase instead of uppercase for compatibility + # with previous versions of the Evergreen naco_normalize routine. + + # Convert to upper-case first; even though final output will be lowercase, doing this will + # ensure that the German eszett (ß) and certain ligatures (ff, fi, ffl, etc.) will be handled correctly. + # If there are any bugs in Perl's implementation of upcasing, they will be passed through here. + $str = uc $str; + + # remove non-filing strings + $str =~ s/\x{0098}.*?\x{009C}//g; + + $str = NFKD($str); + + # additional substitutions - 3.6. + $str =~ s/\x{00C6}/AE/g; + $str =~ s/\x{00DE}/TH/g; + $str =~ s/\x{0152}/OE/g; + $str =~ tr/\x{0110}\x{00D0}\x{00D8}\x{0141}\x{2113}\x{02BB}\x{02BC}]['/DDOLl/d; + + # transformations based on Unicode category codes + $str =~ s/[\p{Cc}\p{Cf}\p{Co}\p{Cs}\p{Lm}\p{Mc}\p{Me}\p{Mn}]//g; + + if ($sf && $sf =~ /^a/o) { + my $commapos = index($str, ','); + if ($commapos > -1) { + if ($commapos != length($str) - 1) { + $str =~ s/,/\x07/; # preserve first comma + } + } + } + + # since we've stripped out the control characters, we can now + # use a few as placeholders temporarily + $str =~ tr/+&@\x{266D}\x{266F}#/\x01\x02\x03\x04\x05\x06/; + $str =~ s/[\p{Pc}\p{Pd}\p{Pe}\p{Pf}\p{Pi}\p{Po}\p{Ps}\p{Sk}\p{Sm}\p{So}\p{Zl}\p{Zp}\p{Zs}]/ /g; + $str =~ tr/\x01\x02\x03\x04\x05\x06\x07/+&@\x{266D}\x{266F}#,/; + + # decimal digits + $str =~ tr/\x{0660}-\x{0669}\x{06F0}-\x{06F9}\x{07C0}-\x{07C9}\x{0966}-\x{096F}\x{09E6}-\x{09EF}\x{0A66}-\x{0A6F}\x{0AE6}-\x{0AEF}\x{0B66}-\x{0B6F}\x{0BE6}-\x{0BEF}\x{0C66}-\x{0C6F}\x{0CE6}-\x{0CEF}\x{0D66}-\x{0D6F}\x{0E50}-\x{0E59}\x{0ED0}-\x{0ED9}\x{0F20}-\x{0F29}\x{1040}-\x{1049}\x{1090}-\x{1099}\x{17E0}-\x{17E9}\x{1810}-\x{1819}\x{1946}-\x{194F}\x{19D0}-\x{19D9}\x{1A80}-\x{1A89}\x{1A90}-\x{1A99}\x{1B50}-\x{1B59}\x{1BB0}-\x{1BB9}\x{1C40}-\x{1C49}\x{1C50}-\x{1C59}\x{A620}-\x{A629}\x{A8D0}-\x{A8D9}\x{A900}-\x{A909}\x{A9D0}-\x{A9D9}\x{AA50}-\x{AA59}\x{ABF0}-\x{ABF9}\x{FF10}-\x{FF19}/0-90-90-90-90-90-90-90-90-90-90-90-90-90-90-90-90-90-90-90-90-90-90-90-90-90-90-90-90-90-90-90-90-90-9/; + + # intentionally skipping step 8 of the NACO algorithm; if the string + # gets normalized away, that's fine. + + # leading and trailing spaces + $str =~ s/\s+/ /g; + $str =~ s/^\s+//; + $str =~ s/\s+$//g; + + return lc $str; +$func$ LANGUAGE 'plperlu' STRICT IMMUTABLE; + +-- Currently, the only difference from naco_normalize is that search_normalize +-- turns apostrophes into spaces, while naco_normalize collapses them. +CREATE OR REPLACE FUNCTION public.search_normalize( TEXT, TEXT ) RETURNS TEXT AS $func$ + + use strict; + use Unicode::Normalize; + use Encode; + + my $str = shift; + my $sf = shift; + + # Apply NACO normalization to input string; based on + # https://www.loc.gov/aba/pcc/naco/documents/SCA_PccNormalization_Final_revised.pdf + # + # Note that unlike a strict reading of the NACO normalization rules, + # output is returned as lowercase instead of uppercase for compatibility + # with previous versions of the Evergreen naco_normalize routine. + + # Convert to upper-case first; even though final output will be lowercase, doing this will + # ensure that the German eszett (ß) and certain ligatures (ff, fi, ffl, etc.) will be handled correctly. + # If there are any bugs in Perl's implementation of upcasing, they will be passed through here. + $str = uc $str; + + # remove non-filing strings + $str =~ s/\x{0098}.*?\x{009C}//g; + + $str = NFKD($str); + + # additional substitutions - 3.6. + $str =~ s/\x{00C6}/AE/g; + $str =~ s/\x{00DE}/TH/g; + $str =~ s/\x{0152}/OE/g; + $str =~ tr/\x{0110}\x{00D0}\x{00D8}\x{0141}\x{2113}\x{02BB}\x{02BC}][/DDOLl/d; + + # transformations based on Unicode category codes + $str =~ s/[\p{Cc}\p{Cf}\p{Co}\p{Cs}\p{Lm}\p{Mc}\p{Me}\p{Mn}]//g; + + if ($sf && $sf =~ /^a/o) { + my $commapos = index($str, ','); + if ($commapos > -1) { + if ($commapos != length($str) - 1) { + $str =~ s/,/\x07/; # preserve first comma + } + } + } + + # since we've stripped out the control characters, we can now + # use a few as placeholders temporarily + $str =~ tr/+&@\x{266D}\x{266F}#/\x01\x02\x03\x04\x05\x06/; + $str =~ s/[\p{Pc}\p{Pd}\p{Pe}\p{Pf}\p{Pi}\p{Po}\p{Ps}\p{Sk}\p{Sm}\p{So}\p{Zl}\p{Zp}\p{Zs}]/ /g; + $str =~ tr/\x01\x02\x03\x04\x05\x06\x07/+&@\x{266D}\x{266F}#,/; + + # decimal digits + $str =~ tr/\x{0660}-\x{0669}\x{06F0}-\x{06F9}\x{07C0}-\x{07C9}\x{0966}-\x{096F}\x{09E6}-\x{09EF}\x{0A66}-\x{0A6F}\x{0AE6}-\x{0AEF}\x{0B66}-\x{0B6F}\x{0BE6}-\x{0BEF}\x{0C66}-\x{0C6F}\x{0CE6}-\x{0CEF}\x{0D66}-\x{0D6F}\x{0E50}-\x{0E59}\x{0ED0}-\x{0ED9}\x{0F20}-\x{0F29}\x{1040}-\x{1049}\x{1090}-\x{1099}\x{17E0}-\x{17E9}\x{1810}-\x{1819}\x{1946}-\x{194F}\x{19D0}-\x{19D9}\x{1A80}-\x{1A89}\x{1A90}-\x{1A99}\x{1B50}-\x{1B59}\x{1BB0}-\x{1BB9}\x{1C40}-\x{1C49}\x{1C50}-\x{1C59}\x{A620}-\x{A629}\x{A8D0}-\x{A8D9}\x{A900}-\x{A909}\x{A9D0}-\x{A9D9}\x{AA50}-\x{AA59}\x{ABF0}-\x{ABF9}\x{FF10}-\x{FF19}/0-90-90-90-90-90-90-90-90-90-90-90-90-90-90-90-90-90-90-90-90-90-90-90-90-90-90-90-90-90-90-90-90-90-9/; + + # intentionally skipping step 8 of the NACO algorithm; if the string + # gets normalized away, that's fine. + + # leading and trailing spaces + $str =~ s/\s+/ /g; + $str =~ s/^\s+//; + $str =~ s/\s+$//g; + + return lc $str; +$func$ LANGUAGE 'plperlu' STRICT IMMUTABLE; + +SELECT evergreen.upgrade_deps_block_check('1030', :eg_version); + +CREATE OR REPLACE FUNCTION evergreen.oils_xslt_process(TEXT, TEXT) RETURNS TEXT AS $func$ + use strict; + + use XML::LibXSLT; + use XML::LibXML; + + my $doc = shift; + my $xslt = shift; + + # The following approach uses the older XML::LibXML 1.69 / XML::LibXSLT 1.68 + # methods of parsing XML documents and stylesheets, in the hopes of broader + # compatibility with distributions + my $parser = $_SHARED{'_xslt_process'}{parsers}{xml} || XML::LibXML->new(); + + # Cache the XML parser, if we do not already have one + $_SHARED{'_xslt_process'}{parsers}{xml} = $parser + unless ($_SHARED{'_xslt_process'}{parsers}{xml}); + + my $xslt_parser = $_SHARED{'_xslt_process'}{parsers}{xslt} || XML::LibXSLT->new(); + + # Cache the XSLT processor, if we do not already have one + $_SHARED{'_xslt_process'}{parsers}{xslt} = $xslt_parser + unless ($_SHARED{'_xslt_process'}{parsers}{xslt}); + + my $stylesheet = $_SHARED{'_xslt_process'}{stylesheets}{$xslt} || + $xslt_parser->parse_stylesheet( $parser->parse_string($xslt) ); + + $_SHARED{'_xslt_process'}{stylesheets}{$xslt} = $stylesheet + unless ($_SHARED{'_xslt_process'}{stylesheets}{$xslt}); + + return $stylesheet->output_as_chars( + $stylesheet->transform( + $parser->parse_string($doc) + ) + ); + +$func$ LANGUAGE 'plperlu' STRICT IMMUTABLE; + +SELECT evergreen.upgrade_deps_block_check('1031', :eg_version); + +INSERT INTO config.org_unit_setting_type + (name, label, description, grp, datatype) +VALUES ( + 'ebook_api.oneclickdigital.base_uri', + oils_i18n_gettext( + 'ebook_api.oneclickdigital.base_uri', + 'OneClickdigital Base URI', + 'coust', + 'label' + ), + oils_i18n_gettext( + 'ebook_api.oneclickdigital.base_uri', + 'Base URI for OneClickdigital API (defaults to https://api.oneclickdigital.com/v1). Using HTTPS here is strongly encouraged.', + 'coust', + 'description' + ), + 'ebook_api', + 'string' +); + COMMIT; \qecho Running some data updates outside of the main transaction -- 2.11.0