From 643cc5c5e8ac2d279d84c60f532c8d430387e985 Mon Sep 17 00:00:00 2001 From: Ralph Amissah Date: Wed, 1 Jul 2009 13:43:41 -0400 Subject: minor fixes and touches --- lib/sisu/v0/concordance.rb | 2 +- lib/sisu/v0/constants.rb | 1 + lib/sisu/v0/dal_metadata.rb | 2 +- lib/sisu/v0/harvest.rb | 4 +--- lib/sisu/v0/odf.rb | 1 - lib/sisu/v0/shared_html_lite.rb | 7 +++---- lib/sisu/v0/xml_dom.rb | 2 +- 7 files changed, 8 insertions(+), 11 deletions(-) (limited to 'lib') diff --git a/lib/sisu/v0/concordance.rb b/lib/sisu/v0/concordance.rb index 4b6530ad..3c2b8326 100644 --- a/lib/sisu/v0/concordance.rb +++ b/lib/sisu/v0/concordance.rb @@ -125,7 +125,7 @@ WOK - SiSU created WordIndex for: #{@md.full_title} + SiSU created Concordance (WordIndex) for: #{@md.full_title} diff --git a/lib/sisu/v0/constants.rb b/lib/sisu/v0/constants.rb index 8929a0bb..5c93d543 100644 --- a/lib/sisu/v0/constants.rb +++ b/lib/sisu/v0/constants.rb @@ -57,6 +57,7 @@ ** Description: system environment, resource control and configuration details =end +Sfx={:txt=>'.txt',:html=>'.html',:xhtml=>'.xhtml',:xml=>'.xml',:epub=>'.epub',:epub_xhtml=>'.xhtml',:odt=>'.odt',:pdf=>'.pdf'} Mx,Rx={},{} Mx[:meta_o],Mx[:meta_c]='〔@','〕' Mx[:lv_o_1],Mx[:lv_o_2],Mx[:lv_o_3],Mx[:lv_o_4],Mx[:lv_o_5],Mx[:lv_o_6],Mx[:lv_o_7],Mx[:lv_o_8],Mx[:lv_o_9]= diff --git a/lib/sisu/v0/dal_metadata.rb b/lib/sisu/v0/dal_metadata.rb index 2555829d..bdf0dace 100644 --- a/lib/sisu/v0/dal_metadata.rb +++ b/lib/sisu/v0/dal_metadata.rb @@ -142,7 +142,7 @@ module SiSU_metadata "\n#{@tr.comments}: #{Mx[:fa_underscore_o]}#{@md.comments}#{Mx[:fa_underscore_c]} #{Mx[:id_o]}~0;m#{ocnm};d#{ocnd}#{Mx[:id_c]}" when /^#{Mx[:meta_o]}cls_loc#{Mx[:meta_c]}/ "\n#{@cls_dewey}: #{Mx[:fa_underscore_o]}#{@md.cls_dewey}#{Mx[:fa_underscore_c]} #{Mx[:id_o]}~0;m#{ocnm};d#{ocnd}#{Mx[:id_c]}" - when /^#{Mx[:meta_o]}cls_dewey#{Mx[:meta_c]}/ + when /^#{Mx[:meta_o]}cls_loc#{Mx[:meta_c]}/ "\n#{@tr.cls_dewey}: #{Mx[:fa_underscore_o]}#{@md.cls_dewey}#{Mx[:fa_underscore_c]} #{Mx[:id_o]}~0;m#{ocnm};d#{ocnd}#{Mx[:id_c]}" when /^#{Mx[:meta_o]}(?:cls_gutenberg|cls_pg)#{Mx[:meta_c]}/ "\n#{@tr.cls_gutenberg}: #{Mx[:fa_underscore_o]}#{@md.cls_gutenberg}#{Mx[:fa_underscore_c]} #{Mx[:id_o]}~0;m#{ocnm};d#{ocnd}#{Mx[:id_c]}" diff --git a/lib/sisu/v0/harvest.rb b/lib/sisu/v0/harvest.rb index 8f262ac8..1e390c50 100644 --- a/lib/sisu/v0/harvest.rb +++ b/lib/sisu/v0/harvest.rb @@ -24,7 +24,7 @@ This program is distributed in the hope that it will be useful, but WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for + FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for more details. You should have received a copy of the GNU General Public License along with @@ -87,8 +87,6 @@ def cases(opt) help end end -branch='v0' -SiSU_lib="sisu/#{branch}" require "#{SiSU_lib}/options" require "#{SiSU_lib}/harvest_topics" require "#{SiSU_lib}/harvest_authors" diff --git a/lib/sisu/v0/odf.rb b/lib/sisu/v0/odf.rb index 62dd1f48..e4873a10 100644 --- a/lib/sisu/v0/odf.rb +++ b/lib/sisu/v0/odf.rb @@ -362,7 +362,6 @@ module SiSU_ODF end end def odf_structure(md,t_o) - @md,@t_o=md,t_o @md,@t_o=md,t_o if t_o.class == Hash para =t_o[:txt] || nil diff --git a/lib/sisu/v0/shared_html_lite.rb b/lib/sisu/v0/shared_html_lite.rb index d1e312e1..7fe77e0b 100644 --- a/lib/sisu/v0/shared_html_lite.rb +++ b/lib/sisu/v0/shared_html_lite.rb @@ -22,7 +22,7 @@ This program is distributed in the hope that it will be useful, but WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for + FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for more details. You should have received a copy of the GNU General Public License along with @@ -65,7 +65,7 @@ module SiSU_Format_Shared @@fns=nil def initialize(md,t_o) @md,@t_o=md,t_o - if t_o.class == Hash + if t_o.class==Hash @txt =t_o[:txt] #|| nil #s/@content/@txt/ @col =t_o[:col] #|| nil @notenumber =t_o[:endnote_nr] || nil @@ -79,9 +79,8 @@ module SiSU_Format_Shared p t_o.class p caller end - @txt.gsub!(/#{Mx[:pa_o]}:i[1-9]#{Mx[:pa_c]}/,'') - @id=@ocn=@col[:id] + @id=@ocn=@col[:ocn] @ocnd,@ocns=@col[:ocnd],@col[:ocns] @lv=@col[:lev].to_s @@hname=if @md.fns != @@fns diff --git a/lib/sisu/v0/xml_dom.rb b/lib/sisu/v0/xml_dom.rb index 7e1945b8..5145be98 100644 --- a/lib/sisu/v0/xml_dom.rb +++ b/lib/sisu/v0/xml_dom.rb @@ -356,7 +356,7 @@ WOK end if @rcdc==false \ and (para =~/~metadata/ \ - or para =~/#{Mx[:lv_o]}1:meta#{Mx[:lv_x]}\s*Document Information/) + or para =~/#{Mx[:lv_o]}1:meta#{Mx[:lv_c]}\s*Document Information/) @rcdc=true end if para !~/(^#{Rx[:meta]}|#{Mx[:br_eof]}|#{Mx[:br_endnotes]})/ -- cgit v1.2.3 From 0cdd579c809f3041df8842adb4d6f74d9cabd457 Mon Sep 17 00:00:00 2001 From: Ralph Amissah Date: Wed, 1 Jul 2009 13:45:51 -0400 Subject: db dbi, interfaces to sqlite and pgsql, fixes, pass individual sql statements --- lib/sisu/v0/db_create.rb | 527 ++++++++++++++++++++++--------------------- lib/sisu/v0/db_import.rb | 129 ++++++----- lib/sisu/v0/db_indexes.rb | 61 ++--- lib/sisu/v0/db_load_tuple.rb | 67 +++--- lib/sisu/v0/db_remove.rb | 7 +- 5 files changed, 410 insertions(+), 381 deletions(-) (limited to 'lib') diff --git a/lib/sisu/v0/db_create.rb b/lib/sisu/v0/db_create.rb index 9f6ae360..2cdb2c06 100644 --- a/lib/sisu/v0/db_create.rb +++ b/lib/sisu/v0/db_create.rb @@ -22,7 +22,7 @@ This program is distributed in the hope that it will be useful, but WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for + FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for more details. You should have received a copy of the GNU General Public License along with @@ -65,7 +65,7 @@ module SiSU_DB_create def initialize(opt,conn,file,sql_type='pg') @opt,@conn,@file,@sql_type=opt,conn,file,sql_type @cX=SiSU_Screen::Ansi.new(@opt.cmd).cX - @comment=Comment.new(@sql_type) + @comment=Comment.new(@conn,@sql_type) @@dl ||=SiSU_Env::Info_env.new.digest.length end def available @@ -167,8 +167,8 @@ module SiSU_DB_create writing_focus_nationality VARCHAR(#{lt_writing_focus_nationality}) NULL, topic_register VARCHAR(#{lt_topic_register}) NULL ); - #{@comment.metadata} - }) + }) + @comment.metadata end def documents # create documents base print %{ @@ -203,8 +203,8 @@ module SiSU_DB_create digest_all CHAR(#{@@dl}), types CHAR(1) NULL ); - #{@comment.documents} - }) + }) + @comment.documents end def endnotes print %{ @@ -225,8 +225,8 @@ module SiSU_DB_create digest_clean CHAR(#{@@dl}), metadata_tid BIGINT REFERENCES metadata ); - #{@comment.endnotes} - }) + }) + @comment.endnotes end def endnotes_asterisk print %{ @@ -247,8 +247,8 @@ module SiSU_DB_create digest_clean CHAR(#{@@dl}), metadata_tid BIGINT REFERENCES metadata ); - #{@comment.endnotes_asterisk} - }) + }) + @comment.endnotes_asterisk end def endnotes_plus print %{ @@ -269,8 +269,8 @@ module SiSU_DB_create digest_clean CHAR(#{@@dl}), metadata_tid BIGINT REFERENCES metadata ); - #{@comment.endnotes_plus} - }) + }) + @comment.endnotes_plus end def urls # create documents file links mapping print %{ @@ -299,276 +299,281 @@ module SiSU_DB_create markup varchar(512), sisupod varchar(512) ); - #{@comment.urls} - }) + }) + @comment.urls end self end end class Comment - def initialize(sql_type='pg') + def initialize(conn,sql_type='pg') + @conn=conn if sql_type =~ /pg/; psql else none end end def psql + def conn_execute_array(sql_arr) + @conn.transaction do |conn| + sql_arr.each do |sql| + conn.execute(sql) + end + end + end + #def conn_execute_array(sql_arr) + # sql_arr.each do |sql| + # @conn.execute(sql) + # end + #end def metadata - %{ - COMMENT ON Table metadata - IS 'contains SiSU documents metadata with metadata'; - COMMENT ON COLUMN metadata.tid - IS 'unique'; - COMMENT ON COLUMN metadata.filename - IS 'document filename'; - COMMENT ON COLUMN metadata.title - IS 'metadata title (dublin core element 1)'; - COMMENT ON COLUMN metadata.subtitle - IS 'document subtitle'; - COMMENT ON COLUMN metadata.creator - IS 'metadata creator (dublin core element 2)'; - COMMENT ON COLUMN metadata.author - IS 'metadata author (dublin core element 2)'; - COMMENT ON COLUMN metadata.illustrator - IS 'metadata illustrator'; - COMMENT ON COLUMN metadata.translator - IS 'metadata translator'; - COMMENT ON COLUMN metadata.subject - IS 'metadata subject (dublin core element 3)'; - COMMENT ON COLUMN metadata.date - IS 'metadata date (dublin core element 7)'; - COMMENT ON COLUMN metadata.date_created - IS 'metadata date created (dublin core)'; - COMMENT ON COLUMN metadata.date_issued - IS 'metadata date of issue (dublin core)'; - COMMENT ON COLUMN metadata.date_available - IS 'metadata date available (dublin core)'; - COMMENT ON COLUMN metadata.date_valid - IS 'metadata date valid (dublin core)'; - COMMENT ON COLUMN metadata.date_modified - IS 'metadata date modified (dublin core)'; - COMMENT ON COLUMN metadata.type - IS 'metadata type (dublin core element 8)'; - COMMENT ON COLUMN metadata.description - IS 'metadata description (dublin core element 4)'; - COMMENT ON COLUMN metadata.publisher - IS 'metadata publisher (dublin core element 5)'; - COMMENT ON COLUMN metadata.contributor - IS 'metadata contributor (dublin core element 6)'; - COMMENT ON COLUMN metadata.prepared_by - IS 'metadata markup prepared by'; - COMMENT ON COLUMN metadata.digitized_by - IS 'metadata digitized by'; - COMMENT ON COLUMN metadata.format - IS 'metadata format (dublin core element 9)'; - COMMENT ON COLUMN metadata.identifier - IS 'metadata identifier (dublin core element 10)'; - COMMENT ON COLUMN metadata.source - IS 'metadata source (dublin core element 11)'; - COMMENT ON COLUMN metadata.language - IS 'metadata language (dublin core element 12)'; - COMMENT ON COLUMN metadata.language_original - IS 'metadata original language'; - COMMENT ON COLUMN metadata.relation - IS 'metadata (dublin core element 13)'; - COMMENT ON COLUMN metadata.coverage - IS 'metadata coverage (dublin core element 14)'; - COMMENT ON COLUMN metadata.rights - IS 'metadata rights / copyright / license (dublin core element 15)'; - COMMENT ON COLUMN metadata.owner - IS 'metadata owner'; - COMMENT ON COLUMN metadata.keywords - IS 'metadata keywords'; - COMMENT ON COLUMN metadata.comment - IS 'metadata comment'; - COMMENT ON COLUMN metadata.abstract - IS 'metadata abstract'; - COMMENT ON COLUMN metadata.loc - IS 'metadata library of congress'; - COMMENT ON COLUMN metadata.dewey - IS 'metadata dewey'; - COMMENT ON COLUMN metadata.isbn - IS 'metadata isbn'; - COMMENT ON COLUMN metadata.pg - IS 'metadata project gutenberg number'; - COMMENT ON COLUMN metadata.prefix_a - IS 'metadata prefix'; - COMMENT ON COLUMN metadata.prefix_b - IS 'metadata prefix'; - COMMENT ON COLUMN metadata.skin - IS 'metadata sisu skin'; - COMMENT ON COLUMN metadata.markup - IS 'metadata markup source'; - COMMENT ON COLUMN metadata.links - IS 'metadata links'; - COMMENT ON COLUMN metadata.information - IS 'metadata information'; - COMMENT ON COLUMN metadata.contact - IS 'metadata contact'; - COMMENT ON COLUMN metadata.suffix - IS 'metadata sisu suffix (output related)'; - COMMENT ON COLUMN metadata.filename - IS 'metadata source filename'; - COMMENT ON COLUMN metadata.types - IS 'document types scroll 1, seg 2, both 3'; - COMMENT ON COLUMN metadata.subj - IS 'subject areas - no way to populate at present as not mapped'; -/* - CREATE FUNCTION fileremoval() RETURNS opaque AS ' - BEGIN - DELETE FROM metadata WHERE tid=#@removetid; - DELETE FROM documents WHERE documents.metadata_tid=#@removetid; - DELETE FROM endnotes WHERE endnotes.metadata_tid=#@removetid; - DELETE FROM endnotes_asterisk WHERE endnotes_asterisk.metadata_tid=#@removetid; - DELETE FROM endnotes_plus WHERE endnotes_plus.metadata_tid=#@removetid; - DELETE FROM urls WHERE urls.metadata_tid=#@removetid; - END; - ' LANGUAGE 'plpgsql'; - CREATE TRIGGER removefile AFTER INSERT - PROCEDURE fileremoval(); -*/ - } + sql_arr=[ + %{COMMENT ON Table metadata + IS 'contains SiSU documents metadata with metadata';}, + %{COMMENT ON COLUMN metadata.tid + IS 'unique';}, + %{COMMENT ON COLUMN metadata.filename + IS 'document filename';}, + %{COMMENT ON COLUMN metadata.title + IS 'metadata title (dublin core element 1)';}, + %{COMMENT ON COLUMN metadata.subtitle + IS 'document subtitle';}, + %{COMMENT ON COLUMN metadata.creator + IS 'metadata creator (dublin core element 2)';}, + %{COMMENT ON COLUMN metadata.author + IS 'metadata author (dublin core element 2)';}, + %{COMMENT ON COLUMN metadata.illustrator + IS 'metadata illustrator';}, + %{COMMENT ON COLUMN metadata.translator + IS 'metadata translator';}, + %{COMMENT ON COLUMN metadata.subject + IS 'metadata subject (dublin core element 3)';}, + %{COMMENT ON COLUMN metadata.date + IS 'metadata date (dublin core element 7)';}, + %{COMMENT ON COLUMN metadata.date_created + IS 'metadata date created (dublin core)';}, + %{COMMENT ON COLUMN metadata.date_issued + IS 'metadata date of issue (dublin core)';}, + %{COMMENT ON COLUMN metadata.date_available + IS 'metadata date available (dublin core)';}, + %{COMMENT ON COLUMN metadata.date_valid + IS 'metadata date valid (dublin core)';}, + %{COMMENT ON COLUMN metadata.date_modified + IS 'metadata date modified (dublin core)';}, + %{COMMENT ON COLUMN metadata.type + IS 'metadata type (dublin core element 8)';}, + %{COMMENT ON COLUMN metadata.description + IS 'metadata description (dublin core element 4)';}, + %{COMMENT ON COLUMN metadata.publisher + IS 'metadata publisher (dublin core element 5)';}, + %{COMMENT ON COLUMN metadata.contributor + IS 'metadata contributor (dublin core element 6)';}, + %{COMMENT ON COLUMN metadata.prepared_by + IS 'metadata markup prepared by';}, + %{COMMENT ON COLUMN metadata.digitized_by + IS 'metadata digitized by';}, + %{COMMENT ON COLUMN metadata.format + IS 'metadata format (dublin core element 9)';}, + %{COMMENT ON COLUMN metadata.identifier + IS 'metadata identifier (dublin core element 10)';}, + %{COMMENT ON COLUMN metadata.source + IS 'metadata source (dublin core element 11)';}, + %{COMMENT ON COLUMN metadata.language + IS 'metadata language (dublin core element 12)';}, + %{COMMENT ON COLUMN metadata.language_original + IS 'metadata original language';}, + %{COMMENT ON COLUMN metadata.relation + IS 'metadata (dublin core element 13)';}, + %{COMMENT ON COLUMN metadata.coverage + IS 'metadata coverage (dublin core element 14)';}, + %{COMMENT ON COLUMN metadata.rights + IS 'metadata rights / copyright / license (dublin core element 15)';}, + %{COMMENT ON COLUMN metadata.owner + IS 'metadata owner';}, + %{COMMENT ON COLUMN metadata.keywords + IS 'metadata keywords';}, + %{COMMENT ON COLUMN metadata.comment + IS 'metadata comment';}, + %{COMMENT ON COLUMN metadata.abstract + IS 'metadata abstract';}, + %{COMMENT ON COLUMN metadata.loc + IS 'metadata library of congress';}, + %{COMMENT ON COLUMN metadata.dewey + IS 'metadata dewey';}, + %{COMMENT ON COLUMN metadata.isbn + IS 'metadata isbn';}, + %{COMMENT ON COLUMN metadata.pg + IS 'metadata project gutenberg number';}, + %{COMMENT ON COLUMN metadata.prefix_a + IS 'metadata prefix';}, + %{COMMENT ON COLUMN metadata.prefix_b + IS 'metadata prefix';}, + %{COMMENT ON COLUMN metadata.skin + IS 'metadata sisu skin';}, + %{COMMENT ON COLUMN metadata.markup + IS 'metadata markup source';}, + %{COMMENT ON COLUMN metadata.links + IS 'metadata links';}, + %{COMMENT ON COLUMN metadata.information + IS 'metadata information';}, + %{COMMENT ON COLUMN metadata.contact + IS 'metadata contact';}, + %{COMMENT ON COLUMN metadata.suffix + IS 'metadata sisu suffix (output related)';}, + %{COMMENT ON COLUMN metadata.filename + IS 'metadata source filename';}, + %{COMMENT ON COLUMN metadata.types + IS 'document types scroll 1, seg 2, both 3';}, + %{COMMENT ON COLUMN metadata.subj + IS 'subject areas - no way to populate at present as not mapped';}, + ] + conn_execute_array(sql_arr) end def documents - %{ - COMMENT ON Table documents - IS 'contains searchable text of SiSU documents'; - COMMENT ON COLUMN documents.lid - IS 'unique'; - COMMENT ON COLUMN documents.metadata_tid - IS 'tie to title in metadata'; - COMMENT ON COLUMN documents.lev - IS 'doc level 1-6 \d\~'; - COMMENT ON COLUMN documents.seg - IS 'segment name from level 4'; - COMMENT ON COLUMN documents.ocn - IS 'object citation number'; - COMMENT ON COLUMN documents.en_a - IS 'first endnote number in text object (eg. NULL or 34) (used with en_z to create range)'; - COMMENT ON COLUMN documents.en_z - IS 'last endnote number within text object (eg. NULL, 34 or say 47) (used with en_a to create range)'; - COMMENT ON COLUMN documents.en_a_asterisk - IS 'first endnote number in text object (eg. NULL or 34) (used with en_z_asterisk to create range)'; - COMMENT ON COLUMN documents.en_z_asterisk - IS 'last endnote number within text object (eg. NULL, 34 or say 47) (used with en_a_asterisk to create range)'; - COMMENT ON COLUMN documents.en_a_plus - IS 'first endnote number in text object (eg. NULL or 34) (used with en_z_plus to create range)'; - COMMENT ON COLUMN documents.en_z_plus - IS 'last endnote number within text object (eg. NULL, 34 or say 47) (used with en_a_plus to create range)'; - COMMENT ON COLUMN documents.types - IS 'document types seg scroll'; - COMMENT ON COLUMN documents.clean - IS 'text object - substantive text: clean, stripped of markup'; - COMMENT ON COLUMN documents.body - IS 'text object - substantive text: light html markup'; - COMMENT ON COLUMN documents.lev1 - IS 'document structure, level 1'; - COMMENT ON COLUMN documents.lev2 - IS 'document structure, level 2'; - COMMENT ON COLUMN documents.lev3 - IS 'document structure, level 3'; - COMMENT ON COLUMN documents.lev4 - IS 'document structure, level 4'; - COMMENT ON COLUMN documents.lev5 - IS 'document structure, level 5'; - COMMENT ON COLUMN documents.lev6 - IS 'document structure, level 6'; - } + sql_arr=[ + %{COMMENT ON Table documents + IS 'contains searchable text of SiSU documents';}, + %{COMMENT ON COLUMN documents.lid + IS 'unique';}, + %{COMMENT ON COLUMN documents.metadata_tid + IS 'tie to title in metadata';}, + %{COMMENT ON COLUMN documents.lev + IS 'doc level 1-6 \d\~';}, + %{COMMENT ON COLUMN documents.seg + IS 'segment name from level 4';}, + %{COMMENT ON COLUMN documents.ocn + IS 'object citation number';}, + %{COMMENT ON COLUMN documents.en_a + IS 'first endnote number in text object (eg. NULL or 34) (used with en_z to create range)';}, + %{COMMENT ON COLUMN documents.en_z + IS 'last endnote number within text object (eg. NULL, 34 or say 47) (used with en_a to create range)';}, + %{COMMENT ON COLUMN documents.en_a_asterisk + IS 'first endnote number in text object (eg. NULL or 34) (used with en_z_asterisk to create range)';}, + %{COMMENT ON COLUMN documents.en_z_asterisk + IS 'last endnote number within text object (eg. NULL, 34 or say 47) (used with en_a_asterisk to create range)';}, + %{COMMENT ON COLUMN documents.en_a_plus + IS 'first endnote number in text object (eg. NULL or 34) (used with en_z_plus to create range)';}, + %{COMMENT ON COLUMN documents.en_z_plus + IS 'last endnote number within text object (eg. NULL, 34 or say 47) (used with en_a_plus to create range)';}, + %{COMMENT ON COLUMN documents.types + IS 'document types seg scroll';}, + %{COMMENT ON COLUMN documents.clean + IS 'text object - substantive text: clean, stripped of markup';}, + %{COMMENT ON COLUMN documents.body + IS 'text object - substantive text: light html markup';}, + %{COMMENT ON COLUMN documents.lev1 + IS 'document structure, level 1';}, + %{COMMENT ON COLUMN documents.lev2 + IS 'document structure, level 2';}, + %{COMMENT ON COLUMN documents.lev3 + IS 'document structure, level 3';}, + %{COMMENT ON COLUMN documents.lev4 + IS 'document structure, level 4';}, + %{COMMENT ON COLUMN documents.lev5 + IS 'document structure, level 5';}, + %{COMMENT ON COLUMN documents.lev6 + IS 'document structure, level 6';} + ] + conn_execute_array(sql_arr) end def endnotes - %{ - COMMENT ON Table endnotes - IS 'contains searchable text of SiSU documents endnotes'; - COMMENT ON COLUMN endnotes.nid - IS 'unique'; - COMMENT ON COLUMN endnotes.document_lid - IS 'ties to text block from which referenced'; - COMMENT ON COLUMN endnotes.nr - IS 'endnote number '; - COMMENT ON COLUMN endnotes.clean - IS 'endnote substantive content, stripped of markup'; - COMMENT ON COLUMN endnotes.body - IS 'endnote substantive content'; - COMMENT ON COLUMN endnotes.ocn - IS 'object citation no# <\~(\d+)> from which endnote is referenced'; - COMMENT ON COLUMN documents.metadata_tid - IS 'tie to title in metadata - unique for each document'; - } + sql_arr=[ + %{COMMENT ON Table endnotes + IS 'contains searchable text of SiSU documents endnotes';}, + %{COMMENT ON COLUMN endnotes.nid + IS 'unique';}, + %{COMMENT ON COLUMN endnotes.document_lid + IS 'ties to text block from which referenced';}, + %{COMMENT ON COLUMN endnotes.nr + IS 'endnote number ';}, + %{COMMENT ON COLUMN endnotes.clean + IS 'endnote substantive content, stripped of markup';}, + %{COMMENT ON COLUMN endnotes.body + IS 'endnote substantive content';}, + %{COMMENT ON COLUMN endnotes.ocn + IS 'object citation no# <\~(\d+)> from which endnote is referenced';}, + %{COMMENT ON COLUMN documents.metadata_tid + IS 'tie to title in metadata - unique for each document';} + ] + conn_execute_array(sql_arr) end def endnotes_asterisk - %{ - COMMENT ON Table endnotes_asterisk - IS 'contains searchable text of SiSU documents endnotes asterisk'; - COMMENT ON COLUMN endnotes_asterisk.nid - IS 'unique'; - COMMENT ON COLUMN endnotes_asterisk.document_lid - IS 'ties to text block from which referenced'; - COMMENT ON COLUMN endnotes_asterisk.nr - IS 'endnote number '; - COMMENT ON COLUMN endnotes_asterisk.clean - IS 'endnote substantive content, stripped of markup'; - COMMENT ON COLUMN endnotes_asterisk.body - IS 'endnote substantive content'; - COMMENT ON COLUMN endnotes_asterisk.ocn - IS 'object citation no# <\~(\d+)> from which endnote is referenced'; - COMMENT ON COLUMN documents.metadata_tid - IS 'tie to title in metadata - unique for each document'; - } + sql_arr=[ + %{COMMENT ON Table endnotes_asterisk + IS 'contains searchable text of SiSU documents endnotes asterisk';}, + %{COMMENT ON COLUMN endnotes_asterisk.nid + IS 'unique';}, + %{COMMENT ON COLUMN endnotes_asterisk.document_lid + IS 'ties to text block from which referenced';}, + %{COMMENT ON COLUMN endnotes_asterisk.nr + IS 'endnote number ';}, + %{COMMENT ON COLUMN endnotes_asterisk.clean + IS 'endnote substantive content, stripped of markup';}, + %{COMMENT ON COLUMN endnotes_asterisk.body + IS 'endnote substantive content';}, + %{COMMENT ON COLUMN endnotes_asterisk.ocn + IS 'object citation no# <\~(\d+)> from which endnote is referenced';}, + %{COMMENT ON COLUMN documents.metadata_tid + IS 'tie to title in metadata - unique for each document';} + ] + conn_execute_array(sql_arr) end def endnotes_plus - %{ - COMMENT ON Table endnotes_plus - IS 'contains searchable text of SiSU documents endnotes'; - COMMENT ON COLUMN endnotes_plus.nid - IS 'unique'; - COMMENT ON COLUMN endnotes_plus.document_lid - IS 'ties to text block from which referenced'; - COMMENT ON COLUMN endnotes_plus.nr - IS 'endnote number '; - COMMENT ON COLUMN endnotes_plus.clean - IS 'endnote substantive content, stripped of markup'; - COMMENT ON COLUMN endnotes_plus.body - IS 'endnote substantive content'; - COMMENT ON COLUMN endnotes_plus.ocn - IS 'object citation no# <\~(\d+)> from which endnote is referenced'; - COMMENT ON COLUMN documents.metadata_tid - IS 'tie to title in metadata - unique for each document'; - } + sql_arr=[ + %{COMMENT ON Table endnotes_plus + IS 'contains searchable text of SiSU documents endnotes';}, + %{COMMENT ON COLUMN endnotes_plus.nid + IS 'unique';}, + %{COMMENT ON COLUMN endnotes_plus.document_lid + IS 'ties to text block from which referenced';}, + %{COMMENT ON COLUMN endnotes_plus.nr + IS 'endnote number ';}, + %{COMMENT ON COLUMN endnotes_plus.clean + IS 'endnote substantive content, stripped of markup';}, + %{COMMENT ON COLUMN endnotes_plus.body + IS 'endnote substantive content';}, + %{COMMENT ON COLUMN endnotes_plus.ocn + IS 'object citation no# <\~(\d+)> from which endnote is referenced';}, + %{COMMENT ON COLUMN documents.metadata_tid + IS 'tie to title in metadata - unique for each document';}, + ] + conn_execute_array(sql_arr) end def urls - %{ - COMMENT ON Table urls - IS 'contains base url links to different SiSU output'; - COMMENT ON COLUMN documents.metadata_tid - IS 'tie to title in metadata - unique for each document, the mapping of rows is one to one'; - COMMENT ON COLUMN urls.plaintext - IS 'plaintext utf-8'; - COMMENT ON COLUMN urls.html_toc - IS 'table of contents for segmented html document'; - COMMENT ON COLUMN urls.html_doc - IS 'html document (scroll)'; - COMMENT ON COLUMN urls.xhtml - IS 'xhtml document (scroll)'; - COMMENT ON COLUMN urls.xml_sax - IS 'xml sax oriented document (scroll)'; - COMMENT ON COLUMN urls.xml_dom - IS 'xml dom oriented document (scroll)'; - COMMENT ON COLUMN urls.odf - IS 'opendocument format text'; - COMMENT ON COLUMN urls.pdf_p - IS 'pdf portrait'; - COMMENT ON COLUMN urls.pdf_l - IS 'pdf landscape'; - COMMENT ON COLUMN urls.concordance - IS 'rudimentary document index linked to html'; - COMMENT ON COLUMN urls.latex_p - IS 'latex portrait'; - COMMENT ON COLUMN urls.latex_l - IS 'latex_landscape'; - COMMENT ON COLUMN urls.markup - IS 'markup'; - COMMENT ON COLUMN urls.sisupod - IS 'SiSU document format .tgz (all SiSU information on document)'; - } + sql_arr=[ + %{COMMENT ON Table urls + IS 'contains base url links to different SiSU output';}, + %{COMMENT ON COLUMN documents.metadata_tid + IS 'tie to title in metadata - unique for each document, the mapping of rows is one to one';}, + %{COMMENT ON COLUMN urls.plaintext + IS 'plaintext utf-8';}, + %{COMMENT ON COLUMN urls.html_toc + IS 'table of contents for segmented html document';}, + %{COMMENT ON COLUMN urls.html_doc + IS 'html document (scroll)';}, + %{COMMENT ON COLUMN urls.xhtml + IS 'xhtml document (scroll)';}, + %{COMMENT ON COLUMN urls.xml_sax + IS 'xml sax oriented document (scroll)';}, + %{COMMENT ON COLUMN urls.xml_dom + IS 'xml dom oriented document (scroll)';}, + %{COMMENT ON COLUMN urls.odf + IS 'opendocument format text';}, + %{COMMENT ON COLUMN urls.pdf_p + IS 'pdf portrait';}, + %{COMMENT ON COLUMN urls.pdf_l + IS 'pdf landscape';}, + %{COMMENT ON COLUMN urls.concordance + IS 'rudimentary document index linked to html';}, + %{COMMENT ON COLUMN urls.latex_p + IS 'latex portrait';}, + %{COMMENT ON COLUMN urls.latex_l + IS 'latex_landscape';}, + %{COMMENT ON COLUMN urls.markup + IS 'markup';}, + %{COMMENT ON COLUMN urls.sisupod + IS 'SiSU document format .tgz (all SiSU information on document)';}, + ] + conn_execute_array(sql_arr) end self end diff --git a/lib/sisu/v0/db_import.rb b/lib/sisu/v0/db_import.rb index 5810f13f..da564639 100644 --- a/lib/sisu/v0/db_import.rb +++ b/lib/sisu/v0/db_import.rb @@ -1,4 +1,4 @@ -# coding: utf-8 +#j coding: utf-8 =begin * Name: SiSU @@ -22,7 +22,7 @@ This program is distributed in the hope that it will be useful, but WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for + FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for more details. You should have received a copy of the GNU General Public License along with @@ -95,9 +95,9 @@ module SiSU_DB_import else @conn.execute( sql ) { |x| x.fetch_all.to_s.to_i } end rescue - puts "#{__FILE__} #{__LINE__}" if @opt.cmd =~/M/ + puts "#{__FILE__}:#{__LINE__}" if @opt.cmd =~/M/ end - @col[:lid] =0 if @col[:lid].nil? or @col[:lid].to_s.empty? + @col[:lid]=0 if @col[:lid].nil? or @col[:lid].to_s.empty? sql='SELECT MAX(nid) FROM endnotes' begin @id_n ||=0 @@ -107,7 +107,7 @@ module SiSU_DB_import @id_n=@conn.execute( sql ) { |x| x.fetch_all.to_s.to_i } end rescue - puts "#{__FILE__} #{__LINE__}" if @opt.cmd =~/M/ + puts "#{__FILE__}:#{__LINE__}" if @opt.cmd =~/M/ end @id_n =0 if @col[:lid].nil? or @col[:lid].to_s.empty? @col[:lv1]=@col[:lv2]=@col[:lv3]=@col[:lv4]=@col[:lv5]=@col[:lv6]=0 @@ -121,59 +121,66 @@ module SiSU_DB_import tell.puts_blue unless @opt.cmd =~/q/ tell=SiSU_Screen::Ansi.new(@opt.cmd,'Marshal Load',@fnm) tell.print_grey if @opt.cmd =~/v/ - case @sql_type - when /sqlite/ #fix logic for sqlite ! - #sqlite watch - #pf_db_import_transaction_open if @opt =~/M/ - db_import_metadata - db_import_documents(@dal_array) - db_import_urls(@dal_array,@fnm) #import OID on/off - #pf_db_import_transaction_close if @opt =~/M/ - #@conn.commit - #@conn.close - #@conn.disconnect - if @opt.cmd =~/M/ + file_exist=if @sql_type=~/sqlite/; nil + else + @conn.select_one(%{ SELECT metadata.tid FROM metadata WHERE metadata.filename ~ '#{@opt.fns}'; }) + end + if (@sql_type!~/sqlite/ and not file_exist) \ + or @sql_type=~/sqlite/ + t_d=[] # transaction_data + t_d << db_import_metadata + t_d << db_import_documents(@dal_array) + t_d << db_import_urls(@dal_array,@fnc) #import OID on/off + t_d=t_d.flatten + if @opt.cmd =~/[MV]/ + puts @conn.class if defined? @conn.class + puts @conn.driver_name if defined? @conn.driver_name + puts @conn.driver if defined? @conn.driver + end + begin + @conn.transaction do |conn| + t_d.each do |sql| + conn.execute(sql) + end + end + rescue + SiSU_Errors::Info_error.new($!,$@,@opt.cmd,@opt.fns).error + puts "#{__FILE__}:#{__LINE__}" if @opt.cmd =~/M/ + ensure + #@conn.execute("COMMIT") + end + if @sql_type=~/sqlite/ \ + and @opt.cmd =~/[MV]/ puts "\n" + @conn.inspect - puts "\nat #{__FILE__} #{__LINE__}" + puts "\nat #{__FILE__}:#{__LINE__}" end else - file_exist=@conn.select_one(%{ SELECT metadata.tid FROM metadata WHERE metadata.filename ~ '#{@opt.fns}'; }) - unless file_exist - @conn.execute('BEGIN') - db_import_metadata - db_import_documents(@dal_array) - db_import_urls(@dal_array,@fnm) #import OID on/off - @conn.execute('COMMIT') - if @opt.cmd =~/[MV]/ - puts "\n" + @conn.inspect - puts "\nat #{__FILE__} #{__LINE__}" - end - else + if file_exist @db=SiSU_Env::Info_db.new puts "\n#{@cX.grey}file #{@cX.off} #{@cX.blue}#{@opt.fns}#{@cX.off} #{@cX.grey}already exists in database#{@cX.off} #{@cX.blue}#{@db.psql.db}#{@cX.off} #{@cX.brown}update instead?#{@cX.off}" end end end - def special_character_escape(string) - string.gsub!(/'/,"''") #string.gsub!(/'/,"\047") #string.gsub!(/'/,"\\'") - string.gsub!(/#{Mx[:br_line]}|#{Mx[:br_nl]}/,"
\n") - string.gsub!(/#{Mx[:gr_o]}(?:code|alt|group|verse)(?:-end)?#{Mx[:gr_c]}/,'') - string.gsub!(/#{Mx[:mk_o]}:name#\S+?#{Mx[:mk_c]}/,'') - string.gsub!(/#{Mx[:lnk_o]}\s*(\S+?\.(?:png|jpg))(?:\s+\d+x\d+)?(.+?)#{Mx[:lnk_c]}\S+/,'[image: \1] \2') - string.gsub!(/#{Mx[:lnk_o]}\s*(.+?)\s*#{Mx[:lnk_c]}(?:https?|file|ftp):\/\/\S+?([.,!?]?(?:\s|$))/,'\1\2') + def special_character_escape(str) + str.gsub!(/'/,"''") #string.gsub!(/'/,"\047") #string.gsub!(/'/,"\\'") + str.gsub!(/#{Mx[:br_line]}|#{Mx[:br_nl]}/,"
\n") + str.gsub!(/#{Mx[:gr_o]}(?:code|alt|group|verse)(?:-end)?#{Mx[:gr_c]}/,'') + str.gsub!(/#{Mx[:mk_o]}:name#\S+?#{Mx[:mk_c]}/,'') + str.gsub!(/#{Mx[:lnk_o]}\s*(\S+?\.(?:png|jpg))(?:\s+\d+x\d+)?(.+?)#{Mx[:lnk_c]}\S+/,'[image: \1] \2') + str.gsub!(/#{Mx[:lnk_o]}\s*(.+?)\s*#{Mx[:lnk_c]}(?:https?|file|ftp):\/\/\S+?([.,!?]?(?:\s|$))/,'\1\2') end - def strip_markup(string) #define rules, make same as in dal clean - string.gsub!(/#{Mx[:fa_superscript_o]}(\d+)#{Mx[:fa_superscript_c]}/,'[\1]') - string.gsub!(/#{Mx[:pa_o]}:i[1-9]#{Mx[:pa_c]}/,'') - string.gsub!(/(?: \\;|#{Mx[:nbsp]})+/,' ') - string.gsub!(/#{Mx[:gr_o]}T[h]?#{Mx[:tc_p]}.+?#{Mx[:gr_c]}/u,"[TABLE]\n") #tables #CHECK should take whole table - string.gsub!(/#{Mx[:tc_o]}#{Mx[:tc_p]}#{Mx[:tc_p]}\d+(.+)#{Mx[:tc_c]}/u,'\1') #tables - string.gsub!(/#{Mx[:tc_p]}#{Mx[:tc_p]}\d+#{Mx[:tc_p]}/u,' ') #tables - string.gsub!(/#{Mx[:tc_p]}/u,' ') #tables tidy later - string.gsub!(/<.+?>/,'') - string.gsub!(/#{Mx[:lnk_o]}.+?\.(?:png|jpg|gif).+?#{Mx[:lnk_c]}(?:https?|file|ftp)\\\:\S+ /,' [image] ') # else image names found in search - string.gsub!(/\s\s+/,' ') - string.strip! + def strip_markup(str) #define rules, make same as in dal clean + str.gsub!(/#{Mx[:fa_superscript_o]}(\d+)#{Mx[:fa_superscript_c]}/,'[\1]') + str.gsub!(/#{Mx[:pa_o]}:i[1-9]#{Mx[:pa_c]}/,'') + str.gsub!(/(?: \\;|#{Mx[:nbsp]})+/,' ') + str.gsub!(/#{Mx[:gr_o]}T[h]?#{Mx[:tc_p]}.+?#{Mx[:gr_c]}/u,"[TABLE]\n") #tables #CHECK should take whole table + str.gsub!(/#{Mx[:tc_o]}#{Mx[:tc_p]}#{Mx[:tc_p]}\d+(.+)#{Mx[:tc_c]}/u,'\1') #tables + str.gsub!(/#{Mx[:tc_p]}#{Mx[:tc_p]}\d+#{Mx[:tc_p]}/u,' ') #tables + str.gsub!(/#{Mx[:tc_p]}/u,' ') #tables tidy later + str.gsub!(/<.+?>/,'') + str.gsub!(/#{Mx[:lnk_o]}.+?\.(?:png|jpg|gif).+?#{Mx[:lnk_c]}(?:https?|file|ftp)\\\:\S+ /,' [image] ') # else image names found in search + str.gsub!(/\s\s+/,' ') + str.strip! end #% import into database tables def pf_db_import_transaction_open @@ -386,7 +393,8 @@ module SiSU_DB_import #if @md.ruby_version; special_character_escape(@md.ruby_version) SiSU_DB_DBI::Test.new(self,@opt).verify #% import title names, filenames (tuple) t=SiSU_DB_tuple::Load_metadata.new(@conn,@tp,@@id_t,@opt,@file) - t.tuple + tuple=t.tuple + tuple end def db_import_documents(dal_array) #% import documents - populate main database table #% import into substantive database tables (tuple) @@ -395,6 +403,7 @@ module SiSU_DB_import @en,@en_ast,@en_pls=[],[],[] @col[:en_a]=nil @col[:en_z]=nil + @tuple_array=[] dal_array.each do |data| #data.gsub!(/<[biu]>(.+?)<\/[biu]>/,'\1') # remove bold, italics, underscore data.gsub!(/#{Mx[:fa_bold_o]}(.+?)#{Mx[:fa_bold_c]}/,'\1') @@ -436,7 +445,7 @@ module SiSU_DB_import if @en_pls[0]; @en_a_plus,@en_z_plus=@en_pls[0].first,@en_pls[0].last end t=SiSU_DB_tuple::Load_documents.new(@conn,@col,@opt,@file) - t.tuple + @tuple_array << t.tuple case @col[:lev] when /1/; @col[:lv1]+=1 when /2/; @col[:lv2]+=1 @@ -478,7 +487,7 @@ module SiSU_DB_import if @en_pls[0]; @en_a_plus,@en_z_plus=@en_pls[0].first,@en_pls[0].last end t=SiSU_DB_tuple::Load_documents.new(@conn,@col,@opt,@file) - t.tuple + @tuple_array << t.tuple @col[:lev]=@col[:plaintext]=@col[:body]='' elsif data[/^#{Mx[:lv_o]}5:\S*?#{Mx[:lv_c]}\s*(.+?)#{Mx[:id_o]}~(\d+);((?:\w|[0-6]:)\d+);(\w\d+)#{Mx[:id_c]}#{Mx[:id_o]}([0-9a-f]{#{@@dl}}):([0-9a-f]{#{@@dl}})#{Mx[:id_c]}/] # header lev5 seg level txt,@col[:ocn],@col[:ocnd],@col[:ocns],@col[:digest_clean],@col[:digest_all]=$1,$2,$3,$4,$5,$6 @@ -518,7 +527,7 @@ module SiSU_DB_import if @en_pls[0]; @en_a_plus,@en_z_plus=@en_pls[0].first,@en_pls[0].last end t=SiSU_DB_tuple::Load_documents.new(@conn,@col,@opt,@file) - t.tuple + @tuple_array << t.tuple @col[:lev]=@col[:plaintext]=@col[:body]='' elsif data[/^#{Mx[:lv_o]}6:\S*?#{Mx[:lv_c]}\s*(.+?)#{Mx[:id_o]}~(\d+);((?:\w|[0-6]:)\d+);(\w\d+)#{Mx[:id_c]}#{Mx[:id_o]}([0-9a-f]{#{@@dl}}):([0-9a-f]{#{@@dl}})#{Mx[:id_c]}/] # header lev6 seg level txt,@col[:ocn],@col[:ocnd],@col[:ocns],@col[:digest_clean],@col[:digest_all]=$1,$2,$3,$4,$5,$6 @@ -558,7 +567,7 @@ module SiSU_DB_import if @en_pls[0]; @en_a_plus,@en_z_plus=@en_pls[0].first,@en_pls[0].last end t=SiSU_DB_tuple::Load_documents.new(@conn,@col,@opt,@file) - t.tuple + @tuple_array << t.tuple @col[:lev]=@col[:plaintext]=@col[:body]='' else #% regular text @col[:lid]+=1 @@ -609,7 +618,7 @@ module SiSU_DB_import @col[:plaintext]=@col[:body].dup strip_markup(@col[:plaintext]) t=SiSU_DB_tuple::Load_documents.new(@conn,@col,@opt,@file) - t.tuple + @tuple_array << t.tuple @en,@en_ast,@en_pls=[],[],[] @col[:en_a]=@col[:en_z]=nil @col[:lev]=@col[:plaintext]=@col[:body]='' @@ -649,7 +658,7 @@ module SiSU_DB_import :hash => digest_clean } t=SiSU_DB_tuple::Load_endnotes.new(@conn,en,@opt,@file) - t.tuple + @tuple_array << t.tuple end end end @@ -691,7 +700,7 @@ module SiSU_DB_import :hash => digest_clean } t=SiSU_DB_tuple::Load_endnotes.new(@conn,en,@opt,@file) - t.tuple + @tuple_array << t.tuple end end end @@ -732,7 +741,7 @@ module SiSU_DB_import :hash => digest_clean } t=SiSU_DB_tuple::Load_endnotes.new(@conn,en,@opt,@file) - t.tuple + @tuple_array << t.tuple end end end @@ -743,6 +752,7 @@ module SiSU_DB_import rescue; SiSU_Errors::Info_error.new($!,$@,@opt.cmd,@opt.fns).error ensure end + @tuple_array end def endnotes(txt) @txt=txt @@ -865,10 +875,11 @@ module SiSU_DB_import f[:sisupod],u[:sisupod]='sisupod,', "'#{base}/#@fnb/#{@opt.fns}.tgz'," end t=SiSU_DB_tuple::Load_urls.new(@conn,f,u,@@id_t,@opt,@file) - t.tuple + tuple=t.tuple rescue; SiSU_Errors::Info_error.new($!,$@,@opt.cmd,@opt.fns).error ensure end + tuple end end end diff --git a/lib/sisu/v0/db_indexes.rb b/lib/sisu/v0/db_indexes.rb index c22d5700..315ae199 100644 --- a/lib/sisu/v0/db_indexes.rb +++ b/lib/sisu/v0/db_indexes.rb @@ -22,7 +22,7 @@ This program is distributed in the hope that it will be useful, but WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for + FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for more details. You should have received a copy of the GNU General Public License along with @@ -63,36 +63,45 @@ module SiSU_DB_index @opt,@conn,@file,@sql_type=opt,conn,file,sql_type end def create_indexes # check added from pg not tested + def conn_execute_array(sql_arr) + @conn.transaction do |conn| + sql_arr.each do |sql| + conn.execute(sql) + end + end + end def base print "\n create documents common indexes\n" unless @opt.cmd =~/q/ - @conn.execute(' - CREATE INDEX object_nr ON documents(ocn); - CREATE INDEX digest_clean ON documents(digest_clean); - CREATE INDEX digest_all ON documents(digest_all); - CREATE INDEX lev1 ON documents(lev1); - CREATE INDEX lev2 ON documents(lev2); - CREATE INDEX lev3 ON documents(lev3); - CREATE INDEX lev4 ON documents(lev4); - CREATE INDEX lev5 ON documents(lev5); - CREATE INDEX lev6 ON documents(lev6); - CREATE INDEX endnote_nr ON endnotes(nr); - CREATE INDEX digest_en ON endnotes(digest_clean); - CREATE INDEX endnote_nr_asterisk ON endnotes_asterisk(nr); - CREATE INDEX endnote_asterisk ON endnotes_asterisk(clean); - CREATE INDEX digest_en_asterisk ON endnotes_asterisk(digest_clean); - CREATE INDEX endnote_nr_plus ON endnotes_plus(nr); - CREATE INDEX endnote_plus ON endnotes_plus(clean); - CREATE INDEX digest_en_plus ON endnotes_plus(digest_clean); - CREATE INDEX title ON metadata(title); - CREATE INDEX filename ON metadata(filename) - ') unless @opt.cmd =~/q/ + sql_arr=[ + %{CREATE INDEX object_nr ON documents(ocn);}, + %{CREATE INDEX digest_clean ON documents(digest_clean);}, + %{CREATE INDEX digest_all ON documents(digest_all);}, + %{CREATE INDEX lev1 ON documents(lev1);}, + %{CREATE INDEX lev2 ON documents(lev2);}, + %{CREATE INDEX lev3 ON documents(lev3);}, + %{CREATE INDEX lev4 ON documents(lev4);}, + %{CREATE INDEX lev5 ON documents(lev5);}, + %{CREATE INDEX lev6 ON documents(lev6);}, + %{CREATE INDEX endnote_nr ON endnotes(nr);}, + %{CREATE INDEX digest_en ON endnotes(digest_clean);}, + %{CREATE INDEX endnote_nr_asterisk ON endnotes_asterisk(nr);}, + %{CREATE INDEX endnote_asterisk ON endnotes_asterisk(clean);}, + %{CREATE INDEX digest_en_asterisk ON endnotes_asterisk(digest_clean);}, + %{CREATE INDEX endnote_nr_plus ON endnotes_plus(nr);}, + %{CREATE INDEX endnote_plus ON endnotes_plus(clean);}, + %{CREATE INDEX digest_en_plus ON endnotes_plus(digest_clean);}, + %{CREATE INDEX title ON metadata(title);}, + %{CREATE INDEX filename ON metadata(filename)}, + ] + conn_execute_array(sql_arr) end def text print "\n create documents text indexes\n" unless @opt.cmd =~/q/ - @conn.execute(' - CREATE INDEX clean ON documents(clean); - CREATE INDEX endnote ON endnotes(clean); - ') unless @opt.cmd =~/q/ + sql_arr=[ + %{CREATE INDEX clean ON documents(clean);}, + %{CREATE INDEX endnote ON endnotes(clean);} + ] + conn_execute_array(sql_arr) end base @opt.cmd=~/D/ || @opt.mod=~/psql/ ? '' : text diff --git a/lib/sisu/v0/db_load_tuple.rb b/lib/sisu/v0/db_load_tuple.rb index 37bfb1e6..447e9354 100644 --- a/lib/sisu/v0/db_load_tuple.rb +++ b/lib/sisu/v0/db_load_tuple.rb @@ -22,7 +22,7 @@ This program is distributed in the hope that it will be useful, but WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for + FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for more details. You should have received a copy of the GNU General Public License along with @@ -77,38 +77,35 @@ module SiSU_DB_tuple @cX=SiSU_Screen::Ansi.new(@opt.cmd).cX end def tuple #% import line - begin - sql_entry=if @col[:en_a] - "INSERT INTO documents (lid, metadata_tid, lev, clean, body, ocn, ocnd, ocns, seg, lev1, lev2, lev3, lev4, lev5, lev6, en_a, en_z, digest_clean, digest_all) VALUES (#{@col[:lid]}, #{@col[:tid]}, #{@col[:lev]}, '#{@col[:plaintext]}', '#{@col[:body]}', '#{@col[:ocn]}', '#{@col[:ocnd]}', '#{@col[:ocns]}', '#{@col[:seg]}', '#{@col[:lv1]}', '#{@col[:lv2]}', '#{@col[:lv3]}', '#{@col[:lv4]}', '#{@col[:lv5]}', '#{@col[:lv6]}', '#{@col[:en_a]}', '#{@col[:en_z]}', '#{@col[:digest_clean]}', '#{@col[:digest_all]}');" - else - "INSERT INTO documents (lid, metadata_tid, lev, clean, body, ocn, ocnd, ocns, seg, lev1, lev2, lev3, lev4, lev5, lev6, digest_clean, digest_all) VALUES (#{@col[:lid]}, #{@col[:tid]}, #{@col[:lev]}, '#{@col[:plaintext]}', '#{@col[:body]}', '#{@col[:ocn]}', '#{@col[:ocnd]}', '#{@col[:ocns]}', '#{@col[:seg]}', '#{@col[:lv1]}', '#{@col[:lv2]}', '#{@col[:lv3]}', '#{@col[:lv4]}', '#{@col[:lv5]}', '#{@col[:lv6]}', '#{@col[:digest_clean]}', '#{@col[:digest_all]}');" - end - if @opt.cmd =~/M/ - if @opt.cmd =~/V/ - puts @file.inspect - puts sql_entry - end - @file.puts sql_entry - else @conn.execute(sql_entry) + sql_entry=if @col[:en_a] + "INSERT INTO documents (lid, metadata_tid, lev, clean, body, ocn, ocnd, ocns, seg, lev1, lev2, lev3, lev4, lev5, lev6, en_a, en_z, digest_clean, digest_all) VALUES (#{@col[:lid]}, #{@col[:tid]}, #{@col[:lev]}, '#{@col[:plaintext]}', '#{@col[:body]}', '#{@col[:ocn]}', '#{@col[:ocnd]}', '#{@col[:ocns]}', '#{@col[:seg]}', '#{@col[:lv1]}', '#{@col[:lv2]}', '#{@col[:lv3]}', '#{@col[:lv4]}', '#{@col[:lv5]}', '#{@col[:lv6]}', '#{@col[:en_a]}', '#{@col[:en_z]}', '#{@col[:digest_clean]}', '#{@col[:digest_all]}');" + else + "INSERT INTO documents (lid, metadata_tid, lev, clean, body, ocn, ocnd, ocns, seg, lev1, lev2, lev3, lev4, lev5, lev6, digest_clean, digest_all) VALUES (#{@col[:lid]}, #{@col[:tid]}, #{@col[:lev]}, '#{@col[:plaintext]}', '#{@col[:body]}', '#{@col[:ocn]}', '#{@col[:ocnd]}', '#{@col[:ocns]}', '#{@col[:seg]}', '#{@col[:lv1]}', '#{@col[:lv2]}', '#{@col[:lv3]}', '#{@col[:lv4]}', '#{@col[:lv5]}', '#{@col[:lv6]}', '#{@col[:digest_clean]}', '#{@col[:digest_all]}');" + end + if @opt.cmd =~/M/ + if @opt.cmd =~/V/ + puts @file.inspect + puts sql_entry end - if @opt.cmd =~/v/ - if @col[:lev].inspect =~/[1235678]/ - lev=case @col[:lev].inspect - when /1/; ':A' - when /2/; ':B' - when /3/; ':C' - when /5/; ' 2' - when /6/; ' 3' - end - puts %{#{lev}>\t#{@col[:lv1]}\t#{@col[:lv2]}\t#{@col[:lv3]}\t#{@col[:lv4]}\t#{@col[:lv5]}\t#{@col[:lv6]}\t#{@col[:ocn]}\t#{@col[:ocnd]}\t#{@col[:ocns]}} - elsif @col[:lev].inspect =~/[4]/ - puts %{ #{@cX.green}1>#{@cX.off}\t#{@col[:lv1]}\t#{@col[:lv2]}\t#{@col[:lv3]}\t#{@col[:lv4]}\t#{@col[:lv5]}\t#{@col[:lv6]}\t#{@col[:ocn]}\t#{@col[:ocnd]}\t#{@col[:ocns]}\t#{@col[:seg]}} + @file.puts sql_entry + else + @file.puts sql_entry if @opt.cmd =~/V/ + end + if @opt.cmd =~/v/ + if @col[:lev].inspect =~/[1235678]/ + lev=case @col[:lev].inspect + when /1/; ':A' + when /2/; ':B' + when /3/; ':C' + when /5/; ' 2' + when /6/; ' 3' end + puts %{#{lev}>\t#{@col[:lv1]}\t#{@col[:lv2]}\t#{@col[:lv3]}\t#{@col[:lv4]}\t#{@col[:lv5]}\t#{@col[:lv6]}\t#{@col[:ocn]}\t#{@col[:ocnd]}\t#{@col[:ocns]}} + elsif @col[:lev].inspect =~/[4]/ + puts %{ #{@cX.green}1>#{@cX.off}\t#{@col[:lv1]}\t#{@col[:lv2]}\t#{@col[:lv3]}\t#{@col[:lv4]}\t#{@col[:lv5]}\t#{@col[:lv6]}\t#{@col[:ocn]}\t#{@col[:ocnd]}\t#{@col[:ocns]}\t#{@col[:seg]}} end - rescue; SiSU_Errors::Info_error.new($!,$@,@opt.cmd,@opt.fns).error - ensure - #@conn.execute("COMMIT") end + sql_entry end end class Load_metadata @@ -120,8 +117,10 @@ module SiSU_DB_tuple if @opt.cmd =~/M/ puts "maintenance mode on: creating sql transaction file (for last transaction set (document) only):\n\t#{@file.inspect}" @file.puts sql_entry - else @conn.execute(sql_entry) + else + @file.puts sql_entry if @opt.cmd =~/V/ end + sql_entry end end class Load_urls @@ -132,8 +131,10 @@ module SiSU_DB_tuple sql_entry="INSERT INTO urls (#{@f[:txt]} #{@f[:html_toc]} #{@f[:html_doc]} #{@f[:xhtml]} #{@f[:xml_sax]} #{@f[:xml_dom]} #{@f[:odf]} #{@f[:pdf_p]} #{@f[:pdf_l]} #{@f[:concordance]} #{@f[:latex_p]} #{@f[:latex_l]} #{@f[:manifest]} #{@f[:digest]} #{@f[:markup]} #{@f[:sisupod]} metadata_tid) VALUES (#{@u[:txt]} #{@u[:html_toc]} #{@u[:html_doc]} #{@u[:xhtml]} #{@u[:xml_sax]} #{@u[:xml_dom]} #{@u[:odf]} #{@u[:pdf_p]} #{@u[:pdf_l]} #{@u[:concordance]} #{@u[:latex_p]} #{@u[:latex_l]} #{@u[:manifest]} #{@u[:digest]} #{@u[:markup]} #{@u[:sisupod]} #{@id});" if @opt.cmd =~/M/ @file.puts sql_entry - else @conn.execute(sql_entry) + else + @file.puts sql_entry if @opt.cmd =~/V/ end + sql_entry end end class Load_endnotes @@ -144,8 +145,10 @@ module SiSU_DB_tuple sql_entry="INSERT INTO #{@en[:type]} (nid, document_lid, nr, clean, body, ocn, ocnd, ocns, metadata_tid, digest_clean) VALUES ('#{@en[:id]}', '#{@en[:lid]}', '#{@en[:nr]}', '#{@en[:txt]}', '#{@en[:body]}', '#{@en[:ocn]}', '#{@en[:ocnd]}', '#{@en[:ocns]}', '#{@en[:id_t]}', '#{@en[:hash]}');" if @opt.cmd =~/M/ @file.puts sql_entry - else @conn.execute(sql_entry) + else + @file.puts sql_entry if @opt.cmd =~/V/ end + sql_entry end end end diff --git a/lib/sisu/v0/db_remove.rb b/lib/sisu/v0/db_remove.rb index b210a3ca..bde5c891 100644 --- a/lib/sisu/v0/db_remove.rb +++ b/lib/sisu/v0/db_remove.rb @@ -22,7 +22,7 @@ This program is distributed in the hope that it will be useful, but WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for + FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for more details. You should have received a copy of the GNU General Public License along with @@ -90,8 +90,9 @@ module SiSU_DB_remove end @conn.commit if driver_sqlite3 else - s=sql_entry.join(' ') - @conn.execute(s) + sql_entry.each do |s| + @conn.execute(s) + end end if @opt.cmd =~/M/ @file.puts sql_entry if @opt.cmd =~/M/ -- cgit v1.2.3 From 1f70e71190d6654b9b3487fff0574ae2956a0e9c Mon Sep 17 00:00:00 2001 From: Ralph Amissah Date: Wed, 1 Jul 2009 13:47:10 -0400 Subject: cgi generated sample search form, fix --- lib/sisu/v0/cgi_pgsql.rb | 4 ++-- lib/sisu/v0/cgi_sqlite.rb | 4 ++-- 2 files changed, 4 insertions(+), 4 deletions(-) (limited to 'lib') diff --git a/lib/sisu/v0/cgi_pgsql.rb b/lib/sisu/v0/cgi_pgsql.rb index 38da777d..4f201dfa 100644 --- a/lib/sisu/v0/cgi_pgsql.rb +++ b/lib/sisu/v0/cgi_pgsql.rb @@ -22,7 +22,7 @@ This program is distributed in the hope that it will be useful, but WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for + FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for more details. You should have received a copy of the GNU General Public License along with @@ -136,7 +136,7 @@ module SiSU_CGI_pgsql @hosturl_db="#{@env.url.webserv_base_cgi}" @hosturl_files="#{@env.url.webserv_files_from_db}" @port="#{@db.psql.port}" - user='' # '#{@env.user}' + user='#{@env.user}' # check user name for access to pg database: '#{@env.user}' WOK_SQL end def search_statement diff --git a/lib/sisu/v0/cgi_sqlite.rb b/lib/sisu/v0/cgi_sqlite.rb index 86d6987b..34cb67dc 100644 --- a/lib/sisu/v0/cgi_sqlite.rb +++ b/lib/sisu/v0/cgi_sqlite.rb @@ -22,7 +22,7 @@ This program is distributed in the hope that it will be useful, but WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for + FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for more details. You should have received a copy of the GNU General Public License along with @@ -93,7 +93,7 @@ module SiSU_CGI_sqlite serve.each do |x| f3 << %{ when /SiSU_#{x}/; "#{@env.path.webserv}/#{x}/sisu_sqlite.db"\n} end - f3 << "else #{@env.path.webserv}/#{serve[0]}/sisu_sqlite.db\n end\n" + f3 << %{ else '#{@env.path.webserv}/#{serve[0]}/sisu_sqlite.db'\n end\n} if FileTest.writable?('.') output=File.open('sisu_sqlite.cgi','w') output << header0 << header1 << header_desc << header2 << f1 << buttons1 << buttons2 << search_request << search_statement << search_statement_common << search_query1 << @common.pages << search_query2 << @common.tail << @common.main1 << f2 << f3 << dbi_connect << @common.main2 -- cgit v1.2.3