reverts unique words list column and indexes; fix for drop indexes; changelog & version updatesisu_2.2.0

* reverts unique word list column on doc_objects and endnotes and associated
  indexes, may reintroduce at a later time

* db_drop, drop TEXT indexes for sqlite only

* update: changelog, version date

9 files changed, 57 insertions, 85 deletions

diff --git a/CHANGELOG_v2 b/CHANGELOG_v2
index 3d5ebb13..715caef8 100644
--- a/CHANGELOG_v2
+++ b/CHANGELOG_v2
@@ -12,7 +12,7 @@ Reverse Chronological:
 
 %% Development branch UNSTABLE
 
-%% 2.2.0.orig.tar.gz (2010-04-19:16/1)
+%% 2.2.0.orig.tar.gz (2010-04-20:16/2)
 http://www.jus.uio.no/sisu/pkg/src/sisu_2.2.0.orig.tar.gz
   sisu_2.2.0.orig.tar.gz
   sisu_2.2.0-1.dsc
@@ -20,8 +20,6 @@ http://www.jus.uio.no/sisu/pkg/src/sisu_2.2.0.orig.tar.gz
 
   * db (sql) table structure, further review and changes (hence breakage & version bump)
     * new pgsql db name prefix "sisu_v2b_"
-    * new table column words in doc_objects & endnotes, VARCHAR 3000 to contain
-      list of unique sorted words in object
     * increase use of VARCHAR
     * new indexes
 
diff --git a/conf/sisu/v2/version.yml b/conf/sisu/v2/version.yml
index 5cb7a079..2fbef6ac 100644
--- a/conf/sisu/v2/version.yml
+++ b/conf/sisu/v2/version.yml
@@ -1,5 +1,5 @@
 --- 
 :version: 2.2.0
-:date_stamp: 2010w16/1
-:date: "2010-04-19"
+:date_stamp: 2010w16/2
+:date: "2010-04-20"
 :project: SiSU
diff --git a/data/doc/sisu/v2/CHANGELOG b/data/doc/sisu/v2/CHANGELOG
index e182f467..feda1a86 100644
--- a/data/doc/sisu/v2/CHANGELOG
+++ b/data/doc/sisu/v2/CHANGELOG
@@ -12,7 +12,7 @@ Reverse Chronological:
 
 %% Development branch UNSTABLE
 
-%% 2.2.0.orig.tar.gz (2010-04-19:16/1)
+%% 2.2.0.orig.tar.gz (2010-04-20:16/2)
 http://www.jus.uio.no/sisu/pkg/src/sisu_2.2.0.orig.tar.gz
   sisu_2.2.0.orig.tar.gz
   sisu_2.2.0-1.dsc
@@ -20,8 +20,6 @@ http://www.jus.uio.no/sisu/pkg/src/sisu_2.2.0.orig.tar.gz
 
   * db (sql) table structure, further review and changes (hence breakage & version bump)
     * new pgsql db name prefix "sisu_v2b_"
-    * new table column words in doc_objects & endnotes, VARCHAR 3000 to contain
-      list of unique sorted words in object
     * increase use of VARCHAR
     * new indexes
 
diff --git a/data/doc/sisu/v2/sisu_markup_samples/sisu_manual/sisu_download.ssi b/data/doc/sisu/v2/sisu_markup_samples/sisu_manual/sisu_download.ssi
index 7b5b2caf..641846b5 100644
--- a/data/doc/sisu/v2/sisu_markup_samples/sisu_manual/sisu_download.ssi
+++ b/data/doc/sisu/v2/sisu_markup_samples/sisu_manual/sisu_download.ssi
@@ -16,7 +16,7 @@
  :issued: 2002-11-12
  :available: 2002-11-12
  :published: 2009-01-18
- :modified: 2010-04-18
+ :modified: 2010-04-20
 
 @make:
  :num_top: 1
@@ -57,7 +57,7 @@
 
 Download the latest version of SiSU (and SiSU markup samples):~{ Breakage and Fixes Report<br> http://www.jus.uio.no/sisu/SiSU/breakage_and_fixes.html }~
 
-_* {~^ sisu_2.2.0.orig.tar.gz (2010-04-19:16/1) }http://www.jus.uio.no/sisu/pkg/src/sisu_2.2.0.orig.tar.gz
+_* {~^ sisu_2.2.0.orig.tar.gz (2010-04-20:16/2) }http://www.jus.uio.no/sisu/pkg/src/sisu_2.2.0.orig.tar.gz
 
 _* {~^ sisu-markup-samples_2.0.4.orig.tar.gz (of 2008-10-09:40/4 ) }http://www.jus.uio.no/sisu/pkg/src/sisu-markup-samples_2.0.4.orig.tar.gz *~sisu-markup-samples
 
diff --git a/lib/sisu/v2/db_create.rb b/lib/sisu/v2/db_create.rb
index c1fed045..c7ce9a6d 100644
--- a/lib/sisu/v2/db_create.rb
+++ b/lib/sisu/v2/db_create.rb
@@ -218,7 +218,6 @@ module SiSU_DB_create
             ocns            VARCHAR(6),
             clean           TEXT NULL,
             body            TEXT NULL,
-            words           VARCHAR(3000) NULL,
             seg             VARCHAR(256) NULL,
             lev_an          VARCHAR(1),
             lev             SMALLINT NULL,
@@ -258,7 +257,6 @@ module SiSU_DB_create
             nr              SMALLINT,
             clean           TEXT NULL,
             body            TEXT NULL,
-            words           VARCHAR(3000) NULL,
             ocn             SMALLINT,
             ocnd            VARCHAR(6),
             ocns            VARCHAR(6),
@@ -281,7 +279,6 @@ module SiSU_DB_create
             nr              SMALLINT,
             clean           TEXT NULL,
             body            TEXT NULL,
-            words           VARCHAR(3000) NULL,
             ocn             SMALLINT,
             ocnd            VARCHAR(6),
             ocns            VARCHAR(6),
@@ -304,7 +301,6 @@ module SiSU_DB_create
             nr              SMALLINT,
             clean           TEXT NULL,
             body            TEXT NULL,
-            words           VARCHAR(3000) NULL,
             ocn             SMALLINT,
             ocnd            VARCHAR(6),
             ocns            VARCHAR(6),
diff --git a/lib/sisu/v2/db_drop.rb b/lib/sisu/v2/db_drop.rb
index 35d971af..edd08345 100644
--- a/lib/sisu/v2/db_drop.rb
+++ b/lib/sisu/v2/db_drop.rb
@@ -133,50 +133,53 @@ module SiSU_DB_drop
         ensure
         end
       end
-      def conn_execute_array(sql_arr)
-        @conn.transaction do |conn|
-          sql_arr.each do |sql|
-            conn.execute(sql)
+      def indexes
+        def conn_execute_array(sql_arr)
+          @conn.transaction do |conn|
+            sql_arr.each do |sql|
+              conn.execute(sql)
+            end
           end
         end
+        def base                                                             #% drop base indexes
+          print "\n          drop documents common indexes\n" unless @opt.cmd =~/q/
+          sql_arr=[
+            %{DROP INDEX idx_title;},
+            %{DROP INDEX idx_author;},
+            %{DROP INDEX idx_filename;},
+            %{DROP INDEX idx_topics;},
+            %{DROP INDEX idx_ocn;},
+            %{DROP INDEX idx_digest_clean;},
+            %{DROP INDEX idx_digest_all;},
+            %{DROP INDEX idx_lev1;},
+            %{DROP INDEX idx_lev2;},
+            %{DROP INDEX idx_lev3;},
+            %{DROP INDEX idx_lev4;},
+            %{DROP INDEX idx_lev5;},
+            %{DROP INDEX idx_lev6;},
+            %{DROP INDEX idx_endnote_nr;},
+            %{DROP INDEX idx_digest_en;},
+            %{DROP INDEX idx_endnote_nr_asterisk;},
+            %{DROP INDEX idx_endnote_asterisk;},
+            %{DROP INDEX idx_digest_en_asterisk;},
+            %{DROP INDEX idx_endnote_nr_plus;},
+            %{DROP INDEX idx_endnote_plus;},
+            %{DROP INDEX idx_digest_en_plus},
+          ]
+          conn_execute_array(sql_arr)
+        end
+        def text                                                             #% drop TEXT indexes, sqlite
+          print "\n          drop documents TEXT indexes\n" unless @opt.cmd =~/q/
+          sql_arr=[
+            %{DROP INDEX idx_clean;},
+            %{DROP INDEX idx_endnote},
+          ]
+          conn_execute_array(sql_arr)
+        end
+        self
       end
-      def indexes                                                             #% drop all indexes
-        print "\n          drop documents common indexes\n" unless @opt.cmd =~/q/
-        sql_arr=[
-          %{DROP INDEX idx_text_words;},
-          %{DROP INDEX idx_title;},
-          %{DROP INDEX idx_author;},
-          %{DROP INDEX idx_filename;},
-          %{DROP INDEX idx_topics;},
-          %{DROP INDEX idx_ocn;},
-          %{DROP INDEX idx_digest_clean;},
-          %{DROP INDEX idx_digest_all;},
-          %{DROP INDEX idx_lev1;},
-          %{DROP INDEX idx_lev2;},
-          %{DROP INDEX idx_lev3;},
-          %{DROP INDEX idx_lev4;},
-          %{DROP INDEX idx_lev5;},
-          %{DROP INDEX idx_lev6;},
-          %{DROP INDEX idx_endnote_words;},
-          %{DROP INDEX idx_endnote_nr;},
-          %{DROP INDEX idx_digest_en;},
-          %{DROP INDEX idx_endnote_words_asterisk;},
-          %{DROP INDEX idx_endnote_nr_asterisk;},
-          %{DROP INDEX idx_endnote_asterisk;},
-          %{DROP INDEX idx_digest_en_asterisk;},
-          %{DROP INDEX idx_endnote_words_plus;},
-          %{DROP INDEX idx_endnote_nr_plus;},
-          %{DROP INDEX idx_endnote_plus;},
-          %{DROP INDEX idx_digest_en_plus},
-        ]
-        conn_execute_array(sql_arr)
-        print "\n          drop documents TEXT indexes\n" unless @opt.cmd =~/q/
-        sql_arr=[
-          %{DROP INDEX idx_clean;},
-          %{DROP INDEX idx_endnote},
-        ]
-        conn_execute_array(sql_arr)
-      end
+      indexes.base
+      @opt.cmd=~/D/ || ((@opt.mod=~/psql/) ? '' : indexes.text)
       self
     end
   end
diff --git a/lib/sisu/v2/db_import.rb b/lib/sisu/v2/db_import.rb
index e351f6fc..0e2db8e3 100644
--- a/lib/sisu/v2/db_import.rb
+++ b/lib/sisu/v2/db_import.rb
@@ -267,8 +267,6 @@ module SiSU_DB_import
               @col[:plaintext]=@col[:body].dup
               @col[:plaintext]=strip_markup(@col[:plaintext])
               @col[:plaintext]=clean_searchable_text(@col[:plaintext])
-              @col[:words]=@col[:plaintext].dup
-              @col[:words]=unique_words(@col[:words])
               if @en[0]; @en_a,@en_z=@en[0].first,@en[0].last
               end
               if @en_ast[0]; @en_a_asterisk,@en_z_asterisk=@en_ast[0].first,@en_ast[0].last
@@ -303,8 +301,6 @@ module SiSU_DB_import
               @col[:plaintext]=@col[:body].dup
               @col[:plaintext]=strip_markup(@col[:plaintext])
               @col[:plaintext]=clean_searchable_text(@col[:plaintext])
-              @col[:words]=@col[:plaintext].dup
-              @col[:words]=unique_words(@col[:words])
               @en_a,@en_z=@en[0].first,@en[0].last if @en[0]
               @en_a_asterisk,@en_z_asterisk=@en_ast[0].first,@en_ast[0].last if @en_ast[0]
               @en_a_plus,@en_z_plus=@en_pls[0].first,@en_pls[0].last if @en_pls[0]
@@ -332,8 +328,6 @@ module SiSU_DB_import
               @col[:plaintext]=@col[:body].dup
               @col[:plaintext]=strip_markup(@col[:plaintext])
               @col[:plaintext]=clean_searchable_text(@col[:plaintext])
-              @col[:words]=@col[:plaintext].dup
-              @col[:words]=unique_words(@col[:words])
               @en_a,@en_z=@en[0].first,@en[0].last if @en[0]
               @en_a_asterisk,@en_z_asterisk=@en_ast[0].first,@en_ast[0].last if @en_ast[0]
               @en_a_plus,@en_z_plus=@en_pls[0].first,@en_pls[0].last if @en_pls[0]
@@ -361,8 +355,6 @@ module SiSU_DB_import
               @col[:plaintext]=@col[:body].dup
               @col[:plaintext]=strip_markup(@col[:plaintext])
               @col[:plaintext]=clean_searchable_text(@col[:plaintext])
-              @col[:words]=@col[:plaintext].dup
-              @col[:words]=unique_words(@col[:words])
               @en_a,@en_z=@en[0].first,@en[0].last if @en[0]
               @en_a_asterisk,@en_z_asterisk=@en_ast[0].first,@en_ast[0].last if @en_ast[0]
               @en_a_plus,@en_z_plus=@en_pls[0].first,@en_pls[0].last if @en_pls[0]
@@ -403,8 +395,6 @@ module SiSU_DB_import
               @col[:plaintext]=@col[:body].dup
               @col[:plaintext]=strip_markup(@col[:plaintext])
               @col[:plaintext]=clean_searchable_text(@col[:plaintext])
-              @col[:words]=@col[:plaintext].dup
-              @col[:words]=unique_words(@col[:words])
               t=SiSU_DB_tuple::Load_documents.new(@conn,@col,@opt,@file)
               @tuple_array << t.tuple
               @en,@en_ast,@en_pls=[],[],[]
@@ -422,8 +412,6 @@ module SiSU_DB_import
                   special_character_escape(txt)
                   body=SiSU_Format_Shared::CSS_Format.new(@md,data).endnote(nr,txt)
                   strip_markup(txt)
-                  words=txt.dup
-                  words=unique_words(words)
                   if txt.size > (SiSU_DB_columns::Column_size.new.endnote_clean - 1)
                     puts "\n\nTOO LARGE (ENDNOTE - see error log)\n\n"
                     open("#{Dir.pwd}/pg_documents_error_log",'a') do |error|
@@ -438,7 +426,6 @@ module SiSU_DB_import
                       :nr      => nr,
                       :txt     => txt,
                       :body    => body,
-                      :words   => words,
                       :ocn     => @col[:ocn],
                       :ocnd    => @col[:ocnd],
                       :ocns    => @col[:ocns],
@@ -463,8 +450,6 @@ module SiSU_DB_import
                   special_character_escape(txt)
                   body=SiSU_Format_Shared::CSS_Format.new(@md,data).endnote(nr,txt)
                   strip_markup(txt)
-                  words=txt.dup
-                  words=unique_words(words)
                   if txt.size > (SiSU_DB_columns::Column_size.new.endnote_clean - 1)
                     puts "\n\nTOO LARGE (ENDNOTE - see error log)\n\n"
                     open("#{Dir.pwd}/pg_documents_error_log",'a') do |error|
@@ -479,7 +464,6 @@ module SiSU_DB_import
                       :nr      => nr,
                       :txt     => txt,
                       :body    => body,
-                      :words   => words,
                       :ocn     => @col[:ocn],
                       :ocnd    => @col[:ocnd],
                       :ocns    => @col[:ocns],
@@ -504,8 +488,6 @@ module SiSU_DB_import
                   special_character_escape(txt)
                   body=SiSU_Format_Shared::CSS_Format.new(@md,data).endnote(nr,txt)
                   strip_markup(txt)
-                  words=txt.dup
-                  words=unique_words(words)
                   if txt.size > (SiSU_DB_columns::Column_size.new.endnote_clean - 1)
                     puts "\n\nTOO LARGE (ENDNOTE - see error log)\n\n"
                     open("#{Dir.pwd}/pg_documents_error_log",'a') do |error|
@@ -520,7 +502,6 @@ module SiSU_DB_import
                       :nr      => nr,
                       :txt     => txt,
                       :body    => body,
-                      :words   => words,
                       :ocn     => @col[:ocn],
                       :ocnd    => @col[:ocnd],
                       :ocns    => @col[:ocns],
diff --git a/lib/sisu/v2/db_indexes.rb b/lib/sisu/v2/db_indexes.rb
index fb5ddd76..abd90409 100644
--- a/lib/sisu/v2/db_indexes.rb
+++ b/lib/sisu/v2/db_indexes.rb
@@ -73,7 +73,6 @@ module SiSU_DB_index
       def base
         print "\n          create documents common indexes\n" unless @opt.cmd =~/q/
         sql_arr=[
-          %{CREATE INDEX idx_text_words ON doc_objects(words);},
           %{CREATE INDEX idx_ocn ON doc_objects(ocn);},
           %{CREATE INDEX idx_digest_clean ON doc_objects(digest_clean);},
           %{CREATE INDEX idx_digest_all ON doc_objects(digest_all);},
@@ -83,14 +82,11 @@ module SiSU_DB_index
           %{CREATE INDEX idx_lev4 ON doc_objects(lev4);},
           %{CREATE INDEX idx_lev5 ON doc_objects(lev5);},
           %{CREATE INDEX idx_lev6 ON doc_objects(lev6);},
-          %{CREATE INDEX idx_endnote_words ON endnotes(words);},
           %{CREATE INDEX idx_endnote_nr ON endnotes(nr);},
           %{CREATE INDEX idx_digest_en ON endnotes(digest_clean);},
-          %{CREATE INDEX idx_endnote_words_asterisk ON endnotes_asterisk(words);},
           %{CREATE INDEX idx_endnote_nr_asterisk ON endnotes_asterisk(nr);},
           %{CREATE INDEX idx_endnote_asterisk ON endnotes_asterisk(clean);},
           %{CREATE INDEX idx_digest_en_asterisk ON endnotes_asterisk(digest_clean);},
-          %{CREATE INDEX idx_endnote_words_plus ON endnotes_plus(words);},
           %{CREATE INDEX idx_endnote_nr_plus ON endnotes_plus(nr);},
           %{CREATE INDEX idx_endnote_plus ON endnotes_plus(clean);},
           %{CREATE INDEX idx_digest_en_plus ON endnotes_plus(digest_clean);},
@@ -110,7 +106,7 @@ module SiSU_DB_index
         conn_execute_array(sql_arr)
       end
       base
-      text #@opt.cmd=~/D/ || ((@opt.mod=~/psql/) ? '' : text)
+      @opt.cmd=~/D/ || ((@opt.mod=~/psql/) ? '' : text)
     end
   end
 end
diff --git a/lib/sisu/v2/db_load_tuple.rb b/lib/sisu/v2/db_load_tuple.rb
index 23b6249d..67c8008f 100644
--- a/lib/sisu/v2/db_load_tuple.rb
+++ b/lib/sisu/v2/db_load_tuple.rb
@@ -79,11 +79,11 @@ module SiSU_DB_tuple
     end
     def tuple                                                                    #% import line
       sql_entry=if @col[:en_a]
-        "INSERT INTO doc_objects (lid, metadata_tid, lev, lev_an, clean, body, words, ocn, ocnd, ocns, seg, lev1, lev2, lev3, lev4, lev5, lev6, en_a, en_z, t_of, t_is, node, parent, digest_clean, digest_all) " +
-        "VALUES (#{@col[:lid]}, #{@col[:tid]}, #{@col[:lev]}, '#{@col[:lev_an]}', '#{@col[:plaintext]}', '#{@col[:body]}', '#{@col[:words]}', '#{@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[:t_of]}', '#{@col[:t_is]}', '#{@col[:node]}', '#{@col[:parent]}', '#{@col[:digest_clean]}', '#{@col[:digest_all]}');"
+        "INSERT INTO doc_objects (lid, metadata_tid, lev, lev_an, clean, body, ocn, ocnd, ocns, seg, lev1, lev2, lev3, lev4, lev5, lev6, en_a, en_z, t_of, t_is, node, parent, digest_clean, digest_all) " +
+        "VALUES (#{@col[:lid]}, #{@col[:tid]}, #{@col[:lev]}, '#{@col[:lev_an]}', '#{@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[:t_of]}', '#{@col[:t_is]}', '#{@col[:node]}', '#{@col[:parent]}', '#{@col[:digest_clean]}', '#{@col[:digest_all]}');"
       else
-        "INSERT INTO doc_objects (lid, metadata_tid, lev, lev_an, clean, body, words, ocn, ocnd, ocns, seg, lev1, lev2, lev3, lev4, lev5, lev6, t_of, t_is, node, parent, digest_clean, digest_all) " +
-        "VALUES (#{@col[:lid]}, #{@col[:tid]}, #{@col[:lev]}, '#{@col[:lev_an]}', '#{@col[:plaintext]}', '#{@col[:body]}', '#{@col[:words]}', '#{@col[:ocn]}', '#{@col[:ocnd]}', '#{@col[:ocns]}', '#{@col[:seg]}', '#{@col[:lv1]}', '#{@col[:lv2]}', '#{@col[:lv3]}', '#{@col[:lv4]}', '#{@col[:lv5]}', '#{@col[:lv6]}', '#{@col[:t_of]}', '#{@col[:t_is]}', '#{@col[:node]}', '#{@col[:parent]}', '#{@col[:digest_clean]}', '#{@col[:digest_all]}');"
+        "INSERT INTO doc_objects (lid, metadata_tid, lev, lev_an, clean, body, ocn, ocnd, ocns, seg, lev1, lev2, lev3, lev4, lev5, lev6, t_of, t_is, node, parent, digest_clean, digest_all) " +
+        "VALUES (#{@col[:lid]}, #{@col[:tid]}, #{@col[:lev]}, '#{@col[:lev_an]}', '#{@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[:t_of]}', '#{@col[:t_is]}', '#{@col[:node]}', '#{@col[:parent]}', '#{@col[:digest_clean]}', '#{@col[:digest_all]}');"
       end
       if @opt.cmd =~/M/
         if @opt.cmd =~/V/
@@ -315,8 +315,8 @@ tid)
       @conn,@en,@opt,@file=conn,en,opt,file
     end
     def tuple
-      sql_entry="INSERT INTO #{@en[:type]} (nid, document_lid, nr, clean, body, words, ocn, ocnd, ocns, metadata_tid, digest_clean) " +
-      "VALUES ('#{@en[:id]}', '#{@en[:lid]}', '#{@en[:nr]}', '#{@en[:txt]}', '#{@en[:body]}', '#{@en[:words]}', '#{@en[:ocn]}', '#{@en[:ocnd]}', '#{@en[:ocns]}', '#{@en[:id_t]}', '#{@en[:hash]}');"
+      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