From fb112dca9c785a71eaf033732b87519a6575b3a8 Mon Sep 17 00:00:00 2001 From: Ralph Amissah Date: Fri, 25 Nov 2022 20:51:34 -0500 Subject: spine-search-cgi separate commits, remove sundry --- sundry/misc/util/rb/cgi/spine.search.cgi | 952 ------------------------------- sundry/misc/util/rb/tex/dr_tex.rb | 122 ---- 2 files changed, 1074 deletions(-) delete mode 100755 sundry/misc/util/rb/cgi/spine.search.cgi delete mode 100755 sundry/misc/util/rb/tex/dr_tex.rb (limited to 'sundry/misc/util/rb') diff --git a/sundry/misc/util/rb/cgi/spine.search.cgi b/sundry/misc/util/rb/cgi/spine.search.cgi deleted file mode 100755 index 9184847..0000000 --- a/sundry/misc/util/rb/cgi/spine.search.cgi +++ /dev/null @@ -1,952 +0,0 @@ -#!/usr/bin/env ruby -=begin - * Name: SiSU information Structuring Universe - * Author: Ralph Amissah - * https://sisudoc.org - * https://git.sisudoc.org - - * Description: generates naive cgi search form for search of sisu database (sqlite) - * Name: SiSU generated sample cgi search form - - * Description: generated sample cgi search form for SiSU - (SiSU is a framework for document structuring, publishing and search) - - * Author: Ralph Amissah - - * Copyright: (C) 1997 - 2014, Ralph Amissah, All Rights Reserved. - - * License: GPL 3 or later: - - SiSU, a framework for document structuring, publishing and search - - Copyright (C) Ralph Amissah - - This program is free software: you can redistribute it and/or modify it - under the terms of the GNU General Public License as published by the Free - Software Foundation, either version 3 of the License, or (at your option) - any later version. - - 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 - more details. - - You should have received a copy of the GNU General Public License along with - this program. If not, see . - - If you have Internet connection, the latest version of the GPL should be - available at these locations: - - - - * SiSU uses: - * Standard SiSU markup syntax, - * Standard SiSU meta-markup syntax, and the - * Standard SiSU object citation numbering and system - - * Homepages: - - - * Ralph Amissah - - - -=end -begin - require 'cgi' - require 'fcgi' - require 'sqlite3' -rescue LoadError - puts 'cgi, fcgi or sqlite3 NOT FOUND (LoadError)' -end -@stub_default = 'search' -@image_src = "https://#{ENV['HTTP_HOST']}/image_sys" -@hosturl_cgi = "https://#{ENV['HTTP_HOST']}#{ENV['PATH_INFO']}" -@hosturl_files = "https://#{ENV['HTTP_HOST']}" -@output_dir_structure_by = 'language' -@lingual = 'multi' -@db_name_prefix = 'spine.' -@base = "https://#{ENV['HTTP_HOST']}#{ENV['PATH_INFO']}#{ENV['SCRIPT_NAME']}" -#Common TOP -@@offset = 0 -@@canned_search_url = @base -@color_heading = '#DDFFAA' -@color_match = '#ffff48' -class Form - def initialize(base,search_field,selected_db,result_type,checked_sql_limit,checked_tip,checked_stats,checked_searched,checked_url,checked_case,checked_echo,checked_sql,checked_all,checked_none,checked_selected,checked_default,search_note,the_can='') - search_note = '' if checked_searched !~ /\S/ - the_can = '' if checked_url !~ /\S/ - search_field = '' if checked_echo !~ /\S/ - @base,@search_field,@selected_db,@result_type,@checked_sql_limit,@checked_tip,@checked_stats,@checked_searched,@checked_url,@checked_case,@checked_echo,@checked_sql,@checked_all,@checked_none,@checked_selected,@checked_default,@search_note,@the_can=base,search_field,selected_db,result_type,checked_sql_limit,checked_tip,checked_stats,checked_searched,checked_url,checked_case,checked_echo,checked_sql,checked_all,checked_none,checked_selected,checked_default,search_note,the_can - @tip = if checked_tip =~ /\S/ - 'text:__; fulltxt:__; keywords:__; title:__; author:__; topic_register:__; subject:__; description:__; publisher:__; editor:__; contributor:__; date:__; type:__; format:__; identifier:__; source:__; language:__; relation:__; coverage:__; rights:__; comment:__; abstract:__; src_filename_base:__;
' - else '' - end - end - def submission_form - search_form =<<-WOK - - - - - <meta charset="utf-8"> - <meta name="sourcefile" content="SiSU._sst" /> - SiSU search form (sample): SiSU information Structuring Universe - - - - - - - - - -
- - -
-
- SiSU - -
- git - -
- 		- -
-
- - -
- - - #{@tip} - #{@search_note} - #{@the_can} -
- - - - - to search: select which database to search (drop-down menu below); enter your search query (in the form above); and click on the search button (below) -
- - - index - text / grep -
- match limit: - 1,000 - 2,500 -
- echo query - result stats - search url - searched - available fields - sql statement -
- checks: - default - selected - all - none - - - -
- WOK - end -end -class SearchRequest #% search_for - attr_accessor :text1,:fulltext,:keywords,:title,:author,:topic_register,:subject,:description,:publisher,:editor,:contributor,:date,:type,:format,:identifier,:source,:language,:relation,:coverage,:rights,:comment,:abstract,:owner,:date_created,:date_issued,:date_modified,:date_available,:date_valid,:src_filename_base - def initialize(search_field='',q='') - @search_field,@q=search_field,q - @text1=@fulltext=@keywords=@title=@author=@topic_register=@subject=@description=@publisher=@editor=@contributor=@date=@type=@format=@identifier=@source=@language=@relation=@coverage=@rights=@comment=@abstract=@owner=@date_created=@date_issued=@date_modified=@date_available=@date_valid=@filename='' - if @search_field=~/\S/ - @text1 = text_to_match('text:') - @fulltext = text_to_match('fulltxt:') - @topic_register = text_to_match('topic_register:') - @title = text_to_match('title:') # DublinCore 1 - title - @author = text_to_match('(?:author|creator)s?:') # DublinCore 2 - creator/author - @subject = text_to_match('subj(?:ect)?:') # DublinCore 3 - subject - @description = text_to_match('description:') # DublinCore 4 - description - @publisher = text_to_match('pub(?:lisher)?:') # DublinCore 5 - publisher - @editor = text_to_match('editor:') - @contributor = text_to_match('contributor:') # DublinCore 6 - contributor - @date = text_to_match('date:') # DublinCore 7 - date dd-mm-yy - @type = text_to_match('type:') # DublinCore 8 - type - @format = text_to_match('format:') # DublinCore 9 - format - @identifier = text_to_match('identifier:') # DublinCore 10 - identifier - @source = text_to_match('source:') # DublinCore 11 - source - @language = text_to_match('language:') # DublinCore 12 - language - @relation = text_to_match('relation:') # DublinCore 13 - relation - @coverage = text_to_match('coverage:') # DublinCore 14 - coverage - @rights = text_to_match('rights:') # DublinCore 15 - rights - @keywords = text_to_match('key(?:words?)?:') - @comment = text_to_match('comment:') - @abstract = text_to_match('abs(?:tract)?:') - @owner = text_to_match('owner:') - @date_created = text_to_match('date_created:') - @date_issued = text_to_match('date_issued:') - @date_modified = text_to_match('date_modified:') - @date_available = text_to_match('date_available:') - @date_valid = text_to_match('date_valid:') - @filename = text_to_match('src_filename_base:') - @text1 = text_to_match unless @keywords or @author or @title or @text1 or @fulltext or @comment or @abstract or @rights or @subject or @publisher or @date or @filename or @topic_register - else - @text1 = q['s1'] if q['s1'] =~ /\S/ - @fulltext = q['ft'] if q['ft'] =~ /\S/ - @keywords = q['key'] if q['key'] =~ /\S/ - @title = q['ti'] if q['ti'] =~ /\S/ - @author = q['au'] if q['au'] =~ /\S/ - @topic_register = q['tr'] if q['tr'] =~ /\S/ - @subject = q['sj'] if q['sj'] =~ /\S/ - @description = q['dsc'] if q['dsc'] =~ /\S/ - @publisher = q['pb'] if q['pb'] =~ /\S/ - @editor = q['cntr'] if q['cntr'] =~ /\S/ - @contributor = q['cntr'] if q['cntr'] =~ /\S/ - @date = q['dt'] if q['dt'] =~ /\S/ - @type = q['ty'] if q['ty'] =~ /\S/ - @identifier = q['id'] if q['id'] =~ /\S/ - @source = q['src'] if q['src'] =~ /\S/ - @language = q['lang'] if q['lang'] =~ /\S/ - @relation = q['rel'] if q['rel'] =~ /\S/ - @coverage = q['cov'] if q['cov'] =~ /\S/ - @rights = q['cr'] if q['cr'] =~ /\S/ - @comment = q['co'] if q['co'] =~ /\S/ - @abstract = q['ab'] if q['ab'] =~ /\S/ - @date_created = q['dtc'] if q['dtc'] =~ /\S/ - @date_issued = q['dti'] if q['dti'] =~ /\S/ - @date_modified = q['dtm'] if q['dtm'] =~ /\S/ - @date_available = q['dta'] if q['dta'] =~ /\S/ - @date_valid = q['dtv'] if q['dtv'] =~ /\S/ - @filename = if q['doc'] and q['search'] !~ /search db/ then q['doc'] - elsif q['fns'] =~ /\S/ then q['fns'] - end - @@limit = q['ltd'] if q['ltd'] =~ /\d+/ # 1000 - @@offset = q['off'] if q['off'] =~ /\d+/ # 0 - end - end - def text_to_match(identifier='') - m={ - string: /#{identifier}\s*(.+?)/, - string: /#{identifier}\s*(.+?)(?:;|\n|\r|$)/, - word: /#{identifier}[\s(]*(\S+)/ - } - search_string=if @search_field =~m[:word] - search_string=if @search_field =~m[:braces] then m[:braces].match(@search_field)[1] - elsif @search_field =~m[:string] then m[:string].match(@search_field)[1] - else - str=m[:word].match(@search_field)[1] - str=str.gsub(/[()]/,'') - str - end - search_string=search_string.strip.gsub(/\s+/,'+') - #else - # "__" - end - end -end -class DBI_SearchString - def initialize(l,t,q,cse=false) - @l,@t,@q=l,t,q - end - def string - search={ search: [], flag: false } - if @t =~/\S+/ or @q =~/\S+/ - if @t =~/\S+/ then unescaped_search=CGI.unescape(@t) - elsif @q =~/\S+/ then unescaped_search=CGI.unescape(@q) - end - search_construct=[] - unescaped_search=unescaped_search.gsub(/\s*(AND|OR)\s*/,"%' \) \\1 #{@l} LIKE \( '%"). - gsub(/(.+)/,"#{@l} LIKE \( '%\\1%' \)") - search_construct << unescaped_search - search_construct=search_construct.join(' ') - search[:search] << search_construct - search[:flag]=true - search - end - search - end -end -class DBI_SearchStatement - attr_reader :text_search_flag,:sql_select_body_format,:sql_offset,:sql_limit - def initialize(conn,search_for,q,c) - @conn=conn - @text_search_flag=false - @sql_statement={ body: '', endnotes: '', range: '' } - #@offset||=@@offset - #@offset+=@@limit - search={ text: [], endnotes: [] } - cse=(c =~/\S/) ? true : false - st=DBI_SearchString.new('doc_objects.clean',search_for.text1,q['s1'],cse).string - se=DBI_SearchString.new('endnotes.clean',search_for.text1,q['s1'],cse).string - @text_search_flag=st[:flag] - if st[:flag] - search[:text] << st[:search] - end - st = DBI_SearchString.new('metadata_and_text.fulltext',search_for.fulltext,q['ft'],cse).string - if st[:flag] - search[:text] << st[:search] - end - st = DBI_SearchString.new('metadata_and_text.title',search_for.title,q['ti'],cse).string - if st[:flag] - search[:text] << st[:search] - end - st = DBI_SearchString.new('metadata_and_text.creator_author',search_for.author,q['au'],cse).string - if st[:flag] - search[:text] << st[:search] - end - st = DBI_SearchString.new('metadata_and_text.classify_topic_register',search_for.topic_register,q['tr'],cse).string - if st[:flag] - search[:text] << st[:search] - end - st = DBI_SearchString.new('metadata_and_text.classify_subject',search_for.subject,q['sj'],cse).string - if st[:flag] - search[:text] << st[:search] - end - st = DBI_SearchString.new('metadata_and_text.classify_keywords',search_for.keywords,q['key'],cse).string - if st[:flag] - search[:text] << st[:search] - end - st = DBI_SearchString.new('metadata_and_text.notes_description',search_for.description,q['dsc'],cse).string - if st[:flag] - search[:text] << st[:search] - end - st = DBI_SearchString.new('metadata_and_text.publisher',search_for.publisher,q['pb'],cse).string - if st[:flag] - search[:text] << st[:search] - end - st = DBI_SearchString.new('metadata_and_text.creator_editor',search_for.editor,q['cntr'],cse).string - if st[:flag] - search[:text] << st[:search] - end - st = DBI_SearchString.new('metadata_and_text.creator_contributor',search_for.contributor,q['cntr'],cse).string - if st[:flag] - search[:text] << st[:search] - end - st = DBI_SearchString.new('metadata_and_text.date_published',search_for.date,q['dt'],cse).string - if st[:flag] - search[:text] << st[:search] - end - st = DBI_SearchString.new('metadata_and_text.notes_type',search_for.type,q['ty'],cse).string - if st[:flag] - search[:text] << st[:search] - end - st = DBI_SearchString.new('metadata_and_text.original_source',search_for.source,q['src'],cse).string - if st[:flag] - search[:text] << st[:search] - end - st = DBI_SearchString.new('metadata_and_text.language_document_char',search_for.language,q['lang'],cse).string - if st[:flag] - search[:text] << st[:search] - end - st = DBI_SearchString.new('metadata_and_text.notes_relation',search_for.relation,q['rel'],cse).string - if st[:flag] - search[:text] << st[:search] - end - st = DBI_SearchString.new('metadata_and_text.notes_coverage',search_for.coverage,q['cov'],cse).string - if st[:flag] - search[:text] << st[:search] - end - st = DBI_SearchString.new('metadata_and_text.rights_all',search_for.rights,q['cr'],cse).string - if st[:flag] - search[:text] << st[:search] - end - st = DBI_SearchString.new('metadata_and_text.notes_comment',search_for.comment,q['co'],cse).string - if st[:flag] - search[:text] << st[:search] - end - st = DBI_SearchString.new('metadata_and_text.notes_abstract',search_for.abstract,q['ab'],cse).string - if st[:flag] - search[:text] << st[:search] - end - st = DBI_SearchString.new('metadata_and_text.src_filename_base',search_for.src_filename_base,q['fns'],cse).string - if st[:flag] - search[:text] << st[:search] - end - @@limit=q['ltd'] if q['ltd']=~/\d+/ # 1000 - @@offset=q['off'] if q['off']=~/\d+/ # 0 - @search_text='' - @search_text=search[:text].flatten.join(' AND ') - @search_text=@search_text.gsub(/(doc_objects\.clean\s+LIKE\s+\(\s*'%[^']+%'\s*\)\s+(?:(?:AND|OR)\s+doc_objects\.clean\s+LIKE\s+\(\s*'%[^']+%'\s*\))+)/,'(\1)') - end - def sql_offset - @@offset - end - def sql_match_limit - @@limit - end - def sql_canned_search - @offset_next=sql_offset.to_i + sql_match_limit.to_i - @offset_previous=sql_offset.to_i - sql_match_limit.to_i - def current - @@canned_search_url.to_s + '<d=' + sql_match_limit.to_s + '&off=' + sql_offset.to_s - end - def next - @@canned_search_url.to_s + '<d=' + sql_match_limit.to_s + '&off=' + @offset_next.to_s - end - def previous - @offset_previous >= 0 \ - ? (@@canned_search_url.to_s + '<d=' + sql_match_limit.to_s + '&off=' + @offset_previous.to_s) - : '' - end - def start - @@canned_search_url.to_s + '<d=' + sql_match_limit.to_s + '&off=' + 0.to_s - end - self - end - def pre_next(beyond_limit,img) - can=sql_canned_search - page=(sql_offset.to_i + sql_match_limit.to_i)/sql_match_limit.to_i - if beyond_limit - if page.to_s =~ /^1$/ - %{
- pg. #{page.to_s} - -  >> - -
} - elsif page.to_s =~ /^2$/ - %{
- - <<  - - pg. #{page.to_s} - -  >> - -
} - else - %{
- - |<  - - - <<  - - pg. #{page.to_s} - -  >> - -
} - end - else - if page.to_s =~ /^1$/ then '' - elsif page.to_s =~ /^2$/ - %{
- - <<  - - pg. #{page.to_s} -
} - else - %{
- - |<  - - - <<  - - pg. #{page.to_s} -
} - end - end - end - def sql_select_body - limit ||= @@limit - offset ||= @@offset - @sql_statement[:body] = %{ - SELECT metadata_and_text.title, metadata_and_text.creator_author, metadata_and_text.src_filename_base, metadata_and_text.language_document_char, metadata_and_text.notes_suffix, doc_objects.body, doc_objects.seg_name, doc_objects.ocn, metadata_and_text.uid - FROM doc_objects, metadata_and_text - WHERE #{@search_text} AND doc_objects.uid_metadata_and_text = metadata_and_text.uid - ORDER BY metadata_and_text.language_document_char, metadata_and_text.title, metadata_and_text.src_filename_base, doc_objects.ocn - } - @sql_statement[:range] = %{LIMIT #{limit} OFFSET #{offset} ;} - select = @sql_statement[:body] + ' ' + @sql_statement[:range] - select - end - def sql_select_body_format - %{#{sql_select_body}} - end - def contents - @conn.execute(sql_select_body) - end -end -def tail - <<-'WOK' -

- - - - - - -
- - -
-
- SiSU - -
- git - -
-		 - -

- Generated by - SiSU 6.3.1 2014-10-19 (2014w41/7) -
- - SiSU © Ralph Amissah - 1993, current 2014. - All Rights Reserved. -
- SiSU is software for document structuring, publishing and search, -
- - www.sisudoc.org - - sources - - git.sisudoc.org - -
- w3 since October 3 1993 - - ralph@amissah.com - -
- mailing list subscription - - https://lists.sisudoc.org/listinfo/sisu - -
- - sisu@lists.sisudoc.org - -

-		 -

- SiSU using: -
Standard SiSU markup syntax, -
Standard SiSU meta-markup syntax, and the -
Standard SiSU object citation numbering and system, (object/text identifying/locating system) -
- © Ralph Amissah 1997, current 2014. - All Rights Reserved. -

-
-

- - .: - -

-		 -

- SiSU is released under - GPL v3 - or later, - - https://www.gnu.org/licenses/gpl.html - -

-		 -

- SiSU, developed using - - Ruby - - on - - Debian/Gnu/Linux - - software infrastructure, - with the usual GPL (or OSS) suspects. -

-
- - - WOK -end -@tail=tail -@counter_txt_doc,@counter_txt_ocn,@counter_endn_doc,@counter_endn_ocn=0,0,0,0 -@counters_txt,@counters_endn,@sql_select_body='','','' -FCGI.each_cgi do |cgi| - begin # all code goes in begin section - @search={ text: [], endnotes: [] } - q=CGI.new - @db=if cgi['db'] =~ /#{@db_name_prefix}(\S+)/ - @stub=$1 - cgi['db'] - else - @stub=@stub_default - @db_name_prefix + @stub - end - checked_url,checked_stats,checked_searched,checked_tip,checked_case,checked_echo,checked_sql,checked_all,checked_none,checked_selected,checked_default,selected_db='','','','','','','','','' - result_type=(cgi['view']=~/text/) \ - ? result_type={ index: '', text: 'checked'} - : result_type={ index: 'checked', text: ''} - @@limit=if cgi['sql_match_limit'].to_s=~/2500/ - checked_sql_limit={ l1000: '', l2500: 'checked'} - '2500' - else - checked_sql_limit={ l1000: 'checked', l2500: ''} - '1000' - end - checked_echo = 'checked' if cgi['echo'] =~/\S/ - checked_stats = 'checked' if cgi['stats'] =~/\S/ - checked_url = 'checked' if cgi['url'] =~/\S/ or cgi['u'].to_i==1 - checked_searched = 'checked' if cgi['searched'] =~/\S/ - checked_tip = 'checked' if cgi['tip'] =~/\S/ - checked_case = 'checked' if cgi['casesense'] =~/\S/ - checked_sql = 'checked' if cgi['sql'] =~/\S/ - if cgi['checks'] =~ /check_all/ or cgi['check_all'] =~/\S/ or cgi['a'].to_i==1 - checked_all = 'checked' - checked_echo=checked_stats=checked_url=checked_searched=checked_tip=checked_sql='checked' - checked_none ='' - elsif cgi['checks'] =~ /check_none/ - checked_none = 'checked' - checked_all=checked_url=checked_stats=checked_searched=checked_tip=checked_echo=checked_sql='' - elsif cgi['checks'] =~ /check_selected/ - checked_selected = 'checked' - elsif cgi['checks'] =~ /check_default/ - checked_default = 'checked' - checked_echo=checked_stats=checked_url='checked' - checked_searched=checked_tip=checked_case=checked_sql='' - else - checked_selected='checked' - checked_echo=checked_stats=checked_url='checked' - checked_searched=checked_tip=checked_case=checked_sql='' - end - selected_db=case cgi['db'] - when /spine.sqlite/ then '' - end - db_name='spine.search.sql.db' - #db_name='spine.sqlite.db' - #db_name='sisu_sqlite.db' - db_sqlite=case cgi['db'] - when /spine.sqlite/ then "/srv/complete.sisudoc.org/web/manual/#{db_name}" - else "/var/www/sqlite/#{db_name}" - end - #when /spine.sqlite/ then "/srv/complete.sisudoc.org/web/manual/#{db_name}" - #else "/srv/complete.sisudoc.org/web/manual/#{db_name}" - #end - #@conn=SQLite3::Database.new(db_sqlite) - @conn=SQLite3::Database.new("/var/www/sqlite/spine.search.sql.db") - #@conn=SQLite3::Database.new("/var/www/spine.sqlite.db") - @conn.results_as_hash=true - search_field=cgi['find'] if cgi['find'] # =~/\S+/ - @search_for=SearchRequest.new(search_field,q) #.analyze #% search_for - #% searches - #Canned_search.new(@base,@search_for.text1,cgi) - if @search_for.text1=~/\S+/ or @search_for.fulltext=~/\S+/ or @search_for.author=~/\S+/ or @search_for.topic_register=~/\S+/ #and search_field =~/\S/ - s1 = 's1=' + CGI.escape(@search_for.text1) if @search_for.text1 =~ /\S/ - ft = '&ft=' + CGI.escape(@search_for.fulltext) if @search_for.fulltext =~ /\S/ - key = 'key=' + CGI.escape(@search_for.keywords) if @search_for.keywords =~ /\S/ - ti = '&ti=' + CGI.escape(@search_for.title) if @search_for.title =~ /\S/ - au = '&au=' + CGI.escape(@search_for.author) if @search_for.author =~ /\S/ - tr = '&tr=' + CGI.escape(@search_for.topic_register) if @search_for.topic_register =~ /\S/ - sj = '&sj=' + CGI.escape(@search_for.subject) if @search_for.subject =~ /\S/ - dsc = '&dsc=' + CGI.escape(@search_for.description) if @search_for.description =~ /\S/ - pb = '&pb=' + CGI.escape(@search_for.publisher) if @search_for.publisher =~ /\S/ - edt = '&edt=' + CGI.escape(@search_for.editor) if @search_for.editor =~ /\S/ - cntr = '&cntr=' + CGI.escape(@search_for.contributor) if @search_for.contributor =~ /\S/ - dt = '&dt=' + CGI.escape(@search_for.date) if @search_for.date =~ /\S/ - ty = '&ty=' + CGI.escape(@search_for.type) if @search_for.type =~ /\S/ - id = '&id=' + CGI.escape(@search_for.identifier) if @search_for.identifier =~ /\S/ - src = '&src=' + CGI.escape(@search_for.source) if @search_for.source =~ /\S/ - lang = '&lang=' + CGI.escape(@search_for.language) if @search_for.language =~ /\S/ - rel = '&rel=' + CGI.escape(@search_for.relation) if @search_for.relation =~ /\S/ - cov = '&cov=' + CGI.escape(@search_for.coverage) if @search_for.coverage =~ /\S/ - cr = '&cr=' + CGI.escape(@search_for.rights) if @search_for.rights =~ /\S/ - co = '&co=' + CGI.escape(@search_for.comment) if @search_for.comment =~ /\S/ - ab = '&ab=' + CGI.escape(@search_for.abstract) if @search_for.abstract =~ /\S/ - dtc = '&dtc=' + CGI.escape(@search_for.date_created) if @search_for.date_created =~ /\S/ - dti = '&dti=' + CGI.escape(@search_for.date_issued) if @search_for.date_issued =~ /\S/ - dtm = '&dtm=' + CGI.escape(@search_for.date_modified) if @search_for.date_modified =~ /\S/ - dta = '&dta=' + CGI.escape(@search_for.date_available) if @search_for.date_available =~ /\S/ - dtv = '&dtv=' + CGI.escape(@search_for.date_valid) if @search_for.date_valid =~ /\S/ - fns = '&fns=' + CGI.escape(@search_for.src_filename_base) if @search_for.src_filename_base =~ /\S/ - @@canned_search_url=(checked_all =~/checked/) \ - ? "#{@base}?#{s1}#{ft}#{key}#{ti}#{au}#{tr}#{sj}#{dsc}#{pb}#{edt}#{cntr}#{dt}#{ty}#{id}#{src}#{lang}#{rel}#{cov}#{cr}#{co}#{ab}#{dtc}#{dti}#{dtm}#{dta}#{dtv}#{fns}&db=#{cgi['db']}&view=#{cgi['view']}&a=1" - : "#{@base}?#{s1}#{ft}#{key}#{ti}#{au}#{tr}#{sj}#{dsc}#{pb}#{edt}#{cntr}#{dt}#{ty}#{id}#{src}#{lang}#{rel}#{cov}#{cr}#{co}#{ab}#{dtc}#{dti}#{dtm}#{dta}#{dtv}#{fns}&db=#{cgi['db']}&view=#{cgi['view']}" - mod=ft=~/\S+/ ? (ft.gsub(/ft/,'s1')) : s1 - @canned_base_url="#{@base}?#{mod}&db=#{cgi['db']}" - if checked_case=~/\S/ - @search[:text][1]=%{doc_objects.clean~'#{@search_for.text1}'} #s1 - else - @search[:text][1]=%{doc_objects.clean~*'#{@search_for.text1}'} #s1 - end - canned_note='search url:' - else - @@canned_search_url="#{@base}?db=#{@db}&view=index" - canned_note='search url example:' - end - if search_field =~/\S+/ - analyze_format=search_field.gsub(/\s*\n/,'; ') - elsif checked_all =~/checked/ or checked_url =~/checked/ - canned_search=@@canned_search_url.scan(/(?:s1|ft|au|ti|fns|tr)=[^&]+/) - af=canned_search.join('; ') - af=af.gsub(/s1=/,'text: '). - gsub(/ft=/,'fulltxt: '). - gsub(/au=/,'author: '). - gsub(/ti=/,'title: '). - gsub(/fns=/,'src_filename_base: '). - gsub(/tr=/,'topic_register: '). - gsub(/%2B/,' ') - analyze_format=af - st=af.split(/\s*;\s*/) - search_field=st.join("\n") - end - green=%{} - canned_search_url_txt=CGI.escapeHTML(@@canned_search_url) - the_can=%{#{canned_note} #{canned_search_url_txt}
} - p_text=p_fulltext=p_keywords=p_title=p_author=p_topic_register=p_subject=p_description=p_publisher=p_editor=p_contributor=p_date=p_type=p_format=p_identifier=p_source=p_language=p_relation=p_coverage=p_rights=p_comment=p_abstract=p_filename='' - p_filename = %{src_filename_base: #{green}#{@search_for.src_filename_base}
} if @search_for.src_filename_base =~ /\S+/ - p_text = %{text: #{green}#{@search_for.text1}
} if @search_for.text1 =~ /\S+/ - p_fulltext = %{fulltxt: #{green}#{@search_for.fulltext}
} if @search_for.fulltext =~ /\S+/ - p_title = %{title: #{green}#{@search_for.title}
} if @search_for.title =~ /\S+/ - p_author = %{author: #{green}#{@search_for.author}
} if @search_for.author =~ /\S+/ - p_editor = %{editor: #{green}#{@search_for.editor}
} if @search_for.editor =~ /\S+/ - p_contributor = %{contributor: #{green}#{@search_for.contributor}
} if @search_for.contributor =~ /\S+/ - p_date = %{date: #{green}#{@search_for.date}
} if @search_for.date =~ /\S+/ - p_rights = %{rights: #{green}#{@search_for.rights}
} if @search_for.rights =~ /\S+/ - p_topic_register = %{topic_register: #{green}#{@search_for.topic_register}
} if @search_for.topic_register =~ /\S+/ - p_subject = %{subject: #{green}#{@search_for.subject}
} if @search_for.subject =~ /\S+/ - p_keywords = %{keywords: #{green}#{@search_for.keywords}
} if @search_for.keywords =~ /\S+/ - p_identifier = %{identifier: #{green}#{@search_for.identifier}
} if @search_for.identifier =~ /\S+/ - p_type = %{type: #{green}#{@search_for.type}
} if @search_for.type =~ /\S+/ - p_format = %{format: #{green}#{@search_for.format}
} if @search_for.format =~ /\S+/ - p_relation = %{relation: #{green}#{@search_for.relation}
} if @search_for.relation =~ /\S+/ - p_coverage = %{coverage: #{green}#{@search_for.coverage}
} if @search_for.coverage =~ /\S+/ - p_description = %{description: #{green}#{@search_for.description}
} if @search_for.description =~ /\S+/ - p_abstract = %{abstract: #{green}#{@search_for.abstract}
} if @search_for.abstract =~ /\S+/ - p_comment = %{comment: #{green}#{@search_for.comment}
} if @search_for.comment =~ /\S+/ - p_publisher = %{publisher: #{green}#{@search_for.publisher}
} if @search_for.publisher =~ /\S+/ - p_source = %{source: #{green}#{@search_for.source}
} if @search_for.source =~ /\S+/ - p_language = %{language: #{green}#{@search_for.language}
} if @search_for.language =~ /\S+/ - search_note=<<-WOK - - database: #{green}#{@db}; selected view: #{green}#{cgi['view']} - search string: "#{green}#{analyze_format}"
- #{p_text} #{p_fulltext} #{p_keywords} #{p_title} #{p_author} #{p_topic_register} #{p_subject} #{p_description} #{p_publisher} #{p_editor} #{p_contributor} #{p_date} #{p_type} #{p_format} #{p_identifier} #{p_source} #{p_language} #{p_relation} #{p_coverage} #{p_rights} #{p_comment} #{p_abstract} #{p_filename} - - WOK - #eg = %{canned search e.g.:
#{url}
find: #{analyze}
database: #{database}} - #% dbi_canning - @header = Form.new(@base,search_field,selected_db,result_type,checked_sql_limit,checked_tip,checked_stats,checked_searched,checked_url,checked_case,checked_echo,checked_sql,checked_all,checked_none,checked_selected,checked_default,search_note,the_can).submission_form #% form - unless q['s1'] =~/\S/ or q['au'] =~/\S/ or @search[:text][1] =~/\S/ - print "Content-type: text/html\n\n" - puts (@header+@tail) - else #% searches - s1=(@search_for.text1 =~/\S/) \ - ? @search_for.text1 - : 'Unavailable' - if checked_case=~/\S/ - @search[:text]<<%{doc_objects.clean~'#{CGI.unescape(s1)}'} - else - @search[:text]<<%{doc_objects.clean~*'#{CGI.unescape(s1)}'} - end - #% dbi_request - dbi_statement=DBI_SearchStatement.new(@conn,@search_for,q,checked_case) - @text_search_flag=false - @text_search_flag=dbi_statement.text_search_flag - s_contents=dbi_statement.contents - @body_main='' - @search_regx=nil - olduid="" - if @text_search_flag - if checked_sql =~/\S/ - sql_select_body=dbi_statement.sql_select_body_format - else sql_select_body='' - end - @body_main << sql_select_body - #@body_main << '


Main Text:
' << sql_select_body - else - end - @hostpath = "#{@hosturl_files}" - #@hostpath="#{@hosturl_files}/#{@stub}" - def path_manifest(fn,ln=nil) - case @output_dir_structure_by - when 'filename' - @lingual =='mono' \ - ? "#{@hostpath}/#{fn}/sisu_manifest.html" - : "#{@hostpath}/#{fn}/sisu_manifest.#{ln}.html" - when 'filetype' - @lingual =='mono' \ - ? "#{@hostpath}/manifest/#{fn}.html" - : "#{@hostpath}/manifest/#{fn}.#{ln}.html" - else - "#{@hostpath}/#{ln}/manifest/#{fn}.html" - end - end - def path_html_seg(fn,ln=nil) - case @output_dir_structure_by - when 'filename' - "#{@hostpath}/#{fn}" - when 'filetype' - "#{@hostpath}/html/#{fn}" - else - "#{@hostpath}/#{ln}/html/#{fn}" - end - end - def path_toc(fn,ln=nil) - if @output_dir_structure_by =='filename' \ - or @output_dir_structure_by =='filetype' - @lingual =='mono' \ - ? "#{path_html_seg(fn,ln)}/toc.html" - : "#{path_html_seg(fn,ln)}/toc.#{ln}.html" - else - "#{path_html_seg(fn,ln)}/toc.html" - end - end - def path_filename(fn,seg_name,ln=nil) - if @output_dir_structure_by =='filename' \ - or @output_dir_structure_by =='filetype' - @lingual =='mono' \ - ? "#{path_html_seg(fn,ln)}/#{seg_name}.html" - : "#{path_html_seg(fn,ln)}/#{seg_name}.#{ln}.html" - else - "#{path_html_seg(fn,ln)}/#{seg_name}.html" - end - end - def path_html_doc(fn,ln=nil) - case @output_dir_structure_by - when 'filename' - @lingual =='mono' \ - ? "#{path_html_seg(fn,ln)}/scroll.html" - : "#{path_html_seg(fn,ln)}/scroll.#{ln}.html" - when 'filetype' - @lingual =='mono' \ - ? "#{@hostpath}/html/#{fn}.html" - : "#{@hostpath}/html/#{fn}.#{ln}.html" - else - "#{@hostpath}/#{ln}/html/#{fn}.html" - end - end - #% text_objects_body - s_contents.each do |c| #% text body - location=c['src_filename_base'][/(.+?)\.(?:ssm\.sst|sst)$/,1] - file_suffix=c['src_filename_base'][/.+?\.(ssm\.sst|sst)$/,1] - lang=if location =~ /\S+?~(\S\S\S?)$/ - l=location[/\S+?~(\S\S\S?)$/,1] - location=location.gsub(/(\S+?)~\S\S\S?/,'\1') - l=".#{l}" - else '' - end - #% metadata_found_body - if c['uid'] != olduid - ti=c['title'] - can_txt_srch=(cgi['view']=~/index/) \ - ? %{search } - : %{search } - title = %{ #{ti} [#{c['language_document_char']}] by #{c['creator_author']} #{can_txt_srch}
} - title=@text_search_flag \ - ? '
'+title - : '
'+title - @counter_txt_doc+=1 - olduid=c['uid'] - else title='' - end - if @text_search_flag - if cgi['view']=~/text/ \ - or (cgi['view']!~/index/ and cgi['search'] !~/search db/) #% txt body - text=if c['suffix'] !~/1/ #seg - if @search_for.text1 =~/\S+/ \ - or q['s1'] =~/\S+/ #% only this branch is working !! - unescaped_search=if @search_for.text1 =~/\S+/ - CGI.unescape(@search_for.text1) - elsif q['s1'] =~/\S+/ - CGI.unescape(q['s1']) - else nil - end - @search_regx=if unescaped_search #check - search_regex=[] - build=unescaped_search.scan(/\S+/).each do |g| - (g.to_s =~/(AND|OR)/) \ - ? (search_regex << '|') - : (search_regex << %{#{g.to_s}}) - end - search_regex=search_regex.join(' ') - search_regex=search_regex.gsub(/\s*\|\s*/,'|') - Regexp.new(search_regex, Regexp::IGNORECASE) - else nil - end - else nil - end - matched_para=(@search_regx.to_s.class==String && @search_regx.to_s=~/\S\S+/) \ - ? (c['body'].gsub(/(<\s]+#{@search_regx}[^>]+?>|#{@search_regx})/mi,%{\\1})) - : c['body'] - %{

ocn #{c['ocn']}:

#{matched_para}} - elsif c['suffix'] =~/1/ #doc - %{#{title}

ocn #{c['ocn']}:#{c['body']}} - end - @counter_txt_ocn+=1 - output=title+text - else #elsif cgi['view']=~/index/ #% idx body - if c['suffix'] !~/1/ #seg - index=%{#{c['ocn']}, } if @text_search_flag - elsif c['suffix'] =~/1/ #doc #FIX - index=%{#{c['ocn']}, } - end - if c['seg_name'] =~/\S+/ - if @text_search_flag - @counter_txt_ocn+=1 - output=title+index - end - else - @counter_txt_ocn+=1 - output=c['suffix'] !~/1/ \ - ? title+index - : %{#{title}#{c['ocn'].sort}, } - end - end - else output=title - end - @counters_txt=if @counter_txt_doc > 0 - if checked_stats =~/\S/ - @@lt_t=(@counter_txt_ocn==dbi_statement.sql_match_limit.to_i) ? true : false - start=(@@offset.to_i+1).to_s - range=(@@offset.to_i+@counter_txt_ocn.to_i).to_s - %{

Found #{@counter_txt_ocn} times in the main body of #{@counter_txt_doc} documents [ matches #{start} to #{range} ]
} - else '' - end - else '' - end - @body_main << output #+ details - end - olduid = "" - offset=dbi_statement.sql_offset.to_s - limit=dbi_statement.sql_match_limit.to_s - @@lt_t ||=false; @@lt_e ||=false - canned=(@@lt_t or @@lt_e) \ - ? dbi_statement.pre_next(true,@image_src).to_s - : dbi_statement.pre_next(false,@image_src).to_s - limit=dbi_statement.sql_match_limit.to_s - cgi.out{ - @header.force_encoding("UTF-8") \ - + @counters_txt.force_encoding("UTF-8") \ - + @counters_endn.force_encoding("UTF-8") \ - + canned.force_encoding("UTF-8") \ - + @body_main.force_encoding("UTF-8") \ - + canned.force_encoding("UTF-8") \ - + @tail.force_encoding("UTF-8") - } #% print cgi_output_header+counters+body - end - rescue Exception => e - s='
' + CGI::escapeHTML(e.backtrace.reverse.join("\n"))
-    s << CGI::escapeHTML(e.message) + '
' - cgi.out{s} - next - ensure # eg. disconnect from server - @conn.disconnect if @conn - end -end diff --git a/sundry/misc/util/rb/tex/dr_tex.rb b/sundry/misc/util/rb/tex/dr_tex.rb deleted file mode 100755 index 67c1220..0000000 --- a/sundry/misc/util/rb/tex/dr_tex.rb +++ /dev/null @@ -1,122 +0,0 @@ -#!/usr/bin/env ruby -=begin -/+ -- Name: Spine, Doc Reform [a part of] - - Description: documents, structuring, processing, publishing, search - - static content generator - - - Author: Ralph Amissah - [ralph.amissah@gmail.com] - - - Copyright: (C) 2015 - 2022 Ralph Amissah, All Rights - Reserved. - - - License: AGPL 3 or later: - - Spine (SiSU), a framework for document structuring, publishing and - search - - Copyright (C) Ralph Amissah - - This program is free software: you can redistribute it and/or modify it - under the terms of the GNU AFERO General Public License as published by the - Free Software Foundation, either version 3 of the License, or (at your - option) any later version. - - 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 - more details. - - You should have received a copy of the GNU General Public License along with - this program. If not, see [https://www.gnu.org/licenses/]. - - If you have Internet connection, the latest version of the AGPL should be - available at these locations: - [https://www.fsf.org/licensing/licenses/agpl.html] - [https://www.gnu.org/licenses/agpl.html] - - - Spine (by Doc Reform, related to SiSU) uses standard: - - docReform markup syntax - - standard SiSU markup syntax with modified headers and minor modifications - - docReform object numbering - - standard SiSU object citation numbering & system - - - Homepages: - [https://www.doc_reform.org] - [https://www.sisudoc.org] - - - Git - [https://git.sisudoc.org/projects/?p=software/spine.git;a=summary] - -+/ -=end -require 'fileutils' -pwd = Dir.pwd -argv,texfiles_with_path,flags=[],[],[] -lngs = %{(am|bg|bn|br|ca|cs|cy|da|de|el|en|eo|es|et|eu|fi|fr|ga|gl|he|hi|hr|hy|ia|is|it|ja|ko|la|lo|lt|lv|ml|mr|nl|no|nn|oc|pl|pt|pt_BR|ro|ru|sa|se|sk|sl|sq|sr|sv|ta|te|th|tk|tr|uk|ur|vi|zh)} -Regexp.new(lngs, Regexp::IGNORECASE) -argv=$* -argv.sort.each{|y| (y =~/^--\S+$/i) ? (flags << y) : (texfiles_with_path << y) } -if flags.length==0 \ -|| flags.inspect =~/"--help"/ - cmd=(/([^\/]+)$/).match($0)[1] - puts < 0 - texfiles_with_path.each do |texfile_with_path| - if texfile_with_path =~/.+\.tex/ - #puts texfile_with_path - if FileTest.file?(texfile_with_path) - file_basename_with_path = texfile_with_path.sub(/\.tex$/,'') - file_basename = file_basename_with_path.sub(/.*?([^\/]+)$/,'\1') - _out_path = out_path - if file_basename =~ /\.#{lngs}$/ - lng = file_basename.match(/\.#{lngs}$/)[1] - puts file_basename - puts lng - puts _out_path - unless _out_path.match(/\/#{lng}\/pdf$/) - _out_path = "#{out_path}/#{lng}/pdf" - FileUtils::mkdir_p(_out_path) - end - end - texpdf_cmd = %{xetex -interaction=batchmode -fmt=xelatex #{texfile_with_path}\n} - puts texpdf_cmd - 2.times { |i| system(texpdf_cmd) } - if (FileTest.file?(%{#{pwd}/#{file_basename}.pdf})) && (FileTest.directory?(_out_path)) - FileUtils::Verbose::mv(%{#{pwd}/#{file_basename}.pdf}, %{#{_out_path}/#{file_basename}.pdf}) - puts (%{#{_out_path}/#{file_basename}.pdf}) - else - puts "issue with pdf file or output directory" - puts "pdf file: #{pwd}/#{file_basename}.pdf}" - puts "output dir: #{_out_path}/" - end - suffix = ['log', 'out', 'toc', 'aux'] - suffix.each { |s| FileUtils::rm_f(%{#{pwd}/#{file_basename}.#{s}})} - end - end - end -end -Dir.chdir(pwd) -__END__ -- cgit v1.2.3