From 3dcd083585b3f486ece3cfaa0780a6e2ec5b43fe Mon Sep 17 00:00:00 2001 From: Ralph Amissah Date: Sat, 11 Apr 2020 20:51:27 -0400 Subject: help & manpages, start work --- util/d/cgi/search/README | 11 - util/d/cgi/search/dub.sdl | 14 - util/d/cgi/search/dub.selections.json | 7 - .../cgi/search/localhostsqlitespine.search.sql.db | 0 util/d/cgi/search/src/spine_cgi_sqlite_search.d | 913 -------------------- util/rb/cgi/search.cgi | 937 -------------------- util/rb/cgi/search_ref.cgi | 937 -------------------- util/rb/cgi/sisu_7a_sqlite.cgi | 937 -------------------- util/rb/cgi/sisu_lng.cgi | 935 -------------------- util/rb/cgi/sisu_search_pg.cgi | 935 -------------------- util/rb/cgi/sisu_search_sqlite.cgi | 937 -------------------- util/rb/cgi/spine.search.cgi | 958 --------------------- util/rb/tex/dr_tex.rb | 70 -- 13 files changed, 7591 deletions(-) delete mode 100644 util/d/cgi/search/README delete mode 100644 util/d/cgi/search/dub.sdl delete mode 100644 util/d/cgi/search/dub.selections.json delete mode 100644 util/d/cgi/search/localhostsqlitespine.search.sql.db delete mode 100644 util/d/cgi/search/src/spine_cgi_sqlite_search.d delete mode 100755 util/rb/cgi/search.cgi delete mode 100755 util/rb/cgi/search_ref.cgi delete mode 100755 util/rb/cgi/sisu_7a_sqlite.cgi delete mode 100755 util/rb/cgi/sisu_lng.cgi delete mode 100755 util/rb/cgi/sisu_search_pg.cgi delete mode 100755 util/rb/cgi/sisu_search_sqlite.cgi delete mode 100755 util/rb/cgi/spine.search.cgi delete mode 100755 util/rb/tex/dr_tex.rb (limited to 'util') diff --git a/util/d/cgi/search/README b/util/d/cgi/search/README deleted file mode 100644 index eb8fcde..0000000 --- a/util/d/cgi/search/README +++ /dev/null @@ -1,11 +0,0 @@ -change db name to match name of db you create -cv.db_selected = "spine.search.sql.db"; - -~dr/bin/spine-ldc -v --sqlite-db-create --sqlite-db-filename="spine.search.db" --cgi-sqlite-search-filename="spine-search" --output=/var/www ~grotto/repo/git.repo/code/project-spine/doc-reform-markup/markup_samples/markup/pod/* - -~dr/bin/spine-ldc -v --sqlite-update --sqlite-db-filename="spine.search.db" --output=/var/www ~grotto/repo/git.repo/code/project-spine/doc-reform-markup/markup_samples/markup/pod/* - -cd util/d/cgi/search/src -dub --force --compiler=ldc2 && sudo cp -v cgi-bin/spine-search /usr/lib/cgi-bin/. - -http://localhost/cgi-bin/spine-search? diff --git a/util/d/cgi/search/dub.sdl b/util/d/cgi/search/dub.sdl deleted file mode 100644 index c1c775c..0000000 --- a/util/d/cgi/search/dub.sdl +++ /dev/null @@ -1,14 +0,0 @@ -name "spine-search" -description "A minimal D application." -authors "ralph" -copyright "Copyright © 2020, ralph" -license "GPL-3.0+" -dependency "d2sqlite3" version="~>0.18.3" -targetType "executable" -targetPath "./cgi-bin" -mainSourceFile "src/spine_cgi_sqlite_search.d" -configuration "default" { - targetType "executable" - targetName "spine-search" - postGenerateCommands "/usr/bin/notify-send -t 0 'D executable ready' 'spine cgi sqlite search d'" -} diff --git a/util/d/cgi/search/dub.selections.json b/util/d/cgi/search/dub.selections.json deleted file mode 100644 index e6e1b26..0000000 --- a/util/d/cgi/search/dub.selections.json +++ /dev/null @@ -1,7 +0,0 @@ -{ - "fileVersion": 1, - "versions": { - "d2sqlite3": "0.18.3", - "dcgi": "0.1.0" - } -} diff --git a/util/d/cgi/search/localhostsqlitespine.search.sql.db b/util/d/cgi/search/localhostsqlitespine.search.sql.db deleted file mode 100644 index e69de29..0000000 diff --git a/util/d/cgi/search/src/spine_cgi_sqlite_search.d b/util/d/cgi/search/src/spine_cgi_sqlite_search.d deleted file mode 100644 index 1460643..0000000 --- a/util/d/cgi/search/src/spine_cgi_sqlite_search.d +++ /dev/null @@ -1,913 +0,0 @@ -/+ dub.sdl - name "spine search" - description "spine cgi search" -+/ -import std.format; -import std.range; -import std.regex; -import arsd.cgi; -import d2sqlite3; -import std.process : environment; -void cgi_function_intro(Cgi cgi) { - string header; - string table; - string form; - struct Config { - string http_request_type; - string http_host; - // string server_name; - string doc_root; - string cgi_root; - string cgi_script; - string data_path_html; - string db_path; - string query_string; - string http_url; - string request_method; - } - auto conf = Config(); - conf.http_request_type = environment.get("REQUEST_SCHEME", "http"); - conf.http_host = environment.get("HTTP_HOST", "localhost"); - // conf.server_name = environment.get("SERVER_NAME", "localhost"); - conf.doc_root = environment.get("DOCUMENT_ROOT", "/var/www/html"); - conf.cgi_root = environment.get("CONTEXT_DOCUMENT_ROOT", "/usr/lib/cgi-bin/"); - // conf.cgi_script = environment.get("SCRIPT_NAME", "/cgi-bin/spine-search"); - conf.query_string = environment.get("QUERY_STRING", ""); - conf.http_url = environment.get("HTTP_REFERER", conf.http_request_type ~ "://" ~ conf.http_host ~ conf.cgi_script ~ "?" ~ conf.query_string); - conf.db_path = "/var/www/html/sqlite/"; // conf.http_host ~ "/sqlite/"; - conf.request_method = environment.get("REQUEST_METHOD", "POST"); - struct CGI_val { - string db_selected = ""; - string sql_match_limit = ""; // radio: ( 1000 | 2500 ) - string sql_match_offset = ""; - string search_text = ""; - string results_type = ""; // index - bool checked_echo = false; - bool checked_stats = false; - bool checked_url = false; - bool checked_searched = false; - bool checked_tip = false; - bool checked_sql = false; - } - auto cv = CGI_val(); - cv.db_selected = "spine.search.db"; // config, set db name - auto text_fields() { - string canned_query_str = environment.get("QUERY_STRING", ""); - if ("query_string" in cgi.post) { - canned_query_str = environment.get("QUERY_STRING", ""); - } - string[string] canned_query; - if (conf.request_method == "POST") { - } else if (conf.request_method == "GET") { - foreach (pair_str; canned_query_str.split("&")) { - // cgi.write(pair_str ~ "
"); - string[] pair = pair_str.split("="); - canned_query[pair[0]] = pair[1]; - } - // foreach (field, content; canned_query) { - // cgi.write(field ~ ": " ~ content ~ "
"); - // } - } - static struct Rgx { - // static canned_query = ctRegex!(`\A(?P.+)\Z`, "m"); - static search_text_area = ctRegex!(`\A(?P.+)\Z`, "m"); - // static fulltext = ctRegex!(`\A(?P.+)\Z`, "m"); - static line = ctRegex!(`^(?P.+?)(?: ~|$)`, "m"); - static text = ctRegex!(`(?:^|\s~\s*)text:\s+(?P.+?)(?: ~|$)`, "m"); - static author = ctRegex!(`(?:^|\s~\s*)author:\s+(?P.+)$`, "m"); - static title = ctRegex!(`(?:^|\s~\s*)title:\s+(?P.+)$`, "m"); - static uid = ctRegex!(`(?:^|\s~\s*)uid:\s+(?P.+)$`, "m"); - static fn = ctRegex!(`(?:^|\s~\s*)fn:\s+(?P.+)$`, "m"); - static keywords = ctRegex!(`(?:^|\s~\s*)keywords:\s+(?P.+)$`, "m"); - static topic_register = ctRegex!(`(?:^|\s~\s*)topic_register:\s+(?P.+)$`, "m"); - static subject = ctRegex!(`(?:^|\s~\s*)subject:\s+(?P.+)$`, "m"); - static description = ctRegex!(`(?:^|\s~\s*)description:\s+(?P.+)$`, "m"); - static publisher = ctRegex!(`(?:^|\s~\s*)publisher:\s+(?P.+)$`, "m"); - static editor = ctRegex!(`(?:^|\s~\s*)editor:\s+(?P.+)$`, "m"); - static contributor = ctRegex!(`(?:^|\s~\s*)contributor:\s+(?P.+)$`, "m"); - static date = ctRegex!(`(?:^|\s~\s*)date:\s+(?P.+)$`, "m"); - static results_type = ctRegex!(`(?:^|\s~\s*)type:\s+(?P.+)$`, "m"); - static format = ctRegex!(`(?:^|\s~\s*)format:\s+(?P.+)$`, "m"); - static identifier = ctRegex!(`(?:^|\s~\s*)identifier:\s+(?P.+)$`, "m"); - static source = ctRegex!(`(?:^|\s~\s*)source:\s+(?P.+)$`, "m"); - static language = ctRegex!(`(?:^|\s~\s*)language:\s+(?P.+)$`, "m"); - static relation = ctRegex!(`(?:^|\s~\s*)relation:\s+(?P.+)$`, "m"); - static coverage = ctRegex!(`(?:^|\s~\s*)coverage:\s+(?P.+)$`, "m"); - static rights = ctRegex!(`(?:^|\s~\s*)rights:\s+(?P.+)$`, "m"); - static comment = ctRegex!(`(?:^|\s~\s*)comment:\s+(?P.+)$`, "m"); - // static abstract_ = ctRegex!(`(?:^|\s~\s*)abstract:\s+(?P.+)$`, "m"); - static src_filename_base = ctRegex!(`^src_filename_base:\s+(?P.+)$`, "m"); - } - struct searchFields { - string canned_query = ""; // GET canned_query == cq - string search_text_area = ""; // POST search_text_area == tsa - string text = ""; // text == txt - string author = ""; // author == au - string title = ""; // title == ti - string uid = ""; // uid == uid - string fn = ""; // fn == fn - string keywords = ""; // keywords == kw - string topic_register = ""; // topic_register == tr - string subject = ""; // subject == su - string description = ""; // description == de - string publisher = ""; // publisher == pb - string editor = ""; // editor == ed - string contributor = ""; // contributor == ct - string date = ""; // date == dt - string format = ""; // format == fmt - string identifier = ""; // identifier == id - string source = ""; // source == src sfn - string language = ""; // language == lng - string relation = ""; // relation == rl - string coverage = ""; // coverage == cv - string rights = ""; // rights == rgt - string comment = ""; // comment == cmt - // string abstract = ""; - string src_filename_base = ""; // src_filename_base == bfn - string results_type = ""; // results_type == rt radio - string sql_match_limit = ""; // sql_match_limit == sml radio - string sql_match_offset = ""; // sql_match_offset == smo - string stats = ""; // stats == sts checked - string echo = ""; // echo == ec checked - string url = ""; // url == url checked - string searched = ""; // searched == se checked - string sql = ""; // sql == sql checked - } - auto rgx = Rgx(); - auto got = searchFields(); - if (environment.get("REQUEST_METHOD", "POST") == "POST") { - if ("sf" in cgi.post) { - got.search_text_area = cgi.post["sf"]; - if (auto m = got.search_text_area.matchFirst(rgx.text)) { - got.text = m["matched"]; - got.canned_query ~= "sf=" ~ m["matched"]; - } else if (auto m = got.search_text_area.matchFirst(rgx.line)) { - if ( - !(m["matched"].matchFirst(rgx.author)) - && !(m["matched"].matchFirst(rgx.title)) - ) { - got.text = m["matched"]; - got.canned_query ~= "sf=" ~ m["matched"]; - } - } - if (auto m = got.search_text_area.matchFirst(rgx.author)) { - got.author = m["matched"]; - got.canned_query ~= "&au=" ~ m["matched"]; - } - if (auto m = got.search_text_area.matchFirst(rgx.title)) { - got.title = m["matched"]; - got.canned_query ~= "&ti=" ~ m["matched"]; - } - if (auto m = got.search_text_area.matchFirst(rgx.uid)) { - got.uid = m["matched"]; - got.canned_query ~= "&uid=" ~ m["matched"]; - } - if (auto m = got.search_text_area.matchFirst(rgx.fn)) { - got.fn = m["matched"]; - got.canned_query ~= "&fn=" ~ m["matched"]; - } - if (auto m = got.search_text_area.matchFirst(rgx.keywords)) { - got.keywords = m["matched"]; - got.canned_query ~= "&kw=" ~ m["matched"]; - } - if (auto m = got.search_text_area.matchFirst(rgx.topic_register)) { - got.topic_register = m["matched"]; - got.canned_query ~= "&tr=" ~ m["matched"]; - } - if (auto m = got.search_text_area.matchFirst(rgx.subject)) { - got.subject = m["matched"]; - got.canned_query ~= "&su=" ~ m["matched"]; - } - if (auto m = got.search_text_area.matchFirst(rgx.description)) { - got.description = m["matched"]; - got.canned_query ~= "&de=" ~ m["matched"]; - } - if (auto m = got.search_text_area.matchFirst(rgx.publisher)) { - got.publisher = m["matched"]; - got.canned_query ~= "&pb=" ~ m["matched"]; - } - if (auto m = got.search_text_area.matchFirst(rgx.editor)) { - got.editor = m["matched"]; - got.canned_query ~= "&ed=" ~ m["matched"]; - } - if (auto m = got.search_text_area.matchFirst(rgx.contributor)) { - got.contributor = m["matched"]; - got.canned_query ~= "&ct=" ~ m["matched"]; - } - if (auto m = got.search_text_area.matchFirst(rgx.date)) { - got.date = m["matched"]; - got.canned_query ~= "&dt=" ~ m["matched"]; - } - // if (auto m = got.search_text_area.matchFirst(rgx.results_type)) { - // got.results_type = m["matched"]; - // got.canned_query ~= "&rt=" ~ m["matched"]; - // } - if (auto m = got.search_text_area.matchFirst(rgx.format)) { - got.format = m["matched"]; - got.canned_query ~= "&fmt=" ~ m["matched"]; - } - if (auto m = got.search_text_area.matchFirst(rgx.identifier)) { - got.identifier = m["matched"]; - got.canned_query ~= "&id=" ~ m["matched"]; - } - if (auto m = got.search_text_area.matchFirst(rgx.source)) { - got.source = m["matched"]; - got.canned_query ~= "&src=" ~ m["matched"]; - } - if (auto m = got.search_text_area.matchFirst(rgx.language)) { - got.language = m["matched"]; - got.canned_query ~= "&lng=" ~ m["matched"]; - } - if (auto m = got.search_text_area.matchFirst(rgx.relation)) { - got.relation = m["matched"]; - got.canned_query ~= "&rl=" ~ m["matched"]; - } - if (auto m = got.search_text_area.matchFirst(rgx.coverage)) { - got.coverage = m["matched"]; - got.canned_query ~= "&cv=" ~ m["matched"]; - } - if (auto m = got.search_text_area.matchFirst(rgx.rights)) { - got.rights = m["matched"]; - got.canned_query ~= "&rgt=" ~ m["matched"]; - } - if (auto m = got.search_text_area.matchFirst(rgx.comment)) { - got.comment = m["matched"]; - got.canned_query ~= "&cmt=" ~ m["matched"]; - } - // if (auto m = search_text_area.matchFirst(rgx.abstract)) { - // got.abstract = m["matched"]; - // } - if (auto m = got.search_text_area.matchFirst(rgx.src_filename_base)) { - got.src_filename_base = m["matched"]; - got.canned_query ~= "&bfn=" ~ m["matched"]; - } - } - if ("fn" in cgi.post) { - got.fn = cgi.post["fn"]; - got.canned_query ~= "&fn=" ~ cgi.post["fn"]; - } - if ("rt" in cgi.post) { - got.results_type = cgi.post["rt"]; - got.canned_query ~= "&rt=" ~ cgi.post["rt"]; - } - if ("sts" in cgi.post) { - got.stats = cgi.post["sts"]; - got.canned_query ~= "&sts=" ~ cgi.post["sts"]; - } - if ("ec" in cgi.post) { - got.echo = cgi.post["ec"]; - got.canned_query ~= "&ec=" ~ cgi.post["ec"]; - } - if ("url" in cgi.post) { - got.url = cgi.post["url"]; - got.canned_query ~= "&url=" ~ cgi.post["url"]; - } - if ("se" in cgi.post) { - got.searched = cgi.post["se"]; - got.canned_query ~= "&se=" ~ cgi.post["se"]; - } - if ("sql" in cgi.post) { - got.sql = cgi.post["sql"]; - got.canned_query ~= "&sql=" ~ cgi.post["sql"]; - } - if ("sml" in cgi.post) { - got.sql_match_limit = cgi.post["sml"]; - got.canned_query ~= "&sml=" ~ cgi.post["sml"]; - } - if ("smo" in cgi.post) { - got.sql_match_offset = "0"; // cgi.post["smo"]; - got.canned_query ~= "&smo=0"; // ~ cgi.post["smo"]; - } - got.canned_query = got.canned_query.strip.split(" ").join("%20"); - conf.query_string = got.canned_query; - // cgi.write("f.canned_query: " ~ got.canned_query ~ "
"); - } else if (environment.get("REQUEST_METHOD", "POST") == "GET") { - got.canned_query = environment.get("QUERY_STRING", ""); - // cgi.write("f.canned_query: " ~ got.canned_query ~ "
"); - got.search_text_area = ""; - if ("sf" in canned_query && !(canned_query["sf"]).empty) { - got.text = canned_query["sf"].split("%20").join(" "); - got.search_text_area ~= "text: " ~ got.text ~ "\n"; - } - if ("au" in canned_query && !(canned_query["au"]).empty) { - got.author = canned_query["au"].split("%20").join(" "); - got.search_text_area ~= "author: " ~ got.author ~ "\n"; - } - if ("ti" in canned_query && !(canned_query["ti"]).empty) { - got.title = canned_query["ti"].split("%20").join(" "); - got.search_text_area ~= "title: " ~ got.title ~ "\n"; - } - if ("uid" in canned_query && !(canned_query["uid"]).empty) { - got.uid = canned_query["uid"].split("%20").join(" "); - got.search_text_area ~= "uid: " ~ got.uid ~ "\n"; - } - if ("fn" in canned_query && !(canned_query["fn"]).empty) { - got.fn = canned_query["fn"].split("%20").join(" "); - got.search_text_area ~= "fn: " ~ got.fn ~ "\n"; - } - if ("kw" in canned_query && !(canned_query["kw"]).empty) { - got.keywords = canned_query["kw"].split("%20").join(" "); - got.search_text_area ~= "keywords: " ~ got.keywords ~ "\n"; - } - if ("tr" in canned_query && !(canned_query["tr"]).empty) { - got.topic_register = canned_query["tr"].split("%20").join(" "); - got.search_text_area ~= "topic_register: " ~ got.topic_register ~ "\n"; - } - if ("su" in canned_query && !(canned_query["su"]).empty) { - got.subject = canned_query["su"].split("%20").join(" "); - got.search_text_area ~= "subject: " ~ got.subject ~ "\n"; - } - if ("de" in canned_query && !(canned_query["de"]).empty) { - got.description = canned_query["de"].split("%20").join(" "); - got.search_text_area ~= "description: " ~ got.description ~ "\n"; - } - if ("pb" in canned_query && !(canned_query["pb"]).empty) { - got.publisher = canned_query["pb"].split("%20").join(" "); - got.search_text_area ~= "publisher: " ~ got.publisher ~ "\n"; - } - if ("ed" in canned_query && !(canned_query["ed"]).empty) { - got.editor = canned_query["ed"].split("%20").join(" "); - got.search_text_area ~= "editor: " ~ got.editor ~ "\n"; - } - if ("ct" in canned_query && !(canned_query["ct"]).empty) { - got.contributor = canned_query["ct"].split("%20").join(" "); - got.search_text_area ~= "contributor: " ~ got.contributor ~ "\n"; - } - if ("dt" in canned_query && !(canned_query["dt"]).empty) { - got.date = canned_query["dt"].split("%20").join(" "); - got.search_text_area ~= "date: " ~ got.date ~ "\n"; - } - if ("rt" in canned_query && !(canned_query["rt"]).empty) { - got.results_type = canned_query["rt"].split("%20").join(" "); - // got.search_text_area ~= "results_type: " ~ got.results_type ~ "\n"; - } - if ("fmt" in canned_query && !(canned_query["fmt"]).empty) { - got.format = canned_query["fmt"].split("%20").join(" "); - got.search_text_area ~= "format: " ~ got.format ~ "\n"; - } - if ("id" in canned_query && !(canned_query["id"]).empty) { - got.identifier = canned_query["id"].split("%20").join(" "); - got.search_text_area ~= "identifier: " ~ got.identifier ~ "\n"; - } - if ("src" in canned_query && !(canned_query["src"]).empty) { - got.source = canned_query["src"].split("%20").join(" "); - got.search_text_area ~= "source: " ~ got.source ~ "\n"; - } - if ("lng" in canned_query && !(canned_query["lng"]).empty) { - got.language = canned_query["lng"].split("%20").join(" "); - got.search_text_area ~= "language: " ~ got.language ~ "\n"; - } - if ("rl" in canned_query && !(canned_query["rl"]).empty) { - got.relation = canned_query["rl"].split("%20").join(" "); - got.search_text_area ~= "relation: " ~ got.relation ~ "\n"; - } - if ("cv" in canned_query && !(canned_query["cv"]).empty) { - got.coverage = canned_query["cv"].split("%20").join(" "); - got.search_text_area ~= "coverage: " ~ got.coverage ~ "\n"; - } - if ("rgt" in canned_query && !(canned_query["rgt"]).empty) { - got.rights = canned_query["rgt"].split("%20").join(" "); - got.search_text_area ~= "rights: " ~ got.rights ~ "\n"; - } - if ("cmt" in canned_query && !(canned_query["cmt"]).empty) { - got.comment = canned_query["cmt"].split("%20").join(" "); - got.search_text_area ~= "comment: " ~ got.comment ~ "\n"; - } - // if ("abstract" in canned_query && !(canned_query["abstract"]).empty) { - // got.abstract = canned_query["abstract"]; - // } - if ("bfn" in canned_query && !(canned_query["bfn"]).empty) { // search_field - got.src_filename_base = canned_query["bfn"].split("%20").join(" "); - got.search_text_area ~= "src_filename_base: " ~ got.src_filename_base ~ "\n"; - } - if ("sml" in canned_query && !(canned_query["sml"]).empty) { - got.sql_match_limit = canned_query["sml"].split("%20").join(" "); - // got.search_text_area ~= "sql_match_limit: " ~ got.sql_match_limit ~ "\n"; - } - // cgi.write("f.search_text_area: " ~ got.search_text_area ~ "
"); - } - return got; - } - auto tf = text_fields; // - struct SQL_select { - string the_body = ""; - string the_range = ""; - } - auto sql_select = SQL_select(); - string base ; // = ""; - string tip ; // = ""; - string search_note ; // = ""; - uint sql_match_offset_count = 0; - string previous_next () { - static struct Rgx { - static track_offset = ctRegex!(`(?P[&]smo=)(?P[0-9]+)`, "m"); - } - auto rgx = Rgx(); - string _previous_next = ""; - int _current_offset_value = 0; - string _set_offset_next = ""; - string _set_offset_previous = ""; - string _url = ""; - string _url_previous = ""; - string _url_next = ""; - string arrow_previous = ""; - string arrow_next = ""; - if (environment.get("REQUEST_METHOD", "POST") == "POST") { - _url = conf.http_request_type ~ "://" ~ conf.http_host ~ conf.cgi_script ~ "?" ~ tf.canned_query; - } else if (environment.get("REQUEST_METHOD", "POST") == "GET") { - _url = conf.http_request_type ~ "://" ~ conf.http_host ~ conf.cgi_script ~ "?" ~ environment.get("QUERY_STRING", ""); - } - if (auto m = _url.matchFirst(rgx.track_offset)) { - _current_offset_value = m.captures["offset_val"].to!int; - _set_offset_next = m.captures["offset_key"] ~ ((m.captures["offset_val"]).to!int + cv.sql_match_limit.to!int).to!string; - _url_next = _url.replace(rgx.track_offset, _set_offset_next); - if (_current_offset_value < cv.sql_match_limit.to!int) { - _url_previous = ""; - } else { - _url_previous = ""; - _set_offset_previous = m.captures["offset_key"] ~ ((m.captures["offset_val"]).to!int - cv.sql_match_limit.to!int).to!string; - _url_previous = _url.replace(rgx.track_offset, _set_offset_previous); - } - } else {// _current_offset_value = 0; - _url_next = _url ~= "&smo=" ~ cv.sql_match_limit.to!string; - } - if (_url_previous.empty) { - arrow_previous = ""; - } else { - arrow_previous = - "" - ~ "" - ~ "<< prev" - ~ " || "; - } - arrow_next = - "" - ~ "" - ~ "next >>" - ~ ""; - _previous_next = "
" ~ arrow_previous ~ arrow_next; - return _previous_next; - } - { - header = format(q"┃ - - - - - - SiSU spine search form (sample) - - - - - - - -┃", - conf.http_host, - ); - } - { - table = format(q"┃ - - - -
- - -
-
- SiSU - -
- git - -
- 		- -
- ┃"); - } - { - string post_value(string field_name, string type="box", string set="on") { - string val = ""; - switch (type) { - case "field": - val = ((field_name in cgi.post && !(cgi.post[field_name]).empty) - ? cgi.post[field_name] - : (field_name in cgi.get) - ? cgi.get[field_name] - : ""); - val = tf.search_text_area; - break; - case "box": // generic for checkbox or radio; checkbox set == "on" radio set == "name set" - val = ((field_name in cgi.post && !(cgi.post[field_name]).empty) - ? (cgi.post[field_name] == set ? "checked" : "off") - : (field_name in cgi.get) - ? (cgi.get[field_name] == set ? "checked" : "off") - : "off"); - break; - case "radio": // used generic bo - val = ((field_name in cgi.post && !(cgi.post[field_name]).empty) - ? (cgi.post[field_name] == set ? "checked" : "off") - : (field_name in cgi.get) - ? (cgi.get[field_name] == set ? "checked" : "off") - : "checked"); - break; - case "checkbox": // used generic bo - val = ((field_name in cgi.post && !(cgi.post[field_name]).empty) - ? (cgi.post[field_name] == set ? "checked" : "off") - : (field_name in cgi.get) - ? (cgi.get[field_name] == set ? "checked" : "off") - : "checked"); - break; - default: - } - return val; - } - string the_can(string fv) { - string show_the_can = post_value("url"); - string _the_can = ""; - if (show_the_can == "checked") { - tf = text_fields; - string method_get_url = conf.http_request_type ~ "://" ~ conf.http_host ~ conf.cgi_script ~ "?" ~ environment.get("QUERY_STRING", ""); - string method_post_url_construct = conf.http_request_type ~ "://" ~ conf.http_host ~ conf.cgi_script ~ "?" ~ tf.canned_query; - // assert(method_get_url == environment.get("HTTP_REFERER", conf.http_request_type ~ "://" ~ conf.http_host ~ conf.cgi_script ~ "?" ~ conf.query_string)); - if (conf.request_method == "POST") { - _the_can = - "" - ~ "POST: " - ~ "" - ~ method_post_url_construct - ~ "" - ~ "
"; - } else if (conf.request_method == "GET") { - _the_can = - "" - ~ "GET:  " - ~ "" - ~ method_get_url - ~ ""; - } - conf.http_url = conf.http_request_type ~ "://" ~ conf.http_host ~ conf.cgi_script ~ tf.canned_query; - } - return _the_can; - } - string provide_tip() { - string searched_tip = post_value("se"); - string tip = ""; - if (searched_tip == "checked") { - string search_field = post_value("sf", "field"); - tf = text_fields; - tip = format(q"┃ - -database: %s; selected view: index -search string: %s %s %s %s %s %s
-%s %s %s %s %s %s - -┃", - cv.db_selected, - (tf.text.empty ? "" : "\"text: " ~ tf.text ~ "; "), - (tf.title.empty ? "" : "\"title: " ~ tf.title ~ "; "), - (tf.author.empty ? "" : "\"author: " ~ tf.author ~ "; "), - (tf.date.empty ? "" : "\"date " ~ tf.date ~ "; "), - (tf.uid.empty ? "" : "\"uid: " ~ tf.uid ~ "; "), - (tf.fn.empty ? "" : "\"fn: " ~ tf.fn ~ "; "), - (tf.text.empty ? "" : "text: " ~ tf.text ~ "
"), - (tf.title.empty ? "" : "title: " ~ tf.title ~ "
"), - (tf.author.empty ? "" : "author: " ~ tf.author ~ "
"), - (tf.date.empty ? "" : "date: " ~ tf.date ~ "
"), - (tf.uid.empty ? "" : "\"uid: " ~ tf.uid ~ "; "), - (tf.fn.empty ? "" : "\"fn: " ~ tf.fn ~ "; "), - ); - } - return tip; - } - form = format(q"┃ -
- - -
- - - %s - %s - %s -
- - - 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 - -
- - - -
-┃", - "spine-search", - (post_value("ec") == "checked") ? post_value("sf", "field") : "", - provide_tip, - search_note, - the_can(post_value("sf", "field")), - cv.db_selected, - cv.db_selected, - post_value("rt", "box", "idx"), - post_value("rt", "box", "txt"), - post_value("sml", "box", "1000"), - post_value("sml", "box", "2500"), - post_value("ec"), - post_value("sts"), - post_value("url"), - post_value("se"), - post_value("tip"), - post_value("sql"), - ); - { - string set_value(string field_name, string default_val) { - string val; - if (field_name in cgi.post) { - val = cgi.post[field_name]; - } else if (field_name in cgi.get) { - val = cgi.get[field_name]; - } else { val = default_val; } - return val; - } - bool set_bool(string field_name) { - bool val; - if (field_name in cgi.post - && cgi.post[field_name] == "on") { - val = true; - } else if (field_name in cgi.get - && cgi.get[field_name] == "on") { - val = true; - } else { val = false; } - return val; - } - cv.db_selected = set_value("selected_db", "spine.search.db"); // selected_db == db - cv.sql_match_limit = set_value("sml", "1000"); - cv.sql_match_offset = set_value("smo", "0"); - cv.search_text = set_value("sf", "test"); // remove test - cv.results_type = set_value("rt", "idx"); - cv.checked_echo = set_bool("ec"); - cv.checked_stats = set_bool("sts"); - cv.checked_url = set_bool("url"); - cv.checked_searched = set_bool("se"); - cv.checked_tip = set_bool("tip"); - cv.checked_sql = set_bool("sql"); - tf = text_fields; - } - } - { - cgi.write(header); - cgi.write(table); - cgi.write(form); - // cgi.write(previous_next); - { // debug environment - // foreach (k, d; environment.toAA) { - // cgi.write(k ~ ": " ~ d ~ "
"); - // } - } - { // debug cgi info - // cgi.write("db_selected: " ~ cv.db_selected ~ "
\n"); - // cgi.write("search_text: " ~ cv.search_text ~ "
\n"); - // cgi.write("sql_match_limit: " ~ cv.sql_match_limit ~ ";\n"); - // cgi.write("sql_match_offset: " ~ cv.sql_match_offset ~ ";\n"); - // cgi.write("results_type: " ~ cv.results_type ~ "
\n"); - // cgi.write("cv.checked_echo: " ~ (cv.checked_echo ? "checked" : "off") ~ "; \n"); - // cgi.write("cv.checked_stats: " ~ (cv.checked_stats ? "checked" : "off") ~ "; \n"); - // cgi.write("cv.checked_url: " ~ (cv.checked_url ? "checked" : "off") ~ "; \n"); - // cgi.write("cv.checked_searched: " ~ (cv.checked_searched ? "checked" : "off") ~ ";
\n"); - // cgi.write("cv.checked_tip: " ~ (cv.checked_tip ? "checked" : "off") ~ "; \n"); - // cgi.write("cv.checked_sql: " ~ (cv.checked_sql ? "checked" : "off") ~ "
\n"); - } - } - auto db = Database(conf.db_path ~ cv.db_selected); - { - uint sql_match_offset_counter(T)(T cv) { - sql_match_offset_count += cv.sql_match_limit.to!uint; - return sql_match_offset_count; - } - void sql_search_query() { - string select_field_like(string db_field, string search_field) { - string where_ = ""; - if (!(search_field.empty)) { - string _sf = search_field.strip.split("%20").join(" "); - if (_sf.match(r" OR ")) { - _sf = _sf.split(" OR ").join("%' OR " ~ db_field ~ " LIKE '%"); - } - if (_sf.match(r" AND ")) { - _sf = _sf.split(" AND ").join("%' AND " ~ db_field ~ " LIKE '%"); - } - _sf = "( " ~ db_field ~ " LIKE\n '%" ~ _sf ~ "%' )"; - where_ ~= format(q"┃ - %s -┃", - _sf - ); - } - return where_; - } - string[] _fields; - _fields ~= select_field_like("doc_objects.clean", tf.text); - _fields ~= select_field_like("metadata_and_text.title", tf.title); - _fields ~= select_field_like("metadata_and_text.creator_author", tf.author); - _fields ~= select_field_like("metadata_and_text.uid", tf.uid); - _fields ~= select_field_like("metadata_and_text.src_filename_base", tf.fn); - _fields ~= select_field_like("metadata_and_text.src_filename_base", tf.src_filename_base); - _fields ~= select_field_like("metadata_and_text.language_document_char", tf.language); - _fields ~= select_field_like("metadata_and_text.date_published", tf.date); - _fields ~= select_field_like("metadata_and_text.classify_keywords", tf.keywords); - _fields ~= select_field_like("metadata_and_text.classify_topic_register", tf.topic_register); - string[] fields; - foreach (f; _fields) { - if (!(f.empty)) { fields ~= f; } - } - string fields_str = ""; - fields_str ~= fields.join(" AND "); - sql_select.the_body ~= format(q"┃ -SELECT - metadata_and_text.uid, - metadata_and_text.title, - metadata_and_text.creator_author_last_first, - metadata_and_text.creator_author, - metadata_and_text.src_filename_base, - metadata_and_text.language_document_char, - metadata_and_text.date_published, - metadata_and_text.classify_keywords, - metadata_and_text.classify_topic_register, - doc_objects.body, - doc_objects.seg_name, - doc_objects.ocn, - metadata_and_text.uid -FROM - doc_objects, - metadata_and_text -WHERE ( - %s - ) -AND - doc_objects.uid_metadata_and_text = metadata_and_text.uid -ORDER BY - metadata_and_text.creator_author_last_first, - metadata_and_text.date_published DESC, - metadata_and_text.title, - metadata_and_text.language_document_char, - metadata_and_text.src_filename_base, - doc_objects.ocn -LIMIT %s OFFSET %s -;┃", - fields_str, - cv.sql_match_limit, - cv.sql_match_offset, - ); - (cv.checked_sql) - ? cgi.write(previous_next ~ "
" ~ sql_select.the_body.split("\n ").join(" ").split("\n").join("
") ~ "\n") - : ""; - cgi.write(previous_next); - auto select_query_results = db.execute(sql_select.the_body).cached; - string _old_uid = ""; - if (!select_query_results.empty) { - foreach (row; select_query_results) { - if (row["uid"].as!string != _old_uid) { - _old_uid = row["uid"].as!string; - auto m = (row["date_published"].as!string).match(regex(r"^([0-9]{4})")); // breaks if row missing or no match? - cgi.write( - "
\"" - ~ row["title"].as!string ~ "\"" - ~ " (" - ~ m.hit - ~ ") " - ~ "[" - ~ row["language_document_char"].as!string - ~ "] " - ~ row["creator_author_last_first"].as!string - ~ ":
\n" - ); - } - if (cv.results_type == "txt") { - cgi.write( - "
" - ~ row["ocn"].as!string - ~ "" - ~ "
" - ~ row["body"].as!string - ); - } else { - cgi.write( - "" - ~ row["ocn"].as!string - ~ ", " - ); - } - } - cgi.write( previous_next); - } else { // offset_not_beyond_limit = false; - cgi.write("select_query_results empty

\n"); - } - } - sql_search_query; - } - { - db.close; - } - { - string tail = format(q"┃ - -┃"); - cgi.write(tail); - } -} -mixin GenericMain!cgi_function_intro; diff --git a/util/rb/cgi/search.cgi b/util/rb/cgi/search.cgi deleted file mode 100755 index 0fe8ea5..0000000 --- a/util/rb/cgi/search.cgi +++ /dev/null @@ -1,937 +0,0 @@ -#!/usr/bin/env ruby -=begin - * Name: SiSU information Structuring Universe - * Author: Ralph Amissah - * http://www.jus.uio.no/sisu - * http://www.jus.uio.no/sisu/SiSU/download - - * 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 - - * Hompages: - - - - * Ralph Amissah - - - -=end - begin - require 'cgi' - require 'fcgi' - require 'sqlite3' - rescue LoadError - puts 'cgi, fcgi or sqlite3 NOT FOUND (LoadError)' - end - @stub_default='manual' - @image_src="http://#{ENV['HTTP_HOST']}/_sisu/image_sys" - @hosturl_cgi="http://#{ENV['HTTP_HOST']}#{ENV['PATH_INFO']}" - @hosturl_files="http://#{ENV['HTTP_HOST']}" - @output_dir_structure_by='filetype' - @lingual='multi' - @db_name_prefix='SiSU.7a.' - @base="http://#{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:__; filename:__;
' - 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,:filename - 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('filename:') - @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',search_for.filename,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, metadata_and_text.language_document_char, metadata_and_text.notes_suffix, doc_objects.body, doc_objects.seg, doc_objects.ocn, metadata_and_text.tid FROM doc_objects, metadata_and_text WHERE #{@search_text} AND doc_objects.metadata_tid = metadata_and_text.tid ORDER BY metadata_and_text.language_document_char, metadata_and_text.title, metadata_and_text.src_filename, 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.jus.uio.no/sisu - - and - - www.sisudoc.org - - sources - - git.sisudoc.org - -
- w3 since October 3 1993 - - ralph@amissah.com - -
- mailing list subscription - - http://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, - - http://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 /SiSU.7a.manual/ then '' - end - db_name='sisu_sqlite.db' - db_sqlite=case cgi['db'] - when /SiSU.7a.manual/ 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.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.filename) if @search_for.filename=~/\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=/,'filename: '). - 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=%{filename: #{green}#{@search_for.filename}
} if @search_for.filename =~/\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 - oldtid=0 - 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}/#{@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,ln=nil) - if @output_dir_structure_by =='filename' \ - or @output_dir_structure_by =='filetype' - @lingual =='mono' \ - ? "#{path_html_seg(fn,ln)}/#{seg}.html" - : "#{path_html_seg(fn,ln)}/#{seg}.#{ln}.html" - else - "#{path_html_seg(fn,ln)}/#{seg}.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'][/(.+?)\.(?:ssm\.sst|sst)$/,1] - file_suffix=c['src_filename'][/.+?\.(ssm\.sst|sst)$/,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['tid'].to_i != oldtid.to_i - ti=c['title'] - can_txt_srch=(cgi['view']=~/index/) \ - ? %{search } - : %{search } - title=%{toc html #{ti} [#{c['language_document_char']}] by #{c['creator_author']} manifest #{can_txt_srch}
} if file_suffix=~/s/ #hmm watch file_suffix - title=@text_search_flag \ - ? '
'+title - : '
'+title - @counter_txt_doc+=1 - oldtid=c['tid'].to_i - 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'] =~/\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 - oldtid = 0 - 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/util/rb/cgi/search_ref.cgi b/util/rb/cgi/search_ref.cgi deleted file mode 100755 index 0fe8ea5..0000000 --- a/util/rb/cgi/search_ref.cgi +++ /dev/null @@ -1,937 +0,0 @@ -#!/usr/bin/env ruby -=begin - * Name: SiSU information Structuring Universe - * Author: Ralph Amissah - * http://www.jus.uio.no/sisu - * http://www.jus.uio.no/sisu/SiSU/download - - * 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 - - * Hompages: - - - - * Ralph Amissah - - - -=end - begin - require 'cgi' - require 'fcgi' - require 'sqlite3' - rescue LoadError - puts 'cgi, fcgi or sqlite3 NOT FOUND (LoadError)' - end - @stub_default='manual' - @image_src="http://#{ENV['HTTP_HOST']}/_sisu/image_sys" - @hosturl_cgi="http://#{ENV['HTTP_HOST']}#{ENV['PATH_INFO']}" - @hosturl_files="http://#{ENV['HTTP_HOST']}" - @output_dir_structure_by='filetype' - @lingual='multi' - @db_name_prefix='SiSU.7a.' - @base="http://#{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:__; filename:__;
' - 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,:filename - 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('filename:') - @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',search_for.filename,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, metadata_and_text.language_document_char, metadata_and_text.notes_suffix, doc_objects.body, doc_objects.seg, doc_objects.ocn, metadata_and_text.tid FROM doc_objects, metadata_and_text WHERE #{@search_text} AND doc_objects.metadata_tid = metadata_and_text.tid ORDER BY metadata_and_text.language_document_char, metadata_and_text.title, metadata_and_text.src_filename, 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.jus.uio.no/sisu - - and - - www.sisudoc.org - - sources - - git.sisudoc.org - -
- w3 since October 3 1993 - - ralph@amissah.com - -
- mailing list subscription - - http://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, - - http://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 /SiSU.7a.manual/ then '' - end - db_name='sisu_sqlite.db' - db_sqlite=case cgi['db'] - when /SiSU.7a.manual/ 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.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.filename) if @search_for.filename=~/\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=/,'filename: '). - 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=%{filename: #{green}#{@search_for.filename}
} if @search_for.filename =~/\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 - oldtid=0 - 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}/#{@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,ln=nil) - if @output_dir_structure_by =='filename' \ - or @output_dir_structure_by =='filetype' - @lingual =='mono' \ - ? "#{path_html_seg(fn,ln)}/#{seg}.html" - : "#{path_html_seg(fn,ln)}/#{seg}.#{ln}.html" - else - "#{path_html_seg(fn,ln)}/#{seg}.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'][/(.+?)\.(?:ssm\.sst|sst)$/,1] - file_suffix=c['src_filename'][/.+?\.(ssm\.sst|sst)$/,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['tid'].to_i != oldtid.to_i - ti=c['title'] - can_txt_srch=(cgi['view']=~/index/) \ - ? %{search } - : %{search } - title=%{toc html #{ti} [#{c['language_document_char']}] by #{c['creator_author']} manifest #{can_txt_srch}
} if file_suffix=~/s/ #hmm watch file_suffix - title=@text_search_flag \ - ? '
'+title - : '
'+title - @counter_txt_doc+=1 - oldtid=c['tid'].to_i - 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'] =~/\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 - oldtid = 0 - 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/util/rb/cgi/sisu_7a_sqlite.cgi b/util/rb/cgi/sisu_7a_sqlite.cgi deleted file mode 100755 index 0fe8ea5..0000000 --- a/util/rb/cgi/sisu_7a_sqlite.cgi +++ /dev/null @@ -1,937 +0,0 @@ -#!/usr/bin/env ruby -=begin - * Name: SiSU information Structuring Universe - * Author: Ralph Amissah - * http://www.jus.uio.no/sisu - * http://www.jus.uio.no/sisu/SiSU/download - - * 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 - - * Hompages: - - - - * Ralph Amissah - - - -=end - begin - require 'cgi' - require 'fcgi' - require 'sqlite3' - rescue LoadError - puts 'cgi, fcgi or sqlite3 NOT FOUND (LoadError)' - end - @stub_default='manual' - @image_src="http://#{ENV['HTTP_HOST']}/_sisu/image_sys" - @hosturl_cgi="http://#{ENV['HTTP_HOST']}#{ENV['PATH_INFO']}" - @hosturl_files="http://#{ENV['HTTP_HOST']}" - @output_dir_structure_by='filetype' - @lingual='multi' - @db_name_prefix='SiSU.7a.' - @base="http://#{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:__; filename:__;
' - 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,:filename - 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('filename:') - @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',search_for.filename,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, metadata_and_text.language_document_char, metadata_and_text.notes_suffix, doc_objects.body, doc_objects.seg, doc_objects.ocn, metadata_and_text.tid FROM doc_objects, metadata_and_text WHERE #{@search_text} AND doc_objects.metadata_tid = metadata_and_text.tid ORDER BY metadata_and_text.language_document_char, metadata_and_text.title, metadata_and_text.src_filename, 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.jus.uio.no/sisu - - and - - www.sisudoc.org - - sources - - git.sisudoc.org - -
- w3 since October 3 1993 - - ralph@amissah.com - -
- mailing list subscription - - http://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, - - http://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 /SiSU.7a.manual/ then '' - end - db_name='sisu_sqlite.db' - db_sqlite=case cgi['db'] - when /SiSU.7a.manual/ 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.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.filename) if @search_for.filename=~/\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=/,'filename: '). - 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=%{filename: #{green}#{@search_for.filename}
} if @search_for.filename =~/\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 - oldtid=0 - 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}/#{@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,ln=nil) - if @output_dir_structure_by =='filename' \ - or @output_dir_structure_by =='filetype' - @lingual =='mono' \ - ? "#{path_html_seg(fn,ln)}/#{seg}.html" - : "#{path_html_seg(fn,ln)}/#{seg}.#{ln}.html" - else - "#{path_html_seg(fn,ln)}/#{seg}.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'][/(.+?)\.(?:ssm\.sst|sst)$/,1] - file_suffix=c['src_filename'][/.+?\.(ssm\.sst|sst)$/,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['tid'].to_i != oldtid.to_i - ti=c['title'] - can_txt_srch=(cgi['view']=~/index/) \ - ? %{search } - : %{search } - title=%{toc html #{ti} [#{c['language_document_char']}] by #{c['creator_author']} manifest #{can_txt_srch}
} if file_suffix=~/s/ #hmm watch file_suffix - title=@text_search_flag \ - ? '
'+title - : '
'+title - @counter_txt_doc+=1 - oldtid=c['tid'].to_i - 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'] =~/\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 - oldtid = 0 - 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/util/rb/cgi/sisu_lng.cgi b/util/rb/cgi/sisu_lng.cgi deleted file mode 100755 index 5e07a16..0000000 --- a/util/rb/cgi/sisu_lng.cgi +++ /dev/null @@ -1,935 +0,0 @@ -#!/usr/bin/env ruby -=begin - * Name: SiSU information Structuring Universe - * Author: Ralph Amissah - * http://www.jus.uio.no/sisu - * http://www.jus.uio.no/sisu/SiSU/download - - * Description: generates naive cgi search form for search of sisu database (pgsql) - * 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 - 2015, 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 - - * Hompages: - - - - * Ralph Amissah - - - -=end - begin - require 'cgi' - require 'fcgi' - require 'pg' - rescue LoadError - puts 'cgi, fcgi or pg NOT FOUND (LoadError)' - end - @stub_default='samples_by_language' - @image_src="http://#{ENV['HTTP_HOST']}/_sisu/image_sys" - @hosturl_cgi="http://#{ENV['HTTP_HOST']}#{ENV['PATH_INFO']}" - @hosturl_files="http://#{ENV['HTTP_HOST']}" - @output_dir_structure_by='language' - @lingual='multi' - @port='5432' - @db_name_prefix='SiSU.7a.' - @user='www-data' # check user name for access to pg database: e.g. www-data or 'ralph' - @base="http://#{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:__; filename:__;
' - 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 - case sensitive -
- 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,:filename - 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('filename:') - @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,@c=l,t,q,cse - 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=if @c - unescaped_search.gsub(/\s*(AND|OR)\s*/,"' \) \\1 #{@l}~\( '"). - gsub(/(.+)/,"#{@l}~\( '\\1' \)") - else - unescaped_search.gsub(/\s*(AND|OR)\s*/,"' \) \\1 #{@l}~*\( '"). - gsub(/(.+)/,"#{@l}~*\( '\\1' \)") - end - 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',search_for.filename,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~[*]?\(\s*'[^']+'\s*\)\s+(?:(?:AND|OR)\s+doc_objects\.clean~[*]?\(\s*'[^']+'\s*\))+)/,'(\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, metadata_and_text.language_document_char, metadata_and_text.notes_suffix, doc_objects.body, doc_objects.seg, doc_objects.ocn, metadata_and_text.tid FROM doc_objects, metadata_and_text WHERE (#{@search_text}) AND doc_objects.metadata_tid = metadata_and_text.tid ORDER BY metadata_and_text.language_document_char, metadata_and_text.title, metadata_and_text.src_filename, 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.exec(sql_select_body) - end - end - def tail - <<-'WOK' -

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

- Generated by - SiSU 7.1.2 2015-05-18 (2015w20/1) -
- - SiSU © Ralph Amissah - 1993, current 2015. - All Rights Reserved. -
- SiSU is software for document structuring, publishing and search, -
- - www.jus.uio.no/sisu - - and - - www.sisudoc.org - - sources - - git.sisudoc.org - -
- w3 since October 3 1993 - - ralph@amissah.com - -
- mailing list subscription - - http://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 2015. - All Rights Reserved. -

-
-

- - .: - -

-		 -

- SiSU is released under - GPL v3 - or later, - - http://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=%{} - @conn=PG::Connection.open(dbname: @db, port: @port, user: @user) - 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.filename) if @search_for.filename=~/\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=/,'filename: '). - 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=%{filename: #{green}#{@search_for.filename}
} if @search_for.filename =~/\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 - oldtid=0 - 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 - else - end - @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,ln=nil) - if @output_dir_structure_by =='filename' \ - or @output_dir_structure_by =='filetype' - @lingual =='mono' \ - ? "#{path_html_seg(fn,ln)}/#{seg}.html" - : "#{path_html_seg(fn,ln)}/#{seg}.#{ln}.html" - else - "#{path_html_seg(fn,ln)}/#{seg}.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'][/(.+?)\.(?:ssm\.sst|sst)$/,1] - file_suffix=c['src_filename'][/.+?\.(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['tid'].to_i != oldtid.to_i - ti=c['title'] - can_txt_srch=(cgi['view']=~/index/) \ - ? %{search } - : %{search } - title=%{toc html #{ti} [#{c['language_document_char']}] by #{c['creator_author']} manifest #{can_txt_srch}
} if file_suffix=~/s/ #hmm watch file_suffix - title=@text_search_flag \ - ? '
'+title - : '
'+title - @counter_txt_doc+=1 - oldtid=c['tid'].to_i - 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=unescaped_search.scan(/\S+/).each.map do |g| - (g.to_s =~/(AND|OR)/) \ - ? ('|') - : (%{#{g.to_s}}) - end.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'] =~/\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 - oldtid = 0 - 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/util/rb/cgi/sisu_search_pg.cgi b/util/rb/cgi/sisu_search_pg.cgi deleted file mode 100755 index 5e07a16..0000000 --- a/util/rb/cgi/sisu_search_pg.cgi +++ /dev/null @@ -1,935 +0,0 @@ -#!/usr/bin/env ruby -=begin - * Name: SiSU information Structuring Universe - * Author: Ralph Amissah - * http://www.jus.uio.no/sisu - * http://www.jus.uio.no/sisu/SiSU/download - - * Description: generates naive cgi search form for search of sisu database (pgsql) - * 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 - 2015, 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 - - * Hompages: - - - - * Ralph Amissah - - - -=end - begin - require 'cgi' - require 'fcgi' - require 'pg' - rescue LoadError - puts 'cgi, fcgi or pg NOT FOUND (LoadError)' - end - @stub_default='samples_by_language' - @image_src="http://#{ENV['HTTP_HOST']}/_sisu/image_sys" - @hosturl_cgi="http://#{ENV['HTTP_HOST']}#{ENV['PATH_INFO']}" - @hosturl_files="http://#{ENV['HTTP_HOST']}" - @output_dir_structure_by='language' - @lingual='multi' - @port='5432' - @db_name_prefix='SiSU.7a.' - @user='www-data' # check user name for access to pg database: e.g. www-data or 'ralph' - @base="http://#{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:__; filename:__;
' - 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 - case sensitive -
- 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,:filename - 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('filename:') - @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,@c=l,t,q,cse - 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=if @c - unescaped_search.gsub(/\s*(AND|OR)\s*/,"' \) \\1 #{@l}~\( '"). - gsub(/(.+)/,"#{@l}~\( '\\1' \)") - else - unescaped_search.gsub(/\s*(AND|OR)\s*/,"' \) \\1 #{@l}~*\( '"). - gsub(/(.+)/,"#{@l}~*\( '\\1' \)") - end - 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',search_for.filename,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~[*]?\(\s*'[^']+'\s*\)\s+(?:(?:AND|OR)\s+doc_objects\.clean~[*]?\(\s*'[^']+'\s*\))+)/,'(\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, metadata_and_text.language_document_char, metadata_and_text.notes_suffix, doc_objects.body, doc_objects.seg, doc_objects.ocn, metadata_and_text.tid FROM doc_objects, metadata_and_text WHERE (#{@search_text}) AND doc_objects.metadata_tid = metadata_and_text.tid ORDER BY metadata_and_text.language_document_char, metadata_and_text.title, metadata_and_text.src_filename, 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.exec(sql_select_body) - end - end - def tail - <<-'WOK' -

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

- Generated by - SiSU 7.1.2 2015-05-18 (2015w20/1) -
- - SiSU © Ralph Amissah - 1993, current 2015. - All Rights Reserved. -
- SiSU is software for document structuring, publishing and search, -
- - www.jus.uio.no/sisu - - and - - www.sisudoc.org - - sources - - git.sisudoc.org - -
- w3 since October 3 1993 - - ralph@amissah.com - -
- mailing list subscription - - http://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 2015. - All Rights Reserved. -

-
-

- - .: - -

-		 -

- SiSU is released under - GPL v3 - or later, - - http://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=%{} - @conn=PG::Connection.open(dbname: @db, port: @port, user: @user) - 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.filename) if @search_for.filename=~/\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=/,'filename: '). - 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=%{filename: #{green}#{@search_for.filename}
} if @search_for.filename =~/\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 - oldtid=0 - 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 - else - end - @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,ln=nil) - if @output_dir_structure_by =='filename' \ - or @output_dir_structure_by =='filetype' - @lingual =='mono' \ - ? "#{path_html_seg(fn,ln)}/#{seg}.html" - : "#{path_html_seg(fn,ln)}/#{seg}.#{ln}.html" - else - "#{path_html_seg(fn,ln)}/#{seg}.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'][/(.+?)\.(?:ssm\.sst|sst)$/,1] - file_suffix=c['src_filename'][/.+?\.(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['tid'].to_i != oldtid.to_i - ti=c['title'] - can_txt_srch=(cgi['view']=~/index/) \ - ? %{search } - : %{search } - title=%{toc html #{ti} [#{c['language_document_char']}] by #{c['creator_author']} manifest #{can_txt_srch}
} if file_suffix=~/s/ #hmm watch file_suffix - title=@text_search_flag \ - ? '
'+title - : '
'+title - @counter_txt_doc+=1 - oldtid=c['tid'].to_i - 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=unescaped_search.scan(/\S+/).each.map do |g| - (g.to_s =~/(AND|OR)/) \ - ? ('|') - : (%{#{g.to_s}}) - end.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'] =~/\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 - oldtid = 0 - 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/util/rb/cgi/sisu_search_sqlite.cgi b/util/rb/cgi/sisu_search_sqlite.cgi deleted file mode 100755 index 0fe8ea5..0000000 --- a/util/rb/cgi/sisu_search_sqlite.cgi +++ /dev/null @@ -1,937 +0,0 @@ -#!/usr/bin/env ruby -=begin - * Name: SiSU information Structuring Universe - * Author: Ralph Amissah - * http://www.jus.uio.no/sisu - * http://www.jus.uio.no/sisu/SiSU/download - - * 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 - - * Hompages: - - - - * Ralph Amissah - - - -=end - begin - require 'cgi' - require 'fcgi' - require 'sqlite3' - rescue LoadError - puts 'cgi, fcgi or sqlite3 NOT FOUND (LoadError)' - end - @stub_default='manual' - @image_src="http://#{ENV['HTTP_HOST']}/_sisu/image_sys" - @hosturl_cgi="http://#{ENV['HTTP_HOST']}#{ENV['PATH_INFO']}" - @hosturl_files="http://#{ENV['HTTP_HOST']}" - @output_dir_structure_by='filetype' - @lingual='multi' - @db_name_prefix='SiSU.7a.' - @base="http://#{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:__; filename:__;
' - 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,:filename - 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('filename:') - @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',search_for.filename,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, metadata_and_text.language_document_char, metadata_and_text.notes_suffix, doc_objects.body, doc_objects.seg, doc_objects.ocn, metadata_and_text.tid FROM doc_objects, metadata_and_text WHERE #{@search_text} AND doc_objects.metadata_tid = metadata_and_text.tid ORDER BY metadata_and_text.language_document_char, metadata_and_text.title, metadata_and_text.src_filename, 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.jus.uio.no/sisu - - and - - www.sisudoc.org - - sources - - git.sisudoc.org - -
- w3 since October 3 1993 - - ralph@amissah.com - -
- mailing list subscription - - http://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, - - http://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 /SiSU.7a.manual/ then '' - end - db_name='sisu_sqlite.db' - db_sqlite=case cgi['db'] - when /SiSU.7a.manual/ 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.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.filename) if @search_for.filename=~/\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=/,'filename: '). - 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=%{filename: #{green}#{@search_for.filename}
} if @search_for.filename =~/\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 - oldtid=0 - 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}/#{@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,ln=nil) - if @output_dir_structure_by =='filename' \ - or @output_dir_structure_by =='filetype' - @lingual =='mono' \ - ? "#{path_html_seg(fn,ln)}/#{seg}.html" - : "#{path_html_seg(fn,ln)}/#{seg}.#{ln}.html" - else - "#{path_html_seg(fn,ln)}/#{seg}.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'][/(.+?)\.(?:ssm\.sst|sst)$/,1] - file_suffix=c['src_filename'][/.+?\.(ssm\.sst|sst)$/,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['tid'].to_i != oldtid.to_i - ti=c['title'] - can_txt_srch=(cgi['view']=~/index/) \ - ? %{search } - : %{search } - title=%{toc html #{ti} [#{c['language_document_char']}] by #{c['creator_author']} manifest #{can_txt_srch}
} if file_suffix=~/s/ #hmm watch file_suffix - title=@text_search_flag \ - ? '
'+title - : '
'+title - @counter_txt_doc+=1 - oldtid=c['tid'].to_i - 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'] =~/\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 - oldtid = 0 - 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/util/rb/cgi/spine.search.cgi b/util/rb/cgi/spine.search.cgi deleted file mode 100755 index cfe9d73..0000000 --- a/util/rb/cgi/spine.search.cgi +++ /dev/null @@ -1,958 +0,0 @@ -#!/usr/bin/env ruby -=begin - * Name: SiSU information Structuring Universe - * Author: Ralph Amissah - * http://www.jus.uio.no/sisu - * http://www.jus.uio.no/sisu/SiSU/download - - * 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 - - * Hompages: - - - - * 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 = "http://#{ENV['HTTP_HOST']}/image_sys" -@hosturl_cgi = "http://#{ENV['HTTP_HOST']}#{ENV['PATH_INFO']}" -@hosturl_files = "http://#{ENV['HTTP_HOST']}" -@output_dir_structure_by = 'language' -@lingual = 'multi' -@db_name_prefix = 'spine.' -@base = "http://#{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.jus.uio.no/sisu - - and - - www.sisudoc.org - - sources - - git.sisudoc.org - -
- w3 since October 3 1993 - - ralph@amissah.com - -
- mailing list subscription - - http://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, - - http://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/util/rb/tex/dr_tex.rb b/util/rb/tex/dr_tex.rb deleted file mode 100755 index 767742c..0000000 --- a/util/rb/tex/dr_tex.rb +++ /dev/null @@ -1,70 +0,0 @@ -#!/usr/bin/env ruby -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