diff options
Diffstat (limited to 'sundry/misc/util/d')
9 files changed, 1995 insertions, 0 deletions
diff --git a/sundry/misc/util/d/cgi/search/README b/sundry/misc/util/d/cgi/search/README new file mode 100644 index 0000000..eb8fcde --- /dev/null +++ b/sundry/misc/util/d/cgi/search/README @@ -0,0 +1,11 @@ +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/sundry/misc/util/d/cgi/search/dub.sdl b/sundry/misc/util/d/cgi/search/dub.sdl new file mode 100644 index 0000000..30b076d --- /dev/null +++ b/sundry/misc/util/d/cgi/search/dub.sdl @@ -0,0 +1,16 @@ +name "spine_search" +description "A minimal D application." +authors "ralph" +copyright "Copyright © 2021, ralph" +license "GPL-3.0+" +dependency "d2sqlite3" version="~>0.18.3" +dependency "arsd-official": "7.2.0" + subConfiguration "arsd-official:cgi" "cgi" +targetType "executable" +targetPath "./cgi-bin" +mainSourceFile "src/spine_cgi_sqlite_search.d" +configuration "default" { + targetType "executable" + targetName "spine-search" + postGenerateCommands "notify-send -t 0 'D executable ready' 'spine cgi sqlite search d'" +} diff --git a/sundry/misc/util/d/cgi/search/src/spine_cgi_sqlite_search.d b/sundry/misc/util/d/cgi/search/src/spine_cgi_sqlite_search.d new file mode 100644 index 0000000..987c319 --- /dev/null +++ b/sundry/misc/util/d/cgi/search/src/spine_cgi_sqlite_search.d @@ -0,0 +1,963 @@ +/+ +- Name: Spine, Doc Reform [a part of] + - Description: documents, structuring, processing, publishing, search + - static content generator + + - Author: Ralph Amissah + [ralph.amissah@gmail.com] + + - Copyright: (C) 2015 - 2021 Ralph Amissah, All Rights + Reserved. + + - License: AGPL 3 or later: + + Spine (SiSU), a framework for document structuring, publishing and + search + + Copyright (C) Ralph Amissah + + This program is free software: you can redistribute it and/or modify it + under the terms of the GNU AFERO General Public License as published by the + Free Software Foundation, either version 3 of the License, or (at your + option) any later version. + + This program is distributed in the hope that it will be useful, but WITHOUT + ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for + more details. + + You should have received a copy of the GNU General Public License along with + this program. If not, see [https://www.gnu.org/licenses/]. + + If you have Internet connection, the latest version of the AGPL should be + available at these locations: + [https://www.fsf.org/licensing/licenses/agpl.html] + [https://www.gnu.org/licenses/agpl.html] + + - Spine (by Doc Reform, related to SiSU) uses standard: + - docReform markup syntax + - standard SiSU markup syntax with modified headers and minor modifications + - docReform object numbering + - standard SiSU object citation numbering & system + + - Hompages: + [https://www.doc_reform.org] + [https://www.sisudoc.org] + + - Git + [https://git.sisudoc.org/projects/?p=software/spine.git;a=summary] + ++/ +/+ 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 ~ "<br>"); + string[] pair = pair_str.split("="); + canned_query[pair[0]] = pair[1]; + } + // foreach (field, content; canned_query) { + // cgi.write(field ~ ": " ~ content ~ "<br>"); + // } + } + static struct Rgx { + // static canned_query = ctRegex!(`\A(?P<matched>.+)\Z`, "m"); + static search_text_area = ctRegex!(`\A(?P<matched>.+)\Z`, "m"); + // static fulltext = ctRegex!(`\A(?P<matched>.+)\Z`, "m"); + static line = ctRegex!(`^(?P<matched>.+?)(?: ~|$)`, "m"); + static text = ctRegex!(`(?:^|\s~\s*)text:\s+(?P<matched>.+?)(?: ~|$)`, "m"); + static author = ctRegex!(`(?:^|\s~\s*)author:\s+(?P<matched>.+)$`, "m"); + static title = ctRegex!(`(?:^|\s~\s*)title:\s+(?P<matched>.+)$`, "m"); + static uid = ctRegex!(`(?:^|\s~\s*)uid:\s+(?P<matched>.+)$`, "m"); + static fn = ctRegex!(`(?:^|\s~\s*)fn:\s+(?P<matched>.+)$`, "m"); + static keywords = ctRegex!(`(?:^|\s~\s*)keywords:\s+(?P<matched>.+)$`, "m"); + static topic_register = ctRegex!(`(?:^|\s~\s*)topic_register:\s+(?P<matched>.+)$`, "m"); + static subject = ctRegex!(`(?:^|\s~\s*)subject:\s+(?P<matched>.+)$`, "m"); + static description = ctRegex!(`(?:^|\s~\s*)description:\s+(?P<matched>.+)$`, "m"); + static publisher = ctRegex!(`(?:^|\s~\s*)publisher:\s+(?P<matched>.+)$`, "m"); + static editor = ctRegex!(`(?:^|\s~\s*)editor:\s+(?P<matched>.+)$`, "m"); + static contributor = ctRegex!(`(?:^|\s~\s*)contributor:\s+(?P<matched>.+)$`, "m"); + static date = ctRegex!(`(?:^|\s~\s*)date:\s+(?P<matched>.+)$`, "m"); + static results_type = ctRegex!(`(?:^|\s~\s*)type:\s+(?P<matched>.+)$`, "m"); + static format = ctRegex!(`(?:^|\s~\s*)format:\s+(?P<matched>.+)$`, "m"); + static identifier = ctRegex!(`(?:^|\s~\s*)identifier:\s+(?P<matched>.+)$`, "m"); + static source = ctRegex!(`(?:^|\s~\s*)source:\s+(?P<matched>.+)$`, "m"); + static language = ctRegex!(`(?:^|\s~\s*)language:\s+(?P<matched>.+)$`, "m"); + static relation = ctRegex!(`(?:^|\s~\s*)relation:\s+(?P<matched>.+)$`, "m"); + static coverage = ctRegex!(`(?:^|\s~\s*)coverage:\s+(?P<matched>.+)$`, "m"); + static rights = ctRegex!(`(?:^|\s~\s*)rights:\s+(?P<matched>.+)$`, "m"); + static comment = ctRegex!(`(?:^|\s~\s*)comment:\s+(?P<matched>.+)$`, "m"); + // static abstract_ = ctRegex!(`(?:^|\s~\s*)abstract:\s+(?P<matched>.+)$`, "m"); + static src_filename_base = ctRegex!(`^src_filename_base:\s+(?P<matched>.+)$`, "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 ~ "<br>"); + } else if (environment.get("REQUEST_METHOD", "POST") == "GET") { + got.canned_query = environment.get("QUERY_STRING", ""); + // cgi.write("f.canned_query: " ~ got.canned_query ~ "<br>"); + 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 ~ "<br>"); + } + 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<offset_key>[&]smo=)(?P<offset_val>[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 = + "<font size=\"2\" color=\"#666666\">" + ~ "<a href=\"" + ~ _url_previous + ~ "\">" + ~ "<< prev" + ~ "</a> || </font>"; + } + arrow_next = + "<font size=\"2\" color=\"#666666\">" + ~ "<a href=\"" + ~ _url_next + ~ "\">" + ~ "next >>" + ~ "</a></font>"; + _previous_next = "<hr>" ~ arrow_previous ~ arrow_next; + return _previous_next; + } + { + header = format(q"┃ +<!DOCTYPE html> +<html> +<head> + <meta http-equiv="Content-Type" content="text/html; charset=UTF-8" /> + <title> + SiSU spine search form (sample) + </title> + <meta name="sourcefile" content="SiSU.sst" /> + <link rel="generator" href="sisudoc.org" /> + <link rel="shortcut icon" href="https://%s/image_sys/spine.ico" /> + <style media = "all"> + *{ + padding : 0px; + margin : 2px; + } + body { + height : 100vh; + background-color : #FFFFFF; + } + body { + color : #000000; + background : #FFFFFF; + background-color : #FFFFFF; + } + a:link { + color : #003399; + text-decoration : none; + } + a:visited { + color : #003399; + text-decoration : none; + } + a:hover { + color : #000000; + background-color : #F9F9AA; + } + a.lnkocn:link { + color : #777777; + text-decoration : none; + } + a.lnkocn:visited { + color : #32CD32; + text-decoration : none; + } + a.lnkocn:hover { + color : #777777; + font-size : 15px; + } + a:hover img { + background-color : #FFFFFF; + } + a:active { + color : #003399; + text-decoration : underline; + } + hr { + width : 100%%; + margin-left : 0%%; + margin-right : 0em; + margin-top : 0.5em; + margin-bottom : 0.5em; + } +</style> +</head> +<body lang="en" xml:lang="en"> +┃", + conf.http_host, + ); + } + { + table = format(q"┃ + <table summary="band" border="0" cellpadding="2" cellspacing="0"> + <tr><td width="20%%"> + <table summary="home button / home information" border="0" cellpadding="2" cellspacing="0"> + <tr><td align="left"> + <br /><a href="https://sisudoc.org/" target="_top"> + <b>SiSU</b> + </a> + <br /><a href="https://git.sisudoc.org/" target="_top"> + git + </a> + </td></tr> + </table> + </td> + <td> + <label for="find"><b>SiSU spine (generated) search form</b></label> + </td></tr> + </table> + ┃"); + } + { + 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 = + "<font size=\"2\" color=\"#666666\">" + ~ "POST: " + ~ "<a href=\"" + ~ method_post_url_construct + ~ "\">" + ~ method_post_url_construct + ~ "</a></font>" + ~ "<br>"; + } else if (conf.request_method == "GET") { + _the_can = + "<font size=\"2\" color=\"#666666\">" + ~ "GET: " + ~ "<a href=\"" + ~ method_get_url + ~ "\">" + ~ method_get_url + ~ "</a></font>"; + } + 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"┃ +<font size="2" color="#666666"> +<b>database:</b> <font size="2" color="#004000">%s</font>; <b>selected view:</b> <font size="2" color="#004000">index</font> +<b>search string:</b> %s %s %s %s %s %s<br /> +%s %s %s %s %s %s +</font> +┃", + cv.db_selected, + (tf.text.empty ? "" : "\"text: <font size=\"2\" color=\"#004000\">" ~ tf.text ~ "</font>; "), + (tf.title.empty ? "" : "\"title: <font size=\"2\" color=\"#004000\">" ~ tf.title ~ "</font>; "), + (tf.author.empty ? "" : "\"author: <font size=\"2\" color=\"#004000\">" ~ tf.author ~ "</font>; "), + (tf.date.empty ? "" : "\"date <font size=\"2\" color=\"#004000\">" ~ tf.date ~ "</font>; "), + (tf.uid.empty ? "" : "\"uid: <font size=\"2\" color=\"#004000\">" ~ tf.uid ~ "</font>; "), + (tf.fn.empty ? "" : "\"fn: <font size=\"2\" color=\"#004000\">" ~ tf.fn ~ "</font>; "), + (tf.text.empty ? "" : "text: <font size=\"2\" color=\"#004000\">" ~ tf.text ~ "</font><br />"), + (tf.title.empty ? "" : "title: <font size=\"2\" color=\"#004000\">" ~ tf.title ~ "</font><br />"), + (tf.author.empty ? "" : "author: <font size=\"2\" color=\"#004000\">" ~ tf.author ~ "</font><br />"), + (tf.date.empty ? "" : "date: <font size=\"2\" color=\"#004000\">" ~ tf.date ~ "</font><br />"), + (tf.uid.empty ? "" : "\"uid: <font size=\"2\" color=\"#004000\">" ~ tf.uid ~ "</font>; "), + (tf.fn.empty ? "" : "\"fn: <font size=\"2\" color=\"#004000\">" ~ tf.fn ~ "</font>; "), + ); + } + return tip; + } + form = format(q"┃ +<form action="%s" id="SubmitForm" method="post" accept-charset="UTF-8"> + <table cellpadding="2"> + <tr><td valign=\"top\"> + <textarea id="find" name="sf" type="text" rows="6" cols="40" maxlength="256" wrap="virtual">%s</textarea> + </td> + <td valign=\"top\"> + %s + %s + %s + </td></tr></table> + <td valign=\"top\"><tr><td> + <font size="2" color="#222222"> + <b>to search:</b> select which database to search (drop-down menu below); enter your search query (in the form above); and <b>click on the search button</b> (below) + <br /> + <select name="db" size="1"> + %s + <option value="%s">spine</option> + </select> + <input type="submit" value="SiSU search" /> + <input type="radio" name="rt" id="results_type_index" value="idx" %s> index + <input type="radio" name="rt" id="results_type_text" value="txt" %s> text / grep; + match limit: + <input type="radio" name="sml" id="sql_match_limit_1000" value="1000" %s> 1,000 + <input type="radio" name="sml" id="sql_match_limit_2500" value="2500" %s> 2,500 + <br /> + <input type="checkbox" name="ec" %s> echo query + <input type="checkbox" name="sts" %s> result stats + <input type="checkbox" name="url" %s> search url + <input type="checkbox" name="se" %s> searched + <input type="checkbox" name="tip" %s> available fields + <input type="checkbox" name="sql" %s> sql statement + <input type="hidden" name="smo" value="0"> + <br /> + </font> + </td></tr> + </table> +</form> +┃", + "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 ~ "<br>"); + // } + } + { // debug cgi info + // cgi.write("db_selected: " ~ cv.db_selected ~ "<br>\n"); + // cgi.write("search_text: " ~ cv.search_text ~ "<br>\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 ~ "<br>\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") ~ ";<br>\n"); + // cgi.write("cv.checked_tip: " ~ (cv.checked_tip ? "checked" : "off") ~ "; \n"); + // cgi.write("cv.checked_sql: " ~ (cv.checked_sql ? "checked" : "off") ~ "<br>\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 ~ "<hr><font size=\"2\" color=\"#666666\">" ~ sql_select.the_body.split("\n ").join(" ").split("\n").join("<br>") ~ "</font>\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( + "<hr><a href=\"" + ~ "https://" ~ conf.http_host ~ "/" + ~ row["language_document_char"].as!string ~ "/html/" + ~ row["src_filename_base"].as!string ~ "/" + ~ "toc.html" + ~ "\">\"" + ~ row["title"].as!string ~ "\"" + ~ "</a> (" + ~ m.hit + ~ ") " + ~ "[" + ~ row["language_document_char"].as!string + ~ "] " + ~ row["creator_author_last_first"].as!string + ~ ":<br>\n" + ); + } + if (cv.results_type == "txt") { + cgi.write( + "<hr><a href=\"" + ~ "https://" ~ conf.http_host ~ "/" + ~ row["language_document_char"].as!string ~ "/html/" + ~ row["src_filename_base"].as!string ~ "/" + ~ row["seg_name"].as!string ~ ".html#" ~ row["ocn"].as!string + ~ "\">" + ~ row["ocn"].as!string + ~ "</a>" + ~ "<br>" + ~ row["body"].as!string + ); + } else { + cgi.write( + "<a href=\"" + ~ "https://" ~ conf.http_host ~ "/" + ~ row["language_document_char"].as!string ~ "/html/" + ~ row["src_filename_base"].as!string ~ "/" + ~ row["seg_name"].as!string ~ ".html#" ~ row["ocn"].as!string + ~ "\">" + ~ row["ocn"].as!string + ~ "</a>, " + ); + } + } + cgi.write( previous_next); + } else { // offset_not_beyond_limit = false; + cgi.write("select_query_results empty<p>\n"); + } + } + sql_search_query; + } + { + db.close; + } + { + string tail = format(q"┃ +</body> +┃"); + cgi.write(tail); + } +} +mixin GenericMain!cgi_function_intro; diff --git a/sundry/misc/util/d/tools/markup_conversion/README b/sundry/misc/util/d/tools/markup_conversion/README new file mode 100644 index 0000000..8b13789 --- /dev/null +++ b/sundry/misc/util/d/tools/markup_conversion/README @@ -0,0 +1 @@ + diff --git a/sundry/misc/util/d/tools/markup_conversion/endnotes_inline_from_binary.d b/sundry/misc/util/d/tools/markup_conversion/endnotes_inline_from_binary.d new file mode 100755 index 0000000..b084052 --- /dev/null +++ b/sundry/misc/util/d/tools/markup_conversion/endnotes_inline_from_binary.d @@ -0,0 +1,123 @@ +#!/usr/bin/env rdmd +/+ + - read in file .sst .ssi .ssm + - loop twice + - first + - check for and skip code blocks + - use unique code marker for endnote markers in text and give an endnote + number ★1, increment + - extract all endnotes in array + - second + - check that the footnote marker number count matches the number of notes + in the array + - if they match either: + - substitute each endnote marker with the array footnote[number-1] + - substitute each endnote marker with footnote + as inlined footnote markup (footnote number not needed) + - if they do not match exit + - check whether changes have been made + - if so write file with inline footnotes in sub-directory converted_output_/ + using the same name as the original file + - else, exit ++/ +import std.stdio; +import std.file; +import std.array : split; +import std.exception; +import core.stdc.errno; +import std.regex; +import std.format; +import std.conv; +void main(string[] args) { + static comment = ctRegex!(`^%+ `); + static block_tic_code_open = ctRegex!("^`{3} code(?:[.](?P<syntax>[a-z][0-9a-z#+_]+))?(?:[(](?P<attrib>[ a-zA-Z0-9;:,]*)[)])?"); + static block_tic_close = ctRegex!("^(`{3})$","m"); + static block_curly_code_open = ctRegex!(`^(?:code(?:[.](?P<syntax>[a-z][0-9a-z_]+))?(?:[(](?P<attrib>[ a-zA-Z0-9;:,]*)[)])?[{][ ]*$)`); + static block_curly_code_close = ctRegex!(`^([}]code)`); + auto rgx_endnote_ref = ctRegex!(`([~]\^)(?P<tail>[)\]]? |$)`, "gm"); + auto rgx_endnote = ctRegex!(`^\^~\s+(.+|\n)`, "gm"); + foreach(arg; args[1..$]) { + if ( + !(arg.match(regex(r"--\w+"))) + && arg.match(regex(r"\w+?\.ss[itm]")) + ) { + writeln(arg); + string filename = arg; + try { + string[] contents, endnotes, endnote_refs; + string text = filename.readText; + string[] paragraphs = text.split("\n\n"); + int endnote_ref_count = 0; + int code_block_status = 0; + enum codeBlock { off, curly, tic, } + foreach (paragraph; paragraphs) { /+ loop to gather binary endnotes +/ + if (code_block_status == codeBlock.off + && paragraph.match(rgx_endnote) + ) { + endnotes ~= replaceAll!(m => m[1]) + (paragraph, rgx_endnote); + } else { + if ((code_block_status == codeBlock.curly + && paragraph.matchFirst(block_curly_code_close)) + || ((code_block_status == codeBlock.tic + && paragraph.matchFirst(block_tic_close)) + ) { + code_block_status = codeBlock.off; + } else if ( type["curly_code"] == 1 || type["tic_code"] == 1) { + // skip, prevent search for endnotes + } else if (paragraph.matchFirst(block_curly_code_open)) { + code_block_status = codeBlock.curly; + } else if (paragraph.matchFirst(block_tic_code_open)) { + code_block_status = codeBlock.tic; + } else if (auto m = paragraph.matchAll(rgx_endnote_ref)) { + foreach (n; m) { + endnote_ref_count++; // endnote_refs ~= (n.captures[1]); + } + } + contents ~= paragraph; + } + } + if (endnotes.length == endnote_ref_count) { + import std.outbuffer; + writeln("endnote ref count: ", endnote_ref_count); + writeln("number of binary endnotes: ", endnotes.length); + int endnote_count = -1; + auto buffer = new OutBuffer(); + foreach (content; contents) { /+ loop to inline endnotes +/ + content = replaceAll!(m => "~{ " ~ endnotes[++endnote_count] ~ " }~" ~ m["tail"] ) + (content, rgx_endnote_ref); + buffer.write(content ~ "\n\n"); + } + if (buffer) { + try { + string dir_out = "converted_output_"; + string path_and_file_out = dir_out ~ "/" ~ filename; + dir_out.mkdirRecurse; + auto f = File(path_and_file_out, "w"); + f.write(buffer); + writeln("wrote: ", path_and_file_out); + } catch (FileException ex) { + writeln("did not write file"); + // Handle errors + } + } + } else { + writeln("ERROR binary endnote mismatch, check markup,\nmisatch in the number of endnotes & endnote references!"); + writeln(" number of endnotes: ", endnotes.length); + writeln(" number of endnote refs: ", endnote_ref_count); // endnote_refs.length, + } + // assert(endnotes.length == endnote_ref_count); + } catch (ErrnoException ex) { + switch(ex.errno) { + case EPERM: + case EACCES: // Permission denied + break; + case ENOENT: // File does not exist + break; + default: // Handle other errors + break; + } + } + } + } +} diff --git a/sundry/misc/util/d/tools/markup_conversion/markup_changes.d b/sundry/misc/util/d/tools/markup_conversion/markup_changes.d new file mode 100644 index 0000000..4274f78 --- /dev/null +++ b/sundry/misc/util/d/tools/markup_conversion/markup_changes.d @@ -0,0 +1,136 @@ +#!/usr/bin/env rdmd +/+ + - read in file .sst .ssi .ssm + - loop twice + - first + - check for and skip code blocks + - use unique code marker for endnote markers in text and give an endnote + number ★1, increment + - extract all endnotes in array + - second + - check that the footnote marker number count matches the number of notes + in the array + - if they match either: + - substitute each endnote marker with the array footnote[number-1] + - substitute each endnote marker with footnote + as inlined footnote markup (footnote number not needed) + - if they do not match exit + - check whether changes have been made + - if so write file with inline footnotes in sub-directory converted_output_/ + using the same name as the original file + - else, exit ++/ +import std.stdio; +import std.file; +import std.array : split; +import std.exception; +import core.stdc.errno; +import std.regex; +import std.format; +import std.conv; +void main(string[] args) { + static comment = ctRegex!(`^%+ `); + static block_tic_code_open = ctRegex!("^`{3} code(?:[.](?P<syntax>[a-z][0-9a-z#+_]+))?(?:[(](?P<attrib>[ a-zA-Z0-9;:,]*)[)])?"); + static block_tic_close = ctRegex!("^(`{3})$","m"); + static block_curly_code_open = ctRegex!(`^(?:code(?:[.](?P<syntax>[a-z][0-9a-z_]+))?(?:[(](?P<attrib>[ a-zA-Z0-9;:,]*)[)])?[{][ ]*$)`); + static block_curly_code_close = ctRegex!(`^([}]code)`); + auto rgx_endnote_ref = ctRegex!(`([~]\^)(?P<tail>[)\]]? |$)`, "gm"); + auto rgx_endnote = ctRegex!(`^\^~\s+(.+|\n)`, "gm"); + foreach(arg; args[1..$]) { + if ( + !(arg.match(regex(r"--\w+"))) + && arg.match(regex(r"\w+?\.ss[itm]")) + ) { + writeln(arg); + string filename = arg; + try { + string[] contents, endnotes, endnote_refs; + string text = filename.readText; + string[] paragraphs = text.split("\n\n"); + int endnote_ref_count = 0; + int[string] type = [ + "curly_code" : 0, + "tic_code" : 0, + ]; + foreach (paragraph; paragraphs) { /+ loop to gather binary endnotes +/ + if ( !( type["curly_code"] == 1 || type["tic_code"] == 1) + && paragraph.match(rgx_endnote) + ) { + endnotes ~= replaceAll!(m => m[1]) + (paragraph, rgx_endnote); + } else { + if ( type["curly_code"] == 1 || type["tic_code"] == 1 + || paragraph.matchFirst(block_curly_code_open) + || paragraph.matchFirst(block_tic_code_open) + ) { /+ code blocks identified, no munging +/ + if ( type["curly_code"] == 1 + && paragraph.matchFirst(block_curly_code_close) + ) { + type["curly_code"] = 0; + } else if (type["tic_code"] == 1 + && paragraph.matchFirst(block_tic_close) + ) { + type["tic_code"] = 0; + } else if (paragraph.matchFirst(block_curly_code_open)) { + type["curly_code"] = 1; + } else if (paragraph.matchFirst(block_tic_code_open)) { + type["tic_code"] = 1; + } + contents ~= paragraph; + } else { /+ regular content, not a code block +/ + if (auto m = paragraph.matchAll(rgx_endnote_ref)) { + foreach (n; m) { + endnote_ref_count++; // endnote_refs ~= (n.captures[1]); + } + } + paragraph = replaceAll!(m => " \\\\ " ) + (paragraph, regex(r"\s*<(?:/\s*|:)?br>\s*")); // (paragraph, regex(r"(<br>)")); + contents ~= paragraph; + } + } + } + { + import std.outbuffer; + auto buffer = new OutBuffer(); + if (endnotes.length == endnote_ref_count) { + // writeln("endnote ref count: ", endnote_ref_count); + // writeln("number of binary endnotes: ", endnotes.length); + int endnote_count = -1; + foreach (content; contents) { /+ loop to inline endnotes +/ + content = replaceAll!(m => "~{ " ~ endnotes[++endnote_count] ~ " }~" ~ m["tail"] ) + (content, rgx_endnote_ref); // endnote_ref cannot occur in a code block or else fail + buffer.write(content ~ "\n\n"); + } + if (buffer) { + try { + string dir_out = "converted_output_"; + string path_and_file_out = dir_out ~ "/" ~ filename; + dir_out.mkdirRecurse; + auto f = File(path_and_file_out, "w"); + f.write(buffer); + writeln("wrote: ", path_and_file_out); + } catch (FileException ex) { + writeln("did not write file"); + // Handle errors + } + } + } else { + foreach (content; contents) { /+ loop to inline endnotes +/ + buffer.write(content ~ "\n\n"); + } + } + } + } catch (ErrnoException ex) { + switch(ex.errno) { + case EPERM: + case EACCES: // Permission denied + break; + case ENOENT: // File does not exist + break; + default: // Handle other errors + break; + } + } + } + } +} diff --git a/sundry/misc/util/d/tools/markup_conversion/markup_changes_header_and_content.d b/sundry/misc/util/d/tools/markup_conversion/markup_changes_header_and_content.d new file mode 100755 index 0000000..86792ff --- /dev/null +++ b/sundry/misc/util/d/tools/markup_conversion/markup_changes_header_and_content.d @@ -0,0 +1,244 @@ +#!/usr/bin/env rdmd +/+ + - read in file .sst .ssi .ssm + - loop twice + - first + - check for and skip code blocks + - use unique code marker for endnote markers in text and give an endnote + number ★1, increment + - extract all endnotes in array + - second + - check that the footnote marker number count matches the number of notes + in the array + - if they match either: + - substitute each endnote marker with the array footnote[number-1] + - substitute each endnote marker with footnote + as inlined footnote markup (footnote number not needed) + - if they do not match exit + - check whether changes have been made + - if so write file with inline footnotes in sub-directory converted_output_/ + using the same name as the original file + - else, exit ++/ +import std.stdio; +import std.file; +import std.array : split; +import std.exception; +// import std.range; +import core.stdc.errno; +import std.regex; +import std.format; +import std.conv; +void main(string[] args) { + static heading_a = ctRegex!(`^:?[A][~] `, "m"); + static comment = ctRegex!(`^%+ `); + static block_tic_code_open = ctRegex!("^`{3} code(?:[.](?P<syntax>[a-z][0-9a-z#+_]+))?(?:[(](?P<attrib>[ a-zA-Z0-9;:,]*)[)])?"); + static block_tic_close = ctRegex!("^(`{3})$","m"); + static block_curly_code_open = ctRegex!(`^(?:code(?:[.](?P<syntax>[a-z][0-9a-z_]+))?(?:[(](?P<attrib>[ a-zA-Z0-9;:,]*)[)])?[{][ ]*$)`); + static block_curly_code_close = ctRegex!(`^([}]code)`); + auto rgx_endnote_ref = ctRegex!(`([~]\^)(?P<tail>[)\]]? |$)`, "gm"); + auto rgx_endnote = ctRegex!(`^\^~\s+(.+|\n)`, "gm"); + char[][] header0Content1(in string src_text) { // cast(char[]) + /+ split string on _first_ match of "^:?A~\s" into [header, content] array/tuple +/ + char[][] header_and_content; + auto m = (cast(char[]) src_text).matchFirst(heading_a); + header_and_content ~= m.pre; + header_and_content ~= m.hit ~ m.post; + assert(header_and_content.length == 2, + "document markup is broken, header body split == " + ~ header_and_content.length.to!string + ~ "; (header / body array split should == 2 (split is on level A~))" + ); + return header_and_content; + } + foreach(arg; args[1..$]) { + if ( + !(arg.match(regex(r"--\w+"))) + && arg.match(regex(r"\w+?\.ss[itm]")) + ) { + writeln(arg); + string filename = arg; + try { + string[] munged_header, munged_contents, munged_endnotes, endnote_refs; + string text = filename.readText; + char[][] hc = header0Content1(text); + char[] src_header = hc[0]; + string[] headers = src_header.to!string.split("\n\n"); + char[] src_txt = hc[1]; + string[] paragraphs = src_txt.to!string.split("\n\n"); + int endnote_ref_count = 0; + int[string] type = [ + "curly_code" : 0, + "tic_code" : 0, + ]; + string _tmp_header; + foreach (h_; headers) { /+ loop to inline endnotes +/ + _tmp_header = ""; + if (h_.match(regex(r"^[@\[]?title[:\]]?"))) { // title + if (auto m = h_.match(regex(r"^@title:(?:\s+(?P<c>.+)|$)"))) { // sisu bespoke markup + if (m.captures["c"].length == 0) { + _tmp_header ~= "title:"; + } else { + _tmp_header ~= "title:\n main: " ~ "\"" ~ m.captures["c"] ~ "\""; + } + } else if (auto m = h_.match(regex(r"^title\s*=\s*(?P<c>.+)"))) { // toml? + if (m.captures["c"].length == 0) { + _tmp_header ~= "title:"; + } else { + _tmp_header ~= "title:\n main: " ~ "\"" ~ m.captures["c"] ~ "\""; + } + } else if (auto m = h_.match(regex(r"^\[title\]"))) { // toml markup + _tmp_header ~= "title:"; + } else if (auto m = h_.match(regex(r"^title(?:\s+(?P<c>.+)|\s+\\$)"))) { // sdlang markup + if (m.captures["c"].length == 0) { + _tmp_header ~= "title:"; + } else { + _tmp_header ~= "title:\n main: " ~ "\"" ~ m.captures["c"] ~ "\""; + } + } + if (h_.match(regex(r"^\s*[:]?(?:main)[:= ]?", "m"))) { + if (auto m = h_.match(regex(r"^\s+(?P<h>:main):(?:\s+(?P<c>.+)|$)", "m"))) { // sisu bespoke markup + _tmp_header ~= " main: " ~ "\"" ~ m.captures["c"] ~ "\""; + } else if (auto m = h_.match(regex(r"^\s*(?P<h>main)\s*=\s*(?P<c>.+)", "m"))) { // toml? + _tmp_header ~= " main: " ~ m.captures["c"]; + } else if (auto m = h_.match(regex(r"^\s+(?P<h>main)(?:\s*\s*(?P<c>.+)|$)", "m"))) { // toml markup + _tmp_header ~= " main: " ~ "\"" ~ m.captures["c"] ~ "\""; + } else if (auto m = h_.match(regex(r"^\s+(?P<h>main)(?:\s+(?P<c>.+)|\s+\\$)", "m"))) { // sdlang markup + _tmp_header ~= " main: " ~ "\"" ~ m.captures["c"] ~ "\""; + } + } + if (h_.match(regex(r"^\s*[:]?(?:sub(title)?)[:= ]?", "m"))) { + if (auto m = h_.match(regex(r"^\s+:sub(?:title)?:(?:\s+(?P<c>.+)|$)", "m"))) { // sisu bespoke markup + _tmp_header ~= " subtitle: " ~ "\"" ~ m.captures["c"] ~ "\""; + } else if (auto m = h_.match(regex(r"^\s*sub(?:title)?\s*=\s*(?P<c>.+)$", "m"))) { // toml? + _tmp_header ~= " subtitle: " ~ m.captures["c"]; + } else if (auto m = h_.match(regex(r"^\s+(?:title)?(?:\s*\s*(?P<c>.+)|$)", "m"))) { // toml markup + _tmp_header ~= " subtitle: " ~ "\"" ~ m.captures["c"] ~ "\""; + } else if (auto m = h_.match(regex(r"^\s+(?:title)?(?:\s+(?P<c>.+)|\s+\\$)", "m"))) { // sdlang markup + _tmp_header ~= " subtitle: " ~ "\"" ~ m.captures["c"] ~ "\""; + } + } + } + if (h_.match(regex(r"^[@\[]?rights[:\]]?"))) { // rights + if (auto m = h_.match(regex(r"^@rights:[ ]+(?P<c>.+)$"))) { // sisu bespoke markup + _tmp_header ~= "rights: \n copyright: \"" ~ m.captures["c"] ~ "\""; + } else if (auto m = h_.match(regex(r"^@rights:"))) { // sisu bespoke markup + _tmp_header ~= "rights:"; + } else if (auto m = h_.match(regex(r"^\[rights\]", "m"))) { // toml markup + _tmp_header ~= "rights:"; + } else if (auto m = h_.match(regex(r"^rights:"))) { // sdlang markup + _tmp_header ~= "rights:"; + } + if (h_.match(regex(r"^\s*[:]?copyright[:= ]?", "m"))) { + if (auto m = h_.match(regex(r"^\s+:copyright:(?:\s+(?P<c>.+)|$)", "m"))) { // sisu bespoke markup + _tmp_header ~= " copyright: " ~ "\"" ~ m.captures["c"] ~ "\""; + } else if (auto m = h_.match(regex(r"^\s*copyright\s*=\s*(?P<c>.+)", "m"))) { // toml? + _tmp_header ~= " copyright: " ~ m.captures["c"]; + } else if (auto m = h_.match(regex(r"^\s+<h>copyright(?:\s*\s*(?P<c>.+)|$)", "m"))) { // toml markup + _tmp_header ~= " copyright: " ~ "\"" ~ m.captures["c"] ~ "\""; + } else if (auto m = h_.match(regex(r"^\s+copyright(?:\s+(?P<c>.+)|\s+\\$)", "m"))) { // sdlang markup + _tmp_header ~= " copyright: " ~ "\"" ~ m.captures["c"] ~ "\""; + } + } + if (h_.match(regex(r"^\s*[:]?licen[cs]e[:= ]?", "m"))) { + if (auto m = h_.match(regex(r"^\s+:licen[cs]e:(?:\s+(?P<c>.+)|$)", "m"))) { // sisu bespoke markup + _tmp_header ~= " license: " ~ "\"" ~ m.captures["c"] ~ "\""; + } else if (auto m = h_.match(regex(r"^\s*licen[cs]e\s*=\s*(?P<c>.+)$", "m"))) { // toml? + _tmp_header ~= " license: " ~ m.captures["c"]; + } else if (auto m = h_.match(regex(r"^\s+licen[cs]e(?:\s*\s*(?P<c>.+)|$)", "m"))) { // toml markup + _tmp_header ~= " license: " ~ "\"" ~ m.captures["c"] ~ "\""; + } else if (auto m = h_.match(regex(r"^\s+licen[cs]e(?:\s+(?P<c>.+)|\s+\\$)", "m"))) { // sdlang markup + _tmp_header ~= " license: " ~ "\"" ~ m.captures["c"] ~ "\""; + } + } + } + if (_tmp_header.length > 0) { + munged_header ~= _tmp_header; + } else { + munged_header ~= h_; + } + } + writeln(munged_header); + foreach (paragraph; paragraphs) { /+ loop to gather binary endnotes +/ + if ( !( type["curly_code"] == 1 || type["tic_code"] == 1) + && paragraph.match(rgx_endnote) + ) { + munged_endnotes ~= replaceAll!(m => m[1]) + (paragraph, rgx_endnote); + } else { + if ( type["curly_code"] == 1 || type["tic_code"] == 1 + || paragraph.matchFirst(block_curly_code_open) + || paragraph.matchFirst(block_tic_code_open) + ) { /+ code blocks identified, no munging +/ + if ( type["curly_code"] == 1 + && paragraph.matchFirst(block_curly_code_close) + ) { + type["curly_code"] = 0; + } else if (type["tic_code"] == 1 + && paragraph.matchFirst(block_tic_close) + ) { + type["tic_code"] = 0; + } else if (paragraph.matchFirst(block_curly_code_open)) { + type["curly_code"] = 1; + } else if (paragraph.matchFirst(block_tic_code_open)) { + type["tic_code"] = 1; + } + munged_contents ~= paragraph; + } else { /+ regular content, not a code block +/ + if (auto m = paragraph.matchAll(rgx_endnote_ref)) { + foreach (n; m) { + endnote_ref_count++; // endnote_refs ~= (n.captures[1]); + } + } + paragraph = replaceAll!(m => " \\\\ " ) + (paragraph, regex(r"\s*<(?:/\s*|:)?br>\s*")); // (paragraph, regex(r"(<br>)")); + munged_contents ~= paragraph; + } + } + } + { + import std.outbuffer; + auto buffer = new OutBuffer(); + foreach (header; munged_header) { /+ loop to inline endnotes +/ + buffer.write(header ~ "\n\n"); + } + if (munged_endnotes.length == endnote_ref_count) { + int endnote_count = -1; + foreach (content; munged_contents) { /+ loop to inline endnotes +/ + content = replaceAll!(m => "~{ " ~ munged_endnotes[++endnote_count] ~ " }~" ~ m["tail"] ) + (content, rgx_endnote_ref); // endnote_ref cannot occur in a code block or else fail + buffer.write(content ~ "\n\n"); + } + if (buffer) { + try { + string dir_out = "converted_output_"; + string path_and_file_out = dir_out ~ "/" ~ filename; + dir_out.mkdirRecurse; + auto f = File(path_and_file_out, "w"); + f.write(buffer); + // writeln("wrote: ", path_and_file_out); + } catch (FileException ex) { + writeln("did not write file"); + // Handle errors + } + } + } else { + foreach (content; munged_contents) { /+ loop to inline endnotes +/ + buffer.write(content ~ "\n\n"); + } + } + } + } catch (ErrnoException ex) { + switch(ex.errno) { + case EPERM: + case EACCES: // Permission denied + break; + case ENOENT: // File does not exist + break; + default: // Handle other errors + break; + } + } + } + } +} diff --git a/sundry/misc/util/d/tools/markup_conversion/markup_conversion_from_sisu_ruby_to_sisu_spine.d b/sundry/misc/util/d/tools/markup_conversion/markup_conversion_from_sisu_ruby_to_sisu_spine.d new file mode 100755 index 0000000..0ec541d --- /dev/null +++ b/sundry/misc/util/d/tools/markup_conversion/markup_conversion_from_sisu_ruby_to_sisu_spine.d @@ -0,0 +1,367 @@ +#!/usr/bin/env rdmd +/+ + - read in file .sst .ssi .ssm + - loop twice + - first + - check for and skip code blocks + - use unique code marker for endnote markers in text and give an endnote + number ★1, increment + - extract all endnotes in array + - second + - check that the footnote marker number count matches the number of notes + in the array + - if they match either: + - substitute each endnote marker with the array footnote[number-1] + - substitute each endnote marker with footnote + as inlined footnote markup (footnote number not needed) + - if they do not match exit + - check whether changes have been made + - if so write file with inline footnotes in sub-directory converted_output_/ + using the same name as the original file + - else, exit ++/ +import std.stdio; +import std.file; +import std.array : split, join; +import std.exception; +// import std.range; +import core.stdc.errno; +import std.regex; +import std.format; +import std.conv; +void main(string[] args) { + static heading_a = ctRegex!(`^:?[A][~] `, "m"); + static comment = ctRegex!(`^%+ `); + static block_tic_code_open = ctRegex!("^`{3} code(?:[.](?P<syntax>[a-z][0-9a-z#+_]+))?(?:[(](?P<attrib>[ a-zA-Z0-9;:,]*)[)])?"); + static block_tic_close = ctRegex!("^(`{3})$","m"); + static block_curly_code_open = ctRegex!(`^(?:code(?:[.](?P<syntax>[a-z][0-9a-z_]+))?(?:[(](?P<attrib>[ a-zA-Z0-9;:,]*)[)])?[{][ ]*$)`); + static block_curly_code_close = ctRegex!(`^([}]code)`); + auto rgx_endnote_ref = ctRegex!(`([~]\^)(?P<tail>[)\]]? |$)`, "gm"); + auto rgx_endnote = ctRegex!(`^\^~\s+(.+|\n)`, "gm"); + char[][] header0Content1(in string src_text) { // cast(char[]) + /+ split string on _first_ match of "^:?A~\s" into [header, content] array/tuple +/ + char[][] header_and_content; + auto m = (cast(char[]) src_text).matchFirst(heading_a); + header_and_content ~= m.pre; + header_and_content ~= m.hit ~ m.post; + assert(header_and_content.length == 2, + "document markup is broken, header body split == " + ~ header_and_content.length.to!string + ~ "; (header / body array split should == 2 (split is on level A~))" + ); + return header_and_content; + } + string format_body_string(string s) { + string o; + o = s + .replaceAll(regex("^<(?:/[ ]*)?br>[ ]*"), " \\\\ ") + .replaceAll(regex("[ ]*<(?:/[ ]*)?br>$"), " \\\\") + .replaceAll(regex("[ ]*<(?:/[ ]*)?br>[ ]*"), " \\\\ "); + return o; + } + string format_header_string(string s) { + string o; + o = s + .replaceAll(regex("\""), "\\\"") + .replaceAll(regex("[ ]*<(?:/[ ]*)?br>$"), " \\\\") + .replaceAll(regex("[ ]*<(?:/[ ]*)?br>[ ]*"), " \\\\ "); + return o; + } + string format_main_header(string hm, string hs = "", string c = "") { + string o; + if (c.length == 0) { + o ~= hm ~ ":\n"; + } else { + o ~= hm ~ ":\n" + ~ " " ~ hs ~ ": " + ~ "\"" ~ format_header_string(c) ~ "\"\n"; + } + return o; + } + string format_sub_header(string hs, string c) { + string o; + o ~= " " ~ hs ~ ": " + ~ "\"" ~ format_header_string(c) ~ "\"\n"; + return o; + } + foreach(arg; args[1..$]) { + if ( + !(arg.match(regex(r"--\w+"))) + && arg.match(regex(r"\w+?\.ss[itm]")) + ) { + writeln(arg); + string filename = arg; + try { + string[] munged_header, munged_contents, munged_endnotes, endnote_refs; + char[][] hc; + char[] src_header; + string[] headers; + char[] src_txt; + string[] paragraphs; + enum codeBlock { off, curly, tic, } + string _tmp_header; + int endnote_ref_count = 0; + int code_block_status = codeBlock.off; + string text = filename.readText; + if (arg.match(regex(r"\w+?\.ss[tm]"))) { + hc = header0Content1(text); + src_header = hc[0]; + headers = src_header.to!string.split("\n\n"); + src_txt = hc[1]; + paragraphs = src_txt.to!string.split("\n\n"); + } else if (arg.match(regex(r"\w+?\.ssi"))) { + headers = []; + paragraphs = text.split("\n\n"); + } + if (headers.length > 0) { + headers[0] = headers[0].replaceFirst(regex(r"^%\s+SiSU.+", "i"), "# SiSU 8.0 spine (auto-conversion)"); + foreach (h_; headers) { + _tmp_header = ""; + if (auto m = h_.match(regex(r"^%\s*", "m"))) { + h_ = h_.replaceAll(regex(r"^%\s*", "m"), "# ") ~ "\n"; + } + if (h_.match(regex(r"^@title:|@subtitle"))) { + if (auto m = h_.match(regex(r"^@(?P<h>title):(?:[ ]+(?P<c>.+)|\n)"))) { + _tmp_header ~= format_main_header(m.captures["h"], "main", m.captures["c"]); + } + if (auto m = h_.match(regex(r"^@(?P<h>subtitle):(?:[ ]+(?P<c>.+)|$)"))) { + if (m.captures["c"].length == 0) { + } else { + _tmp_header ~= format_sub_header(m.captures["h"], m.captures["c"]); + } + } + if (auto m = h_.match(regex(r"^\s+:(?P<h>main):(?:[ ]+(?P<c>.+)|$)", "m"))) { + _tmp_header ~= format_sub_header(m.captures["h"], m.captures["c"]); + } + if (auto m = h_.match(regex(r"^\s+:sub(?:title)?:(?:[ ]+(?P<c>.+)|$)", "m"))) { + _tmp_header ~= format_sub_header("subtitle", m.captures["c"]); + } + } else if (h_.match(regex(r"^@creator:|@author:"))) { + if (auto m = h_.match(regex(r"^(?:@creator:|@author:)(?:[ ]+(?P<c>.+)|\n)"))) { + _tmp_header ~= format_main_header("creator", "author", m.captures["c"]); + } + if (auto m = h_.match(regex(r"^\s+:(?P<h>author):(?:[ ]+(?P<c>.+)|$)", "m"))) { + _tmp_header ~= format_sub_header(m.captures["h"], m.captures["c"]); + } + } else if (h_.match(regex(r"^@rights:"))) { + if (auto m = h_.match(regex(r"^@(?P<h>rights):(?:[ ]+(?P<c>.+)|\n)"))) { + _tmp_header ~= format_main_header(m.captures["h"], "copyright", m.captures["c"]); + } + if (auto m = h_.match(regex(r"^\s+:(?P<h>copyright):(?:[ ]+(?P<c>.+)|$)", "m"))) { + _tmp_header ~= format_sub_header(m.captures["h"], m.captures["c"]); + } + if (auto m = h_.match(regex(r"^\s+:licen[cs]e:(?:[ ]+(?P<c>.+)|$)", "m"))) { + _tmp_header ~= format_sub_header("license", m.captures["c"]); + } + } else if (h_.match(regex(r"^@date:|@date\."))) { + if (auto m = h_.match(regex(r"^@(?P<h>date):(?:[ ]+(?P<c>.+)|\n)"))) { + _tmp_header ~= format_main_header(m.captures["h"], "published", m.captures["c"]); + } + if (auto m = h_.match(regex(r"^\s+:(?P<h>published):(?:[ ]+(?P<c>.+)|$)", "m"))) { + _tmp_header ~= format_sub_header(m.captures["h"], m.captures["c"]); + } + if (auto m = h_.match(regex(r"^\s+:(?P<h>available):(?:[ ]+(?P<c>.+)|$)", "m"))) { + _tmp_header ~= format_sub_header(m.captures["h"], m.captures["c"]); + } + if (auto m = h_.match(regex(r"^\s+:(?P<h>modified):(?:[ ]+(?P<c>.+)|$)", "m"))) { + _tmp_header ~= format_sub_header(m.captures["h"], m.captures["c"]); + } + if (auto m = h_.match(regex(r"^\s+:(?P<h>created):(?:[ ]+(?P<c>.+)|$)", "m"))) { + _tmp_header ~= format_sub_header(m.captures["h"], m.captures["c"]); + } + if (auto m = h_.match(regex(r"^\s+:(?P<h>issued):(?:[ ]+(?P<c>.+)|$)", "m"))) { + _tmp_header ~= format_sub_header(m.captures["h"], m.captures["c"]); + } + if (auto m = h_.match(regex(r"^\s+:(?P<h>valid):(?:[ ]+(?P<c>.+)|$)", "m"))) { + _tmp_header ~= format_sub_header(m.captures["h"], m.captures["c"]); + } + if (auto m = h_.match(regex(r"^@date\.(?P<h>available):[ ]+(?P<c>.+)$"))) { + _tmp_header ~= format_sub_header(m.captures["h"], m.captures["c"]); + } + if (auto m = h_.match(regex(r"^@date\.(?P<h>modified):[ ]+(?P<c>.+)$"))) { + _tmp_header ~= format_sub_header(m.captures["h"], m.captures["c"]); + } + if (auto m = h_.match(regex(r"^@date\.(?P<h>created):[ ]+(?P<c>.+)$"))) { + _tmp_header ~= format_sub_header(m.captures["h"], m.captures["c"]); + } + if (auto m = h_.match(regex(r"^@date\.(?P<h>issued):[ ]+(?P<c>.+)$"))) { + _tmp_header ~= format_sub_header(m.captures["h"], m.captures["c"]); + } + if (auto m = h_.match(regex(r"^@date\.(?P<h>valid):[ ]+(?P<c>.+)$"))) { + _tmp_header ~= format_sub_header(m.captures["h"], m.captures["c"]); + } + } else if (h_.match(regex(r"^@classify:"))) { + if (auto m = h_.match(regex(r"^@classify:"))) { + _tmp_header ~= "classify:\n"; + } + if (auto m = h_.match(regex(r"^\s+:(?P<h>topic_register):(?:[ ]+(?P<c>.+)|$)", "m"))) { + _tmp_header ~= format_sub_header(m.captures["h"], m.captures["c"]); + } + if (auto m = h_.match(regex(r"^\s+:type:(?:[ ]+(?P<c>.+)|$)", "m"))) { + _tmp_header ~= "# type: " ~ "\"" ~ m.captures["c"] ~ "\"\n"; + } + } else if (h_.match(regex(r"^(?:@identifier:|@identify:)"))) { + if (auto m = h_.match(regex(r"^(?:@identifier:|@idenfify)"))) { + _tmp_header ~= "identify:\n"; + } + if (auto m = h_.match(regex(r"^\s+:(?P<h>oclc):(?:[ ]+(?P<c>.+)|$)", "m"))) { + _tmp_header ~= format_sub_header(m.captures["h"], m.captures["c"]); + } + if (auto m = h_.match(regex(r"^\s+:(?P<h>isbn):(?:[ ]+(?P<c>.+)|$)", "m"))) { + _tmp_header ~= format_sub_header(m.captures["h"], m.captures["c"]); + } + if (auto m = h_.match(regex(r"^\s+:(?P<h>dewey):(?:[ ]+(?P<c>.+)|$)", "m"))) { + _tmp_header ~= format_sub_header(m.captures["h"], m.captures["c"]); + } + } else if (h_.match(regex(r"^@publisher:"))) { + if (auto m = h_.match(regex(r"^@publisher:[ ]+(?P<c>.+)$"))) { + _tmp_header ~= "publisher: " ~ "\"" ~ m.captures["c"] ~ "\"\n"; + } + } else if (h_.match(regex(r"^@make:"))) { + // writeln(h_); + if (auto m = h_.match(regex(r"^@make:"))) { + _tmp_header ~= "make:\n"; + } + if (auto m = h_.match(regex(r"^\s+:(?P<h>breaks):(?:[ ]+(?P<c>.+)|$)", "m"))) { + _tmp_header ~= format_sub_header(m.captures["h"], m.captures["c"]); + } + if (auto m = h_.match(regex(r"^\s+:(?P<h>num_top):(?:[ ]+(?P<c>.+)|$)", "m"))) { + _tmp_header ~= format_sub_header(m.captures["h"], m.captures["c"]); + } + if (auto m = h_.match(regex(r"^\s+:(?P<h>headings):(?:[ ]+(?P<c>.+)|$)", "m"))) { + _tmp_header ~= format_sub_header(m.captures["h"], m.captures["c"]); + } + if (auto m = h_.match(regex(r"^\s+:(?P<h>italics):(?:[ ]+(?P<c>.+)|$)", "m"))) { + _tmp_header ~= format_sub_header(m.captures["h"], m.captures["c"]); + } + if (auto m = h_.match(regex(r"^\s+:(?P<h>bold):(?:[ ]+(?P<c>.+)|$)", "m"))) { + _tmp_header ~= format_sub_header(m.captures["h"], m.captures["c"]); + } + if (auto m = h_.match(regex(r"^\s+:(?P<h>emphasis):(?:[ ]+(?P<c>.+)|$)", "m"))) { + _tmp_header ~= format_sub_header(m.captures["h"], m.captures["c"]); + } + if (auto m = h_.match(regex(r"^\s+:(?P<h>substitute):(?:[ ]+(?P<c>.+)|$)", "m"))) { + _tmp_header ~= format_sub_header(m.captures["h"], m.captures["c"]); + } + if (auto m = h_.match(regex(r"^\s+:(?P<h>texpdf_font):(?:[ ]+(?P<c>.+)|$)", "m"))) { + _tmp_header ~= format_sub_header(m.captures["h"], m.captures["c"]); + } + if (auto m = h_.match(regex(r"^\s+:(?P<h>home_button_text):(?:[ ]+(?P<c>.+)|$)", "m"))) { + _tmp_header ~= format_sub_header(m.captures["h"], m.captures["c"]); + } + if (auto m = h_.match(regex(r"^\s+:(?P<h>home_button_image):(?:[ ]+(?P<c>.+)|$)", "m"))) { + _tmp_header ~= format_sub_header(m.captures["h"], m.captures["c"]); + } + if (auto m = h_.match(regex(r"^\s+:(?P<h>cover_image):(?:[ ]+(?P<c>.+)|$)", "m"))) { + _tmp_header ~= format_sub_header(m.captures["h"], m.captures["c"]); + } + if (auto m = h_.match(regex(r"^\s+:(?P<h>footer):(?:[ ]+(?P<c>.+)|$)", "m"))) { + _tmp_header ~= format_sub_header(m.captures["h"], m.captures["c"]); + } + // writeln(_tmp_header); + } else if (h_.match(regex(r"^@\w+:"))) { + _tmp_header ~= "# " ~ h_.split("\n").join("\n# ") ~ "\n"; + } else if (h_.match(regex(r"^\s+:\w+:", "m"))) { + if (auto m = h_.match(regex(r"^(?P<g>\s+:\w+:.*)"))) { + _tmp_header ~= "# " ~ m.captures["g"] ~ "\n"; + } + } + if (h_.match(regex(r"^#", "m"))) { + if (auto m = h_.match(regex(r"^(?P<g>#.*)", "m"))) { + _tmp_header ~= m.captures["g"] ~ "\n"; + } + } + if (_tmp_header.length > 0) { + munged_header ~= _tmp_header.split("\n\n"); + } else if (h_.length > 0) { + writeln("munging required: ", h_); + h_ = h_.replaceAll((regex(r"\n\n\n+", "m")), "\n\n"); + munged_header ~= h_; + } + } + // writeln(munged_header.join("\n")); + } + foreach (paragraph; paragraphs) { /+ loop to gather binary endnotes +/ + if (code_block_status == codeBlock.off + && paragraph.match(rgx_endnote) + ) { + munged_endnotes ~= replaceAll!(m => m[1]) + (paragraph, rgx_endnote); + } else { + if ( code_block_status != codeBlock.off + || paragraph.matchFirst(block_curly_code_open) + || paragraph.matchFirst(block_tic_code_open) + ) { /+ code blocks identified, no munging +/ + if ((code_block_status == codeBlock.curly + && paragraph.matchFirst(block_curly_code_close)) + || (code_block_status == codeBlock.tic + && paragraph.matchFirst(block_tic_close)) + ) { + code_block_status = codeBlock.off; + } else if (paragraph.matchFirst(block_curly_code_open)) { + code_block_status = codeBlock.curly; + } else if (paragraph.matchFirst(block_tic_code_open)) { + code_block_status = codeBlock.tic; + } + munged_contents ~= paragraph; + } else { /+ regular content, not a code block +/ + if (auto m = paragraph.matchAll(rgx_endnote_ref)) { + foreach (n; m) { + endnote_ref_count++; // endnote_refs ~= (n.captures[1]); + } + } + paragraph = format_body_string(paragraph); + // paragraph = replaceAll!(m => " \\\\ " ) + // (paragraph, regex(r"\s*<(?:/\s*|:)?br>\s*")); // (paragraph, regex(r"(<br>)")); + munged_contents ~= paragraph; + } + } + } + { + import std.outbuffer; + auto buffer = new OutBuffer(); + if (munged_header.length > 0) { + foreach (header; munged_header) { /+ loop to inline endnotes +/ + buffer.write(header ~ "\n"); + } + } + if (munged_endnotes.length == endnote_ref_count) { + int endnote_count = -1; + foreach (k, content; munged_contents) { /+ loop to inline endnotes +/ + content = replaceAll!(m => "~{ " ~ munged_endnotes[++endnote_count] ~ " }~" ~ m["tail"] ) + (content, rgx_endnote_ref); // endnote_ref cannot occur in a code block or else fail + buffer.write(content ~ ((k == munged_contents.length - 1) ? "" : "\n\n")); + } + if (buffer) { + try { + string dir_out = "converted_output_"; + string path_and_file_out = dir_out ~ "/" ~ filename; + dir_out.mkdirRecurse; + auto f = File(path_and_file_out, "w"); + f.write(buffer); + // writeln("wrote: ", path_and_file_out); + } catch (FileException ex) { + writeln("did not write file"); + // Handle errors + } + } + } else { + foreach (content; munged_contents) { /+ loop to inline endnotes +/ + buffer.write(content ~ "\n\n"); + } + } + } + } catch (ErrnoException ex) { + switch(ex.errno) { + case EPERM: + case EACCES: // Permission denied + break; + case ENOENT: // File does not exist + break; + default: // Handle other errors + break; + } + } + } + } +} diff --git a/sundry/misc/util/d/tools/spine_scaffold.d b/sundry/misc/util/d/tools/spine_scaffold.d new file mode 100755 index 0000000..dbcc857 --- /dev/null +++ b/sundry/misc/util/d/tools/spine_scaffold.d @@ -0,0 +1,134 @@ +#!/usr/bin/env rund +void main( string[] args ) { + import std; + if (args.length > 1) { + string base_fn_path = args[1].expandTilde; + string base_fn = base_fn_path.baseName; + string sst_fn = base_fn ~ ".sst"; + string txt_for_pod_manifest = format(q"┃doc: + filename: %s + language: en +┃", + sst_fn + ); + string txt_for_sisu_document_make = format(q"┃ +┃", + ); + string txt_for_document_scaffold = format(q"┃# SiSU 8.0 + +title: "As Yet Unnamed" + +creator: + author: "Annon, Unnamed" + +:A~ @title @author + +1~ Summary + +To get you started, the first paragraph following a section or chapter heading. + +Spine / SiSU documents minimum requirements: + +_* a header containing document metadata that must at least contain the fields Title and Creator Author. + +_* text body, identified as starting by the A~ marker at the start of a line, followed by at least one level 1~ section heading with the text that follows it.~{ the document provided here would be a valid Spine document, and this text contained within the tilde and curly braces delimiters would be the first footnote/endnote }~ + +To generate this document to have html and epub output for example you would run: + +``` code +spine --html --epub --output=/tmp/spine-sample-output %s +``` + +1~ Conclusion + +This sample pod is provided to get you started. + +Good luck and good speed. +┃", + base_fn_path + ); + if (!exists(base_fn_path)) { + try { + base_fn_path.mkdirRecurse; + } catch (ErrnoException ex) { + writeln(ex); + } + if (exists(args[1].expandTilde)) { + try { + base_fn_path.buildPath("conf").mkdirRecurse; + } catch (ErrnoException ex) { + writeln(ex); + } + try { + base_fn_path.buildPath("media/text/en").mkdirRecurse; + } catch (ErrnoException ex) { + writeln(ex); + } + { + // 1 // create/write pod.manifest + string fn = base_fn_path.buildPath("pod.manifest"); + File(fn, "w").writeln(txt_for_pod_manifest); + string tell = format(q"┃OK - pod.manifest (yaml file containing filename and languages) + %s +%s +┃", + fn, + txt_for_pod_manifest.strip + ); + writeln(tell); + } + if (exists(base_fn_path.buildPath("conf"))) { + // 2 // create/write conf/sisu_document_make + string fn = base_fn_path.buildPath("conf/sisu_document_make"); + File(fn, "w").writeln(txt_for_sisu_document_make); + // auto f = File(fn, "w"); + // foreach (line; content_array) { + // f.writeln(line); + // } + string tell = format(q"┃OK - sisu_document_make + %s +┃", + fn + ); + writeln(tell); + } + if (exists(base_fn_path.buildPath("media/text/en"))) { + // 3 // create/write media/text/[lang code]/[filename].sst + string fn = base_fn_path.buildPath("media/text/en/" ~ sst_fn); + File(fn, "w").writeln(txt_for_document_scaffold); + // auto f = File(fn, "w"); + // foreach (line; content_array) { + // f.writeln(line); + // } + string tell = format(q"┃OK - .sst [document text content] + %s + - To start editing document (spine pod content): + ${EDITOR} %s + - To generate this document to have html and epub output for example you would run: + spine --html --epub --output=/tmp/spine-sample-output %s +┃", + fn, + fn, + base_fn_path + ); + writeln(tell); + } + } + /+ + pod/[filename] + │ + ├── conf + │ └── sisu_document_make + ├── media + │ └── text + │ └── en + │ └── [filename].charles_stross.sst + └── pod.manifest + +/ + } else { + writeln("requested output pod name with path already exists:\n ", args[1].expandTilde); + } + } else { + writeln( "please provide directory path to operate on, e.g.\n spine_scaffold.d ./pod/filetest" ); + } +} |