#!/usr/bin/env rdmd /+ sdp: sisu document parser a SiSU document parser writen in D see http://sisudoc.org. +/ module sdp.sisu_document_parser; import sdp.conf.compile_time_info, sdp.meta.metadoc; import std.getopt, std.file, std.path, std.process; import sdp.meta, sdp.meta.metadoc_summary, sdp.meta.metadoc_from_src, sdp.meta.conf_make_meta, // sdp.meta.conf_make_meta_native, sdp.meta.conf_make_meta_sdlang, sdp.meta.conf_make_meta_composite, sdp.meta.defaults, sdp.meta.doc_debugs, sdp.meta.read_config_files, sdp.meta.read_source_files, sdp.meta.rgx, sdp.output.hub, sdp.output.paths_source; mixin(import("version.txt")); mixin CompileTimeInfo; /++ A SiSU document parser writen in D. +/ void main(string[] args) { mixin SiSUrgxInit; mixin SiSUregisters; mixin SiSUextractSDLang; mixin SiSUnode; mixin SiSUbiblio; mixin SiSUrgxInitFlags; mixin outputHub; string flag_action; string arg_unrecognized; enum dAM { abstraction, matters } static auto rgx = Rgx(); scope(success) { debug(checkdoc) { writefln( "~ run complete, ok ~ (sdp-%s.%s.%s, %s v%s, %s %s)", ver.major, ver.minor, ver.patch, __VENDOR__, __VERSION__, bits, os, ); } } scope(failure) { debug(checkdoc) { stderr.writefln( "run failure", ); } } bool[string] opts = [ "assertions" : false, "concordance" : false, "debug" : false, "digest" : false, "docbook" : false, "epub" : false, "html" : false, "html-seg" : false, "html-scroll" : false, "manifest" : false, "ocn" : true, "odt" : false, "pdf" : false, "postgresql" : false, "qrcode" : false, "sisupod" : false, "source" : false, "sqlite-discrete" : false, "sqlite-update" : false, "sqlite-create" : false, "sqlite-drop" : false, "text" : false, "verbose" : false, "xhtml" : false, "xml-dom" : false, "xml-sax" : false, "section_toc" : true, "section_body" : true, "section_endnotes" : true, "section_glossary" : true, "section_biblio" : true, "section_bookindex" : true, "section_blurb" : true, "backmatter" : true, "skip-output" : false, ]; string[string] settings = [ "output-dir" : "", "lang" : "all", ]; auto helpInfo = getopt(args, std.getopt.config.passThrough, "assert", "--assert set optional assertions on", &opts["assertions"], "concordance", "--concordance file for document", &opts["concordance"], "debug", "--debug only relevant when debug options compiled in", &opts["debug"], "digest", "--digest hash digest for each object", &opts["digest"], "docbook", "--docbook process docbook output", &opts["docbook"], "epub", "--epub process epub output", &opts["epub"], "html", "--html process html output", &opts["html"], "html-seg", "--html-seg process html output", &opts["html-seg"], "html-scroll", "--html-seg process html output", &opts["html-scroll"], "manifest", "--manifest process manifest output", &opts["manifest"], "ocn", "--ocn object cite numbers (default)", &opts["ocn"], "odf", "--odf process odf:odt output", &opts["odt"], "odt", "--odt process odf:odt output", &opts["odt"], "pdf", "--pdf process pdf output", &opts["pdf"], "pg", "--pg process postgresql output", &opts["postgresql"], "postgresql", "--postgresql process postgresql output", &opts["postgresql"], "qrcode", "--qrcode with document metadata", &opts["qrcode"], "sisupod", "--sisupod sisupod source content bundled", &opts["sisupod"], "source", "--source markup source text content", &opts["source"], "sqlite-discrete", "--sqlite process discrete sqlite output", &opts["sqlite-discrete"], "sqlite-create", "--sqlite-create create db, create tables", &opts["sqlite-create"], "sqlite-drop", "--sqlite-drop drop tables & db", &opts["sqlite-drop"], "sqlite-update", "--sqlite process sqlite output", &opts["sqlite-update"], "text", "--text process text output", &opts["text"], "txt", "--txt process text output", &opts["text"], "verbose|v", "--verbose output to terminal", &opts["verbose"], "xhtml", "--xhtml process xhtml output", &opts["xhtml"], "xml-dom", "--xml-dom process xml dom output", &opts["xml-dom"], "xml-sax", "--xml-sax process xml sax output", &opts["xml-sax"], "section-toc", "--section-toc process table of contents (default)", &opts["section_toc"], "section-body", "--section-body process document body (default)", &opts["section_body"], "section-endnotes", "--section-endnotes process document endnotes (default)", &opts["section_endnotes"], "section-glossary", "--section-glossary process document glossary (default)", &opts["section_glossary"], "section-biblio", "--section-biblio process document biblio (default)", &opts["section_biblio"], "section-bookindex", "--section-bookindex process document bookindex (default)", &opts["section_bookindex"], "section-blurb", "--section-blurb process document blurb (default)", &opts["section_blurb"], "backmatter", "--section-backmatter process document backmatter (default)", &opts["backmatter"], "skip-output", "--skip-output", &opts["skip-output"], "output-dir", "--output-dir=[dir path]", &settings["output-dir"], "lang", "--lang=[lang code e.g. =en or =en,es]", &settings["lang"], ); if (helpInfo.helpWanted) { defaultGetoptPrinter("Some information about the program.", helpInfo.options); } struct OptActions { auto assertions() { auto _k = opts["assertions"]; return _k; } auto concordance() { auto _k = opts["concordance"]; return _k; } auto debug_do() { auto _k = opts["debug"]; return _k; } auto digest() { auto _k = opts["digest"]; return _k; } auto docbook() { auto _k = opts["docbook"]; return _k; } auto epub() { auto _k = opts["epub"]; return _k; } auto html() { auto _k = opts["html"]; return _k; } auto html_seg() { auto _k = opts["html-seg"]; return _k; } auto html_scroll() { auto _k = opts["html-scroll"]; return _k; } auto manifest() { auto _k = opts["manifest"]; return _k; } auto ocn() { auto _k = opts["ocn"]; return _k; } auto odt() { auto _k = opts["odt"]; return _k; } auto pdf() { auto _k = opts["pdf"]; return _k; } auto postgresql() { auto _k = opts["postgresql"]; return _k; } auto qrcode() { auto _k = opts["qrcode"]; return _k; } auto sisupod() { auto _k = opts["sisupod"]; return _k; } auto source() { auto _k = opts["source"]; return _k; } auto sqlite_discrete() { auto _k = opts["sqlite-discrete"]; return _k; } auto sqlite_update() { auto _k = opts["sqlite-update"]; return _k; } auto sqlite_create() { auto _k = opts["sqlite-create"]; return _k; } auto sqlite_drop() { auto _k = opts["sqlite-drop"]; return _k; } auto text() { auto _k = opts["text"]; return _k; } auto verbose() { auto _k = opts["verbose"]; return _k; } auto xhtml() { auto _k = opts["xhtml"]; return _k; } auto xml_dom() { auto _k = opts["xml-dom"]; return _k; } auto xml_sax() { auto _k = opts["xml-sax"]; return _k; } auto section_toc() { auto _k = opts["section_toc"]; return _k; } auto section_body() { auto _k = opts["section_body"]; return _k; } auto section_endnotes() { auto _k = opts["section_endnotes"]; return _k; } auto section_glossary() { auto _k = opts["section_glossary"]; return _k; } auto section_biblio() { auto _k = opts["section_biblio"]; return _k; } auto section_bookindex() { auto _k = opts["section_bookindex"]; return _k; } auto section_blurb() { auto _k = opts["section_blurb"]; return _k; } auto backmatter() { auto _k = opts["backmatter"]; return _k; } auto skip_output() { auto _k = opts["skip-output"]; return _k; } auto languages_set() { auto _k = settings["lang"].split(","); return _k; } auto output_dir_set() { auto _k = settings["output-dir"]; return _k; } } auto _opt_action = OptActions(); auto _env = [ "pwd" : environment["PWD"], "home" : environment["HOME"], ]; auto _manifest = PodManifest!()(); auto _manifest_plus = PodManifestAndSrcFile!()(_opt_action, _env); auto _manifests = [ _manifest_plus ]; foreach(arg; args[1..$]) { _manifest = PodManifest!()(arg); if (arg.match(rgx.flag_action)) { flag_action ~= " " ~ arg; // flags not taken by getopt } else if (arg.match(rgx.src_pth)) { _manifests ~= PodManifestAndSrcFile!()(_opt_action, _env, arg, arg); // gather input markup source file names for processing } else if (_manifest.pod_manifest_file_with_path) { string contents_location_raw_; string contents_location_; string sisudoc_txt_ = _manifest.pod_manifest_file_with_path; enforce( exists(sisudoc_txt_)!=0, "file not found: «" ~ sisudoc_txt_ ~ "»" ); try { if (exists(sisudoc_txt_)) { contents_location_raw_ = sisudoc_txt_.readText; } } catch (ErrnoException ex) { } catch (FileException ex) { // Handle errors } if (contents_location_raw_.match(rgx.pod_content_location)) { // (file name followed by language codes \n)+ foreach (m; contents_location_raw_.matchAll(rgx.pod_content_location)) { foreach (n; m.captures[2].matchAll(rgx.language_codes)) { contents_location_ ~= "media/text/" ~ n.captures[1].to!string ~ "/" ~ m.captures[1].to!string ~ "\n"; } } } else { // (file name with path \n)+ contents_location_ = contents_location_raw_; } auto contents_locations_arr = (cast(char[]) contents_location_).split; auto tmp_dir_ = (sisudoc_txt_).dirName.array; foreach (contents_location; contents_locations_arr) { assert(contents_location.match(rgx.src_pth), "not a recognised file: «" ~ contents_location ~ "»" ); auto contents_location_pth_ = (contents_location).to!string; auto lang_rgx_ = regex(r"/(" ~ _opt_action.languages_set.join("|") ~ ")/"); if (_opt_action.languages_set[0] == "all" || (contents_location_pth_).match(lang_rgx_) ) { auto _fns = (((tmp_dir_).chainPath(contents_location_pth_)).array).to!(string); _manifest_plus = PodManifestAndSrcFile!()(_opt_action, _env, arg, _fns, contents_locations_arr); _manifests ~= _manifest_plus; // TODO how to capture? } } } else if (arg.match(rgx.src_pth_zip)) { // fns_src ~= arg; // gather input markup source file names for processing } else { // anything remaining, unused arg_unrecognized ~= " " ~ arg; } } if (!(_opt_action.skip_output)) { outputHubOp!()(_opt_action); } if (_manifests.length > 1) { // _manifests[0] is dummy element used in initialization to be removed foreach(manifest; _manifests[1..$]) { if (!empty(manifest.src_fn)) { scope(success) { debug(checkdoc) { writefln( "%s\n%s", "~ document complete, ok ~", "------------------------------------------------------------------", ); } } scope(failure) { debug(checkdoc) { stderr.writefln( "~ document run failure ~ (%s v%s)\n\t%s", __VENDOR__, __VERSION__, src_fn ); } } enforce( manifest.src_fn.match(rgx.src_pth_types), "not a sisu markup filename: «" ~ manifest.src_fn ~ "»" ); auto t = SiSUabstraction!()(manifest, _opt_action, _env); static assert(!isTypeTuple!(t)); static assert(t.length==2); auto doc_abstraction = t[dAM.abstraction]; auto doc_matters = t[dAM.matters]; /+ ↓ debugs +/ if (doc_matters.opt_action.verbose) { SiSUabstractionSummary!()(doc_abstraction, doc_matters); } /+ ↓ debugs +/ if ((doc_matters.opt_action.debug_do) || (doc_matters.opt_action.verbose) ) { SiSUdebugs!()(doc_abstraction, doc_matters); } /+ ↓ output hub +/ if (!(doc_matters.opt_action.skip_output)) { outputHub!()(doc_abstraction, doc_matters); } scope(exit) { debug(checkdoc) { writefln( "processed file: %s", manifest.src_fn ); } destroy(manifest); } } else { /+ no recognized filename provided +/ writeln("no recognized filename"); break; // terminate, stop } } } } unittest { /++ name "sdp" description "A SiSU document parser writen in D." homepage "http://sisudoc.org" +/ }