diff options
author | Ralph Amissah <ralph@amissah.com> | 2017-04-12 15:23:23 -0400 |
---|---|---|
committer | Ralph Amissah <ralph@amissah.com> | 2019-04-10 15:14:14 -0400 |
commit | da0f051e1aced4fa1fd5cd13c0548279bf04b2a0 (patch) | |
tree | 3c74421c4ce35e28e93512eb01606219e37e0dfb /org | |
parent | start work on block outputs (diff) |
0.13.9 sisupod & epub3, zipped output
Diffstat (limited to 'org')
-rw-r--r-- | org/ao_debugs.org | 10 | ||||
-rw-r--r-- | org/ao_doc_abstraction.org | 38 | ||||
-rw-r--r-- | org/defaults.org | 218 | ||||
-rw-r--r-- | org/output.org | 932 | ||||
-rw-r--r-- | org/sdp.org | 8 |
5 files changed, 902 insertions, 304 deletions
diff --git a/org/ao_debugs.org b/org/ao_debugs.org index c35ff2e..39fdbac 100644 --- a/org/ao_debugs.org +++ b/org/ao_debugs.org @@ -301,7 +301,7 @@ debug(section_body) { #+name: ao_output_debugs #+BEGIN_SRC d -debug(dom) { +debug(toc_nav_dom) { enum DomTags { none, open, close, close_and_open, open_still, } foreach (sect; doc_matters.keys_seq_seg) { foreach (obj; contents[sect]) { @@ -313,10 +313,10 @@ debug(dom) { break; case DomTags.close_and_open : writeln(markup.indent_by_spaces_provided(k), "</", k, ">"); - writeln(markup.indent_by_spaces_provided(k), "<", k, ">", obj.text); + writeln(markup.indent_by_spaces_provided(k), "<", k, ">", obj.text, " file: ", obj.segment_anchor_tag, ".xhtml#", obj.ocn); break; case DomTags.open : - writeln(markup.indent_by_spaces_provided(k), "<", k, ">", obj.text); + writeln(markup.indent_by_spaces_provided(k), "<", k, ">", obj.text, " file: ", obj.segment_anchor_tag, ".xhtml#", obj.ocn); break; default : break; @@ -336,10 +336,10 @@ debug(dom) { break; case DomTags.close_and_open : writeln(markup.indent_by_spaces_provided(k), "</", k, ">"); - writeln(markup.indent_by_spaces_provided(k), "<", k, ">", obj.text); + writeln(markup.indent_by_spaces_provided(k), "<", k, ">", obj.text, " file: ", obj.segment_anchor_tag, ".xhtml#", obj.ocn); break; case DomTags.open : - writeln(markup.indent_by_spaces_provided(k), "<", k, ">", obj.text); + writeln(markup.indent_by_spaces_provided(k), "<", k, ">", obj.text, " file: ", obj.segment_anchor_tag, ".xhtml#", obj.ocn); break; default : break; diff --git a/org/ao_doc_abstraction.org b/org/ao_doc_abstraction.org index 355c126..240b8df 100644 --- a/org/ao_doc_abstraction.org +++ b/org/ao_doc_abstraction.org @@ -14,6 +14,22 @@ [[./sdp.org][sdp]] [[./][org/]] * 0. the document notes +** abstraction +- abstract for downstream processing + - identify document structure and objects + - identify document structure (headings/levels/sections) + - identify objects + - set document, generate common abstraction for downstream parsing + - set different document sections, toc, body, endnotes, book index, etc. + - object numbers, heading/ chapter numbering etc, endnote numbers + - unify object representations + - multiple markups for same object type given single representation + - extract object attributes + - unify inline markup on objects + - inline markup made easier to identify + +- simplify downstream parsing + ** document sections |--------------+--------------+---+---+--------------------------------------------------+---+---+---| @@ -1784,6 +1800,12 @@ this can be extracted earlier) Build here: - DOM structure - ancestors and decendants + - ancestors could be determined earlier, but convenient to have here + - descendants could be in the form of: headings contained under current + heading, and/or; the range of objects under the current heading +- you could decide on a sequential object list, containing all objects (both + substantive and non-substantive objects), in addition to ocn, which are for + substantive/ citable objects within the document (as needed) up to document heading 1~, lev4 html: @@ -3126,6 +3148,22 @@ void _poem_block_(L,O,T,C,N,Ma)( ***** table block :table: +there are 3 types of table markup that need to be nomalized (given a single representation) here + +- curly brace block +- tic block +- special notation block + +you need: +- identify the type for the munging to create uniform presentation + - curly, tick, special + - table heading row, bool +- present table header info in uniform way + - table_number_of_columns, int (count) + - table_column_widths, int[] column widths (as given or calculate average) + - show table walls, bool +- table content marked up in uniform way + #+name: abs_functions_block_table #+BEGIN_SRC d void _table_block_(L,O,T,Ma)( diff --git a/org/defaults.org b/org/defaults.org index cb4ee80..b83308d 100644 --- a/org/defaults.org +++ b/org/defaults.org @@ -911,103 +911,226 @@ private import #+name: defaults_template_paths #+BEGIN_SRC d template SiSUpaths() { - string _base_filename(string fn_src) { - string _fn_base = ""; - if (extension(fn_src) == ".sst") { - _fn_base = baseName(fn_src, ".sst"); - } else if (extension(fn_src) == ".ssm") { - _fn_base = baseName(fn_src, ".ssm"); - } - return _fn_base; - } +#+END_SRC + +**** base + +#+name: defaults_template_paths +#+BEGIN_SRC d struct DirPaths { string base_filename(string fn_src) { - return _base_filename(fn_src); + return baseName(stripExtension(fn_src)); } } +#+END_SRC + +**** sisupod + +***** pod + +#+name: defaults_template_paths +#+BEGIN_SRC d struct SiSUpodPaths { string base_filename(string fn_src) { - return _base_filename(fn_src); + return baseName(stripExtension(fn_src)); + } + string sisupod_filename(string fn_src) { + return "sisupod".chainPath(base_filename(fn_src) ~ ".zip").array; + } + string base(string fn_src) { + return "sisupod".chainPath(base_filename(fn_src)).array; + } + } +#+END_SRC + +***** pod zipped + +#+name: defaults_template_paths +#+BEGIN_SRC d + struct SiSUpodPathsZipped { + auto spod_pths = SiSUpodPaths(); + string base_filename(string fn_src) { + return spod_pths.base_filename(fn_src); + } + string sisupod_filename(string fn_src) { + return spod_pths.sisupod_filename(fn_src); } string base(string fn_src) { - return chainPath("sisupod", _base_filename(fn_src)).array; + return spod_pths.base(fn_src); } - string doc(string fn_src) { - return chainPath(base(fn_src), "doc").array; - // return chainPath(base(fn_src), "text").array; + auto doc_root(string fn_src) { + return "doc"; } - string doc_lng(string fn_src, string lng) { - return chainPath(doc(fn_src), lng).array; + auto doc(string fn_src) { + return doc_root(fn_src); } - string conf(string fn_src) { - return chainPath(doc(fn_src), "_sisu").array; + auto doc_lng(string fn_src, string lng) { + return doc_root(fn_src).chainPath(lng).array; } - string image(string fn_src) { - return chainPath(conf(fn_src), "image").array; + auto conf(string fn_src) { + return doc_root(fn_src).chainPath("_sisu").array; } - string css(string fn_src) { - return chainPath(conf(fn_src), "css").array; + auto image(string fn_src) { + return conf(fn_src).chainPath("image").array; } - string fn_doc(string fn_src, string lng) { - return chainPath((doc_lng(fn_src, lng)), baseName(fn_src)).array; + auto css(string fn_src) { + return conf(fn_src).chainPath("css").array; } - string fn_doc_insert(string fn_src, string fn_insert, string lng) { - return chainPath((doc_lng(fn_src, lng)), baseName(fn_insert)).array; + auto fn_doc(string fn_src, string lng) { + return (doc_lng(fn_src, lng)).chainPath(baseName(fn_src)).array; + } + auto fn_doc_insert(string fn_src, string fn_insert, string lng) { + return (doc_lng(fn_src, lng)).chainPath(baseName(fn_insert)).array; } } +#+END_SRC + +***** pod unzipped archive + +#+name: defaults_template_paths +#+BEGIN_SRC d + struct SiSUpodPathsFilesystemArchive { + auto spod_pths = SiSUpodPaths(); + string base_filename(string fn_src) { + return spod_pths.base_filename(fn_src); + } + string sisupod_filename(string fn_src) { + return spod_pths.sisupod_filename(fn_src); + } + string base(string fn_src) { + return spod_pths.base(fn_src); + } + auto doc_root(string fn_src) { + return base(fn_src).chainPath("doc").array; + } + auto doc(string fn_src) { + return doc_root(fn_src); + } + auto doc_lng(string fn_src, string lng) { + return doc_root(fn_src).chainPath(lng).array; + } + auto conf(string fn_src) { + return doc_root(fn_src).chainPath("_sisu").array; + } + auto image(string fn_src) { + return conf(fn_src).chainPath("image").array; + } + auto css(string fn_src) { + return conf(fn_src).chainPath("css").array; + } + auto fn_doc(string fn_src, string lng) { + return (doc_lng(fn_src, lng)).chainPath(baseName(fn_src)).array; + } + auto fn_doc_insert(string fn_src, string fn_insert, string lng) { + return (doc_lng(fn_src, lng)).chainPath(baseName(fn_insert)).array; + } + } +#+END_SRC + +**** html5 + +#+name: defaults_template_paths +#+BEGIN_SRC d struct HtmlPaths { string base_filename(string fn_src) { - return _base_filename(fn_src); + return baseName(stripExtension(fn_src)); } string base() { - return chainPath("en", "html").array; + return "en".chainPath("html").array; } string seg(string fn_src) { - return chainPath(base, _base_filename(fn_src)).array; + return base.chainPath(base_filename(fn_src)).array; } string fn_scroll(string fn_src) { - return chainPath(base, _base_filename(fn_src) ~ ".html").array; + return base.chainPath(base_filename(fn_src) ~ ".html").array; } string fn_seg(string fn_src, string seg_filename) { - return chainPath(seg(fn_src), seg_filename ~ ".html").array; + return seg(fn_src).chainPath(seg_filename ~ ".html").array; } } - struct EpubPaths { +#+END_SRC + +**** epub3 + +#+name: defaults_template_paths +#+BEGIN_SRC d + struct Epub3paths { + string dirtop() { + return "".chainPath("").array; + } string base_filename(string fn_src) { - return _base_filename(fn_src); + return baseName(stripExtension(fn_src)); } string base() { - return chainPath("en", "epub").array; + return "en".chainPath("epub3").array; } - string doc(string fn_src) { - return chainPath(base, _base_filename(fn_src)).array; + string epub_file(string fn_src) { + return base.chainPath(base_filename(fn_src) ~ ".epub").array; + } + string docdir(string fn_src) { + return base.chainPath(base_filename(fn_src)).array; } string doc_meta_inf(string fn_src) { - return chainPath(doc(fn_src), "META-INF").array; + return dirtop.chainPath("META-INF").array; } string doc_oebps(string fn_src) { - return chainPath(doc(fn_src), "OEBPS").array; + return dirtop.chainPath("OEBPS").array; } string doc_oebps_css(string fn_src) { - return chainPath(doc_oebps(fn_src), "css").array; + return doc_oebps(fn_src).chainPath("css").array; } string doc_oebps_image(string fn_src) { - return chainPath(doc_oebps(fn_src), "image").array; + return doc_oebps(fn_src).chainPath("image").array; } string fn_mimetypes(string fn_src) { - return chainPath(doc(fn_src), "mimetypes").array; + return dirtop.chainPath("mimetypes").array; } string fn_dmi_container_xml(string fn_src) { - return chainPath(doc_meta_inf(fn_src), "container.xml").array; + return doc_meta_inf(fn_src).chainPath("container.xml").array; + } + string fn_oebps_toc_nav_xhtml(string fn_src) { + return doc_oebps(fn_src).chainPath("toc_nav.xhtml").array; } string fn_oebps_toc_ncx(string fn_src) { - return chainPath(doc_oebps(fn_src), "toc.ncx").array; + return doc_oebps(fn_src).chainPath("toc.ncx").array; } string fn_oebps_content_opf(string fn_src) { - return chainPath(doc_oebps(fn_src), "content.opf").array; + return doc_oebps(fn_src).chainPath("content.opf").array; } string fn_oebps_content_xhtml(string fn_src, string seg_filename) { - return chainPath(doc_oebps(fn_src), seg_filename ~ ".xhtml").array; + return doc_oebps(fn_src).chainPath(seg_filename ~ ".xhtml").array; + } + debug(epub_output) { + string dbg_doc_meta_inf(string fn_src) { + return docdir(fn_src).chainPath("META-INF").array; + } + string dbg_doc_oebps(string fn_src) { + return docdir(fn_src).chainPath("OEBPS").array; + } + string dbg_doc_oebps_css(string fn_src) { + return doc_oebps(fn_src).chainPath("css").array; + } + string dbg_doc_oebps_image(string fn_src) { + return doc_oebps(fn_src).chainPath("image").array; + } + string dbg_fn_mimetypes(string fn_src) { + return docdir(fn_src).chainPath("mimetypes").array; + } + string dbg_fn_dmi_container_xml(string fn_src) { + return doc_meta_inf(fn_src).chainPath("container.xml").array; + } + string dbg_fn_oebps_toc_nav_xhtml(string fn_src) { + return doc_oebps(fn_src).chainPath("toc_nav.xhtml").array; + } + string dbg_fn_oebps_toc_ncx(string fn_src) { + return doc_oebps(fn_src).chainPath("toc.ncx").array; + } + string dbg_fn_oebps_content_opf(string fn_src) { + return doc_oebps(fn_src).chainPath("content.opf").array; + } + string dbg_fn_oebps_content_xhtml(string fn_src, string seg_filename) { + return doc_oebps(fn_src).chainPath(seg_filename ~ ".xhtml").array; + } } } } @@ -1072,8 +1195,7 @@ template InternalMarkup() { auto tc_o = "┏"; //"『"; // "┏" ┓ auto tc_c = "┚"; // "』"; // "┚" table row mark #Mx[:tc_c]="』\n" auto tc_p = "┆"; // table col/misc mark - string indent_by_spaces_provided(int indent) { - auto _indent_spaces ="░░"; // auto nbsp = "░"; + string indent_by_spaces_provided(int indent, string _indent_spaces ="░░") { _indent_spaces = replicate(_indent_spaces, indent); return _indent_spaces; } diff --git a/org/output.org b/org/output.org index e84796d..a9fdc74 100644 --- a/org/output.org +++ b/org/output.org @@ -17,7 +17,7 @@ #+BEGIN_SRC d :tangle ../src/sdp/output_hub.d /++ - output hub<BR> + output hub<br> check & generate output types requested +/ template outputHub() { @@ -38,13 +38,14 @@ template outputHub() { std.traits, std.typecons, std.uni, - std.utf, + std.utf; + import defaults, - output_epub, + output_epub3, output_html, output_xhtmls, - source_sisupod; - import + source_sisupod, + create_zip_file, output_rgx, output_xhtmls; void outputHub(D,I)(D doc_abstraction, I doc_matters) { @@ -83,10 +84,10 @@ template outputHub() { if ((doc_matters.opt_action_bool["verbose"])) {writeln("html scroll done");} } if (doc_matters.opt_action_bool["epub"]) { - if ((doc_matters.opt_action_bool["verbose"])) {write("epub processing... ");} - outputEPub!()(doc_abstraction, doc_matters); + if ((doc_matters.opt_action_bool["verbose"])) {write("epub3 processing... ");} + outputEPub3!()(doc_abstraction, doc_matters); // epub.css_write; - if ((doc_matters.opt_action_bool["verbose"])) {writeln("epub done");} + if ((doc_matters.opt_action_bool["verbose"])) {writeln("epub3 done");} } if (doc_matters.opt_action_bool["pdf"]) { /+ mixin outputPDF; +/ @@ -117,27 +118,53 @@ private import std.algorithm, std.array, std.container, + std.digest.sha, std.exception, std.file, std.getopt, std.json, - std.process, - std.stdio, + std.outbuffer, std.path, + std.process, std.range, std.regex, + std.stdio, std.string, std.traits, std.typecons, std.uni, std.utf, + std.zip, std.conv : to; import + create_zip_file, defaults, output_rgx, output_xhtmls; #+END_SRC +** _zip_ +*** template :template: + +#+BEGIN_SRC d :tangle ../src/sdp/create_zip_file.d +template createZipFile() { + import std.file; + import std.outbuffer; + import std.string; + import std.zip; + void createZipFile( + string zip_file_name, + void[] compressed_zip_data, + ) { + try { + write(zip_file_name, compressed_zip_data); + } catch (ZipException ex) { + // Handle Errors + } + } +} +#+END_SRC + ** _sisupod_ :sisupod: *** template :template: @@ -162,12 +189,13 @@ template SiSUpod() { #+name: source_sisupod_init #+BEGIN_SRC d -debug(asserts){ +debug(asserts) { // static assert(is(typeof(doc_matters) == tuple)); } mixin SiSUoutputRgxInit; mixin SiSUpaths; -auto pth_sisupod = SiSUpodPaths(); +auto pth_sisupod = SiSUpodPathsZipped(); +auto pth_sisupod_filesystem = SiSUpodPathsFilesystemArchive(); mixin SiSUlanguageCodes; auto lang = Lang(); auto rgx = Rgx(); @@ -177,20 +205,20 @@ assert (doc_matters.source_filename.match(rgx.src_fn)); #+name: source_sisupod_mkdirs #+BEGIN_SRC d /+ create directory structure +/ -if (!exists(pth_sisupod.doc(doc_matters.source_filename))) { - pth_sisupod.doc(doc_matters.source_filename).mkdirRecurse; +if (!exists(pth_sisupod_filesystem.doc(doc_matters.source_filename))) { + pth_sisupod_filesystem.doc(doc_matters.source_filename).mkdirRecurse; } -if (!exists(pth_sisupod.conf(doc_matters.source_filename))) { - pth_sisupod.conf(doc_matters.source_filename).mkdirRecurse; +if (!exists(pth_sisupod_filesystem.conf(doc_matters.source_filename))) { + pth_sisupod_filesystem.conf(doc_matters.source_filename).mkdirRecurse; } -if (!exists(pth_sisupod.css(doc_matters.source_filename))) { - pth_sisupod.css(doc_matters.source_filename).mkdirRecurse; +if (!exists(pth_sisupod_filesystem.css(doc_matters.source_filename))) { + pth_sisupod_filesystem.css(doc_matters.source_filename).mkdirRecurse; } -if (!exists(pth_sisupod.image(doc_matters.source_filename))) { - pth_sisupod.image(doc_matters.source_filename).mkdirRecurse; +if (!exists(pth_sisupod_filesystem.image(doc_matters.source_filename))) { + pth_sisupod_filesystem.image(doc_matters.source_filename).mkdirRecurse; } -if (!exists(pth_sisupod.doc_lng(doc_matters.source_filename, doc_matters.language))) { - pth_sisupod.doc_lng(doc_matters.source_filename, doc_matters.language).mkdirRecurse; +if (!exists(pth_sisupod_filesystem.doc_lng(doc_matters.source_filename, doc_matters.language))) { + pth_sisupod_filesystem.doc_lng(doc_matters.source_filename, doc_matters.language).mkdirRecurse; } #+END_SRC @@ -200,54 +228,158 @@ if (!exists(pth_sisupod.doc_lng(doc_matters.source_filename, doc_matters.languag #+BEGIN_SRC d debug(sisupod) { writeln(__LINE__, ": ", - // doc_matters.environment["pwd"], "/", - doc_matters.source_filename, " -> ", - // doc_matters.environment["pwd"], "/", - pth_sisupod.fn_doc( - doc_matters.source_filename, - doc_matters.language - )); -} -if (exists(doc_matters.source_filename)) { - copy( + doc_matters.source_filename, " -> ", + pth_sisupod_filesystem.fn_doc( doc_matters.source_filename, - pth_sisupod.fn_doc( - doc_matters.source_filename, - doc_matters.language + doc_matters.language )); } -if (doc_matters.file_insert_list.length > 0) { - foreach (insert_file; doc_matters.file_insert_list) { - debug(sisupod) { +auto zip = new ZipArchive(); +auto fn_sisupod = pth_sisupod.sisupod_filename(doc_matters.source_filename); +{ /+ bundle images +/ + foreach (image; doc_matters.image_list) { + debug(sisupodimages) { writeln( + "_sisu/image/", image, " -> ", + pth_sisupod.image(doc_matters.source_filename), "/", image + ); + } + auto fn_src = "_sisu/image/"~ image; + auto fn_out = pth_sisupod.image(doc_matters.source_filename).to!string ~ "/" ~ image; + auto fn_out_filesystem = pth_sisupod_filesystem.image(doc_matters.source_filename).to!string ~ "/" ~ image; + if (exists(fn_src)) { + fn_src.copy(fn_out_filesystem); + { + auto zip_arc_member_file = new ArchiveMember(); + zip_arc_member_file.name = fn_out; + auto zip_data = new OutBuffer(); + zip_data.write(cast(char[]) ((fn_src).read)); + zip_arc_member_file.expandedData = zip_data.toBytes(); + zip.addMember(zip_arc_member_file); + createZipFile!()(pth_sisupod.sisupod_filename(fn_src), zip.build()); + } + } + } +} +{ /+ bundle sisu_document_make +/ + auto fn_src = "_sisu/sisu_document_make"; // check (_sisu/sisu_document_make) + auto fn_out = pth_sisupod.conf(doc_matters.source_filename).to!string ~ "/" ~ "sisu_document_make"; + auto fn_out_filesystem = pth_sisupod_filesystem.conf(doc_matters.source_filename).to!string ~ "/" ~ "sisu_document_make"; + if (exists(fn_src)) { + fn_src.copy(fn_out_filesystem); + { + auto zip_arc_member_file = new ArchiveMember(); + zip_arc_member_file.name = fn_out; + auto zip_data = new OutBuffer(); + zip_data.write((fn_src).readText); + zip_arc_member_file.expandedData = zip_data.toBytes(); + zip.addMember(zip_arc_member_file); + createZipFile!()(pth_sisupod.sisupod_filename(fn_src), zip.build()); + } + } +} +{ /+ bundle primary file +/ + auto fn_src = doc_matters.source_filename; + auto fn_out = pth_sisupod.fn_doc(doc_matters.source_filename, doc_matters.language).to!string; + auto fn_out_filesystem = pth_sisupod_filesystem.fn_doc(doc_matters.source_filename, doc_matters.language).to!string; + if (exists(fn_src)) { + fn_src.copy(fn_out_filesystem); + { + auto zip_arc_member_file = new ArchiveMember(); + zip_arc_member_file.name = fn_out; + auto zip_data = new OutBuffer(); + zip_data.write((fn_src).readText); + zip_arc_member_file.expandedData = zip_data.toBytes(); + zip.addMember(zip_arc_member_file); + createZipFile!()(pth_sisupod.sisupod_filename(fn_src), zip.build()); + } + } +} +{ /+ bundle insert files +/ + if (doc_matters.file_insert_list.length > 0) { + foreach (insert_file; doc_matters.file_insert_list) { + debug(sisupod) { + writeln( insert_file, " -> ", pth_sisupod.fn_doc_insert( doc_matters.source_filename, insert_file, doc_matters.language - )); - } - if (exists(insert_file)) { - insert_file.copy( - pth_sisupod.fn_doc_insert( - doc_matters.source_filename, - insert_file, - doc_matters.language - )); + )); + } + auto fn_src = insert_file; + auto fn_out = pth_sisupod.fn_doc_insert( + doc_matters.source_filename, + insert_file, + doc_matters.language + ).to!string; + auto fn_out_filesystem = pth_sisupod_filesystem.fn_doc_insert( + doc_matters.source_filename, + insert_file, + doc_matters.language + ).to!string; + if (exists(fn_src)) { + fn_src.copy(fn_out_filesystem); + { + auto zip_arc_member_file = new ArchiveMember(); + zip_arc_member_file.name = insert_file; + auto zip_data = new OutBuffer(); + zip_data.write((fn_src).readText); + zip_arc_member_file.expandedData = zip_data.toBytes(); + zip.addMember(zip_arc_member_file); + createZipFile!()(pth_sisupod.sisupod_filename(fn_src), zip.build()); + } + } } } } -foreach (image; doc_matters.image_list) { - debug(sisupod) { - writeln( - "_sisu/image/", image, " -> ", - pth_sisupod.image(doc_matters.source_filename), "/", image - ); +#+END_SRC + +*** sha256 of sisupod.zip, zip debug, read zip archive + +#+name: source_sisupod_copy +#+BEGIN_SRC d +if (exists(fn_sisupod)) { + try { + auto data = (cast(byte[]) (fn_sisupod).read); + writefln("%-(%02x%) %s", data.sha256Of, fn_sisupod); + debug(sisupod) { + try { + auto zipped = new ZipArchive((fn_sisupod).read); + foreach (filename, member; zipped.directory) { + auto data = zipped.expand(member); + writeln("> ", filename, " length ", data.length); // filename == member.name + // Use data + } + } + catch (ZipException ex) { + // Handle errors + } + if (doc_matters.source_filename == "en/the_wealth_of_networks.yochai_benkler.sst") { + assert( + ((data).sha256Of).toHexString + == "DDE0013C13C6A4F06D4BE72087E2CDEF47697CA38A6A2D65BA7207DB6B144271", + "\nsisupod: sha256 value for " + ~ doc_matters.source_filename + ~ " has changed, is now: " + ~ ((data).sha256Of).toHexString + ); + } + if (doc_matters.source_filename == "en/sisu_markup_stress_test.sst") { + assert( + ((data).sha256Of).toHexString + == "112C0AEDD2518A1803D91A7CF5785274A3116C0779A631782D0C0813B212C68A", + "\nsisupod: sha256 value for " + ~ doc_matters.source_filename + ~ " has changed, is now: " + ~ ((data).sha256Of).toHexString + ); + } + } } - if (exists("_sisu/image/"~ image)) { - ("_sisu/image/"~ image).copy( - (pth_sisupod.image(doc_matters.source_filename) ~ "/" ~ image) - ); + catch (ErrnoException ex) + { + // Handle errors } } #+END_SRC @@ -279,7 +411,7 @@ string special_characters(string _txt){ .replaceAll(rgx.xhtml_ampersand, "&") .replaceAll(rgx.xhtml_less_than, "<") .replaceAll(rgx.xhtml_greater_than, ">") - .replaceAll(rgx.xhtml_line_break, "<br>"); + .replaceAll(rgx.xhtml_line_break, "<br />"); return _txt; } #+END_SRC @@ -329,7 +461,7 @@ string _xhtml_anchor_tags(const(string[]) anchor_tags) { auto scroll_head(Me)( Me dochead_meta, ) { - debug(asserts){ + debug(asserts) { static assert(is(typeof(dochead_meta) == string[string][string])); } string o; @@ -337,26 +469,27 @@ auto scroll_head(Me)( <html> <head> <meta charset="utf-8"> - <title> - %s%s - </title> -<meta http-equiv="Content-Type" content="text/html;charset=utf-8" /> - <meta name="dc.title" content="Title" /> - <meta name="dc.author" content="Author" /> - <meta name="dc.publisher" content="SiSU http://www.jus.uio.no/sisu (this copy)" /> - <meta name="dc.date" content="year" /> - <meta name="dc.date.created" content="year" /> - <meta name="dc.date.issued" content="year" /> - <meta name="dc.date.available" content="year" /> - <meta name="dc.date.valid" content="year" /> - <meta name="dc.date.modified" content="year" /> - <meta name="dc.language" content="US" /> - <meta name="dc.rights" content="Copyright: Copyright (C) year holder /> - <meta name="generator" content="sdp [SiSU 7.1.8 of 2016w08/5 (2016-02-26)] (n*x and D)" /> - <link rel="generator" href="http://www.sisudoc.org/" /> + <title> + %s%s + </title> + <meta http-equiv="Content-Type" content="text/html;charset=utf-8" /> + <meta name="dc.title" content="Title" /> + <meta name="dc.author" content="Author" /> + <meta name="dc.publisher" content="SiSU http://www.jus.uio.no/sisu (this copy)" /> + <meta name="dc.date" content="year" /> + <meta name="dc.date.created" content="year" /> + <meta name="dc.date.issued" content="year" /> + <meta name="dc.date.available" content="year" /> + <meta name="dc.date.valid" content="year" /> + <meta name="dc.date.modified" content="year" /> + <meta name="dc.language" content="US" /> + <meta name="dc.rights" content="Copyright: Copyright (C) year holder /> + <meta name="generator" content="sdp [SiSU 7.1.8 of 2016w08/5 (2016-02-26)] (n*x and D)" /> + </meta> + <link rel="generator" href="http://www.sisudoc.org/" /> <link rel="shortcut icon" href="../_sisu/image/rb7.ico" /> - <link href="../../_sisu/css/html.css" rel="stylesheet"> - <link href="../../../_sisu/css/html.css" rel="stylesheet"> + <link href="../../_sisu/css/html.css" rel="stylesheet" /> + <link href="../../../_sisu/css/html.css" rel="stylesheet" /> </head> <body lang="en"> <a name="top" id="top"></a>¶", @@ -374,7 +507,7 @@ dochead_meta["title"]["full"], auto seg_head(Me)( Me dochead_meta, ) { - debug(asserts){ + debug(asserts) { static assert(is(typeof(dochead_meta) == string[string][string])); } string o; @@ -382,26 +515,27 @@ auto seg_head(Me)( <html> <head> <meta charset="utf-8"> - <title> - %s%s - </title> -<meta http-equiv="Content-Type" content="text/html;charset=utf-8" /> - <meta name="dc.title" content="Title" /> - <meta name="dc.author" content="Author" /> - <meta name="dc.publisher" content="SiSU http://www.jus.uio.no/sisu (this copy)" /> - <meta name="dc.date" content="year" /> - <meta name="dc.date.created" content="year" /> - <meta name="dc.date.issued" content="year" /> - <meta name="dc.date.available" content="year" /> - <meta name="dc.date.valid" content="year" /> - <meta name="dc.date.modified" content="year" /> - <meta name="dc.language" content="US" /> - <meta name="dc.rights" content="Copyright: Copyright (C) year holder /> - <meta name="generator" content="sdp [SiSU 7.1.8 of 2016w08/5 (2016-02-26)] (n*x and D)" /> - <link rel="generator" href="http://www.sisudoc.org/" /> + <title> + %s%s + </title> + <meta http-equiv="Content-Type" content="text/html;charset=utf-8" /> + <meta name="dc.title" content="Title" /> + <meta name="dc.author" content="Author" /> + <meta name="dc.publisher" content="SiSU http://www.jus.uio.no/sisu (this copy)" /> + <meta name="dc.date" content="year" /> + <meta name="dc.date.created" content="year" /> + <meta name="dc.date.issued" content="year" /> + <meta name="dc.date.available" content="year" /> + <meta name="dc.date.valid" content="year" /> + <meta name="dc.date.modified" content="year" /> + <meta name="dc.language" content="US" /> + <meta name="dc.rights" content="Copyright: Copyright (C) year holder" /> + <meta name="generator" content="sdp [SiSU 7.1.8 of 2016w08/5 (2016-02-26)] (n*x and D)" /> + </meta> + <link rel="generator" href="http://www.sisudoc.org/" /> <link rel="shortcut icon" href="../_sisu/image/rb7.ico" /> - <link href="../../_sisu/css/html.css" rel="stylesheet"> - <link href="../../../_sisu/css/html.css" rel="stylesheet"> + <link href="../../_sisu/css/html.css" rel="stylesheet" /> + <link href="../../../_sisu/css/html.css" rel="stylesheet" /> </head> <body lang="en"> <a name="top" id="top"></a>¶", @@ -485,13 +619,13 @@ auto inline_links(O)( #+name: xhtml_format_objects #+BEGIN_SRC d auto inline_notes_scroll(O)( - auto return ref const O obj, - string _txt, + auto return ref const O obj, + string _txt, ) { if (obj.inline_notes_reg) { _txt = (_txt).replaceAll( rgx.inline_notes_delimiter_al_regular_number_note, - ("<a href=\"#note_$1\"><note id=\"noteref_$1\"> <sup>$1</sup> </note></a>") + ("<a href=\"#note_$1\"><note id=\"noteref_$1\"> <sup>$1</sup> </note></a>") ); } debug(markup_endnotes) { @@ -535,7 +669,7 @@ auto inline_notes_seg(O)( "\">", "<note id=\"note_", m.captures[1], - "\"> <sup>", + "\"> <sup>", m.captures[1], ".</sup></note></a>", m.captures[2], @@ -544,7 +678,7 @@ auto inline_notes_seg(O)( } _txt = (_txt).replaceAll( rgx.inline_notes_delimiter_al_regular_number_note, - ("<a href=\"#note_$1\"><note id=\"noteref_$1\"> <sup>$1</sup> </note></a>") + ("<a href=\"#note_$1\"><note id=\"noteref_$1\"> <sup>$1</sup> </note></a>") ); } else if (_txt.match(rgx.inline_notes_delimiter_al_regular_number_note)) { debug(markup) { @@ -625,7 +759,7 @@ auto heading(O)( auto tags = _xhtml_anchor_tags(obj.anchor_tags); string o; if (obj.obj_cite_number.empty) { - o = format(q"¶<br><hr /><br> + o = format(q"¶<br /><hr /><br /> <div class="substance"> <h%s class="%s">%s %s @@ -638,7 +772,7 @@ auto heading(O)( obj.heading_lev_markup, ); } else { - o = format(q"¶<br><hr /><br> + o = format(q"¶<br /><hr /><br /> <div class="substance"> <label class="ocn"><a href="#%s" class="lnkocn">%s</a></label> <h%s class="%s" id="%s"><a name="%s"></a>%s @@ -707,7 +841,7 @@ auto para(O)( auto tags = _xhtml_anchor_tags(obj.anchor_tags); _txt = font_face(_txt); string o; - _txt = (obj.bullet) ? ("●  " ~ _txt) : _txt; + _txt = (obj.bullet) ? ("●  " ~ _txt) : _txt; if (obj.obj_cite_number.empty) { o = format(q"¶ <div class="substance"> <p class="%s" indent="h%si%s">%s @@ -942,7 +1076,6 @@ auto block(O)( </div>¶", obj.is_a, _txt - // obj.text ); } else { o = format(q"¶ <div class="substance"> @@ -956,7 +1089,6 @@ auto block(O)( obj.is_a, obj.obj_cite_number, _txt - // obj.text ); } return o; @@ -1008,9 +1140,9 @@ auto verse(O)( // using code from code block, review ) { _txt = font_face(_txt); _txt = (_txt) - .replaceAll(rgx.newline, "<br>\n") - .replaceAll(rgx.two_spaces, " " ~ " " ~ " " ~ " ") - .replaceAll(rgx.nbsp_and_space, " " ~ " ") + .replaceAll(rgx.newline, "<br />\n") + .replaceAll(rgx.two_spaces, " " ~ " " ~ " " ~ " ") + .replaceAll(rgx.nbsp_and_space, " " ~ " ") .replaceAll(rgx.strip_br, ""); string o; if (obj.obj_cite_number.empty) { @@ -1084,8 +1216,8 @@ auto verse_seg(O)( ) { string _txt = obj.text; _txt = (_txt) - .replaceAll(rgx.newline, "<br>\n") - .replaceAll(rgx.nbsp_char, " "); + .replaceAll(rgx.newline, "<br />\n") + .replaceAll(rgx.nbsp_char, " "); string o; if (obj.obj_cite_number.empty) { o = format(q"¶ <div class="substance"> @@ -1388,7 +1520,7 @@ void scroll_write_output(Fn,C)( Fn fn_src, C doc, ) { - debug(asserts){ + debug(asserts) { static assert(is(typeof(fn_src) == string)); static assert(is(typeof(doc) == string[])); } @@ -1636,7 +1768,7 @@ void seg_write_output(M,D,E)( D doc_html, E doc_html_endnotes, ) { - debug(asserts){ + debug(asserts) { static assert(is(typeof(doc_html) == string[][string])); } mixin SiSUoutputRgxInit; @@ -2523,104 +2655,225 @@ auto css_write() { #+END_SRC *** _epub_ [#B] :epub: + +|-----------------------+--------------------------+---------------------------+----------------------------------| +| function | filename | module | variable | +|-----------------------+--------------------------+---------------------------+----------------------------------| +| identify doc filetype | mimetype | epub3_mimetypes | mimetypes | +|-----------------------+--------------------------+---------------------------+----------------------------------| +| identify doc root | META-INF/container.xml | epub3_container_xml | meta_inf_container_xml | +|-----------------------+--------------------------+---------------------------+----------------------------------| +| doc manifest | OEBPS/content.opf | epub3_oebps_content | oebps_content_opf | +|-----------------------+--------------------------+---------------------------+----------------------------------| +| doc navigation | OEBPS/toc_nav.xhtml | epub3_oebps_toc_nav_xhtml | oebps_toc_nav_xhtml | +| | OEBPS/toc.ncx | epub2_oebps_toc_ncx | oebps_toc_ncx | +|-----------------------+--------------------------+---------------------------+----------------------------------| +| doc contents | OEBPS/[files ... ].xhtml | outputEPub3 | doc_epub3[seg_filename] | +| | | | doc_epub3_endnotes[seg_filename] | +|-----------------------+--------------------------+---------------------------+----------------------------------| + **** template :template: -#+BEGIN_SRC d :tangle ../src/sdp/output_epub.d -template outputEPub() { +#+BEGIN_SRC d :tangle ../src/sdp/output_epub3.d +template outputEPub3() { <<output_imports>> mixin InternalMarkup; mixin outputXHTMLs; - <<output_epub_fixed>> - <<output_epub_constructs>> - <<output_epub_xhtml>> - <<output_epub_xhtml_seg>> - <<output_epub_css>> + <<output_epub3_fixed>> + <<output_epub3_constructs>> + <<output_epub3_xhtml>> + <<output_epub3_xhtml_seg>> + <<output_epub3_css>> } #+END_SRC -**** epub special files :format: -***** static -****** mimetype (file) +**** special (epub) files :format: +***** DONE static +****** _identify doc filetype_ (mimetype) [static] + +- mimetype file indicating that zip file contains an EPUB -#+name: output_epub_fixed +#+name: output_epub3_fixed #+BEGIN_SRC d -string epub_mimetypes() { +string epub3_mimetypes() { string o; - o = format(q"¶application/epub+zip¶"); + o = format(q"¶application/epub+zip¶") ~ "\n"; return o; } #+END_SRC -****** META-INF/container.xml (file) +****** _identify doc root_ (META-INF/container.xml) [static] rootfile: contains document root path -#+name: output_epub_fixed +- identifies the root package document (so systems can find it), [unchanged from epub2] + +#+name: output_epub3_fixed #+BEGIN_SRC d -string epub_container_xml() { +string epub3_container_xml() { string o; - o = format(q"¶<?xml version='1.0' encoding='utf-8'?> -<container version="1.0" - xmlns="urn:oasis:names:tc:opendocument:xmlns:container"> - <rootfiles> - <rootfile full-path="OEBPS/content.opf" - media-type="application/oebps-package+xml" /> - </rootfiles> -</container>¶"); + o = format(q"¶<?xml version='1.0' encoding='utf-8'?>¶") ~ "\n"; + o ~= format(q"¶<container version="1.0" +xmlns="urn:oasis:names:tc:opendocument:xmlns:container"> +<rootfiles> + <rootfile full-path="OEBPS/content.opf" + media-type="application/oebps-package+xml" /> +</rootfiles>¶") ~ "\n</container>\n"; return o; } #+END_SRC -***** constructs (in OEBPS) -****** TODO OEBPS/content.opf (register content: files, images etc.) +***** constructs (in dir: OEBPS) +****** TODO _doc manifest_ (OEBPS/content.opf) manifest, register content: files, images etc. + +- manifest, listing all resources +- provides the default reading order +- identifies the navigation document -#+name: output_epub_constructs +#+name: output_epub3_constructs #+BEGIN_SRC d -string epub_oebps_content(D,I)(D doc_abstraction, I doc_matters) { - string uuid = "18275d951861c77f78acd05672c9906924c59f18a2e0ba06dad95959693e9bd8"; // TODO shared elsewhere - string content = format(q"¶<?xml version='1.0' encoding='utf-8'?> -<?xml version='1.0' encoding='utf-8'?> +string epub3_oebps_content(D,I,P)(D doc_abstraction, I doc_matters, P parts) { + string uuid = "18275d951861c77f78acd05672c9906924c59f18a2e0ba06dad95959693e9bd8"; // TODO sort uuid in doc_matters! + string content = format(q"¶ <?xml version='1.0' encoding='utf-8'?> <package xmlns="http://www.idpf.org/2007/opf" version="2.0" unique-identifier="EPB-UUID"> - <opf:metadata + <metadata xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" - xmlns:opf="http://www.idpf.org/2007/opf" xmlns:dcterms="http://purl.org/dc/terms/" xmlns:dc="http://purl.org/dc/elements/1.1/" unique-identifier="urn:uuid:%s" version="2.0"> - <dc:title>%s</dc:title> - <dc:creator opf:file-as="%s" opf:role="aut">%s</dc:creator> - <dc:language>en</dc:language> - <dc:date opf:event="published">%s</dc:date> + <!-- <dc:title id="title">%s</dc:title> --> + <dc:title id="title">%s</dc:title> + <meta refines="#title" property="title-type">main</meta> + <dc:title id="subtitle">%s</dc:title> + <meta refines="#subtitle" property="title-type">subtitle</meta> + <dc:creator file-as="%s" id="aut">%s</dc:creator> + <dc:language>%s</dc:language> + <dc:date id="published">%s</dc:date> <dc:rights>Copyright: %s</dc:rights> - <dc:identifier opf:scheme="URI">ox/current/en/epub/sisu_markup.epub</dc:identifier> + <dc:identifier scheme="URI">%s</dc:identifier> <dc:identifier id="bookid">urn:uuid:%s</dc:identifier> <!-- <dc:identifier id="EPB-UUID">urn:uuid:%s</dc:identifier> --> - </opf:metadata> + </metadata> <manifest> - <!-- NCX --> - <item id="ncx" href="toc.ncx" media-type="application/x-dtbncx+xml" /> + <!-- NCX epub2 navigation --> + <item id="ncx" href="toc.ncx" media-type="application/x-dtbncx+xml" /> <!-- CSS Style Sheets --> - <item id="main-css" href="css/xhtml.css" media-type="text/css" />¶", + <item id="main-css" href="css/xhtml.css" media-type="text/css" /> + <!-- nav epub3 navigation --> + <item id="nav" href="toc_nav.xhtml" media-type="application/xhtml+xml" properties="nav" /> +¶", + uuid, + doc_matters.dochead_meta["title"]["full"], + doc_matters.dochead_meta["title"]["main"], + (doc_matters.dochead_meta["title"]["sub"].empty) + ? "" : doc_matters.dochead_meta["title"]["sub"], + (doc_matters.dochead_meta["creator"]["author"].empty) + ? "" : doc_matters.dochead_meta["creator"]["author"], + (doc_matters.dochead_meta["creator"]["author"].empty) + ? "" : doc_matters.dochead_meta["creator"]["author"], + doc_matters.language, + (doc_matters.dochead_meta["date"]["published"].empty) + ? "" : doc_matters.dochead_meta["date"]["published"], + (doc_matters.dochead_meta["rights"]["copyright"].empty) + ? "" : doc_matters.dochead_meta["rights"]["copyright"], uuid, - doc_matters.dochead_meta["title"]["full"], // title - (doc_matters.dochead_meta["creator"]["author"].empty) ? "" : " by " ~ doc_matters.dochead_meta["creator"]["author"], // author - (doc_matters.dochead_meta["creator"]["author"].empty) ? "" : " by " ~ doc_matters.dochead_meta["creator"]["author"], // author - (doc_matters.dochead_meta["date"]["published"].empty) ? "" : " by " ~ doc_matters.dochead_meta["date"]["published"], // date - (doc_matters.dochead_meta["rights"]["copyright"].empty) ? "" : " by " ~ doc_matters.dochead_meta["rights"]["copyright"], // rights uuid, uuid, ); + content ~= " " ~ "<!-- Content Documents -->" ~ "\n "; + content ~= parts["manifest_documents"]; + // TODO sort jpg & png + content ~= " " ~ "<!-- Images -->" ~ "\n "; + foreach (image; doc_matters.image_list) { + content ~= format(q"¶ <item id="%s" href="image/%s" media-type="image/png" /> +¶", + image, // strip image type, remove .png .jpg suffix, use in media-type="image/" + image, + ); + } + content ~= " " ~ "</manifest>" ~ "\n "; + content ~= " " ~ "<spine toc=\"ncx\">" ~ "\n "; + content ~= parts["spine"]; + content ~= " " ~ "</spine>" ~ "\n "; + content ~= " " ~ "<guide>" ~ "\n "; + content ~= parts["guide"]; + content ~= " " ~ "</guide>" ~ "\n "; + content ~= "" ~ "</package>"; + return content; +} +#+END_SRC + +****** _doc navigation epub3_ (OEBPS/toc_nav.xhtml) epub3 navigable toc using Dom structure + +- toc_nav.xhtml declared as nav file in content.opf (epub3 navigation document) + +#+name: output_epub3_constructs +#+BEGIN_SRC d +string epub3_oebps_toc_nav_xhtml(D,I)(D doc_abstraction, I doc_matters) { + enum DomTags { none, open, close, close_and_open, open_still, } + auto markup = InlineMarkup(); + string toc ="<nav epub:type=\"toc\" id=\"toc\">\n"; foreach (sect; doc_matters.keys_seq_seg) { foreach (obj; doc_abstraction[sect]) { + if (obj.is_a == "heading") { + foreach_reverse (n; 0 .. 7) { + string k = n.to!string; + switch (obj.dom_collapsed[n]) { + case DomTags.close : + toc ~= markup.indent_by_spaces_provided((n + 1), " ") ~ "</li>" ~ "\n"; + toc ~= markup.indent_by_spaces_provided(n, " ") ~ "</ol>" ~ "\n"; + break; + case DomTags.close_and_open : + toc ~= markup.indent_by_spaces_provided((n + 1), " ") ~ "</li>" ~ "\n"; + if (obj.dom_markedup[n] < 4) { + toc ~= markup.indent_by_spaces_provided((n + 1), " ") ~ "<li>" ~ "\n" + ~ markup.indent_by_spaces_provided((n + 2), " ") + ~ "<span class=\"navhd\">" ~ obj.text ~ "</span>" ~ "\n"; + } else { + string hashtag =(obj.heading_lev_markup == 4) + ? "" + : ("#" ~ obj.ocn.to!string); + toc ~= markup.indent_by_spaces_provided((n + 1), " ") ~ "<li>" ~ "\n" + ~ markup.indent_by_spaces_provided((n + 2), " ") + ~ "<a href=\"" ~ obj.segment_anchor_tag ~ ".xhtml" ~ hashtag ~ "\">" + ~ obj.text + ~ "</a>" ~ "\n"; + } + break; + case DomTags.open : + toc ~= markup.indent_by_spaces_provided(n, " ") ~ "<ol>" ~ "\n"; + if (obj.dom_markedup[n] < 4) { + toc ~= markup.indent_by_spaces_provided(n, " ") + ~ "<li><span class=\"navhd\">" ~ obj.text ~ "</span>" ~ "\n"; + } else { + string hashtag =(obj.heading_lev_markup == 4) + ? "" + : ("#" ~ obj.ocn.to!string); + toc ~= markup.indent_by_spaces_provided((n + 1), " ") ~ "<li>" ~ "\n" + ~ markup.indent_by_spaces_provided((n + 2), " ") + ~ "<a href=\"" ~ obj.segment_anchor_tag ~ ".xhtml" ~ hashtag ~ "\">" + ~ obj.text + ~ "</a>" ~ "\n"; + } + break; + default : + break; + } + } + } } } - return content; + toc ~="</nav>\n"; + return toc; } #+END_SRC -****** TODO OEBPS/toc.ncx (navigable toc using Dom structure) +****** TODO _doc navigation epub2_ (OEBPS/toc.ncx) navigable toc using Dom structure -#+name: output_epub_constructs +- toc.ncx (epub2 navigation document) + - (replaced in epub3 by a declared xhtml nav file, in our case toc_nav.xhtml) + +#+name: output_epub3_constructs #+BEGIN_SRC d -string epub_oebps_toc(D,I)(D doc_abstraction, I doc_matters) { +string epub2_oebps_toc_ncx(D,I)(D doc_abstraction, I doc_matters) { int counter = 0; string uuid = "18275d951861c77f78acd05672c9906924c59f18a2e0ba06dad95959693e9bd8"; // TODO shared elsewhere auto markup = InlineMarkup(); @@ -2698,27 +2951,24 @@ obj.segment_anchor_tag, // lev < 4 [no link]; lev == 4 [filename] markup.xhtml } #+END_SRC -**** seg :seg: -***** switch (sections & objects) format epub xhtml output +**** the document contents :seg: +***** switch (sections & objects) format epub3 xhtml output -#+name: output_epub_xhtml_seg +#+name: output_epub3_xhtml_seg #+BEGIN_SRC d -void outputEPub(D,I)( +void outputEPub3(D,I)( auto return ref const D doc_abstraction, auto return ref I doc_matters, ) { mixin SiSUoutputRgxInit; auto xhtml_format = outputXHTMLs(); auto rgx = Rgx(); - string[][string] doc_epub; - string[][string] doc_epub_endnotes; + string[][string] doc_epub3; + string[][string] doc_epub3_endnotes; string[] doc; string segment_filename; string[] top_level_headings = ["","","",""]; - auto mimetypes = epub_mimetypes; - auto meta_inf_container_xml = epub_container_xml; - auto oebps_toc_ncx = epub_oebps_toc(doc_abstraction, doc_matters); - auto oebps_content_opf = epub_oebps_content(doc_abstraction, doc_matters); + string[string] oepbs_content_parts; string suffix = ".xhtml"; foreach (part; doc_matters.keys_seq_seg) { foreach (obj; doc_abstraction[part]) { @@ -2753,18 +3003,18 @@ void outputEPub(D,I)( break; case 4: segment_filename = obj.segment_anchor_tag; - doc_epub[segment_filename] ~= xhtml_format.seg_head(doc_matters.dochead_meta); + doc_epub3[segment_filename] ~= xhtml_format.seg_head(doc_matters.dochead_meta); foreach (top_level_heading; top_level_headings) { - doc_epub[segment_filename] ~= top_level_heading; + doc_epub3[segment_filename] ~= top_level_heading; } auto t = xhtml_format.heading_seg(obj, suffix); - doc_epub[segment_filename] ~= t[0]; - doc_epub_endnotes[segment_filename] ~= t[1]; + doc_epub3[segment_filename] ~= t[0]; + doc_epub3_endnotes[segment_filename] ~= t[1]; break; case 5: .. case 7: auto t = xhtml_format.heading_seg(obj, suffix); - doc_epub[segment_filename] ~= t[0]; - doc_epub_endnotes[segment_filename] ~= t[1]; + doc_epub3[segment_filename] ~= t[0]; + doc_epub3_endnotes[segment_filename] ~= t[1]; break; case 8: .. case 9: // unused numbers, if remain check if ((doc_matters.opt_action_bool["debug"])) { @@ -2785,7 +3035,7 @@ void outputEPub(D,I)( case "para": switch (obj.is_a) { case "toc": - doc_epub[segment_filename] ~= xhtml_format.toc(obj); + doc_epub3[segment_filename] ~= xhtml_format.toc(obj); break; default: if ((doc_matters.opt_action_bool["debug"])) { @@ -2807,8 +3057,8 @@ void outputEPub(D,I)( switch (obj.is_a) { case "para": auto t = xhtml_format.para_seg(obj, suffix); - doc_epub[segment_filename] ~= t[0]; - doc_epub_endnotes[segment_filename] ~= t[1]; + doc_epub3[segment_filename] ~= t[0]; + doc_epub3_endnotes[segment_filename] ~= t[1]; break; default: if ((doc_matters.opt_action_bool["debug"])) { @@ -2821,33 +3071,33 @@ void outputEPub(D,I)( switch (obj.is_a) { case "quote": auto t = xhtml_format.quote_seg(obj, suffix); - doc_epub[segment_filename] ~= to!string(t[0]); - doc_epub_endnotes[segment_filename] ~= t[1]; + doc_epub3[segment_filename] ~= to!string(t[0]); + doc_epub3_endnotes[segment_filename] ~= t[1]; break; case "group": auto t = xhtml_format.group_seg(obj, suffix); - doc_epub[segment_filename] ~= to!string(t[0]); - doc_epub_endnotes[segment_filename] ~= t[1]; + doc_epub3[segment_filename] ~= to!string(t[0]); + doc_epub3_endnotes[segment_filename] ~= t[1]; break; case "block": auto t = xhtml_format.block_seg(obj, suffix); - doc_epub[segment_filename] ~= to!string(t[0]); - doc_epub_endnotes[segment_filename] ~= t[1]; + doc_epub3[segment_filename] ~= to!string(t[0]); + doc_epub3_endnotes[segment_filename] ~= t[1]; break; case "poem": break; case "verse": auto t = xhtml_format.verse_seg(obj, suffix); - doc_epub[segment_filename] ~= to!string(t[0]); - doc_epub_endnotes[segment_filename] ~= t[1]; + doc_epub3[segment_filename] ~= to!string(t[0]); + doc_epub3_endnotes[segment_filename] ~= t[1]; break; case "code": - doc_epub[segment_filename] ~= xhtml_format.code(obj); + doc_epub3[segment_filename] ~= xhtml_format.code(obj); break; case "table": auto t = xhtml_format.para_seg(obj, suffix); - doc_epub[segment_filename] ~= t[0]; - doc_epub_endnotes[segment_filename] ~= t[1]; + doc_epub3[segment_filename] ~= t[0]; + doc_epub3_endnotes[segment_filename] ~= t[1]; break; default: if ((doc_matters.opt_action_bool["debug"])) { @@ -2869,27 +3119,27 @@ void outputEPub(D,I)( switch (obj.is_a) { case "endnote": auto t = xhtml_format.para_seg(obj, suffix); - doc_epub[segment_filename] ~= t[0]; + doc_epub3[segment_filename] ~= t[0]; break; case "glossary": auto t = xhtml_format.para_seg(obj, suffix); - doc_epub[segment_filename] ~= t[0]; - doc_epub_endnotes[segment_filename] ~= t[1]; + doc_epub3[segment_filename] ~= t[0]; + doc_epub3_endnotes[segment_filename] ~= t[1]; break; case "bibliography": auto t = xhtml_format.para_seg(obj, suffix); - doc_epub[segment_filename] ~= t[0]; - doc_epub_endnotes[segment_filename] ~= t[1]; + doc_epub3[segment_filename] ~= t[0]; + doc_epub3_endnotes[segment_filename] ~= t[1]; break; case "bookindex": auto t = xhtml_format.para_seg(obj, suffix); - doc_epub[segment_filename] ~= t[0]; - doc_epub_endnotes[segment_filename] ~= t[1]; + doc_epub3[segment_filename] ~= t[0]; + doc_epub3_endnotes[segment_filename] ~= t[1]; break; case "blurb": auto t = xhtml_format.para_seg(obj, suffix); - doc_epub[segment_filename] ~= t[0]; - doc_epub_endnotes[segment_filename] ~= t[1]; + doc_epub3[segment_filename] ~= t[0]; + doc_epub3_endnotes[segment_filename] ~= t[1]; break; default: if ((doc_matters.opt_action_bool["debug"])) { @@ -2914,14 +3164,59 @@ void outputEPub(D,I)( break; } } + if (obj.is_a == "heading") { + if (obj.heading_lev_markup == 4) { + oepbs_content_parts["manifest_documents"] ~= format(q"¶ <item id="%s.xhtml" href="%s.xhtml" media-type="application/xhtml+xml" /> +¶", + obj.segment_anchor_tag, + obj.segment_anchor_tag, + ); + oepbs_content_parts["spine"] ~= format(q"¶ <itemref idref="%s.xhtml" linear="yes" /> +¶", + obj.segment_anchor_tag, + ); + oepbs_content_parts["guide"] ~= format(q"¶ <reference type="%s" href="%s" /> +¶", + obj.segment_anchor_tag, + obj.segment_anchor_tag, + ); + } else if (obj.heading_lev_markup > 4) { + oepbs_content_parts["manifest_documents"] ~= format(q"¶ <item id="%s.xhtml#%s" href="%s.xhtml#%s" media-type="application/xhtml+xml" /> +¶", + obj.segment_anchor_tag, + obj.obj_cite_number, + obj.segment_anchor_tag, + obj.obj_cite_number, + ); + oepbs_content_parts["spine"] ~= format(q"¶ <itemref idref="%s.xhtml#%s" linear="yes" /> +¶", + obj.segment_anchor_tag, + obj.obj_cite_number, + ); + oepbs_content_parts["guide"] ~= format(q"¶ <reference type="%s#%s" href="%s#%s" /> +¶", + obj.segment_anchor_tag, + obj.obj_cite_number, + obj.segment_anchor_tag, + obj.obj_cite_number, + ); + } + } } } - epub_write_output_files( + /+ epub specific documents +/ + auto mimetypes = epub3_mimetypes; + auto meta_inf_container_xml = epub3_container_xml; + auto oebps_toc_ncx = epub2_oebps_toc_ncx(doc_abstraction, doc_matters); + auto oebps_toc_nav_xhtml = epub3_oebps_toc_nav_xhtml(doc_abstraction, doc_matters); + auto oebps_content_opf = epub3_oebps_content(doc_abstraction, doc_matters, oepbs_content_parts); + epub3_write_output_files( doc_matters, - doc_epub, - doc_epub_endnotes, + doc_epub3, + doc_epub3_endnotes, mimetypes, meta_inf_container_xml, + oebps_toc_nav_xhtml, oebps_toc_ncx, oebps_content_opf, ); @@ -2930,71 +3225,214 @@ void outputEPub(D,I)( **** write output files -#+name: output_epub_xhtml_seg +#+name: output_epub3_xhtml_seg #+BEGIN_SRC d -void epub_write_output_files(M,D,E,Mt,Mic,Ot,Oc)( +void epub3_write_output_files(M,D,E,Mt,Mic,Otnx,Otn,Oc)( M doc_matters, - D doc_epub, - E doc_epub_endnotes, + D doc_epub3, + E doc_epub3_endnotes, Mt mimetypes, Mic meta_inf_container_xml, - Ot oebps_toc_ncx, + Otnx oebps_toc_nav_xhtml, + Otn oebps_toc_ncx, Oc oebps_content_opf, ) { - debug(asserts){ - static assert(is(typeof(doc_epub) == string[][string])); + debug(asserts) { + static assert(is(typeof(doc_epub3) == string[][string])); static assert(is(typeof(mimetypes) == string)); static assert(is(typeof(meta_inf_container_xml) == string)); + static assert(is(typeof(oebps_toc_nav_xhtml) == string)); static assert(is(typeof(oebps_toc_ncx) == string)); static assert(is(typeof(oebps_content_opf) == string)); } mixin SiSUpaths; - auto pth_epub = EpubPaths(); + auto pth_epub3 = Epub3paths(); auto xhtml_format = outputXHTMLs(); + /+ zip file +/ + auto fn_epub = pth_epub3.epub_file(doc_matters.source_filename); + auto zip = new ZipArchive(); // ZipArchive zip = new ZipArchive(); + /+ zip archive member files +/ try { - if (!exists(pth_epub.doc_meta_inf(doc_matters.source_filename))) { - pth_epub.doc_meta_inf(doc_matters.source_filename).mkdirRecurse; + if (!exists(pth_epub3.doc_meta_inf(doc_matters.source_filename))) { + pth_epub3.doc_meta_inf(doc_matters.source_filename).mkdirRecurse; } - if (!exists(pth_epub.doc_oebps_css(doc_matters.source_filename))) { - pth_epub.doc_oebps_css(doc_matters.source_filename).mkdirRecurse; + if (!exists(pth_epub3.doc_oebps_css(doc_matters.source_filename))) { + pth_epub3.doc_oebps_css(doc_matters.source_filename).mkdirRecurse; } - if (!exists(pth_epub.doc_oebps_image(doc_matters.source_filename))) { - pth_epub.doc_oebps_image(doc_matters.source_filename).mkdirRecurse; + if (!exists(pth_epub3.doc_oebps_image(doc_matters.source_filename))) { + pth_epub3.doc_oebps_image(doc_matters.source_filename).mkdirRecurse; } - /+ OEBPS/[segments].xhtml +/ - foreach (seg_filename; doc_matters.segnames) { - auto f = File(pth_epub.fn_oebps_content_xhtml(doc_matters.source_filename, seg_filename), "w"); - /+ // f.writeln(seg_head); // not needed built and inserted earlier +/ - foreach (docseg; doc_epub[seg_filename]) { - f.writeln(docseg); + { /+ OEBPS/[segments].xhtml (the document contents) +/ + foreach (seg_filename; doc_matters.segnames) { + string fn = pth_epub3.fn_oebps_content_xhtml(doc_matters.source_filename, seg_filename); + /+ add zip archive file members (with their content) +/ + auto zip_arc_member_file = new ArchiveMember(); + // add seg fn to zip archive + zip_arc_member_file.name = fn; + auto zip_data = new OutBuffer(); + debug(epub_output) { + string fn_dbg = pth_epub3.dbg_fn_oebps_content_xhtml(doc_matters.source_filename, seg_filename); + auto f = File(fn_dbg, "w"); + } + /+ // f.writeln(seg_head); // not needed built and inserted earlier +/ + foreach (docseg; doc_epub3[seg_filename]) { + debug(epub_output) { f.writeln(docseg); } + zip_data.write(docseg.dup); // cast as: char[] + } + foreach (docseg; doc_epub3_endnotes[seg_filename]) { + debug(epub_output) { f.writeln(docseg); } + zip_data.write(docseg.dup); // cast as: char[] + } + debug(epub_output) { f.writeln(xhtml_format.tail); } // needed for each lev4 + zip_data.write(xhtml_format.tail.dup); // cast as: char[] + zip_arc_member_file.expandedData = zip_data.toBytes(); + zip.addMember(zip_arc_member_file); + /+ create the zip file +/ + createZipFile!()(fn_epub, zip.build()); } - foreach (docseg; doc_epub_endnotes[seg_filename]) { - f.writeln(docseg); + } + string fn; + debug(epub_output) { string fn_dbg; } + File f; + { /+ mimetypes (identify zip file type) +/ + debug(epub_output) { + fn_dbg = pth_epub3.dbg_fn_mimetypes(doc_matters.source_filename); + File(fn_dbg, "w").writeln(mimetypes); } - f.writeln(xhtml_format.tail); // needed for each lev4 + fn = pth_epub3.fn_mimetypes(doc_matters.source_filename); + /+ add zip archive file members (with their content) +/ + auto zip_arc_member_file = new ArchiveMember(); + // add mimetypes to zip archive + zip_arc_member_file.name = fn; + auto zip_data = new OutBuffer(); + zip_data.write(mimetypes.dup); // cast as: char[] + zip_arc_member_file.expandedData = zip_data.toBytes(); + zip.addMember(zip_arc_member_file); + /+ create the zip file +/ + createZipFile!()(fn_epub, zip.build()); + } + { /+ META-INF/container.xml (identify doc root) +/ + debug(epub_output) { + fn_dbg = pth_epub3.dbg_fn_dmi_container_xml(doc_matters.source_filename); + File(fn_dbg, "w").writeln(meta_inf_container_xml); + } + fn = pth_epub3.fn_dmi_container_xml(doc_matters.source_filename); + /+ add zip archive file members (with their content) +/ + auto zip_arc_member_file = new ArchiveMember(); + // add META-INF/container.xml to zip archive + zip_arc_member_file.name = fn; + auto zip_data = new OutBuffer(); + zip_data.write(meta_inf_container_xml.dup); // cast as: char[] + zip_arc_member_file.expandedData = zip_data.toBytes(); + zip.addMember(zip_arc_member_file); + /+ create the zip file +/ + createZipFile!()(fn_epub, zip.build()); + } + { /+ OEBPS/toc_nav.xhtml (navigation toc epub3) +/ + debug(epub_output) { + fn_dbg = pth_epub3.dbg_fn_oebps_toc_nav_xhtml(doc_matters.source_filename); + File(fn_dbg, "w").writeln(oebps_toc_nav_xhtml); + } + fn = pth_epub3.fn_oebps_toc_nav_xhtml(doc_matters.source_filename); + /+ add zip archive file members (with their content) +/ + auto zip_arc_member_file = new ArchiveMember(); + // add OEBPS/toc_nav.xhtml to zip archive + zip_arc_member_file.name = fn; + auto zip_data = new OutBuffer(); + zip_data.write(oebps_toc_nav_xhtml.dup); // cast as: char[] + zip_arc_member_file.expandedData = zip_data.toBytes(); + zip.addMember(zip_arc_member_file); + /+ create the zip file +/ + createZipFile!()(fn_epub, zip.build()); + } + { /+ TODO OEBPS/toc.ncx (navigation toc epub2) +/ + debug(epub_output) { + fn_dbg = pth_epub3.dbg_fn_oebps_toc_ncx(doc_matters.source_filename); + File(fn_dbg, "w").writeln(oebps_toc_ncx); + } + fn = pth_epub3.fn_oebps_toc_ncx(doc_matters.source_filename); + /+ add zip archive file members (with their content) +/ + auto zip_arc_member_file = new ArchiveMember(); + // add OEBPS/toc.ncx to zip archive + zip_arc_member_file.name = fn; + auto zip_data = new OutBuffer(); + zip_data.write(oebps_toc_ncx.dup); // cast as: char[] + zip_arc_member_file.expandedData = zip_data.toBytes(); + zip.addMember(zip_arc_member_file); + /+ create the zip file +/ + createZipFile!()(fn_epub, zip.build()); } - /+ mimetypes +/ - auto f = File(pth_epub.fn_mimetypes(doc_matters.source_filename), "w"); - f.writeln(mimetypes); - /+ META-INF/container.xml +/ - f = File(pth_epub.fn_dmi_container_xml(doc_matters.source_filename), "w"); - f.writeln(meta_inf_container_xml); - /+ OEBPS/toc.ncx +/ - f = File(pth_epub.fn_oebps_toc_ncx(doc_matters.source_filename), "w"); - f.writeln(oebps_toc_ncx); - /+ OEBPS/content.opf +/ - f = File(pth_epub.fn_oebps_content_opf(doc_matters.source_filename), "w"); - f.writeln(oebps_content_opf); - foreach (image; doc_matters.image_list) { - if (exists("_sisu/image/"~ image)) { - ("_sisu/image/"~ image) - .copy((pth_epub.doc_oebps_image(doc_matters.source_filename)) ~ "/" ~ image); + { /+ TODO OEBPS/content.opf (doc manifest) +/ + debug(epub_output) { + fn_dbg = pth_epub3.dbg_fn_oebps_content_opf(doc_matters.source_filename); + File(fn_dbg, "w").writeln(oebps_content_opf); + } + fn = pth_epub3.fn_oebps_content_opf(doc_matters.source_filename); + /+ add zip archive file members (with their content) +/ + auto zip_arc_member_file = new ArchiveMember(); + // add OEBPS/content.opf to zip archive + zip_arc_member_file.name = fn; + auto zip_data = new OutBuffer(); + zip_data.write(oebps_content_opf.dup); // cast as: char[] + zip_arc_member_file.expandedData = zip_data.toBytes(); + zip.addMember(zip_arc_member_file); + /+ create the zip file +/ + createZipFile!()(fn_epub, zip.build()); + } + { /+ OEBPS/_sisu/image (images) +/ + foreach (image; doc_matters.image_list) { + if (exists("_sisu/image/"~ image)) { + ("_sisu/image/"~ image) + .copy((pth_epub3.doc_oebps_image(doc_matters.source_filename)) ~ "/" ~ image); + } + } + foreach (image; doc_matters.image_list) { + debug(epub_images) { + writeln( + "_sisu/image/", image, " -> ", + pth_epub3.doc_oebps_image(doc_matters.source_filename), "/", image + ); + } + auto fn_src = "_sisu/image/"~ image; + auto fn_out = pth_epub3.doc_oebps_image(doc_matters.source_filename).to!string ~ "/" ~ image; + if (exists(fn_src)) { + { + auto zip_arc_member_file = new ArchiveMember(); + zip_arc_member_file.name = fn_out; + auto zip_data = new OutBuffer(); + zip_data.write(cast(char[]) ((fn_src).read)); + zip_arc_member_file.expandedData = zip_data.toBytes(); + zip.addMember(zip_arc_member_file); + createZipFile!()(fn_epub, zip.build()); + } + } } } } catch (ErrnoException ex) { // Handle error } +#+END_SRC + +*** zip debug, read zip archive + +#+name: output_epub3_xhtml_seg +#+BEGIN_SRC d + debug(epub_archive) { + if (exists(fn_epub)) { + try { + auto zipped = new ZipArchive((fn_epub).read); + foreach (filename, member; zipped.directory) { + auto data = zipped.expand(member); + writeln(filename, " length ", data.length); // member.name + // Use data + } + } + catch (ZipException ex) { + // Handle errors + } + } + } } #+END_SRC diff --git a/org/sdp.org b/org/sdp.org index ff989c9..6ef3d06 100644 --- a/org/sdp.org +++ b/org/sdp.org @@ -23,7 +23,7 @@ struct Version { int minor; int patch; } -enum ver = Version(0, 13, 8); +enum ver = Version(0, 13, 9); #+END_SRC * 1. sdp (sisu document parser) :sdp: @@ -72,9 +72,9 @@ void main(string[] args) { } unittest { /++ - name "sdp" - description "A SiSU document parser writen in D." - homepage "http://sisudoc.org" + name "sdp" + description "A SiSU document parser writen in D." + homepage "http://sisudoc.org" +/ } #+END_SRC |