aboutsummaryrefslogtreecommitdiffhomepage
diff options
context:
space:
mode:
authorRalph Amissah <ralph@amissah.com>2015-09-30 13:07:43 -0400
committerRalph Amissah <ralph@amissah.com>2015-09-30 13:12:21 -0400
commit45e96028ce7696381aca7f155c21b0b718b6a610 (patch)
treeeefcf5737cffc0d457bc433cd41ba21579076ff2
sdp, abstract objects, a start
Diffstat
-rw-r--r--.gitignore24
-rw-r--r--lib/sdp/ao_abstract_doc_source.d1695
-rw-r--r--lib/sdp/ao_assertions.d222
-rw-r--r--lib/sdp/ao_defaults.d257
-rw-r--r--lib/sdp/ao_emitter.d1322
-rw-r--r--lib/sdp/ao_interface.d145
-rw-r--r--lib/sdp/ao_markup_source_raw.d58
-rw-r--r--lib/sdp/ao_object_setter.d90
-rw-r--r--lib/sdp/ao_output_debugs.d354
-rw-r--r--lib/sdp/ao_rgx.d195
-rw-r--r--lib/sdp/ao_scan_inserts.d229
-rw-r--r--lib/sdp/ao_utils.d74
-rw-r--r--lib/sdp/sdp.d161
-rw-r--r--lib/sdp/sdp.org331
-rw-r--r--sdp.org369
15 files changed, 5526 insertions, 0 deletions
diff --git a/.gitignore b/.gitignore
new file mode 100644
index 0000000..ead1bf3
--- /dev/null
+++ b/.gitignore
@@ -0,0 +1,24 @@
+# git ls-files --others --exclude-from=.git/info/exclude
+*
+!.gitignore
+!*.d
+!*.rl
+!*.org
+!*.ss[tmi]
+!README
+*_.d
+*_.rl
+!**/
+**/scratch
+**/.#*
+#*~
+#\#*
+#*.\#*
+#*_.rl
+#*.rl_
+#*.rb
+#*.[o]
+#*.[^d]
+#*.[^s][^s][^tmi]
+#[^/a-z]*[^.][^d]
+#*[^.][^d]
diff --git a/lib/sdp/ao_abstract_doc_source.d b/lib/sdp/ao_abstract_doc_source.d
new file mode 100644
index 0000000..2fec35d
--- /dev/null
+++ b/lib/sdp/ao_abstract_doc_source.d
@@ -0,0 +1,1695 @@
+/*
+#+OPTIONS: ^:nil _:nil#+OPTIONS: ^:nil _:nil
+* sisu_abstract_doc_source.d
+*/
+mixin template SiSUdocAbstraction() {
+ class Abstraction {
+ auto abstract_doc_source(char[][] markup_sourcefile_content) {
+ mixin ObjectSetters;
+ mixin AssertionsOnMarkupDocumentStructure;
+ mixin AssertionsOnBlocks;
+ mixin ScreenTxtColors;
+ auto rgx = new Rgx();
+ auto set_oa = new ObjectAbstractSet();
+ auto set_header = new HeaderDocMetadataMakeJson();
+ auto notesection = new NotesSection();
+ string[string][131072] contents_arbitrary_max_length_set; // 2000 pg * 50 lines == 100000
+ string[1024] notes;
+ string notes_str;
+ string[string] object, processing, head;
+ string biblio_tag_name, biblio_tag_entry, book_idx_tmp, st;
+ string[1024] biblio_arr_json = biblio_entry_tags_jsonstr;
+ JSONValue[1024] bib_arr_json;
+ uint[string] line_occur;
+ int counter, previous_count, count_biblio_entry, ocn, ocn_, verse_line, bib_entry, heading_pointer, notepoint;
+ string indent_first, indent_second;
+ string[][string][string] bookindex_unordered_hashes;
+ bool bullet = true;
+ uint[string] lv = [
+ "lv" : 0,
+ "h0" : 0,
+ "h1" : 0,
+ "h2" : 0,
+ "h3" : 0,
+ "h4" : 0,
+ "h5" : 0,
+ "h6" : 0,
+ "h7" : 0,
+ "lcn" : 0,
+ ];
+ int[string] collapsed_lev = [
+ "h0" : 0,
+ "h1" : 0,
+ "h2" : 0,
+ "h3" : 0,
+ "h4" : 0,
+ "h5" : 0,
+ "h6" : 0,
+ "h7" : 0
+ ];
+ auto rgx_h_A = regex(r"^(none)");
+ auto rgx_h_B = regex(r"^(none)");
+ auto rgx_h_C = regex(r"^(none)");
+ auto rgx_h_D = regex(r"^(none)");
+ auto rgx_h_1 = regex(r"^(none)");
+ auto rgx_h_2 = regex(r"^(none)");
+ auto rgx_h_3 = regex(r"^(none)");
+ auto rgx_h_4 = regex(r"^(none)");
+ auto str_h_A = "^(none)";
+ auto str_h_B = "^(none)";
+ auto str_h_C = "^(none)";
+ auto str_h_D = "^(none)";
+ auto str_h_1 = "^(none)";
+ auto str_h_2 = "^(none)";
+ auto str_h_3 = "^(none)";
+ auto str_h_4 = "^(none)";
+ string content_non_header = "8";
+ string node;
+ auto obj_im = new ObjInlineMarkup();
+ auto obj_att = new ObjAttrib();
+ auto object_citation_number = new OCNemitter();
+ auto ft = flag_type.dup;
+ int ocn_emit(int ocn_status_flag) {
+ return object_citation_number.ocn_emitter(ocn_status_flag);
+ }
+ auto bookindex_extract_hash = new BookIndexNuggetHash();
+ string[][string][string] bkidx_hash(string bookindex, int ocn) {
+ return bookindex_extract_hash.bookindex_nugget_hash(bookindex, ocn);
+ }
+ auto node_construct = new NodeStructureMetadata();
+ string node_jstr(
+ string lvn,
+ int ocn_,
+ int counter,
+ int heading_pointer,
+ string is_
+ ) {
+ return node_construct.node_emitter(
+ lvn,
+ ocn_,
+ counter,
+ heading_pointer,
+ is_
+ );
+ }
+ string node_jstr_heading(
+ string lvn,
+ string lcn,
+ int ocn_,
+ int counter,
+ int heading_pointer,
+ string is_
+ ) {
+ return node_construct.node_emitter_heading(
+ lvn,
+ lcn,
+ ocn_,
+ counter,
+ heading_pointer,
+ is_
+ );
+ }
+ string[string] ocn_poem = [
+ "start" : "",
+ "end" : ""
+ ];
+ int tell_lo(string color, int ocn, in char[] line) {
+ writeln(scr_txt_marker[color], to!string(ocn), " ", to!string(line));
+ return 0;
+ }
+ int tell_l(string color, in char[] line) {
+ writeln(scr_txt_marker[color], line);
+ return 0;
+ }
+ scope(success) {
+ }
+ scope(failure) {
+ }
+ scope(exit) {
+ destroy(contents_arbitrary_max_length_set);
+ destroy(object);
+ destroy(processing);
+ destroy(biblio_arr_json);
+ }
+ auto dochead_make = parseJSON(header_make_jsonstr).object;
+ auto dochead_metadata = parseJSON(header_metadata_jsonstr).object;
+ foreach (line; markup_sourcefile_content) {
+ scope(exit) {
+ }
+ scope(failure) {
+ writeln(__FILE__, ":", __LINE__, " failed here:");
+ writeln(" line: ", line);
+ writeln(" is : ", object["is"]);
+ writeln(" node: ", node);
+ }
+ line = replaceAll(line, rgx.true_dollar, "$$$$");
+ debug(source) { // source lines
+ writeln(line);
+ }
+ debug(srclines) {
+ if (!line.empty) { // source lines, not empty
+ writeln(scr_txt_marker["green"], line);
+ }
+ }
+ if ((!line.empty) && (ft["ocn_status_multi_obj"] == 0)) {
+ if (match(line, rgx.ocn_block_marks)) {
+ if (match(line, rgx.ocn_off_block)) {
+ ft["ocn_status_multi_obj"] = 1;
+ debug(ocnoff) {
+ tell_l("fuchsia", line);
+ }
+ }
+ if (match(line, rgx.ocn_off_block_dh)) {
+ ft["ocn_status_multi_obj"] = 2;
+ debug(ocnoff) {
+ tell_l("fuchsia", line);
+ }
+ }
+ } else {
+ if (ft["ocn_status_multi_obj"] == 0) {
+ if (match(line, rgx.ocn_off)) {
+ ft["ocn_status"] = 1;
+ } else if (match(line, rgx.ocn_off_dh)) {
+ ft["ocn_status"] = 2;
+ } else {
+ ft["ocn_status"] = 2;
+ ft["ocn_status"] = 0;
+ }
+ } else {
+ ft["ocn_status"] = ft["ocn_status_multi_obj"];
+ }
+ }
+ } else if ((!line.empty) && (ft["ocn_status_multi_obj"] > 0)) {
+ if (auto m = match(line, rgx.ocn_off_block_close)) {
+ ft["ocn_status_multi_obj"] = 0;
+ ft["ocn_status"] = 0;
+ debug(ocnoff) {
+ tell_l("green", line);
+ }
+ }
+ }
+ if (ft["code"] == 1) {
+ if (ft["curly_code"] == 1) {
+ if (auto m = match(line, rgx.block_curly_code_close)) {
+ debug(code) { // code (curly) close
+ tell_l("blue", line);
+ }
+ ft["blocks"] = 2;
+ ft["code"] = 2;
+ ft["curly_code"] = 0;
+ } else {
+ debug(code) { // code (curly) line
+ tell_l("blue", line);
+ }
+ object["obj"] ~= line ~= "\n"; // code (curly) line
+ }
+ } else if (ft["tic_code"] == 1) {
+ if (auto m = match(line, rgx.block_tic_close)) {
+ debug(code) { // code (tic) close
+ tell_l("blue", line);
+ }
+ ft["blocks"] = 2;
+ ft["code"] = 2;
+ ft["tic_code"] = 0;
+ } else {
+ debug(code) { // code (tic) line
+ tell_l("blue", line);
+ }
+ object["obj"] ~= line ~= "\n"; // code (tic) line
+ }
+ }
+ } else if (!match(line, rgx.regular_parse_skip)) {
+ if (((match(line, rgx.heading_biblio)
+ || (ft["heading_biblio"] == 1)))
+ && (!match(line, rgx.heading))
+ && (!match(line, rgx.comment))) {
+ if (match(line, rgx.heading_biblio)) {
+ ft["heading_biblio"] = 1;
+ }
+ if (empty(line) && (bib_entry == 0)) {
+ count_biblio_entry++;
+ bib_entry = 1;
+ }
+ debug(biblio) {
+ writeln(
+ scr_txt_color["yellow"],
+ "* ",
+ scr_txt_color["off"],
+ to!string(count_biblio_entry),
+ " ",
+ line
+ );
+ }
+ if (match(line, rgx.biblio_tags)) {
+ auto bt = match(line, rgx.biblio_tags);
+ bib_entry = 0;
+ st=to!string(bt.captures[1]);
+ biblio_tag_entry=to!string(bt.captures[2]);
+ JSONValue j = parseJSON(biblio_arr_json[count_biblio_entry]);
+ if (match(st, rgx.biblio_abbreviations)) {
+ biblio_tag_name=biblio_tag_map[st];
+ } else {
+ biblio_tag_name=st;
+ }
+ j.object[biblio_tag_name] = biblio_tag_entry;
+ auto header_tag_value=to!string(bt.captures[2]);
+ switch (biblio_tag_name) {
+ case "author_raw": // author_arr author (fn sn)
+ j["author_arr"]=split(header_tag_value, rgx.arr_delimiter);
+ string tmp;
+ foreach (au; j["author_arr"].array) {
+ if (auto x = match(au.str, rgx.name_delimiter)) {
+ tmp ~= x.captures[2] ~ " " ~ x.captures[1] ~ ", ";
+ } else {
+ tmp ~= au.str;
+ }
+ }
+ tmp = replace(tmp, rgx.trailing_comma, "");
+ j["author"].str = tmp;
+ break;
+ case "editor_raw": // editor_arr editor (fn sn)
+ j["editor_arr"]=split(header_tag_value, rgx.arr_delimiter);
+ string tmp;
+ foreach (ed; j["editor_arr"].array) {
+ if (auto x = match(ed.str, rgx.name_delimiter)) {
+ tmp ~= x.captures[2] ~ " " ~ x.captures[1] ~ ", ";
+ } else {
+ tmp ~= ed.str;
+ }
+ }
+ tmp = replace(tmp, rgx.trailing_comma, "");
+ j["editor"].str = tmp;
+ break;
+ case "fulltitle": // title & subtitle
+ break;
+ default:
+ break;
+ }
+ auto s = to!string(j);
+ s = j.toString();
+ debug(biblio) {
+ writeln(
+ scr_txt_color["red"],
+ "* ",
+ scr_txt_color["off"],
+ biblio_tag_name,
+ ": ",
+ biblio_tag_entry
+ );
+ writeln(biblio_arr_json[count_biblio_entry]);
+ writeln(j[biblio_tag_name], ":", j[biblio_tag_name]);
+ }
+ biblio_arr_json[count_biblio_entry] = s;
+ biblio_tag_entry="";
+ }
+ } else if (ft["poem"] == 1) {
+ if (ft["curly_poem"] == 1) {
+ if (auto m = match(line, rgx.block_curly_poem_close)) {
+ object["obj"]="verse"; // check that this is as you please
+ debug(poem) { // poem (curly) close
+ writeln(
+ scr_txt_color["red"],
+ "* [poem curly] ",
+ scr_txt_color["off"],
+ line
+ );
+ }
+ if (processing.length > 0) {
+ object["obj"] = processing["verse"];
+ }
+ debug(poem) { // poem (curly) close
+ writeln(__LINE__);
+ writeln(
+ scr_txt_marker["fuchsia"],
+ ocn,
+ " ",
+ line
+ );
+ }
+ if (object.length > 0) {
+ debug(poem) { // poem (curly) close
+ writeln(__LINE__);
+ tell_lo(
+ "fuchsia",
+ ocn,
+ object["obj"]
+ );
+ writeln(__LINE__);
+ }
+ object["is"] = "verse";
+ object["markup"] =
+ obj_im.obj_inline_markup(object["is"], object["obj"]);
+ object["attrib"] =
+ obj_att.obj_attributes(object["is"], object["obj"], node);
+ contents_arbitrary_max_length_set[counter] =
+ set_oa.contents_block(
+ object["is"],
+ object["markup"],
+ object["attrib"],
+ ocn
+ );
+ object.remove("obj");
+ object.remove("markup");
+ object.remove("is");
+ object.remove("attrib");
+ object.remove("bookindex");
+ processing.remove("verse");
+ counter++;
+ }
+ ocn_poem["end"] = to!string(ocn);
+ ft["blocks"] = 2;
+ ft["poem"] = 2;
+ ft["curly_poem"] = 0;
+ } else {
+ processing["verse"] ~= line ~= "\n";
+ if (ft["verse_new"] == 1) {
+ ocn = ocn_emit(ft["ocn_status"]);
+ ft["verse_new"] = 0;
+ } else if (match(line, rgx.line_delimiter_only)) {
+ verse_line = 0;
+ ft["verse_new"] = 1;
+ }
+ if (ft["verse_new"] == 1) {
+ verse_line=1;
+ object["obj"] = processing["verse"];
+ debug(poem) { // poem verse
+ writeln(scr_txt_marker["green"],
+ ocn,
+ " curly\n",
+ object["obj"]);
+ }
+ processing.remove("verse");
+ object["is"] = "verse";
+ node = node_jstr(
+ content_non_header,
+ ocn,
+ counter,
+ heading_pointer-1,
+ object["is"]
+ );
+ object["markup"] = obj_im.obj_inline_markup(object["is"], object["obj"]);
+ object["attrib"] = obj_att.obj_attributes(object["is"], object["obj"], node);
+ contents_arbitrary_max_length_set[counter] =
+ set_oa.contents_block(
+ object["is"],
+ object["markup"],
+ object["attrib"],
+ ocn
+ );
+ object.remove("obj");
+ object.remove("markup");
+ object.remove("is");
+ object.remove("attrib");
+ object.remove("bookindex");
+ processing.remove("verse");
+ counter++;
+ }
+ }
+ } else if (ft["tic_poem"] == 1) {
+ if (auto m = match(line, rgx.block_tic_close)) { // tic_poem_close
+ object["obj"]="verse"; // check that this is as you please
+ debug(poem) { // poem (curly) close
+ writeln(
+ scr_txt_color["red"],
+ "* [poem tic] ",
+ scr_txt_color["off"],
+ line
+ );
+ }
+ if (processing.length > 0) { // needs looking at
+ object["obj"] = processing["verse"];
+ }
+ if (object.length > 0) {
+ debug(poem) { // poem (tic) close
+ writeln(__LINE__);
+ tell_lo("fuchsia", ocn, line);
+ }
+ processing.remove("verse");
+ object["is"] = "verse";
+ object["markup"] =
+ obj_im.obj_inline_markup(object["is"], object["obj"]);
+ object["attrib"] =
+ obj_att.obj_attributes(object["is"], object["obj"], node);
+ contents_arbitrary_max_length_set[counter] =
+ set_oa.contents_block(
+ object["is"],
+ object["markup"],
+ object["attrib"],
+ ocn
+ );
+ ocn_poem["end"] = to!string(ocn);
+ object.remove("obj");
+ object.remove("markup");
+ object.remove("is");
+ object.remove("attrib");
+ object.remove("bookindex");
+ processing.remove("verse");
+ counter++;
+ }
+ ft["blocks"] = 2;
+ ft["poem"] = 2;
+ ft["tic_poem"] = 0;
+ } else {
+ processing["verse"] ~= line ~= "\n";
+ if (ft["verse_new"] == 1) {
+ ocn = ocn_emit(ft["ocn_status"]);
+ ft["verse_new"] = 0;
+ } else if (match(line, rgx.line_delimiter_only)) {
+ ft["verse_new"] = 1;
+ verse_line = 0;
+ }
+ if (ft["verse_new"] == 1) {
+ verse_line=1;
+ object["obj"] = processing["verse"];
+ debug(poem) { // poem (tic) close
+ writeln(scr_txt_marker["green"],
+ ocn,
+ " tic\n",
+ object["obj"]);
+ }
+ processing.remove("verse");
+ object["is"] = "verse";
+ node =
+ node_jstr(
+ content_non_header,
+ ocn,
+ counter,
+ heading_pointer-1,
+ object["is"]
+ );
+ object["markup"] =
+ obj_im.obj_inline_markup(object["is"], object["obj"]);
+ object["attrib"] =
+ obj_att.obj_attributes(object["is"], object["obj"], node);
+ contents_arbitrary_max_length_set[counter] =
+ set_oa.contents_block(
+ object["is"],
+ object["markup"],
+ object["attrib"],
+ ocn
+ );
+ object.remove("obj");
+ object.remove("markup");
+ object.remove("is");
+ object.remove("attrib");
+ object.remove("bookindex");
+ processing.remove("verse");
+ counter++;
+ }
+ }
+ }
+ } else if (ft["group"] == 1) {
+ if (ft["curly_group"] == 1) {
+ if (auto m = match(line, rgx.block_curly_group_close)) {
+ debug(group) { // group (curly) close
+ tell_l("blue", line);
+ }
+ ft["blocks"] = 2;
+ ft["group"] = 2;
+ ft["curly_group"] = 0;
+ } else {
+ debug(group) { // group
+ tell_l("blue", line);
+ }
+ object["obj"] ~= line ~= "\n"; // build group array (or string)
+ }
+ } else if (ft["tic_group"] == 1) {
+ if (auto m = match(line, rgx.block_tic_close)) {
+ debug(group) { // group (tic) close
+ tell_l("blue", line);
+ }
+ ft["blocks"] = 2;
+ ft["group"] = 2;
+ ft["tic_group"] = 0;
+ } else {
+ debug(group) { // group
+ tell_l("blue", line);
+ }
+ object["obj"] ~= line ~= "\n"; // build group array (or string)
+ }
+ }
+ } else if (ft["block"] == 1) {
+ if (ft["curly_block"] == 1) {
+ if (auto m = match(line, rgx.block_curly_block_close)) {
+ debug(block) { // block (curly) close
+ tell_l("blue", line);
+ }
+ ft["blocks"] = 2;
+ ft["block"] = 2;
+ ft["curly_block"] = 0;
+ } else {
+ debug(block) { // block
+ tell_l("blue", line);
+ }
+ object["obj"] ~= line ~= "\n"; // build block array (or string)
+ }
+ } else if (ft["tic_block"] == 1) {
+ if (auto m = match(line, rgx.block_tic_close)) {
+ debug(block) { // block (tic) close
+ tell_l("blue", line);
+ }
+ ft["blocks"] = 2;
+ ft["block"] = 2;
+ ft["tic_block"] = 0;
+ } else {
+ debug(block) { // block
+ tell_l("blue", line);
+ }
+ object["obj"] ~= line ~= "\n"; // build block array (or string)
+ }
+ }
+ } else if (ft["quote"] == 1) {
+ if (ft["curly_quote"] == 1) {
+ if (auto m = match(line, rgx.block_curly_quote_close)) {
+ debug(quote) { // quote (curly) close
+ tell_l("blue", line);
+ }
+ ft["blocks"] = 2;
+ ft["quote"] = 2;
+ ft["curly_quote"] = 0;
+ } else {
+ debug(quote) { // quote
+ tell_l("blue", line);
+ }
+ object["obj"] ~= line ~= "\n"; // build quote array (or string)
+ }
+ } else if (ft["tic_quote"] == 1) {
+ if (auto m = match(line, rgx.block_tic_close)) {
+ debug(quote) { // quote (tic) close
+ tell_l("blue", line);
+ }
+ ft["blocks"] = 2;
+ ft["quote"] = 2;
+ ft["tic_quote"] = 0;
+ } else {
+ debug(quote) { // quote
+ tell_l("blue", line);
+ }
+ object["obj"] ~= line ~= "\n"; // build quote array (or string)
+ }
+ }
+ } else if (ft["table"] == 1) {
+ if (ft["curly_table"] == 1) {
+ if (auto m = match(line, rgx.block_curly_table_close)) {
+ debug(table) { // table (curly) close
+ tell_l("blue", line);
+ }
+ ft["blocks"] = 2;
+ ft["table"] = 2;
+ ft["curly_table"] = 0;
+ } else {
+ debug(table) { // table
+ tell_l("blue", line);
+ }
+ object["obj"] ~= line ~= "\n"; // build table array (or string)
+ }
+ } else if (ft["tic_table"] == 1) {
+ if (auto m = match(line, rgx.block_tic_close)) {
+ debug(table) { // table (tic) close
+ tell_l("blue", line);
+ }
+ ft["blocks"] = 2;
+ ft["table"] = 2;
+ ft["tic_table"] = 0;
+ } else {
+ debug(table) { // table
+ tell_l("blue", line);
+ }
+ object["obj"] ~= line ~= "\n"; // build table array (or string)
+ }
+ }
+ } else {
+ assert(
+ (ft["blocks"] == 0)
+ || (ft["blocks"] == 2),
+ "block status: none or closed"
+ );
+ assertions_flag_types_block_status_none_or_closed(ft);
+ if (auto m = match(line, rgx.block_curly_code_open)) {
+ debug(code) { // code (curly) open
+ writeln(
+ scr_txt_color["blue"],
+ "* [code curly] ",
+ scr_txt_color["off"],
+ line
+ );
+ }
+ ft["blocks"] = 1;
+ ft["code"] = 1;
+ ft["curly_code"] = 1;
+ } else if (auto m = match(line, rgx.block_curly_poem_open)) {
+ object.remove("obj");
+ object.remove("markup");
+ object.remove("is");
+ object.remove("attrib");
+ object.remove("bookindex");
+ processing.remove("verse");
+ debug(poem) { // poem (curly) open
+ writeln(
+ scr_txt_color["red"],
+ "* [poem curly] ",
+ scr_txt_color["off"],
+ line
+ );
+ }
+ ocn_poem["start"] = to!string(ocn);
+ ft["blocks"] = 1;
+ ft["verse_new"] = 1;
+ ft["poem"] = 1;
+ ft["curly_poem"] = 1;
+ } else if (auto m = match(line, rgx.block_curly_group_open)) {
+ debug(group) { // group (curly) open
+ writeln(
+ scr_txt_color["blue"],
+ "* [group curly] ",
+ scr_txt_color["off"],
+ line
+ );
+ }
+ ft["blocks"] = 1;
+ ft["group"] = 1;
+ ft["curly_group"] = 1;
+ } else if (auto m = match(line, rgx.block_curly_block_open)) {
+ debug(block) { // block (curly) open
+ writeln(
+ scr_txt_color["blue"],
+ "* [block curly] ",
+ scr_txt_color["off"],
+ line
+ );
+ }
+ ft["blocks"] = 1;
+ ft["block"] = 1;
+ ft["curly_block"] = 1;
+ } else if (auto m = match(line, rgx.block_curly_quote_open)) {
+ debug(quote) { // quote (curly) open
+ writeln(
+ scr_txt_color["blue"],
+ "* [quote curly] ",
+ scr_txt_color["off"],
+ line
+ );
+ }
+ ft["blocks"] = 1;
+ ft["quote"] = 1;
+ ft["curly_quote"] = 1;
+ } else if (auto m = match(line, rgx.block_curly_table_open)) {
+ debug(table) { // table (curly) open
+ writeln(
+ scr_txt_color["blue"],
+ "* [table curly] ",
+ scr_txt_color["off"],
+ line
+ );
+ }
+ ft["blocks"] = 1;
+ ft["table"] = 1;
+ ft["curly_table"] = 1;
+ } else if (auto m = match(line, rgx.block_tic_code_open)) {
+ debug(code) { // code (tic) open
+ writeln(
+ scr_txt_color["blue"],
+ "* [code tic] ",
+ scr_txt_color["off"],
+ line
+ );
+ }
+ ft["blocks"] = 1;
+ ft["code"] = 1;
+ ft["tic_code"] = 1;
+ } else if (auto m = match(line, rgx.block_tic_poem_open)) {
+ object.remove("obj");
+ object.remove("markup");
+ object.remove("is");
+ object.remove("attrib");
+ object.remove("bookindex");
+ processing.remove("verse");
+ debug(poem) { // poem (tic) open
+ writeln(
+ scr_txt_color["red"],
+ "* [poem tic] ",
+ scr_txt_color["off"],
+ line
+ );
+ }
+ ocn_poem["start"] = to!string(ocn);
+ ft["blocks"] = 1;
+ ft["verse_new"] = 1;
+ ft["poem"] = 1;
+ ft["tic_poem"] = 1;
+ } else if (auto m = match(line, rgx.block_tic_group_open)) {
+ debug(group) { // group (tic) open
+ writeln(
+ scr_txt_color["blue"],
+ "* [group tic] ",
+ scr_txt_color["off"],
+ line
+ );
+ }
+ ft["blocks"] = 1;
+ ft["group"] = 1;
+ ft["tic_group"] = 1;
+ } else if (auto m = match(line, rgx.block_tic_block_open)) {
+ debug(block) { // block (tic) open
+ writeln(
+ scr_txt_color["blue"],
+ "* [block tic] ",
+ scr_txt_color["off"],
+ line
+ );
+ }
+ ft["blocks"] = 1;
+ ft["block"] = 1;
+ ft["tic_block"] = 1;
+ } else if (auto m = match(line, rgx.block_tic_quote_open)) {
+ debug(quote) { // quote (tic) open
+ writeln(
+ scr_txt_color["blue"],
+ "* [quote tic] ",
+ scr_txt_color["off"],
+ line
+ );
+ }
+ ft["blocks"] = 1;
+ ft["quote"] = 1;
+ ft["tic_quote"] = 1;
+ } else if (auto m = match(line, rgx.block_tic_table_open)) {
+ debug(table) { // table (tic) open
+ writeln(
+ scr_txt_color["blue"],
+ "* [table tic] ",
+ scr_txt_color["off"],
+ line
+ );
+ }
+ ft["blocks"] = 1;
+ ft["table"] = 1;
+ ft["tic_table"] = 1;
+ } else if (!line.empty) {
+ assert(
+ !line.empty,
+ "line tested, line not empty surely"
+ );
+ assert(
+ (ft["blocks"] == 0)
+ || (ft["blocks"] == 2),
+ "code block status: none or closed"
+ );
+ if (ft["blocks"] == 2) {
+ debug(check) { // block
+ writeln(__LINE__);
+ tell_l("red", line);
+ }
+ assert(
+ match(line, rgx.book_index)
+ || match(line, rgx.book_index_open)
+ || ft["book_index"] == 1
+ );
+ }
+ if (auto m = match(line, rgx.book_index)) {
+ debug(bookindexmatch) { // book index
+ writeln(
+ scr_txt_color["blue"], "* [bookindex] ", scr_txt_color["off"],
+ to!string(m.captures[1]), "\n"
+ );
+ }
+ object["bookindex"] = to!string(m.captures[1]);
+ } else if (auto m = match(line, rgx.book_index_open)) {
+ ft["book_index"] = 1;
+ book_idx_tmp = to!string(m.captures[1]);
+ debug(bookindexmatch) { // book index
+ writeln(
+ scr_txt_color["blue"],
+ "* [bookindex] ",
+ scr_txt_color["off"],
+ book_idx_tmp, "\n"
+ );
+ }
+ } else if (ft["book_index"] == 1 ) {
+ if (auto m = match(line, rgx.book_index_close)) {
+ ft["book_index"] = 0;
+ object["bookindex"] = book_idx_tmp ~ to!string(m.captures[1]);
+ debug(bookindexmatch) { // book index
+ writeln(
+ scr_txt_color["blue"],
+ "* [bookindex] ",
+ scr_txt_color["off"],
+ book_idx_tmp, "\n"
+ );
+ }
+ book_idx_tmp = "";
+ } else {
+ book_idx_tmp ~= line;
+ }
+ } else {
+ if (auto m = match(line, rgx.comment)) {
+ debug(comment) {
+ tell_l("blue", line);
+ }
+ object["obj"] ~= line ~= "\n";
+ contents_arbitrary_max_length_set[counter] =
+ set_oa.contents_comment(strip(object["obj"]));
+ object.remove("obj");
+ object.remove("markup");
+ object.remove("is");
+ object.remove("attrib");
+ object.remove("bookindex");
+ processing.remove("verse");
+ line_occur["header_metadata"] = 0;
+ line_occur["header_make"] = 0;
+ line_occur["heading"] = 0;
+ line_occur["para"] = 0;
+ ft["header"] = 0;
+ ft["header_make"] = 0;
+ ft["header_metadata"] = 0;
+ ft["heading"] = 0;
+ ft["para"] = 0;
+ counter++;
+ } else if (auto m = match(line, rgx.header_make)) {
+ debug(header1) { // header
+ tell_l("yellow", line);
+ }
+ ft["header"] = 1;
+ ft["header_make"] = 1;
+ ft["header_metadata"] = 0;
+ ft["heading"] = 0;
+ ft["para"] = 0;
+ line_occur["header_make"]++;
+ object["obj"] ~= line ~= "\n";
+ } else if (auto m = match(line, rgx.header_metadata)) {
+ debug(header1) { // header
+ tell_l("yellow", line);
+ }
+ ft["header"] = 1;
+ ft["header_make"] = 0;
+ ft["header_metadata"] = 1;
+ ft["heading"] = 0;
+ ft["para"] = 0;
+ line_occur["header_metadata"]++;
+ object["obj"] ~= line ~= "\n";
+ } else if (ft["header_make"] == 1
+ && (line_occur["header_make"] > 0)) {
+ if (auto m = match(line, rgx.header_sub)) {
+ debug(header1) { // header sub
+ tell_l("yellow", line);
+ }
+ line_occur["header_make"]++;
+ object["obj"] ~= line ~= "\n";
+ }
+ } else if (ft["header_metadata"] == 1
+ && (line_occur["header_metadata"] > 0)) {
+ if (auto m = match(line, rgx.header_sub)) {
+ debug(header1) { // header sub
+ tell_l("yellow", line);
+ }
+ line_occur["header_metadata"]++;
+ object["obj"] ~= line ~= "\n";
+ }
+ } else if (((line_occur["para"] == 0)
+ && (line_occur["heading"] == 0))
+ && ((ft["para"] == 0)
+ && (ft["heading"] == 0))) {
+ if ((to!string(dochead_make["make"]["headings"]).length > 2)
+ && (ft["make_headings"] == 0)) {
+ debug(headingsfound) {
+ writeln(dochead_make["make"]["headings"]);
+ }
+ auto make_headings_txt =
+ match(
+ to!string(dochead_make["make"]["headings"]),
+ rgx.within_quotes);
+ char[][] make_headings_spl =
+ split(
+ cast(char[]) make_headings_txt.captures[1],
+ rgx.make_heading_delimiter);
+ debug(headingsfound) {
+ writeln(make_headings_spl.length);
+ writeln(make_headings_spl);
+ }
+ switch (make_headings_spl.length) {
+ case 7 :
+ if (!empty(make_headings_spl[6])) {
+ str_h_4 = "^(" ~ to!string(make_headings_spl[6]) ~ ")";
+ rgx_h_4 = regex(str_h_4);
+ }
+ goto case;
+ case 6 :
+ if (!empty(make_headings_spl[5])) {
+ str_h_3 = "^(" ~ to!string(make_headings_spl[5]) ~ ")";
+ rgx_h_3 = regex(str_h_3);
+ }
+ goto case;
+ case 5 :
+ if (!empty(make_headings_spl[4])) {
+ str_h_2 = "^(" ~ to!string(make_headings_spl[4]) ~ ")";
+ rgx_h_2 = regex(str_h_2);
+ }
+ goto case;
+ case 4 :
+ if (!empty(make_headings_spl[3])) {
+ str_h_1 = "^(" ~ to!string(make_headings_spl[3]) ~ ")";
+ rgx_h_1 = regex(str_h_1);
+ }
+ goto case;
+ case 3 :
+ if (!empty(make_headings_spl[2])) {
+ str_h_D = "^(" ~ to!string(make_headings_spl[2]) ~ ")";
+ rgx_h_D = regex(str_h_D);
+ }
+ goto case;
+ case 2 :
+ if (!empty(make_headings_spl[1])) {
+ str_h_C = "^(" ~ to!string(make_headings_spl[1]) ~ ")";
+ rgx_h_C = regex(str_h_C);
+ }
+ goto case;
+ case 1 :
+ if (!empty(make_headings_spl[0])) {
+ str_h_B = "^(" ~ to!string(make_headings_spl[0]) ~ ")";
+ rgx_h_B = regex(str_h_B);
+ }
+ break;
+ default:
+ break;
+ }
+ ft["make_headings"] = 1;
+ }
+ if ((ft["make_headings"] == 1)
+ && ((line_occur["para"] == 0)
+ && (line_occur["heading"] == 0))
+ && ((ft["para"] == 0)
+ && (ft["heading"] == 0))) {
+ if (match(line, rgx_h_B)) {
+ line = "B~ " ~ line;
+ debug(headingsfound) {
+ writeln(line);
+ }
+ }
+ if (match(line, rgx_h_C)) {
+ line = "C~ " ~ line;
+ debug(headingsfound) {
+ writeln(line);
+ }
+ }
+ if (match(line, rgx_h_D)) {
+ line = "D~ " ~ line;
+ debug(headingsfound) {
+ writeln(line);
+ }
+ }
+ if (match(line, rgx_h_1)) {
+ line = "1~ " ~ line;
+ debug(headingsfound) {
+ writeln(line);
+ }
+ }
+ if (match(line, rgx_h_2)) {
+ line = "2~ " ~ line;
+ debug(headingsfound) {
+ writeln(line);
+ }
+ }
+ if (match(line, rgx_h_3)) {
+ line = "3~ " ~ line;
+ debug(headingsfound) {
+ writeln(line);
+ }
+ }
+ if (match(line, rgx_h_4)) {
+ line = "4~ " ~ line;
+ debug(headingsfound) {
+ writeln(line);
+ }
+ }
+ }
+ if (auto m = match(line, rgx.heading)) {
+ ft["heading"] = 1;
+ ft["header"] = 0;
+ ft["header_make"] = 0;
+ ft["header_metadata"] = 0;
+ ft["heading_biblio"] = 0;
+ ft["para"] = 0;
+ line_occur["heading"]++;
+ object["obj"] ~= line ~= "\n";
+ object["lev"] ~= m.captures[1];
+ assertions_doc_structure(object, lv); // includes most of the logic for collapsed levels
+ switch (to!string(object["lev"])) {
+ case "A":
+ object["lvn"]="0";
+ lv["lv"] = 0;
+ lv["h0"]++;
+ lv["h1"] = 0;
+ lv["h2"] = 0;
+ lv["h3"] = 0;
+ lv["h4"] = 0;
+ lv["h5"] = 0;
+ lv["h6"] = 0;
+ lv["h7"] = 0;
+ collapsed_lev["h0"] = 1;
+ object["lcn"] = to!string(collapsed_lev["h0"]);
+ break;
+ case "B":
+ collapsed_lev["h1"] = collapsed_lev["h0"] + 1;
+ object["lcn"] = to!string(collapsed_lev["h1"]);
+ object["lvn"]="1";
+ lv["lv"] = 1;
+ lv["h1"]++;
+ lv["h2"] = 0;
+ lv["h3"] = 0;
+ lv["h4"] = 0;
+ lv["h5"] = 0;
+ lv["h6"] = 0;
+ lv["h7"] = 0;
+ break;
+ case "C":
+ collapsed_lev["h2"] = collapsed_lev["h1"] + 1;
+ object["lcn"] = to!string(collapsed_lev["h2"]);
+ object["lvn"]="2";
+ lv["lv"] = 2;
+ lv["h2"]++;
+ lv["h3"] = 0;
+ lv["h4"] = 0;
+ lv["h5"] = 0;
+ lv["h6"] = 0;
+ lv["h7"] = 0;
+ break;
+ case "D":
+ collapsed_lev["h3"] = collapsed_lev["h2"] + 1;
+ object["lcn"] = to!string(collapsed_lev["h3"]);
+ object["lvn"]="3";
+ lv["lv"] = 3;
+ lv["h3"]++;
+ lv["h4"] = 0;
+ lv["h5"] = 0;
+ lv["h6"] = 0;
+ lv["h7"] = 0;
+ break;
+ case "1":
+ if (lv["h3"] > 0) {
+ collapsed_lev["h4"] = collapsed_lev["h3"] + 1;
+ } else if (lv["h2"] > 0) {
+ collapsed_lev["h4"] = collapsed_lev["h2"] + 1;
+ } else if (lv["h1"] > 0) {
+ collapsed_lev["h4"] = collapsed_lev["h1"] + 1;
+ } else if (lv["h0"] > 0) {
+ collapsed_lev["h4"] = collapsed_lev["h0"] + 1;
+ }
+ object["lcn"] = to!string(collapsed_lev["h4"]);
+ object["lvn"]="4";
+ lv["lv"] = 4;
+ lv["h4"]++;
+ lv["h5"] = 0;
+ lv["h6"] = 0;
+ lv["h7"] = 0;
+ break;
+ case "2":
+ if (lv["h5"] > 0) {
+ object["lcn"] = to!string(collapsed_lev["h5"]);
+ } else if (lv["h4"] > 0) {
+ collapsed_lev["h5"] = collapsed_lev["h4"] + 1;
+ object["lcn"] = to!string(collapsed_lev["h5"]);
+ }
+ object["lvn"]="5";
+ lv["lv"] = 5;
+ lv["h5"]++;
+ lv["h6"] = 0;
+ lv["h7"] = 0;
+ break;
+ case "3":
+ if (lv["h6"] > 0) {
+ object["lcn"] = to!string(collapsed_lev["h6"]);
+ } else if (lv["h5"] > 0) {
+ collapsed_lev["h6"] = collapsed_lev["h5"] + 1;
+ object["lcn"] = to!string(collapsed_lev["h6"]);
+ }
+ object["lvn"]="6";
+ lv["lv"] = 6;
+ lv["h6"]++;
+ lv["h7"] = 0;
+ break;
+ case "4":
+ if (lv["h7"] > 0) {
+ object["lcn"] = to!string(collapsed_lev["h7"]);
+ } else if (lv["h6"] > 0) {
+ collapsed_lev["h7"] = collapsed_lev["h6"] + 1;
+ object["lcn"] = to!string(collapsed_lev["h7"]);
+ }
+ object["lvn"]="7";
+ lv["lv"] = 7;
+ lv["h7"]++;
+ break;
+ default:
+ break;
+ }
+ debug(heading) { // heading
+ tell_l("yellow", strip(line));
+ }
+ } else if (line_occur["para"] == 0) {
+ if (auto m = match(line, rgx.para_indent)) {
+ debug(paraindent) { // para indent
+ tell_l("blue", line);
+ }
+ ft["para"] = 1;
+ object["obj"] ~= line ~= "\n";
+ indent_first = to!string(m.captures[1]);
+ indent_second = "0";
+ bullet = false;
+ } else if (auto m = match(line, rgx.para_bullet)) {
+ debug(parabullet) { // para bullet
+ tell_l("blue", line);
+ }
+ ft["para"] = 1;
+ object["obj"] ~= line;
+ indent_first = "0";
+ indent_second = "0";
+ bullet = true;
+ } else if (auto m = match(line, rgx.para_indent_hang)) {
+ debug(paraindenthang) { // para indent hang
+ tell_l("blue", line);
+ }
+ ft["para"] = 1;
+ object["obj"] ~= line;
+ indent_first = to!string(m.captures[1]);
+ indent_second = to!string(m.captures[2]);
+ bullet = false;
+ } else if (auto m = match(line, rgx.para_bullet_indent)) {
+ debug(parabulletindent) { // para bullet indent
+ tell_l("blue", line);
+ }
+ ft["para"] = 1;
+ object["obj"] ~= line;
+ indent_first = to!string(m.captures[1]);
+ indent_second = "0";
+ bullet = true;
+ } else {
+ ft["para"] = 1;
+ object["obj"] ~= line;
+ indent_first = "0";
+ indent_second = "0";
+ bullet = false;
+ }
+ line_occur["para"]++;
+ }
+ } else if (line_occur["header_make"] > 0) {
+ debug(header) { // para
+ tell_l("red", line);
+ }
+ object["obj"] ~= line ~= "\n";
+ line_occur["header_make"]++;
+ } else if (line_occur["header_metadata"] > 0) {
+ debug(header) { // para
+ tell_l("red", line);
+ }
+ object["obj"] ~= line ~= "\n";
+ line_occur["header_metadata"]++;
+ } else if (line_occur["heading"] > 0) {
+ debug(heading) { // heading
+ tell_l("blue", line);
+ }
+ object["obj"] ~= line ~= "\n";
+ line_occur["heading"]++;
+ } else if (line_occur["para"] > 0) {
+ debug(para) { // para
+ tell_l("blue", line);
+ }
+ object["obj"] ~= line;
+ line_occur["para"]++;
+ }
+ }
+ } else if (ft["blocks"] == 2) {
+ assert(
+ line.empty,
+ "line should be empty"
+ );
+ assert(
+ (ft["blocks"] == 2),
+ "code block status: closed"
+ );
+ assertions_flag_types_block_status_none_or_closed(ft);
+ if (ft["code"] == 2) {
+ ocn = ocn_emit(ft["ocn_status"]);
+ object["bookindex"] =
+ ("bookindex" in object) ? object["bookindex"] : "";
+ bookindex_unordered_hashes =
+ bkidx_hash(object["bookindex"], ocn);
+ object["is"] = "code";
+ node =
+ node_jstr(
+ content_non_header,
+ ocn,
+ counter,
+ heading_pointer-1,
+ object["is"]
+ );
+ object["markup"] =
+ obj_im.obj_inline_markup(object["is"], object["obj"]);
+ object["attrib"] =
+ obj_att.obj_attributes(object["is"], object["obj"], node);
+ contents_arbitrary_max_length_set[counter] =
+ set_oa.contents_block(
+ object["is"],
+ object["markup"],
+ object["attrib"],
+ ocn
+ );
+ object.remove("obj");
+ object.remove("markup");
+ object.remove("is");
+ object.remove("attrib");
+ object.remove("bookindex");
+ processing.remove("verse");
+ counter++;
+ ft["blocks"] = 0;
+ ft["code"] = 0;
+ } else if (ft["poem"] == 2) {
+ object["bookindex"] =
+ ("bookindex" in object) ? object["bookindex"] : "";
+ bookindex_unordered_hashes =
+ bkidx_hash(object["bookindex"], ocn);
+ object["is"] = "verse"; // check also
+ node =
+ node_jstr(
+ content_non_header,
+ ocn,
+ counter,
+ heading_pointer-1,
+ object["is"]
+ );
+ contents_arbitrary_max_length_set[counter] =
+ set_oa.contents_block_ocn_string(
+ "poem",
+ "",
+ (ocn_poem["start"], ocn_poem["end"]),
+ node
+ ); // bookindex
+ object.remove("obj");
+ object.remove("markup");
+ object.remove("is");
+ object.remove("attrib");
+ object.remove("bookindex");
+ processing.remove("verse");
+ ft["blocks"] = 0;
+ ft["poem"] = 0;
+ } else if (ft["table"] == 2) {
+ ocn = ocn_emit(ft["ocn_status"]);
+ object["bookindex"] =
+ ("bookindex" in object) ? object["bookindex"] : "";
+ bookindex_unordered_hashes =
+ bkidx_hash(object["bookindex"], ocn);
+ object["is"] = "table";
+ node =
+ node_jstr(
+ content_non_header,
+ ocn,
+ counter,
+ heading_pointer-1,
+ object["is"]
+ );
+ object["markup"] =
+ obj_im.obj_inline_markup(object["is"], object["obj"]);
+ object["attrib"] =
+ obj_att.obj_attributes(object["is"], object["obj"], node);
+ contents_arbitrary_max_length_set[counter] =
+ set_oa.contents_block(
+ object["is"],
+ object["markup"],
+ object["attrib"],
+ ocn
+ );
+ object.remove("obj");
+ object.remove("markup");
+ object.remove("is");
+ object.remove("attrib");
+ object.remove("bookindex");
+ processing.remove("verse");
+ counter++;
+ ft["blocks"] = 0;
+ ft["table"] = 0;
+ } else if (ft["group"] == 2) {
+ ocn = ocn_emit(ft["ocn_status"]);
+ object["bookindex"] = ("bookindex" in object) ? object["bookindex"] : "";
+ bookindex_unordered_hashes = bkidx_hash(object["bookindex"], ocn);
+ object["is"] = "group";
+ node =
+ node_jstr(
+ content_non_header,
+ ocn,
+ counter,
+ heading_pointer-1,
+ object["is"]
+ );
+ object["markup"] =
+ obj_im.obj_inline_markup(object["is"], object["obj"]);
+ object["attrib"] =
+ obj_att.obj_attributes(object["is"], object["obj"], node);
+ contents_arbitrary_max_length_set[counter] =
+ set_oa.contents_block(
+ object["is"],
+ object["markup"],
+ object["attrib"],
+ ocn
+ );
+ object.remove("obj");
+ object.remove("markup");
+ object.remove("is");
+ object.remove("attrib");
+ object.remove("bookindex");
+ processing.remove("verse");
+ counter++;
+ ft["blocks"] = 0;
+ ft["group"] = 0;
+ } else if (ft["block"] == 2) {
+ ocn = ocn_emit(ft["ocn_status"]);
+ object["bookindex"] = ("bookindex" in object) ? object["bookindex"] : "";
+ bookindex_unordered_hashes = bkidx_hash(object["bookindex"], ocn);
+ object["is"] = "block";
+ node =
+ node_jstr(
+ content_non_header,
+ ocn,
+ counter,
+ heading_pointer-1,
+ object["is"]
+ );
+ object["markup"] =
+ obj_im.obj_inline_markup(object["is"], object["obj"]);
+ object["attrib"] =
+ obj_att.obj_attributes(object["is"], object["obj"], node);
+ contents_arbitrary_max_length_set[counter] =
+ set_oa.contents_block(
+ object["is"],
+ object["markup"],
+ object["attrib"],
+ ocn
+ );
+ object.remove("obj");
+ object.remove("markup");
+ object.remove("is");
+ object.remove("attrib");
+ object.remove("bookindex");
+ processing.remove("verse");
+ counter++;
+ ft["blocks"] = 0;
+ ft["block"] = 0;
+ } else if (ft["quote"] == 2) {
+ ocn = ocn_emit(ft["ocn_status"]);
+ object["bookindex"] = ("bookindex" in object) ? object["bookindex"] : "";
+ bookindex_unordered_hashes =
+ bkidx_hash(object["bookindex"], ocn);
+ object["is"] = "quote";
+ node =
+ node_jstr(
+ content_non_header,
+ ocn,
+ counter,
+ heading_pointer-1,
+ object["is"]
+ );
+ object["markup"] =
+ obj_im.obj_inline_markup(object["is"], object["obj"]);
+ object["attrib"] =
+ obj_att.obj_attributes(object["is"], object["obj"], node);
+ contents_arbitrary_max_length_set[counter] =
+ set_oa.contents_block(
+ object["is"],
+ object["markup"],
+ object["attrib"],
+ ocn
+ );
+ object.remove("obj");
+ object.remove("markup");
+ object.remove("is");
+ object.remove("attrib");
+ object.remove("bookindex");
+ processing.remove("verse");
+ counter++;
+ ft["blocks"] = 0;
+ ft["quote"] = 0;
+ }
+ } else {
+ assert(
+ line.empty,
+ "line should be empty"
+ );
+ assert(
+ (ft["blocks"] == 0),
+ "code block status: none"
+ );
+ if ((ft["header_make"] == 1)
+ && (line_occur["header_make"] > 0)) {
+ auto dochead_metadata_and_make =
+ set_header.header_metadata_and_make_jsonstr(strip(object["obj"]), dochead_metadata, dochead_make);
+ static assert(!isTypeTuple!(dochead_metadata_and_make));
+ dochead_metadata = dochead_metadata_and_make[0];
+ dochead_make = dochead_metadata_and_make[1];
+ line_occur["header_make"] = 0;
+ line_occur["header_metadata"] = 0;
+ line_occur["heading"] = 0;
+ line_occur["para"]= 0;
+ ft["header"] = 0;
+ ft["heading"] = 0;
+ ft["para"] = 0;
+ object.remove("obj");
+ object.remove("markup");
+ object.remove("is");
+ object.remove("attrib");
+ object.remove("bookindex");
+ processing.remove("verse");
+ } else if ((ft["header_metadata"] == 1)
+ && (line_occur["header_metadata"] > 0)) {
+ auto dochead_metadata_and_make =
+ set_header.header_metadata_and_make_jsonstr(strip(object["obj"]), dochead_metadata, dochead_make);
+ static assert(!isTypeTuple!(dochead_metadata_and_make));
+ dochead_metadata = dochead_metadata_and_make[0];
+ dochead_make = dochead_metadata_and_make[1];
+ line_occur["header_make"] = 0;
+ line_occur["header_metadata"] = 0;
+ line_occur["heading"] = 0;
+ line_occur["para"]= 0;
+ ft["header"] = 0;
+ ft["header_make"] = 0;
+ ft["header_metadata"] = 0;
+ ft["heading"] = 0;
+ ft["para"] = 0;
+ object.remove("obj");
+ object.remove("markup");
+ object.remove("is");
+ object.remove("attrib");
+ object.remove("bookindex");
+ processing.remove("verse");
+ } else if ((ft["heading"] == 1)
+ && (line_occur["heading"] > 0)) {
+ ocn = ocn_emit(ft["ocn_status"]);
+ object["bookindex"] =
+ ("bookindex" in object) ? object["bookindex"] : "";
+ bookindex_unordered_hashes =
+ bkidx_hash(object["bookindex"], ocn);
+ object["is"] = "heading";
+ node =
+ node_jstr_heading(
+ object["lvn"],
+ object["lcn"],
+ ocn,
+ counter,
+ heading_pointer,
+ object["is"]
+ ); // heading
+ object["markup"] =
+ obj_im.obj_inline_markup(object["is"], object["obj"]);
+ object["attrib"] =
+ obj_att.obj_attributes(object["is"], object["obj"], node);
+ heading_pointer++;
+ contents_arbitrary_max_length_set[counter] =
+ set_oa.contents_heading(
+ ft["ocn_status"],
+ object["markup"],
+ object["attrib"],
+ ocn, object["lev"],
+ object["lvn"],
+ object["lcn"]
+ );
+ debug(objectrelated1) { // check
+ tell_l("blue", line);
+ }
+ line_occur["header_make"] = 0;
+ line_occur["header_metadata"] = 0;
+ line_occur["heading"] = 0;
+ line_occur["para"] = 0;
+ ft["header"] = 0;
+ ft["header_make"] = 0;
+ ft["header_metadata"] = 0;
+ ft["heading"] = 0;
+ ft["para"] = 0;
+ object.remove("obj");
+ object.remove("markup");
+ object.remove("is");
+ object.remove("attrib");
+ object.remove("lev");
+ object.remove("lvn");
+ object.remove("bookindex");
+ processing.remove("verse");
+ counter++;
+ } else if ((ft["para"] == 1) && (line_occur["para"] > 0)) {
+ ocn = ocn_emit(ft["ocn_status"]);
+ object["bookindex"] =
+ ("bookindex" in object) ? object["bookindex"] : "";
+ bookindex_unordered_hashes =
+ bkidx_hash(object["bookindex"], ocn);
+ object["is"] = "para";
+ node =
+ node_jstr(
+ content_non_header,
+ ocn,
+ counter,
+ heading_pointer-1,
+ object["is"]
+ );
+ object["markup"] =
+ obj_im.obj_inline_markup(object["is"], object["obj"]);
+ object["attrib"] =
+ obj_att.obj_attributes(object["is"], object["obj"], node);
+ contents_arbitrary_max_length_set[counter] =
+ set_oa.contents_para(
+ object["is"],
+ object["markup"],
+ object["attrib"],
+ ocn,
+ indent_first,
+ indent_second,
+ bullet
+ );
+ line_occur["header_make"] = 0;
+ line_occur["header_metadata"] = 0;
+ line_occur["heading"] = 0;
+ line_occur["para"] = 0;
+ ft["header"] = 0;
+ ft["header_make"] = 0;
+ ft["header_metadata"] = 0;
+ ft["heading"] = 0;
+ ft["para"] = 0;
+ indent_first = "0";
+ indent_second = "0";
+ bullet = false;
+ object.remove("obj");
+ object.remove("markup");
+ object.remove("is");
+ object.remove("attrib");
+ object.remove("bookindex");
+ processing.remove("verse");
+ counter++;
+ } else {
+ assert(
+ line == null,
+ "line variable should be empty, should not occur"
+ );
+ }
+ }
+ }
+ }
+ if (((contents_arbitrary_max_length_set[counter-1]["is"] == "para")
+ || (contents_arbitrary_max_length_set[counter-1]["is"] == "heading"))
+ && (counter-1 > previous_count)) {
+ if (match(contents_arbitrary_max_length_set[counter-1]["obj"],
+ rgx.inline_notes_delimiter_al_regular_number_note)) {
+ previous_count=counter-1;
+ notesection.gather_notes_for_endnote_section(contents_arbitrary_max_length_set, counter-1);
+ }
+ }
+ }
+ debug(objectrelated2) { // check
+ tell_l("blue", line);
+ }
+/*
+ Backmatter:
+ * endnotes
+ * glossary
+ * references / bibliography
+ * book index
+*/
+ obj_im.obj_inline_markup("doc_end_reset", "");
+ auto en_tuple = notesection.endnote_objects(ocn);
+ static assert(!isTypeTuple!(en_tuple));
+ auto endnotes = en_tuple[0];
+ ocn = en_tuple[1];
+debug(endnotes) {
+ writeln(__LINE__, " ", endnotes.length);
+ foreach (n; endnotes) {
+ writeln(n);
+ }
+}
+ auto contents = contents_arbitrary_max_length_set[0..counter].dup;
+ auto biblio_unsorted_incomplete = biblio_arr_json[0..count_biblio_entry].dup;
+ auto biblio = new Bibliography();
+ auto biblio_ordered = biblio.bibliography(biblio_unsorted_incomplete);
+ auto bi = new BookIndexReportSection();
+ auto bi_tuple =
+ bi.bookindex_build_section(bookindex_unordered_hashes, ocn);
+ static assert(!isTypeTuple!(bi_tuple));
+ auto bookindex = bi_tuple[0];
+ auto document = contents ~ endnotes ~ bookindex;
+ ocn = bi_tuple[1];
+debug(bookindex) { // bookindex
+ foreach (bi_entry; bookindex) {
+ writeln(bi_entry["obj"]);
+ }
+}
+debug(heading) { // heading
+ string spc;
+ foreach (o; document) {
+ if (o["is"] == "heading") {
+ switch (o["lvn"]) {
+ case "0":
+ spc="";
+ break;
+ case "1":
+ spc=" ";
+ break;
+ case "2":
+ spc=" ";
+ break;
+ case "3":
+ spc=" ";
+ break;
+ case "4":
+ spc=" ";
+ break;
+ case "5":
+ spc=" ";
+ break;
+ case "6":
+ spc=" ";
+ break;
+ case "7":
+ spc=" ";
+ break;
+ case "8":
+ spc=" ";
+ break;
+ default:
+ spc="";
+ break;
+ }
+ writeln(
+ spc, "* ", " ",
+ strip(o["obj"]),
+ "\n ",
+ o["attrib"]
+ );
+ }
+ }
+}
+ destroy(contents);
+ destroy(endnotes);
+ destroy(bookindex);
+ auto t =
+ tuple(
+ document,
+ dochead_make,
+ dochead_metadata,
+ bookindex_unordered_hashes,
+ biblio_ordered
+ );
+ return t;
+ }
+ }
+}
diff --git a/lib/sdp/ao_assertions.d b/lib/sdp/ao_assertions.d
new file mode 100644
index 0000000..7cd1713
--- /dev/null
+++ b/lib/sdp/ao_assertions.d
@@ -0,0 +1,222 @@
+/*
+#+OPTIONS: ^:nil _:nil#+OPTIONS: ^:nil _:nil
+* sisu_assertions.d
+*/
+mixin template AssertionsOnMarkupDocumentStructure() {
+ auto assertions_doc_structure(string[string] object, uint[string] lv) {
+ if (lv["h3"] > 0) {
+ assert(lv["h0"] > 0);
+ assert(lv["h1"] > 0);
+ assert(lv["h2"] > 0);
+ assert(lv["h3"] > 0);
+ } else if (lv["h2"] > 0) {
+ assert(lv["h0"] > 0);
+ assert(lv["h1"] > 0);
+ assert(lv["h2"] > 0);
+ assert(lv["h3"] == 0);
+ } else if (lv["h1"] > 0) {
+ assert(lv["h0"] > 0);
+ assert(lv["h1"] > 0);
+ assert(lv["h2"] == 0);
+ assert(lv["h3"] == 0);
+ } else if (lv["h0"] > 0) {
+ assert(lv["h0"] > 0);
+ assert(lv["h1"] == 0);
+ assert(lv["h2"] == 0);
+ assert(lv["h3"] == 0);
+ } else {
+ assert(lv["h0"] == 0);
+ assert(lv["h1"] == 0);
+ assert(lv["h2"] == 0);
+ assert(lv["h3"] == 0);
+ }
+ if (lv["h7"] > 0) {
+ assert(lv["h4"] > 0);
+ assert(lv["h5"] > 0);
+ assert(lv["h6"] > 0);
+ assert(lv["h7"] > 0);
+ } else if (lv["h6"] > 0) {
+ assert(lv["h4"] > 0);
+ assert(lv["h5"] > 0);
+ assert(lv["h6"] > 0);
+ assert(lv["h7"] == 0);
+ } else if (lv["h5"] > 0) {
+ assert(lv["h4"] > 0);
+ assert(lv["h5"] > 0);
+ assert(lv["h6"] == 0);
+ assert(lv["h7"] == 0);
+ } else if (lv["h4"] > 0) {
+ assert(lv["h4"] > 0);
+ assert(lv["h5"] == 0);
+ assert(lv["h6"] == 0);
+ assert(lv["h7"] == 0);
+ } else {
+ assert(lv["h4"] == 0);
+ assert(lv["h5"] == 0);
+ assert(lv["h6"] == 0);
+ assert(lv["h7"] == 0);
+ }
+ if (lv["h0"] == 0) {
+ assert(lv["h0"] == 0);
+ assert(lv["h1"] == 0);
+ assert(lv["h2"] == 0);
+ assert(lv["h3"] == 0);
+ assert(lv["h4"] == 0);
+ assert(lv["h5"] == 0);
+ assert(lv["h6"] == 0);
+ assert(lv["h7"] == 0);
+ }
+ if (lv["h1"] == 0) {
+ assert(lv["h1"] == 0);
+ assert(lv["h2"] == 0);
+ assert(lv["h3"] == 0);
+ }
+ if (lv["h2"] == 0) {
+ assert(lv["h2"] == 0);
+ assert(lv["h3"] == 0);
+ }
+ if (lv["h3"] == 0) {
+ assert(lv["h3"] == 0);
+ }
+ if (lv["h4"] == 0) {
+ assert(lv["h4"] == 0);
+ assert(lv["h5"] == 0);
+ assert(lv["h6"] == 0);
+ assert(lv["h7"] == 0);
+ }
+ if (lv["h5"] == 0) {
+ assert(lv["h5"] == 0);
+ assert(lv["h6"] == 0);
+ assert(lv["h7"] == 0);
+ }
+ if (lv["h6"] == 0) {
+ assert(lv["h6"] == 0);
+ assert(lv["h7"] == 0);
+ }
+ if (lv["h6"] == 0) {
+ assert(lv["h7"] == 0);
+ }
+ switch (to!string(object["lev"])) {
+ case "A":
+ if (lv["h0"]==0) {
+ assert(lv["h0"] == 0);
+ assert(lv["h1"] == 0);
+ assert(lv["h2"] == 0);
+ assert(lv["h3"] == 0);
+ assert(lv["h4"] == 0);
+ assert(lv["h5"] == 0);
+ assert(lv["h6"] == 0);
+ assert(lv["h7"] == 0);
+ } else { // (lv["h0"] >0)
+ assert(lv["h0"] == 0,"error should not enter level A a second time");
+ }
+ break;
+ case "B":
+ if (lv["h1"]==0) {
+ assert(lv["h0"] > 0);
+ assert(lv["h1"] == 0); //
+ assert(lv["h2"] == 0);
+ assert(lv["h3"] == 0);
+ } else { // (lv["h1"] >0)
+ assert(lv["h0"] > 0);
+ assert(lv["h1"] > 0); //
+ }
+ break;
+ case "C":
+ if (lv["h2"]==0) {
+ assert(lv["h0"] > 0);
+ assert(lv["h1"] > 0);
+ assert(lv["h2"] == 0); //
+ assert(lv["h3"] == 0);
+ } else { // (lv["h2"] > 0)
+ assert(lv["h0"] > 0);
+ assert(lv["h1"] > 0);
+ assert(lv["h2"] > 0); //
+ }
+ break;
+ case "D":
+ if (lv["h3"]==0) {
+ assert(lv["h0"] > 0);
+ assert(lv["h1"] > 0);
+ assert(lv["h2"] > 0);
+ assert(lv["h3"] == 0); //
+ } else { // (lv["h3"] >0)
+ assert(lv["h0"] > 0);
+ assert(lv["h1"] > 0);
+ assert(lv["h2"] > 0);
+ assert(lv["h3"] > 0);
+ }
+ break;
+ case "1":
+ if (lv["h4"]==0) {
+ assert(lv["h0"] > 0);
+ assert(lv["h4"] == 0); //
+ } else { // (lv["h4"] >0)
+ assert(lv["h0"] > 0);
+ assert(lv["h4"] > 0); //
+ }
+ break;
+ case "2":
+ if (lv["h5"]==0) {
+ assert(lv["h0"] > 0);
+ assert(lv["h4"] > 0);
+ assert(lv["h5"] == 0); //
+ } else { // (lv["h5"] >0)
+ assert(lv["h0"] > 0);
+ assert(lv["h4"] > 0);
+ assert(lv["h5"] > 0); //
+ }
+ break;
+ case "3":
+ if (lv["h6"]==0) {
+ assert(lv["h0"] > 0);
+ assert(lv["h4"] > 0);
+ assert(lv["h5"] > 0);
+ assert(lv["h6"] == 0); //
+ } else { // (lv["h6"] >0)
+ assert(lv["h0"] > 0);
+ assert(lv["h4"] > 0);
+ assert(lv["h5"] > 0);
+ assert(lv["h6"] > 0); //
+ }
+ break;
+ case "4":
+ if (lv["h7"]==0) {
+ assert(lv["h0"] > 0);
+ assert(lv["h4"] > 0);
+ assert(lv["h5"] > 0);
+ assert(lv["h6"] > 0);
+ assert(lv["h7"] == 0); //
+ } else { // (lv["h7"] >0)
+ assert(lv["h0"] > 0);
+ assert(lv["h4"] > 0);
+ assert(lv["h5"] > 0);
+ assert(lv["h6"] > 0);
+ assert(lv["h7"] > 0); //
+ }
+ break;
+ default:
+ break;
+ }
+ }
+}
+mixin template AssertionsOnBlocks() {
+ auto assertions_flag_types_block_status_none_or_closed(int[string] flag_type) {
+ assert(
+ (flag_type["code"] == 0) || (flag_type["code"] == 2),
+ "code block status: none or closed");
+ assert(
+ (flag_type["poem"] == 0) || (flag_type["poem"] == 2),
+ "poem status: none or closed");
+ assert(
+ (flag_type["table"] == 0) || (flag_type["table"] == 2),
+ "table status: none or closed");
+ assert(
+ (flag_type["group"] == 0) || (flag_type["group"] == 2),
+ "group block status: none or closed");
+ assert(
+ (flag_type["block"] == 0) || (flag_type["block"] == 2),
+ "block status: none or closed");
+ }
+}
+
diff --git a/lib/sdp/ao_defaults.d b/lib/sdp/ao_defaults.d
new file mode 100644
index 0000000..8996587
--- /dev/null
+++ b/lib/sdp/ao_defaults.d
@@ -0,0 +1,257 @@
+/*
+#+OPTIONS: ^:nil _:nil#+OPTIONS: ^:nil _:nil
+* sisu_defaults.d
+*/
+template SiSUheader() {
+ auto header_make_jsonstr = `{
+ "make": {
+ "cover_image" : "",
+ "home_button_image" : "",
+ "home_button_text" : "",
+ "footer" : "",
+ "headings" : "",
+ "num_top" : "",
+ "breaks" : "",
+ "substitute" : "",
+ "bold" : "",
+ "italics" : "",
+ "emphasis" : "",
+ "texpdf_font" : "",
+ "css" : ""
+ }
+ }`;
+ auto header_metadata_jsonstr = `{
+ "creator": {
+ "author" : "",
+ "translator" : "",
+ "illustrator" : ""
+ },
+ "title": {
+ "main" : "",
+ "sub" : "",
+ "full" : "",
+ "language" : "",
+ "edition" : "",
+ "note" : ""
+ },
+ "rights": {
+ "copyright" : "",
+ "illustrations" : "",
+ "license" : "",
+ "cover" : ""
+ },
+ "date": {
+ "published" : "",
+ "created" : "",
+ "issued" : "",
+ "available" : "",
+ "valid" : "",
+ "modified" : "",
+ "added_to_site" : ""
+ },
+ "original": {
+ "title" : "",
+ "language" : "",
+ "source" : ""
+ },
+ "classify": {
+ "topic_register" : "",
+ "subject" : "",
+ "keywords" : "",
+ "loc" : "",
+ "dewey" : ""
+ },
+ "identifier": {
+ "oclc" : "",
+ "pg" : "",
+ "isbn" : ""
+ },
+ "notes": {
+ "abstract" : "",
+ "description" : ""
+ },
+ "publisher": {
+ "name" : ""
+ },
+ "links": {
+ }
+ }`; // links
+ auto pointer_head_main =
+ [
+ "creator",
+ "title",
+ "rights",
+ "date",
+ "original",
+ "classify",
+ "identifier",
+ "notes",
+ "make",
+ "links"
+ ];
+ auto pointer_head_sub_creator =
+ [
+ "author",
+ "translator",
+ "illustrator",
+ "cover"
+ ];
+ auto pointer_head_sub_title =
+ [
+ "main",
+ "sub",
+ "full",
+ "language",
+ "edition",
+ "note"
+ ];
+ auto pointer_head_sub_rights =
+ [
+ "copyright",
+ "illustrations",
+ "license"
+ ];
+ auto pointer_head_sub_date =
+ [
+ "published",
+ "created",
+ "issued",
+ "valid",
+ "modified",
+ "added_to_site"
+ ];
+ auto pointer_head_sub_original =
+ [
+ "title",
+ "language",
+ "source"
+ ];
+ auto pointer_head_sub_classify =
+ [
+ "topic_register",
+ "subject",
+ "keywords",
+ "loc",
+ "dewey"
+ ];
+ auto pointer_head_sub_identifier =
+ [
+ "oclc",
+ "pg",
+ "isbn"
+ ];
+ auto pointer_head_sub_notes =
+ [
+ "abstract",
+ "description"
+ ];
+ auto pointer_head_sub_publisher =
+ [ "name" ];
+ auto pointer_head_sub_make =
+ [
+ "cover_image",
+ "home_button_image",
+ "home_button_text",
+ "footer", "headings",
+ "num_top",
+ "breaks",
+ "substitute",
+ "bold",
+ "italics",
+ "emphasis",
+ "texpdf_font",
+ "css"
+ ];
+ auto config_jsonstr = `{
+ }`;
+}
+/*
+* RgxInitFlags
+*/
+template SiSUrgxInitFlags() {
+// mixin template RgxInit() {
+ int[string] flag_type = [
+ "make_headings" : 0,
+ "header_make" : 0,
+ "header_metadata" : 0,
+ "heading" : 0,
+ "heading_biblio" : 0,
+ "para" : 0,
+ "blocks" : 0, // 0..2 generic
+ "code" : 0, // 0..2
+ "poem" : 0, // 0..2
+ "table" : 0, // 0..2
+ "group" : 0, // 0..2
+ "block" : 0, // 0..2
+ "quote" : 0, // 0..2
+ "verse_new" : 0,
+ "curly_code" : 0,
+ "curly_poem" : 0,
+ "curly_table" : 0,
+ "curly_group" : 0,
+ "curly_block" : 0,
+ "curly_quote" : 0,
+ "tic_code" : 0,
+ "tic_poem" : 0,
+ "tic_table" : 0,
+ "tic_group" : 0,
+ "tic_block" : 0,
+ "tic_quote" : 0,
+ "ocn_status" : 0, // 0 ocn; 1 no ocn; 2 no ocn & dummy headings
+ "ocn_status_multi_obj" : 0, // 0 ocn; 1 no ocn; 2 no ocn & dummy headings
+ "book_index" : 0,
+ ];
+}
+template SiSUbiblio() {
+ auto biblio_entry_tags_jsonstr = `{
+ "is" : "",
+ "sortby_deemed_author_year_title" : "",
+ "deemed_author" : "",
+ "author_raw" : "",
+ "author" : "",
+ "author_arr" : [ "" ],
+ "editor_raw" : "",
+ "editor" : "",
+ "editor_arr" : [ "" ],
+ "title" : "",
+ "subtitle" : "",
+ "fulltitle" : "",
+ "language" : "",
+ "trans" : "",
+ "src" : "",
+ "journal" : "",
+ "in" : "",
+ "volume" : "",
+ "edition" : "",
+ "year" : "",
+ "place" : "",
+ "publisher" : "",
+ "url" : "",
+ "pages" : "",
+ "note" : "",
+ "short_name" : "",
+ "id" : ""
+ }`; // is: book, article, magazine, newspaper, blog, other
+ auto biblio_tag_map = [
+ "au" : "author_raw",
+ "ed" : "editor_raw",
+ "ti" : "fulltitle",
+ "lng" : "language",
+ "jo" : "journal",
+ "vol" : "volume",
+ "edn" : "edition",
+ "yr" : "year",
+ "pl" : "place",
+ "pb" : "publisher",
+ "pub" : "publisher",
+ "pg" : "pages",
+ "pgs" : "pages",
+ "sn" : "short_name"
+ ]; // is: book, article, magazine, newspaper, blog, other
+}
+template InternalMarkup() {
+ class InternalMarkup {
+ auto en_a_o = "【"; auto en_a_c = "】";
+ auto en_b_o = "〖"; auto en_b_c = "〗";
+ }
+}
diff --git a/lib/sdp/ao_emitter.d b/lib/sdp/ao_emitter.d
new file mode 100644
index 0000000..dd7103d
--- /dev/null
+++ b/lib/sdp/ao_emitter.d
@@ -0,0 +1,1322 @@
+/*
+#+OPTIONS: ^:nil _:nil#+OPTIONS: ^:nil _:nil
+* sisu_emitter.d
+*/
+mixin template Emitters() {
+ mixin InternalMarkup;
+ class CLI {
+ string[string] extract_actions(string cmdlnins, string[string] actions)
+ in { }
+ body {
+ switch (cmdlnins) {
+ case "--no-assert":
+ actions["assert"] = "no";
+ break;
+ default:
+ break;
+ }
+ return actions;
+ }
+ }
+ class OCNemitter : AssertOCN {
+ int ocn, ocn_;
+ int ocn_emitter(int ocn_status_flag)
+ in { assert(ocn_status_flag <= 2); }
+ body {
+ if (ocn_status_flag == 0) {
+ ocn=++ocn_;
+ } else {
+ ocn=0;
+ }
+ return ocn;
+ }
+ invariant() {
+ }
+ }
+ class ObjAttributes {
+ string[string] obj_txt;
+ string para_and_blocks(string obj_txt_in)
+ in { }
+ body {
+ auto rgx = new Rgx();
+ obj_txt["munge"]=obj_txt_in;
+ if (match(obj_txt_in, rgx.para_bullet)) {
+ obj_txt["attrib"] =" \"bullet\": \"true\","
+ ~ " \"indent_first\": 0,"
+ ~ " \"indent_rest\": 0,";
+ } else if (auto m = match(obj_txt_in, rgx.para_bullet_indent)) {
+ obj_txt["attrib"] =" \"bullet\": \"true\","
+ ~ " \"indent_first\": " ~ to!string(m.captures[1]) ~ ","
+ ~ " \"indent_rest\": " ~ to!string(m.captures[1]) ~ ",";
+ } else if (auto m = match(obj_txt_in, rgx.para_indent_hang)) {
+ obj_txt["attrib"] =" \"bullet\": \"false\","
+ ~ " \"indent_first\": " ~ to!string(m.captures[1]) ~ ","
+ ~ " \"indent_rest\": " ~ to!string(m.captures[2]) ~ ",";
+ } else if (auto m = match(obj_txt_in, rgx.para_indent)) {
+ obj_txt["attrib"] =" \"bullet\": \"false\","
+ ~ " \"indent_first\": " ~ to!string(m.captures[1]) ~ ","
+ ~ " \"indent_rest\": " ~ to!string(m.captures[1]) ~ ",";
+ } else {
+ obj_txt["attrib"] =" \"bullet\": \"false\","
+ ~ " \"indent_first\": 0,"
+ ~ " \"indent_rest\": 0,";
+ }
+ return obj_txt["attrib"];
+ }
+ string para(string obj_txt_in)
+ in { }
+ body {
+ obj_txt["munge"]=obj_txt_in;
+ obj_txt["attrib"] = " \"use\": \"content\","
+ ~ " \"of\": \"para\","
+ ~ " \"is\": \"para\"";
+ return obj_txt["attrib"];
+ }
+ invariant() {
+ }
+ string heading(string obj_txt_in)
+ in { }
+ body {
+ obj_txt["munge"]=obj_txt_in;
+ obj_txt["attrib"] = " \"use\": \"content\","
+ ~ " \"of\": \"para\","
+ ~ " \"is\": \"heading\"";
+ return obj_txt["attrib"];
+ }
+ invariant() {
+ }
+ string header_make(string obj_txt_in)
+ in { }
+ body {
+ obj_txt["munge"]=obj_txt_in;
+ obj_txt["attrib"] = " \"use\": \"head\","
+ ~ " \"of\": \"header\","
+ ~ " \"is\": \"header_make\"";
+ return obj_txt["attrib"];
+ }
+ invariant() {
+ }
+ string header_metadata(string obj_txt_in)
+ in { }
+ body {
+ obj_txt["munge"]=obj_txt_in;
+ obj_txt["attrib"] = " \"use\": \"head\","
+ ~ " \"of\": \"header\","
+ ~ " \"is\": \"header_metadata\"";
+ return obj_txt["attrib"];
+ }
+ invariant() {
+ }
+ string code(string obj_txt_in)
+ in { }
+ body {
+ obj_txt["munge"]=obj_txt_in;
+ obj_txt["attrib"] = " \"use\": \"content\","
+ ~ " \"of\": \"block\","
+ ~ " \"is\": \"code\"";
+ return obj_txt["attrib"];
+ }
+ invariant() {
+ }
+ string group(string obj_txt_in)
+ in { }
+ body {
+ obj_txt["munge"]=obj_txt_in;
+ obj_txt["attrib"] = " \"use\": \"content\","
+ ~ " \"of\": \"block\","
+ ~ " \"is\": \"group\"";
+ return obj_txt["attrib"];
+ }
+ invariant() {
+ }
+ string block(string obj_txt_in)
+ in { }
+ body {
+ obj_txt["munge"]=obj_txt_in;
+ obj_txt["attrib"] = " \"use\": \"content\","
+ ~ " \"of\": \"block\","
+ ~ " \"is\": \"block\"";
+ return obj_txt["attrib"];
+ }
+ invariant() {
+ }
+ string verse(string obj_txt_in)
+ in { }
+ body {
+ obj_txt["munge"]=obj_txt_in;
+ obj_txt["attrib"] = " \"use\": \"content\","
+ ~ " \"of\": \"block\","
+ ~ " \"is\": \"verse\"";
+ return obj_txt["attrib"];
+ }
+ invariant() {
+ }
+ string quote(string obj_txt_in)
+ in { }
+ body {
+ obj_txt["munge"]=obj_txt_in;
+ obj_txt["attrib"] = " \"use\": \"content\","
+ ~ " \"of\": \"block\","
+ ~ " \"is\": \"quote\"";
+ return obj_txt["attrib"];
+ }
+ invariant() {
+ }
+ string table(string obj_txt_in)
+ in { }
+ body {
+ obj_txt["munge"]=obj_txt_in;
+ obj_txt["attrib"] = " \"use\": \"content\","
+ ~ " \"of\": \"block\","
+ ~ " \"is\": \"table\"";
+ return obj_txt["attrib"];
+ }
+ invariant() {
+ }
+ string comment(string obj_txt_in)
+ in { }
+ body {
+ obj_txt["munge"]=obj_txt_in;
+ obj_txt["attrib"] = " \"use\": \"comment\","
+ ~ " \"of\": \"comment\","
+ ~ " \"is\": \"comment\"";
+ return obj_txt["attrib"];
+ }
+ invariant() {
+ }
+ }
+ class ObjInlineMarkupMunge {
+ string[string] obj_txt;
+ int n_foot, n_foot_reg, n_foot_sp_asterisk, n_foot_sp_plus;
+ string obj_txt_out, tail, note;
+ private auto initialize_note_numbers() {
+ n_foot = 0;
+ n_foot_reg = 0;
+ n_foot_sp_asterisk = 0;
+ n_foot_sp_plus = 0;
+ }
+ private auto object_notes_(string obj_txt_in)
+ in { }
+ body {
+ auto rgx = new Rgx();
+ auto mkup = new InternalMarkup();
+ obj_txt_out = "";
+ tail = "";
+ obj_txt_in = replaceAll(
+ obj_txt_in,
+ rgx.inline_notes_curly_sp_asterisk,
+ (mkup.en_a_o ~ "*" ~ " $1" ~ mkup.en_a_c)
+ );
+ obj_txt_in =
+ replaceAll(
+ obj_txt_in,
+ rgx.inline_notes_curly_sp_plus,
+ (mkup.en_a_o ~ "+" ~ " $1" ~ mkup.en_a_c)
+ );
+ obj_txt_in =
+ replaceAll(
+ obj_txt_in,
+ rgx.inline_notes_curly,
+ (mkup.en_a_o ~ " $1" ~ mkup.en_a_c)
+ );
+ if (match(obj_txt_in, rgx.inline_notes_al_gen)) {
+ foreach(m; matchAll(obj_txt_in, rgx.inline_text_and_note_al)) {
+ if (match(obj_txt_in, rgx.inline_al_delimiter_open_asterisk)) {
+ n_foot_sp_asterisk++;
+ n_foot=n_foot_sp_asterisk;
+ } else if (match(obj_txt_in, rgx.inline_al_delimiter_open_plus)) {
+ n_foot_sp_plus++;
+ n_foot=n_foot_sp_plus;
+ } else {
+ n_foot_reg++;
+ n_foot=n_foot_reg;
+ }
+ obj_txt_out ~= replaceFirst(
+ m.hit,
+ rgx.inline_al_delimiter_open_regular,
+ (mkup.en_a_o ~ to!string(n_foot))
+ );
+ tail = m.post;
+ }
+ } else {
+ obj_txt_out = obj_txt_in;
+ }
+ debug(footnotes) {
+ writeln(obj_txt_out, tail);
+ }
+ obj_txt_out = obj_txt_out ~ tail;
+ debug(footnotesdone) {
+ foreach(m; matchAll(obj_txt_out,
+ (mkup.en_a_o ~ `\s*(.+?)` ~ mkup.en_a_c))) {
+ writeln(m.captures[1]);
+ writeln(m.hit);
+ }
+ }
+ return obj_txt_out;
+ }
+ string para(string obj_txt_in)
+ in { }
+ body {
+ auto rgx = new Rgx();
+ obj_txt["munge"]=obj_txt_in;
+ obj_txt["munge"]=replaceFirst(obj_txt["munge"], rgx.para_attribs, "");
+ obj_txt["munge"]=replaceFirst(obj_txt["munge"], rgx.ocn_off_all, "");
+ obj_txt["munge"]=object_notes_(obj_txt["munge"]);
+ debug(munge) {
+ writeln(__LINE__);
+ writeln(obj_txt_in);
+ writeln(__LINE__);
+ writeln(to!string(obj_txt["munge"]));
+ }
+ return obj_txt["munge"];
+ }
+ string heading(string obj_txt_in)
+ in { }
+ body {
+ auto rgx = new Rgx();
+ obj_txt["munge"]=obj_txt_in;
+ obj_txt["munge"]=replaceFirst(obj_txt["munge"], rgx.heading, "");
+ obj_txt["munge"]=replaceFirst(obj_txt["munge"], rgx.ocn_off_all, "");
+ obj_txt["munge"]=object_notes_(obj_txt["munge"]);
+ debug(munge) {
+ writeln(__LINE__);
+ writeln(obj_txt_in);
+ writeln(__LINE__);
+ writeln(to!string(obj_txt["munge"]));
+ }
+ return obj_txt["munge"];
+ }
+ invariant() {
+ }
+ string header_make(string obj_txt_in)
+ in { }
+ body {
+ obj_txt["munge"]=obj_txt_in;
+ return obj_txt["munge"];
+ }
+ invariant() {
+ }
+ string header_metadata(string obj_txt_in)
+ in { }
+ body {
+ obj_txt["munge"]=obj_txt_in;
+ return obj_txt["munge"];
+ }
+ invariant() {
+ }
+ string code(string obj_txt_in)
+ in { }
+ body {
+ obj_txt["munge"]=obj_txt_in;
+ return obj_txt["munge"];
+ }
+ invariant() {
+ }
+ string group(string obj_txt_in)
+ in { }
+ body {
+ obj_txt["munge"]=obj_txt_in;
+ obj_txt["munge"]=object_notes_(obj_txt["munge"]);
+ return obj_txt["munge"];
+ }
+ invariant() {
+ }
+ string block(string obj_txt_in)
+ in { }
+ body {
+ obj_txt["munge"]=obj_txt_in;
+ obj_txt["munge"]=object_notes_(obj_txt["munge"]);
+ return obj_txt["munge"];
+ }
+ invariant() {
+ }
+ string verse(string obj_txt_in)
+ in { }
+ body {
+ obj_txt["munge"]=obj_txt_in;
+ obj_txt["munge"]=object_notes_(obj_txt["munge"]);
+ return obj_txt["munge"];
+ }
+ invariant() {
+ }
+ string quote(string obj_txt_in)
+ in { }
+ body {
+ obj_txt["munge"]=obj_txt_in;
+ return obj_txt["munge"];
+ }
+ invariant() {
+ }
+ string table(string obj_txt_in)
+ in { }
+ body {
+ obj_txt["munge"]=obj_txt_in;
+ return obj_txt["munge"];
+ }
+ invariant() {
+ }
+ string comment(string obj_txt_in)
+ in { }
+ body {
+ obj_txt["munge"]=obj_txt_in;
+ return obj_txt["munge"];
+ }
+ invariant() {
+ }
+ }
+ class ObjInlineMarkup : AssertObjInlineMarkup {
+ auto munge = new ObjInlineMarkupMunge();
+ string[string] obj_txt;
+ string obj_inline_markup(string obj_is_, string obj_raw)
+ in { }
+ body {
+ obj_txt["munge"]=obj_raw.dup;
+ obj_txt["munge"]=(match(obj_is_, ctRegex!(`verse|code`)))
+ ? obj_txt["munge"]
+ : strip(obj_txt["munge"]);
+ switch (obj_is_) {
+ case "header_make":
+ obj_txt["munge"]=munge.header_make(obj_txt["munge"]);
+ break;
+ case "header_metadata":
+ obj_txt["munge"]=munge.header_metadata(obj_txt["munge"]);
+ break;
+ case "heading":
+ obj_txt["munge"]=munge.heading(obj_txt["munge"]);
+ break;
+ case "para":
+ obj_txt["munge"]=munge.para(obj_txt["munge"]);
+ break;
+ case "code":
+ obj_txt["munge"]=munge.code(obj_txt["munge"]);
+ break;
+ case "group":
+ obj_txt["munge"]=munge.group(obj_txt["munge"]);
+ break;
+ case "block":
+ obj_txt["munge"]=munge.block(obj_txt["munge"]);
+ break;
+ case "verse":
+ obj_txt["munge"]=munge.verse(obj_txt["munge"]);
+ break;
+ case "quote":
+ obj_txt["munge"]=munge.quote(obj_txt["munge"]);
+ break;
+ case "table":
+ obj_txt["munge"]=munge.table(obj_txt["munge"]);
+ break;
+ case "comment":
+ obj_txt["munge"]=munge.comment(obj_txt["munge"]);
+ break;
+ case "doc_end_reset":
+ munge.initialize_note_numbers();
+ break;
+ default:
+ break;
+ }
+ return obj_txt["munge"];
+ }
+ invariant() {
+ }
+ }
+ class ObjAttrib : AssertObjAttrib {
+// auto sink = appender!(char[])();
+ auto attrib = new ObjAttributes();
+ string[string] obj_attrib;
+ string obj_attributes(string obj_is_, string obj_raw, string node)
+ in { }
+ body {
+ scope(exit) {
+ destroy(obj_raw);
+ destroy(node);
+ }
+ JSONValue node_j = parseJSON(node);
+ obj_attrib.remove("json");
+ obj_attrib["json"] ="{";
+ switch (obj_is_) {
+ case "header_make":
+ obj_attrib["json"] ~= attrib.header_make(obj_raw);
+ break;
+ case "header_metadata":
+ obj_attrib["json"] ~= attrib.header_metadata(obj_raw);
+ break;
+ case "heading":
+ obj_attrib["json"] ~= attrib.heading(obj_raw); //
+ break;
+ case "para":
+ obj_attrib["json"] ~= attrib.para_and_blocks(obj_raw)
+ ~ attrib.para(obj_raw);
+ break;
+ case "code":
+ obj_attrib["json"] ~= attrib.code(obj_raw);
+ break;
+ case "group":
+ obj_attrib["json"] ~= attrib.para_and_blocks(obj_raw)
+ ~ attrib.group(obj_raw);
+ break;
+ case "block":
+ obj_attrib["json"] ~= attrib.para_and_blocks(obj_raw)
+ ~ attrib.block(obj_raw);
+ break;
+ case "verse":
+ obj_attrib["json"] ~= attrib.verse(obj_raw);
+ break;
+ case "quote":
+ obj_attrib["json"] ~= attrib.quote(obj_raw);
+ break;
+ case "table":
+ obj_attrib["json"] ~= attrib.table(obj_raw);
+ break;
+ case "comment":
+ obj_attrib["json"] ~= attrib.comment(obj_raw);
+ break;
+ default:
+ obj_attrib["json"] ~= attrib.para(obj_raw);
+ break;
+ }
+ obj_attrib["json"] ~=" }";
+ JSONValue oa_j = parseJSON(obj_attrib["json"]);
+ assert(
+ (oa_j.type == JSON_TYPE.OBJECT) &&
+ (node_j.type == JSON_TYPE.OBJECT)
+ );
+ if (obj_is_ == "heading") {
+ oa_j.object["ocn"] = node_j["ocn"];
+ oa_j.object["lvn"] = node_j["lvn"];
+ oa_j.object["lcn"] = node_j["lcn"];
+ oa_j.object["heading_pointer"] =
+ node_j["heading_pointer"]; // check
+ oa_j.object["doc_object_pointer"] =
+ node_j["doc_object_pointer"]; // check
+ }
+ oa_j.object["parent_ocn"] = node_j["parent_ocn"];
+ oa_j.object["parent_lvn"] = node_j["parent_lvn"];
+ obj_attrib["json"] = oa_j.toString();
+ debug(structattrib) {
+ if (oa_j["is"].str() == "heading") {
+ writeln(obj_attrib["json"]);
+ writeln(
+ "is: ", oa_j["is"].str(),
+ "; ocn: ", oa_j["ocn"].integer()
+ );
+ }
+ }
+ return obj_attrib["json"];
+ }
+ invariant() {
+ }
+ }
+ class HeaderDocMetadataMakeJson {
+ auto rgx = new Rgx();
+ string hm, hs;
+ auto header_metadata_and_make_jsonstr(
+ string header,
+ JSONValue[string] dochead_metadata,
+ JSONValue[string] dochead_make
+ )
+ in { }
+ body {
+ scope(exit) {
+ destroy(header);
+ destroy(dochead_metadata);
+ destroy(dochead_make);
+ }
+ if (auto t = match(header, rgx.head_main)) {
+ char[][] obj_spl = split(
+ cast(char[]) header,
+ rgx.line_delimiter_ws_strip
+ );
+ auto hm = to!string(t.captures[1]);
+ if (match(hm, rgx.main_headers)) {
+ foreach (line; obj_spl) {
+ if (auto m = match(line, rgx.head_main)) {
+ if (!empty(m.captures[2])) {
+ if (hm == "creator") {
+ dochead_metadata[hm]["author"].str =
+ to!string(m.captures[2]);
+ } else if (hm == "title") {
+ dochead_metadata[hm]["main"].str =
+ to!string(m.captures[2]);
+ } else if (hm == "publisher") {
+ dochead_metadata[hm]["name"].str =
+ to!string(m.captures[2]);
+ }
+ }
+ } else if (auto s = match(line, rgx.head_sub)) {
+ if (!empty(s.captures[2])) {
+ auto hs = to!string(s.captures[1]);
+ if ((hm == "make" )
+ && (dochead_make[hm].type() == JSON_TYPE.OBJECT)) {
+ switch (hm) {
+ case "make":
+ if (match(hs, rgx.subhead_make)) {
+ if (dochead_make[hm][hs].type() == JSON_TYPE.STRING) {
+ dochead_make[hm][hs].str = to!string(s.captures[2]);
+ }
+ } else {
+ writeln("not a valid header type:", hm, ":", hs);
+ destroy(hm);
+ destroy(hs);
+ }
+ break;
+ default:
+ break;
+ }
+ } else if (dochead_metadata[hm].type() == JSON_TYPE.OBJECT) {
+ switch (hm) {
+ case "creator":
+ if (match(hs, rgx.subhead_creator)) {
+ if (dochead_metadata[hm][hs].type() == JSON_TYPE.STRING) {
+ dochead_metadata[hm][hs].str =
+ to!string(s.captures[2]);
+ }
+ } else {
+ writeln("not a valid header type:", hm, ":", hs);
+ destroy(hm);
+ destroy(hs);
+ }
+ break;
+ case "title":
+ if (match(hs, rgx.subhead_title)) {
+ if ((hs == "subtitle")
+ && (dochead_metadata[hm]["sub"].type() == JSON_TYPE.STRING)) {
+ dochead_metadata[hm]["sub"].str =
+ to!string(s.captures[2]);
+ } else if (dochead_metadata[hm][hs].type() == JSON_TYPE.STRING) {
+ dochead_metadata[hm][hs].str =
+ to!string(s.captures[2]);
+ }
+ } else {
+ writeln("not a valid header type:", hm, ":", hs);
+ destroy(hm);
+ destroy(hs);
+ }
+ break;
+ case "rights":
+ if (match(hs, rgx.subhead_rights)) {
+ if (dochead_metadata[hm][hs].type() == JSON_TYPE.STRING) {
+ dochead_metadata[hm][hs].str =
+ to!string(s.captures[2]);
+ }
+ } else {
+ writeln("not a valid header type:", hm, ":", hs);
+ destroy(hm);
+ destroy(hs);
+ }
+ break;
+ case "date":
+ if (match(hs, rgx.subhead_date)) {
+ if (dochead_metadata[hm][hs].type() == JSON_TYPE.STRING) {
+ dochead_metadata[hm][hs].str =
+ to!string(s.captures[2]);
+ }
+ } else {
+ writeln("not a valid header type:", hm, ":", hs);
+ destroy(hm);
+ destroy(hs);
+ }
+ break;
+ case "original":
+ if (match(hs, rgx.subhead_original)) {
+ if (dochead_metadata[hm][hs].type() == JSON_TYPE.STRING) {
+ dochead_metadata[hm][hs].str =
+ to!string(s.captures[2]);
+ }
+ } else {
+ writeln("not a valid header type:", hm, ":", hs);
+ destroy(hm);
+ destroy(hs);
+ }
+ break;
+ case "classify":
+ if (match(hs, rgx.subhead_classify)) {
+ if (dochead_metadata[hm][hs].type() == JSON_TYPE.STRING) {
+ dochead_metadata[hm][hs].str =
+ to!string(s.captures[2]);
+ }
+ } else {
+ writeln("not a valid header type:", hm, ":", hs);
+ destroy(hm);
+ destroy(hs);
+ }
+ break;
+ case "identifier":
+ if (match(hs, rgx.subhead_identifier)) {
+ if (dochead_metadata[hm][hs].type() == JSON_TYPE.STRING) {
+ dochead_metadata[hm][hs].str =
+ to!string(s.captures[2]);
+ }
+ } else {
+ writeln("not a valid header type:", hm, ":", hs);
+ destroy(hm);
+ destroy(hs);
+ }
+ break;
+ case "notes":
+ if (match(hs, rgx.subhead_notes)) {
+ if (dochead_metadata[hm][hs].type() == JSON_TYPE.STRING) {
+ dochead_metadata[hm][hs].str =
+ to!string(s.captures[2]);
+ }
+ } else {
+ writeln("not a valid header type:", hm, ":", hs);
+ destroy(hm);
+ destroy(hs);
+ }
+ break;
+ case "publisher":
+ if (match(hs, rgx.subhead_publisher)) {
+ if (dochead_metadata[hm][hs].type() == JSON_TYPE.STRING) {
+ dochead_metadata[hm][hs].str =
+ to!string(s.captures[2]);
+ }
+ } else {
+ writeln("not a valid header type:", hm, ":", hs);
+ destroy(hm);
+ destroy(hs);
+ }
+ break;
+ case "links":
+ destroy(hm);
+ destroy(hs);
+ break;
+ default:
+ break;
+ }
+ }
+ }
+ }
+ }
+ } else {
+ writeln("not a valid header type:", hm);
+ }
+ }
+ auto t = tuple(dochead_metadata, dochead_make);
+ static assert(!isTypeTuple!(t));
+ return t;
+ }
+ }
+ class HeaderMetadataMakeHash {
+ auto rgx = new Rgx();
+ string header_main;
+ string[string] head;
+ string[string] header_topic_hash(string header)
+ in { }
+ body {
+ if (auto t = match(header, rgx.head_main)) {
+ char[][] obj_spl = split(
+ cast(char[]) header,
+ rgx.line_delimiter_ws_strip
+ );
+ auto header_main = to!string(t.captures[1]);
+ head[header_main] = "{";
+ foreach (line; obj_spl) {
+ if (auto m = match(line, rgx.head_main)) {
+ if (!empty(m.captures[2])) {
+ head[header_main] ~=
+ "\"" ~ header_main ~
+ "\": \"" ~
+ to!string(m.captures[2]) ~
+ "\",";
+ }
+ } else if (auto s = match(line, rgx.head_sub)) {
+ head[header_main] ~= "\"" ~ s.captures[1] ~ "\":";
+ if (!empty(s.captures[2])) {
+ head[header_main] ~= "\"" ~ s.captures[2] ~ "\",";
+ }
+ }
+ }
+ head[header_main] = replaceFirst(
+ head[header_main],
+ rgx.tailing_comma,
+ ""
+ );
+ head[header_main] ~= "}";
+ debug(headerjson) {
+ JSONValue j = parseJSON(head[header_main]);
+ assert(
+ (j.type == JSON_TYPE.OBJECT)
+ );
+ }
+ }
+ return head;
+ }
+ invariant() {
+ }
+ }
+ class BookIndexNuggetHash : AssertBookIndexNuggetHash {
+ string main_term, sub_term, sub_term_bits;
+ uint ocn_offset, ocn_endpoint;
+ string[] ocns;
+ string[][string][string] bi;
+ string[][string][string] hash_nugget;
+ string[] bi_main_terms_split_arr;
+ string[][string][string] bookindex_nugget_hash(string bookindex, int ocn)
+ in { }
+ body {
+ auto rgx = new Rgx();
+ if (!bookindex.empty) {
+ auto bi_main_terms_split_arr =
+ split(bookindex, rgx.bi_main_terms_split);
+ foreach (bi_main_terms_content; bi_main_terms_split_arr) {
+ auto bi_main_term_and_rest =
+ split(bi_main_terms_content, rgx.bi_main_term_plus_rest_split);
+ if (auto m = match(
+ bi_main_term_and_rest[0],
+ rgx.bi_term_and_ocns_match)
+ ) {
+ main_term = strip(m.captures[1]);
+ ocn_offset = to!uint(m.captures[2]);
+ ocn_endpoint=(ocn + ocn_offset);
+ ocns ~= (to!string(ocn) ~ "-" ~ to!string(ocn_endpoint));
+ } else {
+ main_term = strip(bi_main_term_and_rest[0]);
+ ocns ~= to!string(ocn);
+ }
+ bi[main_term]["_a"] ~= ocns;
+ ocns=null;
+ if (bi_main_term_and_rest.length > 1) {
+ auto bi_sub_terms_split_arr =
+ split(
+ bi_main_term_and_rest[1],
+ rgx.bi_sub_terms_plus_ocn_offset_split
+ );
+ foreach (sub_terms_bits; bi_sub_terms_split_arr) {
+ if (auto m = match(sub_terms_bits, rgx.bi_term_and_ocns_match)) {
+ sub_term = strip(m.captures[1]);
+ ocn_offset = to!uint(m.captures[2]);
+ ocn_endpoint=(ocn + ocn_offset);
+ ocns ~= (to!string(ocn) ~ " - " ~ to!string(ocn_endpoint));
+ } else {
+ sub_term = strip(sub_terms_bits);
+ ocns ~= to!string(ocn);
+ }
+ if (!empty(sub_term)) {
+ bi[main_term][sub_term] ~= ocns;
+ }
+ ocns=null;
+ }
+ }
+ }
+ }
+ hash_nugget = bi;
+ return hash_nugget;
+ }
+ invariant() {
+ }
+ }
+ class BookIndexReport {
+ int mkn, skn;
+ auto bookindex_report_sorted(
+ string[][string][string] bookindex_unordered_hashes
+ ) {
+ auto mainkeys=bookindex_unordered_hashes.byKey.array.
+ sort!("toLower(a) < toLower(b)", SwapStrategy.stable).release;
+ foreach (mainkey; mainkeys) {
+ auto subkeys=bookindex_unordered_hashes[mainkey].byKey.array.
+ sort!("toLower(a) < toLower(b)", SwapStrategy.stable).release;
+ foreach (subkey; subkeys) {
+ debug(bookindex) {
+ writeln(
+ mainkey, ": ",
+ subkey, ": ",
+ to!string(bookindex_unordered_hashes[mainkey][subkey])
+ );
+ }
+ skn++;
+ }
+ mkn++;
+ }
+ }
+ }
+ class BookIndexReportIndent {
+ int mkn, skn;
+ auto bookindex_report_indented(
+ string[][string][string] bookindex_unordered_hashes
+ ) {
+ auto mainkeys=
+ bookindex_unordered_hashes.byKey.array.sort().release;
+ foreach (mainkey; mainkeys) {
+ debug(bookindex) {
+ writeln(mainkey);
+ }
+ auto subkeys=
+ bookindex_unordered_hashes[mainkey].byKey.array.sort().release;
+ foreach (subkey; subkeys) {
+ debug(bookindex) {
+ writeln(" ", subkey);
+ writeln(" ", to!string(
+ bookindex_unordered_hashes[mainkey][subkey]
+ ));
+ }
+ skn++;
+ }
+ mkn++;
+ }
+ }
+ }
+ class BookIndexReportSection {
+ mixin ObjectSetters;
+ int mkn, skn;
+ auto rgx = new Rgx();
+ auto bookindex_write_section(
+ string[][string][string] bookindex_unordered_hashes
+ ) {
+ auto mainkeys=bookindex_unordered_hashes.byKey.array.sort().release;
+ foreach (mainkey; mainkeys) {
+ write("_0_1 !{", mainkey, "}! ");
+ foreach (ref_; bookindex_unordered_hashes[mainkey]["_a"]) {
+ auto go = replaceAll(ref_, rgx.book_index_go, "$1");
+ write(" {", ref_, "}#", go, ", ");
+ }
+ writeln(" \\\\");
+ bookindex_unordered_hashes[mainkey].remove("_a");
+ auto subkeys=
+ bookindex_unordered_hashes[mainkey].byKey.array.sort().release;
+ foreach (subkey; subkeys) {
+ write(" ", subkey, ", ");
+ foreach (ref_; bookindex_unordered_hashes[mainkey][subkey]) {
+ auto go = replaceAll(ref_, rgx.book_index_go, "$1");
+ write(" {", ref_, "}#", go, ", ");
+ }
+ writeln(" \\\\");
+ skn++;
+ }
+ mkn++;
+ }
+ }
+ auto bookindex_build_section(
+ string[][string][string] bookindex_unordered_hashes,
+ int ocn
+ ) {
+ string type;
+ int type_heading;
+ string lev, lvn, lcn;
+ string attrib;
+ string indent_first;
+ string indent_second;
+ auto set_oa = new ObjectAbstractSet();
+ auto mainkeys =
+ bookindex_unordered_hashes.byKey.array.sort().release;
+ string bi_tmp;
+ string[string][1024] bookindex_arbitrary_max_length_set;
+ writeln(mainkeys.length);
+ type_heading=1;
+ bi_tmp = "Book Index";
+ attrib="";
+ lev="B";
+ lvn="1";
+ lcn="1";
+ bookindex_arbitrary_max_length_set[mkn] =
+ set_oa.contents_heading(
+ type_heading,
+ bi_tmp,
+ attrib,
+ ocn,
+ lev,
+ lvn,
+ lcn
+ );
+ ocn++;
+ mkn++;
+ type_heading=1;
+ bi_tmp = "Index";
+ attrib="";
+ lev="1";
+ lvn="4";
+ lcn="2";
+ bookindex_arbitrary_max_length_set[mkn] =
+ set_oa.contents_heading(
+ type_heading,
+ bi_tmp,
+ attrib,
+ ocn,
+ lev,
+ lvn,
+ lcn
+ );
+ ocn++;
+ mkn++;
+ foreach (mainkey; mainkeys) {
+ bi_tmp = "!{" ~ mainkey ~ "}! ";
+ foreach (ref_; bookindex_unordered_hashes[mainkey]["_a"]) {
+ auto go = replaceAll(ref_, rgx.book_index_go, "$1");
+ bi_tmp ~= " {" ~ ref_ ~ "}#" ~ go ~ ", ";
+ }
+ bi_tmp ~= " \\\\\n ";
+ bookindex_unordered_hashes[mainkey].remove("_a");
+ auto subkeys =
+ bookindex_unordered_hashes[mainkey].byKey.array.sort().release;
+ foreach (subkey; subkeys) {
+ bi_tmp ~= subkey ~ ", ";
+ foreach (ref_; bookindex_unordered_hashes[mainkey][subkey]) {
+ auto go = replaceAll(ref_, rgx.book_index_go, "$1");
+ bi_tmp ~= " {" ~ ref_ ~ "}#" ~ go ~ ", ";
+ }
+ bi_tmp ~= " \\\\\n ";
+ skn++;
+ }
+ bi_tmp = replaceFirst(bi_tmp, rgx.trailing_linebreak, "");
+ type="para";
+ attrib="";
+ indent_first = "0";
+ indent_second = "1";
+ attrib="";
+ bookindex_arbitrary_max_length_set[mkn] =
+ set_oa.contents_para(
+ type,
+ bi_tmp,
+ attrib,
+ ocn,
+ indent_first,
+ indent_second,
+ false
+ );
+ ocn++;
+ mkn++;
+ }
+ auto bookindex =
+ bookindex_arbitrary_max_length_set[0..mkn].dup;
+ auto t = tuple(bookindex, ocn);
+ return t;
+ }
+ auto bookindex_build_section_(
+ string[][string][string] bookindex_unordered_hashes
+ ) {
+ auto mainkeys =
+ bookindex_unordered_hashes.byKey.array.sort().release;
+ string bi_tmp;
+ string[1024] bookindex_arbitrary_max_length_set;
+ writeln(mainkeys.length);
+ foreach (mainkey; mainkeys) {
+ bi_tmp = "_0_1 !{" ~ mainkey ~ "}! ";
+ foreach (ref_; bookindex_unordered_hashes[mainkey]["_a"]) {
+ auto go = replaceAll(ref_, rgx.book_index_go, "$1");
+ bi_tmp ~= " {" ~ ref_ ~ "}#" ~ go ~ ", ";
+ }
+ bi_tmp ~= " \\\\\n ";
+ bookindex_unordered_hashes[mainkey].remove("_a");
+ auto subkeys =
+ bookindex_unordered_hashes[mainkey].byKey.array.sort().release;
+ foreach (subkey; subkeys) {
+ bi_tmp ~= subkey ~ ", ";
+ foreach (ref_; bookindex_unordered_hashes[mainkey][subkey]) {
+ auto go = replaceAll(ref_, rgx.book_index_go, "$1");
+ bi_tmp ~= " {" ~ ref_ ~ "}#" ~ go ~ ", ";
+ }
+ bi_tmp ~= " \\\\\n ";
+ skn++;
+ }
+ bi_tmp = replaceFirst(bi_tmp, rgx.trailing_linebreak, "");
+ bookindex_arbitrary_max_length_set[mkn] = bi_tmp;
+ mkn++;
+ }
+ auto bookindex =
+ bookindex_arbitrary_max_length_set[0..mkn].dup;
+ return bookindex;
+ }
+ }
+ class NotesSection {
+ mixin ObjectSetters;
+ string object_notes;
+ int previous_count;
+ int mkn;
+ auto rgx = new Rgx();
+ private auto gather_notes_for_endnote_section(
+ string[string][131072] contents_arbitrary_max_length_set,
+ int counter
+ )
+ in {
+ assert((contents_arbitrary_max_length_set[counter]["is"] == "para")
+ || (contents_arbitrary_max_length_set[counter]["is"] == "heading"));
+ assert(counter > previous_count);
+ previous_count=counter;
+ assert(
+ match(contents_arbitrary_max_length_set[counter]["obj"],
+ rgx.inline_notes_delimiter_al_regular_number_note)
+ );
+ }
+ body {
+ foreach(m;
+ matchAll(contents_arbitrary_max_length_set[counter]["obj"],
+ rgx.inline_notes_delimiter_al_regular_number_note)) {
+ debug(endnotes_build) {
+ writeln(
+ "{^{", m.captures[1], ".}^}#noteref_", m.captures[1], " ",
+ m.captures[2]); // sometimes need segment name (segmented html & epub)
+ }
+ object_notes ~=
+ "{^{" ~ m.captures[1] ~ ".}^}#noteref_" ~
+ m.captures[1] ~ " " ~ m.captures[2] ~ "』";
+ }
+ return object_notes;
+ }
+ private auto gathered_notes()
+ in {
+ }
+ body {
+ string[] endnotes_;
+ if (object_notes.length > 1) {
+ endnotes_ = (split(object_notes, rgx.break_string))[0..$-1];
+ }
+ return endnotes_;
+ }
+ private auto endnote_objects(int ocn)
+ in {
+ }
+ body {
+ auto set_oa = new ObjectAbstractSet();
+ string[string][1024] endnotes_arbitrary_max_length_set;
+ auto endnotes_ = gathered_notes();
+ string type;
+ int type_heading;
+ string lev, lvn, lcn;
+ string attrib;
+ string indent_first;
+ string indent_second;
+ type_heading=1;
+ attrib="";
+ lev="B";
+ lvn="1";
+ lcn="1";
+ endnotes_arbitrary_max_length_set[mkn] =
+ set_oa.contents_heading(
+ type_heading,
+ "Endnotes",
+ attrib,
+ ocn,
+ lev,
+ lvn,
+ lcn
+ );
+ ocn++;
+ mkn++;
+ type_heading=1;
+ attrib="";
+ lev="1";
+ lvn="4";
+ lcn="2";
+ endnotes_arbitrary_max_length_set[mkn] =
+ set_oa.contents_heading(
+ type_heading,
+ "Endnotes",
+ attrib,
+ ocn,
+ lev,
+ lvn,
+ lcn
+ );
+ ocn++;
+ mkn++;
+ foreach (endnote; endnotes_) {
+ type="para";
+ attrib="";
+ indent_first = "0";
+ indent_second = "0";
+ attrib="";
+ endnotes_arbitrary_max_length_set[mkn] =
+ set_oa.contents_para(
+ type,
+ endnote,
+ attrib,
+ ocn,
+ indent_first,
+ indent_second,
+ false
+ );
+ ocn++;
+ mkn++;
+ }
+ auto endnotes =
+ endnotes_arbitrary_max_length_set[0..mkn].dup;
+ auto t = tuple(endnotes, ocn);
+ return t;
+ }
+ }
+ class Bibliography {
+ public JSONValue[] bibliography(string[] biblio_unsorted_incomplete)
+ in { }
+ body {
+ JSONValue[] biblio_unsorted =
+ biblio_unsorted_complete(biblio_unsorted_incomplete);
+ JSONValue[] biblio_sorted = biblio_sort(biblio_unsorted);
+ biblio_debug(biblio_sorted);
+ return biblio_sorted;
+ }
+ final private JSONValue[] biblio_unsorted_complete(
+ string[] biblio_unordered
+ ) {
+ JSONValue[1024] bib_arr_json;
+ int count_biblio_entry;
+ count_biblio_entry=0;
+ foreach (bibent; biblio_unordered) {
+ JSONValue j = parseJSON(bibent);
+ if (!empty(j["fulltitle"].str)) {
+ if (!empty(j["author_raw"].str)) {
+ j["deemed_author"]=j["author_arr"][0];
+ } else if (!empty(j["editor_raw"].str)) {
+ j["deemed_author"]=j["editor_arr"][0];
+ }
+ j["sortby_deemed_author_year_title"] = (
+ j["deemed_author"].str ~
+ "; " ~
+ j["year"].str ~
+ "; " ~
+ j["fulltitle"].str
+ );
+ }
+ bib_arr_json[count_biblio_entry] = j;
+ count_biblio_entry++;
+ }
+ JSONValue[] biblio_unsorted_array_of_json_objects =
+ bib_arr_json[0..(count_biblio_entry)].dup;
+ return biblio_unsorted_array_of_json_objects;
+ }
+ final private JSONValue[] biblio_sort(JSONValue[] biblio_unordered) {
+ JSONValue[] biblio_sorted;
+ biblio_sorted =
+ sort!((a, b){
+ return ((a["sortby_deemed_author_year_title"].str) < (b["sortby_deemed_author_year_title"].str));
+ })(biblio_unordered).array;
+ debug(bibliosorted) {
+ foreach (j; biblio_sorted) {
+ if (!empty(j["fulltitle"].str)) {
+ writeln(j["sortby_deemed_author_year_title"]);
+ }
+ }
+ }
+ return biblio_sorted;
+ }
+ auto biblio_debug(JSONValue[] biblio_sorted) {
+ debug(biblio) {
+ foreach (j; biblio_sorted) {
+ if (!empty(j["fulltitle"].str)) {
+ writeln(j["sortby_deemed_author_year_title"]);
+ }
+ }
+ }
+ }
+ }
+ class NodeStructureMetadata : AssertNodeJSON {
+ int lv, lv0, lv1, lv2, lv3, lv4, lv5, lv6, lv7;
+ uint ocn;
+ uint[string] p_; // p_ parent_
+ string node;
+ string node_emitter(
+ string lvn,
+ int ocn_,
+ int counter_,
+ int pointer_,
+ string is_
+ )
+ in {
+ auto rgx = new Rgx();
+ }
+ body {
+ assert(is_ != "heading"); // should not be necessary
+ assert(to!int(ocn_) >= 0); // should not be necessary
+ uint ocn=to!uint(ocn_);
+ if (lv7 > 0) {
+ p_["lvn"] = 7; p_["ocn"] = lv7;
+ } else if (lv6 > 0) {
+ p_["lvn"] = 6; p_["ocn"] = lv6;
+ } else if (lv5 > 0) {
+ p_["lvn"] = 5; p_["ocn"] = lv5;
+ } else {
+ p_["lvn"] = 4; p_["ocn"] = lv4;
+ }
+ node=("{ " ~
+ "\"is\": \"" ~ is_ ~ "\"" ~
+ ", \"heading_pointer\": " ~ to!string(pointer_) ~
+ ", \"doc_object_pointer\": " ~ to!string(counter_) ~
+ ", \"ocn\": " ~ to!string(ocn_) ~
+ ", \"parent_ocn\": " ~ to!string(p_["ocn"]) ~
+ ", \"parent_lvn\": " ~ to!string(p_["lvn"]) ~
+ " }"
+ );
+ return node;
+ }
+ invariant() {
+ }
+ string node_emitter_heading(
+ string lvn,
+ string lcn,
+ int ocn_,
+ int counter_,
+ int pointer_,
+ string is_
+ )
+ in {
+ auto rgx = new Rgx();
+ }
+ body {
+ uint ocn=to!uint(ocn_);
+ switch (lvn) { // switch (to!string(lv)) {
+ case "0":
+ lv=0;
+ lv0=ocn; lv1=0; lv2=0; lv3=0; lv4=0; lv5=0; lv6=0; lv7=0;
+ p_["lvn"] = 0; p_["ocn"] = 0;
+ break;
+ case "1":
+ lv=1;
+ lv1=ocn; lv2=0; lv3=0; lv4=0; lv5=0; lv6=0; lv7=0;
+ p_["lvn"] = 0; p_["ocn"] = lv0;
+ break;
+ case "2":
+ lv=2;
+ lv2=ocn; lv3=0; lv4=0; lv5=0; lv6=0; lv7=0;
+ p_["lvn"] = 1; p_["ocn"] = lv1;
+ break;
+ case "3":
+ lv=3;
+ lv3=ocn; lv4=0; lv5=0; lv6=0; lv7=0;
+ p_["lvn"] = 2; p_["ocn"] = lv2;
+ break;
+ case "4":
+ lv=4;
+ lv4=ocn; lv5=0; lv6=0; lv7=0;
+ if (lv3 > 0) {
+ p_["lvn"] = 3; p_["ocn"] = lv3;
+ } else if (lv2 > 0) {
+ p_["lvn"] = 2; p_["ocn"] = lv2;
+ } else if (lv1 > 0) {
+ p_["lvn"] = 1; p_["ocn"] = lv1;
+ } else {
+ p_["lvn"] = 0; p_["ocn"] = lv0;
+ }
+ break;
+ case "5":
+ lv=5;
+ lv5=ocn; lv6=0; lv7=0;
+ p_["lvn"] = 4; p_["ocn"] = lv4;
+ break;
+ case "6":
+ lv=6;
+ lv6=ocn; lv7=0;
+ p_["lvn"] = 5; p_["ocn"] = lv5;
+ break;
+ case "7":
+ lv=7;
+ lv7=ocn;
+ p_["lvn"] = 6; p_["ocn"] = lv6;
+ break;
+ default:
+ break;
+ }
+ node=("{ " ~
+ "\"is\": \"" ~ is_ ~ "\"" ~
+ ", \"heading_pointer\": " ~ to!string(pointer_) ~
+ ", \"doc_object_pointer\": " ~ to!string(counter_) ~
+ ", \"ocn\": " ~ to!string(ocn_) ~
+ ", \"lvn\": " ~ to!string(lvn) ~
+ ", \"lcn\": " ~ to!string(lcn) ~
+ ", \"parent_ocn\": " ~ to!string(p_["ocn"]) ~
+ ", \"parent_lvn\": " ~ to!string(p_["lvn"]) ~
+ " }"
+ );
+ return node;
+ }
+ invariant() {
+ }
+ }
+}
diff --git a/lib/sdp/ao_interface.d b/lib/sdp/ao_interface.d
new file mode 100644
index 0000000..224603d
--- /dev/null
+++ b/lib/sdp/ao_interface.d
@@ -0,0 +1,145 @@
+/*
+#+OPTIONS: ^:nil _:nil#+OPTIONS: ^:nil _:nil
+* sisu_interface.d
+*/
+mixin template Interfaces() {
+ interface AssertOCN {
+ int ocn_emitter(int ocn_status_flag)
+ in { assert(ocn_status_flag <= 2); }
+ out(ocn) { assert(ocn >= 0); }
+ }
+ interface AssertObjInlineMarkup {
+ string obj_inline_markup(string obj_raw, string obj_type_)
+ in {
+ }
+ out(inline_markup) {
+ }
+ }
+ interface AssertObjAttrib {
+ string obj_attributes(string obj_raw, string node, string obj_type_)
+ in {
+ }
+ out(obj_attrib_json) {
+ }
+ }
+ interface AssertBookIndexNuggetHash {
+ string[][string][string] bookindex_nugget_hash(string bookindex, int ocn)
+ in {
+ debug(bookindexraw) {
+ mixin ScreenTxtColors;
+ if (!bookindex.empty) {
+ writeln(
+ scr_txt_color["blue"], "* [bookindex] ", scr_txt_color["off"],
+ "[", to!string(ocn), "] ", bookindex
+ );
+ }
+ }
+ }
+ out(hash_nugget) {
+ }
+ }
+ interface AssertBookIndexReport {
+ string[][string][][string][] bookindex_nugget_hash(string[][string][string] bookindex_unordered_hashes)
+ in {
+ }
+ }
+ interface AssertNodeJSON {
+ string node_emitter(
+ string lvn,
+ int ocn_,
+ int counter_,
+ int pointer_,
+ string is_
+ )
+ in {
+ auto rgx = new Rgx();
+ assert(is_ != "heading");
+ assert(to!int(ocn_) >= 0);
+ }
+ out(node) {
+ debug(node) {
+ mixin ScreenTxtColors;
+ if (match(lvn, rgx.levels_numbered_headings)) {
+ writeln(scr_txt_marker["yellow"], to!string(node));
+ } else {
+ writeln(scr_txt_marker["white"], to!string(node));
+ }
+ }
+ JSONValue j = parseJSON(node);
+ assert(j["parent_lvn"].integer >= 4);
+ assert(j["parent_lvn"].integer <= 7);
+ assert(j["parent_ocn"].integer >= 0);
+ }
+ string node_emitter_heading(
+ string lvn,
+ string lcn,
+ int ocn_,
+ int counter_,
+ int pointer_,
+ string is_
+ )
+ in {
+ auto rgx = new Rgx();
+ assert(is_ == "heading");
+ assert(to!uint(ocn_) >= 0);
+ assert(
+ match(lvn, rgx.levels_numbered),
+ ("not a valid heading level: " ~ lvn ~ " at " ~ to!string(ocn_))
+ );
+ if (match(lvn, rgx.levels_numbered)) {
+ if (to!uint(lvn) == 0) {
+ assert(to!uint(ocn_) == 1);
+ }
+ }
+ }
+ out(node) {
+ auto rgx = new Rgx();
+ debug(heading) {
+ mixin ScreenTxtColors;
+ if (match(lvn, rgx.levels_numbered_headings)) {
+ writeln(scr_txt_marker["yellow"], to!string(node));
+ }
+ }
+ debug(node) {
+ mixin ScreenTxtColors;
+ if (match(lvn, rgx.levels_numbered_headings)) {
+ writeln(scr_txt_marker["yellow"], to!string(node));
+ } else {
+ writeln(scr_txt_marker["white"], to!string(node));
+ }
+ }
+ JSONValue j = parseJSON(node);
+ assert(j["parent_lvn"].integer <= 7);
+ assert(j["parent_ocn"].integer >= 0);
+ if (match(lvn, rgx.levels_numbered_headings)) {
+ assert(j["lvn"].integer <= 7);
+ assert(j["ocn"].integer >= 0);
+ if (j["parent_lvn"].integer > 0) {
+ assert(j["parent_lvn"].integer < j["lvn"].integer);
+ if (j["ocn"].integer != 0) {
+ assert(j["parent_ocn"].integer < j["ocn"].integer);
+ }
+ }
+ if (j["lvn"].integer == 0) {
+ assert(j["parent_lvn"].integer == 0);
+ } else if (j["lvn"].integer == 1) {
+ assert(j["parent_lvn"].integer == 0);
+ } else if (j["lvn"].integer == 2) {
+ assert(j["parent_lvn"].integer == 1);
+ } else if (j["lvn"].integer == 3) {
+ assert(j["parent_lvn"].integer == 2);
+ } else if (j["lvn"].integer == 4) {
+ assert(j["parent_lvn"].integer <= 3);
+ } else if (j["lvn"].integer == 5) {
+ assert(j["parent_lvn"].integer == 4);
+ } else if (j["lvn"].integer == 6) {
+ assert(j["parent_lvn"].integer == 5);
+ } else if (j["lvn"].integer == 7) {
+ assert(j["parent_lvn"].integer == 6);
+ } else if (j["lvn"].integer == 8) {
+ }
+ }
+ }
+ }
+}
+
diff --git a/lib/sdp/ao_markup_source_raw.d b/lib/sdp/ao_markup_source_raw.d
new file mode 100644
index 0000000..3710ff6
--- /dev/null
+++ b/lib/sdp/ao_markup_source_raw.d
@@ -0,0 +1,58 @@
+/*
+#+OPTIONS: ^:nil _:nil#+OPTIONS: ^:nil _:nil
+* sisu_markup_source_raw.d
+*/
+mixin template SiSUmarkupRaw() {
+ class MarkupRaw {
+ auto rgx = new Rgx();
+ final private string markupSourceString(in char[] fn_src) {
+ enforce(
+ match(fn_src, rgx.src_pth),
+ "not a sisu markup filename"
+ );
+ enforce(
+ exists(fn_src)!=0,
+ "file not found"
+ );
+ string source_txt_str = cast(string) read(fn_src);
+ std.utf.validate(source_txt_str);
+ return source_txt_str;
+ }
+ final private char[][] markupSourceLineArray(in string src_text) {
+ char[][] source_line_arr =
+ split(cast(char[]) src_text, rgx.line_delimiter);
+ return source_line_arr;
+ }
+ final char[][] markupSourceContentRawLineArray(in char[] fn_src) {
+ auto source_txt_str = markupSourceString(fn_src);
+ auto source_line_arr = markupSourceLineArray(source_txt_str);
+ return source_line_arr;
+ }
+ }
+ class MarkupInsertRaw {
+ auto rgx = new Rgx();
+ final private string markupSourceString(in char[] fn_src) {
+ enforce(
+ match(fn_src, rgx.src_fn_find_inserts),
+ "not a sisu markup filename"
+ );
+ enforce(
+ exists(fn_src)!=0,
+ "file not found"
+ );
+ string source_txt_str = cast(string) read(fn_src);
+ std.utf.validate(source_txt_str);
+ return source_txt_str;
+ }
+ final private char[][] markupSourceLineArray(in string src_text) {
+ char[][] source_line_arr =
+ split(cast(char[]) src_text, rgx.line_delimiter);
+ return source_line_arr;
+ }
+ final char[][] markupSourceContentRawLineArray(in char[] fn_src) {
+ auto source_txt_str = markupSourceString(fn_src);
+ auto source_line_arr = markupSourceLineArray(source_txt_str);
+ return source_line_arr;
+ }
+ }
+}
diff --git a/lib/sdp/ao_object_setter.d b/lib/sdp/ao_object_setter.d
new file mode 100644
index 0000000..050b606
--- /dev/null
+++ b/lib/sdp/ao_object_setter.d
@@ -0,0 +1,90 @@
+/*
+#+OPTIONS: ^:nil _:nil#+OPTIONS: ^:nil _:nil
+* sisu_setter.d
+*/
+mixin template ObjectSetters() {
+ class ObjectAbstractSet {
+ import std.conv : to;
+ string[string] contents_comment(in string object) {
+ string object_set[string];
+ object_set["use"] = "comment";
+ object_set["of"] = "comment";
+ object_set["is"] = "comment";
+ object_set["obj"] = object;
+ return object_set;
+ }
+ string[string] contents_heading(
+ in int type,
+ in string object,
+ in string attrib,
+ in int ocn,
+ in string lev,
+ in string lvn,
+ in string lcn,
+ ) {
+ string object_set[string];
+ object_set["use"] = "content";
+ object_set["of"] = "para";
+ object_set["is"] = "heading";
+ object_set["type"] = to!string(type);
+ object_set["obj"] = object;
+ object_set["ocn"] = (ocn==0) ? "" : to!string(ocn);
+ object_set["lev"] = to!string(lev);
+ object_set["lvn"] = to!string(lvn);
+ object_set["lcn"] = to!string(lcn);
+ object_set["attrib"] = attrib;
+ return object_set;
+ }
+ string[string] contents_para(
+ in string type,
+ in string object,
+ in string attrib,
+ in int ocn,
+ in string indent_first,
+ in string indent_second,
+ in bool bullet
+ ) {
+ string object_set[string];
+ object_set["use"] = "content";
+ object_set["of"] = "para";
+ object_set["is"] = type;
+ object_set["obj"] = object;
+ object_set["ocn"] = (ocn==0) ? "" : to!string(ocn);
+ object_set["indent_first"] = indent_first;
+ object_set["indent_second"] = indent_second;
+ object_set["bullet"] = to!string(bullet);
+ object_set["attrib"] = attrib;
+ return object_set;
+ }
+ string[string] contents_block(
+ in string type,
+ in string object,
+ in string attrib,
+ in int ocn
+ ) {
+ string object_set[string];
+ object_set["use"] = "content";
+ object_set["of"] = "block";
+ object_set["is"] = type;
+ object_set["obj"] = object;
+ object_set["ocn"] = (ocn==0) ? "" : to!string(ocn);
+ object_set["attrib"] = attrib;
+ return object_set;
+ }
+ string[string] contents_block_ocn_string(
+ in string type,
+ in string object,
+ in string ocn,
+ in string node
+ ) {
+ string object_set[string];
+ object_set["use"] = "content";
+ object_set["of"] = "block";
+ object_set["is"] = type;
+ object_set["obj"] = object;
+ object_set["ocn"] = ocn;
+ object_set["node"] = node;
+ return object_set;
+ }
+ }
+}
diff --git a/lib/sdp/ao_output_debugs.d b/lib/sdp/ao_output_debugs.d
new file mode 100644
index 0000000..abc48b3
--- /dev/null
+++ b/lib/sdp/ao_output_debugs.d
@@ -0,0 +1,354 @@
+/*
+#+OPTIONS: ^:nil _:nil#+OPTIONS: ^:nil _:nil
+* sdp_output_debugs.d
+*/
+template SiSUoutputDebugs() {
+ class SDPoutputDebugs {
+ auto abstract_doc_source_debugs(
+ string[string][] contents,
+ JSONValue[string] docmake,
+ JSONValue[string] dochead,
+ string[][string][string] bookindex_unordered_hashes,
+ JSONValue[] biblio,
+ string fn_src,
+ string[string] actions
+ ) {
+ mixin RgxInit;
+ mixin ScreenTxtColors;
+ auto rgx = new Rgx();
+ debug(parent) {
+ writeln(__FILE__, ":", __LINE__);
+ foreach (obj; contents) {
+ if (obj["use"] == "content") {
+ if (obj["is"] == "heading") {
+ writeln(scr_txt_marker["cyan"],
+ obj["ocn"],
+ " node: ", obj["node"],
+ " heading: ", obj["lvn"],
+ " ", obj["obj"],
+ );
+ } else {
+ }
+ }
+ }
+ }
+ debug(objects) {
+ writeln("-------------------------------");
+ writeln(__FILE__, ":", __LINE__);
+ foreach (obj; contents) {
+ if (obj["use"] == "content") {
+ writeln(
+ scr_txt_color["green"],
+ "* [", obj["ocn"], "]",
+ "[", obj["is"], "] ",
+ scr_txt_color["off"],
+ obj["obj"]
+ );
+ }
+ }
+ }
+ debug(headermakejson) {
+ writeln("document header, metadata & make instructions:");
+ writeln(dochead);
+ writeln(pointer_head_main);
+ foreach (main_header; pointer_head_main) {
+ switch (main_header) {
+ case "make":
+ foreach (sub_header; pointer_head_sub_make) {
+ if (to!string(dochead[main_header][sub_header]).length > 2) {
+ writeln(
+ main_header, ":",
+ sub_header, ": ",
+ dochead[main_header][sub_header]
+ );
+ }
+ }
+ break;
+ default:
+ break;
+ }
+ }
+ }
+ debug(headermetadatajson) {
+ writeln("document header, metadata & make instructions:");
+ writeln(dochead);
+ writeln(pointer_head_main);
+ foreach (main_header; pointer_head_main) {
+ switch (main_header) {
+ case "creator":
+ foreach (sub_header; pointer_head_sub_creator) {
+ if (to!string(dochead[main_header][sub_header]).length > 2) {
+ writeln(main_header, ":",
+ sub_header, ": ",
+ dochead[main_header][sub_header]
+ );
+ }
+ }
+ break;
+ case "title":
+ foreach (sub_header; pointer_head_sub_title) {
+ if (to!string(dochead[main_header][sub_header]).length > 2) {
+ writeln(main_header, ":",
+ sub_header, ": ",
+ dochead[main_header][sub_header]
+ );
+ }
+ }
+ break;
+ case "rights":
+ foreach (sub_header; pointer_head_sub_rights) {
+ if (to!string(dochead[main_header][sub_header]).length > 2) {
+ writeln(main_header, ":",
+ sub_header, ": ",
+ dochead[main_header][sub_header]
+ );
+ }
+ }
+ break;
+ case "date":
+ foreach (sub_header; pointer_head_sub_date) {
+ if (to!string(dochead[main_header][sub_header]).length > 2) {
+ writeln(main_header, ":",
+ sub_header, ": ",
+ dochead[main_header][sub_header]
+ );
+ }
+ }
+ break;
+ case "original":
+ foreach (sub_header; pointer_head_sub_original) {
+ if (to!string(dochead[main_header][sub_header]).length > 2) {
+ writeln(main_header, ":",
+ sub_header, ": ",
+ dochead[main_header][sub_header]
+ );
+ }
+ }
+ break;
+ case "classify":
+ foreach (sub_header; pointer_head_sub_classify) {
+ if (to!string(dochead[main_header][sub_header]).length > 2) {
+ writeln(main_header, ":",
+ sub_header, ": ",
+ dochead[main_header][sub_header]
+ );
+ }
+ }
+ break;
+ case "identifier":
+ foreach (sub_header; pointer_head_sub_identifier) {
+ if (to!string(dochead[main_header][sub_header]).length > 2) {
+ writeln(main_header, ":",
+ sub_header, ": ",
+ dochead[main_header][sub_header]
+ );
+ }
+ }
+ break;
+ case "notes":
+ foreach (sub_header; pointer_head_sub_notes) {
+ if (to!string(dochead[main_header][sub_header]).length > 2) {
+ writeln(main_header, ":",
+ sub_header, ": ",
+ dochead[main_header][sub_header]
+ );
+ }
+ }
+ break;
+ case "publisher":
+ foreach (sub_header; pointer_head_sub_publisher) {
+ if (to!string(dochead[main_header][sub_header]).length > 2) {
+ writeln(main_header, ":",
+ sub_header, ": ",
+ dochead[main_header][sub_header]
+ );
+ }
+ }
+ break;
+ default:
+ break;
+ }
+ }
+ }
+ debug(bookindex) {
+ writeln("-------------------------------");
+ writeln(__FILE__, ":", __LINE__);
+ auto bookindex = new BookIndexReport();
+ bookindex.bookindex_report_sorted(bookindex_unordered_hashes);
+ }
+ debug(summary) {
+ string[string] check = [
+ "last_ocn" : "NA [debug \"checkdoc\" not run]",
+ ];
+ debug(checkdoc) {
+ foreach (obj; contents) {
+ if (obj["use"] == "content") {
+ if (!empty(obj["ocn"])) {
+ check["last_ocn"] = obj["ocn"];
+ }
+ }
+ }
+ }
+ debug(headings) {
+ writeln("-------------------------------");
+ writeln(__FILE__, ":", __LINE__);
+ foreach (obj; contents) {
+ if (obj["is"] == "heading") {
+ writeln(
+ scr_txt_marker["yellow"],
+ obj["lev"], "~ ",
+ "[", obj["ocn"], "] ",
+ obj["obj"]
+ );
+ }
+ }
+ }
+ writeln(
+ scr_txt_color["green"],
+ "-------------------------------",
+ scr_txt_color["off"],
+ "\n", fn_src,
+ "\nlength contents array: ", contents.length,
+ "\nlast ocn: ", check["last_ocn"],
+ "\nlength bookindex: ", bookindex_unordered_hashes.length,
+ "\n", __FILE__, ":", __LINE__,
+ );
+ debug(checkdoc) {
+ if (auto mfn=match(fn_src, rgx.src_fn)) {
+ if (actions["assert"] == "yes") {
+ switch (mfn.captures[2]) {
+ case "live-manual.ssm":
+ assert(check["last_ocn"] ==
+ "1019","last ocn should be: 1019 (check test, document is frequently updated)"); // ok
+ break;
+ case "sisu_markup.sst":
+ assert(check["last_ocn"] ==
+ "297","last ocn should be: 297"); // ok
+ // assert(check["last_ocn"] == "297","last ocn should be: 297");
+ // notes for first divergance study sisu headings 247 250
+ // sisu has issue with code that contains heading 1~ which results in no ocn! ??
+ // sisu currently has incorrect last body ocn of 294!
+ // bug in sisu? attend
+ break;
+ // sisu-markup-samples:
+ case "accelerando.charles_stross.sst":
+ assert(check["last_ocn"] ==
+ "2861","last ocn should be: 2861"); // ok
+ break;
+ case "alices_adventures_in_wonderland.lewis_carroll.sst":
+ assert(check["last_ocn"] ==
+ "805","last ocn should be: 805"); // 808
+ break;
+ case "autonomy_markup0.sst":
+ assert(check["last_ocn"] ==
+ "77","last ocn should be: 77"); // ok endnotes
+ // assert(check["last_ocn"] == "78","last ocn should be: 78");
+ break;
+ case "content.cory_doctorow.sst":
+ assert(check["last_ocn"] ==
+ "953","last ocn should be: 953"); // 1007 way off, check ocn off switches
+ // assert(check["last_ocn"] == "953","last ocn should be: 953");
+ break;
+ case "democratizing_innovation.eric_von_hippel.sst":
+ // fixed ERROR! range violation, broken check! endnotes, bookindex, biblio
+ // error in bookindex ... (ch1; ch6; ch8 )
+ assert(check["last_ocn"] ==
+ "905","last ocn should be: 905"); // 911
+ break;
+ case "down_and_out_in_the_magic_kingdom.cory_doctorow.sst":
+ assert(check["last_ocn"] ==
+ "1417","last ocn should be: 1417"); // 1455 check ocn off switches
+ break;
+ case "for_the_win.cory_doctorow.sst":
+ assert(check["last_ocn"] ==
+ "3510","last ocn should be: 3510"); // 3569 check ocn off switches
+ break;
+ case "free_as_in_freedom_2.richard_stallman_and_the_free_software_revolution.sam_williams.richard_stallman.sst":
+ assert(check["last_ocn"] ==
+ "1082","last ocn should be: 1082"); // check 1079 too few
+ break;
+ case "free_culture.lawrence_lessig.sst":
+ assert(check["last_ocn"] ==
+ "1330","last ocn should be: 1330"); // 1312
+ // fixed ERROR! range violation, broken check!
+ // error in bookindex ... sections piracy (ch1) & property (ch10 market concentration) fixed
+ break;
+ case "free_for_all.peter_wayner.sst": // endnotes, bookindex, biblio
+ assert(check["last_ocn"] ==
+ "1559","last ocn should be: 1559"); // 1560, check ocn off switches, has endnotes so 2 too many
+ // assert(check["last_ocn"] == "1559","last ocn should be: 1559");
+ break;
+ case "gpl2.fsf.sst":
+ assert(check["last_ocn"] ==
+ "65","last ocn should be: 65"); // ok endnotes? check
+ // assert(check["last_ocn"] == "66","last ocn should be: 66");
+ break;
+ case "gpl3.fsf.sst":
+ assert(check["last_ocn"] ==
+ "123","last ocn should be: 123"); // ok
+ break;
+ case "gullivers_travels.jonathan_swift.sst":
+ assert(check["last_ocn"] ==
+ "668","last ocn should be: 668"); // 674
+ break;
+ case "little_brother.cory_doctorow.sst":
+ assert(check["last_ocn"] ==
+ "3130","last ocn should be: 3130"); // 3204, check ocn off switches
+ break;
+ case "the_cathedral_and_the_bazaar.eric_s_raymond.sst":
+ assert(check["last_ocn"] ==
+ "258","last ocn should be: 258"); // ok
+ break;
+ case "the_public_domain.james_boyle.sst":
+ assert(check["last_ocn"] ==
+ "970","last ocn should be: 970"); // 978
+ break;
+ case "the_wealth_of_networks.yochai_benkler.sst": // endnotes, bookindex
+ assert(check["last_ocn"] ==
+ "829","last ocn should be: 829"); // ok
+ // assert(check["last_ocn"] == "832","last ocn should be: 832");
+ // has endnotes and bookindex, issue with sisu.rb
+ break;
+ case "through_the_looking_glass.lewis_carroll.sst":
+ assert(check["last_ocn"] ==
+ "949","last ocn should be: 949"); // 955
+ break;
+ case "two_bits.christopher_kelty.sst": // endnotes, bookindex, biblio
+ assert(check["last_ocn"] ==
+ "1190","last ocn should be: 1190"); // 1191
+ // assert(check["last_ocn"] == "1193","last ocn should be: 1193"); // 1191 ok?
+ // has endnotes and bookindex, issue with sisu.rb
+ break;
+ // fixed ERROR! range violation!
+ // error in bookindex ... (ch3 the movement)
+ break;
+ case "un_contracts_international_sale_of_goods_convention_1980.sst":
+ assert(check["last_ocn"] ==
+ "377","last ocn should be: 377"); // ok
+ break;
+ case "viral_spiral.david_bollier.sst": // endnotes, bookindex
+ assert(check["last_ocn"] ==
+ "1078","last ocn should be: 1078"); // 1100
+ // fixed ERROR! range violation!
+ // error in bookindex ... (ch7 ... building the cc machine, an extra semi colon)
+ break;
+ // case ".sst":
+ // assert(check["last_ocn"] == "0","last ocn should be: 0");
+ // break;
+ // case ".sst":
+ // assert(check["last_ocn"] == "0","last ocn should be: 0");
+ // break;
+ // case ".sst":
+ // assert(check["last_ocn"] == "0","last ocn should be: 0");
+ // break;
+ default:
+ writeln(fn_src);
+ break;
+ }
+ }
+ }
+ }
+ }
+ }
+ }
+}
diff --git a/lib/sdp/ao_rgx.d b/lib/sdp/ao_rgx.d
new file mode 100644
index 0000000..755ba11
--- /dev/null
+++ b/lib/sdp/ao_rgx.d
@@ -0,0 +1,195 @@
+/*
+#+OPTIONS: ^:nil _:nil#+OPTIONS: ^:nil _:nil
+* sisu_rgx.d
+*/
+mixin template RgxInit() {
+/*
+** misc
+*/
+ class Rgx {
+ static flag_action = ctRegex!(`^(--[a-z][a-z0-9-]+)$`);
+ static flag_action_str = ctRegex!(` (--[a-z][a-z0-9-]+)`);
+ static src_pth = ctRegex!(`^([a-zA-Z0-9._-]+/)*([a-zA-Z0-9._-]+[.]ss[tm])$`);
+ static src_fn = ctRegex!(`^([a-zA-Z0-9._-]+/)*([a-zA-Z0-9._-]+[.]ss[tm])$`);
+ static src_fn_master = ctRegex!(`^([a-zA-Z0-9._-]+/)*([a-zA-Z0-9._-]+[.]ssm)$`);
+ static src_fn_find_inserts = ctRegex!(`^([a-zA-Z0-9._-]+/)*([a-zA-Z0-9._-]+[.]ss[im])$`);
+ static line_delimiter = ctRegex!("\n");
+ static within_quotes = ctRegex!(`"(.+?)"`);
+ static make_heading_delimiter = ctRegex!(`[;][ ]*`);
+ static arr_delimiter = ctRegex!(`[ ]*[;][ ]*`);
+ static name_delimiter = ctRegex!(`^([^,]+)[ ]*,[ ]+(.+?)$`);
+ static book_index_go = ctRegex!("([0-9]+)(?:-[0-9]+)?");
+ static trailing_comma = ctRegex!(",[ ]*$");
+ static trailing_linebreak = ctRegex!(",[ ]{1,2}\\\\\\\\\n[ ]{4}$","m");
+ static line_delimiter_ws_strip = ctRegex!("[ ]*\n[ ]*");
+ static line_delimiter_only = ctRegex!("^\n");
+ static para_delimiter = ctRegex!("\n[ ]*\n+");
+ static levels_markup = ctRegex!(`^[A-D1-4]$`);
+ static levels_numbered = ctRegex!(`^[0-9]$`);
+ static levels_numbered_headings = ctRegex!(`^[0-7]$`);
+/*
+** insert markup file
+*/
+ static insert_src_fn_ssi_or_sst = ctRegex!(`^<<\s*(?P<path>[a-zA-Z0-9._-]+/)*(?P<filename>[a-zA-Z0-9._-]+[.]ss[ti])$`);
+/*
+** header & comments
+*/
+ static comment = ctRegex!(`^%+ `);
+ static header = ctRegex!(`^@([a-z_]+):(?:\s|$)`);
+ static header_make = ctRegex!(`^@(make):(?:\s|$)`);
+ static header_metadata = ctRegex!(`^@([a-z_]+):(?:\s|$)`);
+ static header_sub = ctRegex!(`^[ ]+:([a-z_]+):\s`);
+ static head_main = ctRegex!(`^@([a-z_]+):\s*(.*)`, "m");
+ static head_sub = ctRegex!(`^[ ]*:([a-z_]+):\s+(.+)`, "m");
+/*
+** heading & paragraph operators
+*/
+ static heading = ctRegex!(`^:?([A-D1-4])[~]([a-z0-9_.-]*[?]?) `);
+ static heading_marker = ctRegex!(`^:?([A-D1-4])[~]`);
+ static heading_title = ctRegex!(`^:?[A-D1-4][~][a-z0-9_.-]*[?]?\s+(.+?)$`);
+ static heading_all = ctRegex!(`^:?([A-D1-4])[~]([a-z0-9_.-]*[?]?)\s+(.+?)$`); // test, particularly [2] name/hashtag which may or may not be, does this affect title [3]
+ static heading_biblio = ctRegex!(`^:?(1)[~][!](biblio(?:graphy)?|references?)`);
+ static heading_glossary = ctRegex!(`^:?(1)[~][!](glossary)`);
+ static para_bullet = ctRegex!(`^_[*] `);
+ static para_bullet_indent = ctRegex!(`^_([1-9])[*] `);
+ static para_indent = ctRegex!(`^_([1-9]) `);
+ static para_indent_hang = ctRegex!(`^_([0-9])_([0-9]) `);
+ static para_attribs = ctRegex!(`^_(([0-9])(_([0-9]))?|_([1-9])?[*]) `);
+/*
+** blocked markup tics
+*/
+ static block_tic_code_open = ctRegex!("^`{3} (code)");
+ static block_tic_poem_open = ctRegex!("^`{3} (poem)");
+ static block_tic_group_open = ctRegex!("^`{3} (group)");
+ static block_tic_block_open = ctRegex!("^`{3} (block)");
+ static block_tic_quote_open = ctRegex!("^`{3} (quote)");
+ static block_tic_table_open = ctRegex!("^`{3} (table)");
+ static block_tic_close = ctRegex!("^(`{3})$","m");
+/*
+** blocked markup curly
+*/
+ static block_curly_code_open = ctRegex!(`^(code[{].*?$)`);
+ static block_curly_code_close = ctRegex!(`^([}]code)`);
+ static block_curly_poem_open = ctRegex!(`^(poem[{].*?$)`);
+ static block_curly_poem_close = ctRegex!(`^([}]poem)`);
+ static block_curly_group_open = ctRegex!(`^(group[{].*?$)`);
+ static block_curly_group_close = ctRegex!(`^([}]group)`);
+ static block_curly_block_open = ctRegex!(`^(block[{].*?$)`);
+ static block_curly_block_close = ctRegex!(`^([}]block)`);
+ static block_curly_quote_open = ctRegex!(`^(quote[{].*?$)`);
+ static block_curly_quote_close = ctRegex!(`^([}]quote)`);
+ static block_curly_table_open = ctRegex!(`^(table[{].*?$)`);
+ static block_curly_table_close = ctRegex!(`^([}]table)`);
+/*
+** inline markup font face mod
+*/
+ static inline_emphasis = ctRegex!(`\*\{(?P<text>.+?)\}\*`);
+ static inline_bold = ctRegex!(`!\{(?P<text>.+?)\}!`);
+ static inline_italics = ctRegex!(`/\{(?P<text>.+?)\}/`);
+ static inline_superscript = ctRegex!(`\^\{(?P<text>.+?)\}\^`);
+ static inline_subscript = ctRegex!(`,\{(?P<text>.+?)\},`);
+ static inline_strike = ctRegex!(`-\{(?P<text>.+?)\}-`);
+ static inline_insert = ctRegex!(`\+\{(?P<text>.+?)\}\+`);
+ static inline_mono = ctRegex!(`#\{(?P<text>.+?)\}#`);
+/*
+** inline markup footnotes
+*/
+ static true_dollar = ctRegex!(`\$`, "gm");
+ static inline_notes_al = ctRegex!(`【(?:[*+]\s+|\s*)(.+?)】`, "mg");
+ static inline_notes_al_gen = ctRegex!(`【.+?】`, "m");
+ static inline_notes_curly_gen = ctRegex!(`~\{.+?\}~`, "m");
+ static inline_notes_curly = ctRegex!(`~\{\s*(.+?)\}~`, "mg");
+ static inline_al_delimiter_open_regular = ctRegex!(`【`, "m");
+ static inline_al_delimiter_close_regular = ctRegex!(`】`, "m");
+ static inline_al_delimiter_open_and_close_regular = ctRegex!(`【|】`, "m");
+ static inline_notes_delimiter_al_regular = ctRegex!(`【(.+?)】`, "m");
+ static inline_notes_delimiter_al_regular_number_note = ctRegex!(`【(\d+)\s+(.+?)】`, "m");
+
+ static inline_al_delimiter_open_asterisk = ctRegex!(`【\*`, "m");
+ static inline_al_delimiter_open_plus = ctRegex!(`【\+`, "m");
+
+ static inline_curly_delimiter_open_regular = ctRegex!(`~\{\s*`, "m");
+ static inline_curly_delimiter_close_regular = ctRegex!(`\s*\}~`, "m");
+ static inline_curly_delimiter_open_and_close_regular = ctRegex!(`~\{\s*|\s*\}~`, "m");
+ static inline_notes_delimiter_curly_regular = ctRegex!(`~\{[ ]*(.+?)\}~`, "m");
+ static inline_notes_curly_sp = ctRegex!(`~\{[*+]+\s+(.+?)\}~`, "m");
+ static inline_notes_curly_sp_asterisk = ctRegex!(`~\{[*]+\s+(.+?)\}~`, "m");
+ static inline_notes_curly_sp_plus = ctRegex!(`~\{[+]+\s+(.+?)\}~`, "m");
+ static inline_text_and_note_al = ctRegex!(`(?P<text>.+?)【(?:[*+ ]*)(?P<note>.+?)】`, "mg");
+ static inline_text_and_note_curly = ctRegex!(`(?P<text>.+?)(?:(?:[~])[{][*+ ]*)(?P<note>.+?)(?:[}][~])`, "mg");
+ static inline_note_curly_delimiters = ctRegex!(`(~\{[*+]?\s*)(.+?)(\}~)`, "mg");
+ static inline_notes_square = ctRegex!(`~\[\s*(.+?)\]~`, "mg");
+ static inline_text_and_note_square_sp = ctRegex!(`(.+?)~\[[*+]+\s+(.+?)\]~`, "mg");
+ static inline_text_and_note_square = ctRegex!(`(.+?)~\[\s*(.+?)\]~`, "mg");
+ static inline_note_square_delimiters = ctRegex!(`(~\[\s*)(.+?)(\]~)`, "mg");
+/*
+** inline markup book index
+*/
+ static book_index = ctRegex!(`^=\{\s*(.+?)\}$`, "m");
+ static book_index_open = ctRegex!(`^=\{\s*([^}]+?)$`);
+ static book_index_close = ctRegex!(`^(.*?)\}$`, "m"); // strip
+/*
+** no ocn object
+*/
+ static ocn_off = ctRegex!(`~#$`, "m");
+ static ocn_off_dh = ctRegex!(`-#$`, "m");
+ static ocn_off_all = ctRegex!(`[~-]#$`, "m");
+/*
+** no ocn block
+*/
+ static ocn_off_block = ctRegex!(`^--~#$`);
+ static ocn_off_block_dh = ctRegex!(`^---#$`);
+ static ocn_off_block_close = ctRegex!(`^--\+#$`);
+ static ocn_block_marks = ctRegex!(`^--[+~-]#$`);
+/*
+** ignore outside code blocks
+*/
+ static regular_parse_skip = ctRegex!(`^(--[+~-]#|-[\\]{2}-|=[.\\]{2}=)$`); // not structural info
+/*
+** line& page breaks
+*/
+ static break_line_within_object = ctRegex!(`[\\]{2}( |$)`);
+// static break_line_break_within_object = ctRegex!(`( |^)[\\]{2}( |$)`);
+ static break_page = ctRegex!(`^-[\\]{2}-$`);
+ static break_page_new = ctRegex!(`^=[\\]{2}=$`);
+ static break_page_line_across = ctRegex!(`^=[.]{2}=$`);
+ static break_string = ctRegex!(`』`);
+// ancestry, parent
+ static parent = ctRegex!(`([0-7]):([0-9]+)`);
+/*
+** json
+*/
+ static tailing_comma = ctRegex!(`,$`, "m");
+/*
+** head
+*/
+ static main_headers = ctRegex!(`^(?:creator|title|rights|date|original|classify|identifier|notes|publisher|make|links)$`, "m");
+ static subhead_creator = ctRegex!(`^(?:author|translator|illustrator)$`, "m");
+ static subhead_title = ctRegex!(`^(?:main|sub(?:title)?|full|language|edition|note)$`, "m");
+ static subhead_rights = ctRegex!(`^(?:copyright|illustrations|license|cover)$`, "m");
+ static subhead_date = ctRegex!(`^(?:published|created|issued|available|valid|modified|added_to_site)$`, "m");
+ static subhead_original = ctRegex!(`^(?:title|language|source)$`, "m");
+ static subhead_classify = ctRegex!(`^(?:topic_register|subject|keywords|loc|dewey)$`, "m");
+ static subhead_identifier = ctRegex!(`^(?:oclc|pg|isbn)$`, "m");
+ static subhead_notes = ctRegex!(`^(?:abstract|description)$`, "m");
+ static subhead_publisher = ctRegex!(`^(?:name)$`, "m");
+ static subhead_make = ctRegex!(`^(?:cover_image|home_button_image|home_button_text|footer|headings|num_top|breaks|substitute|bold|italics|emphasis|texpdf_font|css)$`, "m");
+/*
+** biblio tags
+*/
+ static biblio_tags = ctRegex!(`^(is|au|author_raw|author|author_arr|editor_raw|ed|editor_arr|ti|title|subtitle|fulltitle|lng|language|trans|src|jo|journal|in|vol|volume|edn|edition|yr|year|pl|place|pb|pub|publisher|url|pg|pages|note|short_name|id):\s+(.+)`);
+ static biblio_abbreviations = ctRegex!(`^(au|ed|ti|lng|jo|vol|edn|yr|pl|pb|pub|pg|pgs|sn)$`);
+/*
+** bookindex split
+*/
+ static bi_main_terms_split = ctRegex!(`\s*;\s*`);
+ static bi_main_term_plus_rest_split = ctRegex!(`\s*:\s*`);
+ static bi_sub_terms_plus_ocn_offset_split = ctRegex!(`\s*\|\s*`);
+ static bi_term_and_ocns_match = ctRegex!(`^(.+?)\+(\d+)`);
+/*
+* url matching http://url.is/got and { text }http://url.is/got
+* image matching
+* header substitution & bold & italics lists
+*/
+ }
+}
diff --git a/lib/sdp/ao_scan_inserts.d b/lib/sdp/ao_scan_inserts.d
new file mode 100644
index 0000000..e99222a
--- /dev/null
+++ b/lib/sdp/ao_scan_inserts.d
@@ -0,0 +1,229 @@
+/*
+#+OPTIONS: ^:nil _:nil#+OPTIONS: ^:nil _:nil
+* sisu_scan_inserts.d
+*/
+mixin template SiSUdocInserts() {
+ class Inserts {
+ auto scan_subdoc_source(
+ char[][] markup_sourcefile_insert_content, string fn_src, int add
+ ) {
+ char[][100000] cont_arbitrary_max_length_set_;
+ auto ft0 = flag_type.dup;
+ auto ft1 = flag_type.dup;
+ string[string] processing;
+ uint[string] line_occur;
+ auto obj_im = new ObjInlineMarkup();
+ auto obj_att = new ObjAttrib();
+ int[string] counter; counter["add"]=0;
+ mixin ScreenTxtColors;
+ auto rgx = new Rgx();
+ int tell_l(string color, in char[] line) {
+ writeln(scr_txt_marker[color], line);
+ return 0;
+ }
+ auto fn_pth_full = match(fn_src, rgx.src_pth);
+ auto markup_src_file_path = fn_pth_full.captures[1];
+ foreach (line; markup_sourcefile_insert_content) {
+ if (ft1["curly_code"] == 1) {
+ ft1["header_make"] = 0;
+ ft1["header_metadata"] = 0;
+ if (auto m = match(line, rgx.block_curly_code_close)) {
+ ft1["curly_code"] = 0;
+ }
+ cont_arbitrary_max_length_set_[counter["add"]] = line;
+ ++counter["add"]; ++add;
+ } else if (auto m = match(line, rgx.block_curly_code_open)) {
+ ft1["curly_code"] = 1;
+ ft1["header_make"] = 0;
+ ft1["header_metadata"] = 0;
+ cont_arbitrary_max_length_set_[counter["add"]] = line;
+ ++counter["add"]; ++add;
+ } else if (ft1["tic_code"] == 1) {
+ ft1["header_make"] = 0;
+ ft1["header_metadata"] = 0;
+ if (auto m = match(line, rgx.block_tic_close)) {
+ ft1["tic_code"] = 0;
+ }
+ cont_arbitrary_max_length_set_[counter["add"]] = line;
+ ++counter["add"]; ++add;
+ } else if (auto m = match(line, rgx.block_tic_code_open)) {
+ ft1["tic_code"] = 1;
+ ft1["header_make"] = 0;
+ ft1["header_metadata"] = 0;
+ cont_arbitrary_max_length_set_[counter["add"]] = line;
+ ++counter["add"]; ++add;
+ } else if (
+ (ft1["header_make"] == 1) && (line_occur["header_make"] > 0)
+ && match(line, rgx.header_sub)
+ ) {
+ ft1["header_make"] = 1;
+ ft1["header_metadata"] = 0;
+ ++line_occur["header_make"];
+ ++counter["add"];
+ } else if (
+ (ft1["header_metadata"] == 1) && (line_occur["header_metadata"] > 0)
+ && match(line, rgx.header_sub)
+ ) {
+ ft1["header_metadata"] = 1;
+ ft1["header_make"] = 0;
+ ++line_occur["header_metadata"];
+ ++counter["add"];
+ } else if (auto m = match(line, rgx.insert_src_fn_ssi_or_sst)) {
+ ft1["header_make"] = 0;
+ ft1["header_metadata"] = 0;
+ auto insert_fn = m.captures[2];
+ auto insert_sub_pth = m.captures[1];
+ auto fn_src_insert =
+ (markup_src_file_path ~ insert_sub_pth ~ insert_fn);
+ auto raw = new MarkupInsertRaw();
+ auto markup_sourcesubfile_insert_content =
+ raw.markupSourceContentRawLineArray(fn_src_insert);
+ debug(insert) { // insert file
+ tell_l("red", line);
+ tell_l("red", fn_src_insert);
+ tell_l("fuchsia", "ERROR");
+ writeln(
+ " length contents insert array: ",
+ markup_sourcesubfile_insert_content.length
+ );
+ }
+ auto ins = new Inserts();
+ /*
+ 1. load file,
+ 2. read lines;
+ 3. scan lines,
+ 4. if filename insert, and insert filename
+ 5. repeat 1
+ 6. else
+ 7. add line to new array;
+ */
+ } else {
+ ft1["header_make"] = 0;
+ ft1["header_metadata"] = 0;
+ cont_arbitrary_max_length_set_[counter["add"]] = line;
+ ++counter["add"]; ++add;
+ }
+ }
+ auto contents_ = cont_arbitrary_max_length_set_[0 .. counter["add"]].dup;
+ auto t = tuple(contents_, add);
+ return t;
+ }
+ auto scan_doc_source(char[][] markup_sourcefile_content, string fn_src) {
+ char[] cont_arbitrary_max_length_set[100000]; // 2000 pg * 50 lines
+ string[string] processing;
+ uint[string] line_occur;
+ auto obj_im = new ObjInlineMarkup();
+ auto obj_att = new ObjAttrib();
+ auto ft = flag_type.dup;
+ int add;
+ mixin ScreenTxtColors;
+ auto rgx = new Rgx();
+ int tell_l(string color, in char[] line) {
+ writeln(scr_txt_marker[color], line);
+ return 0;
+ }
+ auto fn_pth_full = match(fn_src, rgx.src_pth);
+ auto markup_src_file_path = fn_pth_full.captures[1];
+ foreach (line; markup_sourcefile_content) {
+ if (ft["curly_code"] == 1) {
+ ft["header_make"] = 0;
+ ft["header_metadata"] = 0;
+ if (auto m = match(line, rgx.block_curly_code_close)) {
+ ft["curly_code"] = 0;
+ }
+ cont_arbitrary_max_length_set[add] = line;
+ ++add;
+ } else if (auto m = match(line, rgx.block_curly_code_open)) {
+ ft["curly_code"] = 1;
+ ft["header_make"] = 0;
+ ft["header_metadata"] = 0;
+ cont_arbitrary_max_length_set[add] = line;
+ ++add;
+ } else if (ft["tic_code"] == 1) {
+ ft["header_make"] = 0;
+ ft["header_metadata"] = 0;
+ if (auto m = match(line, rgx.block_tic_close)) {
+ ft["tic_code"] = 0;
+ }
+ cont_arbitrary_max_length_set[add] = line;
+ ++add;
+ } else if (auto m = match(line, rgx.block_tic_code_open)) {
+ ft["tic_code"] = 1;
+ ft["header_make"] = 0;
+ ft["header_metadata"] = 0;
+ cont_arbitrary_max_length_set[add] = line;
+ } else if ((ft["header_make"] == 1)
+ && (line_occur["header_make"] > 0)
+ && match(line, rgx.header_sub)) {
+ ++line_occur["header_make"];
+ cont_arbitrary_max_length_set[add] = line;
+ ++add;
+ } else if ((ft["header_metadata"] == 1)
+ && (line_occur["header_metadata"] > 0)
+ && match(line, rgx.header_sub)) {
+ ++line_occur["header_metadata"];
+ cont_arbitrary_max_length_set[add] = line;
+ ++add;
+ } else if (auto m = match(line, rgx.header_make)) {
+ ft["header_make"] = 1;
+ ++line_occur["header_make"];
+ cont_arbitrary_max_length_set[add] = line;
+ ++add;
+ } else if (auto m = match(line, rgx.header_metadata)) {
+ ft["header_metadata"] = 1;
+ ++line_occur["header_metadata"];
+ cont_arbitrary_max_length_set[add] = line;
+ ++add;
+ } else if (auto m = match(line, rgx.insert_src_fn_ssi_or_sst)) {
+ ft["header_make"] = 0;
+ ft["header_metadata"] = 0;
+ auto insert_fn = m.captures[2];
+ auto insert_sub_pth = m.captures[1];
+ auto fn_src_insert =
+ (markup_src_file_path ~ insert_sub_pth ~ insert_fn);
+ auto raw = new MarkupInsertRaw();
+ auto markup_sourcefile_insert_content =
+ raw.markupSourceContentRawLineArray(fn_src_insert);
+ debug(insert) { // insert file
+ tell_l("red", line);
+ tell_l("red", fn_src_insert);
+ writeln(
+ " length contents insert array: ",
+ markup_sourcefile_insert_content.length
+ );
+ }
+ auto ins = new Inserts();
+ auto t = ins.scan_subdoc_source(
+ markup_sourcefile_insert_content, to!string(fn_src_insert), add
+ );
+ static assert(!isTypeTuple!(t));
+ auto tmparr = t[0];
+ auto addsub = t[1];
+ cont_arbitrary_max_length_set[add .. addsub-1] = tmparr[0 .. $-1];
+ add=addsub;
+ /*
+ 1. load file,
+ 2. read lines;
+ 3. scan lines,
+ 4. if filename insert, and insert filename
+ 5. repeat 1
+ 6. else
+ 7. add line to new array;
+ */
+ } else {
+ ft["header_make"] = 0;
+ ft["header_metadata"] = 0;
+ cont_arbitrary_max_length_set[add] = line;
+ ++add;
+ }
+ }
+ auto contents = cont_arbitrary_max_length_set[0..add].dup;
+ debug(insert) { // insert file
+ writeln(__LINE__);
+ writeln(contents.length);
+ writeln(add);
+ }
+ return contents;
+ }
+ }
+}
diff --git a/lib/sdp/ao_utils.d b/lib/sdp/ao_utils.d
new file mode 100644
index 0000000..70ad667
--- /dev/null
+++ b/lib/sdp/ao_utils.d
@@ -0,0 +1,74 @@
+/*
+#+OPTIONS: ^:nil _:nil#+OPTIONS: ^:nil _:nil
+* sisu_utils.d
+*/
+mixin template ScreenTxtColors() {
+ string[string] scr_txt_color = [
+ "off" : "\033[0m",
+ "white" : "\033[37m",
+ "white_bold" : "\033[1m",
+ "marker" : "\033[42m",
+ "bold" : "\033[1m",
+ "underline" : "\033[4m",
+ "invert" : "\033[7m",
+ "darkgrey_hi" : "\033[100m",
+ "grey_hi" : "\033[47m",
+ "pink_hi" : "\033[105m",
+ "fuchsia_hi" : "\033[45m",
+ "red_hi" : "\033[41m",
+ "orange_hi" : "\033[101m",
+ "yellow_hi" : "\033[103m",
+ "brown_hi" : "\033[43m",
+ "lightgreen_hi" : "\033[102m",
+ "green_hi" : "\033[42m",
+ "cyan_hi" : "\033[106m",
+ "blue_hi" : "\033[104m",
+ "navy_hi" : "\033[44m",
+ "grey" : "\033[90m",
+ "pink" : "\033[95m",
+ "fuchsia" : "\033[35m",
+ "ruby" : "\033[31m",
+ "red" : "\033[91m",
+ "orange" : "\033[91m",
+ "yellow" : "\033[93m",
+ "brown" : "\033[33m",
+ "green" : "\033[92m",
+ "darkgreen" : "\033[32m",
+ "cyan" : "\033[36m",
+ "blue" : "\033[94m",
+ "navy" : "\033[34m",
+ "black" : "\033[30m"
+ ];
+ string[string] scr_txt_marker = [
+ "white" : "\033[37m*\033[0m ",
+ "bold" : "\033[1m*\033[0m ",
+ "invert" : "\033[7m*\033[0m ",
+ "darkgrey_hi" : "\033[100m*\033[0m ",
+ "grey_hi" : "\033[47m*\033[0m ",
+ "pink_hi" : "\033[105m*\033[0m ",
+ "fuchsia_hi" : "\033[45m*\033[0m ",
+ "red_hi" : "\033[41m*\033[0m ",
+ "orange_hi" : "\033[101m*\033[0m ",
+ "yellow_hi" : "\033[103m*\033[0m ",
+ "brown_hi" : "\033[43m*\033[0m ",
+ "lightgreen_hi" : "\033[102m*\033[0m ",
+ "green_hi" : "\033[42m*\033[0m ",
+ "cyan_hi" : "\033[106m*\033[0m ",
+ "blue_hi" : "\033[104m*\033[0m ",
+ "navy_hi" : "\033[44m*\033[0m ",
+ "grey" : "\033[90m*\033[0m ",
+ "pink" : "\033[95m*\033[0m ",
+ "fuchsia" : "\033[35m*\033[0m ",
+ "ruby" : "\033[31m*\033[0m ",
+ "red" : "\033[91m*\033[0m ",
+ "orange" : "\033[91m*\033[0m ",
+ "yellow" : "\033[93m*\033[0m ",
+ "brown" : "\033[33m*\033[0m ",
+ "green" : "\033[92m*\033[0m ",
+ "darkgreen" : "\033[32m*\033[0m ",
+ "cyan" : "\033[36m*\033[0m ",
+ "blue" : "\033[94m*\033[0m ",
+ "navy" : "\033[34m*\033[0m ",
+ "black" : "\033[30m*\033[0m "
+ ];
+}
diff --git a/lib/sdp/sdp.d b/lib/sdp/sdp.d
new file mode 100644
index 0000000..3bfbc5b
--- /dev/null
+++ b/lib/sdp/sdp.d
@@ -0,0 +1,161 @@
+#!/usr/bin/env rdmd
+/*
+#+OPTIONS: ^:nil _:nil#+OPTIONS: ^:nil _:nil
+* sdp.d :sdp:
+*/
+import
+ std.stdio,
+ std.file,
+ std.regex,
+ std.utf,
+ std.string,
+ std.array,
+ std.json,
+ std.process,
+ std.exception,
+ std.typecons,
+ std.algorithm,
+ std.range,
+ std.container,
+ std.traits,
+ lib.sdp.ao_output_debugs, // ao_output_debugs.d
+ lib.sdp.ao_defaults, // ao_defaults.d
+ lib.sdp.ao_rgx, // ao_rgx.d
+ lib.sdp.ao_interface, // ao_interface.d
+ lib.sdp.ao_emitter, // ao_emitter.d
+ lib.sdp.ao_scan_inserts, // ao_scan_inserts.d
+ lib.sdp.ao_markup_source_raw, // ao_markup_source_raw.d
+ lib.sdp.ao_abstract_doc_source, // ao_abstract_doc_source.d
+ lib.sdp.ao_assertions, // ao_assertions.d
+ lib.sdp.ao_object_setter, // ao_object_setter.d
+ lib.sdp.ao_utils; // ao_utils.d
+import std.conv : to;
+mixin RgxInit; mixin Interfaces; mixin Emitters;
+void main(string argv[]) {
+ mixin SiSUheader;
+ mixin SiSUbiblio;
+ mixin SiSUrgxInitFlags;
+ mixin SiSUmarkupRaw;
+ mixin SiSUdocInserts;
+ mixin SiSUdocAbstraction;
+ mixin SiSUoutputDebugs;
+ mixin ScreenTxtColors;
+ auto cli = new CLI();
+ auto raw = new MarkupRaw();
+ auto abs = new Abstraction();
+ auto dbg = new SDPoutputDebugs();
+ char[][] msc;
+ string[1000] fns_src;
+ string flag_action;
+ string[string] actions;
+ int file_count;
+ actions = [
+ "assert" : "yes",
+ ];
+ auto rgx = new Rgx();
+ scope(success) {
+ debug(checkdoc) {
+ writeln(
+ scr_txt_color["cyan"],
+ "~ run complete, ok ~ ",
+ scr_txt_color["off"],
+ );
+ }
+ }
+ scope(failure) {
+ debug(checkdoc) {
+ writeln(
+ scr_txt_color["fucshia"],
+ "~ run failure ~",
+ scr_txt_color["off"],
+ );
+ }
+ }
+ foreach(cmdlnins; argv) {
+ if (match(cmdlnins, rgx.flag_action)) {
+ flag_action ~= " " ~ cmdlnins;
+ actions = cli.extract_actions(cmdlnins, actions);
+ } else if (match(cmdlnins, rgx.src_pth)) {
+ fns_src[file_count] = cmdlnins;
+ file_count++;
+ }
+ }
+ foreach(fn_src; fns_src) {
+ if (!empty(fn_src)) {
+ scope(success) {
+ debug(checkdoc) {
+ writeln(
+ scr_txt_color["green"],
+ "~ document complete, ok ~ ",
+ scr_txt_color["off"],
+ fn_src
+ );
+ }
+ }
+ scope(failure) {
+ debug(checkdoc) {
+ writeln(
+ scr_txt_color["red"],
+ "~ document run failure ~",
+ scr_txt_color["off"],
+ fn_src
+ );
+ }
+ }
+ auto markup_sourcefile_content =
+ raw.markupSourceContentRawLineArray(fn_src); // alternative call
+ debug(insert) {
+ string[string] sysenv;
+ sysenv["pwd"] = shell("pwd");
+ writeln(sysenv["pwd"]);
+ auto m = match(fn_src, rgx.src_pth);
+ auto markup_src_file_path = m.captures[1];
+ writeln("markup source file path: ", markup_src_file_path); // writeln(m.captures[1]);
+ writeln(m.captures[2]);
+ }
+ if (match(fn_src, rgx.src_fn_master)) {
+ auto ins = new Inserts();
+ auto markup_master_sourcefile_content =
+ ins.scan_doc_source(markup_sourcefile_content, fn_src);
+ msc = markup_master_sourcefile_content;
+ } else {
+ msc = markup_sourcefile_content;
+ }
+ debug(raw) {
+ foreach (line; msc) {
+ writeln(line);
+ }
+ }
+ auto t =
+ abs.abstract_doc_source(msc);
+ static assert(!isTypeTuple!(t));
+ auto contents = t[0];
+ auto metadata_json = t[1];
+ auto make_json = t[2];
+ auto bookindex_unordered_hashes = t[3];
+ auto biblio = t[4];
+ debug(checkdoc) {
+ dbg.abstract_doc_source_debugs(
+ contents,
+ make_json,
+ metadata_json,
+ bookindex_unordered_hashes,
+ biblio,
+ fn_src,
+ actions
+ );
+ }
+ scope(exit) {
+ destroy(msc);
+ destroy(t);
+ destroy(contents);
+ destroy(make_json);
+ destroy(metadata_json);
+ destroy(bookindex_unordered_hashes);
+ destroy(fn_src);
+ destroy(biblio);
+ }
+ } else { // terminate, stop
+ }
+ }
+}
diff --git a/lib/sdp/sdp.org b/lib/sdp/sdp.org
new file mode 100644
index 0000000..076b42b
--- /dev/null
+++ b/lib/sdp/sdp.org
@@ -0,0 +1,331 @@
+#+OPTIONS: ^:nil _:nil#+OPTIONS: ^:nil _:nil
+#+PRIORITIES: A F E
+* debug
+ objects
+ header
+ heading
+ poem verse ocn
+
+* TODO [#A] tasks
+** sisu_loop.d
+*** header extraction (make instructions & metadata)
+**** metadata
+title & author heading
+**** make
+***** header make: search and replace
+***** auto-identify structure from make instructions
+***** auto-number headings, with starting level as instructed in header make
+*** markup
+**** para markers: extract (hash store) & clean (remove from text)
+place in hash
+ heading level, numeric
+ indent info, numeric: first, rest
+ bullet, bool
+issue representing complex structures, consider using bits of json!
+string h = "{ \"heading_level\": \"A\" }";
+string para_attrib = "{ \"indent_first\": 0, \"indent_rest\": 0, \"bullet\": false }";
+# string s = "{
+# \"indent_first\": 0,
+# \"indent_rest\": 0,
+# \"bullet\": false,
+# \"name\": "",
+# \"tags\": "",
+# \"digest\": "",
+# }";
+string para_attrib = "{
+ \"indent_first\": 0,
+ \"indent_rest\": 0,
+ \"bullet\": false,
+}";
+string obj_ids = "{
+ \"name\": \"\",
+ \"tags\": \"\",
+ \"digest\": \"\",
+}";
+string obj_lv = "{
+ \"markup\": \"\", // [A-D1-4] lv
+ \"num_markup\": 0, // [0-7] ln
+ \"num_collapsed\": 0, // [0-7] lc
+}";
+string obj_citation = "{
+ \"ocn\": 0, //
+ \"on\": true, //
+}";
+
+**** structure as json?
+odv
+osp
+node
+parent
+
+you could keep ocn info (bool & number?) this way, consider
+
+also clean
+ block markers
+ book index!
+**** inline markup of text for subsequent processing
+regex substitution
+search and replace inline ascii markup with less ambiguous utf-8 markers
+***** footnotes count/number
+*** ocn (on & off)
+*** headings
+**** heading numbering?
+
+**** segment naming & id tags
+
+*** backmatter
+**** book index
+clean from object, store under separate key
+consider json
+**** bibliography
+identify and store under separate hash
+consider using json to structure
+**** glossary
+identify and store under separate hash?
+*** composite documents
+import files
+
+<< path_to/file.sst
+
+** cleanup
+
+** ranges & node structure info: structure information (levels, ranges & relationships)
+*** heading pointers
+**** headings_array heading pointer
+**** data_abstration_array heading pointer
+*** ocn
+*** heading
+**** markup level [A-D1-4]
+**** collapsed level [0-7]
+*** parent
+**** heading markup level [A-D1-4]
+**** heading ocn
+*** range, heading & children (till next heading of same level or higher (close level mark))
+**** array range (x..y)
+includes sub headings and non-heading objects till next heading
+debate whether to use relative or absolute values (i.e. array points)
+**** ocn range (x..y)
+
+NodeStructureMetadata see node_jstr
+abstract_doc: obj_att\|node_jstr\|node
+emitter: ObjAttrib
+heading_pointer
+** misc
+*** temporarily turn off ocn
+
+--~# ---# --+#
+
+~# & -#
+
+*** parent & children
+heading parent & children
+paragraph parent
+
+*** dir (read using dlang lib)
+*** how to deal with complex data structures?
+try hashes with json
+
+*** read files
+**** config
+**** make
+* compile
+ http://www.dprogramming.com/tutorial.php
+ http://www.dprogramming.com/tutorial.php#newusers
+** rdmd
+rdmd --build-only --chatty -d-debug sdp.d
+rdmd -d-debug sisu_ref0.d ../markup/test0.sst
+
+VER='sdp2' && rdmd --build-only --chatty lib/${VER}/sdp.d
+
+** dmd
+dmd -debug sdp.d
+
+VER='sdp1' && dmd -debug -of./bin/${VER} lib/${VER}/sdp.d
+VER='sdp1' && dmd -debug=checkdoc -of./bin/${VER} lib/${VER}/sdp.d
+
+** ldc2
+ldc2 -d-debug sdp.d
+
+VER='1' && ldc2 -unittest -d-debug=summary -of=./bin/sdp${VER} lib/sdp${VER}/sdp.d
+VER='1' && ldc2 -d-debug=checkdoc -d-debug=summary -of=./bin/sdp${VER} lib/sdp${VER}/sdp.d
+VER='1' && ldc2 -d-debug=checkdoc -d-debug=summary -of=./bin/sdp${VER} lib/sdp${VER}/sdp.d
+
+VER='sdp1' && ldc2 -d-debug=objects -d-debug=summary -of=./bin/${VER} lib/${VER}/sdp.d
+
+VER='sdp0'
+VER='sdp1'
+VER='sdp2'
+VER='sdp3'
+VER='sdp'
+ldc2 -d-debug -of=./bin/sisu_${VER} lib/${VER}/sdp.d
+ldc2 -d-debug -of=./bin/sisu_${VER} lib/${VER}/sdp.d
+ldc2 -d-debug=heading -of=./bin/sisu_${VER} lib/${VER}/sdp.d
+ldc2 -d-debug=objects -of=./bin/sisu_${VER} lib/${VER}/sdp.d
+
+VER='sdp1' && ldc2 -d-debug=objects -d-debug=summary -of=./bin/sdp lib/${VER}/sdp.d
+
+*** remove later
+binbuild="sdp1"; ldc2 -d-debug ./${binbuild}.d && time ./${binbuild} markup/test0.sst
+binbuild="sdp1"; gdc -fdebug -o ./${binbuild} ./${binbuild}.d && time ./${binbuild} markup/test0.sst
+
+binbuild="sdp1"
+ldc2 -release ./${binbuild}.d && time ./${binbuild} markup/test0.sst
+
+#cd lib
+#ldc1 -d-debug -of=../bin/sdp0 sdp/sdp.d
+
+** gdc
+gdc -o ./bin/sdp0 lib/sdp.d
+VER='sdp2' &&
+gdc -o ./bin/${VER} lib/${VER}/sdp.d
+
+VER='sdp2' && gdc-5 -o ./bin/${VER} ./lib/${VER}/sdp.d
+
+#VER='sdp2' && gdc -o -d-debug=objects -d-debug=summary -of=./bin/${VER} lib/${VER}/sdp.d
+
+*** remove later
+binbuild="sdp1"
+ldc2 -d-debug ${binbuild}.d && time ${binbuild} markup/test0.sst
+gdc -fdebug -o ${binbuild} ${binbuild}.d && time ${binbuild} markup/test0.sst
+
+* run
+sdp0 markup/test0.sst
+
+~utils/d/bin/sdp0 filename.sst
+~utils/d/bin/sdp1 filename.sst
+
+cd markup
+sdp0 test0.sst
+
+* compile notes
+** ldc
+import path[0] = /usr/include/d/ldc
+import path[1] = /usr/include/d
+** gdc
+gdmd -help
+import path[0] = /usr/include/d/4.9/x86_64-linux-gnu
+import path[1] = /usr/include/d/4.9
+** dmd (non-free) install arch?
+** issues
+
+* notes
+*** read file
+char[][] markup_sourcefile_content = split(cast(char[])read(fn_src), rgx_line_delimiter);
+char[][] markup_sourcefile_content = markupSourceLineArray(markupSourceString(fn_src));
+** build
+
+** book index
+// http://forum.dlang.org/post/k8of07$1bgu$1@digitalmars.com
+// http://forum.dlang.org/post/dfyowpjhdaemhxhepfmk@forum.dlang.org
+ // recast ---
+ // ocns ; sub ; main
+ string[][string][string] bookindex;
+ // as ---
+ // ocns ; sub ; main
+ string[]string[][string][] bookindex_the;
+ // with sorted main & sub
+
+// gdc -release -o ./${binbuild} ./${binbuild}.d && time ./${binbuild} markup/test0.sst
+
+// vim ./lib/sdp1/sisu_*.d
+// vim **/sdp1/sisu_*.d
+
+// emacs **/sdp1/sisu_*.d &
+// emacs ./lib/sdp1/sisu_*.d &
+
+// VER='2' && ldc2 -unittest -d-debug=insert -d-debug=objects -d-debug=headings -d-debug=summary -d-debug=checkdoc -d-debug=subheader -of=./bin/sdp${VER} lib/sdp${VER}/sdp.d
+
+* bugs
+ok
+time ~dlang/bin/sdp1 --html --no-assert en/[a-eg-z]*
+not ok
+time ~dlang/bin/sdp1 --html --no-assert en/free_for_all.peter_wayner.sst en/gpl3.fsf.sst
+works if:
+ poems removed from gpl3;
+ biblio removed from free for all
+time ~dlang/bin/sdp0 --html --no-assert en/free_for_all.peter_wayner.sst en/gpl2.fsf.sst en/gpl3.fsf.sst
+time ~dlang/bin/sdp0 --html --no-assert en/[fg]*
+time ~dlang/bin/sdp0 --html --no-assert en/[a-z]*
+leaving out free_for_all seems to make it ok
+time ~dlang/bin/sdp0 --html --no-assert en/[a-eg-z]*
+leaving out any two bibliography entries within free_for_all appears to fix the problem!
+
+works in dmd not in ldc2
+
+*** Error in `/home/ralph/grotto/repo/git.repo/utils/d/bin/sdp2': corrupted double-linked list: 0x00000008b905b310 ***
+in free_for_all bibliography first instance FatBrain ref
+gets stuck after:
+en/free_for_all.peter_wayner.sst
+* desc
+** process files
+.sst (text) regular
+.ssm (master) contains either .sst or .ssi
+.ssi (insert) processed within .ssm (or called into a .ssm by another .ssi)
+** header
+*** metadata
+*** make (@make:)
+cover_image
+home_button_image
+home_button_text
+footer
+headings
+num_top
+breaks
+substitute
+bold
+italics
+emphasis
+texpdf_font
+css
+
+** structure
+document structure is determined by headings of different levels
+headings must either
+(a) be explicitly marked as such, or
+(b) given by a regex (in the appropriate make header) that allows the program determine headings within text
+types of heading:
+*** document separators (A-D)
+level A is the title
+*** text headings (1-4)
+*** header make heading regex
+**** heading levels
+***** markup level [A-D1-4]
+***** markup level numbers [0-7] or [1-8]
+***** collapsed level numbers [0-7] or [1-8]
+***** nodes
+***** json search segments? chapter equivalent, decide
+**** switches, ocn on off (dummy header)
+** object attributes
+types of object:
+*** headings (document structure objects)
+**** level
+**** segment name
+**** numbering
+*** paragraphs
+*** blocks
+types of block object:
+**** group
+**** block
+**** poem (verse)
+**** code
+**** table
+**** quote
+**** TODO alt?
+** paragraph attributes
+types of paragraph attribute:
+*** indent
+**** paragraph (1 - 9)
+**** first line level (1 - 9), & subsequent text level (1 - 9)
+indent (first, rest), bullet
+*** bullets
+** inline text (paragraph) attributes
+bold, italics, emphasis, superscript, substcript, strike, add, monospace, footnote (number them)
+types of text (within paragraph) attribute:
+*** bold
+*** italics
+*** emphasis
+*** underscore
+*** strike
+*** superscript
+*** subscript
+*** ...
diff --git a/sdp.org b/sdp.org
new file mode 100644
index 0000000..7ae67a4
--- /dev/null
+++ b/sdp.org
@@ -0,0 +1,369 @@
+#+OPTIONS: ^:nil _:nil#+OPTIONS: ^:nil _:nil
+#+PRIORITIES: A F E
+* sdp :sdp:
+** debug :debug:
+ objects
+ header
+ heading
+ poem verse ocn
+
+** tasks :tasks:
+*** sisu_loop.d
+**** TODO [#A] header extraction (make instructions & metadata)
+***** metadata
+title & author heading
+***** make
+****** header make: search and replace
+****** auto-identify structure from make instructions
+****** auto-number headings, with starting level as instructed in header make
+**** markup
+***** para markers: extract (hash store) & clean (remove from text)
+place in hash
+ heading level, numeric
+ indent info, numeric: first, rest
+ bullet, bool
+issue representing complex structures, consider using bits of json!
+string h = "{ \"heading_level\": \"A\" }";
+string para_attrib = "{ \"indent_first\": 0, \"indent_rest\": 0, \"bullet\": false }";
+# string s = "{
+# \"indent_first\": 0,
+# \"indent_rest\": 0,
+# \"bullet\": false,
+# \"name\": "",
+# \"tags\": "",
+# \"digest\": "",
+# }";
+string para_attrib = "{
+ \"indent_first\": 0,
+ \"indent_rest\": 0,
+ \"bullet\": false,
+}";
+string obj_ids = "{
+ \"name\": \"\",
+ \"tags\": \"\",
+ \"digest\": \"\",
+}";
+string obj_lv = "{
+ \"markup\": \"\", // [A-D1-4] lv
+ \"num_markup\": 0, // [0-7] ln
+ \"num_collapsed\": 0, // [0-7] lc
+}";
+string obj_citation = "{
+ \"ocn\": 0, //
+ \"on\": true, //
+}";
+
+***** structure as json?
+odv
+osp
+node
+parent
+
+you could keep ocn info (bool & number?) this way, consider
+
+also clean
+ block markers
+ book index!
+***** inline markup of text for subsequent processing
+regex substitution
+search and replace inline ascii markup with less ambiguous utf-8 markers
+****** footnotes count/number
+**** TODO [#B] endnotes/ footnotes for doc objects other than paragraphs & headings various forms of grouped text
+**** TODO [#C] ocn (on & off)
+**** TODO [#B] headings
+***** heading numbering?
+
+***** segment naming & id tags
+
+**** TODO [#B] backmatter
+***** book index
+clean from object, store under separate key
+consider json
+****** TODO [#B] book index sort
+ sort algorithm currently sorts A-Za-z need Aa-Zz
+ also main terms references need to follow main term ... placed under _a which is not always sorted first
+***** bibliography
+identify and store under separate hash
+consider using json to structure
+***** glossary
+identify and store under separate hash?
+**** DONE [#B] composite documents
+import files
+
+<< path_to/file.sst
+
+*** cleanup
+
+*** ranges & node structure info: structure information (levels, ranges & relationships)
+**** heading pointers
+***** headings_array heading pointer
+***** data_abstration_array heading pointer
+**** ocn
+**** heading
+***** markup level [A-D1-4]
+***** collapsed level [0-7]
+**** parent
+***** heading markup level [A-D1-4]
+***** heading ocn
+**** range, heading & children (till next heading of same level or higher (close level mark))
+***** array range (x..y)
+includes sub headings and non-heading objects till next heading
+debate whether to use relative or absolute values (i.e. array points)
+***** ocn range (x..y)
+
+NodeStructureMetadata see node_jstr
+abstract_doc: obj_att\|node_jstr\|node
+emitter: ObjAttrib
+heading_pointer
+*** misc
+**** temporarily turn off ocn
+
+--~# ---# --+#
+
+~# & -#
+
+**** parent & children
+heading parent & children
+paragraph parent
+
+**** dir (read using dlang lib)
+**** how to deal with complex data structures?
+try hashes with json
+
+**** read files
+***** config
+***** make
+** compile :compile:
+ [[http://www.dprogramming.com/tutorial.php][tutorial]]
+ [[http://www.dprogramming.com/tutorial.php#newusers][tutorial new users]]
+*** rdmd
+rdmd --build-only --chatty -d-debug sdp.d
+rdmd -d-debug sisu_ref0.d ../markup/test0.sst
+
+VER='sdp2' && rdmd --build-only --chatty lib/${VER}/sdp.d
+
+*** dmd :dmd:
+dmd -de -w -unittest -debug sdp.d
+
+VER='sdp2'
+dmd -debug -of./bin/${VER} lib/${VER}/sdp.d
+VER='sdp2' && dmd -debug=checkdoc -of./bin/${VER} lib/${VER}/sdp.d
+
+VER='2' && dmd -debug=checkdoc -debug=summary -of./bin/sdp${VER} lib/sdp${VER}/sdp.d
+
+*** ldc2 :ldc:
+ldc2 -d-debug=checkdoc -d-debug=summary -of=./bin/sdp lib/sdp/sdp.d
+
+ldc2 -de -w -unittest -d-debug sdp.d
+
+VER='2' && ldc2 -d-debug=checkdoc -d-debug=summary -of=./bin/sdp${VER} ./lib/sdp${VER}/sdp.d
+
+VER='2' && ldc2 -unittest -d-debug=summary -of=./bin/sdp${VER} lib/sdp${VER}/sdp.d
+VER='2' && ldc2 -d-debug=checkdoc -d-debug=summary -of=./bin/sdp${VER} lib/sdp${VER}/sdp.d
+VER='2' && ldc2 -d-debug=checkdoc -d-debug=summary -of=./bin/sdp${VER} lib/sdp${VER}/sdp.d
+
+VER='sdp2' && ldc2 -d-debug=objects -d-debug=summary -of=./bin/${VER} lib/${VER}/sdp.d
+
+VER='sdp0'
+VER='sdp1'
+VER='sdp2'
+VER='sdp3'
+VER='sdp'
+ldc2 -d-debug -of=./bin/sisu_${VER} lib/${VER}/sdp.d
+ldc2 -d-debug -of=./bin/sisu_${VER} lib/${VER}/sdp.d
+ldc2 -d-debug=heading -of=./bin/sisu_${VER} lib/${VER}/sdp.d
+ldc2 -d-debug=objects -of=./bin/sisu_${VER} lib/${VER}/sdp.d
+
+VER='sdp2' && ldc2 -d-debug=objects -d-debug=summary -of=./bin/sdp lib/${VER}/sdp.d
+
+**** remove later
+binbuild="sdp1"; ldc2 -d-debug ./${binbuild}.d && time ./${binbuild} markup/test0.sst
+binbuild="sdp1"; gdc -fdebug -o ./${binbuild} ./${binbuild}.d && time ./${binbuild} markup/test0.sst
+
+binbuild="sdp2"
+ldc2 -release ./${binbuild}.d && time ./${binbuild} markup/test0.sst
+
+#cd lib
+#ldc2 -d-debug -of=../bin/sdp0 sdp/sdp.d
+
+*** gdc :gdc:
+ http://wiki.dlang.org/GDC/Using_GDC
+copy/symlink deps, and then "*.d **/*.d"
+
+gdc -o ./bin/sdp0 lib/sdp.d
+VER='sdp2' &&
+gdc -o ./bin/${VER} lib/${VER}/sdp.d
+
+VER='sdp2' && gdc-5 -o ./bin/${VER} ./lib/${VER}/sdp.d
+
+VER='sdp2' && gdc-5 -o ./bin/${VER} ./lib/${VER}/sdp.d ./lib/${VER}/*.d
+
+# VER='sdp2' && gdc -o -d-debug=objects -d-debug=summary -of=./bin/${VER} lib/${VER}/sdp.d
+
+# check flags
+# VER='sdp2' && gdc-5 -I. -O3 -fPIC -c -o ./bin/${VER} ./lib/${VER}/sdp.d
+
+**** remove later
+binbuild="sdp1"
+ldc2 -d-debug ${binbuild}.d && time ${binbuild} markup/test0.sst
+gdc -fdebug -o ${binbuild} ${binbuild}.d && time ${binbuild} markup/test0.sst
+
+**** bug
+
+http://forum.dlang.org/thread/mailman.284.1442659522.22025.digitalmars-d-learn@puremagic.com?page=3
+
+http://www.mail-archive.com/digitalmars-d-learn@puremagic.com/msg61467.html
+
+??
+https://github.com/Dicebot/Arch-PKGBUILDs/blob/master/gdc/folders.diff
+from
+https://www.mail-archive.com/d.gnu@puremagic.com/msg03844.html
+
+https://www.mail-archive.com/digitalmars-d-learn@puremagic.com/msg61470.html
+
+*** run :run:
+
+sdp0 markup/test0.sst
+
+~utils/d/bin/sdp0 filename.sst
+~utils/d/bin/sdp1 filename.sst
+
+cd markup
+sdp0 test0.sst
+
+*** compile notes
+**** ldc
+import path[0] = /usr/include/d/ldc
+import path[1] = /usr/include/d
+**** gdc
+gdmd -help
+import path[0] = /usr/include/d/4.9/x86_64-linux-gnu
+import path[1] = /usr/include/d/4.9
+**** dmd (non-free) install arch?
+**** issues
+
+** notes :notes:
+**** read file
+char[][] markup_sourcefile_content = split(cast(char[])read(fn_src), rgx_line_delimiter);
+char[][] markup_sourcefile_content = markupSourceLineArray(markupSourceString(fn_src));
+*** build
+
+*** book index
+// http://forum.dlang.org/post/k8of07$1bgu$1@digitalmars.com
+// http://forum.dlang.org/post/dfyowpjhdaemhxhepfmk@forum.dlang.org
+ // recast ---
+ // ocns ; sub ; main
+ string[][string][string] bookindex;
+ // as ---
+ // ocns ; sub ; main
+ string[]string[][string][] bookindex_the;
+ // with sorted main & sub
+
+// gdc -release -o ./${binbuild} ./${binbuild}.d && time ./${binbuild} markup/test0.sst
+
+// vim ./lib/sdp2/sisu_*.d
+// vim **/sdp2/sisu_*.d
+
+// emacs **/sdp2/sisu_*.d &
+// emacs ./lib/sdp2/sisu_*.d &
+
+// VER='2' && ldc2 -unittest -d-debug=insert -d-debug=objects -d-debug=headings -d-debug=summary -d-debug=checkdoc -d-debug=subheader -of=./bin/sdp${VER} lib/sdp${VER}/sdp.d
+
+** bugs :bugs:
+ok
+time ~dlang/bin/sdp2 --html --no-assert en/[a-eg-z]*
+not ok
+time ~dlang/bin/sdp2 --html --no-assert en/free_for_all.peter_wayner.sst en/gpl3.fsf.sst
+works if:
+ poems removed from gpl3;
+ biblio removed from free for all
+time ~dlang/bin/sdp2 --html --no-assert en/free_for_all.peter_wayner.sst en/gpl2.fsf.sst en/gpl3.fsf.sst
+time ~dlang/bin/sdp2 --html --no-assert en/[fg]*
+time ~dlang/bin/sdp2 --html --no-assert en/[a-z]*
+leaving out free_for_all seems to make it ok
+time ~dlang/bin/sdp2 --html --no-assert en/[a-eg-z]*
+leaving out any two bibliography entries within free_for_all appears to fix the problem!
+
+works in dmd not in ldc2
+
+**** Error in `/home/ralph/grotto/repo/git.repo/utils/d/bin/sdp2': corrupted double-linked list: 0x00000008b905b310 ***
+in free_for_all bibliography first instance FatBrain ref
+gets stuck after:
+en/free_for_all.peter_wayner.sst
+** desc :desc:
+*** process files
+.sst (text) regular
+.ssm (master) contains either .sst or .ssi
+.ssi (insert) processed within .ssm (or called into a .ssm by another .ssi)
+*** header
+**** metadata
+**** make (@make:)
+cover_image
+home_button_image
+home_button_text
+footer
+headings
+num_top
+breaks
+substitute
+bold
+italics
+emphasis
+texpdf_font
+css
+
+*** structure
+document structure is determined by headings of different levels
+headings must either
+(a) be explicitly marked as such, or
+(b) given by a regex (in the appropriate make header) that allows the program determine headings within text
+types of heading:
+**** document separators (A-D)
+level A is the title
+**** text headings (1-4)
+**** header make heading regex
+***** heading levels
+****** markup level [A-D1-4]
+****** markup level numbers [0-7] or [1-8]
+****** collapsed level numbers [0-7] or [1-8]
+****** nodes
+****** json search segments? chapter equivalent, decide
+***** switches, ocn on off (dummy header)
+*** object attributes
+types of object:
+**** headings (document structure objects)
+***** level
+***** segment name
+***** numbering
+**** paragraphs
+**** blocks
+types of block object:
+***** group
+***** block
+***** poem (verse)
+***** code
+***** table
+***** quote
+***** TODO alt?
+*** paragraph attributes
+types of paragraph attribute:
+**** indent
+***** paragraph (1 - 9)
+***** first line level (1 - 9), & subsequent text level (1 - 9)
+indent (first, rest), bullet
+**** bullets
+*** inline text (paragraph) attributes
+bold, italics, emphasis, superscript, substcript, strike, add, monospace, footnote (number them)
+types of text (within paragraph) attribute:
+**** bold
+**** italics
+**** emphasis
+**** underscore
+**** strike
+**** superscript
+**** subscript
+**** ...
+** package
+*** dub
+ against dub:
+ http://forum.dlang.org/post/hmdyrzbbhbcgqwqznqwz@forum.dlang.org
generated by cgit v1.2.3 (git 2.25.1) at 2025-10-31 09:25:55 +0000