metaverse single line munging tuningdoc-reform_v0.4.3

5 files changed, 75 insertions, 42 deletions

diff --git a/org/default_misc.org b/org/default_misc.org
index a811b91..320021e 100644
--- a/org/default_misc.org
+++ b/org/default_misc.org
@@ -249,6 +249,8 @@ template InternalMarkup() {
     auto tc_c                   = "┚";
     auto tc_p                   = "┆";
     auto img                    = "☼";
+    auto on_o  = "「";       auto on_c  = "」";
+    auto mk_bullet               = "● ";
     static string indent_by_spaces_provided(int indent, string _indent_spaces ="░░") {
       _indent_spaces = replicate(_indent_spaces, indent);
       return _indent_spaces;
diff --git a/org/default_regex.org b/org/default_regex.org
index 2af9ed2..170b74f 100644
--- a/org/default_regex.org
+++ b/org/default_regex.org
@@ -52,7 +52,7 @@ static template DocReformRgxInit() {
 static true_dollar                                    = ctRegex!(`\$`, "gm");
 static flag_action                                    = ctRegex!(`^(--[a-z][a-z0-9-]+)$`);
 static flag_action_str                                = ctRegex!(` (--[a-z][a-z0-9-]+)`);
-static within_quotes                                  = ctRegex!(`"(.+?)"`);
+static within_quotes                                  = ctRegex!(`"(.+?)"`, "m");
 static make_heading_delimiter                         = ctRegex!(`[;][ ]*`);
 static arr_delimiter                                  = ctRegex!(`[ ]*[;][ ]*`);
 static name_delimiter                                 = ctRegex!(`^([^,]+)[ ]*,[ ]+(.+?)$`);
@@ -280,10 +280,11 @@ static smid_inline_link_endnote_url_helper            = ctRegex!(`\{~\^\s+(?P<co
 #+name: meta_rgx
 #+BEGIN_SRC d
 static image                                           = ctRegex!(`([a-zA-Z0-9._-]+?\.(?:png|gif|jpg))`, "mg");
+static smid_image                                      = ctRegex!(`(?P<pre>(?:^|[ ]|[^\S]?)\{(?:~\^\s+|\s*))(?P<image>\S+\.(?:png|gif|jpg))\s*(?P<post>(?:.+?)\s*\}(?:image|(?:(?:https?|git):\/\/|¤?\.\.\/|¤?\.\/|¤|#)\S+?)(?=[;:!,?.]?([ )\]]|$)))`, "mg");
 static smid_image_generic                              = ctRegex!(`(?:^|[ ]|[^\S]?)\{(?:~\^\s+|\s*)\S+\.(?:png|gif|jpg).+?\}(?:image|(?:(?:https?|git):\/\/|¤?\.\.\/|¤?\.\/|¤|#)\S+?)(?=[;:!,?.]?([ )\]]|$))`, "mg");
 static smid_image_with_dimensions                      = ctRegex!(`(?P<pre>(?:^|[ ]|[^\S]?)\{(?:~\^\s+|\s*))(?P<image>\S+\.(?:png|gif|jpg))\s+(?P<width>\d+)x(?P<height>\d+)\s*(?P<post>(?:.+?)\s*\}(?:image|(?:(?:https?|git):\/\/|¤?\.\.\/|¤?\.\/|¤|#)\S+?)(?=[;:!,?.]?([ )\]]|$)))`, "mg");
-static smid_image                                      = ctRegex!(`(?P<pre>(?:^|[ ]|[^\S]?)\{(?:~\^\s+|\s*))(?P<image>\S+\.(?:png|gif|jpg))\s*(?P<post>(?:.+?)\s*\}(?:image|(?:(?:https?|git):\/\/|¤?\.\.\/|¤?\.\/|¤|#)\S+?)(?=[;:!,?.]?([ )\]]|$)))`, "mg");
-static smid_mod_image_without_dimensions               = ctRegex!(`\{(?:~\^\s+|\s*)☼\S+\.(?:png|gif|jpg),w0h0\s+(?:.+?)\s*\}(?:image|(?:https?|git):\/\/\S+?)(?=[;:!,?.]?([ )\]]|$))`, "mg");
+static smid_image_delimit                              = ctRegex!(`(?P<pre>^|[ ]|[^\S]?)\{\s*(?P<text>.+?)\s*\}(?:image)(?=[;:!,?.]?([ )\]]|$))`, "mg");
+static smid_mod_image_without_dimensions               = ctRegex!(`[{┥](?:~\^\s+|\s*)☼\S+\.(?:png|gif|jpg),w0h0\s+(?:.+?)\s*[}┝](?:image|(?:https?|git):\/\/\S+?)(?=[;:!,?.]?([ )\]]|$))`, "mg");
 #+END_SRC
 
 *** inline markup book index                             :inline:bookindex:
@@ -407,11 +408,11 @@ static template DocReformOutputRgxInit() {
 
 #+name: sp_ch_xhtml_rgx
 #+BEGIN_SRC d
-static xhtml_ampersand                            = ctRegex!(`[&]`);      // &amp;
-static xhtml_quotation                            = ctRegex!(`["]`);      // &quot;
-static xhtml_less_than                            = ctRegex!(`[<]`);      // &lt;
-static xhtml_greater_than                         = ctRegex!(`[>]`);      // &gt;
-static xhtml_line_break                           = ctRegex!(` [\\]{2}`); // <br />
+static xhtml_ampersand                            = ctRegex!(`[&]`, "m");      // &amp;
+static xhtml_quotation                            = ctRegex!(`["]`, "m");      // &quot;
+static xhtml_less_than                            = ctRegex!(`[<]`, "m");      // &lt;
+static xhtml_greater_than                         = ctRegex!(`[>]`, "m");      // &gt;
+static xhtml_line_break                           = ctRegex!(` [\\]{2}`, "m"); // <br />
 #+END_SRC
 
 * 2. ctRegex defaults shared by meta & output (generic)
@@ -502,10 +503,13 @@ static inline_text_and_note_al_                       = ctRegex!(`(.+?(?:【[*+]
 #+name: prgmkup_rgx
 #+BEGIN_SRC d
 /+ inline markup footnotes endnotes +/
-static inline_image                                   = ctRegex!(`(?P<pre>┥)☼(?P<imginf>(?P<img>\S+?\.(?:jpg|gif|png)),w(?P<width>\d+)h(?P<height>\d+))\s*(?P<post>.*?┝┤.+?├)`, "mg");
-static inline_image_without_dimensions                = ctRegex!(`(?P<pre>┥)☼(?P<imginf>(?P<img>\S+?\.(?:jpg|gif|png)),w(?P<width>0)h(?P<height>0))\s*(?P<post>.*?┝┤.+?├)`, "mg");
-static inline_link_anchor                             = ctRegex!(`┋(?P<anchor>\S+?)┋`, "mg");
+static inline_image                                   = ctRegex!(`(?P<pre>┥)☼(?P<imginf>(?P<img>\S+?\.(?:jpg|gif|png)),w(?P<width>\d+)h(?P<height>\d+))\s*(?P<post>.*?┝┤.*?├)`, "mg");
+static inline_image_without_dimensions                = ctRegex!(`(?P<pre>┥)☼(?P<imginf>(?P<img>\S+?\.(?:jpg|gif|png)),w(?P<width>0)h(?P<height>0))\s*(?P<post>.*?┝┤.*?├)`, "mg");
+static inline_link_anchor                             = ctRegex!(`┋(?P<anchor>\S+?)┋`, "mg"); // TODO *~text_link_anchor
+static inline_link_                                   = ctRegex!(`┥(?P<text>.+?)┝┤(?P<link>.+?)├`, "mg");
 static inline_link                                    = ctRegex!(`┥(?P<text>.+?)┝┤(?P<link>\S+?)├`, "mg");
+static inline_link_empty                              = ctRegex!(`┥(?P<text>.+?)┝┤├`, "mg");
+static inline_link_number                             = ctRegex!(`┥(?P<text>.+?)┝┤(?P<num>[0-9]+)├`, "mg"); // not used
 static inline_link_number_only                        = ctRegex!(`(┥.+?┝)┤(?P<num>[0-9]+)├`, "mg");
 static inline_link_stow_uri                           = ctRegex!(`┥(?P<text>.+?)┝┤(?P<link>[^ 0-9#┥┝┤├][^ 0-9┥┝┤├]+)├`, "mg"); // will not stow (stowed links) or object number internal links
 static inline_link_hash                               = ctRegex!(`┥(?P<text>.+?)┝┤(?P<link>#(?P<segname>\S+?))├`, "mg");
diff --git a/org/meta_abstraction.org b/org/meta_abstraction.org
index bf67dcc..98f76ec 100644
--- a/org/meta_abstraction.org
+++ b/org/meta_abstraction.org
@@ -659,7 +659,7 @@ line._code_block_(an_object, obj_type_status);
 continue;
 #+END_SRC
 
-**** _non code objects_ (other blocks or regular text) [+4]     :non_code:
+**** _non code objects_ (non-code blocks & regular text: by line) [+4] :non_code:
 ***** inline fontface markup
 
 #+name: abs_in_loop_body_non_code_obj
@@ -1411,7 +1411,7 @@ if ((obj_type_status["heading"] == State.on)
 }
 #+END_SRC
 
-*** regular text objects                                   :text:paragraph:
+*** regular _text objects_ identified                        :text:paragraph:
 
 #+name: abs_in_loop_body_01
 #+BEGIN_SRC d
@@ -1430,6 +1430,7 @@ if (the_document_body_section.length > 0) {
       obj_type_status["glossary_section"] = State.off;
       obj_type_status["blurb_section"]    = State.off;
     }
+    the_document_body_section[$-1].text = (the_document_body_section[$-1].text).inline_markup_faces;
     if (the_document_body_section[$-1].metainfo.is_a == "verse") {
       /+ scan for endnotes for whole poem (each verse in poem) +/
       foreach (i; previous_length .. the_document_body_section.length) {
@@ -1753,7 +1754,7 @@ comp_obj_toc.attrib.indent_base            = indent["base_position"];
 comp_obj_toc.attrib.bullet                 = false;
 if (the_endnotes_section.length > 1) {
   toc_txt_ = format(
-    mkup.lnk_o ~ " %s " ~ mkup.lnk_c ~  mkup.url_o ~ "#%s"~  mkup.url_c,
+    mkup.lnk_o ~ "%s" ~ mkup.lnk_c ~  mkup.url_o ~ "#%s"~  mkup.url_c,
     "Endnotes",
     "endnotes",
   );
@@ -1764,7 +1765,7 @@ if (the_endnotes_section.length > 1) {
 }
 if (the_glossary_section.length > 1) {
   toc_txt_ = format(
-    mkup.lnk_o ~ " %s " ~ mkup.lnk_c ~  mkup.url_o ~ "#%s"~  mkup.url_c,
+    mkup.lnk_o ~ "%s" ~ mkup.lnk_c ~  mkup.url_o ~ "#%s"~  mkup.url_c,
     "Glossary",
     "glossary",
   );
@@ -1775,7 +1776,7 @@ if (the_glossary_section.length > 1) {
 }
 if (the_bibliography_section.length > 1){
   toc_txt_ = format(
-    mkup.lnk_o ~ " %s " ~ mkup.lnk_c ~  mkup.url_o ~ "#%s"~  mkup.url_c,
+    mkup.lnk_o ~ "%s" ~ mkup.lnk_c ~  mkup.url_o ~ "#%s"~  mkup.url_c,
     "Bibliography",
     "bibliography",
   );
@@ -1786,7 +1787,7 @@ if (the_bibliography_section.length > 1){
 }
 if (the_bookindex_section.length > 1) {
   toc_txt_ = format(
-    mkup.lnk_o ~ " %s " ~ mkup.lnk_c ~  mkup.url_o ~ "#%s"~  mkup.url_c,
+    mkup.lnk_o ~ "%s" ~ mkup.lnk_c ~  mkup.url_o ~ "#%s"~  mkup.url_c,
     "Book Index",
     "bookindex",
   );
@@ -1797,7 +1798,7 @@ if (the_bookindex_section.length > 1) {
 }
 if (the_blurb_section.length > 1) {
   toc_txt_ = format(
-    mkup.lnk_o ~ " %s " ~ mkup.lnk_c ~  mkup.url_o ~ "#%s"~  mkup.url_c,
+    mkup.lnk_o ~ "%s" ~ mkup.lnk_c ~  mkup.url_o ~ "#%s"~  mkup.url_c,
     "Blurb",
     "blurb",
   );
@@ -2427,9 +2428,6 @@ if (the_document_body_section.length > 1) {
       tag_assoc[(obj.metainfo.identifier)]["seg_lv1_to_4"]
       = obj.tags.epub_segment_anchor_tag_is;
     }
-    if (obj.metainfo.is_a != "code") {
-      obj.text = obj.text.inline_markup_faces;
-    }
     if (obj.metainfo.is_a == "heading") {
       debug(dom) {
         writeln(obj.text);
@@ -2480,7 +2478,6 @@ if (the_endnotes_section.length > 1) {
   dom_structure_markedup_tags_status         = dom_structure_markedup_tags_status_buffer.dup;
   dom_structure_collapsed_tags_status        = dom_structure_collapsed_tags_status_buffer.dup;
   foreach (ref obj; the_endnotes_section) {
-    obj.text = obj.text.inline_markup_faces;
     if (obj.metainfo.is_a == "heading") {
       debug(dom) {
         writeln(obj.text);
@@ -2680,9 +2677,6 @@ if (the_bookindex_section.length > 1) {
 /+ optional only one 1~ level +/
 if (the_blurb_section.length > 1) {
   foreach (ref obj; the_blurb_section) {
-    if (obj.metainfo.is_a != "code") {
-      obj.text = obj.text.inline_markup_faces;
-    }
     if (obj.metainfo.is_a == "heading") {
       debug(dom) {
         writeln(obj.text);
@@ -2959,7 +2953,7 @@ dom_structure_collapsed_tags_status          = [ 0, 0, 0, 0, 0, 0, 0, 0, 0,];
 dom_structure_collapsed_tags_status_buffer   = [ 0, 0, 0, 0, 0, 0, 0, 0, 0,];
 #+END_SRC
 
-*** [#A] _return document tuple_                               :return:tuple:
+*** _return document tuple_ [#A]                               :return:tuple:
 
 #+name: abs_return_tuple
 #+BEGIN_SRC d
@@ -5413,22 +5407,20 @@ static struct ObjInlineMarkupMunge {
         writeln("Image: ", obj_txt_in);
       }
       if (obj_txt_in.match(rgx.smid_image_with_dimensions)) {
-        obj_txt_in = obj_txt_in.replaceAll(
-            rgx.smid_image_with_dimensions,
-            ("$1"
-              ~ mkup.img ~ "$2,w$3h$4 "
-              ~ "$5")            // ("$1{ $2 }$2$3")
-          );
+        obj_txt_in = obj_txt_in
+          .replaceAll(rgx.smid_image_with_dimensions, ("$1" ~ mkup.img ~ "$2,w$3h$4 " ~ "$5"))
+          .replaceAll(rgx.smid_image_delimit, ("$1"
+            ~ mkup.lnk_o ~ "$2".strip ~ mkup.lnk_c
+            ~ mkup.url_o ~ mkup.url_c));
         debug(images) {
-          writeln("IMAGE with size: ", obj_txt_in); // decide on representation
+          writeln("IMAGE with size: ", obj_txt_in);
         }
       } else if (obj_txt_in.match(rgx.smid_image)) {
-        obj_txt_in = obj_txt_in.replaceAll(
-            rgx.smid_image,
-            ("$1"
-              ~ mkup.img ~ "$2,w0h0 "
-              ~ "$3")            // ("$1{ $2 }$2$3")
-          );
+        obj_txt_in = obj_txt_in
+          .replaceAll(rgx.smid_image, ("$1" ~ mkup.img ~ "$2,w0h0 " ~ "$3"))
+          .replaceAll(rgx.smid_image_delimit, ("$1"
+            ~ mkup.lnk_o ~ "$2".strip ~ mkup.lnk_c
+            ~ mkup.url_o ~ mkup.url_c));
         debug(images) {
           writeln("IMAGE: ", obj_txt_in); // decide on representation
         }
@@ -5965,7 +5957,7 @@ static struct ObjInlineMarkup {
         "base_position" : obj_["lev_markup_number"].to!int,
       ];
       toc_txt_ = format(
-        mkup.lnk_o ~ " %s " ~ mkup.lnk_c ~  mkup.url_o ~ "#%s"~  mkup.url_c,
+        mkup.lnk_o ~ "%s".strip ~ mkup.lnk_c ~  mkup.url_o ~ "#%s"~  mkup.url_c,
         heading_toc_,
         _anchor_tag,
       );
@@ -6025,7 +6017,7 @@ static struct ObjInlineMarkup {
       break;
     case 5: .. case 7:
       subtoc_txt_ = format(
-        mkup.lnk_o ~ " %s " ~ mkup.lnk_c ~  mkup.url_o ~ "#%s"~  mkup.url_c,
+        mkup.lnk_o ~ "%s".strip ~ mkup.lnk_c ~  mkup.url_o ~ "#%s"~  mkup.url_c,
         heading_toc_,
         _anchor_tag,
       );
diff --git a/org/output_sqlite.org b/org/output_sqlite.org
index 13b8702..52839d3 100644
--- a/org/output_sqlite.org
+++ b/org/output_sqlite.org
@@ -733,6 +733,10 @@ auto html_heading(M,O)(
                  M    doc_matters,
   auto ref const O    obj,
 ) {
+  assert(obj.metainfo.is_of_part    == "body" || "frontmatter" || "backmatter");
+  assert(obj.metainfo.is_of_section == "body" || "toc" || "endnotes" || "glossary" || "bibliography" || "bookindex" || "blurb");
+  assert(obj.metainfo.is_of_type    == "para");
+  assert(obj.metainfo.is_a          == "heading");
   string _txt = munge_html(doc_matters, obj);
   _txt = inline_markup(doc_matters, obj, _txt);
   string o = format(q"┋<p class="%s"><b>
@@ -775,6 +779,10 @@ auto html_para(M,O)(
                  M    doc_matters,
   auto ref const O    obj,
 ) {
+  assert(obj.metainfo.is_of_part    == "body" || "frontmatter" || "backmatter");
+  assert(obj.metainfo.is_of_section == "body" || "toc" || "endnotes" || "glossary" || "bibliography" || "bookindex" || "blurb");
+  assert(obj.metainfo.is_of_type    == "para");
+  assert(obj.metainfo.is_a          == "para" || "toc" || "endnotes" || "glossary" || "bibliography" || "bookindex" || "blurb");
   string _txt = munge_html(doc_matters, obj);
   _txt = (obj.attrib.bullet) ? ("●&#160;&#160;" ~ _txt) : _txt;
   _txt = inline_markup(doc_matters, obj, _txt);
@@ -798,6 +806,10 @@ auto html_quote(M,O)(
                  M    doc_matters,
   auto ref const O    obj,
 ) {
+  assert(obj.metainfo.is_of_part    == "body");
+  assert(obj.metainfo.is_of_section == "body" || "glossary" || "bibliography" || "bookindex" || "blurb");
+  assert(obj.metainfo.is_of_type    == "block");
+  assert(obj.metainfo.is_a          == "quote");
   string _txt = munge_html(doc_matters, obj);
   string o = format(q"┋<p class="%s">
     %s
@@ -817,6 +829,10 @@ auto html_group(M,O)(
                  M    doc_matters,
   auto ref const O    obj,
 ) {
+  assert(obj.metainfo.is_of_part    == "body");
+  assert(obj.metainfo.is_of_section == "body" || "glossary" || "bibliography" || "bookindex" || "blurb");
+  assert(obj.metainfo.is_of_type    == "block");
+  assert(obj.metainfo.is_a          == "group");
   string _txt = munge_html(doc_matters, obj);
   string o = format(q"┋<p class="%s">
     %s
@@ -836,6 +852,10 @@ auto html_block(M,O)(
                  M    doc_matters,
   auto ref const O    obj,
 ) {
+  assert(obj.metainfo.is_of_part    == "body");
+  assert(obj.metainfo.is_of_section == "body" || "glossary" || "bibliography" || "bookindex" || "blurb");
+  assert(obj.metainfo.is_of_type    == "block");
+  assert(obj.metainfo.is_a          == "block");
   string _txt = munge_html(doc_matters, obj);
   string o = format(q"┋
   <p class="%s">%s</p>┋",
@@ -854,6 +874,10 @@ auto html_verse(M,O)(
                  M    doc_matters,
   auto ref const O    obj,
 ) {
+  assert(obj.metainfo.is_of_part    == "body");
+  assert(obj.metainfo.is_of_section == "body" || "glossary" || "bibliography" || "bookindex" || "blurb");
+  assert(obj.metainfo.is_of_type    == "block");
+  assert(obj.metainfo.is_a          == "verse");
   string _txt = munge_html(doc_matters, obj);
   string o = format(q"┋<p class="%s">%s</p>┋",
       obj.metainfo.is_a,
@@ -870,6 +894,10 @@ auto html_verse(M,O)(
 auto html_code(O)(
   auto ref const O    obj,
 ) {
+  assert(obj.metainfo.is_of_part    == "body");
+  assert(obj.metainfo.is_of_section == "body");
+  assert(obj.metainfo.is_of_type    == "block");
+  assert(obj.metainfo.is_a          == "code");
   string _txt = html_special_characters_code(obj.text);
   string o = format(q"┋<p class="%s">%s</p>┋",
       obj.metainfo.is_a,
@@ -887,6 +915,10 @@ auto html_table(M,O)(
                  M    doc_matters,
   auto ref const O     obj,
 ) {
+  assert(obj.metainfo.is_of_part    == "body");
+  assert(obj.metainfo.is_of_section == "body");
+  assert(obj.metainfo.is_of_type    == "block");
+  assert(obj.metainfo.is_a          == "table");
   auto _tablarize(O)(
     auto ref const O    obj,
     string                     _txt,
diff --git a/org/output_xmls.org b/org/output_xmls.org
index 27069fd..1e4f91a 100644
--- a/org/output_xmls.org
+++ b/org/output_xmls.org
@@ -447,7 +447,10 @@ auto inline_images(O,M)(
         rgx.inline_image,
         ("$1<img src=\""
           ~ _img_pth
-          ~ "$3\" width=\"$4\" height=\"$5\" naturalsizeflag=\"0\" align=\"bottom\" border=\"0\" /> $6"));
+          ~ "$3\" width=\"$4\" height=\"$5\" naturalsizeflag=\"0\" align=\"bottom\" border=\"0\" /> $6"))
+      .replaceAll(
+        rgx.inline_link_empty,
+        ("$1"));
   }
   return _txt;
 }