0.5.0 per object inline munging (rather than by line)

- munging per object for inline markup
  fontface, links, urls, images, footnotes/endnotes
  (also book index)

3 files changed, 103 insertions, 87 deletions

diff --git a/org/default_regex.org b/org/default_regex.org
index 170b74f..b20c564 100644
--- a/org/default_regex.org
+++ b/org/default_regex.org
@@ -280,11 +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))(?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_mod_image_without_dimensions               = ctRegex!(`[{┥](?:~\^\s+|\s*)☼\S+\.(?:png|gif|jpg),w0h0.*[}┝](?: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:
@@ -293,7 +293,7 @@ static smid_mod_image_without_dimensions               = ctRegex!(`[{┥](?:~\^\
 #+BEGIN_SRC d
 /+ inline markup book index +/
 static book_index                                     = ctRegex!(`^=\{\s*(.+?)\}$`, "m");
-static book_index_open                                = ctRegex!(`^=\{\s*([^}]+?)$`);
+static book_index_open                                = ctRegex!(`^=\{\s*([^}]*?)$`);
 static book_index_close                               = ctRegex!(`^(.*?)\}$`, "m");
 #+END_SRC
 
diff --git a/org/doc_reform.org b/org/doc_reform.org
index c47d00c..d7ea680 100644
--- a/org/doc_reform.org
+++ b/org/doc_reform.org
@@ -26,7 +26,7 @@ struct Version {
   int minor;
   int patch;
 }
-enum _ver = Version(0, 4, 3);
+enum _ver = Version(0, 5, 0);
 #+END_SRC
 
 ** compilation restrictions (supported compilers)
diff --git a/org/meta_abstraction.org b/org/meta_abstraction.org
index 98f76ec..6ea5d5d 100644
--- a/org/meta_abstraction.org
+++ b/org/meta_abstraction.org
@@ -422,6 +422,46 @@ static auto inline_markup_faces(L)(L line) {
   }
   return line;
 }
+static auto links_and_images(L)(L obj_txt) {
+  static auto rgx = Rgx();
+  static auto mkup = InlineMarkup();
+  if (obj_txt.match(rgx.smid_inline_url_generic)) {
+    if (
+      obj_txt.match(rgx.smid_inline_link_endnote_url_helper)
+      || obj_txt.match(rgx.smid_inline_link_endnote_url_helper_punctuated)
+    ) {
+      obj_txt = replaceAll!(m => format("%s%s%s%s%s%s%s %s%s%s%s%s%s %s%s",
+        mkup.lnk_o, m[1].strip, mkup.lnk_c,
+        mkup.url_o, m[2], mkup.url_c,
+        mkup.en_a_o,
+        mkup.lnk_o, m[2].strip, mkup.lnk_c,
+        mkup.url_o, m[2], mkup.url_c,
+        mkup.en_a_c,
+        m[3]
+      ))(obj_txt, rgx.smid_inline_link_endnote_url_helper_punctuated);
+      obj_txt = replaceAll!(m => format("%s%s%s%s%s%s%s %s%s%s%s%s%s %s",
+        mkup.lnk_o, m[1].strip, mkup.lnk_c,
+        mkup.url_o, m[2], mkup.url_c,
+        mkup.en_a_o,
+        mkup.lnk_o, m[2].strip, mkup.lnk_c,
+        mkup.url_o, m[2], mkup.url_c,
+        mkup.en_a_c
+      ))(obj_txt, rgx.smid_inline_link_endnote_url_helper);
+  } else {
+      obj_txt = replaceAll!(m => format("%s%s%s%s%s%s%s",
+        m[1],
+        mkup.lnk_o, m[2].strip, mkup.lnk_c,
+        mkup.url_o, m[3], mkup.url_c
+      ))(obj_txt, rgx.smid_inline_link_markup_regular);
+    }
+      obj_txt = replaceAll!(m => format("%s%s%s%s%s%s%s",
+        m[1],
+        mkup.lnk_o, m[2].strip, mkup.lnk_c,
+        mkup.url_o, m[2], mkup.url_c
+      ))(obj_txt, rgx.smid_inline_link_naked_url); //
+  }
+  return obj_txt;
+}
 /+ book index variables +/
 string book_idx_tmp;
 string[][string][string] bookindex_unordered_hashes;
@@ -672,7 +712,13 @@ line = line.inline_markup_faces; // by text line (rather than by text object), l
 
 #+name: abs_in_loop_body_non_code_obj
 #+BEGIN_SRC d
-if (line.matchFirst(rgx.heading_biblio)
+if ((line.matchFirst(rgx.heading_biblio)
+  && obj_type_status["para"]  != State.on
+  && obj_type_status["group"] != State.on
+  && obj_type_status["block"] != State.on
+  && obj_type_status["poem"]  != State.on
+  && obj_type_status["table"] != State.on
+  && obj_type_status["quote"] != State.on)
 || (obj_type_status["biblio_section"] == State.on
 && (!(line.matchFirst(rgx.heading_blurb_glossary)))
 && (!(line.matchFirst(rgx.heading)))
@@ -702,7 +748,13 @@ if there is a glossary section you need to:
 
 #+name: abs_in_loop_body_non_code_obj
 #+BEGIN_SRC d
-} else if (line.matchFirst(rgx.heading_glossary)
+} else if ((line.matchFirst(rgx.heading_glossary)
+  && obj_type_status["para"]  != State.on
+  && obj_type_status["group"] != State.on
+  && obj_type_status["block"] != State.on
+  && obj_type_status["poem"]  != State.on
+  && obj_type_status["table"] != State.on
+  && obj_type_status["quote"] != State.on)
 || (obj_type_status["glossary_section"] == State.on
 && (!(line.matchFirst(rgx.heading_biblio_blurb)))
 && (!(line.matchFirst(rgx.heading)))
@@ -803,7 +855,13 @@ if there is a blurb section you need to:
 
 #+name: abs_in_loop_body_non_code_obj
 #+BEGIN_SRC d
-} else if (line.matchFirst(rgx.heading_blurb)
+} else if ((line.matchFirst(rgx.heading_blurb)
+  && obj_type_status["para"]  != State.on
+  && obj_type_status["group"] != State.on
+  && obj_type_status["block"] != State.on
+  && obj_type_status["poem"]  != State.on
+  && obj_type_status["table"] != State.on
+  && obj_type_status["quote"] != State.on)
 || (obj_type_status["blurb_section"] == State.on
 && (!(line.matchFirst(rgx.heading_biblio_glossary)))
 && (!(line.matchFirst(rgx.heading)))
@@ -929,7 +987,7 @@ if there is a blurb section you need to:
       comp_obj_para.metainfo.is_of_section        = "blurb";
       comp_obj_para.metainfo.is_of_type           = "para";
       comp_obj_para.metainfo.is_a                 = "blurb";
-      comp_obj_para.text                          = munge.url_links(line.to!string.strip).replaceFirst(rgx.para_attribs, "");
+      comp_obj_para.text                          = links_and_images(line.to!string.strip).replaceFirst(rgx.para_attribs, "");
       comp_obj_para.metainfo.ocn                  = 0;
       comp_obj_para.metainfo.identifier           = "";
       comp_obj_para.metainfo.object_number_off    = true;
@@ -1430,7 +1488,6 @@ 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) {
@@ -1758,7 +1815,7 @@ if (the_endnotes_section.length > 1) {
     "Endnotes",
     "endnotes",
   );
-  toc_txt_= munge.url_links(toc_txt_);
+  toc_txt_= toc_txt_.links_and_images;
   comp_obj_toc.text                       = toc_txt_.to!string.strip;
   comp_obj_toc.has.inline_links           = true;
   the_table_of_contents_section           ~= comp_obj_toc;
@@ -1769,7 +1826,7 @@ if (the_glossary_section.length > 1) {
     "Glossary",
     "glossary",
   );
-  toc_txt_= munge.url_links(toc_txt_);
+  toc_txt_= toc_txt_.links_and_images;
   comp_obj_toc.text                       = toc_txt_.to!string.strip;
   comp_obj_toc.has.inline_links           = true;
   the_table_of_contents_section           ~= comp_obj_toc;
@@ -1780,7 +1837,7 @@ if (the_bibliography_section.length > 1){
     "Bibliography",
     "bibliography",
   );
-  toc_txt_= munge.url_links(toc_txt_);
+  toc_txt_= toc_txt_.links_and_images;
   comp_obj_toc.text                       = toc_txt_.to!string.strip;
   comp_obj_toc.has.inline_links           = true;
   the_table_of_contents_section           ~= comp_obj_toc;
@@ -1791,7 +1848,7 @@ if (the_bookindex_section.length > 1) {
     "Book Index",
     "bookindex",
   );
-  toc_txt_= munge.url_links(toc_txt_);
+  toc_txt_= toc_txt_.links_and_images;
   comp_obj_toc.text                       = toc_txt_.to!string.strip;
   comp_obj_toc.has.inline_links           = true;
   the_table_of_contents_section           ~= comp_obj_toc;
@@ -1802,7 +1859,7 @@ if (the_blurb_section.length > 1) {
     "Blurb",
     "blurb",
   );
-  toc_txt_= munge.url_links(toc_txt_);
+  toc_txt_= toc_txt_.links_and_images;
   comp_obj_toc.has.inline_links           = true;
   comp_obj_toc.text                       = toc_txt_.to!string.strip;
   the_table_of_contents_section           ~= comp_obj_toc;
@@ -2297,7 +2354,13 @@ auto _image_dimensions(O,M)(O obj, M manifest_matter) {
       }
       obj.text = obj.text.replaceFirst(
         rgx.inline_image_without_dimensions,
-        ("$1☼$3,w" ~ _w.to!string ~ "h" ~ _h.to!string ~ " $6")
+        format(q"┋%s☼%s,w%sh%s %s┋",
+          "$1",
+          "$3",
+          _w.to!string,
+          _h.to!string,
+          "$6",
+        )
       );
     }
     debug(images) {
@@ -3528,7 +3591,13 @@ void _biblio_block_(
   mixin DocReformBiblio;
   auto jsn = BibJsnStr();
   static auto rgx = Rgx();
-  if (line.matchFirst(rgx.heading_biblio)) {
+  if (line.matchFirst(rgx.heading_biblio)
+      && obj_type_status["para"]  != State.on
+      && obj_type_status["group"] != State.on
+      && obj_type_status["block"] != State.on
+      && obj_type_status["poem"]  != State.on
+      && obj_type_status["table"] != State.on
+      && obj_type_status["quote"] != State.on) {
     obj_type_status["biblio_section"]   = TriState.on;
     obj_type_status["blurb_section"]    = State.off;
     obj_type_status["glossary_section"] = State.off;
@@ -5331,68 +5400,6 @@ static struct ObjInlineMarkupMunge {
   }
 #+END_SRC
 
-******* url links including images
-
-#+name: meta_emitters_obj_inline_markup_munge
-#+BEGIN_SRC d
-  static auto url_links(Ot)(Ot obj_txt_in) {
-    debug(asserts) {
-      static assert(is(typeof(obj_txt_in) == string));
-    }
-    /+ url matched +/
-    obj_txt_in = obj_txt_in.replaceAll(rgx.inline_notes_al_special, ""); // TODO reinstate when special footnotes are implemented
-    if (obj_txt_in.match(rgx.smid_inline_url_generic)) {
-      /+ link: naked url: http://url +/
-      if (obj_txt_in.match(rgx.smid_inline_link_naked_url)) {
-        obj_txt_in = obj_txt_in.replaceAll(
-            rgx.smid_inline_link_naked_url,
-            ("$1"
-              ~ mkup.lnk_o ~ "$2" ~ mkup.lnk_c
-              ~  mkup.url_o ~ "$2" ~  mkup.url_c
-            ) // ("$1{ $2 }$2$3")
-          );
-      }
-      /+ link with helper for endnote including the url:
-           {~^ link which includes url as footnote }http://url
-         maps to:
-           { link which includes url as footnote }http://url~{ { http://url }http://url }~
-      +/
-      if (obj_txt_in.match(rgx.smid_inline_link_endnote_url_helper)) {
-        obj_txt_in = obj_txt_in
-          .replaceAll(
-            rgx.smid_inline_link_endnote_url_helper_punctuated,
-            (mkup.lnk_o ~ "$1" ~ mkup.lnk_c
-              ~ mkup.url_o ~ "$2" ~ mkup.url_c
-              ~ "~{ " ~ mkup.lnk_o ~ " $2 " ~ mkup.lnk_c
-              ~ mkup.url_o ~ "$2" ~ mkup.url_c
-              ~  " }~$3") // ("{ $1 }$2~{ { $2 }$2 }~$3")
-          )
-          .replaceAll(
-            rgx.smid_inline_link_endnote_url_helper,
-            (mkup.lnk_o ~ "$1" ~ mkup.lnk_c
-              ~ mkup.url_o ~ "$2" ~ mkup.url_c
-              ~ "~{ " ~ mkup.lnk_o ~ " $2 " ~ mkup.lnk_c
-              ~ mkup.url_o ~ "$2" ~ mkup.url_c
-              ~  " }~") // ("{ $1 }$2~{ { $2 }$2 }~")
-          );
-      }
-      /+ link with regular markup:
-         { linked text or image }http://url
-      +/
-      if (obj_txt_in.match(rgx.smid_inline_link_markup_regular)) {
-        obj_txt_in = obj_txt_in.replaceAll(
-          rgx.smid_inline_link_markup_regular,
-          ("$1"
-            ~ mkup.lnk_o ~ "$2" ~ mkup.lnk_c
-            ~  mkup.url_o ~ "$3" ~  mkup.url_c
-          ) // ("$1{ $2 }$3$4")
-        );
-      }
-    }
-    return obj_txt_in;
-  }
-#+END_SRC
-
 #+name: meta_emitters_obj_inline_markup_munge
 #+BEGIN_SRC d
   static auto images(Ot)(Ot obj_txt_in) {
@@ -5417,7 +5424,7 @@ static struct ObjInlineMarkupMunge {
         }
       } 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"))
+          .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));
@@ -5538,7 +5545,7 @@ static struct ObjInlineMarkupMunge {
     /+ url matched +/
     if (obj_txt_in.match(rgx.smid_inline_url)) {
       urls = true;
-      obj_txt_in = url_links(obj_txt_in);
+      obj_txt_in = obj_txt_in.links_and_images;
     }
     if (auto m = obj_txt_in.match(rgx.para_inline_link_anchor)) {
       obj_txt_in = obj_txt_in
@@ -5842,6 +5849,15 @@ static struct ObjInlineMarkup {
     obj_notes_and_links["notes_star"]          = false;
     obj_notes_and_links["links"]               = false;
     obj_notes_and_links["image_no_dimensions"] = false;
+    if ((obj_["is"] == "para")
+      || (obj_["is"] == "heading")
+      || (obj_["is"] == "quote")
+      || (obj_["is"] == "group")
+      || (obj_["is"] == "block")
+      || (obj_["is"] == "verse")) {
+      obj_txt["munge"] = (obj_txt["munge"]).inline_markup_faces;
+      obj_txt["munge"] = (obj_txt["munge"]).links_and_images;
+    }
     switch (obj_["is"]) {
     case "heading":
       if (_new_doc) {
@@ -5961,7 +5977,7 @@ static struct ObjInlineMarkup {
         heading_toc_,
         _anchor_tag,
       );
-      toc_txt_= munge.url_links(toc_txt_);
+      toc_txt_= toc_txt_.links_and_images;
       comp_obj_toc                             = comp_obj_toc.init;
       comp_obj_toc.metainfo.is_of_part         = "frontmatter";
       comp_obj_toc.metainfo.is_of_section      = "toc";
@@ -6022,7 +6038,7 @@ static struct ObjInlineMarkup {
         _anchor_tag,
       );
       lev4_subtoc[tag_in_seg["seg_lv4"]]
-      ~= munge.url_links(obj_["lev_markup_number"]
+      ~= links_and_images(obj_["lev_markup_number"]
            ~ "~ " ~ subtoc_txt_.to!string.strip
          );
       break;
@@ -6869,7 +6885,7 @@ struct BookIndexReportSection {
           string markup = "";
           if (auto m = locs.matchFirst(rgx.book_index_go)) {
             markup
-              = munge.url_links("{ " ~ m["link"] ~ " }"
+              = links_and_images("{ " ~ m["link"] ~ " }"
               ~ "#" ~ m["ocn"] ~ ", ");
           } else {
             writeln(__LINE__, ": ", locs);
@@ -6994,12 +7010,12 @@ struct NotesSection {
       // you need anchor for segments at this point ->
       object_notes["anchor"] ~= "note_" ~ m.captures[1] ~ "』";
       object_notes["notes"]  ~= (tag_in_seg["seg_lv4"].empty)
-      ? (munge.url_links(
+      ? (links_and_images(
           "{" ~ mkup.superscript  ~ mkup.ff_o ~ m.captures[1] ~ "." ~ mkup.ff_c  ~ mkup.superscript  ~ "}#noteref_"
           ~ m.captures[1]) ~ " "
           ~ m.captures[2] ~ "』"
         )
-      : (munge.url_links(
+      : (links_and_images(
           "{" ~ mkup.superscript ~ mkup.ff_o ~ m.captures[1] ~ "." ~ mkup.ff_c  ~ mkup.superscript ~ "}"
            ~ mkup.mark_internal_site_lnk
            ~ tag_in_seg["seg_lv4"]