text output, endnotes, add caller ocn (& some cleaning)

4 files changed, 45 insertions, 25 deletions

diff --git a/src/sisudoc/io_out/rgx.d b/src/sisudoc/io_out/rgx.d
index 666e71f..b4bec5f 100644
--- a/src/sisudoc/io_out/rgx.d
+++ b/src/sisudoc/io_out/rgx.d
@@ -88,28 +88,28 @@ static template spineRgxOut() {
     static inline_notes_al_special                  = ctRegex!(`【(?:[*+]\s+)(.+?)】`, "mg"); // TODO remove match when special footnotes are implemented
     static inline_notes_al_gen                      = ctRegex!(`【.+?】`, "m");
     static inline_notes_al_gen_text                 = ctRegex!(`【(?P<text>.+?)】`, "m");
-    static inline_notes_al_all_note                 = ctRegex!(`【(?P<num>\d+|(?:[*]|[+])+)\s+(?P<note>.+?)\s*】`, "mg");
-    static inline_notes_al_regular_number_note      = ctRegex!(`【(?P<num>\d+)\s+(?P<note>.+?)\s*】`, "mg");
-    // static inline_notes_al_all_note                 = ctRegex!(`【(?P<num>\d+|(?:[*]|[+])+)\s+(?P<note>.+?)\s*(≫\s\d+)?\s*】`, "mg"); // ocn of origin would be useful in endnote section
-    // static inline_notes_al_regular_number_note      = ctRegex!(`【(?P<num>\d+)\s+(?P<note>.+?)\s*(≫\s\d+)?\s*】`, "mg"); // ocn of origin would be useful in endnote section
+    static inline_notes_al_all_note                 = ctRegex!(`【(?P<num>\d+|(?:[*]|[+])+)\s+(?P<note>.+?)\s*(≫\s\d+)?\s*】`, "mg"); // ocn of origin would be useful in endnote section
+    static inline_notes_al_regular_number_note      = ctRegex!(`【(?P<num>\d+)\s+(?P<note>.+?)\s*(≫\s\d+)?\s*】`, "mg"); // ocn of origin would be useful in endnote section
+    // static inline_notes_al_all_note                 = ctRegex!(`【(?P<num>\d+|(?:[*]|[+])+)\s+(?P<note>.+?)\s*】`, "mg");
+    // static inline_notes_al_regular_number_note      = ctRegex!(`【(?P<num>\d+)\s+(?P<note>.+?)\s*】`, "mg");
     static inline_notes_al_special_char_note        = ctRegex!(`【(?P<char>(?:[*]|[+])+)\s+(?P<note>.+?)】`, "mg");
     static inline_al_delimiter_open_regular         = ctRegex!(`【\s`, "m");
     static inline_al_delimiter_open_symbol_star     = ctRegex!(`【[*]\s`, "m");
     static inline_al_delimiter_open_symbol_plus     = ctRegex!(`【[+]\s`, "m");
     static inline_text_and_note_al_                 = ctRegex!(`(.+?(?:【[*+]*\s+.+?】|.+))`, "mg");
+    static endnote_section_note                     = ctRegex!(`┥\s*⑆\^┨(?P<notenumber>\d+)\.┣\^┝┤(?P<link>¤?.+?)├.+`, "mg");
     /+ inline markup links +/
     static inline_image                             = ctRegex!(`(?P<pre>┥)☼(?P<imginf>(?P<img>[a-zA-Z0-9._-]+?\.(?: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>[a-zA-Z0-9._-]+?\.(?:jpg|gif|png)),w(?P<width>0)h(?P<height>0))\s*(?P<post>.*?┝┤.*?├)`, "mg");
     static inline_image_info                        = ctRegex!(`☼?(?P<img>[a-zA-Z0-9._-]+?\.(?:jpg|gif|png)),w(?P<width>\d+)h(?P<height>\d+)`, "mg");
     static inline_link_anchor                       = ctRegex!(`┃(?P<anchor>\S+?)┃`, "mg"); // TODO *~text_link_anchor
-    // space cleaning should not be necessary
-    static inline_link                              = ctRegex!(`┥\s*(?P<text>.+?)\s*┝┤(?P<link>#?(\S+?))├`, "mg");
-    static inline_link_empty                        = ctRegex!(`┥\s*(?P<text>.+?)\s*┝┤├`, "mg");
-    static inline_link_number                       = ctRegex!(`┥\s*(?P<text>.+?)\s*┝┤(?P<num>[0-9]+)├`, "mg"); // not used
-    static inline_link_number_only                  = ctRegex!(`\s*(?P<linked_text>\s*┥.+?┝)┤(?P<num>[0-9]+)├`, "mg");
-    static inline_link_stow_uri                     = ctRegex!(`┥\s*(?P<text>.+?)\s*┝┤(?P<link>[^ 0-9#┥┝┤├][^ 0-9┥┝┤├]+)├`, "mg"); // will not stow (stowed links) or object number internal links
-    static inline_link_hash                         = ctRegex!(`┥\s*(?P<text>.+?)\s*┝┤(?P<link>#(?P<hash>\S+?))├`, "mg");
-    static inline_link_seg_and_hash                 = ctRegex!(`┥\s*(?P<text>.+?)\s*┝┤(?P<link>(?P<seg>[^/#├]*)#(?P<hash>.+?))├`, "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<linked_text>┥.+?┝)┤(?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<hash>\S+?))├`, "mg");
+    static inline_link_seg_and_hash                 = ctRegex!(`┥(?P<text>.+?)┝┤(?P<link>(?P<seg>[^/#├]*)#(?P<hash>.+?))├`, "mg");
     static inline_link_clean                        = ctRegex!(`┤(?:.+?)├|[┥┝]`, "mg");
     static inline_link_toc_to_backmatter            = ctRegex!(`┤#(?P<link>endnotes|bibliography|bookindex|glossary|blurb)├`, "mg");
     static url                                      = ctRegex!(`https?://`, "mg");
diff --git a/src/sisudoc/meta/metadoc_from_src.d b/src/sisudoc/meta/metadoc_from_src.d
index 904444a..4240a3f 100644
--- a/src/sisudoc/meta/metadoc_from_src.d
+++ b/src/sisudoc/meta/metadoc_from_src.d
@@ -770,7 +770,7 @@ template docAbstraction() {
                 comp_obj_.has.inline_links                      = substantive_obj_misc_struct.has_links;
                 comp_obj_.has.image_without_dimensions          = substantive_obj_misc_struct.has_images_without_dimensions;
                 the_document_body_section                       ~= comp_obj_;
-                tag_assoc                                           = an_object.inline_para_link_anchor(tag_in_seg, tag_assoc);
+                tag_assoc                                       = an_object.inline_para_link_anchor(tag_in_seg, tag_assoc);
                 {
                   ST_txt_by_line_common_reset _get = txt_by_line_common_reset_(line_occur, an_object, pith);
                   {
diff --git a/src/sisudoc/meta/metadoc_from_src_functions.d b/src/sisudoc/meta/metadoc_from_src_functions.d
index 6718e82..53e494b 100644
--- a/src/sisudoc/meta/metadoc_from_src_functions.d
+++ b/src/sisudoc/meta/metadoc_from_src_functions.d
@@ -4233,11 +4233,31 @@ template docAbstractionFunctions() {
     int                   html_segnames_ptr_cntr,
     int                   html_segnames_ptr,
   ) {
+    string[string][string] notes_;
+    if (the_document_body_section.length > 1) {
+      string _notes;
+      foreach (ref obj; the_document_body_section) {
+        if (obj.has.inline_notes_reg) {
+          if ((obj.text).matchFirst(rgx.inline_notes_al_gen)) {
+            foreach (m; (obj.text).matchAll(rgx.inline_notes_al_regular_number_note)) {
+              _notes ~= "\n\n" ~ m["num"] ~ ". " ~ m["note"] ~ " ≫" ~ obj.metainfo.ocn.to!string;
+              notes_[(m["num"])]["ocn"] = obj.metainfo.ocn.to!string;
+            }
+          }
+        }
+      }
+    }
     if (the_document_endnotes_section.length > 1) {
       segnames["html"] ~= "endnotes";
       segnames["epub"] ~= "endnotes";
       html_segnames_ptr = html_segnames_ptr_cntr;
       foreach (ref obj; the_document_endnotes_section) {
+        auto matches = (obj.text).matchAll(rgx.endnote_section_note);
+        foreach (m; matches) {
+          obj.text = m.hit ~ " ≫" ~ notes_[(m["notenumber"])]["ocn"];
+        }
+      }
+      foreach (ref obj; the_document_endnotes_section) {
         if (obj.metainfo.is_a == "heading") {
           obj.metainfo.parent_ocn = obj.metainfo.markedup_ancestors[obj.metainfo.parent_lev_markup];
         }
diff --git a/src/sisudoc/meta/rgx.d b/src/sisudoc/meta/rgx.d
index 1a26f73..fcac959 100644
--- a/src/sisudoc/meta/rgx.d
+++ b/src/sisudoc/meta/rgx.d
@@ -229,28 +229,28 @@ static template spineRgxIn() {
     static inline_notes_al_special                  = ctRegex!(`【(?:[*+]\s+)(.+?)】`, "mg"); // TODO remove match when special footnotes are implemented
     static inline_notes_al_gen                      = ctRegex!(`【.+?】`, "m");
     static inline_notes_al_gen_text                 = ctRegex!(`【(?P<text>.+?)】`, "m");
-    static inline_notes_al_all_note                 = ctRegex!(`【(?P<num>\d+|(?:[*]|[+])+)\s+(?P<note>.+?)\s*】`, "mg");
-    static inline_notes_al_regular_number_note      = ctRegex!(`【(?P<num>\d+)\s+(?P<note>.+?)\s*】`, "mg");
-    // static inline_notes_al_all_note                 = ctRegex!(`【(?P<num>\d+|(?:[*]|[+])+)\s+(?P<note>.+?)\s*(≫\s\d+)?\s*】`, "mg"); // ocn of origin would be useful in endnote section
-    // static inline_notes_al_regular_number_note      = ctRegex!(`【(?P<num>\d+)\s+(?P<note>.+?)\s*(≫\s\d+)?\s*】`, "mg"); // ocn of origin would be useful in endnote section
+    static inline_notes_al_all_note                 = ctRegex!(`【(?P<num>\d+|(?:[*]|[+])+)\s+(?P<note>.+?)\s*(≫\s\d+)?\s*】`, "mg"); // ocn of origin would be useful in endnote section
+    static inline_notes_al_regular_number_note      = ctRegex!(`【(?P<num>\d+)\s+(?P<note>.+?)\s*(≫\s\d+)?\s*】`, "mg"); // ocn of origin would be useful in endnote section
+    // static inline_notes_al_all_note                 = ctRegex!(`【(?P<num>\d+|(?:[*]|[+])+)\s+(?P<note>.+?)\s*】`, "mg");
+    // static inline_notes_al_regular_number_note      = ctRegex!(`【(?P<num>\d+)\s+(?P<note>.+?)\s*】`, "mg");
     static inline_notes_al_special_char_note        = ctRegex!(`【(?P<char>(?:[*]|[+])+)\s+(?P<note>.+?)】`, "mg");
     static inline_al_delimiter_open_regular         = ctRegex!(`【\s`, "m");
     static inline_al_delimiter_open_symbol_star     = ctRegex!(`【[*]\s`, "m");
     static inline_al_delimiter_open_symbol_plus     = ctRegex!(`【[+]\s`, "m");
     static inline_text_and_note_al_                 = ctRegex!(`(.+?(?:【[*+]*\s+.+?】|.+))`, "mg");
+    static endnote_section_note                     = ctRegex!(`┥\s*⑆\^┨(?P<notenumber>\d+)\.┣\^┝┤(?P<link>¤?.+?)├.+`, "mg");
     /+ inline markup links +/
     static inline_image                             = ctRegex!(`(?P<pre>┥)☼(?P<imginf>(?P<img>[a-zA-Z0-9._-]+?\.(?: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>[a-zA-Z0-9._-]+?\.(?:jpg|gif|png)),w(?P<width>0)h(?P<height>0))\s*(?P<post>.*?┝┤.*?├)`, "mg");
     static inline_image_info                        = ctRegex!(`☼?(?P<img>[a-zA-Z0-9._-]+?\.(?:jpg|gif|png)),w(?P<width>\d+)h(?P<height>\d+)`, "mg");
     static inline_link_anchor                       = ctRegex!(`┃(?P<anchor>\S+?)┃`, "mg"); // TODO *~text_link_anchor
-    // space cleaning should not be necessary
-    static inline_link                              = ctRegex!(`┥\s*(?P<text>.+?)\s*┝┤(?P<link>#?(\S+?))├`, "mg");
-    static inline_link_empty                        = ctRegex!(`┥\s*(?P<text>.+?)\s*┝┤├`, "mg");
-    static inline_link_number                       = ctRegex!(`┥\s*(?P<text>.+?)\s*┝┤(?P<num>[0-9]+)├`, "mg"); // not used
-    static inline_link_number_only                  = ctRegex!(`\s*(?P<linked_text>\s*┥.+?┝)┤(?P<num>[0-9]+)├`, "mg");
-    static inline_link_stow_uri                     = ctRegex!(`┥\s*(?P<text>.+?)\s*┝┤(?P<link>[^ 0-9#┥┝┤├][^ 0-9┥┝┤├]+)├`, "mg"); // will not stow (stowed links) or object number internal links
-    static inline_link_hash                         = ctRegex!(`┥\s*(?P<text>.+?)\s*┝┤(?P<link>#(?P<hash>\S+?))├`, "mg");
-    static inline_link_seg_and_hash                 = ctRegex!(`┥\s*(?P<text>.+?)\s*┝┤(?P<link>(?P<seg>[^/#├]*)#(?P<hash>.+?))├`, "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<linked_text>┥.+?┝)┤(?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<hash>\S+?))├`, "mg");
+    static inline_link_seg_and_hash                 = ctRegex!(`┥(?P<text>.+?)┝┤(?P<link>(?P<seg>[^/#├]*)#(?P<hash>.+?))├`, "mg");
     static inline_link_clean                        = ctRegex!(`┤(?:.+?)├|[┥┝]`, "mg");
     static inline_link_toc_to_backmatter            = ctRegex!(`┤#(?P<link>endnotes|bibliography|bookindex|glossary|blurb)├`, "mg");
     static url                                      = ctRegex!(`https?://`, "mg");