a text output (and skel an outline)HEADmain

- spine --text [--output=output path] [markup source]

3 files changed, 35 insertions, 25 deletions

diff --git a/src/sisudoc/meta/metadoc_from_src.d b/src/sisudoc/meta/metadoc_from_src.d
index 24ae935..904444a 100644
--- a/src/sisudoc/meta/metadoc_from_src.d
+++ b/src/sisudoc/meta/metadoc_from_src.d
@@ -939,7 +939,7 @@ template docAbstraction() {
     }
     { // document segnames
       ST_segnames get_segnames;
-      get_segnames = the_document_body_section.after_doc_determine_segnames(the_document_endnotes_section, the_document_glossary_section, the_document_bibliography_section, the_document_bookindex_section, the_document_blurb_section, segnames, html_segnames_ptr_cntr, html_segnames_ptr); //
+      get_segnames = the_document_body_section.after_doc_determine_segnames(the_document_endnotes_section, the_document_glossary_section, the_document_bibliography_section, the_document_bookindex_section, the_document_blurb_section, segnames, html_segnames_ptr_cntr, html_segnames_ptr);
       segnames                          = get_segnames.segnames;
       html_segnames_ptr_cntr            = get_segnames.html_segnames_ptr_cntr;
       html_segnames_ptr                 = get_segnames.html_segnames_ptr;
@@ -1376,36 +1376,42 @@ template docAbstraction() {
       "scroll": ["head", "toc", "body",],
       "seg":    ["head", "toc", "body",],
       "sql":    ["head", "body",],
-      "latex":  ["head", "toc", "body",]
+      "latex":  ["head", "toc", "body",],
+      "text":   ["head", "toc", "body",],
     ];
     if (document_the["endnotes"].length > 1) {
       document_section_keys_sequenced["scroll"] ~= "endnotes";
       document_section_keys_sequenced["seg"]    ~= "endnotes";
       document_section_keys_sequenced["latex"]  ~= "endnotes";
+      document_section_keys_sequenced["text"]   ~= "endnotes";
     }
     if (document_the["glossary"].length > 1) {
       document_section_keys_sequenced["scroll"] ~= "glossary";
       document_section_keys_sequenced["seg"]    ~= "glossary";
       document_section_keys_sequenced["sql"]    ~= "glossary";
       document_section_keys_sequenced["latex"]  ~= "glossary";
+      document_section_keys_sequenced["text"]  ~= "glossary";
     }
     if (document_the["bibliography"].length > 1) {
       document_section_keys_sequenced["scroll"] ~= "bibliography";
       document_section_keys_sequenced["seg"]    ~= "bibliography";
       document_section_keys_sequenced["sql"]    ~= "bibliography";
       document_section_keys_sequenced["latex"]  ~= "bibliography";
+      document_section_keys_sequenced["text"]  ~= "bibliography";
     }
     if (document_the["bookindex"].length > 1) {
       document_section_keys_sequenced["scroll"] ~= "bookindex";
       document_section_keys_sequenced["seg"]    ~= "bookindex";
       document_section_keys_sequenced["sql"]    ~= "bookindex";
       document_section_keys_sequenced["latex"]  ~= "bookindex";
+      document_section_keys_sequenced["text"]   ~= "bookindex";
     }
     if (document_the["blurb"].length > 1) {
       document_section_keys_sequenced["scroll"] ~= "blurb";
       document_section_keys_sequenced["seg"]    ~= "blurb";
       document_section_keys_sequenced["sql"]    ~= "blurb";
       document_section_keys_sequenced["latex"]  ~= "blurb";
+      document_section_keys_sequenced["text"]   ~= "blurb";
     }
     if ((opt_action.html)
     || (opt_action.html_scroll)
diff --git a/src/sisudoc/meta/metadoc_from_src_functions.d b/src/sisudoc/meta/metadoc_from_src_functions.d
index 3ae10d1..6718e82 100644
--- a/src/sisudoc/meta/metadoc_from_src_functions.d
+++ b/src/sisudoc/meta/metadoc_from_src_functions.d
@@ -2557,10 +2557,8 @@ template docAbstractionFunctions() {
       CMM              conf_make_meta,
       Flag!"_new_doc"  _new_doc
     ) {
-      obj_txt["munge"]                                = obj_[obj_key_].dup;
-      obj_txt["munge"]                                = (obj_["is"].match(ctRegex!(`verse|code`)))
-      ? obj_txt["munge"]
-      : obj_txt["munge"].strip;
+      obj_txt["munge"]                  = obj_[obj_key_].dup;
+      obj_txt["munge"]                  = (obj_["is"].match(ctRegex!(`verse|code`))) ? obj_txt["munge"] : obj_txt["munge"].strip;
       if (_new_doc) {
         anchor_tag = "";
       }
@@ -2579,8 +2577,8 @@ template docAbstractionFunctions() {
         || (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;
+        obj_txt["munge"]                = (obj_txt["munge"]).inline_markup_faces;
+        obj_txt["munge"]                = (obj_txt["munge"]).links_and_images;
       }
       switch (obj_["is"]) {
       case "heading":
@@ -3299,8 +3297,8 @@ template docAbstractionFunctions() {
   // ↓ - endnotes
   struct NotesSection {
     string[string] object_notes;
-    int previous_count;
-    int mkn;
+    int            previous_count;
+    int            mkn;
     static auto rgx = RgxI();
     private auto gather_notes_for_endnote_section(
       ObjGenericComposite[] contents_am,
@@ -5406,6 +5404,9 @@ template docSectKeysSeq() {
       string[] latex() {
         return document_section_keys_sequenced["latex"];
       }
+      string[] text() {
+        return document_section_keys_sequenced["text"];
+      }
     }
     return doc_sect_keys_seq();
   }
diff --git a/src/sisudoc/meta/rgx.d b/src/sisudoc/meta/rgx.d
index 259ab82..1a26f73 100644
--- a/src/sisudoc/meta/rgx.d
+++ b/src/sisudoc/meta/rgx.d
@@ -148,16 +148,16 @@ static template spineRgxIn() {
     static table_col_separator_nl                   = ctRegex!(`[┊]$`, "mg");
     /+ inline markup footnotes endnotes +/
     static inline_notes_curly_gen                   = ctRegex!(`~\{.+?\}~`, "m");
-    static inline_notes_curly                       = ctRegex!(`~\{\s*(.+?)\}~`, "mg");
-    static inline_notes_curly_sp_asterisk           = ctRegex!(`~\{[*]+\s+(.+?)\}~`, "m");
-    static inline_notes_curly_sp_plus               = ctRegex!(`~\{[+]+\s+(.+?)\}~`, "m");
+    static inline_notes_curly                       = ctRegex!(`~\{\s*(.+?)\s*\}~`, "mg");
+    static inline_notes_curly_sp_asterisk           = ctRegex!(`~\{[*]+\s+(.+?)\s*\}~`, "m");
+    static inline_notes_curly_sp_plus               = ctRegex!(`~\{[+]+\s+(.+?)\s*\}~`, "m");
     static note_ref                                 = ctRegex!(`^\S+?noteref_(?P<ref>[0-9]+)`, "mg");     // {^{73.}^}#noteref_73
     static smid_inline_url_generic                        = ctRegex!(`(?:^|[}(\[ ])(?:(?:https?|git):\/\/|¤?\.\.\/|¤?\.\/|¤|#)[a-zA-Z0-9_#]`, "mg");
     static smid_inline_url                                = ctRegex!(`((?:(?:https?|git):\/\/|¤?\.\.\/|¤?\.\/|¤|#)[a-zA-Z0-9_]\S*)`, "mg");
     static smid_inline_link_naked_url                     = ctRegex!(`(?P<pre>^|[ (\[])(?P<link>(?:(?:https?|git):\/\/|¤?\.\.\/|¤?\.\/|¤)\S+?)(?=[.,;:?!'"]?([ )\]]|$))`, "mg");
     static smid_inline_link_markup_regular                = ctRegex!(`(?P<pre>^|[ (\[])\{\s*(?P<content>.+?)\s*\}(?P<link>(?:(?:https?|git):\/\/|¤?\.\.\/|¤?\.\/|¤|#)\S+?)(?=[;:!,?.]?([ )\]]|$))`, "mg");
-    static smid_inline_link_endnote_url_helper_punctuated = ctRegex!(`\{~\^\s+(?P<content>.+?)\}(?P<link>(?:(?:https?|git):\/\/|¤?\.\.\/|¤?\.\/|¤|#)\S+?)(?=[.,;:?!]?([ ]|$))`, "mg");
-    static smid_inline_link_endnote_url_helper            = ctRegex!(`\{~\^\s+(?P<content>.+?)\}(?P<link>(?:(?:https?|git):\/\/|¤?\.\.\/|¤?\.\/|¤|#)\S+)`, "mg");
+    static smid_inline_link_endnote_url_helper_punctuated = ctRegex!(`\{~\^\s+(?P<content>.+?)\s*\}(?P<link>(?:(?:https?|git):\/\/|¤?\.\.\/|¤?\.\/|¤|#)\S+?)(?=[.,;:?!]?([ ]|$))`, "mg");
+    static smid_inline_link_endnote_url_helper            = ctRegex!(`\{~\^\s+(?P<content>.+?)\s*\}(?P<link>(?:(?:https?|git):\/\/|¤?\.\.\/|¤?\.\/|¤|#)\S+)`, "mg");
     static image                                    = ctRegex!(`([a-zA-Z0-9._-]+?\.(?:png|gif|jpg))`, "mg");
     static smid_image                               = ctRegex!(`(?P<pre>(?:^|[ ])[{┥](?:~\^\s+|\s*))(?P<image>[a-zA-Z0-9._-]+?\.(?:png|gif|jpg))(?P<post>(?:.*?)\s*[}┝](?:image|┤.*?├|(?:(?:https?|git):\/\/|¤?\.\.\/|¤?\.\/|¤|#)\S+?)(?=[;:!,?.]?([ )\]]|$)))`, "mg");
     static smid_image_generic                       = ctRegex!(`(?:^|[ ])[{┥](?:~\^\s+|\s*)\S+\.(?:png|gif|jpg).*?[}┝](?:image|┤.*?├|(?:(?:https?|git):\/\/|¤?\.\.\/|¤?\.\/|¤|#)\S+?)(?=[;:!,?.]?([ )\]]|$))`, "mg");
@@ -221,9 +221,9 @@ static template spineRgxIn() {
     static br_empty_line                            = ctRegex!(`\n[ ]*\n`, "mg");
     static br_linebreaks_newlines                   = ctRegex!(`[\n┘┙]`, "mg");
     static br_linebreaks                            = ctRegex!(`[┘┙]`, "mg");
-    static br_line                                  = ctRegex!(`┘`, "mg");
-    static br_line_inline                           = ctRegex!(`┙`, "mg");
-    static br_line_spaced                           = ctRegex!(`┚`, "mg");
+    static br_line                                  = ctRegex!(`\s*┘\s*`, "mg");
+    static br_line_inline                           = ctRegex!(`\s*┙\s*`, "mg");
+    static br_line_spaced                           = ctRegex!(`\s*┚\s*`, "mg");
     /+ inline markup footnotes endnotes +/
     static inline_notes_al                          = ctRegex!(`【(?:[*+]\s+|\s*)(.+?)】`, "mg");
     static inline_notes_al_special                  = ctRegex!(`【(?:[*+]\s+)(.+?)】`, "mg"); // TODO remove match when special footnotes are implemented
@@ -231,6 +231,8 @@ static template spineRgxIn() {
     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_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");
@@ -241,13 +243,14 @@ static template spineRgxIn() {
     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
-    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");
+    // 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_clean                        = ctRegex!(`┤(?:.+?)├|[┥┝]`, "mg");
     static inline_link_toc_to_backmatter            = ctRegex!(`┤#(?P<link>endnotes|bibliography|bookindex|glossary|blurb)├`, "mg");
     static url                                      = ctRegex!(`https?://`, "mg");