cleaningdoc-reform_v0.4.1

6 files changed, 29 insertions, 71 deletions

diff --git a/src/doc_reform/doc_reform.d b/src/doc_reform/doc_reform.d
index 53ddbcf..2d93c29 100755
--- a/src/doc_reform/doc_reform.d
+++ b/src/doc_reform/doc_reform.d
@@ -44,15 +44,13 @@ void main(string[] args) {
   enum dAM { abstraction, matters }
   static auto rgx = Rgx();
   scope(success) {
-    debug(checkdoc) {
-      writefln(
-        "~ run complete, ok ~ (%s-%s.%s.%s, %s D:%s, %s %s)",
-        program_name,
-        _ver.major, _ver.minor, _ver.patch,
-        __VENDOR__, __VERSION__,
-        bits, os,
-      );
-    }
+    writefln(
+      "~ run complete, ok ~ (%s-%s.%s.%s, %s D:%s, %s %s)",
+      program_name,
+      _ver.major, _ver.minor, _ver.patch,
+      __VENDOR__, __VERSION__,
+      bits, os,
+    );
   }
   scope(failure) {
     debug(checkdoc) {
diff --git a/src/doc_reform/meta/metadoc_from_src.d b/src/doc_reform/meta/metadoc_from_src.d
index 4f12e0b..9d2935c 100644
--- a/src/doc_reform/meta/metadoc_from_src.d
+++ b/src/doc_reform/meta/metadoc_from_src.d
@@ -780,7 +780,7 @@ template DocReformDocAbstraction() {
             } else {
               /+ not book_index +/
               an_object_key="body_nugget";
-              if (auto m = matchFirst(line, rgx.comment)) {
+              if (auto m = line.matchFirst(rgx.comment)) {
                 /+ matched comment +/
                 debug(comment) {
                   writeln(line);
@@ -1047,7 +1047,7 @@ template DocReformDocAbstraction() {
               comp_obj_para.has.inline_notes_reg                        = substantive_obj_misc_tuple[sObj.notes_reg];
               comp_obj_para.has.inline_notes_star                       = substantive_obj_misc_tuple[sObj.notes_star];
               comp_obj_para.has.inline_links                            = substantive_obj_misc_tuple[sObj.links];
-              comp_obj_para.has.contains_image_without_dimensions       = substantive_obj_misc_tuple[sObj.image_no_dimensions];
+              comp_obj_para.has.image_without_dimensions                = substantive_obj_misc_tuple[sObj.image_no_dimensions];
               the_document_body_section                                 ~= comp_obj_para;
               tag_assoc = inline_para_link_anchor(an_object, tag_in_seg, tag_assoc);
               _common_reset_(line_occur, an_object, obj_type_status);
@@ -1698,7 +1698,7 @@ template DocReformDocAbstraction() {
     }
     string[] segnames_lv0_to_4;
     auto _image_dimensions(M,O)(M manifest_matter, O obj) {
-      if (obj.has.contains_image_without_dimensions) {
+      if (obj.has.image_without_dimensions) {
         import std.math;
         import imageformats;
         int w, h, chans;
@@ -2244,50 +2244,7 @@ template DocReformDocAbstraction() {
     dom_structure_markedup_tags_status_buffer    = [ 0, 0, 0, 0, 0, 0, 0, 0, 0,];
     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,];
-    debug(abstraction) {
-      foreach (part; sequenced_document_keys.scroll) {
-        foreach (ref obj; document_the[part]) {
-          debug(node_misc) {
-            if (obj.metainfo.is_a == "heading") {
-              writeln("heading ancestors text?: ", obj.tags.heading_ancestors_text);
-            }
-          }
-          debug(node_headings) {
-            if (obj.metainfo.is_a == "heading") {
-              writeln("---");
-              writeln(obj.text);
-              writeln("  node:                    ", obj.metainfo.node);
-              writeln("  ocn:                     ", obj.metainfo.ocn);
-              writeln("  markedup heading lev:    ", obj.metainfo.heading_lev_markup);
-              writeln("  collapsed heading lev    ", obj.metainfo.heading_lev_collapsed);
-              writeln("  parent ocn:              ", obj.metainfo.parent_ocn);
-              writeln("  parent lev:              ", obj.metainfo.parent_lev_markup);
-              writeln("  markedup ancestors o_n:  ", obj.metainfo.markedup_ancestors);
-              writeln("  dom markedup:            ", obj.metainfo.dom_structure_markedup_tags_status);
-              writeln("  collapsed ancestors o_n: ", obj.metainfo.collapsed_ancestors);
-              writeln("  dom collapsed:           ", obj.metainfo.dom_structure_collapsed_tags_status);
-            }
-          }
-          debug(node_all) {
-            writeln("---");
-            if (obj.metainfo.is_a == "heading") {
-              writeln(obj.text);
-            }
-            writeln("node:                    ", obj.metainfo.node);
-            writeln("ocn:                     ", obj.metainfo.ocn);
-            writeln("markedup heading lev:    ", obj.metainfo.heading_lev_markup);
-            writeln("collapsed heading lev    ", obj.metainfo.heading_lev_collapsed);
-            writeln("markedup ancestors o_n:  ", obj.metainfo.markedup_ancestors);
-            writeln("collapsed ancestors o_n: ", obj.metainfo.collapsed_ancestors);
-            writeln("dom markedup:            ", obj.metainfo.dom_structure_markedup_tags_status);
-            writeln("dom collapsed:           ", obj.metainfo.dom_structure_collapsed_tags_status);
-            writeln("parent ocn:              ", obj.metainfo.parent_ocn);
-            writeln("parent lev:              ", obj.metainfo.parent_lev_markup);
-            writeln("Node:                    ", obj.metainfo.ocn);
-          }
-        }
-      }
-    }
+    
     auto t = tuple(
       document_the,
       sequenced_document_keys,
@@ -4978,7 +4935,7 @@ template DocReformDocAbstraction() {
             if (auto n = munge_.match(rgx.heading_anchor_tag_plus_colon)) {
               auto tag_remunge_ = n.captures[2]
                 .replaceAll(rgx.heading_marker_tag_has_colon, "..");
-              munge_=munge_.replaceFirst(rgx.heading_anchor_tag_plus_colon, n.captures[1] ~ tag_remunge_ ~ " ");
+              munge_ = munge_.replaceFirst(rgx.heading_anchor_tag_plus_colon, n.captures[1] ~ tag_remunge_ ~ " ");
             }
           } else if (auto m = munge_.match(rgx.heading_extract_unnamed_anchor_tag)) {
             munge_ = munge_.replaceFirst(
diff --git a/src/doc_reform/meta/object_setter.d b/src/doc_reform/meta/object_setter.d
index 03197da..a4eaaf6 100644
--- a/src/doc_reform/meta/object_setter.d
+++ b/src/doc_reform/meta/object_setter.d
@@ -10,7 +10,7 @@ template ObjectSetter() {
     string                 is_of_part                         = ""; // frontmatter, body, backmatter
     string                 is_of_section                      = ""; // toc, body, glossary, biography, book index, blurb
     string                 is_of_type                         = ""; // para, block ?
-    string                 is_a                               = ""; // heading, para, table, code block, group, ...
+    string                 is_a                               = ""; // heading, para, table, code block, group, verse/poem ...
     alias                  of_part                            = is_of_part;
     alias                  of_section                         = is_of_section;
     alias                  is_of                              = is_of_type;
@@ -86,7 +86,7 @@ template ObjectSetter() {
     bool                   inline_links                        = false;
     bool                   inline_notes_reg                    = false;
     bool                   inline_notes_star                   = false;
-    bool                   contains_image_without_dimensions   = false;
+    bool                   image_without_dimensions            = false;
   }
   struct DocObj_Table_ {
     int                    number_of_columns                   = 0;
diff --git a/src/doc_reform/meta/rgx.d b/src/doc_reform/meta/rgx.d
index 8c592a6..c43390d 100644
--- a/src/doc_reform/meta/rgx.d
+++ b/src/doc_reform/meta/rgx.d
@@ -247,7 +247,7 @@ static template DocReformRgxInit() {
     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!(`【(.+?)】`, "mg");
-    static inline_notes_delimiter_al_regular_number_note  = ctRegex!(`【(\d+)\s+(.+?)】`, "mg");
+    static inline_notes_delimiter_al_regular_number_note  = ctRegex!(`【(?P<num>\d+)\s+(?P<note>.+?)】`, "mg");
     static inline_al_delimiter_open_asterisk              = ctRegex!(`【\*`, "m");
     static inline_al_delimiter_open_plus                  = ctRegex!(`【\+`, "m");
     static inline_text_and_note_al                        = ctRegex!(`(?P<text>.+?)【(?:[*+ ]*)(?P<note>.+?)】`, "mg");
@@ -282,10 +282,10 @@ static template DocReformRgxInit() {
     static inline_mono_box                                = ctRegex!(`■\{(?P<text>.+?)\}■`, "mg");
     static inline_cite                                    = ctRegex!(`"\{(?P<text>.+?)\}"`, "mg");
     static inline_faces_line                              = ctRegex!(`^[*!/_]_ (?P<text>.+?)((?: [\\]{2}|[~]#){0,2}$)`);
-    static inline_emphasis_line                           = ctRegex!(`^\*_ (?P<text>.+?)((?: [\\]{2}|[~]#){0,2}$)`);
-    static inline_bold_line                               = ctRegex!(`^!_ (?P<text>.+?)((?: [\\]{2}|[~]#){0,2}$)`);
-    static inline_italics_line                            = ctRegex!(`^/_ (?P<text>.+?)((?: [\\]{2}|[~]#){0,2}$)`);
-    static inline_underscore_line                         = ctRegex!(`^__ (?P<text>.+?)((?: [\\]{2}|[~]#){0,2}$)`);
+    static inline_emphasis_line                           = ctRegex!(`^\*_ (?P<text>.+?)(?P<tail>(?: [\\]{2}|[~]#){0,2}$)`);
+    static inline_bold_line                               = ctRegex!(`^!_ (?P<text>.+?)(?P<tail>(?: [\\]{2}|[~]#){0,2}$)`);
+    static inline_italics_line                            = ctRegex!(`^/_ (?P<text>.+?)(?P<tail>(?: [\\]{2}|[~]#){0,2}$)`);
+    static inline_underscore_line                         = ctRegex!(`^__ (?P<text>.+?)(?P<tail>(?: [\\]{2}|[~]#){0,2}$)`);
     static inline_fontface_clean                          = ctRegex!(`[*!_/^,+#■"-]\{|\}[*!_/^,+#■"-]`, "mg");
     static no_header_rgx                                  = ctRegex!(`^=NULL$`);
     /+ table delimiters +/
diff --git a/src/doc_reform/output/hub.d b/src/doc_reform/output/hub.d
index 4cff15e..1534bc0 100644
--- a/src/doc_reform/output/hub.d
+++ b/src/doc_reform/output/hub.d
@@ -18,10 +18,10 @@ template outputHub() {
     void Scheduled(D,I)(int sched, D doc_abstraction, I doc_matters) {
       auto msg = Msg!()(doc_matters);
       if (sched == outTask.pod) {
-        msg.v("sisu source processing... ");
+        msg.v("doc reform source processing... ");
         import doc_reform.output.source_pod;
         DocReformPod!()(doc_matters);
-        msg.vv("sisu source done");
+        msg.vv("doc reform source done");
       }
       if (sched == outTask.epub) {
         msg.v("epub3 processing... ");
@@ -54,6 +54,9 @@ template outputHub() {
         msg.vv("sqlite done");
       }
     }
+    if (!(doc_matters.opt.action.quiet)) {
+      writeln(" ", doc_matters.src.filename_base);
+    }
     if (!(doc_matters.opt.action.parallelise_subprocesses)) {
       foreach(schedule; doc_matters.opt.action.output_task_scheduler) {
         Scheduled!()(schedule, doc_abstraction, doc_matters);
diff --git a/src/doc_reform/output/rgx.d b/src/doc_reform/output/rgx.d
index 02c3cbb..0bcb2b6 100644
--- a/src/doc_reform/output/rgx.d
+++ b/src/doc_reform/output/rgx.d
@@ -55,7 +55,7 @@ static template DocReformOutputRgxInit() {
     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!(`【(.+?)】`, "mg");
-    static inline_notes_delimiter_al_regular_number_note  = ctRegex!(`【(\d+)\s+(.+?)】`, "mg");
+    static inline_notes_delimiter_al_regular_number_note  = ctRegex!(`【(?P<num>\d+)\s+(?P<note>.+?)】`, "mg");
     static inline_al_delimiter_open_asterisk              = ctRegex!(`【\*`, "m");
     static inline_al_delimiter_open_plus                  = ctRegex!(`【\+`, "m");
     static inline_text_and_note_al                        = ctRegex!(`(?P<text>.+?)【(?:[*+ ]*)(?P<note>.+?)】`, "mg");
@@ -90,10 +90,10 @@ static template DocReformOutputRgxInit() {
     static inline_mono_box                                = ctRegex!(`■\{(?P<text>.+?)\}■`, "mg");
     static inline_cite                                    = ctRegex!(`"\{(?P<text>.+?)\}"`, "mg");
     static inline_faces_line                              = ctRegex!(`^[*!/_]_ (?P<text>.+?)((?: [\\]{2}|[~]#){0,2}$)`);
-    static inline_emphasis_line                           = ctRegex!(`^\*_ (?P<text>.+?)((?: [\\]{2}|[~]#){0,2}$)`);
-    static inline_bold_line                               = ctRegex!(`^!_ (?P<text>.+?)((?: [\\]{2}|[~]#){0,2}$)`);
-    static inline_italics_line                            = ctRegex!(`^/_ (?P<text>.+?)((?: [\\]{2}|[~]#){0,2}$)`);
-    static inline_underscore_line                         = ctRegex!(`^__ (?P<text>.+?)((?: [\\]{2}|[~]#){0,2}$)`);
+    static inline_emphasis_line                           = ctRegex!(`^\*_ (?P<text>.+?)(?P<tail>(?: [\\]{2}|[~]#){0,2}$)`);
+    static inline_bold_line                               = ctRegex!(`^!_ (?P<text>.+?)(?P<tail>(?: [\\]{2}|[~]#){0,2}$)`);
+    static inline_italics_line                            = ctRegex!(`^/_ (?P<text>.+?)(?P<tail>(?: [\\]{2}|[~]#){0,2}$)`);
+    static inline_underscore_line                         = ctRegex!(`^__ (?P<text>.+?)(?P<tail>(?: [\\]{2}|[~]#){0,2}$)`);
     static inline_fontface_clean                          = ctRegex!(`[*!_/^,+#■"-]\{|\}[*!_/^,+#■"-]`, "mg");
     static no_header_rgx                                  = ctRegex!(`^=NULL$`);
     /+ table delimiters +/