From 54c662aed1b2b004aeffe3d250a9dbd705897bb4 Mon Sep 17 00:00:00 2001 From: Ralph Amissah Date: Mon, 11 Feb 2019 16:34:54 -0500 Subject: metaverse single line munging tuning --- src/doc_reform/meta/defaults.d | 2 ++ src/doc_reform/meta/metadoc_from_src.d | 46 ++++++++++++++-------------------- src/doc_reform/meta/rgx.d | 16 +++++++----- src/doc_reform/output/defaults.d | 2 ++ src/doc_reform/output/rgx.d | 19 ++++++++------ src/doc_reform/output/sqlite.d | 32 +++++++++++++++++++++++ src/doc_reform/output/xmls.d | 5 +++- 7 files changed, 80 insertions(+), 42 deletions(-) (limited to 'src/doc_reform') diff --git a/src/doc_reform/meta/defaults.d b/src/doc_reform/meta/defaults.d index 7c1a726..fbde36e 100644 --- a/src/doc_reform/meta/defaults.d +++ b/src/doc_reform/meta/defaults.d @@ -152,6 +152,8 @@ 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/src/doc_reform/meta/metadoc_from_src.d b/src/doc_reform/meta/metadoc_from_src.d index d82c60a..470d579 100644 --- a/src/doc_reform/meta/metadoc_from_src.d +++ b/src/doc_reform/meta/metadoc_from_src.d @@ -1086,6 +1086,7 @@ template DocReformDocAbstraction() { 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) { @@ -1316,7 +1317,7 @@ template DocReformDocAbstraction() { 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", ); @@ -1327,7 +1328,7 @@ template DocReformDocAbstraction() { } 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", ); @@ -1338,7 +1339,7 @@ template DocReformDocAbstraction() { } 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", ); @@ -1349,7 +1350,7 @@ template DocReformDocAbstraction() { } 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", ); @@ -1360,7 +1361,7 @@ template DocReformDocAbstraction() { } 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", ); @@ -1830,9 +1831,6 @@ template DocReformDocAbstraction() { 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); @@ -1875,7 +1873,6 @@ template DocReformDocAbstraction() { 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); @@ -2045,9 +2042,6 @@ template DocReformDocAbstraction() { /+ 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); @@ -4338,22 +4332,20 @@ template DocReformDocAbstraction() { 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 ~ "$2".strip ~ mkup.lnk_c + ~ mkup.url_o ~ mkup.url_c)); debug(images) { writeln("IMAGE: ", obj_txt_in); // decide on representation } @@ -4762,7 +4754,7 @@ template DocReformDocAbstraction() { "base_position" : obj_["lev_markup_number"].to!int, ]; toc_txt_ = format( - mkup.lnk_o ~ " %s " ~ mkup.lnk_c ~ mkup.url_o ~ "#%s"~ mkup.url_c, + mkup.lnk_o ~ "%s".strip ~ mkup.lnk_c ~ mkup.url_o ~ "#%s"~ mkup.url_c, heading_toc_, _anchor_tag, ); @@ -4822,7 +4814,7 @@ template DocReformDocAbstraction() { break; case 5: .. case 7: subtoc_txt_ = format( - mkup.lnk_o ~ " %s " ~ mkup.lnk_c ~ mkup.url_o ~ "#%s"~ mkup.url_c, + mkup.lnk_o ~ "%s".strip ~ mkup.lnk_c ~ mkup.url_o ~ "#%s"~ mkup.url_c, heading_toc_, _anchor_tag, ); diff --git a/src/doc_reform/meta/rgx.d b/src/doc_reform/meta/rgx.d index 7dd4a89..f875ce3 100644 --- a/src/doc_reform/meta/rgx.d +++ b/src/doc_reform/meta/rgx.d @@ -9,7 +9,7 @@ static template DocReformRgxInit() { static true_dollar = ctRegex!(`\$`, "gm"); static flag_action = ctRegex!(`^(--[a-z][a-z0-9-]+)$`); 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!(`^([^,]+)[ ]*,[ ]+(.+?)$`); @@ -155,10 +155,11 @@ static template DocReformRgxInit() { static smid_inline_link_endnote_url_helper_punctuated = ctRegex!(`\{~\^\s+(?P.+?)\}(?P(?:(?:https?|git):\/\/|¤?\.\.\/|¤?\.\/|¤|#)\S+?)(?=[.,;:?!]?([ ]|$))`, "mg"); static smid_inline_link_endnote_url_helper = ctRegex!(`\{~\^\s+(?P.+?)\}(?P(?:(?:https?|git):\/\/|¤?\.\.\/|¤?\.\/|¤|#)\S+)`, "mg"); static image = ctRegex!(`([a-zA-Z0-9._-]+?\.(?:png|gif|jpg))`, "mg"); + static smid_image = ctRegex!(`(?P
(?:^|[ ]|[^\S]?)\{(?:~\^\s+|\s*))(?P\S+\.(?:png|gif|jpg))\s*(?P(?:.+?)\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
(?:^|[ ]|[^\S]?)\{(?:~\^\s+|\s*))(?P\S+\.(?:png|gif|jpg))\s+(?P\d+)x(?P\d+)\s*(?P(?:.+?)\s*\}(?:image|(?:(?:https?|git):\/\/|¤?\.\.\/|¤?\.\/|¤|#)\S+?)(?=[;:!,?.]?([ )\]]|$)))`, "mg");
-    static smid_image                                      = ctRegex!(`(?P
(?:^|[ ]|[^\S]?)\{(?:~\^\s+|\s*))(?P\S+\.(?:png|gif|jpg))\s*(?P(?:.+?)\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
^|[ ]|[^\S]?)\{\s*(?P.+?)\s*\}(?:image)(?=[;:!,?.]?([ )\]]|$))`, "mg");
+    static smid_mod_image_without_dimensions               = ctRegex!(`[{┥](?:~\^\s+|\s*)☼\S+\.(?:png|gif|jpg),w0h0\s+(?:.+?)\s*[}┝](?:image|(?:https?|git):\/\/\S+?)(?=[;:!,?.]?([ )\]]|$))`, "mg");
     /+ inline markup book index +/
     static book_index                                     = ctRegex!(`^=\{\s*(.+?)\}$`, "m");
     static book_index_open                                = ctRegex!(`^=\{\s*([^}]+?)$`);
@@ -254,10 +255,13 @@ static template DocReformRgxInit() {
     static inline_text_and_note_al                        = ctRegex!(`(?P.+?)【(?:[*+ ]*)(?P.+?)】`, "mg");
     static inline_text_and_note_al_                       = ctRegex!(`(.+?(?:【[*+]*\s+.+?】|$))`, "mg");
     /+ inline markup footnotes endnotes +/
-    static inline_image                                   = ctRegex!(`(?P
┥)☼(?P(?P\S+?\.(?:jpg|gif|png)),w(?P\d+)h(?P\d+))\s*(?P.*?┝┤.+?├)`, "mg");
-    static inline_image_without_dimensions                = ctRegex!(`(?P
┥)☼(?P(?P\S+?\.(?:jpg|gif|png)),w(?P0)h(?P0))\s*(?P.*?┝┤.+?├)`, "mg");
-    static inline_link_anchor                             = ctRegex!(`┋(?P\S+?)┋`, "mg");
+    static inline_image                                   = ctRegex!(`(?P
┥)☼(?P(?P\S+?\.(?:jpg|gif|png)),w(?P\d+)h(?P\d+))\s*(?P.*?┝┤.*?├)`, "mg");
+    static inline_image_without_dimensions                = ctRegex!(`(?P
┥)☼(?P(?P\S+?\.(?:jpg|gif|png)),w(?P0)h(?P0))\s*(?P.*?┝┤.*?├)`, "mg");
+    static inline_link_anchor                             = ctRegex!(`┋(?P\S+?)┋`, "mg"); // TODO *~text_link_anchor
+    static inline_link_                                   = ctRegex!(`┥(?P.+?)┝┤(?P.+?)├`, "mg");
     static inline_link                                    = ctRegex!(`┥(?P.+?)┝┤(?P\S+?)├`, "mg");
+    static inline_link_empty                              = ctRegex!(`┥(?P.+?)┝┤├`, "mg");
+    static inline_link_number                             = ctRegex!(`┥(?P.+?)┝┤(?P[0-9]+)├`, "mg"); // not used
     static inline_link_number_only                        = ctRegex!(`(┥.+?┝)┤(?P[0-9]+)├`, "mg");
     static inline_link_stow_uri                           = ctRegex!(`┥(?P.+?)┝┤(?P[^ 0-9#┥┝┤├][^ 0-9┥┝┤├]+)├`, "mg"); // will not stow (stowed links) or object number internal links
     static inline_link_hash                               = ctRegex!(`┥(?P.+?)┝┤(?P#(?P\S+?))├`, "mg");
diff --git a/src/doc_reform/output/defaults.d b/src/doc_reform/output/defaults.d
index e54afb9..a038802 100644
--- a/src/doc_reform/output/defaults.d
+++ b/src/doc_reform/output/defaults.d
@@ -33,6 +33,8 @@ 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/src/doc_reform/output/rgx.d b/src/doc_reform/output/rgx.d
index 354de00..bf1d766 100644
--- a/src/doc_reform/output/rgx.d
+++ b/src/doc_reform/output/rgx.d
@@ -62,10 +62,13 @@ static template DocReformOutputRgxInit() {
     static inline_text_and_note_al                        = ctRegex!(`(?P.+?)【(?:[*+ ]*)(?P.+?)】`, "mg");
     static inline_text_and_note_al_                       = ctRegex!(`(.+?(?:【[*+]*\s+.+?】|$))`, "mg");
     /+ inline markup footnotes endnotes +/
-    static inline_image                                   = ctRegex!(`(?P
┥)☼(?P(?P\S+?\.(?:jpg|gif|png)),w(?P\d+)h(?P\d+))\s*(?P.*?┝┤.+?├)`, "mg");
-    static inline_image_without_dimensions                = ctRegex!(`(?P
┥)☼(?P(?P\S+?\.(?:jpg|gif|png)),w(?P0)h(?P0))\s*(?P.*?┝┤.+?├)`, "mg");
-    static inline_link_anchor                             = ctRegex!(`┋(?P\S+?)┋`, "mg");
+    static inline_image                                   = ctRegex!(`(?P
┥)☼(?P(?P\S+?\.(?:jpg|gif|png)),w(?P\d+)h(?P\d+))\s*(?P.*?┝┤.*?├)`, "mg");
+    static inline_image_without_dimensions                = ctRegex!(`(?P
┥)☼(?P(?P\S+?\.(?:jpg|gif|png)),w(?P0)h(?P0))\s*(?P.*?┝┤.*?├)`, "mg");
+    static inline_link_anchor                             = ctRegex!(`┋(?P\S+?)┋`, "mg"); // TODO *~text_link_anchor
+    static inline_link_                                   = ctRegex!(`┥(?P.+?)┝┤(?P.+?)├`, "mg");
     static inline_link                                    = ctRegex!(`┥(?P.+?)┝┤(?P\S+?)├`, "mg");
+    static inline_link_empty                              = ctRegex!(`┥(?P.+?)┝┤├`, "mg");
+    static inline_link_number                             = ctRegex!(`┥(?P.+?)┝┤(?P[0-9]+)├`, "mg"); // not used
     static inline_link_number_only                        = ctRegex!(`(┥.+?┝)┤(?P[0-9]+)├`, "mg");
     static inline_link_stow_uri                           = ctRegex!(`┥(?P.+?)┝┤(?P[^ 0-9#┥┝┤├][^ 0-9┥┝┤├]+)├`, "mg"); // will not stow (stowed links) or object number internal links
     static inline_link_hash                               = ctRegex!(`┥(?P.+?)┝┤(?P#(?P\S+?))├`, "mg");
@@ -116,10 +119,10 @@ static template DocReformOutputRgxInit() {
     /+ table delimiters +/
     static table_delimiter_col                           = ctRegex!("[ ]*[┊][ ]*", "mg");
     static table_delimiter_row                           = ctRegex!("[ ]*\n", "mg");
-    static xhtml_ampersand                            = ctRegex!(`[&]`);      // &
-    static xhtml_quotation                            = ctRegex!(`["]`);      // "
-    static xhtml_less_than                            = ctRegex!(`[<]`);      // <
-    static xhtml_greater_than                         = ctRegex!(`[>]`);      // >
-    static xhtml_line_break                           = ctRegex!(` [\\]{2}`); // 
+ static xhtml_ampersand = ctRegex!(`[&]`, "m"); // & + static xhtml_quotation = ctRegex!(`["]`, "m"); // " + static xhtml_less_than = ctRegex!(`[<]`, "m"); // < + static xhtml_greater_than = ctRegex!(`[>]`, "m"); // > + static xhtml_line_break = ctRegex!(` [\\]{2}`, "m"); //
} } diff --git a/src/doc_reform/output/sqlite.d b/src/doc_reform/output/sqlite.d index 5f4e99d..c57dde9 100644 --- a/src/doc_reform/output/sqlite.d +++ b/src/doc_reform/output/sqlite.d @@ -457,6 +457,10 @@ template SQLiteFormatAndLoadObject() { 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"┋

@@ -471,6 +475,10 @@ template SQLiteFormatAndLoadObject() { 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) ? ("●  " ~ _txt) : _txt; _txt = inline_markup(doc_matters, obj, _txt); @@ -488,6 +496,10 @@ template SQLiteFormatAndLoadObject() { 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"┋

%s @@ -501,6 +513,10 @@ template SQLiteFormatAndLoadObject() { 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"┋

%s @@ -514,6 +530,10 @@ template SQLiteFormatAndLoadObject() { 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"┋

%s

┋", @@ -526,6 +546,10 @@ template SQLiteFormatAndLoadObject() { 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"┋

%s

┋", obj.metainfo.is_a, @@ -536,6 +560,10 @@ template SQLiteFormatAndLoadObject() { 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"┋

%s

┋", obj.metainfo.is_a, @@ -547,6 +575,10 @@ template SQLiteFormatAndLoadObject() { 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/src/doc_reform/output/xmls.d b/src/doc_reform/output/xmls.d index 266ad55..244a618 100644 --- a/src/doc_reform/output/xmls.d +++ b/src/doc_reform/output/xmls.d @@ -338,7 +338,10 @@ template outputXHTMLs() { rgx.inline_image, ("$1 $6")); + ~ "$3\" width=\"$4\" height=\"$5\" naturalsizeflag=\"0\" align=\"bottom\" border=\"0\" /> $6")) + .replaceAll( + rgx.inline_link_empty, + ("$1")); } return _txt; } -- cgit v1.2.3