From f5320e4c3a9b21209ad7fd7c089bf144cfb60971 Mon Sep 17 00:00:00 2001 From: Ralph Amissah Date: Fri, 28 Apr 2017 12:00:37 -0400 Subject: xml family, special characters, deal with once --- src/sdp/output_epub3.d | 31 ++++++++-------- src/sdp/output_html.d | 68 +++++++++++++++++----------------- src/sdp/output_xmls.d | 99 +++++++++++++++++++++++++++----------------------- 3 files changed, 104 insertions(+), 94 deletions(-) (limited to 'src') diff --git a/src/sdp/output_epub3.d b/src/sdp/output_epub3.d index ea33f2e..3df1992 100644 --- a/src/sdp/output_epub3.d +++ b/src/sdp/output_epub3.d @@ -273,6 +273,7 @@ template outputEPub3() { string suffix = ".xhtml"; foreach (part; doc_matters.keys_seq.seg) { foreach (obj; doc_abstraction[part]) { + string _txt = xhtml_format.special_characters(obj, obj.text); if (obj.is_a == "heading") { switch (obj.heading_lev_markup) { case 0: .. case 3: @@ -308,12 +309,12 @@ template outputEPub3() { foreach (top_level_heading; top_level_headings) { doc_epub3[segment_filename] ~= top_level_heading; } - auto t = xhtml_format.heading_seg(obj, suffix); + auto t = xhtml_format.heading_seg(obj, _txt, suffix); doc_epub3[segment_filename] ~= t[0]; doc_epub3_endnotes[segment_filename] ~= t[1]; break; case 5: .. case 7: - auto t = xhtml_format.heading_seg(obj, suffix); + auto t = xhtml_format.heading_seg(obj, _txt, suffix); doc_epub3[segment_filename] ~= t[0]; doc_epub3_endnotes[segment_filename] ~= t[1]; break; @@ -336,7 +337,7 @@ template outputEPub3() { case "para": switch (obj.is_a) { case "toc": - doc_epub3[segment_filename] ~= xhtml_format.toc(obj); + doc_epub3[segment_filename] ~= xhtml_format.toc_seg(obj, _txt); break; default: if ((doc_matters.opt_action_bool["debug"])) { @@ -357,7 +358,7 @@ template outputEPub3() { case "para": switch (obj.is_a) { case "para": - auto t = xhtml_format.para_seg(obj, suffix); + auto t = xhtml_format.para_seg(obj, _txt, suffix); doc_epub3[segment_filename] ~= t[0]; doc_epub3_endnotes[segment_filename] ~= t[1]; break; @@ -371,32 +372,32 @@ template outputEPub3() { case "block": switch (obj.is_a) { case "quote": - auto t = xhtml_format.quote_seg(obj, suffix); + auto t = xhtml_format.quote_seg(obj, _txt, suffix); doc_epub3[segment_filename] ~= to!string(t[0]); doc_epub3_endnotes[segment_filename] ~= t[1]; break; case "group": - auto t = xhtml_format.group_seg(obj, suffix); + auto t = xhtml_format.group_seg(obj, _txt, suffix); doc_epub3[segment_filename] ~= to!string(t[0]); doc_epub3_endnotes[segment_filename] ~= t[1]; break; case "block": - auto t = xhtml_format.block_seg(obj, suffix); + auto t = xhtml_format.block_seg(obj, _txt, suffix); doc_epub3[segment_filename] ~= to!string(t[0]); doc_epub3_endnotes[segment_filename] ~= t[1]; break; case "poem": // double check why both poem & verse break; case "verse": - auto t = xhtml_format.verse_seg(obj, suffix); + auto t = xhtml_format.verse_seg(obj, _txt, suffix); doc_epub3[segment_filename] ~= to!string(t[0]); doc_epub3_endnotes[segment_filename] ~= t[1]; break; case "code": - doc_epub3[segment_filename] ~= xhtml_format.code(obj); + doc_epub3[segment_filename] ~= xhtml_format.code(obj, _txt); break; case "table": - auto t = xhtml_format.para_seg(obj, suffix); + auto t = xhtml_format.para_seg(obj, _txt, suffix); doc_epub3[segment_filename] ~= t[0]; doc_epub3_endnotes[segment_filename] ~= t[1]; break; @@ -419,26 +420,26 @@ template outputEPub3() { case "para": switch (obj.is_a) { case "endnote": - auto t = xhtml_format.para_seg(obj, suffix); + auto t = xhtml_format.para_seg(obj, _txt, suffix); doc_epub3[segment_filename] ~= t[0]; break; case "glossary": - auto t = xhtml_format.para_seg(obj, suffix); + auto t = xhtml_format.para_seg(obj, _txt, suffix); doc_epub3[segment_filename] ~= t[0]; doc_epub3_endnotes[segment_filename] ~= t[1]; break; case "bibliography": - auto t = xhtml_format.para_seg(obj, suffix); + auto t = xhtml_format.para_seg(obj, _txt, suffix); doc_epub3[segment_filename] ~= t[0]; doc_epub3_endnotes[segment_filename] ~= t[1]; break; case "bookindex": - auto t = xhtml_format.para_seg(obj, suffix); + auto t = xhtml_format.para_seg(obj, _txt, suffix); doc_epub3[segment_filename] ~= t[0]; doc_epub3_endnotes[segment_filename] ~= t[1]; break; case "blurb": - auto t = xhtml_format.para_seg(obj, suffix); + auto t = xhtml_format.para_seg(obj, _txt, suffix); doc_epub3[segment_filename] ~= t[0]; doc_epub3_endnotes[segment_filename] ~= t[1]; break; diff --git a/src/sdp/output_html.d b/src/sdp/output_html.d index 155ad48..509ae43 100644 --- a/src/sdp/output_html.d +++ b/src/sdp/output_html.d @@ -42,16 +42,17 @@ template outputHTML() { string suffix = ".html"; foreach (part; doc_matters.keys_seq.scroll) { foreach (obj; doc_abstraction[part]) { + string _txt = xhtml_format.special_characters(obj, obj.text); switch (obj.use) { case "frontmatter": switch (obj.is_of) { case "para": switch (obj.is_a) { case "heading": - doc_html ~= xhtml_format.heading_scroll(obj, suffix); + doc_html ~= xhtml_format.heading_scroll(obj, _txt, suffix); break; case "toc": - doc_html ~= xhtml_format.para_scroll(obj, suffix); + doc_html ~= xhtml_format.para_scroll(obj, _txt, suffix); break; default: if ((doc_matters.opt_action_bool["debug"])) { @@ -72,10 +73,10 @@ template outputHTML() { case "para": switch (obj.is_a) { case "heading": - doc_html ~= xhtml_format.heading_scroll(obj, suffix); + doc_html ~= xhtml_format.heading_scroll(obj, _txt, suffix); break; case "para": - doc_html ~= xhtml_format.para_scroll(obj, suffix); + doc_html ~= xhtml_format.para_scroll(obj, _txt, suffix); break; default: if ((doc_matters.opt_action_bool["debug"])) { @@ -87,24 +88,24 @@ template outputHTML() { case "block": switch (obj.is_a) { case "quote": - doc_html ~= xhtml_format.quote_scroll(obj); + doc_html ~= xhtml_format.quote_scroll(obj, _txt); break; case "group": - doc_html ~= xhtml_format.group_scroll(obj); + doc_html ~= xhtml_format.group_scroll(obj, _txt); break; case "block": - doc_html ~= xhtml_format.block_scroll(obj); + doc_html ~= xhtml_format.block_scroll(obj, _txt); break; case "poem": break; case "verse": - doc_html ~= xhtml_format.verse_scroll(obj, suffix); + doc_html ~= xhtml_format.verse_scroll(obj, _txt, suffix); break; case "code": - doc_html ~= xhtml_format.code(obj); + doc_html ~= xhtml_format.code(obj, _txt); break; case "table": - doc_html ~= xhtml_format.table(obj); + doc_html ~= xhtml_format.table(obj, _txt); break; default: if ((doc_matters.opt_action_bool["debug"])) { @@ -125,22 +126,22 @@ template outputHTML() { case "para": switch (obj.is_a) { case "heading": - doc_html ~= xhtml_format.heading_scroll(obj, suffix); + doc_html ~= xhtml_format.heading_scroll(obj, _txt, suffix); break; case "endnote": - doc_html ~= xhtml_format.para_scroll(obj, suffix); + doc_html ~= xhtml_format.para_scroll(obj, _txt, suffix); break; case "glossary": - doc_html ~= xhtml_format.para_scroll(obj, suffix); + doc_html ~= xhtml_format.para_scroll(obj, _txt, suffix); break; case "bibliography": - doc_html ~= xhtml_format.para_scroll(obj, suffix); + doc_html ~= xhtml_format.para_scroll(obj, _txt, suffix); break; case "bookindex": - doc_html ~= xhtml_format.para_scroll(obj, suffix); + doc_html ~= xhtml_format.para_scroll(obj, _txt, suffix); break; case "blurb": - doc_html ~= xhtml_format.para_scroll(obj, suffix); + doc_html ~= xhtml_format.para_scroll(obj, _txt, suffix); break; default: if ((doc_matters.opt_action_bool["debug"])) { @@ -211,6 +212,7 @@ template outputHTML() { string suffix = ".html"; foreach (part; doc_matters.keys_seq.seg) { foreach (obj; doc_abstraction[part]) { + string _txt = xhtml_format.special_characters(obj, obj.text); if (obj.is_a == "heading") { // all headings: frontmatter, body & backmatter switch (obj.heading_lev_markup) { case 0: .. case 3: @@ -235,8 +237,8 @@ template outputHTML() { top_level_headings[3] = ""; goto default; default: - auto t = xhtml_format.heading_seg(obj, suffix); - top_level_headings[obj.heading_lev_markup] = t[0]; + auto t = xhtml_format.heading_seg(obj, _txt, suffix); + top_level_headings[obj.heading_lev_markup] = t[0]; // should probably have different css tagging (fontsize etc) break; } break; @@ -247,12 +249,12 @@ template outputHTML() { // writeln(top_level_heading); doc_html[segment_filename] ~= top_level_heading; } - auto t = xhtml_format.heading_seg(obj, suffix); + auto t = xhtml_format.heading_seg(obj, _txt, suffix); doc_html[segment_filename] ~= to!string(t[0]); doc_html_endnotes[segment_filename] ~= t[1]; break; case 5: .. case 7: - auto t = xhtml_format.heading_seg(obj, suffix); + auto t = xhtml_format.heading_seg(obj, _txt, suffix); doc_html[segment_filename] ~= to!string(t[0]); doc_html_endnotes[segment_filename] ~= t[1]; break; @@ -275,7 +277,7 @@ template outputHTML() { case "para": switch (obj.is_a) { case "toc": - auto t = xhtml_format.para_seg(obj, suffix); + auto t = xhtml_format.para_seg(obj, _txt, suffix); doc_html[segment_filename] ~= to!string(t[0]); break; default: @@ -297,7 +299,7 @@ template outputHTML() { case "para": switch (obj.is_a) { case "para": - auto t = xhtml_format.para_seg(obj, suffix); + auto t = xhtml_format.para_seg(obj, _txt, suffix); doc_html[segment_filename] ~= to!string(t[0]); doc_html_endnotes[segment_filename] ~= t[1]; break; @@ -311,32 +313,32 @@ template outputHTML() { case "block": switch (obj.is_a) { case "quote": - auto t = xhtml_format.quote_seg(obj, suffix); + auto t = xhtml_format.quote_seg(obj, _txt, suffix); doc_html[segment_filename] ~= to!string(t[0]); doc_html_endnotes[segment_filename] ~= t[1]; break; case "group": - auto t = xhtml_format.group_seg(obj, suffix); + auto t = xhtml_format.group_seg(obj, _txt, suffix); doc_html[segment_filename] ~= to!string(t[0]); doc_html_endnotes[segment_filename] ~= t[1]; break; case "block": - auto t = xhtml_format.block_seg(obj, suffix); + auto t = xhtml_format.block_seg(obj, _txt, suffix); doc_html[segment_filename] ~= to!string(t[0]); doc_html_endnotes[segment_filename] ~= t[1]; break; case "poem": break; case "verse": - auto t = xhtml_format.verse_seg(obj, suffix); + auto t = xhtml_format.verse_seg(obj, _txt, suffix); doc_html[segment_filename] ~= to!string(t[0]); doc_html_endnotes[segment_filename] ~= t[1]; // work on break; case "code": - doc_html[segment_filename] ~= xhtml_format.code(obj); + doc_html[segment_filename] ~= xhtml_format.code(obj, _txt); break; case "table": - doc_html[segment_filename] ~= xhtml_format.table(obj); + doc_html[segment_filename] ~= xhtml_format.table(obj, _txt); doc_html_endnotes[segment_filename] ~= ""; break; default: @@ -358,26 +360,26 @@ template outputHTML() { case "para": switch (obj.is_a) { case "endnote": - auto t = xhtml_format.para_seg(obj, suffix); + auto t = xhtml_format.para_seg(obj, _txt, suffix); doc_html[segment_filename] ~= t[0]; break; case "glossary": - auto t = xhtml_format.para_seg(obj, suffix); + auto t = xhtml_format.para_seg(obj, _txt, suffix); doc_html[segment_filename] ~= t[0]; doc_html_endnotes[segment_filename] ~= t[1]; break; case "bibliography": - auto t = xhtml_format.para_seg(obj, suffix); + auto t = xhtml_format.para_seg(obj, _txt, suffix); doc_html[segment_filename] ~= t[0]; doc_html_endnotes[segment_filename] ~= t[1]; break; case "bookindex": - auto t = xhtml_format.para_seg(obj, suffix); + auto t = xhtml_format.para_seg(obj, _txt, suffix); doc_html[segment_filename] ~= t[0]; doc_html_endnotes[segment_filename] ~= t[1]; break; case "blurb": - auto t = xhtml_format.para_seg(obj, suffix); + auto t = xhtml_format.para_seg(obj, _txt, suffix); doc_html[segment_filename] ~= t[0]; doc_html_endnotes[segment_filename] ~= t[1]; break; diff --git a/src/sdp/output_xmls.d b/src/sdp/output_xmls.d index 27b6585..347409e 100644 --- a/src/sdp/output_xmls.d +++ b/src/sdp/output_xmls.d @@ -31,12 +31,20 @@ template outputXHTMLs() { mixin SiSUoutputRgxInit; struct outputXHTMLs { auto rgx = Rgx(); - string special_characters(string _txt){ + string special_characters(O)( + auto return ref const O obj, + string _txt + ){ _txt = (_txt) - .replaceAll(rgx.xhtml_ampersand, "&") - .replaceAll(rgx.xhtml_less_than, "<") - .replaceAll(rgx.xhtml_greater_than, ">") - .replaceAll(rgx.xhtml_line_break, "
"); + .replaceAll(rgx.xhtml_ampersand, "&") + .replaceAll(rgx.xhtml_quotation, """) + .replaceAll(rgx.xhtml_less_than, "<") + .replaceAll(rgx.xhtml_greater_than, ">") + .replaceAll(rgx.nbsp_char, " "); + if (!(obj.is_a == "code")) { + _txt = (_txt) + .replaceAll(rgx.xhtml_line_break, "
"); + } return _txt; } string font_face(string _txt){ @@ -313,26 +321,25 @@ template outputXHTMLs() { } auto inline_markup_scroll(O)( auto return ref const O obj, + string _txt, string _suffix = ".html", ) { - string _txt = obj.text; - _txt = special_characters(_txt); _txt = inline_links(obj, _txt, _suffix, "scroll"); _txt = inline_notes_scroll(obj, _txt); return _txt; } auto inline_markup_seg(O)( auto return ref const O obj, + string _txt, string _suffix = ".html", ) { - string _txt = obj.text; - _txt = special_characters(_txt); _txt = inline_links(obj, _txt, _suffix, "seg"); auto t = inline_notes_seg(obj, _txt); return t; } - auto toc(O)( + auto toc_seg(O)( auto return ref const O obj, + string _txt, ) { string o; o = format(q"¶
@@ -343,7 +350,7 @@ template outputXHTMLs() { obj.is_a, obj.indent_hang, obj.indent_base, - obj.text + _txt, ); return o; } @@ -395,19 +402,21 @@ template outputXHTMLs() { } auto heading_scroll(O)( auto return ref const O obj, + string _txt, string _suffix = ".html", ) { auto tags = _xhtml_anchor_tags(obj.anchor_tags); - string _txt = inline_markup_scroll(obj, _suffix); // issue + _txt = inline_markup_scroll(obj, _txt, _suffix); // issue string o = heading(obj, _txt); return o; } auto heading_seg(O)( auto return ref const O obj, + string _txt, string _suffix = ".html", ) { - auto t = inline_markup_seg(obj, _suffix); - string _txt = t[0]; + auto t = inline_markup_seg(obj, _txt, _suffix); + _txt = t[0]; string[] _endnotes = t[1]; string o = heading(obj, _txt); auto u = tuple( @@ -457,19 +466,21 @@ template outputXHTMLs() { } auto para_scroll(O)( auto return ref const O obj, + string _txt, string _suffix = ".html", ) { auto tags = _xhtml_anchor_tags(obj.anchor_tags); - string _txt = inline_markup_scroll(obj, _suffix); // issue + _txt = inline_markup_scroll(obj, _txt, _suffix); // issue string o = para(obj, _txt); return o; } auto para_seg(O)( auto return ref const O obj, + string _txt, string _suffix = ".html", ) { - auto t = inline_markup_seg(obj, _suffix); - string _txt = to!string(t[0]); + auto t = inline_markup_seg(obj, _txt, _suffix); + _txt = to!string(t[0]); string[] _endnotes = t[1]; string o = para(obj, _txt); auto u = tuple( @@ -511,19 +522,21 @@ template outputXHTMLs() { } auto quote_scroll(O)( auto return ref const O obj, + string _txt, string _suffix = ".html", ) { auto tags = _xhtml_anchor_tags(obj.anchor_tags); - string _txt = inline_markup_scroll(obj, _suffix); // issue + _txt = inline_markup_scroll(obj, _txt, _suffix); // issue string o = quote(obj, _txt); return o; } auto quote_seg(O)( auto return ref const O obj, + string _txt, string _suffix = ".html", ) { - auto t = inline_markup_seg(obj, _suffix); - string _txt = to!string(t[0]); + auto t = inline_markup_seg(obj, _txt, _suffix); + _txt = to!string(t[0]); string[] _endnotes = t[1]; string o = quote(obj, _txt); auto u = tuple( @@ -565,19 +578,21 @@ template outputXHTMLs() { } auto group_scroll(O)( auto return ref const O obj, + string _txt, string _suffix = ".html", ) { auto tags = _xhtml_anchor_tags(obj.anchor_tags); - string _txt = inline_markup_scroll(obj, _suffix); // issue + _txt = inline_markup_scroll(obj, _txt, _suffix); // issue string o = group(obj, _txt); return o; } auto group_seg(O)( auto return ref const O obj, + string _txt, string _suffix = ".html", ) { - auto t = inline_markup_seg(obj, _suffix); - string _txt = to!string(t[0]); + auto t = inline_markup_seg(obj, _txt, _suffix); + _txt = to!string(t[0]); string[] _endnotes = t[1]; string o = group(obj, _txt); auto u = tuple( @@ -615,19 +630,21 @@ template outputXHTMLs() { } auto block_scroll(O)( auto return ref const O obj, + string _txt, string _suffix = ".html", ) { auto tags = _xhtml_anchor_tags(obj.anchor_tags); - string _txt = inline_markup_scroll(obj, _suffix); // issue + _txt = inline_markup_scroll(obj, _txt, _suffix); // issue string o = block(obj, _txt); return o; } auto block_seg(O)( auto return ref const O obj, + string _txt, string _suffix = ".html", ) { - auto t = inline_markup_seg(obj, _suffix); - string _txt = to!string(t[0]); + auto t = inline_markup_seg(obj, _txt, _suffix); + _txt = to!string(t[0]); string[] _endnotes = t[1]; string o = block(obj, _txt); auto u = tuple( @@ -641,11 +658,6 @@ template outputXHTMLs() { string _txt, ) { _txt = font_face(_txt); - _txt = (_txt) - .replaceAll(rgx.newline, "
\n") - .replaceAll(rgx.two_spaces, " " ~ " " ~ " " ~ " ") - .replaceAll(rgx.nbsp_and_space, " " ~ " ") - .replaceAll(rgx.strip_br, ""); string o; if (obj.obj_cite_number.empty) { o = format(q"¶
@@ -670,19 +682,21 @@ template outputXHTMLs() { } auto verse_scroll(O)( auto return ref const O obj, + string _txt, string _suffix = ".html", ) { auto tags = _xhtml_anchor_tags(obj.anchor_tags); - string _txt = inline_markup_scroll(obj, _suffix); // issue + _txt = inline_markup_scroll(obj, _txt, _suffix); // issue string o = verse(obj, _txt); return o; } auto verse_seg(O)( auto return ref const O obj, + string _txt, string _suffix = ".html", ) { - auto t = inline_markup_seg(obj, _suffix); - string _txt = to!string(t[0]); + auto t = inline_markup_seg(obj, _txt, _suffix); + _txt = to!string(t[0]); string[] _endnotes = t[1]; string o = verse(obj, _txt); auto u = tuple( @@ -726,8 +740,8 @@ template outputXHTMLs() { } auto table(O)( auto return ref const O obj, + string _txt, ) { - string _txt = obj.text; auto tags = _xhtml_anchor_tags(obj.anchor_tags); _txt = font_face(_txt); auto t = tablarize(obj, _txt); @@ -755,6 +769,7 @@ template outputXHTMLs() { } auto endnote(O)( auto return ref const O obj, + string _txt, ) { string o; o = format(q"¶

@@ -763,20 +778,14 @@ template outputXHTMLs() { obj.is_a, obj.indent_hang, obj.indent_base, - obj.text + _txt ); return o; } auto code(O)( auto return ref const O obj, + string _txt, ) { - string _txt = obj.text; - _txt = (_txt) - .replaceAll(rgx.xhtml_ampersand, "&") - .replaceAll(rgx.xhtml_quotation, """) - .replaceAll(rgx.xhtml_less_than, "<") - .replaceAll(rgx.xhtml_greater_than, ">") - .replaceAll(rgx.nbsp_char, " "); string o; if (obj.obj_cite_number.empty) { o = format(q"¶

@@ -788,9 +797,7 @@ template outputXHTMLs() { } else { o = format(q"¶
-

-%s -

+

%s

¶", obj.obj_cite_number, obj.obj_cite_number, -- cgit v1.2.3