module read.html;
import std.array : replace, split, join, appender;
import std.conv : to;
import std.stdio : writeln, File;
import std.string : strip, indexOf, startsWith;
import ocda.model;
void outputHtmlScroll(OcdaDocument doc, string output_file) {
auto buf = appender!(string[]);
buf ~= htmlHead(doc);
/+ ↓ title +/
if (doc.head.length > 0) {
auto title_obj = doc.head[0];
buf ~= `
`;
buf ~= `
` ~ htmlEscape(doc.meta("title.main")) ~ `
`;
if (doc.meta("title.subtitle").length > 0)
buf ~= `
` ~ htmlEscape(doc.meta("title.subtitle")) ~ `
`;
buf ~= `
` ~ htmlEscape(doc.meta("creator.author")) ~ `
`;
buf ~= `
`;
}
/+ ↓ table of contents +/
if (doc.toc.length > 0) {
buf ~= ``;
buf ~= `
Table of Contents
`;
foreach (obj; doc.toc) {
if (obj.is_a == "toc") {
string text = convertInlineMarkup(obj.text);
int indent = obj.indent_base;
string cls = (indent > 4) ? "toc-sub" : "toc-entry";
buf ~= `
` ~ text ~ `
`;
}
}
buf ~= `
`;
buf ~= `
`;
}
/+ ↓ body +/
buf ~= ``;
foreach (obj; doc.body) {
buf ~= renderObject(obj);
}
buf ~= `
`;
/+ ↓ endnotes +/
bool has_endnotes = false;
foreach (obj; doc.endnotes) {
if (obj.is_a == "endnote") { has_endnotes = true; break; }
}
if (has_endnotes) {
buf ~= ``;
buf ~= `
`;
buf ~= `
Endnotes
`;
foreach (obj; doc.endnotes) {
if (obj.is_a == "endnote") {
string text = convertInlineMarkup(obj.text);
string parent_ref = (obj.parent_ocn > 0)
? `
[` ~ obj.parent_ocn.to!string ~ `]`
: "";
buf ~= `
` ~ text ~ parent_ref ~ `
`;
}
}
buf ~= `
`;
}
/+ ↓ glossary +/
if (doc.glossary.length > 0) {
buf ~= ``;
buf ~= `
`;
buf ~= `
Glossary
`;
foreach (obj; doc.glossary) {
string text = convertInlineMarkup(obj.text);
buf ~= `
` ~ text ~ `
`;
}
buf ~= `
`;
}
/+ ↓ bookindex +/
bool has_bookindex = false;
foreach (obj; doc.bookindex) {
if (obj.is_a == "bookindex") { has_bookindex = true; break; }
}
if (has_bookindex) {
buf ~= ``;
buf ~= `
`;
buf ~= `
Book Index
`;
foreach (obj; doc.bookindex) {
if (obj.is_a == "bookindex") {
string text = convertInlineMarkup(obj.text);
buf ~= `
` ~ text ~ `
`;
}
}
buf ~= `
`;
}
buf ~= htmlTail();
/+ ↓ write output +/
string[] output = buf.data;
if (output_file.length > 0) {
auto f = File(output_file, "w");
foreach (line; output) f.writeln(line);
} else {
foreach (line; output) writeln(line);
}
}
private string[] renderObject(OcdaObject obj) {
/+ ↓ markup commentary is carried by the abstraction and is not output.
Rendering it would put the author notes into the document, which
spine itself does not do
+/
if (!obj.renders) { return []; }
string[] lines;
string text = convertInlineMarkup(obj.text);
string ocn_anchor = (obj.ocn > 0 && !obj.ocn_off)
? ` id="o` ~ obj.ocn.to!string ~ `"`
: "";
string ocn_display = (obj.ocn > 0 && !obj.ocn_off)
? `` ~ obj.ocn.to!string ~ ``
: "";
switch (obj.is_a) {
case "heading":
string tag = headingTag(obj.heading_level);
string seg_anchor = (obj.segment.length > 0)
? ` id="` ~ htmlEscape(obj.segment) ~ `"`
: ocn_anchor;
lines ~= `<` ~ tag ~ seg_anchor ~ `>` ~ text ~ `` ~ tag ~ `>`;
break;
case "para":
string indent_cls = "";
if (obj.indent_base > 0) indent_cls = ` class="indent-` ~ obj.indent_base.to!string ~ `"`;
else if (obj.bullet) indent_cls = ` class="bullet"`;
lines ~= `` ~ text ~ ocn_display ~ `
`;
break;
case "code":
lines ~= `` ~ htmlEscape(obj.text) ~ `
`;
break;
case "table":
lines ~= renderTable(obj, ocn_anchor);
break;
case "group":
lines ~= `` ~ text ~ `
`;
break;
case "block":
lines ~= `` ~ htmlEscape(obj.text) ~ `
`;
break;
case "verse":
lines ~= `` ~ text.replace("\n", "
\n") ~ ocn_display ~ `
`;
break;
case "quote":
lines ~= `` ~ text ~ ocn_display ~ `
`;
break;
default:
if (text.length > 0)
lines ~= `` ~ text ~ ocn_display ~ `
`;
break;
}
return lines;
}
private string headingTag(string level) {
switch (level) {
case "A": return "h1";
case "B": return "h2";
case "C": return "h3";
case "D": return "h4";
case "1": return "h3";
case "2": return "h4";
case "3": return "h5";
case "4": return "h6";
default: return "h4";
}
}
private string renderTable(OcdaObject obj, string ocn_anchor) {
string[] lines;
lines ~= ``;
/+ ↓ table content uses ┊ as cell separator, rows separated by newlines +/
auto rows = obj.text.split("\n");
bool first_row = obj.table_header;
foreach (row; rows) {
if (row.strip.length == 0) continue;
string tag = first_row ? "th" : "td";
lines ~= ``;
foreach (cell; row.split("┊")) {
lines ~= `<` ~ tag ~ `>` ~ convertInlineMarkup(cell.strip) ~ `` ~ tag ~ `>`;
}
lines ~= `
`;
first_row = false;
}
lines ~= `
`;
return lines.join("\n");
}
/+ ↓ convert spine internal Unicode markup to HTML +/
string convertInlineMarkup(string text) {
if (text.length == 0) return "";
string result = htmlEscape(text);
/+ ↓ font face markers: ⑆*bold⑆*, ⑆/italic⑆/, etc.
Pattern: ⑆X┨content┣X or ⑆Xcontent⑆X
The ┨┣ form is used within heading content +/
/+ ↓ bold +/
result = replaceInlineMarker(result, "⑆!", "!", "", "");
result = replaceInlineMarkerBracketed(result, "⑆!", "┨", "┣!", "", "");
/+ ↓ emphasis +/
result = replaceInlineMarker(result, "⑆*", "*", "", "");
result = replaceInlineMarkerBracketed(result, "⑆*", "┨", "┣*", "", "");
/+ ↓ italic +/
result = replaceInlineMarker(result, "⑆/", "/", "", "");
result = replaceInlineMarkerBracketed(result, "⑆/", "┨", "┣/", "", "");
/+ ↓ underscore +/
result = replaceInlineMarker(result, "⑆_", "_", "", "");
result = replaceInlineMarkerBracketed(result, "⑆_", "┨", "┣_", "", "");
/+ ↓ superscript +/
result = replaceInlineMarker(result, "⑆^", "^", "", "");
result = replaceInlineMarkerBracketed(result, "⑆^", "┨", "┣^", "", "");
/+ ↓ subscript +/
result = replaceInlineMarker(result, "⑆,", ",", "", "");
result = replaceInlineMarkerBracketed(result, "⑆,", "┨", "┣,", "", "");
/+ ↓ monospace +/
result = replaceInlineMarker(result, "⑆■", "■", "", "");
/+ ↓ links: ┥link text┝┤url├ +/
result = replaceLinks(result);
/+ ↓ footnote markers: 【N text】 +/
result = replaceFootnotes(result);
/+ ↓ line breaks +/
result = result.replace("┘", "
");
result = result.replace("┙", "
");
/+ ↓ non-breaking spaces +/
result = result.replace("░", " ");
/+ ↓ bullet markers +/
result = result.replace("● ", "• ");
/+ ↓ page break markers +/
result = result.replace("┼", "").replace("┿", "").replace("╂", "");
return result;
}
private string replaceInlineMarker(string text, string open_mark, string close_suffix, string html_open, string html_close) {
/+ ↓ replace ⑆Xcontent⑆X pattern (no bracket form) +/
string result = text;
while (true) {
auto open_pos = result.indexOf(open_mark);
if (open_pos < 0) break;
auto after_open = open_pos + open_mark.length;
/+ ↓ look for closing ⑆X +/
string close_mark = "⑆" ~ close_suffix;
auto close_pos = indexOf(result[after_open .. $], close_mark);
if (close_pos < 0) break;
close_pos += after_open;
string content = result[after_open .. close_pos];
result = result[0 .. open_pos] ~ html_open ~ content ~ html_close
~ result[close_pos + close_mark.length .. $];
}
return result;
}
private string replaceInlineMarkerBracketed(string text, string open_mark, string bracket_open, string bracket_close, string html_open, string html_close) {
/+ ↓ replace ⑆X┨content┣X pattern (bracketed form) +/
string result = text;
string full_open = open_mark ~ bracket_open;
while (true) {
auto open_pos = result.indexOf(full_open);
if (open_pos < 0) break;
auto after_open = open_pos + full_open.length;
auto close_pos = indexOf(result[after_open .. $], bracket_close);
if (close_pos < 0) break;
close_pos += after_open;
string content = result[after_open .. close_pos];
result = result[0 .. open_pos] ~ html_open ~ content ~ html_close
~ result[close_pos + bracket_close.length .. $];
}
return result;
}
private string replaceLinks(string text) {
/+ ↓ replace ┥link text┝┤url├ with link text +/
string result = text;
while (true) {
auto link_open = result.indexOf("┥");
if (link_open < 0) break;
auto link_mid = indexOf(result[link_open .. $], "┝┤");
if (link_mid < 0) break;
link_mid += link_open;
auto link_close = indexOf(result[link_mid .. $], "├");
if (link_close < 0) break;
link_close += link_mid;
string link_text = result[link_open + "┥".length .. link_mid];
string url = result[link_mid + "┝┤".length .. link_close];
/+ ↓ handle internal links (¤ prefix) +/
if (url.length > 0 && url[0] == '¤') {
url = url[("¤").length .. $];
}
/+ ↓ handle OCN-only links (#N) +/
if (url.length > 0 && url[0] == '#') {
url = "#o" ~ url[1 .. $];
}
result = result[0 .. link_open]
~ `` ~ link_text ~ ``
~ result[link_close + "├".length .. $];
}
return result;
}
private string replaceFootnotes(string text) {
/+ ↓ replace 【N content】 with superscript note number +/
string result = text;
while (true) {
auto fn_open = result.indexOf("【");
if (fn_open < 0) break;
auto fn_close = indexOf(result[fn_open .. $], "】");
if (fn_close < 0) break;
fn_close += fn_open;
string fn_content = result[fn_open + "【".length .. fn_close];
/+ ↓ extract note number (first token before space) +/
auto space_pos = fn_content.indexOf(' ');
string note_num = (space_pos > 0) ? fn_content[0 .. space_pos] : fn_content;
result = result[0 .. fn_open]
~ `` ~ note_num ~ ``
~ result[fn_close + "】".length .. $];
}
return result;
}
string htmlEscape(string text) {
return text.replace("&", "&").replace("<", "<").replace(">", ">")
.replace("\"", """);
}
private string[] htmlHead(OcdaDocument doc) {
string[] lines;
lines ~= ``;
lines ~= ``;
lines ~= ``;
lines ~= ``;
lines ~= `` ~ htmlEscape(doc.meta("title.main")) ~ ``;
lines ~= ``;
lines ~= ``;
lines ~= ``;
return lines;
}
private string[] htmlTail() {
return [``, ``];
}