summaryrefslogtreecommitdiffhomepage
path: root/dlang/src/read/html.d
diff options
context:
space:
mode:
authorRalph Amissah <ralph.amissah@gmail.com>2026-09-29 19:37:04 -0400
committerRalph Amissah <ralph.amissah@gmail.com>2026-10-02 21:38:49 -0400
commit33821eb37c78b00fedd7b0454ec0b77aeb8342ff (patch)
tree7b0745dee88103c8e7c89c9685fe1e9e0cdac152 /dlang/src/read/html.d
parentD: what a source holds, and what a database holds unread (diff)
D: ocda-read, the reader, over the library, of every form
One reader where there were two. sisudoc-ssp-reader read a .ssp and sisudoc-ocda-db-reader a .ocda.db, each with its own parser; this one is built on the library, so every mode reads a .ssp, a .ocda.db and a .sisupod, and says the same thing of each. Its output modules are the .ssp reader's, copied (the reader repositories are unchanged) and moved onto the library's model, which was the reader's types renamed and added to. From the database reader, --languages and --files. ocda-read [--tree|--outline|--html|--llm-text|--llm-jsonl|--images| --verify --image-dir=<d>|--languages|--files| --report-unknown|--validate] <file> [lang] Two modes are about the file and say so: --files answers for a .ocda.db, and --validate checks a .ssp as text and refuses anything else. Where a file holds several languages and none is named, every form reads the first and says so, where the database used to take one and the pod refuse. In src/read/ beside the library in src/ocda/; dub.json keeps it out of the library (configurations "library" and "ocda-read"), and the flake builds it as a package. The flake's default is now all three programs in one bin/: built separately into the same result link, each replaced the one before, and the pipeline's dump looked for ocda-dump where only ocda-agree was left. Checked over the 36 document-languages: - against the .ssp reader, on a .ssp, byte for byte after the first line (Parsed: is Read:): --tree, --html, --llm-text, --llm-jsonl, --images, --verify, --validate, 36 of 36; the summary differs only in the closing hint, which names the two new modes; - against the database reader, on a .ocda.db: --files 27 of 27, and --languages 27 of 27 on language, source and digest (its id column, the database's own key, is left out); - the same output from the .ssp, the .ocda.db and the .sisupod: the summary and --tree, --html, --llm-text, --llm-jsonl, --images and --report-unknown, 36 of 36; --languages, .ocda.db == .sisupod 27 of 27, and a single-language .ssp == its database, 26 of 26. Not reproduced, deliberately: the database reader's --outline, which ordered the headings by their position within their own section, so that the toc and the "(skip)" headings of other sections fell among the body's. --outline here is --tree. (assisted by Claude-Code)
Diffstat (limited to 'dlang/src/read/html.d')
-rw-r--r--dlang/src/read/html.d388
1 files changed, 388 insertions, 0 deletions
diff --git a/dlang/src/read/html.d b/dlang/src/read/html.d
new file mode 100644
index 0000000..cd679e4
--- /dev/null
+++ b/dlang/src/read/html.d
@@ -0,0 +1,388 @@
+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 ~= `<div class="title">`;
+ buf ~= `<h1>` ~ htmlEscape(doc.meta("title.main")) ~ `</h1>`;
+ if (doc.meta("title.subtitle").length > 0)
+ buf ~= `<h2 class="subtitle">` ~ htmlEscape(doc.meta("title.subtitle")) ~ `</h2>`;
+ buf ~= `<p class="author">` ~ htmlEscape(doc.meta("creator.author")) ~ `</p>`;
+ buf ~= `</div>`;
+ }
+
+ /+ ↓ table of contents +/
+ if (doc.toc.length > 0) {
+ buf ~= `<div class="toc">`;
+ buf ~= `<h2>Table of Contents</h2>`;
+ 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 ~= `<p class="` ~ cls ~ `">` ~ text ~ `</p>`;
+ }
+ }
+ buf ~= `</div>`;
+ buf ~= `<hr/>`;
+ }
+
+ /+ ↓ body +/
+ buf ~= `<div class="body">`;
+ foreach (obj; doc.body) {
+ buf ~= renderObject(obj);
+ }
+ buf ~= `</div>`;
+
+ /+ ↓ endnotes +/
+ bool has_endnotes = false;
+ foreach (obj; doc.endnotes) {
+ if (obj.is_a == "endnote") { has_endnotes = true; break; }
+ }
+ if (has_endnotes) {
+ buf ~= `<div class="endnotes">`;
+ buf ~= `<hr/>`;
+ buf ~= `<h2>Endnotes</h2>`;
+ foreach (obj; doc.endnotes) {
+ if (obj.is_a == "endnote") {
+ string text = convertInlineMarkup(obj.text);
+ string parent_ref = (obj.parent_ocn > 0)
+ ? ` <a href="#o` ~ obj.parent_ocn.to!string ~ `">[` ~ obj.parent_ocn.to!string ~ `]</a>`
+ : "";
+ buf ~= `<p class="endnote">` ~ text ~ parent_ref ~ `</p>`;
+ }
+ }
+ buf ~= `</div>`;
+ }
+
+ /+ ↓ glossary +/
+ if (doc.glossary.length > 0) {
+ buf ~= `<div class="glossary">`;
+ buf ~= `<hr/>`;
+ buf ~= `<h2>Glossary</h2>`;
+ foreach (obj; doc.glossary) {
+ string text = convertInlineMarkup(obj.text);
+ buf ~= `<p class="glossary-entry">` ~ text ~ `</p>`;
+ }
+ buf ~= `</div>`;
+ }
+
+ /+ ↓ bookindex +/
+ bool has_bookindex = false;
+ foreach (obj; doc.bookindex) {
+ if (obj.is_a == "bookindex") { has_bookindex = true; break; }
+ }
+ if (has_bookindex) {
+ buf ~= `<div class="bookindex">`;
+ buf ~= `<hr/>`;
+ buf ~= `<h2>Book Index</h2>`;
+ foreach (obj; doc.bookindex) {
+ if (obj.is_a == "bookindex") {
+ string text = convertInlineMarkup(obj.text);
+ buf ~= `<p class="index-entry">` ~ text ~ `</p>`;
+ }
+ }
+ buf ~= `</div>`;
+ }
+
+ 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)
+ ? `<span class="ocn">` ~ obj.ocn.to!string ~ `</span>`
+ : "";
+
+ 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 ~= `<p` ~ ocn_anchor ~ indent_cls ~ `>` ~ text ~ ocn_display ~ `</p>`;
+ break;
+ case "code":
+ lines ~= `<pre` ~ ocn_anchor ~ `><code>` ~ htmlEscape(obj.text) ~ `</code></pre>`;
+ break;
+ case "table":
+ lines ~= renderTable(obj, ocn_anchor);
+ break;
+ case "group":
+ lines ~= `<div` ~ ocn_anchor ~ ` class="group">` ~ text ~ `</div>`;
+ break;
+ case "block":
+ lines ~= `<pre` ~ ocn_anchor ~ ` class="block">` ~ htmlEscape(obj.text) ~ `</pre>`;
+ break;
+ case "verse":
+ lines ~= `<p` ~ ocn_anchor ~ ` class="verse">` ~ text.replace("\n", "<br/>\n") ~ ocn_display ~ `</p>`;
+ break;
+ case "quote":
+ lines ~= `<blockquote` ~ ocn_anchor ~ `>` ~ text ~ ocn_display ~ `</blockquote>`;
+ break;
+ default:
+ if (text.length > 0)
+ lines ~= `<p` ~ ocn_anchor ~ `>` ~ text ~ ocn_display ~ `</p>`;
+ 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` ~ ocn_anchor ~ `>`;
+ /+ ↓ 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 ~= `<tr>`;
+ foreach (cell; row.split("┊")) {
+ lines ~= `<` ~ tag ~ `>` ~ convertInlineMarkup(cell.strip) ~ `</` ~ tag ~ `>`;
+ }
+ lines ~= `</tr>`;
+ first_row = false;
+ }
+ lines ~= `</table>`;
+ 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, "⑆!", "!", "<b>", "</b>");
+ result = replaceInlineMarkerBracketed(result, "⑆!", "┨", "┣!", "<b>", "</b>");
+
+ /+ ↓ emphasis +/
+ result = replaceInlineMarker(result, "⑆*", "*", "<em>", "</em>");
+ result = replaceInlineMarkerBracketed(result, "⑆*", "┨", "┣*", "<em>", "</em>");
+
+ /+ ↓ italic +/
+ result = replaceInlineMarker(result, "⑆/", "/", "<i>", "</i>");
+ result = replaceInlineMarkerBracketed(result, "⑆/", "┨", "┣/", "<i>", "</i>");
+
+ /+ ↓ underscore +/
+ result = replaceInlineMarker(result, "⑆_", "_", "<u>", "</u>");
+ result = replaceInlineMarkerBracketed(result, "⑆_", "┨", "┣_", "<u>", "</u>");
+
+ /+ ↓ superscript +/
+ result = replaceInlineMarker(result, "⑆^", "^", "<sup>", "</sup>");
+ result = replaceInlineMarkerBracketed(result, "⑆^", "┨", "┣^", "<sup>", "</sup>");
+
+ /+ ↓ subscript +/
+ result = replaceInlineMarker(result, "⑆,", ",", "<sub>", "</sub>");
+ result = replaceInlineMarkerBracketed(result, "⑆,", "┨", "┣,", "<sub>", "</sub>");
+
+ /+ ↓ monospace +/
+ result = replaceInlineMarker(result, "⑆■", "■", "<code>", "</code>");
+
+ /+ ↓ links: ┥link text┝┤url├ +/
+ result = replaceLinks(result);
+
+ /+ ↓ footnote markers: 【N text】 +/
+ result = replaceFootnotes(result);
+
+ /+ ↓ line breaks +/
+ result = result.replace("┘", "<br/>");
+ result = result.replace("┙", "<br/>");
+
+ /+ ↓ non-breaking spaces +/
+ result = result.replace("░", "&nbsp;");
+
+ /+ ↓ bullet markers +/
+ result = result.replace("● ", "&#8226; ");
+
+ /+ ↓ 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 <a href="url">link text</a> +/
+ 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]
+ ~ `<a href="` ~ url ~ `">` ~ link_text ~ `</a>`
+ ~ 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]
+ ~ `<sup class="fn">` ~ note_num ~ `</sup>`
+ ~ result[fn_close + "】".length .. $];
+ }
+ return result;
+}
+
+string htmlEscape(string text) {
+ return text.replace("&", "&amp;").replace("<", "&lt;").replace(">", "&gt;")
+ .replace("\"", "&quot;");
+}
+
+private string[] htmlHead(OcdaDocument doc) {
+ string[] lines;
+ lines ~= `<!DOCTYPE html>`;
+ lines ~= `<html>`;
+ lines ~= `<head>`;
+ lines ~= `<meta charset="utf-8"/>`;
+ lines ~= `<title>` ~ htmlEscape(doc.meta("title.main")) ~ `</title>`;
+ lines ~= `<style>`;
+ lines ~= ` body { max-width: 48em; margin: 2em auto; padding: 0 1em; font-family: serif; line-height: 1.5; }`;
+ lines ~= ` .title { text-align: center; margin-bottom: 2em; }`;
+ lines ~= ` .subtitle { font-weight: normal; font-style: italic; }`;
+ lines ~= ` .ocn { float: right; font-size: 0.7em; color: #999; }`;
+ lines ~= ` .toc { margin-bottom: 2em; }`;
+ lines ~= ` .toc-entry { margin: 0.2em 0; }`;
+ lines ~= ` .toc-sub { margin: 0.2em 0 0.2em 2em; }`;
+ lines ~= ` .indent-1 { margin-left: 2em; }`;
+ lines ~= ` .indent-2 { margin-left: 4em; }`;
+ lines ~= ` .indent-3 { margin-left: 6em; }`;
+ lines ~= ` .bullet { margin-left: 2em; }`;
+ lines ~= ` .bullet:before { content: "\2022 "; }`;
+ lines ~= ` .verse { white-space: pre-wrap; font-style: italic; }`;
+ lines ~= ` .group { margin: 1em 2em; }`;
+ lines ~= ` .block { margin: 1em 2em; background: #f8f8f8; padding: 1em; }`;
+ lines ~= ` pre code { display: block; background: #f4f4f4; padding: 1em; overflow-x: auto; }`;
+ lines ~= ` table { border-collapse: collapse; margin: 1em 0; }`;
+ lines ~= ` th, td { border: 1px solid #ccc; padding: 0.4em 0.8em; }`;
+ lines ~= ` th { background: #f0f0f0; }`;
+ lines ~= ` .endnote { font-size: 0.9em; }`;
+ lines ~= ` .fn { color: #666; }`;
+ lines ~= ` .index-entry { font-size: 0.9em; }`;
+ lines ~= ` blockquote { margin: 1em 2em; padding-left: 1em; border-left: 3px solid #ccc; }`;
+ lines ~= `</style>`;
+ lines ~= `</head>`;
+ lines ~= `<body>`;
+ return lines;
+}
+
+private string[] htmlTail() {
+ return [`</body>`, `</html>`];
+}