From bbe505c8d48e822c012c9820dfe93b83dc61bcab Mon Sep 17 00:00:00 2001 From: Ralph Amissah Date: Thu, 24 Sep 2026 16:33:53 -0400 Subject: --validate, and a second reader, in Gleam --validate: the specification, executed. A validator written from ssp-format-specification.md and from nothing else, so that a file can be held against the document rather than against an implementation. Each finding names the specification section it comes from, so a disagreement can be taken back to the text. It checks the version banner and its major part, the file shape and the order of the preamble blocks and the nine sections, the two spaces of a preamble pair, the object declaration and its sixteen kinds and eight heading levels, that a property is one of the 42 and in the emitted order, that text lines carry their prefix, the ten keys of doc_has, and that no line is of a shape the specification does not define. Every .ssp of the markup document samples validates clean. Five classes of deliberate breakage are caught: an unknown major version, a property that is not one of the 42, a property out of order, a kind that is not one of the sixteen, and a block that is neither preamble nor section. Writing it found two rules the specification implied and did not state (repeated properties are consecutive; no property follows the text), and both were written into it. One repository, a reader per language. The readers are not separate tools that share a name. They are the same specification implemented more than once, and the interesting thing about them is that they agree, so they are published as one thing with that claim at the top of it. The D reader moves to dlang/; the Gleam reader arrives at gleam/. The language directory is named for the language and not for the tool: gleam refuses a hyphenated package name, so ssp-reader cannot be a gleam package and must be ssp_reader. A .gitignore for the repository, denying everything and whitelisting what belongs, covering both languages. Both build under nix, sandboxed and without network. There is no gleam builder in nixpkgs and gleam build fetches from Hex, so the Gleam build uses nix-gleam's builder, kept in gleam/nix-gleam/ (MIT), which fetches each Hex package by the checksum manifest.toml already carries, with no hash to maintain; the result is an escript wrapped with erlang. The D reader depends on nothing beyond phobos, so --skip-registry=all is the whole of what it takes: ldc by default, dmd available as ssp-reader-dmd (given gcc14, GCC 15 having introduced nullptr in headers dmd's ImportC does not yet parse). (assisted by Claude-Code) --- dlang/src/output_llm_breadcrumbs.d | 182 +++++++++++++++++++++++++++++++++++++ 1 file changed, 182 insertions(+) create mode 100644 dlang/src/output_llm_breadcrumbs.d (limited to 'dlang/src/output_llm_breadcrumbs.d') diff --git a/dlang/src/output_llm_breadcrumbs.d b/dlang/src/output_llm_breadcrumbs.d new file mode 100644 index 0000000..5b240d2 --- /dev/null +++ b/dlang/src/output_llm_breadcrumbs.d @@ -0,0 +1,182 @@ +module output_llm_breadcrumbs; + +import std.array : replace, split, join; +import std.conv : to; +import std.stdio : writeln, File; +import std.string : strip, indexOf, stripRight; +import ssp_types; + +/+ ↓ plain structured text with heading breadcrumbs for direct LLM consumption + format: + ## Document Title > Chapter > Section > [OCN] + + Clean paragraph text with inline markup stripped. ++/ +void outputLlmBreadcrumbs(SspDocument doc, string output_file) { + string[] lines; + string doc_title = doc.meta("title.main"); + + /+ ↓ document header +/ + lines ~= "# " ~ doc_title; + if (doc.meta("title.subtitle").length > 0) + lines ~= "# " ~ doc.meta("title.subtitle"); + lines ~= "# " ~ doc.meta("creator.author"); + lines ~= ""; + + /+ ↓ build heading text lookup from ancestors +/ + string[int] heading_text; + foreach (obj; doc.head) { + if (obj.is_a == "heading" && obj.ocn > 0) + heading_text[obj.ocn] = stripMarkup(obj.text); + } + foreach (obj; doc.body) { + if (obj.is_a == "heading") + heading_text[obj.ocn] = stripMarkup(obj.text); + } + + /+ ↓ body objects +/ + string current_breadcrumb = ""; + foreach (obj; doc.body) { + if (obj.is_a == "heading") { + current_breadcrumb = buildBreadcrumb(doc_title, obj.heading_ancestors_text, obj); + lines ~= ""; + lines ~= "## " ~ current_breadcrumb; + lines ~= ""; + continue; + } + + /+ ↓ markup commentary is not content +/ + if (!obj.renders) { continue; } + + string text = stripMarkup(obj.text); + if (text.strip.length == 0) continue; + + string ocn_ref = (obj.ocn > 0 && !obj.ocn_off) + ? " [" ~ obj.ocn.to!string ~ "]" + : ""; + + switch (obj.is_a) { + case "para": + lines ~= text ~ ocn_ref; + lines ~= ""; + break; + case "code": + lines ~= "```"; + lines ~= obj.text; /+ preserve raw text for code +/ + lines ~= "```"; + lines ~= ""; + break; + case "table": + lines ~= text ~ ocn_ref; + lines ~= ""; + break; + case "verse": + lines ~= text ~ ocn_ref; + lines ~= ""; + break; + case "quote": + lines ~= "> " ~ text ~ ocn_ref; + lines ~= ""; + break; + case "group": + case "block": + lines ~= text ~ ocn_ref; + lines ~= ""; + break; + default: + if (text.length > 0) { + lines ~= text ~ ocn_ref; + lines ~= ""; + } + break; + } + } + + /+ ↓ write output +/ + if (output_file.length > 0) { + auto f = File(output_file, "w"); + foreach (line; lines) f.writeln(line); + } else { + foreach (line; lines) writeln(line); + } +} + +private string buildBreadcrumb(string doc_title, string ancestors_text, SspObject obj) { + /+ ↓ ancestors_text is pipe-separated: "Title|Part||Chapter|||" +/ + string[] parts; + if (ancestors_text.length > 0) { + foreach (part; ancestors_text.split("|")) { + string clean = stripMarkup(part).strip; + if (clean.length > 0 && clean != doc_title) { + /+ ↓ truncate very long heading text for breadcrumb +/ + if (clean.length > 60) + clean = clean[0 .. 57] ~ "..."; + parts ~= clean; + } + } + } + /+ ↓ add the current heading itself +/ + string heading_text = stripMarkup(obj.text).strip; + if (heading_text.length > 60) + heading_text = heading_text[0 .. 57] ~ "..."; + + string ocn_ref = (obj.ocn > 0) ? " [" ~ obj.ocn.to!string ~ "]" : ""; + + if (parts.length > 0) + return doc_title ~ " > " ~ parts.join(" > ") ~ " > " ~ heading_text ~ ocn_ref; + else + return doc_title ~ " > " ~ heading_text ~ ocn_ref; +} + +/+ ↓ strip all internal Unicode markup to produce clean plain text +/ +string stripMarkup(string text) { + if (text.length == 0) return ""; + string r = text; + + /+ ↓ links: ┥link text┝┤url├ -> link text +/ + while (true) { + auto lo = r.indexOf("┥"); + if (lo < 0) break; + auto lm = indexOf(r[lo .. $], "┝┤"); + if (lm < 0) break; + lm += lo; + auto lc = indexOf(r[lm .. $], "├"); + if (lc < 0) break; + lc += lm; + string link_text = r[lo + "┥".length .. lm]; + r = r[0 .. lo] ~ link_text ~ r[lc + "├".length .. $]; + } + + /+ ↓ footnotes: 【N content】 -> (remove entirely for clean text) +/ + while (true) { + auto fo = r.indexOf("【"); + if (fo < 0) break; + auto fc = indexOf(r[fo .. $], "】"); + if (fc < 0) break; + fc += fo; + r = r[0 .. fo] ~ r[fc + "】".length .. $]; + } + + /+ ↓ font face markers +/ + r = r.replace("⑆*", "").replace("⑆!", "").replace("⑆/", "") + .replace("⑆_", "").replace("⑆^", "").replace("⑆,", "") + .replace("⑆■", "") + .replace("┨", "").replace("┣*", "").replace("┣!", "") + .replace("┣/", "").replace("┣_", "").replace("┣^", "") + .replace("┣,", "").replace("┣", ""); + + /+ ↓ line breaks and special chars +/ + r = r.replace("┘", "\n").replace("┙", " ").replace("┚", "\n"); + r = r.replace("░", " "); + r = r.replace("● ", "- "); + r = r.replace("┼", "").replace("┿", "").replace("╂", ""); + + /+ ↓ table cell separators +/ + r = r.replace("┊", " | "); + + /+ ↓ clean up multiple spaces +/ + while (r.indexOf(" ") >= 0) + r = r.replace(" ", " "); + + return r.strip; +} -- cgit v1.2.3