diff options
| -rw-r--r-- | .gitignore | 67 | ||||
| -rw-r--r-- | README.md | 84 | ||||
| -rw-r--r-- | dlang/README.md | 49 | ||||
| -rw-r--r-- | dlang/dub.json | 13 | ||||
| -rw-r--r-- | dlang/dub.selections.json | 1 | ||||
| -rw-r--r-- | dlang/flake.lock | 27 | ||||
| -rw-r--r-- | dlang/flake.nix | 49 | ||||
| -rw-r--r-- | dlang/src/ocda/load.d | 58 | ||||
| -rw-r--r-- | dlang/src/ocda/load_db.d | 265 | ||||
| -rw-r--r-- | dlang/src/ocda/load_ssp.d | 305 | ||||
| -rw-r--r-- | dlang/src/ocda/model.d | 143 | ||||
| -rw-r--r-- | dlang/src/ocda/sqlite.d | 101 | ||||
| -rw-r--r-- | dlang/test/agree.d | 84 |
13 files changed, 1246 insertions, 0 deletions
diff --git a/.gitignore b/.gitignore new file mode 100644 index 0000000..94d5386 --- /dev/null +++ b/.gitignore @@ -0,0 +1,67 @@ +# Deny everything, then whitelist what belongs in the repository. +# +# The practice is deliberate: a repository should hold what was decided to +# put in it, not whatever happened to be in the directory when someone ran +# "git add .". Build output, editor droppings, downloaded dependencies and +# exported binaries are numerous, are regenerated, and differ between +# machines; source is few and is chosen. So the default is no, and every +# yes below is a decision that can be read. +# +# To see what is being excluded, and why: +# git status --ignored +# git check-ignore -v <path> +# git ls-files --others --ignored --exclude-standard --directory + +* + +# ── the repository itself ──────────────────────────────────────────────── +!.gitignore +!README.md +!LICENSE + +# ── directories have to be walked into before a file inside can match ──── +!*/ +# but not these, whatever they contain +build/ +.build/ +.direnv/ +.gleam/ +bin/ +result +result-* + +# ── documentation and notes, in any language directory ─────────────────── +!**/*.md +!**/*.org + +# ── nix ────────────────────────────────────────────────────────────────── +!**/*.nix +!**/flake.lock +!**/.envrc + +# ── dlang ──────────────────────────────────────────────────────────────── +!**/*.d +!**/dub.json +!**/dub.sdl +!**/dub.selections.json +*.o +*.a +*.lst + +# ── gleam ──────────────────────────────────────────────────────────────── +!**/*.gleam +# gleam.toml is the manifest, manifest.toml is the lockfile: both belong +!**/*.toml +*.beam +*.ez +erl_crash.dump + +# ── ruby, when it arrives ──────────────────────────────────────────────── +!**/*.rb +!**/Gemfile +!**/Gemfile.lock +!**/*.gemspec + +# ── continuous integration ─────────────────────────────────────────────── +!**/*.yml +!**/*.yaml diff --git a/README.md b/README.md new file mode 100644 index 0000000..de115f1 --- /dev/null +++ b/README.md @@ -0,0 +1,84 @@ +# ocda-lib + +The **object-centric document abstraction as a library**: the model, and +loaders for both of the forms it is written in. + +**One reader per language, in a directory named for the language.** + +| | | +|---|---| +| [`dlang/`](dlang/) | D | +| `gleam/` | to come | +| `ruby/` | to come | + +## What it is for + +The readers in `ssp-reader` and `ocda-db-reader` each read one +serialisation and print. A **writer** needs neither: it needs the document. + +``` + .ssp ─┐ + ├─> the model ─> a writer + .ocda.db ─┘ +``` + +So this library holds the model and both loaders, and **a writer cannot +tell which serialisation it was handed** — exactly as spine's own writers +cannot, since spine 0.25.0. + +That is the whole of the idea. The readers become thin programs over this, +and the writers are functions from the model to bytes. + +## The check that matters + +The claim above is only true if the two loaders agree, so the library asks: + +```sh +nix build && ./result/bin/ocda-agree <doc>.ssp <doc>.ocda.db [lang] +``` + +It compares the two models object by object: citation number, kind, type, +part, parent, heading level, digest, text, ancestors and image count. + +**Over the reference collection the two loaders agree on 36 of 36 +document-languages.** They did not at first: see below. + +## What the check found, first time it was run + +Eight of thirty-six disagreed, and the cause was a defect in the `.ssp` +loader rather than a difference between the formats. + +An object whose **first text line is blank** lost it. The loader decided +whether to start a new line by asking whether the accumulated text was +empty, which is not the same question as whether a line has been seen. Of +the sample collection **seven documents have verse opening on a blank +line**, and in every one of them the blank was dropped. + +Nothing else had caught it. The two `.ssp` readers were compared on +*section counts*, which this does not change; spine's own output was never +diffed against the reader's. It took loading the same document two ways and +comparing the objects. + +Fixed here and in `ssp-reader/dlang`, which carried the same code. + +## What it reads, and what it does not + +| | | +|---|---| +| `.ssp` | yes | +| `.ocda.db` | yes, any language of it | +| `.sisupod` | not yet: unwrap the archive and read the `.ssp` inside it | +| `.sst`, `.ssm` markup | **no, and not planned**: that is a parser, which is spine's work | +| a url | no | + +`ocda/load.d` is the one place that decides what a path is, so a new input +type is added once and every reader and writer gains it. + +## The format + +Specified in **sisudoc-abstraction-format**: `ocda-model.md` for the model +this library implements, and the two format specifications for the loaders. +Section 4 of `ocda-db-format-specification.md` gives the column by column +correspondence that `load_db.d` follows. + +At format **2.x**. diff --git a/dlang/README.md b/dlang/README.md new file mode 100644 index 0000000..d1adb1c --- /dev/null +++ b/dlang/README.md @@ -0,0 +1,49 @@ +# ocda-lib, in D + +The abstraction's model and both its loaders, as a dub library. + +## Modules + +| | | +|---|---| +| `ocda.model` | the document, the object, the eight sections. Imports nothing | +| `ocda.load_ssp` | text -> model | +| `ocda.load_db` | sqlite -> model | +| `ocda.load` | what a path is, and loading it | +| `ocda.sqlite` | the sqlite3 C API, declared rather than depended upon | + +`ocda.model` importing nothing is the property that matters: a writer +depends on the model and on neither loader. + +## Use + +```json +"dependencies": { "ocda-lib": { "path": "../../ocda-lib/dlang" } } +``` + +```d +import ocda.load; +auto doc = load("document.ocda.db", "de"); // or "document.ssp" +foreach (obj; doc.body) { ... } +``` + +Link `sqlite3`; the library declares the dozen functions it needs rather +than taking a binding from the registry, so there is nothing to fetch. + +## The agreement check + +```sh +nix build +./result/bin/ocda-agree <doc>.ssp <doc>.ocda.db [lang] +``` + +`test/agree.d` is the whole of it: load both, compare the models. It is the +library's reason to exist, put to the question. + +## Build + +```sh +nix build # the agreement check +nix develop # ldc, dub, dtools, sqlite +dub build # the library +``` diff --git a/dlang/dub.json b/dlang/dub.json new file mode 100644 index 0000000..f49ef85 --- /dev/null +++ b/dlang/dub.json @@ -0,0 +1,13 @@ +{ + "authors": [ "Ralph Amissah" ], + "copyright": "Copyright (C) 2026 Ralph Amissah", + "name": "ocda-lib", + "version": "0.1.0", + "description": "the object-centric document abstraction as a library: the model, and loaders for its two serialisations", + "homepage": "https://sisudoc.org", + "license": "AGPL-3.0+", + "targetType": "library", + "sourcePaths": [ "./src" ], + "importPaths": [ "./src" ], + "libs": [ "sqlite3" ] +} diff --git a/dlang/dub.selections.json b/dlang/dub.selections.json new file mode 100644 index 0000000..84a60aa --- /dev/null +++ b/dlang/dub.selections.json @@ -0,0 +1 @@ +{ "fileVersion": 1, "versions": {} } diff --git a/dlang/flake.lock b/dlang/flake.lock new file mode 100644 index 0000000..5f236ab --- /dev/null +++ b/dlang/flake.lock @@ -0,0 +1,27 @@ +{ + "nodes": { + "nixpkgs": { + "locked": { + "lastModified": 1790185690, + "narHash": "sha256-xJ+X4hBtOcAFGBOe5nAMyMUeF9foJBmIOu3NjBqBycU=", + "owner": "NixOS", + "repo": "nixpkgs", + "rev": "4975466d324710c576dc11ad614684e6bd8cad8e", + "type": "github" + }, + "original": { + "owner": "NixOS", + "ref": "nixos-unstable", + "repo": "nixpkgs", + "type": "github" + } + }, + "root": { + "inputs": { + "nixpkgs": "nixpkgs" + } + } + }, + "root": "root", + "version": 7 +} diff --git a/dlang/flake.nix b/dlang/flake.nix new file mode 100644 index 0000000..954cad9 --- /dev/null +++ b/dlang/flake.nix @@ -0,0 +1,49 @@ +{ + description = "ocda-lib: the object-centric document abstraction as a D library"; + + inputs.nixpkgs.url = "github:NixOS/nixpkgs/nixos-unstable"; + + outputs = { self, nixpkgs }: + let + system = "x86_64-linux"; # adjust for aarch64-linux / darwin + pkgs = import nixpkgs { inherit system; }; + + /* A library, so there is nothing to install as a binary. What is + built here is the agreement check, which is the library's own + reason to exist put to the question: load a document's .ssp and + its .ocda.db and compare the two models. + */ + mkAgree = { compiler, compilerBin }: pkgs.stdenv.mkDerivation { + pname = "ocda-lib-agree"; + version = "0.1.0"; + src = self; + nativeBuildInputs = [ compiler ]; + buildInputs = [ pkgs.sqlite ]; + buildPhase = '' + runHook preBuild + export HOME=$TMPDIR + ${compilerBin} -I=src -of=agree src/ocda/*.d test/agree.d -L-lsqlite3 + runHook postBuild + ''; + installPhase = '' + runHook preInstall + mkdir -p $out/bin + install -m755 agree $out/bin/ocda-agree + runHook postInstall + ''; + meta = { + description = "checks that the .ssp and .ocda.db loaders give one model"; + mainProgram = "ocda-agree"; + }; + }; + in { + packages.${system} = { + default = self.packages.${system}.ocda-agree; + ocda-agree = mkAgree { compiler = pkgs.ldc; compilerBin = "ldmd2"; }; + }; + + devShells.${system}.default = pkgs.mkShell { + packages = [ pkgs.ldc pkgs.dub pkgs.dtools pkgs.sqlite ]; + }; + }; +} diff --git a/dlang/src/ocda/load.d b/dlang/src/ocda/load.d new file mode 100644 index 0000000..0f630bc --- /dev/null +++ b/dlang/src/ocda/load.d @@ -0,0 +1,58 @@ +module ocda.load; + +/+ ↓ what a path is, and loading it. + . + One place that decides, so that every reader and every writer accepts + the same inputs and a new input type is added once. This mirrors + spine's own ocda/abstraction/load.d, which names the sources it can + enter the pipeline from and tells them apart by suffix. + . + Deliberately *not* here: .sst and .ssm markup. Reading markup means + implementing the parser, which is spine's work and a far larger thing + than a reader or a sample writer needs. This library reads + abstractions. ++/ + +import std.algorithm : endsWith; +import ocda.model; +import ocda.load_ssp; +import ocda.load_db; + +enum Source { + ssp, // .ssp, the abstraction as text + ocda_db, // .ocda.db, the abstraction as sqlite + unknown, +} + +Source sourceOf(string path) { + if (path.endsWith(".ocda.db")) { return Source.ocda_db; } + if (path.endsWith(".ssp")) { return Source.ssp; } + if (path.endsWith(".db")) { return Source.ocda_db; } + return Source.unknown; +} + +string sourceName(Source s) { + final switch (s) { + case Source.ssp: return ".ssp (the abstraction as text)"; + case Source.ocda_db: return ".ocda.db (the abstraction as sqlite)"; + case Source.unknown: return "not an abstraction this library reads"; + } +} + +class OcdaLoadError : Exception { + this(string msg) { super(msg); } +} + +/+ ↓ load whatever the path is into the model. + lang applies only to a .ocda.db, which holds every language of its + document; a .ssp is one language and the argument is ignored. ++/ +OcdaDocument load(string path, string lang = "", bool any_version = false) { + final switch (sourceOf(path)) { + case Source.ssp: return parseSspFile(path); + case Source.ocda_db: return loadDbFile(path, lang, any_version); + case Source.unknown: + throw new OcdaLoadError(path ~ ": " ~ sourceName(Source.unknown) + ~ " (expected .ssp or .ocda.db)"); + } +} diff --git a/dlang/src/ocda/load_db.d b/dlang/src/ocda/load_db.d new file mode 100644 index 0000000..ffc28a8 --- /dev/null +++ b/dlang/src/ocda/load_db.d @@ -0,0 +1,265 @@ +module ocda.load_db; + +/+ ↓ build the model from a .ocda.db. + . + The point of this module is that it returns *the same value* + ocda.load_ssp returns from the same document's .ssp. A writer is then + a function from the model to bytes, and cannot tell which + serialisation it was given, exactly as spine's own writers cannot. + . + Written from the sisudoc-abstraction-format specification, + ocda-db-format-specification.md, whose section 4 gives the column by + column correspondence this module implements. ++/ + +import std.array : split; +import std.conv : to; +import std.string : strip; +import ocda.model; +import ocda.sqlite; + +/+ ↓ the schema major this loader knows (specification section 2) +/ +enum schema_major_read = "2"; + +class OcdaDbError : Exception { + this(string msg) { super(msg); } +} + +/+ ↓ every language the database holds, in manifest order +/ +struct DbLanguage { + int doc_id; + string lang; + string source_filename; + string ssp_digest; +} + +DbLanguage[] dbLanguages(ref Db db) { + DbLanguage[] out_; + foreach (r; db.rows( + "SELECT id, lang, coalesce(source_filename,''), coalesce(ssp_digest,'') + FROM documents ORDER BY id")) { + out_ ~= DbLanguage(r[0].to!int, r[1], r[2], r[3]); + } + return out_; +} + +/+ ↓ load one language of a database as the model. + lang == "" takes the first language the manifest gave. ++/ +OcdaDocument loadDbFile(string path, string lang = "", bool any_version = false) { + auto db = Db.open(path); + scope(exit) { db.close(); } + + if (!db.has("documents") || !db.has("objects") || !db.has("metadata")) { + throw new OcdaDbError(path ~ ": no documents/objects/metadata tables;" + ~ " it does not look like a .ocda.db"); + } + + /+ ↓ specification sections 2 and 3.2: the rows describing the file rather + than a document in it are the only ones with doc_id null +/ + string schema_version = db.one( + "SELECT value FROM metadata WHERE doc_id IS NULL AND key = 'schema.version'"); + if (schema_version.length > 0 && !any_version) { + auto major = schema_version.split(".")[0]; + if (major != schema_major_read) { + throw new OcdaDbError(path ~ " is schema v" ~ schema_version + ~ ", this loader knows v" ~ schema_major_read ~ ".x"); + } + } + + auto languages = dbLanguages(db); + if (languages.length == 0) { + throw new OcdaDbError(path ~ ": no documents rows"); + } + DbLanguage chosen = languages[0]; + if (lang.length > 0) { + bool found = false; + foreach (l; languages) { if (l.lang == lang) { chosen = l; found = true; break; } } + if (!found) { + string have; + foreach (i, l; languages) { have ~= (i > 0 ? " " : "") ~ l.lang; } + throw new OcdaDbError(path ~ ": no language '" ~ lang ~ "'; it holds: " ~ have); + } + } + + OcdaDocument doc; + doc.format_version = schema_version; + doc.source_filename = chosen.source_filename; + + /+ ↓ @source of the .ssp corresponds to the documents row and the + source.digest metadata (specification section 5.1 of the .ssp, and + section 7 here) +/ + doc.source["language"] = chosen.lang; + string languages_joined; + foreach (i, l; languages) { languages_joined ~= (i > 0 ? " " : "") ~ l.lang; } + doc.source["languages"] = languages_joined; + auto digest = db.one("SELECT value FROM metadata WHERE doc_id = " + ~ chosen.doc_id.to!string ~ " AND key = 'source.digest'"); + if (digest.length > 0) { doc.source["digest"] = digest; } + + /+ ↓ @meta: every metadata row of this language that is not a source.* + property. source.* describes the artefact rather than the document + and lives in @source in the text form. + +/ + foreach (r; db.rows("SELECT key, value FROM metadata WHERE doc_id = " + ~ chosen.doc_id.to!string ~ " ORDER BY key")) { + if (r[0].length > 7 && r[0][0 .. 7] == "source.") { continue; } + doc.metadata[r[0]] = r[1]; + } + + /+ ↓ the objects, in document order within each section +/ + foreach (r; db.rows( + "SELECT section, seq, ocn, is_a, coalesce(is_of_part,''), + coalesce(is_of_section,''), coalesce(is_of_type,''), + coalesce(heading_level,-1), coalesce(identifier,''), + coalesce(parent_ocn,0), coalesce(last_descendant_ocn,0), + coalesce(children,''), coalesce(ancestors,''), + coalesce(dummy_heading,0), coalesce(object_number_off,0), + coalesce(indent_base,0), coalesce(indent_hang,0), + coalesce(bullet,0), coalesce(lang,''), + coalesce(has_links,0), coalesce(has_notes_reg,0), + coalesce(has_notes_star,0), coalesce(has_images,0), + coalesce(segment,''), coalesce(segment_prev,''), + coalesce(segment_next,''), coalesce(anchor,''), + coalesce(segment_html_is,''), + coalesce(table_cols,0), coalesce(table_widths,''), + coalesce(table_aligns,''), coalesce(table_header,0), + coalesce(code_linenumbers,0), + coalesce(heading_ancestors_text,''), coalesce(sha256,''), + coalesce(text,''), id + FROM objects WHERE doc_id = " ~ chosen.doc_id.to!string + ~ " ORDER BY CASE section + WHEN 'head' THEN 1 WHEN 'toc' THEN 2 WHEN 'body' THEN 3 + WHEN 'endnotes' THEN 4 WHEN 'glossary' THEN 5 + WHEN 'bibliography' THEN 6 WHEN 'bookindex' THEN 7 + WHEN 'blurb' THEN 8 WHEN 'tail' THEN 9 ELSE 10 END, seq")) { + OcdaObject obj; + obj.section = r[0]; + obj.ocn = r[2].to!int; + obj.is_a = r[3]; + obj.part = r[4]; + obj.own_section = (r[5] == r[0]) ? "" : r[5]; + obj.is_of_type = r[6]; + /+ ↓ the database holds the level as a number, the text form as the + letter or digit the markup wrote. Model section 4 is the mapping. +/ + obj.heading_level = levelName(r[7].to!int); + obj.identifier = r[8]; + obj.parent_ocn = r[9].to!int; + obj.last_descendant_ocn = r[10].to!int; + obj.children = jsonInts(r[11]); + obj.ancestors = jsonInts(r[12]); + obj.dummy_heading = (r[13] != "0"); + obj.ocn_off = (r[14] != "0"); + obj.indent_base = r[15].to!int; + obj.indent_hang = r[16].to!int; + obj.bullet = (r[17] != "0"); + obj.lang = r[18]; + obj.has_links = (r[19] != "0"); + obj.has_notes_reg = (r[20] != "0"); + obj.has_notes_star = (r[21] != "0"); + obj.has_images = (r[22] != "0"); + obj.segment = r[23]; + obj.segment_prev = r[24]; + obj.segment_next = r[25]; + obj.anchor = r[26]; + obj.segment_html_is = r[27]; + obj.table_cols = r[28].to!int; + obj.table_widths = jsonWords(r[29]); + obj.table_aligns = jsonWords(r[30]); + obj.table_header = (r[31] != "0"); + obj.code_linenumbers = (r[32] != "0"); + obj.heading_ancestors_text = jsonJoined(r[33]); + obj.sha256 = r[34]; + obj.text = r[35]; + + /+ ↓ the four repeatable properties of the text form are child tables + here (specification section 4) +/ + string object_id = r[36]; + foreach (i; db.rows("SELECT name, coalesce(sha256,''), coalesce(bytes,0), + coalesce(width,0), coalesce(height,0), + coalesce(missing,0) + FROM object_images WHERE object_id = " ~ object_id + ~ " ORDER BY seq")) { + OcdaImage img; + img.name = i[0]; + img.sha256 = i[1]; + img.bytes = i[2].to!ulong; + img.width = i[3].to!int; + img.height = i[4].to!int; + img.missing = (i[5] != "0"); + obj.images ~= img; + } + foreach (l; db.rows("SELECT url FROM object_links WHERE object_id = " + ~ object_id ~ " ORDER BY seq")) { + obj.stow_link ~= l[0]; + } + + auto section = doc.sectionByName(r[0]); + if (section !is null) { *section ~= obj; } + } + return doc; +} + +/+ ↓ model section 4: the eight levels and their indices +/ +private string levelName(int index) { + switch (index) { + case 0: return "A"; + case 1: return "B"; + case 2: return "C"; + case 3: return "D"; + case 4: return "1"; + case 5: return "2"; + case 6: return "3"; + case 7: return "4"; + default: return ""; + } +} + +/+ ↓ the fixed width arrays are JSON in the database and space separated in + the text form (specification section 3.3) +/ +private int[] jsonInts(string v) { + int[] out_; + foreach (w; jsonWords(v).split(" ")) { + if (w.length == 0) { continue; } + try { out_ ~= w.to!int; } catch (Exception) {} + } + return out_; +} + +private string jsonWords(string v) { + string out_; + bool in_string = false; + foreach (c; v) { + switch (c) { + case '[': case ']': case ' ': break; + case '"': in_string = !in_string; break; + case ',': out_ ~= " "; break; + default: out_ ~= c; break; + } + } + return out_.strip; +} + +/+ ↓ heading_ancestors_text is eight slots, joined with "|" in the text + form and a JSON array here +/ +private string jsonJoined(string v) { + if (v.length == 0) { return ""; } + string out_; + bool in_string = false; + bool first = true; + string cur; + foreach (c; v) { + if (c == '"') { + in_string = !in_string; + if (!in_string) { + if (!first) { out_ ~= "|"; } + out_ ~= cur; + cur = ""; + first = false; + } + continue; + } + if (in_string) { cur ~= c; } + } + return out_; +} diff --git a/dlang/src/ocda/load_ssp.d b/dlang/src/ocda/load_ssp.d new file mode 100644 index 0000000..ccaa0f4 --- /dev/null +++ b/dlang/src/ocda/load_ssp.d @@ -0,0 +1,305 @@ +module ocda.load_ssp; + +import std.algorithm : splitter, startsWith; +import std.array : array, split; +import std.conv : to, ConvException; +import std.file : readText; +import std.stdio : writeln; +import std.string : strip, stripLeft, indexOf; +import ocda.model; + +OcdaDocument parseSspFile(string filename) { + string content = readText(filename); + return parseSsp(content); +} + +OcdaDocument parseSsp(string content) { + OcdaDocument doc; + OcdaObject current_obj; + bool in_object = false; + /+ ↓ whether a text line has been seen for the object being read. + Not "is the text non-empty": an object whose first text line is blank + (a verse opening on an empty line, which the sample set has seven of) + would then lose it, the next line overwriting rather than appending. + +/ + bool seen_text = false; + string current_section = ""; + string current_block = ""; // meta, make, doc_has, or section name + + foreach (line; content.splitter("\n")) { + /+ â comment. The first line of a .ssp declares the format version, and + it is the one comment that carries meaning: a reader checks the + major part and refuses what it does not know rather than loading + an unfamiliar artefact half populated in silence. + +/ + if (line.length > 0 && line[0] == '%') { + enum _banner = "% SiSU Document Abstraction v"; + enum _source = "% Source: "; + if (doc.format_version.length == 0 && line.startsWith(_banner)) { + doc.format_version = line[_banner.length .. $].strip; + } else if (doc.source_filename.length == 0 && line.startsWith(_source)) { + doc.source_filename = line[_source.length .. $].strip; + } + continue; + } + + /+ â blank line - finalize current object +/ + if (line.length == 0 || line.strip.length == 0) { + if (in_object) { + commitObject(doc, current_section, current_obj); + current_obj = OcdaObject.init; + in_object = false; + seen_text = false; + } + continue; + } + + /+ â section/block open +/ + if (line[0] == '@') { + auto brace_pos = line.indexOf('{'); + if (brace_pos > 0) { + string name = line[1 .. brace_pos].strip; + current_block = name; + if (!isPreambleBlock(name)) { + current_section = name; + /+ â a block that is neither preamble nor a section this reader + knows: counted, so that --report-unknown can say so +/ + if (doc.sectionByName(name) is null) { + doc.unknown.block[name]++; + } + } + } + continue; + } + + /+ â section/block close +/ + if (line[0] == '}') { + if (in_object) { + commitObject(doc, current_section, current_obj); + current_obj = OcdaObject.init; + in_object = false; + seen_text = false; + } + current_block = ""; + continue; + } + + /+ â inside meta/make/doc_has blocks: key-value pairs +/ + if (isPreambleBlock(current_block)) { + string stripped = line.stripLeft; + auto colon_pos = stripped.indexOf(':'); + if (colon_pos > 0) { + string key = stripped[0 .. colon_pos].strip; + string value = (colon_pos + 1 < stripped.length) + ? stripped[colon_pos + 1 .. $].strip : ""; + if (current_block == "meta") { doc.metadata[key] = value; } + else if (current_block == "make") { doc.make[key] = value; } + else if (current_block == "source") { doc.source[key] = value; } + else { doc.doc_has[key] = value; } + } + continue; + } + + /+ â object declaration: [N] type ... +/ + if (line[0] == '[') { + if (in_object) { + commitObject(doc, current_section, current_obj); + } + current_obj = OcdaObject.init; + current_obj.section = current_section; + in_object = true; + seen_text = false; + parseObjectDeclaration(line, current_obj); + continue; + } + + /+ â property: .name: value +/ + if (line[0] == '.') { + if (in_object) { + parseProperty(line, current_obj, doc.unknown); + } + continue; + } + + /+ â text content: | content +/ + if (line.length >= 1 && line[0] == '|') { + if (in_object) { + string text_content = (line.length > 2) ? line[2 .. $] : ""; + if (seen_text) { + current_obj.text ~= "\n" ~ text_content; + } else { + current_obj.text = text_content; + seen_text = true; + } + } + continue; + } + + /+ â no known shape. Counted by its first character so that a reader + can be told the file held something this one did not expect + +/ + doc.unknown.line[line[0 .. 1].idup]++; + } + + /+ â finalize last object +/ + if (in_object) { + commitObject(doc, current_section, current_obj); + } + + return doc; +} + +private void parseObjectDeclaration(string line, ref OcdaObject obj) { + /+ parse: [N] type :level identifier +/ + auto bracket_close = line.indexOf(']'); + if (bracket_close < 0) return; + try { + obj.ocn = line[1 .. bracket_close].strip.to!int; + } catch (ConvException) { + obj.ocn = 0; + } + string rest = (bracket_close + 1 < line.length) + ? line[bracket_close + 1 .. $].strip : ""; + if (rest.length == 0) return; + + auto parts = rest.split(" "); + if (parts.length == 0) return; + obj.is_a = parts[0]; + + if (obj.is_a == "heading" && parts.length >= 2) { + /+ parse :A, :B, :1, etc. +/ + string lev = parts[1]; + if (lev.length >= 2 && lev[0] == ':') { + obj.heading_level = lev[1 .. $]; + } + /+ optional identifier after level +/ + if (parts.length >= 3) { + obj.identifier = parts[2]; + } + } +} + +/+ â the blocks that are document preamble rather than sections of objects +/ +private bool isPreambleBlock(string name) { + return name == "source" || name == "meta" || name == "make" || name == "doc_has"; +} + +private void parseProperty(string line, ref OcdaObject obj, ref OcdaUnknown unknown) { + /+ parse: .name: value +/ + auto colon_pos = line.indexOf(':'); + if (colon_pos < 1) return; + string name = line[1 .. colon_pos].strip; + string value = (colon_pos + 1 < line.length) + ? line[colon_pos + 1 .. $].strip : ""; + + switch (name) { + case "part": obj.part = value; break; + case "is_of_type": obj.is_of_type = value; break; + case "section": obj.own_section = value; break; + case "identifier": obj.identifier = value; break; + case "segment_html_is": obj.segment_html_is = value; break; + case "table_aligns": obj.table_aligns = value; break; + case "stow_link": obj.stow_link ~= value; break; + case "parent": obj.parent_ocn = toIntSafe(value); break; + case "last_descendant": obj.last_descendant_ocn = toIntSafe(value); break; + case "children": obj.children = parseIntArray(value); break; + case "ancestors": obj.ancestors = parseIntArray(value); break; + case "dummy": obj.dummy_heading = (value == "true"); break; + case "ocn_off": obj.ocn_off = (value == "true"); break; + case "indent": + auto parts = value.split(" "); + if (parts.length >= 1) obj.indent_base = toIntSafe(parts[0]); + if (parts.length >= 2) obj.indent_hang = toIntSafe(parts[1]); + break; + case "bullet": obj.bullet = (value == "true"); break; + case "lang": obj.lang = value; break; + case "has": + foreach (flag; value.split(" ")) { + switch (flag) { + case "links": obj.has_links = true; break; + case "notes_reg": obj.has_notes_reg = true; break; + case "notes_star": obj.has_notes_star = true; break; + case "images": obj.has_images = true; break; + default: break; + } + } + break; + case "segment": obj.segment = value; break; + case "segment_prev": obj.segment_prev = value; break; + case "segment_next": obj.segment_next = value; break; + case "anchor": obj.anchor = value; break; + case "table_cols": obj.table_cols = toIntSafe(value); break; + case "table_widths": obj.table_widths = value; break; + case "table_header": obj.table_header = (value == "true"); break; + case "code_syntax": obj.code_syntax = value; break; + case "code_linenumbers": obj.code_linenumbers = (value == "true"); break; + case "heading_ancestors_text": obj.heading_ancestors_text = value; break; + case "sha256": obj.sha256 = value; break; + case "image": obj.images ~= parseImageRecord(value); break; + /+ â a property this reader has no use for, or has never heard of. + Ignored, which is the conforming behaviour within a major + version, but counted rather than passed over in silence + +/ + default: unknown.property[name]++; break; + } +} + +private OcdaImage parseImageRecord(string value) { + /+ parse: <filename> sha256:<HEX> bytes:<n> [key:value ...] + filename first, remaining fields order-independent; unrecognised + fields are kept rather than discarded +/ + OcdaImage img; + bool first = true; + foreach (field; value.split(" ")) { + if (field.length == 0) continue; + if (first) { + img.name = field; + first = false; + continue; + } + auto colon_pos = field.indexOf(':'); + if (colon_pos < 1) continue; + string key = field[0 .. colon_pos]; + string val = (colon_pos + 1 < field.length) ? field[colon_pos + 1 .. $] : ""; + switch (key) { + case "sha256": img.sha256 = val; break; + case "bytes": img.bytes = toUlongSafe(val); break; + case "px": + auto dims = val.split("x"); + if (dims.length == 2) { + img.width = toIntSafe(dims[0]); + img.height = toIntSafe(dims[1]); + } + break; + case "missing": img.missing = (val == "true"); break; + default: img.fields[key] = val; break; + } + } + return img; +} + +private void commitObject(ref OcdaDocument doc, string section, ref OcdaObject obj) { + auto sec = doc.sectionByName(section); + if (sec !is null) { + *sec ~= obj; + } +} + +private int toIntSafe(string s) { + try { return s.strip.to!int; } + catch (ConvException) { return 0; } +} + +private ulong toUlongSafe(string s) { + try { return s.strip.to!ulong; } + catch (ConvException) { return 0; } +} + +private int[] parseIntArray(string s) { + int[] result; + foreach (part; s.split(" ")) { + auto v = toIntSafe(part); + result ~= v; + } + return result; +} diff --git a/dlang/src/ocda/model.d b/dlang/src/ocda/model.d new file mode 100644 index 0000000..0ddefa1 --- /dev/null +++ b/dlang/src/ocda/model.d @@ -0,0 +1,143 @@ +module ocda.model; + +struct OcdaImage { + string name; // image filename as referenced by the object + string sha256; // hex-encoded (uppercase) digest of the file + ulong bytes; // file size + int width; // file's own pixel width (not display width) + int height; // file's own pixel height + bool missing; // file absent or unreadable, no sha256/bytes + string[string] fields; // any further/unrecognised key:value fields +} + +struct OcdaObject { + int ocn; + string is_a; // heading, para, toc, table, code, group, block, verse, quote, endnote, glossary, bibliography, bookindex, blurb + string section; // head, toc, body, endnotes, glossary, bibliography, bookindex, blurb + string heading_level; // A, B, C, D, 1, 2, 3, 4 (for headings) + string identifier; // heading: from the declaration line; otherwise .identifier + string part; // frontmatter, body, backmatter + string is_of_type; // para, block, comment: how the text behaves + string own_section; // .section, when it differs from the block it sits in + string segment_html_is;// the html segment this object sits in + string table_aligns; // l c r per column + string[] stow_link; // links extracted from the object + int parent_ocn; + int last_descendant_ocn; + int[] children; // direct child heading OCNs + int[] ancestors; // markedup_ancestors[8] + bool dummy_heading; + bool ocn_off; + int indent_base; + int indent_hang; + bool bullet; + string lang; + bool has_links; + bool has_notes_reg; + bool has_notes_star; + bool has_images; + string segment; + string segment_prev; + string segment_next; + string anchor; + int table_cols; + string table_widths; + bool table_header; + string code_syntax; + bool code_linenumbers; + string heading_ancestors_text; + string sha256; + OcdaImage[] images; // repeatable .image records, in order + string text; // content (lines joined with newline) + + /+ ↓ whether this object is rendered at all. + is_of_type "comment" is markup commentary: carried by the + abstraction so that nothing is lost, and not put into output. An + output that renders it leaks the author notes into the document, + which is what spine itself does not do. + +/ + bool renders() const { + return is_of_type != "comment"; + } + + /+ ↓ the section this object belongs to, which is the block it sits in + unless it says otherwise +/ + string sectionOf() const { + return (own_section.length > 0) ? own_section : section; + } +} + +/+ ↓ what the reader met and did not understand. + A reader that silently drops what it does not know cannot say whether + it understood the document, and cannot be used to check a + specification against an implementation: silence and understanding + look alike. So the parser counts what it ignored, and + --report-unknown prints it. ++/ +struct OcdaUnknown { + size_t[string] property; // .name -> times seen + size_t[string] block; // @name -> times seen + size_t[string] line; // first char -> times seen, lines of no known shape + + bool any() const { + return property.length > 0 || block.length > 0 || line.length > 0; + } +} + +struct OcdaDocument { + string format_version; // as declared on line 1, "" when absent + string source_filename; // from the "% Source:" line + string[string] source; // @source: language, languages, digest + OcdaUnknown unknown; // what was met and not understood + string[string] metadata; // key -> value + string[string] make; // key -> value + string[string] doc_has; // key -> value + OcdaObject[] head; + OcdaObject[] toc; + OcdaObject[] body; + OcdaObject[] endnotes; + OcdaObject[] glossary; + OcdaObject[] bibliography; + OcdaObject[] bookindex; + OcdaObject[] blurb; + OcdaObject[] tail; + + /+ ↓ the major part of the declared version, "" when none was declared +/ + string formatVersionMajor() const { + import std.string : indexOf; + if (format_version.length == 0) { return ""; } + auto dot = format_version.indexOf('.'); + return (dot > 0) ? format_version[0 .. dot] : format_version; + } + + string meta(string key) { + if (auto p = key in metadata) return *p; + return ""; + } + + OcdaObject[]* sectionByName(string name) { + switch (name) { + case "head": return &head; + case "toc": return &toc; + case "body": return &body; + case "endnotes": return &endnotes; + case "glossary": return &glossary; + case "bibliography": return &bibliography; + case "bookindex": return &bookindex; + case "blurb": return &blurb; + case "tail": return &tail; + default: return null; + } + } +} + +/+ ↓ the format major version this reader knows. + The .ssp and the .ocda.db carry one version between them, declared in + band: the .ssp on its first line, the database in its schema.version + row. The minor part is raised when a property is added, and a reader of + the newer format still reads the older one, so only the major part is + checked here. Raise this when the reader has been brought to a new + major, not before: the point of the gate is to refuse what has not been + looked at. ++/ +enum ssp_format_major_read = "2"; diff --git a/dlang/src/ocda/sqlite.d b/dlang/src/ocda/sqlite.d new file mode 100644 index 0000000..1552fc4 --- /dev/null +++ b/dlang/src/ocda/sqlite.d @@ -0,0 +1,101 @@ +module ocda.sqlite; + +/+ ↓ the sqlite3 C API, declared rather than depended upon. + . + A binding from the dub registry would be a dependency to fetch, and + the point of this reader is that it builds in a sandbox with no + network. The dozen functions a reader needs are declared here and the + library is linked directly, which costs a page of extern(C) and saves + a dependency. ++/ + +import std.conv : to; +import std.string : fromStringz, toStringz; + +extern (C) { + struct sqlite3; + struct sqlite3_stmt; + + int sqlite3_open_v2(const(char)* filename, sqlite3** db, int flags, const(char)* vfs); + int sqlite3_close(sqlite3* db); + int sqlite3_prepare_v2(sqlite3* db, const(char)* sql, int nbyte, + sqlite3_stmt** stmt, const(char)** tail); + int sqlite3_step(sqlite3_stmt* stmt); + int sqlite3_finalize(sqlite3_stmt* stmt); + int sqlite3_column_count(sqlite3_stmt* stmt); + const(char)* sqlite3_column_name(sqlite3_stmt* stmt, int col); + const(ubyte)* sqlite3_column_text(sqlite3_stmt* stmt, int col); + int sqlite3_column_int(sqlite3_stmt* stmt, int col); + int sqlite3_column_type(sqlite3_stmt* stmt, int col); + const(char)* sqlite3_errmsg(sqlite3* db); +} + +enum SQLITE_OK = 0; +enum SQLITE_ROW = 100; +enum SQLITE_DONE = 101; +enum SQLITE_NULL = 5; +enum SQLITE_OPEN_READONLY = 0x00000001; + +class SqliteError : Exception { + this(string msg) { super(msg); } +} + +/+ ↓ a database, opened read only. + Read only is deliberate: a reader has no business writing, and a + request that opens a database read-write can create an empty one where + a path is mistyped. ++/ +struct Db { + private sqlite3* _handle; + + static Db open(string path) { + sqlite3* handle; + auto rc = sqlite3_open_v2(path.toStringz, &handle, SQLITE_OPEN_READONLY, null); + if (rc != SQLITE_OK) { + string msg = (handle is null) + ? "cannot open " ~ path + : "cannot open " ~ path ~ ": " ~ sqlite3_errmsg(handle).fromStringz.idup; + if (handle !is null) { sqlite3_close(handle); } + throw new SqliteError(msg); + } + Db db; + db._handle = handle; + return db; + } + + void close() { + if (_handle !is null) { sqlite3_close(_handle); _handle = null; } + } + + /+ ↓ every row of a query, each row as its columns in order +/ + string[][] rows(string sql) { + sqlite3_stmt* stmt; + auto rc = sqlite3_prepare_v2(_handle, sql.toStringz, -1, &stmt, null); + if (rc != SQLITE_OK) { + throw new SqliteError(sqlite3_errmsg(_handle).fromStringz.idup ~ " in: " ~ sql); + } + scope(exit) { sqlite3_finalize(stmt); } + string[][] out_rows; + int cols = sqlite3_column_count(stmt); + while (sqlite3_step(stmt) == SQLITE_ROW) { + string[] row; + foreach (c; 0 .. cols) { + row ~= (sqlite3_column_type(stmt, c) == SQLITE_NULL) + ? "" : (cast(const(char)*) sqlite3_column_text(stmt, c)).fromStringz.idup; + } + out_rows ~= row; + } + return out_rows; + } + + /+ ↓ the first column of the first row, "" when there is none +/ + string one(string sql) { + auto r = rows(sql); + return (r.length > 0 && r[0].length > 0) ? r[0][0] : ""; + } + + /+ ↓ does a table or view of this name exist +/ + bool has(string name) { + return one("SELECT count(*) FROM sqlite_master WHERE name = '" ~ name ~ "'") != "0"; + } +} diff --git a/dlang/test/agree.d b/dlang/test/agree.d new file mode 100644 index 0000000..bdf1b2e --- /dev/null +++ b/dlang/test/agree.d @@ -0,0 +1,84 @@ +/++ + Do the two loaders agree? + + The library's whole purpose is that a writer cannot tell which + serialisation it was handed. That is only true if loading a document's + .ssp and loading its .ocda.db give the same model, so this asks. + + Usage: agree <doc>.ssp <doc>.ocda.db [lang] ++/ +import std.conv : to; +import std.stdio; +import ocda.model; +import ocda.load; + +int main(string[] args) { + if (args.length < 3) { + stderr.writeln("usage: agree <doc>.ssp <doc>.ocda.db [lang]"); + return 2; + } + string lang = (args.length > 3) ? args[3] : ""; + OcdaDocument a, b; + try { + a = load(args[1]); + b = load(args[2], lang); + } catch (Exception e) { + stderr.writeln("error: ", e.msg); + return 2; + } + + int differences = 0; + void differ(string what, string from_ssp, string from_db) { + writeln(" differ: ", what); + writeln(" .ssp: ", from_ssp); + writeln(" .ocda.db: ", from_db); + differences++; + } + + if (a.format_version != b.format_version) { + differ("format_version", a.format_version, b.format_version); + } + if (a.source_filename != b.source_filename) { + differ("source_filename", a.source_filename, b.source_filename); + } + + /+ ↓ the sections, object by object. Position within a section is the + identity to compare on: an ocn is not unique and 0 is shared +/ + static immutable sections = ["head", "toc", "body", "endnotes", "glossary", + "bibliography", "bookindex", "blurb", "tail"]; + foreach (name; sections) { + auto sa = a.sectionByName(name); + auto sb = b.sectionByName(name); + if (sa is null || sb is null) { continue; } + if ((*sa).length != (*sb).length) { + differ(name ~ " object count", (*sa).length.to!string, (*sb).length.to!string); + continue; + } + foreach (i, oa; *sa) { + auto ob = (*sb)[i]; + string at = name ~ "[" ~ i.to!string ~ "]"; + if (oa.ocn != ob.ocn) { differ(at ~ " ocn", oa.ocn.to!string, ob.ocn.to!string); } + if (oa.is_a != ob.is_a) { differ(at ~ " is_a", oa.is_a, ob.is_a); } + if (oa.is_of_type != ob.is_of_type) { differ(at ~ " is_of_type", oa.is_of_type, ob.is_of_type); } + if (oa.part != ob.part) { differ(at ~ " part", oa.part, ob.part); } + if (oa.parent_ocn != ob.parent_ocn) { differ(at ~ " parent", oa.parent_ocn.to!string, ob.parent_ocn.to!string); } + if (oa.heading_level != ob.heading_level) { differ(at ~ " level", oa.heading_level, ob.heading_level); } + if (oa.sha256 != ob.sha256) { differ(at ~ " sha256", oa.sha256, ob.sha256); } + if (oa.text != ob.text) { differ(at ~ " text", oa.text, ob.text); } + if (oa.ancestors != ob.ancestors) { + differ(at ~ " ancestors", oa.ancestors.to!string, ob.ancestors.to!string); + } + if (oa.images.length != ob.images.length) { + differ(at ~ " image count", oa.images.length.to!string, ob.images.length.to!string); + } + if (differences > 12) { writeln(" ... stopping after 12"); return 1; } + } + } + + if (differences == 0) { + writeln("agree: the two loaders give the same model"); + return 0; + } + writeln(differences, " difference(s)"); + return 1; +} |
