summaryrefslogtreecommitdiffhomepage
path: root/org/d-ocda-load.org
diff options
context:
space:
mode:
Diffstat (limited to 'org/d-ocda-load.org')
-rw-r--r--org/d-ocda-load.org953
1 files changed, 953 insertions, 0 deletions
diff --git a/org/d-ocda-load.org b/org/d-ocda-load.org
new file mode 100644
index 0000000..59762a8
--- /dev/null
+++ b/org/d-ocda-load.org
@@ -0,0 +1,953 @@
+-*- mode: org -*-
+#+TITLE: dlang load
+#+DESCRIPTION: dlang lib
+#+FILETAGS: :spine:build:tools:
+#+AUTHOR: Ralph Amissah
+#+EMAIL: [[mailto:ralph.amissah@gmail.com][ralph.amissah@gmail.com]]
+#+COPYRIGHT: Copyright (C) 2015 (continuously updated, current 2026) Ralph Amissah
+#+LANGUAGE: en
+#+STARTUP: content hideblocks hidestars noindent entitiespretty
+#+PROPERTY: header-args+ :eval never-export :exports code
+#+PROPERTY: header-args+ :noweb yes :padline no
+#+PROPERTY: header-args+ :results silent :cache no
+#+PROPERTY: header-args+ :mkdirp yes
+#+OPTIONS: H:3 num:nil toc:t \n:t ::t |:t ^:nil -:t f:t *:t
+- magic single double-quote → " ← FIX changes hilighting behavior (occuring
+ after it) in org document. INVESTIGATE (org-mode CONFIG?) FIND & FIX
+
+* dlang :dlang:
+** load dlang
+
+#+HEADER: :tangle "../dlang/src/ocda/load.d"
+#+BEGIN_SRC d
+<<doc_header_including_copyright_and_license>>
+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;
+import ocda.load_pod;
+
+enum Source {
+ ssp, // .ssp, the abstraction as text
+ ocda_db, // .ocda.db, the abstraction as sqlite
+ pod, // .sisupod or .zip, an archive carrying a .ssp
+ unknown,
+}
+
+Source sourceOf(string path) {
+ if (path.endsWith(".ocda.db")) { return Source.ocda_db; }
+ if (path.endsWith(".ssp")) { return Source.ssp; }
+ /+ ↓ .sisupod is the archive spine writes now; .zip is what it wrote
+ before, and every pod already published carries that name, so both
+ are read. What is inside decides how it is opened, not the name.
+ +/
+ if (path.endsWith(".sisupod")) { return Source.pod; }
+ if (path.endsWith(".zip")) { return Source.pod; }
+ 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.pod: return "a pod archive carrying a .ssp";
+ 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 names which language to take from a .ocda.db, which holds
+ every language of its document, and from a pod, which may carry more
+ than one .ssp. A .ssp is one language by construction and ignores it.
++/
+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.pod: return loadPodFile(path, lang);
+ case Source.unknown:
+ throw new OcdaLoadError(path ~ ": " ~ sourceName(Source.unknown)
+ ~ " (expected .ssp, .ocda.db, .sisupod or .zip)");
+ }
+}
+#+END_SRC
+
+** load db dlang
+
+#+HEADER: :tangle "../dlang/src/ocda/load_db.d"
+#+BEGIN_SRC d
+<<doc_header_including_copyright_and_license>>
+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 : join, split;
+import std.json : JSONType, parseJSON;
+import std.conv : to;
+import std.algorithm : startsWith;
+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")) {
+ string key = r[0];
+ if (key.startsWith("source.")) { continue; }
+ /+ ↓ translation.ocn_aligned says whether the languages of this
+ document share one numbering. A .ocda.db can know it because it
+ holds every language; a .ssp is one language and cannot. So it is
+ a fact about the *file* rather than about the document, and putting
+ it in the document's metadata would let a writer tell which
+ serialisation it was handed, which is the one thing this library
+ exists to prevent. Left out until the model has a place for
+ collection-wide facts.
+ +/
+ if (key.startsWith("translation.")) { continue; }
+ /+ ↓ the database has one metadata table where the text form has three
+ blocks, and tells them apart by a key prefix. Unprefixing them
+ here is what makes the two loaders give one model: a writer asks
+ doc.make["footer"] whichever serialisation it was handed, and
+ never doc.metadata["make.footer"].
+ +/
+ if (key.startsWith("make.")) {
+ doc.make[key["make.".length .. $]] = r[1].strip;
+ } else if (key.startsWith("doc_has.")) {
+ doc.doc_has[key["doc_has.".length .. $]] = r[1].strip;
+ } else {
+ doc.metadata[key] = r[1].strip;
+ }
+ }
+
+ /+ ↓ 2.1 added the container range as two columns. A 2.0 database has
+ neither, and reads as having no range, which is what 2.0 meant. +/
+ bool has_range = false;
+ foreach (c; db.rows("PRAGMA table_info(objects)")) {
+ if (c[1] == "ocn_range_first") { has_range = true; }
+ }
+ string range_cols = has_range
+ ? "coalesce(ocn_range_first,0), coalesce(ocn_range_last,0)"
+ : "0, 0";
+
+ /+ ↓ 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, coalesce(heading_lev_anchor,''),
+ coalesce(segment_epub,''), coalesce(segment_epub_is,''), " ~ range_cols ~ "
+ 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.heading_lev_anchor = r[37];
+ obj.segment_epub = r[38];
+ obj.segment_epub_is = r[39];
+ obj.ocn_range_first = r[40].to!int;
+ obj.ocn_range_last = r[41].to!int;
+ 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];
+ }
+ foreach (a; db.rows("SELECT anchor FROM object_anchors WHERE object_id = "
+ ~ object_id ~ " ORDER BY seq")) {
+ obj.anchor_tags ~= a[0];
+ }
+
+ auto section = doc.sectionByName(r[0]);
+ if (section !is null) { *section ~= obj; }
+ }
+ countUnread(db, chosen.doc_id, doc);
+ return doc;
+}
+
+/+ ↓ what the database holds and the model does not.
+ .
+ The text loader meets every property line and counts those it does not
+ keep, so a reader can say what was read and not understood. This
+ loader asks for columns by name, and would never see the ones it did
+ not ask for: it would report that it had understood everything, which
+ is the silence the count exists to prevent. So it counts them, on the
+ conditions under which the .ssp writes the same property (specification
+ section 6.3), and the report is the same from either form: checked,
+ 36 of 36.
++/
+private void countUnread(ref Db db, int doc_id, ref OcdaDocument doc) {
+ string id = doc_id.to!string;
+ void count(string property, string where) {
+ auto n = db.one("SELECT count(*) FROM objects WHERE doc_id = " ~ id
+ ~ " AND " ~ where).to!size_t;
+ if (n > 0) { doc.unknown.property[property] = n; }
+ }
+ count("ancestors_collapsed", "coalesce(ancestors_collapsed,'') != ''");
+ count("dom_status", "coalesce(dom_status,'') != ''");
+ count("dom_status_collapsed", "coalesce(dom_status_collapsed,'') != ''");
+ count("heading_lev_collapsed", "heading_lev_collapsed IS NOT NULL");
+ count("parent_lev", "coalesce(parent_lev,0) != 0");
+ count("segment_lv4_is", "coalesce(segment_lv4_is,'') != ''");
+ count("attrib", "coalesce(attrib,'') != ''");
+ if (db.has("object_subtoc")) {
+ auto n = db.one("SELECT count(*) FROM object_subtoc s JOIN objects o"
+ ~ " ON o.id = s.object_id WHERE o.doc_id = " ~ id).to!size_t;
+ if (n > 0) { doc.unknown.property["lev4_subtoc"] = n; }
+ }
+}
+
+/+ ↓ 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 JSON columns, read as JSON.
+ .
+ The fixed width arrays are JSON in the database and space separated
+ (or "|" separated) in the text form. This was first written as a
+ character scan that threw away brackets and quotes, which is wrong the
+ moment a value holds an escape: Phobos' JSONValue.toString escapes
+ "/" as "\/", so every heading containing a slash came back with a
+ backslash in it. 36 of 36 documents differed on
+ heading_ancestors_text and nothing else had shown it.
+ .
+ So: parse. The values are small, there are few of them, and a real
+ parser is shorter than the scan it replaces.
++/
+private string[] jsonStrings(string v) {
+ if (v.length == 0) { return []; }
+ string[] out_;
+ try {
+ auto j = parseJSON(v);
+ if (j.type != JSONType.array) { return []; }
+ foreach (e; j.array) {
+ switch (e.type) {
+ case JSONType.string: out_ ~= e.str; break;
+ case JSONType.integer: out_ ~= e.integer.to!string; break;
+ case JSONType.uinteger: out_ ~= e.uinteger.to!string; break;
+ case JSONType.float_: out_ ~= e.floating.to!string; break;
+ case JSONType.true_: out_ ~= "true"; break;
+ case JSONType.false_: out_ ~= "false"; break;
+ default: out_ ~= ""; break;
+ }
+ }
+ } catch (Exception) {
+ return [];
+ }
+ return out_;
+}
+
+private int[] jsonInts(string v) {
+ int[] out_;
+ foreach (s; jsonStrings(v)) {
+ if (s.length == 0) { continue; }
+ try { out_ ~= s.to!int; } catch (Exception) {}
+ }
+ return out_;
+}
+
+/+ ↓ space separated in the text form: table_widths, table_aligns +/
+private string jsonWords(string v) {
+ return jsonStrings(v).join(" ");
+}
+
+/+ ↓ heading_ancestors_text is eight slots, joined with "|" in the text
+ form and a JSON array here. The empty slots are significant: they say
+ which levels the heading sits under, so the separators carry as much
+ as the text does.
++/
+private string jsonJoined(string v) {
+ auto parts = jsonStrings(v);
+ if (parts.length == 0) { return ""; }
+ return parts.join("|");
+}
+#+END_SRC
+
+** load pod dlang
+
+#+HEADER: :tangle "../dlang/src/ocda/load_pod.d"
+#+BEGIN_SRC d
+<<doc_header_including_copyright_and_license>>
+module ocda.load_pod;
+
+/+ ↓ the abstraction out of a pod archive.
+ .
+ A .sisupod is one zstd frame wrapping a stored zip; a .zip is the same
+ archive unwrapped, which is what spine published before it wrapped them.
+ Either way, a pod built with --pod2 carries the abstraction inside it,
+ at media/abstraction/<uid>.<lang>.ssp, and that is what is read.
+ .
+ So this is a third input form and *not* a third model: the .ssp inside
+ is parsed by ocda.load_ssp and comes back as the same value. A writer
+ over the library gains .sisupod without being touched, which is the
+ whole reason the dispatch is in one place.
+ .
+ A pod built without --pod2 carries markup and no abstraction. That is
+ refused, and the refusal says which flag makes a pod this reader can
+ read, because "no abstraction in it" is a fact about the pod rather
+ than about the reader.
++/
+
+import std.algorithm : endsWith, sort;
+import std.array : array;
+import std.file : read;
+import std.string : indexOf;
+import ocda.model;
+import ocda.load_ssp;
+import ocda.zip;
+import ocda.zstd;
+
+/+ ↓ a limit on what a frame may expand to.
+ A reader of an artefact it did not make declines to be told how much
+ memory to allocate. 512 MiB is far above the largest pod in the
+ reference collection (4 MiB) and far below anything that matters.
++/
+enum size_t max_pod_size = 512 * 1024 * 1024;
+
+class OcdaPodError : Exception {
+ this(string msg) { super(msg); }
+}
+
+/+ ↓ which languages of the abstraction the pod carries, in sorted order +/
+string[] podLanguages(string path) {
+ auto bytes = archiveBytes(path);
+ string[] out_;
+ foreach (e; zipFindSuffix(zipEntries(bytes), ".ssp")) {
+ string lang = langOfSspName(e.name);
+ if (lang.length > 0) { out_ ~= lang; }
+ }
+ return out_.sort.array;
+}
+
+/+ ↓ load one language of the abstraction a pod carries.
+ lang == "" takes the only one there is, and where there is a choice it
+ says so rather than choosing, as the .ocda.db loader does.
++/
+OcdaDocument loadPodFile(string path, string lang = "") {
+ auto bytes = archiveBytes(path);
+ auto entries = zipEntries(bytes);
+ auto ssps = zipFindSuffix(entries, ".ssp");
+ if (ssps.length == 0) {
+ throw new OcdaPodError(path ~ ": carries no .ssp."
+ ~ " A pod carries the abstraction only when spine was asked for it:"
+ ~ " spine --pod2 puts it in, spine --source does not.");
+ }
+ ZipEntry chosen = ssps[0];
+ if (lang.length > 0) {
+ bool found = false;
+ foreach (e; ssps) {
+ if (langOfSspName(e.name) == lang) { chosen = e; found = true; break; }
+ }
+ if (!found) {
+ string have;
+ foreach (i, e; ssps) {
+ have ~= (i > 0 ? " " : "") ~ langOfSspName(e.name);
+ }
+ throw new OcdaPodError(path ~ ": no language '" ~ lang
+ ~ "'; it holds: " ~ have);
+ }
+ } else if (ssps.length > 1) {
+ string have;
+ foreach (i, e; ssps) {
+ have ~= (i > 0 ? " " : "") ~ langOfSspName(e.name);
+ }
+ throw new OcdaPodError(path ~ ": holds more than one language ("
+ ~ have ~ "); name the one wanted");
+ }
+ auto ssp = zipRead(bytes, chosen);
+ return parseSsp(cast(string) ssp.idup);
+}
+
+/+ ↓ the archive, unwrapped if it was wrapped.
+ The bytes decide, not the name: a .sisupod is a zstd frame and a .zip
+ is not, and a file misnamed either way still reads.
++/
+package ubyte[] archiveBytes(string path) {
+ auto bytes = cast(ubyte[]) read(path);
+ return zstdIsFrame(bytes)
+ ? zstdDecompress(bytes, max_pod_size)
+ : bytes;
+}
+
+/+ ↓ <uid>.<lang>.ssp -> <lang> +/
+package string langOfSspName(string name) {
+ if (!name.endsWith(".ssp")) { return ""; }
+ string stem = name[0 .. $ - 4];
+ auto dot = stem.lastIndexOf('.');
+ return (dot > 0) ? stem[dot + 1 .. $] : "";
+}
+
+private ptrdiff_t lastIndexOf(string s, char c) {
+ for (ptrdiff_t i = s.length - 1; i >= 0; i--) {
+ if (s[i] == c) { return i; }
+ }
+ return -1;
+}
+#+END_SRC
+
+** load ssp dlang
+
+#+HEADER: :tangle "../dlang/src/ocda/load_ssp.d"
+#+BEGIN_SRC d
+<<doc_header_including_copyright_and_license>>
+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")) {
+ /+ ↓ 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;
+ }
+
+ /+ ↓ 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;
+ }
+
+ /+ ↓ 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;
+ /+ ↓ 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;
+ }
+
+ /+ ↓ 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;
+ }
+
+ /+ ↓ 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;
+ }
+
+ /+ ↓ 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;
+ }
+
+ /+ ↓ property: .name: value +/
+ if (line[0] == '.') {
+ if (in_object) {
+ parseProperty(line, current_obj, doc.unknown);
+ }
+ continue;
+ }
+
+ /+ ↓ 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;
+ }
+
+ /+ ↓ 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]++;
+ }
+
+ /+ ↓ 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];
+ }
+ }
+}
+
+/+ ↓ 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;
+ /+ ↓ the epub segments at heading levels 1 to 4 where the html
+ segments at level 4 alone, so the two are different files and
+ the abstraction records both +/
+ case "segment_epub": obj.segment_epub = value; break;
+ case "segment_epub_is": obj.segment_epub_is = value; break;
+ case "table_aligns": obj.table_aligns = value; break;
+ case "stow_link": obj.stow_link ~= value; break;
+ case "anchor_tag": obj.anchor_tags ~= value; break;
+ case "parent": obj.parent_ocn = toIntSafe(value); break;
+ case "last_descendant": obj.last_descendant_ocn = toIntSafe(value); break;
+ case "ocn_range": {
+ auto r = parseIntArray(value);
+ if (r.length == 2) { obj.ocn_range_first = r[0]; obj.ocn_range_last = r[1]; }
+ 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 "heading_lev_anchor": obj.heading_lev_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;
+ /+ ↓ 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;
+}
+
+/+ ↓ two values the text form leaves out because they can be worked out.
+ .
+ The .ssp emits a property only when it carries information, so
+ .identifier is absent when it is simply the ocn, and .anchor is absent
+ when it is the segment name. The .ocda.db, being columns rather than
+ lines, stores both unconditionally. So a loader that takes the text
+ form literally gives a *different model* from the one the database
+ gives, and the difference is not small: in the reference collection
+ the identifier is omitted on all but a handful of objects.
+ .
+ The model is the thing both serialisations describe, so the loader
+ fills them in. Found by dumping both models and diffing them, which no
+ amount of comparing section counts would have shown.
++/
+private void deriveOmitted(ref OcdaObject obj) {
+ import std.conv : to;
+ if (obj.identifier.length == 0 && obj.ocn != 0) {
+ obj.identifier = obj.ocn.to!string;
+ }
+ if (obj.anchor.length == 0 && obj.segment.length > 0) {
+ obj.anchor = obj.segment;
+ }
+}
+
+private void commitObject(ref OcdaDocument doc, string section, ref OcdaObject obj) {
+ deriveOmitted(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;
+}
+#+END_SRC
+
+* org includes
+** project version
+
+#+NAME: spine_version
+#+HEADER: :noweb yes
+#+BEGIN_SRC emacs-lisp
+<<./sisudoc_spine_version_info_and_doc_header_including_copyright_and_license.org:spine_project_version()>>
+#+END_SRC
+
+** year
+
+#+NAME: year
+#+HEADER: :noweb yes
+#+BEGIN_SRC emacs-lisp
+<<./sisudoc_spine_version_info_and_doc_header_including_copyright_and_license.org:year()>>
+#+END_SRC
+
+** document header including copyright & license
+
+#+NAME: doc_header_including_copyright_and_license
+#+HEADER: :noweb yes
+#+BEGIN_SRC emacs-lisp
+<<./sisudoc_spine_version_info_and_doc_header_including_copyright_and_license.org:spine_doc_header_including_copyright_and_license()>>
+#+END_SRC
+
+* __END__