diff options
Diffstat (limited to 'dlang/src')
| -rw-r--r-- | dlang/src/COPYRIGHT | 45 | ||||
| -rw-r--r-- | dlang/src/ocda/dump.d | 164 | ||||
| -rw-r--r-- | dlang/src/ocda/images.d | 100 | ||||
| -rw-r--r-- | dlang/src/ocda/load.d | 69 | ||||
| -rw-r--r-- | dlang/src/ocda/load_db.d | 310 | ||||
| -rw-r--r-- | dlang/src/ocda/load_pod.d | 115 | ||||
| -rw-r--r-- | dlang/src/ocda/load_ssp.d | 337 | ||||
| -rw-r--r-- | dlang/src/ocda/model.d | 147 | ||||
| -rw-r--r-- | dlang/src/ocda/sqlite.d | 122 | ||||
| -rw-r--r-- | dlang/src/ocda/zip.d | 115 | ||||
| -rw-r--r-- | dlang/src/ocda/zstd.d | 79 |
11 files changed, 1603 insertions, 0 deletions
diff --git a/dlang/src/COPYRIGHT b/dlang/src/COPYRIGHT new file mode 100644 index 0000000..7e7dd56 --- /dev/null +++ b/dlang/src/COPYRIGHT @@ -0,0 +1,45 @@ +- Name: sisudoc-ocda-lib + - Description: part of SiSU spine (Doc Reform): documents, structuring, + processing, publishing and search + - [https://www.sisudoc.org] + + - Author: Ralph Amissah + [ralph.amissah@gmail.com] + + - Copyright: (C) 2026 Ralph Amissah, All Rights Reserved. + + - License: AGPL 3 or later, for everything in this repository unless a file or + a directory specifies otherwise.: + + sisudoc-ocda-lib + + part of SiSU spine (Doc Reform): documents, structuring, + processing, publishing and search + + Copyright (C) Ralph Amissah + + This program is free software: you can redistribute it and/or modify it + under the terms of the GNU Affero General Public License (AGPLv3) as + published by the Free Software Foundation, either version 3 of the License, + or (at your option) any later version. + + This program is distributed in the hope that it will be useful, but + WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY + or FITNESS FOR A PARTICULAR PURPOSE. See the GNU Affero General Public + License for more details. + + You should have received a copy of the GNU Affero General Public License + along with this program. If not, see [https://www.gnu.org/licenses/]. + + If you have Internet connection, the latest version of the AGPL should be + available at: [https://www.gnu.org/licenses/agpl-3.0.html] + + - Spine, Doc Reform (related to SiSU) uses standard: + - docReform markup syntax (based on SiSU markup) + - standard SiSU markup syntax with modified headers and minor + modifications + - docReform object numbering (based on SiSU object citation numbering) + - standard SiSU document object numbering + + - Homepages: + [https://www.sisudoc.org] diff --git a/dlang/src/ocda/dump.d b/dlang/src/ocda/dump.d new file mode 100644 index 0000000..7a4f11a --- /dev/null +++ b/dlang/src/ocda/dump.d @@ -0,0 +1,164 @@ +module ocda.dump; + +/+ ↓ the model, written out canonically. + . + Not an output format: an *oracle*. Two libraries in two languages + implement the same model from the same specification, and the cheap + way to ask whether they agree is to have each write the whole loaded + document as text and diff the two. That is only useful if the text is + fully determined by the model, so: + . + - every line is "<key> <value>", the value running to end of line, + and only one free-form value per line; + - a field at its default is *omitted*, so the output says what the + document has rather than what the struct declares; + - dictionaries are emitted in sorted key order, because neither + language's hash map has an order worth relying on; + - sections come in the fixed order of the format, not + alphabetically. + . + Anything that reads this to reconstruct a document has misunderstood + it. Load the .ssp or the .ocda.db. ++/ + +import std.algorithm : sort, splitter; +import std.array : appender, array, join; +import std.conv : to; +import ocda.model; + +/+ ↓ the nine sections, in format order +/ +static immutable string[] dump_sections = ["head", "toc", "body", "endnotes", + "glossary", "bibliography", "bookindex", "blurb", "tail"]; + +string dumpDocument(ref OcdaDocument doc) { + auto out_ = appender!string; + + void kv(string key, string value) { + if (value.length == 0) { return; } + out_ ~= key; out_ ~= " "; out_ ~= value; out_ ~= "\n"; + } + void kn(string key, long value) { + if (value == 0) { return; } + kv(key, value.to!string); + } + void kb(string key, bool value) { + if (!value) { return; } + kv(key, "1"); + } + void dict(string prefix, string[string] d) { + foreach (key; d.keys.dup.sort) { + out_ ~= prefix; out_ ~= " "; out_ ~= key; out_ ~= " "; + out_ ~= d[key]; out_ ~= "\n"; + } + } + + kv("version", doc.format_version); + kv("source_filename", doc.source_filename); + dict("source", doc.source); + dict("meta", doc.metadata); + dict("make", doc.make); + dict("doc_has", doc.doc_has); + + foreach (name; dump_sections) { + auto sec = doc.sectionByName(name); + if (sec is null || (*sec).length == 0) { continue; } + kv("section", name ~ " " ~ (*sec).length.to!string); + } + + foreach (name; dump_sections) { + auto sec = doc.sectionByName(name); + if (sec is null) { continue; } + foreach (i, obj; *sec) { + out_ ~= "object "; out_ ~= name; out_ ~= " "; + out_ ~= i.to!string; out_ ~= "\n"; + kn("ocn", obj.ocn); + kv("is_a", obj.is_a); + kv("own_section", obj.own_section); + kv("level", obj.heading_level); + kv("identifier", obj.identifier); + kv("part", obj.part); + kv("is_of_type", obj.is_of_type); + kv("segment_html_is", obj.segment_html_is); + kv("segment_epub", obj.segment_epub); + kv("segment_epub_is", obj.segment_epub_is); + kn("parent", obj.parent_ocn); + kn("last_descendant", obj.last_descendant_ocn); + kv("children", ints(obj.children)); + kv("ancestors", ints(obj.ancestors)); + kb("dummy", obj.dummy_heading); + kb("ocn_off", obj.ocn_off); + kn("indent_base", obj.indent_base); + kn("indent_hang", obj.indent_hang); + kb("bullet", obj.bullet); + kv("lang", obj.lang); + kb("has_links", obj.has_links); + kb("has_notes_reg", obj.has_notes_reg); + kb("has_notes_star", obj.has_notes_star); + kb("has_images", obj.has_images); + kv("segment", obj.segment); + kv("segment_prev", obj.segment_prev); + kv("segment_next", obj.segment_next); + kv("anchor", obj.anchor); + kv("heading_lev_anchor", obj.heading_lev_anchor); + kn("table_cols", obj.table_cols); + kv("table_widths", obj.table_widths); + kv("table_aligns", obj.table_aligns); + kb("table_header", obj.table_header); + kv("code_syntax", obj.code_syntax); + kb("code_linenumbers", obj.code_linenumbers); + kv("heading_ancestors_text", obj.heading_ancestors_text); + kv("sha256", obj.sha256); + foreach (url; obj.stow_link) { kv("stow_link", url); } + foreach (a; obj.anchor_tags) { kv("anchor_tag", a); } + foreach (img; obj.images) { + /+ ↓ the name last, because a filename may hold a space where + none of the other fields can +/ + kv("image", img.sha256 ~ " " ~ img.bytes.to!string ~ " " + ~ img.width.to!string ~ "x" ~ img.height.to!string ~ " " + ~ (img.missing ? "1" : "0") ~ " " ~ img.name); + foreach (key; img.fields.keys.dup.sort) { + kv("image_field", key ~ " " ~ img.fields[key]); + } + } + /+ ↓ text, when there is any. An object whose only text line is + blank holds "" here, indistinguishable from no text at all, + because the model joins the lines into one string. Both + libraries lose the same distinction in the same place, which is + what makes them comparable; it is recorded rather than hidden. + +/ + if (obj.text.length > 0) { + auto lines = obj.text.splitter("\n").array; + kv("text", lines.length.to!string); + foreach (line; lines) { + out_ ~= "| "; out_ ~= line; out_ ~= "\n"; + } + } + } + } + return out_.data; +} + +/+ ↓ what the reader met and did not understand, sorted. Separate from the + document dump: it describes the reader, not the document, and the + .ocda.db loader has nothing to report where the .ssp loader does. ++/ +string dumpUnknown(ref OcdaDocument doc) { + auto out_ = appender!string; + void counts(string prefix, size_t[string] d) { + foreach (key; d.keys.dup.sort) { + out_ ~= prefix; out_ ~= " "; out_ ~= key; out_ ~= " "; + out_ ~= d[key].to!string; out_ ~= "\n"; + } + } + counts("property", doc.unknown.property); + counts("block", doc.unknown.block); + counts("line", doc.unknown.line); + return out_.data; +} + +private string ints(int[] xs) { + if (xs.length == 0) { return ""; } + string[] parts; + foreach (x; xs) { parts ~= x.to!string; } + return parts.join(","); +} diff --git a/dlang/src/ocda/images.d b/dlang/src/ocda/images.d new file mode 100644 index 0000000..b3a9652 --- /dev/null +++ b/dlang/src/ocda/images.d @@ -0,0 +1,100 @@ +module ocda.images; + +/+ ↓ an image's bytes, from whichever source the document came from. + . + The model *names* images, with digest, byte size and pixel size; it does + not hold them. That is right - an abstraction of a document is not a + bundle of its assets - but a writer of any format that shows images + needs the bytes, so something has to know where they are. This is that + something, and it is in the library rather than in a writer because the + answer depends on the *input form* and not on the output. + . + Three answers, and one refusal: + . + .ocda.db the files table, role 'image', by name + .sisupod the archive entry whose path ends in /image/<name> + .zip the same + .ssp beside it: a pod puts the abstraction in + media/abstraction/ and its images in media/image/, so the + path is documented rather than guessed + . + A .ssp that is not in a pod has nowhere to look, and that is reported as + absent rather than as an error: a reader that cannot find an image + should say so and carry on, because the document is still readable. ++/ + +import std.algorithm : endsWith; +import std.array : array; +import std.file : exists, isFile, read; +import std.path : buildPath, dirName; +import ocda.load; +import ocda.sqlite; +import ocda.zip; +import ocda.zstd; + +/+ ↓ the bytes, or an empty slice when the source has no such image +/ +ubyte[] imageBytes(string source, string name) { + final switch (sourceOf(source)) { + case Source.ocda_db: return fromDb(source, name); + case Source.pod: return fromArchive(source, name); + case Source.ssp: return fromBeside(source, name); + case Source.unknown: return []; + } +} + +/+ ↓ can this source give images at all? + A writer asks before it decides whether to emit them, because an <img> + pointing at a file it did not include is worse than no image. ++/ +bool canGiveImages(string source) { + final switch (sourceOf(source)) { + case Source.ocda_db: return true; + case Source.pod: return true; + case Source.ssp: return imageDirBeside(source).length > 0; + case Source.unknown: return false; + } +} + +private ubyte[] fromDb(string path, string name) { + auto db = Db.open(path); + scope(exit) { db.close(); } + if (!db.has("files")) { return []; } + /+ ↓ the name is from the abstraction, not from a caller, and the quote + doubling is what keeps it a value rather than syntax +/ + return db.blob("SELECT data FROM files WHERE role = 'image' AND name = '" + ~ sqlQuote(name) ~ "'"); +} + +private ubyte[] fromArchive(string path, string name) { + auto bytes = cast(ubyte[]) read(path); + if (zstdIsFrame(bytes)) { bytes = zstdDecompress(bytes, 512 * 1024 * 1024); } + auto entries = zipEntries(bytes); + foreach (e; entries) { + if (e.name.endsWith("/image/" ~ name)) { return zipRead(bytes, e); } + } + return []; +} + +private ubyte[] fromBeside(string path, string name) { + string dir = imageDirBeside(path); + if (dir.length == 0) { return []; } + string file = buildPath(dir, name); + return file.exists && file.isFile ? cast(ubyte[]) read(file) : []; +} + +/+ ↓ media/abstraction/<x>.ssp -> media/image/ +/ +private string imageDirBeside(string path) { + string dir = path.dirName; + if (!dir.endsWith("abstraction")) { return ""; } + string image_dir = buildPath(dir.dirName, "image"); + return image_dir.exists ? image_dir : ""; +} + +/+ ↓ a single quote doubled is how sql says a single quote +/ +private string sqlQuote(string s) { + string out_; + foreach (c; s) { + out_ ~= (c == '\'') ? "''" : [c]; + } + return out_; +} diff --git a/dlang/src/ocda/load.d b/dlang/src/ocda/load.d new file mode 100644 index 0000000..89c8dcc --- /dev/null +++ b/dlang/src/ocda/load.d @@ -0,0 +1,69 @@ +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)"); + } +} diff --git a/dlang/src/ocda/load_db.d b/dlang/src/ocda/load_db.d new file mode 100644 index 0000000..dec0626 --- /dev/null +++ b/dlang/src/ocda/load_db.d @@ -0,0 +1,310 @@ +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; + } + } + + /+ ↓ 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,'') + 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.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; } + } + 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 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("|"); +} diff --git a/dlang/src/ocda/load_pod.d b/dlang/src/ocda/load_pod.d new file mode 100644 index 0000000..75993be --- /dev/null +++ b/dlang/src/ocda/load_pod.d @@ -0,0 +1,115 @@ +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. ++/ +private ubyte[] archiveBytes(string path) { + auto bytes = cast(ubyte[]) read(path); + return zstdIsFrame(bytes) + ? zstdDecompress(bytes, max_pod_size) + : bytes; +} + +/+ ↓ <uid>.<lang>.ssp -> <lang> +/ +private 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; +} diff --git a/dlang/src/ocda/load_ssp.d b/dlang/src/ocda/load_ssp.d new file mode 100644 index 0000000..34d156c --- /dev/null +++ b/dlang/src/ocda/load_ssp.d @@ -0,0 +1,337 @@ +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 "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; +} diff --git a/dlang/src/ocda/model.d b/dlang/src/ocda/model.d new file mode 100644 index 0000000..403502a --- /dev/null +++ b/dlang/src/ocda/model.d @@ -0,0 +1,147 @@ +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 segment_epub; // the epub segment this heading opens + string segment_epub_is;// the epub segment this object sits in + string table_aligns; // l c r per column + string[] stow_link; // links extracted from the object + string[] anchor_tags; // named targets the markup placed on this 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; + string heading_lev_anchor; // a heading's own named target + 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..6f3753c --- /dev/null +++ b/dlang/src/ocda/sqlite.d @@ -0,0 +1,122 @@ +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); + const(void)* sqlite3_column_blob(sqlite3_stmt* stmt, int col); + int sqlite3_column_bytes(sqlite3_stmt* stmt, int col); +} + +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] : ""; + } + + /+ ↓ the first column of the first row as bytes, for a blob. + Separate from one(), because a blob is not text: an image read as text + stops at the first zero byte, and a png's ninth byte is zero. + +/ + ubyte[] blob(string sql) { + sqlite3_stmt* stmt; + if (sqlite3_prepare_v2(_handle, sql.toStringz, -1, &stmt, null) != SQLITE_OK) { + throw new SqliteError("prepare: " ~ sqlite3_errmsg(_handle).fromStringz.idup + ~ " [" ~ sql ~ "]"); + } + scope(exit) { sqlite3_finalize(stmt); } + if (sqlite3_step(stmt) != SQLITE_ROW) { return []; } + int n = sqlite3_column_bytes(stmt, 0); + if (n <= 0) { return []; } + auto p = cast(const(ubyte)*) sqlite3_column_blob(stmt, 0); + if (p is null) { return []; } + return p[0 .. n].dup; + } + + /+ ↓ 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/src/ocda/zip.d b/dlang/src/ocda/zip.d new file mode 100644 index 0000000..9dff6f4 --- /dev/null +++ b/dlang/src/ocda/zip.d @@ -0,0 +1,115 @@ +module ocda.zip; + +/+ ↓ enough of the zip format to find one file in a pod and read it. + . + Not a zip library. A pod archive holds a handful of entries, spine + writes them **stored** (uncompressed) so that the outer zstd frame does + the compressing once over the whole thing, and what is wanted from it + here is one named entry. So: read the central directory, find the + entry, return its bytes. + . + Deflate is *refused rather than mishandled*. Phobos can inflate, but a + library that says it read an entry it in fact skipped is worse than one + that says it cannot, and spine's own archives do not need it. ++/ + +import std.algorithm : endsWith; +import std.conv : to; + +class OcdaZipError : Exception { + this(string msg) { super(msg); } +} + +struct ZipEntry { + string name; + uint method; // 0 stored, 8 deflate + uint compressed; + uint uncompressed; + uint local_offset; +} + +/+ ↓ the entries, from the central directory at the end of the file +/ +ZipEntry[] zipEntries(const(ubyte)[] bytes) { + enum uint eocd_sig = 0x06054b50; + enum uint cd_sig = 0x02014b50; + if (bytes.length < 22) { + throw new OcdaZipError("too short to be a zip archive"); + } + /+ ↓ the end of central directory record is last, and may be followed by a + comment of up to 65535 bytes, so it is searched for backwards +/ + ptrdiff_t eocd = -1; + ptrdiff_t lowest = bytes.length > (22 + 65535) ? bytes.length - (22 + 65535) : 0; + for (ptrdiff_t i = bytes.length - 22; i >= lowest; i--) { + if (u32(bytes, i) == eocd_sig) { eocd = i; break; } + } + if (eocd < 0) { + throw new OcdaZipError("no end of central directory record;" + ~ " it does not look like a zip archive"); + } + uint count = u16(bytes, eocd + 10); + uint offset = u32(bytes, eocd + 16); + ZipEntry[] out_; + size_t p = offset; + foreach (_; 0 .. count) { + if (p + 46 > bytes.length || u32(bytes, p) != cd_sig) { + throw new OcdaZipError("central directory entry " + ~ out_.length.to!string ~ " is malformed"); + } + ZipEntry e; + e.method = u16(bytes, p + 10); + e.compressed = u32(bytes, p + 20); + e.uncompressed = u32(bytes, p + 24); + uint name_len = u16(bytes, p + 28); + uint extra_len = u16(bytes, p + 30); + uint cmnt_len = u16(bytes, p + 32); + e.local_offset = u32(bytes, p + 42); + e.name = cast(string) bytes[p + 46 .. p + 46 + name_len].idup; + out_ ~= e; + p += 46 + name_len + extra_len + cmnt_len; + } + return out_; +} + +/+ ↓ one entry's bytes, from its local header +/ +ubyte[] zipRead(const(ubyte)[] bytes, ZipEntry e) { + enum uint local_sig = 0x04034b50; + size_t p = e.local_offset; + if (p + 30 > bytes.length || u32(bytes, p) != local_sig) { + throw new OcdaZipError(e.name ~ ": local header is malformed"); + } + uint name_len = u16(bytes, p + 26); + uint extra_len = u16(bytes, p + 28); + size_t start = p + 30 + name_len + extra_len; + size_t end = start + e.compressed; + if (end > bytes.length) { + throw new OcdaZipError(e.name ~ ": runs past the end of the archive"); + } + if (e.method != 0) { + throw new OcdaZipError(e.name ~ ": compression method " + ~ e.method.to!string ~ "; this reader takes only stored entries," + ~ " which is what spine writes"); + } + return bytes[start .. end].dup; +} + +/+ ↓ the first entry whose name ends this way, or none. + Used to find media/abstraction/<uid>.<lang>.ssp without knowing the uid. ++/ +ZipEntry[] zipFindSuffix(ZipEntry[] entries, string suffix) { + ZipEntry[] out_; + foreach (e; entries) { + if (e.name.endsWith(suffix)) { out_ ~= e; } + } + return out_; +} + +private uint u16(const(ubyte)[] b, size_t i) { + return cast(uint) b[i] | (cast(uint) b[i + 1] << 8); +} + +private uint u32(const(ubyte)[] b, size_t i) { + return cast(uint) b[i] + | (cast(uint) b[i + 1] << 8) + | (cast(uint) b[i + 2] << 16) + | (cast(uint) b[i + 3] << 24); +} diff --git a/dlang/src/ocda/zstd.d b/dlang/src/ocda/zstd.d new file mode 100644 index 0000000..401f1a3 --- /dev/null +++ b/dlang/src/ocda/zstd.d @@ -0,0 +1,79 @@ +module ocda.zstd; + +/+ ↓ libzstd, declared rather than bound. + . + A .sisupod is one zstd frame wrapping a zip archive, so reading one + needs exactly two things from the library: is this a frame, and what is + in it. Both are declared here and the C library is linked, which is the + same arrangement ocda.sqlite uses: no vendored tree, no generated + header, and the prototypes say what is being called. ++/ + +extern (C) @nogc nothrow private { + size_t ZSTD_decompress(void* dst, size_t dstCapacity, + const(void)* src, size_t compressedSize); + ulong ZSTD_getFrameContentSize(const(void)* src, size_t srcSize); + uint ZSTD_isError(size_t code); + const(char)* ZSTD_getErrorName(size_t code); +} + +/+ ↓ the two values ZSTD_getFrameContentSize returns in place of a size +/ +private enum ulong contentSizeUnknown = ulong.max; +private enum ulong contentSizeError = ulong.max - 1; + +/+ ↓ the magic number of a zstd frame, little endian 0xFD2FB528 +/ +private static immutable ubyte[4] zstd_magic = [0x28, 0xB5, 0x2F, 0xFD]; + +class OcdaZstdError : Exception { + this(string msg) { super(msg); } +} + +/+ ↓ does this begin with a zstd frame? + Asked of the bytes rather than of the filename, because what is inside + decides how a thing is opened. A .sisupod is a frame; a .zip published + before spine wrapped them is not, and both are read. ++/ +bool zstdIsFrame(const(ubyte)[] bytes) { + if (bytes.length < zstd_magic.length) { return false; } + foreach (i, b; zstd_magic) { + if (bytes[i] != b) { return false; } + } + return true; +} + +/+ ↓ one frame in, its contents out. + max_size is a refusal rather than a buffer size: a frame declares how + much it expands to, and a frame that claims more than the caller is + willing to hold is not decompressed at all. A reader of an artefact it + did not make wants that limit. ++/ +ubyte[] zstdDecompress(const(ubyte)[] bytes, size_t max_size) { + if (!zstdIsFrame(bytes)) { + throw new OcdaZstdError("not a zstd frame"); + } + ulong declared = ZSTD_getFrameContentSize(bytes.ptr, bytes.length); + if (declared == contentSizeError) { + throw new OcdaZstdError("zstd frame: could not read its content size"); + } + if (declared == contentSizeUnknown) { + throw new OcdaZstdError("zstd frame declares no content size;" + ~ " this reader takes only frames that do"); + } + if (declared > max_size) { + import std.conv : to; + throw new OcdaZstdError("zstd frame expands to " ~ declared.to!string + ~ " bytes, over the " ~ max_size.to!string ~ " byte limit"); + } + auto out_ = new ubyte[](cast(size_t) declared); + size_t got = ZSTD_decompress(out_.ptr, out_.length, bytes.ptr, bytes.length); + if (ZSTD_isError(got)) { + import std.string : fromStringz; + throw new OcdaZstdError("zstd: " + ~ ZSTD_getErrorName(got).fromStringz.idup); + } + if (got != declared) { + throw new OcdaZstdError("zstd frame expanded to a different size" + ~ " than it declared"); + } + return out_; +} |
