diff options
| author | Ralph Amissah <ralph.amissah@gmail.com> | 2026-09-24 16:33:53 -0400 |
|---|---|---|
| committer | Ralph Amissah <ralph.amissah@gmail.com> | 2026-09-24 16:33:53 -0400 |
| commit | bbe505c8d48e822c012c9820dfe93b83dc61bcab (patch) | |
| tree | 3385f5420959ff20af295c3125a080297555a72b /dlang/src/verify_images.d | |
| parent | dealing with six properties including .is_of_type (diff) | |
--validate, and a second reader, in Gleam
--validate: the specification, executed. A validator written from
ssp-format-specification.md and from nothing else, so that a file can
be held against the document rather than against an implementation.
Each finding names the specification section it comes from, so a
disagreement can be taken back to the text.
It checks the version banner and its major part, the file shape and
the order of the preamble blocks and the nine sections, the two
spaces of a preamble pair, the object declaration and its sixteen
kinds and eight heading levels, that a property is one of the 42 and
in the emitted order, that text lines carry their prefix, the ten
keys of doc_has, and that no line is of a shape the specification
does not define.
Every .ssp of the markup document samples validates clean. Five
classes of deliberate breakage are caught: an unknown major version, a
property that is not one of the 42, a property out of order, a kind
that is not one of the sixteen, and a block that is neither preamble
nor section. Writing it found two rules the specification implied
and did not state (repeated properties are consecutive; no property
follows the text), and both were written into it.
One repository, a reader per language. The readers are not separate
tools that share a name. They are the same specification implemented
more than once, and the interesting thing about them is that they
agree, so they are published as one thing with that claim at the top
of it. The D reader moves to dlang/; the Gleam reader arrives at
gleam/. The language directory is named for the language and not
for the tool: gleam refuses a hyphenated package name, so ssp-reader
cannot be a gleam package and must be ssp_reader.
A .gitignore for the repository, denying everything and whitelisting
what belongs, covering both languages.
Both build under nix, sandboxed and without network. There is no gleam
builder in nixpkgs and gleam build fetches from Hex, so the Gleam build
uses nix-gleam's builder, kept in gleam/nix-gleam/ (MIT), which fetches
each Hex package by the checksum manifest.toml already carries, with no
hash to maintain; the result is an escript wrapped with erlang. The D
reader depends on nothing beyond phobos, so --skip-registry=all is the
whole of what it takes: ldc by default, dmd available as ssp-reader-dmd
(given gcc14, GCC 15 having introduced nullptr in headers dmd's ImportC
does not yet parse).
(assisted by Claude-Code)
Diffstat (limited to 'dlang/src/verify_images.d')
| -rw-r--r-- | dlang/src/verify_images.d | 212 |
1 files changed, 212 insertions, 0 deletions
diff --git a/dlang/src/verify_images.d b/dlang/src/verify_images.d new file mode 100644 index 0000000..216c02a --- /dev/null +++ b/dlang/src/verify_images.d @@ -0,0 +1,212 @@ +module verify_images; + +import std.algorithm : sort; +import std.array : array, join; +import std.conv : to; +import std.digest : toHexString; +import std.digest.sha : SHA256, digest; +import std.file : dirEntries, exists, isDir, SpanMode, getSize; +import std.path : baseName, buildPath, extension; +import std.stdio : writeln, File; +import std.string : toLower; +import ssp_types; +import output_images : gatherImageRecords; + +/+ ↓ verification: recompute what the .image records claim, against the + images as they stand in a directory (a pod's media/image). + + ssp-reader --verify --image-dir=<pod>/media/image doc.ssp + + Reports one line per distinct file: + + OK won_benkler_2_1.png + MISMATCH won_benkler_2_1.png sha256 recorded 5BA4... file 1C3D... + ABSENT won_benkler_2_1.png (recorded sha256 5BA4..., not in directory) + PRESENT ffa.png (recorded missing, but the file is there) + EXTRA unused.png (in directory, no record in this .ssp) + + Returns the number of failures. EXTRA is reported but is not a failure: + a pod carries the images of every language version of a document, while + one .ssp covers one language. ++/ +int verifyImages(SspDocument doc, string image_dir, string output_file) { + string[] lines; + int failures = 0; + int ok = 0; + int mismatch = 0; + int absent = 0; + int extra = 0; + + if (!(image_dir.exists) || !(image_dir.isDir)) { + writeln("ERROR: image directory not found: ", image_dir); + return 1; + } + auto gathered = gatherImageRecords(doc); + bool[string] recorded; + + foreach (e; gathered.entries) { + recorded[e.name] = true; + string pth = buildPath(image_dir, e.name); + if (!(pth.exists)) { + if (e.missing) { + /+ recorded missing, and missing here too: consistent +/ + ok += 1; + lines ~= "OK " ~ e.name ~ " (recorded missing, absent here)"; + } else { + absent += 1; + failures += 1; + lines ~= "ABSENT " ~ e.name + ~ " (recorded sha256 " ~ e.sha256 ~ ", not in directory)"; + } + continue; + } + if (e.missing) { + mismatch += 1; + failures += 1; + lines ~= "PRESENT " ~ e.name ~ " (recorded missing, but the file is there)"; + continue; + } + auto file_ = readFileStat(pth); + string[] differs; + if (file_.sha256 != e.sha256) { + differs ~= "sha256 recorded " ~ e.sha256 ~ " file " ~ file_.sha256; + } + if (file_.bytes != e.bytes) { + differs ~= "bytes recorded " ~ e.bytes.to!string + ~ " file " ~ file_.bytes.to!string; + } + /+ px is written only where the dimensions could be read, and read here + only for the formats below, so compare only when both are known +/ + if (e.width > 0 && e.height > 0 && file_.width > 0 && file_.height > 0 + && (file_.width != e.width || file_.height != e.height)) { + differs ~= "px recorded " ~ e.width.to!string ~ "x" ~ e.height.to!string + ~ " file " ~ file_.width.to!string ~ "x" ~ file_.height.to!string; + } + if (differs.length > 0) { + mismatch += 1; + failures += 1; + lines ~= "MISMATCH " ~ e.name ~ " " ~ differs.join("; "); + } else { + ok += 1; + lines ~= "OK " ~ e.name; + } + } + + /+ ↓ files in the directory that no record names +/ + string[] in_dir; + foreach (entry; dirEntries(image_dir, SpanMode.shallow)) { + if (!(entry.isFile)) continue; + string nm = entry.name.baseName; + switch (nm.extension.toLower) { + case ".png": case ".jpg": case ".jpeg": case ".gif": + in_dir ~= nm; + break; + default: break; + } + } + in_dir.sort; + foreach (nm; in_dir) { + if (nm !in recorded) { + extra += 1; + lines ~= "EXTRA " ~ nm ~ " (in directory, no record in this .ssp)"; + } + } + + string head = "Verify: " ~ gathered.entries.length.to!string ~ " distinct file" + ~ ((gathered.entries.length == 1) ? "" : "s") + ~ " in " ~ gathered.records.to!string ~ " record" + ~ ((gathered.records == 1) ? "" : "s") + ~ ", against " ~ image_dir; + lines = [head, ""] ~ lines; + lines ~= ""; + lines ~= "verify: " ~ ok.to!string ~ " ok, " + ~ mismatch.to!string ~ " mismatch, " + ~ absent.to!string ~ " absent, " + ~ extra.to!string ~ " extra" + ~ ((failures == 0) ? " PASS" : " FAIL"); + + /+ ↓ write output +/ + if (output_file.length > 0) { + auto f = File(output_file, "w"); + foreach (line; lines) f.writeln(line); + } else { + foreach (line; lines) writeln(line); + } + return failures; +} + +private struct FileStat_ { + string sha256; + ulong bytes; + int width; + int height; +} + +private FileStat_ readFileStat(string pth) { + FileStat_ ret; + auto f = File(pth, "rb"); + ubyte[32] sha = digest!SHA256(f.byChunk(4096 * 1024)); + ret.sha256 = sha.toHexString.to!string; + ret.bytes = pth.getSize; + auto dim = readImageDimensions(pth); + ret.width = dim[0]; + ret.height = dim[1]; + return ret; +} + +/+ ↓ pixel dimensions from the file header, for the formats spine's markup + admits (png, gif, jpg). Header read only, no decoding, and no dependency + beyond phobos. Returns [0, 0] where the header cannot be read +/ +private int[2] readImageDimensions(string pth) { + int[2] ret = [0, 0]; + ubyte[] head; + try { + auto f = File(pth, "rb"); + head = new ubyte[](64 * 1024); + head = f.rawRead(head); + } catch (Exception ex) { + return ret; + } + if (head.length >= 24 + && head[0 .. 8] == cast(ubyte[])[0x89, 'P', 'N', 'G', 0x0d, 0x0a, 0x1a, 0x0a]) { + /+ png: IHDR width & height, big endian, at 16 and 20 +/ + ret[0] = beInt(head[16 .. 20]); + ret[1] = beInt(head[20 .. 24]); + return ret; + } + if (head.length >= 10 && (head[0 .. 3] == cast(ubyte[])['G', 'I', 'F'])) { + /+ gif: logical screen width & height, little endian, at 6 and 8 +/ + ret[0] = head[6] | (head[7] << 8); + ret[1] = head[8] | (head[9] << 8); + return ret; + } + if (head.length >= 4 && head[0] == 0xff && head[1] == 0xd8) { + /+ jpeg: walk the segments to a start of frame, height then width, + big endian, at offsets 5 and 7 of the segment +/ + size_t i = 2; + while (i + 9 < head.length) { + if (head[i] != 0xff) { i += 1; continue; } + ubyte marker = head[i + 1]; + if (marker == 0xd8 || marker == 0x01 + || (marker >= 0xd0 && marker <= 0xd7)) { i += 2; continue; } + if (marker == 0xff) { i += 1; continue; } + size_t seg_len = (head[i + 2] << 8) | head[i + 3]; + bool is_sof = ((marker >= 0xc0 && marker <= 0xc3) + || (marker >= 0xc5 && marker <= 0xc7) + || (marker >= 0xc9 && marker <= 0xcb) + || (marker >= 0xcd && marker <= 0xcf)); + if (is_sof) { + ret[1] = (head[i + 5] << 8) | head[i + 6]; + ret[0] = (head[i + 7] << 8) | head[i + 8]; + return ret; + } + if (seg_len < 2) break; + i += 2 + seg_len; + } + } + return ret; +} + +private int beInt(const(ubyte)[] b) { + return cast(int)((b[0] << 24) | (b[1] << 16) | (b[2] << 8) | b[3]); +} |
