summaryrefslogtreecommitdiffhomepage
path: root/dlang/src/ocda/zip.d
diff options
context:
space:
mode:
authorRalph Amissah <ralph.amissah@gmail.com>2026-09-25 22:57:24 -0400
committerRalph Amissah <ralph.amissah@gmail.com>2026-10-02 21:38:24 -0400
commit483c14bf6cc284710e06c9d27747e1ecf5d9466b (patch)
tree7ff1513f2e0db2312e131dfb2899a99a3a347634 /dlang/src/ocda/zip.d
parenttest: the fixture indented its property lines, so none were read (diff)
a third input form: the abstraction out of a pod archive
A pod built with --pod2 carries the abstraction inside it, at media/abstraction/<uid>.<lang>.ssp. So ocda.load gains .sisupod and .zip, and because the dispatch is in one place a writer over the library gained a third input form without being touched. Over the reference collection a .sisupod gives the same model as the .ssp beside it: 36 of 36 document-languages, byte identical dumps. And the text writer, unchanged, renders a document from its .sisupod byte identically to spine --text, 36 of 36. Two small readers, neither of them a library: ocda.zstd declares the four libzstd entry points needed to unwrap a frame, as ocda.sqlite declares sqlite3; ocda.zip reads a central directory and one stored entry. Deflate is refused rather than mishandled, since spine writes stored entries and a library that says it read what it skipped is worse than one that says it cannot. A frame that declares an expansion over 512 MiB is refused before anything is allocated: a reader of an artefact it did not make declines to be told how much memory to take. The Gleam library reads the zip and not the frame. The only zstd on the BEAM is a NIF that clones zstd from github in its own build, so it cannot be built sandboxed without patching it. A .zip pod is read in both languages, a .sisupod in D only, and the Gleam refusal says why and says "zstd -d" rather than claiming the file is malformed. It is a packaging limit, not anything about the format, and the only place the two libraries differ in what they accept. A pod without an abstraction is refused with a message naming the flag that puts one in, because that is a fact about the pod. (assisted by Claude-Code)
Diffstat (limited to 'dlang/src/ocda/zip.d')
-rw-r--r--dlang/src/ocda/zip.d115
1 files changed, 115 insertions, 0 deletions
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);
+}