module read.verify; 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 ocda.model; import read.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=/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(OcdaDocument 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]); }