diff options
| author | Ralph Amissah <ralph.amissah@gmail.com> | 2026-09-29 19:37:04 -0400 |
|---|---|---|
| committer | Ralph Amissah <ralph.amissah@gmail.com> | 2026-10-02 21:38:49 -0400 |
| commit | 33821eb37c78b00fedd7b0454ec0b77aeb8342ff (patch) | |
| tree | 7b0745dee88103c8e7c89c9685fe1e9e0cdac152 /dlang/src/read/images.d | |
| parent | D: what a source holds, and what a database holds unread (diff) | |
D: ocda-read, the reader, over the library, of every form
One reader where there were two. sisudoc-ssp-reader read a .ssp and
sisudoc-ocda-db-reader a .ocda.db, each with its own parser; this one
is built on the library, so every mode reads a .ssp, a .ocda.db and a
.sisupod, and says the same thing of each. Its output modules are the
.ssp reader's, copied (the reader repositories are unchanged) and
moved onto the library's model, which was the reader's types renamed
and added to. From the database reader, --languages and --files.
ocda-read [--tree|--outline|--html|--llm-text|--llm-jsonl|--images|
--verify --image-dir=<d>|--languages|--files|
--report-unknown|--validate] <file> [lang]
Two modes are about the file and say so: --files answers for a
.ocda.db, and --validate checks a .ssp as text and refuses anything
else. Where a file holds several languages and none is named, every
form reads the first and says so, where the database used to take one
and the pod refuse.
In src/read/ beside the library in src/ocda/; dub.json keeps it out of
the library (configurations "library" and "ocda-read"), and the flake
builds it as a package. The flake's default is now all three programs
in one bin/: built separately into the same result link, each replaced
the one before, and the pipeline's dump looked for ocda-dump where
only ocda-agree was left.
Checked over the 36 document-languages:
- against the .ssp reader, on a .ssp, byte for byte after the first
line (Parsed: is Read:): --tree, --html, --llm-text, --llm-jsonl,
--images, --verify, --validate, 36 of 36; the summary differs only
in the closing hint, which names the two new modes;
- against the database reader, on a .ocda.db: --files 27 of 27, and
--languages 27 of 27 on language, source and digest (its id column,
the database's own key, is left out);
- the same output from the .ssp, the .ocda.db and the .sisupod: the
summary and --tree, --html, --llm-text, --llm-jsonl, --images and
--report-unknown, 36 of 36; --languages, .ocda.db == .sisupod 27 of
27, and a single-language .ssp == its database, 26 of 26.
Not reproduced, deliberately: the database reader's --outline, which
ordered the headings by their position within their own section, so
that the toc and the "(skip)" headings of other sections fell among
the body's. --outline here is --tree.
(assisted by Claude-Code)
Diffstat (limited to 'dlang/src/read/images.d')
| -rw-r--r-- | dlang/src/read/images.d | 114 |
1 files changed, 114 insertions, 0 deletions
diff --git a/dlang/src/read/images.d b/dlang/src/read/images.d new file mode 100644 index 0000000..afddc74 --- /dev/null +++ b/dlang/src/read/images.d @@ -0,0 +1,114 @@ +module read.images; + +import std.array : join; +import std.conv : to; +import std.stdio : writeln, File; +import ocda.model; + +/+ ↓ the .image records of a document, gathered per distinct file, with the + objects referencing each file, in order of first appearance +/ +struct ImageEntry { + string name; + string sha256; + ulong bytes; + int width; + int height; + bool missing; + string[] refs; + string[] other_sha256; // same filename, differing digest +} + +struct ImageRecords { + int records; // .image lines, an image referenced twice counts twice + ImageEntry[] entries; // distinct files +} + +ImageRecords gatherImageRecords(OcdaDocument doc) { + ImageRecords ret; + size_t[string] seen; + foreach (section; sectionNames) { + auto objs = doc.sectionByName(section); + if (objs is null) continue; + foreach (obj; *objs) { + foreach (img; obj.images) { + ret.records += 1; + string _ref = section ~ "[" ~ obj.ocn.to!string ~ "]"; + if (auto at = img.name in seen) { + if (ret.entries[*at].sha256 != img.sha256 + && img.sha256.length > 0 + && ret.entries[*at].sha256.length > 0) { + ret.entries[*at].other_sha256 ~= img.sha256; + } + ret.entries[*at].refs ~= _ref; + } else { + ImageEntry e_; + e_.name = img.name; + e_.sha256 = img.sha256; + e_.bytes = img.bytes; + e_.width = img.width; + e_.height = img.height; + e_.missing = img.missing; + e_.refs = [_ref]; + seen[img.name] = ret.entries.length; + ret.entries ~= e_; + } + } + } + } + return ret; +} + +/+ ↓ image manifest, line oriented and greppable: + + <sha256> <bytes> <px> <filename> refs: body[97] body[412] + MISSING <filename> refs: body[840] + + The point of the record in the .ssp is verification (is the image + shipped in this pod the image the abstraction was built from), so this + output is the shape a verifier wants: one line per distinct file. ++/ +void outputImages(OcdaDocument doc, string output_file) { + auto gathered = gatherImageRecords(doc); + string[] lines; + int missing = 0; + foreach (e; gathered.entries) { + if (e.missing) missing += 1; + } + lines ~= "Images: " ~ gathered.records.to!string ~ " record" + ~ ((gathered.records == 1) ? "" : "s") + ~ ", " ~ gathered.entries.length.to!string ~ " distinct file" + ~ ((gathered.entries.length == 1) ? "" : "s") + ~ ", " ~ missing.to!string ~ " missing"; + lines ~= ""; + foreach (e; gathered.entries) { + string px = (e.width > 0 && e.height > 0) + ? e.width.to!string ~ "x" ~ e.height.to!string : "-"; + lines ~= (e.missing) + ? "MISSING" ~ " " ~ e.name ~ " refs: " ~ e.refs.join(" ") + : e.sha256 ~ " " ~ e.bytes.to!string ~ " " ~ px + ~ " " ~ e.name ~ " refs: " ~ e.refs.join(" "); + /+ ↓ one filename, more than one digest: the .ssp is inconsistent, + or two distinct files share a name +/ + foreach (other; e.other_sha256) { + lines ~= " WARNING differing digest for same filename: " ~ other; + } + } + + /+ ↓ 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); + } +} + +/+ ↓ count of .image records in a document, for the parse summary +/ +int imageRecordCount(OcdaDocument doc) { + return gatherImageRecords(doc).records; +} + +package immutable string[] sectionNames = [ + "head", "toc", "body", "endnotes", + "glossary", "bibliography", "bookindex", "blurb", +]; |
