diff options
| author | Ralph Amissah <ralph.amissah@gmail.com> | 2026-09-24 11:12:28 -0400 |
|---|---|---|
| committer | Ralph Amissah <ralph.amissah@gmail.com> | 2026-09-24 11:12:28 -0400 |
| commit | da833f8b157ae501c9f6eec827dd4a965bfa7265 (patch) | |
| tree | 9368bbfe07dc130867dc8241d20bc3d125f3e510 /src/output_images.d | |
| parent | commencement: a reader for the .ssp (diff) | |
format 2.0: the version gate
The reader as it stood when the format reached 2.0, in D: a parser of
the .ssp with no dependency beyond phobos, and outputs from it - a
heading tree, an html scroll, breadcrumbed text, chunked jsonl for
embedding pipelines, an image manifest, and a check of image records
against the images on disk.
Brought to abstraction format 2.0, and made able to say what it does
not understand, so a reader can check that its format specification is
complete. Previously the reader ignored what it did not recognise and
reported nothing, which made it seem it had understood a 2.0 file (and
drop things in silence).
Now:
- the banner is read, and the major part checked. A major this
reader does not know is refused, exit 3, because an unknown major
means a property may have changed meaning or gone away and loading
it half populated in silence is the failure the check exists to
prevent. --any-version reads it regardless, for looking at a file
rather than trusting one. A file with no banner warns and is read.
- @source is a preamble block beside @meta, @make and @doc_has, and
the summary line shows the language and the markup digest.
- tail is a section like the rest.
- --report-unknown lists every property, block and line shape met and
not understood, with counts. Ignoring them remains the conforming
behaviour within a major version; the counting is so that it is not
silent.
Over the markup document samples that report names 18 properties,
from .is_of_type at 56,882 occurrences down to .attrib at
1. Several are legitimately of no interest to a renderer and several
are not. Deciding which is which is the next pass, and it now has a
measured work list rather than a guess.
(assisted by Claude-Code)
Diffstat (limited to 'src/output_images.d')
| -rw-r--r-- | src/output_images.d | 114 |
1 files changed, 114 insertions, 0 deletions
diff --git a/src/output_images.d b/src/output_images.d new file mode 100644 index 0000000..69fb458 --- /dev/null +++ b/src/output_images.d @@ -0,0 +1,114 @@ +module output_images; + +import std.array : join; +import std.conv : to; +import std.stdio : writeln, File; +import ssp_types; + +/+ ↓ 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(SspDocument 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(SspDocument 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(SspDocument doc) { + return gatherImageRecords(doc).records; +} + +package immutable string[] sectionNames = [ + "head", "toc", "body", "endnotes", + "glossary", "bibliography", "bookindex", "blurb", +]; |
