From a4ef474cabc4113c3dca72bf08bc477c452c624c Mon Sep 17 00:00:00 2001 From: Ralph Amissah Date: Wed, 26 Aug 2026 22:53:30 -0400 Subject: image digest: single read, cache file read & hash For image digests cache file read & hash, one read per image file Fix issue: images referenced from several objects were read and hashed once per reference. [as an example in the sisu-manual sm_tux.png accounts for 6 of the document's image records (12 across the sample set), each of them a fresh read of the same bytes, and source_pod.d hashes the file again for digests.txt.] Memoise on the full path within safeComputeHashAndSize. static is thread-local in D, so documents processed in parallel each get their own cache and no synchronisation is involved. Files are not expected to change during a run. Output is unchanged: identical .ssp output. (An image that is missing or unreadable now warns once to stdout rather than once per reference). (assisted by Claude-Code) --- src/sisudoc/ocda/meta/metadoc_from_src_functions.d | 12 +++++++++++- 1 file changed, 11 insertions(+), 1 deletion(-) (limited to 'src/sisudoc/ocda/meta') diff --git a/src/sisudoc/ocda/meta/metadoc_from_src_functions.d b/src/sisudoc/ocda/meta/metadoc_from_src_functions.d index 6a000ea..cc79a67 100644 --- a/src/sisudoc/ocda/meta/metadoc_from_src_functions.d +++ b/src/sisudoc/ocda/meta/metadoc_from_src_functions.d @@ -3190,7 +3190,16 @@ template docAbstractionFunctions() { M manifested, ) { ST_file_name_hash_size_ safeComputeHashAndSize(N,P)(N filename, P file_path) @trusted { - auto file_with_path = file_path ~ filename; + string file_with_path = (file_path ~ filename).to!string; + /+ ↓ read & hash each image file once: an image referenced from several + objects (or from several documents sharing an image directory) was + otherwise re-read and re-hashed for every reference. static is + thread-local in D, so the cache needs no synchronisation + +/ + static ST_file_name_hash_size_[string] _image_file_info_cache; + if (auto _cached = file_with_path in _image_file_info_cache) { + return *_cached; + } ST_file_name_hash_size_ _file_info; _file_info.fileName = filename; /+ ↓ a referenced image that is absent or unreadable is recorded as @@ -3226,6 +3235,7 @@ template docAbstractionFunctions() { } } } + _image_file_info_cache[file_with_path] = _file_info; return _file_info; } obj.metainfo.sha256.text = obj.text.sha256Of; -- cgit v1.2.3