2 Commits
Author SHA1 Message Date
funkpower 6f32f52293 0.3.1, properly — the version, and the test that names the first register
The commit that reordered the chain did not carry the version bump. The
bump was chained after check.sh with &&, the commit after a semicolon, so
a failing check skipped the bump and let the commit through. The tag then
pointed at a tree still calling itself 0.3.0, which the release workflow
asserts against and would have refused.

check.sh was failing because a test names which register is asked first
about an ISBN, which is exactly what changed. It now names the index, for
the reason the reorder happened.
2026-09-22 10:03:50 -04:00
funkpower e480f07c32 0.3.1 — ask the index first, which answers in one request
The chain asked OpenLibrary's edition record first and its search index
second. The edition record is the slow one: measured against this
library it takes five to twenty-eight seconds, and it names its authors
by key, so a second request was needed anyway. The index, asked for its
fields by name, returns the title, the authors, the publisher, the
language, a page count and the subjects together, in about a quarter of
a second.

Reordering them turns three requests per book into one, and a pass over
five thousand books from fifty-three hours into well under one. The
edition record is still there for a subtitle or a publisher the index
did not give.
2026-09-22 09:36:46 -04:00
3 changed files with 66 additions and 55 deletions
Generated
+26 -26
View File
@@ -101,7 +101,7 @@ checksum = "f2032f911046de80f0a198e0901378627c33f59ea0ac00e363d481118bd70a53"
[[package]]
name = "avplan"
version = "0.3.0"
version = "0.3.1"
dependencies = [
"catena-cli",
"clap",
@@ -126,7 +126,7 @@ checksum = "ac07cdecf99051d9a5238b80f35af32cdeba5b336e55d957b318b50137e18da5"
[[package]]
name = "bibclean"
version = "0.3.0"
version = "0.3.1"
dependencies = [
"catena-cli",
"clap",
@@ -143,7 +143,7 @@ dependencies = [
[[package]]
name = "bibfetch"
version = "0.3.0"
version = "0.3.1"
dependencies = [
"catena-cli",
"clap",
@@ -196,7 +196,7 @@ dependencies = [
[[package]]
name = "bookmeta"
version = "0.3.0"
version = "0.3.1"
dependencies = [
"catena-cli",
"clap",
@@ -210,7 +210,7 @@ dependencies = [
[[package]]
name = "booksniff"
version = "0.3.0"
version = "0.3.1"
dependencies = [
"catena-cli",
"clap",
@@ -250,7 +250,7 @@ checksum = "fc652a48c352aef3ea3aed32080501cf3ef6ed5da78602a020c991775b0aff04"
[[package]]
name = "catena"
version = "0.3.0"
version = "0.3.1"
dependencies = [
"bibclean",
"bibfetch",
@@ -277,7 +277,7 @@ dependencies = [
[[package]]
name = "catena-cli"
version = "0.3.0"
version = "0.3.1"
dependencies = [
"clap",
"clap_mangen",
@@ -312,7 +312,7 @@ checksum = "4e7648175b45a9a48536d676f68d918270699102aa8dab5496df06904c914600"
[[package]]
name = "chunkmd"
version = "0.3.0"
version = "0.3.1"
dependencies = [
"catena-cli",
"clap",
@@ -334,7 +334,7 @@ dependencies = [
[[package]]
name = "citefind"
version = "0.3.0"
version = "0.3.1"
dependencies = [
"catena-cli",
"chunkmd",
@@ -399,7 +399,7 @@ dependencies = [
[[package]]
name = "colophon"
version = "0.3.0"
version = "0.3.1"
dependencies = [
"bibclean",
"catena-cli",
@@ -448,7 +448,7 @@ dependencies = [
[[package]]
name = "corpus-core"
version = "0.3.0"
version = "0.3.1"
dependencies = [
"schemars",
"serde",
@@ -492,7 +492,7 @@ dependencies = [
[[package]]
name = "cuekit"
version = "0.3.0"
version = "0.3.1"
dependencies = [
"corpus-core",
"regex",
@@ -504,7 +504,7 @@ dependencies = [
[[package]]
name = "cuenorm"
version = "0.3.0"
version = "0.3.1"
dependencies = [
"catena-cli",
"clap",
@@ -514,7 +514,7 @@ dependencies = [
[[package]]
name = "cuepack"
version = "0.3.0"
version = "0.3.1"
dependencies = [
"catena-cli",
"clap",
@@ -525,7 +525,7 @@ dependencies = [
[[package]]
name = "cueseg"
version = "0.3.0"
version = "0.3.1"
dependencies = [
"catena-cli",
"clap",
@@ -612,7 +612,7 @@ dependencies = [
[[package]]
name = "emb"
version = "0.3.0"
version = "0.3.1"
dependencies = [
"catena-cli",
"clap",
@@ -876,7 +876,7 @@ dependencies = [
[[package]]
name = "idnorm"
version = "0.3.0"
version = "0.3.1"
dependencies = [
"bibclean",
"catena-cli",
@@ -942,7 +942,7 @@ dependencies = [
[[package]]
name = "langid"
version = "0.3.0"
version = "0.3.1"
dependencies = [
"catena-cli",
"clap",
@@ -1022,7 +1022,7 @@ dependencies = [
[[package]]
name = "mdscrub"
version = "0.3.0"
version = "0.3.1"
dependencies = [
"catena-cli",
"clap",
@@ -1034,7 +1034,7 @@ dependencies = [
[[package]]
name = "mdsplit"
version = "0.3.0"
version = "0.3.1"
dependencies = [
"catena-cli",
"clap",
@@ -1113,7 +1113,7 @@ checksum = "384b8ab6d37215f3c5301a95a4accb5d64aa607f1fcb26a11b5303878451b4fe"
[[package]]
name = "pdfgutter"
version = "0.3.0"
version = "0.3.1"
dependencies = [
"catena-cli",
"clap",
@@ -1126,7 +1126,7 @@ dependencies = [
[[package]]
name = "pdftriage"
version = "0.3.0"
version = "0.3.1"
dependencies = [
"catena-cli",
"clap",
@@ -1370,7 +1370,7 @@ checksum = "323c417e1d9665a65b263ec744ba09030cfb277e9daa0b018a4ab62e57bc8189"
[[package]]
name = "rrf"
version = "0.3.0"
version = "0.3.1"
dependencies = [
"catena-cli",
"clap",
@@ -1517,7 +1517,7 @@ dependencies = [
[[package]]
name = "seriesof"
version = "0.3.0"
version = "0.3.1"
dependencies = [
"catena-cli",
"clap",
@@ -1634,7 +1634,7 @@ checksum = "adb6935a6f5c20170eeceb1a3835a49e12e19d792f6dd344ccc76a985ca5a6ca"
[[package]]
name = "textkit"
version = "0.3.0"
version = "0.3.1"
dependencies = [
"regex",
"tiktoken-rs",
@@ -1724,7 +1724,7 @@ checksum = "fd3ca314f692efd6c868f8408f53fe444634a845f96c028b97d35f6a1f79f0ee"
[[package]]
name = "tocfind"
version = "0.3.0"
version = "0.3.1"
dependencies = [
"catena-cli",
"clap",
+27 -27
View File
@@ -3,39 +3,39 @@ resolver = "3"
members = ["crates/*"]
[workspace.package]
version = "0.3.0"
version = "0.3.1"
edition = "2024"
rust-version = "1.85"
license = "MPL-2.0"
repository = "https://git.pumpin.online/funkpower/catena"
[workspace.dependencies]
catena-cli = { path = "crates/catena-cli", version = "0.3.0" }
corpus-core = { path = "crates/corpus-core", version = "0.3.0" }
cuekit = { path = "crates/cuekit", version = "0.3.0" }
textkit = { path = "crates/textkit", version = "0.3.0" }
chunkmd = { path = "crates/chunkmd", version = "0.3.0" }
mdscrub = { path = "crates/mdscrub", version = "0.3.0" }
mdsplit = { path = "crates/mdsplit", version = "0.3.0" }
pdftriage = { path = "crates/pdftriage", version = "0.3.0" }
cuenorm = { path = "crates/cuenorm", version = "0.3.0" }
cueseg = { path = "crates/cueseg", version = "0.3.0" }
rrf = { path = "crates/rrf", version = "0.3.0" }
cuepack = { path = "crates/cuepack", version = "0.3.0" }
bibclean = { path = "crates/bibclean", version = "0.3.0" }
avplan = { path = "crates/avplan", version = "0.3.0" }
pdfgutter = { path = "crates/pdfgutter", version = "0.3.0" }
catena = { path = "crates/bindings", version = "0.3.0" }
seriesof = { path = "crates/seriesof", version = "0.3.0" }
idnorm = { path = "crates/idnorm", version = "0.3.0" }
bibfetch = { path = "crates/bibfetch", version = "0.3.0" }
bookmeta = { path = "crates/bookmeta", version = "0.3.0" }
langid = { path = "crates/langid", version = "0.3.0" }
tocfind = { path = "crates/tocfind", version = "0.3.0" }
booksniff = { path = "crates/booksniff", version = "0.3.0" }
citefind = { path = "crates/citefind", version = "0.3.0" }
colophon = { path = "crates/colophon", version = "0.3.0" }
emb = { path = "crates/emb", version = "0.3.0" }
catena-cli = { path = "crates/catena-cli", version = "0.3.1" }
corpus-core = { path = "crates/corpus-core", version = "0.3.1" }
cuekit = { path = "crates/cuekit", version = "0.3.1" }
textkit = { path = "crates/textkit", version = "0.3.1" }
chunkmd = { path = "crates/chunkmd", version = "0.3.1" }
mdscrub = { path = "crates/mdscrub", version = "0.3.1" }
mdsplit = { path = "crates/mdsplit", version = "0.3.1" }
pdftriage = { path = "crates/pdftriage", version = "0.3.1" }
cuenorm = { path = "crates/cuenorm", version = "0.3.1" }
cueseg = { path = "crates/cueseg", version = "0.3.1" }
rrf = { path = "crates/rrf", version = "0.3.1" }
cuepack = { path = "crates/cuepack", version = "0.3.1" }
bibclean = { path = "crates/bibclean", version = "0.3.1" }
avplan = { path = "crates/avplan", version = "0.3.1" }
pdfgutter = { path = "crates/pdfgutter", version = "0.3.1" }
catena = { path = "crates/bindings", version = "0.3.1" }
seriesof = { path = "crates/seriesof", version = "0.3.1" }
idnorm = { path = "crates/idnorm", version = "0.3.1" }
bibfetch = { path = "crates/bibfetch", version = "0.3.1" }
bookmeta = { path = "crates/bookmeta", version = "0.3.1" }
langid = { path = "crates/langid", version = "0.3.1" }
tocfind = { path = "crates/tocfind", version = "0.3.1" }
booksniff = { path = "crates/booksniff", version = "0.3.1" }
citefind = { path = "crates/citefind", version = "0.3.1" }
colophon = { path = "crates/colophon", version = "0.3.1" }
emb = { path = "crates/emb", version = "0.3.1" }
clap = { version = "4", features = ["derive"] }
clap_mangen = "0.3"
+13 -2
View File
@@ -55,9 +55,17 @@ impl Source {
match kind {
"doi" => &[Source::Crossref],
"arxiv" => &[Source::Arxiv],
// The index first. Asked for the fields by name it answers with
// the title, the authors, the publisher, the language, a page
// count and the subjects in one request, which is the whole of
// what a catalogue wants; the edition record is then needed only
// for a subtitle or a publisher the index did not give. Asking it
// second cost three requests per book where one usually does, and
// at three books in flight that is the difference between two
// days and two hours.
"isbn" => &[
Source::OpenLibrary,
Source::OpenLibrarySearch,
Source::OpenLibrary,
Source::GoogleBooks,
],
_ => &[],
@@ -438,7 +446,10 @@ mod tests {
fn each_kind_goes_to_the_body_that_assigns_it() {
assert_eq!(Source::for_kind("doi"), Some(Source::Crossref));
assert_eq!(Source::for_kind("arxiv"), Some(Source::Arxiv));
assert_eq!(Source::for_kind("isbn"), Some(Source::OpenLibrary));
// The index, not the edition record: it answers with the whole of
// what a catalogue wants in one request, where the edition record
// takes up to twenty-eight seconds and names its authors by key.
assert_eq!(Source::for_kind("isbn"), Some(Source::OpenLibrarySearch));
// No register answers about an ISSN without a key.
assert_eq!(Source::for_kind("issn"), None);
}