langid and tocfind: what language a book is in, and what it says its chapters are

This commit is contained in:
funkpower
2026-09-20 10:02:15 -04:00
parent 05759ab902
commit d24e37bd12
15 changed files with 1928 additions and 0 deletions
Generated
+26
View File
@@ -907,6 +907,18 @@ dependencies = [
"wasm-bindgen",
]
[[package]]
name = "langid"
version = "0.1.0"
dependencies = [
"catena-cli",
"clap",
"corpus-core",
"schemars",
"serde",
"serde_json",
]
[[package]]
name = "lazy_static"
version = "1.5.0"
@@ -1699,6 +1711,20 @@ version = "1.13.3"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "fd3ca314f692efd6c868f8408f53fe444634a845f96c028b97d35f6a1f79f0ee"
[[package]]
name = "tocfind"
version = "0.1.0"
dependencies = [
"catena-cli",
"clap",
"corpus-core",
"lopdf",
"schemars",
"serde",
"serde_json",
"zip",
]
[[package]]
name = "ttf-parser"
version = "0.25.1"