mirror of
https://git.pumpin.online/funkpower/catena.git
synced 2026-11-07 05:45:39 +00:00
mdscrub: residual html, control characters, headings, page markers
This commit is contained in:
34 files changed
+975
-18
No files matched your search
@@ -13,6 +13,7 @@ repository = "https://git.pumpin.online/funkpower/catena"
|
||||
corpus-core = { path = "crates/corpus-core", version = "0.1.0" }
|
||||
textkit = { path = "crates/textkit", version = "0.1.0" }
|
||||
chunkmd = { path = "crates/chunkmd", version = "0.1.0" }
|
||||
mdscrub = { path = "crates/mdscrub", version = "0.1.0" }
|
||||
|
||||
clap = { version = "4", features = ["derive"] }
|
||||
fancy-regex = "0.16"
|
||||
|
||||
Reference in new issue
Block a user