funkpower/catena
1
0
Fork 0
mirror of https://git.pumpin.online/funkpower/catena.git synced 2026-10-22 18:57:14 +00:00
Code Issues Packages Projects Releases Wiki Activity

mdscrub: residual html, control characters, headings, page markers

Browse Source
This commit is contained in:
funkpower
2026-09-19 11:30:05 -04:00
parent e0473fb8ae
commit 1b3c002b3d
34 changed files with 975 additions and 18 deletions
Download Patch File Download Diff File Expand all files Collapse all files
Cargo.lock
Generated
+11
View File
@@ -218,6 +218,16 @@ version = "1.5.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "bbd2bcb4c963f2ddae06a2efc7e9f3591312473c50c6685e1f298068316e66fe"
[[package]]
name = "mdscrub"
version = "0.1.0"
dependencies = [
"clap",
"corpus-core",
"regex",
"textkit",
]
[[package]]
name = "memchr"
version = "2.8.3"
@@ -236,6 +246,7 @@ version = "0.1.0"
dependencies = [
"chunkmd",
"corpus-core",
"mdscrub",
"serde_json",
"textkit",
]