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

pdftriage: text layer verdicts, including the reflected-font recovery

Browse Source
This commit is contained in:
funkpower
2026-09-19 11:46:34 -04:00
parent bd0ae11d01
commit 33c2e40a1a
16 changed files with 1465 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files
Cargo.toml
+6 -1
View File
@@ -14,14 +14,19 @@ 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" }
pdftriage = { path = "crates/pdftriage", version = "0.1.0" }
clap = { version = "4", features = ["derive"] }
fancy-regex = "0.16"
regex = "1"
schemars = "1"
serde = { version = "1", features = ["derive"] }
serde_json = "1"
# float_roundtrip: without it a float read back from JSON can be one unit in
# the last place away from the one that was written, which would make a
# record that round-trips through a pipe not the record it started as.
serde_json = { version = "1", features = ["float_roundtrip"] }
thiserror = "2"
unicode-general-category = "1"
tiktoken-rs = "0.12"
[workspace.lints.rust]