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

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
Generated
+19
View File
@@ -247,10 +247,23 @@ dependencies = [
"chunkmd",
"corpus-core",
"mdscrub",
"pdftriage",
"serde_json",
"textkit",
]
[[package]]
name = "pdftriage"
version = "0.1.0"
dependencies = [
"clap",
"corpus-core",
"regex",
"serde_json",
"textkit",
"unicode-general-category",
]
[[package]]
name = "proc-macro2"
version = "1.0.107"
@@ -462,6 +475,12 @@ dependencies = [
"rustc-hash",
]
[[package]]
name = "unicode-general-category"
version = "1.1.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "0b993bddc193ae5bd0d623b49ec06ac3e9312875fdae725a975c51db1cc1677f"
[[package]]
name = "unicode-ident"
version = "1.0.26"