Introduce a simple FST based chinese word segmenter

This commit is contained in:
Clément Renault
2020-10-03 14:58:41 +02:00
parent 6cc6addc2f
commit acd2a63879
4 changed files with 349234 additions and 6 deletions

View File

@ -11,7 +11,7 @@ bstr = "0.2.13"
byteorder = "1.3.4"
csv = "1.1.3"
flate2 = "1.0.17"
fst = "0.4.3"
fst = "0.4.4"
fxhash = "0.2.1"
heed = { version = "0.8.1", default-features = false, features = ["lmdb"] }
human_format = "1.0.3"
@ -48,6 +48,9 @@ warp = "0.2.2"
[dev-dependencies]
criterion = "0.3"
[build-dependencies]
fst = "0.4.4"
[features]
default = []