Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Feature/analysis #31

Draft
wants to merge 10 commits into
base: main
Choose a base branch
from

WIP

17f5b24
Select commit
Loading
Failed to load commit list.
Draft

Feature/analysis #31

WIP
17f5b24
Select commit
Loading
Failed to load commit list.
divvun-taskcluster / Decision task succeeded May 10, 2024 in 1m 52s

Taskcluster Divvun (pull_request)

Details

View task in Taskcluster
View logs in Taskcluster


- "windows_x86_64_msvc 0.52.0",
+ "windows_aarch64_gnullvm 0.52.4",
+ "windows_aarch64_msvc 0.52.4",
+ "windows_i686_gnu 0.52.4",
+ "windows_i686_msvc 0.52.4",
+ "windows_x86_64_gnu 0.52.4",
+ "windows_x86_64_gnullvm 0.52.4",
+ "windows_x86_64_msvc 0.52.4",
 ]
 
 [[package]]
@@ -3082,9 +3002,9 @@ checksum = "2b38e32f0abccf9987a4e3079dfb67dcd799fb61361e53e2882c3cbaf0d905d8"
 
 [[package]]
 name = "windows_aarch64_gnullvm"
-version = "0.52.0"
+version = "0.52.4"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "cb7764e35d4db8a7921e09562a0304bf2f93e0a51bfccee0bd0bb0b666b015ea"
+checksum = "bcf46cf4c365c6f2d1cc93ce535f2c8b244591df96ceee75d8e83deb70a9cac9"
 
 [[package]]
 name = "windows_aarch64_msvc"
@@ -3094,9 +3014,9 @@ checksum = "dc35310971f3b2dbbf3f0690a219f40e2d9afcf64f9ab7cc1be722937c26b4bc"
 
 [[package]]
 name = "windows_aarch64_msvc"
-version = "0.52.0"
+version = "0.52.4"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "bbaa0368d4f1d2aaefc55b6fcfee13f41544ddf36801e793edbbfd7d7df075ef"
+checksum = "da9f259dd3bcf6990b55bffd094c4f7235817ba4ceebde8e6d11cd0c5633b675"
 
 [[package]]
 name = "windows_i686_gnu"
@@ -3106,9 +3026,9 @@ checksum = "a75915e7def60c94dcef72200b9a8e58e5091744960da64ec734a6c6e9b3743e"
 
 [[package]]
 name = "windows_i686_gnu"
-version = "0.52.0"
+version = "0.52.4"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "a28637cb1fa3560a16915793afb20081aba2c92ee8af57b4d5f28e4b3e7df313"
+checksum = "b474d8268f99e0995f25b9f095bc7434632601028cf86590aea5c8a5cb7801d3"
 
 [[package]]
 name = "windows_i686_msvc"
@@ -3118,9 +3038,9 @@ checksum = "8f55c233f70c4b27f66c523580f78f1004e8b5a8b659e05a4eb49d4166cca406"
 
 [[package]]
 name = "windows_i686_msvc"
-version = "0.52.0"
+version = "0.52.4"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "ffe5e8e31046ce6230cc7215707b816e339ff4d4d67c65dffa206fd0f7aa7b9a"
+checksum = "1515e9a29e5bed743cb4415a9ecf5dfca648ce85ee42e15873c3cd8610ff8e02"
 
 [[package]]
 name = "windows_x86_64_gnu"
@@ -3130,9 +3050,9 @@ checksum = "53d40abd2583d23e4718fddf1ebec84dbff8381c07cae67ff7768bbf19c6718e"
 
 [[package]]
 name = "windows_x86_64_gnu"
-version = "0.52.0"
+version = "0.52.4"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "3d6fa32db2bc4a2f5abeacf2b69f7992cd09dca97498da74a151a3132c26befd"
+checksum = "5eee091590e89cc02ad514ffe3ead9eb6b660aedca2183455434b93546371a03"
 
 [[package]]
 name = "windows_x86_64_gnullvm"
@@ -3142,9 +3062,9 @@ checksum = "0b7b52767868a23d5bab768e390dc5f5c55825b6d30b86c844ff2dc7414044cc"
 
 [[package]]
 name = "windows_x86_64_gnullvm"
-version = "0.52.0"
+version = "0.52.4"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "1a657e1e9d3f514745a572a6846d3c7aa7dbe1658c056ed9c3344c4109a6949e"
+checksum = "77ca79f2451b49fa9e2af39f0747fe999fcda4f5e241b2898624dca97a1f2177"
 
 [[package]]
 name = "windows_x86_64_msvc"
@@ -3154,9 +3074,9 @@ checksum = "ed94fce61571a4006852b7389a063ab983c02eb1bb37b47f8272ce92d06d9538"
 
 [[package]]
 name = "windows_x86_64_msvc"
-version = "0.52.0"
+version = "0.52.4"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "dff9641d1cd4be8d1a070daf9e3773c5f67e78b4d9d42263020c057706765c04"
+checksum = "32b752e52a2da0ddfbdbcc6fceadfeede4c939ed16d13e648833a61dfb611ed8"
 
 [[package]]
 name = "winreg"
@@ -3194,6 +3114,26 @@ dependencies = [
  "lzma-sys",
 ]
 
+[[package]]
+name = "zerocopy"
+version = "0.7.32"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "74d4d3961e53fa4c9a25a8637fc2bfaf2595b3d3ae34875568a5cf64787716be"
+dependencies = [
+ "zerocopy-derive",
+]
+
+[[package]]
+name = "zerocopy-derive"
+version = "0.7.32"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "9ce1b18ccd8e73a9321186f97e46f9f04b778851177567b1975109d26a08d2a6"
+dependencies = [
+ "proc-macro2",
+ "quote",
+ "syn 2.0.52",
+]
+
 [[package]]
 name = "zip"
 version = "0.5.13"
diff --git a/accuracy/Cargo.toml b/accuracy/Cargo.toml
index eda84e1..46e4ff5 100644
--- a/accuracy/Cargo.toml
+++ b/accuracy/Cargo.toml
@@ -15,7 +15,7 @@ rayon = { version = "1.4.0" }
 indicatif = { version = "0.15", features = ["with_rayon"] }
 # box-format = { git = "https://github.com/bbqsrc/box", branch = "master" }
 # tempdir = "0.3.7"
-pretty_env_logger = "0.4.0"
+pretty_env_logger = "0.5.0"
 # ctor = "*"
 # gumdrop = "0.8.0"
 # thiserror = "1.0.20"
diff --git a/divvunspell-bin/Cargo.toml b/divvunspell-bin/Cargo.toml
index 72dd7b6..2c6d18d 100644
--- a/divvunspell-bin/Cargo.toml
+++ b/divvunspell-bin/Cargo.toml
@@ -16,7 +16,7 @@ serde = { version = "1.0.116", features = ["derive"] }
 serde_json = "1.0.57"
 divvunspell = { version = "1.0.0-beta.3", features = ["internal_convert", "compression"], path = "../divvunspell" }
 box-format = { version = "0.3.2", features = ["reader"], default-features = false }
-pretty_env_logger = "0.4.0"
+pretty_env_logger = "0.5.0"
 gumdrop = "0.8.0"
 anyhow = "1.0.32"
 structopt = "0.3.17"
diff --git a/divvunspell/Cargo.toml b/divvunspell/Cargo.toml
index 9df4ee4..b2eaba1 100644
--- a/divvunspell/Cargo.toml
+++ b/divvunspell/Cargo.toml
@@ -13,28 +13,28 @@ crate-type = ["rlib", "staticlib", "cdylib"]
 
 [dependencies]
 libc = "0.2"
-memmap2 = "0.5.0"
+memmap2 = "0.9.4"
 byteorder = "1.3.4"
 serde = { version = "1.0.116", features = ["derive"] }
 serde_json = "1.0.57"
-serde-xml-rs = { version = "0.5.0", default-features = false }
+serde-xml-rs = { version = "0.6.0", default-features = false }
 zip = { version = "0.5", default-features = false }
 unic-segment = "0.9.0"
 unic-char-range = "0.9.0"
 unic-char-property = "0.9.0"
 unic-ucd-category = "0.9.0"
-parking_lot = "0.11.2"
-hashbrown = { version = "0.11", features = ["serde"] }
+parking_lot = "0.12.1"
+hashbrown = { version = "0.14.3", features = ["serde"] }
 lifeguard = "0.6.1"
-smol_str = { version = "0.1.16", features = ["serde"] }
+smol_str = { version = "0.2.1", features = ["serde"] }
 box-format = { version = "0.3.2", features = ["reader"], default-features = false }
-itertools = "0.10"
-strsim = "0.10.0"
+itertools = "0.12.1"
+strsim = "0.11.0"
 log = "0.4.11"
-cffi = "0.1.6"
+cffi = { path = "../../../github/cffi", optional = true } #{ git = "https://github.com/cffi-rs/cffi", optional = true }
 unic-ucd-common = "0.9.0"
 flatbuffers = { version = "0.6.1", optional = true }
-env_logger = { version = "0.9", optional = true }
+env_logger = { version = "0.11.2", optional = true }
 thiserror = "1.0.20"
 tch = { version = "0.6.1", optional = true }
 rust-bert = { version = "0.17.0", optional = true }
@@ -44,7 +44,7 @@ fs_extra = "1.2.0"
 eieio = "1.0.0"
 pathos = "0.3.0"
 language-tags = "0.3.2"
-globwalk = "0.8.1"
+globwalk = "0.9.1"
 
 [features]
 compression = ["zip/deflate"]
@@ -53,4 +53,4 @@ gpt2 = ["tch", "rust-bert", "rust_tokenizers"]
 
 # Internal features: unstable, not for external use!
 internal_convert = []
-internal_ffi = ["flatbuffers", "logging"]
+internal_ffi = ["flatbuffers", "logging", "cffi"]
diff --git a/divvunspell/src/archive/mod.rs b/divvunspell/src/archive/mod.rs
index cea3da4..a56cf54 100644
--- a/divvunspell/src/archive/mod.rs
+++ b/divvunspell/src/archive/mod.rs
@@ -79,7 +79,7 @@ pub(crate) mod ffi {
     use cffi::{FromForeign, ToForeign};
     use std::error::Error;
 
-    #[cffi::marshal(return_marshaler = "cffi::ArcMarshaler::<dyn SpellerArchive + Send + Sync>")]
+    #[cffi::marshal(return_marshaler = cffi::ArcMarshaler::<dyn SpellerArchive + Send + Sync>)]
     pub extern "C" fn divvun_speller_archive_open(
         #[marshal(cffi::PathBufMarshaler)] path: std::path::PathBuf,
     ) -> Result<Arc<dyn SpellerArchive + Send + Sync>, Box<dyn Error>> {
diff --git a/divvunspell/src/speller/mod.rs b/divvunspell/src/speller/mod.rs
index 16d0782..334f54f 100644
--- a/divvunspell/src/speller/mod.rs
+++ b/divvunspell/src/speller/mod.rs
@@ -471,7 +471,7 @@ pub(crate) mod ffi {
                 },
                 case_handling,
                 node_pool_size: config.node_pool_size,
-                completion_marker: None,
+                continuation_marker: None,
             };
 
             Ok(out)

From 17f5b2441ae48769736398a1502beee603e2035c Mon Sep 17 00:00:00 2001
From: Brendan Molloy <[email protected]>
Date: Fri, 10 May 2024 19:58:20 +0200
Subject: [PATCH] WIP

---
 Cargo.lock                     | 702 +++++++++++++++------------------
 accuracy/Cargo.toml            |   2 +-
 divvunspell-bin/Cargo.toml     |   2 +-
 divvunspell/Cargo.toml         |  22 +-
 divvunspell/src/archive/mod.rs |   2 +-
 divvunspell/src/speller/mod.rs |   2 +-
 6 files changed, 336 insertions(+), 396 deletions(-)


[taskcluster 2024-05-10 18:00:34.895Z] === Task Finished ===
[taskcluster 2024-05-10 18:00:34.895Z] Successful task run with exit code: 0 completed in 2.431 seconds