diff --git a/.idea/.gitignore b/.idea/.gitignore
new file mode 100644
index 0000000..30cf57e
--- /dev/null
+++ b/.idea/.gitignore
@@ -0,0 +1,10 @@
+# Default ignored files
+/shelf/
+/workspace.xml
+# Editor-based HTTP Client requests
+/httpRequests/
+# Ignored default folder with query files
+/queries/
+# Datasource local storage ignored files
+/dataSources/
+/dataSources.local.xml
diff --git a/.idea/breadarr.iml b/.idea/breadarr.iml
new file mode 100644
index 0000000..f2b3868
--- /dev/null
+++ b/.idea/breadarr.iml
@@ -0,0 +1,13 @@
+
+
+
+
+
+
+
+
+
+
+
+
+
\ No newline at end of file
diff --git a/.idea/modules.xml b/.idea/modules.xml
new file mode 100644
index 0000000..393ed2f
--- /dev/null
+++ b/.idea/modules.xml
@@ -0,0 +1,8 @@
+
+
+
+
+
+
+
+
\ No newline at end of file
diff --git a/.idea/vcs.xml b/.idea/vcs.xml
new file mode 100644
index 0000000..35eb1dd
--- /dev/null
+++ b/.idea/vcs.xml
@@ -0,0 +1,6 @@
+
+
+
+
+
+
\ No newline at end of file
diff --git a/Cargo.lock b/Cargo.lock
index ce77140..e1300da 100644
--- a/Cargo.lock
+++ b/Cargo.lock
@@ -2,6 +2,12 @@
# It is not intended for manual editing.
version = 4
+[[package]]
+name = "adler2"
+version = "2.0.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "320119579fcad9c21884f5c4861d16174d0e06250625266f50fe6898340abefa"
+
[[package]]
name = "ahash"
version = "0.8.12"
@@ -156,15 +162,48 @@ checksum = "2af50177e190e07a26ab74f8b1efbfe2ef87da2116221318cb1c2e82baf7de06"
[[package]]
name = "bitflags"
-version = "2.13.0"
+version = "2.13.1"
source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "b4388bee8683e3d04af747c73422af53102d2bd24d9eadb6cbc100baef4b43f8"
+checksum = "b588b76d00fde79687d7646a9b5bdf3cc0f655e0bbd080335a95d7e96f3587da"
+
+[[package]]
+name = "block-buffer"
+version = "0.10.4"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "3078c7629b62d3f0439517fa394996acacc5cbc91c5a20d8c658e77abd503a71"
+dependencies = [
+ "generic-array",
+]
+
+[[package]]
+name = "bread-onnx"
+version = "0.3.0"
+dependencies = [
+ "anyhow",
+ "bread-utils",
+ "hex",
+ "ort",
+ "sha2",
+ "tokenizers",
+ "tracing",
+ "ureq 2.12.1",
+]
+
+[[package]]
+name = "bread-utils"
+version = "0.3.0"
+dependencies = [
+ "dirs",
+ "serde",
+ "serde_json",
+]
[[package]]
name = "breadarr-shared"
version = "0.1.0"
dependencies = [
"anyhow",
+ "bread-utils",
"chrono",
"reqwest",
"serde",
@@ -192,6 +231,7 @@ dependencies = [
"anyhow",
"async-trait",
"axum",
+ "bread-onnx",
"breadarr-shared",
"chrono",
"fastrand",
@@ -245,9 +285,9 @@ dependencies = [
[[package]]
name = "cc"
-version = "1.2.66"
+version = "1.3.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "f5d6cac793997bd970000024b2934968efe83b382de4fdcf4fcb46b6ee4ad996"
+checksum = "c89588d05638b5b4594a3348a2d6c20277e43a7f5c5202b05cc56888475a47b8"
dependencies = [
"find-msvc-tools",
"shlex",
@@ -261,9 +301,9 @@ checksum = "9330f8b2ff13f34540b44e946ef35111825727b38d33286ef986142615121801"
[[package]]
name = "cfg_aliases"
-version = "0.2.1"
+version = "0.2.2"
source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "613afe47fcd5fac7ccf1db93babcb082c5994d996f20b8b159f2ad1658eb5724"
+checksum = "f079e83a288787bcd14a6aea84cee5c87a67c5a3e660c30f557a3d24761b3527"
[[package]]
name = "chrono"
@@ -375,6 +415,24 @@ version = "0.8.7"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "773648b94d0e5d620f64f280777445740e61fe701025087ec8b57f45c791888b"
+[[package]]
+name = "cpufeatures"
+version = "0.2.17"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "59ed5838eebb26a2bb2e58f6d5b5316989ae9d08bab10e0e6d103e656d1b0280"
+dependencies = [
+ "libc",
+]
+
+[[package]]
+name = "crc32fast"
+version = "1.5.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "9481c1c90cbf2ac953f07c8d4a58aa3945c425b7185c9154d67a65e4230da511"
+dependencies = [
+ "cfg-if",
+]
+
[[package]]
name = "crossbeam-deque"
version = "0.8.7"
@@ -425,6 +483,16 @@ dependencies = [
"winapi",
]
+[[package]]
+name = "crypto-common"
+version = "0.1.7"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "78c8292055d1c1df0cce5d180393dc8cce0abec0a7102adb6c7b1eef6016d60a"
+dependencies = [
+ "generic-array",
+ "typenum",
+]
+
[[package]]
name = "cssparser"
version = "0.31.2"
@@ -590,6 +658,37 @@ dependencies = [
"syn",
]
+[[package]]
+name = "digest"
+version = "0.10.7"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "9ed9a281f7bc9b7576e61468ba615a66a5c8cfdff42420a70aa82701a3b1e292"
+dependencies = [
+ "block-buffer",
+ "crypto-common",
+]
+
+[[package]]
+name = "dirs"
+version = "5.0.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "44c45a9d03d6676652bcb5e724c7e988de1acad23a711b5217ab9cbecbec2225"
+dependencies = [
+ "dirs-sys",
+]
+
+[[package]]
+name = "dirs-sys"
+version = "0.4.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "520f05a5cbd335fae5a99ff7a6ab8627577660ee5cfd6a94a6a929b52ff0321c"
+dependencies = [
+ "libc",
+ "option-ext",
+ "redox_users",
+ "windows-sys 0.48.0",
+]
+
[[package]]
name = "displaydoc"
version = "0.2.6"
@@ -701,6 +800,16 @@ version = "0.1.9"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "5baebc0774151f905a1a2cc41989300b1e6fbb29aff0ceffa1064fdd3088d582"
+[[package]]
+name = "flate2"
+version = "1.1.9"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "843fba2746e448b37e26a819579957415c8cef339bf08564fe8b7ddbd959573c"
+dependencies = [
+ "crc32fast",
+ "miniz_oxide",
+]
+
[[package]]
name = "fnv"
version = "1.0.7"
@@ -749,36 +858,36 @@ dependencies = [
[[package]]
name = "futures-channel"
-version = "0.3.32"
+version = "0.3.33"
source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "07bbe89c50d7a535e539b8c17bc0b49bdb77747034daa8087407d655f3f7cc1d"
+checksum = "262590f4fe6afeb0bc83be1daa64e52657fe185690a958af7f3ad0e92085c5ae"
dependencies = [
"futures-core",
]
[[package]]
name = "futures-core"
-version = "0.3.32"
+version = "0.3.33"
source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "7e3450815272ef58cec6d564423f6e755e25379b217b0bc688e295ba24df6b1d"
+checksum = "2cd50c473c80f6d7c3670a752354b8e569b1a7cbfdc0419ec88e5edad85e0dc7"
[[package]]
name = "futures-sink"
-version = "0.3.32"
+version = "0.3.33"
source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "c39754e157331b013978ec91992bde1ac089843443c49cbc7f46150b0fad0893"
+checksum = "e34418ac499d6305c2fb5ad0ed2f6ac998c5f8ca209b4510f7f94242c647e307"
[[package]]
name = "futures-task"
-version = "0.3.32"
+version = "0.3.33"
source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "037711b3d59c33004d3856fbdc83b99d4ff37a24768fa1be9ce3538a1cde4393"
+checksum = "b231ed28831efb4a61a08580c4bc233ec56bc009f4cd8f52da2c3cb97df0c109"
[[package]]
name = "futures-util"
-version = "0.3.32"
+version = "0.3.33"
source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "389ca41296e6190b48053de0321d02a77f32f8a5d2461dd38762c0593805c6d6"
+checksum = "a77a90a256fce34da66415271e30f94ee91c57b04b8a2c042d9cf3220179deaa"
dependencies = [
"futures-core",
"futures-task",
@@ -795,6 +904,16 @@ dependencies = [
"byteorder",
]
+[[package]]
+name = "generic-array"
+version = "0.14.7"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "85649ca51fd72272d7821adaf274ad91c288277713d9c18820d8499a7ff69e9a"
+dependencies = [
+ "typenum",
+ "version_check",
+]
+
[[package]]
name = "getopts"
version = "0.2.24"
@@ -898,6 +1017,12 @@ version = "0.5.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "2304e00983f87ffb38b55b444b5e3b60a884b5d30c0fca7d82fe33449bbe55ea"
+[[package]]
+name = "hex"
+version = "0.4.3"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "7f24254aa9a54b5c858eaee2f5bccdb46aaf0e486a595ed5fd8f86ba55232a70"
+
[[package]]
name = "hmac-sha256"
version = "1.1.14"
@@ -930,9 +1055,9 @@ dependencies = [
[[package]]
name = "http-body"
-version = "1.0.1"
+version = "1.1.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "1efedce1fb8e6913f23e0c92de8e62cd5b772a67e7b3946df930a62566c93184"
+checksum = "ca2a8f2913ee65f60facd6a5905613afaa448497a0230cc41ce022d93290bc2c"
dependencies = [
"bytes",
"http",
@@ -940,9 +1065,9 @@ dependencies = [
[[package]]
name = "http-body-util"
-version = "0.1.3"
+version = "0.1.4"
source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "b021d93e26becf5dc7e1b75b1bed1fd93124b374ceb73f43d4d4eafec896a64a"
+checksum = "e9f41fd6a08e4d4ec69df65976da761afd5ad5e58a9d4acb46bd1c953a9e3ff2"
dependencies = [
"bytes",
"futures-core",
@@ -1272,6 +1397,15 @@ version = "0.2.186"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "68ab91017fe16c622486840e4c83c9a37afeff978bd239b5293d61ece587de66"
+[[package]]
+name = "libredox"
+version = "0.1.18"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "c943259e342f1e06ff2da7a83eabdfe7f92ce10262688dbf1895ff0b3e6e4652"
+dependencies = [
+ "libc",
+]
+
[[package]]
name = "libsqlite3-sys"
version = "0.28.0"
@@ -1390,9 +1524,9 @@ checksum = "0e7465ac9959cc2b1404e8e2367b43684a6d13790fe23056cc8c6c5a6b7bcb94"
[[package]]
name = "matrixmultiply"
-version = "0.3.10"
+version = "0.3.11"
source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "a06de3016e9fae57a36fd14dba131fccf49f74b40b7fbdb472f96e361ec71a08"
+checksum = "3f607c237553f086e7043417a51df26b2eb899d3caff94e6a67592ff992fedc7"
dependencies = [
"autocfg",
"rawpointer",
@@ -1427,10 +1561,20 @@ source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "68354c5c6bd36d73ff3feceb05efa59b6acb7626617f4962be322a825e61f79a"
[[package]]
-name = "mio"
-version = "1.2.1"
+name = "miniz_oxide"
+version = "0.8.9"
source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "02bd0af71c67b473010cbbc60715ee815645a4dc942899111f494b4b737d6fda"
+checksum = "1fa76a2c86f704bdb222d66965fb3d63269ce38518b83cb0575fca855ebb6316"
+dependencies = [
+ "adler2",
+ "simd-adler32",
+]
+
+[[package]]
+name = "mio"
+version = "1.2.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "30d65c71f1ce40ab09135ce117d742b9f8a19ff91a41a8b57ed50bc2de59c427"
dependencies = [
"libc",
"log",
@@ -1633,6 +1777,12 @@ dependencies = [
"vcpkg",
]
+[[package]]
+name = "option-ext"
+version = "0.2.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "04744f49eae99ab78e0d5c0b603ab218f515ea8cfe5a456d7629ad883a3b6e7d"
+
[[package]]
name = "ort"
version = "2.0.0-rc.12"
@@ -1643,7 +1793,7 @@ dependencies = [
"ort-sys",
"smallvec",
"tracing",
- "ureq",
+ "ureq 3.3.0",
]
[[package]]
@@ -1654,7 +1804,7 @@ checksum = "d7b497d21a8b6fbb4b5a544f8fadb77e801a09ae0add9e411d31c6f89e3c1e90"
dependencies = [
"hmac-sha256",
"lzma-rust2",
- "ureq",
+ "ureq 3.3.0",
]
[[package]]
@@ -1805,9 +1955,9 @@ checksum = "19f132c84eca552bf34cab8ec81f1c1dcc229b811638f9d283dceabe58c5569e"
[[package]]
name = "portable-atomic"
-version = "1.13.1"
+version = "1.14.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "c33a9471896f1c69cecef8d20cbe2f7accd12527ce60845ff44c153bb2a21b49"
+checksum = "3d20d5497ef88037a52ff98267d066e7f11fcc5e99bbfbd58a42336193aacec3"
[[package]]
name = "portable-atomic-util"
@@ -2030,10 +2180,21 @@ dependencies = [
]
[[package]]
-name = "regex"
-version = "1.13.0"
+name = "redox_users"
+version = "0.4.6"
source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "2a0e75113e14dc5acb068cd0786884f214f1312650a3d36d269f5c4f3cdee8a2"
+checksum = "ba009ff324d1fc1b900bd1fdb31564febe58a8ccc8a6fdbb93b543d33b13ca43"
+dependencies = [
+ "getrandom 0.2.17",
+ "libredox",
+ "thiserror 1.0.69",
+]
+
+[[package]]
+name = "regex"
+version = "1.13.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "f020237b6c8eed93db2e2cb53c00c60a8e1bc73da7d073199a1180401450218d"
dependencies = [
"aho-corasick",
"memchr",
@@ -2043,9 +2204,9 @@ dependencies = [
[[package]]
name = "regex-automata"
-version = "0.4.15"
+version = "0.4.16"
source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "1f388202e4b80542a0921078cc23b6333bcf1409c1e3f86404cae4766a6131db"
+checksum = "8fcfdb36bda0c880c5931cdc7a2bcdc8ba4556847b9d912bca70bc94708711ad"
dependencies = [
"aho-corasick",
"memchr",
@@ -2158,11 +2319,13 @@ dependencies = [
[[package]]
name = "rustls"
-version = "0.23.41"
+version = "0.23.42"
source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "6b92b125634d9b795e7beca796cc790df15a7fb38323bf3196fda83292d06b1f"
+checksum = "3c54fcab019b409d04215d3a17cb438fd7fbf192ee61461f20f4fe18704bc138"
dependencies = [
+ "log",
"once_cell",
+ "ring",
"rustls-pki-types",
"rustls-webpki",
"subtle",
@@ -2358,6 +2521,17 @@ dependencies = [
"stable_deref_trait",
]
+[[package]]
+name = "sha2"
+version = "0.10.9"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "a7507d819769d01a365ab707794a4084392c824f54a7a6a7862f8c3d0892b283"
+dependencies = [
+ "cfg-if",
+ "cpufeatures",
+ "digest",
+]
+
[[package]]
name = "sharded-slab"
version = "0.1.7"
@@ -2404,6 +2578,12 @@ dependencies = [
"libc",
]
+[[package]]
+name = "simd-adler32"
+version = "0.3.10"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "3a219298ac11a56ea9a6d2120044824d6f01aeb034955e7af7bc16858527deea"
+
[[package]]
name = "siphasher"
version = "0.3.11"
@@ -2430,9 +2610,9 @@ checksum = "8ed6a63f02c8539c91a8685a86f4099661ba3da017932f6ebbea6de3f0fa7c90"
[[package]]
name = "socket2"
-version = "0.6.4"
+version = "0.6.5"
source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "52d1cfed4120b4d927bf7c0f86d2087a4a7d6027c906d9f9d525a80573b9be51"
+checksum = "c3d1e2c7f27f8d4cb10542a02c49005dbd6e93095799d6f3be745fae9f8fedd4"
dependencies = [
"libc",
"windows-sys 0.61.2",
@@ -2534,9 +2714,9 @@ checksum = "13c2bddecc57b384dee18652358fb23172facb8a2c51ccc10d74c157bdea3292"
[[package]]
name = "syn"
-version = "2.0.118"
+version = "2.0.119"
source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "1b9ae57f904213ebb649ce6895b8a66c66f0203b9319718f69a5612a065b1422"
+checksum = "872831b642d1a07999a962a351ed35b955ea2cfc8f3862091e2a240a84f17297"
dependencies = [
"proc-macro2",
"quote",
@@ -2608,13 +2788,33 @@ dependencies = [
"utf-8",
]
+[[package]]
+name = "thiserror"
+version = "1.0.69"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "b6aaf5339b578ea85b50e080feb250a3e8ae8cfcdff9a461c9ec2904bc923f52"
+dependencies = [
+ "thiserror-impl 1.0.69",
+]
+
[[package]]
name = "thiserror"
version = "2.0.18"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "4288b5bcbc7920c07a1149a35cf9590a2aa808e0bc1eafaade0b80947865fbc4"
dependencies = [
- "thiserror-impl",
+ "thiserror-impl 2.0.18",
+]
+
+[[package]]
+name = "thiserror-impl"
+version = "1.0.69"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "4fee6c4efc90059e10f81e6d42c60a18f76588c3d74cb83a0b242a2b6c7504c1"
+dependencies = [
+ "proc-macro2",
+ "quote",
+ "syn",
]
[[package]]
@@ -2705,7 +2905,7 @@ dependencies = [
"serde",
"serde_json",
"spm_precompiled",
- "thiserror",
+ "thiserror 2.0.18",
"unicode-normalization-alignments",
"unicode-segmentation",
"unicode_categories",
@@ -2713,9 +2913,9 @@ dependencies = [
[[package]]
name = "tokio"
-version = "1.52.3"
+version = "1.53.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "8fc7f01b389ac15039e4dc9531aa973a135d7a4135281b12d7c1bc79fd57fffe"
+checksum = "d988bcd52dbe076d3d46903332f58c912b87a2c49b1428419a5845154762ffee"
dependencies = [
"bytes",
"libc",
@@ -2730,9 +2930,9 @@ dependencies = [
[[package]]
name = "tokio-macros"
-version = "2.7.0"
+version = "2.7.1"
source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "385a6cb71ab9ab790c5fe8d67f1645e6c450a7ce006a33de03daa956cf70a496"
+checksum = "6328af13490e73a9b4694030fafd93f8c8c6a9dede33e821c3fc63eddf8042ba"
dependencies = [
"proc-macro2",
"quote",
@@ -2927,6 +3127,12 @@ version = "0.2.5"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "e421abadd41a4225275504ea4d6566923418b7f05506fbc9c0fe86ba7396114b"
+[[package]]
+name = "typenum"
+version = "1.20.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "b6f5e870be6c3b371b77fe0ee0bafb859fa4964b4404c27de1d380043c4dda20"
+
[[package]]
name = "unicase"
version = "2.9.0"
@@ -2995,6 +3201,24 @@ version = "0.9.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "8ecb6da28b8a351d773b68d5825ac39017e680750f980f3a1a85cd8dd28a47c1"
+[[package]]
+name = "ureq"
+version = "2.12.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "02d1a66277ed75f640d608235660df48c8e3c19f3b4edb6a263315626cc3c01d"
+dependencies = [
+ "base64 0.22.1",
+ "flate2",
+ "log",
+ "once_cell",
+ "rustls",
+ "rustls-pki-types",
+ "serde",
+ "serde_json",
+ "url",
+ "webpki-roots 0.26.11",
+]
+
[[package]]
name = "ureq"
version = "3.3.0"
@@ -3174,9 +3398,27 @@ dependencies = [
[[package]]
name = "webpki-root-certs"
-version = "1.0.8"
+version = "1.0.9"
source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "0d46a5a140e6f7afeccd8eae97eff335163939eac8b929834875168b29b3d267"
+checksum = "b96554aa2acc8ccdb7e1c9a58a7a68dd5d13bccc69cd124cb09406db612a1c9b"
+dependencies = [
+ "rustls-pki-types",
+]
+
+[[package]]
+name = "webpki-roots"
+version = "0.26.11"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "521bc38abb08001b01866da9f51eb7c5d647a19260e00054a8c7fd5f9e57f7a9"
+dependencies = [
+ "webpki-roots 1.0.9",
+]
+
+[[package]]
+name = "webpki-roots"
+version = "1.0.9"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "7dcd9d09a39985f5344844e66b0c530a33843579125f23e21e9f0f220850f22a"
dependencies = [
"rustls-pki-types",
]
@@ -3273,13 +3515,22 @@ dependencies = [
"windows-link",
]
+[[package]]
+name = "windows-sys"
+version = "0.48.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "677d2418bec65e3338edb076e806bc1ec15693c5d0104683f2efe857f61056a9"
+dependencies = [
+ "windows-targets 0.48.5",
+]
+
[[package]]
name = "windows-sys"
version = "0.52.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "282be5f36a8ce781fad8c8ae18fa3f9beff57ec1b52cb3de0789201425d9a33d"
dependencies = [
- "windows-targets",
+ "windows-targets 0.52.6",
]
[[package]]
@@ -3288,7 +3539,7 @@ version = "0.59.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "1e38bc4d79ed67fd075bcc251a1c39b32a1776bbe92e5bef1f0bf1f8c531853b"
dependencies = [
- "windows-targets",
+ "windows-targets 0.52.6",
]
[[package]]
@@ -3300,34 +3551,67 @@ dependencies = [
"windows-link",
]
+[[package]]
+name = "windows-targets"
+version = "0.48.5"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "9a2fa6e2155d7247be68c096456083145c183cbbbc2764150dda45a87197940c"
+dependencies = [
+ "windows_aarch64_gnullvm 0.48.5",
+ "windows_aarch64_msvc 0.48.5",
+ "windows_i686_gnu 0.48.5",
+ "windows_i686_msvc 0.48.5",
+ "windows_x86_64_gnu 0.48.5",
+ "windows_x86_64_gnullvm 0.48.5",
+ "windows_x86_64_msvc 0.48.5",
+]
+
[[package]]
name = "windows-targets"
version = "0.52.6"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "9b724f72796e036ab90c1021d4780d4d3d648aca59e491e6b98e725b84e99973"
dependencies = [
- "windows_aarch64_gnullvm",
- "windows_aarch64_msvc",
- "windows_i686_gnu",
+ "windows_aarch64_gnullvm 0.52.6",
+ "windows_aarch64_msvc 0.52.6",
+ "windows_i686_gnu 0.52.6",
"windows_i686_gnullvm",
- "windows_i686_msvc",
- "windows_x86_64_gnu",
- "windows_x86_64_gnullvm",
- "windows_x86_64_msvc",
+ "windows_i686_msvc 0.52.6",
+ "windows_x86_64_gnu 0.52.6",
+ "windows_x86_64_gnullvm 0.52.6",
+ "windows_x86_64_msvc 0.52.6",
]
+[[package]]
+name = "windows_aarch64_gnullvm"
+version = "0.48.5"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "2b38e32f0abccf9987a4e3079dfb67dcd799fb61361e53e2882c3cbaf0d905d8"
+
[[package]]
name = "windows_aarch64_gnullvm"
version = "0.52.6"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "32a4622180e7a0ec044bb555404c800bc9fd9ec262ec147edd5989ccd0c02cd3"
+[[package]]
+name = "windows_aarch64_msvc"
+version = "0.48.5"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "dc35310971f3b2dbbf3f0690a219f40e2d9afcf64f9ab7cc1be722937c26b4bc"
+
[[package]]
name = "windows_aarch64_msvc"
version = "0.52.6"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "09ec2a7bb152e2252b53fa7803150007879548bc709c039df7627cabbd05d469"
+[[package]]
+name = "windows_i686_gnu"
+version = "0.48.5"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "a75915e7def60c94dcef72200b9a8e58e5091744960da64ec734a6c6e9b3743e"
+
[[package]]
name = "windows_i686_gnu"
version = "0.52.6"
@@ -3340,24 +3624,48 @@ version = "0.52.6"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "0eee52d38c090b3caa76c563b86c3a4bd71ef1a819287c19d586d7334ae8ed66"
+[[package]]
+name = "windows_i686_msvc"
+version = "0.48.5"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "8f55c233f70c4b27f66c523580f78f1004e8b5a8b659e05a4eb49d4166cca406"
+
[[package]]
name = "windows_i686_msvc"
version = "0.52.6"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "240948bc05c5e7c6dabba28bf89d89ffce3e303022809e73deaefe4f6ec56c66"
+[[package]]
+name = "windows_x86_64_gnu"
+version = "0.48.5"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "53d40abd2583d23e4718fddf1ebec84dbff8381c07cae67ff7768bbf19c6718e"
+
[[package]]
name = "windows_x86_64_gnu"
version = "0.52.6"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "147a5c80aabfbf0c7d901cb5895d1de30ef2907eb21fbbab29ca94c5b08b1a78"
+[[package]]
+name = "windows_x86_64_gnullvm"
+version = "0.48.5"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "0b7b52767868a23d5bab768e390dc5f5c55825b6d30b86c844ff2dc7414044cc"
+
[[package]]
name = "windows_x86_64_gnullvm"
version = "0.52.6"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "24d5b23dc417412679681396f2b49f3de8c1473deb516bd34410872eff51ed0d"
+[[package]]
+name = "windows_x86_64_msvc"
+version = "0.48.5"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "ed94fce61571a4006852b7389a063ab983c02eb1bb37b47f8272ce92d06d9538"
+
[[package]]
name = "windows_x86_64_msvc"
version = "0.52.6"
@@ -3490,6 +3798,6 @@ dependencies = [
[[package]]
name = "zmij"
-version = "1.0.21"
+version = "1.0.23"
source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "b8848ee67ecc8aedbaf3e4122217aff892639231befc6a1b58d29fff4c2cabaa"
+checksum = "29666d0abbfad1e3dc4dcf6144730dd3a3ab225bbbdac83319345b1b44ccfc1b"
diff --git a/bakery.toml b/bakery.toml
deleted file mode 100644
index cad7a26..0000000
--- a/bakery.toml
+++ /dev/null
@@ -1,21 +0,0 @@
-name = "breadarr"
-description = "Lightweight Sonarr/Radarr/Prowlarr replacement"
-binaries = ["breadarrd", "breadarr-tui"]
-# breadarr runs natively (not in Docker), so unlike the old Sonarr/Radarr/
-# Prowlarr containers it needs these on the host PATH directly.
-system_deps = ["mkvtoolnix-cli", "ffmpeg"]
-optional_system_deps = []
-bread_deps = []
-
-[[service]]
-unit = "breadarrd.service"
-enable = true
-
-[config]
-dir = "~/.config/breadarr"
-example = "config.example.toml"
-
-[install]
-post_install = [
- "systemctl --user is-active --quiet breadarrd || systemctl --user start breadarrd",
-]
diff --git a/breadarr-shared/Cargo.toml b/breadarr-shared/Cargo.toml
index 0018ea6..91a9a26 100644
--- a/breadarr-shared/Cargo.toml
+++ b/breadarr-shared/Cargo.toml
@@ -9,3 +9,5 @@ anyhow.workspace = true
toml.workspace = true
reqwest.workspace = true
chrono.workspace = true
+# TODO(owner): switch to tag-pinned git dependency once bread-utils is merged and tagged, matching the bread-theme pattern
+bread-utils = { path = "../../bread-ecosystem/bread-utils" }
diff --git a/breadarr-shared/src/config.rs b/breadarr-shared/src/config.rs
index 64e47b6..1a9928b 100644
--- a/breadarr-shared/src/config.rs
+++ b/breadarr-shared/src/config.rs
@@ -314,10 +314,16 @@ fn config_path() -> PathBuf {
}
fn expand_home(input: &str) -> PathBuf {
+ // Was: falls through to `PathBuf::from(input)` — a literal, unexpanded
+ // "~/..." string — whenever the `HOME` env var itself isn't set.
+ // PathBuf/std::fs never expand `~`, so that fallback silently produced
+ // a path relative to the current working directory instead of the
+ // user's actual home. Same bug class as breadclip-core/breadpad-shared/
+ // breadmon (see bread_utils::xdg's doc comment); bread_utils::xdg::home_dir
+ // resolves a real home directory (falling back to `/root`, never a
+ // literal tilde) before this ever needs to fall back at all.
if let Some(stripped) = input.strip_prefix("~/") {
- if let Ok(home) = env::var("HOME") {
- return Path::new(&home).join(stripped);
- }
+ return bread_utils::xdg::home_dir().join(stripped);
}
PathBuf::from(input)
}
diff --git a/breadarrd/Cargo.toml b/breadarrd/Cargo.toml
index 77824c6..af3d900 100644
--- a/breadarrd/Cargo.toml
+++ b/breadarrd/Cargo.toml
@@ -19,6 +19,8 @@ regex.workspace = true
serde_json.workspace = true
ort.workspace = true
tokenizers.workspace = true
+# TODO(owner): switch to tag-pinned git dependency once bread-onnx is merged and tagged, matching the bread-theme pattern
+bread-onnx = { path = "../../bread-ecosystem/bread-onnx" }
scraper.workspace = true
chrono.workspace = true
fastrand.workspace = true
diff --git a/breadarrd/src/importer/mod.rs b/breadarrd/src/importer/mod.rs
index fd230a8..779c3ba 100644
--- a/breadarrd/src/importer/mod.rs
+++ b/breadarrd/src/importer/mod.rs
@@ -218,6 +218,15 @@ pub(crate) fn walk_files(dir: &Path) -> Result> {
Ok(out)
}
+/// TV episode files live under a `Season NN` subfolder of the show's
+/// `root_folder`, matching the layout Jellyfin/Sonarr/library-scan already
+/// use — episodes imported flat into the show root previously left new
+/// grabs sitting alongside, rather than inside, the season structure that
+/// pre-existing library files were organized into.
+pub(crate) fn season_dir(root_folder: &str, season_number: u32) -> PathBuf {
+ Path::new(root_folder).join(format!("Season {season_number:02}"))
+}
+
pub(crate) fn deterministic_filename(
series_title: &str,
season: u32,
@@ -1533,7 +1542,7 @@ fn import_one(conn: &Connection, grab: &PendingGrab, content_path: &Path) -> Res
// clean import below, same as an already-English-default file.
}
- let (root_folder, filename, episode_id) = match grab {
+ let (dest_dir, filename, episode_id) = match grab {
PendingGrab::Episode {
series_title,
season_number,
@@ -1550,7 +1559,8 @@ fn import_one(conn: &Connection, grab: &PendingGrab, content_path: &Path) -> Res
episode_title.as_deref(),
&ext,
);
- (root_folder.as_str(), filename, Some(*episode_id))
+ let dest_dir = season_dir(root_folder, *season_number);
+ (dest_dir, filename, Some(*episode_id))
}
PendingGrab::Movie {
title,
@@ -1559,7 +1569,7 @@ fn import_one(conn: &Connection, grab: &PendingGrab, content_path: &Path) -> Res
..
} => {
let filename = deterministic_movie_filename(title, *year, &ext);
- (root_folder.as_str(), filename, None)
+ (PathBuf::from(root_folder), filename, None)
}
// `process_pending_grabs` dispatches `SeasonPack` to
// `import_season_pack` and never reaches this function with one.
@@ -1568,8 +1578,15 @@ fn import_one(conn: &Connection, grab: &PendingGrab, content_path: &Path) -> Res
),
};
- std::fs::create_dir_all(root_folder)?;
- let dest = Path::new(root_folder).join(&filename);
+ std::fs::create_dir_all(&dest_dir)?;
+ let dest = dest_dir.join(&filename);
+
+ // Set below (to the renamed-aside stale file's path) only when this
+ // import is an upgrade over an existing, worse-scoring file — see the
+ // `dest.exists()` branch. Used to restore the original on any failure
+ // between here and the replacement being confirmed on disk, and to
+ // gate the deferred cleanup (old row + old file) once it succeeds.
+ let mut old_sibling: Option = None;
// The deterministic filename means a second release for the same
// episode/movie collides on this exact path. `link_or_copy_file`'s copy
@@ -1620,33 +1637,44 @@ fn import_one(conn: &Connection, grab: &PendingGrab, content_path: &Path) -> Res
}
return Ok(ImportOutcome::SkippedAlreadyHaveBetter);
}
- // The new file scores strictly better than what's currently there —
- // remove the stale file and its tracking row before placing the
- // replacement, rather than letting `link_or_copy_file`'s copy
- // fallback silently overwrite it in place. This matters for two
- // reasons: it keeps exactly one `episode_file` row per episode (an
- // old row left behind plus the fresh `INSERT` below would otherwise
- // leave a duplicate — the same bug class found live in the
- // Dr.STONE/Battlestar Galactica rows), and it lets the primary
- // hardlink path actually succeed (`std::fs::hard_link` fails
- // outright if the destination already exists), so an upgrade is a
- // cheap hardlink swap instead of an unnecessary full copy.
- conn.execute(
- "DELETE FROM episode_file WHERE path = ?1",
- params![dest.to_string_lossy()],
- )?;
- std::fs::remove_file(&dest).ok();
+ // The new file scores strictly better than what's currently there.
+ // Move the stale file sideways to a `.old` sibling — rather than
+ // deleting it and its tracking row outright — so the replacement is
+ // placed and confirmed *before* the original is actually given up.
+ // A `rename` (not a delete) still frees up `dest` for the primary
+ // hardlink path (`std::fs::hard_link` fails outright if the
+ // destination already exists), so an upgrade is still a cheap
+ // hardlink swap in the common case; it just also means that if the
+ // free-space check or `link_or_copy_file` below fails (I/O error,
+ // dest dir vanished, disk full), the original file gets moved back
+ // into place instead of being gone for good. The DB row is left
+ // alone until the replacement is confirmed on disk, for the same
+ // reason.
+ old_sibling = Some(PathBuf::from(format!("{}.old", dest.display())));
+ std::fs::rename(&dest, old_sibling.as_ref().unwrap())?;
}
let needed_bytes = std::fs::metadata(&working_path)?.len();
- if insufficient_space(Path::new(root_folder), needed_bytes)? {
+ if insufficient_space(&dest_dir, needed_bytes)? {
+ if let Some(old_sibling) = &old_sibling {
+ std::fs::rename(old_sibling, &dest).ok();
+ }
anyhow::bail!(
- "not enough free space at {root_folder} for {needed_bytes} bytes (source: {})",
+ "not enough free space at {} for {needed_bytes} bytes (source: {})",
+ dest_dir.display(),
working_path.display()
);
}
- link_or_copy_file(&working_path, &dest)?;
+ if let Err(err) = link_or_copy_file(&working_path, &dest) {
+ // Restore the original file rather than leaving the user with
+ // neither the old file nor the new one — this is the exact failure
+ // mode a `DELETE`-then-place ordering used to leave unrecoverable.
+ if let Some(old_sibling) = &old_sibling {
+ std::fs::rename(old_sibling, &dest).ok();
+ }
+ return Err(err);
+ }
if remuxed {
// `working_path` here is the scratch remux output, not qBittorrent's
// original content file (which was already removed above, in the
@@ -1655,6 +1683,16 @@ fn import_one(conn: &Connection, grab: &PendingGrab, content_path: &Path) -> Res
std::fs::remove_file(&working_path).ok();
}
+ // The replacement is confirmed in place on disk — only now is it safe
+ // to drop the old tracking row and the renamed-aside original.
+ if let Some(old_sibling) = old_sibling {
+ conn.execute(
+ "DELETE FROM episode_file WHERE path = ?1",
+ params![dest.to_string_lossy()],
+ )?;
+ std::fs::remove_file(&old_sibling).ok();
+ }
+
let size_bytes = std::fs::metadata(&dest)?.len();
conn.execute(
"INSERT INTO episode_file (episode_id, media_item_id, path, size_bytes, subtitle_status) VALUES (?1, ?2, ?3, ?4, 'none')",
@@ -1921,12 +1959,15 @@ fn import_season_pack_file(
episode_title.as_deref(),
&ext,
);
- let dest = Path::new(root_folder).join(&filename);
+ let dest_dir = season_dir(root_folder, season_number);
+ std::fs::create_dir_all(&dest_dir)?;
+ let dest = dest_dir.join(&filename);
// Same reasoning as import_one's own dest-collision check: a second
// release for the same episode (here, from a *different* pack or a
// single-episode grab) must not silently overwrite a better file
// already in place.
+ let mut old_sibling: Option = None;
if dest.exists() {
let existing_best: Option = conn.query_row(
"SELECT MAX(score) FROM release WHERE status = 'imported' AND id != ?1 AND episode_id = ?2",
@@ -1936,27 +1977,43 @@ fn import_season_pack_file(
if existing_best.is_some_and(|best| best >= release_score) {
return Ok(PackFileOutcome::SkippedAlreadyHaveBetter);
}
- // This episode's file is being upgraded — clear the stale row and
- // file first so the hardlink below is a real hardlink swap rather
- // than a copy-fallback overwrite, and so no duplicate episode_file
- // row survives. See import_one's matching comment for the fuller
- // reasoning.
- conn.execute(
- "DELETE FROM episode_file WHERE path = ?1",
- params![dest.to_string_lossy()],
- )?;
- std::fs::remove_file(&dest).ok();
+ // This episode's file is being upgraded. Move the stale file aside
+ // to a `.old` sibling rather than deleting it (and its row) outright
+ // — `dest` is still free for the hardlink fast path, but the
+ // original survives on disk until the replacement is confirmed in
+ // place, so a failed free-space check or `link_or_copy_file` below
+ // can't lose the file. See import_one's matching comment for the
+ // fuller reasoning; this is the same fix applied there.
+ old_sibling = Some(PathBuf::from(format!("{}.old", dest.display())));
+ std::fs::rename(&dest, old_sibling.as_ref().unwrap())?;
}
let needed_bytes = std::fs::metadata(source_path)?.len();
- if insufficient_space(Path::new(root_folder), needed_bytes)? {
+ if insufficient_space(&dest_dir, needed_bytes)? {
+ if let Some(old_sibling) = &old_sibling {
+ std::fs::rename(old_sibling, &dest).ok();
+ }
anyhow::bail!(
- "not enough free space at {root_folder} for {needed_bytes} bytes (source: {})",
+ "not enough free space at {} for {needed_bytes} bytes (source: {})",
+ dest_dir.display(),
source_path.display()
);
}
- link_or_copy_file(source_path, &dest)?;
+ if let Err(err) = link_or_copy_file(source_path, &dest) {
+ if let Some(old_sibling) = &old_sibling {
+ std::fs::rename(old_sibling, &dest).ok();
+ }
+ return Err(err);
+ }
+
+ if let Some(old_sibling) = old_sibling {
+ conn.execute(
+ "DELETE FROM episode_file WHERE path = ?1",
+ params![dest.to_string_lossy()],
+ )?;
+ std::fs::remove_file(&old_sibling).ok();
+ }
let size_bytes = std::fs::metadata(&dest)?.len();
conn.execute(
@@ -3107,6 +3164,78 @@ mod tests {
std::fs::remove_dir_all(&dir).unwrap();
}
+ #[test]
+ fn import_one_places_a_single_episode_grab_under_its_season_subfolder() {
+ // Regression: a real single-episode grab (Mushoku Tensei S03E02/E03,
+ // not part of a season pack) landed flat in the show's root_folder
+ // instead of alongside the rest of the season's already-organized
+ // files in `Season 03/`, once the pre-existing library-scanned
+ // structure had nothing left to mask it.
+ let conn = Connection::open_in_memory().unwrap();
+ crate::db::init(&conn).unwrap();
+ conn.execute(
+ "INSERT INTO media_item (id, kind, title, year, monitored, quality_profile_id, root_folder)
+ VALUES (1, 'series', 'Some Show', 2021, 1, 1, '/tmp')",
+ [],
+ )
+ .unwrap();
+ conn.execute(
+ "INSERT INTO source (id, name, kind, base_url) VALUES (1, 'tpb', 'scrape', 'http://x')",
+ [],
+ )
+ .unwrap();
+ conn.execute(
+ "INSERT INTO episode (id, media_item_id, season_number, episode_number, monitored, has_file)
+ VALUES (1, 1, 3, 2, 1, 0)",
+ [],
+ )
+ .unwrap();
+ conn.execute(
+ "INSERT INTO release (id, media_item_id, episode_id, raw_title, source_id, guid, status, torrent_hash, grabbed_at)
+ VALUES (1, 1, 1, 'Some Show S03E02 1080p', 1, 'guid-1', 'grabbed', 'deadbeef', datetime('now'))",
+ [],
+ )
+ .unwrap();
+
+ let dir = std::env::temp_dir().join(format!(
+ "breadarr-single-episode-season-dir-{}",
+ std::process::id()
+ ));
+ std::fs::create_dir_all(&dir).unwrap();
+ let dest_root = dir.join("library");
+ std::fs::create_dir_all(&dest_root).unwrap();
+ let content = dir.join("Some.Show.S03E02.1080p.mp4");
+ std::fs::write(&content, b"fake episode data").unwrap();
+
+ let grab = PendingGrab::Episode {
+ release_id: 1,
+ episode_id: 1,
+ media_item_id: 1,
+ torrent_hash: "deadbeef".to_string(),
+ series_title: "Some Show".to_string(),
+ season_number: 3,
+ episode_number: 2,
+ episode_title: None,
+ root_folder: dest_root.to_string_lossy().to_string(),
+ };
+
+ let outcome = import_one(&conn, &grab, &content).unwrap();
+ assert!(matches!(outcome, ImportOutcome::Imported { .. }));
+
+ let dest = dest_root.join("Season 03").join("Some Show - S03E02.mp4");
+ assert!(
+ dest.exists(),
+ "expected {} to exist under the season subfolder",
+ dest.display()
+ );
+ assert!(
+ !dest_root.join("Some Show - S03E02.mp4").exists(),
+ "must not also land flat in the show's root folder"
+ );
+
+ std::fs::remove_dir_all(&dir).unwrap();
+ }
+
#[test]
fn import_one_flags_quality_when_the_real_file_is_under_1080p() {
// Mirrors a real production case: a release whose title carries no
@@ -3561,9 +3690,18 @@ mod tests {
.unwrap();
assert_eq!(status, "imported");
- assert!(dest_root.join("Some Show - S01E01.mkv").exists());
- assert!(dest_root.join("Some Show - S01E02.mkv").exists());
- assert!(dest_root.join("Some Show - S01E03.mkv").exists());
+ assert!(dest_root
+ .join("Season 01")
+ .join("Some Show - S01E01.mkv")
+ .exists());
+ assert!(dest_root
+ .join("Season 01")
+ .join("Some Show - S01E02.mkv")
+ .exists());
+ assert!(dest_root
+ .join("Season 01")
+ .join("Some Show - S01E03.mkv")
+ .exists());
std::fs::remove_dir_all(&dir).unwrap();
}
@@ -3580,7 +3718,8 @@ mod tests {
std::fs::write(pack_dir.join("Show.S01E01.mkv"), b"new e01").unwrap();
std::fs::write(pack_dir.join("Show.S01E02.mkv"), b"new e02").unwrap();
let dest_root = dir.join("library");
- std::fs::create_dir_all(&dest_root).unwrap();
+ let season_dir = dest_root.join("Season 01");
+ std::fs::create_dir_all(&season_dir).unwrap();
// Episode 1 already has a higher-scoring imported release.
conn.execute(
@@ -3589,7 +3728,7 @@ mod tests {
[],
)
.unwrap();
- let existing = dest_root.join("Some Show - S01E01.mkv");
+ let existing = season_dir.join("Some Show - S01E01.mkv");
std::fs::write(&existing, b"already-better e01").unwrap();
conn.execute(
"INSERT INTO episode_file (episode_id, media_item_id, path, size_bytes, subtitle_status)
@@ -3616,7 +3755,7 @@ mod tests {
b"already-better e01",
"episode 1's better file must survive untouched"
);
- assert!(dest_root.join("Some Show - S01E02.mkv").exists());
+ assert!(season_dir.join("Some Show - S01E02.mkv").exists());
std::fs::remove_dir_all(&dir).unwrap();
}
diff --git a/breadarrd/src/matcher/embed.rs b/breadarrd/src/matcher/embed.rs
index 4f9bdf9..13902a9 100644
--- a/breadarrd/src/matcher/embed.rs
+++ b/breadarrd/src/matcher/embed.rs
@@ -1,10 +1,8 @@
use std::path::Path;
use anyhow::Result;
-use ort::session::builder::GraphOptimizationLevel;
-use ort::session::Session;
-use ort::value::Tensor;
-use tokenizers::Tokenizer;
+use bread_onnx::embedding::EmbeddingSession;
+use bread_onnx::Provider;
/// all-MiniLM-L6-v2's trained max sequence length. Release/show titles are
/// always far shorter than this, but truncate defensively rather than let a
@@ -12,9 +10,7 @@ use tokenizers::Tokenizer;
const MAX_SEQ_LEN: usize = 256;
pub struct OrtEmbedder {
- session: Session,
- tokenizer: Tokenizer,
- dim: usize,
+ inner: EmbeddingSession,
}
impl OrtEmbedder {
@@ -23,130 +19,24 @@ impl OrtEmbedder {
/// MiniLM-class model is cheap enough on CPU that a multi-backend GPU
/// setup isn't worth the added complexity for a model this small.
pub fn load(model_path: &Path, tokenizer_path: &Path, dim: usize) -> Result {
- let session = Session::builder()
- .map_err(|e| anyhow::anyhow!("failed to create ort session builder: {e}"))?
- .with_optimization_level(GraphOptimizationLevel::Level3)
- .map_err(|e| anyhow::anyhow!("failed to set optimization level: {e}"))?
- .commit_from_file(model_path)
- .map_err(|e| {
- anyhow::anyhow!("failed to load model from {}: {e}", model_path.display())
- })?;
-
- let tokenizer = Tokenizer::from_file(tokenizer_path)
- .map_err(|e| anyhow::anyhow!("failed to load tokenizer: {e}"))?;
-
- Ok(Self {
- session,
- tokenizer,
- dim,
- })
+ let inner = EmbeddingSession::load(model_path, tokenizer_path, dim, MAX_SEQ_LEN, &[Provider::Cpu])?;
+ Ok(Self { inner })
}
pub fn embed(&mut self, text: &str) -> Result> {
- let encoding = self
- .tokenizer
- .encode(text, true)
- .map_err(|e| anyhow::anyhow!("tokenization failed: {e}"))?;
-
- let mut ids: Vec = encoding.get_ids().iter().map(|&x| x as i64).collect();
- let mut mask: Vec = encoding
- .get_attention_mask()
- .iter()
- .map(|&x| x as i64)
- .collect();
- let mut type_ids: Vec = encoding.get_type_ids().iter().map(|&x| x as i64).collect();
-
- ids.truncate(MAX_SEQ_LEN);
- mask.truncate(MAX_SEQ_LEN);
- type_ids.truncate(MAX_SEQ_LEN);
-
- let seq_len = ids.len() as i64;
- let id_tensor = Tensor::::from_array((vec![1i64, seq_len], ids))
- .map_err(|e| anyhow::anyhow!("failed to build input_ids tensor: {e}"))?;
- let mask_tensor = Tensor::::from_array((vec![1i64, seq_len], mask.clone()))
- .map_err(|e| anyhow::anyhow!("failed to build attention_mask tensor: {e}"))?;
- let type_tensor = Tensor::::from_array((vec![1i64, seq_len], type_ids))
- .map_err(|e| anyhow::anyhow!("failed to build token_type_ids tensor: {e}"))?;
-
- let outputs = self
- .session
- .run(ort::inputs! {
- "input_ids" => id_tensor,
- "attention_mask" => mask_tensor,
- "token_type_ids" => type_tensor,
- })
- .map_err(|e| anyhow::anyhow!("ort inference failed: {e}"))?;
-
- let (shape, data) = outputs["last_hidden_state"]
- .try_extract_tensor::()
- .map_err(|e| anyhow::anyhow!("failed to extract last_hidden_state: {e}"))?;
-
- let actual_seq = shape[1] as usize;
- let actual_dim = shape[2] as usize;
-
- // Mean-pool over non-padded positions only.
- let mut result = vec![0.0f32; actual_dim];
- let mut count = 0usize;
- for t in 0..actual_seq.min(mask.len()) {
- if mask[t] > 0 {
- for d in 0..actual_dim {
- result[d] += data[t * actual_dim + d];
- }
- count += 1;
- }
- }
- if count > 0 {
- for x in &mut result {
- *x /= count as f32;
- }
- }
-
- l2_normalize(&mut result);
- result.truncate(self.dim);
- while result.len() < self.dim {
- result.push(0.0);
- }
-
- Ok(result)
+ self.inner.embed(text)
}
}
-fn l2_normalize(v: &mut [f32]) {
- let norm: f32 = v.iter().map(|x| x * x).sum::().sqrt();
- if norm > 1e-10 {
- for x in v.iter_mut() {
- *x /= norm;
- }
- }
-}
-
-pub fn cosine_similarity(a: &[f32], b: &[f32]) -> f32 {
- a.iter().zip(b).map(|(x, y)| x * y).sum()
-}
+pub use bread_onnx::embedding::cosine_similarity;
#[cfg(test)]
mod tests {
use super::*;
- #[test]
- fn l2_normalize_produces_unit_vector() {
- let mut v = vec![3.0, 4.0];
- l2_normalize(&mut v);
- let norm: f32 = v.iter().map(|x| x * x).sum::().sqrt();
- assert!((norm - 1.0).abs() < 1e-6);
- }
-
- #[test]
- fn l2_normalize_leaves_zero_vector_untouched() {
- let mut v = vec![0.0, 0.0, 0.0];
- l2_normalize(&mut v);
- assert_eq!(v, vec![0.0, 0.0, 0.0]);
- }
-
#[test]
fn cosine_similarity_of_identical_unit_vectors_is_one() {
- let mut v = vec![1.0, 2.0, 3.0];
- l2_normalize(&mut v);
+ let v = vec![0.6, 0.8]; // already unit length
let sim = cosine_similarity(&v, &v);
assert!((sim - 1.0).abs() < 1e-6);
}
diff --git a/breadarrd/src/matcher/mod.rs b/breadarrd/src/matcher/mod.rs
index ef19a56..fc82c08 100644
--- a/breadarrd/src/matcher/mod.rs
+++ b/breadarrd/src/matcher/mod.rs
@@ -16,6 +16,13 @@ const TOKENIZER_URL: &str =
/// Downloads the embedding model into `model_dir` if it isn't already
/// there — keeps setup to "run the daemon," no separate fetch step, in
/// keeping with the project's minimal-setup goal.
+///
+/// `bread_onnx::download::ensure_file` is sync/blocking (`ureq`, matching
+/// this workspace's `bakery` download convention) — this used to be a
+/// `reqwest`-based async implementation local to this crate, genuinely
+/// duplicating breadmill's own sync/`ureq` downloader. Since this fn is
+/// called from an async context, each call is dispatched via
+/// `spawn_blocking` rather than blocking the async runtime directly.
pub async fn ensure_model(model_dir: &Path) -> Result<(PathBuf, PathBuf)> {
std::fs::create_dir_all(model_dir)
.with_context(|| format!("failed to create {}", model_dir.display()))?;
@@ -25,28 +32,19 @@ pub async fn ensure_model(model_dir: &Path) -> Result<(PathBuf, PathBuf)> {
if !model_path.exists() {
tracing::info!("downloading title-matching model (~90MB, one-time)");
- download(MODEL_URL, &model_path).await?;
+ download(MODEL_URL, model_path.clone()).await?;
}
if !tokenizer_path.exists() {
- download(TOKENIZER_URL, &tokenizer_path).await?;
+ download(TOKENIZER_URL, tokenizer_path.clone()).await?;
}
Ok((model_path, tokenizer_path))
}
-async fn download(url: &str, dest: &Path) -> Result<()> {
- let bytes = reqwest::get(url)
+async fn download(url: &'static str, dest: PathBuf) -> Result<()> {
+ tokio::task::spawn_blocking(move || bread_onnx::download::ensure_file(url, &dest, None))
.await
- .with_context(|| format!("failed to download {url}"))?
- .error_for_status()
- .with_context(|| format!("{url} returned an error status"))?
- .bytes()
- .await
- .with_context(|| format!("failed to read response body from {url}"))?;
- let tmp = dest.with_extension("part");
- std::fs::write(&tmp, &bytes).with_context(|| format!("failed to write {}", tmp.display()))?;
- std::fs::rename(&tmp, dest)
- .with_context(|| format!("failed to finalize {}", dest.display()))?;
+ .context("download task panicked")??;
Ok(())
}
@@ -190,15 +188,28 @@ impl TitleMatcher {
}
}
+/// Grammatical filler words that show up across countless unrelated titles
+/// and carry no discriminating signal on their own — English articles and
+/// the short romaji particles ubiquitous in Japanese titles ("X no Y", "X ga
+/// Y", ...). Without this, two completely unrelated shows sharing nothing
+/// but e.g. "no" register as real overlap and slip past `MIN_TOKEN_OVERLAP`
+/// (verified live: "Yomi no Tsugai" / "Kami no Shizuku" / "Saijo no Osewa"
+/// all cleared the guard against "Kimetsu no Yaiba" on "no" alone).
+const STOPWORDS: &[&str] = &[
+ "a", "an", "the", "of", "to", "and", "no", "wa", "wo", "ga", "ni", "de", "ha", "he", "da",
+];
+
/// Word-level overlap between `a` and `b`, as a fraction of the *shorter*
/// title's word count — so a short alias fully contained in a longer title
/// (or vice versa) still scores 1.0, rather than being penalized by length
-/// mismatch. Case-insensitive, splits on non-alphanumeric runs.
+/// mismatch. Case-insensitive, splits on non-alphanumeric runs, and ignores
+/// `STOPWORDS` so shared filler words don't count as real overlap.
fn token_overlap_ratio(a: &str, b: &str) -> f32 {
let tokenize = |s: &str| -> std::collections::HashSet {
s.split(|c: char| !c.is_alphanumeric())
.filter(|t| !t.is_empty())
.map(|t| t.to_lowercase())
+ .filter(|t| !STOPWORDS.contains(&t.as_str()))
.collect()
};
let ta = tokenize(a);
@@ -275,4 +286,24 @@ mod tests {
fn empty_input_has_zero_overlap() {
assert_eq!(token_overlap_ratio("", "Mushoku Tensei"), 0.0);
}
+
+ #[test]
+ fn shared_particle_alone_is_not_real_overlap() {
+ // The bug found live in the review queue: unrelated titles sharing
+ // only the Japanese particle "no" scored a nonzero ratio and slipped
+ // past MIN_TOKEN_OVERLAP, flooding review with false matches against
+ // "Demon Slayer" (Kimetsu no Yaiba).
+ assert_eq!(
+ token_overlap_ratio("Yomi no Tsugai", "Kimetsu no Yaiba"),
+ 0.0
+ );
+ assert_eq!(
+ token_overlap_ratio("Kami no Shizuku", "Kimetsu no Yaiba"),
+ 0.0
+ );
+ assert_eq!(
+ token_overlap_ratio("Saijo no Osewa", "Kimetsu no Yaiba"),
+ 0.0
+ );
+ }
}