xberg 1.0.0.pre.rc.33 → 1.0.0.pre.rc.34

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: e9c58dd2f7faf056ebc864d535ff983a8a4826c7999a6506ad82af5408c23961
-  data.tar.gz: effa2a8663dffe2f7136bb327464f88c06ffd58a5ad5f62a9493e883f46f52d8
+  metadata.gz: cf47d3f2efc7d844f00708ab91c1336658080ff5d0034aa1fb6772b9cd37ef86
+  data.tar.gz: fd283ae6a94a760ee46f4c1fd6ad2c74434cb59b60e6c494acb676050f73ea2d
 SHA512:
-  metadata.gz: eea8d788ea172a5dce2f192520bb55ae28af356bdee7f40c13f82b779bc92596a5499a0889708e0a1b6723522537e4cb1f906b0cbc44404d73e8e6a071c70f00
-  data.tar.gz: 2c1c5dbdb015e2abc5a487895ca995076b8650b0cce43f1184a6c5a61c68baaefe5abc31d0cc6861f19c40bc6eb1bea87bf04dbb0e7e8b912cd51c4e811d3e5f
+  metadata.gz: d8a1fb04ca8b61b4c8a31b13d3ea13cb912b6c0d162792a931741a503de39d4e57afc8ea49452f0cff01c3cbb008d0e2ed177a0fc20e2bfc380219ba329789d4
+  data.tar.gz: 6b89b365a18babb6998b3aa05582e6d668d3f859d4fb5a7ee988bf476bf275df6d867d935c5f9ac2ac1dfcf09e2249d4376341263fd7d83c37c238cafadc4f72

data/ext/xberg_rb/native/Cargo.lock

@@ -461,6 +461,12 @@ version = "0.22.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "72b3254f16251a8381aa12e40e3c4d2f0199f8c6508fbecb9d91f575e0fbb8c6"
 
+[[package]]
+name = "base64"
+version = "0.23.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "b25655df2c3cdd83c5e5b293b88acd880332b2ddadd7c30ac43144fdc0033da9"
+
 [[package]]
 name = "base64ct"
 version = "1.8.3"
@@ -2009,6 +2015,12 @@ version = "0.2.7"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "caf1079563223d5d59d83c85886a56e586cfd5c1a26292e971a0fa266531ac5a"
 
+[[package]]
+name = "fax"
+version = "0.3.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "70ed8646f3993cad0585c6669ffba6f7e5440a0bfb0a1f16600cae33ce7cf307"
+
 [[package]]
 name = "fd-lock"
 version = "4.0.4"
@@ -2112,6 +2124,15 @@ dependencies = [
  "bytemuck",
 ]
 
+[[package]]
+name = "font-types"
+version = "0.12.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "ad67eced03f5504d9cbd3a879b5958b5c54d4e5fd794361c6eb21b05fb703411"
+dependencies = [
+ "bytemuck",
+]
+
 [[package]]
 name = "fontconfig-parser"
 version = "0.5.8"
@@ -2579,6 +2600,18 @@ dependencies = [
  "zerocopy",
 ]
 
+[[package]]
+name = "harfrust"
+version = "0.12.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "c03d949a14aa089bbb282f7dd76a498a7f684428e4257202efc119ec010376f9"
+dependencies = [
+ "bitflags 2.13.1",
+ "bytemuck",
+ "read-fonts 0.41.0",
+ "smallvec",
+]
+
 [[package]]
 name = "hashbrown"
 version = "0.12.3"
@@ -3423,36 +3456,6 @@ dependencies = [
  "windows-sys 0.45.0",
 ]
 
-[[package]]
-name = "jni"
-version = "0.22.4"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "5efd9a482cf3a427f00d6b35f14332adc7902ce91efb778580e180ff90fa3498"
-dependencies = [
- "cfg-if 1.0.4",
- "combine",
- "jni-macros",
- "jni-sys 0.4.1",
- "log",
- "simd_cesu8",
- "thiserror 2.0.19",
- "walkdir",
- "windows-link",
-]
-
-[[package]]
-name = "jni-macros"
-version = "0.22.4"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "a00109accc170f0bdb141fed3e393c565b6f5e072365c3bd58f5b062591560a3"
-dependencies = [
- "proc-macro2",
- "quote",
- "rustc_version",
- "simd_cesu8",
- "syn 2.0.119",
-]
-
 [[package]]
 name = "jni-sys"
 version = "0.3.1"
@@ -3732,9 +3735,9 @@ checksum = "92daf443525c4cce67b150400bc2316076100ce0b3686209eb8cf3c31612e6f0"
 
 [[package]]
 name = "liter-llm"
-version = "1.10.1"
+version = "1.11.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "c69b78084d1eed21747ab8352bbdedb0462724ff46e03986241aa71d326a81fa"
+checksum = "016fbd9e5fc66d4cb10eb5faa45242e54add93101816926fe9348bcfb0cb051a"
 dependencies = [
  "ahash 0.8.12",
  "arc-swap",
@@ -4800,9 +4803,9 @@ dependencies = [
 
 [[package]]
 name = "pdf_oxide"
-version = "0.3.74"
+version = "0.3.75"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "1b97a8330bf3a3a4011ad84704b3bdcb9b0ef3fd5b03a1bdc371dde40bee1689"
+checksum = "2e00ca5f52780bb764da7fc1783c0c6f549fcf960d69734c8d7cf7996bdbb49d"
 dependencies = [
  "aes 0.9.1",
  "base64 0.22.1",
@@ -4815,10 +4818,11 @@ dependencies = [
  "encoding_rs",
  "env_logger",
  "fast_image_resize",
- "fax",
+ "fax 0.3.0",
  "flate2",
  "fontdb",
  "getrandom 0.4.3",
+ "harfrust",
  "hayro-jbig2",
  "hayro-jpeg2000 0.4.0",
  "image 0.25.10",
@@ -4832,7 +4836,6 @@ dependencies = [
  "phf 0.14.0",
  "quick-xml 0.41.0",
  "regex",
- "rustybuzz",
  "serde",
  "serde_json",
  "sha2 0.11.0",
@@ -5664,7 +5667,18 @@ source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "c4ed38b89c2c77ff968c524145ad65fb010f38af5c7a224b53b81d47ac2daa81"
 dependencies = [
  "bytemuck",
- "font-types",
+ "font-types 0.11.3",
+]
+
+[[package]]
+name = "read-fonts"
+version = "0.41.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "046a7d674daf459825b32f5062056d6882db0d2f5a479fbd76ccfc870ac18709"
+dependencies = [
+ "bytemuck",
+ "font-types 0.12.1",
+ "once_cell",
 ]
 
 [[package]]
@@ -5815,7 +5829,7 @@ dependencies = [
  "quinn",
  "rustls",
  "rustls-pki-types",
- "rustls-platform-verifier 0.7.0",
+ "rustls-platform-verifier",
  "serde",
  "serde_json",
  "serde_urlencoded",
@@ -6032,15 +6046,6 @@ version = "2.1.3"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "6b1e7f9a428571be2dc5bc0505c13fb6bf936822b894ec87abf8a08a4e51742d"
 
-[[package]]
-name = "rustc_version"
-version = "0.4.1"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "cfcb3a22ef46e85b45de6ee7e79d063319ebb6594faafcf1c225ea92ab6e9b92"
-dependencies = [
- "semver",
-]
-
 [[package]]
 name = "rustfft"
 version = "6.4.1"
@@ -6098,9 +6103,9 @@ dependencies = [
 
 [[package]]
 name = "rustls-pki-types"
-version = "1.15.0"
+version = "1.15.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "764899a24af3980067ee14bc143654f297b22eaebfe3c7b6b211920a5a59b046"
+checksum = "2f4925028c7eb5d1fcdaf196971378ed9d2c1c4efc7dc5d011256f76c99c0a96"
 dependencies = [
  "web-time",
  "zeroize",
@@ -6114,28 +6119,7 @@ checksum = "1d99feebc72bae7ab76ba994bb5e121b8d83d910ca40b36e0921f53becc41784"
 dependencies = [
  "core-foundation 0.10.1",
  "core-foundation-sys",
- "jni 0.21.1",
- "log",
- "once_cell",
- "rustls",
- "rustls-native-certs",
- "rustls-platform-verifier-android",
- "rustls-webpki",
- "security-framework",
- "security-framework-sys",
- "webpki-root-certs",
- "windows-sys 0.61.2",
-]
-
-[[package]]
-name = "rustls-platform-verifier"
-version = "0.7.0"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "26d1e2536ce4f35f4846aa13bff16bd0ff40157cdb14cc056c7b14ba41233ba0"
-dependencies = [
- "core-foundation 0.10.1",
- "core-foundation-sys",
- "jni 0.22.4",
+ "jni",
  "log",
  "once_cell",
  "rustls",
@@ -6172,24 +6156,6 @@ version = "1.0.23"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "cf54715a573b99ac80df0bc206da022bcd442c974952c7b9720069370852e21f"
 
-[[package]]
-name = "rustybuzz"
-version = "0.20.1"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "fd3c7c96f8a08ee34eff8857b11b49b07d71d1c3f4e88f8a88d4c9e9f90b1702"
-dependencies = [
- "bitflags 2.13.1",
- "bytemuck",
- "core_maths",
- "log",
- "smallvec",
- "ttf-parser",
- "unicode-bidi-mirroring",
- "unicode-ccc",
- "unicode-properties",
- "unicode-script",
-]
-
 [[package]]
 name = "ryu"
 version = "1.0.23"
@@ -6334,12 +6300,6 @@ dependencies = [
  "libc",
 ]
 
-[[package]]
-name = "semver"
-version = "1.0.28"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "8a7852d02fc848982e0c167ef163aaff9cd91dc640ba85e263cb1ce46fae51cd"
-
 [[package]]
 name = "seq-macro"
 version = "0.3.6"
@@ -6590,16 +6550,6 @@ version = "0.3.10"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "3a219298ac11a56ea9a6d2120044824d6f01aeb034955e7af7bc16858527deea"
 
-[[package]]
-name = "simd_cesu8"
-version = "1.2.0"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "11031e251abf8611c80f460e19dbdeb54a66db918e49c65a7065b46ac7aec520"
-dependencies = [
- "rustc_version",
- "simdutf8",
-]
-
 [[package]]
 name = "simd_helpers"
 version = "0.1.0"
@@ -6646,7 +6596,7 @@ source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "0c34617370ae968efb7161bb2beb517d9084659aae19e24b89e3db25b46e4564"
 dependencies = [
  "bytemuck",
- "read-fonts",
+ "read-fonts 0.39.2",
 ]
 
 [[package]]
@@ -7263,7 +7213,7 @@ version = "0.11.3"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "b63feaf3343d35b6ca4d50483f94843803b0f51634937cc2ec519fc32232bc52"
 dependencies = [
- "fax",
+ "fax 0.2.7",
  "flate2",
  "half",
  "quick-error",
@@ -7915,18 +7865,6 @@ version = "0.3.18"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "5c1cb5db39152898a79168971543b1cb5020dff7fe43c8dc468b0885f5e29df5"
 
-[[package]]
-name = "unicode-bidi-mirroring"
-version = "0.4.0"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "5dfa6e8c60bb66d49db113e0125ee8711b7647b5579dc7f5f19c42357ed039fe"
-
-[[package]]
-name = "unicode-ccc"
-version = "0.4.0"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "ce61d488bcdc9bc8b5d1772c404828b17fc481c0a582b5581e95fb233aef503e"
-
 [[package]]
 name = "unicode-general-category"
 version = "1.1.0"
@@ -7969,12 +7907,6 @@ version = "0.1.4"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "7df058c713841ad818f1dc5d3fd88063241cc61f49f5fbea4b951e8cf5a8d71d"
 
-[[package]]
-name = "unicode-script"
-version = "0.5.8"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "383ad40bb927465ec0ce7720e033cb4ca06912855fc35db31b5755d0de75b1ee"
-
 [[package]]
 name = "unicode-segmentation"
 version = "1.13.3"
@@ -8034,7 +7966,7 @@ dependencies = [
  "percent-encoding",
  "rustls",
  "rustls-pki-types",
- "rustls-platform-verifier 0.6.2",
+ "rustls-platform-verifier",
  "serde",
  "serde_json",
  "socks",
@@ -8833,11 +8765,11 @@ version = "0.48.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "cb731d4c4d93eacc69a1ad2f270f905788a98e4a3438267bcafbe08d3431c8d8"
 dependencies = [
- "font-types",
+ "font-types 0.11.3",
  "indexmap",
  "kurbo",
  "log",
- "read-fonts",
+ "read-fonts 0.39.2",
 ]
 
 [[package]]
@@ -8867,16 +8799,16 @@ dependencies = [
 
 [[package]]
 name = "xberg"
-version = "1.0.0-rc.33"
+version = "1.0.0-rc.35"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "0bf1060d70870a43018bf4c9a44d8582fa8d5f3be3ecea967f03e86d93ebb2ca"
+checksum = "0581ec37e59e63cb6319bbfa19cd301c4035b2a221c1c3cb6e793e0951a63736"
 dependencies = [
  "aes-gcm",
  "ahash 0.8.12",
  "async-trait",
  "auto_enums",
  "axum",
- "base64 0.22.1",
+ "base64 0.23.0",
  "biblatex",
  "biblib",
  "bitvec",
@@ -8895,6 +8827,7 @@ dependencies = [
  "fast_image_resize",
  "flate2",
  "fs2",
+ "futures",
  "getrandom 0.2.17",
  "getrandom 0.3.4",
  "getrandom 0.4.3",
@@ -8991,9 +8924,9 @@ dependencies = [
 
 [[package]]
 name = "xberg-gliner"
-version = "1.0.0-rc.33"
+version = "1.0.0-rc.35"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "65f21f1c7a0f96f502d1ec5aa35405c3c1a1ec168fb77f7401ab14450264f395"
+checksum = "33c64291b8a897f09c6f30e1d9f789a389275c6af75e050fcec06c44d4d869c4"
 dependencies = [
  "getrandom 0.2.17",
  "getrandom 0.3.4",
@@ -9007,9 +8940,9 @@ dependencies = [
 
 [[package]]
 name = "xberg-libheif"
-version = "1.0.0-rc.33"
+version = "1.0.0-rc.35"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "2147eac7d54ba62b5f6dd9cd170fdafb32b29924532bafb1e161cd8e5b9c51fa"
+checksum = "c5571fe5c6b798deca7a884b126fe284a3d8a74f80250b6771d9ff050b32cd58"
 dependencies = [
  "cfg-if 1.0.4",
  "enumn",
@@ -9020,9 +8953,9 @@ dependencies = [
 
 [[package]]
 name = "xberg-paddle-ocr"
-version = "1.0.0-rc.33"
+version = "1.0.0-rc.35"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "0d574aa7d5752564411a8ee1d78fc98efdfa69ae2e385b3fdab919cb29247c8e"
+checksum = "2c46b77432007b4830e359fadb5db7d6cdab9ce401fe73364f672d9fa6e33309"
 dependencies = [
  "geo-clipper",
  "geo-types",
@@ -9037,7 +8970,7 @@ dependencies = [
 
 [[package]]
 name = "xberg-rb"
-version = "1.0.0-rc.33"
+version = "1.0.0-rc.34"
 dependencies = [
  "async-trait",
  "crawlberg",
@@ -9052,9 +8985,9 @@ dependencies = [
 
 [[package]]
 name = "xberg-tesseract"
-version = "1.0.0-rc.33"
+version = "1.0.0-rc.35"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "955a17a1528e0b1f3260f5ec3cc0bacc31645e4db59300d1db6f79782329253d"
+checksum = "2a132a94a86ccfd18ae24a29089fe511d1609a2ea7d1a496cafe9f61b5cdeee1"
 dependencies = [
  "cc",
  "cmake",

data/ext/xberg_rb/native/Cargo.toml

@@ -1,6 +1,6 @@
 [package]
 name = "xberg-rb"
-version = "1.0.0-rc.33"
+version = "1.0.0-rc.34"
 edition = "2024"
 license = "MIT"
 description = "High-performance document intelligence library"
@@ -64,10 +64,10 @@ serde = { version = "1", features = ["derive"] }
 serde_json = "1"
 tokio = { version = "1", features = ["rt-multi-thread"] }
 [target.'cfg(not(any(target_os = "windows", all(target_os = "macos", target_arch = "x86_64"))))'.dependencies]
-xberg = { version = "1.0.0-rc.33", features = ["full", "pdf", "ocr", "paddle-ocr", "paddle-ocr-types", "layout-detection", "layout-types", "embeddings", "embedding-presets", "reranker", "reranker-presets", "sparse-embeddings", "sparse-embedding-presets", "late-interaction", "late-interaction-presets", "chunking", "keywords-yake", "keywords-rake", "language-detection", "html", "tree-sitter", "office", "email", "archives", "stopwords", "auto-rotate", "auto-rotate-types", "tokio-runtime", "api", "api-types", "mcp", "liter-llm", "quality", "svg", "transcription", "transcription-types", "classification", "captioning", "ner-onnx", "ner-llm", "diff", "markdown-footnotes", "redaction", "enrichment", "heuristics", "presets", "structured", "url-ingestion"] }
+xberg = { version = "1.0.0-rc.34", features = ["full", "pdf", "ocr", "paddle-ocr", "paddle-ocr-types", "layout-detection", "layout-types", "embeddings", "embedding-presets", "reranker", "reranker-presets", "sparse-embeddings", "sparse-embedding-presets", "late-interaction", "late-interaction-presets", "chunking", "keywords-yake", "keywords-rake", "language-detection", "html", "tree-sitter", "office", "email", "archives", "stopwords", "auto-rotate", "auto-rotate-types", "tokio-runtime", "api", "api-types", "mcp", "liter-llm", "quality", "svg", "transcription", "transcription-types", "classification", "captioning", "ner-onnx", "ner-llm", "diff", "markdown-footnotes", "redaction", "enrichment", "heuristics", "presets", "structured", "url-ingestion"] }
 
 [target.'cfg(target_os = "windows")'.dependencies]
-xberg = { version = "1.0.0-rc.33", features = ["windows-target"] }
+xberg = { version = "1.0.0-rc.34", features = ["windows-target"] }
 
 [target.'cfg(all(target_os = "macos", target_arch = "x86_64"))'.dependencies]
-xberg = { version = "1.0.0-rc.33", features = ["macos-intel-target"] }
+xberg = { version = "1.0.0-rc.34", features = ["macos-intel-target"] }

data/ext/xberg_rb/src/lib.rs

@@ -1,5 +1,5 @@
 // This file is auto-generated by alef. DO NOT EDIT.
-// alef:hash:5d08f1be5b4c1fa04c24ca290ca4b06275054d9e7515f174e0df09fda497db73
+// alef:hash:4e21c71a5751b345136e5ca51dea30bbd3862f7fdc63aa50e6b36be84c454e0e
 // Re-generate with: alef generate
 #![allow(dead_code, unused_imports, unused_variables)]
 #![allow(
@@ -3239,6 +3239,8 @@ pub struct OcrQualityThresholds {
     alnum_ws_ratio_threshold: f64,
     pipeline_min_quality: f64,
     min_undecodable_ratio: f64,
+    enable_provenance_ocr_routing: bool,
+    min_provenance_fallback_ratio: f64,
 }
 
 unsafe impl IntoValueFromNative for OcrQualityThresholds {}
@@ -3350,6 +3352,14 @@ impl OcrQualityThresholds {
                 .get(ruby.to_symbol("min_undecodable_ratio"))
                 .and_then(|v| f64::try_convert(v).ok())
                 .unwrap_or_default(),
+            enable_provenance_ocr_routing: kwargs
+                .get(ruby.to_symbol("enable_provenance_ocr_routing"))
+                .and_then(|v| bool::try_convert(v).ok())
+                .unwrap_or_default(),
+            min_provenance_fallback_ratio: kwargs
+                .get(ruby.to_symbol("min_provenance_fallback_ratio"))
+                .and_then(|v| f64::try_convert(v).ok())
+                .unwrap_or_default(),
         })
     }
 
@@ -3420,6 +3430,14 @@ impl OcrQualityThresholds {
     fn min_undecodable_ratio(&self) -> f64 {
         self.min_undecodable_ratio
     }
+
+    fn enable_provenance_ocr_routing(&self) -> bool {
+        self.enable_provenance_ocr_routing
+    }
+
+    fn min_provenance_fallback_ratio(&self) -> f64 {
+        self.min_provenance_fallback_ratio
+    }
 }
 
 #[derive(Clone, Debug, serde::Serialize, serde::Deserialize)]
@@ -31587,6 +31605,8 @@ impl From<OcrQualityThresholds> for xberg::OcrQualityThresholds {
             alnum_ws_ratio_threshold: val.alnum_ws_ratio_threshold,
             pipeline_min_quality: val.pipeline_min_quality,
             min_undecodable_ratio: val.min_undecodable_ratio,
+            enable_provenance_ocr_routing: val.enable_provenance_ocr_routing,
+            min_provenance_fallback_ratio: val.min_provenance_fallback_ratio,
             ..Default::default()
         }
     }
@@ -31613,6 +31633,8 @@ impl From<xberg::OcrQualityThresholds> for OcrQualityThresholds {
             alnum_ws_ratio_threshold: val.alnum_ws_ratio_threshold,
             pipeline_min_quality: val.pipeline_min_quality,
             min_undecodable_ratio: val.min_undecodable_ratio,
+            enable_provenance_ocr_routing: val.enable_provenance_ocr_routing,
+            min_provenance_fallback_ratio: val.min_provenance_fallback_ratio,
         }
     }
 }
@@ -39315,6 +39337,16 @@ fn ruby_init(ruby: &Ruby) -> Result<(), Error> {
         method!(OcrQualityThresholds::min_undecodable_ratio, 0),
     )?;
 
+    class.define_method(
+        "enable_provenance_ocr_routing",
+        method!(OcrQualityThresholds::enable_provenance_ocr_routing, 0),
+    )?;
+
+    class.define_method(
+        "min_provenance_fallback_ratio",
+        method!(OcrQualityThresholds::min_provenance_fallback_ratio, 0),
+    )?;
+
     let class = module.define_class("OcrPipelineStage", ruby.class_object())?;
 
     class.define_singleton_method("new", function!(OcrPipelineStage::new, -1))?;

data/lib/xberg/native.rb

@@ -1,5 +1,5 @@
 # This file is auto-generated by alef — DO NOT EDIT.
-# alef:hash:5d08f1be5b4c1fa04c24ca290ca4b06275054d9e7515f174e0df09fda497db73
+# alef:hash:4e21c71a5751b345136e5ca51dea30bbd3862f7fdc63aa50e6b36be84c454e0e
 # To regenerate: alef generate
 # To verify freshness: alef verify --exit-code
 # frozen_string_literal: true

data/lib/xberg/version.rb

@@ -1,10 +1,10 @@
 # This file is auto-generated by alef — DO NOT EDIT.
-# alef:hash:5d08f1be5b4c1fa04c24ca290ca4b06275054d9e7515f174e0df09fda497db73
+# alef:hash:4e21c71a5751b345136e5ca51dea30bbd3862f7fdc63aa50e6b36be84c454e0e
 # To regenerate: alef generate
 # To verify freshness: alef verify --exit-code
 # frozen_string_literal: true
 
 module Xberg
   ## The version string for this package.
-  VERSION = "1.0.0.pre.rc.33"
+  VERSION = "1.0.0.pre.rc.34"
 end

data/lib/xberg.rb

@@ -1,5 +1,5 @@
 # This file is auto-generated by alef — DO NOT EDIT.
-# alef:hash:5d08f1be5b4c1fa04c24ca290ca4b06275054d9e7515f174e0df09fda497db73
+# alef:hash:4e21c71a5751b345136e5ca51dea30bbd3862f7fdc63aa50e6b36be84c454e0e
 # To regenerate: alef generate
 # To verify freshness: alef verify --exit-code
 # frozen_string_literal: true

data/sig/types.rbs

@@ -1,5 +1,5 @@
 # This file is auto-generated by alef — DO NOT EDIT.
-# alef:hash:5d08f1be5b4c1fa04c24ca290ca4b06275054d9e7515f174e0df09fda497db73
+# alef:hash:4e21c71a5751b345136e5ca51dea30bbd3862f7fdc63aa50e6b36be84c454e0e
 # To regenerate: alef generate
 # To verify freshness: alef verify --exit-code
 
@@ -366,8 +366,10 @@ def initialize: (?backend: NerBackendKind, ?categories: Array[EntityCategory], ?
         attr_accessor alnum_ws_ratio_threshold: Float?
         attr_accessor pipeline_min_quality: Float?
         attr_accessor min_undecodable_ratio: Float?
+        attr_accessor enable_provenance_ocr_routing: bool?
+        attr_accessor min_provenance_fallback_ratio: Float?
 
-    def initialize: (?min_total_non_whitespace: Integer, ?min_non_whitespace_per_page: Float, ?min_meaningful_word_len: Integer, ?min_meaningful_words: Integer, ?min_alnum_ratio: Float, ?min_garbage_chars: Integer, ?max_fragmented_word_ratio: Float, ?critical_fragmented_word_ratio: Float, ?min_avg_word_length: Float, ?min_words_for_avg_length_check: Integer, ?min_consecutive_repeat_ratio: Float, ?min_words_for_repeat_check: Integer, ?substantive_min_chars: Integer, ?non_text_min_chars: Integer, ?alnum_ws_ratio_threshold: Float, ?pipeline_min_quality: Float, ?min_undecodable_ratio: Float) -> void
+    def initialize: (?min_total_non_whitespace: Integer, ?min_non_whitespace_per_page: Float, ?min_meaningful_word_len: Integer, ?min_meaningful_words: Integer, ?min_alnum_ratio: Float, ?min_garbage_chars: Integer, ?max_fragmented_word_ratio: Float, ?critical_fragmented_word_ratio: Float, ?min_avg_word_length: Float, ?min_words_for_avg_length_check: Integer, ?min_consecutive_repeat_ratio: Float, ?min_words_for_repeat_check: Integer, ?substantive_min_chars: Integer, ?non_text_min_chars: Integer, ?alnum_ws_ratio_threshold: Float, ?pipeline_min_quality: Float, ?min_undecodable_ratio: Float, ?enable_provenance_ocr_routing: bool, ?min_provenance_fallback_ratio: Float) -> void
     def self.default: () -> OcrQualityThresholds
     end
 

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: xberg
 version: !ruby/object:Gem::Version
-  version: 1.0.0.pre.rc.33
+  version: 1.0.0.pre.rc.34
 platform: ruby
 authors:
 - Na'aman Hirschfeld <naaman@xberg.io>
 autorequire:
 bindir: bin
 cert_chain: []
-date: 2026-07-23 00:00:00.000000000 Z
+date: 2026-07-24 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: rb_sys