xberg 1.0.0.pre.rc.5 → 1.0.0.pre.rc.9

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: fed75d3a0eb4b36e4678f04a53e9235dc49d431ce66ed615e2087b221c328305
-  data.tar.gz: a8cfc8cb1d431100f941a0caa5ec89e2404df60011ba4d1db99b032ae9b2778c
+  metadata.gz: c426c771373b092f070bb61bb9479785b38fce29336a8ccca7a99203715351f6
+  data.tar.gz: 5b206ba76956c60c6ff3eb3d567a8792fecf71be02203354dc9a5d99edb4359b
 SHA512:
-  metadata.gz: 6bc43cfaf3bf98784c2b4e727677a2aa0051f75cf6542773db5003d1ac0fb538e098cddb9bb8c82171ea337a9b977cb79d0ee612032d92c8965e07a132ba311d
-  data.tar.gz: e5a03eb280da8eabac05bfa66490580d4e35be0b9690223f26e9fc9f0c5fbea0c7459be5ca312bc72bc95fb66da0b520b19b1f72af8cce6c552033bf8bc501b1
+  metadata.gz: 1934ce27152766156b6446d41ee34e257469374ee6436f01c5a9b08e43fc35e505a07b32069d2b6a75071f7eda215d030e52e39bfcf9d0ee66cd857b773e303f
+  data.tar.gz: b0067920fc491c15012fa0117193d027081ac365d8b8b31c04eb92de7fd3d9ed34c88f019d47fc365620bbc8ff79e427cd54ee48ec6a6da93394ecdeab9f74f5

data/ext/xberg_rb/native/Cargo.lock

@@ -1230,9 +1230,9 @@ dependencies = [
 
 [[package]]
 name = "crawlberg"
-version = "1.0.2"
+version = "1.0.3"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "e361dcd0b6433eaa4cc3e269f2e983e7f8ddea09b597bc5257d9a356e3d8882c"
+checksum = "46b3f6dfec53e26f1f989b4685943153a54e1d2101f8bd3ae5afd810b7957423"
 dependencies = [
  "ahash 0.8.12",
  "aho-corasick",
@@ -1486,9 +1486,9 @@ checksum = "ac6b926516df9c60bfa16e107b21086399f8285a44ca9711344b9e553c5146e2"
 
 [[package]]
 name = "defmt"
-version = "1.1.0"
+version = "1.1.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "a6e524506490a1953d237cb87b1cfc1e46f88c18f10a22dfe0f507dc6bfc7f7f"
+checksum = "e2953bfe4f93bbd20cc71198842756f77d161884c99ebbabc41d80231ded88d1"
 dependencies = [
  "bitflags 1.3.2",
  "defmt-macros",
@@ -1496,12 +1496,11 @@ dependencies = [
 
 [[package]]
 name = "defmt-macros"
-version = "1.1.0"
+version = "1.1.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "f0a27770e9c8f719a79d8b638281f4d828f77d8fd61e0bd94451b9b85e576a0b"
+checksum = "bad9c72e7ca2137e0dc3813245a0d282fd6daad32fd800af018306a9169b5fe8"
 dependencies = [
  "defmt-parser",
- "proc-macro-error2",
  "proc-macro2",
  "quote",
  "syn 2.0.118",
@@ -2534,9 +2533,9 @@ dependencies = [
 
 [[package]]
 name = "html-to-markdown-rs"
-version = "3.8.1"
+version = "3.8.2"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "5b8defe72747832a90e54cd6b0daad64f89a970b9b3c977f40ba968d3f7f50c6"
+checksum = "bfb98086035f41cf7bcdb6bd1dab14b118e53b035e003e268698a6003c413fa0"
 dependencies = [
  "ahash 0.8.12",
  "astral-tl",
@@ -3141,12 +3140,10 @@ checksum = "ccfe6121cbe750cf81efa362d85c0bde7ea298ec43092d3a193baca59cdbd634"
 dependencies = [
  "defmt",
  "jiff-static",
- "jiff-tzdb-platform",
  "log",
  "portable-atomic",
  "portable-atomic-util",
  "serde_core",
- "windows-link",
 ]
 
 [[package]]
@@ -3160,21 +3157,6 @@ dependencies = [
  "syn 2.0.118",
 ]
 
-[[package]]
-name = "jiff-tzdb"
-version = "0.1.6"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "c900ef84826f1338a557697dc8fc601df9ca9af4ac137c7fb61d4c6f2dfd3076"
-
-[[package]]
-name = "jiff-tzdb-platform"
-version = "0.1.3"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "875a5a69ac2bab1a891711cf5eccbec1ce0341ea805560dcd90b7a2e925132e8"
-dependencies = [
- "jiff-tzdb",
-]
-
 [[package]]
 name = "jni"
 version = "0.21.1"
@@ -3191,6 +3173,36 @@ 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",
+ "combine",
+ "jni-macros",
+ "jni-sys 0.4.1",
+ "log",
+ "simd_cesu8",
+ "thiserror 2.0.18",
+ "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 2.0.118",
+]
+
 [[package]]
 name = "jni-sys"
 version = "0.3.1"
@@ -3410,9 +3422,9 @@ checksum = "92daf443525c4cce67b150400bc2316076100ce0b3686209eb8cf3c31612e6f0"
 
 [[package]]
 name = "liter-llm"
-version = "1.9.2"
+version = "1.9.3"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "42b3c1f3725f552f5e954a3a991aa9be1373b621a7b2f090bb93272e67a7ab60"
+checksum = "b2262222bbb692fb6c788b90bc24c1f8358d75f845374e4a0df6c70630541017"
 dependencies = [
  "ahash 0.8.12",
  "async-trait",
@@ -3505,24 +3517,20 @@ dependencies = [
  "aes 0.9.1",
  "bitflags 2.13.0",
  "cbc 0.2.1",
- "chrono",
  "ecb",
  "encoding_rs",
  "flate2",
  "getrandom 0.4.3",
  "indexmap",
  "itoa",
- "jiff",
  "log",
  "md-5",
  "nom 8.0.0",
  "rand 0.10.2",
  "rangemap",
- "rayon",
  "sha2 0.11.0",
  "stringprep",
  "thiserror 2.0.18",
- "time",
  "ttf-parser",
  "weezl 0.2.1",
 ]
@@ -4018,9 +4026,9 @@ dependencies = [
 
 [[package]]
 name = "num-bigint"
-version = "0.4.7"
+version = "0.4.8"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "c863e9ab5e7bf9c99ba75e1050f1e4d624ae87ed3532d6238ffbdc7b585dbbe6"
+checksum = "c89e69e7e0f03bea5ef08013795c25018e101932225a656383bd384495ecc367"
 dependencies = [
  "num-integer",
  "num-traits",
@@ -4117,16 +4125,16 @@ checksum = "830b246a0e5f20af87141b25c173cd1b609bd7779a4617d6ec582abaf90870f3"
 
 [[package]]
 name = "office_oxide"
-version = "0.1.2"
+version = "0.1.3"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "866a8fa5e1a756f8cc9f9f614031ad7e33adc7f6972eab74a35b0c799fe08da5"
+checksum = "8900703278aea7d2329f5c490b62653306b1083efc7993ee18e3e86dcfd5afeb"
 dependencies = [
  "atoi_simd 0.18.1",
  "encoding_rs",
  "fast-float2",
  "libc",
  "log",
- "quick-xml 0.40.1",
+ "quick-xml 0.41.0",
  "serde",
  "serde_json",
  "thiserror 2.0.18",
@@ -4342,9 +4350,9 @@ dependencies = [
 
 [[package]]
 name = "pdf_oxide"
-version = "0.3.70"
+version = "0.3.72"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "3be9e4752f2319dec7c079ca96ec141e1be70faac82b21cb06a53bb6c2e0034e"
+checksum = "3b7fe525ccb850888a423bd211c1efd1af704761a7084e83edae1b99d0c7d2b4"
 dependencies = [
  "aes 0.9.1",
  "base64 0.22.1",
@@ -4667,28 +4675,6 @@ dependencies = [
  "toml_edit",
 ]
 
-[[package]]
-name = "proc-macro-error-attr2"
-version = "2.0.0"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "96de42df36bb9bba5542fe9f1a054b8cc87e172759a1868aa05c1f3acc89dfc5"
-dependencies = [
- "proc-macro2",
- "quote",
-]
-
-[[package]]
-name = "proc-macro-error2"
-version = "2.0.1"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "11ec05c52be0a07b08061f7dd003e7d7092e0472bc731b4af7bb1ef876109802"
-dependencies = [
- "proc-macro-error-attr2",
- "proc-macro2",
- "quote",
- "syn 2.0.118",
-]
-
 [[package]]
 name = "proc-macro2"
 version = "1.0.106"
@@ -4845,16 +4831,6 @@ dependencies = [
  "memchr",
 ]
 
-[[package]]
-name = "quick-xml"
-version = "0.40.1"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "2474bd2e5029e7ccb6abb2ba48cf2383a333851dedf495901544281590c7da7f"
-dependencies = [
- "memchr",
- "serde",
-]
-
 [[package]]
 name = "quick-xml"
 version = "0.41.0"
@@ -5311,7 +5287,7 @@ dependencies = [
  "quinn",
  "rustls",
  "rustls-pki-types",
- "rustls-platform-verifier",
+ "rustls-platform-verifier 0.7.0",
  "serde",
  "serde_json",
  "serde_urlencoded",
@@ -5510,9 +5486,18 @@ dependencies = [
 
 [[package]]
 name = "rustc-hash"
-version = "2.1.2"
+version = "2.1.3"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "94300abf3f1ae2e2b8ffb7b58043de3d399c73fa6f4b73826402a5c457614dbe"
+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"
@@ -5587,7 +5572,28 @@ checksum = "1d99feebc72bae7ab76ba994bb5e121b8d83d910ca40b36e0921f53becc41784"
 dependencies = [
  "core-foundation 0.10.1",
  "core-foundation-sys",
- "jni",
+ "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",
  "log",
  "once_cell",
  "rustls",
@@ -5746,6 +5752,12 @@ 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"
@@ -5974,6 +5986,16 @@ version = "0.3.9"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "703d5c7ef118737c72f1af64ad2f6f8c5e1921f818cdcb97b8fe6fc69bf66214"
 
+[[package]]
+name = "simd_cesu8"
+version = "1.1.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "94f90157bb87cddf702797c5dadfa0be7d266cdf49e22da2fcaa32eff75b2c33"
+dependencies = [
+ "rustc_version",
+ "simdutf8",
+]
+
 [[package]]
 name = "simd_helpers"
 version = "0.1.0"
@@ -7023,9 +7045,9 @@ dependencies = [
 
 [[package]]
 name = "tree-sitter"
-version = "0.26.9"
+version = "0.26.10"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "4dab76d0b724ba557954125188cf0633a1ca43199ced82d95c7b9c32cc3de1f3"
+checksum = "3c343ed63e3f5c64d1acdecb5d2c13d4e169cb5fde0052106ebaa6c6f27f9e55"
 dependencies = [
  "cc",
  "regex",
@@ -7043,15 +7065,15 @@ checksum = "009994f150cc0cd50ff54917d5bc8bffe8cad10ca10d81c34da2ec421ae61782"
 
 [[package]]
 name = "tree-sitter-language-pack"
-version = "1.12.2"
+version = "1.12.4"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "3379f087c3935b801e5eb926ab2e77529c2397e0ccaa81a79c1d444fbb9bd00c"
+checksum = "d49e30d1927ccc08599c054380bda399817781f74eb9184007e90606c7ff3a2c"
 dependencies = [
  "ahash 0.8.12",
  "cc",
  "dirs",
  "fd-lock",
- "getrandom 0.2.17",
+ "getrandom 0.4.3",
  "libloading 0.9.0",
  "memchr",
  "serde",
@@ -7105,15 +7127,15 @@ checksum = "2896d95c02a80c6d6a5d6e953d479f5ddf2dfdb6a244441010e373ac0fb88971"
 
 [[package]]
 name = "unhwp"
-version = "0.5.1"
+version = "0.5.2"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "4b0109dc52c6db66836c28af0d86f051b0a846f8c7a0a483fd9debd90f431279"
+checksum = "9db2add52da5275c7e850c5b2da1d8e580b223cd18a97807afcbd1026ffe3525"
 dependencies = [
  "cfb 0.10.0",
  "flate2",
  "pulldown-cmark 0.12.2",
  "pulldown-cmark-to-cmark",
- "quick-xml 0.37.5",
+ "quick-xml 0.41.0",
  "rayon",
  "regex",
  "serde",
@@ -7269,7 +7291,7 @@ dependencies = [
  "percent-encoding",
  "rustls",
  "rustls-pki-types",
- "rustls-platform-verifier",
+ "rustls-platform-verifier 0.6.2",
  "serde",
  "serde_json",
  "socks",
@@ -8041,9 +8063,9 @@ dependencies = [
 
 [[package]]
 name = "xberg"
-version = "1.0.0-rc.5"
+version = "1.0.0-rc.9"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "58e6e5aad16fbd5fcc7b6502fae40cdb5e704578352d19f717ed147beae4d656"
+checksum = "627033553a27835485fee775b7b10cf8ed4e162f12d0df4e077ffb45846944f3"
 dependencies = [
  "ahash 0.8.12",
  "async-trait",
@@ -8159,9 +8181,9 @@ dependencies = [
 
 [[package]]
 name = "xberg-gliner"
-version = "1.0.0-rc.5"
+version = "1.0.0-rc.9"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "14960d4f14be04ad7599e9b4bc9971d886daab9af3b1c8c18cb5e47c5c1f087e"
+checksum = "86e43aeca6ee9066bb9a457c8f5649705b8e04d0e04645103ad60fdbdd8596b6"
 dependencies = [
  "ndarray 0.17.2",
  "ort",
@@ -8173,9 +8195,9 @@ dependencies = [
 
 [[package]]
 name = "xberg-libheif"
-version = "1.0.0-rc.5"
+version = "1.0.0-rc.9"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "63979f3aaceb7223c7487da9adb4218f0fd8b24945f7addc39c703367005b82b"
+checksum = "47142402f9ab8e1f1041acb5d8fbd3dae397fd9a6b4c65f22be9c4434c81731b"
 dependencies = [
  "cfg-if",
  "enumn",
@@ -8186,9 +8208,9 @@ dependencies = [
 
 [[package]]
 name = "xberg-paddle-ocr"
-version = "1.0.0-rc.5"
+version = "1.0.0-rc.9"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "a7312f7dd14925ba307cfbae49a401f00cb10adc61ee0143eebf1823a7d6dde2"
+checksum = "d0d77debe5b69db07cb3a184bf240c3e33414bf37540f27c0586fcfc0dc47b7d"
 dependencies = [
  "geo-clipper",
  "geo-types",
@@ -8203,7 +8225,7 @@ dependencies = [
 
 [[package]]
 name = "xberg-rb"
-version = "1.0.0-rc.5"
+version = "1.0.0-rc.9"
 dependencies = [
  "async-trait",
  "crawlberg",
@@ -8217,9 +8239,9 @@ dependencies = [
 
 [[package]]
 name = "xberg-tesseract"
-version = "1.0.0-rc.5"
+version = "1.0.0-rc.9"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "baa8f3da708f99800852607a72dd0e7a606a8dc55959c4eac05e1c62836aa31b"
+checksum = "7ec0056f3798302ed20cf62cea73a1eac49c987758d7bd52585a55f8e2b8648a"
 dependencies = [
  "cc",
  "cmake",

data/ext/xberg_rb/native/Cargo.toml

@@ -1,6 +1,6 @@
 [package]
 name = "xberg-rb"
-version = "1.0.0-rc.5"
+version = "1.0.0-rc.9"
 edition = "2024"
 license = "MIT"
 description = "High-performance document intelligence library"
@@ -17,13 +17,12 @@ path = "../src/lib.rs"
 crate-type = ["cdylib"]
 
 [features]
-default = ["api", "api-types", "auto-rotate-types", "chunking-tokenizers", "diff", "heic", "heuristics", "html", "keywords-rake", "keywords-yake", "layout-types", "liter-llm", "markdown-footnotes", "ocr", "ocr-wasm", "office", "paddle-ocr-types", "pdf", "presets", "quality", "redaction", "reranker", "reranker-presets", "svg", "transcription-types", "tree-sitter", "url-config-types", "url-ingestion", "xml"]
+default = ["api", "api-types", "auto-rotate-types", "chunking-tokenizers", "diff", "heuristics", "html", "keywords-rake", "keywords-yake", "layout-types", "liter-llm", "markdown-footnotes", "ocr", "ocr-wasm", "office", "paddle-ocr-types", "pdf", "presets", "quality", "redaction", "reranker", "reranker-presets", "svg", "transcription-types", "tree-sitter", "url-config-types", "url-ingestion", "xml"]
 api = ["xberg/api"]
 api-types = ["xberg/api-types"]
 auto-rotate-types = ["xberg/auto-rotate-types"]
 chunking-tokenizers = ["xberg/chunking-tokenizers"]
 diff = ["xberg/diff"]
-heic = ["xberg/heic"]
 heuristics = ["xberg/heuristics"]
 html = ["xberg/html"]
 keywords-rake = ["xberg/keywords-rake"]
@@ -50,17 +49,17 @@ xml = ["xberg/xml"]
 
 [dependencies]
 async-trait = "0.1"
-crawlberg = { default-features = false, version = "1.0.2" }
+crawlberg = { default-features = false, version = "1.0.3" }
 magnus = "0.8"
 rb-sys = ">=0.9, <0.9.128"
 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.5", features = ["full", "pdf", "ocr", "paddle-ocr", "paddle-ocr-types", "layout-detection", "layout-types", "embeddings", "embedding-presets", "reranker", "reranker-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.9", features = ["full", "pdf", "ocr", "paddle-ocr", "paddle-ocr-types", "layout-detection", "layout-types", "embeddings", "embedding-presets", "reranker", "reranker-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.5", features = ["windows-target"] }
+xberg = { version = "1.0.0-rc.9", features = ["windows-target"] }
 
 [target.'cfg(all(target_os = "macos", target_arch = "x86_64"))'.dependencies]
-xberg = { version = "1.0.0-rc.5", features = ["macos-intel-target"] }
+xberg = { version = "1.0.0-rc.9", features = ["macos-intel-target"] }