RubyGems - kreuzberg - Versions diffs - 4.3.3 → 4.3.4 - Mend

kreuzberg 4.3.3 → 4.3.4

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.

Files changed (686) hide show

checksums.yaml CHANGED Viewed

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 801d80170e744ae0641ce1fd08c3f09d2bed1a88e41a1ffc533a7d8d8eafe391
-  data.tar.gz: 58437edacbe5d45d45b95695fd75992559ab2f3120d4b69ddfd7153e0adfdd18
+  metadata.gz: f3c080ecb465d2860ccaef34aff627bf155689e912b0ff48ae72d99a16f045cf
+  data.tar.gz: 8cd3f4aae7a19c229bfb2451811233f59e04c39a9aa9d6d9d69f9e12d747ec04
 SHA512:
-  metadata.gz: 6e7a486189ce2ce1878ef898a9d7784a95666a673177e66e1921ed67f33d82cfb735356890e9dff449c404a45480f94c34794c6c97988a57f59e28d799d43a8b
-  data.tar.gz: 7951e6aaa0c882dd65c702bff65cce5980401a2a31423707b38a9f63d4c8983d919fcfe50b8843ac1e908e9e754d6c2f7e2e52d7b64a66a762fbeeceedb41def
+  metadata.gz: c1948824a088e4d6296bd8f161bd59624a252763b47ef21b2b0763d8be0a472de814f95273e03fd82b6c1f8c66aea2fde8fd70c3315ad296be1eaaf09cf3e64c
+  data.tar.gz: 46340a09386141c8ddc19c4c23f9a3b9e4b74cfa8070d3aeec6ae0e339aec114cf3d83a5d08ef1d9734f293186829b075f1cb79f619fd59133148f9571fa9a4a

data/Gemfile.lock CHANGED Viewed

@@ -1,7 +1,7 @@
 PATH
   remote: .
   specs:
-    kreuzberg (4.3.3)
+    kreuzberg (4.3.4)
       rb_sys (~> 0.9.119)
 GEM
@@ -123,7 +123,7 @@ GEM
       rubocop (~> 1.81)
     ruby-progressbar (1.13.0)
     securerandom (0.4.1)
-    sorbet-runtime (0.6.12940)
+    sorbet-runtime (0.6.12942)
     steep (1.10.0)
       activesupport (>= 5.1)
       concurrent-ruby (>= 1.1.10)
@@ -163,6 +163,7 @@ PLATFORMS
   x86-linux-gnu
   x86-linux-musl
   x86_64-darwin
+  x86_64-linux
   x86_64-linux-gnu
   x86_64-linux-musl
@@ -209,7 +210,7 @@ CHECKSUMS
   i18n (1.14.8) sha256=285778639134865c5e0f6269e0b818256017e8cde89993fdfcbfb64d088824a5
   io-console (0.8.2) sha256=d6e3ae7a7cc7574f4b8893b4fca2162e57a825b223a177b7afa236c5ef9814cc
   json (2.18.1) sha256=fe112755501b8d0466b5ada6cf50c8c3f41e897fa128ac5d263ec09eedc9f986
-  kreuzberg (4.3.3)
+  kreuzberg (4.3.4)
   language_server-protocol (3.17.0.5) sha256=fd1e39a51a28bf3eec959379985a72e296e9f9acfce46f6a79d31ca8760803cc
   lint_roller (1.1.0) sha256=2c0c845b632a7d172cb849cc90c1bce937a28c5c8ccccb50dfd46a485003cc87
   listen (3.10.0) sha256=c6e182db62143aeccc2e1960033bebe7445309c7272061979bb098d03760c9d2
@@ -244,7 +245,7 @@ CHECKSUMS
   rubocop-rspec (3.9.0) sha256=8fa70a3619408237d789aeecfb9beef40576acc855173e60939d63332fdb55e2
   ruby-progressbar (1.13.0) sha256=80fc9c47a9b640d6834e0dc7b3c94c9df37f08cb072b7761e4a71e22cff29b33
   securerandom (0.4.1) sha256=cc5193d414a4341b6e225f0cb4446aceca8e50d5e1888743fac16987638ea0b1
-  sorbet-runtime (0.6.12940) sha256=e935193a35cc5fc92d0bbe60db50fbdfbb787052a3cf01b2daa7af4cecb318cd
+  sorbet-runtime (0.6.12942) sha256=967bda04814d234e4239c4f883c1d0ee6de3e47bf8bafd2c0cc30d18df2ddd3a
   steep (1.10.0) sha256=1b295b55f9aaff1b8d3ee42453ee55bc2a1078fda0268f288edb2dc014f4d7d1
   strscan (3.1.7) sha256=5f76462b94a3ea50b44973225b7d75b2cb96d4e1bee9ef1319b99ca117b72c8c
   terminal-table (4.0.0) sha256=f504793203f8251b2ea7c7068333053f0beeea26093ec9962e62ea79f94301d2
@@ -256,4 +257,4 @@ CHECKSUMS
   yard (0.9.38) sha256=721fb82afb10532aa49860655f6cc2eaa7130889df291b052e1e6b268283010f
 BUNDLED WITH
-  4.0.3
+  4.0.5

data/README.md CHANGED Viewed

@@ -22,7 +22,7 @@
     <img src="https://img.shields.io/maven-central/v/dev.kreuzberg/kreuzberg?label=Java&color=007ec6" alt="Java">
   </a>
   <a href="https://github.com/kreuzberg-dev/kreuzberg/releases">
-    <img src="https://img.shields.io/github/v/tag/kreuzberg-dev/kreuzberg?label=Go&color=007ec6&filter=v4.3.3" alt="Go">
+    <img src="https://img.shields.io/github/v/tag/kreuzberg-dev/kreuzberg?label=Go&color=007ec6&filter=v4.3.4" alt="Go">
   </a>
   <a href="https://www.nuget.org/packages/Kreuzberg/">
     <img src="https://img.shields.io/nuget/v/Kreuzberg?label=C%23&color=007ec6" alt="C#">

data/ext/kreuzberg_rb/native/Cargo.lock CHANGED Viewed

@@ -26,6 +26,7 @@ source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "5a15f179cd60c4584b8a8c596927aadc462e27f2ca70c04e0071964a73ba7a75"
 dependencies = [
  "cfg-if",
+ "const-random",
  "getrandom 0.3.4",
  "once_cell",
  "serde",
@@ -693,7 +694,7 @@ dependencies = [
  "log",
  "quick-xml 0.38.4",
  "serde",
- "zip",
+ "zip 7.4.0",
 ]
 [[package]]
@@ -735,9 +736,9 @@ dependencies = [
 [[package]]
 name = "cc"
-version = "1.2.55"
+version = "1.2.56"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "47b26a0954ae34af09b50f0de26458fa95369a0d478d8236d3f93082b219bd29"
+checksum = "aebf35691d1bfb0ac386a69bac2fde4dd276fb618cf8bf4f5318fe285e821bb2"
 dependencies = [
  "find-msvc-tools",
  "jobserver",
@@ -773,9 +774,9 @@ dependencies = [
 [[package]]
 name = "cfb"
-version = "0.13.0"
+version = "0.14.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "faf95238deba2ee636895c6b8ec16676ec997be9dc63ac99b3f08a9c977ca350"
+checksum = "a347dcabdae9c31b0825fd6a8bed285ec9c2acb89c47827126d52fa4f59cece3"
 dependencies = [
  "fnv",
  "uuid",
@@ -984,6 +985,26 @@ dependencies = [
  "web-sys",
 ]
+[[package]]
+name = "const-random"
+version = "0.1.18"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "87e00182fe74b066627d63b85fd550ac2998d4b0bd86bfed477a0ae4c7c71359"
+dependencies = [
+ "const-random-macro",
+]
+[[package]]
+name = "const-random-macro"
+version = "0.1.16"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "f9d839f2a20b0aee515dc581a6172f2321f96cab76c1a38a4c584a194955390e"
+dependencies = [
+ "getrandom 0.2.16",
+ "once_cell",
+ "tiny-keccak",
+]
 [[package]]
 name = "constant_time_eq"
 version = "0.3.1"
@@ -1774,16 +1795,6 @@ version = "2.0.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "e6d5a32815ae3f33302d95fdcb2ce17862f8c65363dcfd29360480ba1001fc9c"
-[[package]]
-name = "futf"
-version = "0.1.5"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "df420e2e84819663797d1ec6544b13c5be84629e7bb00dc960d6917db2987843"
-dependencies = [
- "mac",
- "new_debug_unreachable",
-]
 [[package]]
 name = "futures"
 version = "0.3.31"
@@ -2247,9 +2258,9 @@ dependencies = [
 [[package]]
 name = "html-to-markdown-rs"
-version = "2.24.5"
+version = "2.25.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "fd0940e15a42f085d4a4ed3ac20c8278af7f8d06cd44f6b7a18148e9347c68db"
+checksum = "bb31d75f2fdbc8d889d78a912e10c22c30451afb44ee3310f5bfcabf79a31a17"
 dependencies = [
  "ahash",
  "astral-tl",
@@ -2258,7 +2269,6 @@ dependencies = [
  "html5ever",
  "image",
  "lru",
- "markup5ever_rcdom",
  "once_cell",
  "regex",
  "serde",
@@ -2268,9 +2278,9 @@ dependencies = [
 [[package]]
 name = "html5ever"
-version = "0.36.1"
+version = "0.38.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "6452c4751a24e1b99c3260d505eaeee76a050573e61f30ac2c924ddc7236f01e"
+checksum = "1054432bae2f14e0061e33d23402fbaa67a921d319d56adc6bcf887ddad1cbc2"
 dependencies = [
  "log",
  "markup5ever",
@@ -2870,7 +2880,7 @@ dependencies = [
 [[package]]
 name = "kreuzberg"
-version = "4.3.0"
+version = "4.3.4"
 dependencies = [
  "ahash",
  "async-trait",
@@ -2882,7 +2892,7 @@ dependencies = [
  "bitvec",
  "bytes",
  "calamine",
- "cfb 0.13.0",
+ "cfb 0.14.0",
  "chardetng",
  "dashmap",
  "dirs",
@@ -2891,7 +2901,7 @@ dependencies = [
  "fastembed",
  "fb2",
  "flate2",
- "getrandom 0.3.4",
+ "getrandom 0.4.1",
  "hayro-jbig2",
  "hayro-jpeg2000",
  "hex",
@@ -2908,7 +2918,7 @@ dependencies = [
  "lazy_static",
  "libc",
  "lopdf",
- "lzma-rust2",
+ "lzma-rust2 0.15.7",
  "mail-parser",
  "memchr",
  "mime_guess",
@@ -2923,7 +2933,7 @@ dependencies = [
  "pkg-config",
  "polars",
  "pulldown-cmark",
- "quick-xml 0.39.0",
+ "quick-xml 0.39.1",
  "rake",
  "rayon",
  "regex",
@@ -2945,7 +2955,7 @@ dependencies = [
  "thiserror 2.0.18",
  "tiff 0.11.0",
  "tokio",
- "toml 1.0.0+spec-1.1.0",
+ "toml 1.0.1+spec-1.1.0",
  "tower",
  "tower-http",
  "tracing",
@@ -2957,12 +2967,12 @@ dependencies = [
  "uuid",
  "whatlang",
  "yake-rust",
- "zip",
+ "zip 8.0.0",
 ]
 [[package]]
 name = "kreuzberg-ffi"
-version = "4.3.0"
+version = "4.3.4"
 dependencies = [
  "ahash",
  "async-trait",
@@ -2978,7 +2988,7 @@ dependencies = [
 [[package]]
 name = "kreuzberg-paddle-ocr"
-version = "4.3.0"
+version = "4.3.4"
 dependencies = [
  "geo-clipper",
  "geo-types",
@@ -2993,7 +3003,7 @@ dependencies = [
 [[package]]
 name = "kreuzberg-pdfium-render"
-version = "4.3.0"
+version = "4.3.4"
 dependencies = [
  "bitflags",
  "bytemuck",
@@ -3017,7 +3027,7 @@ dependencies = [
 [[package]]
 name = "kreuzberg-rb"
-version = "4.3.0"
+version = "4.3.4"
 dependencies = [
  "async-trait",
  "html-to-markdown-rs",
@@ -3034,14 +3044,14 @@ dependencies = [
 [[package]]
 name = "kreuzberg-tesseract"
-version = "4.3.0"
+version = "4.3.4"
 dependencies = [
  "cc",
  "cmake",
  "libc",
  "reqwest 0.13.2",
  "thiserror 2.0.18",
- "zip",
+ "zip 8.0.0",
 ]
 [[package]]
@@ -3091,9 +3101,9 @@ checksum = "2c4a545a15244c7d945065b5d392b2d2d7f21526fba56ce51467b06ed445e8f7"
 [[package]]
 name = "libc"
-version = "0.2.181"
+version = "0.2.182"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "459427e2af2b9c839b132acb702a1c654d95e10f8c326bfc2ad11310e458b1c5"
+checksum = "6800badb6cb2082ffd7b6a67e6125bb39f18782f793520caee8cb8846be06112"
 [[package]]
 name = "libfuzzer-sys"
@@ -3270,10 +3280,14 @@ dependencies = [
 ]
 [[package]]
-name = "mac"
-version = "0.1.1"
+name = "lzma-rust2"
+version = "0.16.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "c41e0c4fef86961ac6d6f8a82609f55f31b05e4fce149ac5710e439df7619ba4"
+checksum = "d673a11333485e7d8b93d62a9a5b07b22daf5e8a8655a44c1bb18aa4bf3d1524"
+dependencies = [
+ "crc",
+ "sha2",
+]
 [[package]]
 name = "macro_rules_attribute"
@@ -3314,37 +3328,24 @@ dependencies = [
 [[package]]
 name = "mail-parser"
-version = "0.11.1"
+version = "0.11.2"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "dcf4390741c4e6fa330bdeccdfb580815dbb462952de91838b723357985119a3"
+checksum = "f82a3d6522697593ba4c683e0a6ee5a40fee93bc1a525e3cc6eeb3da11fd8897"
 dependencies = [
- "encoding_rs",
  "hashify",
 ]
 [[package]]
 name = "markup5ever"
-version = "0.36.1"
+version = "0.38.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "6c3294c4d74d0742910f8c7b466f44dda9eb2d5742c1e430138df290a1e8451c"
+checksum = "8983d30f2915feeaaab2d6babdd6bc7e9ed1a00b66b5e6d74df19aa9c0e91862"
 dependencies = [
  "log",
  "tendril",
  "web_atoms",
 ]
-[[package]]
-name = "markup5ever_rcdom"
-version = "0.36.0+unofficial"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "3e5fc8802e8797c0dfdd2ce5c21aa0aee21abbc7b3b18559100651b3352a7b63"
-dependencies = [
- "html5ever",
- "markup5ever",
- "tendril",
- "xml5ever",
-]
 [[package]]
 name = "matchgen"
 version = "0.3.1"
@@ -4869,9 +4870,9 @@ dependencies = [
 [[package]]
 name = "quick-xml"
-version = "0.39.0"
+version = "0.39.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "f2e3bf4aa9d243beeb01a7b3bc30b77cfe2c44e24ec02d751a7104a53c2c49a1"
+checksum = "bd58c6a1fc307e1092aa0bb23d204ca4d1f021764142cd0424dccc84d2d5d106"
 dependencies = [
  "memchr",
  "serde",
@@ -5847,7 +5848,7 @@ dependencies = [
  "crc32fast",
  "getrandom 0.3.4",
  "js-sys",
- "lzma-rust2",
+ "lzma-rust2 0.15.7",
  "ppmd-rust",
  "sha2",
  "wasm-bindgen",
@@ -6132,7 +6133,6 @@ dependencies = [
  "parking_lot",
  "phf_shared 0.13.1",
  "precomputed-hash",
- "serde",
 ]
 [[package]]
@@ -6275,12 +6275,11 @@ dependencies = [
 [[package]]
 name = "tendril"
-version = "0.4.3"
+version = "0.5.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "d24a120c5fc464a3458240ee02c299ebcb9d67b5249c8848b09d639dca8d7bb0"
+checksum = "c4790fc369d5a530f4b544b094e31388b9b3a37c0f4652ade4505945f5660d24"
 dependencies = [
- "futf",
- "mac",
+ "new_debug_unreachable",
  "utf-8",
 ]
@@ -6417,6 +6416,15 @@ dependencies = [
  "time-core",
 ]
+[[package]]
+name = "tiny-keccak"
+version = "2.0.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "2c9d3793400a45f954c52e73d068316d76b6f4e36977e3fcebb13a2721e80237"
+dependencies = [
+ "crunchy",
+]
 [[package]]
 name = "tinystr"
 version = "0.8.2"
@@ -6576,9 +6584,9 @@ dependencies = [
 [[package]]
 name = "toml"
-version = "1.0.0+spec-1.1.0"
+version = "1.0.1+spec-1.1.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "d1d7e18e3dd1d31e0ee5e863a8091ffec2fcc271636586042452b656a22c8ee1"
+checksum = "bbe30f93627849fa362d4a602212d41bb237dc2bd0f8ba0b2ce785012e124220"
 dependencies = [
  "indexmap",
  "serde_core",
@@ -6632,9 +6640,9 @@ dependencies = [
 [[package]]
 name = "toml_parser"
-version = "1.0.7+spec-1.1.0"
+version = "1.0.8+spec-1.1.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "247eaa3197818b831697600aadf81514e577e0cba5eab10f7e064e78ae154df1"
+checksum = "0742ff5ff03ea7e67c8ae6c93cac239e0d9784833362da3f9a9c1da8dfefcbdc"
 dependencies = [
  "winnow",
 ]
@@ -7139,11 +7147,11 @@ dependencies = [
 [[package]]
 name = "uuid"
-version = "1.20.0"
+version = "1.21.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "ee48d38b119b0cd71fe4141b30f5ba9c7c5d9f4e7a3a8b4a674e4b6ef789976f"
+checksum = "b672338555252d43fd2240c714dc444b8c6fb0a5c5335e65a07bba7742735ddb"
 dependencies = [
- "getrandom 0.3.4",
+ "getrandom 0.4.1",
  "js-sys",
  "serde_core",
  "wasm-bindgen",
@@ -7369,9 +7377,9 @@ dependencies = [
 [[package]]
 name = "web_atoms"
-version = "0.2.0"
+version = "0.2.3"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "acd0c322f146d0f8aad130ce6c187953889359584497dac6561204c8e17bb43d"
+checksum = "57a9779e9f04d2ac1ce317aee707aa2f6b773afba7b931222bff6983843b1576"
 dependencies = [
  "phf 0.13.1",
  "phf_codegen",
@@ -7897,16 +7905,6 @@ dependencies = [
  "rustix",
 ]
-[[package]]
-name = "xml5ever"
-version = "0.36.1"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "f57dd51b88a4b9f99f9b55b136abb86210629d61c48117ddb87f567e51e66be7"
-dependencies = [
- "log",
- "markup5ever",
-]
 [[package]]
 name = "xxhash-rust"
 version = "0.8.15"
@@ -8063,6 +8061,20 @@ name = "zip"
 version = "7.4.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "cc12baa6db2b15a140161ce53d72209dacea594230798c24774139b54ecaa980"
+dependencies = [
+ "crc32fast",
+ "flate2",
+ "indexmap",
+ "memchr",
+ "typed-path",
+ "zopfli",
+]
+[[package]]
+name = "zip"
+version = "8.0.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "79b32dd4ad3aca14ae109f8cce0495ac1c57f6f4f00ad459a40e582f89440d97"
 dependencies = [
  "aes",
  "bzip2",
@@ -8073,7 +8085,7 @@ dependencies = [
  "getrandom 0.4.1",
  "hmac",
  "indexmap",
- "lzma-rust2",
+ "lzma-rust2 0.16.1",
  "memchr",
  "pbkdf2",
  "ppmd-rust",

data/ext/kreuzberg_rb/native/Cargo.toml CHANGED Viewed

@@ -37,7 +37,7 @@ collapsible_if = "allow"
 [package]
 name = "kreuzberg-rb"
-version = "4.3.3"
+version = "4.3.4"
 edition = "2024"
 rust-version = "1.91"
 authors = ["Na'aman Hirschfeld <nhirschfeld@gmail.com>"]

data/ext/kreuzberg_rb/native/libpdfium.so CHANGED Viewed

Binary file

data/ext/kreuzberg_rb/native/src/plugins/ocr_backend.rs CHANGED Viewed

@@ -101,6 +101,9 @@ impl OcrBackend for RubyOcrBackend {
                 elements: None,
                 ocr_elements: None,
                 document: None,
+                extracted_keywords: None,
+                quality_score: None,
+                processing_warnings: vec![],
             })
         })
     }

data/ext/kreuzberg_rb/native/src/result.rs CHANGED Viewed

@@ -555,5 +555,50 @@ pub fn extraction_result_to_ruby(ruby: &Ruby, result: RustExtractionResult) -> R
         set_hash_entry(ruby, &hash, "document", ruby.qnil().as_value())?;
     }
+    // Convert extracted keywords
+    if let Some(keywords) = result.extracted_keywords {
+        let keywords_array = ruby.ary_new();
+        for kw in keywords {
+            let kw_hash = ruby.hash_new();
+            kw_hash.aset("text", kw.text.as_str())?;
+            kw_hash.aset("score", ruby.float_from_f64(kw.score as f64).into_value_with(ruby))?;
+            let algo_str = serde_json::to_value(&kw.algorithm)
+                .ok()
+                .and_then(|v| v.as_str().map(String::from))
+                .unwrap_or_default();
+            kw_hash.aset("algorithm", algo_str.as_str())?;
+            if let Some(positions) = kw.positions {
+                let positions_array = ruby.ary_new();
+                for pos in positions {
+                    positions_array.push(pos as i64)?;
+                }
+                kw_hash.aset("positions", positions_array)?;
+            } else {
+                kw_hash.aset("positions", ruby.qnil().as_value())?;
+            }
+            keywords_array.push(kw_hash)?;
+        }
+        set_hash_entry(ruby, &hash, "extracted_keywords", keywords_array.into_value_with(ruby))?;
+    } else {
+        set_hash_entry(ruby, &hash, "extracted_keywords", ruby.qnil().as_value())?;
+    }
+    // Convert quality score
+    if let Some(score) = result.quality_score {
+        set_hash_entry(ruby, &hash, "quality_score", ruby.float_from_f64(score).into_value_with(ruby))?;
+    } else {
+        set_hash_entry(ruby, &hash, "quality_score", ruby.qnil().as_value())?;
+    }
+    // Convert processing warnings
+    let warnings_array = ruby.ary_new();
+    for warning in result.processing_warnings {
+        let w_hash = ruby.hash_new();
+        w_hash.aset("source", warning.source.as_str())?;
+        w_hash.aset("message", warning.message.as_str())?;
+        warnings_array.push(w_hash)?;
+    }
+    set_hash_entry(ruby, &hash, "processing_warnings", warnings_array.into_value_with(ruby))?;
     Ok(hash)
 }

data/lib/kreuzberg/result.rb CHANGED Viewed

@@ -14,7 +14,7 @@ module Kreuzberg
   class Result
     attr_reader :content, :mime_type, :metadata, :metadata_json, :tables,
                 :detected_languages, :chunks, :images, :pages, :elements, :ocr_elements, :djot_content,
-                :document
+                :document, :extracted_keywords, :quality_score, :processing_warnings
     # @!attribute [r] cells
     #   @return [Array<Array<String>>] Table cells (2D array)
@@ -332,6 +332,9 @@ module Kreuzberg
       @ocr_elements = parse_ocr_elements(get_value(hash, 'ocr_elements'))
       @djot_content = parse_djot_content(get_value(hash, 'djot_content'))
       @document = parse_document_structure(get_value(hash, 'document'))
+      @extracted_keywords = parse_extracted_keywords(get_value(hash, 'extracted_keywords'))
+      @quality_score = get_value(hash, 'quality_score')
+      @processing_warnings = parse_processing_warnings(get_value(hash, 'processing_warnings'))
     end
     # rubocop:enable Metrics/AbcSize
@@ -352,7 +355,10 @@ module Kreuzberg
         elements: serialize_elements,
         ocr_elements: serialize_ocr_elements,
         djot_content: @djot_content&.to_h,
-        document: @document&.to_h
+        document: @document&.to_h,
+        extracted_keywords: @extracted_keywords&.map(&:to_h),
+        quality_score: @quality_score,
+        processing_warnings: @processing_warnings.map(&:to_h)
       }
     end
@@ -653,6 +659,30 @@ module Kreuzberg
       DocumentStructure.new(document_data)
     end
+    def parse_extracted_keywords(keywords_data)
+      return nil if keywords_data.nil?
+      keywords_data.map do |kw_hash|
+        Kreuzberg::ExtractedKeyword.new(
+          text: kw_hash['text'] || '',
+          score: (kw_hash['score'] || 0.0).to_f,
+          algorithm: kw_hash['algorithm'] || '',
+          positions: kw_hash['positions']
+        )
+      end
+    end
+    def parse_processing_warnings(warnings_data)
+      return [] if warnings_data.nil?
+      warnings_data.map do |w_hash|
+        Kreuzberg::ProcessingWarning.new(
+          source: w_hash['source'] || '',
+          message: w_hash['message'] || ''
+        )
+      end
+    end
   end
   # rubocop:enable Metrics/ClassLength
 end