xberg 1.0.0.pre.rc.11 → 1.0.0.pre.rc.13

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 27216830b9ad0a6aff2852974c6105718cbb550c484388dd4719c847f2ab0caa
-  data.tar.gz: c4fae0cf29c44159776894148ebbd8460accce0f738132203675bcb9048c8af9
+  metadata.gz: 93271fcd87972e2eb3a678d1e33f243ee76323f3c6ef8c31e63225e7ab8cac05
+  data.tar.gz: 5ce8d87ae1032f4593364185fb54089d9bd76b7170e1f57f26c001682317d501
 SHA512:
-  metadata.gz: fd984db0aa91e4a9551ce2fbb678b2fa31a23749a09a4950fdcaa216c5c85fa1e907d151a47d44ef6d858e40ed839d086f69b6c3b8279a20c353fe631b3c71a7
-  data.tar.gz: 426a425faa9f4171b45e879b4f416033cc639d931ada76d24ac044a3eda291931d1dac776f68df6a09215532eff8210ec49ad709af9e40b51d792b16e69313da
+  metadata.gz: 67cf983c3da0b78d87f98961444165562c67fc87ddfcbb08f3ab51e643e335a4e601007b9e9dc836b177514e124c10c917512bc17023583d05710fa216762be7
+  data.tar.gz: 1f74a9e41caa0eb5db2e09a047b0b9eb06276f12b80c3a04c8bb7f92913bd5ac48bd9922b16d43a770053c012e8384fc21628041c4258756f607b71f60172828

data/ext/xberg_rb/native/Cargo.lock

@@ -1463,9 +1463,9 @@ checksum = "be1e0bca6c3637f992fc1cc7cbc52a78c1ef6db076dbf1059c4323d6a2048376"
 
 [[package]]
 name = "dbase"
-version = "0.7.0"
+version = "0.8.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "15526d487321e5121f43efab7f9929f0f0581859b8d710fec545938b2d2d4489"
+checksum = "abde818b4b82df61e01348c2b4610c221bcecb97cb7f567da086edf295d8d126"
 dependencies = [
  "bufrw",
  "byteorder",
@@ -3233,11 +3233,11 @@ dependencies = [
 
 [[package]]
 name = "jobserver"
-version = "0.1.34"
+version = "0.1.35"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "9afb3de4395d6b3e67a780b6de64b51c978ecf11cb9a462c66be7d4ca9039d33"
+checksum = "1c00acbd29eabad4a2392fa0e921c874934dbbf4194312ad20f04a0ed67a3cb3"
 dependencies = [
- "getrandom 0.3.4",
+ "getrandom 0.4.3",
  "libc",
 ]
 
@@ -5626,9 +5626,9 @@ dependencies = [
 
 [[package]]
 name = "rustversion"
-version = "1.0.22"
+version = "1.0.23"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "b39cdef0fa800fc44525c84ccb54a029961a8215f9619753635a9c0d2538d46d"
+checksum = "cf54715a573b99ac80df0bc206da022bcd442c974952c7b9720069370852e21f"
 
 [[package]]
 name = "rustybuzz"
@@ -7065,9 +7065,9 @@ checksum = "009994f150cc0cd50ff54917d5bc8bffe8cad10ca10d81c34da2ec421ae61782"
 
 [[package]]
 name = "tree-sitter-language-pack"
-version = "1.12.4"
+version = "1.12.5"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "d49e30d1927ccc08599c054380bda399817781f74eb9184007e90606c7ff3a2c"
+checksum = "f860e7a7df78207ed80a1f8a4cab7fd5e366ed9bfd5fa74f2d1ed3022905a058"
 dependencies = [
  "ahash 0.8.12",
  "cc",
@@ -8063,9 +8063,9 @@ dependencies = [
 
 [[package]]
 name = "xberg"
-version = "1.0.0-rc.11"
+version = "1.0.0-rc.13"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "48027a596691044dbb108ce96099138b5f2723983975c35c773f933e4e7a6ef5"
+checksum = "6819b396096da99a7e57c8188daebfe9ed8e80f5effc7cdf1e7709019aac71be"
 dependencies = [
  "ahash 0.8.12",
  "async-trait",
@@ -8181,9 +8181,9 @@ dependencies = [
 
 [[package]]
 name = "xberg-gliner"
-version = "1.0.0-rc.11"
+version = "1.0.0-rc.13"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "4e0efdb1378539dc7337854eeba22f48cc162c057e554f1daf23157cfeb723a6"
+checksum = "4e52cac01a2e651a57127b3b1a3b0e25939dfdf6bb6792e31ec7708cec2e092c"
 dependencies = [
  "ndarray 0.17.2",
  "ort",
@@ -8195,9 +8195,9 @@ dependencies = [
 
 [[package]]
 name = "xberg-libheif"
-version = "1.0.0-rc.11"
+version = "1.0.0-rc.13"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "9b51c5dd552e0adfb76f0f8b64f4d9442b95ac9a9737bb29f08961d5a1996035"
+checksum = "05e3e60dc8704cd66708b94b74306135895281ff0e0f9b2df9f0948df249c0f5"
 dependencies = [
  "cfg-if",
  "enumn",
@@ -8208,9 +8208,9 @@ dependencies = [
 
 [[package]]
 name = "xberg-paddle-ocr"
-version = "1.0.0-rc.11"
+version = "1.0.0-rc.13"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "e795e9f7b70d212dc06d4775f2283287916ec4e8b133672dd0e5e2ccd0a233ab"
+checksum = "7490a234118acb62781f3ef6e258435bce77f1b4b99598e9ff83385665ee6b2f"
 dependencies = [
  "geo-clipper",
  "geo-types",
@@ -8225,7 +8225,7 @@ dependencies = [
 
 [[package]]
 name = "xberg-rb"
-version = "1.0.0-rc.11"
+version = "1.0.0-rc.13"
 dependencies = [
  "async-trait",
  "crawlberg",
@@ -8239,9 +8239,9 @@ dependencies = [
 
 [[package]]
 name = "xberg-tesseract"
-version = "1.0.0-rc.11"
+version = "1.0.0-rc.13"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "bd810c90a03d6ca2f6536f327e35b96acf1938d49063d8bd0de3199f23d87db1"
+checksum = "92d753ce7d55f901afd93ac1531bf0a8c49fa7d23d809994d3f0197e923e80ac"
 dependencies = [
  "cc",
  "cmake",
@@ -8296,18 +8296,18 @@ dependencies = [
 
 [[package]]
 name = "zerocopy"
-version = "0.8.52"
+version = "0.8.53"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "ce1022995ff5ff5d841ad7d994facc23098cd40152f2c1d11cd607c6f530653f"
+checksum = "75726053136156d419e285b9b7eddaaea9e3fea6ce32eed44a89901f0bd98de1"
 dependencies = [
  "zerocopy-derive",
 ]
 
 [[package]]
 name = "zerocopy-derive"
-version = "0.8.52"
+version = "0.8.53"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "1ae7f38b72ec2a254e2b87ef277cf2cd4fb97cbebf944faa6f33354da0867930"
+checksum = "4714fd92cf900833d49538023a9b3915155210801d1c1169eba513b2addefd71"
 dependencies = [
  "proc-macro2",
  "quote",

data/ext/xberg_rb/native/Cargo.toml

@@ -1,6 +1,6 @@
 [package]
 name = "xberg-rb"
-version = "1.0.0-rc.11"
+version = "1.0.0-rc.13"
 edition = "2024"
 license = "MIT"
 description = "High-performance document intelligence library"
@@ -56,10 +56,10 @@ 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.11", 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.13", 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.11", features = ["windows-target"] }
+xberg = { version = "1.0.0-rc.13", features = ["windows-target"] }
 
 [target.'cfg(all(target_os = "macos", target_arch = "x86_64"))'.dependencies]
-xberg = { version = "1.0.0-rc.11", features = ["macos-intel-target"] }
+xberg = { version = "1.0.0-rc.13", 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:49d7737c4c8395f019e87ea16ab3317aeda42281d98fd36f5ee4369a81b3e523
+// alef:hash:38dce430f8d9bea3dcf8465197cc598552462cd7a5930cc5e7e769e1d0990c01
 // Re-generate with: alef generate
 #![allow(dead_code, unused_imports, unused_variables)]
 #![allow(
@@ -3973,6 +3973,7 @@ pub struct EmbeddingConfig {
     cache_dir: Option<String>,
     acceleration: Option<AccelerationConfig>,
     max_embed_duration_secs: Option<u64>,
+    max_sequence_length: Option<usize>,
 }
 
 unsafe impl IntoValueFromNative for EmbeddingConfig {}
@@ -4041,6 +4042,9 @@ impl EmbeddingConfig {
             max_embed_duration_secs: kwargs
                 .get(ruby.to_symbol("max_embed_duration_secs"))
                 .and_then(|v| u64::try_convert(v).ok()),
+            max_sequence_length: kwargs
+                .get(ruby.to_symbol("max_sequence_length"))
+                .and_then(|v| usize::try_convert(v).ok()),
         })
     }
 
@@ -4071,6 +4075,10 @@ impl EmbeddingConfig {
     fn max_embed_duration_secs(&self) -> Option<u64> {
         self.max_embed_duration_secs
     }
+
+    fn max_sequence_length(&self) -> Option<usize> {
+        self.max_sequence_length
+    }
 }
 
 #[derive(Clone, Debug, serde::Serialize, serde::Deserialize)]
@@ -8057,6 +8065,84 @@ impl Entity {
     }
 }
 
+#[derive(Clone, Debug, serde::Serialize, serde::Deserialize)]
+#[serde(default)]
+#[magnus::wrap(class = "Xberg::DocumentCounts")]
+pub struct DocumentCounts {
+    pages: usize,
+    tables: usize,
+    images: usize,
+}
+
+unsafe impl IntoValueFromNative for DocumentCounts {}
+
+impl magnus::TryConvert for DocumentCounts {
+    fn try_convert(val: magnus::Value) -> Result<Self, magnus::Error> {
+        if let Ok(r) = <&DocumentCounts as magnus::TryConvert>::try_convert(val) {
+            return Ok(r.clone());
+        }
+        let json_str: String = if let Ok(s) = <String as magnus::TryConvert>::try_convert(val) {
+            s
+        } else {
+            val.funcall::<_, _, String>("to_json", ()).map_err(|e| {
+                magnus::Error::new(
+                    unsafe { magnus::Ruby::get_unchecked() }.exception_type_error(),
+                    format!("no implicit conversion into DocumentCounts: {}", e),
+                )
+            })?
+        };
+        serde_json::from_str::<DocumentCounts>(&json_str).map_err(|e| {
+            magnus::Error::new(
+                unsafe { magnus::Ruby::get_unchecked() }.exception_type_error(),
+                format!("failed to deserialize DocumentCounts: {}", e),
+            )
+        })
+    }
+}
+
+unsafe impl TryConvertOwned for DocumentCounts {}
+
+impl Default for DocumentCounts {
+    fn default() -> Self {
+        xberg::DocumentCounts::default().into()
+    }
+}
+
+impl DocumentCounts {
+    fn new(args: &[magnus::Value]) -> Result<Self, magnus::Error> {
+        let ruby = unsafe { magnus::Ruby::get_unchecked() };
+        let args = magnus::scan_args::scan_args::<(), (Option<magnus::RHash>,), (), (), (), ()>(args)?;
+        let (kwargs_opt,) = args.optional;
+        let kwargs = kwargs_opt.unwrap_or_else(|| ruby.hash_new());
+        Ok(Self {
+            pages: kwargs
+                .get(ruby.to_symbol("pages"))
+                .and_then(|v| usize::try_convert(v).ok())
+                .unwrap_or_default(),
+            tables: kwargs
+                .get(ruby.to_symbol("tables"))
+                .and_then(|v| usize::try_convert(v).ok())
+                .unwrap_or_default(),
+            images: kwargs
+                .get(ruby.to_symbol("images"))
+                .and_then(|v| usize::try_convert(v).ok())
+                .unwrap_or_default(),
+        })
+    }
+
+    fn pages(&self) -> usize {
+        self.pages
+    }
+
+    fn tables(&self) -> usize {
+        self.tables
+    }
+
+    fn images(&self) -> usize {
+        self.images
+    }
+}
+
 #[derive(Clone, Debug, serde::Serialize, serde::Deserialize)]
 #[serde(default)]
 #[magnus::wrap(class = "Xberg::ExtractedDocument")]
@@ -8066,6 +8152,7 @@ pub struct ExtractedDocument {
     metadata: Metadata,
     extraction_method: Option<ExtractionMethod>,
     tables: Vec<Table>,
+    counts: DocumentCounts,
     detected_languages: Option<Vec<String>>,
     chunks: Option<Vec<Chunk>>,
     images: Option<Vec<ExtractedImage>>,
@@ -8155,6 +8242,10 @@ impl ExtractedDocument {
                 .get(ruby.to_symbol("tables"))
                 .and_then(|v| <Vec<Table>>::try_convert(v).ok())
                 .unwrap_or_default(),
+            counts: kwargs
+                .get(ruby.to_symbol("counts"))
+                .and_then(|v| DocumentCounts::try_convert(v).ok())
+                .unwrap_or_default(),
             detected_languages: kwargs
                 .get(ruby.to_symbol("detected_languages"))
                 .and_then(|v| <Vec<String>>::try_convert(v).ok()),
@@ -8262,6 +8353,10 @@ impl ExtractedDocument {
         self.tables.clone()
     }
 
+    fn counts(&self) -> DocumentCounts {
+        self.counts.clone()
+    }
+
     fn detected_languages(&self) -> Option<Vec<String>> {
         self.detected_languages.clone()
     }
@@ -28581,6 +28676,7 @@ impl From<EmbeddingConfig> for xberg::EmbeddingConfig {
             cache_dir: val.cache_dir.map(Into::into),
             acceleration: val.acceleration.map(Into::into),
             max_embed_duration_secs: val.max_embed_duration_secs,
+            max_sequence_length: val.max_sequence_length,
         }
     }
 }
@@ -28596,6 +28692,7 @@ impl From<xberg::EmbeddingConfig> for EmbeddingConfig {
             cache_dir: val.cache_dir.map(|p| p.to_string_lossy().to_string()),
             acceleration: val.acceleration.map(Into::into),
             max_embed_duration_secs: val.max_embed_duration_secs,
+            max_sequence_length: val.max_sequence_length,
         }
     }
 }
@@ -29582,6 +29679,28 @@ impl From<xberg::Entity> for Entity {
     }
 }
 
+#[allow(clippy::redundant_closure, clippy::useless_conversion)]
+impl From<DocumentCounts> for xberg::DocumentCounts {
+    fn from(val: DocumentCounts) -> Self {
+        Self {
+            pages: val.pages,
+            tables: val.tables,
+            images: val.images,
+        }
+    }
+}
+
+#[allow(clippy::redundant_closure, clippy::useless_conversion)]
+impl From<xberg::DocumentCounts> for DocumentCounts {
+    fn from(val: xberg::DocumentCounts) -> Self {
+        Self {
+            pages: val.pages,
+            tables: val.tables,
+            images: val.images,
+        }
+    }
+}
+
 #[allow(clippy::field_reassign_with_default, clippy::let_and_return)]
 #[allow(clippy::redundant_closure, clippy::useless_conversion)]
 impl From<ExtractedDocument> for xberg::ExtractedDocument {
@@ -29592,6 +29711,7 @@ impl From<ExtractedDocument> for xberg::ExtractedDocument {
         __result.metadata = val.metadata.into();
         __result.extraction_method = val.extraction_method.map(Into::into);
         __result.tables = val.tables.into_iter().map(Into::into).collect();
+        __result.counts = val.counts.into();
         __result.detected_languages = val.detected_languages.map(|v| v.into_iter().collect());
         __result.chunks = val.chunks.map(|v| v.into_iter().map(Into::into).collect());
         __result.images = val.images.map(|v| v.into_iter().map(Into::into).collect());
@@ -29640,6 +29760,7 @@ impl From<xberg::ExtractedDocument> for ExtractedDocument {
             metadata: val.metadata.into(),
             extraction_method: val.extraction_method.map(Into::into),
             tables: val.tables.into_iter().map(Into::into).collect(),
+            counts: val.counts.into(),
             detected_languages: val.detected_languages.map(|v| v.into_iter().collect()),
             chunks: val.chunks.map(|v| v.into_iter().map(Into::into).collect()),
             images: val.images.map(|v| v.into_iter().map(Into::into).collect()),
@@ -35190,6 +35311,8 @@ fn ruby_init(ruby: &Ruby) -> Result<(), Error> {
         method!(EmbeddingConfig::max_embed_duration_secs, 0),
     )?;
 
+    class.define_method("max_sequence_length", method!(EmbeddingConfig::max_sequence_length, 0))?;
+
     let class = module.define_class("RedactionConfig", ruby.class_object())?;
 
     class.define_singleton_method("new", function!(RedactionConfig::new, -1))?;
@@ -35836,6 +35959,16 @@ fn ruby_init(ruby: &Ruby) -> Result<(), Error> {
 
     class.define_method("confidence", method!(Entity::confidence, 0))?;
 
+    let class = module.define_class("DocumentCounts", ruby.class_object())?;
+
+    class.define_singleton_method("new", function!(DocumentCounts::new, -1))?;
+
+    class.define_method("pages", method!(DocumentCounts::pages, 0))?;
+
+    class.define_method("tables", method!(DocumentCounts::tables, 0))?;
+
+    class.define_method("images", method!(DocumentCounts::images, 0))?;
+
     let class = module.define_class("ExtractedDocument", ruby.class_object())?;
 
     class.define_singleton_method("new", function!(ExtractedDocument::new, -1))?;
@@ -35850,6 +35983,8 @@ fn ruby_init(ruby: &Ruby) -> Result<(), Error> {
 
     class.define_method("tables", method!(ExtractedDocument::tables, 0))?;
 
+    class.define_method("counts", method!(ExtractedDocument::counts, 0))?;
+
     class.define_method("detected_languages", method!(ExtractedDocument::detected_languages, 0))?;
 
     class.define_method("chunks", method!(ExtractedDocument::chunks, 0))?;