refactor(core): 提炼公共类型

- 将 AxisDim、TensorInfo 等公共类型下沉至 ddddocr_core::types
- 项目结构优化

ddddocr-core/src/det/builder.rs

@@ -1,26 +1,11 @@
 use crate::det::executor::Detector;
 // use ddddocr_tract::det::session::DetSession;
-use crate::DetEngine;
-
-pub struct DetBuilder {
-    use_gpu: bool,
-    device_id: u8,
-}
+use crate::traits::DetEngine;
+#[derive(Default)]
+pub struct DetBuilder;
 
 impl DetBuilder {
-    fn use_gpu(mut self) -> Self {
-        self.use_gpu = true;
-        self
-    }
-    fn device_id(mut self, device_id: u8) -> Self {
-        self.device_id = device_id;
-        self
-    }
     fn build<E: DetEngine>(self, session: &E) -> Detector<'_> {
-        Detector {
-            session,
-            use_gpu: self.use_gpu,
-            device_id: self.device_id,
-        }
+        Detector { session }
     }
 }

ddddocr-core/src/det/executor.rs

@@ -5,7 +5,8 @@ use std::fmt;
 // use tract_onnx::prelude::{Tensor};
 
 // use ddddocr_tract::det::session::DetSession;
-use crate::{DetEngine, DetOutput};
+use crate::{DetBuilder, DetOutput, OcrBuilder};
+use crate::traits::DetEngine;
 #[derive(Debug, Clone, Copy)]
 pub struct DetectionResult {
     pub x1: i32,
@@ -29,21 +30,17 @@ impl fmt::Display for DetectionResult {
 
 pub struct Detector<'a> {
     pub(crate) session: &'a dyn DetEngine,
-    #[allow(dead_code)]
-    pub(crate) use_gpu: bool,
-    #[allow(dead_code)]
-    pub(crate) device_id: u8,
 }
 
 impl<'a> Detector<'a> {
     pub fn new(session: &'a dyn DetEngine) -> Self {
-        Detector {
-            session,
-            use_gpu: false,
-            device_id: 0,
-        }
+        Detector { session }
     }
-
+    pub fn builder() -> DetBuilder {
+        DetBuilder::default()
+    }
+}
+impl<'a> Detector<'a> {
     pub fn predict(&self, image: &DynamicImage) -> Result<Vec<DetectionResult>> {
         // Rust 中通常在调用层处理文件/PIL转换，这里直接进入核心逻辑
         Ok(self.get_bbox(image)?)

ddddocr-core/src/lib.rs

@@ -3,14 +3,14 @@ pub mod error;
 mod ocr;
 mod slide;
 pub mod utils;
-
-use error::{Result, TensorError};
-use std::path::Path;
+pub mod types;
+pub mod traits;
 
 pub use crate::det::{DetBuilder, DetectionResult, Detector};
 pub use crate::ocr::{Charset, ModelMetadata, Normalization, Ocr, OcrBuilder, OcrResult, Resize};
 pub use crate::slide::{SlideResult, Slider};
 
+
 // DetSession
 
 pub enum OcrOutput {
@@ -22,24 +22,3 @@ pub enum DetOutput {
     Detection(ndarray::Array3<f32>), // 拥有完整所有权的 2维矩阵，可任意传递和返回
 }
 
-/// 核心层定义的统一推理引擎接口。
-/// 未来的 ddddocr-tract 和 ddddocr-ort 都必须实现这个 Trait
-pub trait InferenceEngine {
-    /// 关联类型：具体的 Session 需要声明自己到底产出什么枚举
-    type Output;
-    fn inference(&self, input_array: ndarray::Array4<f32>) -> Result<Self::Output, TensorError>;
-}
-
-pub trait OcrEngine: InferenceEngine<Output = OcrOutput> {
-    fn metadata(&self) -> &ModelMetadata;
-}
-
-pub trait DetEngine: InferenceEngine<Output = DetOutput> {}
-
-pub trait ModelBuilder {
-    type Session;
-    type Error;
-    fn model_for_path<P: AsRef<Path>>(&self,model_path: P) -> Result<Self::Session, Self::Error>;
-
-    fn model_from_bytes(&self,model_bytes: &[u8]) -> Result<Self::Session, Self::Error>;
-}

ddddocr-core/src/ocr/builder.rs

@@ -1,9 +1,9 @@
 use crate::ocr::executor::Ocr;
 // use ddddocr_tract::session::OcrSession;
-use crate::OcrEngine;
+use crate::traits::OcrEngine;
 use crate::ocr::color_filter::ColorFilter;
 use crate::ocr::token_filter::TokenFilter;
-
+#[derive(Default)]
 pub struct OcrBuilder {
     /// 是否修复PNG格式问题
     png_fix: bool,
@@ -49,14 +49,14 @@ impl OcrBuilder {
         self.charset_restrict = Some(Box::new(restrict));
         self
     }
-    pub fn build<E: OcrEngine>(self, session: &E) -> Ocr<'_> {
+    pub fn runner<E: OcrEngine>(self, runtime: &E) -> Ocr<'_> {
         // 1. 原地解析颜色过滤器
         let final_color_ranges = match &self.color_filter {
             Some(filter) => filter.collect_to_vec(),
             None => Ok(None),
         };
         // 2. 原地解析字符集过滤
-        let tokens = &session.metadata().charset.tokens;
+        let tokens = &runtime.metadata().charset.tokens;
         let final_charset_indices = match &self.charset_restrict {
             Some(restrict) => restrict.apply_to_charset(tokens),
             None => None,
@@ -64,7 +64,7 @@ impl OcrBuilder {
 
         // Ocr::new(session, self)
         Ocr {
-            session,
+            runtime,
             png_fix: self.png_fix, // 原地解构出来
             probability: self.probability,
             final_color_ranges,

ddddocr-core/src/ocr/executor.rs

@@ -16,7 +16,8 @@ use ndarray::ArrayView2;
 //     Logits(ndarray::Array2<f32>),  // 拥有完整所有权的 2维矩阵，可任意传递和返回
 // }
 use crate::error::{ImagePreprocessError, Result, TensorError};
-use crate::{OcrEngine, OcrOutput};
+use crate::{OcrBuilder, OcrOutput};
+use crate::traits::OcrEngine;
 use tracing::{ warn};
 #[derive(Debug, Clone)]
 pub enum OcrResult {
@@ -103,7 +104,7 @@ impl fmt::Display for OcrResult {
 }
 
 pub struct Ocr<'a> {
-    pub(crate) session: &'a dyn OcrEngine,
+    pub(crate) runtime: &'a dyn OcrEngine,
     pub(crate) png_fix: bool,
     pub(crate) probability: bool,
     /// 颜色过滤：保留的颜色列表
@@ -116,15 +117,19 @@ pub struct Ocr<'a> {
 impl<'a> Ocr<'a> {
     // 初始化任务，设置默认参数
 
-    pub fn new(session: &'a dyn OcrEngine) -> Self {
+    pub fn new(runtime: &'a dyn OcrEngine) -> Self {
         Ocr {
-            session,
+            runtime,
             png_fix: false, // 默认值
             probability: false,
             final_color_ranges: Ok(None),
             final_charset_indices: None,
         }
     }
+    pub fn builder() -> OcrBuilder {
+        OcrBuilder::default()
+    }
+
 }
 impl<'a> Ocr<'a> {
     pub fn predict(&self, image: &DynamicImage) -> Result<OcrResult> {
@@ -157,7 +162,7 @@ impl<'a> Ocr<'a> {
         };
         let tensor = self.preprocess_image(&img_cow)?;
 
-        let raw_tensor = self.session.inference(tensor)?;
+        let raw_tensor = self.runtime.inference(tensor)?;
 
         // 3. 后处理分流：直接返回 OcrResult
         // let ocr_output = match raw_tensor.datum_type() {
@@ -178,7 +183,7 @@ impl<'a> Ocr<'a> {
     /// 负责：透明背景修复 -> 灰度化 -> 按比例 Resize -> 归一化 -> 4维张量转换
     fn preprocess_image(&self, img: &DynamicImage) -> Result<ndarray::Array4<f32>,ImagePreprocessError> {
         // 1. 获取模型元数据配置
-        let meta = self.session.metadata();
+        let meta = self.runtime.metadata();
         let norm = &meta.normalization; // 获取归一化器
 
         // A. 修复 PNG 透明背景 (内部逻辑你之前已实现)
@@ -326,7 +331,7 @@ impl<'a> Ocr<'a> {
 }
 impl<'a> Ocr<'a> {
     fn is_valid_indices(&self, idx: usize) -> bool {
-        if idx >= self.session.metadata().charset.size() {
+        if idx >= self.runtime.metadata().charset.size() {
             return false;
         }
 
@@ -338,7 +343,7 @@ impl<'a> Ocr<'a> {
     /// 【按需延迟打印】：当用户真的需要“知道当前有哪些限制字符”时，一秒反查并打印
     /// 这里的 &str 完美借用了自 tokens，依然是彻底的零拷贝！
     pub fn valid_tokens(&self) -> Vec<&str> {
-        let charset = &self.session.metadata().charset;
+        let charset = &self.runtime.metadata().charset;
         let tokens = &charset.tokens;
         match &self.final_charset_indices {
             Some(indices) => indices
@@ -352,7 +357,7 @@ impl<'a> Ocr<'a> {
     pub fn valid_size(&self) -> usize {
         match &self.final_charset_indices {
             Some(indices) => indices.len(),
-            None => self.session.metadata().charset.tokens.len(),
+            None => self.runtime.metadata().charset.tokens.len(),
         }
     }
     /// 变体 B 核心处理器：单次遍历 2D 视图，融合计算 Softmax、Argmax、置信度并输出概率大包
@@ -500,7 +505,7 @@ impl<'a> Ocr<'a> {
     /// 获取有效字符索引列表 (用于外部验证或过滤)
     fn ctc_decode_to_string(&self, predicted_indices: &[i64]) -> String {
         println!("indices模型输出原始数据: {:?}", predicted_indices);
-        let charset = &self.session.metadata().charset;
+        let charset = &self.runtime.metadata().charset;
         let tokens = &charset.tokens;
         // let valid_indices = &charset.valid_indices;
 

ddddocr-core/src/traits.rs

@@ -0,0 +1,42 @@
+use crate::error::TensorError;
+use crate::types::{ModelInfo, TensorInfo};
+use crate::{DetOutput, ModelMetadata, OcrOutput};
+use std::path::Path;
+
+
+pub trait Info {
+    fn input_info(&self) -> crate::error::Result<Vec<TensorInfo>>;
+    fn output_info(&self) -> crate::error::Result<Vec<TensorInfo>>;
+    fn model_info(&self) -> crate::error::Result<ModelInfo>;
+}
+
+/// 核心层定义的统一推理引擎接口。
+/// 未来的 ddddocr-tract 和 ddddocr-ort 都必须实现这个 Trait
+pub trait InferenceEngine {
+    /// 关联类型：具体的 Session 需要声明自己到底产出什么枚举
+    type Output;
+    fn inference(
+        &self,
+        input_array: ndarray::Array4<f32>,
+    ) -> crate::error::Result<Self::Output, TensorError>;
+}
+
+pub trait OcrEngine: InferenceEngine<Output = OcrOutput> + Info {
+    fn metadata(&self) -> &ModelMetadata;
+}
+
+pub trait DetEngine: InferenceEngine<Output = DetOutput> {}
+
+pub trait Loader {
+    type Session;
+    type Error;
+    fn build_for_path<P: AsRef<Path>>(
+        &self,
+        model_path: P,
+    ) -> crate::error::Result<Self::Session, Self::Error>;
+
+    fn build_from_bytes(
+        &self,
+        model_bytes: &[u8],
+    ) -> crate::error::Result<Self::Session, Self::Error>;
+}

ddddocr-core/src/types.rs

@@ -0,0 +1,46 @@
+#[derive(Debug,Clone)]
+pub enum TensorType{
+    F32,
+    I64,
+    Other
+}
+/// 明确命名为 AxisDim，代表模型某一个轴的维度特征
+#[derive(Clone, PartialEq, Eq)]
+pub enum AxisDim {
+    /// 静态固定维度（如通道数固定为 1，高度固定为 64）
+    Static(usize),
+    /// 动态符号维度（如宽度是动态的 "image_width"）
+    Dynamic(String),
+}
+
+impl AxisDim {
+    /// 便捷方法：判断是否为动态维度
+    pub fn is_dynamic(&self) -> bool {
+        matches!(self, AxisDim::Dynamic(_))
+    }
+}
+/// 自定义 Debug 格式化输出，彻底融化套娃外壳，保证日志干净漂亮
+impl std::fmt::Debug for AxisDim {
+    fn fmt(&self, f: &mut std::fmt::Formatter<'_>) -> std::fmt::Result {
+        match self {
+            AxisDim::Static(size) => write!(f, "{}", size),
+            AxisDim::Dynamic(expr) => write!(f, "Dynamic(\"{}\")", expr),
+        }
+    }
+}
+/// 模拟 Python 的 input_info 和 output_info 结构
+#[derive(Debug, Clone)]
+pub struct TensorInfo {
+    pub name: String,
+    pub shape: Vec<AxisDim>, // 既包含 Fixed 静态维度，也包含 Dynamic 动态符号
+    pub tensor_type: TensorType, // 对应 Python 的 type
+}
+
+/// 最终返回的模型完整信息
+#[derive(Debug, Clone)]
+pub struct ModelInfo {
+    pub inputs: Vec<TensorInfo>,
+    pub outputs: Vec<TensorInfo>,
+    /// 硬件执行提供者（采用 Option 兼容不同底层的推理引擎）
+    pub providers: Option<Vec<String>>,
+}