1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179
//! Productive and safe Rust bindings/wrappers for Leptonica and Tesseract. //! //! Overview //! -------- //! //! It comes with a high level wrapper [LepTess](struct.LepTess.html) focusing on productivity and //! memory safty: //! //! ```rust,no_run //! let mut lt = leptess::LepTess::new(Some("./tests/tessdata"), "eng").unwrap(); //! lt.set_image("./tests/di.png"); //! println!("{}", lt.get_utf8_text().unwrap()); //! ``` //! //! It also exposes low level bindings to for flexibitliy and close mirroring of upstream C APIs: //! //! ```rust,no_run //! use std::path::Path; //! let mut api = leptess::tesseract::TessApi::new(Some("./tests/tessdata"), "eng").unwrap(); //! let mut pix = leptess::leptonica::pix_read(Path::new("./tests/di.png")).unwrap(); //! api.set_image(&pix); //! //! let text = api.get_utf8_text(); //! println!("{}", text.unwrap()); //! ``` //! //! Raw unsafe C API [bindings](capi/index.html) are auto-generated using bindgen. To update the //! binding, run: //! //! ```bash //! make gen //! ``` //! //! Build dependencies //! ------------------ //! //! Make sure you have Leptonica and Tesseract installed. //! //! For Ubuntu user: //! //! ```bash //! sudo apt-get install libleptonica-dev libtesseract-dev //! ``` //! //! You will also need to install tesseract language data based on your OCR needs: //! //! ```bash //! sudo apt-get install tesseract-ocr-eng //! ``` pub mod capi; pub mod leptonica; pub mod tesseract; use std::path::Path; /// High level wrapper for Tesseract and Leptonica /// /// # Examples /// /// ## Full page OCR /// /// ``` /// let mut lt = leptess::LepTess::new(Some("./tests/tessdata"), "eng").unwrap(); /// lt.set_image("./tests/di.png"); /// println!("{}", lt.get_utf8_text().unwrap()); /// ``` /// /// ## OCR on a specific region of the image /// /// ``` /// # let mut lt = leptess::LepTess::new(Some("./tests/tessdata"), "eng").unwrap(); /// # lt.set_image("./tests/di.png"); /// lt.set_rectangle(&leptess::leptonica::Box::new( /// 10, 10, 200, 60, /// ).unwrap()); /// println!("{}", lt.get_utf8_text().unwrap()); /// ``` /// /// ## Iterate bounding boxes for each recognized word /// /// ``` /// # let mut lt = leptess::LepTess::new(None, "eng").unwrap(); /// # lt.set_image("./tests/di.png"); /// let boxes = lt.get_component_boxes( /// leptess::capi::TessPageIteratorLevel_RIL_WORD, /// true, /// ).unwrap(); /// /// for b in &boxes { /// println!("{:?}", b.get_val()); /// } /// ``` pub struct LepTess { tess_api: tesseract::TessApi, } impl LepTess { pub fn new(data_path: Option<&str>, lang: &str) -> Result<LepTess, tesseract::TessInitError> { Ok(LepTess { tess_api: tesseract::TessApi::new(data_path, lang)? }) } /// Set image to use for OCR. pub fn set_image(&mut self, img_uri: &str) -> bool { // TODO: support more uri scheme, default to file:// let path = Path::new(img_uri); let re = leptonica::pix_read(path); match re { Some(pix) => { self.tess_api.set_image(&pix); true } None => false, } } pub fn recognize(&self) -> i32 { self.tess_api.recognize() } /// Restrict OCR to a specific region of the image. pub fn set_rectangle<'a, 'b>(&'a mut self, b: &'b leptonica::Box) { self.tess_api.set_rectangle(b) } /// Extract text from current selected region of the image. By default, it is the full page. /// But it can be changed through [set_rectangle](struct.LepTess.html#method.set_rectangle) /// api. /// /// # Example /// /// ```no_run /// let mut lt = leptess::LepTess::new(None, "eng").unwrap(); /// lt.set_image("./tests/di.png"); /// println!("{}", lt.get_utf8_text().unwrap()); /// ``` pub fn get_utf8_text(&self) -> Result<String, std::str::Utf8Error> { self.tess_api.get_utf8_text() } pub fn mean_text_conf(&self) -> i32 { self.tess_api.mean_text_conf() } pub fn get_regions(&self) -> Option<leptonica::Boxa> { self.tess_api.get_regions() } /// Get the given level kind of components (block, textline, word etc.) as a leptonica-style /// Boxa, in reading order.If text_only is true, then only text components are returned. /// /// # Example /// /// ## Get word bounding boxes /// /// ```no_run /// let mut lt = leptess::LepTess::new(None, "eng").unwrap(); /// lt.set_image("./tests/di.png"); /// let boxes = lt.get_component_boxes( /// leptess::capi::TessPageIteratorLevel_RIL_WORD, /// true, /// ).unwrap(); /// /// for b in &boxes { /// println!("{:?}", b.get_val()); /// } /// ``` pub fn get_component_boxes( &self, level: capi::TessPageIteratorLevel, text_only: bool, ) -> Option<leptonica::Boxa> { self.tess_api.get_component_images(level, text_only) } }