Add support for set_page_seg_mode (#36)

* Add support for set_page_seg_mode

#33

* Add final new line to python file

Author: ccouzens

Cargo.toml

@@ -1,6 +1,6 @@
 [package]
 name          = "tesseract"
-version       = "0.12.1"
+version       = "0.13.0"
 authors       = ["Kevin Kwok <[email protected]>", "Chris Couzens <[email protected]>"]
 documentation = "https://docs.rs/tesseract"
 repository    = "https://github.com/antimatter15/tesseract-rs"
@@ -11,5 +11,5 @@ categories    = ["api-bindings", "multimedia::images"]
 
 [dependencies]
 tesseract-sys = "~0.5"
-tesseract-plumbing = "~0.8"
+tesseract-plumbing = "~0.9"
 thiserror = "1.0"

Makefile

@@ -0,0 +1,2 @@
+src/page_seg_mode.rs: page-seg-modes.txt build_page_seg_modes.py
+	python build_page_seg_modes.py < page-seg-modes.txt | rustfmt > $@

build_page_seg_modes.py

@@ -0,0 +1,53 @@
+import sys
+from itertools import islice
+
+class PageSegMode:
+    def __init__(self, name, comment):
+        self.name = name
+        self.comment = comment
+    
+    def name_as_enum(self):
+        return ''.join(n.capitalize() for n in self.name.split("_"))
+    
+    def name_as_variable(self):
+        return 'tesseract_sys::TessPageSegMode_' + self.name
+
+name = None
+page_seg_modes = []
+i = 0;
+
+for line in islice(sys.stdin, 1, None):
+    if i == 0:
+        name = line.rstrip('\n')
+    elif i == 1:
+        comment = line.rstrip('\n')
+        page_seg_mode = PageSegMode(name, comment)
+        page_seg_modes.append(page_seg_mode)
+    i = (i + 1) % 3
+
+print("// ⚠️ This file is generated")
+print("// ⚠️ Regenerate with `make src/page_seg_mode.rs`")
+print()
+print("use tesseract_sys::TessPageSegMode;")
+print()
+print("/// Enum representing different PageSegMode options accepted by Tesseract")
+print("#[derive(Debug, Clone, Copy, PartialEq, Eq)]")
+print("pub enum PageSegMode {")
+
+for page_seg_mode in page_seg_modes:
+    print(f"    /// {page_seg_mode.comment}")
+    print(f"    {page_seg_mode.name_as_enum()},",)
+
+print("}")
+print()
+print("impl PageSegMode {")
+print("    /// Get the page-seg-mode's value as used by Tesseract")
+print("    pub fn as_tess_page_seg_mode(&self) -> TessPageSegMode {")
+print("        match self {")
+
+for page_seg_mode in page_seg_modes:
+    print(f"            PageSegMode::{page_seg_mode.name_as_enum()} => {page_seg_mode.name_as_variable()},")
+
+print("        }")
+print("    }")
+print("}")

page-seg-modes.txt

@@ -0,0 +1,42 @@
+# Copied from https://tesseract-ocr.github.io/tessapi/5.x/a01818.html#a338d4c8b5d497b5ec3e6e4269d8ac66aab76fe3ca390d99e070ea60b892ee18ef
+PSM_OSD_ONLY 	
+Orientation and script detection only.
+
+PSM_AUTO_OSD 	
+Automatic page segmentation with orientation and script detection. (OSD)
+
+PSM_AUTO_ONLY 	
+Automatic page segmentation, but no OSD, or OCR.
+
+PSM_AUTO 	
+Fully automatic page segmentation, but no OSD.
+
+PSM_SINGLE_COLUMN 	
+Assume a single column of text of variable sizes.
+
+PSM_SINGLE_BLOCK_VERT_TEXT 	
+Assume a single uniform block of vertically aligned text.
+
+PSM_SINGLE_BLOCK 	
+Assume a single uniform block of text. (Default.)
+
+PSM_SINGLE_LINE 	
+Treat the image as a single text line.
+
+PSM_SINGLE_WORD 	
+Treat the image as a single word.
+
+PSM_CIRCLE_WORD 	
+Treat the image as a single word in a circle.
+
+PSM_SINGLE_CHAR 	
+Treat the image as a single character.
+
+PSM_SPARSE_TEXT 	
+Find as much text as possible in no particular order.
+
+PSM_SPARSE_TEXT_OSD 	
+Sparse text with orientation and script det.
+
+PSM_RAW_LINE 	
+Treat the image as a single text line, bypassing hacks that are Tesseract-specific.

src/lib.rs

@@ -7,6 +7,9 @@ use std::ffi::CString;
 use std::ffi::NulError;
 use std::os::raw::c_int;
 use std::str;
+mod page_seg_mode;
+
+pub use page_seg_mode::PageSegMode;
 
 use self::tesseract_sys::{
     TessOcrEngineMode, TessOcrEngineMode_OEM_DEFAULT, TessOcrEngineMode_OEM_LSTM_ONLY,
@@ -214,6 +217,10 @@ impl Tesseract {
             .to_string_lossy()
             .into_owned())
     }
+
+    pub fn set_page_seg_mode(&mut self, mode: PageSegMode) {
+        self.0.set_page_seg_mode(mode.as_tess_page_seg_mode());
+    }
 }
 
 pub fn ocr(filename: &str, language: &str) -> Result<String, TesseractError> {

src/page_seg_mode.rs

@@ -0,0 +1,61 @@
+// ⚠️ This file is generated
+// ⚠️ Regenerate with `make src/page_seg_mode.rs`
+
+use tesseract_sys::TessPageSegMode;
+
+/// Enum representing different PageSegMode options accepted by Tesseract
+#[derive(Debug, Clone, Copy, PartialEq, Eq)]
+pub enum PageSegMode {
+    /// Orientation and script detection only.
+    PsmOsdOnly,
+    /// Automatic page segmentation with orientation and script detection. (OSD)
+    PsmAutoOsd,
+    /// Automatic page segmentation, but no OSD, or OCR.
+    PsmAutoOnly,
+    /// Fully automatic page segmentation, but no OSD.
+    PsmAuto,
+    /// Assume a single column of text of variable sizes.
+    PsmSingleColumn,
+    /// Assume a single uniform block of vertically aligned text.
+    PsmSingleBlockVertText,
+    /// Assume a single uniform block of text. (Default.)
+    PsmSingleBlock,
+    /// Treat the image as a single text line.
+    PsmSingleLine,
+    /// Treat the image as a single word.
+    PsmSingleWord,
+    /// Treat the image as a single word in a circle.
+    PsmCircleWord,
+    /// Treat the image as a single character.
+    PsmSingleChar,
+    /// Find as much text as possible in no particular order.
+    PsmSparseText,
+    /// Sparse text with orientation and script det.
+    PsmSparseTextOsd,
+    /// Treat the image as a single text line, bypassing hacks that are Tesseract-specific.
+    PsmRawLine,
+}
+
+impl PageSegMode {
+    /// Get the page-seg-mode's value as used by Tesseract
+    pub fn as_tess_page_seg_mode(&self) -> TessPageSegMode {
+        match self {
+            PageSegMode::PsmOsdOnly => tesseract_sys::TessPageSegMode_PSM_OSD_ONLY,
+            PageSegMode::PsmAutoOsd => tesseract_sys::TessPageSegMode_PSM_AUTO_OSD,
+            PageSegMode::PsmAutoOnly => tesseract_sys::TessPageSegMode_PSM_AUTO_ONLY,
+            PageSegMode::PsmAuto => tesseract_sys::TessPageSegMode_PSM_AUTO,
+            PageSegMode::PsmSingleColumn => tesseract_sys::TessPageSegMode_PSM_SINGLE_COLUMN,
+            PageSegMode::PsmSingleBlockVertText => {
+                tesseract_sys::TessPageSegMode_PSM_SINGLE_BLOCK_VERT_TEXT
+            }
+            PageSegMode::PsmSingleBlock => tesseract_sys::TessPageSegMode_PSM_SINGLE_BLOCK,
+            PageSegMode::PsmSingleLine => tesseract_sys::TessPageSegMode_PSM_SINGLE_LINE,
+            PageSegMode::PsmSingleWord => tesseract_sys::TessPageSegMode_PSM_SINGLE_WORD,
+            PageSegMode::PsmCircleWord => tesseract_sys::TessPageSegMode_PSM_CIRCLE_WORD,
+            PageSegMode::PsmSingleChar => tesseract_sys::TessPageSegMode_PSM_SINGLE_CHAR,
+            PageSegMode::PsmSparseText => tesseract_sys::TessPageSegMode_PSM_SPARSE_TEXT,
+            PageSegMode::PsmSparseTextOsd => tesseract_sys::TessPageSegMode_PSM_SPARSE_TEXT_OSD,
+            PageSegMode::PsmRawLine => tesseract_sys::TessPageSegMode_PSM_RAW_LINE,
+        }
+    }
+}