Merge pull request #1 from prateekmedia/add-psm-rust

feat: add psm for rust parser

src/rust/src/args.rs

@@ -596,7 +596,26 @@ pub struct Args {
     /// Tesseract v3 : default mode is 0,
     /// Tesseract v4 : default mode is 1.
     #[arg(long, verbatim_doc_comment, value_name="mode", help_heading=OUTPUT_AFFECTING_OUTPUT_FILES)]
-    pub oem: Option<i32>,
+    pub oem: Option<u8>,
+    /// Select the PSM mode for Tesseract.
+    /// Available Page segmentation modes:
+    /// 0    Orientation and script detection (OSD) only.
+    /// 1    Automatic page segmentation with OSD.
+    /// 2    Automatic page segmentation, but no OSD, or OCR.
+    /// 3    Fully automatic page segmentation, but no OSD. (Default)
+    /// 4    Assume a single column of text of variable sizes.
+    /// 5    Assume a single uniform block of vertically aligned text.
+    /// 6    Assume a single uniform block of text.
+    /// 7    Treat the image as a single text line.
+    /// 8    Treat the image as a single word.
+    /// 9    Treat the image as a single word in a circle.
+    /// 10    Treat the image as a single character.
+    /// 11    Sparse text. Find as much text as possible in no particular order.
+    /// 12    Sparse text with OSD.
+    /// 13    Raw line. Treat the image as a single text line,
+    /// bypassing hacks that are Tesseract-specific.
+    #[arg(long, verbatim_doc_comment, value_name="mode", help_heading=OUTPUT_AFFECTING_OUTPUT_FILES)]
+    pub psm: Option<u8>,
     /// For MKV subtitles, select which language's caption
     /// stream will be processed. e.g. 'eng' for English.
     /// Language codes can be either the 3 letters bibliographic

src/rust/src/common.rs

@@ -843,6 +843,7 @@ pub struct CcxOptions {
     pub dvblang: Option<String>,
     pub ocrlang: Option<String>,
     pub ocr_oem: i32,
+    pub psm: i32,
     pub ocr_quantmode: i32,
     pub mkvlang: Option<String>,
     pub analyze_video_stream: bool,
@@ -950,6 +951,7 @@ impl Default for CcxOptions {
             ocrlang: None,
             ocr_oem: -1,
             ocr_quantmode: 1,
+            psm: 3,
             mkvlang: None,
             analyze_video_stream: false,
             hardsubx_ocr_mode: 0,

src/rust/src/parser.rs

@@ -753,7 +753,15 @@ impl CcxOptions {
                 println!("Invalid oem value");
                 std::process::exit(ExitCode::MalformedParameter as i32);
             }
-            self.ocr_oem = *oem;
+            self.ocr_oem = *oem as _;
+        }
+
+        if let Some(ref psm) = args.psm {
+            if !(0..=13).contains(psm) {
+                println!("--psm must be between 0 and 13");
+                std::process::exit(ExitCode::MalformedParameter as i32);
+            }
+            self.psm = *psm as _;
         }
 
         if let Some(ref lang) = args.mkvlang {