fix(ocr): use PSM integer values directly instead of constructor (#2578)

* fix(ocr): use PSM integer values directly instead of constructor

- Use integer psm value directly instead of calling tesserocr.PSM()
- Fixed in both main_psm and script_readers initialization
- tesserocr.PSM is a class with integer constants, not an enum

Fixes #2576

* DCO Remediation Commit for mulgyeol <[email protected]>

I, mulgyeol <[email protected]>, hereby add my Signed-off-by to this commit: da63a17

Signed-off-by: mulgyeol <[email protected]>

---------

Signed-off-by: mulgyeol <[email protected]>

Author: Mulgyeol

docling/models/tesseract_ocr_model.py

@@ -97,9 +97,7 @@ def __init__(
 
             # Set main OCR reader with configurable PSM
             main_psm = (
-                tesserocr.PSM(self.options.psm)
-                if self.options.psm is not None
-                else tesserocr.PSM.AUTO
+                self.options.psm if self.options.psm is not None else tesserocr.PSM.AUTO
             )
             if lang == "auto":
                 self.reader = tesserocr.PyTessBaseAPI(psm=main_psm, **tesserocr_kwargs)
@@ -195,7 +193,7 @@ def __call__(
                                         tesserocr.PyTessBaseAPI(
                                             path=self.reader.GetDatapath(),
                                             lang=lang,
-                                            psm=tesserocr.PSM(self.options.psm)
+                                            psm=self.options.psm
                                             if self.options.psm is not None
                                             else tesserocr.PSM.AUTO,
                                             init=True,

tests/test_e2e_ocr_conversion.py

@@ -63,6 +63,7 @@ def test_e2e_conversions():
         (TesseractOcrOptions(), True),
         (TesseractCliOcrOptions(), True),
         (EasyOcrOptions(), False),
+        (TesseractOcrOptions(psm=3), True),
         (TesseractOcrOptions(force_full_page_ocr=True), True),
         (TesseractOcrOptions(force_full_page_ocr=True, lang=["auto"]), True),
         (TesseractCliOcrOptions(force_full_page_ocr=True), True),