feat(OCR): Introduce support for the language path in the pipelines of both Tesseract OCR engines.

Signed-off-by: Nikos Livathinos <nli@zurich.ibm.com>

docling/datamodel/pipeline_options.py

@@ -40,6 +40,7 @@ class TesseractOcrOptions(OcrOptions):
     kind: Literal["tesseract"] = "tesseract"
     lang: List[str] = ["fra", "deu", "spa", "eng"]
     tesseract_cmd: str = "tesseract"
+    path: Optional[str] = None
 
     model_config = ConfigDict(
         extra="forbid",
@@ -49,6 +50,7 @@ class TesseractOcrOptions(OcrOptions):
 class TesserOcrOptions(OcrOptions):
     kind: Literal["tesserocr"] = "tesserocr"
     lang: List[str] = ["fra", "deu", "spa", "eng"]
+    path: Optional[str] = None
 
     model_config = ConfigDict(
         extra="forbid",

docling/models/tesseract_model.py

@@ -67,12 +67,16 @@ class TesseractOcrModel(BaseOcrModel):
 
         return name, version
 
-    def _run_tesseract(self, ifilename, languages=None):
+    def _run_tesseract(self, ifilename: str):
 
         cmd = [self.options.tesseract_cmd]
 
-        if languages:
-            cmd += ["-l", "+".join(languages)]
+        if self.options.lang is not None and len(self.options.lang) > 0:
+            cmd.append("-l")
+            cmd.append("+".join(self.options.lang))
+        if self.options.path is not None:
+            cmd.append("--tessdata-dir")
+            cmd.append(self.options.path)
 
         cmd += [ifilename, "stdout", "tsv"]
         _log.info("command: {}".format(" ".join(cmd)))

docling/models/tesserocr_model.py

@@ -39,8 +39,20 @@ class TesserOcrModel(BaseOcrModel):
 
             # Initialize the tesseractAPI
             lang = "+".join(self.options.lang)
+            if self.options.path is not None:
                 self.reader = tesserocr.PyTessBaseAPI(
-                lang=lang, psm=tesserocr.PSM.AUTO, init=True, oem=tesserocr.OEM.DEFAULT
+                    path=self.options.path,
+                    lang=lang,
+                    psm=tesserocr.PSM.AUTO,
+                    init=True,
+                    oem=tesserocr.OEM.DEFAULT,
+                )
+            else:
+                self.reader = tesserocr.PyTessBaseAPI(
+                    lang=lang,
+                    psm=tesserocr.PSM.AUTO,
+                    init=True,
+                    oem=tesserocr.OEM.DEFAULT,
                 )
             self.reader_RIL = tesserocr.RIL