fix: Refactor the TesseractOcrModel and TesseractOcrCliModel to validate if the auto-detected

language is installed in the system and if not fall back to a default option without language.

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

docling/models/tesseract_ocr_cli_model.py

@@ -30,11 +30,13 @@ class TesseractOcrCliModel(BaseOcrModel):
 
         self._name: Optional[str] = None
         self._version: Optional[str] = None
-        self._script_prefix = None
+        self._tesseract_languages: Optional[List[str]] = None
+        self._script_prefix: Optional[str] = None
 
         if self.enabled:
             try:
                 self._get_name_and_version()
+                self._set_languages_and_prefix()
 
             except Exception as exc:
                 raise RuntimeError(
@@ -119,8 +121,10 @@ class TesseractOcrCliModel(BaseOcrModel):
 
     def _detect_language(self, ifilename: str):
         r"""
-        Run tesseract in PSM 0 mode to detect the document language
+        Run tesseract in PSM 0 mode to detect the language
         """
+        assert self._tesseract_languages is not None
+
         cmd = [self.options.tesseract_cmd]
         cmd.extend(["--psm", "0", "-l", "osd", ifilename, "stdout"])
         _log.info("command: {}".format(" ".join(cmd)))
@@ -134,36 +138,43 @@ class TesseractOcrCliModel(BaseOcrModel):
         if len(scripts) == 0:
             _log.warning("Tesseract cannot detect the script of the page")
             return None
+
         script = map_tesseract_script(scripts[0].strip())
+        lang = f"{self._script_prefix}{script}"
+
+        # Check if the detected language has been installed
+        if lang not in self._tesseract_languages:
+            msg = f"Tesseract detected the script '{script}' and language '{lang}'."
+            msg += " However this language is not installed in your system and will be ignored."
+            _log.warning(msg)
+            return None
 
-        # Translate the script into language
-        script_prefix = self._get_script_prefix()
-        lang = f"{script_prefix}{script}"
         _log.debug(
-            f'Using tesseract model for the detected script "{script}" and language "{lang}"'
+            f"Using tesseract model for the detected script '{script}' and language '{lang}'"
         )
-
         return lang
 
-    def _get_script_prefix(self) -> str:
-        if self._script_prefix is not None:
-            return self._script_prefix
-
+    def _set_languages_and_prefix(self):
+        r"""
+        Read and set the languages installed in tesseract and decide the script prefix
+        """
         # Get all languages
         cmd = [self.options.tesseract_cmd]
         cmd.append("--list-langs")
+        _log.info("command: {}".format(" ".join(cmd)))
         proc = Popen(cmd, stdout=PIPE, stderr=DEVNULL)
         output, _ = proc.communicate()
         decoded_data = output.decode("utf-8")
         df = pd.read_csv(io.StringIO(decoded_data), header=None)
-        all_languages = df[0].tolist()[1:]
+        self._tesseract_languages = df[0].tolist()[1:]
 
         # Decide the script prefix
-        if any([l.startswith("script/") for l in all_languages]):
+        if any([l.startswith("script/") for l in self._tesseract_languages]):
             script_prefix = "script/"
         else:
             script_prefix = ""
-        return script_prefix
+
+        self._script_prefix = script_prefix
 
     def __call__(
         self, conv_res: ConversionResult, page_batch: Iterable[Page]
@@ -179,7 +190,6 @@ class TesseractOcrCliModel(BaseOcrModel):
                 yield page
             else:
                 with TimeRecorder(conv_res, "ocr"):
-
                     ocr_rects = self.get_ocr_rects(page)
 
                     all_ocr_cells = []

docling/models/tesseract_ocr_model.py

@@ -21,6 +21,7 @@ class TesseractOcrModel(BaseOcrModel):
 
         self.scale = 3  # multiplier for 72 dpi == 216 dpi.
         self.reader = None
+        self.osd_reader = None
 
         if self.enabled:
             install_errmsg = (
@@ -48,8 +49,8 @@ class TesseractOcrModel(BaseOcrModel):
             except:
                 raise ImportError(install_errmsg)
 
-            _, tesserocr_languages = tesserocr.get_languages()
-            if not tesserocr_languages:
+            _, self._tesserocr_languages = tesserocr.get_languages()
+            if not self._tesserocr_languages:
                 raise ImportError(missing_langs_errmsg)
 
             # Initialize the tesseractAPI
@@ -58,7 +59,7 @@ class TesseractOcrModel(BaseOcrModel):
 
             self.script_readers: dict[str, tesserocr.PyTessBaseAPI] = {}
 
-            if any([l.startswith("script/") for l in tesserocr_languages]):
+            if any([l.startswith("script/") for l in self._tesserocr_languages]):
                 self.script_prefix = "script/"
             else:
                 self.script_prefix = ""
@@ -73,14 +74,14 @@ class TesseractOcrModel(BaseOcrModel):
                 tesserocr_kwargs["path"] = self.options.path
 
             if lang == "auto":
-                self.reader = tesserocr.PyTessBaseAPI(
+                self.reader = tesserocr.PyTessBaseAPI(**tesserocr_kwargs)
+                self.osd_reader = tesserocr.PyTessBaseAPI(
                     **{"lang": "osd", "psm": tesserocr.PSM.OSD_ONLY} | tesserocr_kwargs
                 )
             else:
                 self.reader = tesserocr.PyTessBaseAPI(
                     **{"lang": lang} | tesserocr_kwargs,
                 )
-
             self.reader_RIL = tesserocr.RIL
 
     def __del__(self):
@@ -97,8 +98,6 @@ class TesseractOcrModel(BaseOcrModel):
             yield from page_batch
             return
 
-        import tesserocr
-
         for page in page_batch:
             assert page._backend is not None
             if not page._backend.is_valid():
@@ -106,6 +105,7 @@ class TesseractOcrModel(BaseOcrModel):
             else:
                 with TimeRecorder(conv_res, "ocr"):
                     assert self.reader is not None
+                    assert self._tesserocr_languages is not None
 
                     ocr_rects = self.get_ocr_rects(page)
 
@@ -118,11 +118,12 @@ class TesseractOcrModel(BaseOcrModel):
                             scale=self.scale, cropbox=ocr_rect
                         )
 
-                        # Retrieve text snippets with their bounding boxes
-                        self.reader.SetImage(high_res_image)
+                        local_reader = self.reader
+                        if "auto" in self.options.lang:
+                            assert self.osd_reader is not None
 
-                        if self.options.lang == ["auto"]:
-                            osd = self.reader.DetectOrientationScript()
+                            self.osd_reader.SetImage(high_res_image)
+                            osd = self.osd_reader.DetectOrientationScript()
 
                             # No text, probably
                             if osd is None:
@@ -130,24 +131,29 @@ class TesseractOcrModel(BaseOcrModel):
 
                             script = osd["script_name"]
                             script = map_tesseract_script(script)
-                            _log.debug(
-                                f'Using model for the detected script "{script}"'
-                            )
+                            lang = f"{self.script_prefix}{script}"
 
-                            if script not in self.script_readers:
-                                self.script_readers[script] = tesserocr.PyTessBaseAPI(
-                                    path=self.reader.GetDatapath(),
-                                    lang=f"{self.script_prefix}{script}",
-                                    psm=tesserocr.PSM.AUTO,
-                                    init=True,
-                                    oem=tesserocr.OEM.DEFAULT,
-                                )
+                            # Check if the detected languge is present in the system
+                            if lang not in self._tesserocr_languages:
+                                msg = f"Tesseract detected the script '{script}' and language '{lang}'."
+                                msg += " However this language is not installed in your system and will be ignored."
+                                _log.warning(msg)
+                            else:
+                                if script not in self.script_readers:
+                                    import tesserocr
 
-                            local_reader = self.script_readers[script]
-                            local_reader.SetImage(high_res_image)
-                        else:
-                            local_reader = self.reader
+                                    self.script_readers[script] = (
+                                        tesserocr.PyTessBaseAPI(
+                                            path=self.reader.GetDatapath(),
+                                            lang=lang,
+                                            psm=tesserocr.PSM.AUTO,
+                                            init=True,
+                                            oem=tesserocr.OEM.DEFAULT,
+                                        )
+                                    )
+                                local_reader = self.script_readers[script]
 
+                        local_reader.SetImage(high_res_image)
                         boxes = local_reader.GetComponentImages(
                             self.reader_RIL.TEXTLINE, True
                         )

docs/examples/tesseract_lang_detection.py

@@ -16,7 +16,9 @@ def main():
     # ocr_options = TesseractOcrOptions(lang=["auto"])
     ocr_options = TesseractCliOcrOptions(lang=["auto"])
 
-    pipeline_options = PdfPipelineOptions(do_ocr=True, ocr_options=ocr_options)
+    pipeline_options = PdfPipelineOptions(
+        do_ocr=True, force_full_page_ocr=True, ocr_options=ocr_options
+    )
 
     converter = DocumentConverter(
         format_options={