feat(RapidOcr): Support generic extra arguments for RapidOcr (#2266)

* feat: add support for additional parameters in RapidOcrOptions and fix RapidOcr font_path * DCO Remediation Commit for David Morady <29502285+dmorady1@users.noreply.github.com> I, David Morady <29502285+dmorady1@users.noreply.github.com>, hereby add my Signed-off-by to this commit: 133d989060 Signed-off-by: David Morady <29502285+dmorady1@users.noreply.github.com> * fix: RapidOcr ensure backwards compatibility and add deprecation note * add warning log for rec_font_path * DCO Remediation Commit for David Morady <29502285+dmorady1@users.noreply.github.com> I, David Morady <29502285+dmorady1@users.noreply.github.com>, hereby add my Signed-off-by to this commit: 133d989060 I, David Morady <29502285+dmorady1@users.noreply.github.com>, hereby add my Signed-off-by to this commit: 0a65eed28a I, David Morady <29502285+dmorady1@users.noreply.github.com>, hereby add my Signed-off-by to this commit: ac96f1483f Signed-off-by: David Morady <29502285+dmorady1@users.noreply.github.com> * add tests for code coverage for rapidocr * DCO Remediation Commit for David Morady <29502285+dmorady1@users.noreply.github.com> I, David Morady <29502285+dmorady1@users.noreply.github.com>, hereby add my Signed-off-by to this commit: 133d989060 I, David Morady <29502285+dmorady1@users.noreply.github.com>, hereby add my Signed-off-by to this commit: 0a65eed28a I, David Morady <29502285+dmorady1@users.noreply.github.com>, hereby add my Signed-off-by to this commit: ac96f1483f I, David Morady <29502285+dmorady1@users.noreply.github.com>, hereby add my Signed-off-by to this commit: af5df4bb30 Signed-off-by: David Morady <29502285+dmorady1@users.noreply.github.com> * add small comment for test * DCO Remediation Commit for David Morady <29502285+dmorady1@users.noreply.github.com> I, David Morady <29502285+dmorady1@users.noreply.github.com>, hereby add my Signed-off-by to this commit: 133d989060 I, David Morady <29502285+dmorady1@users.noreply.github.com>, hereby add my Signed-off-by to this commit: 0a65eed28a I, David Morady <29502285+dmorady1@users.noreply.github.com>, hereby add my Signed-off-by to this commit: ac96f1483f I, David Morady <29502285+dmorady1@users.noreply.github.com>, hereby add my Signed-off-by to this commit: af5df4bb30 I, David Morady <29502285+dmorady1@users.noreply.github.com>, hereby add my Signed-off-by to this commit: ab893b637f Signed-off-by: David Morady <29502285+dmorady1@users.noreply.github.com> * fix test comment * DCO Remediation Commit for David Morady <29502285+dmorady1@users.noreply.github.com> I, David Morady <29502285+dmorady1@users.noreply.github.com>, hereby add my Signed-off-by to this commit: 133d989060 I, David Morady <29502285+dmorady1@users.noreply.github.com>, hereby add my Signed-off-by to this commit: 0a65eed28a I, David Morady <29502285+dmorady1@users.noreply.github.com>, hereby add my Signed-off-by to this commit: ac96f1483f I, David Morady <29502285+dmorady1@users.noreply.github.com>, hereby add my Signed-off-by to this commit: af5df4bb30 I, David Morady <29502285+dmorady1@users.noreply.github.com>, hereby add my Signed-off-by to this commit: ab893b637f I, David Morady <29502285+dmorady1@users.noreply.github.com>, hereby add my Signed-off-by to this commit: 028e332aa9 Signed-off-by: David Morady <29502285+dmorady1@users.noreply.github.com> --------- Signed-off-by: David Morady <29502285+dmorady1@users.noreply.github.com>
2025-12-08 12:48:28 +00:00 · 2025-09-16 07:26:10 +02:00
parent ad2f738231
commit 0e95171dd6
3 changed files with 52 additions and 26 deletions
--- a/docling/datamodel/pipeline_options.py
+++ b/docling/datamodel/pipeline_options.py
@@ -114,7 +114,11 @@ class RapidOcrOptions(OcrOptions):
    cls_model_path: Optional[str] = None  # same default as rapidocr
    rec_model_path: Optional[str] = None  # same default as rapidocr
    rec_keys_path: Optional[str] = None  # same default as rapidocr
-    rec_font_path: Optional[str] = None  # same default as rapidocr
+    rec_font_path: Optional[str] = None  # Deprecated, please use font_path instead
+    font_path: Optional[str] = None  # same default as rapidocr
+
+    # Dictionary to overwrite or pass-through additional parameters
+    rapidocr_params: Dict[str, Any] = Field(default_factory=dict)

    model_config = ConfigDict(
        extra="forbid",
--- a/docling/models/rapid_ocr_model.py
+++ b/docling/models/rapid_ocr_model.py
@@ -62,32 +62,44 @@ class RapidOcrModel(BaseOcrModel):
            }
            backend_enum = _ALIASES.get(self.options.backend, EngineType.ONNXRUNTIME)

+            params = {
+                # Global settings (these are still correct)
+                "Global.text_score": self.options.text_score,
+                "Global.font_path": self.options.font_path,
+                # "Global.verbose": self.options.print_verbose,
+                # Detection model settings
+                "Det.model_path": self.options.det_model_path,
+                "Det.use_cuda": use_cuda,
+                "Det.use_dml": use_dml,
+                "Det.intra_op_num_threads": intra_op_num_threads,
+                # Classification model settings
+                "Cls.model_path": self.options.cls_model_path,
+                "Cls.use_cuda": use_cuda,
+                "Cls.use_dml": use_dml,
+                "Cls.intra_op_num_threads": intra_op_num_threads,
+                # Recognition model settings
+                "Rec.model_path": self.options.rec_model_path,
+                "Rec.font_path": self.options.rec_font_path,
+                "Rec.keys_path": self.options.rec_keys_path,
+                "Rec.use_cuda": use_cuda,
+                "Rec.use_dml": use_dml,
+                "Rec.intra_op_num_threads": intra_op_num_threads,
+                "Det.engine_type": backend_enum,
+                "Cls.engine_type": backend_enum,
+                "Rec.engine_type": backend_enum,
+            }
+
+            if self.options.rec_font_path is not None:
+                _log.warning(
+                    "The 'rec_font_path' option for RapidOCR is deprecated. Please use 'font_path' instead."
+                )
+            user_params = self.options.rapidocr_params
+            if user_params:
+                _log.debug("Overwriting RapidOCR params with user-provided values.")
+                params.update(user_params)
+
            self.reader = RapidOCR(
-                params={
-                    # Global settings (these are still correct)
-                    "Global.text_score": self.options.text_score,
-                    # "Global.verbose": self.options.print_verbose,
-                    # Detection model settings
-                    "Det.model_path": self.options.det_model_path,
-                    "Det.use_cuda": use_cuda,
-                    "Det.use_dml": use_dml,
-                    "Det.intra_op_num_threads": intra_op_num_threads,
-                    # Classification model settings
-                    "Cls.model_path": self.options.cls_model_path,
-                    "Cls.use_cuda": use_cuda,
-                    "Cls.use_dml": use_dml,
-                    "Cls.intra_op_num_threads": intra_op_num_threads,
-                    # Recognition model settings
-                    "Rec.model_path": self.options.rec_model_path,
-                    "Rec.font_path": self.options.rec_font_path,
-                    "Rec.keys_path": self.options.rec_keys_path,
-                    "Rec.use_cuda": use_cuda,
-                    "Rec.use_dml": use_dml,
-                    "Rec.intra_op_num_threads": intra_op_num_threads,
-                    "Det.engine_type": backend_enum,
-                    "Cls.engine_type": backend_enum,
-                    "Rec.engine_type": backend_enum,
-                }
+                params=params,
            )

    def __call__(
--- a/tests/test_e2e_ocr_conversion.py
+++ b/tests/test_e2e_ocr_conversion.py
@@ -74,6 +74,16 @@ def test_e2e_conversions():
    if sys.version_info < (3, 13):
        engines.append((RapidOcrOptions(), False))
        engines.append((RapidOcrOptions(force_full_page_ocr=True), False))
+        engines.append(
+            (
+                RapidOcrOptions(
+                    force_full_page_ocr=True,
+                    rec_font_path="test",
+                    rapidocr_params={"Rec.font_path": None},  # overwrites rec_font_path
+                ),
+                False,
+            )
+        )

    # only works on mac
    if "darwin" == sys.platform: