fix(rapidocr): complete parsing parameters

python/demo.py

@@ -5,27 +5,13 @@ import cv2
 
 from rapidocr import RapidOCR, VisRes
 
-# from rapidocr_onnxruntime import RapidOCR, VisRes
-# from rapidocr_torch import RapidOCR, VisRes
-
-# from rapidocr_paddle import RapidOCR, VisRes
-# from rapidocr_openvino import RapidOCR, VisRes
-
-# yaml_path = "tests/test_files/config.yaml"
-# engine = RapidOCR(config_path=yaml_path)
-
-# engine = engine = RapidOCR(
-#     params={"Global.with_onnx": True, "EngineConfig.onnxruntime.use_cuda": True}
-# )
-# engine = RapidOCR(params={"Global.with_torch": True, "Global.lang": "ch"})
-engine = RapidOCR(params={"Global.with_openvino": True, "Global.lang_rec": "ch_server"})
+engine = RapidOCR(params={"Global.with_openvino": True})
 vis = VisRes()
 
 image_path = "tests/test_files/ch_en_num.jpg"
 with open(image_path, "rb") as f:
     img = f.read()
 
-# result, elapse_list = engine(img, use_det=True, use_cls=False, use_rec=False)
 result = engine(img, return_word_box=True)
 print(result)
 print(result.elapse)

python/rapidocr/main.py

@@ -351,12 +351,12 @@ def main(arg_list: Optional[List[str]] = None):
             vis_img = vis(args.img_path, words_boxes, words, words_scores)
             save_path = cur_dir / f"{Path(args.img_path).stem}_vis_single.png"
             cv2.imwrite(str(save_path), vis_img)
-            print("The vis single result has saved in %s", save_path)
+            print(f"The vis single result has saved in {save_path}")
         else:
             save_path = cur_dir / f"{Path(args.img_path).stem}_vis.png"
             vis_img = vis(args.img_path, result.boxes, result.txts, result.scores)
             cv2.imwrite(str(save_path), vis_img)
-            print("The vis result has saved in %s", save_path)
+            print(f"The vis result has saved in {save_path}")
 
 
 if __name__ == "__main__":

python/rapidocr/utils/parse_parameters.py

@@ -122,119 +122,20 @@ class ParseLang:
             return "devanagari"
 
         if lang in ["ch", "en"]:
-            return
+            pass
 
         raise ValueError(f"lang: {lang} is not in the supported list.")
 
 
-def parse_lang(lang):
-    latin_lang = [
-        "af",
-        "az",
-        "bs",
-        "cs",
-        "cy",
-        "da",
-        "de",
-        "es",
-        "et",
-        "fr",
-        "ga",
-        "hr",
-        "hu",
-        "id",
-        "is",
-        "it",
-        "ku",
-        "la",
-        "lt",
-        "lv",
-        "mi",
-        "ms",
-        "mt",
-        "nl",
-        "no",
-        "oc",
-        "pi",
-        "pl",
-        "pt",
-        "ro",
-        "rs_latin",
-        "sk",
-        "sl",
-        "sq",
-        "sv",
-        "sw",
-        "tl",
-        "tr",
-        "uz",
-        "vi",
-        "french",
-        "german",
-    ]
-    arabic_lang = ["ar", "fa", "ug", "ur"]
-    cyrillic_lang = [
-        "ru",
-        "rs_cyrillic",
-        "be",
-        "bg",
-        "uk",
-        "mn",
-        "abq",
-        "ady",
-        "kbd",
-        "ava",
-        "dar",
-        "inh",
-        "che",
-        "lbe",
-        "lez",
-        "tab",
-    ]
-    devanagari_lang = [
-        "hi",
-        "mr",
-        "ne",
-        "bh",
-        "mai",
-        "ang",
-        "bho",
-        "mah",
-        "sck",
-        "new",
-        "gom",
-        "sa",
-        "bgc",
-    ]
-    if lang in latin_lang:
-        lang = "latin"
-    elif lang in arabic_lang:
-        lang = "arabic"
-    elif lang in cyrillic_lang:
-        lang = "cyrillic"
-    elif lang in devanagari_lang:
-        lang = "devanagari"
-    elif lang in ["ch", "en"]:
-        pass
-    else:
-        raise ValueError(f"lang: {lang} is not in the supported list.")
-
-    if lang == "ch":
-        det_lang = "ch"
-    elif lang in ["en", "latin"]:
-        det_lang = "en"
-    else:
-        det_lang = "Multilingual"
-
-    return det_lang, lang
-
-
 class ParseParams(OmegaConf):
     def __init__(self):
         pass
 
     @classmethod
     def update_batch(cls, cfg: DictConfig, params: Dict[str, str]) -> DictConfig:
+        global_keys = list(OmegaConf.to_container(cfg.Global).keys())
         for k, v in params.items():
+            if k.startswith("Global") and k.split(".")[1] not in global_keys:
+                raise ValueError(f"{k} is not a valid key.")
             cls.update(cfg, k, v)
         return cfg

python/requirements.txt

@@ -6,4 +6,5 @@ Shapely>=1.7.1,!=2.0.4  # python3.12 2.0.4 bug
 PyYAML
 Pillow
 onnxruntime>=1.7.0
-tqdm
+tqdm
+omegaconf

python/tests/test_main.py

@@ -79,11 +79,11 @@ def test_error_lang():
 
 
 def test_lang():
-    engine = get_engine(params={"Global.lang": "en"})
+    engine = get_engine(params={"Global.lang_rec": "en_mobile"})
     img_path = tests_dir / "en.jpg"
     result = engine(img_path)
     assert result.txts is not None
-    assert result.txts[0] == "MovieShots Dataset"
+    assert result.txts[0] == "3"
 
 
 def test_engine_openvino():