From 24dfd8b2b2d688cfe6b44c9e4893a34a4840109a Mon Sep 17 00:00:00 2001
From: littletomatodonkey <dazhiningsibuqu@163.com>
Date: Sat, 19 Sep 2020 12:06:23 +0000
Subject: [PATCH] fix whl doc and add multi-language

---
 doc/doc_ch/whl.md    |  4 +++-
 doc/doc_en/whl_en.md |  4 ++++
 paddleocr.py         | 25 +++++++++++++++++++++++--
 3 files changed, 30 insertions(+), 3 deletions(-)

diff --git a/doc/doc_ch/whl.md b/doc/doc_ch/whl.md
index 657f9837..46796ce6 100644
--- a/doc/doc_ch/whl.md
+++ b/doc/doc_ch/whl.md
@@ -19,7 +19,9 @@ pip install dist/paddleocr-x.x.x-py3-none-any.whl # x.x.x是paddleocr的版本
 * 检测+分类+识别全流程
 ```python
 from paddleocr import PaddleOCR, draw_ocr
-ocr = PaddleOCR(use_angle_cls=True) # need to run only once to download and load model into memory
+# Paddleocr目前支持中英文、英文、法语、德语、韩语、日语，可以通过修改lang参数进行切换
+# 参数依次为`zh`, `en`, `french`, `german`, `korean`, `japan`。
+ocr = PaddleOCR(use_angle_cls=True, lang="ch") # need to run only once to download and load model into memory
 img_path = 'PaddleOCR/doc/imgs/11.jpg'
 result = ocr.ocr(img_path, cls=True)
 for line in result:
diff --git a/doc/doc_en/whl_en.md b/doc/doc_en/whl_en.md
index b62e5454..4049d9dc 100644
--- a/doc/doc_en/whl_en.md
+++ b/doc/doc_en/whl_en.md
@@ -17,12 +17,16 @@ pip install dist/paddleocr-x.x.x-py3-none-any.whl # x.x.x is the version of padd
 * detection classification and recognition
 ```python
 from paddleocr import PaddleOCR,draw_ocr
+# Paddleocr supports Chinese, English, French, German, Korean and Japanese.
+# You can set the parameter `lang` as `zh`, `en`, `french`, `german`, `korean`, `japan`
+# to switch the language model in order.
 ocr = PaddleOCR(use_angle_cls=True, lang='en') # need to run only once to download and load model into memory
 img_path = 'PaddleOCR/doc/imgs_en/img_12.jpg'
 result = ocr.ocr(img_path, cls=True)
 for line in result:
     print(line)
 
+
 # draw result
 from PIL import Image
 image = Image.open(img_path).convert('RGB')
diff --git a/paddleocr.py b/paddleocr.py
index 55ca87ac..7e9b2402 100644
--- a/paddleocr.py
+++ b/paddleocr.py
@@ -46,6 +46,26 @@ model_urls = {
             'url':
             'https://paddleocr.bj.bcebos.com/20-09-22/mobile/en/en_ppocr_mobile_v1.1_rec_infer.tar',
             'dict_path': './ppocr/utils/ic15_dict.txt'
+        },
+        'french': {
+            'url':
+            'https://paddleocr.bj.bcebos.com/20-09-22/mobile/fr/french_ppocr_mobile_v1.1_rec_infer.tar',
+            'dict_path': './ppocr/utils/french_dict.txt'
+        },
+        'german': {
+            'url':
+            'https://paddleocr.bj.bcebos.com/20-09-22/mobile/ge/german_ppocr_mobile_v1.1_rec_infer.tar',
+            'dict_path': './ppocr/utils/german_dict.txt'
+        },
+        'korean': {
+            'url':
+            'https://paddleocr.bj.bcebos.com/20-09-22/mobile/kr/korean_ppocr_mobile_v1.1_rec_infer.tar',
+            'dict_path': './ppocr/utils/korean_dict.txt'
+        },
+        'japan': {
+            'url':
+            'https://paddleocr.bj.bcebos.com/20-09-22/mobile/jp/japan_ppocr_mobile_v1.1_rec_infer.tar',
+            'dict_path': './ppocr/utils/japan_dict.txt'
         }
     },
     'cls':
@@ -165,8 +185,9 @@ class PaddleOCR(predict_system.TextSystem):
         postprocess_params.__dict__.update(**kwargs)
         self.use_angle_cls = postprocess_params.use_angle_cls
         lang = postprocess_params.lang
-        assert lang in model_urls['rec'], 'param lang must in {}'.format(
-            model_urls['rec'].keys())
+        assert lang in model_urls[
+            'rec'], 'param lang must in {}, but got {}'.format(
+                model_urls['rec'].keys(), lang)
         if postprocess_params.rec_char_dict_path is None:
             postprocess_params.rec_char_dict_path = model_urls['rec'][lang][
                 'dict_path']
-- 
GitLab