SinaTools 0.1.24__py2.py3-none-any.whl → 0.1.25__py2.py3-none-any.whl

{SinaTools-0.1.24.dist-info → SinaTools-0.1.25.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: SinaTools
-Version: 0.1.24
+Version: 0.1.25
 Summary: Open-source Python toolkit for Arabic Natural Understanding, allowing people to integrate it in their system workflow.
 Home-page: https://github.com/SinaLab/sinatools
 License: MIT license

{SinaTools-0.1.24.dist-info → SinaTools-0.1.25.dist-info}/RECORD

@@ -1,5 +1,5 @@
-SinaTools-0.1.24.data/data/sinatools/environment.yml,sha256=OzilhLjZbo_3nU93EQNUFX-6G5O3newiSWrwxvMH2Os,7231
-sinatools/VERSION,sha256=S6iCAVLWhyRA7MIGZk5mjvtI6v6w1_bWDqhs5ui2fDk,6
+SinaTools-0.1.25.data/data/sinatools/environment.yml,sha256=OzilhLjZbo_3nU93EQNUFX-6G5O3newiSWrwxvMH2Os,7231
+sinatools/VERSION,sha256=ZC9GuKFeLfVc4onMU4koq0Nk_oc7Tx3zDdE0H4bcUKU,6
 sinatools/__init__.py,sha256=bEosTU1o-FSpyytS6iVP_82BXHF2yHnzpJxPLYRbeII,135
 sinatools/environment.yml,sha256=OzilhLjZbo_3nU93EQNUFX-6G5O3newiSWrwxvMH2Os,7231
 sinatools/install_env.py,sha256=EODeeE0ZzfM_rz33_JSIruX03Nc4ghyVOM5BHVhsZaQ,404
@@ -20,7 +20,7 @@ sinatools/CLI/utils/sentence_tokenizer.py,sha256=Wli8eiDbWSd_Z8UKpu_JkaS8jImowa1
 sinatools/CLI/utils/text_dublication_detector.py,sha256=dW70O5O20GxeUDDF6zVYn52wWLmJF-HBZgvqIeVL2rQ,1661
 sinatools/CLI/utils/text_transliteration.py,sha256=vz-3kxWf8pNYVCqNAtBAiA6u_efrS5NtWT-ofN1NX6I,2014
 sinatools/DataDownload/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-sinatools/DataDownload/downloader.py,sha256=sLmVvnr3mG_tqvGCggzxwsi2sixlKlgCbMnZhCclSpg,6390
+sinatools/DataDownload/downloader.py,sha256=F-SV-0mbYMYFSNCx8FoAYXhn0X1j0dF37PTLU0nUBVg,6482
 sinatools/arabert/__init__.py,sha256=ely2PttjgSv7vKdzskuD1rtK_l_UOpmxJSz8isrveD0,16
 sinatools/arabert/preprocess.py,sha256=qI0FsuMTOzdRlYGCtLrjpXgikNElUZPv9bnjaKDZKJ4,33024
 sinatools/arabert/arabert/__init__.py,sha256=KbSAH-XqbRygn0y59m5-ZYOLXgpT1gSgE3F-qd4rKEc,627
@@ -113,10 +113,10 @@ sinatools/wsd/__init__.py,sha256=yV-SQSCzSrjbNkciMbDCqzGZ_EESchL7rlJk56uibVI,309
 sinatools/wsd/disambiguator.py,sha256=8HrVAGpEQyrzwiuEreLX9X82WSL-U2Aeca0ttrtIw2Y,19998
 sinatools/wsd/settings.py,sha256=6XflVTFKD8SVySX9Wj7zYQtV26WDTcQ2-uW8-gDNHKE,747
 sinatools/wsd/wsd.py,sha256=gHIBUFXegoY1z3rRnIlK6TduhYq2BTa_dHakOjOlT4k,4434
-SinaTools-0.1.24.dist-info/AUTHORS.rst,sha256=aTWeWlIdfLi56iLJfIUAwIrmqDcgxXKLji75_Fjzjyg,174
-SinaTools-0.1.24.dist-info/LICENSE,sha256=uwsKYG4TayHXNANWdpfMN2lVW4dimxQjA_7vuCVhD70,1088
-SinaTools-0.1.24.dist-info/METADATA,sha256=TS_IfzeMqZsoClo4KPnnhsTHbuo8sWNBXB2ByHkrY_M,953
-SinaTools-0.1.24.dist-info/WHEEL,sha256=6T3TYZE4YFi2HTS1BeZHNXAi8N52OZT4O-dJ6-ome_4,116
-SinaTools-0.1.24.dist-info/entry_points.txt,sha256=ZwZLolnWog2fjdDrfaHNHob8SE_YtMbD6ayzsOzItxs,1234
-SinaTools-0.1.24.dist-info/top_level.txt,sha256=8tNdPTeJKw3TQCaua8IJIx6N6WpgZZmVekf1OdBNJpE,10
-SinaTools-0.1.24.dist-info/RECORD,,
+SinaTools-0.1.25.dist-info/AUTHORS.rst,sha256=aTWeWlIdfLi56iLJfIUAwIrmqDcgxXKLji75_Fjzjyg,174
+SinaTools-0.1.25.dist-info/LICENSE,sha256=uwsKYG4TayHXNANWdpfMN2lVW4dimxQjA_7vuCVhD70,1088
+SinaTools-0.1.25.dist-info/METADATA,sha256=0tDl5B000Z0gvhNCSzdlOzfyC0YQrP2uSZSm4OEP_EQ,953
+SinaTools-0.1.25.dist-info/WHEEL,sha256=6T3TYZE4YFi2HTS1BeZHNXAi8N52OZT4O-dJ6-ome_4,116
+SinaTools-0.1.25.dist-info/entry_points.txt,sha256=ZwZLolnWog2fjdDrfaHNHob8SE_YtMbD6ayzsOzItxs,1234
+SinaTools-0.1.25.dist-info/top_level.txt,sha256=8tNdPTeJKw3TQCaua8IJIx6N6WpgZZmVekf1OdBNJpE,10
+SinaTools-0.1.25.dist-info/RECORD,,

sinatools/DataDownload/downloader.py

@@ -95,37 +95,41 @@ def download_file(url, dest_path=get_appdatadir()):
     print(filename)
     headers = {'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/58.0.3029.110 Safari/537.3'}
 
-    # try:
-    with requests.get(url, headers=headers, stream=True) as r:
-        r.raise_for_status()
-        with open(file_path, 'wb') as f:
-            total_size = int(r.headers.get('content-length', 0))
-            block_size = 8192
-            progress_bar = tqdm(total=total_size, unit='iB', unit_scale=True)
-            for chunk in r.iter_content(chunk_size=block_size):
-                if chunk:
-                    f.write(chunk)
-                    progress_bar.update(len(chunk))
-            progress_bar.close()
-    # Check the file type and extract accordingly
-    file_extension = os.path.splitext(file_path)[1]
-    extracted_folder_name = os.path.splitext(file_path)[0]
-    
-    if file_extension == '.zip':
-        extract_zip(file_path, extracted_folder_name)
-    elif file_extension == '.gz':
-        extract_tar(file_path, extracted_folder_name)
-    elif file_extension =='.pickle':
-        print(f'Done: {file_extension}')
-    else:
-        print(f'Unsupported file type for extraction: {file_extension}')
-    return file_path
-
-    # except requests.exceptions.HTTPError as e:
-        # if e.response.status_code == 403:
-            # print(f'Error 403: Forbidden. The requested file URL {url} could not be downloaded due to insufficient permissions. Please check the URL and try again.')
-        # else:
-            # print('An error occurred while downloading the file:', e)
+    try:
+        with requests.get(url, headers=headers, stream=True) as r:
+            r.raise_for_status()
+            with open(file_path, 'wb') as f:
+                total_size = int(r.headers.get('content-length', 0))
+                block_size = 8192
+                progress_bar = tqdm(total=total_size, unit='iB', unit_scale=True)
+                for chunk in r.iter_content(chunk_size=block_size):
+                    if chunk:
+                        f.write(chunk)
+                        progress_bar.update(len(chunk))
+                progress_bar.close()
+
+        # Check the file type and extract accordingly
+        file_extension = os.path.splitext(file_path)[1]
+        extracted_folder_name = os.path.splitext(file_path)[0]
+        
+        if file_extension == '.zip':
+            extract_zip(file_path, extracted_folder_name)
+        elif file_extension == '.gz':
+
+            extract_tar(file_path, extracted_folder_name)
+        elif file_extension =='.pickle':
+            print(f'Done: {file_extension}')
+
+        else:
+            print(f'Unsupported file type for extraction: {file_extension}')
+
+        return file_path
+
+    except requests.exceptions.HTTPError as e:
+        if e.response.status_code == 403:
+            print(f'Error 403: Forbidden. The requested file URL {url} could not be downloaded due to insufficient permissions. Please check the URL and try again.')
+        else:
+            print('An error occurred while downloading the file:', e)
 
 def extract_zip(file_path, extracted_folder_name):
     """

sinatools/VERSION

@@ -1 +1 @@
-0.1.24
+0.1.25