ddi-fw 0.0.18__py3-none-any.whl → 0.0.20__py3-none-any.whl

ddi_fw/drugbank/drugbank_processor.py

@@ -67,12 +67,12 @@ class DrugBankProcessor():
         return external_identifier_list
 
     def process(self,
+                ner_data_path,
                 input_path='drugs',
                 output_path='output',
                 save_as_sql=True,
                 db_path=r"./drugbank.db",
-                zip_outputs=True,
-                ner_data_path):
+                zip_outputs=True):
         if not os.path.exists(output_path):
             os.makedirs(output_path)
         ner_df = CTakesNER().load(ner_data_path)

ddi_fw/utils/zip_helper.py

@@ -15,6 +15,18 @@ class ZipHelper:
         with z.ZipFile(f'{output_path}/{name}.zip', 'w', compression=z.ZIP_LZMA, compresslevel=z.ZIP_LZMA) as zipObj:
             zipObj.write(file_path, basename(file_path))
 
+    def zip_as_multipart(self, name, file_path,output_path, chunk_size):
+        self.zip_single_file(name,file_path, output_path+"/parts")
+        with open(file_path, 'rb') as f:
+            chunk_number = 1
+            while True:
+                chunk = f.read(chunk_size)
+                if not chunk:
+                    break
+                with open(f"{file_path}.part{chunk_number:03}", 'wb') as chunk_file:
+                    chunk_file.write(chunk)
+                chunk_number += 1
+
     def zip(self, zip_prefix, input_path, output_path, chunk_size):
         files_paths = [input_path+'/' + p for p in os.listdir(input_path)]
         count_of_chunks = math.ceil(len(files_paths) / chunk_size)
@@ -50,6 +62,15 @@ class ZipHelper:
                     z1.extractall(path=output_path)
                     print(f'{file_path} has been extracted')
 
+    def extract_multiparts(self, output_path, parts_path):
+        input_parts = [parts_path+'/' + p for p in os.listdir(parts_path)]
+        with open(output_file, 'wb') as outfile:
+            for part in input_parts:
+                with open(part, 'rb') as infile:
+                    outfile.write(infile.read())
+        self.extract(parts_path,output_path)
+        
+
 
 # if __name__ == "__main__":
 #     helper = ZipHelper()
@@ -63,4 +84,4 @@ class ZipHelper:
     # df = pd.DataFrame(data=d)
     # df.to_pickle('test/dataframe.pickle')
     # helper.zip_single_file(file_path='test/dataframe.pickle',output_path='test/output', name='zip')
-    # helper.extract(input_path='test/output', output_path='test/output')
+    # helper.extract(input_path='test/output', output_path='test/output')

{ddi_fw-0.0.18.dist-info → ddi_fw-0.0.20.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: ddi_fw
-Version: 0.0.18
+Version: 0.0.20
 Summary: Do not use :)
 Author-email: Kıvanç Bayraktar <bayraktarkivanc@gmail.com>
 Maintainer-email: Kıvanç Bayraktar <bayraktarkivanc@gmail.com>
@@ -22,6 +22,7 @@ Classifier: Topic :: Scientific/Engineering :: Information Analysis
 Classifier: Topic :: Scientific/Engineering :: Medical Science Apps.
 Requires-Python: >=3.8
 Description-Content-Type: text/markdown
+Requires-Dist: python-stopwatch
 Requires-Dist: importlib-resources
 Requires-Dist: lxml
 Requires-Dist: matplotlib

{ddi_fw-0.0.18.dist-info → ddi_fw-0.0.20.dist-info}/RECORD

@@ -53,7 +53,7 @@ ddi_fw/datasets/mdf_sa_ddi/indexes/validation_fold_4.txt,sha256=STKdpjRqA0Vi63RJ
 ddi_fw/drugbank/__init__.py,sha256=4_eKdZsnXUSJyr-TZpHwIn13JC6PqS5imeLJJbgt2-A,94
 ddi_fw/drugbank/drugbank.xsd,sha256=y-WzMHANyzmf5T_0ywlMOq63ft9uW41B5I1WfBKbh9c,43306
 ddi_fw/drugbank/drugbank_parser.py,sha256=lxUuhB0s8ef_aPNDs0V8ClKF7-KIWugNIV9gVsRvzrw,5610
-ddi_fw/drugbank/drugbank_processor.py,sha256=7I6YYnIagqm7tZGrRHAKTq9QoCxg5R3oS0CgjsyzMBY,18127
+ddi_fw/drugbank/drugbank_processor.py,sha256=vmkt68n9nFLevufgGyXhOSDtTo4G1XzwT9PVncGTXtk,18127
 ddi_fw/drugbank/drugbank_processor_org.py,sha256=eO5Yset50P91qkic79RUXPoEuxRxQKFkKW0l4G29Mas,13322
 ddi_fw/drugbank/event_extractor.py,sha256=6odoZohhK7OdLF-LF0l-5BFq0_NMG_5jrFJbHrBXsI8,4600
 ddi_fw/experiments/__init__.py,sha256=UJwd2i3QcuaI1YjC_2yGCiLuEMTT5Yo7rDFxw89chIw,108
@@ -78,8 +78,8 @@ ddi_fw/test/type_guarding_test.py,sha256=KxjyBxohDu7lwpejalCj-REjtJ-k1S1wQbOB6TG
 ddi_fw/utils/__init__.py,sha256=nhNU_sEp55xsZ5VtvhozjKg6r4GWP6SJI13v8F_jbCg,217
 ddi_fw/utils/enums.py,sha256=19eJ3fX5eRK_xPvkYcukmug144jXPH4X9zQqtsFBj5A,671
 ddi_fw/utils/utils.py,sha256=Na6Y8mY-CFbQjrgd9xC8agcrjVvTj_7KIXqFm1H_3qU,3549
-ddi_fw/utils/zip_helper.py,sha256=DjtwcGBoYw8zOP-Ye5OxzeR1OgN3WfNkVx85nb0wbJA,2635
-ddi_fw-0.0.18.dist-info/METADATA,sha256=tE1vK0fU12Rww6VOIqBShgWFPDqf-tndbEXF6YNkHlk,1508
-ddi_fw-0.0.18.dist-info/WHEEL,sha256=cVxcB9AmuTcXqmwrtPhNK88dr7IR_b6qagTj0UvIEbY,91
-ddi_fw-0.0.18.dist-info/top_level.txt,sha256=PMwHICFZTZtcpzQNPV4UQnfNXYIeLR_Ste-Wfc1h810,7
-ddi_fw-0.0.18.dist-info/RECORD,,
+ddi_fw/utils/zip_helper.py,sha256=Rwpgslpea8HKCr6Q9yML9t6HbiyUcX5VlWnyBGMWcCQ,3528
+ddi_fw-0.0.20.dist-info/METADATA,sha256=hKr40hLqVDLM3Tvn-Y0_0gLSphtCH3PW3Q0Aeho5ShM,1541
+ddi_fw-0.0.20.dist-info/WHEEL,sha256=cVxcB9AmuTcXqmwrtPhNK88dr7IR_b6qagTj0UvIEbY,91
+ddi_fw-0.0.20.dist-info/top_level.txt,sha256=PMwHICFZTZtcpzQNPV4UQnfNXYIeLR_Ste-Wfc1h810,7
+ddi_fw-0.0.20.dist-info/RECORD,,