ddi-fw 0.0.27__py3-none-any.whl → 0.0.28__py3-none-any.whl

ddi_fw/utils/__init__.py

@@ -1,3 +1,4 @@
 from .utils import create_folder_if_not_exists, utc_time_as_string,utc_time_as_string_simple_format, compress_and_save_data
 from .zip_helper import ZipHelper
+from .py7zr_helper import Py7ZipHelper
 from .enums import UMLSCodeTypes, DrugBankTextDataTypes

ddi_fw/utils/py7zr_helper.py

@@ -0,0 +1,100 @@
+from collections import defaultdict
+import math
+import py7zr
+import os
+from os.path import basename
+
+
+class Py7ZipHelper:
+    def __init__(self):
+        pass
+
+    def create_archive_from_file(self, archive_name, file_path, output_path):
+        with py7zr.SevenZipFile(output_path+'/'+archive_name, 'w') as archive:
+            # for file in files_to_archive:
+            archive.write(file_path)
+
+    def create_archive_from_folder(self, archive_name, folder_path, output_path):
+        with py7zr.SevenZipFile(output_path+'/'+archive_name, 'w') as archive:
+            for root, dirs, files in os.walk(folder_path):
+                for file in files:
+                    archive.write(os.path.join(root, file),
+                                  os.path.relpath(os.path.join(root, file),
+                                                  os.path.join(folder_path, '..')))
+                    # archive.write(root+"/"+file)
+
+    def create_archive_multiparts(self, zip_name, file_path, output_path, chunk_size):
+        parent_folder = os.path.dirname(file_path)
+
+        # parts_path = f"{parent_folder}/parts"
+        # create_folder_if_not_exists(parts_path)
+        # file_name, file_extension = os.path.splitext(file_path)
+        # file_name = os.path.basename(file_path)
+        # file_name, folder = get_file_name_and_folder(file_path)
+
+        if os.path.isdir(file_path):
+            self.create_archive_from_folder(zip_name, file_path, output_path)
+        elif os.path.isfile(file_path):
+            self.create_archive_from_file(zip_name, file_path, output_path)
+        else:
+            return
+        with open(output_path+'/'+zip_name, 'rb') as f:
+            chunk_number = 1
+            while True:
+                chunk = f.read(chunk_size)
+                if not chunk:
+                    break
+                with open(f"{output_path}/{zip_name}.part{chunk_number:03}", 'wb') as chunk_file:
+                    chunk_file.write(chunk)
+                chunk_number += 1
+        if os.path.exists(output_path+'/'+zip_name):
+            os.remove(output_path+'/'+zip_name)
+
+    def create_archive(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)
+        zero_padding_length = len(str(int(count_of_chunks))) + 2
+
+        if not os.path.exists(output_path):
+            os.makedirs(output_path)
+
+        part = 1
+        i = 0
+        zip_dict = defaultdict(list)
+        for filePath in files_paths:
+            padded_part = f'{part}'.zfill(zero_padding_length)
+            key = f'{zip_prefix}.{padded_part}'
+            zip_dict[key].append(filePath)
+            i += 1
+            if i % chunk_size == 0:
+                i = 0
+                part += 1
+
+        for key, value in zip_dict.items():
+            with py7zr.SevenZipFile(f'{output_path}/{key}.7z', 'w') as archive:
+                for file_path in value:
+                    archive.write(file_path, basename(file_path))
+
+    def extract(self, input_path, output_path):
+        files_paths = [input_path+'/' + p for p in os.listdir(input_path)]
+        if not os.path.exists(output_path):
+            os.makedirs(output_path)
+        for file_path in files_paths:
+            if file_path.endswith('7z'):
+                with py7zr.SevenZipFile(file_path, 'r') as z1:
+                    z1.extractall(path=output_path)
+                    print(f'{file_path} has been extracted')
+
+    def extract_archive(self, archive_name, extract_path):
+        with py7zr.SevenZipFile(archive_name, 'r') as archive:
+            archive.extractall(path=extract_path)
+
+    def extract_multiparts(self, input_path, output_path, output_file):
+        parts = [input_path+'/' + p for p in os.listdir(input_path)]
+        # create_folder_if_not_exists(output_path)
+        with open(f"{output_path}/{output_file}", 'wb') as outfile:
+            for part in parts:
+                with open(part, 'rb') as infile:
+                    outfile.write(infile.read())
+        self.extract_archive(f"{output_path}/{output_file}", output_path)
+        os.remove(f"{output_path}/{output_file}")

ddi_fw/utils/zip_helper.py

@@ -58,7 +58,7 @@ class ZipHelper:
                 chunk = f.read(chunk_size)
                 if not chunk:
                     break
-                with open(f"{output_path}/{zip_name}.part{chunk_number:03}.zip", 'wb') as chunk_file:
+                with open(f"{output_path}/{zip_name}.zip.part{chunk_number:03}", 'wb') as chunk_file:
                     chunk_file.write(chunk)
                 chunk_number += 1
         if os.path.exists(output_path+'/'+zip_name+'.zip'):

{ddi_fw-0.0.27.dist-info → ddi_fw-0.0.28.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: ddi_fw
-Version: 0.0.27
+Version: 0.0.28
 Summary: Do not use :)
 Author-email: Kıvanç Bayraktar <bayraktarkivanc@gmail.com>
 Maintainer-email: Kıvanç Bayraktar <bayraktarkivanc@gmail.com>
@@ -40,4 +40,5 @@ Requires-Dist: tokenizers
 Requires-Dist: tqdm
 Requires-Dist: xmlschema
 Requires-Dist: zipp
+Requires-Dist: py7zr
 

{ddi_fw-0.0.27.dist-info → ddi_fw-0.0.28.dist-info}/RECORD

@@ -75,11 +75,12 @@ ddi_fw/test/sklearn-tfidf.py,sha256=cjtg27vLskEMXgrsqUR_EapRGVd4xgwOQ9zYsu72zjs,
 ddi_fw/test/test.py,sha256=zJh9ZBcZl-vZIFDvuftcRrRV8WAwtiFVhPPd6Et4OU4,2997
 ddi_fw/test/torch_cuda_test.py,sha256=R-4VGVErl_Ufk54DoZbgL_YXWoCYFyanIVWd6P39IEk,312
 ddi_fw/test/type_guarding_test.py,sha256=KxjyBxohDu7lwpejalCj-REjtJ-k1S1wQbOB6TGY0O8,766
-ddi_fw/utils/__init__.py,sha256=nhNU_sEp55xsZ5VtvhozjKg6r4GWP6SJI13v8F_jbCg,217
+ddi_fw/utils/__init__.py,sha256=cbvKldLWGINnVWIVwRQ04zdJpqOf-Ci9X03I8OgmJcw,257
 ddi_fw/utils/enums.py,sha256=19eJ3fX5eRK_xPvkYcukmug144jXPH4X9zQqtsFBj5A,671
+ddi_fw/utils/py7zr_helper.py,sha256=c3itu4YwcnHX4gwxKd-7v3q50cz4doyJwHUEQnHR7zM,4305
 ddi_fw/utils/utils.py,sha256=Na6Y8mY-CFbQjrgd9xC8agcrjVvTj_7KIXqFm1H_3qU,3549
-ddi_fw/utils/zip_helper.py,sha256=9BzT5jnpqtiEprV8sI-fIz-2-og-8o2wlifSXPp_jv0,5479
-ddi_fw-0.0.27.dist-info/METADATA,sha256=xq1C1HN_BnaimD50kcijGFTqDR9HjGmb1a_2QsXPu5I,1541
-ddi_fw-0.0.27.dist-info/WHEEL,sha256=cVxcB9AmuTcXqmwrtPhNK88dr7IR_b6qagTj0UvIEbY,91
-ddi_fw-0.0.27.dist-info/top_level.txt,sha256=PMwHICFZTZtcpzQNPV4UQnfNXYIeLR_Ste-Wfc1h810,7
-ddi_fw-0.0.27.dist-info/RECORD,,
+ddi_fw/utils/zip_helper.py,sha256=7HHxOVAeltxRfNNtQPGojCAo7WiypWg_aVMR4NSj0Ys,5479
+ddi_fw-0.0.28.dist-info/METADATA,sha256=fxaezPvDWpy98dSdPTnF-PCK0HJFfBbOm2IHCuo5r5k,1563
+ddi_fw-0.0.28.dist-info/WHEEL,sha256=5Mi1sN9lKoFv_gxcPtisEVrJZihrm_beibeg5R6xb4I,91
+ddi_fw-0.0.28.dist-info/top_level.txt,sha256=PMwHICFZTZtcpzQNPV4UQnfNXYIeLR_Ste-Wfc1h810,7
+ddi_fw-0.0.28.dist-info/RECORD,,

{ddi_fw-0.0.27.dist-info → ddi_fw-0.0.28.dist-info}/WHEEL

@@ -1,5 +1,5 @@
 Wheel-Version: 1.0
-Generator: setuptools (74.1.2)
+Generator: setuptools (75.0.0)
 Root-Is-Purelib: true
 Tag: py3-none-any