zipFly64 1.2.0__tar.gz → 1.2.3__tar.gz

{zipfly64-1.2.0/src/zipFly64.egg-info → zipfly64-1.2.3}/PKG-INFO

@@ -1,6 +1,6 @@
-Metadata-Version: 2.2
+Metadata-Version: 2.4
 Name: zipFly64
-Version: 1.2.0
+Version: 1.2.3
 Summary: Stream zip64 archives on the fly.
 Author: Pamparampampam
 License: MIT License
@@ -33,6 +33,7 @@ Requires-Python: >=3.7
 Description-Content-Type: text/markdown
 License-File: LICENSE
 Requires-Dist: aiofiles>=24.1.0
+Dynamic: license-file
 
 # ZipFly
 
@@ -64,6 +65,7 @@ Generating ZIPs on-demand in a web server is a typical use case for zipFly.**
 - Only 1 dependency
 - Automatic detection and changing of duplicate names
 - `Zip64` format compatible files
+- **21.37%** test coverage
 
 
 This library is based upon [this library](https://github.com/kbbdy/zipstream) <sub>_(this library was a piece of work...)_<sub>
@@ -91,8 +93,7 @@ with open("out/file.zip", 'wb') as f_out:
     for chunk in zipFly.stream():
         f_out.write(chunk)
 ```
-> [!CAUTION]
-> You mustn't reuse `ZipFly` instances. They should be re-created everytime you call `stream()` or `async_stream()`
+
 
 ### Supports dynamically created files
 ```py
@@ -106,7 +107,7 @@ def file_generator():
     
 # size is optional, it allows to calculate the total size of the archive before any data is generated
 # modification_time in epoch time, defaults to time.time()
-file1 = GenFile(name="file.txt", generator=lambda: file_generator(), modification_time=time.time(), size=size, compression_method=consts.COMPRESSION_DEFLATE)
+file1 = GenFile(name="file.txt", generator=file_generator(), modification_time=time.time(), size=size, compression_method=consts.COMPRESSION_DEFLATE)
 file2 = LocalFile(file_path='files/as61aade2ebfd.mp4', compression_method=consts.NO_COMPRESSION) #  or consts.COMPRESSION_DEFLATE 
 
 files = [file1, file2]
@@ -126,7 +127,7 @@ for chunk in zipFly.stream():
 ```py
 import asyncio
 from zipFly import ZipFly, LocalFile, consts, GenFile
-file1 = GenFile(name="file.txt", generator=lambda: file_generator())
+file1 = GenFile(name="file.txt", generator=file_generator())
 file2 = LocalFile(file_path='public/2ae9dcd01a3aa.mp4', name="files/my_file2.mp4")
 
 files = [file1, file2]
@@ -153,12 +154,10 @@ If you use `LocalFile` then it's not a problem as it can very fast go tru the en
 
 ```py
 
-file1 = GenFile(name="file.txt", generator=lambda: file_generator(), crc=crc)
+file1 = GenFile(name="file.txt", generator=file_generator(), crc=crc)
 file2 = LocalFile(file_path='public/2ae9dcd01a3aa.mp4', name="files/my_file2.mp4")
-files = [file1, file2]
-
-zipFly1 = ZipFly(files)
-zipFly2 = ZipFly(files)
+files1 = [file1, file2]
+zipFly1 = ZipFly(files1)
 
 # Simulating pause/resume
 STOP_BYTE = 300
@@ -173,7 +172,13 @@ async def async_save_pause():
             byte_offset += len(chunk)
             if byte_offset >= STOP_BYTE:
                 break
-            
+                
+# Later...                
+file3 = GenFile(name="file.txt", generator=file_generator(), crc=crc)
+file4 = LocalFile(file_path='public/2ae9dcd01a3aa.mp4', name="files/my_file2.mp4")
+files2 = [file3, file4]
+zipFly2 = ZipFly(files2)
+
 async def async_save_resume():
     with open("out/file.zip", 'ab') as f_out: # Append mode
         async for chunk in zipFly2.async_stream(byte_offset=STOP_BYTE):
@@ -190,16 +195,33 @@ If resume ZipFly instance has diffrent files than pause ZipFly instance there wi
 > [!NOTE]  
 > For byte offset mode to work you must use `const.NO_COMPRESSION` and specify `crc` for `GenFile`
 
+> [!CAUTION]
+> You mustn't reuse `ZipFly` instances. They should be re-created everytime you call `stream()` or `async_stream()`
+
+> [!CAUTION]
+> You mustn't reuse `GenFile` instances. 
 
 ### Other
 Python is not optimized for async I/O operations, thus to speed up the async streaming the chunk_size is changed to 4MB, you can override this by passing chunksize as argument to LocalFile.
 
-
-I created this library for my I Drive project.
+I created this library for my [iDrive](https://github.com/pam-param-pam/I-Drive) project.
 
 If you have a different use case scenario, and LocalFile and GenFile are not enough, you can extend BaseFile and everything else should work out of the box.
 
+If you extend `BaseFile` keep in mind that `zipFly` attempts to "deepcopy" files. It will successfully 
+deepcopy `LocalFile`, so LocalFile instances can be re-used. However, it will completely skip deep-coping any file 
+instance that has a generator.
+
+### Testing
 
+With [pytest](https://docs.pytest.org/en/stable/) and
+[pytest-asyncio](https://pytest-asyncio.readthedocs.io/en/stable/) installed,
+call `pytest` from the top-level directory (same as this `README.md`)
+to run tests.
+The 4GB tests are slow. If your machine has enough memory (~4GB free) and a fast
+disk/SSD, [pytest-xdist](https://pytest-xdist.readthedocs.io/en/stable/)
+can speed things up by running tests in parallel.
+Use it by calling `pytest -n auto`.
 
 ### PS
 

{zipfly64-1.2.0 → zipfly64-1.2.3}/README.md

@@ -28,6 +28,7 @@ Generating ZIPs on-demand in a web server is a typical use case for zipFly.**
 - Only 1 dependency
 - Automatic detection and changing of duplicate names
 - `Zip64` format compatible files
+- **21.37%** test coverage
 
 
 This library is based upon [this library](https://github.com/kbbdy/zipstream) <sub>_(this library was a piece of work...)_<sub>
@@ -55,8 +56,7 @@ with open("out/file.zip", 'wb') as f_out:
     for chunk in zipFly.stream():
         f_out.write(chunk)
 ```
-> [!CAUTION]
-> You mustn't reuse `ZipFly` instances. They should be re-created everytime you call `stream()` or `async_stream()`
+
 
 ### Supports dynamically created files
 ```py
@@ -70,7 +70,7 @@ def file_generator():
     
 # size is optional, it allows to calculate the total size of the archive before any data is generated
 # modification_time in epoch time, defaults to time.time()
-file1 = GenFile(name="file.txt", generator=lambda: file_generator(), modification_time=time.time(), size=size, compression_method=consts.COMPRESSION_DEFLATE)
+file1 = GenFile(name="file.txt", generator=file_generator(), modification_time=time.time(), size=size, compression_method=consts.COMPRESSION_DEFLATE)
 file2 = LocalFile(file_path='files/as61aade2ebfd.mp4', compression_method=consts.NO_COMPRESSION) #  or consts.COMPRESSION_DEFLATE 
 
 files = [file1, file2]
@@ -90,7 +90,7 @@ for chunk in zipFly.stream():
 ```py
 import asyncio
 from zipFly import ZipFly, LocalFile, consts, GenFile
-file1 = GenFile(name="file.txt", generator=lambda: file_generator())
+file1 = GenFile(name="file.txt", generator=file_generator())
 file2 = LocalFile(file_path='public/2ae9dcd01a3aa.mp4', name="files/my_file2.mp4")
 
 files = [file1, file2]
@@ -117,12 +117,10 @@ If you use `LocalFile` then it's not a problem as it can very fast go tru the en
 
 ```py
 
-file1 = GenFile(name="file.txt", generator=lambda: file_generator(), crc=crc)
+file1 = GenFile(name="file.txt", generator=file_generator(), crc=crc)
 file2 = LocalFile(file_path='public/2ae9dcd01a3aa.mp4', name="files/my_file2.mp4")
-files = [file1, file2]
-
-zipFly1 = ZipFly(files)
-zipFly2 = ZipFly(files)
+files1 = [file1, file2]
+zipFly1 = ZipFly(files1)
 
 # Simulating pause/resume
 STOP_BYTE = 300
@@ -137,7 +135,13 @@ async def async_save_pause():
             byte_offset += len(chunk)
             if byte_offset >= STOP_BYTE:
                 break
-            
+                
+# Later...                
+file3 = GenFile(name="file.txt", generator=file_generator(), crc=crc)
+file4 = LocalFile(file_path='public/2ae9dcd01a3aa.mp4', name="files/my_file2.mp4")
+files2 = [file3, file4]
+zipFly2 = ZipFly(files2)
+
 async def async_save_resume():
     with open("out/file.zip", 'ab') as f_out: # Append mode
         async for chunk in zipFly2.async_stream(byte_offset=STOP_BYTE):
@@ -154,16 +158,33 @@ If resume ZipFly instance has diffrent files than pause ZipFly instance there wi
 > [!NOTE]  
 > For byte offset mode to work you must use `const.NO_COMPRESSION` and specify `crc` for `GenFile`
 
+> [!CAUTION]
+> You mustn't reuse `ZipFly` instances. They should be re-created everytime you call `stream()` or `async_stream()`
+
+> [!CAUTION]
+> You mustn't reuse `GenFile` instances. 
 
 ### Other
 Python is not optimized for async I/O operations, thus to speed up the async streaming the chunk_size is changed to 4MB, you can override this by passing chunksize as argument to LocalFile.
 
-
-I created this library for my I Drive project.
+I created this library for my [iDrive](https://github.com/pam-param-pam/I-Drive) project.
 
 If you have a different use case scenario, and LocalFile and GenFile are not enough, you can extend BaseFile and everything else should work out of the box.
 
+If you extend `BaseFile` keep in mind that `zipFly` attempts to "deepcopy" files. It will successfully 
+deepcopy `LocalFile`, so LocalFile instances can be re-used. However, it will completely skip deep-coping any file 
+instance that has a generator.
+
+### Testing
 
+With [pytest](https://docs.pytest.org/en/stable/) and
+[pytest-asyncio](https://pytest-asyncio.readthedocs.io/en/stable/) installed,
+call `pytest` from the top-level directory (same as this `README.md`)
+to run tests.
+The 4GB tests are slow. If your machine has enough memory (~4GB free) and a fast
+disk/SSD, [pytest-xdist](https://pytest-xdist.readthedocs.io/en/stable/)
+can speed things up by running tests in parallel.
+Use it by calling `pytest -n auto`.
 
 ### PS
 

zipfly64-1.2.3/pyproject.toml

@@ -0,0 +1,116 @@
+# pyproject.toml
+
+[build-system]
+requires      = ["setuptools>=61.0.0", "wheel"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "zipFly64"
+version = "1.2.3"
+description = "Stream zip64 archives on the fly."
+readme = "README.md"
+authors = [{ name = "Pamparampampam" }]
+license = { file = "LICENSE" }
+classifiers = [
+    "License :: OSI Approved :: MIT License",
+    "Programming Language :: Python",
+    "Programming Language :: Python :: 3",
+]
+keywords = ["zip64", "zip", "streaming", "zipfly", "zipfly64"]
+dependencies = [
+    "aiofiles >= 24.1.0",
+]
+requires-python = ">=3.7"
+
+[project.urls]
+Github = "https://github.com/pam-param-pam/ZipFly"
+
+[tool.pytest.ini_options]
+minversion = "6.0"
+addopts = "-ra -q"
+testpaths = [
+    "tests",
+]
+markers = [
+    "slow: marks tests as slow (deselect with '-m \"not slow\"')",
+    "asyncio",
+]
+
+[tool.ruff]
+# Exclude a variety of commonly ignored directories.
+exclude = [
+    ".bzr",
+    ".direnv",
+    ".eggs",
+    ".git",
+    ".git-rewrite",
+    ".hg",
+    ".ipynb_checkpoints",
+    ".mypy_cache",
+    ".nox",
+    ".pants.d",
+    ".pyenv",
+    ".pytest_cache",
+    ".pytype",
+    ".ruff_cache",
+    ".svn",
+    ".tox",
+    ".venv",
+    ".vscode",
+    "__pypackages__",
+    "_build",
+    "buck-out",
+    "build",
+    "dist",
+    "node_modules",
+    "site-packages",
+    "venv",
+]
+
+line-length = 190
+indent-width = 4
+
+# Assume Python 3.9
+target-version = "py39"
+
+[tool.ruff.lint]
+# Enable Pyflakes (`F`) and a subset of the pycodestyle (`E`)  codes by default.
+# Unlike Flake8, Ruff doesn't enable pycodestyle warnings (`W`) or
+# McCabe complexity (`C901`) by default.
+select = ["E4", "E7", "E9", "F" ,"ALL"]
+ignore = []
+# Allow fix for all enabled rules (when `--fix`) is provided.
+fixable = ["ALL"]
+# Disable fix for unused imports (`F401`).
+unfixable = ["F401"]
+
+# Allow unused variables when underscore-prefixed.
+dummy-variable-rgx = "^(_+|(_+[a-zA-Z0-9_]*[a-zA-Z0-9]+?))$"
+
+[tool.ruff.format]
+# Like Black, use double quotes for strings.
+quote-style = "double"
+
+# Like Black, indent with spaces, rather than tabs.
+indent-style = "space"
+
+# Like Black, respect magic trailing commas.
+skip-magic-trailing-comma = false
+
+# Like Black, automatically detect the appropriate line ending.
+line-ending = "auto"
+
+# Enable auto-formatting of code examples in docstrings. Markdown,
+# reStructuredText code/literal blocks and doctests are all supported.
+#
+# This is currently disabled by default, but it is planned for this
+# to be opt-out in the future.
+docstring-code-format = false
+
+# Set the line length limit used when formatting code snippets in
+# docstrings.
+#
+# This only has an effect when the `docstring-code-format` setting is
+# enabled.
+docstring-code-line-length = "dynamic"
+

{zipfly64-1.2.0 → zipfly64-1.2.3}/src/zipFly/BaseFile.py

@@ -1,6 +1,6 @@
 import time
 from abc import ABC, abstractmethod
-from typing import Generator, AsyncGenerator
+from collections.abc import AsyncGenerator, Generator
 
 from . import consts
 from .Compressor import Compressor
@@ -18,10 +18,13 @@ class BaseFile(ABC):
     def __str__(self):
         return f"FILE[{self.name}]"
 
-    def generate_processed_file_data(self) -> Generator[bytes, None, None]:
+    def _check_if_used(self):
         if self.__used:
-            raise KeyError("ERROR: This file has already been used for streaming")
+            raise RuntimeError("Do not re-use file instances. Recreate it.")
         self.__used = True
+
+    def generate_processed_file_data(self) -> Generator[bytes, None, None]:
+        self._check_if_used()
         compressor = Compressor(self)
 
         """
@@ -31,15 +34,12 @@ class BaseFile(ABC):
             chunk = compressor.process(chunk)
             if len(chunk) > 0:
                 yield chunk
-            chunk = compressor.tail()
-            if len(chunk) > 0:
-                yield chunk
+        chunk = compressor.tail()
+        if len(chunk) > 0:
+            yield chunk
 
     async def async_generate_processed_file_data(self) -> AsyncGenerator[bytes, None]:
-        if self.__used:
-            raise KeyError("ERROR: This file has already been used for streaming")
-        self.__used = True
-
+        self._check_if_used()
         compressor = Compressor(self)
 
         """
@@ -49,9 +49,9 @@ class BaseFile(ABC):
             chunk = compressor.process(chunk)
             if len(chunk) > 0:
                 yield chunk
-            chunk = compressor.tail()
-            if len(chunk) > 0:
-                yield chunk
+        chunk = compressor.tail()
+        if len(chunk) > 0:
+            yield chunk
 
     def get_mod_time(self) -> int:
         # Extract hours, minutes, and seconds from the modification time

{zipfly64-1.2.0 → zipfly64-1.2.3}/src/zipFly/GenFile.py

@@ -1,21 +1,22 @@
 import time
-from typing import Generator, AsyncGenerator, Callable
+from typing import Generator, AsyncGenerator, Union
+
+from . import consts
 from .BaseFile import BaseFile
 
 
 class GenFile(BaseFile):
-
-    def __init__(self, name: str, generator: Callable, compression_method: int = None, modification_time: float = None, size: int = None, crc: int = None):
+    """DO NOT REUSE GenFile instances!"""
+    def __init__(self, name: str, generator: Union[Generator[bytes, None, None], AsyncGenerator[bytes, None]], compression_method: int = consts.NO_COMPRESSION, modification_time: float = None, size: int = None, crc: int = None):
         super().__init__(compression_method)
         self._name = name
-        self._generator_func = generator
+        self._generator = generator
         self._size = size
-        self._crc = crc
+        self._overriden_crc = crc  # used in byte offset mode
         self._modification_time = modification_time if modification_time else time.time()
 
     def _get_generator(self):
-        """Return a new generator instance every time this is called."""
-        return self._generator_func()
+        return self._generator
 
     def _generate_file_data(self) -> Generator[bytes, None, None]:
         generator = self._get_generator()
@@ -40,7 +41,7 @@ class GenFile(BaseFile):
     def size(self) -> int:
         if self._size is not None:
             return self._size
-        raise ValueError("Archive size not known before streaming. Probably GenFile() is missing size attribute.")
+        raise RuntimeError("Archive size not known before streaming. Probably GenFile() is missing size attribute.")
 
     @property
     def modification_time(self) -> float:
@@ -50,6 +51,6 @@ class GenFile(BaseFile):
         self._name = new_name
 
     def calculate_crc(self) -> int:
-        if self._crc:
-            return self._crc
+        if self._overriden_crc:
+            return self._overriden_crc
         raise ValueError("Crc must be explicitly set to allow for byte offset streaming!")

{zipfly64-1.2.0 → zipfly64-1.2.3}/src/zipFly/LocalFile.py

@@ -1,20 +1,23 @@
 import os
-import time
 import zlib
-from typing import Generator, AsyncGenerator
-from .BaseFile import BaseFile
-import binascii
+from pathlib import Path
+from typing import Generator, AsyncGenerator, Union
 
 import aiofiles
 
-class LocalFile(BaseFile):
+from . import consts
+from .BaseFile import BaseFile
 
-    def __init__(self, file_path: str, name: str = None, compression_method: int = None, chunk_size=None):
-        if not os.path.isfile(file_path):
+
+class LocalFile(BaseFile):
+    def __init__(self, file_path: Union[str, Path], name: str = None, compression_method: int = consts.NO_COMPRESSION, chunk_size=None):
+        file_path = Path(file_path)
+        if not file_path.is_file():
             raise ValueError(f"{file_path} is not a correct file path.")
-        self._file_path = file_path
+
+        self._file_path = str(file_path)
         self.chunk_size = chunk_size
-        self._name = name if name else file_path
+        self._name = name if name else self._file_path
         super().__init__(compression_method)
 
     async def _async_generate_file_data(self) -> AsyncGenerator[bytes, None]:

{zipfly64-1.2.0 → zipfly64-1.2.3}/src/zipFly/ZipBase.py

@@ -1,6 +1,3 @@
-import copy
-import types
-from collections import defaultdict
 from typing import List
 
 from . import consts
@@ -63,63 +60,10 @@ I hope, that i made it a bit more clear to anyone reading, including future me.
 """
 
 
-def process_file_names(files) -> list[BaseFile]:
-    name_counts = defaultdict(int)
-    for file in files:
-        # Split the name into base and extension
-        base, ext = file.name.rsplit('.', 1) if '.' in file.name else (file.name, '')
-
-        # Increment the count for this base name
-        name_counts[base] += 1
-
-        # Append the count to the base name if it's not the first occurrence
-        if name_counts[base] > 1:
-            new_base = f"{base} ({name_counts[base] - 1})"
-        else:
-            new_base = base
-
-        # Reassemble the filename
-        file.set_file_name(f"{new_base}.{ext}" if ext else new_base)
-
-    return files
-
-
-def deepcopy_skip_generators(obj_list):
-    """
-    Deep copies a list of objects while skipping generator attributes.
-    """
-
-    def custom_copy(obj, memo=None):
-        if memo is None:
-            memo = {}
-
-        if isinstance(obj, dict):
-            return {k: custom_copy(v, memo) for k, v in obj.items()}
-        elif isinstance(obj, (list, tuple, set)):
-            return type(obj)(custom_copy(item, memo) for item in obj)
-        elif isinstance(obj, (int, float, str, bool, type(None))):  # Immutable types
-            return obj
-        elif isinstance(obj, (types.GeneratorType, types.AsyncGeneratorType)):  # Skip generators
-            return obj
-        elif hasattr(obj, '__dict__'):  # Handle custom objects
-            new_obj = copy.copy(obj)  # Shallow copy first
-            for key, value in obj.__dict__.items():
-                setattr(new_obj, key, custom_copy(value, memo))
-            return new_obj
-        else:
-            return copy.deepcopy(obj, memo)  # Default deep copy
-
-    return [custom_copy(obj) for obj in obj_list]
-
-
 class ZipBase:
-
     def __init__(self, files: List[BaseFile]):
         self.__version_to_extract = 45
-
-        # process file names to make sure there are no duplicates
-        processed_files = process_file_names(deepcopy_skip_generators(files))
-        self.files = processed_files
+        self.files = files
 
         self.__offset = 0  # Tracks the current offset within the ZIP archive
         self._cdir_size = 0