Version 0.9.4 (#52)

- Adding sync_dirs function
- Adding sanitized_input function (Thanks to Dogeek)
- Breaking change: Changing find_files to return pathlib objects by default on Python 3.4+
- Removing python 2.6 from travis tests

Author: cdgriffith

.travis.yml

@@ -2,14 +2,16 @@ sudo: required
 dist: trusty
 language: python
 python:
-    - "2.6"
     - "2.7"
-    - "3.3"
     - "3.4"
     - "3.5"
     - "3.6"
-    - "3.7-dev"
     - "pypy"
+matrix:
+  include:
+    - python: "3.7"
+      dist: xenial
+      sudo: true
 before_install:
     - sudo apt-get -qq update
     - sudo apt-get install -y unrar

AUTHORS.rst

@@ -5,3 +5,4 @@ reporting, all input is greatly appreciated!
 
 - Clara Griffith (beautiousmax)
 - Hellowlol
+- Dogeek

CHANGES.rst

@@ -1,6 +1,14 @@
 Changelog
 =========
 
+Version 0.9.4
+-------------
+
+- Adding sync_dirs function
+- Adding sanitized_input function (Thanks to Dogeek)
+- Breaking change: Changing find_files to return pathlib objects by default on Python 3.4+
+- Removing python 2.6 from travis tests
+
 Version 0.9.3
 -------------
 

LICENSE

@@ -1,6 +1,6 @@
 The MIT License (MIT)
 
-Copyright (c) 2014-2017 Chris Griffith
+Copyright (c) 2014-2019 Chris Griffith
 
 Permission is hereby granted, free of charge, to any person obtaining a copy of
 this software and associated documentation files (the "Software"), to deal in

README.rst

@@ -394,7 +394,7 @@ License
 
 The MIT License (MIT)
 
-Copyright (c) 2014-2017 Chris Griffith
+Copyright (c) 2014-2019 Chris Griffith
 
 Permission is hereby granted, free of charge, to any person obtaining a copy of
 this software and associated documentation files (the "Software"), to deal in

requirements-test.txt

@@ -1,6 +1,8 @@
-pytest
-coverage >= 3.6
+pytest >= 4.1.1
+coverage >= 4.5.2
 rarfile
 scandir
 tox
 pytest-cov
+mock
+future

reusables/__init__.py

@@ -18,6 +18,7 @@
 from reusables.tasker import *
 from reusables.web import *
 from reusables.wrappers import *
+from reusables.sanitizers import *
 
 __author__ = "Chris Griffith"
-__version__ = "0.9.3"
+__version__ = "0.9.4"

reusables/cli.py

@@ -116,7 +116,7 @@ def find(name=None, ext=None, directory=".", match_case=False,
     """
     return find_files_list(directory=directory, ext=ext, name=name,
                            match_case=match_case, disable_glob=disable_glob,
-                           depth=depth)
+                           depth=depth, disable_pathlib=True)
 
 
 def head(file_path, lines=10, encoding="utf-8", printed=True,

reusables/file_operations.py

@@ -3,7 +3,7 @@
 #
 # Part of the Reusables package.
 #
-# Copyright (c) 2014-2017 - Chris Griffith - MIT License
+# Copyright (c) 2014-2019 - Chris Griffith - MIT License
 import os
 import zipfile
 import tarfile
@@ -12,6 +12,7 @@
 import json
 import hashlib
 import glob
+import shutil
 from collections import defaultdict
 try:
     import ConfigParser as ConfigParser
@@ -27,7 +28,7 @@
            'directory_duplicates', 'dup_finder', 'file_hash', 'find_files',
            'find_files_list', 'join_here', 'join_paths',
            'remove_empty_directories', 'remove_empty_files',
-           'safe_filename', 'safe_path', 'touch']
+           'safe_filename', 'safe_path', 'touch', 'sync_dirs']
 
 logger = logging.getLogger('reusables')
 
@@ -168,7 +169,8 @@ def archive(files_to_archive, name="archive.zip", archive_type=None,
                     raise OSError("File {0} does not exist".format(file_path))
                 write(file_path)
             elif os.path.isdir(file_path):
-                for nf in find_files(file_path, abspath=False, depth=depth):
+                for nf in find_files(file_path, abspath=False,
+                                     depth=depth, disable_pathlib=True):
                     write(nf)
     except (Exception, KeyboardInterrupt) as err:
         logger.exception("Could not archive {0}".format(files_to_archive))
@@ -327,7 +329,7 @@ def config_dict(config_file=None, auto_find=False, verify=True, **cfg_options):
     if auto_find:
         cfg_files.extend(find_files_list(
             current_root if isinstance(auto_find, bool) else auto_find,
-            ext=(".cfg", ".config", ".ini")))
+            ext=(".cfg", ".config", ".ini"), disable_pathlib=True))
 
     logger.info("config files to be used: {0}".format(cfg_files))
 
@@ -462,12 +464,15 @@ def count_files(*args, **kwargs):
 
 def find_files(directory=".", ext=None, name=None,
                match_case=False, disable_glob=False, depth=None,
-               abspath=False, enable_scandir=False):
+               abspath=False, enable_scandir=False, disable_pathlib=False):
     """
     Walk through a file directory and return an iterator of files
     that match requirements. Will autodetect if name has glob as magic
     characters.
 
+    Returns pathlib objects by default with Python versions 3.4 or grater
+    unless disable_pathlib is enabled.
+
     Note: For the example below, you can use find_files_list to return as a
     list, this is simply an easy way to show the output.
 
@@ -497,8 +502,15 @@ def find_files(directory=".", ext=None, name=None,
     :param depth: How many directories down to search
     :param abspath: Return files with their absolute paths
     :param enable_scandir: on python < 3.5 enable external scandir package
+    :param disable_pathlib: only return string, not path objects
     :return: generator of all files in the specified directory
     """
+    def pathed(path):
+        if python_version < (3, 4) or disable_pathlib:
+            return path
+        import pathlib
+        return pathlib.Path(path)
+
     if ext or not name:
         disable_glob = True
     if not disable_glob:
@@ -522,7 +534,7 @@ def find_files(directory=".", ext=None, name=None,
                                  "either disable glob or not set match_case")
             glob_generator = glob.iglob(os.path.join(root, name))
             for item in glob_generator:
-                yield item
+                yield pathed(item)
             continue
 
         for file_name in files:
@@ -538,7 +550,7 @@ def find_files(directory=".", ext=None, name=None,
                     continue
                 elif name.lower() not in file_name.lower():
                     continue
-            yield os.path.join(root, file_name)
+            yield pathed(os.path.join(root, file_name))
 
 
 def remove_empty_directories(root_directory, dry_run=False, ignore_errors=True,
@@ -703,7 +715,7 @@ def directory_duplicates(directory, hash_type='md5', **kwargs):
     :return: list of lists of dups"""
     size_map, hash_map = defaultdict(list), defaultdict(list)
 
-    for item in find_files(directory, **kwargs):
+    for item in find_files(directory, disable_pathlib=True, **kwargs):
         file_size = os.path.getsize(item)
         size_map[file_size].append(item)
 
@@ -853,6 +865,51 @@ def safe_path(path, replacement="_"):
     return sanitized_path
 
 
+def sync_dirs(dir1, dir2, checksums=True, overwrite=False,
+              only_log_errors=True):
+    """
+    Make sure all files in directory 1 exist in directory 2.
+
+    :param dir1: Copy from
+    :param dir2: Copy too
+    :param checksums: Use hashes to make sure file contents match
+    :param overwrite: If sizes don't match, overwrite with file from dir 1
+    :param only_log_errors: Do not raise copy errors, only log them
+    :return: None
+    """
+    def cp(f1, f2):
+        try:
+            shutil.copy(f1, f2)
+        except OSError:
+            if only_log_errors:
+                logger.error("Could not copy {} to {}".format(f1, f2))
+            else:
+                raise
+
+    for file in find_files(dir1, disable_pathlib=True):
+        path_two = os.path.join(dir2, file[len(dir1)+1:])
+        try:
+            os.makedirs(os.path.dirname(path_two))
+        except OSError:
+            pass  # Because exists_ok doesn't exist in 2.x
+        if os.path.exists(path_two):
+            if os.path.getsize(file) != os.path.getsize(path_two):
+                logger.info("File sizes do not match: "
+                            "{} - {}".format(file, path_two))
+                if overwrite:
+                    logger.info("Overwriting {}".format(path_two))
+                    cp(file, path_two)
+            elif checksums and (file_hash(file) != file_hash(path_two)):
+                logger.warning("Files do not match: "
+                               "{} - {}".format(file, path_two))
+                if overwrite:
+                    logger.info("Overwriting {}".format(file, path_two))
+                    cp(file, path_two)
+        else:
+            logger.info("Copying {} to {}".format(file, path_two))
+            cp(file, path_two)
+
+
 
 
 

reusables/log.py

@@ -17,7 +17,7 @@
 from reusables.namespace import Namespace
 from reusables.shared_variables import sizes
 
-__all__ = ['log_formats', 'get_logger', 'get_registered_loggers',
+__all__ = ['log_formats', 'get_logger', 'setup_logger', 'get_registered_loggers',
            'get_file_handler', 'get_stream_handler', 'add_file_handler',
            'add_stream_handler', 'add_rotating_file_handler',
            'add_timed_rotating_file_handler', 'change_logger_levels',
@@ -43,6 +43,13 @@ def emit(self, record):
     logging.NullHandler = NullHandler
 
 
+def get_logger(*args, **kwargs):
+    """ Depreciated, use setup_logger"""
+    warnings.warn("get_logger is changing name to setup_logger",
+                  DeprecationWarning)
+    return setup_logger(*args, **kwargs)
+
+
 def get_stream_handler(stream=sys.stderr, level=logging.INFO,
                        log_format=log_formats.easy_read):
     """
@@ -108,13 +115,6 @@ def setup_logger(module_name=None, level=logging.INFO, stream=sys.stderr,
     return new_logger
 
 
-def get_logger(*args, **kwargs):
-    """ Depreciated, use setup_logger"""
-    warnings.warn("get_logger is changing name to setup_logger",
-                  DeprecationWarning)
-    return setup_logger(*args, **kwargs)
-
-
 def add_stream_handler(logger=None, stream=sys.stderr, level=logging.INFO,
                        log_format=log_formats.easy_read):
     """

reusables/sanitizers.py

@@ -0,0 +1,90 @@
+try:
+    from collections.abc import Iterable, Callable
+except ImportError:
+    from collections import Iterable, Callable
+
+from reusables.shared_variables import ReusablesError
+
+
+class InvalidInputError(ReusablesError):
+    pass
+
+
+class RetryCountExceededError(ReusablesError):
+    pass
+
+
+def _get_input(prompt):
+    try:
+        return raw_input(prompt)
+    except NameError:
+        return input(prompt)
+
+
+def sanitized_input(message="", cast_as=None, number_of_retries=-1,
+                    error_message="", valid_input=(), raise_on_invalid=False):
+    """
+        Clean up and cast user input.
+
+        :param message: string to show the user (default: "")
+        :param cast_as: an object to cast the string into. Object must have a __new__
+                       method that can take a string as the first positional argument
+                       and be a subclass of type.
+                       The object should raise a ValueError exception if a
+                       string can't be cast into that object.
+                       cast_as can also be a tuple or a list, which will
+                       chain casts until the end of the list. Casts are chained in
+                       reverse order of the list (to mimic the syntax int(float(x))) (default: str)
+        :param number_of_retries: number of retries. No limit if n_retries == -1 (default: -1)
+        :param error_message: message to show the user before asking the input again in
+                            case an error occurs (default: repr of the exception).
+                            Can include {error}.
+        :param valid_input: an iterable to check if the result is allowed.
+        :param raise_on_invalid: boolean, whether this function will raise a
+                               reusables.InvalidInputError if the input doesn't match
+                               the valid_input argument.
+        :return: string literal casted into the cast_as as per that object's rules.
+
+        :raises: RetryCountExceededError if the retry count has exceeded the n_retries limit.
+
+
+        Examples:
+            integer = sanitized_input("How many apples?", int,
+                      error_msg="Please enter a valid number")
+            # returns an int, will prompt until the user enters an integer.
+
+            validated = sanitized_input(">>>", valid_input=["string"], raise_on_invalid=True)
+            # returns the value "string", and will raise InvalidInputError otherwise.
+
+            chain_cast = sanitized_input(">>>", cast_as=[int, float])
+            # returns an int, prompts like '2.3' won't raise a ValueError Exception.
+    """
+    retry_count = 0
+
+    cast_as = cast_as if cast_as is not None else str
+    cast_objects = list(cast_as) if isinstance(cast_as, Iterable) else (cast_as, )
+    for cast_obj in cast_objects:
+        if not isinstance(cast_obj, Callable):
+            raise ValueError("ValueError: argument 'cast_as'"
+                             "cannot be of type '{}'".format(type(cast_as)))
+
+    if not hasattr(valid_input, '__iter__'):
+        valid_input = (valid_input, )
+
+    while retry_count < number_of_retries or number_of_retries == -1:
+        try:
+            return_value = _get_input(message)
+            for cast_obj in reversed(cast_objects):
+                return_value = cast_obj(return_value)
+            if valid_input and return_value not in valid_input:
+                raise InvalidInputError("InvalidInputError: input invalid"
+                                        "in function 'sanitized_input' of {}".format(__name__))
+            return return_value
+        except (InvalidInputError, ValueError) as err:
+            if raise_on_invalid and type(err).__name__ == "InvalidInputError":
+                raise err
+            print(error_message.format(error=str(err)) if error_message else repr(err))
+            retry_count += 1
+            continue
+    raise RetryCountExceededError("RetryCountExceededError : count exceeded in"
+                                  "function 'sanitized_input' of {}".format(__name__))

setup.py

@@ -39,13 +39,13 @@
     classifiers=[
         'Programming Language :: Python',
         'Programming Language :: Python :: 2',
-        'Programming Language :: Python :: 2.6',
         'Programming Language :: Python :: 2.7',
         'Programming Language :: Python :: 3',
         'Programming Language :: Python :: 3.3',
         'Programming Language :: Python :: 3.4',
         'Programming Language :: Python :: 3.5',
         'Programming Language :: Python :: 3.6',
+        'Programming Language :: Python :: 3.7',
         'Programming Language :: Python :: Implementation :: CPython',
         'Programming Language :: Python :: Implementation :: PyPy',
         'Development Status :: 4 - Beta',