Refactor code for improved readability and performance

- Updated file reading methods in DropboxFolderCopyReader and DropboxFileCopyReader to use context managers without explicit mode.
- Removed unnecessary future import in parse_format.py.
- Simplified string formatting using f-strings in multiple classes within parse_format.py.
- Replaced old-style class definitions with new-style in various utility classes.
- Optimized recursive directory iteration functions in local_files.py using yield from.
- Enhanced type hinting in w_helpful_folder_not_found_error function.
- Streamlined zip function usage in mk_kv_from_keygen.
- Updated glom.py to use f-strings for better readability in error messages and representations.
- Changed type imports to use collections.abc for better compatibility.
- Refactored mongoquery.py to utilize f-strings for error messages.
- Minor adjustments in tests/utils_for_testing.py for clarity in user prompts.

Author: thorwhalen

misc/best of 2020 demo.ipynb

@@ -22,7 +22,7 @@ def __init__(self, url, path=tempfile.gettempdir()):
     def __getitem__(self, rel_path):
         real_path = os.path.join(self.path, rel_path)
         try:
-            with open(real_path, 'r') as f:
+            with open(real_path) as f:
                 return f.read()
         except FileNotFoundError:
             raise KeyError(f"Key doesn't exist: {rel_path}")
@@ -50,7 +50,7 @@ def __init__(self, url, path=None):
         self.path = path or self._get_filename_from_url()
 
         download_from_dropbox(self.url, self.path)
-        self.file = open(self.path, 'r')
+        self.file = open(self.path)
 
     def __getitem__(self, index):
         self.file.seek(0)

py2store/examples/dropbox_w_urllib.py

@@ -401,7 +401,6 @@
 See the end of the source file for the license of use.
 """
 
-from __future__ import absolute_import
 
 __version__ = '1.9.0'
 
@@ -500,7 +499,7 @@ def __init__(self, offset, name):
         self._name = name
 
     def __repr__(self):
-        return '<%s %s %s>' % (self.__class__.__name__, self._name, self._offset,)
+        return '<{} {} {}>'.format(self.__class__.__name__, self._name, self._offset)
 
     def utcoffset(self, dt):
         return self._offset
@@ -708,7 +707,7 @@ def extract_format(format, extra_types):
 PARSE_RE = re.compile(r'''({{|}}|{\w*(?:(?:\.\w+)|(?:\[[^\]]+\]))*(?::[^}]+)?})''')
 
 
-class Parser(object):
+class Parser:
     """Encapsulate a format string that may be used to parse other strings."""
 
     def __init__(self, format, extra_types=None, case_sensitive=False):
@@ -744,8 +743,8 @@ def __init__(self, format, extra_types=None, case_sensitive=False):
 
     def __repr__(self):
         if len(self._format) > 20:
-            return '<%s %r>' % (self.__class__.__name__, self._format[:17] + '...',)
-        return '<%s %r>' % (self.__class__.__name__, self._format)
+            return '<{} {!r}>'.format(self.__class__.__name__, self._format[:17] + '...')
+        return '<{} {!r}>'.format(self.__class__.__name__, self._format)
 
     @property
     def _search_re(self):
@@ -880,7 +879,7 @@ def evaluate_result(self, m):
             named_fields[korig] = value
 
         # now figure the match spans
-        spans = dict((n, m.span(name_map[n])) for n in named_fields)
+        spans = {n: m.span(name_map[n]) for n in named_fields}
         spans.update((i, m.span(n + 1)) for i, n in enumerate(self._fixed_fields))
 
         # and that's our result
@@ -921,7 +920,7 @@ def _to_group_name(self, field):
             elif '_' in field:
                 group = field.replace('_', '_' * n)
             else:
-                raise KeyError('duplicated group name %r' % (field,))
+                raise KeyError('duplicated group name {!r}'.format(field))
 
         # save off the mapping
         self._group_to_name_map[group] = field
@@ -1034,7 +1033,7 @@ def f(string, m):
             )
             self._group_index += 7
         elif type == 'tg':
-            s = r'(\d{1,2}[-/](\d{1,2}|%s)[-/]\d{4})(\s+%s)?%s?%s?' % (
+            s = r'(\d{{1,2}}[-/](\d{{1,2}}|{})[-/]\d{{4}})(\s+{})?{}?{}?'.format(
                 ALL_MONTHS_PAT,
                 TIME_PAT,
                 AM_PAT,
@@ -1046,7 +1045,7 @@ def f(string, m):
             )
             self._group_index += 9
         elif type == 'ta':
-            s = r'((\d{1,2}|%s)[-/]\d{1,2}[-/]\d{4})(\s+%s)?%s?%s?' % (
+            s = r'((\d{{1,2}}|{})[-/]\d{{1,2}}[-/]\d{{4}})(\s+{})?{}?{}?'.format(
                 ALL_MONTHS_PAT,
                 TIME_PAT,
                 AM_PAT,
@@ -1059,7 +1058,7 @@ def f(string, m):
             self._group_index += 9
         elif type == 'te':
             # this will allow microseconds through if they're present, but meh
-            s = r'(%s,\s+)?(\d{1,2}\s+%s\s+\d{4})\s+%s%s' % (
+            s = r'({},\s+)?(\d{{1,2}}\s+{}\s+\d{{4}})\s+{}{}'.format(
                 DAYS_PAT,
                 MONTHS_PAT,
                 TIME_PAT,
@@ -1072,14 +1071,14 @@ def f(string, m):
             self._group_index += 8
         elif type == 'th':
             # slight flexibility here from the stock Apache format
-            s = r'(\d{1,2}[-/]%s[-/]\d{4}):%s%s' % (MONTHS_PAT, TIME_PAT, TZ_PAT,)
+            s = r'(\d{{1,2}}[-/]{}[-/]\d{{4}}):{}{}'.format(MONTHS_PAT, TIME_PAT, TZ_PAT)
             n = self._group_index
             self._type_conversions[group] = partial(
                 date_convert, dmy=n + 1, hms=n + 3, tz=n + 6
             )
             self._group_index += 6
         elif type == 'tc':
-            s = r'(%s)\s+%s\s+(\d{1,2})\s+%s\s+(\d{4})' % (
+            s = r'({})\s+{}\s+(\d{{1,2}})\s+{}\s+(\d{{4}})'.format(
                 DAYS_PAT,
                 MONTHS_PAT,
                 TIME_PAT,
@@ -1090,7 +1089,7 @@ def f(string, m):
             )
             self._group_index += 8
         elif type == 'tt':
-            s = r'%s?%s?%s?' % (TIME_PAT, AM_PAT, TZ_PAT)
+            s = r'{}?{}?{}?'.format(TIME_PAT, AM_PAT, TZ_PAT)
             n = self._group_index
             self._type_conversions[group] = partial(
                 date_convert, hms=n + 1, am=n + 4, tz=n + 5
@@ -1108,7 +1107,7 @@ def f(string, m):
             s = r'\%s+' % type
         elif format.get('precision'):
             if format.get('width'):
-                s = '.{%s,%s}?' % (format['width'], format['precision'])
+                s = '.{{{},{}}}?'.format(format['width'], format['precision'])
             else:
                 s = '.{1,%s}?' % format['precision']
         elif format.get('width'):
@@ -1154,16 +1153,16 @@ def f(string, m):
 
         # align "=" has been handled
         if align == '<':
-            s = '%s%s*' % (s, fill)
+            s = '{}{}*'.format(s, fill)
         elif align == '>':
-            s = '%s*%s' % (fill, s)
+            s = '{}*{}'.format(fill, s)
         elif align == '^':
-            s = '%s*%s%s*' % (fill, s, fill)
+            s = '{}*{}{}*'.format(fill, s, fill)
 
         return s
 
 
-class Result(object):
+class Result:
     """The result of a parse() or search().
 
     Fixed results may be looked up using result[index]. Named results may be
@@ -1181,10 +1180,10 @@ def __getitem__(self, item):
         return self.named[item]
 
     def __repr__(self):
-        return '<%s %r %r>' % (self.__class__.__name__, self.fixed, self.named)
+        return '<{} {!r} {!r}>'.format(self.__class__.__name__, self.fixed, self.named)
 
 
-class Match(object):
+class Match:
     """The result of a parse() or search() if no results are generated.
 
     This class is only used to expose internal used regex match objects
@@ -1200,7 +1199,7 @@ def evaluate_result(self):
         return self.parser.evaluate_result(self.match)
 
 
-class ResultIterator(object):
+class ResultIterator:
     """The result of a findall() operation.
 
     Each element is a Result instance.

py2store/parse_format.py

@@ -89,10 +89,9 @@ def iter_filepaths_in_folder_recursively(
     for full_path in paths_in_dir(root_folder):
         if os.path.isdir(full_path):
             if _current_level < max_levels:
-                for entry in iter_filepaths_in_folder_recursively(
+                yield from iter_filepaths_in_folder_recursively(
                     full_path, max_levels, _current_level + 1
-                ):
-                    yield entry
+                )
         else:
             if os.path.isfile(full_path):
                 yield full_path
@@ -105,10 +104,9 @@ def iter_dirpaths_in_folder_recursively(root_folder, max_levels=None, _current_l
         if os.path.isdir(full_path):
             yield full_path
             if _current_level < max_levels:
-                for entry in iter_dirpaths_in_folder_recursively(
+                yield from iter_dirpaths_in_folder_recursively(
                     full_path, max_levels, _current_level + 1
-                ):
-                    yield entry
+                )
 
 
 class PrefixedFilepaths:
@@ -214,13 +212,14 @@ def first_non_existing_parent_dir(dirpath):
 # Local File Persistence : Classes
 
 from functools import wraps
-from typing import Union, Callable
+from typing import Union
+from collections.abc import Callable
 
 
 def w_helpful_folder_not_found_error(
     *,
     raise_error=KeyError,
-    extra_msg: Union[str, Callable] = '',
+    extra_msg: str | Callable = '',
     caught_errors=FileNotFoundError,
 ):
     if isinstance(extra_msg, str):
@@ -237,7 +236,7 @@ def wrapped_method(*args, **kwargs):
             try:
                 return method(*args, **kwargs)
             except caught_errors as e:
-                msg = '{}: {}\n'.format(type(e).__name__, e) + extra_msg(
+                msg = f'{type(e).__name__}: {e}\n' + extra_msg(
                     *args, **kwargs
                 )
                 raise raise_error(msg)

py2store/persisters/local_files.py

@@ -3,7 +3,7 @@
 """
 
 
-class AffineConverter(object):
+class AffineConverter:
     """
     Getting a callable that will perform an affine conversion.
     Note, it does it as

py2store/utils/affine_conversion.py

@@ -23,7 +23,7 @@
 ncaches = 0
 
 
-class _CachedProperty(object):
+class _CachedProperty:
     """
     Cached property implementation class.
     """
@@ -92,7 +92,7 @@ def factory(function):
     return factory
 
 
-class Lazy(object):
+class Lazy:
     """Lazy Attributes."""
 
     def __init__(self, func, name=None):
@@ -111,7 +111,7 @@ def __get__(self, inst, class_):
         return value
 
 
-class readproperty(object):
+class readproperty:
     def __init__(self, func):
         self.func = func
         update_wrapper(self, func)
@@ -124,7 +124,7 @@ def __get__(self, inst, class_):
         return func(inst)
 
 
-class cachedIn(object):
+class cachedIn:
     """Cached property with given cache attribute."""
 
     def __init__(self, attribute_name):

py2store/utils/cache_descriptors.py

@@ -41,8 +41,7 @@ def join_string_values_and_key_as_current_utc_milliseconds(gen):
 
 def mk_kv_from_keygen(keygen=itertools.count()):
     def aggregate(gen):
-        for k, v in zip(keygen, gen):
-            yield k, v
+        yield from zip(keygen, gen)
 
     return aggregate