Some refactoring to tidy up hash methods

Author: mredolatti

splitio/hashfns/.ropeproject/config.py

@@ -0,0 +1,103 @@
+# The default ``config.py``
+# flake8: noqa
+
+
+def set_prefs(prefs):
+    """This function is called before opening the project"""
+
+    # Specify which files and folders to ignore in the project.
+    # Changes to ignored resources are not added to the history and
+    # VCSs.  Also they are not returned in `Project.get_files()`.
+    # Note that ``?`` and ``*`` match all characters but slashes.
+    # '*.pyc': matches 'test.pyc' and 'pkg/test.pyc'
+    # 'mod*.pyc': matches 'test/mod1.pyc' but not 'mod/1.pyc'
+    # '.svn': matches 'pkg/.svn' and all of its children
+    # 'build/*.o': matches 'build/lib.o' but not 'build/sub/lib.o'
+    # 'build//*.o': matches 'build/lib.o' and 'build/sub/lib.o'
+    prefs['ignored_resources'] = [
+        '*.pyc', '*~', '.ropeproject', '.hg', '.svn', '_svn',
+        '.git', '.tox', '.env', 'env', 'venv', 'node_modules',
+        'bower_components'
+    ]
+
+    # Specifies which files should be considered python files.  It is
+    # useful when you have scripts inside your project.  Only files
+    # ending with ``.py`` are considered to be python files by
+    # default.
+    #prefs['python_files'] = ['*.py']
+
+    # Custom source folders:  By default rope searches the project
+    # for finding source folders (folders that should be searched
+    # for finding modules).  You can add paths to that list.  Note
+    # that rope guesses project source folders correctly most of the
+    # time; use this if you have any problems.
+    # The folders should be relative to project root and use '/' for
+    # separating folders regardless of the platform rope is running on.
+    # 'src/my_source_folder' for instance.
+    #prefs.add('source_folders', 'src')
+
+    # You can extend python path for looking up modules
+    #prefs.add('python_path', '~/python/')
+
+    # Should rope save object information or not.
+    prefs['save_objectdb'] = True
+    prefs['compress_objectdb'] = False
+
+    # If `True`, rope analyzes each module when it is being saved.
+    prefs['automatic_soa'] = True
+    # The depth of calls to follow in static object analysis
+    prefs['soa_followed_calls'] = 0
+
+    # If `False` when running modules or unit tests "dynamic object
+    # analysis" is turned off.  This makes them much faster.
+    prefs['perform_doa'] = True
+
+    # Rope can check the validity of its object DB when running.
+    prefs['validate_objectdb'] = True
+
+    # How many undos to hold?
+    prefs['max_history_items'] = 32
+
+    # Shows whether to save history across sessions.
+    prefs['save_history'] = True
+    prefs['compress_history'] = False
+
+    # Set the number spaces used for indenting.  According to
+    # :PEP:`8`, it is best to use 4 spaces.  Since most of rope's
+    # unit-tests use 4 spaces it is more reliable, too.
+    prefs['indent_size'] = 4
+
+    # Builtin and c-extension modules that are allowed to be imported
+    # and inspected by rope.
+    prefs['extension_modules'] = []
+
+    # Add all standard c-extensions to extension_modules list.
+    prefs['import_dynload_stdmods'] = True
+
+    # If `True` modules with syntax errors are considered to be empty.
+    # The default value is `False`; When `False` syntax errors raise
+    # `rope.base.exceptions.ModuleSyntaxError` exception.
+    prefs['ignore_syntax_errors'] = False
+
+    # If `True`, rope ignores unresolvable imports.  Otherwise, they
+    # appear in the importing namespace.
+    prefs['ignore_bad_imports'] = False
+
+    # If `True`, rope will insert new module imports as
+    # `from <package> import <module>` by default.
+    prefs['prefer_module_from_imports'] = False
+
+    # If `True`, rope will transform a comma list of imports into
+    # multiple separate import statements when organizing
+    # imports.
+    prefs['split_imports'] = False
+
+    # If `True`, rope will sort imports alphabetically by module name
+    # instead of alphabetically by import statement, with from imports
+    # after normal imports.
+    prefs['sort_imports_alphabetically'] = False
+
+
+def project_opened(project):
+    """This function is called after opening the project"""
+    # Do whatever you like here!

splitio/hashfns/.ropeproject/globalnames

@@ -0,0 +1,38 @@
+"""
+This module contains hash functions implemented in pure python
+as well as the optional import (if installed) of a C compiled murmur hash
+function with python bindings.
+"""
+from __future__ import absolute_import, division, print_function, \
+    unicode_literals
+
+from splitio.hashfns import legacy
+
+try:
+    # First attempt to import module with C++ core (faster)
+    import mmh3
+    from ctypes import c_uint
+
+    def _murmur_hash(key, seed):
+        ukey = key.encode('utf8')
+        return c_uint(mmh3.hash(ukey, seed)).value
+except:
+    # Fallback to interpreted python hash algoritm (slower)
+    from splitio.hashfns import murmur3py
+    _murmur_hash = murmur3py.murmur32_py
+
+
+_HASH_ALGORITHMS = {
+    'legacy': legacy.legacy_hash,
+    'murmur': _murmur_hash
+}
+
+
+def get_hash_fn(algo):
+    """
+    Return appropriate hash function for requested algorithm
+    :param algo: Algoritm to use
+    :return: Hash function
+    :rtype: function
+    """
+    return _HASH_ALGORITHMS.get(algo, legacy.legacy_hash)

splitio/hashfns/.ropeproject/history

@@ -0,0 +1,26 @@
+from __future__ import absolute_import, division, print_function, \
+    unicode_literals
+
+
+def as_int32(value):
+    if not -2147483649 <= value <= 2147483648:
+        return (value + 2147483648) % 4294967296 - 2147483648
+    return value
+
+
+def legacy_hash(key, seed):
+    """
+    Generates a hash for a key and a feature seed.
+    :param key: The key for which to get the hash
+    :type key: str
+    :param seed: The feature seed
+    :type seed: int
+    :return: The hash for the key and seed
+    :rtype: int
+    """
+    h = 0
+
+    for c in map(ord, key):
+        h = as_int32(as_int32(31 * as_int32(h)) + c)
+
+    return int(as_int32(h ^ as_int32(seed)))

splitio/hashfns/.ropeproject/objectdb

@@ -1,11 +1,7 @@
-"""
-This module contains hash functions implemented in pure python
-as well as the optional import (if installed) of a C compiled murmur hash
-function with python bindings.
-"""
 from __future__ import absolute_import, division, print_function, \
     unicode_literals
 
+
 import sys as _sys
 if (_sys.version_info > (3, 0)):
     def xrange(a, b, c):
@@ -72,56 +68,3 @@ def fmix(h):
 
     unsigned_val = fmix(h1 ^ length)
     return unsigned_val
-
-
-try:
-    # First attempt to import module with C++ core (faster)
-    import mmh3
-    from ctypes import c_uint
-
-    def _murmur_hash(key, seed):
-        ukey = key.encode('utf8')
-        return c_uint(mmh3.hash(ukey, seed)).value
-except:
-    # Fallback to interpreted python hash algoritm (slower)
-    _murmur_hash = murmur32_py
-
-
-def as_int32(value):
-    if not -2147483649 <= value <= 2147483648:
-        return (value + 2147483648) % 4294967296 - 2147483648
-    return value
-
-
-def _basic_hash(key, seed):
-    """
-    Generates a hash for a key and a feature seed.
-    :param key: The key for which to get the hash
-    :type key: str
-    :param seed: The feature seed
-    :type seed: int
-    :return: The hash for the key and seed
-    :rtype: int
-    """
-    h = 0
-
-    for c in map(ord, key):
-        h = as_int32(as_int32(31 * as_int32(h)) + c)
-
-    return int(as_int32(h ^ as_int32(seed)))
-
-
-_HASH_ALGORITHMS = {
-    'legacy': _basic_hash,
-    'murmur': _murmur_hash
-}
-
-
-def get_hash_fn(algo):
-    """
-    Return appropriate hash function for requested algorithm
-    :param algo: Algoritm to use
-    :return: Hash function
-    :rtype: function
-    """
-    return _HASH_ALGORITHMS.get(algo, _basic_hash)

splitio/hashfns/__init__.py

@@ -17,7 +17,7 @@
 from splitio.splits import Partition, HashAlgorithm
 from splitio.splitters import Splitter
 from splitio.treatments import CONTROL
-from splitio.hashfns import _basic_hash, _murmur_hash
+from splitio.hashfns import _HASH_ALGORITHMS
 from splitio.tests.utils import MockUtilsMixin, random_alphanumeric_string
 import io
 
@@ -118,37 +118,41 @@ def test_with_sample_data(self):
         """
         Tests basic hash against expected values using alphanumeric values
         """
+        hashfn = _HASH_ALGORITHMS['legacy']
         with open(join(dirname(__file__), 'sample-data.jsonl')) as f:
             for line in map(loads, f):
                 seed, key, hash_, bucket = line
-                self.assertEqual(int(hash_), _basic_hash(key, int(seed)))
+                self.assertEqual(int(hash_), hashfn(key, int(seed)))
     @skip
     def test_with_non_alpha_numeric_sample_data(self):
         """
         Tests basic hash against expected values using non alphanumeric values
         """
+        hashfn = _HASH_ALGORITHMS['legacy']
         with io.open(join(dirname(__file__), 'sample-data-non-alpha-numeric.jsonl'), 'r', encoding='utf-8') as f:
             for line in map(loads, f):
                 seed, key, hash_, bucket = line
-                self.assertEqual(int(hash_), _basic_hash(key, int(seed)))
+                self.assertEqual(int(hash_), hashfn(key, int(seed)))
 
     def test_murmur_with_sample_data(self):
         """
         Tests murmur32 hash against expected values using alphanumeric values
         """
+        hashfn = _HASH_ALGORITHMS['murmur']
         with open(join(dirname(__file__), 'murmur3-sample-data-v2.csv')) as f:
             for line in f:
                 seed, key, hash_, bucket = line.split(',')
-                self.assertEqual(int(hash_), _murmur_hash(key, int(seed)))
+                self.assertEqual(int(hash_), hashfn(key, int(seed)))
 
     def test_murmur_with_non_alpha_numeric_sample_data(self):
         """
         Tests murmur32 hash against expected values using non alphanumeric values
         """
+        hashfn = _HASH_ALGORITHMS['murmur']
         with io.open(join(dirname(__file__), 'murmur3-sample-data-non-alpha-numeric-v2.csv'), 'r', encoding='utf-8') as f:
             for line in f:
                 seed, key, hash_, bucket = line.split(',')
-                self.assertEqual(int(hash_), _murmur_hash(key, int(seed)))
+                self.assertEqual(int(hash_), hashfn(key, int(seed)))
 
 
 class SplitterGetBucketUnitTests(TestCase):