Skip to content

Add a cache on top of python27 hashing #2724

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 8 commits into from
Dec 14, 2022
Merged

Add a cache on top of python27 hashing #2724

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
8 commits
Select commit Hold shift + click to select a range
397d361
Add a cache on top of python27 hashing functionality to reduce transf…
Dec 14, 2022
6d1376f
Fix type errors
Dec 14, 2022
7119af1
Merge branch 'develop' into cache_hash
acristin Dec 14, 2022
253b643
Merge branch 'develop' into cache_hash
acristin Dec 14, 2022
e95fb2d
Remove type hints that are no longer needed after decoration with lru…
Dec 14, 2022
636ca9d
Reorder isinstance checks
Dec 14, 2022
787dc54
Merge branch 'develop' into cache_hash
acristin Dec 14, 2022
8871ebf
Merge branch 'develop' into cache_hash
acristin Dec 14, 2022
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
11 changes: 7 additions & 4 deletions samtranslator/third_party/py27hash/hash.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2,10 +2,12 @@
Compatibility methods to support Python 2.7 style hashing in Python 3.X+

This is designed for compatibility not performance.

"""

import ctypes
import math
from functools import lru_cache


def hash27(value): # type: ignore[no-untyped-def]
Expand All @@ -19,7 +21,7 @@ def hash27(value): # type: ignore[no-untyped-def]
Python 2.7 hash
"""

return Hash.hash(value) # type: ignore[no-untyped-call]
return Hash.hash(value)


class Hash(object):
Expand All @@ -28,6 +30,7 @@ class Hash(object):
"""

@staticmethod
@lru_cache(maxsize=2048)
def hash(value): # type: ignore[no-untyped-def]
"""
Returns a Python 2.7 hash for a value.
Expand All @@ -39,14 +42,14 @@ def hash(value): # type: ignore[no-untyped-def]
Python 2.7 hash
"""

if isinstance(value, ("".__class__, bytes)) or type(value).__name__ == "buffer":
return Hash.shash(value) # type: ignore[no-untyped-call]
if isinstance(value, tuple):
return Hash.thash(value) # type: ignore[no-untyped-call]
if isinstance(value, float):
return Hash.fhash(value) # type: ignore[no-untyped-call]
if isinstance(value, int):
return hash(value)
if isinstance(value, ("".__class__, bytes)) or type(value).__name__ == "buffer":
return Hash.shash(value) # type: ignore[no-untyped-call]

raise TypeError("unhashable type: '%s'" % (type(value).__name__))

Expand All @@ -73,7 +76,7 @@ def thash(value): # type: ignore[no-untyped-def]
for y in value:
length -= 1

y = Hash.hash(y) # type: ignore[no-untyped-call]
y = Hash.hash(y)
x = (x ^ y) * mult
mult += 82520 + length + length

Expand Down
4 changes: 2 additions & 2 deletions samtranslator/utils/py27hash_fix.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -141,7 +141,7 @@ def __deepcopy__(self, memo): # type: ignore[no-untyped-def]
def _get_py27_hash(self): # type: ignore[no-untyped-def]
h = getattr(self, "_py27_hash", None)
if h is None:
self._py27_hash = h = ctypes.c_size_t(Hash.hash(self)).value # type: ignore[no-untyped-call]
self._py27_hash = h = ctypes.c_size_t(Hash.hash(self)).value
return h


Expand Down Expand Up @@ -198,7 +198,7 @@ def _get_key_idx(self, k): # type: ignore[no-untyped-def]
if isinstance(k, Py27UniStr):
h = k._get_py27_hash() # type: ignore[no-untyped-call]
else:
h = ctypes.c_size_t(Hash.hash(k)).value # type: ignore[no-untyped-call]
h = ctypes.c_size_t(Hash.hash(k)).value

i = h & self.mask

Expand Down