Skip to content

Benchmark improvements #44

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

Open
wants to merge 3 commits into
base: master
Choose a base branch
from
Open

Benchmark improvements #44

Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
d4a3d54
Clarify benchmark results table
rtobar May 20, 2020
f972eb6
De-duplicate common functionality in benchmark
rtobar May 20, 2020
f329d36
Fix comparison with ijson's items functions
rtobar May 20, 2020
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
66 changes: 30 additions & 36 deletions benchmark.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -64,78 +64,72 @@ def __exit__(self, *args):

results = []

def _assert_items(parser, item_getter=lambda x: x, item_key='id'):
n = 0
for n, item in enumerate(parser):
assert(item_getter(item)[item_key] == n)
assert(n + 1 == args.json_size)

with TestCase('json.loads()', 'str', args.json_size, results):
for n, item in enumerate(json.loads(jsondata)['level1']['level2']):
assert(item['id'] == n)
_assert_items(json.loads(jsondata)['level1']['level2'])

with TestCase('json.load(StringIO())', 'str', args.json_size, results):
gen = io.StringIO(jsondata)
for n, item in enumerate(json.load(gen)['level1']['level2']):
assert(item['id'] == n)
_assert_items(json.load(gen)['level1']['level2'])

with TestCase('**JsonSlicer (no paths, binary input, binary output)**', 'bytes', args.json_size, results):
with TestCase('**JsonSlicer (no paths, binary input)**', 'bytes', args.json_size, results):
gen = io.BytesIO(jsondata.encode('utf-8'))
parser = JsonSlicer(gen, (b'level1', b'level2', None), binary=True)
for n, item in enumerate(parser):
assert(item[b'id'] == n)
_assert_items(parser, item_key=b'id')

with TestCase('**JsonSlicer (no paths, unicode input, binary output)**', 'bytes', args.json_size, results):
with TestCase('**JsonSlicer (no paths, unicode input)**', 'bytes', args.json_size, results):
gen = io.StringIO(jsondata)
parser = JsonSlicer(gen, (b'level1', b'level2', None), binary=True)
for n, item in enumerate(parser):
assert(item[b'id'] == n)
_assert_items(parser, item_key=b'id')

with TestCase('**JsonSlicer (no paths, binary input, unicode output)**', 'str', args.json_size, results):
with TestCase('**JsonSlicer (no paths, binary input)**', 'str', args.json_size, results):
gen = io.BytesIO(jsondata.encode('utf-8'))
parser = JsonSlicer(gen, ('level1', 'level2', None))
for n, item in enumerate(parser):
assert(item['id'] == n)
_assert_items(parser)

with TestCase('**JsonSlicer (no paths, unicode input, unicode output)**', 'str', args.json_size, results):
with TestCase('**JsonSlicer (no paths, unicode input)**', 'str', args.json_size, results):
gen = io.StringIO(jsondata)
parser = JsonSlicer(gen, ('level1', 'level2', None))
for n, item in enumerate(parser):
assert(item['id'] == n)
_assert_items(parser)

with TestCase('**JsonSlicer (full paths, binary output)**', 'bytes', args.json_size, results):
with TestCase('**JsonSlicer (full paths)**', 'bytes', args.json_size, results):
gen = io.BytesIO(jsondata.encode('utf-8'))
parser = JsonSlicer(gen, (b'level1', b'level2', None), path_mode='full', binary=True)
for n, (*path, item) in enumerate(parser):
assert(item[b'id'] == n)
_assert_items(parser, item_getter=lambda x: x[-1], item_key=b'id')

with TestCase('**JsonSlicer (full paths, unicode output)**', 'str', args.json_size, results):
with TestCase('**JsonSlicer (full paths)**', 'str', args.json_size, results):
gen = io.StringIO(jsondata)
parser = JsonSlicer(gen, ('level1', 'level2', None), path_mode='full')
for n, (*path, item) in enumerate(parser):
assert(item['id'] == n)
_assert_items(parser, item_getter=lambda x: x[-1])

with TestCase('ijson.yajl2_c', 'bytes', args.json_size, results):
with TestCase('ijson.yajl2_c', 'str', args.json_size, results):
gen = io.BytesIO(jsondata.encode('utf-8'))
parser = ijson_yajl2_c.items(gen, b'level1.level2.item')
for n, item in enumerate(parser):
assert(item['id'] == n)
parser = ijson_yajl2_c.items(gen, 'level1.level2.item')
_assert_items(parser)

with TestCase('ijson.yajl2_cffi', 'bytes', args.json_size, results):
with TestCase('ijson.yajl2_cffi', 'str', args.json_size, results):
gen = io.BytesIO(jsondata.encode('utf-8'))
parser = ijson_yajl2_cffi.items(gen, b'level1.level2.item')
for n, item in enumerate(parser):
assert(item['id'] == n)
parser = ijson_yajl2_cffi.items(gen, 'level1.level2.item')
_assert_items(parser)

with TestCase('ijson.yajl2', 'bytes', args.json_size, results):
with TestCase('ijson.yajl2', 'str', args.json_size, results):
gen = io.BytesIO(jsondata.encode('utf-8'))
parser = ijson_yajl2.items(gen, 'level1.level2.item')
for n, item in enumerate(parser):
assert(item['id'] == n)
_assert_items(parser)

with TestCase('ijson.python', 'str', args.json_size, results):
gen = io.StringIO(jsondata)
parser = ijson_python.items(gen, 'level1.level2.item')
for n, item in enumerate(parser):
assert(item['id'] == n)
_assert_items(parser)

print(tabulate(
results,
headers=['Facility', 'Type', 'Objects/sec'],
headers=['Facility', 'Output type', 'Objects/sec'],
stralign='right',
# colalign=['left', 'center', 'right'],
tablefmt='pipe'
Expand Down