FilesExpand file tree

 master

/

bench_html.py

Copy path

Blame

More file actions

Blame

More file actions

Latest commit

 

History

History

History

57 lines (38 loc) · 1.53 KB

 master

/

bench_html.py

Copy path

Top

File metadata and controls

• Code
• Blame

57 lines (38 loc) · 1.53 KB

Raw

Copy raw file

Download raw file

Open symbols panel

Edit and raw actions

1

2

3

4

5

6

7

8

9

10

11

12

13

14

15

16

17

18

19

20

21

22

23

24

25

26

27

28

29

30

31

32

33

34

35

36

37

38

39

40

41

42

43

44

45

46

47

48

49

50

51

52

53

54

55

56

57

import io

import os

import sys

import pyperf

sys.path[0:0] = [os.path.join(os.path.dirname(__file__), "..")]

import html5lib # noqa: E402

def bench_parse(fh, treebuilder):

fh.seek(0)

html5lib.parse(fh, treebuilder=treebuilder, useChardet=False)

def bench_serialize(loops, fh, treebuilder):

fh.seek(0)

doc = html5lib.parse(fh, treebuilder=treebuilder, useChardet=False)

range_it = range(loops)

t0 = pyperf.perf_counter()

for loops in range_it:

html5lib.serialize(doc, tree=treebuilder, encoding="ascii", inject_meta_charset=False)

return pyperf.perf_counter() - t0

BENCHMARKS = ["parse", "serialize"]

def add_cmdline_args(cmd, args):

if args.benchmark:

cmd.append(args.benchmark)

if __name__ == "__main__":

runner = pyperf.Runner(add_cmdline_args=add_cmdline_args)

runner.metadata["description"] = "Run benchmarks based on Anolis"

runner.argparser.add_argument("benchmark", nargs="?", choices=BENCHMARKS)

args = runner.parse_args()

if args.benchmark:

benchmarks = (args.benchmark,)

else:

benchmarks = BENCHMARKS

with open(os.path.join(os.path.dirname(__file__), "data", "html.html"), "rb") as fh:

source = io.BytesIO(fh.read())

if "parse" in benchmarks:

for tb in ("etree", "dom", "lxml"):

runner.bench_func("html_parse_%s" % tb, bench_parse, source, tb)

if "serialize" in benchmarks:

for tb in ("etree", "dom", "lxml"):

runner.bench_time_func("html_serialize_%s" % tb, bench_serialize, source, tb)