annotate: optimize line counting
We used len(text.splitlines()) to count lines. This allocates, copies, and
deallocates an object for every line in a file. Instead, we use
count("\n") to count newlines and adjust based on whether there's a
trailing newline.
This improves the speed of annotating localrepo.py from 4.2 to 4.0
seconds.
--- a/mercurial/context.py Mon May 16 14:21:39 2016 -0700
+++ b/mercurial/context.py Wed May 18 16:37:32 2016 -0500
@@ -930,16 +930,20 @@
this returns fixed value(False is used) as linenumber,
if "linenumber" parameter is "False".'''
+ def lines(text):
+ if text.endswith("\n"):
+ return text.count("\n")
+ return text.count("\n") + 1
+
if linenumber is None:
def decorate(text, rev):
- return ([rev] * len(text.splitlines()), text)
+ return ([rev] * lines(text), text)
elif linenumber:
def decorate(text, rev):
- size = len(text.splitlines())
- return ([(rev, i) for i in xrange(1, size + 1)], text)
+ return ([(rev, i) for i in xrange(1, lines(text) + 1)], text)
else:
def decorate(text, rev):
- return ([(rev, False)] * len(text.splitlines()), text)
+ return ([(rev, False)] * lines(text), text)
def pair(parent, child):
blocks = mdiff.allblocks(parent[1], child[1], opts=diffopts,