mercurial/osutil.py

Take advantage of fstat calls clustering per directory if OS support it.

util module implements two versions of statfiles function

_statfiles calls lstat per file

_statfiles_clustered takes advantage of optimizations in osutil.c, stats all
files in directory at once when new directory is hit and caches the results

util.statfiles dispatches to appropriate version during module loading

The speedup on directory tree with 2k directories and 63k files is about
factor of 1.8 (1.3s -> 0.8s for hg diff - hg startup overhead about .2s)

At this point only Win32 now benefit from this patch.
Rest of OSes use the non clustered implementation.

import os
import stat as _stat

def _mode_to_kind(mode):
    if _stat.S_ISREG(mode): return _stat.S_IFREG
    if _stat.S_ISDIR(mode): return _stat.S_IFDIR
    if _stat.S_ISLNK(mode): return _stat.S_IFLNK
    if _stat.S_ISBLK(mode): return _stat.S_IFBLK
    if _stat.S_ISCHR(mode): return _stat.S_IFCHR
    if _stat.S_ISFIFO(mode): return _stat.S_IFIFO
    if _stat.S_ISSOCK(mode): return _stat.S_IFSOCK
    return mode

def listdir(path, stat=False, skip=None):
    '''listdir(path, stat=False) -> list_of_tuples

    Return a sorted list containing information about the entries
    in the directory.

    If stat is True, each element is a 3-tuple:

      (name, type, stat object)

    Otherwise, each element is a 2-tuple:

      (name, type)
    '''
    result = []
    prefix = path + os.sep
    names = os.listdir(path)
    names.sort()
    for fn in names:
        st = os.lstat(prefix + fn)
        if fn == skip and _stat.S_ISDIR(st.st_mode):
            return []
        if stat:
            result.append((fn, _mode_to_kind(st.st_mode), st))
        else:
            result.append((fn, _mode_to_kind(st.st_mode)))
    return result