GeezerVison is showing github.com — cpython/Tools/scripts/byext.py at 3.7 · python/cpython

Expand file tree

byext.py

Copy path

More file actions

Latest commit

History

executable file

132 lines (116 loc) · 3.81 KB

byext.py

Copy path

File metadata and controls

executable file

132 lines (116 loc) · 3.81 KB

Raw

Copy raw file

Download raw file

Open symbols panel

Edit and raw actions

100

101

102

103

104

105

106

107

108

109

110

111

112

113

114

115

116

117

118

119

120

121

122

123

124

125

126

127

128

129

130

131

132

#! /usr/bin/env python3

"""Show file statistics by extension."""

import os

import sys

class Stats:

def __init__(self):

self.stats = {}

def statargs(self, args):

for arg in args:

if os.path.isdir(arg):

self.statdir(arg)

elif os.path.isfile(arg):

self.statfile(arg)

else:

sys.stderr.write("Can't find %s\n" % arg)

self.addstats("<???>", "unknown", 1)

def statdir(self, dir):

self.addstats("<dir>", "dirs", 1)

try:

names = os.listdir(dir)

except OSError as err:

sys.stderr.write("Can't list %s: %s\n" % (dir, err))

self.addstats("<dir>", "unlistable", 1)

return

for name in sorted(names):

if name.startswith(".#"):

continue # Skip CVS temp files

if name.endswith("~"):

continue # Skip Emacs backup files

full = os.path.join(dir, name)

if os.path.islink(full):

self.addstats("<lnk>", "links", 1)

elif os.path.isdir(full):

self.statdir(full)

else:

self.statfile(full)

def statfile(self, filename):

head, ext = os.path.splitext(filename)

head, base = os.path.split(filename)

if ext == base:

ext = "" # E.g. .cvsignore is deemed not to have an extension

ext = os.path.normcase(ext)

if not ext:

ext = "<none>"

self.addstats(ext, "files", 1)

try:

with open(filename, "rb") as f:

data = f.read()

except IOError as err:

sys.stderr.write("Can't open %s: %s\n" % (filename, err))

self.addstats(ext, "unopenable", 1)

return

self.addstats(ext, "bytes", len(data))

if b'\0' in data:

self.addstats(ext, "binary", 1)

return

if not data:

self.addstats(ext, "empty", 1)

# self.addstats(ext, "chars", len(data))

lines = str(data, "latin-1").splitlines()

self.addstats(ext, "lines", len(lines))

del lines

words = data.split()

self.addstats(ext, "words", len(words))

def addstats(self, ext, key, n):

d = self.stats.setdefault(ext, {})

d[key] = d.get(key, 0) + n

def report(self):

exts = sorted(self.stats)

# Get the column keys

columns = {}

for ext in exts:

columns.update(self.stats[ext])

cols = sorted(columns)

colwidth = {}

colwidth["ext"] = max(map(len, exts))

minwidth = 6

self.stats["TOTAL"] = {}

for col in cols:

total = 0

cw = max(minwidth, len(col))

for ext in exts:

value = self.stats[ext].get(col)

if value is None:

w = 0

else:

w = len("%d" % value)

total += value

cw = max(cw, w)

cw = max(cw, len(str(total)))

colwidth[col] = cw

self.stats["TOTAL"][col] = total

exts.append("TOTAL")

for ext in exts:

self.stats[ext]["ext"] = ext

cols.insert(0, "ext")

def printheader():

for col in cols:

print("%*s" % (colwidth[col], col), end=' ')

print()

printheader()

for ext in exts:

for col in cols:

value = self.stats[ext].get(col, "")

print("%*s" % (colwidth[col], value), end=' ')

print()

printheader() # Another header at the bottom

def main():

args = sys.argv[1:]

if not args:

args = [os.curdir]

s = Stats()

s.statargs(args)

s.report()

if __name__ == "__main__":

main()