support/scripts/size-stats-compare

   1 #!/usr/bin/env python
   2
   3 # Copyright (C) 2016 Thomas De Schampheleire <thomas.de.schampheleire@gmail.com>
   4
   5 # This program is free software; you can redistribute it and/or modify
   6 # it under the terms of the GNU General Public License as published by
   7 # the Free Software Foundation; either version 2 of the License, or
   8 # (at your option) any later version.
   9 #
  10 # This program is distributed in the hope that it will be useful,
  11 # but WITHOUT ANY WARRANTY; without even the implied warranty of
  12 # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
  13 # General Public License for more details.
  14 #
  15 # You should have received a copy of the GNU General Public License
  16 # along with this program; if not, write to the Free Software
  17 # Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
  18
  19 # TODO (improvements)
  20 # - support K,M,G size suffixes for threshold
  21 # - output CSV file in addition to stdout reporting
  22
  23 import csv
  24 import argparse
  25 import sys
  26
  27 def read_file_size_csv(inputf, detail=None):
  28     """Extract package or file sizes from CSV file into size dictionary"""
  29     sizes = {}
  30     reader = csv.reader(inputf)
  31
  32     header = next(reader)
  33     if (header[0] != 'File name' or header[1] != 'Package name' or
  34         header[2] != 'File size' or header[3] != 'Package size'):
  35         print(("Input file %s does not contain the expected header. Are you "
  36                "sure this file corresponds to the file-size-stats.csv "
  37                "file created by 'make graph-size'?") % inputf.name)
  38         sys.exit(1)
  39
  40     for row in reader:
  41         if detail:
  42             sizes[row[0]] = int(row[2])
  43         else:
  44             sizes[row[1]] = int(row[3])
  45
  46     return sizes
  47
  48 def compare_sizes(old, new):
  49     """Return delta/added/removed dictionaries based on two input size
  50     dictionaries"""
  51     delta = {}
  52     oldkeys = set(old.keys())
  53     newkeys = set(new.keys())
  54
  55     # packages/files in both
  56     for entry in newkeys.intersection(oldkeys):
  57         delta[entry] = ('', new[entry] - old[entry])
  58     # packages/files only in new
  59     for entry in newkeys.difference(oldkeys):
  60         delta[entry] = ('added', new[entry])
  61     # packages/files only in old
  62     for entry in oldkeys.difference(newkeys):
  63         delta[entry] = ('removed', -old[entry])
  64
  65     return delta
  66
  67 def print_results(result, threshold):
  68     """Print the given result dictionary sorted by size, ignoring any entries
  69     below or equal to threshold"""
  70
  71     from six import iteritems
  72     list_result = list(iteritems(result))
  73     # result is a dictionary: name -> (flag, size difference)
  74     # list_result is a list of tuples: (name, (flag, size difference))
  75
  76     for entry in sorted(list_result, key=lambda entry: entry[1][1]):
  77         if threshold is not None and abs(entry[1][1]) <= threshold:
  78             continue
  79         print('%12s %7s %s' % (entry[1][1], entry[1][0], entry[0]))
  80
  81
  82 # main #########################################################################
  83
  84 description = """
  85 Compare rootfs size between Buildroot compilations, for example after changing
  86 configuration options or after switching to another Buildroot release.
  87
  88 This script compares the file-size-stats.csv file generated by 'make graph-size'
  89 with the corresponding file from another Buildroot compilation.
  90 The size differences can be reported per package or per file.
  91 Size differences smaller or equal than a given threshold can be ignored.
  92 """
  93
  94 parser = argparse.ArgumentParser(description=description,
  95                                  formatter_class=argparse.RawDescriptionHelpFormatter)
  96
  97 parser.add_argument('-d', '--detail', action='store_true',
  98                     help='''report differences for individual files rather than
  99                             packages''')
 100 parser.add_argument('-t', '--threshold', type=int,
 101                     help='''ignore size differences smaller or equal than this
 102                             value (bytes)''')
 103 parser.add_argument('old_file_size_csv', type=argparse.FileType('r'),
 104                     metavar='old-file-size-stats.csv',
 105                     help="""old CSV file with file and package size statistics,
 106                             generated by 'make graph-size'""")
 107 parser.add_argument('new_file_size_csv', type=argparse.FileType('r'),
 108                     metavar='new-file-size-stats.csv',
 109                     help='new CSV file with file and package size statistics')
 110 args = parser.parse_args()
 111
 112 if args.detail:
 113     keyword = 'file'
 114 else:
 115     keyword = 'package'
 116
 117 old_sizes = read_file_size_csv(args.old_file_size_csv, args.detail)
 118 new_sizes = read_file_size_csv(args.new_file_size_csv, args.detail)
 119
 120 delta = compare_sizes(old_sizes, new_sizes)
 121
 122 print('Size difference per %s (bytes), threshold = %s' % (keyword, args.threshold))
 123 print(80*'-')
 124 print_results(delta, args.threshold)
 125 print(80*'-')
 126 print_results({'TOTAL': ('', sum(new_sizes.values()) - sum(old_sizes.values()))},
 127               threshold=None)