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
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
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
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
|
#!/usr/bin/perl -w
# asm_count - count physical lines of code in Assembly programs.
# Usage: asm_count [-f file] [list_of_files]
# file: file with a list of files to count (if "-", read list from stdin)
# list_of_files: list of files to count
# -f file or list_of_files can be used, or both
# This is a trivial/naive program.
# For each file, it looks at the contents to heuristically determine
# if C comments are permitted and what the "comment" character is.
# If /* and */ are in the file, then C comments are permitted.
# The punctuation mark that starts the most lines must be the comment
# character (but ignoring "/" if C comments are allowed, and
# ignoring '#' if cpp commands appear to be used)
# This is part of SLOCCount, a toolsuite that counts
# source lines of code (SLOC).
# Copyright (C) 2001-2004 David A. Wheeler.
#
# This program is free software; you can redistribute it and/or modify
# it under the terms of the GNU General Public License as published by
# the Free Software Foundation; either version 2 of the License, or
# (at your option) any later version.
#
# This program is distributed in the hope that it will be useful,
# but WITHOUT ANY WARRANTY; without even the implied warranty of
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
# GNU General Public License for more details.
#
# You should have received a copy of the GNU General Public License
# along with this program; if not, write to the Free Software
# Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
#
# To contact David A. Wheeler, see his website at:
# http://www.dwheeler.com.
$total_sloc = 0;
# Do we have "-f" (read list of files from second argument)?
if (($#ARGV >= 1) && ($ARGV[0] eq "-f")) {
# Yes, we have -f
if ($ARGV[1] eq "-") {
# The list of files is in STDIN
while (<STDIN>) {
chomp ($_);
&count_file ($_);
}
} else {
# The list of files is in the file $ARGV[1]
open (FILEWITHLIST, $ARGV[1]) || die "Error: Could not open $ARGV[1]\n";
while (<FILEWITHLIST>) {
chomp ($_);
&count_file ($_);
}
close FILEWITHLIST;
}
shift @ARGV; shift @ARGV;
}
# Process all (remaining) arguments as file names
while ($file = shift @ARGV) {
&count_file ($file);
}
print "Total:\n";
print "$total_sloc\n";
sub count_file {
my ($file) = @_;
# First, use heuristics to determine the comment char and if it uses C comments
$found_c_start = 0;
$found_c_end = 0;
$cpp_suspicious = 0;
$cpp_likely = 0;
$cpp_used = 0;
%count = ();
if ($file eq "") {
*CURRENTFILE = *STDIN
} else {
open(CURRENTFILE, "<$file");
}
while (<CURRENTFILE>) {
if (m!\/\*!) { $found_c_start++;}
if (m!\*\/!) { $found_c_end++;}
if ( (m!^#\s*define\s!) || (m!^#\s*else!)) {$cpp_suspicious++;}
if ( (m!^#\s*ifdef\s!) || (m!^#\s*endif!) || (m!#\s*include!)) {$cpp_likely++;}
if (m/^\s*([;!\/#\@\|\*])/) { $count{$1}++; } # Found a likely comment char.
}
# Done examing file, let's figure out the parameters.
if ($found_c_start && $found_c_end) {
$ccomments = 1;
$count{'/'} = 0;
# $count{'*'} = 0; # Do this to ignore '*' if C comments are used.
} else {
$ccomments = 0;
}
if (($cpp_suspicious > 2) || ($cpp_likely >= 1)) {
$cpp_used = 1;
$count{'#'} = 0;
} else {
$cpp_used = 0;
}
$likeliest = ';';
$likeliest_count = 0;
foreach $i (keys(%count)) {
# print "DEBUG: key=$i count=$count{$i}\n";
if ($count{$i} > $likeliest_count) {
$likeliest = $i;
$likeliest_count = $count{$i};
}
}
# print "DEBUG: likeliest = $likeliest\n";
$commentchar=$likeliest;
close(CURRENTFILE);
# Now count SLOC.
$sloc = 0;
$isincomment = 0;
open(CURRENTFILE, "<$file");
while (<CURRENTFILE>) {
# We handle C comments first, so that if an EOL-comment
# occurs inside a C comment, it's ignored.
if ($ccomments) {
# Handle C /* */ comments; this will get fooled if they're in strings,
# but that would be rare in assembly.
while ( (m!\/\*!) || (m!\*\/!)) { # While unprocessed C comment.
if ($isincomment) {
s!.*?\*\/.*!!;
$isincomment = 0;
} else { # Not in C comment, but have end comment marker.
if (! m/\/\*/) { # Whups, there's no starting marker!
print STDERR "Warning: file $file line $. has unmatched comment end\n";
# Get us back to a plausible state:
s/.*//; # Destroy everything
$isincomment = 0;
} else {
if (! s!\/\*.*?\*\/!!) { # Try to delete whole comment.
# We couldn't delete whole comment. Delete what's there.
s!\/\*.*!!;
$isincomment = 1;
}
}
}
}
} # End of handling C comments.
# This requires $[ be unchanged.
$locate_comment = index($_, $commentchar);
if ($locate_comment >= 0) { # We found a comment character, delete comment
$_ = substr($_, 0, $locate_comment);
# print "DEBUG New text: @",$_,"@\n";
}
# old: s/${commentchar}.*//; # Delete leading comments.
# FOR DEBUG: print "Finally isincomment=$isincomment line=$_\n";
if ((! $isincomment) && (m/\S/)) {$sloc++;}
}
# End-of-file processing
print "$sloc (commentchar=$commentchar C-comments=$ccomments) $file\n";
$total_sloc += $sloc;
$sloc = 0;
if ($isincomment) {
print STDERR "Missing comment close in file $file\n";
}
}
|
