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
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
|
#!/usr/bin/env perl
#***************************************************************************
# _ _ ____ _
# Project ___| | | | _ \| |
# / __| | | | |_) | |
# | (__| |_| | _ <| |___
# \___|\___/|_| \_\_____|
#
# Copyright (C) Viktor Szakats
#
# This software is licensed as described in the file COPYING, which
# you should have received as part of this distribution. The terms
# are also available at https://curl.se/docs/copyright.html.
#
# You may opt to use, copy, modify, merge, publish, distribute and/or sell
# copies of the Software, and permit persons to whom the Software is
# furnished to do so, under the terms of the COPYING file.
#
# This software is distributed on an "AS IS" basis, WITHOUT WARRANTY OF ANY
# KIND, either express or implied.
#
# SPDX-License-Identifier: curl
#
###########################################################################
use strict;
use warnings;
my @tabs = (
"^m4/zz40-xc-ovr.m4",
"Makefile\\.(am|example)\$",
"\\.sln\$",
"^tests/data/data1706-stdout.txt",
"^tests/data/test",
);
my @need_crlf = (
"\\.(bat|sln)\$",
);
my @double_empty_lines = (
"RELEASE-NOTES",
"^lib/.+\\.(c|h)\$",
"^projects/OS400",
"^projects/vms",
"^tests/data/test",
"\\.(m4|py)\$",
);
my @non_ascii_allowed = (
'\xC3\xB6', # UTF-8 for https://codepoints.net/U+00F6 LATIN SMALL LETTER O WITH DIAERESIS
);
my $non_ascii_allowed = join(', ', @non_ascii_allowed);
my @non_ascii = (
".github/scripts/pyspelling.words",
".mailmap",
"RELEASE-NOTES",
"docs/BINDINGS.md",
"docs/THANKS",
"docs/THANKS-filter",
);
sub fn_match {
my ($filename, @masklist) = @_;
foreach my $mask (@masklist) {
if($filename =~ $mask) {
return 1;
}
}
return 0;
}
sub eol_detect {
my ($content) = @_;
my $cr = () = $content =~ /\r/g;
my $lf = () = $content =~ /\n/g;
if($cr > 0 && $lf == 0) {
return "cr";
}
elsif($cr == 0 && $lf > 0) {
return "lf";
}
elsif($cr == 0 && $lf == 0) {
return "bin";
}
elsif($cr == $lf) {
return "crlf";
}
return "";
}
my $issues = 0;
open(my $git_ls_files, '-|', 'git ls-files') or die "Failed running git ls-files: $!";
while(my $filename = <$git_ls_files>) {
chomp $filename;
open(my $fh, '<', $filename) or die "Cannot open '$filename': $!";
my $content = do { local $/; <$fh> };
close $fh;
my @err = ();
if(!fn_match($filename, @tabs) &&
$content =~ /\t/) {
push @err, "content: has tab";
}
my $eol = eol_detect($content);
if($eol eq "") {
push @err, "content: has mixed EOL types";
}
if($eol ne "crlf" &&
fn_match($filename, @need_crlf)) {
push @err, "content: must use CRLF EOL for this file type";
}
if($eol ne "lf" && $content ne "" &&
!fn_match($filename, @need_crlf)) {
push @err, "content: must use LF EOL for this file type";
}
if($content =~ /[ \t]\n/) {
my $line;
for my $l (split(/\n/, $content)) {
$line++;
if($l =~ /[ \t]$/) {
push @err, "line $line: trailing whitespace";
}
}
}
if($content ne "" &&
$content !~ /\n\z/) {
push @err, "content: has no EOL at EOF";
}
if($content =~ /\n\n\z/ ||
$content =~ /\r\n\r\n\z/) {
push @err, "content: has multiple EOL at EOF";
}
if(!fn_match($filename, @double_empty_lines)) {
if($content =~ /\n\n\n/ ||
$content =~ /\r\n\r\n\r\n/) {
my $line = 0;
my $blank = 0;
for my $l (split(/\n/, $content)) {
chomp $l;
$line++;
if($l =~ /^$/) {
if($blank) {
my $lineno = sprintf("duplicate empty line @ line %d", $line);
push @err, $lineno;
}
$blank = 1;
}
else {
$blank = 0;
}
}
}
}
if($content =~ /([\x00-\x08\x0b\x0c\x0e-\x1f\x7f])/) {
push @err, "content: has binary contents";
}
if($filename !~ /tests\/data/) {
# the tests have no allowed UTF bytes
$content =~ s/[$non_ascii_allowed]//g;
}
if(!fn_match($filename, @non_ascii) &&
($content =~ /([\x80-\xff]+)/)) {
my $non = $1;
my $hex;
for my $e (split(//, $non)) {
$hex .= sprintf("%s%02x", $hex ? " ": "", ord($e));
}
my $line;
for my $l (split(/\n/, $content)) {
$line++;
if($l =~ /([\x80-\xff]+)/) {
push @err, "line $line: has non-ASCII: '$non' ($hex)";
}
}
}
if(@err) {
$issues++;
foreach my $err (@err) {
print "$filename: $err\n";
}
}
}
close $git_ls_files;
if($issues) {
exit 1;
}
|
