Skip to content

Commit

Permalink
strip literal '\x' from JSON output string, AlDanial#575
Browse files Browse the repository at this point in the history
  • Loading branch information
@AlDanial
AlDanial committed Mar 29, 2021
1 parent eded021 commit ed852a2
Show file tree
Hide file tree
Showing 2 changed files with 103 additions and 88 deletions.
100 changes: 56 additions & 44 deletions Unix/cloc
View file
Original file line number Diff line number Diff line change
Expand Up @@ -616,7 +616,7 @@ Usage: $script [options] <file(s)/dir(s)/git hash(es)> | <set 1> <set 2> | <repo
m meaning lines of comments
cm meaning lines of code + comments
Appending a percent sign to N changes
the calculation from straight count to
the calculation from straight count to
percentage.
Ignored with --diff or --by-file.
--sql=<file> Write results as SQL create and insert statements
Expand Down Expand Up @@ -1136,11 +1136,11 @@ die $brief_usage unless defined $opt_version or
$list_no_autogen or
scalar @ARGV >= 1;
if (!$opt_diff_list_file) {
die "--diff requires two arguments; got ", scalar @ARGV, "\n"
if $opt_diff and !$opt_sum_reports and scalar @ARGV != 2;
die "--diff arguments are identical; nothing done", "\n"
if $opt_diff and !$opt_sum_reports and scalar @ARGV == 2
and $ARGV[0] eq $ARGV[1];
die "--diff requires two arguments; got ", scalar @ARGV, "\n"
if $opt_diff and !$opt_sum_reports and scalar @ARGV != 2;
die "--diff arguments are identical; nothing done", "\n"
if $opt_diff and !$opt_sum_reports and scalar @ARGV == 2
and $ARGV[0] eq $ARGV[1];
}
trick_pp_packer_encode() if $ON_WINDOWS and $opt_file_encoding;
$File::Find::dont_use_nlink = 1 if $opt_stat or top_level_SMB_dir(\@ARGV);
Expand All @@ -1153,7 +1153,7 @@ my $nFiles_Found = 0; # updated in make_file_list
my (%Language_by_Extension, %Language_by_Script,
%Filters_by_Language, %Not_Code_Extension, %Not_Code_Filename,
%Language_by_File, %Scale_Factor, %Known_Binary_Archives,
%EOL_Continuation_re,
%Language_by_Prefix, %EOL_Continuation_re,
);
my $ALREADY_SHOWED_HEADER = 0;
my $ALREADY_SHOWED_XML_SECTION = 0;
Expand Down Expand Up @@ -1203,6 +1203,7 @@ if ($opt_force_lang_def) {
\%Language_by_Extension, # Language_by_Extension{f} = 'Fortran 77'
\%Language_by_Script , # Language_by_Script{sh} = 'Bourne Shell'
\%Language_by_File , # Language_by_File{makefile} = 'make'
\%Language_by_Prefix , # Language_by_Prefix{Dockerfile} = 'Dockerfile'
\%Filters_by_Language , # Filters_by_Language{Bourne Shell}[0] =
# [ 'remove_matches' , '^\s*#' ]
\%Not_Code_Extension , # Not_Code_Extension{jpg} = 1
Expand Down Expand Up @@ -1644,7 +1645,7 @@ my @files_removed_tot = ();
my @file_pairs_tot = ();
# make file lists for each separate argument
if ($opt_diff_list_file) {
@files_for_set = ( (), () );
@files_for_set = ( (), () );
file_pairs_from_file($opt_diff_list_file, # in
\@files_added_tot , # out
\@files_removed_tot , # out
Expand All @@ -1656,16 +1657,16 @@ if ($opt_diff_list_file) {
$upper_lower_map{$lc} = $F;
$F = $lc;
}
push @{$files_for_set[1]}, $F;
}
push @{$files_for_set[1]}, $F;
}
foreach my $F (@files_removed_tot) {
if ($ON_WINDOWS) {
(my $lc = lc $F) =~ s{\\}{/}g;
$upper_lower_map{$lc} = $F;
$F = $lc;
}
push @{$files_for_set[0]}, $F;
}
push @{$files_for_set[0]}, $F;
}
foreach my $pair (@file_pairs_tot) {
if ($ON_WINDOWS) {
push @{$files_for_set[0]}, lc $pair->[0];
Expand All @@ -1674,18 +1675,18 @@ if ($opt_diff_list_file) {
push @{$files_for_set[0]}, $pair->[0];
push @{$files_for_set[1]}, $pair->[1];
}
}
@ARGV = (1, 2); # place holders
}
@ARGV = (1, 2); # place holders
}
for (my $i = 0; $i < scalar @ARGV; $i++) {
if ($opt_diff_list_file) {
push @fh, make_file_list($files_for_set[$i],
if ($opt_diff_list_file) {
push @fh, make_file_list($files_for_set[$i],
\%Error_Codes, \@Errors, \%Ignored);
@{$files_for_set[$i]} = @file_list;
@{$files_for_set[$i]} = @file_list;
} else {
push @fh, make_file_list([ $ARGV[$i] ],
push @fh, make_file_list([ $ARGV[$i] ],
\%Error_Codes, \@Errors, \%Ignored);
@{$files_for_set[$i]} = @file_list;
@{$files_for_set[$i]} = @file_list;
}
if ($opt_exclude_list_file) {
# note: process_exclude_list_file() references global @file_list
Expand Down Expand Up @@ -1761,8 +1762,8 @@ my $n_filepairs_compared = 0;
my $tot_counted = 0;

if ( scalar @fh != 2 ) {
print "Error: incorrect length fh array when preparing diff at step 6.\n";
exit 1;
print "Error: incorrect length fh array when preparing diff at step 6.\n";
exit 1;
}
if (!$opt_diff_list_file) {
align_by_pairs(\%{$unique_source_file{$fset_a}} , # in
Expand Down Expand Up @@ -2117,7 +2118,7 @@ sub summary_cutoff_error { # {{{
sub apply_cutoff { # {{{1
my ($criterion,
$rhh_by_lang) = @_;

my %aggregated_Results_by_Language = ();
my $by_pct = 0;
my ($key, $value) = split(':', $criterion, 2);
Expand Down Expand Up @@ -2158,7 +2159,7 @@ sub apply_cutoff { # {{{1
$rhh_by_lang->{$lang}{'comment'} <= $value;
}
foreach my $category (qw(nFiles comment blank code)) {
$aggregated_Results_by_Language{$agg_lang}{$category} +=
$aggregated_Results_by_Language{$agg_lang}{$category} +=
$rhh_by_lang->{$lang}{$category};
}
}
Expand Down Expand Up @@ -5869,6 +5870,11 @@ sub classify_file { # {{{1
$look_at_first_line = 1;
}
}
# if all else fails look at the prefix instead of extension
( my $stem = $file ) =~ s/^(.*?)\.\S+$/$1/;
if ($stem and defined($Language_by_Prefix{$stem})) {
return $Language_by_Prefix{$stem}
}
} elsif (defined $Language_by_File{lc $file}) {
return $Language_by_File{lc $file};
} elsif ($opt_lang_no_ext and
Expand Down Expand Up @@ -6233,6 +6239,8 @@ sub write_file { # {{{1
sprintf "\"%s\":\"%s\"", $rh_options->{'columns'}[$i], $entries[$i];
}
if ($opt_json) {
# JSON can't literal '\x' in filenames, #575
$pairs[0] =~ s/\\x//g;
push @json_lines, join(", ", @pairs );
} else {
print $OUT "- {", join(", ", @pairs), "}\n";
Expand All @@ -6244,7 +6252,7 @@ sub write_file { # {{{1
}
}
if ($opt_json) {
print $OUT "[{", join("}, {", @json_lines), "}]\n";
print $OUT "[{", join("},\n {", @json_lines), "}]\n";
}
if (!$opt_json and !$opt_yaml and !$opt_xml and !$opt_csv) {
print $OUT join("\n", @lines), "\n";
Expand Down Expand Up @@ -6275,33 +6283,33 @@ sub file_pairs_from_file { # {{{1
#
# Example valid input format for $file
# 1)
# A/d1/hello.f90 | B/d1/hello.f90
# A/hello.C | B/hello.C
# A/d2/hi.py | B/d2/hi.py
# A/d1/hello.f90 | B/d1/hello.f90
# A/hello.C | B/hello.C
# A/d2/hi.py | B/d2/hi.py
#
# 2)
# Files added: 1
# + B/extra_file.pl ; Perl
#
# Files removed: 1
# - A/d2/hello.java ; Java
#
# File pairs compared: 3
# != A/d1/hello.f90 | B/d1/hello.f90 ; Fortran 90
# != A/hello.C | B/hello.C ; C++
# == A/d2/hi.py | B/d2/hi.py ; Python
# Files added: 1
# + B/extra_file.pl ; Perl
#
# Files removed: 1
# - A/d2/hello.java ; Java
#
# File pairs compared: 3
# != A/d1/hello.f90 | B/d1/hello.f90 ; Fortran 90
# != A/hello.C | B/hello.C ; C++
# == A/d2/hi.py | B/d2/hi.py ; Python

print "-> file_pairs_from_file($file)\n" if $opt_v and $opt_v > 2;
@{$ra_compare_list} = ();
my @lines = read_file($file);
my $mode = "compare";
foreach my $L (@lines) {
next if $L =~ /^\s*$/ or $L =~ /^\s*#/;
chomp($L);
chomp($L);
if ($L =~ /^Files\s+(added|removed):/) {
$mode = $1;
} elsif ($L =~ /^File\s+pairs\s+compared:/) {
$mode = "compare";
$mode = "compare";
} elsif ($mode eq "added" or $mode eq "removed") {
$L =~ m/^\s*[+-]\s+(.*?)\s+;/;
my $F = $1;
Expand All @@ -6316,7 +6324,7 @@ sub file_pairs_from_file { # {{{1
push @{$ra_removed}, $F;
}
} else {
$L =~ m/^\s*([!=]=\s*)?(.*?)\s*\|\s*(.*?)\s*(;.*?)?$/;
$L =~ m/^\s*([!=]=\s*)?(.*?)\s*\|\s*(.*?)\s*(;.*?)?$/;
if (!defined $2 or !defined $3) {
warn "file_pairs_from_file($file) parse failure\n",
"in compare mode for '$L', ignoring\n";
Expand Down Expand Up @@ -6807,8 +6815,8 @@ sub rm_comments_in_strings { # {{{1
$in_ml_string = 1;
}
elsif ( scalar @sub_token == 2 ) {
# The line has some more content after the string
# marker that starts a multiline string
# The line has some more content after the string
# marker that starts a multiline string
$t = $sub_token[0] . $firstpart_marker;
$sub_token[1] =~ s/\Q${start_comment}\E/xx/g;
$sub_token[1] =~ s/\Q${end_comment}\E/xx/g if $end_comment;
Expand Down Expand Up @@ -7483,6 +7491,7 @@ sub set_constants { # {{{1
my ($rh_Language_by_Extension , # out
$rh_Language_by_Script , # out
$rh_Language_by_File , # out
$rh_Language_by_Prefix , # out
$rhaa_Filters_by_Language , # out
$rh_Not_Code_Extension , # out
$rh_Not_Code_Filename , # out
Expand Down Expand Up @@ -8429,8 +8438,11 @@ sub set_constants { # {{{1
'Rakefile' => 'Ruby' ,
'rakefile' => 'Ruby' ,
'Dockerfile' => 'Dockerfile' ,
'Dockerfile.build' => 'Dockerfile' ,
'Dockerfile.test' => 'Dockerfile' ,
'Dockerfile.m4' => 'Dockerfile' ,
);
# 1}}}
%{$rh_Language_by_Prefix} = ( # {{{1
'Dockerfile' => 'Dockerfile' ,
);
# 1}}}
%{$rhaa_Filters_by_Language} = ( # {{{1
Expand Down
Loading

0 comments on commit ed852a2

Please sign in to comment.