#!/usr/bin/perl -w
+#
+# i18n-diff-auditor
+# Copyright (C)2018 Ian Jackson
+# GPLv3+, NO WARRANTY, see below.
+#
+#
+# Usage:
+# something like this
+# git-log -n1 -p | ./i18n-diff-auditor -D 2>&1 |less -j10 +/'^!.*'
+#
+# -D is for debug. Currently only one level.
+#
+# Output is the relevant diff hunks, with each line prepended with
+# space for ok lines and ! for questionable ones, and with relevant
+# diff lines prepended with lines starting !! (and lines starting #
+# for debug output), so ovrall:
+#
+# !! <message> reasoning for subsequent questionable diff line(s)
+# !+ diff line found to be questionable
+# !- diff line found to be questionable
+# @@@ etc. diff furniture
+# + diff line checked and ok
+# - diff line checked and ok
+# # <stuff> debug output (normally precedes relevant output)
+#
+# Changes are generally marked as ok if they correspond to a known
+# intended code change pattern. (That includes changing error calls
+# to different error calls.) If they don't correspond to any known
+# pattern, they are "questionable" and the first thing that doesn't
+# match the most common pattern is reported.
+#
+# Might be useful for projects other than dgit, provided it uses
+# the same gettext aliases (__ f_ i_) and similar error calls
+# (die, confess, fail).
+#
+#
+# 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 3 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, see <http://www.gnu.org/licenses/>.
+
use strict;
use Carp;
use Data::Dumper;
}{ $1 }xe) {
$o[$#o]{V} = $2;
} else {
- s{ \n (.*) }{ \n }s;
- $o[$#o]{V} = $1;
+ m{^.*\n} or confess;
+ $_ = $&;
+ $o[$#o]{V} = $';
$o[$#o]{Invented} = 1;
}
} elsif (s{^ (["'])( (?: [^\\'"]
push @o, { T => 'specvar', E => $&, P => $& };
} elsif (!length) {
last;
+ } elsif (s{^\#.*\n}{}) {
} else {
m{^.{0,10}};
die "cannot tokenise \`$&'";
our @analysed_y;
sub analyse_chunk_core () {
+ $before //= '';
die "plain deletion\n" unless defined $after;
- die "plain insertion\n" unless defined $before;
my @xs = semiparse $before;
my @ys = semiparse $after;
@analysed_x = @analysed_y = ();
my $next_x = sub { $next_something->(\@xs, \@analysed_x, \$x, 'before'); };
my $next_y = sub { $next_something->(\@ys, \@analysed_y, \$y, 'after' ); };
our @y_expect_suffix = ();
+ ANALYSE:
for (;;) {
while (my $e = shift @y_expect_suffix) {
$next_y->();
next if $x->{E} eq $y->{E};
next if $x->{E} eq 'sprintf' and $y->{E} eq 'f_';
next if $x->{E} eq 'die' and $y->{E} eq 'confess';
+ next if $x->{E} eq 'die' and $y->{E} eq 'fail';
+ foreach my $with_fh (qw(0 1)) {
+ next unless $x->{E} eq 'printf';
+ next unless $y->{E} eq 'print';
+ next unless @xs >= $with_fh;
+ next unless @ys > $with_fh;
+ if ($with_fh) {
+ next unless $xs[0]{E} eq $ys[0]{E};
+ next unless
+ $xs[0]{E} =~ m{^[A-Z]+$} or
+ $xs[0]{T} eq 'ident' && $xs[0]{E} =~ m{^\$};
+ }
+ next unless $ys[$with_fh]{E} eq 'f_';
+ # yay!
+ $next_x->() if $with_fh;
+ $next_y->() if $with_fh;
+ $next_y->(); # f_
+ next ANALYSE;
+ }
if ($y->{E} eq '+'
and @ys >= 3
and $ys[0]{E} eq '('
}
if ($ye eq 'f_') {
my $fmt = $y->{V};
- die "no percent in _f string\n" unless $fmt =~ m{\%};
+ die "no percent in f_ string\n" unless $fmt =~ m{\%};
next unless $string_changed;
die "f_ old string '-quoted\n" if $x->{Q} ne '"';
my $xs = $x->{V};