Make genlang faster by doing better regexes.
With this change generating all languages takes only two-thirds the time. It changes the acceptable syntax for target wildcards in language files, however: instead of a comma-separated list of glob-style wildcards it requires that it be a comma-separated list of prefix matches, i.e. the * can only appear at the end of each wildcard, and ? cannot be used. This does not require any changes to existing language files as they are all already in this form. git-svn-id: svn://svn.rockbox.org/rockbox/trunk@30481 a1c6a512-1295-4272-9138-f99709370657
This commit is contained in:
parent
87daeae7c2
commit
82acdd3e1c
1 changed files with 21 additions and 16 deletions
|
@ -121,7 +121,23 @@ if(!$target && !$update && !$sortfile) {
|
||||||
print STDERR "Please specify a target (with -t)!\n";
|
print STDERR "Please specify a target (with -t)!\n";
|
||||||
exit;
|
exit;
|
||||||
}
|
}
|
||||||
my @target_parts = split ':', $target;
|
|
||||||
|
# Build up a regex which can be applied to target wildcard lists. We only need
|
||||||
|
# to support prefix matches, so a target parameter of foo:bar can be expanded
|
||||||
|
# to the regex "\*|f\*|fo\*|foo|b\*|ba\*|bar" and applied to the wildcard list
|
||||||
|
# (plus end-of-string or commas on either side). The regex engine should
|
||||||
|
# discard any duplicates generated for us in the process of constructing the
|
||||||
|
# state machine, so we don't bother to check.
|
||||||
|
my $target_regex = "(?:^|,) *(?:\\*";
|
||||||
|
foreach my $target_part (split ':', $target) {
|
||||||
|
for (my $c=1; $c<length $target_part; $c++) {
|
||||||
|
my $partial = substr $target_part, 0, $c;
|
||||||
|
$target_regex .= "|$partial\\*";
|
||||||
|
}
|
||||||
|
$target_regex .= "|$target_part";
|
||||||
|
}
|
||||||
|
$target_regex .= ") *(?:,|\$)";
|
||||||
|
$target_regex = qr/$target_regex/;
|
||||||
|
|
||||||
my $binpath = "";
|
my $binpath = "";
|
||||||
if ($binary =~ m|(.*)/[^/]+|) {
|
if ($binary =~ m|(.*)/[^/]+|) {
|
||||||
|
@ -178,21 +194,10 @@ sub options {
|
||||||
sub parsetarget {
|
sub parsetarget {
|
||||||
my ($debug, $strref, $full, $n, $v)=@_;
|
my ($debug, $strref, $full, $n, $v)=@_;
|
||||||
my $string;
|
my $string;
|
||||||
my @all= split(" *, *", $n);
|
if ($n =~ $target_regex) {
|
||||||
my $test;
|
$string = $v;
|
||||||
for $test (@all) {
|
$$strref = $string;
|
||||||
$test =~ s/\*/.*/g;
|
return $string;
|
||||||
$test =~ s/\?/./g;
|
|
||||||
|
|
||||||
# print "TEST ($debug) $target for $test\n";
|
|
||||||
for my $part (@target_parts) {
|
|
||||||
if($part =~ /^$test\z/) {
|
|
||||||
$string = $v;
|
|
||||||
# print "MATCH: $test => $v\n";
|
|
||||||
$$strref = $string;
|
|
||||||
return $string;
|
|
||||||
}
|
|
||||||
}
|
|
||||||
}
|
}
|
||||||
}
|
}
|
||||||
|
|
||||||
|
|
Loading…
Reference in a new issue