tAdd dumptables option - transliterate - Transliteration engine
HTML git clone git://lumidify.org/transliterate.git (fast, but not encrypted)
HTML git clone https://lumidify.org/git/transliterate.git (encrypted, but very slow)
DIR Log
DIR Files
DIR Refs
DIR README
DIR LICENSE
---
DIR commit 30989566256dc25ac95db7b9ccaefd4a400cad2c
DIR parent a30baf4b4f41cf66cc9c7e9e9507291f698ac83c
HTML Author: lumidify <nobody@lumidify.org>
Date: Tue, 9 Mar 2021 08:59:56 +0100
Add dumptables option
Diffstat:
A .gitignore | 2 ++
M transliterate.pl | 23 +++++++++++++++++++++--
2 files changed, 23 insertions(+), 2 deletions(-)
---
DIR diff --git a/.gitignore b/.gitignore
t@@ -0,0 +1,2 @@
+ur.aff
+ur.dic
DIR diff --git a/transliterate.pl b/transliterate.pl
t@@ -943,6 +943,16 @@ sub interpret_config {
warn "ERROR: no file of words to ignore specified.\n";
return;
}
+ if ($args->{"dumptables"}) {
+ foreach my $table_id (keys %tables) {
+ my $table_path = $table_id_to_path{$table_id};
+ if ($config{"display_tables"}->{$table_path}) {
+ for my $word (keys %{$tables{$table_id}}) {
+ print NFC($word) . "\n";
+ }
+ }
+ }
+ }
return \%config;
}
t@@ -1452,7 +1462,7 @@ GetOptions(
"force", "start=i",
"output=s", "config=s",
"errors=s", "help",
- "checkduplicates") or pod2usage(1);
+ "checkduplicates", "dumptables") or pod2usage(1);
pod2usage(-exitval => 0, -verbose => 2) if $args{"help"};
pod2usage(-exitval => 1, -verbose => 1) if @ARGV > 1;
t@@ -1464,7 +1474,7 @@ my $config = load_config \%args;
if (!$config) {
die "ERROR: Invalid config\n";
}
-exit 0 if ($args{"checkduplicates"});
+exit 0 if ($args{"checkduplicates"} || $args{"dumptables"});
my $inputfh;
my $total_lines = "UNKNOWN";
t@@ -1572,6 +1582,15 @@ On that note, before duplicates are checked between tables in the
same replacement group, duplicates inside the same file are already
replaced, so that might be a bit confusing as well.
+=item B<--dumptables>
+
+Prints the words of all tables that don't have B<nodisplay> set.
+
+This is mainly meant to be used for generating word lists in order to
+use them in a spell checker. Note that the words printed here are in
+UTF-8 NFC (Unicode Canonical Composition Form), so it may not be ideal
+when the spellchecked text is not in the same form.
+
=item B<--nochoices>
Disables prompting for the right word when multiple replacement words exist.