From dc95919f41955987bc28c0f922f3949f0f0ed575 Mon Sep 17 00:00:00 2001
From: "YAMASHIRO, Jun" <yamajun@ofug.net>
Date: Sun, 11 May 2014 13:57:44 +0900
Subject: [PATCH] =?utf8?q?1be894d798e=20=E3=81=A7=E5=BF=98=E3=82=8C?=
 =?utf8?q?=E3=81=A6=E3=81=84=E3=81=9F=20wcount.pl=20=E3=81=AE=20UTF-8=20?=
 =?utf8?q?=E5=AF=BE=E5=BF=9C=E3=82=92=20commit=20=E3=81=97=E3=81=9F?=
 =?utf8?q?=E3=80=82?=
MIME-Version: 1.0
Content-Type: text/plain; charset=utf8
Content-Transfer-Encoding: 8bit

---
 script/wcount.pl | 91 ++++++++++++++++++++++----------------------------------
 1 file changed, 35 insertions(+), 56 deletions(-)

diff --git a/script/wcount.pl b/script/wcount.pl
index e8d4375..633953c 100755
--- a/script/wcount.pl
+++ b/script/wcount.pl
@@ -1,28 +1,29 @@
 #!/usr/bin/perl
 #
-# wcount.pl - ²­Æì¼­½ñ¤Îñ¸ì¿ô¤ò¥Õ¥¡¥¤¥ë¤´¤È¤Ë½¸·×
+# wcount.pl - 沖縄辞書の単語数をファイルごとに集計
 #
 #		$Id: wcount.pl,v 1.5 2002/06/16 04:31:52 void Exp $
 #
-#     # foreach i (*.dic)
-#		nkf -e $i | ./wcount.pl | wc -l
+#     # foreach i (../*.dic)
+#		cat $i | ./wcount.pl | wc -l
 #		echo $i
 #     end
 require 5.6.0;
+require 'ODIC.pm';
 use strict;
 our $phonate;
 our $word;
 our $class;
 
 while (<>) {
-	s/#.*$//;		# `#'°Ü¹Ô¤ò¼è¤êµî¤ë
-	next if (/^\s*$/);	# ¤½¤Î·ë²Ì¶õ¹Ô¤Ë¤Ê¤Ã¤¿¹Ô¤ÏÆɤßÈô¤Ð¤¹¡£
+	s/#.*$//;		# `#'以降を取り去る
+	next if (/^\s*$/);	# その結果空行になった行は読み飛ばす。
 	if (/(\S+)\s+(\S+)\s+(\S+)/) {
-		$phonate  = $1;	# Æɤß
-		$word = $2;	# ñ¸ì
-		$class = $3;	# ÉÊ»ì
-		&check_phonate;
-		&check_word;
+		$phonate = $1;	# 読み
+		$word    = $2;	# 単語
+		$class   = $3;	# 品詞
+		ODIC::check_phonate($phonate);
+		ODIC::check_word($word);
 		&check_class;
 	}
 	else {
@@ -33,99 +34,77 @@ while (<>) {
 exit 0;
 
 
-sub check_phonate
-{
-	if (length($phonate) > 40) {
-		print STDERR "Warning: $.: too long phonate `$phonate'\n";
-	}
-	if ($phonate =~ /[^¤¢¤¤¤¦¤¨¤ª¤«¤­¤¯¤±¤³¤µ¤·¤¹¤»¤½¤¿¤Á¤Ä¤Æ¤È¤Ê¤Ë¤Ì¤Í¤Î¤Ï¤Ò¤Õ¤Ø¤Û¤Þ¤ß¤à¤á¤â¤é¤ê¤ë¤ì¤í¤¬¤®¤°¤²¤´¤¶¤¸¤º¤¼¤¾¤À¤Â¤Å¤Ç¤É¤Ð¤Ó¤Ö¤Ù¤Ü¤¡¤£¤¥¤§¤©¤Ã¤ç¤ã¤å¤î¤Ñ¤Ô¤×¤Ú¤Ý¤ä¤æ¤è¤ï¤ò¤ó¥ô¡¼]/) {
-		print STDERR "Warning: $.: ilegal character in `$phonate'\n";
-	}
-}
-
-
-sub check_word
-{
-	if (length($word) > 64) {
-		print STDERR "Warning: $.: too long word `$word'\n";
-	}
-	if ($word =~ /[ \t",#]/) {
-		print STDERR "Warning: $.: ilegal character in `$word'\n";
-	}
-}
-
-
 sub check_class {
-	if ($class eq "ÉáÄÌ̾»ì") {
+	if ($class eq "普通名詞") {
 		print "$phonate\t$word\tclass\n";
 	}
-	elsif ($class eq "¥µÊÑ̾»ì") {
+	elsif ($class eq "サ変名詞") {
 		print "$phonate\t$word\tclass\n";
 	}
-	elsif ($class eq "·Áư̾»ì") {
+	elsif ($class eq "形動名詞") {
 		print "$phonate\t$word\tclass\n";
 	}
-	elsif ($class eq "À«") {
+	elsif ($class eq "姓") {
 		print "$phonate\t$word\tclass\n";
 	}
-	elsif ($class eq "̾") {
+	elsif ($class eq "名") {
 		print "$phonate\t$word\tclass\n";
 	}
-	elsif ($class eq "¤½¤Î¾¤Î¿Í̾") {
+	elsif ($class eq "その他の人名") {
 		print "$phonate\t$word\tclass\n";
 	}
-	elsif ($class eq "ñ½ãÃÏ̾") {
+	elsif ($class eq "単純地名") {
 		print "$phonate\t$word\tclass\n";
 	}
-	elsif ($class eq "ÀÜÈø¸ìÉÕ¤­ÃÏ̾") {
+	elsif ($class eq "接尾語付き地名") {
 		print "$phonate\t$word\tclass\n";
 	}
-	elsif ($class eq "ÁÈ¿¥Ì¾") {
+	elsif ($class eq "組織名") {
 		print "$phonate\t$word\tclass\n";
 	}
-	elsif ($class eq "¤½¤Î¾¸Çͭ̾»ì") {
+	elsif ($class eq "その他固有名詞") {
 		print "$phonate\t$word\tclass\n";
 	}
-	elsif ($class eq "Éû»ì") {
+	elsif ($class eq "副詞") {
 		print "$phonate\t$word\tclass\n";
 	}
-	elsif ($class eq "Àܳ»ì") {
+	elsif ($class eq "接続詞") {
 		print "$phonate\t$word\tclass\n";
 	}
-	elsif ($class eq "´¶Æ°»ì") {
+	elsif ($class eq "感動詞") {
 		print "$phonate\t$word\tclass\n";
 	}
-	elsif ($class eq "·ÁÍÆ»ì") {
+	elsif ($class eq "形容詞") {
 		print "$phonate\t$word\tclass\n";
 	}
-	elsif ($class eq "·ÁÍÆÆ°»ì") {
+	elsif ($class eq "形容動詞") {
 		print "$phonate\t$word\tclass\n";
 	}
-	elsif ($class eq "ÀÜƬ¸ì") {
+	elsif ($class eq "接頭語") {
 		print "$phonate\t$word\tclass\n";
 	}
-	elsif ($class eq "¿ô»úÎóÀÜƬ¸ì") {
+	elsif ($class eq "数字列接頭語") {
 		print "$phonate\t$word\tclass\n";
 	}
-	elsif ($class eq "ÀÜÈø¸ì") {
+	elsif ($class eq "接尾語") {
 		print "$phonate\t$word\tclass\n";
 	}
-	elsif ($class eq "¿Í̾ÀÜÈø¸ì") {
+	elsif ($class eq "人名接尾語") {
 		print "$phonate\t$word\tclass\n";
 	}
-	elsif ($class eq "ÃÏ̾ÀÜÈø¸ì") {
+	elsif ($class eq "地名接尾語") {
 		print "$phonate\t$word\tclass\n";
 	}
-	elsif ($class eq "ÁÈ¿¥Ì¾ÀÜÈø¸ì") {
+	elsif ($class eq "組織名接尾語") {
 		print "$phonate\t$word\tclass\n";
 	}
-	elsif ($class eq "¿ô»úÎóÀÜÈø¸ì") {
+	elsif ($class eq "数字列接尾語") {
 		print "$phonate\t$word\tclass\n";
 	}
-	elsif ($class eq "À®¶ç") {
+	elsif ($class eq "成句") {
 		print "$phonate\t$word\tclass\n";
 	}
-	elsif ($class eq "̵ÉÊ»ì") {
+	elsif ($class eq "無品詞") {
 		print "$phonate\t$word\tclass\n";
 	}
 	else {
-- 
2.11.0