man/man-db-2.5.2-chinese.dif

--- src/encodings.c
+++ src/encodings.c	2008-08-12 15:26:22.959763175 +0200
@@ -106,6 +106,11 @@ static struct directory_entry directory_
 	{ "cs",		"ISO-8859-2",	"ISO-8859-2"		}, /* Czech */
 	{ "hr",		"ISO-8859-2",	"ISO-8859-2"		}, /* Croatian */
 	{ "hu",		"ISO-8859-2",	"ISO-8859-2"		}, /* Hungarian */
+	{ "zh_TW",	"BIG5",		"BIG5"			}, /* Traditional Chinese */
+	{ "zh_HK",	"BIG5HKSCS",	"BIG5HKSCS"		}, /* Traditional Chinese */
+	{ "zh_CN",	"GB18030",	"GB18030"		}, /* Simplified Chinese */
+	{ "zh_SG",	"GB18030",	"GB18030"		}, /* Simplified Chinese */
+	{ "zh",		"GB18030",	"GB18030"		}, /* Simplified Chinese */
 	{ "ja",		"EUC-JP",	"EUC-JP"		}, /* Japanese */
 	{ "ko",		"EUC-KR",	"EUC-KR"		}, /* Korean */
 	{ "pl",		"ISO-8859-2",	"ISO-8859-2"		}, /* Polish */
@@ -208,6 +213,7 @@ static struct charset_entry charset_tabl
 	{ "EUC-CN",		"nippon"	},
 	{ "EUC-JP",		"nippon"	},
 	{ "EUC-TW",		"nippon"	},
+	{ "GB18030",		"nippon"	},
 	{ "GBK",		"nippon"	},
 #endif /* MULTIBYTE_GROFF */
 
@@ -281,6 +287,7 @@ static struct less_charset_entry less_ch
 	{ "UTF-8",		"utf-8",	NULL		},
 
 #ifdef MULTIBYTE_GROFF
+	{ "GB18030",		"zh",		NULL		},
 	{ "EUC-JP",		"iso8859",	"japanese-ujis"	},
 	{ "KOI8-R",		"koi8-r",	NULL		},
 #endif /* MULTIBYTE_GROFF */
@@ -405,6 +412,13 @@ char *get_page_encoding (const char *lan
  *     roff encoding = UTF-8
  *     output encoding = UTF-8
  *     EUC-JP -> iconv -> UTF-8 -> groff -Tutf8 -> UTF-8
+ *
+ *   /usr/share/man/zh_CN.GB18030, locale zh_CN.UTF-8
+ *     page encoding = GB18030
+ *     source encoding = GB18030
+ *     roff encoding = UTF-8
+ *     output encoding = UTF-8
+ *     GB18030 -> iconv -> UTF-8 -> groff -Tutf8 -> UTF-8
  */
 const char *get_source_encoding (const char *lang)
 {
@@ -545,7 +559,7 @@ static int compatible_encodings (const c
 	 */
 	if ((STREQ (input, "BIG5") || STREQ (input, "BIG5HKSCS") ||
 	     STREQ (input, "EUC-JP") ||
-	     STREQ (input, "EUC-CN") || STREQ (input, "GBK") ||
+	     STREQ (input, "EUC-CN") || STREQ (input, "GB18030") || STREQ (input, "GBK") ||
 	     STREQ (input, "EUC-KR") ||
 	     STREQ (input, "EUC-TW")) &&
 	    STREQ (output, "UTF-8"))
@@ -639,7 +653,7 @@ const char *get_roff_encoding (const cha
 		    STRNEQ (ctype, "zh_HK", 5) ||
 		    STRNEQ (ctype, "zh_SG", 5) ||
 		    STRNEQ (ctype, "zh_TW", 5))
-			roff_encoding = "UTF-8";
+			roff_encoding = source_encoding; /* "UTF-8"; */
 	}
 #endif /* MULTIBYTE_GROFF */