sb-languages.rc

这是一个从音频信号里提取特征参量的程序

# Arabic email
:0
* ARABIC ?? no
* LANGFILTER ?? yes
{
 :0
 *  ^(Content-Type:((.*$)+|.*; )charset[ ]?=[ ]?.?(iso.8859-6|windows-1256)([^a-z0-9\.]|$)|\
      (From|To|Message-ID):.*(iso.8859-6|windows-1256)([^a-z0-9\.]|$))
 { ARB=yes }

 :0
 * LEANTAG ?? no
 * !ARB ?? yes
 {
 :0 B
  * !--.*forwarded message --
  * !^forwarded message:
  * !^-----BEGIN PGP SIGNED MESSAGE-----
  * -1000^0
  *  -500^0   ^Subject: Re:
  *  -200^1   ^[:;#>]
  *  1100^0   ^Content-Type: text/(html|plain)((.*$)+|.*; )charset[ ]?=[ ]?.?(iso.8859-6|windows-1256).?$
  { ARB=yes }
 }

 :0
 * ARB ?? yes
 {
  :0 f
  | ${FORMAIL} -A"X-SBRule: Arabic (iso-8859-6|windows-1256)"

  :0
  { BLOCKTAG=yes }

  :0
  * BLOCKREPLY ?? NOTIFY
  { BLOCKTHIS=yes }
 }
}

# Chinese email
:0
* CHINESE ?? no
* LANGFILTER ?? yes
{
 :0
 *  ^(Content-Type:((.*$)+|.*; )charset[ ]?=[ ]?.?(hz-)?(big5|gb-?1988|gb-?2312)([^a-z0-9\.]|$)|\
      (From|To|Message-ID):.*(hz-)?(big5|gb-?1988|gb-?2312)([^a-z0-9\.]|$)|\
      Subject:.*(hz-)?(big5|gb-?1988|gb-?2312))
 { CN=yes }

 :0 HB
 *  charset[ ]?=[ ]?.?(hz-)?(big5|gb-?1988|gb-?2312)
 { CN=yes }

 :0
 * LEANTAG ?? no
 * CN ?? no
 {
  :0 B
  * !--.*forwarded message --
  * !^forwarded message:
  * !^-----BEGIN PGP SIGNED MESSAGE-----
  * -1000^0
  *  -500^0   ^Subject: Re:
  *  -200^1   ^[:;#>]
  *  1100^0   ^Content-Type: text/(html|plain)((.*$)+|.*; )charset[ ]?=[ ]?.?(hz-)?(big5|gb-?1988|gb-?2312)([^a-z0-9\.]|$)
  { CN=yes }
 }

 :0
 * CN ?? yes
 {
  :0 f
  | ${FORMAIL} -A"X-SBRule: Chinese (big5|gb1988|gb2312)"

  :0
  { BLOCKTAG=yes }

  :0
  * BLOCKREPLY ?? NOTIFY
  { BLOCKTHIS=yes }
 }
}

# Cyrillic email
:0
* CYRILLIC ?? no
* LANGFILTER ?? yes
{
 :0
 *  ^(Content-Type:((.*$)+|.*; )charset[ ]?=[ ]?.?(ecma.cyrillic|inis.cyrillic|iso.5427|iso.8859-5)([^a-z0-9\.]|$)|\
      (From|To|Message-ID):.*(ecma.cyrillic|inis.cyrillic|iso.5427|iso.8859-5)([^a-z0-9\.]|$))
 { CYR=yes }

 :0
 * LEANTAG ?? no
 * !CYR ?? yes
 {
  :0 B
  * !--.*forwarded message --
  * !^forwarded message:
  * !^-----BEGIN PGP SIGNED MESSAGE-----
  * -1000^0
  *  -500^0   ^Subject: Re:
  *  -200^1   ^[:;#>]
  *  1100^0   ^Content-Type: text/(html|plain)((.*$)+|.*; )charset[ ]?=[ ]?.?(ecma.cyrillic|inis.cyrillic|iso.5427|iso.8859-5).?$
  { CYR=yes }
 }

 :0
 * CYR ?? yes
 {
  :0 f
  | ${FORMAIL} -A"X-SBRule: Cyrillic Alphabet (ecma-cyrillic|inis-cyrillic|iso-5427|iso-8859-5)"

  :0
  { BLOCKTAG=yes }

  :0
  * BLOCKREPLY ?? NOTIFY
  { BLOCKTHIS=yes }
 }
}

# Greek email
:0
* GREEK ?? no
* LANGFILTER ?? yes
{
 :0
 *  ^(Content-Type:((.*$)+|.*; )charset[ ]?=[ ]?.?(greek-ccitt|greek7|greek7-old|iso.5428|iso.8859-7|windows-1253)([^a-z0-9\.]|$)|\
      (From|To|Message-ID):.*(greek-ccitt|greek7|greek7-old|iso.5428|iso.8859-7|windows-1253)([^a-z0-9\.]|$))
 { GRK=yes }

 :0 B
 * LEANTAG ?? no
 * !GRK ?? yes
 {
  :0 B
  * !--.*forwarded message --
  * !^forwarded message:
  * !^-----BEGIN PGP SIGNED MESSAGE-----
  * -1000^0
  *  -500^0   ^Subject: Re:
  *  -200^1   ^[:;#>]
  *  1100^0   ^Content-Type: text/(html|plain)((.*$)+|.*; )charset[ ]?=[ ]?.?(greek-ccitt|greek7|greek7-old|iso.5428|iso.8859-7|windows-1253).?$
  { GRK=yes }
 }

 :0
 * GRK ?? yes
 {
  :0 f
  | ${FORMAIL} -A"X-SBRule: Greek (greek-ccitt|greek7|iso-5428|iso-8859-7|windows-1253)"

  :0
  { BLOCKTAG=yes }

  :0
  * BLOCKREPLY ?? NOTIFY
  { BLOCKTHIS=yes }
 }
}


# Hebrew email
:0
* HEBREW ?? no
* LANGFILTER ?? yes
{
 :0
 *  ^(Content-Type:((.*$)+|.*; )charset[ ]?=[ ]?.?(iso.8859-8|windows-1255)([^a-z0-9\.]|$)|\
      (From|To|Message-ID):.*(iso.8859-8|windows-1255)([^a-z0-9\.]|$))
 { HBRW=yes }

 :0
 * LEANTAG ?? no
 * !HBRW ?? yes
 {
  :0 B
  * !--.*forwarded message --
  * !^forwarded message:
  * !^-----BEGIN PGP SIGNED MESSAGE-----
  * -1000^0
  *  -500^0   ^Subject: Re:
  *  -200^1   ^[:;#>]
  *  1100^0   ^Content-Type: text/(html|plain)((.*$)+|.*; )charset[ ]?=[ ]?.?(iso.8859-8|windows-1255).?$
  { HBRW=yes }
 }

 :0
 * HBRW ?? yes
 {
  :0 f
  | ${FORMAIL} -A"X-SBRule: Hebrew (iso-8859-8|windows-1255)"

  :0
  { BLOCKTAG=yes }

  :0
  * BLOCKREPLY ?? NOTIFY
  { BLOCKTHIS=yes }
 }
}


# Japanese ISO 2022, jis C622, jis x0201, and other charset email
:0
* JAPANESE ?? no
* LANGFILTER ?? yes
{
 :0
 *  ^(Content-Type:((.*$)+|.*; )charset[ ]?=[ ]?.?(iso-2022-jp|jis.C6220|JIS_C622[0-9]|jis.x0201|shift.jis|windows.31j)|\
      (From|To|Message-ID):.*(iso-2022-jp|jis.C622[0-9]|jis.x0201|shift.jis|windows.31j))
 { JP=yes }

 :0
 * LEANTAG ?? no
 * !JP ?? yes
 {
  :0 B
  * !--.*forwarded message --
  * !^forwarded message:
  * !^-----BEGIN PGP SIGNED MESSAGE-----
  * -1000^0
  *  -500^0   ^Subject: Re:
  *  -200^1   ^[:;#>]
  *  1100^0   ^Content-Type: text/(html|plain)((.*$)+|.*; )charset[ ]?=[ ]?.?(iso-2022-jp|jis.C622[0-9]|jis.x0201|shift.jis|windows.31j)[-_a-z0-9]*.?$
  { JP=yes }
 }

 :0
 * JP ?? yes
 {
  :0 f
  | ${FORMAIL} -A"X-SBRule: Japanese (iso-2022-jp|jis-c622[0-9]|jis-x020|shift-jis|windows-31j)"

  :0
  { BLOCKTAG=yes }

  :0
  * BLOCKREPLY ?? NOTIFY
  { BLOCKTHIS=yes }
 }
}

# Korean email
:0
* KOREAN ?? no
* LANGFILTER ?? yes
{
 :0
 *  ^(Content-Type:((.*$)+|.*; )charset[ ]?=[ ]?.?(euc-kr|iso-2022-kr|ks.c.5601-198[79])([^a-z0-9\.]|$)|\
      (From|To|Message-ID):.*(euc-kr|iso-2022-kr|ks.c.5601-198[79])([^a-z0-9\.]|$))
 { KR=yes }

 :0
 * LEANTAG ?? no
 * !KR ?? yes
 {
  :0 B
  * !--.*forwarded message --
  * !^forwarded message:
  * !^-----BEGIN PGP SIGNED MESSAGE-----
  * -1000^0
  *  -500^0   ^Subject: Re:
  *  -200^1   ^[:;#>]
  *  1100^0   ^Content-Type: text/(html|plain)((.*$)+|.*; )charset[ ]?=[ ]?.?(euc-kr|iso-2022-kr|ks.c.5601-198[79]).?$
  { KR=yes }
 }

 :0
 * KR ?? yes
 {
  :0 f
  | ${FORMAIL} -A"X-SBRule: Korean (euc-kr|iso-2022-kr|ks-c-5601-198(7|9))"

  :0
  { BLOCKTAG=yes }

  :0
  * BLOCKREPLY ?? NOTIFY
  { BLOCKTHIS=yes }
 }
}

# Russian email
:0
* RUSSIAN ?? no
* LANGFILTER ?? yes
{
 :0
 *  ^(Content-Type:((.*$)+|.*; )charset[ ]?=[ ]?.?(iso-ir-111|koi8-[ru]|windows-1251)([^a-z0-9\.]|$)|\
      (From|To|Message-ID):.*(iso-ir-111|koi8-[ru]|windows-1251)([^a-z0-9\.]|$))
 { RUS=yes }

 :0
 * LEANTAG ?? no
 * !RUS ?? yes
 {
  :0 B
  * !--.*forwarded message --
  * !^forwarded message:
  * !^-----BEGIN PGP SIGNED MESSAGE-----
  * -1000^0
  *  -500^0   ^Subject: Re:
  *  -200^1   ^[:;#>]
  *  1100^0   ^Content-Type: text/html((.*$)+|.*; )charset[ ]?=[ ]?.?(iso-ir-111|koi8-[ru]|windows-1251).?$
  { RUS=yes }
 }

 :0
 * RUS ?? yes
 {
  :0 f
  | ${FORMAIL} -A"X-SBRule: Russian (iso-ir-111|koi8-r|koi8-u|windows-1251)"

  :0
  { BLOCKTAG=yes }

  :0
  * BLOCKREPLY ?? NOTIFY
  { BLOCKTHIS=yes }
 }
}


# Turkish email
:0
* TURKISH ?? no
* LANGFILTER ?? yes
{
 :0
 *  ^(Content-Type:((.*$)+|.*; )charset[ ]?=[ ]?.?iso-8859-3([^a-z0-9\.]|$)|\
      Content-Type:((.*$)+|.*; )charset[ ]?=[ ]?.?iso-8859-9([^a-z0-9\.]|$)|\
      Content-Type:((.*$)+|.*; )charset[ ]?=[ ]?.?windows-1254([^a-z0-9\.]|$)|\
      (From|To|Message-ID):.*iso-8859-3([^a-z0-9\.]|$)|\
      (From|To|Message-ID):.*windows-1254([^a-z0-9\.]|$)|\
      (From|To|Message-ID):.*iso-8859-9([^a-z0-9\.]|$))
 { TK=yes }

 :0
 * LEANTAG ?? no
 * !TK ?? yes
 {
  :0 B
  * !--.*forwarded message --
  * !^forwarded message:
  * !^-----BEGIN PGP SIGNED MESSAGE-----
  * -1000^0
  *  1100^0   ^Content-Type: text/(html|plain)((.*$)+|.*; )charset=.?(iso-8859-[39]|windows-1254).?$
  *   200^1   (^|[^0-9a-z])adresi([^0-9a-z]|$)
  *   200^1   (^|[^0-9a-z])adresinde([^0-9a-z]|$)
  *   200^1   (^|[^0-9a-z])ad[y齗n[y齗(n)?([^0-9a-z]|$)
  *   200^1   (^|[^0-9a-z])Bilgisayar([^0-9a-z]|$)
  *   200^1   (^|[^0-9a-z])bir([^0-9a-z]|$)
  *   200^1   (^|[^0-9a-z])bulsun([^0-9a-z]|$)
  *   200^1   (^|[^0-9a-z])bulup([^0-9a-z]|$)
  *   200^1   (^|[^0-9a-z])calis(ir|maz)([^0-9a-z]|$)
  *   200^1   (^|[^0-9a-z])[c鏬e