You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@spamassassin.apache.org by jh...@apache.org on 2014/10/25 21:42:45 UTC

svn commit: r1634248 - /spamassassin/trunk/rules/25_replace.cf

Author: jhardin
Date: Sat Oct 25 19:42:45 2014
New Revision: 1634248

URL: http://svn.apache.org/r1634248
Log:
expansion of replace tags for more characters, lots yet to do - this should be automated!

Modified:
    spamassassin/trunk/rules/25_replace.cf

Modified: spamassassin/trunk/rules/25_replace.cf
URL: http://svn.apache.org/viewvc/spamassassin/trunk/rules/25_replace.cf?rev=1634248&r1=1634247&r2=1634248&view=diff
==============================================================================
--- spamassassin/trunk/rules/25_replace.cf (original)
+++ spamassassin/trunk/rules/25_replace.cf Sat Oct 25 19:42:45 2014
@@ -29,22 +29,22 @@ ifplugin Mail::SpamAssassin::Plugin::Rep
 
 replace_tag	A	(?:[gra\@\xc0\xc1\xc2\xc3\xc4\xc5\xc6\xe4\xe3\xe2\xe0\xe1\xe2\xe3\xe4\xe5\xe60o]|[\xce][\x86\x91\x94\x9b\xac\xb1]|[\xd0][\x90\xb0]|[\xd1][\xa6\xa7]|[\xd3][\x90\x91\x92\x93]|[\xe1][\x8e][\xaa])
 replace_tag	B	(?:[b8]|[\xce][\x92\xb2]|[\xcf][\x90\xb8]|[\xd0][\x91\x92\xac\xb1\xb2]|[\xd1][\x8a\x8c\xa2\xa3]|[\xd2][\x8c\x8d])
-replace_tag	C	(?:[ck\xc7\xe7@]|[\xc3][\x87]|[\xc4][\x86\x87\x88\x89\x8a\x8b\x8c\x8d]|[\xcf][\x82\x9a\x9b\xb2\xb9\xbe]|[\xd0][\xa1]|[\xd1][\x81]|[\xd2][\x80\x81\xaa\xab]|[\xd5][\x87])
+replace_tag	C	(?:[ck\xc7\xe7@]|[\xc3][\x87]|[\xc4][\x86\x87\x88\x89\x8a\x8b\x8c\x8d]|[\xcf][\x82\x9a\x9b\xb2\xb9\xbe]|[\xd0][\xa1]|[\xd1][\x81]|[\xd2][\x80\x81\xaa\xab]|[\xd5][\x87]|&\#(?:1(?:0(?:10|17|22|57|89)|1(?:52|53|94|95)|99)|2(?:31|6[2-9])|39[12]|x(?:3(?:f2|f9|fe)|4(?:21|41|80|81|aa|ab)));)
 replace_tag	D	(?:[d\xd0]|[\xd4][\x80\x81]|[\xd5][\xaa])
-replace_tag	E	(?:[e3]|[\xc4][\x92\x93\x94\x95\x96\x97\x98\x99\x9a\x9b]|[\xc8][\x84\x85\x86\x87\xa8\xa9]|[\xce][\x88\x95\xa3\xad\xb5\xbe]|[\xcf][\xb5]|[\xd0][\x80\x81\x84\x95\xb5]|[\xd1][\x90\x91\x94\xb3]|[\xd2][\xbc\xbd\xbe\xbf]|[\xd3][\x96\x97\xa9\xab]|[\xd4][\x90\x91]|[\xc8\xc9\xca\xcb\xe8\xe9\xea\xeb\xa4])
+replace_tag	E	(?:[e3]|[\xc4][\x92\x93\x94\x95\x96\x97\x98\x99\x9a\x9b]|[\xc8][\x84\x85\x86\x87\xa8\xa9]|[\xce][\x88\x95\xa3\xad\xb5\xbe]|[\xcf][\xb5]|[\xd0][\x80\x81\x84\x95\xb5]|[\xd1][\x90\x91\x94\xb3]|[\xd2][\xbc\xbd\xbe\xbf]|[\xd3][\x96\x97\xa9\xab]|[\xd4][\x90\x91]|[\xc8\xc9\xca\xcb\xe8\xe9\xea\xeb\xa4]|&\#(?:1(?:0(?:13|2[458]|45|77)|108|2(?:1[2-5]|3[89]|9[67]))|2(?:0[0-3]|3[2-5]|7[4-9]|8[0-3])|400|51[6-9]|5[58][23]|603|9(?:04|17|[34]1|49));)
 replace_tag	F	(?:f|[\xcf][\x9c\x9d]|[\xd2][\x92\x93]|[\xd3][\xba\xbb]|[\xd4][\xb2]|[\xd5][\xa2])
 replace_tag	G	(?:[gk]|[\xd2][\xa8\xa9]|[\xd4][\x8c\x8d]|[\xd6][\x81])
-replace_tag	H	(?:h|[\xce][\x89\x97]|[\xcf][\xa6]|[\xd0][\x8a\x8b\x9d\xbd]|[\xd1][\x92\x9b]|[\xd2][\x94\x95\xa2\xa3\xa4\xa5\xba\xbb]|[\xd3][\x87\x88\x89\x8a]|[\xd4][\xbb]|[\xd5][\xab\xb0])
-replace_tag	I	(?:[il|!1y?\xcc\xcd\xce\xcf\xec\xed\xee\xef]|[\xc4][\xa8]|[\xc7][\x8f\x90]|[\xce][\x8a\x90\x99\xaa\xaf\xb9]|[\xcf][\x8a]|[\xd0][\x86\x87]|[\xd1][\x96\x97]|[\xd3][\x80\x8f]|[\xd5][\xac])
+replace_tag	H	(?:h|[\xce][\x89\x97]|[\xcf][\xa6]|[\xd0][\x8a\x8b\x9d\xbd]|[\xd1][\x92\x9b]|[\xd2][\x94\x95\xa2\xa3\xa4\xa5\xba\xbb]|[\xd3][\x87\x88\x89\x8a]|[\xd4][\xbb]|[\xd5][\xab\xb0]|&\#(:?2(?:22[3-6]|9[2-5])|54[23]|1(?:0(?:53|85)|18[6-9]));)
+replace_tag	I	(?:[il|!1y?\xcc\xcd\xce\xcf\xec\xed\xee\xef]|[\xc4][\xa8]|[\xc7][\x8f\x90]|[\xce][\x8a\x90\x99\xaa\xaf\xb9]|[\xcf][\x8a]|[\xd0][\x86\x87]|[\xd1][\x96\x97]|[\xd3][\x80\x8f]|[\xd5][\xac]|&\#(?:1(?:03[01]|11[01]|216|231)|2(?:0[4-7]|3[6-9]|9[6-9])|3(?:0[0-5])|4(?:0[67]|6[34])|52[0-3]);)
 replace_tag	J	(?:j|[\xcf][\xb3]|[\xd0][\x88]|[\xd1][\x98]|[\xd5][\xb5])
-replace_tag	K	(?:k|[\xc7][\xa8\xa9]|[\xce][\x9a\xba]|[\xd0][\x8c\x9a\xba]|[\xd1][\x9c]|[\xd2][\x9a\x9b\x9c\x9d\x9e\x9f\xa0\xa1]|[\xd3][\x83\x84]|[\xd4][\x9e\x9f])
-replace_tag	L	(?:[il|!1\xa3]|[\xc4][\xb9\xba\xbb\xbc\xbd\xbe\xbf]|[\xc5][\x80\x81\x82]|[\xc8][\xbd]|[\xd3][\x80\x8f]|[\xd4][\xbc]|[\xd5][\xac]|[\xd6][\x82])
+replace_tag	K	(?:k|[\xc7][\xa8\xa9]|[\xce][\x9a\xba]|[\xd0][\x8c\x9a\xba]|[\xd1][\x9c]|[\xd2][\x9a\x9b\x9c\x9d\x9e\x9f\xa0\xa1]|[\xd3][\x83\x84]|[\xd4][\x9e\x9f]|&\#(?:31[0-2]|4[08][89]|9(?:22|54|75)|1(?:0(?:36|50|82)|1(?:16|7[89]|8[0-5])|219|220|31[01]));)
+replace_tag	L	(?:[il|!1\xa3]|[\xc4][\xb9\xba\xbb\xbc\xbd\xbe\xbf]|[\xc5][\x80\x81\x82]|[\xc8][\xbd]|[\xd3][\x80\x8f]|[\xd4][\xbc]|[\xd5][\xac]|[\xd6][\x82]|&\#(?:1340|3(?:1[3-9]|2[0-2])|x53c);)
 replace_tag	M	(?:m|rn|[\xd0][\x9c\xbc]|[\xd2][\xa7]|[\xd3][\x8d\x8e])
 replace_tag	N	(?:[n\xd1\xf1]|[\xd0][\x98\x99\x9f\xb8\xb9\xbb\xbf]|[\xd1][\x9d]|[\xd2][\x8a\x8b]|[\xd3][\x86\xa2\xa3\xa4\xa5]|[\xd4][\xa5]|[\xd5][\x88\x8c\xa4\xa8\xb2\xb8\xbc]|[\xd6][\x80])
 replace_tag	O	(?:[go0\xd2\xd3\xd4\xd5\xd6\xd8\xf0\xf2\xf3\xf4\xf5\xf6\xf8]|[\xd0][\x9e\xae\xbe]|[\xd1][\xba\xbb]|[\xd3][\xa6\xa7\xa8\xaa]|[\xd4][\x9a]|[\xd5][\x95\xae]|[\xd6][\x85]|[\xd7][\xa1])
 replace_tag	P	(?:[p\xfe]|[\xd0][\xa0]|[\xd1][\x80]|[\xd2][\x8e\x8f]|[\xd4][\x97]|[\xd5][\xa9]|[\xd6][\x84])
 replace_tag	Q	(?:q|[\xd4][\x9a\x9b\xb3]|[\xd5][\xa3\xa6])
-replace_tag	R	(?:r|[\xc5][\x94\x95\x96\x97\x98\x99]|[\xc8][\x90\x91\x92\x93]|[\xd0][\x93\xaf]|[\xd1][\x8f\x93]|[\xd2][\x90\x91\x93]|[\xd3][\xb6\xb7]|[\xd4][\xb8\xbb]|[\xd5][\x90\x92]|[\xd6][\x80])
+replace_tag	R	(?:r|[\xc5][\x94\x95\x96\x97\x98\x99]|[\xc8][\x90\x91\x92\x93]|[\xd0][\x93\xaf]|[\xd1][\x8f\x93]|[\xd2][\x90\x91\x93]|[\xd3][\xb6\xb7]|[\xd4][\xb8\xbb]|[\xd5][\x90\x92]|[\xd6][\x80]|&\#(?:1(?:071|103)|34[0-5]|422|5(?:2[89]|3[01]|8[89])|6(?:3[67]|40));)
 replace_tag	S	(?:[sz\xa6\xa7]|[\xd0][\x85]|[\xd1][\x95]|[\xd5][\x8f])
 replace_tag	T	(?:t|[\xd0][\x93\xa2]|[\xd1][\x82]|[\xd2][\x90\xac\xad]|[\xd3][\xb6]|[\xd4][\xb5\xb7]|[\xd5][\x92\xa7])
 replace_tag	U	(?:[uv\xb5\xd9\xda\xdb\xdc\xfc\xfb\xfa\xf9\xfd]|[\xd0][\x8f\xa6]|[\xd1][\x86\x9f]|[\xd4][\xb1\xbf]|[\xd5][\x84\x8d\xb4\xb6\xbd\xbe]|[\xd6][\x87])
@@ -55,7 +55,7 @@ replace_tag	Y	(?:[y\xff\xfd\xa5j]|[\xd0]
 replace_tag	Z	[zs]
 replace_tag	IMG	(?:jpe?g|gif|png)
 replace_tag	SP	[\s\d_*\$\%(),.:;?!}{\[\]|\/?^\#~\xa1`'+-]
-replace_tag	WS	(?:\s|[\xe2](?:[\x80][\x82\x83\x84\x85\x86\x87\x88\x89\x8a\x8b\x8c\x8d\xaf]|[\x81][\x9f]))
+replace_tag	WS	(?:=?\s|[\xe2](?:[\x80][\x80\x81\x82\x83\x84\x85\x86\x87\x88\x89\x8a\x8b\x8c\x8d\xaf]|[\x81][\x9f])|&(?:\#(?:8(?:19[2-9]|20[0-5]|239|287)|160|xa0)|(?:e[nm]|nb)sp);)
 replace_tag	CUR	[\$\xa5\xa3\xa4\xa2]
 
 replace_inter	SP	[\s\d_*\$\%(),.:;?!}{\[\]|\/?^\#~\xa1`'+-]