Mercurial > traipse_dev

comparison orpg/chat/chat_util.py @ 71:449a8900f9ac ornery-dev

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
Code refining almost completed, for this round. Some included files are still in need of some clean up, but this is test worthy.
author sirebral
date Thu, 20 Aug 2009 03:00:39 -0500
parents 4385a7d0efd1
children 1ed2feab0db9
comparison
equal deleted inserted replaced
70:52a5fa913008 71:449a8900f9ac
1 # utility function; see Post() in chatwnd.py 1 # utility function; see Post() in chatwnd.py
2 2
3 import re 3 import re
4 import string 4 import string
5 from orpg.orpgCore import *
6 from orpg.tools.orpg_log import logger
7 from orpg.tools.decorators import debugging
5 8
6 #============================================ 9 #============================================
7 # simple_html_repair(string) 10 # simple_html_repair(string)
8 # 11 #
9 # Crude html/xml parser/verifier. 12 # Crude html/xml parser/verifier.
14 # html like <script> or <li> which are known 17 # html like <script> or <li> which are known
15 # to cause issues with the chat display 18 # to cause issues with the chat display
16 # 19 #
17 # Created 04-25-2005 by Snowdog 20 # Created 04-25-2005 by Snowdog
18 #============================================= 21 #=============================================
22 @debugging
19 def simple_html_repair(string): 23 def simple_html_repair(string):
20 "Returns string with extra > symbols to isolate badly formated HTML" 24 "Returns string with extra > symbols to isolate badly formated HTML"
21 #walk though string checking positions of < and > tags. 25 #walk though string checking positions of < and > tags.
22 first_instance = string.find('<') 26 first_instance = string.find('<')
23 if first_instance == -1: return string #no html, bail out. 27 if first_instance == -1: return string #no html, bail out.
65 #tack them on the end to avoid open-tag conditions 69 #tack them on the end to avoid open-tag conditions
66 diff = string.count('<') - string.count('>') 70 diff = string.count('<') - string.count('>')
67 if diff > 0: 71 if diff > 0:
68 for d in range(1,diff): 72 for d in range(1,diff):
69 string = string+">" 73 string = string+">"
70
71 return string 74 return string
72 75
76 """ Depricated! Might as well use the already made component.get('xml')
73 def strip_unicode(txt): 77 def strip_unicode(txt):
74 for i in xrange(len(txt)): 78 for i in xrange(len(txt)):
75 if txt[i] not in string.printable: 79 if txt[i] not in string.printable:
76 try: 80 try:
77 txt = txt.replace(txt[i], '&#' + str(ord(txt[i])) + ';') 81 txt = txt.replace(txt[i], '&#' + str(ord(txt[i])) + ';')
78 except: 82 except:
79 txt = txt.replace(txt[i], '{?}') 83 txt = txt.replace(txt[i], '{?}')
80 return txt 84 return txt
85 """
81 86
82 #================================================ 87 #================================================
83 # strip_script_tags(string) 88 # strip_script_tags(string)
84 # 89 #
85 # removes all script tags (start and end) 90 # removes all script tags (start and end)
86 # 04-26-2005 Snowdog 91 # 04-26-2005 Snowdog
87 #================================================ 92 #================================================
93 @debugging
88 def strip_script_tags(string): 94 def strip_script_tags(string):
89 #kill the <script> issue 95 #kill the <script> issue
90 p = re.compile( '<(\s*)(/*)[Ss][Cc][Rr][Ii][Pp][Tt](.*?)>') 96 p = re.compile( '<(\s*)(/*)[Ss][Cc][Rr][Ii][Pp][Tt](.*?)>')
91 string = p.sub( "<!-- script tag removed //-->", string) 97 string = p.sub( "<!-- script tag removed //-->", string)
92 return string 98 return string
95 # strip_li_tags(string) 101 # strip_li_tags(string)
96 # 102 #
97 # removes all li tags (start and end) 103 # removes all li tags (start and end)
98 # 05-13-2005 104 # 05-13-2005
99 #================================================ 105 #================================================
106 @debugging
100 def strip_li_tags(string): 107 def strip_li_tags(string):
101 #kill the <li> issue 108 #kill the <li> issue
102 string = re.sub( r'<(\s*)[Ll][Ii](.*?)>', r'<b><font color="#000000" size=+1>*</font></b> ', string) 109 string = re.sub( r'<(\s*)[Ll][Ii](.*?)>', r'<b><font color="#000000" size=+1>*</font></b> ', string)
103 string = re.sub( r'<(/*)[Ll][Ii](.*?)>', r'<br />', string) 110 string = re.sub( r'<(/*)[Ll][Ii](.*?)>', r'<br />', string)
104 return string 111 return string
109 # removes all body tags (start and end) from messages 116 # removes all body tags (start and end) from messages
110 # should not break the setting of custom background colors 117 # should not break the setting of custom background colors
111 # through legitimate means such as the OpenRPG settings. 118 # through legitimate means such as the OpenRPG settings.
112 # 07-27-2005 by mDuo13 119 # 07-27-2005 by mDuo13
113 #================================================ 120 #================================================
121 @debugging
114 def strip_body_tags(string): 122 def strip_body_tags(string):
115 bodytag_regex = re.compile(r"""<\/?body.*?>""", re.I) 123 bodytag_regex = re.compile(r"""<\/?body.*?>""", re.I)
116 string = re.sub(bodytag_regex, "", string) 124 string = re.sub(bodytag_regex, "", string)
117 return string 125 return string
118 126
127 # return the text to its normal alignment, so this 135 # return the text to its normal alignment, so this
128 # algorithm simply closes them, allowing them to be 136 # algorithm simply closes them, allowing them to be
129 # used legitimately without causing much annoyance. 137 # used legitimately without causing much annoyance.
130 # 07-27-2005 mDuo13 138 # 07-27-2005 mDuo13
131 #================================================ 139 #================================================
140 @debugging
132 def strip_misalignment_tags(string): 141 def strip_misalignment_tags(string):
133 alignment_regex = re.compile(r"""<p([^>]*?)align\s*=\s*('.*?'|".*?"|[^\s>]*)(.*?)>""", re.I) 142 alignment_regex = re.compile(r"""<p([^>]*?)align\s*=\s*('.*?'|".*?"|[^\s>]*)(.*?)>""", re.I)
134 string = re.sub(alignment_regex, "<p\\1\\3>", string) 143 string = re.sub(alignment_regex, "<p\\1\\3>", string)
135 144
136 center_regex = re.compile(r"""<center.*?>""", re.I) 145 center_regex = re.compile(r"""<center.*?>""", re.I)
147 # 156 #
148 # removes all img tags (start and end) 157 # removes all img tags (start and end)
149 # 05-13-2005 158 # 05-13-2005
150 # redone 07-11-2005 by mDuo13 159 # redone 07-11-2005 by mDuo13
151 #================================================ 160 #================================================
161 @debugging
152 def strip_img_tags(string): 162 def strip_img_tags(string):
153 #This is a Settings definable feature, Allowing users to enable or disable image display to fix the client crash due to large img posted to chat. 163 #This is a Settings definable feature, Allowing users to enable or disable image display to fix the client crash due to large img posted to chat.
154 #p = re.sub( r'<(\s*)(/*)[Ii][Mm][Gg][ ][Ss][Rr][Cc][=](.*?)>', r'<!-- img tag removed //--> <a href=\3>\3</a>', string) 164 #p = re.sub( r'<(\s*)(/*)[Ii][Mm][Gg][ ][Ss][Rr][Cc][=](.*?)>', r'<!-- img tag removed //--> <a href=\3>\3</a>', string)
155 165
156 #this regex is substantially more powerful than the one above 166 #this regex is substantially more powerful than the one above