utils.py 6.52 KB
Newer Older
Yusei Tahara's avatar
Yusei Tahara committed
1 2 3
import re
import os
import sys
4
from sgmllib import SGMLParser, SGMLParseError
Yusei Tahara's avatar
Yusei Tahara committed
5 6

try:
7 8 9 10 11
    # Need to be imported before win32api to avoid dll loading
    # problems.
    import pywintypes
    import pythoncom

Yusei Tahara's avatar
Yusei Tahara committed
12 13 14 15 16 17 18
    import win32api
    WIN32 = True
except ImportError:
    WIN32 = False

class MissingBinary(Exception): pass

19
envPath = os.getenv('PATH', '')
Yusei Tahara's avatar
Yusei Tahara committed
20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44
bin_search_path = [path for path in envPath.split(os.pathsep)
                   if os.path.isdir(path)]

cygwin = 'c:/cygwin'

# cygwin support
if sys.platform == 'win32' and os.path.isdir(cygwin):
    for p in ['/bin', '/usr/bin', '/usr/local/bin' ]:
        p = os.path.join(cygwin, p)
        if os.path.isdir(p):
            bin_search_path.append(p)

if sys.platform == 'win32':
    extensions = ('.exe', '.com', '.bat', )
else:
    extensions = ()

def bin_search(binary):
    """search the bin_search_path for a given binary returning its fullname or
       raises MissingBinary"""
    mode   = os.R_OK | os.X_OK
    for path in bin_search_path:
        for ext in ('', ) + extensions:
            pathbin = os.path.join(path, binary) + ext
            if os.access(pathbin, mode) == 1:
45 46 47 48
                return pathbin

    raise MissingBinary('Unable to find binary "%s" in %s' % 
                        (binary, os.pathsep.join(bin_search_path)))
Yusei Tahara's avatar
Yusei Tahara committed
49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122

def getShortPathName(binary):
    if WIN32:
        try:
            binary = win32api.GetShortPathName(binary)
        except win32api.error:
            log("Failed to GetShortPathName for '%s'" % binary)
    return binary

def sansext(path):
    return os.path.splitext(os.path.basename(path))[0]


##########################################################################
# The code below is taken from CMFDefault.utils to remove
# dependencies for Python-only installations
##########################################################################

def bodyfinder(text):
    """ Return body or unchanged text if no body tags found.

    Always use html_headcheck() first.
    """
    lowertext = text.lower()
    bodystart = lowertext.find('<body')
    if bodystart == -1:
        return text
    bodystart = lowertext.find('>', bodystart) + 1
    if bodystart == 0:
        return text
    bodyend = lowertext.rfind('</body>', bodystart)
    if bodyend == -1:
        return text
    return text[bodystart:bodyend]


#
#   HTML cleaning code
#

# These are the HTML tags that we will leave intact
VALID_TAGS = { 'a'          : 1
             , 'b'          : 1
             , 'base'       : 0
             , 'blockquote' : 1
             , 'body'       : 1
             , 'br'         : 0
             , 'caption'    : 1
             , 'cite'       : 1
             , 'code'       : 1
             , 'div'        : 1
             , 'dl'         : 1
             , 'dt'         : 1
             , 'dd'         : 1
             , 'em'         : 1
             , 'h1'         : 1
             , 'h2'         : 1
             , 'h3'         : 1
             , 'h4'         : 1
             , 'h5'         : 1
             , 'h6'         : 1
             , 'head'       : 1
             , 'hr'         : 0
             , 'html'       : 1
             , 'i'          : 1
             , 'img'        : 0
             , 'kbd'        : 1
             , 'li'         : 1
             , 'meta'       : 0
             , 'ol'         : 1
             , 'p'          : 1
             , 'pre'        : 1
             , 'span'       : 1
             , 'strong'     : 1
123
             , 'strike'     : 1
Yusei Tahara's avatar
Yusei Tahara committed
124 125
             , 'table'      : 1
             , 'tbody'      : 1
126
             , 'thead'      : 1
Yusei Tahara's avatar
Yusei Tahara committed
127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209
             , 'td'         : 1
             , 'th'         : 1
             , 'title'      : 1
             , 'tr'         : 1
             , 'tt'         : 1
             , 'u'          : 1
             , 'ul'         : 1
             }

NASTY_TAGS = { 'script'     : 1
             , 'object'     : 1
             , 'embed'      : 1
             , 'applet'     : 1
             }

class IllegalHTML( ValueError ):
    pass

class StrippingParser( SGMLParser ):
    """ Pass only allowed tags;  raise exception for known-bad.  """

    from htmlentitydefs import entitydefs # replace entitydefs from sgmllib

    def __init__( self ):

        SGMLParser.__init__( self )
        self.result = ""

    def handle_data( self, data ):

        if data:
            self.result = self.result + data

    def handle_charref( self, name ):

        self.result = "%s&#%s;" % ( self.result, name )

    def handle_entityref(self, name):

        if self.entitydefs.has_key(name):
            x = ';'
        else:
            # this breaks unstandard entities that end with ';'
            x = ''

        self.result = "%s&%s%s" % (self.result, name, x)

    def unknown_starttag(self, tag, attrs):

        """ Delete all tags except for legal ones.
        """
        if VALID_TAGS.has_key(tag):

            self.result = self.result + '<' + tag

            for k, v in attrs:

                if k.lower().startswith( 'on' ):
                    raise IllegalHTML, 'Javascipt event "%s" not allowed.' % k

                if v.lower().startswith( 'javascript:' ):
                    raise IllegalHTML, 'Javascipt URI "%s" not allowed.' % v

                self.result = '%s %s="%s"' % (self.result, k, v)

            endTag = '</%s>' % tag
            if VALID_TAGS.get(tag):
                self.result = self.result + '>'
            else:
                self.result = self.result + ' />'

        elif NASTY_TAGS.get( tag ):
            raise IllegalHTML, 'Dynamic tag "%s" not allowed.' % tag

        else:
            pass    # omit tag

    def unknown_endtag(self, tag):

        if VALID_TAGS.get( tag ):

            self.result = "%s</%s>" % (self.result, tag)
            remTag = '</%s>' % tag
210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229
    
    def parse_declaration(self, i):
        """Fix handling of CDATA sections. Code borrowed from BeautifulSoup.
        """
        j = None
        if self.rawdata[i:i+9] == '<![CDATA[':
             k = self.rawdata.find(']]>', i)
             if k == -1:
                 k = len(self.rawdata)
             data = self.rawdata[i+9:k]
             j = k+3
             self.result.append("<![CDATA[%s]]>" % data)
        else:
            try:
                j = SGMLParser.parse_declaration(self, i)
            except SGMLParseError:
                toHandle = self.rawdata[i:]
                self.result.append(toHandle)
                j = i + len(toHandle)
        return j
Yusei Tahara's avatar
Yusei Tahara committed
230 231 232 233 234 235 236

def scrubHTML( html ):
    """ Strip illegal HTML tags from string text.  """
    parser = StrippingParser()
    parser.feed( html )
    parser.close()
    return parser.result