/usr/share/pyshared/swap/n3p_tm.py is in python-swap 1.2.1-5.
This file is owned by root:root, with mode 0o644.
The actual contents of the file can be viewed below.
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 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 45 46 47 48 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 | """Why??
$$
"""
from n3p import n3p
import os
from uripath import join
class absolutizer(unicode):
def __getitem__(self, other):
return join(self, other)
Logic_NS = "http://www.w3.org/2000/10/swap/log#"
RDF_type_URI = "http://www.w3.org/1999/02/22-rdf-syntax-ns#type"
RDF_NS_URI = "http://www.w3.org/1999/02/22-rdf-syntax-ns#"
# DAML_NS=DPO_NS = "http://www.daml.org/2001/03/daml+oil#" # DAML plus oil
OWL_NS = "http://www.w3.org/2002/07/owl#"
DAML_sameAs_URI = OWL_NS+"sameAs"
parsesTo_URI = Logic_NS + "parsesTo"
RDF_spec = "http://www.w3.org/TR/REC-rdf-syntax/"
#List_NS = DPO_NS # We have to pick just one all the time
List_NS = RDF_NS_URI # From 20030808
LOG_implies_URI = "http://www.w3.org/2000/10/swap/log#implies"
INTEGER_DATATYPE = "http://www.w3.org/2001/XMLSchema#integer"
FLOAT_DATATYPE = "http://www.w3.org/2001/XMLSchema#double"
DECIMAL_DATATYPE = "http://www.w3.org/2001/XMLSchema#decimal"
NORMAL = 1
PREFIX = 2
FORSOME = 4
FORALL = 5
NEED_PERIOD = 8
LITERAL = 9
KEYWORDS = 10
class n3p_tm(n3p.N3Parser):
def __init__(self, uri, tm, baseURI=False):
n3p.N3Parser.__init__(self, 'nowhere', n3p.branches, n3p.regexps)
self.tm = tm
self.productions = []
if baseURI:
self._baseURI = baseURI + '#'
else:
self._baseURI = uri + '#'
self.prefixes = {'':self._baseURI}
self.abs = absolutizer(self._baseURI[:-1])
def parse(self, start=n3p.start):
n3p.N3Parser.parse(self, start)
def startDoc(self):
self.tm.start()
def endDoc(self):
return self.tm.end()
def feed(self, data):
self.data = data.decode('utf_8')
self._mode = NORMAL
self.parse()
def onStart(self, prod):
self.productions.append(prod)
if prod == 'literal':
self._mode = LITERAL
#print 'begin' + prod
def onFinish(self):
prod = self.productions.pop()
if prod == 'literal':
self.tm.addLiteral(self.literal['string'], self.literal['type'], self.literal['lang'])
self._mode = NORMAL
#print 'end' + prod
def onToken(self, prod, tok):
tm = self.tm
if 1:
if self._mode == NORMAL:
if prod == '.':
try:
tm.endStatement()
except ValueError:
tm.forewardPath()
elif prod == ';':
tm.endStatement()
tm.addNode(None)
elif prod == ',':
tm.endStatement()
tm.addNode(None)
tm.addNode(None)
elif prod == '=>':
tm.addSymbol(LOG_implies_URI)
elif prod == '<=':
tm.IsOf()
tm.addSymbol(LOG_implies_URI)
elif prod == '=':
tm.addSymbol(DAML_sameAs_URI)
elif prod == '@forAll':
self._mode = FORALL
elif prod == '@forSome':
self._mode = FORSOME
elif prod == '@a':
tm.addSymbol(RDF_type_URI)
elif prod == '@is':
tm.IsOf()
elif prod == '@of':
assert tm.checkIsOf()
elif prod == '{':
tm.beginFormula()
elif prod == '}':
tm.endFormula()
elif prod == '[':
tm.beginAnonymous()
elif prod == ']':
tm.endAnonymous()
elif prod == '(':
tm.beginList()
elif prod == ')':
tm.endList()
elif prod == '@has':
pass
elif prod == '@this':
tm.addNode('@this')
elif prod == '^':
tm.backwardPath()
elif prod == '!':
tm.forewardPath()
elif prod == '@prefix':
self._mode = PREFIX
elif prod == 'qname':
ret = self.decodeQName(tok, True)
if type(ret) is tuple:
tm.addAnonymous(ret[0])
else:
tm.addSymbol(ret)
elif prod == 'explicituri':
tm.addSymbol(self.abs[tok[1:-1]])
elif prod == 'numericliteral':
if '.' in tok or 'e' in tok:
tm.addLiteral(float(tok))
else:
tm.addLiteral(int(tok))
elif prod == 'variable':
tm.addQuestionMarkedSymbol(self._baseURI+tok[1:])
elif prod == '@keywords':
self._mode = KEYWORDS
elif self._mode == LITERAL:
if prod == 'string':
self.literal = {'string': unEscape(tok), 'type':None, 'lang':None}
elif prod == 'qname':
self.literal['type'] = self.decodeQName(tok, False)
elif prod == 'explicituri':
self.literal['type'] = self.abs[tok[1:-1]]
elif prod == 'langcode':
self.literal['lang'] = tok
else:
pass
elif self._mode == PREFIX:
if prod == 'qname':
n = tok.find(':')
self._newPrefix = tok[:n]
elif prod == 'explicituri':
tm.bind(self._newPrefix, self.abs[tok[1:-1]])
self.prefixes[self._newPrefix] = self.abs[tok[1:-1]]
elif prod == '.':
self._mode = NORMAL
elif self._mode == FORALL:
if prod == 'qname':
uri = self.decodeQName(tok, False)
tm.declareUniversal(uri)
elif prod == 'explicituri':
tm.declareUniversal(self.abs[tok[1:-1]])
elif prod == ',':
pass
elif prod == '.':
self._mode = NORMAL
elif self._mode == FORSOME:
if prod == 'qname':
uri = self.decodeQName(tok, False)
tm.declareExistential(uri)
elif prod == 'explicituri':
tm.declareExistential(self.abs[tok[1:-1]])
elif prod == ',':
pass
elif prod == '.':
self._mode = NORMAL
if prod == '.':
self._mode = NORMAL
parent = self.productions[-1]
#print 'mode=', self._mode, '. prod=', prod, '. tok =', tok
def decodeQName(self, qName, bNode):
n = qName.find(':')
if n < 0:
pfx = ''
frag = qName
else:
pfx = qName[:n]
frag = qName[n+1:]
try:
self.prefixes[pfx]
except KeyError:
if pfx == '_':
if bNode:
return (frag,)
else:
return qName
raise
return self.prefixes[pfx]+frag
def unEscape(string):
if string[:3] == '"""':
real_str = string[3:-3]
triple = True
else:
real_str = string[1:-1]
triple = False
ret = u''
n = 0
while n < len(real_str):
ch = real_str[n]
if ch == '\r':
pass
elif ch == '\\':
a = real_str[n+1:n+2]
if a == '':
raise RuntimeError
k = 'abfrtvn\\"'.find(a)
if k >= 0:
ret += '\a\b\f\r\t\v\n\\"'[k]
n += 1
elif a == 'u':
m = real_str[n+2:n+6]
assert len(m) == 4
ret += unichr(int(m, 16))
n += 5
elif a == 'U':
m = real_str[n+2:n+10]
assert len(m) == 8
ret += unichr(int(m, 16))
n += 9
else:
raise ValueError('Bad Escape')
else:
ret += ch
n += 1
return ret
def parse(uri, options):
baseURI = options.baseURI
sink = object()
if options.root:
sink.quantify = lambda *args: True
sink.flatten = lambda *args: True
if ':' not in uri:
uri = 'file://' + os.path.join(os.getcwd(), uri)
if baseURI and (':' not in baseURI):
baseURI = 'file://' + os.path.join(os.getcwd(), baseURI)
p = n3p_tm(uri, sink, baseURI=baseURI)
p.parse()
def main(argv=None):
import optparse
class MyHelpFormatter(optparse.HelpFormatter):
def __init__(self):
kargs = {'indent_increment': 2, 'short_first': 1,
'max_help_position': 25, 'width': None}
optparse.HelpFormatter.__init__(self, **kargs)
def format_usage(self, usage):
return optparse._("%s") % usage.lstrip()
def format_heading(self, heading):
return "%*s%s:\n" % (self.current_indent, "", heading)
formatter = MyHelpFormatter()
parser = optparse.OptionParser(usage=__doc__, formatter=formatter)
parser.add_option("-b", "--baseURI", dest="baseURI", default=False,
help="set the baseURI", metavar="URI")
parser.add_option("-r", "--root", dest="root",
action="store_true", default=False,
help="print triples in the root formula only")
options, args = parser.parse_args(argv)
if len(args) == 1:
parse(args[0], options)
else: parser.print_help()
if __name__=="__main__":
main()
|