/usr/lib/gdesklets/utils/Trie.py is in gdesklets 0.36.1-7.
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 | _DELIMITER = "delimiter"
_MATCH_ONE = "?"
_MATCH_MANY = "*"
#
# Class for the node of a compressed trie.
#
class _TrieNode(object):
__slots__ = ('__body', '__children', '__values')
def __init__(self):
# the body elements; since the trie is compressed, there may be more
# than one
self.__body = []
# the children of the node
self.__children = {}
# the values stored in the node
self.__values = []
def _set_body(self, body): self.__body = body[:]
def _set_children(self, children): self.__children = children.copy()
def _set_values(self, values): self.__values = values[:]
#
# Inserts a new string into the trie.
#
def insert(self, data, value):
# if the node is empty, just fill it
if (not self.__body):
self._set_body(data)
self.__values.append(value)
return
index = 0
length = len(self.__body)
# check how far the elements match
while (index < length):
# split up node if elements don't match
if (data[index] != self.__body[index]):
ext_node = _TrieNode()
ext_node._set_body(self.__body[index:])
ext_node._set_children(self.__children)
ext_node._set_values(self.__values)
new_node = _TrieNode()
new_node.insert(data[index:], value)
self.__children = {self.__body[index]: ext_node,
data[index]: new_node}
self.__body = self.__body[:index]
self.__values = []
return
#end if
index += 1
#end while
# use this node if the given string exactly matches the body string
if (index == len(data)):
self.__values.append(value)
return
# insert node
node = self.__children.get(data[index])
if (node):
# insert into existing node
node.insert(data[index:], value)
else:
# create a new node
new_node = _TrieNode()
new_node.insert(data[index:], value)
self.__children[data[index]] = new_node
#
# Retrieves the values which are stored for the given string. The string
# may contain the wildcards ? (match any character) and * (match zero or
# more characters).
#
# FIXME: clean up
#
def retrieve(self, data, case_sensitive):
index = 0
length = len(self.__body)
values = []
while (index < length):
if (case_sensitive):
next = data[index]
char = self.__body[index]
else:
next = data[index].lower()
char = self.__body[index].lower()
if (next == _MATCH_ONE and char != _DELIMITER):
index += 1
elif (next == _MATCH_ONE):
return []
# the MANY wildcard can be translated to ONE wildcards
elif (next == _MATCH_MANY):
prefix = data[:index]
suffix = data[index + 1:]
values += self.retrieve(prefix + suffix, case_sensitive)
values += self.retrieve(prefix + [_MATCH_ONE, _MATCH_MANY] +
suffix, case_sensitive)
return values
elif (next != char):
return []
else:
index += 1
#end while
if (index >= len(data)): return self.__values
next = data[index]
if (next in (_MATCH_ONE, _MATCH_MANY)):
for node in self.__children.values():
values += node.retrieve(data[index:], case_sensitive)
return values
else:
node1 = self.__children.get(next)
if (not case_sensitive): node2 = self.__children.get(next.lower())
else: node2 = None
if (not case_sensitive): node3 = self.__children.get(next.upper())
else: node3 = None
if (node1 or node2 or node3):
l1 = []
l2 = []
l3 = []
if (node1):
l1 = node1.retrieve(data[index:], case_sensitive)
if (node2):
l2 = node2.retrieve(data[index:], case_sensitive)
if (node3):
l3 = node3.retrieve(data[index:], case_sensitive)
return values + l1 + l2 + l3
else:
return values + self.__values
#
# Recursive method for removing entries. If it return True, then the node
# could be removed successfully, otherwise the node is still in use.
#
def remove(self, key, value):
# recursively check the children, if the key matches
if (len(key) > len(self.__body) and
key[:len(self.__body)] == self.__body):
key = key[len(self.__body):]
next = key[0]
child = self.__children.get(next)
if (child):
to_remove = child.remove(key, value)
if (to_remove):
del self.__children[next]
# remove the value from this node
else:
try:
self.__values.remove(value)
except ValueError:
pass
# if the node has become empty, then we can remove it
if (not self.__values and not self.__children):
return True
else:
return False
def get_size(self):
size = 1
for c in self.__children.values():
size += c.get_size()
return size
#
# Class for a trie.
#
class Trie:
__slots__ = ('__root', '__case_sensitive')
def __init__(self):
self.__root = _TrieNode()
self.__case_sensitive = True
# table for storing all indices of a value: value -> [indices]
self.__index_table = {}
#
# Sets the case sensitivity for searches in the trie.
#
def set_case_sensitive(self, value): self.__case_sensitive = value
#
# Inserts a value into the trie for the given list of key elements.
# A list element is usually a letter of a string which is to be indexed.
#
def insert(self, key, value):
key = [_DELIMITER] + key + [_DELIMITER]
self.__root.insert(key, value)
if (not value in self.__index_table): self.__index_table[value] = []
self.__index_table[value].append(key)
#
# Retrieves the stored value for the given list of key elements. A list
# element is usually a letter of an indexed string.
#
def retrieve(self, key):
key = [_DELIMITER] + key + [_DELIMITER]
values = self.__root.retrieve(key, self.__case_sensitive)
if len(values) <= 1:
return values
# remove duplicates
values.sort()
new = []
current = None
for v in values:
if (v != current):
new.append(v)
current = v
#end for
return new
#
# Removes the given value from the trie.
#
def remove(self, value):
indices = self.__index_table.get(value, [])
for index in indices:
self.__root.remove(index, value)
def get_size(self):
return self.__root.get_size()
if (__name__ == "__main__"):
text = """
This is just a plain text which we are going to index. There are lots of
words in it, so this will be some kind of stress test for our trie
implementation. Let's see how well this will work with compressed tries.
"""
import sys
if '.' not in sys.path: sys.path.append('.')
if '..' not in sys.path: sys.path.append('..')
def stats():
from libdesklets.system.gtop import proc_mem, proc_time
from os import getpid
pid = getpid()
print 'CPU time: %ds\tMemory usage: %0.2f' % (proc_time(pid).utime / 100,
proc_mem(pid).resident / (1024.0**2),)
stats()
keys = text.split() #open('/usr/share/dict/words').read().split()#[:1000]
stats()
t = Trie()
for word in keys:
t.insert(list(word), word)
stats()
for key in keys:
t.retrieve(list(key))
stats()
a = t.retrieve(list("w?ll*"))
print a, len(a)
for word in text.split():
t.remove(word)
print t.get_size()
for word in keys:
t.insert(list(word), word)
print t.get_size()
a = t.retrieve(list("*"))
print a, len(a)
stats()
|