/usr/lib/python2.7/dist-packages/dictdlib.py is in python-dictdlib 2.0.4.1+nmu1build1.
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 | # Dictionary creation library
# Copyright (C) 2002 John Goerzen
# <jgoerzen@complete.org>
#
# This program is free software; you can redistribute it and/or modify
# it under the terms of the GNU General Public License as published by
# the Free Software Foundation; either version 2 of the License, or
# (at your option) any later version.
#
# This program is distributed in the hope that it will be useful,
# but WITHOUT ANY WARRANTY; without even the implied warranty of
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
# GNU General Public License for more details.
#
# You should have received a copy of the GNU General Public License
# along with this program; if not, write to the Free Software
# Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
import sys, string, gzip, os
b64_list = "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789+/"
url_headword = "00-database-url"
short_headword = "00-database-short"
info_headword = "00-database-info"
def b64_encode(val):
"""Takes as input an integer val and returns a string of it encoded
with the base64 algorithm used by dict indexes."""
startfound = 0
retval = ""
for i in range(5, -1, -1):
thispart = (val >> (6 * i)) & ((2 ** 6) - 1)
if (not startfound) and (not thispart):
# Both zero -- keep going.
continue
startfound = 1
retval += b64_list[thispart]
if len(retval):
return retval
else:
return b64_list[0]
def b64_decode(str):
"""Takes as input a string and returns an integer value of it decoded
with the base64 algorithm used by dict indexes."""
if not len(str):
return 0
retval = 0
shiftval = 0
for i in range(len(str) - 1, -1, -1):
val = b64_list.index(str[i])
retval = retval | (val << shiftval)
shiftval += 6
return retval
validdict = {}
for x in string.ascii_letters + string.digits + " \t":
validdict[x] = 1
def sortnormalize(x):
"""Returns a value such that x is mapped to a format that sorts properly
with standard comparison."""
x2 = ''
for i in range(len(x)):
if validdict.has_key(x[i]):
x2 += x[i]
return x2.upper() + "\0" + x.upper()
def sortfunc(x, y):
"""Emulate sort -df."""
xl = x.split("\0")
yl = y.split("\0")
ret = cmp(xl[0], yl[0])
if ret != 0:
return ret
return cmp(xl[1], yl[1])
class DictDB:
def __init__(self, basename, mode = 'read', quiet = 0):
#, url = 'unknown', shortname = 'unknown',
# longinfo = 'unknown', quiet = 0):
"""Initialize a DictDB object.
Mode must be one of:
read -- read-only access
write -- write-only access, truncates existing files, does not work
with .dz. dict created if nonexistant.
update -- read/write access, dict created if nonexistant. Does not
work with .dz.
Read can read dict or dict.dz files. Write and update will NOT work
with dict.dz files.
If quiet is nonzero, status messages
will be suppressed."""
self.mode = mode
self.quiet = quiet
self.indexentries = {}
self.count = 0
self.basename = basename
self.indexfilename = self.basename + ".index"
if os.path.isfile(self.basename + ".dict.dz"):
self.dictfilename = self.basename + ".dict.dz"
self.usecompression = 1
else:
self.dictfilename = self.basename + ".dict"
self.usecompression = 0
if mode == 'read':
self.indexfile = open(self.indexfilename, "rt")
if self.usecompression:
self.dictfile = gzip.GzipFile(self.dictfilename, "rb")
else:
self.dictfile = open(self.dictfilename, "rb")
self._initindex()
elif mode == 'write':
self.indexfile = open(self.indexfilename, "wt")
if self.usecompression:
raise ValueError, "'write' mode incompatible with .dz files"
else:
self.dictfile = open(self.dictfilename, "wb")
elif mode == 'update':
try:
self.indexfile = open(self.indexfilename, "r+b")
except IOError:
self.indexfile = open(self.indexfilename, "w+b")
if self.usecompression:
# Open it read-only since we don't support mods.
self.dictfile = gzip.GzipFile(self.dictfilename, "rb")
else:
try:
self.dictfile = open(self.dictfilename, "r+b")
except IOError:
self.dictfile = open(self.dictfilename, "w+b")
self._initindex()
else:
raise ValueError, "mode must be 'read', 'write', or 'update'"
#self.writeentry(url_headword + "\n " + url, [url_headword])
#self.writeentry(short_headword + "\n " + shortname,
# [short_headword])
#self.writeentry(info_headword + "\n" + longinfo, [info_headword])
def _initindex(self):
"""Load the entire index off disk into memory."""
self.indexfile.seek(0)
for line in self.indexfile.xreadlines():
splits = line.rstrip().split("\t")
if not self.indexentries.has_key(splits[0]):
self.indexentries[splits[0]] = []
self.indexentries[splits[0]].append([b64_decode(splits[1]),
b64_decode(splits[2])])
def addindexentry(self, word, start, size):
"""Adds an entry to the index. word is the relevant word.
start is the starting position in the dictionary and size is the
size of the definition; both are integers."""
if not self.indexentries.has_key(word):
self.indexentries[word] = []
self.indexentries[word].append([start, size])
def delindexentry(self, word, start = None, size = None):
"""Removes an entry from the index; word is the word to search for.
start and size are optional. If they are specified, only index
entries matching the specified values will be removed.
For instance, if word is "foo" and start and size are not specified,
all index entries for the word foo will be removed. If start and size
are specified, only those entries matching all criteria will be
removed.
This function does not actually remove the data from the .dict file.
Therefore, information removed by this function will still
exist on-disk in the .dict file, but the dict server will just
not "see" it -- there will be no way to get to it anymore.
Returns a count of the deleted entries."""
if not self.indexentries.has_key(word):
return 0
retval = 0
entrylist = self.indexentries[word]
for i in range(len(entrylist) - 1, -1, -1):
# Go backwords so the del doesn't effect the index.
if (start == None or start == entrylist[i][0]) and \
(size == None or size == entrylist[i][1]):
del(entrylist[i])
retval += 1
if len(entrylist) == 0: # If we emptied it, del it completely
del(self.indexentries[word])
return retval
def update(self, string):
"""Writes string out, if not quiet."""
if not self.quiet:
sys.stdout.write(string)
sys.stdout.flush()
def seturl(self, url):
"""Sets the URL attribute of this database. If there was
already a URL specified, we will use delindexentry() on it
first."""
self.delindexentry(url_headword)
self.addentry(url_headword + "\n " + url, [url_headword])
def setshortname(self, shortname):
"""Sets the shortname for this database. If there was already
a shortname specified, we will use delindexentry() on it first."""
self.delindexentry(short_headword)
self.addentry(short_headword + "\n " + shortname,
[short_headword])
def setlonginfo(self, longinfo):
"""Sets the extended information for this database. If there was
already long info specified, we will use delindexentry() on it
first."""
self.delindexentry(info_headword)
self.addentry(info_headword + "\n" + longinfo, [info_headword])
def addentry(self, defstr, headwords):
"""Writes an entry. defstr holds the content of the definition.
headwords is a list specifying one or more words under which this
definition should be indexed. This function always adds \\n
to the end of defstr."""
self.dictfile.seek(0, 2) # Seek to end of file
start = self.dictfile.tell()
defstr += "\n"
self.dictfile.write(defstr)
for word in headwords:
self.addindexentry(word, start, len(defstr))
self.count += 1
if self.count % 1000 == 0:
self.update("Processed %d records\r" % self.count)
def finish(self, dosort = 1):
"""Called to finish the writing process.
**REQUIRED IF OPENED WITH 'update' OR 'write' MODES**.
This will write the index and close the files.
dosort is optional and defaults to true. If set to false,
dictlib will not sort the index file. In this case, you
MUST manually sort it through "sort -df" before it can be used."""
self.update("Processed %d records.\n" % self.count)
if dosort:
self.update("Sorting index: converting")
indexlist = []
for word, defs in self.indexentries.items():
for thisdef in defs:
indexlist.append("%s\t%s\t%s" % (word,
b64_encode(thisdef[0]),
b64_encode(thisdef[1])))
self.update(" mapping")
sortmap = {}
for entry in indexlist:
norm = sortnormalize(entry)
if sortmap.has_key(norm):
sortmap[norm].append(entry)
sortmap[norm].sort(sortfunc)
else:
sortmap[norm] = [entry]
self.update(" listing")
normalizedentries = sortmap.keys()
self.update(" sorting")
normalizedentries.sort()
self.update(" re-mapping")
indexlist = []
for normentry in normalizedentries:
for entry in sortmap[normentry]:
indexlist.append(entry)
self.update(", done.\n")
self.update("Writing index...\n")
self.indexfile.seek(0)
for entry in indexlist:
self.indexfile.write(entry + "\n")
if self.mode == 'update':
# In case things were deleted
self.indexfile.truncate()
self.indexfile.close()
self.dictfile.close()
self.update("Complete.\n")
def getdeflist(self):
"""Returns a list of strings naming all definitions contained
in this dictionary."""
return self.indexentries.keys()
def hasdef(self, word):
return self.indexentries.has_key(word)
def getdef(self, word):
"""Given a definition name, returns a list of strings with all
matching definitions. This is an *exact* match, not a
case-insensitive one. Returns [] if word is not in the dictionary."""
retval = []
if not self.hasdef(word):
return retval
for start, length in self.indexentries[word]:
self.dictfile.seek(start)
retval.append(self.dictfile.read(length))
return retval
class DictReader:
"""This object provides compatibility with earlier versions
of dictdlib. It is now deprecated."""
def __init__(self, basename):
"""Initialize a DictReader object. Provide it with the basename."""
self.dictdb = DictDB(basename, 'read')
def getdeflist(self):
"""Returns a list of strings naming all definitions contained
in this dictionary."""
return self.dictdb.getdeflist()
def getdef(self, defname):
"""Given a definition name, returns a list of strings
with all matching definitions."""
return self.dictdb.getdef(defname)
class DictWriter:
"""This object provides compatibility with earlier versions
of dictdlib. It is now deprecated."""
def __init__(self, basename, url = 'unknown', shortname = 'unknown',
longinfo = 'unknown', quiet = 0):
"""Initialize a DictWriter object. Will create 'basename.dict' and
'basename.index' files. url, shortname, and longinfo specify the
respective attributes of the database. If quiet is 1,
status messages are not printed."""
self.dictdb = DictDB(basename, 'write', quiet)
self.dictdb.seturl(url)
self.dictdb.setshortname(shortname)
self.dictdb.setlonginfo(longinfo)
def writeentry(self, defstr, headwords):
"""Writes an entry. defstr holds the content of the definition.
headwords is a list specifying one or more words under which this
definition should be indexed. This function always adds \\n
to the end of defstr."""
self.dictdb.addentry(defstr, headwords)
def finish(self, dosort = 1):
"""Called to finish the writing process. **REQUIRED**.
This will write the index and close the files.
dosort is optional and defaults to true. If set to false,
dictlib will not sort the index file. In this case, you
MUST manually sort it through "sort -df" before it can be used."""
self.dictdb.finish(dosort)
|