def write_ext(glos, filename, sort=True, dictZip=True):
if sort:
g = glos.copy()
g.data.sort()
else:
g = glos
try:
import _stardictbuilder
except ImportError:
printAsError('Binary module "_stardictbuilder" can not be imported! '+\
'Using internal StarDict builder')
return g.writeStardict(filename, sort=False)
db = _stardictbuilder.new_StarDictBuilder(filename)
_stardictbuilder.StarDictBuilder_swigregister(db)
for item in g.data:
_stardictbuilder.StarDictBuilder_addHeadword(db, item[0], item[1], '')
_stardictbuilder.StarDictBuilder_setTitle(db, g.getInfo('name'))
_stardictbuilder.StarDictBuilder_setAuthor(db, g.getInfo('author'))
_stardictbuilder.StarDictBuilder_setLicense(db, g.getInfo('license'))
_stardictbuilder.StarDictBuilder_setOrigLang(db, g.getInfo('origLang'))
_stardictbuilder.StarDictBuilder_setDestLang(db, g.getInfo('destLang'))
_stardictbuilder.StarDictBuilder_setDescription(db,
g.getInfo('description'))
_stardictbuilder.StarDictBuilder_setComments(db, g.getInfo('comments'))
_stardictbuilder.StarDictBuilder_setEmail(db, g.getInfo('email'))
_stardictbuilder.StarDictBuilder_setWebsite(db, g.getInfo('website'))
_stardictbuilder.StarDictBuilder_setVersion(db, g.getInfo('version'))
_stardictbuilder.StarDictBuilder_setcreationTime(db, '')
_stardictbuilder.StarDictBuilder_setLastUpdate(db, '')
_stardictbuilder.StarDictBuilder_finish(db)
if dictZip:
if filename[-4:] == '.ifo':
filename = filename[:-4]
runDictzip(filename)
def readIdxFile(self):
if isfile(self.fileBasePath + '.idx.gz'):
import gzip
with gzip.open(self.fileBasePath + '.idx.gz') as f:
idxStr = f.read()
else:
with open(self.fileBasePath + '.idx', 'rb') as f:
idxStr = f.read()
self.indexData = []
i = 0
while i < len(idxStr):
beg = i
i = idxStr.find('\x00', beg)
if i < 0:
printAsError("Index file is corrupted.")
break
word = idxStr[beg:i]
i += 1
if i + 8 > len(idxStr):
printAsError("Index file is corrupted")
break
offset = binStrToInt(idxStr[i:i + 4])
i += 4
size = binStrToInt(idxStr[i:i + 4])
i += 4
self.indexData.append([word, offset, size, [], []])
def copyResources(self, fromPath, toPath, overwrite):
'''Copy resource files from fromPath to toPath.
'''
if not fromPath:
return
fromPath = os.path.abspath(fromPath)
toPath = os.path.abspath(toPath)
if fromPath == toPath:
return
if not isdir(fromPath):
return
if len(os.listdir(fromPath)) == 0:
return
if overwrite and os.path.exists(toPath):
shutil.rmtree(toPath)
if os.path.exists(toPath):
if len(os.listdir(toPath)) > 0:
printAsError(
'''Output resource directory is not empty: "{0}". Resources will not be copied!
Clean the output directory before running the converter or pass option: --write-options=res-overwrite=True.'''\
.format(toPath)
)
return
os.rmdir(toPath)
shutil.copytree(fromPath, toPath)
def readDictFile(self, sametypesequence):
if isfile(self.fileBasePath+'.dict.dz'):
import gzip
dictFd = gzip.open(self.fileBasePath+'.dict.dz')
else:
dictFd = open(self.fileBasePath+'.dict', 'rb')
for rec in self.indexData:
dictFd.seek(rec[1])
if dictFd.tell() != rec[1]:
printAsError("Unable to read definition for word \"{0}\"".format(rec[0]))
rec[0] = None
continue
data = dictFd.read(rec[2])
if len(data) != rec[2]:
printAsError("Unable to read definition for word \"{0}\"".format(rec[0]))
rec[0] = None
continue
if sametypesequence:
res = self.parseDefiBlockCompact(data, sametypesequence, rec[0])
else:
res = self.parseDefiBlockGeneral(data, rec[0])
if res == None:
rec[0] = None
continue
res = self.convertDefinitionsToPyglossaryFormat(res)
if len(res) == 0:
rec[0] = None
continue
rec[3] = res
dictFd.close()
def write_ext(glos, filename, sort=True, dictZip=True):
if sort:
g = glos.copy()
g.data.sort()
else:
g = glos
try:
import _stardictbuilder
except ImportError:
printAsError('Binary module "_stardictbuilder" can not be imported! '+\
'Using internal StarDict builder')
return g.writeStardict(filename, sort=False)
db = _stardictbuilder.new_StarDictBuilder(filename)
_stardictbuilder.StarDictBuilder_swigregister(db)
for item in g.data:
_stardictbuilder.StarDictBuilder_addHeadword(db,item[0],item[1], '')
_stardictbuilder.StarDictBuilder_setTitle(db, g.getInfo('name'))
_stardictbuilder.StarDictBuilder_setAuthor(db, g.getInfo('author'))
_stardictbuilder.StarDictBuilder_setLicense(db, g.getInfo('license'))
_stardictbuilder.StarDictBuilder_setOrigLang(db, g.getInfo('origLang'))
_stardictbuilder.StarDictBuilder_setDestLang(db, g.getInfo('destLang'))
_stardictbuilder.StarDictBuilder_setDescription(db, g.getInfo('description'))
_stardictbuilder.StarDictBuilder_setComments(db, g.getInfo('comments'))
_stardictbuilder.StarDictBuilder_setEmail(db, g.getInfo('email'))
_stardictbuilder.StarDictBuilder_setWebsite(db, g.getInfo('website'))
_stardictbuilder.StarDictBuilder_setVersion(db, g.getInfo('version'))
_stardictbuilder.StarDictBuilder_setcreationTime(db, '')
_stardictbuilder.StarDictBuilder_setLastUpdate(db, '')
_stardictbuilder.StarDictBuilder_finish(db)
if dictZip:
if filename[-4:]=='.ifo':
filename = filename[:-4]
runDictzip(filename)
def readIdxFile(self):
if isfile(self.fileBasePath+'.idx.gz'):
import gzip
with gzip.open(self.fileBasePath+'.idx.gz') as f:
idxStr = f.read()
else:
with open(self.fileBasePath+'.idx', 'rb') as f:
idxStr = f.read()
self.indexData = []
i = 0
while i < len(idxStr):
beg = i
i = idxStr.find('\x00', beg)
if i < 0:
printAsError("Index file is corrupted.")
break
word = idxStr[beg:i]
i += 1
if i + 8 > len(idxStr):
printAsError("Index file is corrupted")
break
offset = binStrToInt(idxStr[i:i+4])
i += 4
size = binStrToInt(idxStr[i:i+4])
i += 4
self.indexData.append([word, offset, size, [], []])
def copyResources(self, fromPath, toPath, overwrite):
'''Copy resource files from fromPath to toPath.
'''
if not fromPath:
return
fromPath = os.path.abspath(fromPath)
toPath = os.path.abspath(toPath)
if fromPath == toPath:
return
if not isdir(fromPath):
return
if len(os.listdir(fromPath))==0:
return
if overwrite and os.path.exists(toPath):
shutil.rmtree(toPath)
if os.path.exists(toPath):
if len(os.listdir(toPath)) > 0:
printAsError(
'''Output resource directory is not empty: "{0}". Resources will not be copied!
Clean the output directory before running the converter or pass option: --write-options=res-overwrite=True.'''\
.format(toPath)
)
return
os.rmdir(toPath)
shutil.copytree(fromPath, toPath)
def verifySameTypeSequence(s):
if not s:
return True
for t in s:
if not isAsciiAlpha(t):
printAsError("Invalid sametypesequence option")
return False
return True
def verifySameTypeSequence(s):
if not s:
return True
for t in s:
if not isAsciiAlpha(t):
printAsError("Invalid sametypesequence option")
return False
return True
def parseDefiBlockGeneral(self, data, word):
"""Parse definition block when sametypesequence option is not specified.
"""
dataFileCorruptedError = "Data file is corrupted. Word \"{0}\"".format(
word)
res = []
i = 0
while i < len(data):
t = data[i]
if not isAsciiAlpha(t):
printAsError(dataFileCorruptedError)
return None
i += 1
if isAsciiLower(t):
beg = i
i = data.find('\x00', beg)
if i < 0:
printAsError(dataFileCorruptedError)
return None
res.append((data[beg:i], t))
i += 1
else:
assert isAsciiUpper(t)
if i + 4 > len(data):
printAsError(dataFileCorruptedError)
return None
size = binStrToInt(data[i:i + 4])
i += 4
if i + size > len(data):
printAsError(dataFileCorruptedError)
return None
res.append((data[i:i + size], t))
i += size
return res
def parseDefiBlockGeneral(self, data, word):
"""Parse definition block when sametypesequence option is not specified.
"""
dataFileCorruptedError = "Data file is corrupted. Word \"{0}\"".format(word)
res = []
i = 0
while i < len(data):
t = data[i]
if not isAsciiAlpha(t):
printAsError(dataFileCorruptedError)
return None
i += 1
if isAsciiLower(t):
beg = i
i = data.find('\x00', beg)
if i < 0:
printAsError(dataFileCorruptedError)
return None
res.append((data[beg:i], t))
i += 1
else:
assert isAsciiUpper(t)
if i + 4 > len(data):
printAsError(dataFileCorruptedError)
return None
size = binStrToInt(data[i:i+4])
i += 4
if i + size > len(data):
printAsError(dataFileCorruptedError)
return None
res.append((data[i:i+size], t))
i += size
return res
def readSynFile(self):
if not isfile(self.fileBasePath + '.syn'):
return
with open(self.fileBasePath + '.syn', 'rb') as f:
synStr = f.read()
i = 0
while i < len(synStr):
beg = i
i = synStr.find('\x00', beg)
if i < 0:
printAsError("Synonym file is corrupted.")
break
word = synStr[beg:i]
i += 1
if i + 4 > len(synStr):
printAsError("Synonym file is corrupted.")
break
index = binStrToInt(synStr[i:i + 4])
i += 4
if index >= len(self.indexData):
printAsError(
"Corrupted synonym file. Word \"{0}\" references invalid item."
.format(word))
continue
self.indexData[index][4].append(word)
def readDictFile(self, sametypesequence):
if isfile(self.fileBasePath + '.dict.dz'):
import gzip
dictFd = gzip.open(self.fileBasePath + '.dict.dz')
else:
dictFd = open(self.fileBasePath + '.dict', 'rb')
for rec in self.indexData:
dictFd.seek(rec[1])
if dictFd.tell() != rec[1]:
printAsError(
"Unable to read definition for word \"{0}\"".format(
rec[0]))
rec[0] = None
continue
data = dictFd.read(rec[2])
if len(data) != rec[2]:
printAsError(
"Unable to read definition for word \"{0}\"".format(
rec[0]))
rec[0] = None
continue
if sametypesequence:
res = self.parseDefiBlockCompact(data, sametypesequence,
rec[0])
else:
res = self.parseDefiBlockGeneral(data, rec[0])
if res == None:
rec[0] = None
continue
res = self.convertDefinitionsToPyglossaryFormat(res)
if len(res) == 0:
rec[0] = None
continue
rec[3] = res
dictFd.close()
def readSynFile(self):
if not isfile(self.fileBasePath+'.syn'):
return
with open(self.fileBasePath+'.syn', 'rb') as f:
synStr = f.read()
i = 0
while i < len(synStr):
beg = i
i = synStr.find('\x00', beg)
if i < 0:
printAsError("Synonym file is corrupted.")
break
word = synStr[beg:i]
i += 1
if i + 4 > len(synStr):
printAsError("Synonym file is corrupted.")
break
index = binStrToInt(synStr[i:i+4])
i += 4
if index >= len(self.indexData):
printAsError("Corrupted synonym file. Word \"{0}\" references invalid item.".format(word))
continue
self.indexData[index][4].append(word)
def parseDefiBlockCompact(self, data, sametypesequence, word):
"""Parse definition block when sametypesequence option is specified.
"""
assert type(sametypesequence) == str
assert len(sametypesequence) > 0
dataFileCorruptedError = "Data file is corrupted. Word \"{0}\"".format(
word)
res = []
i = 0
for t in sametypesequence[:-1]:
if i >= len(data):
printAsError(dataFileCorruptedError)
return None
if isAsciiLower(t):
beg = i
i = data.find('\x00', beg)
if i < 0:
printAsError(dataFileCorruptedError)
return None
res.append((data[beg:i], t))
i += 1
else:
assert isAsciiUpper(t)
if i + 4 > len(data):
printAsError(dataFileCorruptedError)
return None
size = binStrToInt(data[i:i + 4])
i += 4
if i + size > len(data):
printAsError(dataFileCorruptedError)
return None
res.append((data[i:i + size], t))
i += size
if i >= len(data):
printAsError(dataFileCorruptedError)
return None
t = sametypesequence[-1]
if isAsciiLower(t):
i2 = data.find('\x00', i)
if i2 >= 0:
printAsError(dataFileCorruptedError)
return None
res.append((data[i:], t))
else:
assert isAsciiUpper(t)
res.append((data[i:], t))
return res
def parseDefiBlockCompact(self, data, sametypesequence, word):
"""Parse definition block when sametypesequence option is specified.
"""
assert type(sametypesequence) == str
assert len(sametypesequence) > 0
dataFileCorruptedError = "Data file is corrupted. Word \"{0}\"".format(word)
res = []
i = 0
for t in sametypesequence[:-1]:
if i >= len(data):
printAsError(dataFileCorruptedError)
return None
if isAsciiLower(t):
beg = i
i = data.find('\x00', beg)
if i < 0:
printAsError(dataFileCorruptedError)
return None
res.append((data[beg:i], t))
i += 1
else:
assert isAsciiUpper(t)
if i + 4 > len(data):
printAsError(dataFileCorruptedError)
return None
size = binStrToInt(data[i:i+4])
i += 4
if i + size > len(data):
printAsError(dataFileCorruptedError)
return None
res.append((data[i:i+size], t))
i += size
if i >= len(data):
printAsError(dataFileCorruptedError)
return None
t = sametypesequence[-1]
if isAsciiLower(t):
i2 = data.find('\x00', i)
if i2 >= 0:
printAsError(dataFileCorruptedError)
return None
res.append((data[i:], t))
else:
assert isAsciiUpper(t)
res.append((data[i:], t))
return res