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:
log.error('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 write_ext(glos, filename, sort=True, dictZip=True):
if sort:
g = glos.copy()
g.data.sort()
else:
g = glos
try:
import _stardictbuilder
except ImportError:
log.error('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 write(glos, filename, dictzip=True, install=True): ## FIXME
from pyglossary.text_utils import runDictzip
(filename_nox, ext) = splitext(filename)
if ext.lower() == '.index':
filename = filename_nox
indexFd = open(filename + '.index', 'wb')
dictFd = open(filename + '.dict', 'wb')
dictMark = 0
for entry in glos:
word = toBytes(entry.getWord())
defi = toBytes(entry.getDefi())
lm = len(defi)
indexFd.write(word + b'\t' + intToIndexStr(dictMark) + b'\t' +
intToIndexStr(lm) + b'\n') ## FIXME
dictFd.write(toBytes(defi))
dictMark += lm
indexFd.close()
dictFd.close()
#for key, value in glos.iterInfo():
# if not value:
# continue
# pass ## FIXME
if dictzip:
runDictzip(filename)
if install:
installToDictd(filename, glos.getInfo('name').replace(' ', '_'))
def write(glos, filename, sort=True, dictZip=True, install=True): ## FIXME
if sort:
glos = glos.copy()
glos.sortWords()
(filename_nox, ext) = splitext(filename)
if ext.lower() == '.index':
filename = filename_nox
indexFd = open(filename + '.index', 'wb')
dictFd = open(filename + '.dict', 'wb')
dictMark = 0
for entry in glos:
word = entry.getWord()
defi = entry.getDefi()
lm = len(defi)
indexFd.write(word + '\t' + intToIndexStr(dictMark) + '\t' +
intToIndexStr(lm) + '\n') ## FIXME
dictFd.write(defi)
dictMark += lm
indexFd.close()
dictFd.close()
#for key in glos.infoKeys():
# value = glos.getInfo(key)
# if value!='':
# pass ## FIXME
if dictZip:
runDictzip(filename)
if install:
installToDictd(filename, glos.getInfo('name').replace(' ', '_'))
def write(
self,
filename: str,
dictzip: bool = False,
install: bool = True,
) -> Generator[None, "BaseEntry", None]:
from pyglossary.text_utils import runDictzip
glos = self._glos
filename_nox, ext = splitext(filename)
if ext.lower() == ".index":
filename = filename_nox
dictdb = DictDB(filename, "write", 1)
while True:
entry = yield
if entry is None:
break
if entry.isData():
# does dictd support resources? and how? FIXME
continue
dictdb.addentry(entry.b_defi, entry.l_word)
dictdb.finish(dosort=1)
if dictzip:
runDictzip(filename)
if install:
installToDictd(filename, dictzip,
glos.getInfo("name").replace(" ", "_"))
def write(glos, filename, dictzip=True, install=True): # FIXME
from pyglossary.text_utils import runDictzip
(filename_nox, ext) = splitext(filename)
if ext.lower() == ".index":
filename = filename_nox
indexFd = open(filename+".index", "wb")
dictFd = open(filename+".dict", "wb")
dictMark = 0
for entry in glos:
if entry.isData():
# does dictd support resources? and how? FIXME
continue
word = toBytes(entry.getWord())
defi = toBytes(entry.getDefi())
lm = len(defi)
indexFd.write(
word + b"\t" +
intToIndexStr(dictMark) + b"\t" +
intToIndexStr(lm) + b"\n"
) # FIXME
dictFd.write(toBytes(defi))
dictMark += lm
indexFd.close()
dictFd.close()
# for key, value in glos.iterInfo():
# if not value:
# continue
# pass # FIXME
if dictzip:
runDictzip(filename)
if install:
installToDictd(filename, glos.getInfo("name").replace(" ", "_"))
def write( self, filename, dictzip=True, ): fileBasePath = "" ## if splitext(filename)[1].lower() == ".ifo": fileBasePath = splitext(filename)[0] elif filename.endswith(os.sep): if not isdir(filename): os.makedirs(filename) fileBasePath = join(filename, split(filename[:-1])[-1]) elif isdir(filename): fileBasePath = join(filename, split(filename)[-1]) ## if fileBasePath: fileBasePath = realpath(fileBasePath) self._filename = fileBasePath self._resDir = join(dirname(self._filename), "res") self.writeGeneral() # if self.glossaryHasAdditionalDefinitions(): # self.writeGeneral() # else: # defiFormat = self.detectMainDefinitionFormat() # if defiFormat == None: # self.writeGeneral() # else: # self.writeCompact(defiFormat) if dictzip: runDictzip(self._filename)
def run(self, dictZip, resOverwrite):
## no more direct access to glos.data, must use glos.sortWords for sorting
## no support for cmp argument because it's not supported in Python 3
## using my key function `stardictStrKey` might not be safe
#self.glos.sortWords(key=stardictStrKey)
## the safest way in Python 3 is using functools.cmp_to_key
self.glos.sortWords(key=cmp_to_key(stardict_strcmp))
self.writeGeneral()
#if self.glossaryHasAdditionalDefinitions():
# self.writeGeneral()
#else:
# defiFormat = self.detectMainDefinitionFormat()
# if defiFormat == None:
# self.writeGeneral()
# else:
# self.writeCompact(defiFormat)
if dictZip:
runDictzip(self.fileBasePath)
self.copyResources(
self.glos.resPath,
join(os.path.dirname(self.fileBasePath), 'res'),
resOverwrite
)
def write(glos, filename, dictzip=True, install=True): # FIXME
from pyglossary.text_utils import runDictzip
(filename_nox, ext) = splitext(filename)
if ext.lower() == ".index":
filename = filename_nox
indexFd = open(filename + ".index", "wb")
dictFd = open(filename + ".dict", "wb")
dictMark = 0
for entry in glos:
if entry.isData():
# does dictd support resources? and how? FIXME
continue
word = toBytes(entry.getWord())
defi = toBytes(entry.getDefi())
lm = len(defi)
indexFd.write(word + b"\t" + intToIndexStr(dictMark) + b"\t" +
intToIndexStr(lm) + b"\n") # FIXME
dictFd.write(toBytes(defi))
dictMark += lm
indexFd.close()
dictFd.close()
# for key, value in glos.iterInfo():
# if not value:
# continue
# pass # FIXME
if dictzip:
runDictzip(filename)
if install:
installToDictd(filename, glos.getInfo("name").replace(" ", "_"))
def write(
self,
filename,
dictzip=True,
):
fileBasePath = ""
##
if splitext(filename)[1].lower() == ".ifo":
fileBasePath = splitext(filename)[0]
elif filename.endswith(os.sep):
if not isdir(filename):
os.makedirs(filename)
fileBasePath = join(filename, split(filename[:-1])[-1])
elif isdir(filename):
fileBasePath = join(filename, split(filename)[-1])
##
if fileBasePath:
fileBasePath = realpath(fileBasePath)
self._filename = fileBasePath
self._resDir = join(dirname(self._filename), "res")
self.writeGeneral()
# if self.glossaryHasAdditionalDefinitions():
# self.writeGeneral()
# else:
# defiFormat = self.detectMainDefinitionFormat()
# if defiFormat == None:
# self.writeGeneral()
# else:
# self.writeCompact(defiFormat)
if dictzip:
runDictzip(self._filename)
def run(self, dictzip, resOverwrite):
## no more direct access to glos.data, must use glos.sortWords for sorting
## no support for cmp argument because it's not supported in Python 3
## key function's argument is a str (word)
self.glos.sortWords(
key = sortKey,
)
self.writeGeneral()
#if self.glossaryHasAdditionalDefinitions():
# self.writeGeneral()
#else:
# defiFormat = self.detectMainDefinitionFormat()
# if defiFormat == None:
# self.writeGeneral()
# else:
# self.writeCompact(defiFormat)
if dictzip:
runDictzip(self.fileBasePath)
self.copyResources(
self.glos.resPath,
join(os.path.dirname(self.fileBasePath), 'res'),
resOverwrite
)
def write(
self,
filename: str,
dictzip: bool = True,
sametypesequence: str = "", # type: Literal["", "h", "m"]
) -> None:
fileBasePath = filename
##
if splitext(filename)[1].lower() == ".ifo":
fileBasePath = splitext(filename)[0]
elif filename.endswith(os.sep):
if not isdir(filename):
os.makedirs(filename)
fileBasePath = join(filename, split(filename[:-1])[-1])
elif isdir(filename):
fileBasePath = join(filename, split(filename)[-1])
##
if fileBasePath:
fileBasePath = realpath(fileBasePath)
self._filename = fileBasePath
self._resDir = join(dirname(self._filename), "res")
if sametypesequence:
log.debug(
f"Using write option sametypesequence={sametypesequence}")
self.writeCompact(sametypesequence)
else:
self.writeGeneral()
if dictzip:
runDictzip(self._filename)
def write(glos, filename, dictzip=True, install=True):## FIXME
from pyglossary.text_utils import runDictzip
(filename_nox, ext) = splitext(filename)
if ext.lower()=='.index':
filename = filename_nox
indexFd = open(filename+'.index', 'wb')
dictFd = open(filename+'.dict', 'wb')
dictMark = 0
for entry in glos:
word = toBytes(entry.getWord())
defi = toBytes(entry.getDefi())
lm = len(defi)
indexFd.write(word + b'\t' + intToIndexStr(dictMark) + b'\t' + intToIndexStr(lm) + b'\n')## FIXME
dictFd.write(toBytes(defi))
dictMark += lm
indexFd.close()
dictFd.close()
#for key, value in glos.iterInfo():
# if not value:
# continue
# pass ## FIXME
if dictzip:
runDictzip(filename)
if install:
installToDictd(filename, glos.getInfo('name').replace(' ', '_'))
def write(self) -> Generator[None, "BaseEntry", None]:
if self._sametypesequence:
yield from self.writeCompact(self._sametypesequence)
else:
yield from self.writeGeneral()
if self._dictzip:
runDictzip(self._filename)
def write(glos, filename, sort=True, dictZip=True, install=True):## FIXME
if sort:
glos = glos.copy()
glos.sortWords()
(filename_nox, ext) = splitext(filename)
if ext.lower()=='.index':
filename = filename_nox
indexFd = open(filename+'.index', 'wb')
dictFd = open(filename+'.dict', 'wb')
dictMark = 0
for entry in glos:
word = entry.getWord()
defi = entry.getDefi()
lm = len(defi)
indexFd.write(word + '\t' + intToIndexStr(dictMark) + '\t' + intToIndexStr(lm) + '\n')## FIXME
dictFd.write(defi)
dictMark += lm
indexFd.close()
dictFd.close()
#for key in glos.infoKeys():
# value = glos.getInfo(key)
# if value!='':
# pass ## FIXME
if dictZip:
runDictzip(filename)
if install:
installToDictd(filename, glos.getInfo('name').replace(' ', '_'))
def finish(self):
from pyglossary.text_utils import runDictzip
self._dictdb.finish(dosort=1)
if self._dictzip:
runDictzip(self._filename)
if self._install:
installToDictd(
self._filename,
self._dictzip,
self._glos.getInfo("name").replace(" ", "_"),
)
self._filename = None
def write(self) -> "Generator[None, BaseEntry, None]": if self._sametypesequence: if self._merge_syns: yield from self.writeCompactMergeSyns(self._sametypesequence) else: yield from self.writeCompact(self._sametypesequence) else: if self._merge_syns: yield from self.writeGeneralMergeSyns() else: yield from self.writeGeneral() if self._dictzip: runDictzip(self._filename)
def write(
self,
filename: str,
dictzip: bool = True,
sametypesequence: str = "", # type: Literal["", "h", "m"]
stardict_client: bool = False,
) -> None:
self._stardict_client = stardict_client
fileBasePath = filename
##
if splitext(filename)[1].lower() == ".ifo":
fileBasePath = splitext(filename)[0]
elif filename.endswith(os.sep):
if not isdir(filename):
os.makedirs(filename)
fileBasePath = join(filename, split(filename[:-1])[-1])
elif isdir(filename):
fileBasePath = join(filename, split(filename)[-1])
parentDir = split(fileBasePath)[0]
if not isdir(parentDir):
log.info(f"Creating directory {parentDir}")
os.mkdir(parentDir)
##
if fileBasePath:
fileBasePath = realpath(fileBasePath)
self._filename = fileBasePath
self._resDir = join(dirname(self._filename), "res")
self._sourceLang = self._glos.sourceLang
self._targetLang = self._glos.targetLang
if sametypesequence:
log.debug(f"Using write option sametypesequence={sametypesequence}")
else:
stat = self._glos.collectDefiFormat(100)
log.info(f"defiFormat stat: {stat}")
if stat["m"] > 0.97:
log.info(f"Auto-selecting sametypesequence=m")
sametypesequence = "m"
elif stat["h"] > 0.5:
log.info(f"Auto-selecting sametypesequence=h")
sametypesequence = "h"
if sametypesequence:
yield from self.writeCompact(sametypesequence)
else:
yield from self.writeGeneral()
if dictzip:
runDictzip(self._filename)
def run(self, dictZip, resOverwrite):
self.glos.data.sort(stardict_strcmp, lambda x: x[0])
if self.GlossaryHasAdditionalDefinitions():
self.writeGeneral()
else:
articleFormat = self.DetectMainDefinitionFormat()
if articleFormat == None:
self.writeGeneral()
else:
self.writeCompact(articleFormat)
if dictZip:
runDictzip(self.fileBasePath)
self.copyResources(self.glos.resPath, join(os.path.dirname(self.fileBasePath), "res"), resOverwrite)
def run(self, dictzip, resOverwrite):
self.writeGeneral()
#if self.glossaryHasAdditionalDefinitions():
# self.writeGeneral()
#else:
# defiFormat = self.detectMainDefinitionFormat()
# if defiFormat == None:
# self.writeGeneral()
# else:
# self.writeCompact(defiFormat)
if dictzip:
runDictzip(self.fileBasePath)
self.copyResources(self.glos.resPath,
join(os.path.dirname(self.fileBasePath), 'res'),
resOverwrite)
def run(self, dictZip, resOverwrite):
self.glos.data.sort(stardict_strcmp, lambda x: x[0])
if self.GlossaryHasAdditionalDefinitions():
self.writeGeneral()
else:
articleFormat = self.DetectMainDefinitionFormat()
if articleFormat == None:
self.writeGeneral()
else:
self.writeCompact(articleFormat)
if dictZip:
runDictzip(self.fileBasePath)
self.copyResources(self.glos.resPath,
join(os.path.dirname(self.fileBasePath), 'res'),
resOverwrite)
def run(self, dictzip, resOverwrite):
self.writeGeneral()
#if self.glossaryHasAdditionalDefinitions():
# self.writeGeneral()
#else:
# defiFormat = self.detectMainDefinitionFormat()
# if defiFormat == None:
# self.writeGeneral()
# else:
# self.writeCompact(defiFormat)
if dictzip:
runDictzip(self.fileBasePath)
self.copyResources(
self.glos.resPath,
join(os.path.dirname(self.fileBasePath), 'res'),
resOverwrite
)
def run(self, dictZip, resOverwrite):
## no more direct access to glos.data, must use glos.sortWords for sorting
## no support for cmp argument because it's not supported in Python 3
## key function's argument is a str (word)
self.glos.sortWords(key=stardictStrKey, )
self.writeGeneral()
#if self.glossaryHasAdditionalDefinitions():
# self.writeGeneral()
#else:
# defiFormat = self.detectMainDefinitionFormat()
# if defiFormat == None:
# self.writeGeneral()
# else:
# self.writeCompact(defiFormat)
if dictZip:
runDictzip(self.fileBasePath)
self.copyResources(self.glos.resPath,
join(os.path.dirname(self.fileBasePath), 'res'),
resOverwrite)
def write(
glos: GlossaryType,
filename: str,
dictzip: bool = False,
install: bool = True,
) -> None:
from pyglossary.text_utils import runDictzip
(filename_nox, ext) = splitext(filename)
if ext.lower() == ".index":
filename = filename_nox
dictdb = DictDB(filename, "write", 1)
for entry in glos:
if entry.isData():
# does dictd support resources? and how? FIXME
continue
dictdb.addentry(entry.b_defi, entry.l_word)
dictdb.finish(dosort=1)
if dictzip:
runDictzip(filename)
if install:
installToDictd(filename, dictzip,
glos.getInfo("name").replace(" ", "_"))
def write(
self,
filename: str,
dictzip: bool = True,
sametypesequence: str = "", # type: Literal["", "h", "m"]
) -> None:
fileBasePath = filename
##
if splitext(filename)[1].lower() == ".ifo":
fileBasePath = splitext(filename)[0]
elif filename.endswith(os.sep):
if not isdir(filename):
os.makedirs(filename)
fileBasePath = join(filename, split(filename[:-1])[-1])
elif isdir(filename):
fileBasePath = join(filename, split(filename)[-1])
##
if fileBasePath:
fileBasePath = realpath(fileBasePath)
self._filename = fileBasePath
self._resDir = join(dirname(self._filename), "res")
if sametypesequence:
log.debug("Using write option sametypesequence=%s" %
sametypesequence)
self.writeCompact(sametypesequence)
# elif self.glossaryHasAdditionalDefinitions():
# self.writeGeneral()
else:
# defiFormat = self.detectMainDefinitionFormat()
# if defiFormat == None:
self.writeGeneral()
# else:
# self.writeCompact(defiFormat)
if dictzip:
runDictzip(self._filename)