def main():
filename,limit, output_format, wordtype, version= grabargs()
#print "#--",filename,limit,display_format, wordtype;
#exit();
try:
fl = open(filename);
except:
print " Error :No such file or directory: %s" % filename
sys.exit(0)
#~ print "#",filename,limit, output_format, wordtype, version
#~ sys.exit()
#display_format="txt"
line = fl.readline().decode("utf8");
text = u""
noun_table = [];
nb_field = 2;
while line :
line = line.strip('\n')#.strip()
if not line.startswith("#"):
liste = line.split(Separator);
if len(liste) >= nb_field:
noun_table.append(liste);
line = fl.readline().decode("utf8");
fl.close();
#print "#", (u'\t'.join(field_id.keys())).encode('utf8');
model = 0;
if output_format == "sql":
import sqldict
mydict = sqldict.SqlDict(wordtype, version);
elif output_format == "xml":
import xmldict
mydict = xmldict.XmlDict(wordtype, version);
elif output_format == "stardict":
import stardict
mydict = stardict.StarDict(wordtype, version);
elif output_format == "tags":
import tagsdict
mydict = tagsdict.TagsDict(wordtype, version);
elif output_format == "spell":
import spelldict
mydict = spelldict.SpellDict(wordtype, version);
else:
import csvdict
mydict = csvdict.CsvDict(wordtype, version)
# create header
h = mydict.add_header()
if h:
print h.encode('utf8')
for tuple_noun in noun_table[:limit]:
l = mydict.add_record(tuple_noun)
if l:
print l.encode('utf8')
# create footer
f = mydict.add_footer()
if f:
print f.encode('utf8')
def __init__(self, model=None):
self.stops = set(stopwords.words('english'))
path = '/Users/dpmorg_mac/dpm_gdrive/insight/polibot/depedencies/'
if model is None:
self.model = sqldict.SqlDict(path + "GoogleNews-vectors.db")
else:
pretrained = path + 'GoogleNews-vectors-negative300.bin.gz'
self.model = Word2Vec.load_word2vec_format(pretrained, binary=True)
self.nlp = spacy.load('en')
def main():
filename, limit, output_format, version = grabargs()
try:
fl = open(filename)
except:
print " Error :No such file or directory: %s" % filename
sys.exit(0)
verb_field_number = 2
verb_cat_field_number = 3
line = fl.readline().decode("utf")
text = u""
verb_table = []
nb_field = 12
if output_format == "sql":
import sqldict
mydict = sqldict.SqlDict(version)
elif output_format == "xml":
import xmldict
mydict = xmldict.XmlDict(version)
elif output_format == "stardict":
import stardict
mydict = stardict.StarDict(version)
elif output_format == "spell":
import spelldict
elif output_format == "tags":
import tagsdict
mydict = tagsdict.TagsDict(version)
else:
import csvdict
mydict = csvdict.CsvDict(version)
while line:
line = line.strip('\n').strip()
if not line.startswith("#"):
liste = line.split("\t")
if len(liste) >= nb_field:
verb_table.append(liste)
line = fl.readline().decode("utf8")
fl.close()
# create header
print mydict.add_header().encode('utf8')
for tuple_verb in verb_table[:limit]:
#~ verb_dict = decode_tuple_verb(tuple_verb);
print mydict.add_record(tuple_verb).encode('utf8')
# create footer
print mydict.add_footer().encode('utf8')
def factory(output_format, version):
import csvdict
mydict = csvdict.CsvDict(version)
if output_format == "sql":
import sqldict
mydict = sqldict.SqlDict(version)
elif output_format == "xml":
import xmldict
mydict = xmldict.XmlDict(version)
elif output_format == "stardict":
import stardict
mydict = stardict.StarDict(version)
elif output_format == "spell":
import spelldict
elif output_format == "tags":
import tagsdict
mydict = tagsdict.TagsDict(version)
elif output_format == "check":
import checkdict
mydict = checkdict.checkDict(version)
else:
import csvdict
mydict = csvdict.CsvDict(version)
return mydict
def main():
args = grabargs()
filename = args.filename
limit = args.limit
output_format = args.outformat
wordtype = args.wordtype
version = args.version
#print "#--",filename,limit,display_format, wordtype;
#exit();
try:
fl = open(filename, encoding='utf-8')
except:
print(" Error :No such file or directory: %s" % filename)
sys.exit(0)
#~ print "#",filename,limit, output_format, wordtype, version
#~ sys.exit()
#display_format="txt"
line = fl.readline()
text = u""
noun_table = []
nb_field = 2
while line:
line = line.strip('\n') #.strip()
if not line.startswith("#"):
liste = line.split(Separator)
if len(liste) >= nb_field:
noun_table.append(liste)
line = fl.readline()
fl.close()
#print "#", (u'\t'.join(field_id.keys())).encode('utf8');
model = 0
if output_format == "sql":
import sqldict
mydict = sqldict.SqlDict(wordtype, version)
elif output_format == "xml":
import xmldict
mydict = xmldict.XmlDict(wordtype, version)
elif output_format == "stardict":
import stardict
mydict = stardict.StarDict(wordtype, version)
elif output_format == "tags":
import tagsdict
mydict = tagsdict.TagsDict(wordtype, version)
elif output_format == "spell":
import spelldict
mydict = spelldict.SpellDict(wordtype, version)
elif output_format == "check":
import checkdict
mydict = checkdict.checkDict(version)
else:
import csvdict
mydict = csvdict.CsvDict(wordtype, version)
# create header
h = "" # mydict.add_header()
if h:
print(h)
for tuple_noun in noun_table[:limit]:
l = mydict.add_record(tuple_noun)
if l:
print(l)
# create footer
f = mydict.add_footer()
if f:
print(f)
def main():
args = grabargs()
#~ filename, outputformat, allforms, version=grabargs()
filename = args.filename
outputformat = args.outformat
allforms = True if args.all else False
version = args.version if args.version else ""
print(filename, outputformat, allforms, version)
#~ sys.exit()
outputformat = string.lower(outputformat)
if outputformat not in ('csv', 'python', 'py', 'sql'):
outputformat = 'csv'
print "--~# generated format", outputformat
print "--~#file name ", filename
print "--~#output format", outputformat
#~sys.exit()
if outputformat in ('python', 'py'):
import pydict
mydict = pydict.PyDict(allforms, version)
elif outputformat == 'sql':
import sqldict
mydict = sqldict.SqlDict(allforms, version)
else:
import csvdict
mydict = csvdict.CsvDict(allforms, version)
if (not filename):
usage()
sys.exit(0)
option = ""
try:
fl = open(filename)
except:
print " Error :No such file or directory: %s" % filename
return None
line = fl.readline().decode("utf8")
text = u""
limit = 10000
nb_fields = 9
stop_table = []
while line:
line = line.strip('\n').strip()
if not line.startswith("#"):
liste = line.split("\t")
if len(liste) >= nb_fields:
stop_table.append(liste)
line = fl.readline().decode("utf8")
fl.close()
# create header
line = mydict.add_header().encode('utf8')
if line: print line
for tuple_stop in stop_table[:limit]:
line = mydict.add_record(tuple_stop).encode('utf8')
if line:
print line
# create footer
line = mydict.add_footer().encode('utf8')
if line: print line
