def prettyprint(self):
file = open(self.path)
for line in file:
srcnode = binarize.CBinarizedTreeNode()
srcnode.load(line)
print srcnode.prettyprint()
file.close()
def process(self):
file = open(self.path)
for line in file:
srcnode = binarize.CBinarizedTreeNode()
srcnode.load(line)
print srcnode.tokens(self.sep)
file.close()
def prettyprint(self):
file = open(self.path)
for line in file:
if not line.strip(): print; continue
srcnode = binarize.CBinarizedTreeNode()
srcnode.load(line)
print srcnode.prettyprint(self.escape)
file.close()
def process(self, retval):
file = open(self.path)
for line in file:
srcnode = binarize.CBinarizedTreeNode()
srcnode.load(line)
self.extract_rules(srcnode, retval)
file.close()
def topipe(self):
sys.path.append(os.path.join(os.path.dirname(__file__), '../../../ccg'))
import pipe
file = open(self.path)
for line in file:
if not line.strip(): print; continue
srcnode = binarize.CBinarizedTreeNode()
srcnode.load(line)
print pipe.PrintBinarizedTree(srcnode)
file.close()
def process(self):
file = open(self.path)
for line in file:
if not line.strip(): print; continue
srcnode = binarize.CBinarizedTreeNode()
srcnode.load(line)
nodes = self.build_node(srcnode)
assert len(nodes) == 1
yield nodes[0]
file.close()
def topipe(self):
sys.path.append(os.path.join(os.path.dirname(__file__), '../ext/zpar/scripts/ccg'))
import pipe
file = open(self.path)
for line in file:
if not line.strip(): print; continue
tokens = line.split()
nIndex = 0
while True:
srcnode = binarize.CBinarizedTreeNode()
nIndex = srcnode.load_list(tokens, nIndex)
print pipe.PrintBinarizedTree(srcnode)
assert nIndex <= len(tokens)
if nIndex == len(tokens):
break
file.close()
def updatepos(path, pospath, sSep, output):
def updatenode(node, sent):
if node.type == 'token':
node.name = sent[0][1]
sent.pop(0)
else:
updatenode(node.left_child, sent)
if node.right_child:
updatenode(node.right_child, sent)
file = codecs.open(path, encoding='utf-8')
pos_it = posio.posread(pospath, sSep)
for line in file:
pos = pos_it.next()
# get node
srcnode = binarize.CBinarizedTreeNode()
srcnode.load(line)
updatenode(srcnode, pos)
# prin
output.write(srcnode.utf8print() + "\n")
def updatepos(path, pospath, sSep):
def updatenode(node, sent):
if node.type == 'token':
node.name = sent[0][1]
sent.pop(0)
else:
updatenode(node.left_child, sent)
if node.right_child:
updatenode(node.right_child, sent)
file = open(path)
pos_it = posio.posread(pospath, sSep)
for line in file:
pos = pos_it.next()
# get node
srcnode = binarize.CBinarizedTreeNode()
srcnode.load(line)
updatenode(srcnode, pos)
# prin
print srcnode
opts, args = getopt.getopt(sys.argv[1:], "d:i:o:r:")
except getopt.GetoptError:
print "\nUsage: append_wordstructure.py [-iinfile] [-ddictionary_file] [-ooutfile] [-rdictionaryout_file]\n"
sys.exit(1)
sInfile = None
sDictionary = None
sOutfile = None
sDictOutFile = None
for opt in opts:
if opt[0] == '-d':
sDictionary = opt[1]
elif opt[0] == '-i':
sInfile = opt[1]
elif opt[0] == '-o':
sOutfile = opt[1]
elif opt[0] == '-r':
sDictOutFile = opt[1]
wordstut = CWordStrucutre(sDictionary,sDictOutFile)
if sInfile == None or sOutfile == None or sDictOutFile == None:
print "\nUsage: append_wordstructure.py [-iinfile] [-ddictionary_file] [-ooutfile] [-rdictionaryout_file]\n"
sys.exit(1)
file = codecs.open(sInfile,encoding='utf-8')
wfile = codecs.open(sOutfile,'w',encoding='utf-8')
for line in file:
znode = binarize.CBinarizedTreeNode();
znode.load(line)
newtree = wordstut.process(znode)
wfile.write(newtree.utf8print()+"\n")
wfile.close()