def wsjtree2pos(wsj_corpus_path):
print >> sys.stderr, "Reading in corpus..."
sentences = []
for d in os.listdir(wsj_corpus_path):
if os.path.isdir(wsj_corpus_path + "/" + d) and d != "CVS" and int(d) < 8:
for f in os.listdir(wsj_corpus_path + "/" + d):
if f.endswith(".mrg"):
fname = wsj_corpus_path + "/" + d + "/" + f
# print fname
tree_f = open(fname, "r")
tree_string = ""
for line in tree_f:
if line.strip():
if line.startswith("( (") or line.startswith("(("):
if tree_string:
tr = Tree(tree_string)
sentences.append(tr.pos())
tree_string = line.strip()
else:
tree_string = line.strip()
else:
tree_string += line.strip()
if tree_string:
tr = Tree(tree_string)
sentences.append(tr.pos())
return sentences
def parse_coord(t: Tree, is_coord: bool):
if len(t.leaves()) == 1:
if t.pos()[0][1] == '-NONE-':
return []
else:
return [(t.leaves()[0], is_coord)]
res = []
for subtree in t:
res += parse_coord(subtree, is_coord or "COORD" in subtree.label())
return res
def getPOS(message):
body = {
"language" : "en",
"analyzerIds" : ["22a6b758-420f-4745-8a3c-46835a67c0d2"],
"text" : message
};
try:
conn = HTTPSConnection('api.projectoxford.ai')
conn.connect()
conn.request("POST", "/linguistics/v1.0/analyze", json.dumps(body), headers)
response = conn.getresponse()
data = json.loads(response.read().decode())
conn.close()
ct = Tree.fromstring(data[0]['result'][0])
pos = Tree.pos(ct)
return pos;
except Exception as e: #Error occurred
print(e)
return False;
Tree('Item', ['f1']),
Tree('List',
[Tree('Item', ['f2']),
Tree('List', [Tree('Item', ['f3'])])])
]), 'to',
Tree('Item', ['folder'])
])
print(t2)
print(t2.flatten())
print(type(t2.flatten()))
print(t2.collapse_unary())
max_subtree = Tree('', [])
for subtree in t2.subtrees(filter=lambda x: x.label() == 'List'):
if len(subtree.flatten().pos()) > len(max_subtree.pos()):
max_subtree = subtree
print(max_subtree)
'''
tmp = t2
i =
while tmp.label() != 'List':
i += 1
tmp = tmp.pos()
print("the " + str(i) + " time:")
print(tmp)
print(type(tmp))
tmp = tmp.flatten()
print(t2)
'''
def from_parsed_sentence(cls, parsed_sent: Tree) -> 'GenerativeOracle':
actions = cls.get_actions(parsed_sent)
_, pos_tags = zip(*parsed_sent.pos())
return cls(actions, list(pos_tags))
def from_parsed_sentence(cls, parsed_sent: Tree) -> 'DiscriminativeOracle':
actions = cls.get_actions(parsed_sent)
words, pos_tags = zip(*parsed_sent.pos())
return cls(actions, list(pos_tags), list(words))
Tree('List', [
Tree('Item', ['f1']),
Tree('List', [
Tree('Item', ['f2']),
Tree('List', [Tree('Item', ['f3'])])])]),
'to',
Tree('Item', ['folder'])])
print(t2)
print(t2.flatten())
print(type(t2.flatten()))
print(t2.collapse_unary())
max_subtree = Tree('', [])
for subtree in t2.subtrees(filter = lambda x: x.label() == 'List'):
if len(subtree.flatten().pos()) > len(max_subtree.pos()):
max_subtree = subtree
print(max_subtree)
'''
tmp = t2
i =
while tmp.label() != 'List':
i += 1
tmp = tmp.pos()
print("the " + str(i) + " time:")
print(tmp)
print(type(tmp))
tmp = tmp.flatten()
def from_tree(cls, tree: Tree) -> 'DiscOracle':
actions = cls.get_actions(tree)
words, pos_tags = zip(*tree.pos())
return cls(actions, list(pos_tags), list(words))
def from_tree(cls, tree: Tree) -> 'GenOracle':
actions = cls.get_actions(tree)
_, pos_tags = zip(*tree.pos())
return cls(actions, list(pos_tags))
def traverse(node):
def extract_tags(W):
pos = [W.getAttribute('lc') if W.getAttribute('lc') else None]
if W.getAttribute('clitic') in {
'ezafe', 'pronominal', 'verb', 'prep', 'adv', 'det'
}:
pos.append(W.getAttribute('clitic'))
if W.getAttribute('ne_sort'):
pos.append(W.getAttribute('ne_sort'))
if W.getAttribute('n_type'):
pos.append(W.getAttribute('n_type'))
if W.getAttribute('ya_type'):
pos.append(W.getAttribute('ya_type'))
if W.getAttribute('ke_type'):
pos.append(W.getAttribute('ke_type'))
if W.getAttribute('type'):
pos.append(W.getAttribute('type'))
if W.getAttribute('kind'):
pos.append(W.getAttribute('kind'))
return pos
def clitic_join(tree, clitic):
if type(tree[-1]) == Tree:
return clitic_join(tree[-1], clitic)
else:
if (clitic[0][0][0] == 'ا'):
clitic[0] = ('' + clitic[0][0], clitic[0][1])
tree[-1] = (tree[-1][0] + clitic[0][0], clitic[0][1])
tree.set_label('CLITICS')
return
if not len(node.childNodes):
return
first = node.childNodes[0]
if first.tagName == 'w':
pos = extract_tags(first)
return Tree(node.tagName, [(first.childNodes[0].data.replace(
'می ', 'می'), self._pos_map(pos))])
childs = node.childNodes[
2:] if node.tagName == 'S' else node.childNodes
for child in childs:
if not len(child.childNodes):
childs.remove(child)
tree = Tree(node.tagName, map(traverse, childs))
if self._join_clitics and len(tree) > 1 and type(
tree[1]) == Tree and tree[1].label(
) == 'CLITIC' and tree[1][0][1] not in {'P', 'V'}:
clitic = tree[-1]
tree = Tree(tree.label(), [subtree for subtree in tree[0]])
clitic_join(tree, clitic)
if self._join_verb_parts and len(tree) > 1 and type(
tree[1]) == Tree and type(
tree[0]) == Tree and tree[0].label() == 'AUX' and tree[
0][0][0] in self._tokenizer.before_verbs:
tree[1][0] = (tree[0][0][0] + ' ' + tree[1][0][0],
tree[1][0][1])
tree.remove(tree[0])
if self._join_verb_parts and len(
tree.leaves()) > 1 and tree.leaves(
)[-1][0] in self._tokenizer.after_verbs and tree.leaves(
)[-2][0] in self._tokenizer.verbe:
tree[1][0] = (tree[0].leaves()[-1][0] + ' ' + tree[1][0][0],
tree[1][0][1])
path = tree.leaf_treeposition(len(tree.leaves()) - 2)
removingtree = tree
while len(path) > 2:
removingtree = removingtree[path[0]]
path = path[1:]
removingtree.remove(
Tree(tree.pos()[-2][1], [tree.pos()[-2][0]]))
if self._join_verb_parts and len(
tree.leaves()) > 1 and tree.leaves(
)[-1][0] in self._tokenizer.after_verbs and tree.leaves(
)[-2][0] in self._tokenizer.verbe:
tree[1][0] = (tree[0].leaves()[-1][0] + ' ' + tree[1][0][0],
tree[1][0][1])
path = tree.leaf_treeposition(len(tree.leaves()) - 2)
removingtree = tree
while len(path) > 2:
removingtree = removingtree[path[0]]
path = path[1:]
removingtree.remove(
Tree(tree.pos()[-2][1], [tree.pos()[-2][0]]))
return tree
def traverse(node):
def extract_tags(W):
pos = [W.getAttribute('lc') if W.getAttribute('lc') else None]
if W.getAttribute('clitic') in {'ezafe', 'pronominal', 'verb', 'prep', 'adv', 'det'}:
pos.append(W.getAttribute('clitic'))
if W.getAttribute('ne_sort'):
pos.append(W.getAttribute('ne_sort'))
if W.getAttribute('n_type'):
pos.append(W.getAttribute('n_type'))
if W.getAttribute('ya_type'):
pos.append(W.getAttribute('ya_type'))
if W.getAttribute('ke_type'):
pos.append(W.getAttribute('ke_type'))
if W.getAttribute('type'):
pos.append(W.getAttribute('type'))
if W.getAttribute('kind'):
pos.append(W.getAttribute('kind'))
return pos
def clitic_join(tree, clitic):
if type(tree[-1]) == Tree:
return clitic_join(tree[-1], clitic)
else:
if(clitic[0][0][0] == 'ا'):
clitic[0] = ('' + clitic[0][0], clitic[0][1])
tree[-1]=(tree[-1][0] + clitic[0][0], clitic[0][1])
tree.set_label('CLITICS')
return
if not len(node.childNodes):
return
first = node.childNodes[0]
if first.tagName == 'w':
pos=extract_tags(first)
return Tree(node.tagName, [(first.childNodes[0].data.replace('می ', 'می'), self._pos_map(pos))])
childs = node.childNodes[2:] if node.tagName == 'S' else node.childNodes
for child in childs:
if not len(child.childNodes):
childs.remove(child)
tree = Tree(node.tagName, map(traverse, childs))
if self._join_clitics and len(tree) > 1 and type(tree[1]) == Tree and tree[1].label() == 'CLITIC' and tree[1][0][1] not in {'P', 'V'}:
clitic=tree[-1]
tree = Tree(tree.label(), [subtree for subtree in tree[0]])
clitic_join(tree, clitic)
if self._join_verb_parts and len(tree) > 1 and type(tree[1]) == Tree and type(tree[0]) == Tree and tree[0].label() == 'AUX' and tree[0][0][0] in self._tokenizer.before_verbs:
tree[1][0] = (tree[0][0][0] + ' ' + tree[1][0][0], tree[1][0][1])
tree.remove(tree[0])
if self._join_verb_parts and len(tree.leaves()) > 1 and tree.leaves()[-1][0] in self._tokenizer.after_verbs and tree.leaves()[-2][0] in self._tokenizer.verbe :
tree[1][0] = (tree[0].leaves()[-1][0] + ' ' + tree[1][0][0], tree[1][0][1])
path = tree.leaf_treeposition(len(tree.leaves())-2)
removingtree = tree
while len(path) > 2 :
removingtree = removingtree[path[0]]
path = path[1:]
removingtree.remove(Tree(tree.pos()[-2][1],[tree.pos()[-2][0]]))
if self._join_verb_parts and len(tree.leaves()) > 1 and tree.leaves()[-1][0] in self._tokenizer.after_verbs and tree.leaves()[-2][0] in self._tokenizer.verbe :
tree[1][0] = (tree[0].leaves()[-1][0] + ' ' + tree[1][0][0], tree[1][0][1])
path = tree.leaf_treeposition(len(tree.leaves())-2)
removingtree = tree
while len(path) > 2 :
removingtree = removingtree[path[0]]
path = path[1:]
removingtree.remove(Tree(tree.pos()[-2][1],[tree.pos()[-2][0]]))
return tree
