def extract_cp(phs):
if not phs:
return []
cps = []
for pi, ph in phs.items():
previous_w = mynlp.WordClass()
if not ph.parent_id:
continue
for word in ph.words:
if previous_w.pos_detail == "形式名詞":
continue
if word.pos_detail == "格助詞" and previous_w.pos == "名詞":
if ph.parent_id < 0:
continue
parent = phs[ph.parent_id]
parent_self_w = _extract_self_sufficient_word(parent.words)
if not parent_self_w:
continue
cp = {}
cp["noun"] = previous_w.base
cp["particle"] = word.particle
cp["predicate"] = parent_self_w.base
cp["cateogory"] = word.category
cps.append(cp)
return cps
def _knp(sentence):
if sentence == "":
return None
knp = pyknp.KNP()
try:
result = knp.parse(sentence)
except:
return None
# 情報をクラスに格納
phrases = OrderedDict() # 文節クラスのディクショナリ
for bnst in result.bnst_list():
ph = mynlp.PhraseClass(parent_id=bnst.parent_id,
dpndtype=bnst.dpndtype)
# この文節にふくまれる単語情報を格納
for mrph in bnst.mrph_list(): # mrph_list:文節内の形態素リスト
word = mynlp.WordClass(surface=mrph.midasi,
base=mrph.genkei,
yomi=mrph.yomi)
# 品詞関連詳細情報
pos_info = mrph.spec().split(" ") # or .new_spec()
# 表層形 読み 見出し語 品詞大分類 品詞大分類ID 品詞細分類 品詞細分類ID 活用型 活用型ID 活用形 活用形ID 意味情報
word.pos = pos_info[3] # 品詞
word.pos_detail = pos_info[5] # 品詞細分類
# 意味情報関連
imis = mrph.imis.split() # 代表表記,漢字読み,カテゴリなど
for imi in imis:
if "代表表記" in imi:
word.descriptions = imi.split(":", 1)[-1]
elif "カテゴリ" in imi:
word.category = imi.split(":", 1)[-1]
elif "ドメイン" in imi:
word.domain = imi.split(":", 1)[-1]
elif ("人名:" in imi) or ("地名:" in imi): # 固有名詞
word.proper_noun = imi.split(":", 1)[-1]
else:
word.another = word.another + imi + " "
ph.words.append(word)
phrases[bnst.bnst_id] = ph
for ph_i, ph in phrases.items():
if ph.parent_id != -1:
phrases[ph.parent_id].children.append(ph_i)
return phrases
def _embed_to_class(bnsts):
phs = OrderedDict()
if not bnsts:
return None
for bnst_i, bnst in enumerate(bnsts):
ph = mynlp.PhraseClass(parent_id=bnst["parent_id"], parent=bnst["parent"],
children=bnst["children"], dpndtype=bnst["dpndtype"])
for mrph in bnst["words"]:
word = mynlp.WordClass(mrph["surface"],mrph["base"],mrph["yomi"],
mrph["pos"],mrph["pos_detail"],mrph["descriptions"],
mrph["category"],mrph["domain"],mrph["another"],
mrph["proper_noun"])
ph.words.append(word)
phs[bnst_i] = ph
return phs
def _cross_word(w1, w2):
nw = mynlp.WordClass()
nw.base = w1.surface + w2.base
nw.surface = w1.surface + w2.surface
nw.yomi = w1.yomi + w2.yomi
nw.pos = w2.pos
nw.pos_detail = w2.pos_detail
ll = w1.original_words
if len(w2.original_words) > 0:
ll.extend(w2.original_words)
else:
ll.append(w2.base)
nw.original_words = ll
try:
nw.descriptions = w1.descriptions + "," + w2.descriptions
except:
if w1.descriptions:
nw.descriptions = w1.descriptions
try:
nw.cateegory = w1.category.extend(w2.category)
except:
if w2.category:
nw.cateegory = w2.category
try:
nw.domain = w1.domain.extend(w2.domain)
except:
if w2.domain:
nw.domain = w2.domain
try:
nw.another = w1.another.extend(w2.another)
except:
if w2.domain:
nw.domain = w2.domain
try:
nw.another = w1.another.extend(w2.another)
except:
if w2.another:
nw.another = w2.another
try:
nw.proper_noun = w1.proper_noun.extend(w2.proper_noun)
except:
if w2.proper_noun:
nw.proper_noun = w2.proper_noun
return nw