def test_full_text_extract6():
"""地址在开头 4级地址测试"""
pca, addr = addressparser._full_text_extract('泉州市洛江区万安塘西工业区', 8)
print(pca, addr)
assert addr == '万安塘西工业区'
assert pca.province_pos == -1
assert pca.city == '泉州市'
assert pca.city_pos == 0
assert pca.area == '洛江区'
assert pca.area_pos == 3
def test_full_text_extract5():
"""测试满足贪婪匹配模式"""
pca, addr = addressparser._full_text_extract('湖北武汉武昌区复兴路1号', 3)
print(pca, addr)
assert addr == '复兴路1号'
assert pca.province == '湖北省'
assert pca.province_pos == 0
assert pca.city == '武汉市'
assert pca.city_pos == 2
assert pca.area == '武昌区'
assert pca.area_pos == 4
def test_full_text_extract4():
"""测试较小的lookahead"""
pca, addr = addressparser._full_text_extract('湖北武汉东西湖区复兴路1号', 2)
print(pca, addr)
assert addr == '东西湖区复兴路1号'
assert pca.province == '湖北省'
assert pca.province_pos == 0
assert pca.city == '武汉市'
assert pca.city_pos == 2
assert pca.area == ''
assert pca.area_pos == -1
def test_full_text_extract3():
"""地址在中间, 验证地址截取规则:只截取句子开头提取到的地址"""
pca, addr = addressparser._full_text_extract('我家的地址是湖北武汉武昌区复兴路1号', 8)
print(pca, addr)
assert addr == '我家的地址是湖北武汉武昌区复兴路1号'
assert pca.province == '湖北省'
assert pca.province_pos == 6
assert pca.city == '武汉市'
assert pca.city_pos == 8
assert pca.area == '武昌区'
assert pca.area_pos == 10
def test_full_text_extract2():
"""地址在结尾"""
pca, addr = addressparser._full_text_extract('我的家在湖北武汉武昌区', 8)
assert addr == '我的家在湖北武汉武昌区'
assert pca.province == '湖北省'
assert pca.province_pos == 4
assert pca.city == '武汉市'
assert pca.city_pos == 6
assert pca.area == '武昌区'
assert pca.area_pos == 8
def test_full_text_extract1():
"""地址在开头"""
pca, addr = addressparser._full_text_extract('湖北武汉武昌区复兴路111号', 8)
assert addr == '复兴路111号'
assert pca.province == '湖北省'
assert pca.province_pos == 0
assert pca.city == '武汉市'
assert pca.city_pos == 2
assert pca.area == '武昌区'
assert pca.area_pos == 4
