BIDI_ML_INFO_EXTRACTION/BiddingKG/dl/test/7.py

#coding:UTF-8
a = 1<<10
b = bin(a)
print(int(b[2:],2)>>10)
c = a | (1<<2)
print(b)
print(a)

a = "1234"

print("-",a[3:])

import math
print(2**32)
print(math.pow(2,32))

print(hex(ord('g')))

def get_s16(val):
    if val < 0x80000000:
        return val
    else:
        return (val - 0x100000000)
print(hex(336860180))

print(0xf0551700)
print(0xe8c81900)

print([int(math.floor(abs(math.sin(i + 1)) * (2 ** 32))) for i in range(64)])

import re
_pattern = "(?P<projectDigest>项目概况.{10,1000})"
# _pattern = "(建筑面积[约为是]*[\d,]+(\.\d+)?[十百千万]*(㎡|平方米))"

text = '''
项目名称：淮上区2020年市政道路维修及绿化养护施工工程监理 
'''
text = text.replace("\r","").replace("\n",'')



def extract_proportion(content):
    _pattern = "(?P<proportion>((建筑|建设|区域)?面积|全长|项目规模)[大概约为是:：【\[\s]*[\d,]+(\.\d+)?[十百千万]*([\]】平方kK千万公㎡mM米里]*))"
    _pattern_search = re.search(_pattern,content)
    _proportion = ""
    if _pattern_search is not None:
        _proportion = _pattern_search.groupdict().get("proportion","")
    return _proportion

def extract_projectDigest(content):
    _pattern = "(?P<projectDigest>(项目|工程|标的|需求|建设|招标|采购|内容)(概况|规模|简介|信息|范围|内容|说明|摘要).{10,300})"
    _pattern_search = re.search(_pattern,content)
    _projectDigest = ""
    _find = ""
    if _pattern_search is not None:
        _find = _pattern_search.groupdict().get("projectDigest","")
    if len(_find)>0:
        _projectDigest = "。".join(_find.split("。")[0:3])
    return _projectDigest

print(extract_proportion(text))

print(re.findall(_pattern,text))
print(extract_projectDigest(text))

import uuid

print(uuid.uuid4())

def extract_legal_stage(content,_pattern):
    dict_stage = {"设计阶段":"设计",
                  "环评阶段":"环评",
                  "施工准备":"监理",
                  "施工在建":"施工"}
    list_stage_v = []
    for k,v in dict_stage.items():
        list_stage_v.append("(?P<%s>%s)"%(k,v))
    stage_pattern = "|".join(list_stage_v)
    list_stage = []
    for stage_search in re.finditer(stage_pattern,content):
        for k,v in stage_search.groupdict().items():
            if v is not None:
                list_stage.append(k)
    if len(list_stage)>0:
        return list_stage[-1]
    return None

print(extract_legal_stage(text,"工程"))