ourdaidai

The repository for the assignment is public and Github does not allow the creation of private forks for public repositories.

The correct way of creating a private frok by duplicating the repo is documented here.

For this assignment the commands are:

1. Create a bare clone of the repository. (This is temporary and will be removed so just do it wherever.)

git clone --bare git@github.com:usi-systems/easytrace.git

ourdaidai

import uniout
from pprint import pprint
langs = [
    'Hello, world!',
    '你好，世界！',
    'こんにちは世界',
    u'Hello, world!',
    u'你好，世界！',
    u'こんにちは世界'
]

ourdaidai

# -*- coding: utf-8 -*-

from shapely.geometry import Point, LineString, Polygon, MultiPolygon
from shapely import wkt
import geopandas as gpd
import pandas as pd
import os
#os.environ['NLS_LANG'] = 'SIMPLIFIED CHINESE_CHINA.UTF8' # 万一中文有问题

ourdaidai

匹配表注释，只保留中文英文，忽略数据字典
	^[\u4e00-\u9fa5_a-zA-Z0-9]+
    
匹配XX_AA_XX中的 'AA'
    (?<=_).*?(?=_)

# 匹配 'CREATE  TABLE    TEST22    SELECT   uid   from test1' 中的 'TEST22'
def extract_table_name(sql):
    sql = re.sub(r'\s+', ' ', sql)
    p_name = re.compile(r'(?<=(CREATE TABLE\s))\S+')

ourdaidai

import pymysql

def reconnect_mysql(func):
    def wrapper(self, *args, **kwargs):
        try:
            self.connection.ping(reconnect=True)
        except pymysql.OperationalError:
            self.connection = pymysql.connect(host=self.host, port=self.port, user=self.user, password=self.password,
                                              db=self.db, charset='utf8mb4')
        finally:

ourdaidai

import yaml

file = open('config.yaml', 'r', encoding='utf-8')
file_data = file.read()
file.close()
config = yaml.full_load(file_data)


CONNECT_DEBUG = config[config['DB_TABLES_DEBUG']['CONNECT']]
CONNECT_PRODUCE = config[config['DB_TABLES_PRODUCE']['CONNECT']]

ourdaidai

# -*- coding: utf-8 -*-
"""
Created on Fri Aug 28 10:06:04 2020

@author: tangliang
"""

import pymysql
import pandas as pd
from tqdm import tqdm

ourdaidai

import unicodedata

if self._do_lower_case:
  if is_py2:
    text = unicode(text)
    text = unicodedata.normalize('NFD', text)
    text = ''.join([
      ch for ch in text if unicodedata.category(ch) != 'Mn'
    ])
    text = text.lower()

ourdaidai

import pymysql
import datetime
import time
import pandas as pd
from sqlalchemy import Column, String, create_engine
import os
from ftplib import FTP

current_path = os.path.dirname(__file__)

ourdaidai

with open(filename, 'rb') as f:
  for line in f:
    <do something with the line>