前言
最近刚学python,写一个小工具时需要提取sql语句中表名,查询一番后找到一篇文章挺不错的,mark一下
PS.那篇文章是转载的,且没有标注转载自哪里
正文
import ply.lex as lex, re
def extract_table_name_from_sql(sql_str):
# remove the /* */ comments
q = re.sub(r"/\*[^*]*\*+(?:[^*/][^*]*\*+)*/", "", sql_str)
# remove whole line -- and # comments
lines = [line for line in q.splitlines() if not re.match("^\s*(--|#)", line)]
# remove trailing -- and # comments
q = " ".join([re.split("--|#", line)[0] for line in lines])
# split on blanks, parens and semicolons
tokens = re.split(r"[\s)(;]+", q)
# scan the tokens. if we see a FROM or JOIN, we set the get_next
# flag, and grab the next one (unless it's SELECT).
result = []
get_next = False
for token in tok