确实，这不是一件容易的事。您可以使用词法分析器（在此示例中为ply）并定义一些规则以从字符串中获取多个标记。以下代码为SQL字符串的不同部分定义了这些规则，并将它们放在一起，因为输入字符串中可能会有别名。结果，您将获得一个
result以不同表名作为键的字典（）。
import ply.lex as lex, retokens = ( "TABLE", "JOIN", "COLUMN", "TRASH")tables = {"tables": {}, "alias": {}}columns = []t_TRASH = r"Select|on|=|;|s+|,|t|r"def t_TABLE(t): r"froms(w+)sass(w+)" regex = re.compile(t_TABLE.__doc__) m = regex.search(t.value) if m is not None: tbl = m.group(1) alias = m.group(2) tables["tables"][tbl] = "" tables["alias"][alias] = tbl return tdef t_JOIN(t): r"inners+joins+(w+)s+ass+(w+)" regex = re.compile(t_JOIN.__doc__) m = regex.search(t.value) if m is not None: tbl = m.group(1) alias = m.group(2) tables["tables"][tbl] = "" tables["alias"][alias] = tbl return tdef t_COLUMN(t): r"(w+.w+)" regex = re.compile(t_COLUMN.__doc__) m = regex.search(t.value) if m is not None: t.value = m.group(1) columns.append(t.value) return tdef t_error(t): raise TypeError("Unknown text '%s'" % (t.value,)) t.lexer.skip(len(t.value))# here is where the magic startsdef mylex(inp): lexer = lex.lex() lexer.input(inp) for token in lexer: pass result = {} for col in columns: tbl, c = col.split('.') if tbl in tables["alias"].keys(): key = tables["alias"][tbl] else: key = tbl if key in result: result[key].append(c) else: result[key] = list() result[key].append(c) print result # {'tb1': ['col1', 'col7'], 'tb2': ['col2', 'col8']}string = "Select a.col1, b.col2 from tb1 as a inner join tb2 as b on tb1.col7 = tb2.col8;"mylex(string)
