python - antlr4 python 3 从 plsql 语法打印或转储标记

Question

我在Python中使用antlr4来读取以下语法:

https://github.com/antlr/grammars-v4/tree/master/plsql

文件 grants.sql 只有“begin select 'bob' from Dual; end;”

打印像树一样的 Lisp 的简单代码

from antlr4 import *
from PlSqlLexer import PlSqlLexer
from PlSqlParser import PlSqlParser
from PlSqlParserListener import PlSqlParserListener

input = FileStream('grants.sql')
lexer = PlSqlLexer(input)

stream = CommonTokenStream(lexer)
parser = PlSqlParser(stream)
tree = parser.sql_script()

print ("Tree " + tree.toStringTree(recog=parser));

输出如下:

tree(sql_script(unit_statement(anonymous_block begin)(seq_of_statements(squl_statement(data_manipulation _Statement) (compound_expression(condenation(model_expression(unary_expression) (atom (constant (quoted_string 'bob')))))))))))))) (from_clause FROM (table_ref_list (table_ref (table_ref_aux (table_ref_aux_internal (dml_table_expression_clause (tableview_name (identifier (id_expression (regular_id DUAL))))))) )))))))))))) ;) 结束 ;)) )

我希望能够有 python 代码列出上述内容，而不是像 lisp 那样的语句，而是列出所有规则和标记..即

1. .sql_脚本
2. ..unit_statement
3. ...anonymous_block
4. ...开始

等等等等

有人可以提供执行此操作的 python 代码或给我一些提示吗？不胜感激。

Answer 1

这是一个开始:

from antlr4 import *
from antlr4.tree.Tree import TerminalNodeImpl
from PlSqlLexer import PlSqlLexer
from PlSqlParser import PlSqlParser

# Generate the lexer nad parser like this:
#
#   java -jar antlr-4.7.1-complete.jar -Dlanguage=Python3 *.g4
#
def main():
    lexer = PlSqlLexer(InputStream("SELECT * FROM TABLE_NAME"))
    parser = PlSqlParser(CommonTokenStream(lexer))
    tree = parser.sql_script()
    traverse(tree, parser.ruleNames)

def traverse(tree, rule_names, indent = 0):
    if tree.getText() == "<EOF>":
        return
    elif isinstance(tree, TerminalNodeImpl):
        print("{0}TOKEN='{1}'".format("  " * indent, tree.getText()))
    else:
        print("{0}{1}".format("  " * indent, rule_names[tree.getRuleIndex()]))
        for child in tree.children:
            traverse(child, rule_names, indent + 1)

if __name__ == '__main__':
    main()

打印:

sql_script
  unit_statement
    data_manipulation_language_statements
      select_statement
        subquery
          subquery_basic_elements
            query_block
              TOKEN='SELECT'
              TOKEN='*'
              from_clause
                TOKEN='FROM'
                table_ref_list
                  table_ref
                    table_ref_aux
                      table_ref_aux_internal
                        dml_table_expression_clause
                          tableview_name
                            identifier
                              id_expression
                                regular_id
                                  TOKEN='TABLE_NAME'

请注意，为了使词法分析器和解析器正常工作，我添加了以下 Python 类:

# PlSqlBaseLexer.py
from antlr4 import *

class PlSqlBaseLexer(Lexer):

    def IsNewlineAtPos(self, pos):
        la = self._input.LA(pos)
        return la == -1 or la == '\n'

和:

# PlSqlBaseParser.py
from antlr4 import *

class PlSqlBaseParser(Parser):

    _isVersion10 = False
    _isVersion12 = True

    def isVersion10(self):
        return self._isVersion10

    def isVersion12(self):
        return self._isVersion12

    def setVersion10(self, value):
        self._isVersion10 = value

    def setVersion12(self, value):
        self._isVersion12 = value

我将其放置在与生成的 Python 类相同的文件夹中。我还需要在生成的 PlSqlLexer.py 类中添加 import 语句 from PlSqlBaseLexer import PlSqlBaseLexer ，并修复 PlSqlParser.py 中的导入语句从 from ./PlSqlBaseParser import PlSqlBaseParser 到 from PlSqlBaseParser import PlSqlBaseParser。

请注意，运行演示相当慢。除非您有在 Python 中执行此操作的硬性要求，否则我建议您使用(快得多!)更快的 Java 或 C# 目标。