Question

I am working on a simple SQL select like query parser and I need to be able to capture subqueries that can occur at certain places literally. I found lexer states are the best solution and was able to do a POC using curly braces to mark the start and end. However, the subqueries will be delimited by parenthesis, not curlys, and the parenthesis can occur at other places as well, so I can’t being the state with every open-paren. This information is readily available with the parser, so I was hoping to call begin and end at appropriate locations in the parser rules. This however didn’t work because lexer seem to tokenize the stream all at once, and so the tokens get generated in the INITIAL state. Is there a workaround for this problem? Here is an outline of what I tried to do:

def p_value_subquery(p):
    """
     value : start_sub end_sub
    """
    p[0] = "( " + p[1] + " )"

def p_start_sub(p):
    """
    start_sub : OPAR
    """
    start_subquery(p.lexer)
    p[0] = p[1]

def p_end_sub(p):
    """
    end_sub : CPAR
    """
    subquery = end_subquery(p.lexer)
    p[0] = subquery

The start_subquery() and end_subquery() are defined like this:

def start_subquery(lexer):
    lexer.code_start = lexer.lexpos        # Record the starting position
    lexer.level = 1
    lexer.begin('subquery') 

def end_subquery(lexer):
    value = lexer.lexdata[lexer.code_start:lexer.lexpos-1]
    lexer.lineno += value.count('\n')
    lexer.begin('INITIAL')
    return value

The lexer tokens are simply there to detect the close-paren:

@lex.TOKEN(r"\(")
def t_subquery_SUBQST(t):
    lexer.level += 1

@lex.TOKEN(r"\)")
def t_subquery_SUBQEN(t):
    lexer.level -= 1

@lex.TOKEN(r".")
def t_subquery_anychar(t):
    pass

I would appreciate any help.

Answer 1

Based on PLY author’s response, I came up with this better solution. I am yet to figure out how to return the subquery as a token, but the rest looks much better and need not be considered a hack anymore.

def start_subquery(lexer):
    lexer.code_start = lexer.lexpos        # Record the starting position
    lexer.level = 1
    lexer.begin("subquery")

def end_subquery(lexer):
    lexer.begin("INITIAL")

def get_subquery(lexer):
    value = lexer.lexdata[lexer.code_start:lexer.code_end-1]
    lexer.lineno += value.count('\n')
    return value

@lex.TOKEN(r"\(")
def t_subquery_OPAR(t):
    lexer.level += 1

@lex.TOKEN(r"\)")
def t_subquery_CPAR(t):
    lexer.level -= 1
    if lexer.level == 0:
        lexer.code_end = lexer.lexpos        # Record the ending position
        return t

@lex.TOKEN(r".")
def t_subquery_anychar(t):
    pass

def p_value_subquery(p):
    """
    value : check_subquery_start OPAR check_subquery_end CPAR
    """
    p[0] = "( " + get_subquery(p.lexer) + " )"

def p_check_subquery_start(p):
    """
    check_subquery_start : 
    """
    # Here last_token would be yacc's lookahead.
    if last_token.type == "OPAR":
        start_subquery(p.lexer)

def p_check_subquery_end(p):
    """
    check_subquery_end : 
    """
    # Here last_token would be yacc's lookahead.
    if last_token.type == "CPAR":
        end_subquery(p.lexer)

last_token = None

def p_error(p):
    global subquery_retry_pos
    if p is None:
        print >> sys.stderr, "ERROR: unexpected end of query"
    else:
        print >> sys.stderr, "ERROR: Skipping unrecognized token", p.type, "("+ \
                p.value+") at line:", p.lineno, "and column:", find_column(p.lexer.lexdata, p)
        # Just discard the token and tell the parser it's okay.
        yacc.errok()

def get_token():
    global last_token
    last_token = lexer.token()
    return last_token

def parse_query(input, debug=0):
    lexer.input(input)
    return parser.parse(input, tokenfunc=get_token, debug=0)