I'm parsing sentences like:
"CS 2310 or equivalent experience"
The desired output:
[[("CS", 2310)], ["equivalent experience"]]
YACC tokenizer symbols:
tokens = [
'DEPT_CODE',
'COURSE_NUMBER',
'OR_CONJ',
'MISC_TEXT',
]
t_DEPT_CODE = r'[A-Z]{2,}'
t_COURSE_NUMBER = r'[0-9]{4}'
t_OR_CONJ = r'or'
t_ignore = ' \t'
terms = {'DEPT_CODE': t_DEPT_CODE,
'COURSE_NUMBER': t_COURSE_NUMBER,
'OR_CONJ': t_OR_CONJ}
for name, regex in terms.items():
terms[name] = "^%s$" % regex
def t_MISC_TEXT(t):
r'\S+'
for name, regex in terms.items():
# print "trying to match %s with regex %s" % (t.value, regex)
if re.match(regex, t.value):
t.type = name
return t
return t
(MISC_TEXT is meant to match anything not caught by the other terms.)
Some relevant rules from the parser:
precedence = (
('left', 'MISC_TEXT'),
)
def p_statement_course_data(p):
'statement : course_data'
p[0] = p[1]
def p_course_data(p):
'course_data : course'
p[0] = p[1]
def p_course(p):
'course : DEPT_CODE COURSE_NUMBER'
p[0] = make_course(p[1], int(p[2]))
def p_or_phrase(p):
'or_phrase : statement OR_CONJ statement'
p[0] = [[p[1]], [p[3]]]
def p_misc_text(p):
'''text_aggregate : MISC_TEXT MISC_TEXT
| MISC_TEXT text_aggregate
| text_aggregate MISC_TEXT '''
p[0] = "%s %s" % (p[0], [1])
def p_text_aggregate_statement(p):
'statement : text_aggregate'
p[0] = p[1]
Unfortunately, this fails:
# works as it should
>>> token_list("CS 2110 or equivalent experience")
[LexToken(DEPT_CODE,'CS',1,0), LexToken(COURSE_NUMBER,'2110',1,3), LexToken(OR_CONJ,'or',1,8), LexToken(MISC_TEXT,'equivalent',1,11), LexToken(MISC_TEXT,'experience',1,22)]
# fails. bummer.
>>> parser.parse("CS 2110 or equivalent experience")
Syntax error in input: LexToken(MISC_TEXT,'equivalent',1,11)
What am I doing wrong? I don't fully understand how to set precedence rules.
Also, this is my error function:
def p_error(p):
print "Syntax error in input: %s" % p
Is there a way to see which rule the parser was trying when it failed? Or some other way to make the parser print which rules its trying?
