summaryrefslogtreecommitdiff
path: root/ext/ply/test/lex_hedit.py
blob: 34f15a173365bed9f1dc5fe5b52b0a6c92c073f2 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
# -----------------------------------------------------------------------------
# hedit.py
#
# Paring of Fortran H Edit descriptions (Contributed by Pearu Peterson)
#
# These tokens can't be easily tokenized because they are of the following
# form:
#
#   nHc1...cn
#
# where n is a positive integer and c1 ... cn are characters.
#
# This example shows how to modify the state of the lexer to parse
# such tokens
# -----------------------------------------------------------------------------
import sys
if ".." not in sys.path: sys.path.insert(0,"..")

import ply.lex as lex

tokens = (
    'H_EDIT_DESCRIPTOR',
    )

# Tokens
t_ignore = " \t\n"

def t_H_EDIT_DESCRIPTOR(t):
    r"\d+H.*"                     # This grabs all of the remaining text
    i = t.value.index('H')
    n = eval(t.value[:i])
    
    # Adjust the tokenizing position
    t.lexer.lexpos -= len(t.value) - (i+1+n)
    t.value = t.value[i+1:i+1+n]
    return t                                  
    
def t_error(t):
    print("Illegal character '%s'" % t.value[0])
    t.lexer.skip(1)
    
# Build the lexer
lex.lex()
lex.runmain(data="3Habc 10Habcdefghij 2Hxy")