此代码结合使用ast
(以查找初始参数偏移)和正则表达式(以识别参数的边界):
import ast
import re
def collect_offsets(call_string):
def _abs_offset(lineno, col_offset):
current_lineno = 0
total = 0
for line in call_string.splitlines():
current_lineno += 1
if current_lineno == lineno:
return col_offset + total
total += len(line)
# parse call_string with ast
call = ast.parse(call_string).body[0].value
# collect offsets provided by ast
offsets = []
for arg in call.args:
a = arg
while isinstance(a, ast.BinOp):
a = a.left
offsets.append(_abs_offset(a.lineno, a.col_offset))
for kw in call.keywords:
offsets.append(_abs_offset(kw.value.lineno, kw.value.col_offset))
if call.starargs:
offsets.append(_abs_offset(call.starargs.lineno, call.starargs.col_offset))
if call.kwargs:
offsets.append(_abs_offset(call.kwargs.lineno, call.kwargs.col_offset))
offsets.append(len(call_string))
return offsets
def argpos(call_string):
def _find_start(prev_end, offset):
s = call_string[prev_end:offset]
m = re.search('(\(|,)(\s*)(.*?)$', s)
return prev_end + m.regs[3][0]
def _find_end(start, next_offset):
s = call_string[start:next_offset]
m = re.search('(\s*)$', s[:max(s.rfind(','), s.rfind(')'))])
return start + m.start()
offsets = collect_offsets(call_string)
result = []
# previous end
end = 0
# given offsets = [9, 14, 21, ...],
# zip(offsets, offsets[1:]) returns [(9, 14), (14, 21), ...]
for offset, next_offset in zip(offsets, offsets[1:]):
#print 'I:', offset, next_offset
start = _find_start(end, offset)
end = _find_end(start, next_offset)
#print 'R:', start, end
result.append((start, end))
return result
if __name__ == '__main__':
try:
while True:
call_string = raw_input()
positions = argpos(call_string)
for p in positions:
print ' ' * p[0] + '^' + ((' ' * (p[1] - p[0] - 2) + '^') if p[1] - p[0] > 1 else '')
print positions
except EOFError, KeyboardInterrupt:
pass
输出:
whatever(foo, baz(), 'puppet', 24+2, meow=3, *meowargs, **meowargs)
^ ^
^ ^
^ ^
^ ^
^ ^
^ ^
^ ^
[(9, 12), (14, 19), (21, 29), (31, 35), (37, 43), (45, 54), (56, 66)]
f(1, len(document_text) - 1 - position)
^
^ ^
[(2, 3), (5, 38)]