有人理解为什么这不编译?

时间:2011-12-28 01:10:30

标签: python regex svg python-3.x

我正在尝试用这种模式解析svg路径W3C SVG Paths编辑:好的我已经改变了我的模式并且有一个样本一个新问题。看到我有一些新的模式可以解决的问题。我现在正在研究line_to正则表达式,并且svg规范要求值能够支持以下一点:L100,200到许多点,例如:L100,200 100,400 0,100我似乎无法让它工作。我正在解析inkscape_path2并重新输出这样的输出。

我们只关注输出的第一个元组:

这就是我得到的:

('L 6,82 ','L ','6','82')

这就是我想要的:

('L 6,82 6,14 6,12 ','L ','6','82','6','14','6','12')

实际代码:

from PyQt4.QtGui import QPainterPath
import string,re

inkscape_path1 = "M 12,6 C 8.676,6 6,8.676 6,12 l 0,2 0,68 0,2 c 0,0.334721 0.04135,0.6507 0.09375,0.96875 0.0487,0.295596 0.09704,0.596915 0.1875,0.875 0.00988,0.03038 0.020892,0.0636 0.03125,0.09375 0.098865,0.287771 0.2348802,0.547452 0.375,0.8125 0.1445918,0.273507 0.3156161,0.535615 0.5,0.78125 0.1843839,0.245635 0.3737765,0.473472 0.59375,0.6875 0.439947,0.428056 0.94291,0.814526 1.5,1.09375 0.278545,0.139612 0.5734731,0.246947 0.875,0.34375 -0.2562018,-0.100222 -0.4867109,-0.236272 -0.71875,-0.375 -0.00741,-0.0044 -0.023866,0.0045 -0.03125,0 -0.031933,-0.0193 -0.062293,-0.04251 -0.09375,-0.0625 -0.120395,-0.0767 -0.2310226,-0.163513 -0.34375,-0.25 -0.1061728,-0.0808 -0.2132809,-0.161112 -0.3125,-0.25 C 8.4783201,88.557317 8.3087904,88.373362 8.15625,88.1875 8.0486711,88.057245 7.9378561,87.922215 7.84375,87.78125 7.818661,87.74287 7.805304,87.69538 7.78125,87.65625 7.716487,87.553218 7.6510225,87.451733 7.59375,87.34375 7.4927417,87.149044 7.3880752,86.928049 7.3125,86.71875 7.30454,86.69694 7.288911,86.6782 7.28125,86.65625 7.2494249,86.5643 7.2454455,86.469419 7.21875,86.375 7.1884177,86.268382 7.1483606,86.171969 7.125,86.0625 7.0521214,85.720988 7,85.364295 7,85 L 7,83 7,15 7,13 C 7,10.218152 9.2181517,8 12,8 l 2,0 68,0 2,0 c 2.781848,0 5,2.218152 5,5 l 0,2 0,68 0,2 c 0,0.364295 -0.05212,0.720988 -0.125,1.0625 -0.04415,0.206893 -0.08838,0.397658 -0.15625,0.59375 -0.0077,0.02195 -0.0233,0.04069 -0.03125,0.0625 -0.06274,0.173739 -0.138383,0.367449 -0.21875,0.53125 -0.04158,0.0828 -0.07904,0.169954 -0.125,0.25 -0.0546,0.09721 -0.126774,0.18835 -0.1875,0.28125 -0.09411,0.140965 -0.204921,0.275995 -0.3125,0.40625 -0.143174,0.17445 -0.303141,0.346998 -0.46875,0.5 -0.01117,0.0102 -0.01998,0.02115 -0.03125,0.03125 -0.138386,0.125556 -0.285091,0.234436 -0.4375,0.34375 -0.102571,0.07315 -0.204318,0.153364 -0.3125,0.21875 -0.0074,0.0045 -0.02384,-0.0044 -0.03125,0 -0.232039,0.138728 -0.462548,0.274778 -0.71875,0.375 0.301527,-0.0968 0.596455,-0.204138 0.875,-0.34375 0.55709,-0.279224 1.060053,-0.665694 1.5,-1.09375 0.219973,-0.214028 0.409366,-0.441865 0.59375,-0.6875 0.184384,-0.245635 0.355408,-0.507743 0.5,-0.78125 0.14012,-0.265048 0.276135,-0.524729 0.375,-0.8125 0.01041,-0.03078 0.02133,-0.06274 0.03125,-0.09375 0.09046,-0.278085 0.1388,-0.579404 0.1875,-0.875 C 89.95865,84.6507 90,84.334721 90,84 l 0,-2 0,-68 0,-2 C 90,8.676 87.324,6 84,6 L 12,6 z"

inkscape_path2 = "M 12,90 C 8.676,90 6,87.324 6,84 L 6,82 6,14 6,12 c 0,-0.334721 0.04135,-0.6507 0.09375,-0.96875 0.0487,-0.295596 0.09704,-0.596915 0.1875,-0.875 C 6.29113,10.12587 6.302142,10.09265 6.3125,10.0625 6.411365,9.774729 6.5473802,9.515048 6.6875,9.25 6.8320918,8.976493 7.0031161,8.714385 7.1875,8.46875 7.3718839,8.223115 7.5612765,7.995278 7.78125,7.78125 8.221197,7.353194 8.72416,6.966724 9.28125,6.6875 9.559795,6.547888 9.8547231,6.440553 10.15625,6.34375 9.9000482,6.443972 9.6695391,6.580022 9.4375,6.71875 c -0.00741,0.0044 -0.023866,-0.0045 -0.03125,0 -0.031933,0.0193 -0.062293,0.04251 -0.09375,0.0625 -0.120395,0.0767 -0.2310226,0.163513 -0.34375,0.25 -0.1061728,0.0808 -0.2132809,0.161112 -0.3125,0.25 C 8.4783201,7.442683 8.3087904,7.626638 8.15625,7.8125 8.0486711,7.942755 7.9378561,8.077785 7.84375,8.21875 7.818661,8.25713 7.805304,8.30462 7.78125,8.34375 7.716487,8.446782 7.6510225,8.548267 7.59375,8.65625 7.4927417,8.850956 7.3880752,9.071951 7.3125,9.28125 7.30454,9.30306 7.288911,9.3218 7.28125,9.34375 7.2494249,9.4357 7.2454455,9.530581 7.21875,9.625 7.1884177,9.731618 7.1483606,9.828031 7.125,9.9375 7.0521214,10.279012 7,10.635705 7,11 l 0,2 0,68 0,2 c 0,2.781848 2.2181517,5 5,5 l 2,0 68,0 2,0 c 2.781848,0 5,-2.218152 5,-5 l 0,-2 0,-68 0,-2 C 89,10.635705 88.94788,10.279012 88.875,9.9375 88.83085,9.730607 88.78662,9.539842 88.71875,9.34375 88.71105,9.3218 88.69545,9.30306 88.6875,9.28125 88.62476,9.107511 88.549117,8.913801 88.46875,8.75 88.42717,8.6672 88.38971,8.580046 88.34375,8.5 88.28915,8.40279 88.216976,8.31165 88.15625,8.21875 88.06214,8.077785 87.951329,7.942755 87.84375,7.8125 87.700576,7.63805 87.540609,7.465502 87.375,7.3125 87.36383,7.3023 87.35502,7.29135 87.34375,7.28125 87.205364,7.155694 87.058659,7.046814 86.90625,6.9375 86.803679,6.86435 86.701932,6.784136 86.59375,6.71875 c -0.0074,-0.0045 -0.02384,0.0044 -0.03125,0 -0.232039,-0.138728 -0.462548,-0.274778 -0.71875,-0.375 0.301527,0.0968 0.596455,0.204138 0.875,0.34375 0.55709,0.279224 1.060053,0.665694 1.5,1.09375 0.219973,0.214028 0.409366,0.441865 0.59375,0.6875 0.184384,0.245635 0.355408,0.507743 0.5,0.78125 0.14012,0.265048 0.276135,0.524729 0.375,0.8125 0.01041,0.03078 0.02133,0.06274 0.03125,0.09375 0.09046,0.278085 0.1388,0.579404 0.1875,0.875 C 89.95865,11.3493 90,11.665279 90,12 l 0,2 0,68 0,2 c 0,3.324 -2.676,6 -6,6 l -72,0 z"
w3c_path1 = "M100,200 C100,100 250,100 250,200 S400,300 400,200"
w3c_path2 = '''
           M600,350 l 50,-25 \n
           a25,25 -30 0,1 50,-25 l 50,-25 \n
           a25,50 -30 0,1 50,-25 l 50,-25 \n
           a25,75 -30 0,1 50,-25 l 50,-25 \n
           a25,100 -30 0,1 50,-25 l 50,-25 \n
           '''

  if __name__ == '__main__':
    data = inkscape_path2
    assert re.match('M', data)
    integer = r'-\d+|\d+' # A negative or positive set of digits of unknown length
    float = r'-\d+\.\d+|\d+\.\d+' # The same as above but looks for a decimal
    number = r'({}|{})'.format(integer, float) 
    point = r'{},{}'.format(number, number)
    move_to = r'([Mm]\s*){}'.format(point)
    line_to = r'(([Ll]\s*){}+\s)'.format(point)
    curve_to = r'(([Cc]\s*){}\s{}\s{})'.format(point, point, point)
    t = re.findall(line_to, data)
    for token in t: # we're only testing line_to right now move_to some what works.
        print(token)
    print(data)
    print(line_to)

1 个答案:

答案 0 :(得分:3)

您尚未提供任何代码,实际错误消息,示例输入或其他任何内容。所以我只想猜测:

我不相信你可以在匹配组之外使用?P<label>语法。所以当你有这个:

?P<point>(\d[(,)|\s]\d)

你真的需要这些:

(?P<point>(\d[(,)|\s]\d))

注意括起整个表达式的额外括号。举个例子:

>>> re.compile('''?P<point>(\d[(,)|\s]\d)''')
Traceback (most recent call last):
  File "<stdin>", line 1, in <module>
  File "/usr/lib64/python2.7/re.py", line 190, in compile
    return _compile(pattern, flags)
  File "/usr/lib64/python2.7/re.py", line 244, in _compile
    raise error, v # invalid expression
sre_constants.error: nothing to repeat

Vs的:

>>> re.compile('''(?P<point>(\d[(,)|\s]\d))''')
<_sre.SRE_Pattern object at 0x7f8b14a3fa80>