Extracting parts of string between anchor points

[Tim Chase]

On 2014-02-27 15:45, Tim Chase wrote:
> >>> r = re.compile(r"^([^:]*)(?::((?:(?!-:-).)*)(?:-:-(.*))?)?")

If you want to compare both the re method and the string method,
here's a test-harness to play with:

  import re
  examples = [
    ("", (None, None, None)),
    ("Test1A", ("Test1A", None, None)),
    ("Test2A: Test2B", ("Test2A", "Test2B", None)),
    ("Test3A: Test3B -:- Test3C", ("Test3A", "Test3B", "Test3C")),
    ("Test4A -:- Test4B", None),
    ("Test5A : Test5B : Test5C -:- Test5D", None),
    ("Test6A : Test6B -:- Test6C -:- Test6D", None),
    ]

  splitter_re = re.compile(r"^([^:]*)(?::((?:(?!-:-).)*)(?:-:-(.*))?)?")

  def clean(t):
    return [
      s.strip() if s else None
      for s in t
      ]

  def splitter1(s):
    "using regexp"
    m = splitter_re.match(s)
    if m:
      return tuple(clean(m.groups()))
    else:
      return (None, None, None)

  def splitter2(s):
    "using string methods"
    out1 = out2 = out3 = None
    if ":" in s:
      if "-:-" in s:
        left, _, out3 = clean(s.partition("-:-"))
        if ":" in left:
          out1, _, out2 = clean(left.partition(":"))
        else:
          out1 = left
      else:
        out1, _, out2 = clean(s.partition(":"))
    else:
      if s:
        out1 = s
    return (out1, out2, out3)

  for method in (splitter1, splitter2):
    print("")
    print(method.__doc__)
    print("=" * len(method.__doc__))
    for s, expected in examples:
      result = method(s)
      if expected is not None:
        if result != expected:
          print("FAIL: %r got %r, not %r" % (s, result, expected))
        else:
          print("PASS: %r got %r" % (s, result))
      else:
        print("UNKN: %r got %r" % (s, result))

Note the differences in Test4.

-tkc