diff options
| -rw-r--r-- | lib/impure/re.nim | 20 | ||||
| -rw-r--r-- | web/news.txt | 6 |
2 files changed, 19 insertions, 7 deletions
diff --git a/lib/impure/re.nim b/lib/impure/re.nim index c24734f89..ff2b70d2d 100644 --- a/lib/impure/re.nim +++ b/lib/impure/re.nim @@ -373,23 +373,26 @@ iterator split*(s: string, sep: Regex): string = ## Results in: ## ## .. code-block:: nim + ## "" ## "this" ## "is" ## "an" ## "example" + ## "" ## var - first = 0 - last = 0 + first = -1 + last = -1 while last < len(s): var x = matchLen(s, sep, last) if x > 0: inc(last, x) first = last + if x == 0: inc(last) while last < len(s): - inc(last) x = matchLen(s, sep, last) - if x > 0: break - if first < last: + if x >= 0: break + inc(last) + if first <= last: yield substr(s, first, last-1) proc split*(s: string, sep: Regex): seq[string] = @@ -471,7 +474,12 @@ when isMainModule: var accum: seq[string] = @[] for word in split("00232this02939is39an22example111", re"\d+"): accum.add(word) - assert(accum == @["this", "is", "an", "example"]) + assert(accum == @["", "this", "is", "an", "example", ""]) + + accum = @[] + for word in split("AAA : : BBB", re"\s*:\s*"): + accum.add(word) + assert(accum == @["AAA", "", "BBB"]) for x in findAll("abcdef", re"^{.}", 3): assert x == "d" diff --git a/web/news.txt b/web/news.txt index 9fd7c31b3..af44f91a1 100644 --- a/web/news.txt +++ b/web/news.txt @@ -73,7 +73,11 @@ News for ``expr`` and ``stmt``. The new names capture the semantics much better and most likely ``expr`` and ``stmt`` will be deprecated in favor of the new names. - + - The ``split`` method in module ``re`` has changed. It now handles the case + of matches having a length of 0, and empty strings being yielded from the + iterator. A notable change might be that a pattern being matched at the + beginning and end of a string, will result in an empty string being produced + at the start and the end of the iterator. Language Additions ------------------ |