From 0e0d182c6719b402bc910b4b75bc1558c27be8ef Mon Sep 17 00:00:00 2001 From: WGH Date: Thu, 24 Jan 2019 03:33:18 +0300 Subject: [PATCH] Fix Pcre::searchAll behaviour wrt empty capturing groups Previously, searchAll would stop search when it encountered an empty matching group in any position. This means that, for example, regular expression "(a)(b?)(c)" would match string "ac", but the resulting group list would be ["ac", "a"]. After this change, the resulting list for the aforementioned regular expression becomes ["ac", "a", "", "c"] like it should've been. Additionally, this also changes behaviour for multiple matches. For example, when "aaa00bbb" is matched by "[a-z]*", previously only "aaa" would be returned. Now the matching list is ["aaa", "", "", "bbb", ""]. The old behaviour was confusing and almost certainly a bug. The new behaviour is the same as in Python's re.findall. For reference, though, Go does it somewhat differently: empty matches at the end of non-empty matches are ignored, so in Go above example is ["aaa", "", "bbb"] instead. --- src/regex/backend/pcre.cc | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/src/regex/backend/pcre.cc b/src/regex/backend/pcre.cc index e9cdd549..4f1d08e2 100644 --- a/src/regex/backend/pcre.cc +++ b/src/regex/backend/pcre.cc @@ -87,11 +87,11 @@ std::list Pcre::searchAll(const std::string& s) const { std::string match = std::string(tmpString, start, len); offset = start + len; retList.push_front(RegexMatch(match, start)); + } - if (len == 0) { - rc = 0; - break; - } + offset = ovector[1]; // end + if (offset == ovector[0]) { // start == end (size == 0) + offset++; } } while (rc > 0);