Add a primop for regular expression pattern matching

The function ‘builtins.match’ takes a POSIX extended regular
expression and an arbitrary string. It returns ‘null’ if the string
does not match the regular expression. Otherwise, it returns a list
containing substring matches corresponding to parenthesis groups in
the regex. The regex must match the entire string (i.e. there is an
implied "^<pat>$" around the regex).  For example:

  match "foo" "foobar" => null
  match "foo" "foo" => []
  match "f(o+)(.*)" "foooobar" => ["oooo" "bar"]
  match "(.*/)?([^/]*)" "/dir/file.nix" => ["/dir/" "file.nix"]
  match "(.*/)?([^/]*)" "file.nix" => [null "file.nix"]

The following example finds all regular files with extension .nix or
.patch underneath the current directory:

  let

    findFiles = pat: dir: concatLists (mapAttrsToList (name: type:
      if type == "directory" then
        findFiles pat (dir + "/" + name)
      else if type == "regular" && match pat name != null then
        [(dir + "/" + name)]
      else []) (readDir dir));

  in findFiles ".*\\.(nix|patch)" (toString ./.)

1 files changed, 8 insertions, 1 deletions

diff --git a/src/libutil/regex.hh b/src/libutil/regex.hh
index aa012b721cb7..53e31f4edc4a 100644
--- a/src/libutil/regex.hh
+++ b/src/libutil/regex.hh
@@ -5,16 +5,23 @@
 #include <sys/types.h>
 #include <regex.h>
 
+#include <map>
+
 namespace nix {
 
+MakeError(RegexError, Error)
+
 class Regex
 {
 public:
-    Regex(const string & pattern);
+    Regex(const string & pattern, bool subs = false);
     ~Regex();
     bool matches(const string & s);
+    typedef std::map<unsigned int, string> Subs;
+    bool matches(const string & s, Subs & subs);
 
 private:
+    unsigned nrParens;
     regex_t preg;
     string showError(int err);
 };