NixOS · May 17, 2017 · May 17, 2017
Showing with 36 additions and 20 deletions.

+10 −4 doc/manual/expressions/builtins.xml

+23 −16 src/libexpr/primops.cc

+3 −0 tests/lang/eval-okay-regex-match.nix
diff --git a/doc/manual/expressions/builtins.xml b/doc/manual/expressions/builtins.xml
@@ -213,10 +213,11 @@ if builtins ? getEnv then builtins.getEnv "PATH" else ""</programlisting>
   <varlistentry><term><function>builtins.match</function>
   <replaceable>regex</replaceable> <replaceable>str</replaceable></term>
 
-  <listitem><para>Returns a list if
-    <replaceable>regex</replaceable> matches
-    <replaceable>str</replaceable> precisely, otherwise returns <literal>null</literal>.
-    Each item in the list is a regex group.
+  <listitem><para>Returns a list if the <link
+  xlink:href="http://pubs.opengroup.org/onlinepubs/9699919799/basedefs/V1_chap09.html#tag_09_04">extended
+  POSIX regular expression</link> <replaceable>regex</replaceable>
+  matches <replaceable>str</replaceable> precisely, otherwise returns
+  <literal>null</literal>.  Each item in the list is a regex group.
 
 <programlisting>
 builtins.match "ab" "abc"
@@ -236,6 +237,11 @@ builtins.match "a(b)(c)" "abc"
 
 Evaluates to <literal>[ "b" "c" ]</literal>.
 
+<programlisting>
+builtins.match "[[:space:]]+([[:upper:]]+)[[:space:]]+" "  FOO   "
+</programlisting>
+
+Evaluates to <literal>[ "foo" ]</literal>.
 
   </para></listitem>
   </varlistentry>

diff --git a/src/libexpr/primops.cc b/src/libexpr/primops.cc
@@ -1709,26 +1709,33 @@ static void prim_hashString(EvalState & state, const Pos & pos, Value * * args,
    ‘null’ or a list containing substring matches. */
 static void prim_match(EvalState & state, const Pos & pos, Value * * args, Value & v)
 {
-    std::regex regex(state.forceStringNoCtx(*args[0], pos), std::regex::extended);
+    auto re = state.forceStringNoCtx(*args[0], pos);
 
-    PathSet context;
-    const std::string str = state.forceString(*args[1], context, pos);
+    try {
 
+        std::regex regex(re, std::regex::extended);
 
-    std::smatch match;
-    if (!std::regex_match(str, match, regex)) {
-        mkNull(v);
-        return;
-    }
+        PathSet context;
+        const std::string str = state.forceString(*args[1], context, pos);
 
-    // the first match is the whole string
-    const size_t len = match.size() - 1;
-    state.mkList(v, len);
-    for (size_t i = 0; i < len; ++i) {
-        if (!match[i+1].matched)
-            mkNull(*(v.listElems()[i] = state.allocValue()));
-        else
-            mkString(*(v.listElems()[i] = state.allocValue()), match[i + 1].str().c_str());
+        std::smatch match;
+        if (!std::regex_match(str, match, regex)) {
+            mkNull(v);
+            return;
+        }
+
+        // the first match is the whole string
+        const size_t len = match.size() - 1;
+        state.mkList(v, len);
+        for (size_t i = 0; i < len; ++i) {
+            if (!match[i+1].matched)
+                mkNull(*(v.listElems()[i] = state.allocValue()));
+            else
+                mkString(*(v.listElems()[i] = state.allocValue()), match[i + 1].str().c_str());
+        }
+
+    } catch (std::regex_error &) {
+        throw EvalError("invalid regular expression ‘%s’, at %s", re, pos);
     }
 }
 

diff --git a/tests/lang/eval-okay-regex-match.nix b/tests/lang/eval-okay-regex-match.nix
@@ -17,8 +17,11 @@ assert  matches "fo+" "foo";
 assert  matches "fo{1,2}" "foo";
 assert !matches "fo{1,2}" "fooo";
 assert !matches "fo*" "foobar";
+assert  matches "[[:space:]]+([^[:space:]]+)[[:space:]]+" "  foo   ";
+assert !matches "[[:space:]]+([[:upper:]]+)[[:space:]]+" "  foo   ";
 
 assert match "(.*)\\.nix" "foobar.nix" == [ "foobar" ];
+assert match "[[:space:]]+([[:upper:]]+)[[:space:]]+" "  FOO   " == [ "FOO" ];
 
 assert splitFN "/path/to/foobar.nix" == [ "/path/to/" "/path/to" "foobar" "nix" ];
 assert splitFN "foobar.cc" == [ null null "foobar" "cc" ];