Merge branch 'tokenize' of https://github.com/nbp/nix

3 files changed, 153 insertions, 0 deletions

diff --git a/doc/manual/expressions/builtins.xml b/doc/manual/expressions/builtins.xml
index 86c36da1b..615314880 100644
--- a/doc/manual/expressions/builtins.xml
+++ b/doc/manual/expressions/builtins.xml
@@ -873,6 +873,43 @@ builtins.sort builtins.lessThan [ 483 249 526 147 42 77 ]
   </varlistentry>
 
 
+  <varlistentry><term><function>builtins.split</function>
+  <replaceable>regex</replaceable> <replaceable>str</replaceable></term>
+
+  <listitem><para>Returns a list composed of non matched strings interleaved
+  with the lists of 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
+  of <replaceable>str</replaceable>. Each item in the lists of matched
+  sequences is a regex group.
+
+<programlisting>
+builtins.split "(a)b" "abc"
+</programlisting>
+
+Evaluates to <literal>[ "" [ "a" ] "c" ]</literal>.
+
+<programlisting>
+builtins.split "([ac])" "abc"
+</programlisting>
+
+Evaluates to <literal>[ "" [ "a" ] "b" [ "c" ] "" ]</literal>.
+
+<programlisting>
+builtins.split "(a)|(c)" "abc"
+</programlisting>
+
+Evaluates to <literal>[ "" [ "a" null ] "b" [ null "c" ] "" ]</literal>.
+
+<programlisting>
+builtins.split "([[:upper:]]+)" "  FOO   "
+</programlisting>
+
+Evaluates to <literal>[ "  " [ "FOO" ] "   " ]</literal>.
+
+  </para></listitem>
+  </varlistentry>
+
   <varlistentry><term><function>builtins.stringLength</function>
   <replaceable>e</replaceable></term>
 
diff --git a/src/libexpr/primops.cc b/src/libexpr/primops.cc
index 4e51e8ff2..fcd3f8efe 100644
--- a/src/libexpr/primops.cc
+++ b/src/libexpr/primops.cc
@@ -1745,6 +1745,73 @@ static void prim_match(EvalState & state, const Pos & pos, Value * * args, Value
 }
 
 
+/* Split a string with a regular expression, and return a list of the
+   non-matching parts interleaved by the lists of the matching groups. */
+static void prim_split(EvalState & state, const Pos & pos, Value * * args, Value & v)
+{
+    auto re = state.forceStringNoCtx(*args[0], pos);
+
+    try {
+
+        std::regex regex(re, std::regex::extended);
+
+        PathSet context;
+        const std::string str = state.forceString(*args[1], context, pos);
+
+        auto begin = std::sregex_iterator(str.begin(), str.end(), regex);
+        auto end = std::sregex_iterator();
+
+        // Any matches results are surrounded by non-matching results.
+        const size_t len = std::distance(begin, end);
+        state.mkList(v, 2 * len + 1);
+        size_t idx = 0;
+        Value * elem;
+
+        if (len == 0) {
+            v.listElems()[idx++] = args[1];
+            return;
+        }
+
+        for (std::sregex_iterator i = begin; i != end; ++i) {
+            assert(idx <= 2 * len + 1 - 3);
+            std::smatch match = *i;
+
+            // Add a string for non-matched characters.
+            elem = v.listElems()[idx++] = state.allocValue();
+            mkString(*elem, match.prefix().str().c_str());
+
+            // Add a list for matched substrings.
+            const size_t slen = match.size() - 1;
+            elem = v.listElems()[idx++] = state.allocValue();
+
+            // Start at 1, beacause the first match is the whole string.
+            state.mkList(*elem, slen);
+            for (size_t si = 0; si < slen; ++si) {
+                if (!match[si + 1].matched)
+                    mkNull(*(elem->listElems()[si] = state.allocValue()));
+                else
+                    mkString(*(elem->listElems()[si] = state.allocValue()), match[si + 1].str().c_str());
+            }
+
+            // Add a string for non-matched suffix characters.
+            if (idx == 2 * len) {
+                elem = v.listElems()[idx++] = state.allocValue();
+                mkString(*elem, match.suffix().str().c_str());
+            }
+        }
+        assert(idx == 2 * len + 1);
+
+    } catch (std::regex_error &e) {
+        if (e.code() == std::regex_constants::error_space) {
+          // limit is _GLIBCXX_REGEX_STATE_LIMIT for libstdc++
+          throw EvalError("memory limit exceeded by regular expression '%s', at %s", re, pos);
+        } else {
+          throw EvalError("invalid regular expression '%s', at %s", re, pos);
+        }
+    }
+}
+
+
 static void prim_concatStringSep(EvalState & state, const Pos & pos, Value * * args, Value & v)
 {
     PathSet context;
@@ -2039,6 +2106,7 @@ void EvalState::createBaseEnv()
     addPrimOp("__unsafeDiscardOutputDependency", 1, prim_unsafeDiscardOutputDependency);
     addPrimOp("__hashString", 2, prim_hashString);
     addPrimOp("__match", 2, prim_match);
+    addPrimOp("__split", 2, prim_split);
     addPrimOp("__concatStringsSep", 2, prim_concatStringSep);
     addPrimOp("__replaceStrings", 3, prim_replaceStrings);
 
diff --git a/tests/lang/eval-okay-regex-split.nix b/tests/lang/eval-okay-regex-split.nix
new file mode 100644
index 000000000..0073e0577
--- /dev/null
+++ b/tests/lang/eval-okay-regex-split.nix
@@ -0,0 +1,48 @@
+with builtins;
+
+# Non capturing regex returns empty lists
+assert  split "foobar" "foobar"  == ["" [] ""];
+assert  split "fo*" "f"          == ["" [] ""];
+assert  split "fo+" "f"          == ["f"];
+assert  split "fo*" "fo"         == ["" [] ""];
+assert  split "fo*" "foo"        == ["" [] ""];
+assert  split "fo+" "foo"        == ["" [] ""];
+assert  split "fo{1,2}" "foo"    == ["" [] ""];
+assert  split "fo{1,2}" "fooo"   == ["" [] "o"];
+assert  split "fo*" "foobar"     == ["" [] "bar"];
+
+# Capturing regex returns a list of sub-matches
+assert  split "(fo*)" "f"        == ["" ["f"] ""];
+assert  split "(fo+)" "f"        == ["f"];
+assert  split "(fo*)" "fo"       == ["" ["fo"] ""];
+assert  split "(f)(o*)" "f"      == ["" ["f" ""] ""];
+assert  split "(f)(o*)" "foo"    == ["" ["f" "oo"] ""];
+assert  split "(fo+)" "foo"      == ["" ["foo"] ""];
+assert  split "(fo{1,2})" "foo"  == ["" ["foo"] ""];
+assert  split "(fo{1,2})" "fooo" == ["" ["foo"] "o"];
+assert  split "(fo*)" "foobar"   == ["" ["foo"] "bar"];
+
+# Matches are greedy.
+assert  split "(o+)" "oooofoooo" == ["" ["oooo"] "f" ["oooo"] ""];
+
+# Matches multiple times.
+assert  split "(b)" "foobarbaz"  == ["foo" ["b"] "ar" ["b"] "az"];
+
+# Split large strings containing newlines. null are inserted when a
+# pattern within the current did not match anything.
+assert  split "[[:space:]]+|([',.!?])" ''
+  Nix Rocks!
+  That's why I use it.
+''  == [
+  "Nix" [ null ] "Rocks" ["!"] "" [ null ]
+  "That" ["'"] "s" [ null ] "why" [ null ] "I" [ null ] "use" [ null ] "it" ["."] "" [ null ]
+  ""
+];
+
+# Documentation examples
+assert  split  "(a)b" "abc"      == [ "" [ "a" ] "c" ];
+assert  split  "([ac])" "abc"    == [ "" [ "a" ] "b" [ "c" ] "" ];
+assert  split  "(a)|(c)" "abc"   == [ "" [ "a" null ] "b" [ null "c" ] "" ];
+assert  split  "([[:upper:]]+)" "  FOO   " == [ "  " [ "FOO" ] "   " ];
+
+true