about summary refs log tree commit diff
path: root/src/libexpr
diff options
context:
space:
mode:
authorNicolas B. Pierron <nicolas.b.pierron@gmail.com>2017-08-15T18·08+0000
committerNicolas B. Pierron <nicolas.b.pierron@gmail.com>2017-08-15T20·04+0000
commitb8867a0239b1930a16f9ef3f7f3e864b01416dff (patch)
treece0154e733d0dd1a58d7472283a2bd64aed11659 /src/libexpr
parentf76e85d8f581cc8f71b66386e86ed93c2c3d6992 (diff)
Add builtins.string function.
The function 'builtins.split' takes a POSIX extended regular expression
and an arbitrary string. It returns a list of non-matching substring
interleaved by lists of matched groups of the regular expression.

```nix
with builtins;
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" ] "   " ];
```
Diffstat (limited to 'src/libexpr')
-rw-r--r--src/libexpr/primops.cc68
1 files changed, 68 insertions, 0 deletions
diff --git a/src/libexpr/primops.cc b/src/libexpr/primops.cc
index 4e51e8ff2562..fcd3f8efee3f 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);