Add a fromTOML primop

This is primarily useful for processing Cargo.lock files.

release-common.nix

@@ -2,6 +2,23 @@
 
 with pkgs;
 
+let
+
+  cpptoml = runCommand "cpptoml"
+    { src = fetchFromGitHub {
+        owner = "skystrife";
+        repo = "cpptoml";
+        rev = "43d7d8e52de149fd84aedf7eb71814ff9e6b2f7e";
+        sha256 = "0gdxk1mj5hpj93df1kwfl903w06nihbb1ayr3x336775jm2d2cw6";
+      };
+    }
+    ''
+      mkdir -p $out/include
+      cp $src/include/cpptoml.h $out/include/
+    '';
+
+in
+
 rec {
   # Use "busybox-sandbox-shell" if present,
   # if not (legacy) fallback and hope it's sufficient.
@@ -52,6 +69,7 @@ rec {
       bzip2 xz brotli
       openssl pkgconfig sqlite boehmgc
       boost
+      cpptoml
 
       # Tests
       git

src/libexpr/primops/fromTOML.cc

@@ -0,0 +1,77 @@
+#include "primops.hh"
+#include "eval-inline.hh"
+
+#include <cpptoml.h>
+
+namespace nix {
+
+static void prim_fromTOML(EvalState & state, const Pos & pos, Value * * args, Value & v)
+{
+    using namespace cpptoml;
+
+    auto toml = state.forceStringNoCtx(*args[0], pos);
+
+    std::istringstream tomlStream(toml);
+
+    std::function<void(Value &, std::shared_ptr<base>)> visit;
+
+    visit = [&](Value & v, std::shared_ptr<base> t) {
+
+        if (auto t2 = t->as_table()) {
+
+            size_t size = 0;
+            for (auto & i : *t2) size++;
+
+            state.mkAttrs(v, size);
+
+            for (auto & i : *t2) {
+                auto & v2 = *state.allocAttr(v, state.symbols.create(i.first));
+
+                if (auto i2 = i.second->as_table_array()) {
+                    size_t size2 = i2->get().size();
+                    state.mkList(v2, size2);
+                    for (size_t j = 0; j < size2; ++j)
+                        visit(*(v2.listElems()[j] = state.allocValue()), i2->get()[j]);
+                }
+                else
+                    visit(v2, i.second);
+            }
+
+            v.attrs->sort();
+        }
+
+        else if (auto t2 = t->as_array()) {
+            size_t size = t2->get().size();
+
+            state.mkList(v, size);
+
+            for (size_t i = 0; i < size; ++i)
+                visit(*(v.listElems()[i] = state.allocValue()), t2->get()[i]);
+        }
+
+        else if (t->is_value()) {
+            if (auto val = t->as<NixInt>())
+                mkInt(v, val->get());
+            else if (auto val = t->as<NixFloat>())
+                mkFloat(v, val->get());
+            else if (auto val = t->as<bool>())
+                mkBool(v, val->get());
+            else if (auto val = t->as<std::string>())
+                mkString(v, val->get());
+            else
+                throw EvalError("unsupported value type in TOML");
+        }
+
+        else abort();
+    };
+
+    try {
+        visit(v, parser(tomlStream).parse());
+    } catch (std::runtime_error & e) {
+        throw EvalError("while parsing a TOML string at %s: %s", pos, e.what());
+    }
+}
+
+static RegisterPrimOp r("fromTOML", 1, prim_fromTOML);
+
+}

tests/lang/eval-okay-fromTOML.exp

@@ -0,0 +1 @@
+[ { clients = { data = [ [ "gamma" "delta" ] [ 1 2 ] ]; hosts = [ "alpha" "omega" ]; }; database = { connection_max = 5000; enabled = true; ports = [ 8001 8001 8002 ]; server = "192.168.1.1"; }; owner = { name = "Tom Preston-Werner"; }; servers = { alpha = { dc = "eqdc10"; ip = "10.0.0.1"; }; beta = { dc = "eqdc10"; ip = "10.0.0.2"; }; }; title = "TOML Example"; } { "'key2'" = "value"; "1234" = "value"; "127.0.0.1" = "value"; a = { b = { c = { }; }; }; arr1 = [ 1 2 3 ]; arr2 = [ "red" "yellow" "green" ]; arr3 = [ [ 1 2 ] [ 3 4 5 ] ]; arr4 = [ "all" "strings" "are the same" "type" ]; arr5 = [ [ 1 2 ] [ "a" "b" "c" ] ]; arr7 = [ 1 2 3 ]; arr8 = [ 1 2 ]; bare-key = "value"; bare_key = "value"; bool1 = true; bool2 = false; "character encoding" = "value"; d = { e = { f = { }; }; }; flt1 = 1; flt2 = 3.1415; flt3 = -0.01; flt4 = 5e+22; flt5 = 1e+06; flt6 = -0.02; flt7 = 6.626e-34; flt8 = 9.22462e+06; g = { h = { i = { }; }; }; int1 = 99; int2 = 42; int3 = 0; int4 = -17; int5 = 1000; int6 = 5349221; int7 = 12345; j = { "ʞ" = { "'l'" = { }; }; }; key = "value"; name = "Orange"; products = [ { name = "Hammer"; sku = 738594937; } { } { color = "gray"; name = "Nail"; sku = 284758393; } ]; str = "I'm a string. \"You can quote me\". Name\tJosé\nLocation\tSF."; table-1 = { key1 = "some string"; key2 = 123; }; table-2 = { key1 = "another string"; key2 = 456; }; x = { y = { z = { w = { name = { first = "Tom"; last = "Preston-Werner"; }; point = { x = 1; y = 2; }; }; }; }; }; "ʎǝʞ" = "value"; } { metadata = { "checksum aho-corasick 0.6.4 (registry+https://github.com/rust-lang/crates.io-index)" = "d6531d44de723825aa81398a6415283229725a00fa30713812ab9323faa82fc4"; "checksum ansi_term 0.11.0 (registry+https://github.com/rust-lang/crates.io-index)" = "ee49baf6cb617b853aa8d93bf420db2383fab46d314482ca2803b40d5fde979b"; "checksum ansi_term 0.9.0 (registry+https://github.com/rust-lang/crates.io-index)" = "23ac7c30002a5accbf7e8987d0632fa6de155b7c3d39d0067317a391e00a2ef6"; "checksum arrayvec 0.4.7 (registry+https://github.com/rust-lang/crates.io-index)" = "a1e964f9e24d588183fcb43503abda40d288c8657dfc27311516ce2f05675aef"; }; package = [ { dependencies = [ "memchr 2.0.1 (registry+https://github.com/rust-lang/crates.io-index)" ]; name = "aho-corasick"; source = "registry+https://github.com/rust-lang/crates.io-index"; version = "0.6.4"; } { name = "ansi_term"; source = "registry+https://github.com/rust-lang/crates.io-index"; version = "0.9.0"; } { dependencies = [ "libc 0.2.42 (registry+https://github.com/rust-lang/crates.io-index)" "termion 1.5.1 (registry+https://github.com/rust-lang/crates.io-index)" "winapi 0.3.5 (registry+https://github.com/rust-lang/crates.io-index)" ]; name = "atty"; source = "registry+https://github.com/rust-lang/crates.io-index"; version = "0.2.10"; } ]; } ]

tests/lang/eval-okay-fromTOML.nix

@@ -0,0 +1,184 @@
+[
+
+  (builtins.fromTOML ''
+    # This is a TOML document.
+
+    title = "TOML Example"
+
+    [owner]
+    name = "Tom Preston-Werner"
+    #dob = 1979-05-27T07:32:00-08:00 # First class dates
+
+    [database]
+    server = "192.168.1.1"
+    ports = [ 8001, 8001, 8002 ]
+    connection_max = 5000
+    enabled = true
+
+    [servers]
+
+      # Indentation (tabs and/or spaces) is allowed but not required
+      [servers.alpha]
+      ip = "10.0.0.1"
+      dc = "eqdc10"
+
+      [servers.beta]
+      ip = "10.0.0.2"
+      dc = "eqdc10"
+
+    [clients]
+    data = [ ["gamma", "delta"], [1, 2] ]
+
+    # Line breaks are OK when inside arrays
+    hosts = [
+      "alpha",
+      "omega"
+    ]
+  '')
+
+  (builtins.fromTOML ''
+    key = "value"
+    bare_key = "value"
+    bare-key = "value"
+    1234 = "value"
+
+    "127.0.0.1" = "value"
+    "character encoding" = "value"
+    "ʎǝʞ" = "value"
+    'key2' = "value"
+    #'quoted "value"' = "value"
+
+    name = "Orange"
+
+    # FIXME: cpptoml doesn't handle dotted keys properly yet.
+    #physical.color = "orange"
+    #physical.shape = "round"
+    #site."google.com" = true
+
+    #a.b.c = 1
+    #a.d = 2
+
+    str = "I'm a string. \"You can quote me\". Name\tJos\u00E9\nLocation\tSF."
+
+    int1 = +99
+    int2 = 42
+    int3 = 0
+    int4 = -17
+    int5 = 1_000
+    int6 = 5_349_221
+    int7 = 1_2_3_4_5
+
+    # FIXME: cpptoml doesn't support these yet:
+
+    #hex1 = 0xDEADBEEF
+    #hex2 = 0xdeadbeef
+    #hex3 = 0xdead_beef
+
+    #oct1 = 0o01234567
+    #oct2 = 0o755
+
+    #bin1 = 0b11010110
+
+    flt1 = +1.0
+    flt2 = 3.1415
+    flt3 = -0.01
+    flt4 = 5e+22
+    flt5 = 1e6
+    flt6 = -2E-2
+    flt7 = 6.626e-34
+    flt8 = 9_224_617.445_991_228_313
+
+    bool1 = true
+    bool2 = false
+
+    # FIXME: not supported because Nix doesn't have a date/time type.
+    #odt1 = 1979-05-27T07:32:00Z
+    #odt2 = 1979-05-27T00:32:00-07:00
+    #odt3 = 1979-05-27T00:32:00.999999-07:00
+    #odt4 = 1979-05-27 07:32:00Z
+    #ldt1 = 1979-05-27T07:32:00
+    #ldt2 = 1979-05-27T00:32:00.999999
+    #ld1 = 1979-05-27
+    #lt1 = 07:32:00
+    #lt2 = 00:32:00.999999
+
+    arr1 = [ 1, 2, 3 ]
+    arr2 = [ "red", "yellow", "green" ]
+    arr3 = [ [ 1, 2 ], [3, 4, 5] ]
+    arr4 = [ "all", 'strings', """are the same""", ''''type'''']
+    arr5 = [ [ 1, 2 ], ["a", "b", "c"] ]
+
+    arr7 = [
+      1, 2, 3
+    ]
+
+    arr8 = [
+      1,
+      2, # this is ok
+    ]
+
+    [table-1]
+    key1 = "some string"
+    key2 = 123
+
+
+    [table-2]
+    key1 = "another string"
+    key2 = 456
+
+    #[dog."tater.man"]
+    #type.name = "pug"
+
+    [a.b.c]
+    [ d.e.f ]
+    [ g .  h  . i ]
+    [ j . "ʞ" . 'l' ]
+    [x.y.z.w]
+
+    name = { first = "Tom", last = "Preston-Werner" }
+    point = { x = 1, y = 2 }
+    #animal = { type.name = "pug" }
+
+    [[products]]
+    name = "Hammer"
+    sku = 738594937
+
+    [[products]]
+
+    [[products]]
+    name = "Nail"
+    sku = 284758393
+    color = "gray"
+  '')
+
+  (builtins.fromTOML ''
+    [[package]]
+    name = "aho-corasick"
+    version = "0.6.4"
+    source = "registry+https://github.com/rust-lang/crates.io-index"
+    dependencies = [
+     "memchr 2.0.1 (registry+https://github.com/rust-lang/crates.io-index)",
+    ]
+
+    [[package]]
+    name = "ansi_term"
+    version = "0.9.0"
+    source = "registry+https://github.com/rust-lang/crates.io-index"
+
+    [[package]]
+    name = "atty"
+    version = "0.2.10"
+    source = "registry+https://github.com/rust-lang/crates.io-index"
+    dependencies = [
+     "libc 0.2.42 (registry+https://github.com/rust-lang/crates.io-index)",
+     "termion 1.5.1 (registry+https://github.com/rust-lang/crates.io-index)",
+     "winapi 0.3.5 (registry+https://github.com/rust-lang/crates.io-index)",
+    ]
+
+    [metadata]
+    "checksum aho-corasick 0.6.4 (registry+https://github.com/rust-lang/crates.io-index)" = "d6531d44de723825aa81398a6415283229725a00fa30713812ab9323faa82fc4"
+    "checksum ansi_term 0.11.0 (registry+https://github.com/rust-lang/crates.io-index)" = "ee49baf6cb617b853aa8d93bf420db2383fab46d314482ca2803b40d5fde979b"
+    "checksum ansi_term 0.9.0 (registry+https://github.com/rust-lang/crates.io-index)" = "23ac7c30002a5accbf7e8987d0632fa6de155b7c3d39d0067317a391e00a2ef6"
+    "checksum arrayvec 0.4.7 (registry+https://github.com/rust-lang/crates.io-index)" = "a1e964f9e24d588183fcb43503abda40d288c8657dfc27311516ce2f05675aef"
+  '')
+]