mirror of
https://github.com/NixOS/nix.git
synced 2025-11-08 19:46:02 +01:00
Merge pull request #13745 from NixOS/mergify/bp/2.28-maintenance/pr-13741
libexpr: Canonicalize TOML timestamps for toml11 > 4.0 (backport #13741)
This commit is contained in:
Jörg Thalheim
GitHub
commit
75e6c8dc90
4 changed files with 148 additions and 25 deletions
|
|
@ -72,6 +72,12 @@ toml11 = dependency(
|
|||
method : 'cmake',
|
||||
include_type: 'system',
|
||||
)
|
||||
|
||||
configdata_priv.set(
|
||||
'HAVE_TOML11_4',
|
||||
toml11.version().version_compare('>= 4.0.0').to_int(),
|
||||
)
|
||||
|
||||
deps_other += toml11
|
||||
|
||||
config_priv_h = configure_file(
|
||||
|
|
|
|||
|
|
@ -1,73 +1,140 @@
|
|||
#include "nix/expr/primops.hh"
|
||||
#include "nix/expr/eval-inline.hh"
|
||||
|
||||
#include "expr-config-private.hh"
|
||||
|
||||
#include <sstream>
|
||||
|
||||
#include <toml.hpp>
|
||||
|
||||
namespace nix {
|
||||
|
||||
#if HAVE_TOML11_4
|
||||
|
||||
/**
|
||||
* This is what toml11 < 4.0 did when choosing the subsecond precision.
|
||||
* TOML 1.0.0 spec doesn't define how sub-millisecond ranges should be handled and calls it
|
||||
* implementation defined behavior. For a lack of a better choice we stick with what older versions
|
||||
* of toml11 did [1].
|
||||
*
|
||||
* [1]: https://github.com/ToruNiina/toml11/blob/dcfe39a783a94e8d52c885e5883a6fbb21529019/toml/datetime.hpp#L282
|
||||
*/
|
||||
static size_t normalizeSubsecondPrecision(toml::local_time lt)
|
||||
{
|
||||
auto millis = lt.millisecond;
|
||||
auto micros = lt.microsecond;
|
||||
auto nanos = lt.nanosecond;
|
||||
if (millis != 0 || micros != 0 || nanos != 0) {
|
||||
if (micros != 0 || nanos != 0) {
|
||||
if (nanos != 0)
|
||||
return 9;
|
||||
return 6;
|
||||
}
|
||||
return 3;
|
||||
}
|
||||
return 0;
|
||||
}
|
||||
|
||||
/**
|
||||
* Normalize date/time formats to serialize to the same strings as versions prior to toml11 4.0.
|
||||
*
|
||||
* Several things to consider:
|
||||
*
|
||||
* 1. Sub-millisecond range is represented the same way as in toml11 versions prior to 4.0. Precisioun is rounded
|
||||
* towards the next multiple of 3 or capped at 9 digits.
|
||||
* 2. Seconds must be specified. This may become optional in (yet unreleased) TOML 1.1.0, but 1.0.0 defined local time
|
||||
* in terms of RFC3339 [1].
|
||||
* 3. date-time separator (`t`, `T` or space ` `) is canonicalized to an upper T. This is compliant with RFC3339
|
||||
* [1] 5.6:
|
||||
* > Applications that generate this format SHOULD use upper case letters.
|
||||
*
|
||||
* [1]: https://datatracker.ietf.org/doc/html/rfc3339#section-5.6
|
||||
*/
|
||||
static void normalizeDatetimeFormat(toml::value & t)
|
||||
{
|
||||
if (t.is_local_datetime()) {
|
||||
auto & ldt = t.as_local_datetime();
|
||||
t.as_local_datetime_fmt() = {
|
||||
.delimiter = toml::datetime_delimiter_kind::upper_T,
|
||||
// https://datatracker.ietf.org/doc/html/rfc3339#section-5.6
|
||||
.has_seconds = true, // Mandated by TOML 1.0.0
|
||||
.subsecond_precision = normalizeSubsecondPrecision(ldt.time),
|
||||
};
|
||||
return;
|
||||
}
|
||||
|
||||
if (t.is_offset_datetime()) {
|
||||
auto & odt = t.as_offset_datetime();
|
||||
t.as_offset_datetime_fmt() = {
|
||||
.delimiter = toml::datetime_delimiter_kind::upper_T,
|
||||
// https://datatracker.ietf.org/doc/html/rfc3339#section-5.6
|
||||
.has_seconds = true, // Mandated by TOML 1.0.0
|
||||
.subsecond_precision = normalizeSubsecondPrecision(odt.time),
|
||||
};
|
||||
return;
|
||||
}
|
||||
|
||||
if (t.is_local_time()) {
|
||||
auto & lt = t.as_local_time();
|
||||
t.as_local_time_fmt() = {
|
||||
.has_seconds = true, // Mandated by TOML 1.0.0
|
||||
.subsecond_precision = normalizeSubsecondPrecision(lt),
|
||||
};
|
||||
return;
|
||||
}
|
||||
}
|
||||
|
||||
#endif
|
||||
|
||||
static void prim_fromTOML(EvalState & state, const PosIdx pos, Value ** args, Value & val)
|
||||
{
|
||||
auto toml = state.forceStringNoCtx(*args[0], pos, "while evaluating the argument passed to builtins.fromTOML");
|
||||
|
||||
std::istringstream tomlStream(std::string{toml});
|
||||
|
||||
std::function<void(Value &, toml::value)> visit;
|
||||
|
||||
visit = [&](Value & v, toml::value t) {
|
||||
auto visit = [&](auto & self, Value & v, toml::value t) -> void {
|
||||
switch (t.type()) {
|
||||
case toml::value_t::table: {
|
||||
auto table = toml::get<toml::table>(t);
|
||||
|
||||
size_t size = 0;
|
||||
for (auto & i : table) {
|
||||
(void) i;
|
||||
size++;
|
||||
}
|
||||
|
||||
auto attrs = state.buildBindings(size);
|
||||
auto attrs = state.buildBindings(table.size());
|
||||
|
||||
for (auto & elem : table) {
|
||||
forceNoNullByte(elem.first);
|
||||
visit(attrs.alloc(elem.first), elem.second);
|
||||
self(self, attrs.alloc(elem.first), elem.second);
|
||||
}
|
||||
|
||||
v.mkAttrs(attrs);
|
||||
} break;
|
||||
;
|
||||
case toml::value_t::array: {
|
||||
auto array = toml::get<std::vector<toml::value>>(t);
|
||||
|
||||
auto list = state.buildList(array.size());
|
||||
for (const auto & [n, v] : enumerate(list))
|
||||
visit(*(v = state.allocValue()), array[n]);
|
||||
self(self, *(v = state.allocValue()), array[n]);
|
||||
v.mkList(list);
|
||||
} break;
|
||||
;
|
||||
case toml::value_t::boolean:
|
||||
v.mkBool(toml::get<bool>(t));
|
||||
break;
|
||||
;
|
||||
case toml::value_t::integer:
|
||||
v.mkInt(toml::get<int64_t>(t));
|
||||
break;
|
||||
;
|
||||
case toml::value_t::floating:
|
||||
v.mkFloat(toml::get<NixFloat>(t));
|
||||
break;
|
||||
;
|
||||
case toml::value_t::string: {
|
||||
auto s = toml::get<std::string_view>(t);
|
||||
forceNoNullByte(s);
|
||||
v.mkString(s);
|
||||
} break;
|
||||
;
|
||||
case toml::value_t::local_datetime:
|
||||
case toml::value_t::offset_datetime:
|
||||
case toml::value_t::local_date:
|
||||
case toml::value_t::local_time: {
|
||||
if (experimentalFeatureSettings.isEnabled(Xp::ParseTomlTimestamps)) {
|
||||
#if HAVE_TOML11_4
|
||||
normalizeDatetimeFormat(t);
|
||||
#endif
|
||||
auto attrs = state.buildBindings(2);
|
||||
attrs.alloc("_type").mkString("timestamp");
|
||||
std::ostringstream s;
|
||||
|
|
@ -80,16 +147,24 @@ static void prim_fromTOML(EvalState & state, const PosIdx pos, Value ** args, Va
|
|||
throw std::runtime_error("Dates and times are not supported");
|
||||
}
|
||||
} break;
|
||||
;
|
||||
case toml::value_t::empty:
|
||||
v.mkNull();
|
||||
break;
|
||||
;
|
||||
}
|
||||
};
|
||||
|
||||
try {
|
||||
visit(val, toml::parse(tomlStream, "fromTOML" /* the "filename" */));
|
||||
visit(
|
||||
visit,
|
||||
val,
|
||||
toml::parse(
|
||||
tomlStream,
|
||||
"fromTOML" /* the "filename" */
|
||||
#if HAVE_TOML11_4
|
||||
,
|
||||
toml::spec::v(1, 0, 0) // Be explicit that we are parsing TOML 1.0.0 without extensions
|
||||
#endif
|
||||
));
|
||||
} catch (std::exception & e) { // TODO: toml::syntax_error
|
||||
state.error<EvalError>("while parsing TOML: %s", e.what()).atPos(pos).debugThrow();
|
||||
}
|
||||
|
|
|
|||
|
|
@ -1 +1 @@
|
|||
{ "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"; bin1 = 214; bool1 = true; bool2 = false; "character encoding" = "value"; d = { e = { f = { }; }; }; dog = { "tater.man" = { type = { name = "pug"; }; }; }; 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; fruit = [ { name = "apple"; physical = { color = "red"; shape = "round"; }; variety = [ { name = "red delicious"; } { name = "granny smith"; } ]; } { name = "banana"; variety = [ { name = "plantain"; } ]; } ]; g = { h = { i = { }; }; }; hex1 = 3735928559; hex2 = 3735928559; hex3 = 3735928559; int1 = 99; int2 = 42; int3 = 0; int4 = -17; int5 = 1000; int6 = 5349221; int7 = 12345; j = { "ʞ" = { l = { }; }; }; key = "value"; key2 = "value"; ld1 = { _type = "timestamp"; value = "1979-05-27"; }; ldt1 = { _type = "timestamp"; value = "1979-05-27T07:32:00"; }; ldt2 = { _type = "timestamp"; value = "1979-05-27T00:32:00.999999"; }; lt1 = { _type = "timestamp"; value = "07:32:00"; }; lt2 = { _type = "timestamp"; value = "00:32:00.999999"; }; name = "Orange"; oct1 = 342391; oct2 = 493; odt1 = { _type = "timestamp"; value = "1979-05-27T07:32:00Z"; }; odt2 = { _type = "timestamp"; value = "1979-05-27T00:32:00-07:00"; }; odt3 = { _type = "timestamp"; value = "1979-05-27T00:32:00.999999-07:00"; }; odt4 = { _type = "timestamp"; value = "1979-05-27T07:32:00Z"; }; physical = { color = "orange"; shape = "round"; }; products = [ { name = "Hammer"; sku = 738594937; } { } { color = "gray"; name = "Nail"; sku = 284758393; } ]; "quoted \"value\"" = "value"; site = { "google.com" = true; }; 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 = { animal = { type = { name = "pug"; }; }; name = { first = "Tom"; last = "Preston-Werner"; }; point = { x = 1; y = 2; }; }; }; }; }; "ʎǝʞ" = "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"; bin1 = 214; bool1 = true; bool2 = false; "character encoding" = "value"; d = { e = { f = { }; }; }; dog = { "tater.man" = { type = { name = "pug"; }; }; }; 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; fruit = [ { name = "apple"; physical = { color = "red"; shape = "round"; }; variety = [ { name = "red delicious"; } { name = "granny smith"; } ]; } { name = "banana"; variety = [ { name = "plantain"; } ]; } ]; g = { h = { i = { }; }; }; hex1 = 3735928559; hex2 = 3735928559; hex3 = 3735928559; int1 = 99; int2 = 42; int3 = 0; int4 = -17; int5 = 1000; int6 = 5349221; int7 = 12345; j = { "ʞ" = { l = { }; }; }; key = "value"; key2 = "value"; ld1 = { _type = "timestamp"; value = "1979-05-27"; }; ldt1 = { _type = "timestamp"; value = "1979-05-27T07:32:00"; }; ldt10 = { _type = "timestamp"; value = "1979-05-27T00:32:00.123456789"; }; ldt11 = { _type = "timestamp"; value = "1979-05-27T00:32:00.123456789"; }; ldt2 = { _type = "timestamp"; value = "1979-05-27T07:32:00.100"; }; ldt3 = { _type = "timestamp"; value = "1979-05-27T07:32:00.120"; }; ldt4 = { _type = "timestamp"; value = "1979-05-27T07:32:00.123"; }; ldt5 = { _type = "timestamp"; value = "1979-05-27T00:32:00.123400"; }; ldt6 = { _type = "timestamp"; value = "1979-05-27T00:32:00.123450"; }; ldt7 = { _type = "timestamp"; value = "1979-05-27T00:32:00.123456"; }; ldt8 = { _type = "timestamp"; value = "1979-05-27T00:32:00.123456700"; }; ldt9 = { _type = "timestamp"; value = "1979-05-27T00:32:00.123456780"; }; lt1 = { _type = "timestamp"; value = "07:32:00"; }; lt10 = { _type = "timestamp"; value = "00:32:00.123456789"; }; lt11 = { _type = "timestamp"; value = "00:32:00.123456789"; }; lt2 = { _type = "timestamp"; value = "00:32:00.100"; }; lt3 = { _type = "timestamp"; value = "00:32:00.120"; }; lt4 = { _type = "timestamp"; value = "00:32:00.123"; }; lt5 = { _type = "timestamp"; value = "00:32:00.123400"; }; lt6 = { _type = "timestamp"; value = "00:32:00.123450"; }; lt7 = { _type = "timestamp"; value = "00:32:00.123456"; }; lt8 = { _type = "timestamp"; value = "00:32:00.123456700"; }; lt9 = { _type = "timestamp"; value = "00:32:00.123456780"; }; name = "Orange"; oct1 = 342391; oct2 = 493; odt1 = { _type = "timestamp"; value = "1979-05-27T07:32:00Z"; }; odt10 = { _type = "timestamp"; value = "1979-05-27T07:32:00.123456Z"; }; odt11 = { _type = "timestamp"; value = "1979-05-27T07:32:00.123456700Z"; }; odt12 = { _type = "timestamp"; value = "1979-05-27T07:32:00.123456780Z"; }; odt13 = { _type = "timestamp"; value = "1979-05-27T07:32:00.123456789Z"; }; odt14 = { _type = "timestamp"; value = "1979-05-27T07:32:00.123456789Z"; }; odt2 = { _type = "timestamp"; value = "1979-05-27T00:32:00-07:00"; }; odt3 = { _type = "timestamp"; value = "1979-05-27T00:32:00.999999-07:00"; }; odt4 = { _type = "timestamp"; value = "1979-05-27T07:32:00Z"; }; odt5 = { _type = "timestamp"; value = "1979-05-27T07:32:00.100Z"; }; odt6 = { _type = "timestamp"; value = "1979-05-27T07:32:00.120Z"; }; odt7 = { _type = "timestamp"; value = "1979-05-27T07:32:00.123Z"; }; odt8 = { _type = "timestamp"; value = "1979-05-27T07:32:00.123400Z"; }; odt9 = { _type = "timestamp"; value = "1979-05-27T07:32:00.123450Z"; }; physical = { color = "orange"; shape = "round"; }; products = [ { name = "Hammer"; sku = 738594937; } { } { color = "gray"; name = "Nail"; sku = 284758393; } ]; "quoted \"value\"" = "value"; site = { "google.com" = true; }; 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 = { animal = { type = { name = "pug"; }; }; name = { first = "Tom"; last = "Preston-Werner"; }; point = { x = 1; y = 2; }; }; }; }; }; "ʎǝʞ" = "value"; }
|
||||
|
|
|
|||
|
|
@ -55,11 +55,53 @@ builtins.fromTOML ''
|
|||
odt2 = 1979-05-27T00:32:00-07:00
|
||||
odt3 = 1979-05-27T00:32:00.999999-07:00
|
||||
odt4 = 1979-05-27 07:32:00Z
|
||||
# milliseconds
|
||||
odt5 = 1979-05-27 07:32:00.1Z
|
||||
odt6 = 1979-05-27 07:32:00.12Z
|
||||
odt7 = 1979-05-27 07:32:00.123Z
|
||||
# microseconds
|
||||
odt8 = 1979-05-27t07:32:00.1234Z
|
||||
odt9 = 1979-05-27t07:32:00.12345Z
|
||||
odt10 = 1979-05-27t07:32:00.123456Z
|
||||
# nanoseconds
|
||||
odt11 = 1979-05-27 07:32:00.1234567Z
|
||||
odt12 = 1979-05-27 07:32:00.12345678Z
|
||||
odt13 = 1979-05-27 07:32:00.123456789Z
|
||||
# no more precision after nanoseconds
|
||||
odt14 = 1979-05-27t07:32:00.1234567891Z
|
||||
|
||||
ldt1 = 1979-05-27T07:32:00
|
||||
ldt2 = 1979-05-27T00:32:00.999999
|
||||
# milliseconds
|
||||
ldt2 = 1979-05-27T07:32:00.1
|
||||
ldt3 = 1979-05-27T07:32:00.12
|
||||
ldt4 = 1979-05-27T07:32:00.123
|
||||
# microseconds
|
||||
ldt5 = 1979-05-27t00:32:00.1234
|
||||
ldt6 = 1979-05-27t00:32:00.12345
|
||||
ldt7 = 1979-05-27t00:32:00.123456
|
||||
# nanoseconds
|
||||
ldt8 = 1979-05-27 00:32:00.1234567
|
||||
ldt9 = 1979-05-27 00:32:00.12345678
|
||||
ldt10 = 1979-05-27 00:32:00.123456789
|
||||
# no more precision after nanoseconds
|
||||
ldt11 = 1979-05-27t00:32:00.1234567891
|
||||
|
||||
ld1 = 1979-05-27
|
||||
lt1 = 07:32:00
|
||||
lt2 = 00:32:00.999999
|
||||
# milliseconds
|
||||
lt2 = 00:32:00.1
|
||||
lt3 = 00:32:00.12
|
||||
lt4 = 00:32:00.123
|
||||
# microseconds
|
||||
lt5 = 00:32:00.1234
|
||||
lt6 = 00:32:00.12345
|
||||
lt7 = 00:32:00.123456
|
||||
# nanoseconds
|
||||
lt8 = 00:32:00.1234567
|
||||
lt9 = 00:32:00.12345678
|
||||
lt10 = 00:32:00.123456789
|
||||
# no more precision after nanoseconds
|
||||
lt11 = 00:32:00.1234567891
|
||||
|
||||
arr1 = [ 1, 2, 3 ]
|
||||
arr2 = [ "red", "yellow", "green" ]
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue