summaryrefslogtreecommitdiff
path: root/absl/strings/cord.h
diff options
context:
space:
mode:
authorGravatar Abseil Team <absl-team@google.com>2020-03-03 11:22:10 -0800
committerGravatar Andy Soffer <asoffer@google.com>2020-03-03 17:32:55 -0500
commitb19ba96766db08b1f32605cb4424a0e7ea0c7584 (patch)
treec4ba295b067b000b9d84410ec81e0095715641a5 /absl/strings/cord.h
parent06f0e767d13d4d68071c4fc51e25724e0fc8bc74 (diff)
Export of internal Abseil changes
-- a3e58c1870a9626039f4d178d2d599319bd9f8a8 by Matt Kulukundis <kfm@google.com>: Allow MakeCordFromExternal to take a zero arg releaser. PiperOrigin-RevId: 298650274 -- 01897c4a9bb99f3dc329a794019498ad345ddebd by Samuel Benzaquen <sbenza@google.com>: Reduce library bloat for absl::Flag by moving the definition of base virtual functions to a .cc file. This removes the duplicate symbols in user translation units and has the side effect of moving the vtable definition too (re key function) PiperOrigin-RevId: 298617920 -- 190f0d3782c63aed01046886d7fbc1be5bca2de9 by Derek Mauro <dmauro@google.com>: Import GitHub #596: Unbreak stacktrace code for UWP apps PiperOrigin-RevId: 298600834 -- cd5cf6f8c87b35b85a9584e94da2a99057345b73 by Gennadiy Rozental <rogeeff@google.com>: Use union of heap allocated pointer, one word atomic and two word atomic to represent flags value. Any type T, which is trivially copy-able and with with sizeof(T) <= 8, will be stored in atomic int64_t. Any type T, which is trivially copy-able and with with 8 < sizeof(T) <= 16, will be stored in atomic AlignedTwoWords. We also introducing value storage type to distinguish these cases. PiperOrigin-RevId: 298497200 -- f8fe7bd53bfed601f002f521e34ab4bc083fc28b by Matthew Brown <matthewbr@google.com>: Ensure a deep copy and proper equality on absl::Status::ErasePayload PiperOrigin-RevId: 298482742 -- a5c9ccddf4b04f444e3f7e27dbc14faf1fcb5373 by Gennadiy Rozental <rogeeff@google.com>: Change ChunkIterator implementation to use fixed capacity collection of CordRep*. We can now assume that depth never exceeds 91. That makes comparison operator exception safe. I've tested that with this CL we do not observe an overhead of chunk_end. Compiler optimized this iterator completely. PiperOrigin-RevId: 298458472 -- 327ea5e8910bc388b03389c730763f9823abfce5 by Abseil Team <absl-team@google.com>: Minor cleanups in b-tree code: - Rename some variables: fix issues of different param names between definition/declaration, move away from `x` as a default meaningless variable name. - Make init_leaf/init_internal be non-static methods (they already take the node as the first parameter). - In internal_emplace/try_shrink, update root/rightmost the same way as in insert_unique/insert_multi. - Replace a TODO with a comment. PiperOrigin-RevId: 298432836 -- 8020ce9ec8558ee712d9733ae3d660ac1d3ffe1a by Abseil Team <absl-team@google.com>: Guard against unnecessary copy in case the buffer is empty. This is important in cases were the user is explicitly tuning their chunks to match PiecewiseChunkSize(). PiperOrigin-RevId: 298366044 -- 89324441d1c0c697c90ba7d8fc63639805fcaa9d by Abseil Team <absl-team@google.com>: Internal change PiperOrigin-RevId: 298219363 GitOrigin-RevId: a3e58c1870a9626039f4d178d2d599319bd9f8a8 Change-Id: I28dffc684b6fd0292b94807b88ec6664d5d0e183
Diffstat (limited to 'absl/strings/cord.h')
-rw-r--r--absl/strings/cord.h100
1 files changed, 91 insertions, 9 deletions
diff --git a/absl/strings/cord.h b/absl/strings/cord.h
index 40566cba..68a7e52f 100644
--- a/absl/strings/cord.h
+++ b/absl/strings/cord.h
@@ -41,13 +41,13 @@
#include <iostream>
#include <iterator>
#include <string>
+#include <type_traits>
#include "absl/base/internal/endian.h"
#include "absl/base/internal/invoke.h"
#include "absl/base/internal/per_thread_tls.h"
#include "absl/base/macros.h"
#include "absl/base/port.h"
-#include "absl/container/inlined_vector.h"
#include "absl/functional/function_ref.h"
#include "absl/meta/type_traits.h"
#include "absl/strings/internal/cord_internal.h"
@@ -66,6 +66,73 @@ template <typename H>
H HashFragmentedCord(H, const Cord&);
}
+namespace cord_internal {
+
+// It's expensive to keep a tree perfectly balanced, so instead we keep trees
+// approximately balanced. A tree node N of depth D(N) that contains a string
+// of L(N) characters is considered balanced if L >= Fibonacci(D + 2).
+// The "+ 2" is used to ensure that every leaf node contains at least one
+// character. Here we presume that
+// Fibonacci(0) = 0
+// Fibonacci(1) = 1
+// Fibonacci(2) = 1
+// Fibonacci(3) = 2
+// ...
+//
+// Fibonacci numbers are convenient because it means when two balanced trees of
+// the same depth are made the children of a new node, the resulting tree is
+// guaranteed to also be balanced:
+//
+//
+// L(left) >= Fibonacci(D(left) + 2)
+// L(right) >= Fibonacci(D(right) + 2)
+//
+// L(left) + L(right) >= Fibonacci(D(left) + 2) + Fibonacci(D(right) + 2)
+// L(left) + L(right) == L(new_tree)
+//
+// L(new_tree) >= 2 * Fibonacci(D(child) + 2)
+// D(child) == D(new_tree) - 1
+//
+// L(new_tree) >= 2 * Fibonacci(D(new_tree) + 1)
+// 2 * Fibonacci(N) >= Fibonacci(N + 1)
+//
+// L(new_tree) >= Fibonacci(D(new_tree) + 2)
+//
+//
+// The 93rd Fibonacci number is the largest Fibonacci number that can be
+// represented in 64 bits, so the size of a balanced Cord of depth 92 is too big
+// for an unsigned 64 bit integer to hold. Therefore we can safely assume that
+// the maximum depth of a Cord is 91.
+constexpr size_t MaxCordDepth() { return 91; }
+
+// This class models fixed max size stack of CordRep pointers.
+// The elements are being pushed back and popped from the back.
+template <typename CordRepPtr, size_t N>
+class CordTreePath {
+ public:
+ CordTreePath() {}
+ explicit CordTreePath(CordRepPtr root) { push_back(root); }
+
+ bool empty() const { return size_ == 0; }
+ size_t size() const { return size_; }
+ void clear() { size_ = 0; }
+
+ CordRepPtr back() { return data_[size_ - 1]; }
+
+ void pop_back() {
+ --size_;
+ assert(size_ < N);
+ }
+ void push_back(CordRepPtr elem) { data_[size_++] = elem; }
+
+ private:
+ CordRepPtr data_[N];
+ size_t size_ = 0;
+};
+
+using CordTreeMutablePath = CordTreePath<CordRep*, MaxCordDepth()>;
+} // namespace cord_internal
+
// A Cord is a sequence of characters.
class Cord {
private:
@@ -114,7 +181,8 @@ class Cord {
// finished with `data`. The data must remain live and unchanging until the
// releaser is called. The requirements for the releaser are that it:
// * is move constructible,
- // * supports `void operator()(absl::string_view) const`,
+ // * supports `void operator()(absl::string_view) const` or
+ // `void operator()() const`,
// * does not have alignment requirement greater than what is guaranteed by
// ::operator new. This is dictated by alignof(std::max_align_t) before
// C++17 and __STDCPP_DEFAULT_NEW_ALIGNMENT__ if compiling with C++17 or
@@ -127,8 +195,8 @@ class Cord {
// FillBlock(block);
// return absl::MakeCordFromExternal(
// block->ToStringView(),
- // [pool, block](absl::string_view /*ignored*/) {
- // pool->FreeBlock(block);
+ // [pool, block](absl::string_view v) {
+ // pool->FreeBlock(block, v);
// });
// }
//
@@ -282,8 +350,7 @@ class Cord {
absl::cord_internal::CordRep* current_leaf_ = nullptr;
// The number of bytes left in the `Cord` over which we are iterating.
size_t bytes_remaining_ = 0;
- absl::InlinedVector<absl::cord_internal::CordRep*, 4>
- stack_of_right_children_;
+ absl::cord_internal::CordTreeMutablePath stack_of_right_children_;
};
// Returns an iterator to the first chunk of the `Cord`.
@@ -667,6 +734,21 @@ ExternalRepReleaserPair NewExternalWithUninitializedReleaser(
absl::string_view data, ExternalReleaserInvoker invoker,
size_t releaser_size);
+struct Rank1 {};
+struct Rank0 : Rank1 {};
+
+template <typename Releaser, typename = ::absl::base_internal::InvokeT<
+ Releaser, absl::string_view>>
+void InvokeReleaser(Rank0, Releaser&& releaser, absl::string_view data) {
+ ::absl::base_internal::Invoke(std::forward<Releaser>(releaser), data);
+}
+
+template <typename Releaser,
+ typename = ::absl::base_internal::InvokeT<Releaser>>
+void InvokeReleaser(Rank1, Releaser&& releaser, absl::string_view) {
+ ::absl::base_internal::Invoke(std::forward<Releaser>(releaser));
+}
+
// Creates a new `CordRep` that owns `data` and `releaser` and returns a pointer
// to it, or `nullptr` if `data` was empty.
template <typename Releaser>
@@ -684,14 +766,14 @@ CordRep* NewExternalRep(absl::string_view data, Releaser&& releaser) {
using ReleaserType = absl::decay_t<Releaser>;
if (data.empty()) {
// Never create empty external nodes.
- ::absl::base_internal::Invoke(
- ReleaserType(std::forward<Releaser>(releaser)), data);
+ InvokeReleaser(Rank0{}, ReleaserType(std::forward<Releaser>(releaser)),
+ data);
return nullptr;
}
auto releaser_invoker = [](void* type_erased_releaser, absl::string_view d) {
auto* my_releaser = static_cast<ReleaserType*>(type_erased_releaser);
- ::absl::base_internal::Invoke(std::move(*my_releaser), d);
+ InvokeReleaser(Rank0{}, std::move(*my_releaser), d);
my_releaser->~ReleaserType();
return sizeof(Releaser);
};