diff options
| author | Douglas B. Rumbaugh <dbr4@psu.edu> | 2024-12-06 13:13:51 -0500 |
|---|---|---|
| committer | GitHub <noreply@github.com> | 2024-12-06 18:13:51 +0000 |
| commit | 9fe305c7d28e993e55c55427f377ae7e3251ea4f (patch) | |
| tree | 384b687f64b84eb81bde2becac8a5f24916b07b4 /include/framework/interface/Record.h | |
| parent | 47916da2ba5ed5bee2dda3cbcc58d39e1e931bfc (diff) | |
| download | dynamic-extension-9fe305c7d28e993e55c55427f377ae7e3251ea4f.tar.gz | |
Interface update (#5)
* Query Interface Adjustments/Refactoring
Began the process of adjusting the query interface (and also the shard
interface, to a lesser degree) to better accommodate the user. In
particular the following changes have been made,
1. The number of necessary template arguments for the query type
has been drastically reduced, while also removing the void pointers
and manual delete functions from the interface.
This was accomplished by requiring many of the sub-types associated
with a query (parameters, etc.) to be nested inside the main query
class, and by forcing the SHARD type to expose its associated
record type.
2. User-defined query return types are now supported.
Queries no longer are required to return strictly sets of records.
Instead, the query now has LocalResultType and ResultType
template parameters (which can be defaulted using a typedef in
the Query type itself), allowing much more flexibility.
Note that, at least for the short term, the LocalResultType must
still expose the same is_deleted/is_tombstone interface as a
Wrapped<R> used to, as this is currently needed for delete
filtering. A better approach to this is, hopefully, forthcoming.
3. Updated the ISAMTree.h shard and rangequery.h query to use the
new interfaces, and adjusted the associated unit tests as well.
4. Dropped the unnecessary "get_data()" function from the ShardInterface
concept.
5. Dropped the need to specify a record type in the ShardInterface
concept. This is now handled using a required Shard::RECORD
member of the Shard class itself, which should expose the name
of the record type.
* Updates to framework to support new Query/Shard interfaces
Pretty extensive adjustments to the framework, particularly to the
templates themselves, along with some type-renaming work, to support
the new query and shard interfaces.
Adjusted the external query interface to take an rvalue reference, rather
than a pointer, to the query parameters.
* Removed framework-level delete filtering
This was causing some issues with the new query interface, and should
probably be reworked anyway, so I'm temporarily (TM) removing the
feature.
* Updated benchmarks + remaining code for new interface
Diffstat (limited to 'include/framework/interface/Record.h')
| -rw-r--r-- | include/framework/interface/Record.h | 335 |
1 files changed, 155 insertions, 180 deletions
diff --git a/include/framework/interface/Record.h b/include/framework/interface/Record.h index 19ccadd..d3e77d8 100644 --- a/include/framework/interface/Record.h +++ b/include/framework/interface/Record.h @@ -1,272 +1,247 @@ /* * include/framework/interface/Record.h * - * Copyright (C) 2023 Douglas Rumbaugh <drumbaugh@psu.edu> + * Copyright (C) 2023-2024 Douglas Rumbaugh <drumbaugh@psu.edu> * * Distributed under the Modified BSD License. * - * FIXME: the record implementations could probably be broken out into + * FIXME: the record implementations could probably be broken out into * different files, leaving only the interface here */ #pragma once -#include <cstring> -#include <concepts> #include <cmath> +#include <concepts> +#include <cstring> #include "psu-util/hash.h" namespace de { -template<typename R> +template <typename R> concept RecordInterface = requires(R r, R s) { - { r < s } ->std::convertible_to<bool>; - { r == s } ->std::convertible_to<bool>; + { r < s } -> std::convertible_to<bool>; + { r == s } -> std::convertible_to<bool>; }; -template<typename R> +template <typename R> concept WeightedRecordInterface = requires(R r) { - {r.weight} -> std::convertible_to<double>; + { r.weight } -> std::convertible_to<double>; }; -template<typename R> +template <typename R> concept NDRecordInterface = RecordInterface<R> && requires(R r, R s) { - {r.calc_distance(s)} -> std::convertible_to<double>; + { r.calc_distance(s) } -> std::convertible_to<double>; }; template <typename R> concept KVPInterface = RecordInterface<R> && requires(R r) { - r.key; - r.value; + r.key; + r.value; }; -template<typename R> +template <typename R> concept AlexInterface = KVPInterface<R> && requires(R r) { - {r.key} -> std::convertible_to<size_t>; - {r.value} -> std::convertible_to<size_t>; + { r.key } -> std::convertible_to<size_t>; + { r.value } -> std::convertible_to<size_t>; }; -template<typename R> -concept WrappedInterface = RecordInterface<R> && requires(R r, R s, bool b, int i) { - {r.header} -> std::convertible_to<uint32_t>; - r.rec; - {r.set_delete()}; - {r.is_deleted()} -> std::convertible_to<bool>; - {r.set_tombstone(b)}; - {r.is_tombstone()} -> std::convertible_to<bool>; - {r.set_timestamp(i)}; - {r.get_timestamp()} -> std::convertible_to<uint32_t>; - {r.clear_timestamp()}; - {r.is_visible()} -> std::convertible_to<bool>; - {r.set_visible()}; - {r < s} -> std::convertible_to<bool>; - {r == s} ->std::convertible_to<bool>; +template <typename R> +concept WrappedInterface = RecordInterface<R> && + requires(R r, R s, bool b, int i) { + { r.header } -> std::convertible_to<uint32_t>; + r.rec; + {r.set_delete()}; + { r.is_deleted() } -> std::convertible_to<bool>; + {r.set_tombstone(b)}; + { r.is_tombstone() } -> std::convertible_to<bool>; + {r.set_timestamp(i)}; + { r.get_timestamp() } -> std::convertible_to<uint32_t>; + {r.clear_timestamp()}; + { r.is_visible() } -> std::convertible_to<bool>; + {r.set_visible()}; + { r < s } -> std::convertible_to<bool>; + { r == s } -> std::convertible_to<bool>; }; -template<RecordInterface R> -struct Wrapped { - uint32_t header; - R rec; +template <RecordInterface R> struct Wrapped { + uint32_t header; + R rec; - inline void set_delete() { - header |= 2; - } + inline void set_delete() { header |= 2; } - inline bool is_deleted() const { - return header & 2; - } + inline bool is_deleted() const { return header & 2; } - inline void set_visible() { - header |= 4; - } + inline void set_visible() { header |= 4; } - inline bool is_visible() const { - return header & 4; - } + inline bool is_visible() const { return header & 4; } - inline void set_timestamp(int ts) { - header |= (ts << 3); - } - - inline int get_timestamp() const { - return header >> 3; - } + inline void set_timestamp(int ts) { header |= (ts << 3); } - inline void clear_timestamp() { - header &= 7; - } + inline int get_timestamp() const { return header >> 3; } - inline void set_tombstone(bool val=true) { - if (val) { - header |= 1; - } else { - header &= 0; - } - } + inline void clear_timestamp() { header &= 7; } - inline bool is_tombstone() const { - return header & 1; + inline void set_tombstone(bool val = true) { + if (val) { + header |= 1; + } else { + header &= 0; } + } - inline bool operator<(const Wrapped& other) const { - return rec < other.rec || (rec == other.rec && header < other.header); - } + inline bool is_tombstone() const { return header & 1; } - inline bool operator==(const Wrapped& other) const { - return rec == other.rec; - } + inline bool operator<(const Wrapped &other) const { + return rec < other.rec || (rec == other.rec && header < other.header); + } + inline bool operator==(const Wrapped &other) const { + return rec == other.rec; + } }; -template <typename K, typename V> -struct Record { - K key; - V value; +template <typename K, typename V> struct Record { + K key; + V value; - inline bool operator<(const Record& other) const { - return key < other.key || (key == other.key && value < other.value); - } + inline bool operator<(const Record &other) const { + return key < other.key || (key == other.key && value < other.value); + } - inline bool operator==(const Record& other) const { - return key == other.key && value == other.value; - } + inline bool operator==(const Record &other) const { + return key == other.key && value == other.value; + } }; -template<typename V> -struct Record<const char*, V> { - const char* key; - V value; - size_t len; +template <typename V> struct Record<const char *, V> { + const char *key; + V value; + size_t len; - inline bool operator<(const Record& other) const { - size_t n = std::min(len, other.len) + 1; - return strncmp(key, other.key, n) < 0; - } + inline bool operator<(const Record &other) const { + size_t n = std::min(len, other.len) + 1; + return strncmp(key, other.key, n) < 0; + } - inline bool operator==(const Record& other) const { - size_t n = std::min(len, other.len) + 1; - return strncmp(key, other.key, n) == 0; - } + inline bool operator==(const Record &other) const { + size_t n = std::min(len, other.len) + 1; + return strncmp(key, other.key, n) == 0; + } }; -template <typename K, typename V, typename W> -struct WeightedRecord { - K key; - V value; - W weight = 1; +template <typename K, typename V, typename W> struct WeightedRecord { + K key; + V value; + W weight = 1; - inline bool operator==(const WeightedRecord& other) const { - return key == other.key && value == other.value; - } + inline bool operator==(const WeightedRecord &other) const { + return key == other.key && value == other.value; + } - inline bool operator<(const WeightedRecord& other) const { - return key < other.key || (key == other.key && value < other.value); - } + inline bool operator<(const WeightedRecord &other) const { + return key < other.key || (key == other.key && value < other.value); + } }; +template <typename V, size_t D = 2> struct CosinePoint { + V data[D]; -template <typename V, size_t D=2> -struct CosinePoint{ - V data[D]; - - inline bool operator==(const CosinePoint& other) const { - for (size_t i=0; i<D; i++) { - if (data[i] != other.data[i]) { - return false; - } - } - - return true; + inline bool operator==(const CosinePoint &other) const { + for (size_t i = 0; i < D; i++) { + if (data[i] != other.data[i]) { + return false; + } } - /* lexicographic order */ - inline bool operator<(const CosinePoint& other) const { - for (size_t i=0; i<D; i++) { - if (data[i] < other.data[i]) { - return true; - } else if (data[i] > other.data[i]) { - return false; - } - } + return true; + } + /* lexicographic order */ + inline bool operator<(const CosinePoint &other) const { + for (size_t i = 0; i < D; i++) { + if (data[i] < other.data[i]) { + return true; + } else if (data[i] > other.data[i]) { return false; + } } - inline double calc_distance(const CosinePoint& other) const { + return false; + } - double prod = 0; - double asquared = 0; - double bsquared = 0; + inline double calc_distance(const CosinePoint &other) const { - for (size_t i=0; i<D; i++) { - prod += data[i] * other.data[i]; - asquared += data[i]*data[i]; - bsquared += other.data[i]*other.data[i]; - } + double prod = 0; + double asquared = 0; + double bsquared = 0; - return prod / std::sqrt(asquared * bsquared); + for (size_t i = 0; i < D; i++) { + prod += data[i] * other.data[i]; + asquared += data[i] * data[i]; + bsquared += other.data[i] * other.data[i]; } + + return prod / std::sqrt(asquared * bsquared); + } }; +template <typename V, size_t D = 2> struct EuclidPoint { + V data[D]; -template <typename V, size_t D=2> -struct EuclidPoint{ - V data[D]; + inline bool operator==(const EuclidPoint &other) const { + for (size_t i = 0; i < D; i++) { + if (data[i] != other.data[i]) { + return false; + } + } - inline bool operator==(const EuclidPoint& other) const { - for (size_t i=0; i<D; i++) { - if (data[i] != other.data[i]) { - return false; - } - } + return true; + } + /* lexicographic order */ + inline bool operator<(const EuclidPoint &other) const { + for (size_t i = 0; i < D; i++) { + if (data[i] < other.data[i]) { return true; + } else if (data[i] > other.data[i]) { + return false; + } } - /* lexicographic order */ - inline bool operator<(const EuclidPoint& other) const { - for (size_t i=0; i<D; i++) { - if (data[i] < other.data[i]) { - return true; - } else if (data[i] > other.data[i]) { - return false; - } - } + return false; + } - return false; + inline double calc_distance(const EuclidPoint &other) const { + double dist = 0; + for (size_t i = 0; i < D; i++) { + dist += (data[i] - other.data[i]) * (data[i] - other.data[i]); } - inline double calc_distance(const EuclidPoint& other) const { - double dist = 0; - for (size_t i=0; i<D; i++) { - dist += (data[i] - other.data[i]) * (data[i] - other.data[i]); - } - - return std::sqrt(dist); - } + return std::sqrt(dist); + } }; -template<RecordInterface R> -struct RecordHash { - size_t operator()(R const &rec) const { - return psudb::hash_bytes((std::byte *) &rec, sizeof(R)); - } +template <RecordInterface R> struct RecordHash { + size_t operator()(R const &rec) const { + return psudb::hash_bytes((std::byte *)&rec, sizeof(R)); + } }; -template <typename R> -class DistCmpMax { +template <typename R> class DistCmpMax { public: - DistCmpMax(R *baseline) : P(baseline) {} + DistCmpMax(R *baseline) : P(baseline) {} - inline bool operator()(const R *a, const R *b) requires WrappedInterface<R> { - return a->rec.calc_distance(P->rec) > b->rec.calc_distance(P->rec); - } + inline bool operator()(const R *a, const R *b) requires WrappedInterface<R> { + return a->rec.calc_distance(P->rec) > b->rec.calc_distance(P->rec); + } - inline bool operator()(const R *a, const R *b) requires (!WrappedInterface<R>){ - return a->calc_distance(*P) > b->calc_distance(*P); - } + inline bool operator()(const R *a, + const R *b) requires(!WrappedInterface<R>) { + return a->calc_distance(*P) > b->calc_distance(*P); + } private: - R *P; + R *P; }; -} +} // namespace de |