Class StringDictionaryProxy¶

class StringDictionaryProxy¶

Public Types

using TransientMap = robin_hood::unordered_node_map<std::string, int32_t, HeterogeneousStringHash, HeterogeneousStringEqual>¶

Public Functions

StringDictionaryProxy(StringDictionaryProxy const&)¶

StringDictionaryProxy const &operator=(StringDictionaryProxy const&)¶

StringDictionaryProxy(std::shared_ptr<StringDictionary> sd, const int32_t string_dict_id, const int64_t generation)¶

int32_t getDictId() const¶

bool operator==(StringDictionaryProxy const &rhs) const¶

bool operator!=(StringDictionaryProxy const &rhs) const¶

int32_t getOrAdd(const std::string &str)¶

StringDictionary *getDictionary() const¶

int64_t getGeneration() const¶

std::vector<int32_t> getTransientBulk(const std::vector<std::string> &strings) const¶

Executes read-only lookup of a vector of strings and returns a vector of their integer ids.

This function, unlike getOrAddTransientBulk, will not add strings to the dictionary. Use this function if strings that don’t currently exist in the StringDictionaryProxy should not be added to the proxy as transient entries. This method also has performance advantages over getOrAddTransientBulk for read-only use cases, in that it can: 1) Take a read lock instead of a write lock for the transient lookups 2) Use a tbb::parallel_for implementation of the transient string lookups as we are guaranteed that the underlying map of strings to int ids cannot change

Return

A vector of string_ids of the same length as strings, containing the id of any strings for which were found in the underlying StringDictionary instance or in the proxy’s tranient map, otherwise StringDictionary::INVALID_STR_ID for strings not found.

Parameters

strings: - Vector of strings to perform string id lookups on

int32_t getOrAddTransient(const std::string &str)¶

std::vector<int32_t> getOrAddTransientBulk(const std::vector<std::string> &strings)¶

int32_t getIdOfString(const std::string &str) const¶

int32_t getIdOfStringNoGeneration(const std::string &str) const¶

std::string getString(int32_t string_id) const¶

std::vector<std::string> getStrings(const std::vector<int32_t> &string_ids) const¶

std::pair<const char *, size_t> getStringBytes(int32_t string_id) const¶

IdMap initIdMap() const¶

StringDictionaryProxy::IdMap buildIntersectionTranslationMapToOtherProxy(const StringDictionaryProxy *dest_proxy) const¶

Builds a vectorized string_id translation map from this proxy to dest_proxy.

Return

An IdMap which encapsulates a std::vector<int32_t> of string ids for both transient and non-transient strings, mapping to their translated string_ids. offset_ is defined to be the number of transient entries + 1. The ordering of values in the vector_map_ is:

the transient ids (there are offset_-1 of these)
INVALID_STR_ID (=-1)
the non-transient string ids For example if there are 3 transient entries in this proxy and 20 in the underlying string dictionary, then vector_map_ will be of size() == 24 and offset_=3+1. The formula to translate ids is new_id = vector_map_[offset_ + old_id]. It is always the case that vector_map_[offset_-1]==-1 so that INVALID_STR_ID maps to INVALID_STR_ID.

Parameters

dest_proxy: StringDictionaryProxy that we are to map this proxy’s string ids to

StringDictionaryProxy::IdMap buildUnionTranslationMapToOtherProxy(StringDictionaryProxy *dest_proxy) const¶

size_t storageEntryCount() const¶

Returns the number of string entries in the underlying string dictionary, at this proxy’s generation_ if it is set/valid, otherwise just the current size of the dictionary.

Return: size_t Number of entries in the string dictionary (at this proxy’s generation if set)

size_t transientEntryCount() const¶

Returns the number of transient string entries for this proxy,.

Return: size_t Number of transient string entries for this proxy

size_t entryCount() const¶

Returns the number of total string entries for this proxy, both stored in the underlying dictionary and in the transient map. Equal to storageEntryCount() + transientEntryCount()

Return: size_t Number of total string entries for this proxy

void updateGeneration(const int64_t generation)¶

std::vector<int32_t> getLike(const std::string &pattern, const bool icase, const bool is_simple, const char escape) const¶

std::vector<int32_t> getCompare(const std::string &pattern, const std::string &comp_operator) const¶

std::vector<int32_t> getRegexpLike(const std::string &pattern, const char escape) const¶

const std::vector<std::string const *> &getTransientVector() const¶

void eachStringSerially(StringDictionary::StringCallback &serial_callback) const¶

StringDictionaryProxy::IdMap transientUnion(StringDictionaryProxy const &sdp_rhs)¶

Public Static Functions

static unsigned transientIdToIndex(int32_t const id)¶

static int32_t transientIndexToId(unsigned const index)¶

Private Functions

std::string getStringUnlocked(const int32_t string_id) const¶

size_t transientEntryCountUnlocked() const¶

size_t entryCountUnlocked() const¶

template<typename String> int32_t lookupTransientStringUnlocked(const String &lookup_string) const¶

size_t getTransientBulkImpl(const std::vector<std::string> &strings, int32_t *string_ids, const bool take_read_lock) const¶

template<typename String> size_t transientLookupBulk(const std::vector<String> &lookup_strings, int32_t *string_ids, const bool take_read_lock) const¶

template<typename String> size_t transientLookupBulkUnlocked(const std::vector<String> &lookup_strings, int32_t *string_ids) const¶

template<typename String> size_t transientLookupBulkParallelUnlocked(const std::vector<String> &lookup_strings, int32_t *string_ids) const¶

StringDictionaryProxy::IdMap buildIntersectionTranslationMapToOtherProxyUnlocked(const StringDictionaryProxy *dest_proxy) const¶

template<typename String> int32_t getIdOfStringFromClient(String const &str) const¶

template<typename String> int32_t getOrAddTransientUnlocked(String const &str)¶

Private Members

std::shared_ptr<StringDictionary> string_dict_¶

const int32_t string_dict_id_¶

TransientMap transient_str_to_int_¶

std::vector<std::string const *> transient_string_vec_¶

int64_t generation_¶

std::shared_mutex rw_mutex_¶

Friends

friend StringDictionaryProxy::StringLocalCallback

friend StringDictionaryProxy::StringNetworkCallback

struct HeterogeneousStringEqual¶

Public Types

using is_transparent = void¶

Public Functions

bool operator()(std::string_view const lhs, std::string_view const rhs) const¶

struct HeterogeneousStringHash¶

Public Types

using is_transparent = void¶

Public Functions

size_t operator()(std::string_view const key) const¶

class IdMap¶

Public Functions

IdMap(uint32_t const tran_size, uint32_t const dict_size)¶

IdMap(IdMap const&)¶

IdMap(IdMap&&)¶

bool empty() const¶

size_t getIndex(int32_t const id) const¶

std::vector<int32_t> const &getVectorMap() const¶

size_t size() const¶

size_t numTransients() const¶

size_t numNonTransients() const¶

int32_t *data()¶

int32_t const *data() const¶

int32_t domainStart() const¶

int32_t domainEnd() const¶

size_t numUntranslatedStrings() const¶

void setNumUntranslatedStrings(const size_t num_untranslated_strings)¶

int32_t *storageData()¶

int32_t &operator[](int32_t const id)¶

int32_t operator[](int32_t const id) const¶

Private Members

size_t const offset_¶

std::vector<int32_t> vector_map_¶

int64_t num_untranslated_strings_ = {-1}¶

Friends

std::ostream &operator<<(std::ostream &os, IdMap const &id_map)¶