Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Make the Vocabulary class aware of the different Datatypes #443

Merged
merged 1 commit into from
Jul 23, 2021
Merged

Make the Vocabulary class aware of the different Datatypes #443

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Jump to
Jump to file
Failed to load files.
Diff view
Diff view
40 changes: 40 additions & 0 deletions src/index/Vocabulary.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -474,6 +474,44 @@ const std::optional<string> Vocabulary<S, C>::idToOptionalString(Id id) const {
return _externalLiterals[id];
}
}

// ___________________________________________________________________________
template <typename S, typename C>
ad_utility::HashMap<typename Vocabulary<S, C>::Datatypes, std::pair<Id, Id>>
Vocabulary<S, C>::getRangesForDatatypes() const {
ad_utility::HashMap<Datatypes, std::pair<Id, Id>> result;
result[Datatypes::Float] = prefix_range(VALUE_FLOAT_PREFIX);
result[Datatypes::Date] = prefix_range(VALUE_DATE_PREFIX);
result[Datatypes::Literal] = prefix_range("\"");
result[Datatypes::Iri] = prefix_range("<");

return result;
};

template <typename S, typename C>
template <typename, typename>
void Vocabulary<S, C>::printRangesForDatatypes() {
auto ranges = getRangesForDatatypes();
auto logRange = [&](const auto& range) {
LOG(INFO) << range.first << " " << range.second << '\n';
if (range.second > range.first) {
LOG(INFO) << idToOptionalString(range.first).value() << '\n';
LOG(INFO) << idToOptionalString(range.second - 1).value() << '\n';
}
if (range.second < _words.size()) {
LOG(INFO) << idToOptionalString(range.second).value() << '\n';
}

if (range.first > 0) {
LOG(INFO) << idToOptionalString(range.first - 1).value() << '\n';
}
};

for (const auto& pair : ranges) {
logRange(pair.second);
}
}

template const std::optional<string>
RdfsVocabulary::idToOptionalString<CompressedString, void>(Id id) const;

Expand All @@ -492,6 +530,8 @@ template void RdfsVocabulary::prefixCompressFile<CompressedString, void>(
const string& infile, const string& outfile,
const vector<string>& prefixes);

template void RdfsVocabulary::printRangesForDatatypes();

template void TextVocabulary::createFromSet<std::string, void>(
const ad_utility::HashSet<std::string>& set);
template void TextVocabulary::writeToFile<std::string, void>(
Expand Down
9 changes: 9 additions & 0 deletions src/index/Vocabulary.h
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -74,6 +74,9 @@ struct Prefix {
//! CompressedString -> prefix compression is applied
template <class StringType, class ComparatorType>
class Vocabulary {
// The different type of data that is stored in the vocabulary
enum class Datatypes { Literal, Iri, Float, Date };

template <typename T, typename R = void>
using enable_if_compressed =
std::enable_if_t<std::is_same_v<T, CompressedString>>;
Expand Down Expand Up @@ -177,6 +180,12 @@ class Vocabulary {
// consider using the prefixRange function.
bool getIdRangeForFullTextPrefix(const string& word, IdRange* range) const;

ad_utility::HashMap<Datatypes, std::pair<Id, Id>> getRangesForDatatypes()
const;

template <typename U = StringType, typename = enable_if_compressed<U>>
void printRangesForDatatypes();

// only used during Index building, not needed for compressed vocabulary
template <typename U = StringType, typename = enable_if_uncompressed<U>>
void createFromSet(const ad_utility::HashSet<StringType>& set);
Expand Down