Skip to content

fix: Output documents in a streaming fashion to avoid 2GB limit #190

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

Merged
varungandhi-src merged 1 commit into from
Jun 26, 2023
Merged

fix: Output documents in a streaming fashion to avoid 2GB limit #190

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.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
43 changes: 36 additions & 7 deletions scip_indexer/SCIPIndexer.cc
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1128,6 +1128,34 @@ class CFGTraversal final {

namespace sorbet::pipeline::semantic_extension {

struct IndexWriter {
scip::Index index;
ostream &outputStream;

~IndexWriter() {
this->write();
}

void writeDocument(scip::Document &&doc) {
*this->index.add_documents() = std::move(doc);
this->write();
}

void writeExternalSymbol(scip::SymbolInformation &&symbolInfo) {
*this->index.add_external_symbols() = std::move(symbolInfo);
if (this->index.external_symbols_size() % 1024 == 0) {
this->write();
}
}

private:
void write() {
this->index.SerializeToOstream(&this->outputStream);
this->index.clear_documents();
this->index.clear_external_symbols();
}
};

using LocalSymbolTable = UnorderedMap<core::LocalVariable, core::Loc>;

class SCIPSemanticExtension : public SemanticExtension {
Expand Down Expand Up @@ -1269,19 +1297,20 @@ class SCIPSemanticExtension : public SemanticExtension {
return s1.symbol() < s2.symbol();
});

// TODO: Is it OK to do I/O here? Or should it be elsewhere?
ofstream out(indexFilePath);

scip::Index index;
*index.mutable_metadata() = metadata;
index.SerializeToOstream(&out);

IndexWriter writer{scip::Index{}, out};
for (auto &document : allDocuments) {
*index.add_documents() = move(document);
writer.writeDocument(move(document));
}
for (auto &symbol : allExternalSymbols) {
*index.add_external_symbols() = move(symbol);
writer.writeExternalSymbol(move(symbol));
}

ofstream out(indexFilePath);
// TODO: Is it OK to do I/O here? Or should it be elsewhere?
index.SerializeToOstream(&out);
out.close();
};

virtual void typecheck(const core::GlobalState &gs, core::FileRef file, cfg::CFG &cfg,
Expand Down