Including <iostream> has two problems:
* Compile times are worse because of over-inclusion
* Binary sizes are worse when statically linking libstdc++ because
iostreams cannot be dead-code-stripped
simdjson only needs std::ostream. Include the header declaring only what
we need (<ostream>), omitting stuff we don't need (std::cout and its
initialization, for example).
This commit should not change behavior, but it might break users who
assume that including <simdjson/simdjson.h> will make std::cout
available (such as many of simdjson's own files).
* Adding test.
* Verifies and fix issue 1668. This commit updates the previous behavior of the
On Demand stream support by return a value type (document_reference) instead
of a reference to a document. This allows us to bridge with the usually simdjson
error system, with its simdjson_result types.
* Minor reformat.
* Adds a test with initial tests passing.
* Adding an example.
* Update basic.md to document JSON pointer for On Demand.
* Add automatic rewind for at_pointer
* Remove DOM examples in basics.md and update documentation reflecting addition of at_pointer automatic rewinding.
* Review
* Add test
* Naive implementation for doubles in string.
* Add double from string in atom doc.
* Simplification (removed all *_from_string())
* Add int and uint parsing in string.
* Make duplicates instead.
* Make tests exceptionless.
* Add missing declarations.
* Add more tests (errors, JSON pointer).
* Add crypto json tests.
* Update doc.
* Update doc after review.
Co-authored-by: Daniel Lemire <lemire@gmail.com>
* Update basic.md to document JSON pointer for On Demand.
* Add automatic rewind for at_pointer
* Remove DOM examples in basics.md and update documentation reflecting addition of at_pointer automatic rewinding.
* Review
* Add test
* Add document_stream constructors and iterate_many
* Attempt to implement streaming.
* Kind of fixed next() for getting next document
* Temporary save.
* Putting in working order.
* Add working doc_index and add function next_document()
* Attempt to implement streaming.
* Re-anchoring json_iterator after a call to stage 1
* I am convinced it should be a 'while'.
* Add source() with test.
* Add truncated_bytes().
* Fix casting issues.
* Fix old style cast.
* Fix privacy issue.
* Fix privacy issues.
* Again
* .
* Add more tests. Add error() for iterator class.
* Fix source() to not included whitespaces between documents.
* Fixing CI.
* Fix source() for multiple batches. Add new tests.
* Fix batch_start when document has leading spaces. Add new tests for that.
* Add new tests.
* Temporary save.
* Working hacky multithread version.
* Small fix in header files.
* Correct version (not working).
* Adding a move assignment to ondemand::parser.
* Fix attempt by changing std::swap.
* Moving DEFAULT_BATCH_SIZE and MINIMAL_BATCH_SIZE.
* Update doc and readme tests.
* Update basics.md
* Update readme_examples tests.
* Fix exceptions in test.
* Partial setup for amazon_cellphones.
* Benchmark with vectors.
* Benchmark with maps
* With vectors again.
* Fix for weighted average.
* DOM benchmark.
* Fix typos. Add On Demand benchmark.
* Add large amazon_cellphones benchmark for DOM
* Add benchmark for On demand.
* Fix broken read_me test.
* Add parser.threaded to enable/disable thread usage.
Co-authored-by: Daniel Lemire <lemire@gmail.com>
* Changing the name of the function to 'to_json_string' from 'to_string' to avoid confusion.
* Moving to a fast string_view model
* Making it exception-safe.
* Tweaking.
* Workaround for exceptions.
* more robust to_json_string (#1651)
* WIP.
* Fuzzing timeout (bug fix) (#1650)
* prove pull request #1648 introduces an infinite loop
* Interesting bug!
* Tweak.
Co-authored-by: Paul Dreik <github@pauldreik.se>
* It should now work.
* Moving car examples to exception mode
* Simplifying somewhat.
* I forgot to abandon. Let us do that.
* Adding more tests.
* WIP.
* It should now work.
* Moving car examples to exception mode
* Simplifying somewhat.
* I forgot to abandon. Let us do that.
* Adding more tests.
Co-authored-by: Paul Dreik <github@pauldreik.se>
Co-authored-by: Paul Dreik <github@pauldreik.se>
* upload corpus to https://www.pauldreik.se/ from the x64 github action job (keep the github action cache)
* drop the github action cache (which was not working anyway) for power fuzzer and download the fuzz corpus from https://www.pauldreik.se/ instead
* resurrect arm64 fuzzing on drone CI, downloading the fuzz corpus from https://www.pauldreik.se/
* update the fuzzing documentation
* Update basic.md to document JSON pointer for On Demand.
* Add automatic rewind for at_pointer
* Remove DOM examples in basics.md and update documentation reflecting addition of at_pointer automatic rewinding.
* Review
* Add test
Co-authored-by: Daniel Lemire <lemire@gmail.com>
Paul Dreik
Daniel Lemire
strager
Dirk Stolle
Nicolas Boyer