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).
This refactors the dynamic check of which implementations are supported at runtime.
It also reduces duplicated effort in the CI fuzzing job, the differential fuzzers don't need to run with different values of SIMDJSON_FORCE_IMPLEMENTATION.
There is also a convenience script to run the fuzzers locally, to quickly check that the fuzzers still build, run and no easy to find bugs are there. It should be handy not only when developing the fuzzers, but also when modifying simdjson.
* Make it possible to check that an implementation is supported at runtime.
* add CI fuzzing on arm 64 bit
This adds fuzzing on drone.io arm64
For some reason, leak detection had to be disabled. If it is enabled, the fuzzer falsely reports a crash at the end of fuzzing.
Closes: #1188
* Guarding the implementation accesses.
* Better doc.
* Updating cxxopts.
* Make it possible to check that an implementation is supported at runtime.
* Guarding the implementation accesses.
* Better doc.
* Updating cxxopts.
* We need to accomodate cxxopts
Co-authored-by: Paul Dreik <github@pauldreik.se>
This adds fuzzing on drone.io arm64
For some reason, leak detection had to be disabled. If it is enabled, the fuzzer falsely reports a crash at the end of fuzzing.
Closes: #1188
This adds a fuzzer which parses the same input using all the available implementations (haswell, westmere, fallback on x64).
This should get the otherwise uncovered sourcefiles (mostly fallback) to show up in the fuzz coverage.
For instance, the fallback directory has only one line covered.
As of the 20200909 report, 1866 lines are covered out of 4478.
Also, it will detect if the implementations behave differently:
by making sure they all succeed, or all error
turning the parsed data into text again, should produce equal results
While at it, I corrected some minor things:
clean up building too many variants, run with forced implementation (closes#815 )
always store crashes as artefacts, good in case the fuzzer finds something
return value of the fuzzer function should always be 0
reduce log spam
introduce max size for the seed corpus and the CI fuzzer
strager
Paul Dreik
Daniel Lemire