Signed-off-by: Brodie Rao <brodie@sf.io>

Signed-off-by: Brodie Rao <brodie@sf.io>

Signed-off-by: Brodie Rao <brodie@sf.io>

Add orig_commit.

Handle git_buf's from users more liberally

Solaris doesn't have qsort_r either

Add missing `git_reference_symbolic_create_with_log`.

Fix spelling mistake

Closes #2029

submodule branch option + little VS2013 fix

Use our strnlen on MacOS for backward compat

Apparently MacOS didn't have strnlen on 10.6 and earlier.  To
avoid having linking problems on older versions, we'll just use
our internal version.

It's exported in the headers, but the implementation was missing.

Accept 'submodule.*.fetchRecurseSubmodules' config 'on-demand' value

Updated fetch.c test to pass.

I am not sure why there was 6 in the first place.

docs: Remove non existing wrapper from the readme

libgit2net stopped to exist, all hail libgit2sharp

Reference operations with log

Overwrite ignored files on checkout

Clean up some error handling and change callback error behavior

The size_t is 32-bit already, so it overflows before going into the
function. The `-1` test should handle this gracefully in both cases
anyway.

Ok, scrap the previous commit. This is the right overflow check that
takes care of 64 bit overflow **and** 32-bit overflow, which needs to be
considered because the pool malloc can only allocate 32-bit elements in
one go.

Note that `git_pool_strdup` cannot really return any error codes,
 because the pool doesn't set errors on OOM.

 The only place where `giterr_set_oom` is called is in
 `git_pool_strndup`, in a conditional check that is always optimized
 away. `n + 1` cannot be zero if `n` is unsigned because the compiler
 doesn't take wraparound into account.

 This check has been removed altogether because `size_t` is not
 particularly going to overflow.

Validate struct versions in merge, revert

This wasn't being tested and since it has a callback, I fixed it
even though the return value of this callback is not treated like
any of the other callbacks in the API.