Disambiguate error values: return `GIT_ENOTFOUND` when the item cannot
exist in the repository (perhaps because the repository is inmemory or
otherwise not backed by a filesystem), return `-1` when there is a hard
failure.

Update version number to 0.26

CHANGELOG: add various changes introduced since v0.25

Ensure packfiles with different contents have different names

Update to forced checkout and untracked files

Only ignore `EBUSY` from `rmdir` when the `GIT_RMDIR_SKIP_NONEMPTY` bit
is set.

When deleting a directory during checkout, do not simply delete the
directory, since there may be untracked files.  Instead, go into
the iterator and examine each file.

In the original code (the code with the faulty assumption), we look to
see if there's an index entry beneath the directory that we want to
remove.   Eg, it looks to see if we have a workdir entry foo and an
index entry foo/bar.txt. If this is not the case, then the working
directory must have precious files in that directory. This part is okay.
The part that's not okay is if there is an index entry foo/bar.txt. It
just blows away the whole damned directory.

That's not cool.

Instead, by simply pushing the directory itself onto the stack and
iterating each entry, we will deal with the files one by one - whether
they're in the index (and can be force removed) or not (and are
precious).

The original code was a bad optimization, assuming that we didn't need
to git_iterator_advance_into if there was any index entry in the folder.
That's wrong - we could have optimized this iff all folder entries are
in the index.

Instead, we need to simply dig into the directory and analyze its
entries.

If the `GIT_CHECKOUT_FORCE` flag is given to any of the `git_checkout`
invocations, we remove files which were previously staged. But while
doing so, we unfortunately also remove unstaged files in a directory
which contains at least one staged file, resulting in potential data
loss.

This commit adds two tests to verify behavior.

settings: rename `GIT_OPT_ENABLE_SYNCHRONOUS_OBJECT_CREATION`

Initially, the setting has been solely used to enable the use of
`fsync()` when creating objects. Since then, the use has been extended
to also cover references and index files. As the option is not yet part
of any release, we can still correct this by renaming the option to
something more sensible, indicating not only correlation to objects.

This commit renames the option to `GIT_OPT_ENABLE_FSYNC_GITDIR`. We also
move the variable from the object to repository source code.

Buffer growing cleanups

Coverity fixes

The `git_buf_init` function has an optional length parameter, which will
cause the buffer to be initialized and allocated in one step. This can
be used instead of static initialization with `GIT_BUF_INIT` followed by
a `git_buf_grow`. This patch does so for two functions where it is
applicable.

Both the `git_buf_init` and `git_buf_attach` functions may call
`git_buf_grow` in case they were given an allocation length as
parameter. As such, it is possible for these functions to fail when we
run out of memory. While it won't probably be used anytime soon, it does
indeed make sense to also record this fact by returning an error code
from both functions. As they belong to the internal API only, this
change does not break our interface.

The `ENSURE_SIZE` macro can be used to grow a buffer if its currently
allocated size does not suffice a required target size. While most of
the code already uses this macro, the `git_buf_join` and `git_buf_join3`
functions do not yet use it. Due to the macro first checking whether we
have to grow the buffer at all, this has the benefit of saving a
function call when it is not needed. While this is nice to have, it will
probably not matter at all performance-wise -- instead, this only serves
for consistency across the code.

While the `ENSURE_SIZE` macro gets a reference to both the buffer that
is to be resized and a new size, we were not consistently referencing
the passed buffer, but instead a variable `buf`, which is not passed in.
Funnily enough, we never noticed because our buffers seem to always be
named `buf` whenever the macro was being used.

Fix the macro by always using the passed-in buffer. While at it, add
braces around all mentions of passed-in variables as should be done with
macros to avoid subtle errors.

Found-by: Edward Thompson

The function `git_buf_try_grow` consistently calls `giterr_set_oom`
whenever growing the buffer fails due to insufficient memory being
available. So in fact, we do not have to do this ourselves when a call
to any buffer-growing function has failed due to an OOM situation. But
we still do so in two functions, which this patch cleans up.

SHA1DC update

The updated SHA1DC library allows us to use custom includes instead of
using standard includes. Due to requirements with cross-platform, we
provide some custom system includes files like for example the
"stdint.h" file on Win32. Because of this, we want to make sure to avoid
breaking cross-platform compatibility when SHA1DC is enabled.

To use the new mechanism, we can simply define
`SHA1DC_NO_STANDARD_INCLUDES`. Furthermore, we can specify custom
include files via two defines, which we now use to include our
"common.h" header.

This updates our version of SHA1DC to e139984 (Merge pull request #35
from lidl/master, 2017-05-30).

Fix path computations for compressed index entries

(Temporarily) disable UNC tests

(Temporarily) disable UNC path tests to work around AppVeyor issues.

Fix build with libressl

OpenSSL v1.1 has introduced a new way of initializing the library
without having to call various functions of different subsystems. In
libgit2, we have been adapting to that change with 88520151
(openssl_stream: use new initialization function on OpenSSL version
>=1.1, 2017-04-07), where we added an #ifdef depending on the OpenSSL
version. This change broke building with libressl, though, which has not
changed its API in the same way.

Fix the issue by expanding the #ifdef condition to use the old way of
initializing with libressl.

Signed-off-by: Marc-Antoine Perennou <Marc-Antoine@Perennou.com>

The current write test does not trigger some edge-cases in the index
version 4 path compression code. Rewrite the test to start off the an
empty standard repository, creating index entries with interesting paths
itself. This allows for more fine-grained control over checked paths.
Furthermore, we now also verify that entry paths are actually
reconstructed correctly.

While we do have a test which checks whether a written index of version
4 has the correct version set, we do not check whether this actually
enables path compression for index entries. This commit adds a new test
by adding a number of index entries with equal path prefixes to the
index and subsequently flushing that to disk. With suffix compression
enabled by index version 4, only the last few bytes of these paths will
actually have to be written to the index, saving a lot of disk space.
For the test, differences are about an order of magnitude, allowing us
to easily verify without taking a deeper look at actual on-disk
contents.

While we have a simple test to determine whether we can write an index
of version 4, we never verified that we are able to read this kind of
index (and in fact, we were not able to do so). Add a new repository
which has an index of version 4. This repository is then read from a new
test.

The init and cleanup functions for test suites are usually prepended to
our actual tests. The index::version test suite does not adhere to this
stile. Fix this.

In our code writing index entries, we carry around a `disk_size`
representing how much memory we have in total and pass this value to
`git_encode_varint` to do bounds checks. This does not make much sense,
as at the time when passing on this variable it is already out of date.
Fix this by subtracting used memory from `disk_size` as we go along.
Furthermore, assert we've actually got enough space left to do the final
path memcpy.

When using compressed index entries, each entry's path is preceded by a
varint encoding how long the shared prefix with the previous index entry
actually is. We currently encode a length of `(path_len - same_len)`,
which is doubly wrong. First, `path_len` is already set to `path_len -
same_len` previously. Second, we want to encode the shared prefix rather
than the un-shared suffix length.

Fix this by using `same_len` as the varint value instead.