The `config_read` function currently performs both reading the
on-disk config file as well as parsing the retrieved buffer
contents. To optimize how we refresh our config entries from an
in-memory buffer, we need to be able to directly parse buffers,
though, without involving any on-disk files at all.

Extract a new function `config_read_buffer` that sets up the
parsing logic and then parses config entries from a buffer, only.
Have `config_read` use it to avoid duplicated logic.

We are quite lazy in how we refresh our config file backend when
updating any of its keys: instead of just updating our in-memory
representation of the keys, we just discard the old set of keys
and then re-read the config file contents from disk. This refresh
currently happens separately at every callsite of `config_write`,
but it is clear that we _always_ want to refresh if we have
written the config file to disk. If we didn't, then we'd run
around with an outdated config file backend that does not
represent what we have on disk.

By moving the refresh into `config_write`, we are also able to
optimize the case where the config file is currently locked.
Before, we would've tried to re-read the file even if we have
only updated its cached contents without touching the on-disk
file. Thus we'd have unnecessarily stat'd the file, even though
we know that it shouldn't have been modified in the meantime due
to its lock.

To decide whether a config file has changed, we always hash its
complete contents. This is unnecessarily expensive, as
well-behaved filesystems will always update stat information for
files which have changed. So before computing the hash, we should
first check whether the stat info has actually changed for either
the configuration file or any of its includes. This avoids having
to re-read the configuration file and its includes every time
when we check whether it's been modified.

Tracing the for-each-ref example previous to this commit, one can
see that we repeatedly re-open both the repo configuration as
well as the global configuration:

	$ strace lg2 for-each-ref |& grep config
	access("/home/pks/.gitconfig", F_OK)    = -1 ENOENT (No such file or directory)
	access("/home/pks/.config/git/config", F_OK) = 0
	access("/etc/gitconfig", F_OK)          = -1 ENOENT (No such file or directory)
	stat("/tmp/repo/.git/config", {st_mode=S_IFREG|0644, st_size=92, ...}) = 0
	access("/tmp/repo/.git/config", F_OK)   = 0
	stat("/tmp/repo/.git/config", {st_mode=S_IFREG|0644, st_size=92, ...}) = 0
	open("/tmp/repo/.git/config", O_RDONLY|O_CLOEXEC) = 3
	stat("/home/pks/.gitconfig", 0x7ffd15c05290) = -1 ENOENT (No such file or directory)
	access("/home/pks/.gitconfig", F_OK)    = -1 ENOENT (No such file or directory)
	stat("/home/pks/.config/git/config", {st_mode=S_IFREG|0644, st_size=1154, ...}) = 0
	access("/home/pks/.config/git/config", F_OK) = 0
	stat("/home/pks/.config/git/config", {st_mode=S_IFREG|0644, st_size=1154, ...}) = 0
	open("/home/pks/.config/git/config", O_RDONLY|O_CLOEXEC) = 3
	stat("/tmp/repo/.git/config", {st_mode=S_IFREG|0644, st_size=92, ...}) = 0
	open("/tmp/repo/.git/config", O_RDONLY|O_CLOEXEC) = 3
	stat("/home/pks/.gitconfig", 0x7ffd15c051f0) = -1 ENOENT (No such file or directory)
	stat("/home/pks/.config/git/config", {st_mode=S_IFREG|0644, st_size=1154, ...}) = 0
	open("/home/pks/.config/git/config", O_RDONLY|O_CLOEXEC) = 3
	stat("/tmp/repo/.git/config", {st_mode=S_IFREG|0644, st_size=92, ...}) = 0
	open("/tmp/repo/.git/config", O_RDONLY|O_CLOEXEC) = 3
	stat("/home/pks/.gitconfig", 0x7ffd15c05090) = -1 ENOENT (No such file or directory)
	stat("/home/pks/.config/git/config", {st_mode=S_IFREG|0644, st_size=1154, ...}) = 0
	open("/home/pks/.config/git/config", O_RDONLY|O_CLOEXEC) = 3
	stat("/tmp/repo/.git/config", {st_mode=S_IFREG|0644, st_size=92, ...}) = 0
	open("/tmp/repo/.git/config", O_RDONLY|O_CLOEXEC) = 3
	stat("/home/pks/.gitconfig", 0x7ffd15c05090) = -1 ENOENT (No such file or directory)
	stat("/home/pks/.config/git/config", {st_mode=S_IFREG|0644, st_size=1154, ...}) = 0
	open("/home/pks/.config/git/config", O_RDONLY|O_CLOEXEC) = 3
	stat("/tmp/repo/.git/config", {st_mode=S_IFREG|0644, st_size=92, ...}) = 0
	open("/tmp/repo/.git/config", O_RDONLY|O_CLOEXEC) = 3
	stat("/home/pks/.gitconfig", 0x7ffd15c05090) = -1 ENOENT (No such file or directory)
	stat("/home/pks/.config/git/config", {st_mode=S_IFREG|0644, st_size=1154, ...}) = 0
	open("/home/pks/.config/git/config", O_RDONLY|O_CLOEXEC) = 3

With the change, we only do stats for those files and open them a
single time, only:

	$ strace lg2 for-each-ref |& grep config
	access("/home/pks/.gitconfig", F_OK)    = -1 ENOENT (No such file or directory)
	access("/home/pks/.config/git/config", F_OK) = 0
	access("/etc/gitconfig", F_OK)          = -1 ENOENT (No such file or directory)
	stat("/tmp/repo/.git/config", {st_mode=S_IFREG|0644, st_size=92, ...}) = 0
	access("/tmp/repo/.git/config", F_OK)   = 0
	stat("/tmp/repo/.git/config", {st_mode=S_IFREG|0644, st_size=92, ...}) = 0
	stat("/tmp/repo/.git/config", {st_mode=S_IFREG|0644, st_size=92, ...}) = 0
	open("/tmp/repo/.git/config", O_RDONLY|O_CLOEXEC) = 3
	stat("/home/pks/.gitconfig", 0x7ffe70540d20) = -1 ENOENT (No such file or directory)
	access("/home/pks/.gitconfig", F_OK)    = -1 ENOENT (No such file or directory)
	stat("/home/pks/.config/git/config", {st_mode=S_IFREG|0644, st_size=1154, ...}) = 0
	access("/home/pks/.config/git/config", F_OK) = 0
	stat("/home/pks/.config/git/config", {st_mode=S_IFREG|0644, st_size=1154, ...}) = 0
	stat("/home/pks/.config/git/config", {st_mode=S_IFREG|0644, st_size=1154, ...}) = 0
	open("/home/pks/.config/git/config", O_RDONLY|O_CLOEXEC) = 3
	stat("/tmp/repo/.git/config", {st_mode=S_IFREG|0644, st_size=92, ...}) = 0
	stat("/home/pks/.gitconfig", 0x7ffe70540ca0) = -1 ENOENT (No such file or directory)
	stat("/home/pks/.gitconfig", 0x7ffe70540c80) = -1 ENOENT (No such file or directory)
	stat("/home/pks/.config/git/config", {st_mode=S_IFREG|0644, st_size=1154, ...}) = 0
	stat("/tmp/repo/.git/config", {st_mode=S_IFREG|0644, st_size=92, ...}) = 0
	stat("/home/pks/.gitconfig", 0x7ffe70540b40) = -1 ENOENT (No such file or directory)
	stat("/home/pks/.gitconfig", 0x7ffe70540b20) = -1 ENOENT (No such file or directory)
	stat("/home/pks/.config/git/config", {st_mode=S_IFREG|0644, st_size=1154, ...}) = 0
	stat("/tmp/repo/.git/config", {st_mode=S_IFREG|0644, st_size=92, ...}) = 0
	stat("/home/pks/.gitconfig", 0x7ffe70540b40) = -1 ENOENT (No such file or directory)
	stat("/home/pks/.gitconfig", 0x7ffe70540b20) = -1 ENOENT (No such file or directory)
	stat("/home/pks/.config/git/config", {st_mode=S_IFREG|0644, st_size=1154, ...}) = 0
	stat("/tmp/repo/.git/config", {st_mode=S_IFREG|0644, st_size=92, ...}) = 0
	stat("/home/pks/.gitconfig", 0x7ffe70540b40) = -1 ENOENT (No such file or directory)
	stat("/home/pks/.gitconfig", 0x7ffe70540b20) = -1 ENOENT (No such file or directory)
	stat("/home/pks/.config/git/config", {st_mode=S_IFREG|0644, st_size=1154, ...}) = 0

The following benchmark has been performed with and without the
stat cache in a best-of-ten run:

```

int lg2_repro(git_repository *repo, int argc, char **argv)
{
	git_config *cfg;
	int32_t dummy;
	int i;

	UNUSED(argc);
	UNUSED(argv);

	check_lg2(git_repository_config(&cfg, repo),
			"Could not obtain config", NULL);

	for (i = 1; i < 100000; ++i)
		git_config_get_int32(&dummy, cfg, "foo.bar");

	git_config_free(cfg);
	return 0;
}
```

Without stat cache:

	$ time lg2 repro
	real    0m1.528s
	user    0m0.568s
	sys     0m0.944s

With stat cache:

	$ time lg2 repro
	real    0m0.526s
	user    0m0.268s
	sys     0m0.258s

This benchmark shows a nearly three-fold performance improvement.

This change requires that we check our configuration stress tests
as we're now in fact becoming more racy. If somebody is writing a
configuration file at nearly the same time (there is a window of
100ns on Windows-based systems), then it might be that we realize
that this file has actually changed and thus may not re-read it.
This will only happen if either an external process is rewriting
the configuration file or if the same process has multiple
`git_config` structures pointing to the same time, where one of
both is being used to write and the other one is used to read
values.

Implement a new example that resembles git-config(1). Right now,
this example can both read and set configuration keys, only.

Depending on the platform and on build options, we may or may not
build libgit2 with support for nanoseconds when using `stat`
calls. It's currently unclear though whether sub-second stat
information is used at all.

Add feature info for this to tell at configure time whether it's
being used or not.

ci: build with ENABLE_WERROR on Windows

The function `git_win32__stack__set_aux_cb` expects the second parameter
to be a function callback of type `git_win32__stack__aux_cb_lookup`,
which expects a `size_t` parameter. In our test suite
trace::windows::stacktrace, we declare the callback with `unsigned int`
as parameter, though, causing a compiler warning.

Correct the parameter type to silence the warning.

In both `git_win32__stack_format` and `git_win32__stack`, we handle
buffer lengths via an integer variable. As we only ever pass buffer
sizes to it, this should be a `size_t` though to avoid loss of
precision. As we also use it to compare with other `size_t` variables,
this also silences signed/unsigned comparison warnings.

We use the `__LINE__` macro in several places throughout clar to allow
easier traceability when e.g. a test fails. While `__LINE__` is of type
`size_t`, the clar functions all accept an integer and thus may loose
precision. While unlikely that any file in our codebase will exceed a
linecount of `INT_MAX`, let's convert it anyway to silence any compiler
warnings.

When iterating over index entries, we store the indices in an unsigned
int. As the index entrycount is a `size_t` though, this may be a loss of
precision which a compiler might rightfully complain about.

Use `size_t` instead to fix any warnings.

When computing the progress, we perform some arithmetics that are
implicitly converting from `size_t` to `int`. In one case we're
calclulating a percentage, so we know that it should always be in the
range of [0,100] and thus we're fine. In the other case we convert from
bytes to kilobytes -- this should be stored in a `size_t` to avoid loss
of precision, even though it probably won't matter due to limited
download rates.

The memchr(3P) function expects a `size_t` as its last parameter, but we
do pass it an object size, which is of signed type `git_off_t`. As we
can be sure that the result will be non-negative, let's just cast the
parameter to a `size_t`.

When reallocating commit arrays in `opts_add_commit` and
`opts_add_refish`, respectively, we simply pass the const pointer to
`xrealloc`. As `xrealloc` expects a non-const pointer, though, this will
generate a warning with some compilers.

Cast away the constness to silence compilers.

Fix Regression: attr: Correctly load system attr file (on Windows)

There were no tests that verified that system-level gitattributes files
get handled correctly. In fact, we have recently introduced a regression
that caused us to abort if there was a system-level gitattributes file
available.

Add two tests that verify that we're able to handle system-level
gitattributes files. The test attr::repo::sysdir_with_session would've
failed without the fix to the described regression.

The function `git_attr_session__init` is currently only initializing
setting up the attribute's session key by incrementing the repo-global
key by one. Most notably, all other members of the `git_attr_session`
struct are not getting initialized at all. So if one is to allocate a
session on the stack and then calls `git_attr_session__init`, the
session will still not be fully initialized. We have fared just fine
with that until now as all users of the function have allocated the
session structure as part of bigger structs with `calloc`, and thus its
contents have been zero-initialized implicitly already.

Fix this by explicitly zeroing out the session to enable allocation of
sessions on the stack.

Regression introduced in commit 5452e49f on PR #4967.

Signed-off-by: Sven Strickroth <email@cs-ware.de>

hash: fix missing error return on production builds

When no hash algorithm has been initialized in a given hash context,
then we will simply `assert` and not return a value at all. This works
just fine in debug builds, but on non-debug builds the assert will be
converted to a no-op and thus we do not have a proper return value.

Fix this by returning an error code in addition to the asserts.

Resolve static check warnings in example code

Using cppcheck on libgit2 sources indicated two warnings in
example code.

merge.c was reported as having a memory leak. Fix applied
was to `free()` memory pointed to by `parents`.

init.c was reported as having a null pointer dereference
on variable arg. Function 'usage' was being called with
a null variable. Changed supplied parameter to empty string.

Multiple hash algorithms

More documentation

Incomplete commondir support

For example, https://git-scm.com/docs/gitrepository-layout says:

    info
    Additional information about the repository is recorded in this directory.
    This directory is ignored if $GIT_COMMON_DIR is set
    and "$GIT_COMMON_DIR/info" will be used instead.

So when looking for `info/attributes`, we need to check the commondir first,
or fallback to "our" `info/attributes`.

As with the preceding commit, the ignore code tries to load code from
info/exclude, and we fail to ignore a non-existent file here.

If creating a repository without a common directory (e.g. by
using `git_repository_new`), then `git_repository_item_path` will
return `GIT_ENOTFOUND` for every file that's usually located in
this directory. While we do not care for this case when looking
up the "info/attributes" file, we fail to properly ignore these
errors when setting up or collecting attributes files. Thus, the
gitattributes lookup is broken and will only ever return
`GIT_ENOTFOUND`.

Fix this issue by properly ignoring `GIT_ENOTFOUND` returned by
`git_repository_item_path`.

The code in the `attr_setup` function is not really matching our
current coding style. Besides alignment issues, it's also hard to
see what functions calls depend on one another because they're
split up over multiple conditional statements.

Fix these issues by grouping together dependent function calls
and adjusting the alignment.

Build with -Werror's equivalent (/WX) on MSVC

Remove warnings

Re-run flaky tests

Our online tests are occasionally flaky since they hit real network
endpoints.  Re-run them up to 5 times if they fail, to allow us to
avoid having to fail the whole build.