Test SSH in travis

fileops: stat() before open()ing in git_futils_readbuffer_updated()

Do not use the "experimental" lookup mode

Set up the ssh credentials so we are able to talk to localhost and
issue git commands. Move to use a script, as the command list is
getting somewhat long.

While here, delay installing valgrind until we need it, as it and its
dependencies are by far the largest downloads and this allows us to
start compiling (and failing) faster and we only incur this cost when
the test suite runs successfully.

Speed up build under MSVC

Bigger buffer for utf-8 parsing in win32

This reverts refactoring done in 13224ea4
that introduces a performance regression for NFS when reading files that
don't exist. open() forces a cache invalidation on NFS, while stat()ing a
file just uses the cache and is very quick.

To give a specific example, say you have a repo with a thousand packed
refs. Before this change, looking up every single one ould incur a thousand
slow open() calls. With this change, it's a thousand fast stat() calls.

This is just a bunch of small fixes that I noticed while looking
at the UTF8 and UTF16 path stuff.  It fixes a slowdown in looking
for an empty directory (not exiting loop asap), makes the dir name
in the git__DIR structure be a GIT_FLEX_ARRAY to save an allocation,
and fixes some slightly odd assumptions in the cl_getenv helper.

SSH username fixes

With the current code, running 'cmake .' in an already-configured
directory causes the removal of ssh flags passed to the compiler,
making it impossible to build with ssh support but by removing CMake's
cache.

Remove the check for LIBSSH2_LIBRARY and let CMake do the right thing
wrt finding the library.

Key-based authentication also needs an username, so include it in each
one.

Also stop assuming a default username of "git" in the ssh transport
which has no business making such a decision.

By the time we recognise this as an ambiguous id, the object's data
has been loaded into memory. Free it when returning EABMIGUOUS.

Fix issue 1766 - bugs in managing ignore file lists

Fixes to safely reading the index

This just cleans up the improved logic for popping ignore dirs
and documents why the complex behavior is needed.

The routines to push and pop ignore files while traversing a
directory had some issues. In particular, setting up the initial
list would sometimes push an ignore file before it ought to be
applied if the starting path was a directory containing an ignore
file. Also, the pop function was not always matching the right
part of the path and would fail to pop ignores from the list in
some cases.

This adds some tests that exercise a particular problematic case
and then fixes the problems that I could find related to this.

At some point, I'd like to isolate this ignore rule management
code and rewrite it, but that's a larger project and right now,
I'll opt to just try to fix the broken behaviors.

Revert PR #1462 and provide alternative fix

This rolls back the changes to fnmatch parsing from commit
2e40a60e except for the tests
that were added.  Instead this adds couple of new flags that can
be passed in when attempting to parse an fnmatch pattern.  Also,
this changes the pathspec match logic to special case matching a
filename with a '!' prefix against a negative pattern.

This fixes the build.

Add rename from rewrites to status

status: fix handling of filenames with special prefixes

config: allow setting  empty string as value

`git_config_set_string(config, "config.section", "")` fails when
escaping the value.

The buffer in `escape_value` is allocated without NULL-termination. And
in case of empty string 0 is passed for buffer size in `git_buf_grow`.

`git_buf_detach` returns NULL when the allocated size is 0 and that
leads to an error return in `GITERR_CHECK_ALLOC` called after
`escape_value`

The change in `config_file.c` was suggested by Russell Belfer <rb@github.com>

Avoid wrapping around extension size when reading, avoid walking off
the end of the buffer when reading names.