Don't try to update anything if there are no heads to update. This
saves us from trying to look into a fetch refspec when there is none.

A better fix for compatibility with git when using remotes without
refspecs is still needed, but this stops us from segfaulting.

Keep the data around until free, as expected by our own fetch example

OpenBSD & sparc64 fixes

Mixing int and size_t through pointers leads to problems
in big-endian machines.

commit: correctly detect the start of the commit message

The end of the header is signaled by to consecutive LFs and the commit
message starts immediately after. Jumping over LFs at the start of the
message is a bug and leads to creating different commits if
when rebuilding history.

This also fixes an empty commit message being returned as "\n".

dec refcount on refdb instead of always freeing

Branch upstream configuration

Add functions to set and unset the upstream configuration to
complement the getter we already have.

Correctly return matched pathspec when passing "*" or "."

I also moved all tests related to notifying in their own file.

Reduce the number of unnecessary objects in pushed packs

Submodule diff tests and fixes

This adds tests for diffs with submodules in them and (perhaps
unsurprisingly) requires further fixes to be made.  Specifically,
this fixes:

- when considering if a submodule is dirty in the workdir, it was
  being treated as dirty even if only the index was dirty.
- git_diff_patch_to_str (and git_diff_patch_print) were "printing"
  the headers for files (and submodules) that were unmodified or
  had no meaningful content.
- added comment to previous fix and removed unneeded parens.

Fix submodule dirty states not showing if submodules comes before files, or there are only dirty submodules but no changed files

GIT_DIFF_PATCH_DIFFABLE was not set, so the diff content was not shown

When submodule is dirty, the hash may be the same, but the length is different because -dirty is appended

We can therefore compare the length or hash

Updated link to Haskell bindings

The old one hasn't been updated in a long time. This one is current.

This test file could probably be improved by a framework like
the one in git.git:t/, or by using a language like Python instead
of shell.

The other examples would benefit from tests too.  Probably best
to settle on a framework to write them in, then add more tests.

Signed-off-by: Greg Price <price@mit.edu>

This demonstrates parts of the interface for specifying revisions that
Git users are familiar with from 'git rev-list', 'git log', and other
Git commands.  A similar query interface is used in out-of-core
command-line programs that browse a Git repo (like 'tig'), and may be
useful for an 'advanced search' interface in GUI or web applications.

In this version, we parse all the query modifiers we can support with
the existing logic in revwalk: basic include/exclude commits, and the
ordering flags.  More logic will be required to support '--grep',
'--author', the pickaxe '-S', etc.

Signed-off-by: Greg Price <price@mit.edu>

All the hard work is already in revparse.

Signed-off-by: Greg Price <price@mit.edu>

Signed-off-by: Greg Price <price@mit.edu>

Fix the general.c example to run against testrepo.git

Fixes #1455

Properly GIT_EXPORT git_reference__alloc

branch: Fix git_branch_create() documentation

Avoid pre-Win7 WinHTTP self-redirect quirk

Signed-off-by: Greg Price <price@mit.edu>

The purported command output was already inaccurate, as the refs
aren't where it shows.  In any event, the labels a reader of this
file really needs are the indices used in commit_sorting_*, to make
it possible to understand them by referring directly from those
arrays to the diagram rather than from the index arrays, to commit_ids,
to the diagram.  Add those.

Signed-off-by: Greg Price <price@mit.edu>

Signed-off-by: Greg Price <price@mit.edu>