Conflicts:

	src/fileops.c

Fixed a Windows TO-DO in the prettifying functions.

Fileops:retrieve_path_root_offset is now named gitfo_retrieve_path_root_offset (like other public functions). Added platform specific directory separator definition.

Fix fake wstream write

Fixed some error messages related to searching objects from a short oid. Fixed forgot to check that prefix length is greater than minimum prefix length in read_unique_short_oid method from pack backend.

Deleted unused method git_cached_object_match, since we do not explore the cache when searching objects from a short oid.

Changed return value of git_oid_match to be consistent with the other compare methods (0 means oids match). Added method to compare prefixes of hex formatted oids.

Added a GIT_OID_MINPREFIXLEN constant to define the minimum length allowed for oid prefixes (set to 4, like in git). Consequently updated some object lookup methods and their documentation.

Implemented find_unique_short_oid for pack backend, based on git sha1 lookup method;
finding an object given its full oid is just a particular case of searching
the unique object matching an oid prefix (short oid).

Added git_odb_read_unique_short_oid, which iterates over all the backends to
find and read the unique object matching the given oid prefix.

Added a git_object_lookup_short_oid method to find the unique object in
the repository matching a given oid prefix : it generalizes git_object_lookup
which now does nothing but calls git_object_lookup_short_oid.

Added error for ambiguous oid prefixes. Added methods to compare the first nth hexadecimal characters (i.e. packets of 4 bits) of OIDs.

Added a read_unique_short_oid method to backends, to make it possible to find objects from sha1 prefixes in the future. Default implementations throw GIT_ENOTIMPLEMENTED for strict prefixes (i.e. length < GIT_OID_HEXSZ).

Fix tag and signature parsing

Fix typos

test_lib.c: flush stdout after every test-run

Plug a leak in the index unmerged entries vector

Config bugfix

Add git_repository_is_bare() accessor

A TREE extension with an entry count of -1 means that it was
invalidated and we should ignore it. Do so instead of returning an
error.

This fixes issue #202

Signed-off-by: Carlos Martín Nieto <cmn@elego.de>

There are two reasons why read_tree_internal might return a NULL
tree. The first one is a corrupt index, but the second one is an
invalidated TREE extension. Up to now, its only way to communicate
with its caller was through the return value being NULL or not.

Allow read_tree_internal to report its exit status independently from
the tree pointer.

Signed-off-by: Carlos Martín Nieto <cmn@elego.de>

The `git_repository_index` call now returns a brand new index that must
be manually free'd.

Before this commit, malformed tag and signature were considered as
valid by the parser. See the test t3800-mktag.sh of git to see example
of malformed tag and signature.

Signed-off-by: Carlos Martín Nieto <cmn@elego.de>

Signed-off-by: Carlos Martín Nieto <cmn@elego.de>

Signed-off-by: Carlos Martín Nieto <cmn@elego.de>

Signed-off-by: Carlos Martín Nieto <cmn@elego.de>

Nothing is allowed betwen the closing quotation mark and the ] so
return an error if there is.

Signed-off-by: Carlos Martín Nieto <cmn@elego.de>

Also free the subsection if we find too many quotes

Signed-off-by: Carlos Martín Nieto <cmn@elego.de>

If parse_section_header{,_ext} return an error, current_section
doesn't get allocated. Set it to NULL after freeing so we don't try to
free it again.

This fixes part 2-2 of Issue #210.

Signed-off-by: Carlos Martín Nieto <cmn@elego.de>

Simplify cfg_readline and at the same time fix it so that it does
really ignore empty lines.

This fixes point 2-1 of Issue #210

Signed-off-by: Carlos Martín Nieto <cmn@elego.de>

On error, it would free the configuration object even though it didn't
own that memory, which would cause a double-free.

This fixes the first part of Issue #210

Signed-off-by: Carlos Martín Nieto <cmn@elego.de>

Signed-off-by: Carlos Martín Nieto <cmn@elego.de>

Make sure the user immediately sees the feedback, '.' or 'F', for a
test. If it's only in the buffer, it may gets "lost" in case of error.

Signed-off-by: schu <schu-github@schulog.org>