We cannot assume that non-bare repositories have an index file, because
'git index' doesn't create it by default.

Signed-off-by: Vicent Marti <tanoku@gmail.com>

Commit object must be internally free'd after each parse attempt, even
it fails.

Signed-off-by: Vicent Marti <tanoku@gmail.com>

The internal contents of the blob were being free'd but not the blob
object itself.

Signed-off-by: Vicent Marti <tanoku@gmail.com>

Actually add files to the index by creating their corresponding blob and
storing it on the repository, then getting the hash and updating the
index file.

Signed-off-by: Vicent Marti <tanoku@gmail.com>

Note to self: don't be stupid

Signed-off-by: Vicent Marti <tanoku@gmail.com>

Blob files can now be loaded from the repository like all the other base
Git types.

Signed-off-by: Vicent Marti <tanoku@gmail.com>

Several private methods of the Index API are now public, including the
methods to remove, get and add index entries.

All the methods only take an integer value for the position of the entry
to get/remove. To get or remove entries based on their path names, look
them up first using the git_index_find method.

Signed-off-by: Vicent Marti <tanoku@gmail.com>

Old descriptions have been updated and new ones have been added for the
'git_strerror' function.

Signed-off-by: Vicent Marti <tanoku@gmail.com>

All initialization functions now return error codes instead of pointers.
Error codes are now properly propagated on most functions. Several new
and more specific error codes have been added in common.h

Signed-off-by: Vicent Marti <tanoku@gmail.com>

Added -fPIC (position-independent code) to the EXTRA_CFLAGS var in the
Makefile. Required in x64 when building the shared library.

Signed-off-by: Vicent Marti <tanoku@gmail.com>

The constructor to git_repository is now called

	'git_repository_open(path)'

and takes a path to a git repository instead of an existing ODB object.
Unit tests have been updated accordingly and the two test repositories
have been merged into one.

Signed-off-by: Vicent Marti <tanoku@gmail.com>

Issue 9 on the tracker. The commit object getters for in-memory objects
were trying to parse an inexistant on-disk object when one of the commit
attributes which were still not set was queried.

We now return a NULL value when this happens.

Signed-off-by: Vicent Marti <tanoku@gmail.com>

Before changing the attributes of a commit, make sure that the internal
status is consistent with the one in the repository.

Signed-off-by: Vicent Marti <tanoku@gmail.com>

You can know access the owning repository of any existing object, or the
repository on which a revision walker is working on.

Signed-off-by: Vicent Marti <tanoku@gmail.com>

Test the new method by loading all the objects in the sample ODB with a
full-read and a header-only read, and comparing the types and sizes.

Signed-off-by: Vicent Marti <tanoku@gmail.com>

As requested, git_odb_read_header looks up an object on the ODB, but loads
only the header information (type & size) without loading any of the
actual file contents in memory.

It is significantly faster than doing a git_odb_read if you only need an
object's information and not its contents.

Signed-off-by: Vicent Marti <tanoku@gmail.com>

String mememory is now managed in a much more sane manner.

Fixes include:

	- git_person email and name is no longer limited to 64 characters
	- git_tree_entry filename is no longer limited to 255 characters
	- raw objects are properly opened & closed the minimum amount of
	times required for parsing
	- unit tests no longer leak
	- removed 5 other misc memory leaks as reported by Valgrind
	- tree writeback no longer segfaults on rare ocassions

The git_person struct is no longer public. It is now managed by the
library, and getter methods are in place to access its internal
attributes.

Signed-off-by: Vicent Marti <tanoku@gmail.com>

In particular, msvc complains thus:

    t0603-sort.c(23) : warning C4244: 'function' : conversion from \
        'time_t' to 'unsigned int', possible loss of data

Note that msvc, by default, defines time_t as a 64-bit type, whereas
srand() is expecting an (32-bit) unsigned int. In order to suppress
the warning, we simply cast the return value of the time() function
call to 'unsigned int'.

Signed-off-by: Ramsay Jones <ramsay@ramsay1.demon.co.uk>

Since commit 70aab459, the msvc and MinGW builds have relied on
the built-in implementation of ntohl() and htonl(), rather than
linking the wsock32 library. The new index manipulation code now
calls ntohs()/htons() in addition to ntohl()/htonl(), so we need
to provide a built-in implementation of the 16-bit functions.

Signed-off-by: Ramsay Jones <ramsay@ramsay1.demon.co.uk>

will generate documenation and not hide them.

Signed-off-by: Benjamin C Meyer <ben@meyerhome.net>

Signed-off-by: Benjamin C Meyer <ben@meyerhome.net>

Signed-off-by: Benjamin C Meyer <ben@meyerhome.net>

The tree array wasn't being initialized when instantiating a tree object
in memory instead of loading it from disk.

New unit tests added to check for the problem.

Signed-off-by: Vicent Marti <tanoku@gmail.com>

Basic write-back & in-memory editing for objects is now tested in t0403
(commits), t0802 (tags) and t0902 (trees).

Add new helper functions in test_helpers.c to remove the loose objects
created when doing write-back tests.

Signed-off-by: Vicent Marti <tanoku@gmail.com>

Tag files can now be created and modified in-memory (all the setter
methods have been implemented), and written back to disk using the
generic git_object_write() method.

Signed-off-by: Vicent Marti <tanoku@gmail.com>

git_tree_entry_byname was dereferencing a NULL pointer when the searched
file couldn't be found on the tree.

New test cases have been added to check for entry access methods.

Signed-off-by: Vicent Marti <tanoku@gmail.com>

All the setter methods for git_tree have been added, including the
setters for attributes on each git_tree_entry and methods to add/remove
entries of the tree.

Modified trees and trees created in-memory from scratch can be written
back to the repository using git_object_write().

Signed-off-by: Vicent Marti <tanoku@gmail.com>

All repository objects can now be created from scratch in memory using
either the git_object_new() method, or the corresponding git_XXX_new()
for each object.

So far, only git_commits can be written back to disk once created in
memory.

Signed-off-by: Vicent Marti <tanoku@gmail.com>

All the required git_commit_set_XXX methods have been implemented; all
the attributes of a commit object can now be modified in-memory.

The new method git_object_write() automatically writes back the
in-memory changes of any object to the repository. So far it only
supports git_commit objects.

Signed-off-by: Vicent Marti <tanoku@gmail.com>

The new 'git__source_printf' does an overflow-safe printf on a source
bfufer.

The new 'git__source_write' does an overflow-safe byte write on a source
buffer.

Signed-off-by: Vicent Marti <tanoku@gmail.com>

The 'git_obj' structure is now called 'git_rawobj', since
it represents a raw object read from the ODB.

The 'git_repository_object' structure is now called 'git_object',
since it's the base object class for all objects.

Signed-off-by: Vicent Marti <tanoku@gmail.com>

git_repository_object has now several internal methods to write back the
object information in the repository.

- git_repository__dbo_prepare_write()
	Prepares the DBO object to be modified

- git_repository__dbo_write()
	Writes new bytes to the DBO object

- git_repository__dbo_writeback()
	Writes back the changes to the repository

Signed-off-by: Vicent Marti <tanoku@gmail.com>

Added several methods to access:

	- The ODB behind a repo
	- The SHA1 id behind a generic repo object
	- The type of a generic repo object

Signed-off-by: Vicent Marti <tanoku@gmail.com>