Currently, parsing objects is strictly tied to having an ODB object
available. This makes it hard to parse an object when all that is
available is its raw object and size. Furthermore, hacking around that
limitation by directly creating an ODB structure either on stack or on
heap does not really work that well due to ODB objects being reference
counted and then automatically free'd when reaching a reference count of
zero.

Implement a function `git_tag__parse_raw` to parse a tag object from a
pair of `data` and `size`.

Currently, parsing objects is strictly tied to having an ODB object
available. This makes it hard to parse an object when all that is
available is its raw object and size. Furthermore, hacking around that
limitation by directly creating an ODB structure either on stack or on
heap does not really work that well due to ODB objects being reference
counted and then automatically free'd when reaching a reference count of
zero.

Implement a function `git_commit__parse_raw` to parse a commit object
from a pair of `data` and `size`.

Currently, parsing objects is strictly tied to having an ODB object
available. This makes it hard to parse an object when all that is
available is its raw object and size. Furthermore, hacking around that
limitation by directly creating an ODB structure either on stack or on
heap does not really work that well due to ODB objects being reference
counted and then automatically free'd when reaching a reference count of
zero.

In some occasions parsing raw objects without touching the ODB
is actually recuired, though. One use case is for example object
verification, where we want to assure that an object is valid before
inserting it into the ODB or writing it into the git repository.

Asa first step towards that, introduce a distinction between raw and ODB
objects for blobs. Creation of ODB objects stays the same by simply
using `git_blob__parse`, but a new function `git_blob__parse_raw` has
been added that creates a blob from a pair of data and size. By setting
a new flag inside of the blob, we can now distinguish whether it is a
raw or ODB object now and treat it accordingly in several places.

Note that the blob data passed in is not being copied. Because of that,
callers need to make sure to keep it alive during the blob's life time.
This is being used to avoid unnecessarily increasing the memory
footprint when parsing largish blobs.

Going forward, we will have to change how blob sizes are calculated
based on whether the blob is a cahed object part of the ODB or not. In
order to not have to distinguish between those two object types
repeatedly when accessing the blob's data or size, encapsulate all
existing direct uses of those fields by instead using
`git_blob_rawcontent` and `git_blob_rawsize`.

The `git_walk_objects` structure is currently only being used inside of
the pack-objects.c file, but being declared in its header. This has
actually been the case since its inception in 04a36fef (pack-objects:
fill a packbuilder from a walk, 2014-10-11) and has never really
changed.

Move the struct declaration into pack-objects.c to improve code
encapsulation.

Fix last references to deprecated git_buf_free

revwalk: avoid walking the entire history when output is unsorted

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

Add mailmap support.

tree: remove unused functions

Link `mbedTLS` libraries in when `SHA1_BACKEND` == "mbedTLS"

editorconfig: allow trailing whitespace in markdown

Also matches git.

This matches git.

Not that it matters much anyway but...