Re: [PATCH v2 1/2] read-cache: factor out get_sha1_from_index() helper

[Duy Nguyen <pclouds@gmail.com>]

On Wed, Oct 12, 2016 at 8:47 PM,  <tboegi@web.de> wrote:
> From: Torsten Bögershausen <tboegi@web.de>
>
> Factor out the retrieval of the sha1 for a given path in
> read_blob_data_from_index() into the function get_sha1_from_index().
>
> This will be used in the next commit, when convert.c can do the
> analyze for "text=auto" without slurping the whole blob into memory
> at once.
>
> Add a wrapper definition get_sha1_from_cache().
>
> Signed-off-by: Torsten Bögershausen <tboegi@web.de>
> ---
>  cache.h      |  3 +++
>  read-cache.c | 29 ++++++++++++++++++-----------
>  2 files changed, 21 insertions(+), 11 deletions(-)
>
> diff --git a/cache.h b/cache.h
> index 1604e29..04de209 100644
> --- a/cache.h
> +++ b/cache.h
> @@ -380,6 +380,7 @@ extern void free_name_hash(struct index_state *istate);
>  #define unmerge_cache_entry_at(at) unmerge_index_entry_at(&the_index, at)
>  #define unmerge_cache(pathspec) unmerge_index(&the_index, pathspec)
>  #define read_blob_data_from_cache(path, sz) read_blob_data_from_index(&the_index, (path), (sz))
> +#define get_sha1_from_cache(path)  get_sha1_from_index (&the_index, (path))
>  #endif
>
>  enum object_type {
> @@ -1089,6 +1090,8 @@ static inline void *read_sha1_file(const unsigned char *sha1, enum object_type *
>         return read_sha1_file_extended(sha1, type, size, LOOKUP_REPLACE_OBJECT);
>  }
>
> +const unsigned char *get_sha1_from_index(struct index_state *istate, const char *path);
> +
>  /*
>   * This internal function is only declared here for the benefit of
>   * lookup_replace_object().  Please do not call it directly.
> diff --git a/read-cache.c b/read-cache.c
> index 38d67fa..5a1df14 100644
> --- a/read-cache.c
> +++ b/read-cache.c
> @@ -2290,13 +2290,27 @@ int index_name_is_other(const struct index_state *istate, const char *name,
>
>  void *read_blob_data_from_index(struct index_state *istate, const char *path, unsigned long *size)
>  {
> -       int pos, len;
> +       const unsigned char *sha1;
>         unsigned long sz;
>         enum object_type type;
>         void *data;
>
> -       len = strlen(path);
> -       pos = index_name_pos(istate, path, len);
> +       sha1 = get_sha1_from_index(istate, path);
> +       if (!sha1)
> +               return NULL;
> +       data = read_sha1_file(sha1, &type, &sz);
> +       if (!data || type != OBJ_BLOB) {
> +               free(data);
> +               return NULL;
> +       }
> +       if (size)
> +               *size = sz;
> +       return data;
> +}
> +
> +const unsigned char *get_sha1_from_index(struct index_state *istate, const char *path)

Let's try to embrace struct object_id to make our lives easier when
the time comes to convert to a new hash algorithm by returning struct
object_id * here instead of the internal hash.

> +{
> +       int pos = index_name_pos(istate, path, strlen(path));
>         if (pos < 0) {
>                 /*
>                  * We might be in the middle of a merge, in which
> @@ -2312,14 +2326,7 @@ void *read_blob_data_from_index(struct index_state *istate, const char *path, un
>         }
>         if (pos < 0)
>                 return NULL;
> -       data = read_sha1_file(istate->cache[pos]->oid.hash, &type, &sz);
> -       if (!data || type != OBJ_BLOB) {
> -               free(data);
> -               return NULL;
> -       }
> -       if (size)
> -               *size = sz;
> -       return data;
> +       return istate->cache[pos]->oid.hash;
>  }
>
>  void stat_validity_clear(struct stat_validity *sv)
-- 
Duy