[1/8] sparse-index: create expand_to_pattern_list()

Commit Message

Derrick Stolee May 16, 2022, 6:11 p.m. UTC

From: Derrick Stolee <[e-mail]>

This is the first change in a series to allow modifying the
sparse-checkout pattern set without expanding a sparse index to a full
one in the process. Here, we focus on the problem of expanding the
pattern set through a command like 'git sparse-checkout add <path>'
which needs to create new index entries for the paths now being written
to the worktree.

To achieve this, we need to be able to replace sparse directory entries
with their contained files and subdirectories. Once this is complete,
other code paths can discover those cache entries and write the
corresponding files to disk before committing the index.

We already have logic in ensure_full_index() that expands the index
entries, so we will use that as our base. Create a new method,
expand_to_pattern_list(), which takes a pattern list, but for now mostly
ignores it. The current implementation is only correct when the pattern
list is NULL as that does the same as ensure_full_index(). In fact,
ensure_full_index() is converted to a shim over
expand_to_pattern_list().

A future update will actually implement expand_to_pattern_list() to its
full capabilities. For now, it is created and documented.

Signed-off-by: Derrick Stolee <[e-mail]>
---
 sparse-index.c | 35 ++++++++++++++++++++++++++++++++---
 sparse-index.h | 14 ++++++++++++++
 2 files changed, 46 insertions(+), 3 deletions(-)

Comments

Victoria Dye May 16, 2022, 8:36 p.m. UTC | #1

Derrick Stolee via GitGitGadget wrote:
> From: Derrick Stolee <[e-mail]>
> 
> This is the first change in a series to allow modifying the
> sparse-checkout pattern set without expanding a sparse index to a full
> one in the process. Here, we focus on the problem of expanding the
> pattern set through a command like 'git sparse-checkout add <path>'
> which needs to create new index entries for the paths now being written
> to the worktree.
> 
> To achieve this, we need to be able to replace sparse directory entries
> with their contained files and subdirectories. Once this is complete,
> other code paths can discover those cache entries and write the
> corresponding files to disk before committing the index.
> 
> We already have logic in ensure_full_index() that expands the index
> entries, so we will use that as our base. Create a new method,
> expand_to_pattern_list(), which takes a pattern list, but for now mostly
> ignores it. The current implementation is only correct when the pattern
> list is NULL as that does the same as ensure_full_index(). In fact,
> ensure_full_index() is converted to a shim over
> expand_to_pattern_list().
> 
> A future update will actually implement expand_to_pattern_list() to its
> full capabilities. For now, it is created and documented.
> 
> Signed-off-by: Derrick Stolee <[e-mail]>
> ---
>  sparse-index.c | 35 ++++++++++++++++++++++++++++++++---
>  sparse-index.h | 14 ++++++++++++++
>  2 files changed, 46 insertions(+), 3 deletions(-)
> 
> diff --git a/sparse-index.c b/sparse-index.c
> index 8636af72de5..37c7df877a6 100644
> --- a/sparse-index.c
> +++ b/sparse-index.c
> @@ -248,19 +248,41 @@ static int add_path_to_index(const struct object_id *oid,
>  	return 0;
>  }
>  
> -void ensure_full_index(struct index_state *istate)
> +void expand_to_pattern_list(struct index_state *istate,
> +			      struct pattern_list *pl)

Hyper-nit: I don't think this is aligned (it's probably not worth fixing
unless you end up rerolling for something else).

>  {
>  	int i;
>  	struct index_state *full;
>  	struct strbuf base = STRBUF_INIT;
>  
> +	/*
> +	 * If the index is already full, then keep it full. We will convert
> +	 * it to a sparse index on write, if possible.
> +	 */
>  	if (!istate || !istate->sparse_index)
>  		return;
>  
> +	/*
> +	 * If our index is sparse, but our new pattern set does not use
> +	 * cone mode patterns, then we need to expand the index before we
> +	 * continue. A NULL pattern set indicates a full expansion to a
> +	 * full index.
> +	 */
> +	if (pl && !pl->use_cone_patterns)
> +		pl = NULL;
> +
>  	if (!istate->repo)
>  		istate->repo = the_repository;
>  
> -	trace2_region_enter("index", "ensure_full_index", istate->repo);
> +	/*
> +	 * A NULL pattern set indicates we are expanding a full index, so
> +	 * we use a special region name that indicates the full expansion.
> +	 * This is used by test cases, but also helps to differentiate the
> +	 * two cases.
> +	 */
> +	trace2_region_enter("index",
> +			    pl ? "expand_to_pattern_list" : "ensure_full_index",
> +			    istate->repo);
>  
>  	/* initialize basics of new index */
>  	full = xcalloc(1, sizeof(struct index_state));
> @@ -322,7 +344,14 @@ void ensure_full_index(struct index_state *istate)
>  	cache_tree_free(&istate->cache_tree);
>  	cache_tree_update(istate, 0);
>  
> -	trace2_region_leave("index", "ensure_full_index", istate->repo);
> +	trace2_region_leave("index",
> +			    pl ? "expand_to_pattern_list" : "ensure_full_index",
> +			    istate->repo);
> +}
> +
> +void ensure_full_index(struct index_state *istate)
> +{
> +	expand_to_pattern_list(istate, NULL);
>  }
>  
>  void ensure_correct_sparsity(struct index_state *istate)
> diff --git a/sparse-index.h b/sparse-index.h
> index 633d4fb7e31..037b541f49d 100644
> --- a/sparse-index.h
> +++ b/sparse-index.h
> @@ -23,4 +23,18 @@ void expand_to_path(struct index_state *istate,
>  struct repository;
>  int set_sparse_index_config(struct repository *repo, int enable);
>  
> +struct pattern_list;
> +
> +/**
> + * Scan the given index and compare its entries to the given pattern list.
> + * If the index is sparse and the pattern list uses cone mode patterns,
> + * then modify the index to contain the all of the file entries within that
> + * new pattern list. This expands sparse directories only as far as needed.
> + *
> + * If the pattern list is NULL or does not use cone mode patterns, then the
> + * index is expanded to a full index.
> + */
> +void expand_to_pattern_list(struct index_state *istate,
> +			      struct pattern_list *pl);
> +
>  #endif

Derrick Stolee May 16, 2022, 8:49 p.m. UTC | #2

On 5/16/2022 4:36 PM, Victoria Dye wrote:
> Derrick Stolee via GitGitGadget wrote:

>> -void ensure_full_index(struct index_state *istate)
>> +void expand_to_pattern_list(struct index_state *istate,
>> +			      struct pattern_list *pl)
> 
> Hyper-nit: I don't think this is aligned (it's probably not worth fixing
> unless you end up rerolling for something else).

You're right. When I saw this I thought it was just the
"off by one" issue when patches have a "+" in the beginning,
but it's actually the backwards order. Thanks for catching it.

-Stolee

Patch

diff --git a/sparse-index.c b/sparse-index.c
index 8636af72de5..37c7df877a6 100644
--- a/sparse-index.c
+++ b/sparse-index.c
@@ -248,19 +248,41 @@  static int add_path_to_index(const struct object_id *oid,
 	return 0;
 }
 
-void ensure_full_index(struct index_state *istate)
+void expand_to_pattern_list(struct index_state *istate,
+			      struct pattern_list *pl)
 {
 	int i;
 	struct index_state *full;
 	struct strbuf base = STRBUF_INIT;
 
+	/*
+	 * If the index is already full, then keep it full. We will convert
+	 * it to a sparse index on write, if possible.
+	 */
 	if (!istate || !istate->sparse_index)
 		return;
 
+	/*
+	 * If our index is sparse, but our new pattern set does not use
+	 * cone mode patterns, then we need to expand the index before we
+	 * continue. A NULL pattern set indicates a full expansion to a
+	 * full index.
+	 */
+	if (pl && !pl->use_cone_patterns)
+		pl = NULL;
+
 	if (!istate->repo)
 		istate->repo = the_repository;
 
-	trace2_region_enter("index", "ensure_full_index", istate->repo);
+	/*
+	 * A NULL pattern set indicates we are expanding a full index, so
+	 * we use a special region name that indicates the full expansion.
+	 * This is used by test cases, but also helps to differentiate the
+	 * two cases.
+	 */
+	trace2_region_enter("index",
+			    pl ? "expand_to_pattern_list" : "ensure_full_index",
+			    istate->repo);
 
 	/* initialize basics of new index */
 	full = xcalloc(1, sizeof(struct index_state));
@@ -322,7 +344,14 @@  void ensure_full_index(struct index_state *istate)
 	cache_tree_free(&istate->cache_tree);
 	cache_tree_update(istate, 0);
 
-	trace2_region_leave("index", "ensure_full_index", istate->repo);
+	trace2_region_leave("index",
+			    pl ? "expand_to_pattern_list" : "ensure_full_index",
+			    istate->repo);
+}
+
+void ensure_full_index(struct index_state *istate)
+{
+	expand_to_pattern_list(istate, NULL);
 }
 
 void ensure_correct_sparsity(struct index_state *istate)
diff --git a/sparse-index.h b/sparse-index.h
index 633d4fb7e31..037b541f49d 100644
--- a/sparse-index.h
+++ b/sparse-index.h
@@ -23,4 +23,18 @@  void expand_to_path(struct index_state *istate,
 struct repository;
 int set_sparse_index_config(struct repository *repo, int enable);
 
+struct pattern_list;
+
+/**
+ * Scan the given index and compare its entries to the given pattern list.
+ * If the index is sparse and the pattern list uses cone mode patterns,
+ * then modify the index to contain the all of the file entries within that
+ * new pattern list. This expands sparse directories only as far as needed.
+ *
+ * If the pattern list is NULL or does not use cone mode patterns, then the
+ * index is expanded to a full index.
+ */
+void expand_to_pattern_list(struct index_state *istate,
+			      struct pattern_list *pl);
+
 #endif