summary refs log tree commit diff
path: root/chunk-format.h
diff options
context:
space:
mode:
authorDerrick Stolee <dstolee@microsoft.com>2021-02-18 14:07:34 +0000
committerJunio C Hamano <gitster@pobox.com>2021-02-18 13:38:16 -0800
commit5f0879f54b1f5cda348528a49af57a9c3fd620f9 (patch)
tree9931f4a58baaf254e8e7bb1f6d96c3469c13f476 /chunk-format.h
parent63a8f0e9b9d9ce636738094391619c35856f7665 (diff)
chunk-format: create read chunk API
Add the capability to read the table of contents, then pair the chunks
with necessary logic using read_chunk_fn pointers. Callers will be added
in future changes, but the typical outline will be:

 1. initialize a 'struct chunkfile' with init_chunkfile(NULL).
 2. call read_table_of_contents().
 3. for each chunk to parse,
    a. call pair_chunk() to assign a pointer with the chunk position, or
    b. call read_chunk() to run a callback on the chunk start and size.
 4. call free_chunkfile() to clear the 'struct chunkfile' data.

We are re-using the anonymous 'struct chunkfile' data, as it is internal
to the chunk-format API. This gives it essentially two modes: write and
read. If the same struct instance was used for both reads and writes,
then there would be failures.

Helped-by: Junio C Hamano <gitster@pobox.com>
Signed-off-by: Derrick Stolee <dstolee@microsoft.com>
Signed-off-by: Junio C Hamano <gitster@pobox.com>
Diffstat (limited to 'chunk-format.h')
-rw-r--r--chunk-format.h47
1 files changed, 47 insertions, 0 deletions
diff --git a/chunk-format.h b/chunk-format.h
index ce598b66d9..9ccbe00377 100644
--- a/chunk-format.h
+++ b/chunk-format.h
@@ -8,6 +8,20 @@ struct chunkfile;
 
 #define CHUNK_TOC_ENTRY_SIZE (sizeof(uint32_t) + sizeof(uint64_t))
 
+/*
+ * Initialize a 'struct chunkfile' for writing _or_ reading a file
+ * with the chunk format.
+ *
+ * If writing a file, supply a non-NULL 'struct hashfile *' that will
+ * be used to write.
+ *
+ * If reading a file, use a NULL 'struct hashfile *' and then call
+ * read_table_of_contents(). Supply the memory-mapped data to the
+ * pair_chunk() or read_chunk() methods, as appropriate.
+ *
+ * DO NOT MIX THESE MODES. Use different 'struct chunkfile' instances
+ * for reading and writing.
+ */
 struct chunkfile *init_chunkfile(struct hashfile *f);
 void free_chunkfile(struct chunkfile *cf);
 int get_num_chunks(struct chunkfile *cf);
@@ -18,4 +32,37 @@ void add_chunk(struct chunkfile *cf,
 	       chunk_write_fn fn);
 int write_chunkfile(struct chunkfile *cf, void *data);
 
+int read_table_of_contents(struct chunkfile *cf,
+			   const unsigned char *mfile,
+			   size_t mfile_size,
+			   uint64_t toc_offset,
+			   int toc_length);
+
+#define CHUNK_NOT_FOUND (-2)
+
+/*
+ * Find 'chunk_id' in the given chunkfile and assign the
+ * given pointer to the position in the mmap'd file where
+ * that chunk begins.
+ *
+ * Returns CHUNK_NOT_FOUND if the chunk does not exist.
+ */
+int pair_chunk(struct chunkfile *cf,
+	       uint32_t chunk_id,
+	       const unsigned char **p);
+
+typedef int (*chunk_read_fn)(const unsigned char *chunk_start,
+			     size_t chunk_size, void *data);
+/*
+ * Find 'chunk_id' in the given chunkfile and call the
+ * given chunk_read_fn method with the information for
+ * that chunk.
+ *
+ * Returns CHUNK_NOT_FOUND if the chunk does not exist.
+ */
+int read_chunk(struct chunkfile *cf,
+	       uint32_t chunk_id,
+	       chunk_read_fn fn,
+	       void *data);
+
 #endif