[PATCH v3 12/17] chunk-format: create read chunk API

From: Derrick Stolee via GitGitGadget <gitgitgadget@gmail.com>
Date: Feb 5, 2021, 14:30 UTC
Message-ID: <366eb2afee839feccdfd2244b231d2ad718c76d4.1612535453.git.gitgitgadget@gmail.com>
In-Reply-To: <pull.848.v3.git.1612535452.gitgitgadget@gmail.com>

From: Derrick Stolee <dstolee@microsoft.com>

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>
---
 chunk-format.c | 80 ++++++++++++++++++++++++++++++++++++++++++++++++++
 chunk-format.h | 46 +++++++++++++++++++++++++++++
 2 files changed, 126 insertions(+)

diff --git a/chunk-format.c b/chunk-format.c
index 6e0f1900213e..bc9d4caf7276 100644
--- a/chunk-format.c
+++ b/chunk-format.c
@@ -12,6 +12,8 @@ struct chunk_info {
 	uint32_t id;
 	uint64_t size;
 	chunk_write_fn write_fn;
+
+	const void *start;
 };
 
 struct chunkfile {
@@ -89,3 +91,81 @@ int write_chunkfile(struct chunkfile *cf, void *data)
 
 	return 0;
 }
+
+int read_table_of_contents(struct chunkfile *cf,
+			   const unsigned char *mfile,
+			   size_t mfile_size,
+			   uint64_t toc_offset,
+			   int toc_length)
+{
+	uint32_t chunk_id;
+	const unsigned char *table_of_contents = mfile + toc_offset;
+
+	ALLOC_GROW(cf->chunks, toc_length, cf->chunks_alloc);
+
+	while (toc_length--) {
+		uint64_t chunk_offset, next_chunk_offset;
+
+		chunk_id = get_be32(table_of_contents);
+		chunk_offset = get_be64(table_of_contents + 4);
+
+		if (!chunk_id) {
+			error(_("terminating chunk id appears earlier than expected"));
+			return 1;
+		}
+
+		table_of_contents += CHUNK_LOOKUP_WIDTH;
+		next_chunk_offset = get_be64(table_of_contents + 4);
+
+		if (next_chunk_offset < chunk_offset ||
+		    next_chunk_offset > mfile_size - the_hash_algo->rawsz) {
+			error(_("improper chunk offset(s) %"PRIx64" and %"PRIx64""),
+			      chunk_offset, next_chunk_offset);
+			return -1;
+		}
+
+		cf->chunks[cf->chunks_nr].id = chunk_id;
+		cf->chunks[cf->chunks_nr].start = mfile + chunk_offset;
+		cf->chunks[cf->chunks_nr].size = next_chunk_offset - chunk_offset;
+		cf->chunks_nr++;
+	}
+
+	chunk_id = get_be32(table_of_contents);
+	if (chunk_id) {
+		error(_("final chunk has non-zero id %"PRIx32""), chunk_id);
+		return -1;
+	}
+
+	return 0;
+}
+
+static int pair_chunk_fn(const unsigned char *chunk_start,
+			 size_t chunk_size,
+			 void *data)
+{
+	const unsigned char **p = data;
+	*p = chunk_start;
+	return 0;
+}
+
+int pair_chunk(struct chunkfile *cf,
+	       uint32_t chunk_id,
+	       const unsigned char **p)
+{
+	return read_chunk(cf, chunk_id, pair_chunk_fn, p);
+}
+
+int read_chunk(struct chunkfile *cf,
+	       uint32_t chunk_id,
+	       chunk_read_fn fn,
+	       void *data)
+{
+	int i;
+
+	for (i = 0; i < cf->chunks_nr; i++) {
+		if (cf->chunks[i].id == chunk_id)
+			return fn(cf->chunks[i].start, cf->chunks[i].size, data);
+	}
+
+	return CHUNK_NOT_FOUND;
+}
diff --git a/chunk-format.h b/chunk-format.h
index 9a1d770accec..0edcc57db4e7 100644
--- a/chunk-format.h
+++ b/chunk-format.h
@@ -6,6 +6,19 @@
 struct hashfile;
 struct chunkfile;
 
+/*
+ * 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, then 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);
@@ -16,4 +29,37 @@ 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

-- 
gitgitgadget