summaryrefslogtreecommitdiff
path: root/oid-array.h
diff options
context:
space:
mode:
authorJeff King <peff@peff.net>2020-03-30 14:03:46 (GMT)
committerJunio C Hamano <gitster@pobox.com>2020-03-30 17:59:08 (GMT)
commitfe299ec5ae7b419990bbc3efd4e6bfa3f0773b45 (patch)
treecabe7f75d348ca4dac662a909d736ac53a94f4fa /oid-array.h
parenteccce5253b9bfb17238f7d94c9ccf1cfd935eeb2 (diff)
downloadgit-fe299ec5ae7b419990bbc3efd4e6bfa3f0773b45.zip
git-fe299ec5ae7b419990bbc3efd4e6bfa3f0773b45.tar.gz
git-fe299ec5ae7b419990bbc3efd4e6bfa3f0773b45.tar.bz2
oid_array: rename source file from sha1-array
We renamed the actual data structure in 910650d2f8 (Rename sha1_array to oid_array, 2017-03-31), but the file is still called sha1-array. Besides being slightly confusing, it makes it more annoying to grep for leftover occurrences of "sha1" in various files, because the header is included in so many places. Let's complete the transition by renaming the source and header files (and fixing up a few comment references). I kept the "-" in the name, as that seems to be our style; cf. fc1395f4a4 (sha1_file.c: rename to use dash in file name, 2018-04-10). We also have oidmap.h and oidset.h without any punctuation, but those are "struct oidmap" and "struct oidset" in the code. We _could_ make this "oidarray" to match, but somehow it looks uglier to me because of the length of "array" (plus it would be a very invasive patch for little gain). Signed-off-by: Jeff King <peff@peff.net> Signed-off-by: Junio C Hamano <gitster@pobox.com>
Diffstat (limited to 'oid-array.h')
-rw-r--r--oid-array.h109
1 files changed, 109 insertions, 0 deletions
diff --git a/oid-array.h b/oid-array.h
new file mode 100644
index 0000000..f28d322
--- /dev/null
+++ b/oid-array.h
@@ -0,0 +1,109 @@
+#ifndef SHA1_ARRAY_H
+#define SHA1_ARRAY_H
+
+/**
+ * The API provides storage and manipulation of sets of object identifiers.
+ * The emphasis is on storage and processing efficiency, making them suitable
+ * for large lists. Note that the ordering of items is not preserved over some
+ * operations.
+ *
+ * Examples
+ * --------
+ * -----------------------------------------
+ * int print_callback(const struct object_id *oid,
+ * void *data)
+ * {
+ * printf("%s\n", oid_to_hex(oid));
+ * return 0; // always continue
+ * }
+ *
+ * void some_func(void)
+ * {
+ * struct oid_array hashes = OID_ARRAY_INIT;
+ * struct object_id oid;
+ *
+ * // Read objects into our set
+ * while (read_object_from_stdin(oid.hash))
+ * oid_array_append(&hashes, &oid);
+ *
+ * // Check if some objects are in our set
+ * while (read_object_from_stdin(oid.hash)) {
+ * if (oid_array_lookup(&hashes, &oid) >= 0)
+ * printf("it's in there!\n");
+ *
+ * // Print the unique set of objects. We could also have
+ * // avoided adding duplicate objects in the first place,
+ * // but we would end up re-sorting the array repeatedly.
+ * // Instead, this will sort once and then skip duplicates
+ * // in linear time.
+ *
+ * oid_array_for_each_unique(&hashes, print_callback, NULL);
+ * }
+ */
+
+/**
+ * A single array of object IDs. This should be initialized by assignment from
+ * `OID_ARRAY_INIT`. The `oid` member contains the actual data. The `nr` member
+ * contains the number of items in the set. The `alloc` and `sorted` members
+ * are used internally, and should not be needed by API callers.
+ */
+struct oid_array {
+ struct object_id *oid;
+ size_t nr;
+ size_t alloc;
+ int sorted;
+};
+
+#define OID_ARRAY_INIT { NULL, 0, 0, 0 }
+
+/**
+ * Add an item to the set. The object ID will be placed at the end of the array
+ * (but note that some operations below may lose this ordering).
+ */
+void oid_array_append(struct oid_array *array, const struct object_id *oid);
+
+/**
+ * Perform a binary search of the array for a specific object ID. If found,
+ * returns the offset (in number of elements) of the object ID. If not found,
+ * returns a negative integer. If the array is not sorted, this function has
+ * the side effect of sorting it.
+ */
+int oid_array_lookup(struct oid_array *array, const struct object_id *oid);
+
+/**
+ * Free all memory associated with the array and return it to the initial,
+ * empty state.
+ */
+void oid_array_clear(struct oid_array *array);
+
+typedef int (*for_each_oid_fn)(const struct object_id *oid,
+ void *data);
+/**
+ * Iterate over each element of the list, executing the callback function for
+ * each one. Does not sort the list, so any custom hash order is retained.
+ * If the callback returns a non-zero value, the iteration ends immediately
+ * and the callback's return is propagated; otherwise, 0 is returned.
+ */
+int oid_array_for_each(struct oid_array *array,
+ for_each_oid_fn fn,
+ void *data);
+
+/**
+ * Iterate over each unique element of the list in sorted order, but otherwise
+ * behave like `oid_array_for_each`. If the array is not sorted, this function
+ * has the side effect of sorting it.
+ */
+int oid_array_for_each_unique(struct oid_array *array,
+ for_each_oid_fn fn,
+ void *data);
+
+/**
+ * Apply the callback function `want` to each entry in the array, retaining
+ * only the entries for which the function returns true. Preserve the order
+ * of the entries that are retained.
+ */
+void oid_array_filter(struct oid_array *array,
+ for_each_oid_fn want,
+ void *cbdata);
+
+#endif /* SHA1_ARRAY_H */