Merge branch 'jk/argv-array'

* jk/argv-array:
  run_hook: use argv_array API
  checkout: use argv_array API
  bisect: use argv_array API
  quote: provide sq_dequote_to_argv_array
  refactor argv_array into generic code
  quote.h: fix bogus comment
  add sha1_array API docs

Documentation/technical/api-argv-array.txt

@@ -0,0 +1,46 @@
+argv-array API
+==============
+
+The argv-array API allows one to dynamically build and store
+NULL-terminated lists.  An argv-array maintains the invariant that the
+`argv` member always points to a non-NULL array, and that the array is
+always NULL-terminated at the element pointed to by `argv[argc]`. This
+makes the result suitable for passing to functions expecting to receive
+argv from main(), or the link:api-run-command.html[run-command API].
+
+The link:api-string-list.html[string-list API] is similar, but cannot be
+used for these purposes; instead of storing a straight string pointer,
+it contains an item structure with a `util` field that is not compatible
+with the traditional argv interface.
+
+Each `argv_array` manages its own memory. Any strings pushed into the
+array are duplicated, and all memory is freed by argv_array_clear().
+
+Data Structures
+---------------
+
+`struct argv_array`::
+
+	A single array. This should be initialized by assignment from
+	`ARGV_ARRAY_INIT`, or by calling `argv_array_init`. The `argv`
+	member contains the actual array; the `argc` member contains the
+	number of elements in the array, not including the terminating
+	NULL.
+
+Functions
+---------
+
+`argv_array_init`::
+	Initialize an array. This is no different than assigning from
+	`ARGV_ARRAY_INIT`.
+
+`argv_array_push`::
+	Push a copy of a string onto the end of the array.
+
+`argv_array_pushf`::
+	Format a string and push it onto the end of the array. This is a
+	convenience wrapper combining `strbuf_addf` and `argv_array_push`.
+
+`argv_array_clear`::
+	Free all memory associated with the array and return it to the
+	initial, empty state.

Documentation/technical/api-sha1-array.txt

@@ -0,0 +1,79 @@
+sha1-array API
+==============
+
+The sha1-array API provides storage and manipulation of sets of SHA1
+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.
+
+Data Structures
+---------------
+
+`struct sha1_array`::
+
+	A single array of SHA1 hashes. This should be initialized by
+	assignment from `SHA1_ARRAY_INIT`.  The `sha1` 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.
+
+Functions
+---------
+
+`sha1_array_append`::
+	Add an item to the set. The sha1 will be placed at the end of
+	the array (but note that some operations below may lose this
+	ordering).
+
+`sha1_array_sort`::
+	Sort the elements in the array.
+
+`sha1_array_lookup`::
+	Perform a binary search of the array for a specific sha1.
+	If found, returns the offset (in number of elements) of the
+	sha1. If not found, returns a negative integer. If the array is
+	not sorted, this function has the side effect of sorting it.
+
+`sha1_array_clear`::
+	Free all memory associated with the array and return it to the
+	initial, empty state.
+
+`sha1_array_for_each_unique`::
+	Efficiently iterate over each unique element of the list,
+	executing the callback function for each one. If the array is
+	not sorted, this function has the side effect of sorting it.
+
+Examples
+--------
+
+-----------------------------------------
+void print_callback(const unsigned char sha1[20],
+		    void *data)
+{
+	printf("%s\n", sha1_to_hex(sha1));
+}
+
+void some_func(void)
+{
+	struct sha1_array hashes = SHA1_ARRAY_INIT;
+	unsigned char sha1[20];
+
+	/* Read objects into our set */
+	while (read_object_from_stdin(sha1))
+		sha1_array_append(&hashes, sha1);
+
+	/* Check if some objects are in our set */
+	while (read_object_from_stdin(sha1)) {
+		if (sha1_array_lookup(&hashes, sha1) >= 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.
+	 */
+	sha1_array_for_each_unique(&hashes, print_callback, NULL);
+}
+-----------------------------------------

Makefile

@@ -501,6 +501,7 @@ VCSSVN_LIB=vcs-svn/lib.a
 
 LIB_H += advice.h
 LIB_H += archive.h
+LIB_H += argv-array.h
 LIB_H += attr.h
 LIB_H += blob.h
 LIB_H += builtin.h
@@ -584,6 +585,7 @@ LIB_OBJS += alloc.o
 LIB_OBJS += archive.o
 LIB_OBJS += archive-tar.o
 LIB_OBJS += archive-zip.o
+LIB_OBJS += argv-array.o
 LIB_OBJS += attr.o
 LIB_OBJS += base85.o
 LIB_OBJS += bisect.o

argv-array.c

@@ -0,0 +1,51 @@
+#include "cache.h"
+#include "argv-array.h"
+#include "strbuf.h"
+
+static const char *empty_argv_storage = NULL;
+const char **empty_argv = &empty_argv_storage;
+
+void argv_array_init(struct argv_array *array)
+{
+	array->argv = empty_argv;
+	array->argc = 0;
+	array->alloc = 0;
+}
+
+static void argv_array_push_nodup(struct argv_array *array, const char *value)
+{
+	if (array->argv == empty_argv)
+		array->argv = NULL;
+
+	ALLOC_GROW(array->argv, array->argc + 2, array->alloc);
+	array->argv[array->argc++] = value;
+	array->argv[array->argc] = NULL;
+}
+
+void argv_array_push(struct argv_array *array, const char *value)
+{
+	argv_array_push_nodup(array, xstrdup(value));
+}
+
+void argv_array_pushf(struct argv_array *array, const char *fmt, ...)
+{
+	va_list ap;
+	struct strbuf v = STRBUF_INIT;
+
+	va_start(ap, fmt);
+	strbuf_vaddf(&v, fmt, ap);
+	va_end(ap);
+
+	argv_array_push_nodup(array, strbuf_detach(&v, NULL));
+}
+
+void argv_array_clear(struct argv_array *array)
+{
+	if (array->argv != empty_argv) {
+		int i;
+		for (i = 0; i < array->argc; i++)
+			free((char **)array->argv[i]);
+		free(array->argv);
+	}
+	argv_array_init(array);
+}

argv-array.h

@@ -0,0 +1,20 @@
+#ifndef ARGV_ARRAY_H
+#define ARGV_ARRAY_H
+
+extern const char **empty_argv;
+
+struct argv_array {
+	const char **argv;
+	int argc;
+	int alloc;
+};
+
+#define ARGV_ARRAY_INIT { empty_argv, 0, 0 }
+
+void argv_array_init(struct argv_array *);
+void argv_array_push(struct argv_array *, const char *);
+__attribute__((format (printf,2,3)))
+void argv_array_pushf(struct argv_array *, const char *fmt, ...);
+void argv_array_clear(struct argv_array *);
+
+#endif /* ARGV_ARRAY_H */

bisect.c

@@ -10,18 +10,13 @@
 #include "log-tree.h"
 #include "bisect.h"
 #include "sha1-array.h"
+#include "argv-array.h"
 
 static struct sha1_array good_revs;
 static struct sha1_array skipped_revs;
 
 static const unsigned char *current_bad_sha1;
 
-struct argv_array {
-	const char **argv;
-	int argv_nr;
-	int argv_alloc;
-};
-
 static const char *argv_checkout[] = {"checkout", "-q", NULL, "--", NULL};
 static const char *argv_show_branch[] = {"show-branch", NULL, NULL};
 static const char *argv_update_ref[] = {"update-ref", "--no-deref", "BISECT_HEAD", NULL, NULL};
@@ -405,21 +400,6 @@ struct commit_list *find_bisection(struct commit_list *list,
 	return best;
 }
 
-static void argv_array_push(struct argv_array *array, const char *string)
-{
-	ALLOC_GROW(array->argv, array->argv_nr + 1, array->argv_alloc);
-	array->argv[array->argv_nr++] = string;
-}
-
-static void argv_array_push_sha1(struct argv_array *array,
-				 const unsigned char *sha1,
-				 const char *format)
-{
-	struct strbuf buf = STRBUF_INIT;
-	strbuf_addf(&buf, format, sha1_to_hex(sha1));
-	argv_array_push(array, strbuf_detach(&buf, NULL));
-}
-
 static int register_ref(const char *refname, const unsigned char *sha1,
 			int flags, void *cb_data)
 {
@@ -449,16 +429,10 @@ static void read_bisect_paths(struct argv_array *array)
 		die_errno("Could not open file '%s'", filename);
 
 	while (strbuf_getline(&str, fp, '\n') != EOF) {
-		char *quoted;
-		int res;
-
 		strbuf_trim(&str);
-		quoted = strbuf_detach(&str, NULL);
-		res = sq_dequote_to_argv(quoted, &array->argv,
-					 &array->argv_nr, &array->argv_alloc);
-		if (res)
+		if (sq_dequote_to_argv_array(str.buf, array))
 			die("Badly quoted content in file '%s': %s",
-			    filename, quoted);
+			    filename, str.buf);
 	}
 
 	strbuf_release(&str);
@@ -623,25 +597,25 @@ static void bisect_rev_setup(struct rev_info *revs, const char *prefix,
 			     const char *bad_format, const char *good_format,
 			     int read_paths)
 {
-	struct argv_array rev_argv = { NULL, 0, 0 };
+	struct argv_array rev_argv = ARGV_ARRAY_INIT;
 	int i;
 
 	init_revisions(revs, prefix);
 	revs->abbrev = 0;
 	revs->commit_format = CMIT_FMT_UNSPECIFIED;
 
 	/* rev_argv.argv[0] will be ignored by setup_revisions */
-	argv_array_push(&rev_argv, xstrdup("bisect_rev_setup"));
-	argv_array_push_sha1(&rev_argv, current_bad_sha1, bad_format);
+	argv_array_push(&rev_argv, "bisect_rev_setup");
+	argv_array_pushf(&rev_argv, bad_format, sha1_to_hex(current_bad_sha1));
 	for (i = 0; i < good_revs.nr; i++)
-		argv_array_push_sha1(&rev_argv, good_revs.sha1[i],
-				     good_format);
-	argv_array_push(&rev_argv, xstrdup("--"));
+		argv_array_pushf(&rev_argv, good_format,
+				 sha1_to_hex(good_revs.sha1[i]));
+	argv_array_push(&rev_argv, "--");
 	if (read_paths)
 		read_bisect_paths(&rev_argv);
-	argv_array_push(&rev_argv, NULL);
 
-	setup_revisions(rev_argv.argv_nr, rev_argv.argv, revs, NULL);
+	setup_revisions(rev_argv.argc, rev_argv.argv, revs, NULL);
+	/* XXX leak rev_argv, as "revs" may still be pointing to it */
 }
 
 static void bisect_common(struct rev_info *revs)

builtin/checkout.c

@@ -19,6 +19,7 @@
 #include "ll-merge.h"
 #include "resolve-undo.h"
 #include "submodule.h"
+#include "argv-array.h"
 
 static const char * const checkout_usage[] = {
 	"git checkout [options] <branch>",
@@ -588,24 +589,12 @@ static void update_refs_for_switch(struct checkout_opts *opts,
 		report_tracking(new);
 }
 
-struct rev_list_args {
-	int argc;
-	int alloc;
-	const char **argv;
-};
-
-static void add_one_rev_list_arg(struct rev_list_args *args, const char *s)
-{
-	ALLOC_GROW(args->argv, args->argc + 1, args->alloc);
-	args->argv[args->argc++] = s;
-}
-
 static int add_one_ref_to_rev_list_arg(const char *refname,
 				       const unsigned char *sha1,
 				       int flags,
 				       void *cb_data)
 {
-	add_one_rev_list_arg(cb_data, refname);
+	argv_array_push(cb_data, refname);
 	return 0;
 }
 
@@ -685,15 +674,14 @@ static void suggest_reattach(struct commit *commit, struct rev_info *revs)
  */
 static void orphaned_commit_warning(struct commit *commit)
 {
-	struct rev_list_args args = { 0, 0, NULL };
+	struct argv_array args = ARGV_ARRAY_INIT;
 	struct rev_info revs;
 
-	add_one_rev_list_arg(&args, "(internal)");
-	add_one_rev_list_arg(&args, sha1_to_hex(commit->object.sha1));
-	add_one_rev_list_arg(&args, "--not");
+	argv_array_push(&args, "(internal)");
+	argv_array_push(&args, sha1_to_hex(commit->object.sha1));
+	argv_array_push(&args, "--not");
 	for_each_ref(add_one_ref_to_rev_list_arg, &args);
-	add_one_rev_list_arg(&args, "--");
-	add_one_rev_list_arg(&args, NULL);
+	argv_array_push(&args, "--");
 
 	init_revisions(&revs, NULL);
 	if (setup_revisions(args.argc - 1, args.argv, &revs, NULL) != 1)
@@ -705,6 +693,7 @@ static void orphaned_commit_warning(struct commit *commit)
 	else
 		describe_detached_head(_("Previous HEAD position was"), commit);
 
+	argv_array_clear(&args);
 	clear_commit_marks(commit, -1);
 	for_each_ref(clear_commit_marks_from_one_ref, NULL);
 }