run-command: add duplicate_output_fn to run_processes_parallel_opts

Add duplicate_output_fn as an optionally set function in
run_process_parallel_opts. If set, output from each child process is
copied and passed to the callback function whenever output from the
child process is buffered to allow for separate parsing.

Signed-off-by: Calvin Wan <calvinwan@google.com>
Signed-off-by: Taylor Blau <me@ttaylorr.com>

4 files changed, 95 insertions, 2 deletions

diff --git a/run-command.c b/run-command.c
index c772acd743..b8f430eb03 100644
--- a/run-command.c
+++ b/run-command.c
@@ -1560,6 +1560,9 @@ static void pp_init(struct parallel_processes *pp,
 
 	if (!opts->get_next_task)
 		BUG("you need to specify a get_next_task function");
+	
+	if (opts->duplicate_output && opts->ungroup)
+		BUG("duplicate_output and ungroup are incompatible with each other");
 
 	CALLOC_ARRAY(pp->children, n);
 	if (!opts->ungroup)
@@ -1680,8 +1683,14 @@ static void pp_buffer_stderr(struct parallel_processes *pp,
 	for (size_t i = 0; i < opts->processes; i++) {
 		if (pp->children[i].state == GIT_CP_WORKING &&
 		    pp->pfd[i].revents & (POLLIN | POLLHUP)) {
-			int n = strbuf_read_once(&pp->children[i].err,
-						 pp->children[i].process.err, 0);
+			struct strbuf buf = STRBUF_INIT;
+			int n = strbuf_read_once(&buf, pp->children[i].process.err, 0);
+			strbuf_addbuf(&pp->children[i].err, &buf);
+			if (opts->duplicate_output)
+				opts->duplicate_output(&buf, &pp->children[i].err,
+					  opts->data,
+					  pp->children[i].data);
+			strbuf_release(&buf);
 			if (n == 0) {
 				close(pp->children[i].process.err);
 				pp->children[i].state = GIT_CP_WAIT_CLEANUP;
diff --git a/run-command.h b/run-command.h
index e3e1ea01ad..dd6d6a86c2 100644
--- a/run-command.h
+++ b/run-command.h
@@ -441,6 +441,24 @@ typedef int (*start_failure_fn)(struct strbuf *out,
 				void *pp_task_cb);
 
 /**
+ * This callback is called whenever output from a child process is buffered
+ * 
+ * "struct strbuf *process_out" contains the output from the child process
+ * 
+ * See run_processes_parallel() below for a discussion of the "struct
+ * strbuf *out" parameter.
+ *
+ * pp_cb is the callback cookie as passed into run_processes_parallel,
+ * pp_task_cb is the callback cookie as passed into get_next_task_fn.
+ *
+ * This function is incompatible with "ungroup"
+ */
+typedef void (*duplicate_output_fn)(struct strbuf *process_out,
+				    struct strbuf *out,
+				    void *pp_cb,
+				    void *pp_task_cb);
+
+/**
  * This callback is called on every child process that finished processing.
  *
  * See run_processes_parallel() below for a discussion of the "struct
@@ -494,6 +512,12 @@ struct run_process_parallel_opts
 	start_failure_fn start_failure;
 
 	/**
+	 * duplicate_output: See duplicate_output_fn() above. This should be
+	 * NULL unless process specific output is needed
+	 */
+	duplicate_output_fn duplicate_output;
+
+	/**
 	 * task_finished: See task_finished_fn() above. This can be
 	 * NULL to omit any special handling.
 	 */
diff --git a/t/helper/test-run-command.c b/t/helper/test-run-command.c
index 3ecb830f4a..40dd329e02 100644
--- a/t/helper/test-run-command.c
+++ b/t/helper/test-run-command.c
@@ -52,6 +52,21 @@ static int no_job(struct child_process *cp,
 	return 0;
 }
 
+static void duplicate_output(struct strbuf *process_out,
+			struct strbuf *out,
+			void *pp_cb,
+			void *pp_task_cb)
+{
+	struct string_list list = STRING_LIST_INIT_DUP;
+
+	string_list_split(&list, process_out->buf, '\n', -1);
+	for (size_t i = 0; i < list.nr; i++) {
+		if (strlen(list.items[i].string) > 0)
+			fprintf(stderr, "duplicate_output: %s\n", list.items[i].string);
+	}
+	string_list_clear(&list, 0);
+}
+
 static int task_finished(int result,
 			 struct strbuf *err,
 			 void *pp_cb,
@@ -439,6 +454,12 @@ int cmd__run_command(int argc, const char **argv)
 		opts.ungroup = 1;
 	}
 
+	if (!strcmp(argv[1], "--duplicate-output")) {
+		argv += 1;
+		argc -= 1;
+		opts.duplicate_output = duplicate_output;
+	}
+
 	jobs = atoi(argv[2]);
 	strvec_clear(&proc.args);
 	strvec_pushv(&proc.args, (const char **)argv + 3);
diff --git a/t/t0061-run-command.sh b/t/t0061-run-command.sh
index 7b5423eebd..130aec7c68 100755
--- a/t/t0061-run-command.sh
+++ b/t/t0061-run-command.sh
@@ -134,6 +134,15 @@ test_expect_success 'run_command runs in parallel with more jobs available than
 	test_cmp expect actual
 '
 
+test_expect_success 'run_command runs in parallel with more jobs available than tasks --duplicate-output' '
+	test-tool run-command --duplicate-output run-command-parallel 5 sh -c "printf \"%s\n%s\n\" Hello World" >out 2>err &&
+	test_must_be_empty out &&
+	test 4 = $(grep -c "duplicate_output: Hello" err) &&
+	test 4 = $(grep -c "duplicate_output: World" err) &&
+	sed "/duplicate_output/d" err > err1 &&
+	test_cmp expect err1
+'
+
 test_expect_success 'run_command runs ungrouped in parallel with more jobs available than tasks' '
 	test-tool run-command --ungroup run-command-parallel 5 sh -c "printf \"%s\n%s\n\" Hello World" >out 2>err &&
 	test_line_count = 8 out &&
@@ -145,6 +154,15 @@ test_expect_success 'run_command runs in parallel with as many jobs as tasks' '
 	test_cmp expect actual
 '
 
+test_expect_success 'run_command runs in parallel with as many jobs as tasks --duplicate-output' '
+	test-tool run-command --duplicate-output run-command-parallel 4 sh -c "printf \"%s\n%s\n\" Hello World" >out 2>err &&
+	test_must_be_empty out &&
+	test 4 = $(grep -c "duplicate_output: Hello" err) &&
+	test 4 = $(grep -c "duplicate_output: World" err) &&
+	sed "/duplicate_output/d" err > err1 &&
+	test_cmp expect err1
+'
+
 test_expect_success 'run_command runs ungrouped in parallel with as many jobs as tasks' '
 	test-tool run-command --ungroup run-command-parallel 4 sh -c "printf \"%s\n%s\n\" Hello World" >out 2>err &&
 	test_line_count = 8 out &&
@@ -156,6 +174,15 @@ test_expect_success 'run_command runs in parallel with more tasks than jobs avai
 	test_cmp expect actual
 '
 
+test_expect_success 'run_command runs in parallel with more tasks than jobs available --duplicate-output' '
+	test-tool run-command --duplicate-output run-command-parallel 3 sh -c "printf \"%s\n%s\n\" Hello World" >out 2>err &&
+	test_must_be_empty out &&
+	test 4 = $(grep -c "duplicate_output: Hello" err) &&
+	test 4 = $(grep -c "duplicate_output: World" err) &&
+	sed "/duplicate_output/d" err > err1 &&
+	test_cmp expect err1
+'
+
 test_expect_success 'run_command runs ungrouped in parallel with more tasks than jobs available' '
 	test-tool run-command --ungroup run-command-parallel 3 sh -c "printf \"%s\n%s\n\" Hello World" >out 2>err &&
 	test_line_count = 8 out &&
@@ -176,6 +203,12 @@ test_expect_success 'run_command is asked to abort gracefully' '
 	test_cmp expect actual
 '
 
+test_expect_success 'run_command is asked to abort gracefully --duplicate-output' '
+	test-tool run-command --duplicate-output run-command-abort 3 false >out 2>err &&
+	test_must_be_empty out &&
+	test_cmp expect err
+'
+
 test_expect_success 'run_command is asked to abort gracefully (ungroup)' '
 	test-tool run-command --ungroup run-command-abort 3 false >out 2>err &&
 	test_must_be_empty out &&
@@ -191,6 +224,12 @@ test_expect_success 'run_command outputs ' '
 	test_cmp expect actual
 '
 
+test_expect_success 'run_command outputs --duplicate-output' '
+	test-tool run-command --duplicate-output run-command-no-jobs 3 sh -c "printf \"%s\n%s\n\" Hello World" >out 2>err &&
+	test_must_be_empty out &&
+	test_cmp expect err
+'
+
 test_expect_success 'run_command outputs (ungroup) ' '
 	test-tool run-command --ungroup run-command-no-jobs 3 sh -c "printf \"%s\n%s\n\" Hello World" >out 2>err &&
 	test_must_be_empty out &&