Merge branch 'bp/sub-process-convert-filter'

Code from "conversion using external process" codepath has been
extracted to a separate sub-process.[ch] module.

* bp/sub-process-convert-filter:
  convert: update subprocess_read_status() to not die on EOF
  sub-process: move sub-process functions into separate files
  convert: rename reusable sub-process functions
  convert: update generic functions to only use generic data structures
  convert: separate generic structures and variables from the filter specific ones
  convert: split start_multi_file_filter() into two separate functions
  pkt-line: annotate packet_writel with LAST_ARG_MUST_BE_NULL
  convert: move packet_write_line() into pkt-line as packet_writel()
  pkt-line: add packet_read_line_gently()
  pkt-line: fix packet_read_line() to handle len < 0 errors
  convert: remove erroneous tests for errno == EPIPE

Author: gitster

Documentation/technical/api-sub-process.txt

@@ -0,0 +1,59 @@
+sub-process API
+===============
+
+The sub-process API makes it possible to run background sub-processes
+for the entire lifetime of a Git invocation. If Git needs to communicate
+with an external process multiple times, then this can reduces the process
+invocation overhead. Git and the sub-process communicate through stdin and
+stdout.
+
+The sub-processes are kept in a hashmap by command name and looked up
+via the subprocess_find_entry function.  If an existing instance can not
+be found then a new process should be created and started.  When the
+parent git command terminates, all sub-processes are also terminated.
+
+This API is based on the run-command API.
+
+Data structures
+---------------
+
+* `struct subprocess_entry`
+
+The sub-process structure.  Members should not be accessed directly.
+
+Types
+-----
+
+'int(*subprocess_start_fn)(struct subprocess_entry *entry)'::
+
+	User-supplied function to initialize the sub-process.  This is
+	typically used to negotiate the interface version and capabilities.
+
+
+Functions
+---------
+
+`cmd2process_cmp`::
+
+	Function to test two subprocess hashmap entries for equality.
+
+`subprocess_start`::
+
+	Start a subprocess and add it to the subprocess hashmap.
+
+`subprocess_stop`::
+
+	Kill a subprocess and remove it from the subprocess hashmap.
+
+`subprocess_find_entry`::
+
+	Find a subprocess in the subprocess hashmap.
+
+`subprocess_get_child_process`::
+
+	Get the underlying `struct child_process` from a subprocess.
+
+`subprocess_read_status`::
+
+	Helper function to read packets looking for the last "status=<foo>"
+	key/value pair.

Makefile

@@ -842,6 +842,7 @@ LIB_OBJS += streaming.o
 LIB_OBJS += string-list.o
 LIB_OBJS += submodule.o
 LIB_OBJS += submodule-config.o
+LIB_OBJS += sub-process.o
 LIB_OBJS += symlinks.o
 LIB_OBJS += tag.o
 LIB_OBJS += tempfile.o

convert.c

@@ -4,6 +4,7 @@
 #include "quote.h"
 #include "sigchain.h"
 #include "pkt-line.h"
+#include "sub-process.h"
 
 /*
  * convert.c - convert a file when checking it out and checking it in.
@@ -497,126 +498,26 @@ static int apply_single_file_filter(const char *path, const char *src, size_t le
 #define CAP_SMUDGE   (1u<<1)
 
 struct cmd2process {
-	struct hashmap_entry ent; /* must be the first member! */
+	struct subprocess_entry subprocess; /* must be the first member! */
 	unsigned int supported_capabilities;
-	const char *cmd;
-	struct child_process process;
 };
 
-static int cmd_process_map_initialized;
-static struct hashmap cmd_process_map;
-
-static int cmd2process_cmp(const struct cmd2process *e1,
-			   const struct cmd2process *e2,
-			   const void *unused)
-{
-	return strcmp(e1->cmd, e2->cmd);
-}
-
-static struct cmd2process *find_multi_file_filter_entry(struct hashmap *hashmap, const char *cmd)
-{
-	struct cmd2process key;
-	hashmap_entry_init(&key, strhash(cmd));
-	key.cmd = cmd;
-	return hashmap_get(hashmap, &key, NULL);
-}
+static int subprocess_map_initialized;
+static struct hashmap subprocess_map;
 
-static int packet_write_list(int fd, const char *line, ...)
+static int start_multi_file_filter_fn(struct subprocess_entry *subprocess)
 {
-	va_list args;
 	int err;
-	va_start(args, line);
-	for (;;) {
-		if (!line)
-			break;
-		if (strlen(line) > LARGE_PACKET_DATA_MAX)
-			return -1;
-		err = packet_write_fmt_gently(fd, "%s\n", line);
-		if (err)
-			return err;
-		line = va_arg(args, const char*);
-	}
-	va_end(args);
-	return packet_flush_gently(fd);
-}
-
-static void read_multi_file_filter_status(int fd, struct strbuf *status)
-{
-	struct strbuf **pair;
-	char *line;
-	for (;;) {
-		line = packet_read_line(fd, NULL);
-		if (!line)
-			break;
-		pair = strbuf_split_str(line, '=', 2);
-		if (pair[0] && pair[0]->len && pair[1]) {
-			/* the last "status=<foo>" line wins */
-			if (!strcmp(pair[0]->buf, "status=")) {
-				strbuf_reset(status);
-				strbuf_addbuf(status, pair[1]);
-			}
-		}
-		strbuf_list_free(pair);
-	}
-}
-
-static void kill_multi_file_filter(struct hashmap *hashmap, struct cmd2process *entry)
-{
-	if (!entry)
-		return;
-
-	entry->process.clean_on_exit = 0;
-	kill(entry->process.pid, SIGTERM);
-	finish_command(&entry->process);
-
-	hashmap_remove(hashmap, entry, NULL);
-	free(entry);
-}
-
-static void stop_multi_file_filter(struct child_process *process)
-{
-	sigchain_push(SIGPIPE, SIG_IGN);
-	/* Closing the pipe signals the filter to initiate a shutdown. */
-	close(process->in);
-	close(process->out);
-	sigchain_pop(SIGPIPE);
-	/* Finish command will wait until the shutdown is complete. */
-	finish_command(process);
-}
-
-static struct cmd2process *start_multi_file_filter(struct hashmap *hashmap, const char *cmd)
-{
-	int err;
-	struct cmd2process *entry;
-	struct child_process *process;
-	const char *argv[] = { cmd, NULL };
+	struct cmd2process *entry = (struct cmd2process *)subprocess;
 	struct string_list cap_list = STRING_LIST_INIT_NODUP;
 	char *cap_buf;
 	const char *cap_name;
-
-	entry = xmalloc(sizeof(*entry));
-	entry->cmd = cmd;
-	entry->supported_capabilities = 0;
-	process = &entry->process;
-
-	child_process_init(process);
-	process->argv = argv;
-	process->use_shell = 1;
-	process->in = -1;
-	process->out = -1;
-	process->clean_on_exit = 1;
-	process->clean_on_exit_handler = stop_multi_file_filter;
-
-	if (start_command(process)) {
-		error("cannot fork to run external filter '%s'", cmd);
-		return NULL;
-	}
-
-	hashmap_entry_init(entry, strhash(cmd));
+	struct child_process *process = &subprocess->process;
+	const char *cmd = subprocess->cmd;
 
 	sigchain_push(SIGPIPE, SIG_IGN);
 
-	err = packet_write_list(process->in, "git-filter-client", "version=2", NULL);
+	err = packet_writel(process->in, "git-filter-client", "version=2", NULL);
 	if (err)
 		goto done;
 
@@ -632,7 +533,7 @@ static struct cmd2process *start_multi_file_filter(struct hashmap *hashmap, cons
 	if (err)
 		goto done;
 
-	err = packet_write_list(process->in, "capability=clean", "capability=smudge", NULL);
+	err = packet_writel(process->in, "capability=clean", "capability=smudge", NULL);
 
 	for (;;) {
 		cap_buf = packet_read_line(process->out, NULL);
@@ -661,14 +562,7 @@ static struct cmd2process *start_multi_file_filter(struct hashmap *hashmap, cons
 done:
 	sigchain_pop(SIGPIPE);
 
-	if (err || errno == EPIPE) {
-		error("initialization for external filter '%s' failed", cmd);
-		kill_multi_file_filter(hashmap, entry);
-		return NULL;
-	}
-
-	hashmap_add(hashmap, entry);
-	return entry;
+	return err;
 }
 
 static int apply_multi_file_filter(const char *path, const char *src, size_t len,
@@ -682,22 +576,26 @@ static int apply_multi_file_filter(const char *path, const char *src, size_t len
 	struct strbuf filter_status = STRBUF_INIT;
 	const char *filter_type;
 
-	if (!cmd_process_map_initialized) {
-		cmd_process_map_initialized = 1;
-		hashmap_init(&cmd_process_map, (hashmap_cmp_fn) cmd2process_cmp, 0);
+	if (!subprocess_map_initialized) {
+		subprocess_map_initialized = 1;
+		hashmap_init(&subprocess_map, (hashmap_cmp_fn) cmd2process_cmp, 0);
 		entry = NULL;
 	} else {
-		entry = find_multi_file_filter_entry(&cmd_process_map, cmd);
+		entry = (struct cmd2process *)subprocess_find_entry(&subprocess_map, cmd);
 	}
 
 	fflush(NULL);
 
 	if (!entry) {
-		entry = start_multi_file_filter(&cmd_process_map, cmd);
-		if (!entry)
+		entry = xmalloc(sizeof(*entry));
+		entry->supported_capabilities = 0;
+
+		if (subprocess_start(&subprocess_map, &entry->subprocess, cmd, start_multi_file_filter_fn)) {
+			free(entry);
 			return 0;
+		}
 	}
-	process = &entry->process;
+	process = &entry->subprocess.process;
 
 	if (!(wanted_capability & entry->supported_capabilities))
 		return 0;
@@ -737,7 +635,10 @@ static int apply_multi_file_filter(const char *path, const char *src, size_t len
 	if (err)
 		goto done;
 
-	read_multi_file_filter_status(process->out, &filter_status);
+	err = subprocess_read_status(process->out, &filter_status);
+	if (err)
+		goto done;
+
 	err = strcmp(filter_status.buf, "success");
 	if (err)
 		goto done;
@@ -746,13 +647,16 @@ static int apply_multi_file_filter(const char *path, const char *src, size_t len
 	if (err)
 		goto done;
 
-	read_multi_file_filter_status(process->out, &filter_status);
+	err = subprocess_read_status(process->out, &filter_status);
+	if (err)
+		goto done;
+
 	err = strcmp(filter_status.buf, "success");
 
 done:
 	sigchain_pop(SIGPIPE);
 
-	if (err || errno == EPIPE) {
+	if (err) {
 		if (!strcmp(filter_status.buf, "error")) {
 			/* The filter signaled a problem with the file. */
 		} else if (!strcmp(filter_status.buf, "abort")) {
@@ -768,7 +672,8 @@ static int apply_multi_file_filter(const char *path, const char *src, size_t len
 			 * Force shutdown and restart if another blob requires filtering.
 			 */
 			error("external filter '%s' failed", cmd);
-			kill_multi_file_filter(&cmd_process_map, entry);
+			subprocess_stop(&subprocess_map, &entry->subprocess);
+			free(entry);
 		}
 	} else {
 		strbuf_swap(dst, &nbuf);

pkt-line.c

@@ -171,6 +171,25 @@ int packet_write_fmt_gently(int fd, const char *fmt, ...)
 	return status;
 }
 
+int packet_writel(int fd, const char *line, ...)
+{
+	va_list args;
+	int err;
+	va_start(args, line);
+	for (;;) {
+		if (!line)
+			break;
+		if (strlen(line) > LARGE_PACKET_DATA_MAX)
+			return -1;
+		err = packet_write_fmt_gently(fd, "%s\n", line);
+		if (err)
+			return err;
+		line = va_arg(args, const char*);
+	}
+	va_end(args);
+	return packet_flush_gently(fd);
+}
+
 static int packet_write_gently(const int fd_out, const char *buf, size_t size)
 {
 	static char packet_write_buffer[LARGE_PACKET_MAX];
@@ -315,14 +334,26 @@ static char *packet_read_line_generic(int fd,
 			      PACKET_READ_CHOMP_NEWLINE);
 	if (dst_len)
 		*dst_len = len;
-	return len ? packet_buffer : NULL;
+	return (len > 0) ? packet_buffer : NULL;
 }
 
 char *packet_read_line(int fd, int *len_p)
 {
 	return packet_read_line_generic(fd, NULL, NULL, len_p);
 }
 
+int packet_read_line_gently(int fd, int *dst_len, char **dst_line)
+{
+	int len = packet_read(fd, NULL, NULL,
+			      packet_buffer, sizeof(packet_buffer),
+			      PACKET_READ_CHOMP_NEWLINE|PACKET_READ_GENTLE_ON_EOF);
+	if (dst_len)
+		*dst_len = len;
+	if (dst_line)
+		*dst_line = (len > 0) ? packet_buffer : NULL;
+	return len;
+}
+
 char *packet_read_line_buf(char **src, size_t *src_len, int *dst_len)
 {
 	return packet_read_line_generic(-1, src, src_len, dst_len);

pkt-line.h

@@ -25,6 +25,8 @@ void packet_buf_flush(struct strbuf *buf);
 void packet_buf_write(struct strbuf *buf, const char *fmt, ...) __attribute__((format (printf, 2, 3)));
 int packet_flush_gently(int fd);
 int packet_write_fmt_gently(int fd, const char *fmt, ...) __attribute__((format (printf, 2, 3)));
+LAST_ARG_MUST_BE_NULL
+int packet_writel(int fd, const char *line, ...);
 int write_packetized_from_fd(int fd_in, int fd_out);
 int write_packetized_from_buf(const char *src_in, size_t len, int fd_out);
 
@@ -73,6 +75,17 @@ int packet_read(int fd, char **src_buffer, size_t *src_len, char
  */
 char *packet_read_line(int fd, int *size);
 
+/*
+ * Convenience wrapper for packet_read that sets the PACKET_READ_GENTLE_ON_EOF
+ * and CHOMP_NEWLINE options. The return value specifies the number of bytes
+ * read into the buffer or -1 on truncated input. If the *dst_line parameter
+ * is not NULL it will return NULL for a flush packet or when the number of
+ * bytes copied is zero and otherwise points to a static buffer (that may be
+ * overwritten by subsequent calls). If the size parameter is not NULL, the
+ * length of the packet is written to it.
+ */
+int packet_read_line_gently(int fd, int *size, char **dst_line);
+
 /*
  * Same as packet_read_line, but read from a buf rather than a descriptor;
  * see packet_read for details on how src_* is used.