git/builtin/am.c

/*
 * Builtin "git am"
 *
 * Based on git-am.sh by Junio C Hamano.
 */
#define USE_THE_INDEX_COMPATIBILITY_MACROS
#include "cache.h"
#include "config.h"
#include "builtin.h"
#include "exec-cmd.h"
#include "parse-options.h"
#include "dir.h"
#include "run-command.h"
#include "quote.h"
#include "tempfile.h"
#include "lockfile.h"
#include "cache-tree.h"
#include "refs.h"
#include "commit.h"
#include "diff.h"
#include "diffcore.h"
#include "unpack-trees.h"
#include "branch.h"
#include "sequencer.h"
#include "revision.h"
#include "merge-recursive.h"
#include "log-tree.h"
#include "notes-utils.h"
#include "rerere.h"
#include "prompt.h"
#include "mailinfo.h"
#include "apply.h"
#include "string-list.h"
#include "packfile.h"
#include "repository.h"

/**
 * Returns the length of the first line of msg.
 */
static int linelen(const char *msg)
{
	return strchrnul(msg, '\n') - msg;
}

/**
 * Returns true if `str` consists of only whitespace, false otherwise.
 */
static int str_isspace(const char *str)
{
	for (; *str; str++)
		if (!isspace(*str))
			return 0;

	return 1;
}

enum patch_format {
	PATCH_FORMAT_UNKNOWN = 0,
	PATCH_FORMAT_MBOX,
	PATCH_FORMAT_STGIT,
	PATCH_FORMAT_STGIT_SERIES,
	PATCH_FORMAT_HG,
	PATCH_FORMAT_MBOXRD
};

enum keep_type {
	KEEP_FALSE = 0,
	KEEP_TRUE,      /* pass -k flag to git-mailinfo */
	KEEP_NON_PATCH  /* pass -b flag to git-mailinfo */
};

enum scissors_type {
	SCISSORS_UNSET = -1,
	SCISSORS_FALSE = 0,  /* pass --no-scissors to git-mailinfo */
	SCISSORS_TRUE        /* pass --scissors to git-mailinfo */
};

enum signoff_type {
	SIGNOFF_FALSE = 0,
	SIGNOFF_TRUE = 1,
	SIGNOFF_EXPLICIT /* --signoff was set on the command-line */
};

enum show_patch_type {
	SHOW_PATCH_RAW = 0,
	SHOW_PATCH_DIFF = 1,
};

struct am_state {
	/* state directory path */
	char *dir;

	/* current and last patch numbers, 1-indexed */
	int cur;
	int last;

	/* commit metadata and message */
	char *author_name;
	char *author_email;
	char *author_date;
	char *msg;
	size_t msg_len;

	/* when --rebasing, records the original commit the patch came from */
	struct object_id orig_commit;

	/* number of digits in patch filename */
	int prec;

	/* various operating modes and command line options */
	int interactive;
	int threeway;
	int quiet;
	int signoff; /* enum signoff_type */
	int utf8;
	int keep; /* enum keep_type */
	int message_id;
	int scissors; /* enum scissors_type */
	int quoted_cr; /* enum quoted_cr_action */
	struct strvec git_apply_opts;
	const char *resolvemsg;
	int committer_date_is_author_date;
	int ignore_date;
	int allow_rerere_autoupdate;
	const char *sign_commit;
	int rebasing;
};

/**
 * Initializes am_state with the default values.
 */
static void am_state_init(struct am_state *state)
{
	int gpgsign;

	memset(state, 0, sizeof(*state));

	state->dir = git_pathdup("rebase-apply");

	state->prec = 4;

	git_config_get_bool("am.threeway", &state->threeway);

	state->utf8 = 1;

	git_config_get_bool("am.messageid", &state->message_id);

	state->scissors = SCISSORS_UNSET;
	state->quoted_cr = quoted_cr_unset;

	strvec_init(&state->git_apply_opts);

	if (!git_config_get_bool("commit.gpgsign", &gpgsign))
		state->sign_commit = gpgsign ? "" : NULL;
}

/**
 * Releases memory allocated by an am_state.
 */
static void am_state_release(struct am_state *state)
{
	free(state->dir);
	free(state->author_name);
	free(state->author_email);
	free(state->author_date);
	free(state->msg);
	strvec_clear(&state->git_apply_opts);
}

static int am_option_parse_quoted_cr(const struct option *opt,
				     const char *arg, int unset)
{
	BUG_ON_OPT_NEG(unset);

	if (mailinfo_parse_quoted_cr_action(arg, opt->value) != 0)
		return error(_("bad action '%s' for '%s'"), arg, "--quoted-cr");
	return 0;
}

/**
 * Returns path relative to the am_state directory.
 */
static inline const char *am_path(const struct am_state *state, const char *path)
{
	return mkpath("%s/%s", state->dir, path);
}

/**
 * For convenience to call write_file()
 */
static void write_state_text(const struct am_state *state,
			     const char *name, const char *string)
{
	write_file(am_path(state, name), "%s", string);
}

static void write_state_count(const struct am_state *state,
			      const char *name, int value)
{
	write_file(am_path(state, name), "%d", value);
}

static void write_state_bool(const struct am_state *state,
			     const char *name, int value)
{
	write_state_text(state, name, value ? "t" : "f");
}

/**
 * If state->quiet is false, calls fprintf(fp, fmt, ...), and appends a newline
 * at the end.
 */
__attribute__((format (printf, 3, 4)))
static void say(const struct am_state *state, FILE *fp, const char *fmt, ...)
{
	va_list ap;

	va_start(ap, fmt);
	if (!state->quiet) {
		vfprintf(fp, fmt, ap);
		putc('\n', fp);
	}
	va_end(ap);
}

/**
 * Returns 1 if there is an am session in progress, 0 otherwise.
 */
static int am_in_progress(const struct am_state *state)
{
	struct stat st;

	if (lstat(state->dir, &st) < 0 || !S_ISDIR(st.st_mode))
		return 0;
	if (lstat(am_path(state, "last"), &st) || !S_ISREG(st.st_mode))
		return 0;
	if (lstat(am_path(state, "next"), &st) || !S_ISREG(st.st_mode))
		return 0;
	return 1;
}

/**
 * Reads the contents of `file` in the `state` directory into `sb`. Returns the
 * number of bytes read on success, -1 if the file does not exist. If `trim` is
 * set, trailing whitespace will be removed.
 */
static int read_state_file(struct strbuf *sb, const struct am_state *state,
			const char *file, int trim)
{
	strbuf_reset(sb);

	if (strbuf_read_file(sb, am_path(state, file), 0) >= 0) {
		if (trim)
			strbuf_trim(sb);

		return sb->len;
	}

	if (errno == ENOENT)
		return -1;

	die_errno(_("could not read '%s'"), am_path(state, file));
}

/**
 * Reads and parses the state directory's "author-script" file, and sets
 * state->author_name, state->author_email and state->author_date accordingly.
 * Returns 0 on success, -1 if the file could not be parsed.
 *
 * The author script is of the format:
 *
 *	GIT_AUTHOR_NAME='$author_name'
 *	GIT_AUTHOR_EMAIL='$author_email'
 *	GIT_AUTHOR_DATE='$author_date'
 *
 * where $author_name, $author_email and $author_date are quoted. We are strict
 * with our parsing, as the file was meant to be eval'd in the old git-am.sh
 * script, and thus if the file differs from what this function expects, it is
 * better to bail out than to do something that the user does not expect.
 */
static int read_am_author_script(struct am_state *state)
{
	const char *filename = am_path(state, "author-script");

	assert(!state->author_name);
	assert(!state->author_email);
	assert(!state->author_date);

	return read_author_script(filename, &state->author_name,
				  &state->author_email, &state->author_date, 1);
}

/**
 * Saves state->author_name, state->author_email and state->author_date in the
 * state directory's "author-script" file.
 */
static void write_author_script(const struct am_state *state)
{
	struct strbuf sb = STRBUF_INIT;

	strbuf_addstr(&sb, "GIT_AUTHOR_NAME=");
	sq_quote_buf(&sb, state->author_name);
	strbuf_addch(&sb, '\n');

	strbuf_addstr(&sb, "GIT_AUTHOR_EMAIL=");
	sq_quote_buf(&sb, state->author_email);
	strbuf_addch(&sb, '\n');

	strbuf_addstr(&sb, "GIT_AUTHOR_DATE=");
	sq_quote_buf(&sb, state->author_date);
	strbuf_addch(&sb, '\n');

	write_state_text(state, "author-script", sb.buf);

	strbuf_release(&sb);
}

/**
 * Reads the commit message from the state directory's "final-commit" file,
 * setting state->msg to its contents and state->msg_len to the length of its
 * contents in bytes.
 *
 * Returns 0 on success, -1 if the file does not exist.
 */
static int read_commit_msg(struct am_state *state)
{
	struct strbuf sb = STRBUF_INIT;

	assert(!state->msg);

	if (read_state_file(&sb, state, "final-commit", 0) < 0) {
		strbuf_release(&sb);
		return -1;
	}

	state->msg = strbuf_detach(&sb, &state->msg_len);
	return 0;
}

/**
 * Saves state->msg in the state directory's "final-commit" file.
 */
static void write_commit_msg(const struct am_state *state)
{
	const char *filename = am_path(state, "final-commit");
	write_file_buf(filename, state->msg, state->msg_len);
}

/**
 * Loads state from disk.
 */
static void am_load(struct am_state *state)
{
	struct strbuf sb = STRBUF_INIT;

	if (read_state_file(&sb, state, "next", 1) < 0)
		BUG("state file 'next' does not exist");
	state->cur = strtol(sb.buf, NULL, 10);

	if (read_state_file(&sb, state, "last", 1) < 0)
		BUG("state file 'last' does not exist");
	state->last = strtol(sb.buf, NULL, 10);

	if (read_am_author_script(state) < 0)
		die(_("could not parse author script"));

	read_commit_msg(state);

	if (read_state_file(&sb, state, "original-commit", 1) < 0)
		oidclr(&state->orig_commit);
	else if (get_oid_hex(sb.buf, &state->orig_commit) < 0)
		die(_("could not parse %s"), am_path(state, "original-commit"));

	read_state_file(&sb, state, "threeway", 1);
	state->threeway = !strcmp(sb.buf, "t");

	read_state_file(&sb, state, "quiet", 1);
	state->quiet = !strcmp(sb.buf, "t");

	read_state_file(&sb, state, "sign", 1);
	state->signoff = !strcmp(sb.buf, "t");

	read_state_file(&sb, state, "utf8", 1);
	state->utf8 = !strcmp(sb.buf, "t");

	if (file_exists(am_path(state, "rerere-autoupdate"))) {
		read_state_file(&sb, state, "rerere-autoupdate", 1);
		state->allow_rerere_autoupdate = strcmp(sb.buf, "t") ?
			RERERE_NOAUTOUPDATE : RERERE_AUTOUPDATE;
	} else {
		state->allow_rerere_autoupdate = 0;
	}

	read_state_file(&sb, state, "keep", 1);
	if (!strcmp(sb.buf, "t"))
		state->keep = KEEP_TRUE;
	else if (!strcmp(sb.buf, "b"))
		state->keep = KEEP_NON_PATCH;
	else
		state->keep = KEEP_FALSE;

	read_state_file(&sb, state, "messageid", 1);
	state->message_id = !strcmp(sb.buf, "t");

	read_state_file(&sb, state, "scissors", 1);
	if (!strcmp(sb.buf, "t"))
		state->scissors = SCISSORS_TRUE;
	else if (!strcmp(sb.buf, "f"))
		state->scissors = SCISSORS_FALSE;
	else
		state->scissors = SCISSORS_UNSET;

	read_state_file(&sb, state, "quoted-cr", 1);
	if (!*sb.buf)
		state->quoted_cr = quoted_cr_unset;
	else if (mailinfo_parse_quoted_cr_action(sb.buf, &state->quoted_cr) != 0)
		die(_("could not parse %s"), am_path(state, "quoted-cr"));

	read_state_file(&sb, state, "apply-opt", 1);
	strvec_clear(&state->git_apply_opts);
	if (sq_dequote_to_strvec(sb.buf, &state->git_apply_opts) < 0)
		die(_("could not parse %s"), am_path(state, "apply-opt"));

	state->rebasing = !!file_exists(am_path(state, "rebasing"));

	strbuf_release(&sb);
}

/**
 * Removes the am_state directory, forcefully terminating the current am
 * session.
 */
static void am_destroy(const struct am_state *state)
{
	struct strbuf sb = STRBUF_INIT;

	strbuf_addstr(&sb, state->dir);
	remove_dir_recursively(&sb, 0);
	strbuf_release(&sb);
}

/**
 * Runs applypatch-msg hook. Returns its exit code.
 */
static int run_applypatch_msg_hook(struct am_state *state)
{
	int ret;

	assert(state->msg);
	ret = run_hook_le(NULL, "applypatch-msg", am_path(state, "final-commit"), NULL);

	if (!ret) {
		FREE_AND_NULL(state->msg);
		if (read_commit_msg(state) < 0)
			die(_("'%s' was deleted by the applypatch-msg hook"),
				am_path(state, "final-commit"));
	}

	return ret;
}

/**
 * Runs post-rewrite hook. Returns it exit code.
 */
static int run_post_rewrite_hook(const struct am_state *state)
{
	struct child_process cp = CHILD_PROCESS_INIT;
	const char *hook = find_hook("post-rewrite");
	int ret;

	if (!hook)
		return 0;

	strvec_push(&cp.args, hook);
	strvec_push(&cp.args, "rebase");

	cp.in = xopen(am_path(state, "rewritten"), O_RDONLY);
	cp.stdout_to_stderr = 1;
	cp.trace2_hook_name = "post-rewrite";

	ret = run_command(&cp);

	close(cp.in);
	return ret;
}

/**
 * Reads the state directory's "rewritten" file, and copies notes from the old
 * commits listed in the file to their rewritten commits.
 *
 * Returns 0 on success, -1 on failure.
 */
static int copy_notes_for_rebase(const struct am_state *state)
{
	struct notes_rewrite_cfg *c;
	struct strbuf sb = STRBUF_INIT;
	const char *invalid_line = _("Malformed input line: '%s'.");
	const char *msg = "Notes added by 'git rebase'";
	FILE *fp;
	int ret = 0;

	assert(state->rebasing);

	c = init_copy_notes_for_rewrite("rebase");
	if (!c)
		return 0;

	fp = xfopen(am_path(state, "rewritten"), "r");

	while (!strbuf_getline_lf(&sb, fp)) {
		struct object_id from_obj, to_obj;
		const char *p;

		if (sb.len != the_hash_algo->hexsz * 2 + 1) {
			ret = error(invalid_line, sb.buf);
			goto finish;
		}

		if (parse_oid_hex(sb.buf, &from_obj, &p)) {
			ret = error(invalid_line, sb.buf);
			goto finish;
		}

		if (*p != ' ') {
			ret = error(invalid_line, sb.buf);
			goto finish;
		}

		if (get_oid_hex(p + 1, &to_obj)) {
			ret = error(invalid_line, sb.buf);
			goto finish;
		}

		if (copy_note_for_rewrite(c, &from_obj, &to_obj))
			ret = error(_("Failed to copy notes from '%s' to '%s'"),
					oid_to_hex(&from_obj), oid_to_hex(&to_obj));
	}

finish:
	finish_copy_notes_for_rewrite(the_repository, c, msg);
	fclose(fp);
	strbuf_release(&sb);
	return ret;
}

/**
 * Determines if the file looks like a piece of RFC2822 mail by grabbing all
 * non-indented lines and checking if they look like they begin with valid
 * header field names.
 *
 * Returns 1 if the file looks like a piece of mail, 0 otherwise.
 */
static int is_mail(FILE *fp)
{
	const char *header_regex = "^[!-9;-~]+:";
	struct strbuf sb = STRBUF_INIT;
	regex_t regex;
	int ret = 1;

	if (fseek(fp, 0L, SEEK_SET))
		die_errno(_("fseek failed"));

	if (regcomp(&regex, header_regex, REG_NOSUB | REG_EXTENDED))
		die("invalid pattern: %s", header_regex);

	while (!strbuf_getline(&sb, fp)) {
		if (!sb.len)
			break; /* End of header */

		/* Ignore indented folded lines */
		if (*sb.buf == '\t' || *sb.buf == ' ')
			continue;

		/* It's a header if it matches header_regex */
		if (regexec(&regex, sb.buf, 0, NULL, 0)) {
			ret = 0;
			goto done;
		}
	}

done:
	regfree(&regex);
	strbuf_release(&sb);
	return ret;
}

/**
 * Attempts to detect the patch_format of the patches contained in `paths`,
 * returning the PATCH_FORMAT_* enum value. Returns PATCH_FORMAT_UNKNOWN if
 * detection fails.
 */
static int detect_patch_format(const char **paths)
{
	enum patch_format ret = PATCH_FORMAT_UNKNOWN;
	struct strbuf l1 = STRBUF_INIT;
	struct strbuf l2 = STRBUF_INIT;
	struct strbuf l3 = STRBUF_INIT;
	FILE *fp;

	/*
	 * We default to mbox format if input is from stdin and for directories
	 */
	if (!*paths || !strcmp(*paths, "-") || is_directory(*paths))
		return PATCH_FORMAT_MBOX;

	/*
	 * Otherwise, check the first few lines of the first patch, starting
	 * from the first non-blank line, to try to detect its format.
	 */

	fp = xfopen(*paths, "r");

	while (!strbuf_getline(&l1, fp)) {
		if (l1.len)
			break;
	}

	if (starts_with(l1.buf, "From ") || starts_with(l1.buf, "From: ")) {
		ret = PATCH_FORMAT_MBOX;
		goto done;
	}

	if (starts_with(l1.buf, "# This series applies on GIT commit")) {
		ret = PATCH_FORMAT_STGIT_SERIES;
		goto done;
	}