Merge branch 'pw/am-rebase-read-author-script'

Unify code to read the author-script used in "git am" and the
commands that use the sequencer machinery, e.g. "git rebase -i".

* pw/am-rebase-read-author-script:
  sequencer: use read_author_script()
  add read_author_script() to libgit
  am: rename read_author_script()
  am: improve author-script error reporting
  am: don't die in read_author_script()

1 files changed, 121 insertions, 71 deletions

diff --git a/sequencer.c b/sequencer.c
index 405d5ef..1869435 100644
--- a/sequencer.c
+++ b/sequencer.c
@@ -669,55 +669,131 @@ missing_author:
 	return res;
 }
 
+/**
+ * Take a series of KEY='VALUE' lines where VALUE part is
+ * sq-quoted, and append <KEY, VALUE> at the end of the string list
+ */
+static int parse_key_value_squoted(char *buf, struct string_list *list)
+{
+	while (*buf) {
+		struct string_list_item *item;
+		char *np;
+		char *cp = strchr(buf, '=');
+		if (!cp) {
+			np = strchrnul(buf, '\n');
+			return error(_("no key present in '%.*s'"),
+				     (int) (np - buf), buf);
+		}
+		np = strchrnul(cp, '\n');
+		*cp++ = '\0';
+		item = string_list_append(list, buf);
+
+		buf = np + (*np == '\n');
+		*np = '\0';
+		cp = sq_dequote(cp);
+		if (!cp)
+			return error(_("unable to dequote value of '%s'"),
+				     item->string);
+		item->util = xstrdup(cp);
+	}
+	return 0;
+}
 
-/*
- * write_author_script() used to fail to terminate the last line with a "'" and
- * also escaped "'" incorrectly as "'\\\\''" rather than "'\\''". We check for
- * the terminating "'" on the last line to see how "'" has been escaped in case
- * git was upgraded while rebase was stopped.
+/**
+ * Reads and parses the state directory's "author-script" file, and sets name,
+ * email and 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/git-rebase--interactive.sh scripts, 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 quoting_is_broken(const char *s, size_t n)
+int read_author_script(const char *path, char **name, char **email, char **date,
+		       int allow_missing)
 {
-	/* Skip any empty lines in case the file was hand edited */
-	while (n > 0 && s[--n] == '\n')
-		; /* empty */
-	if (n > 0 && s[n] != '\'')
-		return 1;
+	struct strbuf buf = STRBUF_INIT;
+	struct string_list kv = STRING_LIST_INIT_DUP;
+	int retval = -1; /* assume failure */
+	int i, name_i = -2, email_i = -2, date_i = -2, err = 0;
 
-	return 0;
+	if (strbuf_read_file(&buf, path, 256) <= 0) {
+		strbuf_release(&buf);
+		if (errno == ENOENT && allow_missing)
+			return 0;
+		else
+			return error_errno(_("could not open '%s' for reading"),
+					   path);
+	}
+
+	if (parse_key_value_squoted(buf.buf, &kv))
+		goto finish;
+
+	for (i = 0; i < kv.nr; i++) {
+		if (!strcmp(kv.items[i].string, "GIT_AUTHOR_NAME")) {
+			if (name_i != -2)
+				name_i = error(_("'GIT_AUTHOR_NAME' already given"));
+			else
+				name_i = i;
+		} else if (!strcmp(kv.items[i].string, "GIT_AUTHOR_EMAIL")) {
+			if (email_i != -2)
+				email_i = error(_("'GIT_AUTHOR_EMAIL' already given"));
+			else
+				email_i = i;
+		} else if (!strcmp(kv.items[i].string, "GIT_AUTHOR_DATE")) {
+			if (date_i != -2)
+				date_i = error(_("'GIT_AUTHOR_DATE' already given"));
+			else
+				date_i = i;
+		} else {
+			err = error(_("unknown variable '%s'"),
+				    kv.items[i].string);
+		}
+	}
+	if (name_i == -2)
+		error(_("missing 'GIT_AUTHOR_NAME'"));
+	if (email_i == -2)
+		error(_("missing 'GIT_AUTHOR_EMAIL'"));
+	if (date_i == -2)
+		error(_("missing 'GIT_AUTHOR_DATE'"));
+	if (date_i < 0 || email_i < 0 || date_i < 0 || err)
+		goto finish;
+	*name = kv.items[name_i].util;
+	*email = kv.items[email_i].util;
+	*date = kv.items[date_i].util;
+	retval = 0;
+finish:
+	string_list_clear(&kv, !!retval);
+	strbuf_release(&buf);
+	return retval;
 }
 
 /*
- * Read a list of environment variable assignments (such as the author-script
- * file) into an environment block. Returns -1 on error, 0 otherwise.
+ * Read a GIT_AUTHOR_NAME, GIT_AUTHOR_EMAIL AND GIT_AUTHOR_DATE from a
+ * file with shell quoting into struct argv_array. Returns -1 on
+ * error, 0 otherwise.
  */
 static int read_env_script(struct argv_array *env)
 {
-	struct strbuf script = STRBUF_INIT;
-	int i, count = 0, sq_bug;
-	const char *p2;
-	char *p;
+	char *name, *email, *date;
 
-	if (strbuf_read_file(&script, rebase_path_author_script(), 256) <= 0)
+	if (read_author_script(rebase_path_author_script(),
+			       &name, &email, &date, 0))
 		return -1;
-	/* write_author_script() used to quote incorrectly */
-	sq_bug = quoting_is_broken(script.buf, script.len);
-	for (p = script.buf; *p; p++)
-		if (sq_bug && skip_prefix(p, "'\\\\''", &p2))
-			strbuf_splice(&script, p - script.buf, p2 - p, "'", 1);
-		else if (skip_prefix(p, "'\\''", &p2))
-			strbuf_splice(&script, p - script.buf, p2 - p, "'", 1);
-		else if (*p == '\'')
-			strbuf_splice(&script, p-- - script.buf, 1, "", 0);
-		else if (*p == '\n') {
-			*p = '\0';
-			count++;
-		}
 
-	for (i = 0, p = script.buf; i < count; i++) {
-		argv_array_push(env, p);
-		p += strlen(p) + 1;
-	}
+	argv_array_pushf(env, "GIT_AUTHOR_NAME=%s", name);
+	argv_array_pushf(env, "GIT_AUTHOR_EMAIL=%s", email);
+	argv_array_pushf(env, "GIT_AUTHOR_DATE=%s", date);
+	free(name);
+	free(email);
+	free(date);
 
 	return 0;
 }
@@ -737,54 +813,28 @@ static char *get_author(const char *message)
 /* Read author-script and return an ident line (author <email> timestamp) */
 static const char *read_author_ident(struct strbuf *buf)
 {
-	const char *keys[] = {
-		"GIT_AUTHOR_NAME=", "GIT_AUTHOR_EMAIL=", "GIT_AUTHOR_DATE="
-	};
 	struct strbuf out = STRBUF_INIT;
-	char *in, *eol;
-	const char *val[3];
-	int i = 0;
+	char *name, *email, *date;
 
-	if (strbuf_read_file(buf, rebase_path_author_script(), 256) <= 0)
+	if (read_author_script(rebase_path_author_script(),
+			       &name, &email, &date, 0))
 		return NULL;
 
-	/* dequote values and construct ident line in-place */
-	for (in = buf->buf; i < 3 && in - buf->buf < buf->len; i++) {
-		if (!skip_prefix(in, keys[i], (const char **)&in)) {
-			warning(_("could not parse '%s' (looking for '%s')"),
-				rebase_path_author_script(), keys[i]);
-			return NULL;
-		}
-
-		eol = strchrnul(in, '\n');
-		*eol = '\0';
-		if (!sq_dequote(in)) {
-			warning(_("bad quoting on %s value in '%s'"),
-				keys[i], rebase_path_author_script());
-			return NULL;
-		}
-		val[i] = in;
-		in = eol + 1;
-	}
-
-	if (i < 3) {
-		warning(_("could not parse '%s' (looking for '%s')"),
-			rebase_path_author_script(), keys[i]);
-		return NULL;
-	}
-
 	/* validate date since fmt_ident() will die() on bad value */
-	if (parse_date(val[2], &out)){
+	if (parse_date(date, &out)){
 		warning(_("invalid date format '%s' in '%s'"),
-			val[2], rebase_path_author_script());
+			date, rebase_path_author_script());
 		strbuf_release(&out);
 		return NULL;
 	}
 
 	strbuf_reset(&out);
-	strbuf_addstr(&out, fmt_ident(val[0], val[1], val[2], 0));
+	strbuf_addstr(&out, fmt_ident(name, email, date, 0));
 	strbuf_swap(buf, &out);
 	strbuf_release(&out);
+	free(name);
+	free(email);
+	free(date);
 	return buf->buf;
 }