From be1fd7de6291a86dab983210e55e70dd6fb48579 Mon Sep 17 00:00:00 2001 From: Phillip Wood Date: Fri, 1 May 2026 16:16:38 +0100 Subject: [PATCH 1/2] sequencer: factor out parsing of todo commands Move the code that parses todo commands into a separate function so that it can be shared with "git status" in the next commit. As we know the input is NUL terminated we do not pass a pointer to the end of the line and instead test for a blank line by looking for NUL, CR LF, or LF. We use starts_with() instead of starts_with_mem() for the same reason. This results in slightly different behavior when there a CR at the start of the line that is not followed by LF. Previously such a line was treated as a comment rather than an invalid line. Signed-off-by: Phillip Wood Signed-off-by: Junio C Hamano --- sequencer.c | 39 +++++++++++++++++++++++++++------------ sequencer.h | 8 ++++++++ 2 files changed, 35 insertions(+), 12 deletions(-) diff --git a/sequencer.c b/sequencer.c index b7d8dca47f..b8e860434a 100644 --- a/sequencer.c +++ b/sequencer.c @@ -2627,6 +2627,27 @@ static int is_command(enum todo_command command, const char **bol) return 0; } +bool sequencer_parse_todo_command(const char **p, enum todo_command *cmd) +{ + const char *s = *p; + + for (int i = 0; i < TODO_COMMENT; i++) + if (is_command(i, p)) { + *cmd = i; + return true; + } + + if (starts_with(s, comment_line_str)) { + *cmd = TODO_COMMENT; + return true; + } else if (s[0] == '\n' || (s[0] == '\r' && s[1] == '\n') || !s[0]) { + *cmd = TODO_COMMENT; + return true; + } + + return false; +} + static int check_label_or_ref_arg(enum todo_command command, const char *arg) { switch (command) { @@ -2716,30 +2737,24 @@ static int parse_insn_line(struct repository *r, struct replay_opts *opts, { struct object_id commit_oid; char *end_of_object_name; - int i, saved, status, padding; + int saved, status, padding; item->flags = 0; /* left-trim */ bol += strspn(bol, " \t"); - if (bol == eol || *bol == '\r' || starts_with_mem(bol, eol - bol, comment_line_str)) { - item->command = TODO_COMMENT; + if (!sequencer_parse_todo_command(&bol, &item->command)) + return error(_("invalid command '%.*s'"), + (int)strcspn(bol, " \t\r\n"), bol); + + if (item->command == TODO_COMMENT) { item->commit = NULL; item->arg_offset = bol - buf; item->arg_len = eol - bol; return 0; } - for (i = 0; i < TODO_COMMENT; i++) - if (is_command(i, &bol)) { - item->command = i; - break; - } - if (i >= TODO_COMMENT) - return error(_("invalid command '%.*s'"), - (int)strcspn(bol, " \t\r\n"), bol); - /* Eat up extra spaces/ tabs before object name */ padding = strspn(bol, " \t"); bol += padding; diff --git a/sequencer.h b/sequencer.h index a6fa670c7c..28fabef926 100644 --- a/sequencer.h +++ b/sequencer.h @@ -262,6 +262,14 @@ int read_author_script(const char *path, char **name, char **email, char **date, int write_basic_state(struct replay_opts *opts, const char *head_name, struct commit *onto, const struct object_id *orig_head); void sequencer_post_commit_cleanup(struct repository *r, int verbose); + +/* + * Try to parse the todo command pointed to by *p. On success sets cmd, + * advances p and returns true. On failure returns false, leaves p and + * cmd unchanged. + */ +bool sequencer_parse_todo_command(const char **p, enum todo_command *cmd); + int sequencer_get_last_command(struct repository* r, enum replay_action *action); int sequencer_determine_whence(struct repository *r, enum commit_whence *whence); From 07596ce695ba88d7845463b47f2019a3bee7749d Mon Sep 17 00:00:00 2001 From: Phillip Wood Date: Fri, 1 May 2026 16:16:39 +0100 Subject: [PATCH 2/2] status: improve rebase todo list parsing When there is rebase in progress "git status" displays the last couple of completed and the next couple of pending commands from the todo list. When it does this it tries to abbreviate the object ids of the commits to be picked. Unfortunately it does not abbreviate the object ids when the line starts with "fixup -C" or "merge -C". It also mistakenly replaces the refname in "reset main" and "update-ref refs/heads/main" with the object id that the ref points to. Use the function added in the last commit to parse the command name and only try to abbreviate the argument for commands that take an object id. When trying to abbreviate an object id, only replace the object name if it starts with the abbreviated object id so that labels or branch names that contain only hex digits are left unchanged. Comments are now processed after stripping any leading whitespace from the line. This matches what the sequencer does in parse_insn_line(). The existing test cases are updated to test a wider variety of commands. Only the pending commands in the tests are changed to avoid removing existing coverage. Helped-by: Elijah Newren Signed-off-by: Phillip Wood Signed-off-by: Junio C Hamano --- t/t7512-status-help.sh | 74 +++++++++++++++--------- wt-status.c | 127 +++++++++++++++++++++++++++++++++-------- 2 files changed, 151 insertions(+), 50 deletions(-) diff --git a/t/t7512-status-help.sh b/t/t7512-status-help.sh index 08e82f7914..aca4b6d332 100755 --- a/t/t7512-status-help.sh +++ b/t/t7512-status-help.sh @@ -224,7 +224,7 @@ test_expect_success 'status when splitting a commit' ' COMMIT3=$(git rev-parse --short split_commit) && test_commit four_split main.txt four && COMMIT4=$(git rev-parse --short split_commit) && - FAKE_LINES="1 edit 2 3" && + FAKE_LINES="reword 1 edit 2 fixup_-C 3" && export FAKE_LINES && test_when_finished "git rebase --abort" && ONTO=$(git rev-parse --short HEAD~3) && @@ -233,10 +233,10 @@ test_expect_success 'status when splitting a commit' ' cat >expected <todo <<-EOF && + edit several_edits^^ # two_edits + edit several_edits^ # three_edits + merge $(git rev-parse main) $(git rev-parse several_edits) + EOF + ( + set_replace_editor todo && + git rebase -i HEAD~3 + ) && git commit --amend -m "c" && git rebase --continue && git commit --amend -m "d" && @@ -477,7 +483,7 @@ Last commands done (2 commands done): edit $COMMIT2 # two_edits edit $COMMIT3 # three_edits Next command to do (1 remaining command): - pick $COMMIT4 # four_edits + merge $(git rev-parse --short main) $COMMIT4 (use "git rebase --edit-todo" to view and edit) You are currently editing a commit while rebasing branch '\''several_edits'\'' on '\''$ONTO'\''. (use "git commit --amend" to amend the current commit) @@ -525,14 +531,21 @@ EOF test_expect_success 'status: (split first edit) second edit and split' ' git reset --hard several_edits && - FAKE_LINES="edit 1 edit 2 3" && - export FAKE_LINES && test_when_finished "git rebase --abort" && COMMIT2=$(git rev-parse --short several_edits^^) && COMMIT3=$(git rev-parse --short several_edits^) && COMMIT4=$(git rev-parse --short several_edits) && + cat >todo <<-EOF && + edit several_edits^^ # two_edits + edit several_edits^ # three_edits + reset $(git rev-parse main) + merge -C several_edits topic # title + EOF ONTO=$(git rev-parse --short HEAD~3) && - git rebase -i HEAD~3 && + ( + set_replace_editor todo && + git rebase -i HEAD~3 + ) && git reset HEAD^ && git add main.txt && git commit --amend -m "f" && @@ -543,8 +556,9 @@ interactive rebase in progress; onto $ONTO Last commands done (2 commands done): edit $COMMIT2 # two_edits edit $COMMIT3 # three_edits -Next command to do (1 remaining command): - pick $COMMIT4 # four_edits +Next commands to do (2 remaining commands): + reset $(git rev-parse --short main) + merge -C $COMMIT4 topic # title (use "git rebase --edit-todo" to view and edit) You are currently splitting a commit while rebasing branch '\''several_edits'\'' on '\''$ONTO'\''. (Once your working directory is clean, run "git rebase --continue") @@ -563,14 +577,21 @@ EOF test_expect_success 'status: (split first edit) second edit and amend' ' git reset --hard several_edits && - FAKE_LINES="edit 1 edit 2 3" && - export FAKE_LINES && test_when_finished "git rebase --abort" && + git branch cafe main && COMMIT2=$(git rev-parse --short several_edits^^) && COMMIT3=$(git rev-parse --short several_edits^) && - COMMIT4=$(git rev-parse --short several_edits) && + cat >todo <<-EOF && + edit several_edits^^ # two_edits + edit several_edits^ # three_edits + update-ref refs/heads/main + reset cafe + EOF ONTO=$(git rev-parse --short HEAD~3) && - git rebase -i HEAD~3 && + ( + set_replace_editor todo && + git rebase -i HEAD~3 + ) && git reset HEAD^ && git add main.txt && git commit --amend -m "g" && @@ -581,8 +602,9 @@ interactive rebase in progress; onto $ONTO Last commands done (2 commands done): edit $COMMIT2 # two_edits edit $COMMIT3 # three_edits -Next command to do (1 remaining command): - pick $COMMIT4 # four_edits +Next commands to do (2 remaining commands): + update-ref refs/heads/main + reset cafe (use "git rebase --edit-todo" to view and edit) You are currently editing a commit while rebasing branch '\''several_edits'\'' on '\''$ONTO'\''. (use "git commit --amend" to amend the current commit) diff --git a/wt-status.c b/wt-status.c index 479ccc3304..94c159d9d4 100644 --- a/wt-status.c +++ b/wt-status.c @@ -1365,35 +1365,118 @@ static int split_commit_in_progress(struct wt_status *s) return split_in_progress; } +/* + * If the whitespace-delimited token starting at or just after *pp * + * is a hex object id that is longer than its default abbreviation, * + * abbreviate it in-place, shrinking `line` accordingly. On return + * *pp points one past the (possibly abbreviated) token. Leaves both + * `line` and *pp-advanced-past-the-token unchanged in all other cases + * (non-hex token, unresolvable, or a refname that happens to consist + * only of hex digits). + */ +static void abbrev_oid_in_line(struct repository *r, + struct strbuf *line, char **pp) +{ + char *p = *pp; + char *end_of_object_name, saved; + const char *abbrev; + struct object_id oid; + bool have_oid; + + p += strspn(p, " \t"); + end_of_object_name = p + strcspn(p, " \t"); + /* + * For "merge" and "reset" the object name may be a label or + * ref rather than a hex object id. Only abbreviate the object + * name if it is a hex object id. + */ + for (const char *q = p; q < end_of_object_name; q++) { + if (!isxdigit(*q)) + goto out; + } + saved = *end_of_object_name; + *end_of_object_name = '\0'; + have_oid = !repo_get_oid(r, p, &oid); + *end_of_object_name = saved; + if (!have_oid) + goto out; /* object name was a label */ + abbrev = repo_find_unique_abbrev(r, &oid, DEFAULT_ABBREV); + if (!starts_with(p, abbrev)) + goto out; /* object name was a refname containing only xdigits */ + p += strlen(abbrev); + strbuf_remove(line, p - line->buf, end_of_object_name - p); + end_of_object_name = p; +out: + *pp = end_of_object_name; +} + +static void skip_dash_c(char **pp) +{ + char *p = *pp; + + p += strspn(p, " \t"); + /* The (void) cast is required to silence -Wunused-value */ + (void)(skip_prefix(p, "-C", &p) || skip_prefix(p, "-c", &p)); + *pp = p; +} + /* * Turn * "pick d6a2f0303e897ec257dd0e0a39a5ccb709bc2047 some message" * into * "pick d6a2f03 some message" * - * The function assumes that the line does not contain useless spaces - * before or after the command. + * Returns false on comment lines, true otherwise */ -static void abbrev_oid_in_line(struct repository *r, struct strbuf *line) +static bool format_todo_line(struct repository *r, struct strbuf *line) { - struct string_list split = STRING_LIST_INIT_DUP; - struct object_id oid; + enum todo_command cmd; + char *p = line->buf; - if (starts_with(line->buf, "exec ") || - starts_with(line->buf, "x ") || - starts_with(line->buf, "label ") || - starts_with(line->buf, "l ")) - return; + if (!sequencer_parse_todo_command((const char**)&p, &cmd)) + return true; /* keep invalid lines */ - if ((2 <= string_list_split(&split, line->buf, " ", 2)) && - !repo_get_oid(r, split.items[1].string, &oid)) { - strbuf_reset(line); - strbuf_addf(line, "%s ", split.items[0].string); - strbuf_add_unique_abbrev(line, &oid, DEFAULT_ABBREV); - for (size_t i = 2; i < split.nr; i++) - strbuf_addf(line, " %s", split.items[i].string); + switch (cmd) { + case TODO_COMMENT: + return false; + + case TODO_MERGE: + skip_dash_c(&p); + while (true) { + p += strspn(p, " \t"); + if (!p[0] || (p[0] == '#' && (!p[1] || isspace(p[1])))) + break; + abbrev_oid_in_line(r, line, &p); + } + break; + + case TODO_FIXUP: + skip_dash_c(&p); + /* fallthrough */ + case TODO_DROP: + case TODO_EDIT: + case TODO_PICK: + case TODO_RESET: + case TODO_REVERT: + case TODO_REWORD: + case TODO_SQUASH: + abbrev_oid_in_line(r, line, &p); + break; + + /* + * Avoid "default" and instead list all the other commands so + * that -Wswitch (which is included in -Wall) warns if a new + * command is added without handling it in this function. + */ + case TODO_BREAK: + case TODO_EXEC: + case TODO_LABEL: + case TODO_NOOP: + case TODO_UPDATE_REF: + break; } - string_list_clear(&split, 0); + + return true; } static int read_rebase_todolist(struct repository *r, const char *fname, struct string_list *lines) @@ -1411,13 +1494,9 @@ static int read_rebase_todolist(struct repository *r, const char *fname, struct repo_git_path_replace(r, &buf, "%s", fname)); } while (!strbuf_getline_lf(&buf, f)) { - if (starts_with(buf.buf, comment_line_str)) - continue; strbuf_trim(&buf); - if (!buf.len) - continue; - abbrev_oid_in_line(r, &buf); - string_list_append(lines, buf.buf); + if (format_todo_line(r, &buf)) + string_list_append(lines, buf.buf); } fclose(f);