From 7481d2bfca7fd36f63fd437508be2bca338c9477 Mon Sep 17 00:00:00 2001 From: Mark Ruvald Pedersen Date: Thu, 10 Aug 2023 16:34:59 +0000 Subject: [PATCH 1/2] sequencer: truncate labels to accommodate loose refs Some commits may have unusually long subject lines. When those subject lines are used as labels in the `--rebase-merges` mode of `git rebase`, they can cause errors when writing the corresponding loose refs because most file systems have a maximal file name length of 255 (`NAME_MAX`). The symptom looks like this: $ git rebase --continue error: cannot lock ref 'refs/rewritten/SANITIZED-SUBJECT': Unable to create '.git/refs/rewritten/SANITIZED-SUBJECT.lock': File name too long - where SANITIZED-SUBJECT is very long Let's accommodate this situation by truncating the labels. Care must be taken in case the subject line contains multi-byte characters so as not to truncate in the middle of a character. Signed-off-by: Mark Ruvald Pedersen Signed-off-by: Johannes Schindelin Signed-off-by: Junio C Hamano --- git-compat-util.h | 4 ++++ sequencer.c | 41 ++++++++++++++++++++++++++++++++++++----- 2 files changed, 40 insertions(+), 5 deletions(-) diff --git a/git-compat-util.h b/git-compat-util.h index 5b2b99c17c..e1f7e15d9e 100644 --- a/git-compat-util.h +++ b/git-compat-util.h @@ -422,6 +422,10 @@ char *gitdirname(char *); #define PATH_MAX 4096 #endif +#ifndef NAME_MAX +#define NAME_MAX 255 +#endif + typedef uintmax_t timestamp_t; #define PRItime PRIuMAX #define parse_timestamp strtoumax diff --git a/sequencer.c b/sequencer.c index bceb6abcb6..c3e23a91f3 100644 --- a/sequencer.c +++ b/sequencer.c @@ -50,6 +50,15 @@ #define GIT_REFLOG_ACTION "GIT_REFLOG_ACTION" +/* + * To accommodate common filesystem limitations, where the loose refs' file + * names must not exceed `NAME_MAX`, the labels generated by `git rebase + * --rebase-merges` need to be truncated if the corresponding commit subjects + * are too long. + * Add some margin to stay clear from reaching `NAME_MAX`. + */ +#define GIT_MAX_LABEL_LENGTH ((NAME_MAX) - (LOCK_SUFFIX_LEN) - 16) + static const char sign_off_header[] = "Signed-off-by: "; static const char cherry_picked_prefix[] = "(cherry picked from commit "; @@ -5386,6 +5395,8 @@ static const char *label_oid(struct object_id *oid, const char *label, } } else { struct strbuf *buf = &state->buf; + int label_is_utf8 = 1; /* start with this assumption */ + size_t max_len = buf->len + GIT_MAX_LABEL_LENGTH; /* * Sanitize labels by replacing non-alpha-numeric characters @@ -5394,14 +5405,34 @@ static const char *label_oid(struct object_id *oid, const char *label, * * Note that we retain non-ASCII UTF-8 characters (identified * via the most significant bit). They should be all acceptable - * in file names. We do not validate the UTF-8 here, that's not - * the job of this function. + * in file names. + * + * As we will use the labels as names of (loose) refs, it is + * vital that the name not be longer than the maximum component + * size of the file system (`NAME_MAX`). We are careful to + * truncate the label accordingly, allowing for the `.lock` + * suffix and for the label to be UTF-8 encoded (i.e. we avoid + * truncating in the middle of a character). */ - for (; *label; label++) - if ((*label & 0x80) || isalnum(*label)) + for (; *label && buf->len + 1 < max_len; label++) + if (isalnum(*label) || + (!label_is_utf8 && (*label & 0x80))) strbuf_addch(buf, *label); + else if (*label & 0x80) { + const char *p = label; + + utf8_width(&p, NULL); + if (p) { + if (buf->len + (p - label) > max_len) + break; + strbuf_add(buf, label, p - label); + label = p - 1; + } else { + label_is_utf8 = 0; + strbuf_addch(buf, *label); + } /* avoid leading dash and double-dashes */ - else if (buf->len && buf->buf[buf->len - 1] != '-') + } else if (buf->len && buf->buf[buf->len - 1] != '-') strbuf_addch(buf, '-'); if (!buf->len) { strbuf_addstr(buf, "rev-"); From ac300bda10a137be06b7ac7c41452dbf8864f134 Mon Sep 17 00:00:00 2001 From: Johannes Schindelin Date: Thu, 10 Aug 2023 16:35:00 +0000 Subject: [PATCH 2/2] rebase: allow overriding the maximal length of the generated labels With this change, users can override the compiled-in default for the maximal length of the label names generated by `git rebase --rebase-merges`. Signed-off-by: Johannes Schindelin Signed-off-by: Mark Ruvald Pedersen Signed-off-by: Junio C Hamano --- Documentation/config/rebase.txt | 6 ++++++ sequencer.c | 8 ++++++-- t/t3430-rebase-merges.sh | 11 +++++++++++ 3 files changed, 23 insertions(+), 2 deletions(-) diff --git a/Documentation/config/rebase.txt b/Documentation/config/rebase.txt index afaf6dad99..9c248accec 100644 --- a/Documentation/config/rebase.txt +++ b/Documentation/config/rebase.txt @@ -77,3 +77,9 @@ rebase.rebaseMerges:: equivalent to `--no-rebase-merges`. Passing `--rebase-merges` on the command line, with or without an argument, overrides any `rebase.rebaseMerges` configuration. + +rebase.maxLabelLength:: + When generating label names from commit subjects, truncate the names to + this length. By default, the names are truncated to a little less than + `NAME_MAX` (to allow e.g. `.lock` files to be written for the + corresponding loose refs). diff --git a/sequencer.c b/sequencer.c index c3e23a91f3..5b9b81ea87 100644 --- a/sequencer.c +++ b/sequencer.c @@ -5339,6 +5339,7 @@ struct label_state { struct oidmap commit2label; struct hashmap labels; struct strbuf buf; + int max_label_length; }; static const char *label_oid(struct object_id *oid, const char *label, @@ -5396,7 +5397,7 @@ static const char *label_oid(struct object_id *oid, const char *label, } else { struct strbuf *buf = &state->buf; int label_is_utf8 = 1; /* start with this assumption */ - size_t max_len = buf->len + GIT_MAX_LABEL_LENGTH; + size_t max_len = buf->len + state->max_label_length; /* * Sanitize labels by replacing non-alpha-numeric characters @@ -5494,7 +5495,8 @@ static int make_script_with_merges(struct pretty_print_context *pp, struct string_entry *entry; struct oidset interesting = OIDSET_INIT, child_seen = OIDSET_INIT, shown = OIDSET_INIT; - struct label_state state = { OIDMAP_INIT, { NULL }, STRBUF_INIT }; + struct label_state state = + { OIDMAP_INIT, { NULL }, STRBUF_INIT, GIT_MAX_LABEL_LENGTH }; int abbr = flags & TODO_LIST_ABBREVIATE_CMDS; const char *cmd_pick = abbr ? "p" : "pick", @@ -5502,6 +5504,8 @@ static int make_script_with_merges(struct pretty_print_context *pp, *cmd_reset = abbr ? "t" : "reset", *cmd_merge = abbr ? "m" : "merge"; + git_config_get_int("rebase.maxlabellength", &state.max_label_length); + oidmap_init(&commit2todo, 0); oidmap_init(&state.commit2label, 0); hashmap_init(&state.labels, labels_cmp, NULL, 0); diff --git a/t/t3430-rebase-merges.sh b/t/t3430-rebase-merges.sh index 96ae0edf1e..ac5c390652 100755 --- a/t/t3430-rebase-merges.sh +++ b/t/t3430-rebase-merges.sh @@ -586,4 +586,15 @@ test_expect_success 'progress shows the correct total' ' test_line_count = 14 progress ' +test_expect_success 'truncate label names' ' + commit=$(git commit-tree -p HEAD^ -p HEAD -m "0123456789 我 123" HEAD^{tree}) && + git merge --ff-only $commit && + + done="$(git rev-parse --git-path rebase-merge/done)" && + git -c rebase.maxLabelLength=14 rebase --rebase-merges -x "cp \"$done\" out" --root && + grep "label 0123456789-我$" out && + git -c rebase.maxLabelLength=13 rebase --rebase-merges -x "cp \"$done\" out" --root && + grep "label 0123456789-$" out +' + test_done