diff options
| -rw-r--r-- | Documentation/RelNotes/2.45.0.txt | 64 | ||||
| -rw-r--r-- | Documentation/config/receive.txt | 2 | ||||
| -rw-r--r-- | Documentation/date-formats.txt | 2 | ||||
| -rw-r--r-- | Documentation/git-fast-import.txt | 37 | ||||
| -rw-r--r-- | Documentation/git-replay.txt | 2 | ||||
| -rwxr-xr-x | GIT-VERSION-GEN | 2 | ||||
| -rw-r--r-- | apply.c | 33 | ||||
| -rw-r--r-- | bisect.c | 39 | ||||
| -rw-r--r-- | builtin/fast-import.c | 162 | ||||
| -rw-r--r-- | builtin/receive-pack.c | 21 | ||||
| -rw-r--r-- | editor.c | 7 | ||||
| -rw-r--r-- | git-compat-util.h | 1 | ||||
| -rw-r--r-- | imap-send.c | 35 | ||||
| -rw-r--r-- | mem-pool.c | 3 | ||||
| -rw-r--r-- | midx.c | 7 | ||||
| -rw-r--r-- | pack-bitmap.c | 41 | ||||
| -rw-r--r-- | reftable/block.c | 176 | ||||
| -rw-r--r-- | reftable/block.h | 47 | ||||
| -rw-r--r-- | reftable/block_test.c | 6 | ||||
| -rw-r--r-- | reftable/iter.c | 2 | ||||
| -rw-r--r-- | reftable/reader.c | 176 | ||||
| -rw-r--r-- | rerere.c | 5 | ||||
| -rw-r--r-- | run-command.c | 19 | ||||
| -rw-r--r-- | run-command.h | 7 | ||||
| -rw-r--r-- | strbuf.c | 4 | ||||
| -rwxr-xr-x | t/t4200-rerere.sh | 63 | ||||
| -rwxr-xr-x | t/t5326-multi-pack-bitmaps.sh | 17 | ||||
| -rwxr-xr-x | t/t9300-fast-import.sh | 630 | ||||
| -rwxr-xr-x | t/t9604-cvsimport-timestamps.sh | 29 | ||||
| -rw-r--r-- | trailer.c | 81 | ||||
| -rw-r--r-- | trailer.h | 13 | ||||
| -rw-r--r-- | wrapper.c | 2 |
32 files changed, 1104 insertions, 631 deletions
diff --git a/Documentation/RelNotes/2.45.0.txt b/Documentation/RelNotes/2.45.0.txt index 0570dcd877..fec193679f 100644 --- a/Documentation/RelNotes/2.45.0.txt +++ b/Documentation/RelNotes/2.45.0.txt @@ -77,8 +77,10 @@ UI, Workflows & Features skip showing the hunk immediately after it has already been shown, and an additional action to explicitly ask to reshow the current hunk. - * "git pack-refs" learned the "--auto" option, which is a useful - addition to be triggered from "git gc --auto". + * "git pack-refs" learned the "--auto" option, which defers the decision of + whether and how to pack to the ref backend. This is used by the reftable + backend to avoid repacking of an already-optimal ref database. The new mode + is triggered from "git gc --auto". * "git add -u <pathspec>" and "git commit [-i] <pathspec>" did not diagnose a pathspec element that did not match any files in certain @@ -86,6 +88,19 @@ UI, Workflows & Features * The userdiff patterns for C# has been updated. + * Git writes a "waiting for your editor" message on an incomplete + line after launching an editor, and then append another error + message on the same line if the editor errors out. It now clears + the "waiting for..." line before giving the error message. + + * The filename used for rejected hunks "git apply --reject" creates + was limited to PATH_MAX, which has been lifted. + + * When "git bisect" reports the commit it determined to be the + culprit, we used to show it in a format that does not honor common + UI tweaks, like log.date and log.decorate. The code has been + taught to use "git show" to follow more customizations. + Performance, Internal Implementation, Development Support etc. @@ -100,7 +115,7 @@ Performance, Internal Implementation, Development Support etc. * The way placeholders are to be marked-up in documentation have been specified; use "_<placeholder>_" to typeset the word inside a pair - of <angle-brakets> emphasized. + of <angle-brackets> emphasized. * "git --no-lazy-fetch cmd" allows to run "cmd" while disabling lazy fetching of objects from the promisor remote, which may be handy @@ -110,9 +125,6 @@ Performance, Internal Implementation, Development Support etc. clean.requireForce has been simplified, together with the documentation. - * The code to iterate over refs with the reftable backend has seen - some optimization. - * Uses of xwrite() helper have been audited and updated for better error checking and simpler code. @@ -185,6 +197,19 @@ Performance, Internal Implementation, Development Support etc. operations accumulate many entries has been improved to avoid accumulating too many tables uncollected. + * The code to iterate over reftable blocks has seen some optimization + to reduce memory allocation and deallocation. + + * The way "git fast-import" handles paths described in its input has + been tightened up and more clearly documented. + + * The cvsimport tests required that the platform understands + traditional timezone notations like CST6CDT, which has been + updated to work on those systems as long as they understand + POSIX notation with explicit tz transition dates. + + * The code to format trailers have been cleaned up. + Fixes since v2.44 ----------------- @@ -231,7 +256,7 @@ Fixes since v2.44 (merge 5edd126720 jk/reflog-special-cases-fix later to maint). * An error message from "git upload-pack", which responds to "git - fetch" requests, had a trialing NUL in it, which has been + fetch" requests, had a trailing NUL in it, which has been corrected. (merge 3f4c7a0805 sg/upload-pack-error-message-fix later to maint). @@ -248,7 +273,7 @@ Fixes since v2.44 This has been corrected. (merge 199f44cb2e ps/remote-helper-repo-initialization-fix later to maint). - * Various parts of upload-pack has been updated to bound the resource + * Various parts of upload-pack have been updated to bound the resource consumption relative to the size of the repository to protect from abusive clients. (merge 6cd05e768b jk/upload-pack-bounded-resources later to maint). @@ -295,11 +320,11 @@ Fixes since v2.44 variable that is no longer used. (merge 72a8d3f027 pw/rebase-i-ignore-cherry-pick-help-environment later to maint). - * The code to find the effective end of log message can fall into an + * The code to find the effective end of log messages can fall into an endless loop, which has been corrected. (merge 2541cba2d6 fs/find-end-of-log-message-fix later to maint). - * Mark-ups used in the documentation has been improved for + * Mark-up used in the documentation has been improved for consistency. (merge 45d5ed3e50 ja/doc-markup-fixes later to maint). @@ -393,7 +418,7 @@ Fixes since v2.44 configuration variable used to leak, which has been corrected. (merge 0e0fefb29f jc/unleak-core-excludesfile later to maint). - * vreportf(), which is usede by error() and friends, has been taught + * vreportf(), which is used by error() and friends, has been taught to give the error message printf-format string when its vsnprintf() call fails, instead of showing nothing useful to identify the nature of the error. @@ -402,6 +427,20 @@ Fixes since v2.44 * Adjust to an upcoming changes to GNU make that breaks our Makefiles. (merge 227b8fd902 tb/make-indent-conditional-with-non-spaces later to maint). + * Git 2.44 introduced a regression that makes the updated code to + barf in repositories with multi-pack index written by older + versions of Git, which has been corrected. + + * When .git/rr-cache/ rerere database gets corrupted or rerere is fed to + work on a file with conflicted hunks resolved incompletely, the rerere + machinery got confused and segfaulted, which has been corrected. + (merge 167395bb47 mr/rerere-crash-fix later to maint). + + * The "receive-pack" program (which responds to "git push") was not + converted to run "git maintenance --auto" when other codepaths that + used to run "git gc --auto" were updated, which has been corrected. + (merge 7bf3057d9c ps/run-auto-maintenance-in-receive-pack later to maint). + * Other code cleanup, docfix, build fix, etc. (merge f0e578c69c rs/use-xstrncmpz later to maint). (merge 83e6eb7d7a ba/credential-test-clean-fix later to maint). @@ -432,3 +471,6 @@ Fixes since v2.44 (merge b4454d5a7b pw/t3428-cleanup later to maint). (merge 84a7c33a4b pf/commitish-committish later to maint). (merge 8882ee9d68 la/mailmap-entry later to maint). + (merge 44bdba2fa6 rs/no-openssl-compilation-fix-on-macos later to maint). + (merge f412d72c19 yb/replay-doc-linkfix later to maint). + (merge 5da40be8d7 xx/rfc2822-date-format-in-doc later to maint). diff --git a/Documentation/config/receive.txt b/Documentation/config/receive.txt index c77e55b1cd..36a1e6f2d2 100644 --- a/Documentation/config/receive.txt +++ b/Documentation/config/receive.txt @@ -8,7 +8,7 @@ receive.advertisePushOptions:: capability to its clients. False by default. receive.autogc:: - By default, git-receive-pack will run "git-gc --auto" after + By default, git-receive-pack will run "git maintenance run --auto" after receiving data from git-push and updating refs. You can stop it by setting this variable to false. diff --git a/Documentation/date-formats.txt b/Documentation/date-formats.txt index 67645cae64..e24517c496 100644 --- a/Documentation/date-formats.txt +++ b/Documentation/date-formats.txt @@ -11,7 +11,7 @@ Git internal format:: For example CET (which is 1 hour ahead of UTC) is `+0100`. RFC 2822:: - The standard email format as described by RFC 2822, for example + The standard date format as described by RFC 2822, for example `Thu, 07 Apr 2005 22:13:13 +0200`. ISO 8601:: diff --git a/Documentation/git-fast-import.txt b/Documentation/git-fast-import.txt index b2607366b9..3d435157a6 100644 --- a/Documentation/git-fast-import.txt +++ b/Documentation/git-fast-import.txt @@ -303,7 +303,7 @@ and some sanity checks on the numeric values may also be performed. with e.g. bogus timezone values. `rfc2822`:: - This is the standard email format as described by RFC 2822. + This is the standard date format as described by RFC 2822. + An example value is ``Tue Feb 6 11:22:18 2007 -0500''. The Git parser is accurate, but a little on the lenient side. It is the @@ -630,18 +630,28 @@ in octal. Git only supports the following modes: In both formats `<path>` is the complete path of the file to be added (if not already existing) or modified (if already existing). -A `<path>` string must use UNIX-style directory separators (forward -slash `/`), may contain any byte other than `LF`, and must not -start with double quote (`"`). - -A path can use C-style string quoting; this is accepted in all cases -and mandatory if the filename starts with double quote or contains -`LF`. In C-style quoting, the complete name should be surrounded with -double quotes, and any `LF`, backslash, or double quote characters -must be escaped by preceding them with a backslash (e.g., -`"path/with\n, \\ and \" in it"`). - -The value of `<path>` must be in canonical form. That is it must not: +A `<path>` can be written as unquoted bytes or a C-style quoted string. + +When a `<path>` does not start with a double quote (`"`), it is an +unquoted string and is parsed as literal bytes without any escape +sequences. However, if the filename contains `LF` or starts with double +quote, it cannot be represented as an unquoted string and must be +quoted. Additionally, the source `<path>` in `filecopy` or `filerename` +must be quoted if it contains SP. + +When a `<path>` starts with a double quote (`"`), it is a C-style quoted +string, where the complete filename is enclosed in a pair of double +quotes and escape sequences are used. Certain characters must be escaped +by preceding them with a backslash: `LF` is written as `\n`, backslash +as `\\`, and double quote as `\"`. Some characters may optionally be +written with escape sequences: `\a` for bell, `\b` for backspace, `\f` +for form feed, `\n` for line feed, `\r` for carriage return, `\t` for +horizontal tab, and `\v` for vertical tab. Any byte can be written with +3-digit octal codes (e.g., `\033`). All filenames can be represented as +quoted strings. + +A `<path>` must use UNIX-style directory separators (forward slash `/`) +and its value must be in canonical form. That is it must not: * contain an empty directory component (e.g. `foo//bar` is invalid), * end with a directory separator (e.g. `foo/` is invalid), @@ -651,6 +661,7 @@ The value of `<path>` must be in canonical form. That is it must not: The root of the tree can be represented by an empty string as `<path>`. +`<path>` cannot contain NUL, either literally or escaped as `\000`. It is recommended that `<path>` always be encoded using UTF-8. `filedelete` diff --git a/Documentation/git-replay.txt b/Documentation/git-replay.txt index f6c269c62d..8f3300c683 100644 --- a/Documentation/git-replay.txt +++ b/Documentation/git-replay.txt @@ -46,7 +46,7 @@ the new commits (in other words, this mimics a cherry-pick operation). Range of commits to replay. More than one <revision-range> can be passed, but in `--advance <branch>` mode, they should have a single tip, so that it's clear where <branch> should point - to. See "Specifying Ranges" in linkgit:git-rev-parse and the + to. See "Specifying Ranges" in linkgit:git-rev-parse[1] and the "Commit Limiting" options below. include::rev-list-options.txt[] diff --git a/GIT-VERSION-GEN b/GIT-VERSION-GEN index dabd2b5b89..c92f98b3db 100755 --- a/GIT-VERSION-GEN +++ b/GIT-VERSION-GEN @@ -1,7 +1,7 @@ #!/bin/sh GVF=GIT-VERSION-FILE -DEF_VER=v2.45.0-rc0 +DEF_VER=v2.45.0-rc1 LF=' ' @@ -4614,7 +4614,7 @@ static int write_out_one_result(struct apply_state *state, static int write_out_one_reject(struct apply_state *state, struct patch *patch) { FILE *rej; - char namebuf[PATH_MAX]; + char *namebuf; struct fragment *frag; int fd, cnt = 0; struct strbuf sb = STRBUF_INIT; @@ -4647,30 +4647,29 @@ static int write_out_one_reject(struct apply_state *state, struct patch *patch) say_patch_name(stderr, sb.buf, patch); strbuf_release(&sb); - cnt = strlen(patch->new_name); - if (ARRAY_SIZE(namebuf) <= cnt + 5) { - cnt = ARRAY_SIZE(namebuf) - 5; - warning(_("truncating .rej filename to %.*s.rej"), - cnt - 1, patch->new_name); - } - memcpy(namebuf, patch->new_name, cnt); - memcpy(namebuf + cnt, ".rej", 5); + namebuf = xstrfmt("%s.rej", patch->new_name); fd = open(namebuf, O_CREAT | O_EXCL | O_WRONLY, 0666); if (fd < 0) { - if (errno != EEXIST) - return error_errno(_("cannot open %s"), namebuf); - if (unlink(namebuf)) - return error_errno(_("cannot unlink '%s'"), namebuf); + if (errno != EEXIST) { + error_errno(_("cannot open %s"), namebuf); + goto error; + } + if (unlink(namebuf)) { + error_errno(_("cannot unlink '%s'"), namebuf); + goto error; + } fd = open(namebuf, O_CREAT | O_EXCL | O_WRONLY, 0666); - if (fd < 0) - return error_errno(_("cannot open %s"), namebuf); + if (fd < 0) { + error_errno(_("cannot open %s"), namebuf); + goto error; + } } rej = fdopen(fd, "w"); if (!rej) { error_errno(_("cannot open %s"), namebuf); close(fd); - return -1; + goto error; } /* Normal git tools never deal with .rej, so do not pretend @@ -4695,6 +4694,8 @@ static int write_out_one_reject(struct apply_state *state, struct patch *patch) fputc('\n', rej); } fclose(rej); +error: + free(namebuf); return -1; } @@ -946,23 +946,32 @@ static enum bisect_error check_good_are_ancestors_of_bad(struct repository *r, } /* - * This does "git diff-tree --pretty COMMIT" without one fork+exec. + * Display a commit summary to the user. */ -static void show_diff_tree(struct repository *r, - const char *prefix, - struct commit *commit) +static void show_commit(struct commit *commit) { - const char *argv[] = { - "diff-tree", "--pretty", "--stat", "--summary", "--cc", NULL - }; - struct rev_info opt; - - git_config(git_diff_ui_config, NULL); - repo_init_revisions(r, &opt, prefix); + struct child_process show = CHILD_PROCESS_INIT; - setup_revisions(ARRAY_SIZE(argv) - 1, argv, &opt, NULL); - log_tree_commit(&opt, commit); - release_revisions(&opt); + /* + * Call git show with --no-pager, as it would otherwise + * paginate the "git show" output only, not the output + * from bisect_next_all(); this can be fixed by moving + * it into a --format parameter, but that would override + * the user's default options for "git show", which we + * are trying to honour. + */ + strvec_pushl(&show.args, + "--no-pager", + "show", + "--stat", + "--summary", + "--no-abbrev-commit", + "--diff-merges=first-parent", + oid_to_hex(&commit->object.oid), NULL); + show.git_cmd = 1; + if (run_command(&show)) + die(_("unable to start 'show' for object '%s'"), + oid_to_hex(&commit->object.oid)); } /* @@ -1079,7 +1088,7 @@ enum bisect_error bisect_next_all(struct repository *r, const char *prefix) printf("%s is the first %s commit\n", oid_to_hex(bisect_rev), term_bad); - show_diff_tree(r, prefix, revs.commits->item); + show_commit(revs.commits->item); /* * This means the bisection process succeeded. * Using BISECT_INTERNAL_SUCCESS_1ST_BAD_FOUND (-10) diff --git a/builtin/fast-import.c b/builtin/fast-import.c index 782bda007c..dc5a9d32dd 100644 --- a/builtin/fast-import.c +++ b/builtin/fast-import.c @@ -2210,7 +2210,7 @@ static int parse_mapped_oid_hex(const char *hex, struct object_id *oid, const ch * * idnum ::= ':' bigint; * - * Return the first character after the value in *endptr. + * Update *endptr to point to the first character after the value. * * Complain if the following character is not what is expected, * either a space or end of the string. @@ -2243,8 +2243,8 @@ static uintmax_t parse_mark_ref_eol(const char *p) } /* - * Parse the mark reference, demanding a trailing space. Return a - * pointer to the space. + * Parse the mark reference, demanding a trailing space. Update *p to + * point to the first character after the space. */ static uintmax_t parse_mark_ref_space(const char **p) { @@ -2258,10 +2258,62 @@ static uintmax_t parse_mark_ref_space(const char **p) return mark; } +/* + * Parse the path string into the strbuf. The path can either be quoted with + * escape sequences or unquoted without escape sequences. Unquoted strings may + * contain spaces only if `is_last_field` is nonzero; otherwise, it stops + * parsing at the first space. + */ +static void parse_path(struct strbuf *sb, const char *p, const char **endp, + int is_last_field, const char *field) +{ + if (*p == '"') { + if (unquote_c_style(sb, p, endp)) + die("Invalid %s: %s", field, command_buf.buf); + if (strlen(sb->buf) != sb->len) + die("NUL in %s: %s", field, command_buf.buf); + } else { + /* + * Unless we are parsing the last field of a line, + * SP is the end of this field. + */ + *endp = is_last_field + ? p + strlen(p) + : strchrnul(p, ' '); + strbuf_add(sb, p, *endp - p); + } +} + +/* + * Parse the path string into the strbuf, and complain if this is not the end of + * the string. Unquoted strings may contain spaces. + */ +static void parse_path_eol(struct strbuf *sb, const char *p, const char *field) +{ + const char *end; + + parse_path(sb, p, &end, 1, field); + if (*end) + die("Garbage after %s: %s", field, command_buf.buf); +} + +/* + * Parse the path string into the strbuf, and ensure it is followed by a space. + * Unquoted strings may not contain spaces. Update *endp to point to the first + * character after the space. + */ +static void parse_path_space(struct strbuf *sb, const char *p, + const char **endp, const char *field) +{ + parse_path(sb, p, endp, 0, field); + if (**endp != ' ') + die("Missing space after %s: %s", field, command_buf.buf); + (*endp)++; +} + static void file_change_m(const char *p, struct branch *b) { - static struct strbuf uq = STRBUF_INIT; - const char *endp; + static struct strbuf path = STRBUF_INIT; struct object_entry *oe; struct object_id oid; uint16_t mode, inline_data = 0; @@ -2298,16 +2350,12 @@ static void file_change_m(const char *p, struct branch *b) die("Missing space after SHA1: %s", command_buf.buf); } - strbuf_reset(&uq); - if (!unquote_c_style(&uq, p, &endp)) { - if (*endp) - die("Garbage after path in: %s", command_buf.buf); - p = uq.buf; - } + strbuf_reset(&path); + parse_path_eol(&path, p, "path"); /* Git does not track empty, non-toplevel directories. */ - if (S_ISDIR(mode) && is_empty_tree_oid(&oid) && *p) { - tree_content_remove(&b->branch_tree, p, NULL, 0); + if (S_ISDIR(mode) && is_empty_tree_oid(&oid) && *path.buf) { + tree_content_remove(&b->branch_tree, path.buf, NULL, 0); return; } @@ -2328,10 +2376,6 @@ static void file_change_m(const char *p, struct branch *b) if (S_ISDIR(mode)) die("Directories cannot be specified 'inline': %s", command_buf.buf); - if (p != uq.buf) { - strbuf_addstr(&uq, p); - p = uq.buf; - } while (read_next_command() != EOF) { const char *v; if (skip_prefix(command_buf.buf, "cat-blob ", &v)) @@ -2357,74 +2401,48 @@ static void file_change_m(const char *p, struct branch *b) command_buf.buf); } - if (!*p) { + if (!*path.buf) { tree_content_replace(&b->branch_tree, &oid, mode, NULL); return; } - tree_content_set(&b->branch_tree, p, &oid, mode, NULL); + tree_content_set(&b->branch_tree, path.buf, &oid, mode, NULL); } static void file_change_d(const char *p, struct branch *b) { - static struct strbuf uq = STRBUF_INIT; - const char *endp; + static struct strbuf path = STRBUF_INIT; - strbuf_reset(&uq); - if (!unquote_c_style(&uq, p, &endp)) { - if (*endp) - die("Garbage after path in: %s", command_buf.buf); - p = uq.buf; - } - tree_content_remove(&b->branch_tree, p, NULL, 1); + strbuf_reset(&path); + parse_path_eol(&path, p, "path"); + tree_content_remove(&b->branch_tree, path.buf, NULL, 1); } -static void file_change_cr(const char *s, struct branch *b, int rename) +static void file_change_cr(const char *p, struct branch *b, int rename) { - const char *d; - static struct strbuf s_uq = STRBUF_INIT; - static struct strbuf d_uq = STRBUF_INIT; - const char *endp; + static struct strbuf source = STRBUF_INIT; + static struct strbuf dest = STRBUF_INIT; struct tree_entry leaf; - strbuf_reset(&s_uq); - if (!unquote_c_style(&s_uq, s, &endp)) { - if (*endp != ' ') - die("Missing space after source: %s", command_buf.buf); - } else { - endp = strchr(s, ' '); - if (!endp) - die("Missing space after source: %s", command_buf.buf); - strbuf_add(&s_uq, s, endp - s); - } - s = s_uq.buf; - - endp++; - if (!*endp) - die("Missing dest: %s", command_buf.buf); - - d = endp; - strbuf_reset(&d_uq); - if (!unquote_c_style(&d_uq, d, &endp)) { - if (*endp) - die("Garbage after dest in: %s", command_buf.buf); - d = d_uq.buf; - } + strbuf_reset(&source); + parse_path_space(&source, p, &p, "source"); + strbuf_reset(&dest); + parse_path_eol(&dest, p, "dest"); memset(&leaf, 0, sizeof(leaf)); if (rename) - tree_content_remove(&b->branch_tree, s, &leaf, 1); + tree_content_remove(&b->branch_tree, source.buf, &leaf, 1); else - tree_content_get(&b->branch_tree, s, &leaf, 1); + tree_content_get(&b->branch_tree, source.buf, &leaf, 1); if (!leaf.versions[1].mode) - die("Path %s not in branch", s); - if (!*d) { /* C "path/to/subdir" "" */ + die("Path %s not in branch", source.buf); + if (!*dest.buf) { /* C "path/to/subdir" "" */ tree_content_replace(&b->branch_tree, &leaf.versions[1].oid, leaf.versions[1].mode, leaf.tree); return; } - tree_content_set(&b->branch_tree, d, + tree_content_set(&b->branch_tree, dest.buf, &leaf.versions[1].oid, leaf.versions[1].mode, leaf.tree); @@ -2432,7 +2450,6 @@ static void file_change_cr(const char *s, struct branch *b, int rename) static void note_change_n(const char *p, struct branch *b, unsigned char *old_fanout) { - static struct strbuf uq = STRBUF_INIT; struct object_entry *oe; struct branch *s; struct object_id oid, commit_oid; @@ -2497,10 +2514,6 @@ static void note_change_n(const char *p, struct branch *b, unsigned char *old_fa die("Invalid ref name or SHA1 expression: %s", p); if (inline_data) { - if (p != uq.buf) { - strbuf_addstr(&uq, p); - p = uq.buf; - } read_next_command(); parse_and_store_blob(&last_blob, &oid, 0); } else if (oe) { @@ -3152,6 +3165,7 @@ static void print_ls(int mode, const unsigned char *hash, const char *path) static void parse_ls(const char *p, struct branch *b) { + static struct strbuf path = STRBUF_INIT; struct tree_entry *root = NULL; struct tree_entry leaf = {NULL}; @@ -3168,17 +3182,9 @@ static void parse_ls(const char *p, struct branch *b) root->versions[1].mode = S_IFDIR; load_tree(root); } - if (*p == '"') { - static struct strbuf uq = STRBUF_INIT; - const char *endp; - strbuf_reset(&uq); - if (unquote_c_style(&uq, p, &endp)) - die("Invalid path: %s", command_buf.buf); - if (*endp) - die("Garbage after path in: %s", command_buf.buf); - p = uq.buf; - } - tree_content_get(root, p, &leaf, 1); + strbuf_reset(&path); + parse_path_eol(&path, p, "path"); + tree_content_get(root, path.buf, &leaf, 1); /* * A directory in preparation would have a sha1 of zero * until it is saved. Save, for simplicity. @@ -3186,7 +3192,7 @@ static void parse_ls(const char *p, struct branch *b) if (S_ISDIR(leaf.versions[1].mode)) store_tree(&leaf); - print_ls(leaf.versions[1].mode, leaf.versions[1].oid.hash, p); + print_ls(leaf.versions[1].mode, leaf.versions[1].oid.hash, path.buf); if (leaf.tree) release_tree_content_recursive(leaf.tree); if (!b || root != &b->branch_tree) diff --git a/builtin/receive-pack.c b/builtin/receive-pack.c index 56d8a77ed7..e8d7df14b6 100644 --- a/builtin/receive-pack.c +++ b/builtin/receive-pack.c @@ -2585,17 +2585,16 @@ int cmd_receive_pack(int argc, const char **argv, const char *prefix) if (auto_gc) { struct child_process proc = CHILD_PROCESS_INIT; - proc.no_stdin = 1; - proc.stdout_to_stderr = 1; - proc.err = use_sideband ? -1 : 0; - proc.git_cmd = proc.close_object_store = 1; - strvec_pushl(&proc.args, "gc", "--auto", "--quiet", - NULL); - - if (!start_command(&proc)) { - if (use_sideband) - copy_to_sideband(proc.err, -1, NULL); - finish_command(&proc); + if (prepare_auto_maintenance(1, &proc)) { + proc.no_stdin = 1; + proc.stdout_to_stderr = 1; + proc.err = use_sideband ? -1 : 0; + + if (!start_command(&proc)) { + if (use_sideband) + copy_to_sideband(proc.err, -1, NULL); + finish_command(&proc); + } } } if (auto_update_server_info) @@ -104,16 +104,15 @@ static int launch_specified_editor(const char *editor, const char *path, sigchain_pop(SIGQUIT); if (sig == SIGINT || sig == SIGQUIT) raise(sig); - if (ret) - return error("There was a problem with the editor '%s'.", - editor); - if (print_waiting_for_editor && !is_terminal_dumb()) /* * Erase the entire line to avoid wasting the * vertical space. */ term_clear_line(); + if (ret) + return error("there was a problem with the editor '%s'", + editor); } if (!buffer) diff --git a/git-compat-util.h b/git-compat-util.h index 044f87454a..ca7678a379 100644 --- a/git-compat-util.h +++ b/git-compat-util.h @@ -403,6 +403,7 @@ char *gitdirname(char *); #ifndef NO_OPENSSL #ifdef __APPLE__ +#undef __AVAILABILITY_MACROS_USES_AVAILABILITY #define __AVAILABILITY_MACROS_USES_AVAILABILITY 0 #include <AvailabilityMacros.h> #undef DEPRECATED_ATTRIBUTE diff --git a/imap-send.c b/imap-send.c index 4caa8668e6..0afd088d8a 100644 --- a/imap-send.c +++ b/imap-send.c @@ -68,20 +68,6 @@ static void imap_warn(const char *, ...); static char *next_arg(char **); -static int nfvasprintf(char **strp, const char *fmt, va_list ap) -{ - int len; - char tmp[8192]; - - len = vsnprintf(tmp, sizeof(tmp), fmt, ap); - if (len < 0) - die("Fatal: Out of memory"); - if (len >= sizeof(tmp)) - die("imap command overflow!"); - *strp = xmemdupz(tmp, len); - return len; -} - struct imap_server_conf { const char *name; const char *tunnel; @@ -503,11 +489,11 @@ static struct imap_cmd *issue_imap_cmd(struct imap_store *ctx, { struct imap *imap = ctx->imap; struct imap_cmd *cmd; - int n, bufl; - char buf[1024]; + int n; + struct strbuf buf = STRBUF_INIT; cmd = xmalloc(sizeof(struct imap_cmd)); - nfvasprintf(&cmd->cmd, fmt, ap); + cmd->cmd = xstrvfmt(fmt, ap); cmd->tag = ++imap->nexttag; if (cb) @@ -519,27 +505,30 @@ static struct imap_cmd *issue_imap_cmd(struct imap_store *ctx, get_cmd_result(ctx, NULL); if (!cmd->cb.data) - bufl = xsnprintf(buf, sizeof(buf), "%d %s\r\n", cmd->tag, cmd->cmd); + strbuf_addf(&buf, "%d %s\r\n", cmd->tag, cmd->cmd); else - bufl = xsnprintf(buf, sizeof(buf), "%d %s{%d%s}\r\n", - cmd->tag, cmd->cmd, cmd->cb.dlen, - CAP(LITERALPLUS) ? "+" : ""); + strbuf_addf(&buf, "%d %s{%d%s}\r\n", cmd->tag, cmd->cmd, + cmd->cb.dlen, CAP(LITERALPLUS) ? "+" : ""); + if (buf.len > INT_MAX) + die("imap command overflow!"); if (0 < verbosity) { if (imap->num_in_progress) printf("(%d in progress) ", imap->num_in_progress); if (!starts_with(cmd->cmd, "LOGIN")) - printf(">>> %s", buf); + printf(">>> %s", buf.buf); else printf(">>> %d LOGIN <user> <pass>\n", cmd->tag); } - if (socket_write(&imap->buf.sock, buf, bufl) != bufl) { + if (socket_write(&imap->buf.sock, buf.buf, buf.len) != buf.len) { free(cmd->cmd); free(cmd); if (cb) free(cb->data); + strbuf_release(&buf); return NULL; } + strbuf_release(&buf); if (cmd->cb.data) { if (CAP(LITERALPLUS)) { n = socket_write(&imap->buf.sock, cmd->cb.data, cmd->cb.dlen); diff --git a/mem-pool.c b/mem-pool.c index 3065b12b23..a3ba38831d 100644 --- a/mem-pool.c +++ b/mem-pool.c @@ -4,6 +4,7 @@ #include "git-compat-util.h" #include "mem-pool.h" +#include "gettext.h" #define BLOCK_GROWTH_SIZE (1024 * 1024 - sizeof(struct mp_block)) @@ -122,7 +123,7 @@ static char *mem_pool_strvfmt(struct mem_pool *pool, const char *fmt, len = vsnprintf(next_free, available, fmt, cp); va_end(cp); if (len < 0) - BUG("your vsnprintf is broken (returned %d)", len); + die(_("unable to format message: %s"), fmt); size = st_add(len, 1); /* 1 for NUL */ ret = mem_pool_alloc(pool, size); @@ -170,9 +170,10 @@ struct multi_pack_index *load_multi_pack_index(const char *object_dir, int local pair_chunk(cf, MIDX_CHUNKID_LARGEOFFSETS, &m->chunk_large_offsets, &m->chunk_large_offsets_len); - pair_chunk(cf, MIDX_CHUNKID_BITMAPPEDPACKS, - (const unsigned char **)&m->chunk_bitmapped_packs, - &m->chunk_bitmapped_packs_len); + if (git_env_bool("GIT_TEST_MIDX_READ_BTMP", 1)) + pair_chunk(cf, MIDX_CHUNKID_BITMAPPEDPACKS, + (const unsigned char **)&m->chunk_bitmapped_packs, + &m->chunk_bitmapped_packs_len); if (git_env_bool("GIT_TEST_MIDX_READ_RIDX", 1)) pair_chunk(cf, MIDX_CHUNKID_REVINDEX, &m->chunk_revindex, diff --git a/pack-bitmap.c b/pack-bitmap.c index 2baeabacee..35c5ef9d3c 100644 --- a/pack-bitmap.c +++ b/pack-bitmap.c @@ -2049,7 +2049,10 @@ void reuse_partial_packfile_from_bitmap(struct bitmap_index *bitmap_git, load_reverse_index(r, bitmap_git); - if (bitmap_is_midx(bitmap_git)) { + if (!bitmap_is_midx(bitmap_git) || !bitmap_git->midx->chunk_bitmapped_packs) + multi_pack_reuse = 0; + + if (multi_pack_reuse) { for (i = 0; i < bitmap_git->midx->num_packs; i++) { struct bitmapped_pack pack; if (nth_bitmapped_pack(r, bitmap_git->midx, &pack, i) < 0) { @@ -2062,34 +2065,32 @@ void reuse_partial_packfile_from_bitmap(struct bitmap_index *bitmap_git, if (!pack.bitmap_nr) continue; - if (!multi_pack_reuse && pack.bitmap_pos) { - /* - * If we're only reusing a single pack, skip - * over any packs which are not positioned at - * the beginning of the MIDX bitmap. - * - * This is consistent with the existing - * single-pack reuse behavior, which only reuses - * parts of the MIDX's preferred pack. - */ - continue; - } - ALLOC_GROW(packs, packs_nr + 1, packs_alloc); memcpy(&packs[packs_nr++], &pack, sizeof(pack)); objects_nr += pack.p->num_objects; - - if (!multi_pack_reuse) - break; } QSORT(packs, packs_nr, bitmapped_pack_cmp); } else { - ALLOC_GROW(packs, packs_nr + 1, packs_alloc); + struct packed_git *pack; + + if (bitmap_is_midx(bitmap_git)) { + uint32_t preferred_pack_pos; + + if (midx_preferred_pack(bitmap_git->midx, &preferred_pack_pos) < 0) { + warning(_("unable to compute preferred pack, disabling pack-reuse")); + return; + } - packs[packs_nr].p = bitmap_git->pack; - packs[packs_nr].bitmap_nr = bitmap_git->pack->num_objects; + pack = bitmap_git->midx->packs[preferred_pack_pos]; + } else { + pack = bitmap_git->pack; + } + + ALLOC_GROW(packs, packs_nr + 1, packs_alloc); + packs[packs_nr].p = pack; + packs[packs_nr].bitmap_nr = pack->num_objects; packs[packs_nr].bitmap_pos = 0; objects_nr = packs[packs_nr++].bitmap_nr; diff --git a/reftable/block.c b/reftable/block.c index 298e8c56b9..3e87460cba 100644 --- a/reftable/block.c +++ b/reftable/block.c @@ -175,11 +175,6 @@ int block_writer_finish(struct block_writer *w) return w->next; } -uint8_t block_reader_type(struct block_reader *r) -{ - return r->block.data[r->header_off]; -} - int block_reader_init(struct block_reader *br, struct reftable_block *block, uint32_t header_off, uint32_t table_block_size, int hash_size) @@ -191,7 +186,8 @@ int block_reader_init(struct block_reader *br, struct reftable_block *block, uint16_t restart_count = 0; uint32_t restart_start = 0; uint8_t *restart_bytes = NULL; - uint8_t *uncompressed = NULL; + + reftable_block_done(&br->block); if (!reftable_is_block_type(typ)) { err = REFTABLE_FORMAT_ERROR; @@ -199,37 +195,57 @@ int block_reader_init(struct block_reader *br, struct reftable_block *block, } if (typ == BLOCK_TYPE_LOG) { - int block_header_skip = 4 + header_off; - uLongf dst_len = sz - block_header_skip; /* total size of dest - buffer. */ - uLongf src_len = block->len - block_header_skip; + uint32_t block_header_skip = 4 + header_off; + uLong dst_len = sz - block_header_skip; + uLong src_len = block->len - block_header_skip; /* Log blocks specify the *uncompressed* size in their header. */ - REFTABLE_ALLOC_ARRAY(uncompressed, sz); + REFTABLE_ALLOC_GROW(br->uncompressed_data, sz, + br->uncompressed_cap); /* Copy over the block header verbatim. It's not compressed. */ - memcpy(uncompressed, block->data, block_header_skip); + memcpy(br->uncompressed_data, block->data, block_header_skip); - /* Uncompress */ - if (Z_OK != - uncompress2(uncompressed + block_header_skip, &dst_len, - block->data + block_header_skip, &src_len)) { + if (!br->zstream) { + REFTABLE_CALLOC_ARRAY(br->zstream, 1); + err = inflateInit(br->zstream); + } else { + err = inflateReset(br->zstream); + } + if (err != Z_OK) { err = REFTABLE_ZLIB_ERROR; goto done; } - if (dst_len + block_header_skip != sz) { + br->zstream->next_in = block->data + block_header_skip; + br->zstream->avail_in = src_len; + br->zstream->next_out = br->uncompressed_data + block_header_skip; + br->zstream->avail_out = dst_len; + + /* + * We know both input as well as output size, and we know that + * the sizes should never be bigger than `uInt_MAX` because + * blocks can at most be 16MB large. We can thus use `Z_FINISH` + * here to instruct zlib to inflate the data in one go, which + * is more efficient than using `Z_NO_FLUSH`. + */ + err = inflate(br->zstream, Z_FINISH); + if (err != Z_STREAM_END) { + err = REFTABLE_ZLIB_ERROR; + goto done; + } + err = 0; + + if (br->zstream->total_out + block_header_skip != sz) { err = REFTABLE_FORMAT_ERROR; goto done; } /* We're done with the input data. */ reftable_block_done(block); - block->data = uncompressed; - uncompressed = NULL; + block->data = br->uncompressed_data; block->len = sz; - block->source = malloc_block_source(); - full_block_size = src_len + block_header_skip; + full_block_size = src_len + block_header_skip - br->zstream->avail_in; } else if (full_block_size == 0) { full_block_size = sz; } else if (sz < full_block_size && sz < block->len && @@ -257,18 +273,52 @@ int block_reader_init(struct block_reader *br, struct reftable_block *block, br->restart_bytes = restart_bytes; done: - reftable_free(uncompressed); return err; } -static uint32_t block_reader_restart_offset(struct block_reader *br, int i) +void block_reader_release(struct block_reader *br) +{ + inflateEnd(br->zstream); + reftable_free(br->zstream); + reftable_free(br->uncompressed_data); + reftable_block_done(&br->block); +} + +uint8_t block_reader_type(const struct block_reader *r) +{ + return r->block.data[r->header_off]; +} + +int block_reader_first_key(const struct block_reader *br, struct strbuf *key) +{ + int off = br->header_off + 4, n; + struct string_view in = { + .buf = br->block.data + off, + .len = br->block_len - off, + }; + uint8_t extra = 0; + + strbuf_reset(key); + + n = reftable_decode_key(key, &extra, in); + if (n < 0) + return n; + if (!key->len) + return REFTABLE_FORMAT_ERROR; + + return 0; +} + +static uint32_t block_reader_restart_offset(const struct block_reader *br, int i) { return get_be24(br->restart_bytes + 3 * i); } -void block_reader_start(struct block_reader *br, struct block_iter *it) +void block_iter_seek_start(struct block_iter *it, const struct block_reader *br) { - it->br = br; + it->block = br->block.data; + it->block_len = br->block_len; + it->hash_size = br->hash_size; strbuf_reset(&it->last_key); it->next_off = br->header_off + 4; } @@ -276,7 +326,7 @@ void block_reader_start(struct block_reader *br, struct block_iter *it) struct restart_needle_less_args { int error; struct strbuf needle; - struct block_reader *reader; + const struct block_reader *reader; }; static int restart_needle_less(size_t idx, void *_args) @@ -315,25 +365,17 @@ static int restart_needle_less(size_t idx, void *_args) return args->needle.len < suffix_len; } -void block_iter_copy_from(struct block_iter *dest, struct block_iter *src) -{ - dest->br = src->br; - dest->next_off = src->next_off; - strbuf_reset(&dest->last_key); - strbuf_addbuf(&dest->last_key, &src->last_key); -} - int block_iter_next(struct block_iter *it, struct reftable_record *rec) { struct string_view in = { - .buf = it->br->block.data + it->next_off, - .len = it->br->block_len - it->next_off, + .buf = (unsigned char *) it->block + it->next_off, + .len = it->block_len - it->next_off, }; struct string_view start = in; uint8_t extra = 0; int n = 0; - if (it->next_off >= it->br->block_len) + if (it->next_off >= it->block_len) return 1; n = reftable_decode_key(&it->last_key, &extra, in); @@ -343,7 +385,7 @@ int block_iter_next(struct block_iter *it, struct reftable_record *rec) return REFTABLE_FORMAT_ERROR; string_view_consume(&in, n); - n = reftable_record_decode(rec, it->last_key, extra, in, it->br->hash_size, + n = reftable_record_decode(rec, it->last_key, extra, in, it->hash_size, &it->scratch); if (n < 0) return -1; @@ -353,29 +395,13 @@ int block_iter_next(struct block_iter *it, struct reftable_record *rec) return 0; } -int block_reader_first_key(struct block_reader *br, struct strbuf *key) +void block_iter_reset(struct block_iter *it) { - int off = br->header_off + 4, n; - struct string_view in = { - .buf = br->block.data + off, - .len = br->block_len - off, - }; - uint8_t extra = 0; - - strbuf_reset(key); - - n = reftable_decode_key(key, &extra, in); - if (n < 0) - return n; - if (!key->len) - return REFTABLE_FORMAT_ERROR; - - return 0; -} - -int block_iter_seek(struct block_iter *it, struct strbuf *want) -{ - return block_reader_seek(it->br, it, want); + strbuf_reset(&it->last_key); + it->next_off = 0; + it->block = NULL; + it->block_len = 0; + it->hash_size = 0; } void block_iter_close(struct block_iter *it) @@ -384,14 +410,13 @@ void block_iter_close(struct block_iter *it) strbuf_release(&it->scratch); } -int block_reader_seek(struct block_reader *br, struct block_iter *it, - struct strbuf *want) +int block_iter_seek_key(struct block_iter *it, const struct block_reader *br, + struct strbuf *want) { struct restart_needle_less_args args = { .needle = *want, .reader = br, }; - struct block_iter next = BLOCK_ITER_INIT; struct reftable_record rec; int err = 0; size_t i; @@ -436,7 +461,9 @@ int block_reader_seek(struct block_reader *br, struct block_iter *it, it->next_off = block_reader_restart_offset(br, i - 1); else it->next_off = br->header_off + 4; - it->br = br; + it->block = br->block.data; + it->block_len = br->block_len; + it->hash_size = br->hash_size; reftable_record_init(&rec, block_reader_type(br)); @@ -448,11 +475,13 @@ int block_reader_seek(struct block_reader *br, struct block_iter *it, * far and then back up. */ while (1) { - block_iter_copy_from(&next, it); - err = block_iter_next(&next, &rec); + size_t prev_off = it->next_off; + + err = block_iter_next(it, &rec); if (err < 0) goto done; if (err > 0) { + it->next_off = prev_off; err = 0; goto done; } @@ -463,18 +492,23 @@ int block_reader_seek(struct block_reader *br, struct block_iter *it, * record does not exist in the block and can thus abort early. * In case it is equal to the sought-after key we have found * the desired record. + * + * Note that we store the next record's key record directly in + * `last_key` without restoring the key of the preceding record + * in case we need to go one record back. This is safe to do as + * `block_iter_next()` would return the ref whose key is equal + * to `last_key` now, and naturally all keys share a prefix + * with themselves. */ reftable_record_key(&rec, &it->last_key); - if (strbuf_cmp(&it->last_key, want) >= 0) + if (strbuf_cmp(&it->last_key, want) >= 0) { + it->next_off = prev_off; goto done; - - block_iter_copy_from(it, &next); + } } done: - block_iter_close(&next); reftable_record_release(&rec); - return err; } diff --git a/reftable/block.h b/reftable/block.h index 47acc62c0a..ea4384a7e2 100644 --- a/reftable/block.h +++ b/reftable/block.h @@ -56,6 +56,8 @@ int block_writer_finish(struct block_writer *w); /* clears out internally allocated block_writer members. */ void block_writer_release(struct block_writer *bw); +struct z_stream; + /* Read a block. */ struct block_reader { /* offset of the block header; nonzero for the first block in a @@ -66,6 +68,11 @@ struct block_reader { struct reftable_block block; int hash_size; + /* Uncompressed data for log entries. */ + z_stream *zstream; + unsigned char *uncompressed_data; + size_t uncompressed_cap; + /* size of the data, excluding restart data. */ uint32_t block_len; uint8_t *restart_bytes; @@ -76,11 +83,26 @@ struct block_reader { uint32_t full_block_size; }; +/* initializes a block reader. */ +int block_reader_init(struct block_reader *br, struct reftable_block *bl, + uint32_t header_off, uint32_t table_block_size, + int hash_size); + +void block_reader_release(struct block_reader *br); + +/* Returns the block type (eg. 'r' for refs) */ +uint8_t block_reader_type(const struct block_reader *r); + +/* Decodes the first key in the block */ +int block_reader_first_key(const struct block_reader *br, struct strbuf *key); + /* Iterate over entries in a block */ struct block_iter { /* offset within the block of the next entry to read. */ uint32_t next_off; - struct block_reader *br; + const unsigned char *block; + size_t block_len; + int hash_size; /* key for last entry we read. */ struct strbuf last_key; @@ -92,31 +114,18 @@ struct block_iter { .scratch = STRBUF_INIT, \ } -/* initializes a block reader. */ -int block_reader_init(struct block_reader *br, struct reftable_block *bl, - uint32_t header_off, uint32_t table_block_size, - int hash_size); - /* Position `it` at start of the block */ -void block_reader_start(struct block_reader *br, struct block_iter *it); +void block_iter_seek_start(struct block_iter *it, const struct block_reader *br); /* Position `it` to the `want` key in the block */ -int block_reader_seek(struct block_reader *br, struct block_iter *it, - struct strbuf *want); - -/* Returns the block type (eg. 'r' for refs) */ -uint8_t block_reader_type(struct block_reader *r); - -/* Decodes the first key in the block */ -int block_reader_first_key(struct block_reader *br, struct strbuf *key); - -void block_iter_copy_from(struct block_iter *dest, struct block_iter *src); +int block_iter_seek_key(struct block_iter *it, const struct block_reader *br, + struct strbuf *want); /* return < 0 for error, 0 for OK, > 0 for EOF. */ int block_iter_next(struct block_iter *it, struct reftable_record *rec); -/* Seek to `want` with in the block pointed to by `it` */ -int block_iter_seek(struct block_iter *it, struct strbuf *want); +/* Reset the block iterator to pristine state without releasing its memory. */ +void block_iter_reset(struct block_iter *it); /* deallocate memory for `it`. The block reader and its block is left intact. */ void block_iter_close(struct block_iter *it); diff --git a/reftable/block_test.c b/reftable/block_test.c index e162c6e33f..26a9cfbc83 100644 --- a/reftable/block_test.c +++ b/reftable/block_test.c @@ -69,7 +69,7 @@ static void test_block_read_write(void) block_reader_init(&br, &block, header_off, block_size, GIT_SHA1_RAWSZ); - block_reader_start(&br, &it); + block_iter_seek_start(&it, &br); while (1) { int r = block_iter_next(&it, &rec); @@ -89,7 +89,7 @@ static void test_block_read_write(void) strbuf_reset(&want); strbuf_addstr(&want, names[i]); - n = block_reader_seek(&br, &it, &want); + n = block_iter_seek_key(&it, &br, &want); EXPECT(n == 0); n = block_iter_next(&it, &rec); @@ -98,7 +98,7 @@ static void test_block_read_write(void) EXPECT_STREQ(names[i], rec.u.ref.refname); want.len--; - n = block_reader_seek(&br, &it, &want); + n = block_iter_seek_key(&it, &br, &want); EXPECT(n == 0); n = block_iter_next(&it, &rec); diff --git a/reftable/iter.c b/reftable/iter.c index 7aa30c4a51..aa9ac199b1 100644 --- a/reftable/iter.c +++ b/reftable/iter.c @@ -115,7 +115,7 @@ static int indexed_table_ref_iter_next_block(struct indexed_table_ref_iter *it) /* indexed block does not exist. */ return REFTABLE_FORMAT_ERROR; } - block_reader_start(&it->block_reader, &it->cur); + block_iter_seek_start(&it->cur, &it->block_reader); return 0; } diff --git a/reftable/reader.c b/reftable/reader.c index b113daab77..481dff10d4 100644 --- a/reftable/reader.c +++ b/reftable/reader.c @@ -220,6 +220,7 @@ struct table_iter { struct reftable_reader *r; uint8_t typ; uint64_t block_off; + struct block_reader br; struct block_iter bi; int is_finished; }; @@ -227,16 +228,6 @@ struct table_iter { .bi = BLOCK_ITER_INIT \ } -static void table_iter_copy_from(struct table_iter *dest, - struct table_iter *src) -{ - dest->r = src->r; - dest->typ = src->typ; - dest->block_off = src->block_off; - dest->is_finished = src->is_finished; - block_iter_copy_from(&dest->bi, &src->bi); -} - static int table_iter_next_in_block(struct table_iter *ti, struct reftable_record *rec) { @@ -250,14 +241,8 @@ static int table_iter_next_in_block(struct table_iter *ti, static void table_iter_block_done(struct table_iter *ti) { - if (!ti->bi.br) { - return; - } - reftable_block_done(&ti->bi.br->block); - FREE_AND_NULL(ti->bi.br); - - ti->bi.last_key.len = 0; - ti->bi.next_off = 0; + block_reader_release(&ti->br); + block_iter_reset(&ti->bi); } static int32_t extract_block_size(uint8_t *data, uint8_t *typ, uint64_t off, @@ -321,32 +306,27 @@ done: return err; } -static int table_iter_next_block(struct table_iter *dest, - struct table_iter *src) +static void table_iter_close(struct table_iter *ti) { - uint64_t next_block_off = src->block_off + src->bi.br->full_block_size; - struct block_reader br = { 0 }; - int err = 0; + table_iter_block_done(ti); + block_iter_close(&ti->bi); +} - dest->r = src->r; - dest->typ = src->typ; - dest->block_off = next_block_off; +static int table_iter_next_block(struct table_iter *ti) +{ + uint64_t next_block_off = ti->block_off + ti->br.full_block_size; + int err; - err = reader_init_block_reader(src->r, &br, next_block_off, src->typ); - if (err > 0) { - dest->is_finished = 1; - return 1; - } - if (err != 0) + err = reader_init_block_reader(ti->r, &ti->br, next_block_off, ti->typ); + if (err > 0) + ti->is_finished = 1; + if (err) return err; - else { - struct block_reader *brp = - reftable_malloc(sizeof(struct block_reader)); - *brp = br; - dest->is_finished = 0; - block_reader_start(brp, &dest->bi); - } + ti->block_off = next_block_off; + ti->is_finished = 0; + block_iter_seek_start(&ti->bi, &ti->br); + return 0; } @@ -356,7 +336,6 @@ static int table_iter_next(struct table_iter *ti, struct reftable_record *rec) return REFTABLE_API_ERROR; while (1) { - struct table_iter next = TABLE_ITER_INIT; int err; if (ti->is_finished) @@ -376,15 +355,11 @@ static int table_iter_next(struct table_iter *ti, struct reftable_record *rec) * table and retry. If there are no more blocks then the * iterator is drained. */ - err = table_iter_next_block(&next, ti); - table_iter_block_done(ti); + err = table_iter_next_block(ti); if (err) { ti->is_finished = 1; return err; } - - table_iter_copy_from(ti, &next); - block_iter_close(&next.bi); } } @@ -393,16 +368,14 @@ static int table_iter_next_void(void *ti, struct reftable_record *rec) return table_iter_next(ti, rec); } -static void table_iter_close(void *p) +static void table_iter_close_void(void *ti) { - struct table_iter *ti = p; - table_iter_block_done(ti); - block_iter_close(&ti->bi); + table_iter_close(ti); } static struct reftable_iterator_vtable table_iter_vtable = { .next = &table_iter_next_void, - .close = &table_iter_close, + .close = &table_iter_close_void, }; static void iterator_from_table_iter(struct reftable_iterator *it, @@ -417,19 +390,16 @@ static int reader_table_iter_at(struct reftable_reader *r, struct table_iter *ti, uint64_t off, uint8_t typ) { - struct block_reader br = { 0 }; - struct block_reader *brp = NULL; + int err; - int err = reader_init_block_reader(r, &br, off, typ); + err = reader_init_block_reader(r, &ti->br, off, typ); if (err != 0) return err; - brp = reftable_malloc(sizeof(struct block_reader)); - *brp = br; ti->r = r; - ti->typ = block_reader_type(brp); + ti->typ = block_reader_type(&ti->br); ti->block_off = off; - block_reader_start(brp, &ti->bi); + block_iter_seek_start(&ti->bi, &ti->br); return 0; } @@ -454,23 +424,52 @@ static int reader_seek_linear(struct table_iter *ti, { struct strbuf want_key = STRBUF_INIT; struct strbuf got_key = STRBUF_INIT; - struct table_iter next = TABLE_ITER_INIT; struct reftable_record rec; int err = -1; reftable_record_init(&rec, reftable_record_type(want)); reftable_record_key(want, &want_key); + /* + * First we need to locate the block that must contain our record. To + * do so we scan through blocks linearly until we find the first block + * whose first key is bigger than our wanted key. Once we have found + * that block we know that the key must be contained in the preceding + * block. + * + * This algorithm is somewhat unfortunate because it means that we + * always have to seek one block too far and then back up. But as we + * can only decode the _first_ key of a block but not its _last_ key we + * have no other way to do this. + */ while (1) { - err = table_iter_next_block(&next, ti); + struct table_iter next = *ti; + + /* + * We must be careful to not modify underlying data of `ti` + * because we may find that `next` does not contain our desired + * block, but that `ti` does. In that case, we would discard + * `next` and continue with `ti`. + * + * This also means that we cannot reuse allocated memory for + * `next` here. While it would be great if we could, it should + * in practice not be too bad given that we should only ever + * end up doing linear seeks with at most three blocks. As soon + * as we have more than three blocks we would have an index, so + * we would not do a linear search there anymore. + */ + memset(&next.br.block, 0, sizeof(next.br.block)); + next.br.zstream = NULL; + next.br.uncompressed_data = NULL; + next.br.uncompressed_cap = 0; + + err = table_iter_next_block(&next); if (err < 0) goto done; - - if (err > 0) { + if (err > 0) break; - } - err = block_reader_first_key(next.bi.br, &got_key); + err = block_reader_first_key(&next.br, &got_key); if (err < 0) goto done; @@ -480,16 +479,20 @@ static int reader_seek_linear(struct table_iter *ti, } table_iter_block_done(ti); - table_iter_copy_from(ti, &next); + *ti = next; } - err = block_iter_seek(&ti->bi, &want_key); + /* + * We have located the block that must contain our record, so we seek + * the wanted key inside of it. If the block does not contain our key + * we know that the corresponding record does not exist. + */ + err = block_iter_seek_key(&ti->bi, &ti->br, &want_key); if (err < 0) goto done; err = 0; done: - block_iter_close(&next.bi); reftable_record_release(&rec); strbuf_release(&want_key); strbuf_release(&got_key); @@ -508,6 +511,7 @@ static int reader_seek_indexed(struct reftable_reader *r, .u.idx = { .last_key = STRBUF_INIT }, }; struct table_iter index_iter = TABLE_ITER_INIT; + struct table_iter empty = TABLE_ITER_INIT; struct table_iter next = TABLE_ITER_INIT; int err = 0; @@ -549,7 +553,6 @@ static int reader_seek_indexed(struct reftable_reader *r, * not exist. */ err = table_iter_next(&index_iter, &index_result); - table_iter_block_done(&index_iter); if (err != 0) goto done; @@ -558,7 +561,7 @@ static int reader_seek_indexed(struct reftable_reader *r, if (err != 0) goto done; - err = block_iter_seek(&next.bi, &want_index.u.idx.last_key); + err = block_iter_seek_key(&next.bi, &next.br, &want_index.u.idx.last_key); if (err < 0) goto done; @@ -572,18 +575,20 @@ static int reader_seek_indexed(struct reftable_reader *r, break; } - table_iter_copy_from(&index_iter, &next); + table_iter_close(&index_iter); + index_iter = next; + next = empty; } if (err == 0) { - struct table_iter empty = TABLE_ITER_INIT; struct table_iter *malloced = reftable_calloc(1, sizeof(*malloced)); - *malloced = empty; - table_iter_copy_from(malloced, &next); + *malloced = next; + next = empty; iterator_from_table_iter(it, malloced); } + done: - block_iter_close(&next.bi); + table_iter_close(&next); table_iter_close(&index_iter); reftable_record_release(&want_index); reftable_record_release(&index_result); @@ -597,25 +602,28 @@ static int reader_seek_internal(struct reftable_reader *r, struct reftable_reader_offsets *offs = reader_offsets_for(r, reftable_record_type(rec)); uint64_t idx = offs->index_offset; - struct table_iter ti = TABLE_ITER_INIT; - int err = 0; + struct table_iter ti = TABLE_ITER_INIT, *p; + int err; + if (idx > 0) return reader_seek_indexed(r, it, rec); err = reader_start(r, &ti, reftable_record_type(rec), 0); if (err < 0) - return err; + goto out; + err = reader_seek_linear(&ti, rec); if (err < 0) - return err; - else { - struct table_iter *p = - reftable_malloc(sizeof(struct table_iter)); - *p = ti; - iterator_from_table_iter(it, p); - } + goto out; - return 0; + REFTABLE_ALLOC_ARRAY(p, 1); + *p = ti; + iterator_from_table_iter(it, p); + +out: + if (err) + table_iter_close(&ti); + return err; } static int reader_seek(struct reftable_reader *r, struct reftable_iterator *it, @@ -219,6 +219,11 @@ static void read_rr(struct repository *r, struct string_list *rr) buf.buf[hexsz] = '\0'; id = new_rerere_id_hex(buf.buf); id->variant = variant; + /* + * make sure id->collection->status has enough space + * for the variant we are interested in + */ + fit_variant(id->collection, variant); string_list_insert(rr, path)->util = id; } strbuf_release(&buf); diff --git a/run-command.c b/run-command.c index 0e7435718a..1b821042b4 100644 --- a/run-command.c +++ b/run-command.c @@ -1793,20 +1793,27 @@ void run_processes_parallel(const struct run_process_parallel_opts *opts) trace2_region_leave(tr2_category, tr2_label, NULL); } -int run_auto_maintenance(int quiet) +int prepare_auto_maintenance(int quiet, struct child_process *maint) { int enabled; - struct child_process maint = CHILD_PROCESS_INIT; if (!git_config_get_bool("maintenance.auto", &enabled) && !enabled) return 0; - maint.git_cmd = 1; - maint.close_object_store = 1; - strvec_pushl(&maint.args, "maintenance", "run", "--auto", NULL); - strvec_push(&maint.args, quiet ? "--quiet" : "--no-quiet"); + maint->git_cmd = 1; + maint->close_object_store = 1; + strvec_pushl(&maint->args, "maintenance", "run", "--auto", NULL); + strvec_push(&maint->args, quiet ? "--quiet" : "--no-quiet"); + + return 1; +} +int run_auto_maintenance(int quiet) +{ + struct child_process maint = CHILD_PROCESS_INIT; + if (!prepare_auto_maintenance(quiet, &maint)) + return 0; return run_command(&maint); } diff --git a/run-command.h b/run-command.h index 1f22cc3827..55f6631a2a 100644 --- a/run-command.h +++ b/run-command.h @@ -218,6 +218,13 @@ int finish_command_in_signal(struct child_process *); int run_command(struct child_process *); /* + * Prepare a `struct child_process` to run auto-maintenance. Returns 1 if the + * process has been prepared and is ready to run, or 0 in case auto-maintenance + * should be skipped. + */ +int prepare_auto_maintenance(int quiet, struct child_process *maint); + +/* * Trigger an auto-gc */ int run_auto_maintenance(int quiet); @@ -277,7 +277,7 @@ void strbuf_vinsertf(struct strbuf *sb, size_t pos, const char *fmt, va_list ap) len = vsnprintf(sb->buf + sb->len, 0, fmt, cp); va_end(cp); if (len < 0) - BUG("your vsnprintf is broken (returned %d)", len); + die(_("unable to format message: %s"), fmt); if (!len) return; /* nothing to do */ if (unsigned_add_overflows(sb->len, len)) @@ -404,7 +404,7 @@ void strbuf_vaddf(struct strbuf *sb, const char *fmt, va_list ap) len = vsnprintf(sb->buf + sb->len, sb->alloc - sb->len, fmt, cp); va_end(cp); if (len < 0) - BUG("your vsnprintf is broken (returned %d)", len); + die(_("unable to format message: %s"), fmt); if (len > strbuf_avail(sb)) { strbuf_grow(sb, len); len = vsnprintf(sb->buf + sb->len, sb->alloc - sb->len, fmt, ap); diff --git a/t/t4200-rerere.sh b/t/t4200-rerere.sh index fb53dddf79..b0a3e84984 100755 --- a/t/t4200-rerere.sh +++ b/t/t4200-rerere.sh @@ -671,4 +671,67 @@ test_expect_success 'test simple stage 1 handling' ' ) ' +test_expect_success 'rerere does not crash with missing preimage' ' + git config rerere.enabled true && + + echo bar >test && + git add test && + git commit -m "one" && + git branch rerere_no_crash && + + echo foo >>test && + git add test && + git commit -m "two" && + + git checkout rerere_no_crash && + echo "bar" >>test && + git add test && + git commit -m "three" && + + test_must_fail git rebase main && + rm .git/rr-cache/*/preimage && + git rebase --abort +' + +test_expect_success 'rerere does not crash with unmatched conflict marker' ' + git config rerere.enabled true && + + echo bar >test && + git add test && + git commit -m "one" && + git branch rerere_no_preimage && + + cat >test <<-EOF && + test + bar + foobar + EOF + git add test && + git commit -m "two" && + + git checkout rerere_no_preimage && + echo "bar" >>test && + git add test && + git commit -m "three" && + + cat >test <<-EOF && + foobar + bar + bar + EOF + git add test && + git commit -m "four" && + + test_must_fail git rebase main && + cat >test <<-EOF && + test + bar + <<<<<<< HEAD + foobar + bar + EOF + git add test && + test_must_fail git rebase --continue +' + test_done diff --git a/t/t5326-multi-pack-bitmaps.sh b/t/t5326-multi-pack-bitmaps.sh index 70d1b58709..5d7d321840 100755 --- a/t/t5326-multi-pack-bitmaps.sh +++ b/t/t5326-multi-pack-bitmaps.sh @@ -513,4 +513,21 @@ test_expect_success 'corrupt MIDX with bitmap causes fallback' ' ) ' +for allow_pack_reuse in single multi +do + test_expect_success "reading MIDX without BTMP chunk does not complain with $allow_pack_reuse pack reuse" ' + test_when_finished "rm -rf midx-without-btmp" && + git init midx-without-btmp && + ( + cd midx-without-btmp && + test_commit initial && + + git repack -Adbl --write-bitmap-index --write-midx && + GIT_TEST_MIDX_READ_BTMP=false git -c pack.allowPackReuse=$allow_pack_reuse \ + pack-objects --all --use-bitmap-index --stdout </dev/null >/dev/null 2>err && + test_must_be_empty err + ) + ' +done + test_done diff --git a/t/t9300-fast-import.sh b/t/t9300-fast-import.sh index 60e30fed3c..1e68426852 100755 --- a/t/t9300-fast-import.sh +++ b/t/t9300-fast-import.sh @@ -1059,30 +1059,33 @@ test_expect_success 'M: rename subdirectory to new subdirectory' ' compare_diff_raw expect actual ' -test_expect_success 'M: rename root to subdirectory' ' - cat >input <<-INPUT_END && - commit refs/heads/M4 - committer $GIT_COMMITTER_NAME <$GIT_COMMITTER_EMAIL> $GIT_COMMITTER_DATE - data <<COMMIT - rename root - COMMIT +for root in '""' '' +do + test_expect_success "M: rename root ($root) to subdirectory" ' + cat >input <<-INPUT_END && + commit refs/heads/M4 + committer $GIT_COMMITTER_NAME <$GIT_COMMITTER_EMAIL> $GIT_COMMITTER_DATE + data <<COMMIT + rename root + COMMIT - from refs/heads/M2^0 - R "" sub + from refs/heads/M2^0 + R $root sub - INPUT_END + INPUT_END - cat >expect <<-EOF && - :100644 100644 $oldf $oldf R100 file2/oldf sub/file2/oldf - :100755 100755 $f4id $f4id R100 file4 sub/file4 - :100755 100755 $newf $newf R100 i/am/new/to/you sub/i/am/new/to/you - :100755 100755 $f6id $f6id R100 newdir/exec.sh sub/newdir/exec.sh - :100644 100644 $f5id $f5id R100 newdir/interesting sub/newdir/interesting - EOF - git fast-import <input && - git diff-tree -M -r M4^ M4 >actual && - compare_diff_raw expect actual -' + cat >expect <<-EOF && + :100644 100644 $oldf $oldf R100 file2/oldf sub/file2/oldf + :100755 100755 $f4id $f4id R100 file4 sub/file4 + :100755 100755 $newf $newf R100 i/am/new/to/you sub/i/am/new/to/you + :100755 100755 $f6id $f6id R100 newdir/exec.sh sub/newdir/exec.sh + :100644 100644 $f5id $f5id R100 newdir/interesting sub/newdir/interesting + EOF + git fast-import <input && + git diff-tree -M -r M4^ M4 >actual && + compare_diff_raw expect actual + ' +done ### ### series N @@ -1259,49 +1262,52 @@ test_expect_success PIPE 'N: empty directory reads as missing' ' test_cmp expect actual ' -test_expect_success 'N: copy root directory by tree hash' ' - cat >expect <<-EOF && - :100755 000000 $newf $zero D file3/newf - :100644 000000 $oldf $zero D file3/oldf - EOF - root=$(git rev-parse refs/heads/branch^0^{tree}) && - cat >input <<-INPUT_END && - commit refs/heads/N6 - committer $GIT_COMMITTER_NAME <$GIT_COMMITTER_EMAIL> $GIT_COMMITTER_DATE - data <<COMMIT - copy root directory by tree hash - COMMIT - - from refs/heads/branch^0 - M 040000 $root "" - INPUT_END - git fast-import <input && - git diff-tree -C --find-copies-harder -r N4 N6 >actual && - compare_diff_raw expect actual -' +for root in '""' '' +do + test_expect_success "N: copy root ($root) by tree hash" ' + cat >expect <<-EOF && + :100755 000000 $newf $zero D file3/newf + :100644 000000 $oldf $zero D file3/oldf + EOF + root_tree=$(git rev-parse refs/heads/branch^0^{tree}) && + cat >input <<-INPUT_END && + commit refs/heads/N6 + committer $GIT_COMMITTER_NAME <$GIT_COMMITTER_EMAIL> $GIT_COMMITTER_DATE + data <<COMMIT + copy root directory by tree hash + COMMIT -test_expect_success 'N: copy root by path' ' - cat >expect <<-EOF && - :100755 100755 $newf $newf C100 file2/newf oldroot/file2/newf - :100644 100644 $oldf $oldf C100 file2/oldf oldroot/file2/oldf - :100755 100755 $f4id $f4id C100 file4 oldroot/file4 - :100755 100755 $f6id $f6id C100 newdir/exec.sh oldroot/newdir/exec.sh - :100644 100644 $f5id $f5id C100 newdir/interesting oldroot/newdir/interesting - EOF - cat >input <<-INPUT_END && - commit refs/heads/N-copy-root-path - committer $GIT_COMMITTER_NAME <$GIT_COMMITTER_EMAIL> $GIT_COMMITTER_DATE - data <<COMMIT - copy root directory by (empty) path - COMMIT + from refs/heads/branch^0 + M 040000 $root_tree $root + INPUT_END + git fast-import <input && + git diff-tree -C --find-copies-harder -r N4 N6 >actual && + compare_diff_raw expect actual + ' + + test_expect_success "N: copy root ($root) by path" ' + cat >expect <<-EOF && + :100755 100755 $newf $newf C100 file2/newf oldroot/file2/newf + :100644 100644 $oldf $oldf C100 file2/oldf oldroot/file2/oldf + :100755 100755 $f4id $f4id C100 file4 oldroot/file4 + :100755 100755 $f6id $f6id C100 newdir/exec.sh oldroot/newdir/exec.sh + :100644 100644 $f5id $f5id C100 newdir/interesting oldroot/newdir/interesting + EOF + cat >input <<-INPUT_END && + commit refs/heads/N-copy-root-path + committer $GIT_COMMITTER_NAME <$GIT_COMMITTER_EMAIL> $GIT_COMMITTER_DATE + data <<COMMIT + copy root directory by (empty) path + COMMIT - from refs/heads/branch^0 - C "" oldroot - INPUT_END - git fast-import <input && - git diff-tree -C --find-copies-harder -r branch N-copy-root-path >actual && - compare_diff_raw expect actual -' + from refs/heads/branch^0 + C $root oldroot + INPUT_END + git fast-import <input && + git diff-tree -C --find-copies-harder -r branch N-copy-root-path >actual && + compare_diff_raw expect actual + ' +done test_expect_success 'N: delete directory by copying' ' cat >expect <<-\EOF && @@ -1431,98 +1437,102 @@ test_expect_success 'N: reject foo/ syntax in ls argument' ' INPUT_END ' -test_expect_success 'N: copy to root by id and modify' ' - echo "hello, world" >expect.foo && - echo hello >expect.bar && - git fast-import <<-SETUP_END && - commit refs/heads/N7 - committer $GIT_COMMITTER_NAME <$GIT_COMMITTER_EMAIL> $GIT_COMMITTER_DATE - data <<COMMIT - hello, tree - COMMIT - - deleteall - M 644 inline foo/bar - data <<EOF - hello - EOF - SETUP_END - - tree=$(git rev-parse --verify N7:) && - git fast-import <<-INPUT_END && - commit refs/heads/N8 - committer $GIT_COMMITTER_NAME <$GIT_COMMITTER_EMAIL> $GIT_COMMITTER_DATE - data <<COMMIT - copy to root by id and modify - COMMIT +for root in '""' '' +do + test_expect_success "N: copy to root ($root) by id and modify" ' + echo "hello, world" >expect.foo && + echo hello >expect.bar && + git fast-import <<-SETUP_END && + commit refs/heads/N7 + committer $GIT_COMMITTER_NAME <$GIT_COMMITTER_EMAIL> $GIT_COMMITTER_DATE + data <<COMMIT + hello, tree + COMMIT - M 040000 $tree "" - M 644 inline foo/foo - data <<EOF - hello, world - EOF - INPUT_END - git show N8:foo/foo >actual.foo && - git show N8:foo/bar >actual.bar && - test_cmp expect.foo actual.foo && - test_cmp expect.bar actual.bar -' + deleteall + M 644 inline foo/bar + data <<EOF + hello + EOF + SETUP_END -test_expect_success 'N: extract subtree' ' - branch=$(git rev-parse --verify refs/heads/branch^{tree}) && - cat >input <<-INPUT_END && - commit refs/heads/N9 - committer $GIT_COMMITTER_NAME <$GIT_COMMITTER_EMAIL> $GIT_COMMITTER_DATE - data <<COMMIT - extract subtree branch:newdir - COMMIT + tree=$(git rev-parse --verify N7:) && + git fast-import <<-INPUT_END && + commit refs/heads/N8 + committer $GIT_COMMITTER_NAME <$GIT_COMMITTER_EMAIL> $GIT_COMMITTER_DATE + data <<COMMIT + copy to root by id and modify + COMMIT - M 040000 $branch "" - C "newdir" "" - INPUT_END - git fast-import <input && - git diff --exit-code branch:newdir N9 -' + M 040000 $tree $root + M 644 inline foo/foo + data <<EOF + hello, world + EOF + INPUT_END + git show N8:foo/foo >actual.foo && + git show N8:foo/bar >actual.bar && + test_cmp expect.foo actual.foo && + test_cmp expect.bar actual.bar + ' + + test_expect_success "N: extract subtree to the root ($root)" ' + branch=$(git rev-parse --verify refs/heads/branch^{tree}) && + cat >input <<-INPUT_END && + commit refs/heads/N9 + committer $GIT_COMMITTER_NAME <$GIT_COMMITTER_EMAIL> $GIT_COMMITTER_DATE + data <<COMMIT + extract subtree branch:newdir + COMMIT -test_expect_success 'N: modify subtree, extract it, and modify again' ' - echo hello >expect.baz && - echo hello, world >expect.qux && - git fast-import <<-SETUP_END && - commit refs/heads/N10 - committer $GIT_COMMITTER_NAME <$GIT_COMMITTER_EMAIL> $GIT_COMMITTER_DATE - data <<COMMIT - hello, tree - COMMIT + M 040000 $branch $root + C "newdir" $root + INPUT_END + git fast-import <input && + git diff --exit-code branch:newdir N9 + ' + + test_expect_success "N: modify subtree, extract it to the root ($root), and modify again" ' + echo hello >expect.baz && + echo hello, world >expect.qux && + git fast-import <<-SETUP_END && + commit refs/heads/N10 + committer $GIT_COMMITTER_NAME <$GIT_COMMITTER_EMAIL> $GIT_COMMITTER_DATE + data <<COMMIT + hello, tree + COMMIT - deleteall - M 644 inline foo/bar/baz - data <<EOF - hello - EOF - SETUP_END + deleteall + M 644 inline foo/bar/baz + data <<EOF + hello + EOF + SETUP_END - tree=$(git rev-parse --verify N10:) && - git fast-import <<-INPUT_END && - commit refs/heads/N11 - committer $GIT_COMMITTER_NAME <$GIT_COMMITTER_EMAIL> $GIT_COMMITTER_DATE - data <<COMMIT - copy to root by id and modify - COMMIT + tree=$(git rev-parse --verify N10:) && + git fast-import <<-INPUT_END && + commit refs/heads/N11 + committer $GIT_COMMITTER_NAME <$GIT_COMMITTER_EMAIL> $GIT_COMMITTER_DATE + data <<COMMIT + copy to root by id and modify + COMMIT - M 040000 $tree "" - M 100644 inline foo/bar/qux - data <<EOF - hello, world - EOF - R "foo" "" - C "bar/qux" "bar/quux" - INPUT_END - git show N11:bar/baz >actual.baz && - git show N11:bar/qux >actual.qux && - git show N11:bar/quux >actual.quux && - test_cmp expect.baz actual.baz && - test_cmp expect.qux actual.qux && - test_cmp expect.qux actual.quux' + M 040000 $tree $root + M 100644 inline foo/bar/qux + data <<EOF + hello, world + EOF + R "foo" $root + C "bar/qux" "bar/quux" + INPUT_END + git show N11:bar/baz >actual.baz && + git show N11:bar/qux >actual.qux && + git show N11:bar/quux >actual.quux && + test_cmp expect.baz actual.baz && + test_cmp expect.qux actual.qux && + test_cmp expect.qux actual.quux + ' +done ### ### series O @@ -2142,6 +2152,7 @@ test_expect_success 'Q: deny note on empty branch' ' EOF test_must_fail git fast-import <input ' + ### ### series R (feature and option) ### @@ -2790,7 +2801,7 @@ test_expect_success 'R: blob appears only once' ' ' ### -### series S +### series S (mark and path parsing) ### # # Make sure missing spaces and EOLs after mark references @@ -3060,21 +3071,283 @@ test_expect_success 'S: ls with garbage after sha1 must fail' ' test_grep "space after tree-ish" err ' +# +# Path parsing +# +# There are two sorts of ways a path can be parsed, depending on whether it is +# the last field on the line. Additionally, ls without a <dataref> has a special +# case. Test every occurrence of <path> in the grammar against every error case. +# Paths for the root (empty strings) are tested elsewhere. +# + +# +# Valid paths at the end of a line: filemodify, filedelete, filecopy (dest), +# filerename (dest), and ls. +# +# commit :301 from root -- modify hello.c (for setup) +# commit :302 from :301 -- modify $path +# commit :303 from :302 -- delete $path +# commit :304 from :301 -- copy hello.c $path +# commit :305 from :301 -- rename hello.c $path +# ls :305 $path +# +test_path_eol_success () { + local test="$1" path="$2" unquoted_path="$3" + test_expect_success "S: paths at EOL with $test must work" ' + test_when_finished "git branch -D S-path-eol" && + + git fast-import --export-marks=marks.out <<-EOF >out 2>err && + blob + mark :401 + data <<BLOB + hello world + BLOB + + blob + mark :402 + data <<BLOB + hallo welt + BLOB + + commit refs/heads/S-path-eol + mark :301 + committer $GIT_COMMITTER_NAME <$GIT_COMMITTER_EMAIL> $GIT_COMMITTER_DATE + data <<COMMIT + initial commit + COMMIT + M 100644 :401 hello.c + + commit refs/heads/S-path-eol + mark :302 + committer $GIT_COMMITTER_NAME <$GIT_COMMITTER_EMAIL> $GIT_COMMITTER_DATE + data <<COMMIT + commit filemodify + COMMIT + from :301 + M 100644 :402 $path + + commit refs/heads/S-path-eol + mark :303 + committer $GIT_COMMITTER_NAME <$GIT_COMMITTER_EMAIL> $GIT_COMMITTER_DATE + data <<COMMIT + commit filedelete + COMMIT + from :302 + D $path + + commit refs/heads/S-path-eol + mark :304 + committer $GIT_COMMITTER_NAME <$GIT_COMMITTER_EMAIL> $GIT_COMMITTER_DATE + data <<COMMIT + commit filecopy dest + COMMIT + from :301 + C hello.c $path + + commit refs/heads/S-path-eol + mark :305 + committer $GIT_COMMITTER_NAME <$GIT_COMMITTER_EMAIL> $GIT_COMMITTER_DATE + data <<COMMIT + commit filerename dest + COMMIT + from :301 + R hello.c $path + + ls :305 $path + EOF + + commit_m=$(grep :302 marks.out | cut -d\ -f2) && + commit_d=$(grep :303 marks.out | cut -d\ -f2) && + commit_c=$(grep :304 marks.out | cut -d\ -f2) && + commit_r=$(grep :305 marks.out | cut -d\ -f2) && + blob1=$(grep :401 marks.out | cut -d\ -f2) && + blob2=$(grep :402 marks.out | cut -d\ -f2) && + + ( + printf "100644 blob $blob2\t$unquoted_path\n" && + printf "100644 blob $blob1\thello.c\n" + ) | sort >tree_m.exp && + git ls-tree $commit_m | sort >tree_m.out && + test_cmp tree_m.exp tree_m.out && + + printf "100644 blob $blob1\thello.c\n" >tree_d.exp && + git ls-tree $commit_d >tree_d.out && + test_cmp tree_d.exp tree_d.out && + + ( + printf "100644 blob $blob1\t$unquoted_path\n" && + printf "100644 blob $blob1\thello.c\n" + ) | sort >tree_c.exp && + git ls-tree $commit_c | sort >tree_c.out && + test_cmp tree_c.exp tree_c.out && + + printf "100644 blob $blob1\t$unquoted_path\n" >tree_r.exp && + git ls-tree $commit_r >tree_r.out && + test_cmp tree_r.exp tree_r.out && + + test_cmp out tree_r.exp + ' +} + +test_path_eol_success 'quoted spaces' '" hello world.c "' ' hello world.c ' +test_path_eol_success 'unquoted spaces' ' hello world.c ' ' hello world.c ' +test_path_eol_success 'octal escapes' '"\150\151\056\143"' 'hi.c' + +# +# Valid paths before a space: filecopy (source) and filerename (source). +# +# commit :301 from root -- modify $path (for setup) +# commit :302 from :301 -- copy $path hello2.c +# commit :303 from :301 -- rename $path hello2.c +# +test_path_space_success () { + local test="$1" path="$2" unquoted_path="$3" + test_expect_success "S: paths before space with $test must work" ' + test_when_finished "git branch -D S-path-space" && + + git fast-import --export-marks=marks.out <<-EOF 2>err && + blob + mark :401 + data <<BLOB + hello world + BLOB + + commit refs/heads/S-path-space + mark :301 + committer $GIT_COMMITTER_NAME <$GIT_COMMITTER_EMAIL> $GIT_COMMITTER_DATE + data <<COMMIT + initial commit + COMMIT + M 100644 :401 $path + + commit refs/heads/S-path-space + mark :302 + committer $GIT_COMMITTER_NAME <$GIT_COMMITTER_EMAIL> $GIT_COMMITTER_DATE + data <<COMMIT + commit filecopy source + COMMIT + from :301 + C $path hello2.c + + commit refs/heads/S-path-space + mark :303 + committer $GIT_COMMITTER_NAME <$GIT_COMMITTER_EMAIL> $GIT_COMMITTER_DATE + data <<COMMIT + commit filerename source + COMMIT + from :301 + R $path hello2.c + + EOF + + commit_c=$(grep :302 marks.out | cut -d\ -f2) && + commit_r=$(grep :303 marks.out | cut -d\ -f2) && + blob=$(grep :401 marks.out | cut -d\ -f2) && + + ( + printf "100644 blob $blob\t$unquoted_path\n" && + printf "100644 blob $blob\thello2.c\n" + ) | sort >tree_c.exp && + git ls-tree $commit_c | sort >tree_c.out && + test_cmp tree_c.exp tree_c.out && + + printf "100644 blob $blob\thello2.c\n" >tree_r.exp && + git ls-tree $commit_r >tree_r.out && + test_cmp tree_r.exp tree_r.out + ' +} + +test_path_space_success 'quoted spaces' '" hello world.c "' ' hello world.c ' +test_path_space_success 'no unquoted spaces' 'hello_world.c' 'hello_world.c' +test_path_space_success 'octal escapes' '"\150\151\056\143"' 'hi.c' + +# +# Test a single commit change with an invalid path. Run it with all occurrences +# of <path> in the grammar against all error kinds. +# +test_path_fail () { + local change="$1" what="$2" prefix="$3" path="$4" suffix="$5" err_grep="$6" + test_expect_success "S: $change with $what must fail" ' + test_must_fail git fast-import <<-EOF 2>err && + blob + mark :1 + data <<BLOB + hello world + BLOB + + commit refs/heads/S-path-fail + mark :2 + committer $GIT_COMMITTER_NAME <$GIT_COMMITTER_EMAIL> $GIT_COMMITTER_DATE + data <<COMMIT + commit setup + COMMIT + M 100644 :1 hello.c + + commit refs/heads/S-path-fail + committer $GIT_COMMITTER_NAME <$GIT_COMMITTER_EMAIL> $GIT_COMMITTER_DATE + data <<COMMIT + commit with bad path + COMMIT + from :2 + $prefix$path$suffix + EOF + + test_grep "$err_grep" err + ' +} + +test_path_base_fail () { + local change="$1" prefix="$2" field="$3" suffix="$4" + test_path_fail "$change" 'unclosed " in '"$field" "$prefix" '"hello.c' "$suffix" "Invalid $field" + test_path_fail "$change" "invalid escape in quoted $field" "$prefix" '"hello\xff"' "$suffix" "Invalid $field" + test_path_fail "$change" "escaped NUL in quoted $field" "$prefix" '"hello\000"' "$suffix" "NUL in $field" +} +test_path_eol_quoted_fail () { + local change="$1" prefix="$2" field="$3" + test_path_base_fail "$change" "$prefix" "$field" '' + test_path_fail "$change" "garbage after quoted $field" "$prefix" '"hello.c"' 'x' "Garbage after $field" + test_path_fail "$change" "space after quoted $field" "$prefix" '"hello.c"' ' ' "Garbage after $field" +} +test_path_eol_fail () { + local change="$1" prefix="$2" field="$3" + test_path_eol_quoted_fail "$change" "$prefix" "$field" +} +test_path_space_fail () { + local change="$1" prefix="$2" field="$3" + test_path_base_fail "$change" "$prefix" "$field" ' world.c' + test_path_fail "$change" "missing space after quoted $field" "$prefix" '"hello.c"' 'x world.c' "Missing space after $field" + test_path_fail "$change" "missing space after unquoted $field" "$prefix" 'hello.c' '' "Missing space after $field" +} + +test_path_eol_fail filemodify 'M 100644 :1 ' path +test_path_eol_fail filedelete 'D ' path +test_path_space_fail filecopy 'C ' source +test_path_eol_fail filecopy 'C hello.c ' dest +test_path_space_fail filerename 'R ' source +test_path_eol_fail filerename 'R hello.c ' dest +test_path_eol_fail 'ls (in commit)' 'ls :2 ' path + +# When 'ls' has no <dataref>, the <path> must be quoted. +test_path_eol_quoted_fail 'ls (without dataref in commit)' 'ls ' path + ### ### series T (ls) ### # Setup is carried over from series S. -test_expect_success 'T: ls root tree' ' - sed -e "s/Z\$//" >expect <<-EOF && - 040000 tree $(git rev-parse S^{tree}) Z - EOF - sha1=$(git rev-parse --verify S) && - git fast-import --import-marks=marks <<-EOF >actual && - ls $sha1 "" - EOF - test_cmp expect actual -' +for root in '""' '' +do + test_expect_success "T: ls root ($root) tree" ' + sed -e "s/Z\$//" >expect <<-EOF && + 040000 tree $(git rev-parse S^{tree}) Z + EOF + sha1=$(git rev-parse --verify S) && + git fast-import --import-marks=marks <<-EOF >actual && + ls $sha1 $root + EOF + test_cmp expect actual + ' +done test_expect_success 'T: delete branch' ' git branch to-delete && @@ -3176,30 +3449,33 @@ test_expect_success 'U: validate directory delete result' ' compare_diff_raw expect actual ' -test_expect_success 'U: filedelete root succeeds' ' - cat >input <<-INPUT_END && - commit refs/heads/U - committer $GIT_COMMITTER_NAME <$GIT_COMMITTER_EMAIL> $GIT_COMMITTER_DATE - data <<COMMIT - must succeed - COMMIT - from refs/heads/U^0 - D "" +for root in '""' '' +do + test_expect_success "U: filedelete root ($root) succeeds" ' + cat >input <<-INPUT_END && + commit refs/heads/U-delete-root + committer $GIT_COMMITTER_NAME <$GIT_COMMITTER_EMAIL> $GIT_COMMITTER_DATE + data <<COMMIT + must succeed + COMMIT + from refs/heads/U^0 + D $root - INPUT_END + INPUT_END - git fast-import <input -' + git fast-import <input + ' -test_expect_success 'U: validate root delete result' ' - cat >expect <<-EOF && - :100644 000000 $f7id $ZERO_OID D hello.c - EOF + test_expect_success "U: validate root ($root) delete result" ' + cat >expect <<-EOF && + :100644 000000 $f7id $ZERO_OID D hello.c + EOF - git diff-tree -M -r U^1 U >actual && + git diff-tree -M -r U U-delete-root >actual && - compare_diff_raw expect actual -' + compare_diff_raw expect actual + ' +done ### ### series V (checkpoint) diff --git a/t/t9604-cvsimport-timestamps.sh b/t/t9604-cvsimport-timestamps.sh index 2ff4aa932d..2d03259729 100755 --- a/t/t9604-cvsimport-timestamps.sh +++ b/t/t9604-cvsimport-timestamps.sh @@ -3,11 +3,28 @@ test_description='git cvsimport timestamps' . ./lib-cvs.sh +test_lazy_prereq POSIX_TIMEZONE ' + local tz=XST-1XDT,M3.5.0,M11.1.0 + echo "1711846799 -> 2024-03-31 01:59:59 +0100" >expected && + TZ="$tz" test-tool date show:iso-local 1711846799 >actual && + test_cmp expected actual && + echo "1711846800 -> 2024-03-31 03:00:00 +0200" >expected && + TZ="$tz" test-tool date show:iso-local 1711846800 >actual && + test_cmp expected actual && + echo "1730591999 -> 2024-11-03 01:59:59 +0200" >expected && + TZ="$tz" test-tool date show:iso-local 1730591999 >actual && + test_cmp expected actual && + echo "1730592000 -> 2024-11-03 01:00:00 +0100" >expected && + TZ="$tz" test-tool date show:iso-local 1730592000 >actual && + test_cmp expected actual +' + setup_cvs_test_repository t9604 -test_expect_success PERL 'check timestamps are UTC (TZ=CST6CDT)' ' +test_expect_success PERL,POSIX_TIMEZONE 'check timestamps are UTC' ' - TZ=CST6CDT git cvsimport -p"-x" -C module-1 module && + TZ=CST6CDT,M4.1.0,M10.5.0 \ + git cvsimport -p"-x" -C module-1 module && git cvsimport -p"-x" -C module-1 module && ( cd module-1 && @@ -34,13 +51,13 @@ test_expect_success PERL 'check timestamps are UTC (TZ=CST6CDT)' ' test_cmp expect-1 actual-1 ' -test_expect_success PERL 'check timestamps with author-specific timezones' ' +test_expect_success PERL,POSIX_TIMEZONE 'check timestamps with author-specific timezones' ' cat >cvs-authors <<-EOF && user1=User One <user1@domain.org> - user2=User Two <user2@domain.org> CST6CDT - user3=User Three <user3@domain.org> EST5EDT - user4=User Four <user4@domain.org> MST7MDT + user2=User Two <user2@domain.org> CST6CDT,M4.1.0,M10.5.0 + user3=User Three <user3@domain.org> EST5EDT,M4.1.0,M10.5.0 + user4=User Four <user4@domain.org> MST7MDT,M4.1.0,M10.5.0 EOF git cvsimport -p"-x" -A cvs-authors -C module-2 module && ( @@ -144,38 +144,6 @@ static char last_non_space_char(const char *s) return '\0'; } -static void print_tok_val(struct strbuf *out, const char *tok, const char *val) -{ - char c; - - if (!tok) { - strbuf_addf(out, "%s\n", val); - return; - } - - c = last_non_space_char(tok); - if (!c) - return; - if (strchr(separators, c)) - strbuf_addf(out, "%s%s\n", tok, val); - else - strbuf_addf(out, "%s%c %s\n", tok, separators[0], val); -} - -void format_trailers(const struct process_trailer_options *opts, - struct list_head *trailers, - struct strbuf *out) -{ - struct list_head *pos; - struct trailer_item *item; - list_for_each(pos, trailers) { - item = list_entry(pos, struct trailer_item, list); - if ((!opts->trim_empty || strlen(item->value) > 0) && - (!opts->only_trailers || item->token)) - print_tok_val(out, item->token, item->value); - } -} - static struct trailer_item *trailer_from_arg(struct arg_item *arg_tok) { struct trailer_item *new_item = xcalloc(1, sizeof(*new_item)); @@ -1084,26 +1052,32 @@ void trailer_info_release(struct trailer_info *info) free(info->trailers); } -static void format_trailer_info(const struct process_trailer_options *opts, - const struct trailer_info *info, - struct strbuf *out) +void format_trailers(const struct process_trailer_options *opts, + struct list_head *trailers, + struct strbuf *out) { size_t origlen = out->len; - size_t i; - - for (i = 0; i < info->trailer_nr; i++) { - char *trailer = info->trailers[i]; - ssize_t separator_pos = find_separator(trailer, separators); + struct list_head *pos; + struct trailer_item *item; - if (separator_pos >= 1) { + list_for_each(pos, trailers) { + item = list_entry(pos, struct trailer_item, list); + if (item->token) { struct strbuf tok = STRBUF_INIT; struct strbuf val = STRBUF_INIT; + strbuf_addstr(&tok, item->token); + strbuf_addstr(&val, item->value); + + /* + * Skip key/value pairs where the value was empty. This + * can happen from trailers specified without a + * separator, like `--trailer "Reviewed-by"` (no + * corresponding value). + */ + if (opts->trim_empty && !strlen(item->value)) + continue; - parse_trailer(&tok, &val, NULL, trailer, separator_pos); if (!opts->filter || opts->filter(&tok, opts->filter_data)) { - if (opts->unfold) - unfold_value(&val); - if (opts->separator && out->len != origlen) strbuf_addbuf(out, opts->separator); if (!opts->value_only) @@ -1111,8 +1085,11 @@ static void format_trailer_info(const struct process_trailer_options *opts, if (!opts->key_only && !opts->value_only) { if (opts->key_value_separator) strbuf_addbuf(out, opts->key_value_separator); - else - strbuf_addstr(out, ": "); + else { + char c = last_non_space_char(tok.buf); + if (c && !strchr(separators, c)) + strbuf_addf(out, "%c ", separators[0]); + } } if (!opts->key_only) strbuf_addbuf(out, &val); @@ -1126,13 +1103,13 @@ static void format_trailer_info(const struct process_trailer_options *opts, if (opts->separator && out->len != origlen) { strbuf_addbuf(out, opts->separator); } - strbuf_addstr(out, trailer); - if (opts->separator) { + strbuf_addstr(out, item->value); + if (opts->separator) strbuf_rtrim(out); - } + else + strbuf_addch(out, '\n'); } } - } void format_trailers_from_commit(const struct process_trailer_options *opts, @@ -1151,7 +1128,7 @@ void format_trailers_from_commit(const struct process_trailer_options *opts, strbuf_add(out, msg + info.trailer_block_start, info.trailer_block_end - info.trailer_block_start); } else - format_trailer_info(opts, &info, out); + format_trailers(opts, &trailer_objects, out); free_trailers(&trailer_objects); trailer_info_release(&info); @@ -107,17 +107,10 @@ void format_trailers(const struct process_trailer_options *, void free_trailers(struct list_head *); /* - * Format the trailers from the commit msg "msg" into the strbuf "out". - * Note two caveats about "opts": - * - * - this is primarily a helper for pretty.c, and not - * all of the flags are supported. - * - * - this differs from process_trailers slightly in that we always format - * only the trailer block itself, even if the "only_trailers" option is not - * set. + * Convenience function to format the trailers from the commit msg "msg" into + * the strbuf "out". Reuses format_trailers() internally. */ -void format_trailers_from_commit(const struct process_trailer_options *opts, +void format_trailers_from_commit(const struct process_trailer_options *, const char *msg, struct strbuf *out); @@ -670,7 +670,7 @@ int xsnprintf(char *dst, size_t max, const char *fmt, ...) va_end(ap); if (len < 0) - BUG("your snprintf is broken"); + die(_("unable to format message: %s"), fmt); if (len >= max) BUG("attempt to snprintf into too-small buffer"); return len; |