diff options
| -rw-r--r-- | Documentation/git-ls-tree.txt | 68 | ||||
| -rw-r--r-- | builtin/ls-tree.c | 366 | ||||
| -rw-r--r-- | contrib/coccinelle/strbuf.cocci | 6 | ||||
| -rwxr-xr-x | t/t3101-ls-tree-dirname.sh | 55 | ||||
| -rwxr-xr-x | t/t3103-ls-tree-misc.sh | 15 | ||||
| -rwxr-xr-x | t/t3104-ls-tree-format.sh | 76 |
6 files changed, 492 insertions, 94 deletions
diff --git a/Documentation/git-ls-tree.txt b/Documentation/git-ls-tree.txt index db02d6d79a..43aebb9938 100644 --- a/Documentation/git-ls-tree.txt +++ b/Documentation/git-ls-tree.txt @@ -10,7 +10,7 @@ SYNOPSIS -------- [verse] 'git ls-tree' [-d] [-r] [-t] [-l] [-z] - [--name-only] [--name-status] [--full-name] [--full-tree] [--abbrev[=<n>]] + [--name-only] [--name-status] [--object-only] [--full-name] [--full-tree] [--abbrev[=<n>]] [--format=<format>] <tree-ish> [<path>...] DESCRIPTION @@ -59,6 +59,15 @@ OPTIONS --name-only:: --name-status:: List only filenames (instead of the "long" output), one per line. + Cannot be combined with `--object-only`. + +--object-only:: + List only names of the objects, one per line. Cannot be combined + with `--name-only` or `--name-status`. + This is equivalent to specifying `--format='%(objectname)'`, but + for both this option and that exact format the command takes a + hand-optimized codepath instead of going through the generic + formatting mechanism. --abbrev[=<n>]:: Instead of showing the full 40-byte hexadecimal object @@ -74,6 +83,16 @@ OPTIONS Do not limit the listing to the current working directory. Implies --full-name. +--format=<format>:: + A string that interpolates `%(fieldname)` from the result + being shown. It also interpolates `%%` to `%`, and + `%xx` where `xx` are hex digits interpolates to character + with hex code `xx`; for example `%00` interpolates to + `\0` (NUL), `%09` to `\t` (TAB) and `%0a` to `\n` (LF). + When specified, `--format` cannot be combined with other + format-altering options, including `--long`, `--name-only` + and `--object-only`. + [<path>...]:: When paths are given, show them (note that this isn't really raw pathnames, but rather a list of patterns to match). Otherwise @@ -82,16 +101,29 @@ OPTIONS Output Format ------------- - <mode> SP <type> SP <object> TAB <file> + +The output format of `ls-tree` is determined by either the `--format` +option, or other format-altering options such as `--name-only` etc. +(see `--format` above). + +The use of certain `--format` directives is equivalent to using those +options, but invoking the full formatting machinery can be slower than +using an appropriate formatting option. + +In cases where the `--format` would exactly map to an existing option +`ls-tree` will use the appropriate faster path. Thus the default format +is equivalent to: + + %(objectmode) %(objecttype) %(objectname)%x09%(path) This output format is compatible with what `--index-info --stdin` of 'git update-index' expects. When the `-l` option is used, format changes to - <mode> SP <type> SP <object> SP <object size> TAB <file> + %(objectmode) %(objecttype) %(objectname) %(objectsize:padded)%x09%(path) -Object size identified by <object> is given in bytes, and right-justified +Object size identified by <objectname> is given in bytes, and right-justified with minimum width of 7 characters. Object size is given only for blobs (file) entries; for other entries `-` character is used in place of size. @@ -100,6 +132,34 @@ quoted as explained for the configuration variable `core.quotePath` (see linkgit:git-config[1]). Using `-z` the filename is output verbatim and the line is terminated by a NUL byte. +Customized format: + +It is possible to print in a custom format by using the `--format` option, +which is able to interpolate different fields using a `%(fieldname)` notation. +For example, if you only care about the "objectname" and "path" fields, you +can execute with a specific "--format" like + + git ls-tree --format='%(objectname) %(path)' <tree-ish> + +FIELD NAMES +----------- + +Various values from structured fields can be used to interpolate +into the resulting output. For each outputing line, the following +names can be used: + +objectmode:: + The mode of the object. +objecttype:: + The type of the object (`blob` or `tree`). +objectname:: + The name of the object. +objectsize[:padded]:: + The size of the object ("-" if it's a tree). + It also supports a padded format of size with "%(size:padded)". +path:: + The pathname of the object. + GIT --- Part of the linkgit:git[1] suite diff --git a/builtin/ls-tree.c b/builtin/ls-tree.c index 6cb554cbb0..5dac9ee5b9 100644 --- a/builtin/ls-tree.c +++ b/builtin/ls-tree.c @@ -16,22 +16,102 @@ static int line_termination = '\n'; #define LS_RECURSIVE 1 -#define LS_TREE_ONLY 2 -#define LS_SHOW_TREES 4 -#define LS_NAME_ONLY 8 -#define LS_SHOW_SIZE 16 +#define LS_TREE_ONLY (1 << 1) +#define LS_SHOW_TREES (1 << 2) static int abbrev; static int ls_options; static struct pathspec pathspec; static int chomp_prefix; static const char *ls_tree_prefix; +static const char *format; +struct show_tree_data { + unsigned mode; + enum object_type type; + const struct object_id *oid; + const char *pathname; + struct strbuf *base; +}; static const char * const ls_tree_usage[] = { N_("git ls-tree [<options>] <tree-ish> [<path>...]"), NULL }; -static int show_recursive(const char *base, int baselen, const char *pathname) +static enum ls_tree_cmdmode { + MODE_DEFAULT = 0, + MODE_LONG, + MODE_NAME_ONLY, + MODE_NAME_STATUS, + MODE_OBJECT_ONLY, +} cmdmode; + +static void expand_objectsize(struct strbuf *line, const struct object_id *oid, + const enum object_type type, unsigned int padded) +{ + if (type == OBJ_BLOB) { + unsigned long size; + if (oid_object_info(the_repository, oid, &size) < 0) + die(_("could not get object info about '%s'"), + oid_to_hex(oid)); + if (padded) + strbuf_addf(line, "%7"PRIuMAX, (uintmax_t)size); + else + strbuf_addf(line, "%"PRIuMAX, (uintmax_t)size); + } else if (padded) { + strbuf_addf(line, "%7s", "-"); + } else { + strbuf_addstr(line, "-"); + } +} + +static size_t expand_show_tree(struct strbuf *sb, const char *start, + void *context) +{ + struct show_tree_data *data = context; + const char *end; + const char *p; + unsigned int errlen; + size_t len = strbuf_expand_literal_cb(sb, start, NULL); + + if (len) + return len; + if (*start != '(') + die(_("bad ls-tree format: element '%s' does not start with '('"), start); + + end = strchr(start + 1, ')'); + if (!end) + die(_("bad ls-tree format: element '%s' does not end in ')'"), start); + + len = end - start + 1; + if (skip_prefix(start, "(objectmode)", &p)) { + strbuf_addf(sb, "%06o", data->mode); + } else if (skip_prefix(start, "(objecttype)", &p)) { + strbuf_addstr(sb, type_name(data->type)); + } else if (skip_prefix(start, "(objectsize:padded)", &p)) { + expand_objectsize(sb, data->oid, data->type, 1); + } else if (skip_prefix(start, "(objectsize)", &p)) { + expand_objectsize(sb, data->oid, data->type, 0); + } else if (skip_prefix(start, "(objectname)", &p)) { + strbuf_add_unique_abbrev(sb, data->oid, abbrev); + } else if (skip_prefix(start, "(path)", &p)) { + const char *name = data->base->buf; + const char *prefix = chomp_prefix ? ls_tree_prefix : NULL; + struct strbuf quoted = STRBUF_INIT; + struct strbuf sbuf = STRBUF_INIT; + strbuf_addstr(data->base, data->pathname); + name = relative_path(data->base->buf, prefix, &sbuf); + quote_c_style(name, "ed, NULL, 0); + strbuf_addbuf(sb, "ed); + strbuf_release(&sbuf); + strbuf_release("ed); + } else { + errlen = (unsigned long)len; + die(_("bad ls-tree format: %%%.*s"), errlen, start); + } + return len; +} + +static int show_recursive(const char *base, size_t baselen, const char *pathname) { int i; @@ -43,7 +123,7 @@ static int show_recursive(const char *base, int baselen, const char *pathname) for (i = 0; i < pathspec.nr; i++) { const char *spec = pathspec.items[i].match; - int len, speclen; + size_t len, speclen; if (strncmp(base, spec, baselen)) continue; @@ -61,69 +141,197 @@ static int show_recursive(const char *base, int baselen, const char *pathname) return 0; } -static int show_tree(const struct object_id *oid, struct strbuf *base, - const char *pathname, unsigned mode, void *context) +static int show_tree_fmt(const struct object_id *oid, struct strbuf *base, + const char *pathname, unsigned mode, void *context) { - int retval = 0; - int baselen; - const char *type = blob_type; - - if (S_ISGITLINK(mode)) { - /* - * Maybe we want to have some recursive version here? - * - * Something similar to this incomplete example: - * - if (show_subprojects(base, baselen, pathname)) - retval = READ_TREE_RECURSIVE; - * - */ - type = commit_type; - } else if (S_ISDIR(mode)) { - if (show_recursive(base->buf, base->len, pathname)) { - retval = READ_TREE_RECURSIVE; - if (!(ls_options & LS_SHOW_TREES)) - return retval; - } - type = tree_type; - } - else if (ls_options & LS_TREE_ONLY) + size_t baselen; + int recurse = 0; + struct strbuf sb = STRBUF_INIT; + enum object_type type = object_type(mode); + + struct show_tree_data data = { + .mode = mode, + .type = type, + .oid = oid, + .pathname = pathname, + .base = base, + }; + + if (type == OBJ_TREE && show_recursive(base->buf, base->len, pathname)) + recurse = READ_TREE_RECURSIVE; + if (type == OBJ_TREE && recurse && !(ls_options & LS_SHOW_TREES)) + return recurse; + if (type == OBJ_BLOB && (ls_options & LS_TREE_ONLY)) return 0; - if (!(ls_options & LS_NAME_ONLY)) { - if (ls_options & LS_SHOW_SIZE) { - char size_text[24]; - if (!strcmp(type, blob_type)) { - unsigned long size; - if (oid_object_info(the_repository, oid, &size) == OBJ_BAD) - xsnprintf(size_text, sizeof(size_text), - "BAD"); - else - xsnprintf(size_text, sizeof(size_text), - "%"PRIuMAX, (uintmax_t)size); - } else - xsnprintf(size_text, sizeof(size_text), "-"); - printf("%06o %s %s %7s\t", mode, type, - find_unique_abbrev(oid, abbrev), - size_text); - } else - printf("%06o %s %s\t", mode, type, - find_unique_abbrev(oid, abbrev)); - } baselen = base->len; + strbuf_expand(&sb, format, expand_show_tree, &data); + strbuf_addch(&sb, line_termination); + fwrite(sb.buf, sb.len, 1, stdout); + strbuf_release(&sb); + strbuf_setlen(base, baselen); + return recurse; +} + +static int show_tree_common(struct show_tree_data *data, int *recurse, + const struct object_id *oid, struct strbuf *base, + const char *pathname, unsigned mode) +{ + enum object_type type = object_type(mode); + int ret = -1; + + *recurse = 0; + data->mode = mode; + data->type = type; + data->oid = oid; + data->pathname = pathname; + data->base = base; + + if (type == OBJ_BLOB) { + if (ls_options & LS_TREE_ONLY) + ret = 0; + } else if (type == OBJ_TREE && + show_recursive(base->buf, base->len, pathname)) { + *recurse = READ_TREE_RECURSIVE; + if (!(ls_options & LS_SHOW_TREES)) + ret = *recurse; + } + + return ret; +} + +static void show_tree_common_default_long(struct strbuf *base, + const char *pathname, + const size_t baselen) +{ + strbuf_addstr(base, pathname); + write_name_quoted_relative(base->buf, + chomp_prefix ? ls_tree_prefix : NULL, stdout, + line_termination); + strbuf_setlen(base, baselen); +} + +static int show_tree_default(const struct object_id *oid, struct strbuf *base, + const char *pathname, unsigned mode, + void *context) +{ + int early; + int recurse; + struct show_tree_data data = { 0 }; + + early = show_tree_common(&data, &recurse, oid, base, pathname, mode); + if (early >= 0) + return early; + + printf("%06o %s %s\t", data.mode, type_name(data.type), + find_unique_abbrev(data.oid, abbrev)); + show_tree_common_default_long(base, pathname, data.base->len); + return recurse; +} + +static int show_tree_long(const struct object_id *oid, struct strbuf *base, + const char *pathname, unsigned mode, void *context) +{ + int early; + int recurse; + struct show_tree_data data = { 0 }; + char size_text[24]; + + early = show_tree_common(&data, &recurse, oid, base, pathname, mode); + if (early >= 0) + return early; + + if (data.type == OBJ_BLOB) { + unsigned long size; + if (oid_object_info(the_repository, data.oid, &size) == OBJ_BAD) + xsnprintf(size_text, sizeof(size_text), "BAD"); + else + xsnprintf(size_text, sizeof(size_text), + "%" PRIuMAX, (uintmax_t)size); + } else { + xsnprintf(size_text, sizeof(size_text), "-"); + } + + printf("%06o %s %s %7s\t", data.mode, type_name(data.type), + find_unique_abbrev(data.oid, abbrev), size_text); + show_tree_common_default_long(base, pathname, data.base->len); + return 1; +} + +static int show_tree_name_only(const struct object_id *oid, struct strbuf *base, + const char *pathname, unsigned mode, void *context) +{ + int early; + int recurse; + const size_t baselen = base->len; + struct show_tree_data data = { 0 }; + + early = show_tree_common(&data, &recurse, oid, base, pathname, mode); + if (early >= 0) + return early; + strbuf_addstr(base, pathname); write_name_quoted_relative(base->buf, chomp_prefix ? ls_tree_prefix : NULL, stdout, line_termination); strbuf_setlen(base, baselen); - return retval; + return recurse; +} + +static int show_tree_object(const struct object_id *oid, struct strbuf *base, + const char *pathname, unsigned mode, void *context) +{ + int early; + int recurse; + struct show_tree_data data = { 0 }; + + early = show_tree_common(&data, &recurse, oid, base, pathname, mode); + if (early >= 0) + return early; + + printf("%s%c", find_unique_abbrev(oid, abbrev), line_termination); + return recurse; } +struct ls_tree_cmdmode_to_fmt { + enum ls_tree_cmdmode mode; + const char *const fmt; + read_tree_fn_t fn; +}; + +static struct ls_tree_cmdmode_to_fmt ls_tree_cmdmode_format[] = { + { + .mode = MODE_DEFAULT, + .fmt = "%(objectmode) %(objecttype) %(objectname)%x09%(path)", + .fn = show_tree_default, + }, + { + .mode = MODE_LONG, + .fmt = "%(objectmode) %(objecttype) %(objectname) %(objectsize:padded)%x09%(path)", + .fn = show_tree_long, + }, + { + .mode = MODE_NAME_ONLY, /* And MODE_NAME_STATUS */ + .fmt = "%(path)", + .fn = show_tree_name_only, + }, + { + .mode = MODE_OBJECT_ONLY, + .fmt = "%(objectname)", + .fn = show_tree_object + }, + { + /* fallback */ + .fn = show_tree_default, + }, +}; + int cmd_ls_tree(int argc, const char **argv, const char *prefix) { struct object_id oid; struct tree *tree; int i, full_tree = 0; + read_tree_fn_t fn = NULL; const struct option ls_tree_options[] = { OPT_BIT('d', NULL, &ls_options, N_("only show trees"), LS_TREE_ONLY), @@ -133,20 +341,26 @@ int cmd_ls_tree(int argc, const char **argv, const char *prefix) LS_SHOW_TREES), OPT_SET_INT('z', NULL, &line_termination, N_("terminate entries with NUL byte"), 0), - OPT_BIT('l', "long", &ls_options, N_("include object size"), - LS_SHOW_SIZE), - OPT_BIT(0, "name-only", &ls_options, N_("list only filenames"), - LS_NAME_ONLY), - OPT_BIT(0, "name-status", &ls_options, N_("list only filenames"), - LS_NAME_ONLY), + OPT_CMDMODE('l', "long", &cmdmode, N_("include object size"), + MODE_LONG), + OPT_CMDMODE(0, "name-only", &cmdmode, N_("list only filenames"), + MODE_NAME_ONLY), + OPT_CMDMODE(0, "name-status", &cmdmode, N_("list only filenames"), + MODE_NAME_STATUS), + OPT_CMDMODE(0, "object-only", &cmdmode, N_("list only objects"), + MODE_OBJECT_ONLY), OPT_SET_INT(0, "full-name", &chomp_prefix, N_("use full path names"), 0), OPT_BOOL(0, "full-tree", &full_tree, N_("list entire tree; not just current directory " "(implies --full-name)")), + OPT_STRING_F(0, "format", &format, N_("format"), + N_("format to use for the output"), + PARSE_OPT_NONEG), OPT__ABBREV(&abbrev), OPT_END() }; + struct ls_tree_cmdmode_to_fmt *m2f = ls_tree_cmdmode_format; git_config(git_default_config, NULL); ls_tree_prefix = prefix; @@ -159,11 +373,23 @@ int cmd_ls_tree(int argc, const char **argv, const char *prefix) ls_tree_prefix = prefix = NULL; chomp_prefix = 0; } + /* + * We wanted to detect conflicts between --name-only and + * --name-status, but once we're done with that subsequent + * code should only need to check the primary name. + */ + if (cmdmode == MODE_NAME_STATUS) + cmdmode = MODE_NAME_ONLY; + /* -d -r should imply -t, but -d by itself should not have to. */ if ( (LS_TREE_ONLY|LS_RECURSIVE) == ((LS_TREE_ONLY|LS_RECURSIVE) & ls_options)) ls_options |= LS_SHOW_TREES; + if (format && cmdmode) + usage_msg_opt( + _("--format can't be combined with other format-altering options"), + ls_tree_usage, ls_tree_options); if (argc < 1) usage_with_options(ls_tree_usage, ls_tree_options); if (get_oid(argv[0], &oid)) @@ -185,6 +411,24 @@ int cmd_ls_tree(int argc, const char **argv, const char *prefix) tree = parse_tree_indirect(&oid); if (!tree) die("not a tree object"); - return !!read_tree(the_repository, tree, - &pathspec, show_tree, NULL); + /* + * The generic show_tree_fmt() is slower than show_tree(), so + * take the fast path if possible. + */ + while (m2f) { + if (!m2f->fmt) { + fn = format ? show_tree_fmt : show_tree_default; + } else if (format && !strcmp(format, m2f->fmt)) { + cmdmode = m2f->mode; + fn = m2f->fn; + } else if (!format && cmdmode == m2f->mode) { + fn = m2f->fn; + } else { + m2f++; + continue; + } + break; + } + + return !!read_tree(the_repository, tree, &pathspec, fn, NULL); } diff --git a/contrib/coccinelle/strbuf.cocci b/contrib/coccinelle/strbuf.cocci index d9ada69b43..0970d98ad7 100644 --- a/contrib/coccinelle/strbuf.cocci +++ b/contrib/coccinelle/strbuf.cocci @@ -15,7 +15,7 @@ constant fmt !~ "%"; @@ expression E; struct strbuf SB; -format F =~ "s"; +format F =~ "^s$"; @@ - strbuf_addf(E, "%@F@", SB.buf); + strbuf_addbuf(E, &SB); @@ -23,7 +23,7 @@ format F =~ "s"; @@ expression E; struct strbuf *SBP; -format F =~ "s"; +format F =~ "^s$"; @@ - strbuf_addf(E, "%@F@", SBP->buf); + strbuf_addbuf(E, SBP); @@ -44,7 +44,7 @@ struct strbuf *SBP; @@ expression E1, E2; -format F =~ "s"; +format F =~ "^s$"; @@ - strbuf_addf(E1, "%@F@", E2); + strbuf_addstr(E1, E2); diff --git a/t/t3101-ls-tree-dirname.sh b/t/t3101-ls-tree-dirname.sh index 05fde64225..217006d1bf 100755 --- a/t/t3101-ls-tree-dirname.sh +++ b/t/t3101-ls-tree-dirname.sh @@ -201,31 +201,34 @@ EOF test_cmp expected check ' -test_expect_success 'ls-tree --name-only' ' - git ls-tree --name-only $tree >current && - cat >expected <<\EOF && -1.txt -2.txt -path0 -path1 -path2 -path3 -EOF - test_output -' - -test_expect_success 'ls-tree --name-only -r' ' - git ls-tree --name-only -r $tree >current && - cat >expected <<\EOF && -1.txt -2.txt -path0/a/b/c/1.txt -path1/b/c/1.txt -path2/1.txt -path3/1.txt -path3/2.txt -EOF - test_output -' +for opt in --name-only --name-status +do + test_expect_success "ls-tree $opt" ' + git ls-tree $opt $tree >current && + cat >expected <<-\EOF && + 1.txt + 2.txt + path0 + path1 + path2 + path3 + EOF + test_output + ' + + test_expect_success "ls-tree $opt -r" ' + git ls-tree $opt -r $tree >current && + cat >expected <<-\EOF && + 1.txt + 2.txt + path0/a/b/c/1.txt + path1/b/c/1.txt + path2/1.txt + path3/1.txt + path3/2.txt + EOF + test_output + ' +done test_done diff --git a/t/t3103-ls-tree-misc.sh b/t/t3103-ls-tree-misc.sh index d18ba1bd84..81c6343962 100755 --- a/t/t3103-ls-tree-misc.sh +++ b/t/t3103-ls-tree-misc.sh @@ -23,4 +23,19 @@ test_expect_success 'ls-tree fails with non-zero exit code on broken tree' ' test_must_fail git ls-tree -r HEAD ' +for opts in \ + "--long --name-only" \ + "--name-only --name-status" \ + "--name-status --object-only" \ + "--object-only --long" +do + test_expect_success "usage: incompatible options: $opts" ' + test_expect_code 129 git ls-tree $opts $tree + ' + + one_opt=$(echo "$opts" | cut -d' ' -f1) + test_expect_success "usage: incompatible options: $one_opt and --format" ' + test_expect_code 129 git ls-tree $one_opt --format=fmt $tree + ' +done test_done diff --git a/t/t3104-ls-tree-format.sh b/t/t3104-ls-tree-format.sh new file mode 100755 index 0000000000..0769a933d6 --- /dev/null +++ b/t/t3104-ls-tree-format.sh @@ -0,0 +1,76 @@ +#!/bin/sh + +test_description='ls-tree --format' + +TEST_PASSES_SANITIZE_LEAK=true +. ./test-lib.sh + +test_expect_success 'ls-tree --format usage' ' + test_expect_code 129 git ls-tree --format=fmt -l HEAD && + test_expect_code 129 git ls-tree --format=fmt --name-only HEAD && + test_expect_code 129 git ls-tree --format=fmt --name-status HEAD +' + +test_expect_success 'setup' ' + mkdir dir && + test_commit dir/sub-file && + test_commit top-file +' + +test_ls_tree_format () { + format=$1 && + opts=$2 && + fmtopts=$3 && + shift 2 && + + test_expect_success "ls-tree '--format=<$format>' is like options '$opts $fmtopts'" ' + git ls-tree $opts -r HEAD >expect && + git ls-tree --format="$format" -r $fmtopts HEAD >actual && + test_cmp expect actual + ' + + test_expect_success "ls-tree '--format=<$format>' on optimized v.s. non-optimized path" ' + git ls-tree --format="$format" -r $fmtopts HEAD >expect && + git ls-tree --format="> $format" -r $fmtopts HEAD >actual.raw && + sed "s/^> //" >actual <actual.raw && + test_cmp expect actual + ' +} + +test_ls_tree_format \ + "%(objectmode) %(objecttype) %(objectname)%x09%(path)" \ + "" + +test_ls_tree_format \ + "%(objectmode) %(objecttype) %(objectname) %(objectsize:padded)%x09%(path)" \ + "--long" + +test_ls_tree_format \ + "%(path)" \ + "--name-only" + +test_ls_tree_format \ + "%(objectname)" \ + "--object-only" + +test_ls_tree_format \ + "%(objectname)" \ + "--object-only --abbrev" \ + "--abbrev" + +test_ls_tree_format \ + "%(objectmode) %(objecttype) %(objectname)%x09%(path)" \ + "-t" \ + "-t" + +test_ls_tree_format \ + "%(objectmode) %(objecttype) %(objectname)%x09%(path)" \ + "--full-name" \ + "--full-name" + +test_ls_tree_format \ + "%(objectmode) %(objecttype) %(objectname)%x09%(path)" \ + "--full-tree" \ + "--full-tree" + +test_done |