[GSoC Patch 2/2] repo: add Unicode support for `repo structure` output
K Jayatheerth <[email protected]>
| Newsgroups | org.kernel.vger.git |
|---|---|
| Message-ID | <[email protected]> |
ASCII output ignores locale support for UTF-8. Use box-drawing characters and bullets when the locale supports UTF-8, since modern terminals render tables cleanly this way, and fall back to ASCII otherwise. Tests now discover an available UTF-8 locale to set a `UTF8_LOCALE` prerequisite, and existing ASCII table tests are explicitly pinned to `LC_ALL=C` so their behavior remains deterministic regardless of the runner's environment. Mentored-by: Justin Tobler <[email protected]> Mentored-by: Lucas Seiki Oshiro <[email protected]> Signed-off-by: K Jayatheerth <[email protected]> --- builtin/repo.c | 110 ++++++++++++++++------------- t/t1901-repo-structure.sh | 141 +++++++++++++++++++++++++++++++++++++- 2 files changed, 203 insertions(+), 48 deletions(-) diff --git a/builtin/repo.c b/builtin/repo.c index 84e012f83f..2c1cca6f2e 100644 --- a/builtin/repo.c +++ b/builtin/repo.c @@ -498,82 +498,86 @@ static void stats_table_setup_structure(struct stats_table *table, size_t object_count_total; size_t disk_object_total; size_t ref_total; + const int utf8 = is_utf8_locale(); + const char *bullet_l0 = utf8 ? "•" : "*"; + const char *bullet_l1 = utf8 ? " •" : " *"; + const char *bullet_l2 = utf8 ? " •" : " *"; ref_total = get_total_reference_count(refs); - stats_table_addf(table, "* %s", _("References")); - stats_table_count_addf(table, ref_total, " * %s", _("Count")); - stats_table_count_addf(table, refs->branches, " * %s", _("Branches")); - stats_table_count_addf(table, refs->tags, " * %s", _("Tags")); - stats_table_count_addf(table, refs->remotes, " * %s", _("Remotes")); - stats_table_count_addf(table, refs->others, " * %s", _("Others")); + stats_table_addf(table, "%s %s", bullet_l0, _("References")); + stats_table_count_addf(table, ref_total, "%s %s", bullet_l1, _("Count")); + stats_table_count_addf(table, refs->branches, "%s %s", bullet_l2, _("Branches")); + stats_table_count_addf(table, refs->tags, "%s %s", bullet_l2, _("Tags")); + stats_table_count_addf(table, refs->remotes, "%s %s", bullet_l2, _("Remotes")); + stats_table_count_addf(table, refs->others, "%s %s", bullet_l2, _("Others")); object_count_total = get_total_object_values(&objects->type_counts); stats_table_addf(table, ""); - stats_table_addf(table, "* %s", _("Reachable objects")); - stats_table_count_addf(table, object_count_total, " * %s", _("Count")); + stats_table_addf(table, "%s %s", bullet_l0, _("Reachable objects")); + stats_table_count_addf(table, object_count_total, "%s %s", bullet_l1, _("Count")); stats_table_count_addf(table, objects->type_counts.commits, - " * %s", _("Commits")); + "%s %s", bullet_l2, _("Commits")); stats_table_count_addf(table, objects->type_counts.trees, - " * %s", _("Trees")); + "%s %s", bullet_l2, _("Trees")); stats_table_count_addf(table, objects->type_counts.blobs, - " * %s", _("Blobs")); + "%s %s", bullet_l2, _("Blobs")); stats_table_count_addf(table, objects->type_counts.tags, - " * %s", _("Tags")); + "%s %s", bullet_l2, _("Tags")); inflated_object_total = get_total_object_values(&objects->inflated_sizes); stats_table_size_addf(table, inflated_object_total, - " * %s", _("Inflated size")); + "%s %s", bullet_l1, _("Inflated size")); stats_table_size_addf(table, objects->inflated_sizes.commits, - " * %s", _("Commits")); + "%s %s", bullet_l2, _("Commits")); stats_table_size_addf(table, objects->inflated_sizes.trees, - " * %s", _("Trees")); + "%s %s", bullet_l2, _("Trees")); stats_table_size_addf(table, objects->inflated_sizes.blobs, - " * %s", _("Blobs")); + "%s %s", bullet_l2, _("Blobs")); stats_table_size_addf(table, objects->inflated_sizes.tags, - " * %s", _("Tags")); + "%s %s", bullet_l2, _("Tags")); disk_object_total = get_total_object_values(&objects->disk_sizes); stats_table_size_addf(table, disk_object_total, - " * %s", _("Disk size")); + "%s %s", bullet_l1, _("Disk size")); stats_table_size_addf(table, objects->disk_sizes.commits, - " * %s", _("Commits")); + "%s %s", bullet_l2, _("Commits")); stats_table_size_addf(table, objects->disk_sizes.trees, - " * %s", _("Trees")); + "%s %s", bullet_l2, _("Trees")); stats_table_size_addf(table, objects->disk_sizes.blobs, - " * %s", _("Blobs")); + "%s %s", bullet_l2, _("Blobs")); stats_table_size_addf(table, objects->disk_sizes.tags, - " * %s", _("Tags")); + "%s %s", bullet_l2, _("Tags")); stats_table_addf(table, ""); - stats_table_addf(table, "* %s", _("Largest objects")); - stats_table_addf(table, " * %s", _("Commits")); + stats_table_addf(table, "%s %s", bullet_l0, _("Largest objects")); + stats_table_addf(table, "%s %s", bullet_l1, _("Commits")); stats_table_object_size_addf(table, &objects->largest.commit_size.oid, objects->largest.commit_size.value, - " * %s", _("Maximum size")); + "%s %s", bullet_l2, _("Maximum size")); stats_table_object_count_addf(table, &objects->largest.parent_count.oid, objects->largest.parent_count.value, - " * %s", _("Maximum parents")); - stats_table_addf(table, " * %s", _("Trees")); + "%s %s", bullet_l2, _("Maximum parents")); + stats_table_addf(table, "%s %s", bullet_l1, _("Trees")); stats_table_object_size_addf(table, &objects->largest.tree_size.oid, objects->largest.tree_size.value, - " * %s", _("Maximum size")); + "%s %s", bullet_l2, _("Maximum size")); stats_table_object_count_addf(table, &objects->largest.tree_entries.oid, objects->largest.tree_entries.value, - " * %s", _("Maximum entries")); - stats_table_addf(table, " * %s", _("Blobs")); + "%s %s", bullet_l2, _("Maximum entries")); + stats_table_addf(table, "%s %s", bullet_l1, _("Blobs")); stats_table_object_size_addf(table, &objects->largest.blob_size.oid, objects->largest.blob_size.value, - " * %s", _("Maximum size")); - stats_table_addf(table, " * %s", _("Tags")); + "%s %s", bullet_l2, _("Maximum size")); + stats_table_addf(table, "%s %s", bullet_l1, _("Tags")); stats_table_object_size_addf(table, &objects->largest.tag_size.oid, objects->largest.tag_size.value, - " * %s", _("Maximum size")); + "%s %s", bullet_l2, _("Maximum size")); } #define INDEX_WIDTH 4 @@ -589,28 +593,42 @@ static void stats_table_print_structure(const struct stats_table *table) int unit_col_width = table->unit_col_width; struct string_list_item *item; struct strbuf buf = STRBUF_INIT; + const int utf8 = is_utf8_locale(); + const char *border_left = utf8 ? "│ " : "| "; + const char *border_mid = utf8 ? " │ " : " | "; + const char *border_right = utf8 ? " │" : " |"; if (title_name_width > name_col_width) name_col_width = title_name_width; if (title_value_width > value_col_width + unit_col_width + 1) value_col_width = title_value_width - unit_col_width; - strbuf_addstr(&buf, "| "); + strbuf_addstr(&buf, border_left); strbuf_utf8_align(&buf, ALIGN_LEFT, name_col_width + INDEX_WIDTH, name_col_title); - strbuf_addstr(&buf, " | "); + strbuf_addstr(&buf, border_mid); strbuf_utf8_align(&buf, ALIGN_LEFT, value_col_width + unit_col_width + 1, value_col_title); - strbuf_addstr(&buf, " |"); + strbuf_addstr(&buf, border_right); printf("%s\n", buf.buf); - printf("| "); - for (int i = 0; i < name_col_width + INDEX_WIDTH; i++) - putchar('-'); - printf(" | "); - for (int i = 0; i < value_col_width + unit_col_width + 1; i++) - putchar('-'); - printf(" |\n"); + if (utf8) { + printf("├─"); + for (int i = 0; i < name_col_width + INDEX_WIDTH; i++) + printf("─"); + printf("─┼─"); + for (int i = 0; i < value_col_width + unit_col_width + 1; i++) + printf("─"); + printf("─┤\n"); + } else { + printf("| "); + for (int i = 0; i < name_col_width + INDEX_WIDTH; i++) + putchar('-'); + printf(" | "); + for (int i = 0; i < value_col_width + unit_col_width + 1; i++) + putchar('-'); + printf(" |\n"); + } for_each_string_list_item(item, &table->rows) { struct stats_table_entry *entry = item->util; @@ -624,7 +642,7 @@ static void stats_table_print_structure(const struct stats_table *table) } strbuf_reset(&buf); - strbuf_addstr(&buf, "| "); + strbuf_addstr(&buf, border_left); strbuf_utf8_align(&buf, ALIGN_LEFT, name_col_width, item->string); if (entry && entry->oid) @@ -633,11 +651,11 @@ static void stats_table_print_structure(const struct stats_table *table) else strbuf_addchars(&buf, ' ', INDEX_WIDTH); - strbuf_addstr(&buf, " | "); + strbuf_addstr(&buf, border_mid); strbuf_utf8_align(&buf, ALIGN_RIGHT, value_col_width, value); strbuf_addch(&buf, ' '); strbuf_utf8_align(&buf, ALIGN_LEFT, unit_col_width, unit); - strbuf_addstr(&buf, " |"); + strbuf_addstr(&buf, border_right); printf("%s\n", buf.buf); } diff --git a/t/t1901-repo-structure.sh b/t/t1901-repo-structure.sh index 02cc2b594a..926db09175 100755 --- a/t/t1901-repo-structure.sh +++ b/t/t1901-repo-structure.sh @@ -4,6 +4,29 @@ test_description='test git repo structure' . ./test-lib.sh +# Detect if a UTF-8 locale is available on the test system. +if test -z "$GIT_TEST_UTF8_LOCALE" +then + case "${LC_ALL:-$LANG}" in + *.[Uu][Tt][Ff]8 | *.[Uu][Tt][Ff]-8) + GIT_TEST_UTF8_LOCALE="${LC_ALL:-$LANG}" + ;; + *) + if type locale >/dev/null 2>&1 + then + GIT_TEST_UTF8_LOCALE=$(locale -a 2>/dev/null | sed -n '/\.[uU][tT][fF]-*8$/{ + p + q + }') + fi + ;; + esac +fi +if test -n "$GIT_TEST_UTF8_LOCALE" +then + test_set_prereq UTF8_LOCALE +fi + object_type_disk_usage() { disk_usage_opt="--disk-usage" @@ -66,7 +89,10 @@ test_expect_success 'empty repository' ' | * Maximum size | 0 B | EOF - git repo structure >out 2>err && + # Force a non-UTF8 locale so this test always exercises the + # ASCII fallback formatting, regardless of what locale the + # runner defaults to. + LC_ALL=C git repo structure >out 2>err && test_cmp expect out && test_line_count = 0 err @@ -137,7 +163,10 @@ test_expect_success SHA1 'repository with references and objects' ' [6] 4dae4f5954f5e6feb3577cfb1b181daa3fd3afd2 EOF - git repo structure >out 2>err && + # Force a non-UTF8 locale so this test always exercises the + # ASCII fallback formatting, regardless of what locale the + # runner defaults to. + LC_ALL=C git repo structure >out 2>err && test_cmp expect out && test_line_count = 0 err @@ -230,4 +259,112 @@ test_expect_success 'git repo structure -h shows only repo structure usage' ' test_grep ! "git repo info" actual ' +test_expect_success UTF8_LOCALE 'unicode output under UTF-8 locale with missing locale dir' ' + test_when_finished "rm -rf repo" && + git init repo && + ( + cd repo && + cat >expect <<-\EOF && + │ Repository structure │ Value │ + ├───────────────────────────┼────────┤ + │ • References │ │ + │ • Count │ 0 │ + │ • Branches │ 0 │ + │ • Tags │ 0 │ + │ • Remotes │ 0 │ + │ • Others │ 0 │ + │ │ │ + │ • Reachable objects │ │ + │ • Count │ 0 │ + │ • Commits │ 0 │ + │ • Trees │ 0 │ + │ • Blobs │ 0 │ + │ • Tags │ 0 │ + │ • Inflated size │ 0 B │ + │ • Commits │ 0 B │ + │ • Trees │ 0 B │ + │ • Blobs │ 0 B │ + │ • Tags │ 0 B │ + │ • Disk size │ 0 B │ + │ • Commits │ 0 B │ + │ • Trees │ 0 B │ + │ • Blobs │ 0 B │ + │ • Tags │ 0 B │ + │ │ │ + │ • Largest objects │ │ + │ • Commits │ │ + │ • Maximum size │ 0 B │ + │ • Maximum parents │ 0 │ + │ • Trees │ │ + │ • Maximum size │ 0 B │ + │ • Maximum entries │ 0 │ + │ • Blobs │ │ + │ • Maximum size │ 0 B │ + │ • Tags │ │ + │ • Maximum size │ 0 B │ + EOF + # Point GIT_TEXTDOMAINDIR at a nonexistent path so + # git_setup_gettext() takes its early-return path (its + # locale-directory check fails) and never populates the + # gettext-internal charset. This exercises the + # is_utf8_locale() fallback that derives the charset + # directly from LC_ALL/LC_CTYPE/LANG instead, regardless of + # whether gettext itself was able to initialize. + GIT_TEXTDOMAINDIR="$TRASH_DIRECTORY/nonexistent-locale-dir" \ + LC_ALL="$GIT_TEST_UTF8_LOCALE" git repo structure >out 2>err && + test_cmp expect out && + test_line_count = 0 err + ) +' + +test_expect_success UTF8_LOCALE 'unicode output under UTF-8 locale' ' + test_when_finished "rm -rf repo" && + git init repo && + ( + cd repo && + cat >expect <<-\EOF && + │ Repository structure │ Value │ + ├───────────────────────────┼────────┤ + │ • References │ │ + │ • Count │ 0 │ + │ • Branches │ 0 │ + │ • Tags │ 0 │ + │ • Remotes │ 0 │ + │ • Others │ 0 │ + │ │ │ + │ • Reachable objects │ │ + │ • Count │ 0 │ + │ • Commits │ 0 │ + │ • Trees │ 0 │ + │ • Blobs │ 0 │ + │ • Tags │ 0 │ + │ • Inflated size │ 0 B │ + │ • Commits │ 0 B │ + │ • Trees │ 0 B │ + │ • Blobs │ 0 B │ + │ • Tags │ 0 B │ + │ • Disk size │ 0 B │ + │ • Commits │ 0 B │ + │ • Trees │ 0 B │ + │ • Blobs │ 0 B │ + │ • Tags │ 0 B │ + │ │ │ + │ • Largest objects │ │ + │ • Commits │ │ + │ • Maximum size │ 0 B │ + │ • Maximum parents │ 0 │ + │ • Trees │ │ + │ • Maximum size │ 0 B │ + │ • Maximum entries │ 0 │ + │ • Blobs │ │ + │ • Maximum size │ 0 B │ + │ • Tags │ │ + │ • Maximum size │ 0 B │ + EOF + LC_ALL="$GIT_TEST_UTF8_LOCALE" git repo structure >out 2>err && + test_cmp expect out && + test_line_count = 0 err + ) +' + test_done -- 2.55.GIT