branch -v: align even when branch names are in UTF-8

Branch names are usually in ASCII so they are not the problem. The
problem most likely comes from "(no branch)" translation, which is
in UTF-8 and makes display-width calculation just wrong.  Clarify
this by renaming the field "len" in struct ref_item to "width", as
it stores the display-width and is used to compute the width of the
screen needed to show the names of all the branches, and compute the
display width using utf8_strwidth(), not byte-length with strlen().

Update document to mention the fact that we may want ref names in
UTF-8. Encodings that produce invalid UTF-8 are safe as utf8_strwidth()
falls back to strlen(). The ones that incidentally produce valid UTF-8
sequences will cause misalignment.

Signed-off-by: Nguyễn Thái Ngọc Duy <pclouds@gmail.com>
Signed-off-by: Junio C Hamano <gitster@pobox.com>

diff --git a/Documentation/revisions.txt b/Documentation/revisions.txt
index dc0070bcb7ec2f4e6773066ffb745967d9df6fb3..175d39780df4ecd689398d47582e1f1dca552471 100644 (file)
--- a/Documentation/revisions.txt
+++ b/Documentation/revisions.txt
@@ -55,6 +55,8 @@ when you run `git cherry-pick`.
 +
 Note that any of the 'refs/*' cases above may come either from
 the '$GIT_DIR/refs' directory or from the '$GIT_DIR/packed-refs' file.
+While the ref name encoding is unspecified, UTF-8 is prefered as
+some output processing may assume ref names in UTF-8.
 
 '<refname>@\{<date>\}', e.g. 'master@\{yesterday\}', 'HEAD@\{5 minutes ago\}'::
   A ref followed by the suffix '@' with a date specification

diff --git a/builtin/branch.c b/builtin/branch.c
index 0e060f2e4a982efdda0f88d021e0a9d3f23c6b75..4ec556fe18812167b8f3fb5884b71afede7b9bb1 100644 (file)
--- a/builtin/branch.c
+++ b/builtin/branch.c
@@ -17,6 +17,7 @@
 #include "revision.h"
 #include "string-list.h"
 #include "column.h"
+#include "utf8.h"
 
 static const char * const builtin_branch_usage[] = {
        "git branch [options] [-r | -a] [--merged | --no-merged]",
@@ -249,7 +250,7 @@ static int delete_branches(int argc, const char **argv, int force, int kinds,
 struct ref_item {
        char *name;
        char *dest;
-       unsigned int kind, len;
+       unsigned int kind, width;
        struct commit *commit;
 };
 
@@ -354,14 +355,14 @@ static int append_ref(const char *refname, const unsigned char *sha1, int flags,
        newitem->name = xstrdup(refname);
        newitem->kind = kind;
        newitem->commit = commit;
-       newitem->len = strlen(refname);
+       newitem->width = utf8_strwidth(refname);
        newitem->dest = resolve_symref(orig_refname, prefix);
        /* adjust for "remotes/" */
        if (newitem->kind == REF_REMOTE_BRANCH &&
            ref_list->kinds != REF_REMOTE_BRANCH)
-               newitem->len += 8;
-       if (newitem->len > ref_list->maxwidth)
-               ref_list->maxwidth = newitem->len;
+               newitem->width += 8;
+       if (newitem->width > ref_list->maxwidth)
+               ref_list->maxwidth = newitem->width;
 
        return 0;
 }
@@ -490,11 +491,12 @@ static void print_ref_item(struct ref_item *item, int maxwidth, int verbose,
        }
 
        strbuf_addf(&name, "%s%s", prefix, item->name);
-       if (verbose)
+       if (verbose) {
+               int utf8_compensation = strlen(name.buf) - utf8_strwidth(name.buf);
                strbuf_addf(&out, "%c %s%-*s%s", c, branch_get_color(color),
-                           maxwidth, name.buf,
+                           maxwidth + utf8_compensation, name.buf,
                            branch_get_color(BRANCH_COLOR_RESET));
-       else
+       } else
                strbuf_addf(&out, "%c %s%s%s", c, branch_get_color(color),
                            name.buf, branch_get_color(BRANCH_COLOR_RESET));
 
@@ -519,8 +521,8 @@ static int calc_maxwidth(struct ref_list *refs)
        for (i = 0; i < refs->index; i++) {
                if (!matches_merge_filter(refs->list[i].commit))
                        continue;
-               if (refs->list[i].len > w)
-                       w = refs->list[i].len;
+               if (refs->list[i].width > w)
+                       w = refs->list[i].width;
        }
        return w;
 }
@@ -533,12 +535,12 @@ static void show_detached(struct ref_list *ref_list)
        if (head_commit && is_descendant_of(head_commit, ref_list->with_commit)) {
                struct ref_item item;
                item.name = xstrdup(_("(no branch)"));
-               item.len = strlen(item.name);
+               item.width = utf8_strwidth(item.name);
                item.kind = REF_LOCAL_BRANCH;
                item.dest = NULL;
                item.commit = head_commit;
-               if (item.len > ref_list->maxwidth)
-                       ref_list->maxwidth = item.len;
+               if (item.width > ref_list->maxwidth)
+                       ref_list->maxwidth = item.width;
                print_ref_item(&item, ref_list->maxwidth, ref_list->verbose, ref_list->abbrev, 1, "");
                free(item.name);
        }