Merge branch 'nd/pretty-formats'

pretty-printing body of the commit that is stored in non UTF-8
encoding did not work well.  The early part of this series fixes
it.  And then it adds %C(auto) specifier that turns the coloring on
when we are emitting to the terminal, and adds column-aligning
format directives.

* nd/pretty-formats:
  pretty: support %>> that steal trailing spaces
  pretty: support truncating in %>, %< and %><
  pretty: support padding placeholders, %< %> and %><
  pretty: add %C(auto) for auto-coloring
  pretty: split color parsing into a separate function
  pretty: two phase conversion for non utf-8 commits
  utf8.c: add reencode_string_len() that can handle NULs in string
  utf8.c: add utf8_strnwidth() with the ability to skip ansi sequences
  utf8.c: move display_mode_esc_sequence_len() for use by other functions
  pretty: share code between format_decoration and show_decorations
  pretty-formats.txt: wrap long lines
  pretty: get the correct encoding for --pretty:format=%e
  pretty: save commit encoding from logmsg_reencode if the caller needs it

Documentation/pretty-formats.txt

@@ -106,18 +106,22 @@ The placeholders are:
 - '%P': parent hashes
 - '%p': abbreviated parent hashes
 - '%an': author name
-- '%aN': author name (respecting .mailmap, see linkgit:git-shortlog[1] or linkgit:git-blame[1])
+- '%aN': author name (respecting .mailmap, see linkgit:git-shortlog[1]
+  or linkgit:git-blame[1])
 - '%ae': author email
-- '%aE': author email (respecting .mailmap, see linkgit:git-shortlog[1] or linkgit:git-blame[1])
+- '%aE': author email (respecting .mailmap, see
+  linkgit:git-shortlog[1] or linkgit:git-blame[1])
 - '%ad': author date (format respects --date= option)
 - '%aD': author date, RFC2822 style
 - '%ar': author date, relative
 - '%at': author date, UNIX timestamp
 - '%ai': author date, ISO 8601 format
 - '%cn': committer name
-- '%cN': committer name (respecting .mailmap, see linkgit:git-shortlog[1] or linkgit:git-blame[1])
+- '%cN': committer name (respecting .mailmap, see
+  linkgit:git-shortlog[1] or linkgit:git-blame[1])
 - '%ce': committer email
-- '%cE': committer email (respecting .mailmap, see linkgit:git-shortlog[1] or linkgit:git-blame[1])
+- '%cE': committer email (respecting .mailmap, see
+  linkgit:git-shortlog[1] or linkgit:git-blame[1])
 - '%cd': committer date
 - '%cD': committer date, RFC2822 style
 - '%cr': committer date, relative
@@ -138,9 +142,11 @@ The placeholders are:
 - '%gD': reflog selector, e.g., `refs/stash@{1}`
 - '%gd': shortened reflog selector, e.g., `stash@{1}`
 - '%gn': reflog identity name
-- '%gN': reflog identity name (respecting .mailmap, see linkgit:git-shortlog[1] or linkgit:git-blame[1])
+- '%gN': reflog identity name (respecting .mailmap, see
+  linkgit:git-shortlog[1] or linkgit:git-blame[1])
 - '%ge': reflog identity email
-- '%gE': reflog identity email (respecting .mailmap, see linkgit:git-shortlog[1] or linkgit:git-blame[1])
+- '%gE': reflog identity email (respecting .mailmap, see
+  linkgit:git-shortlog[1] or linkgit:git-blame[1])
 - '%gs': reflog subject
 - '%Cred': switch color to red
 - '%Cgreen': switch color to green
@@ -150,13 +156,28 @@ The placeholders are:
   adding `auto,` at the beginning will emit color only when colors are
   enabled for log output (by `color.diff`, `color.ui`, or `--color`, and
   respecting the `auto` settings of the former if we are going to a
-  terminal)
+  terminal). `auto` alone (i.e. `%C(auto)`) will turn on auto coloring
+  on the next placeholders until the color is switched again.
 - '%m': left, right or boundary mark
 - '%n': newline
 - '%%': a raw '%'
 - '%x00': print a byte from a hex code
 - '%w([<w>[,<i1>[,<i2>]]])': switch line wrapping, like the -w option of
   linkgit:git-shortlog[1].
+- '%<(<N>[,trunc|ltrunc|mtrunc])': make the next placeholder take at
+  least N columns, padding spaces on the right if necessary.
+  Optionally truncate at the beginning (ltrunc), the middle (mtrunc)
+  or the end (trunc) if the output is longer than N columns.
+  Note that truncating only works correctly with N >= 2.
+- '%<|(<N>)': make the next placeholder take at least until Nth
+  columns, padding spaces on the right if necessary
+- '%>(<N>)', '%>|(<N>)': similar to '%<(<N>)', '%<|(<N>)'
+  respectively, but padding spaces on the left
+- '%>>(<N>)', '%>>|(<N>)': similar to '%>(<N>)', '%>|(<N>)'
+  respectively, except that if the next placeholder takes more spaces
+  than given and there are spaces on its left, use those spaces
+- '%><(<N>)', '%><|(<N>)': similar to '% <(<N>)', '%<|(<N>)'
+  respectively, but padding both sides (i.e. the text is centered)
 
 NOTE: Some placeholders may depend on other options given to the
 revision traversal engine. For example, the `%g*` reflog options will

builtin/blame.c

@@ -1430,7 +1430,7 @@ static void get_commit_info(struct commit *commit,
 	commit_info_init(ret);
 
 	encoding = get_log_output_encoding();
-	message = logmsg_reencode(commit, encoding);
+	message = logmsg_reencode(commit, NULL, encoding);
 	get_ac_line(message, "\nauthor ",
 		    &ret->author, &ret->author_mail,
 		    &ret->author_time, &ret->author_tz);

builtin/commit.c

@@ -955,7 +955,7 @@ static const char *read_commit_message(const char *name)
 	if (!commit)
 		die(_("could not lookup commit %s"), name);
 	out_enc = get_commit_output_encoding();
-	return logmsg_reencode(commit, out_enc);
+	return logmsg_reencode(commit, NULL, out_enc);
 }
 
 static int parse_and_validate_options(int argc, const char *argv[],

commit.h

@@ -101,6 +101,7 @@ struct userformat_want {
 extern int has_non_ascii(const char *text);
 struct rev_info; /* in revision.h, it circularly uses enum cmit_fmt */
 extern char *logmsg_reencode(const struct commit *commit,
+			     char **commit_encoding,
 			     const char *output_encoding);
 extern void logmsg_free(char *msg, const struct commit *commit);
 extern void get_commit_format(const char *arg, struct rev_info *);

compat/precompose_utf8.c

@@ -78,7 +78,7 @@ void precompose_argv(int argc, const char **argv)
 		size_t namelen;
 		oldarg = argv[i];
 		if (has_non_ascii(oldarg, (size_t)-1, &namelen)) {
-			newarg = reencode_string_iconv(oldarg, namelen, ic_precompose);
+			newarg = reencode_string_iconv(oldarg, namelen, ic_precompose, NULL);
 			if (newarg)
 				argv[i] = newarg;
 		}

log-tree.c

@@ -175,36 +175,52 @@ static void show_children(struct rev_info *opt, struct commit *commit, int abbre
 	}
 }
 
-void show_decorations(struct rev_info *opt, struct commit *commit)
+/*
+ * The caller makes sure there is no funny color before
+ * calling. format_decorations makes sure the same after return.
+ */
+void format_decorations(struct strbuf *sb,
+			const struct commit *commit,
+			int use_color)
 {
 	const char *prefix;
 	struct name_decoration *decoration;
 	const char *color_commit =
-		diff_get_color_opt(&opt->diffopt, DIFF_COMMIT);
+		diff_get_color(use_color, DIFF_COMMIT);
 	const char *color_reset =
-		decorate_get_color_opt(&opt->diffopt, DECORATION_NONE);
+		decorate_get_color(use_color, DECORATION_NONE);
 
-	if (opt->show_source && commit->util)
-		printf("\t%s", (char *) commit->util);
-	if (!opt->show_decorations)
-		return;
 	decoration = lookup_decoration(&name_decoration, &commit->object);
 	if (!decoration)
 		return;
 	prefix = " (";
 	while (decoration) {
-		printf("%s", prefix);
+		strbuf_addstr(sb, color_commit);
-		fputs(decorate_get_color_opt(&opt->diffopt, decoration->type),
+		strbuf_addstr(sb, prefix);
-		      stdout);
+		strbuf_addstr(sb, decorate_get_color(use_color, decoration->type));
 		if (decoration->type == DECORATION_REF_TAG)
-			fputs("tag: ", stdout);
+			strbuf_addstr(sb, "tag: ");
-		printf("%s", decoration->name);
+		strbuf_addstr(sb, decoration->name);
-		fputs(color_reset, stdout);
+		strbuf_addstr(sb, color_reset);
-		fputs(color_commit, stdout);
 		prefix = ", ";
 		decoration = decoration->next;
 	}
-	putchar(')');
+	strbuf_addstr(sb, color_commit);
+	strbuf_addch(sb, ')');
+	strbuf_addstr(sb, color_reset);
+}
+
+void show_decorations(struct rev_info *opt, struct commit *commit)
+{
+	struct strbuf sb = STRBUF_INIT;
+
+	if (opt->show_source && commit->util)
+		printf("\t%s", (char *) commit->util);
+	if (!opt->show_decorations)
+		return;
+	format_decorations(&sb, commit, opt->diffopt.use_color);
+	fputs(sb.buf, stdout);
+	strbuf_release(&sb);
 }
 
 static unsigned int digits_in_number(unsigned int number)
@@ -540,8 +556,8 @@ void show_log(struct rev_info *opt)
 			printf(" (from %s)",
 			       find_unique_abbrev(parent->object.sha1,
 						  abbrev_commit));
+		fputs(diff_get_color_opt(&opt->diffopt, DIFF_RESET), stdout);
 		show_decorations(opt, commit);
-		printf("%s", diff_get_color_opt(&opt->diffopt, DIFF_RESET));
 		if (opt->commit_format == CMIT_FMT_ONELINE) {
 			putchar(' ');
 		} else {

log-tree.h

@@ -13,6 +13,7 @@ int log_tree_diff_flush(struct rev_info *);
 int log_tree_commit(struct rev_info *, struct commit *);
 int log_tree_opt_parse(struct rev_info *, const char **, int);
 void show_log(struct rev_info *opt);
+void format_decorations(struct strbuf *sb, const struct commit *commit, int use_color);
 void show_decorations(struct rev_info *opt, struct commit *commit);
 void log_write_email_headers(struct rev_info *opt, struct commit *commit,
 			     const char **subject_p,

pretty.c

@@ -606,6 +606,7 @@ static char *replace_encoding_header(char *buf, const char *encoding)
 }
 
 char *logmsg_reencode(const struct commit *commit,
+		      char **commit_encoding,
 		      const char *output_encoding)
 {
 	static const char *utf8 = "UTF-8";
@@ -627,9 +628,15 @@ char *logmsg_reencode(const struct commit *commit,
 			    sha1_to_hex(commit->object.sha1), typename(type));
 	}
 
-	if (!output_encoding || !*output_encoding)
+	if (!output_encoding || !*output_encoding) {
+		if (commit_encoding)
+			*commit_encoding =
+				get_header(commit, msg, "encoding");
 		return msg;
+	}
 	encoding = get_header(commit, msg, "encoding");
+	if (commit_encoding)
+		*commit_encoding = encoding;
 	use_encoding = encoding ? encoding : utf8;
 	if (same_encoding(use_encoding, output_encoding)) {
 		/*
@@ -670,6 +677,7 @@ char *logmsg_reencode(const struct commit *commit,
 	if (out)
 		out = replace_encoding_header(out, output_encoding);
 
+	if (!commit_encoding)
 		free(encoding);
 	/*
 	 * If the re-encoding failed, out might be NULL here; in that
@@ -764,19 +772,38 @@ struct chunk {
 	size_t len;
 };
 
+enum flush_type {
+	no_flush,
+	flush_right,
+	flush_left,
+	flush_left_and_steal,
+	flush_both
+};
+
+enum trunc_type {
+	trunc_none,
+	trunc_left,
+	trunc_middle,
+	trunc_right
+};
+
 struct format_commit_context {
 	const struct commit *commit;
 	const struct pretty_print_context *pretty_ctx;
 	unsigned commit_header_parsed:1;
 	unsigned commit_message_parsed:1;
 	struct signature_check signature_check;
+	enum flush_type flush_type;
+	enum trunc_type truncate;
 	char *message;
+	char *commit_encoding;
 	size_t width, indent1, indent2;
+	int auto_color;
+	int padding;
 
 	/* These offsets are relative to the start of the commit message. */
 	struct chunk author;
 	struct chunk committer;
-	struct chunk encoding;
 	size_t message_off;
 	size_t subject_off;
 	size_t body_off;
@@ -823,9 +850,6 @@ static void parse_commit_header(struct format_commit_context *context)
 		} else if (!prefixcmp(msg + i, "committer ")) {
 			context->committer.off = i + 10;
 			context->committer.len = eol - i - 10;
-		} else if (!prefixcmp(msg + i, "encoding ")) {
-			context->encoding.off = i + 9;
-			context->encoding.len = eol - i - 9;
 		}
 		i = eol;
 	}
@@ -906,23 +930,6 @@ static void parse_commit_message(struct format_commit_context *c)
 	c->commit_message_parsed = 1;
 }
 
-static void format_decoration(struct strbuf *sb, const struct commit *commit)
-{
-	struct name_decoration *d;
-	const char *prefix = " (";
-
-	load_ref_decorations(DECORATE_SHORT_REFS);
-	d = lookup_decoration(&name_decoration, &commit->object);
-	while (d) {
-		strbuf_addstr(sb, prefix);
-		prefix = ", ";
-		strbuf_addstr(sb, d->name);
-		d = d->next;
-	}
-	if (prefix[0] == ',')
-		strbuf_addch(sb, ')');
-}
-
 static void strbuf_wrap(struct strbuf *sb, size_t pos,
 			size_t width, size_t indent1, size_t indent2)
 {
@@ -969,18 +976,10 @@ static int format_reflog_person(struct strbuf *sb,
 	return format_person_part(sb, part, ident, strlen(ident), dmode);
 }
 
-static size_t format_commit_one(struct strbuf *sb, const char *placeholder,
+static size_t parse_color(struct strbuf *sb, /* in UTF-8 */
-				void *context)
+			  const char *placeholder,
+			  struct format_commit_context *c)
 {
-	struct format_commit_context *c = context;
-	const struct commit *commit = c->commit;
-	const char *msg = c->message;
-	struct commit_list *p;
-	int h1, h2;
-
-	/* these are independent of the commit */
-	switch (placeholder[0]) {
-	case 'C':
 	if (placeholder[1] == '(') {
 		const char *begin = placeholder + 2;
 		const char *end = strchr(begin, ')');
@@ -1013,6 +1012,101 @@ static size_t format_commit_one(struct strbuf *sb, const char *placeholder,
 		return 6;
 	} else
 		return 0;
+}
+
+static size_t parse_padding_placeholder(struct strbuf *sb,
+					const char *placeholder,
+					struct format_commit_context *c)
+{
+	const char *ch = placeholder;
+	enum flush_type flush_type;
+	int to_column = 0;
+
+	switch (*ch++) {
+	case '<':
+		flush_type = flush_right;
+		break;
+	case '>':
+		if (*ch == '<') {
+			flush_type = flush_both;
+			ch++;
+		} else if (*ch == '>') {
+			flush_type = flush_left_and_steal;
+			ch++;
+		} else
+			flush_type = flush_left;
+		break;
+	default:
+		return 0;
+	}
+
+	/* the next value means "wide enough to that column" */
+	if (*ch == '|') {
+		to_column = 1;
+		ch++;
+	}
+
+	if (*ch == '(') {
+		const char *start = ch + 1;
+		const char *end = start + strcspn(start, ",)");
+		char *next;
+		int width;
+		if (!end || end == start)
+			return 0;
+		width = strtoul(start, &next, 10);
+		if (next == start || width == 0)
+			return 0;
+		c->padding = to_column ? -width : width;
+		c->flush_type = flush_type;
+
+		if (*end == ',') {
+			start = end + 1;
+			end = strchr(start, ')');
+			if (!end || end == start)
+				return 0;
+			if (!prefixcmp(start, "trunc)"))
+				c->truncate = trunc_right;
+			else if (!prefixcmp(start, "ltrunc)"))
+				c->truncate = trunc_left;
+			else if (!prefixcmp(start, "mtrunc)"))
+				c->truncate = trunc_middle;
+			else
+				return 0;
+		} else
+			c->truncate = trunc_none;
+
+		return end - placeholder + 1;
+	}
+	return 0;
+}
+
+static size_t format_commit_one(struct strbuf *sb, /* in UTF-8 */
+				const char *placeholder,
+				void *context)
+{
+	struct format_commit_context *c = context;
+	const struct commit *commit = c->commit;
+	const char *msg = c->message;
+	struct commit_list *p;
+	int h1, h2;
+
+	/* these are independent of the commit */
+	switch (placeholder[0]) {
+	case 'C':
+		if (!prefixcmp(placeholder + 1, "(auto)")) {
+			c->auto_color = 1;
+			return 7; /* consumed 7 bytes, "C(auto)" */
+		} else {
+			int ret = parse_color(sb, placeholder, c);
+			if (ret)
+				c->auto_color = 0;
+			/*
+			 * Otherwise, we decided to treat %C<unknown>
+			 * as a literal string, and the previous
+			 * %C(auto) is still valid.
+			 */
+			return ret;
+		}
 	case 'n':		/* newline */
 		strbuf_addch(sb, '\n');
 		return 1;
@@ -1050,6 +1144,10 @@ static size_t format_commit_one(struct strbuf *sb, const char *placeholder,
 			return end - placeholder + 1;
 		} else
 			return 0;
+
+	case '<':
+	case '>':
+		return parse_padding_placeholder(sb, placeholder, c);
 	}
 
 	/* these depend on the commit */
@@ -1058,13 +1156,19 @@ static size_t format_commit_one(struct strbuf *sb, const char *placeholder,
 
 	switch (placeholder[0]) {
 	case 'H':		/* commit hash */
+		strbuf_addstr(sb, diff_get_color(c->auto_color, DIFF_COMMIT));
 		strbuf_addstr(sb, sha1_to_hex(commit->object.sha1));
+		strbuf_addstr(sb, diff_get_color(c->auto_color, DIFF_RESET));
 		return 1;
 	case 'h':		/* abbreviated commit hash */
-		if (add_again(sb, &c->abbrev_commit_hash))
+		strbuf_addstr(sb, diff_get_color(c->auto_color, DIFF_COMMIT));
+		if (add_again(sb, &c->abbrev_commit_hash)) {
+			strbuf_addstr(sb, diff_get_color(c->auto_color, DIFF_RESET));
 			return 1;
+		}
 		strbuf_addstr(sb, find_unique_abbrev(commit->object.sha1,
 						     c->pretty_ctx->abbrev));
+		strbuf_addstr(sb, diff_get_color(c->auto_color, DIFF_RESET));
 		c->abbrev_commit_hash.len = sb->len - c->abbrev_commit_hash.off;
 		return 1;
 	case 'T':		/* tree hash */
@@ -1101,7 +1205,8 @@ static size_t format_commit_one(struct strbuf *sb, const char *placeholder,
 		strbuf_addstr(sb, get_revision_mark(NULL, commit));
 		return 1;
 	case 'd':
-		format_decoration(sb, commit);
+		load_ref_decorations(DECORATE_SHORT_REFS);
+		format_decorations(sb, commit, c->auto_color);
 		return 1;
 	case 'g':		/* reflog info */
 		switch(placeholder[1]) {
@@ -1180,7 +1285,8 @@ static size_t format_commit_one(struct strbuf *sb, const char *placeholder,
 				   msg + c->committer.off, c->committer.len,
 				   c->pretty_ctx->date_mode);
 	case 'e':	/* encoding */
-		strbuf_add(sb, msg + c->encoding.off, c->encoding.len);
+		if (c->commit_encoding)
+			strbuf_addstr(sb, c->commit_encoding);
 		return 1;
 	case 'B':	/* raw body */
 		/* message_off is always left at the initial newline */
@@ -1206,7 +1312,111 @@ static size_t format_commit_one(struct strbuf *sb, const char *placeholder,
 	return 0;	/* unknown placeholder */
 }
 
-static size_t format_commit_item(struct strbuf *sb, const char *placeholder,
+static size_t format_and_pad_commit(struct strbuf *sb, /* in UTF-8 */
+				    const char *placeholder,
+				    struct format_commit_context *c)
+{
+	struct strbuf local_sb = STRBUF_INIT;
+	int total_consumed = 0, len, padding = c->padding;
+	if (padding < 0) {
+		const char *start = strrchr(sb->buf, '\n');
+		int occupied;
+		if (!start)
+			start = sb->buf;
+		occupied = utf8_strnwidth(start, -1, 1);
+		padding = (-padding) - occupied;
+	}
+	while (1) {
+		int modifier = *placeholder == 'C';
+		int consumed = format_commit_one(&local_sb, placeholder, c);
+		total_consumed += consumed;
+
+		if (!modifier)
+			break;
+
+		placeholder += consumed;
+		if (*placeholder != '%')
+			break;
+		placeholder++;
+		total_consumed++;
+	}
+	len = utf8_strnwidth(local_sb.buf, -1, 1);
+
+	if (c->flush_type == flush_left_and_steal) {
+		const char *ch = sb->buf + sb->len - 1;
+		while (len > padding && ch > sb->buf) {
+			const char *p;
+			if (*ch == ' ') {
+				ch--;
+				padding++;
+				continue;
+			}
+			/* check for trailing ansi sequences */
+			if (*ch != 'm')
+				break;
+			p = ch - 1;
+			while (ch - p < 10 && *p != '\033')
+				p--;
+			if (*p != '\033' ||
+			    ch + 1 - p != display_mode_esc_sequence_len(p))
+				break;
+			/*
+			 * got a good ansi sequence, put it back to
+			 * local_sb as we're cutting sb
+			 */
+			strbuf_insert(&local_sb, 0, p, ch + 1 - p);
+			ch = p - 1;
+		}
+		strbuf_setlen(sb, ch + 1 - sb->buf);
+		c->flush_type = flush_left;
+	}
+
+	if (len > padding) {
+		switch (c->truncate) {
+		case trunc_left:
+			strbuf_utf8_replace(&local_sb,
+					    0, len - (padding - 2),
+					    "..");
+			break;
+		case trunc_middle:
+			strbuf_utf8_replace(&local_sb,
+					    padding / 2 - 1,
+					    len - (padding - 2),
+					    "..");
+			break;
+		case trunc_right:
+			strbuf_utf8_replace(&local_sb,
+					    padding - 2, len - (padding - 2),
+					    "..");
+			break;
+		case trunc_none:
+			break;
+		}
+		strbuf_addstr(sb, local_sb.buf);
+	} else {
+		int sb_len = sb->len, offset = 0;
+		if (c->flush_type == flush_left)
+			offset = padding - len;
+		else if (c->flush_type == flush_both)
+			offset = (padding - len) / 2;
+		/*
+		 * we calculate padding in columns, now
+		 * convert it back to chars
+		 */
+		padding = padding - len + local_sb.len;
+		strbuf_grow(sb, padding);
+		strbuf_setlen(sb, sb_len + padding);
+		memset(sb->buf + sb_len, ' ', sb->len - sb_len);
+		memcpy(sb->buf + sb_len + offset, local_sb.buf,
+		       local_sb.len);
+	}
+	strbuf_release(&local_sb);
+	c->flush_type = no_flush;
+	return total_consumed;
+}
+
+static size_t format_commit_item(struct strbuf *sb, /* in UTF-8 */
+				 const char *placeholder,
 				 void *context)
 {
 	int consumed;
@@ -1235,6 +1445,9 @@ static size_t format_commit_item(struct strbuf *sb, const char *placeholder,
 		placeholder++;
 
 	orig_len = sb->len;
+	if (((struct format_commit_context *)context)->flush_type != no_flush)
+		consumed = format_and_pad_commit(sb, placeholder, context);
+	else
 		consumed = format_commit_one(sb, placeholder, context);
 	if (magic == NO_MAGIC)
 		return consumed;
@@ -1286,16 +1499,37 @@ void format_commit_message(const struct commit *commit,
 {
 	struct format_commit_context context;
 	const char *output_enc = pretty_ctx->output_encoding;
+	const char *utf8 = "UTF-8";
 
 	memset(&context, 0, sizeof(context));
 	context.commit = commit;
 	context.pretty_ctx = pretty_ctx;
 	context.wrap_start = sb->len;
-	context.message = logmsg_reencode(commit, output_enc);
+	context.message = logmsg_reencode(commit,
+					  &context.commit_encoding,
+					  output_enc);
 
 	strbuf_expand(sb, format, format_commit_item, &context);
 	rewrap_message_tail(sb, &context, 0, 0, 0);
 
+	if (output_enc) {
+		if (same_encoding(utf8, output_enc))
+			output_enc = NULL;
+	} else {
+		if (context.commit_encoding &&
+		    !same_encoding(context.commit_encoding, utf8))
+			output_enc = context.commit_encoding;
+	}
+
+	if (output_enc) {
+		int outsz;
+		char *out = reencode_string_len(sb->buf, sb->len,
+						output_enc, utf8, &outsz);
+		if (out)
+			strbuf_attach(sb, out, outsz, outsz + 1);
+	}
+
+	free(context.commit_encoding);
 	logmsg_free(context.message, commit);
 	free(context.signature_check.gpg_output);
 	free(context.signature_check.signer);
@@ -1454,7 +1688,7 @@ void pretty_print_commit(const struct pretty_print_context *pp,
 	}
 
 	encoding = get_log_output_encoding();
-	msg = reencoded = logmsg_reencode(commit, encoding);
+	msg = reencoded = logmsg_reencode(commit, NULL, encoding);
 
 	if (pp->fmt == CMIT_FMT_ONELINE || pp->fmt == CMIT_FMT_EMAIL)
 		indent = 0;

revision.c

@@ -2292,7 +2292,7 @@ static int commit_match(struct commit *commit, struct rev_info *opt)
 	 * in it.
 	 */
 	encoding = get_log_output_encoding();
-	message = logmsg_reencode(commit, encoding);
+	message = logmsg_reencode(commit, NULL, encoding);
 
 	/* Copy the commit to temporary if we are using "fake" headers */
 	if (buf.len)

t/t4205-log-pretty-formats.sh

@@ -99,4 +99,179 @@ test_expect_failure 'NUL termination with --stat' '
 	test_i18ncmp expected actual
 '
 
+test_expect_success 'setup more commits' '
+	test_commit "message one" one one message-one &&
+	test_commit "message two" two two message-two
+'
+
+test_expect_success 'left alignment formatting' '
+	git log --pretty="format:%<(40)%s" >actual &&
+	# complete the incomplete line at the end
+	echo >>actual &&
+	qz_to_tab_space <<\EOF >expected &&
+message two                            Z
+message one                            Z
+add bar                                Z
+initial                                Z
+EOF
+	test_cmp expected actual
+'
+
+test_expect_success 'left alignment formatting at the nth column' '
+	git log --pretty="format:%h %<|(40)%s" >actual &&
+	# complete the incomplete line at the end
+	echo >>actual &&
+	qz_to_tab_space <<\EOF >expected &&
+fa33ab1 message two                    Z
+7cd6c63 message one                    Z
+1711bf9 add bar                        Z
+af20c06 initial                        Z
+EOF
+	test_cmp expected actual
+'
+
+test_expect_success 'left alignment formatting with no padding' '
+	git log --pretty="format:%<(1)%s" >actual &&
+	# complete the incomplete line at the end
+	echo >>actual &&
+	cat <<\EOF >expected &&
+message two
+message one
+add bar
+initial
+EOF
+	test_cmp expected actual
+'
+
+test_expect_success 'left alignment formatting with trunc' '
+	git log --pretty="format:%<(10,trunc)%s" >actual &&
+	# complete the incomplete line at the end
+	echo >>actual &&
+	qz_to_tab_space <<\EOF >expected &&
+message ..
+message ..
+add bar  Z
+initial  Z
+EOF
+	test_cmp expected actual
+'
+
+test_expect_success 'left alignment formatting with ltrunc' '
+	git log --pretty="format:%<(10,ltrunc)%s" >actual &&
+	# complete the incomplete line at the end
+	echo >>actual &&
+	qz_to_tab_space <<\EOF >expected &&
+..sage two
+..sage one
+add bar  Z
+initial  Z
+EOF
+	test_cmp expected actual
+'
+
+test_expect_success 'left alignment formatting with mtrunc' '
+	git log --pretty="format:%<(10,mtrunc)%s" >actual &&
+	# complete the incomplete line at the end
+	echo >>actual &&
+	qz_to_tab_space <<\EOF >expected &&
+mess.. two
+mess.. one
+add bar  Z
+initial  Z
+EOF
+	test_cmp expected actual
+'
+
+test_expect_success 'right alignment formatting' '
+	git log --pretty="format:%>(40)%s" >actual &&
+	# complete the incomplete line at the end
+	echo >>actual &&
+	qz_to_tab_space <<\EOF >expected &&
+Z                            message two
+Z                            message one
+Z                                add bar
+Z                                initial
+EOF
+	test_cmp expected actual
+'
+
+test_expect_success 'right alignment formatting at the nth column' '
+	git log --pretty="format:%h %>|(40)%s" >actual &&
+	# complete the incomplete line at the end
+	echo >>actual &&
+	qz_to_tab_space <<\EOF >expected &&
+fa33ab1                      message two
+7cd6c63                      message one
+1711bf9                          add bar
+af20c06                          initial
+EOF
+	test_cmp expected actual
+'
+
+test_expect_success 'right alignment formatting with no padding' '
+	git log --pretty="format:%>(1)%s" >actual &&
+	# complete the incomplete line at the end
+	echo >>actual &&
+	cat <<\EOF >expected &&
+message two
+message one
+add bar
+initial
+EOF
+	test_cmp expected actual
+'
+
+test_expect_success 'center alignment formatting' '
+	git log --pretty="format:%><(40)%s" >actual &&
+	# complete the incomplete line at the end
+	echo >>actual &&
+	qz_to_tab_space <<\EOF >expected &&
+Z             message two              Z
+Z             message one              Z
+Z               add bar                Z
+Z               initial                Z
+EOF
+	test_cmp expected actual
+'
+
+test_expect_success 'center alignment formatting at the nth column' '
+	git log --pretty="format:%h %><|(40)%s" >actual &&
+	# complete the incomplete line at the end
+	echo >>actual &&
+	qz_to_tab_space <<\EOF >expected &&
+fa33ab1           message two          Z
+7cd6c63           message one          Z
+1711bf9             add bar            Z
+af20c06             initial            Z
+EOF
+	test_cmp expected actual
+'
+
+test_expect_success 'center alignment formatting with no padding' '
+	git log --pretty="format:%><(1)%s" >actual &&
+	# complete the incomplete line at the end
+	echo >>actual &&
+	cat <<\EOF >expected &&
+message two
+message one
+add bar
+initial
+EOF
+	test_cmp expected actual
+'
+
+test_expect_success 'left/right alignment formatting with stealing' '
+	git commit --amend -m short --author "long long long <long@me.com>" &&
+	git log --pretty="format:%<(10,trunc)%s%>>(10,ltrunc)% an" >actual &&
+	# complete the incomplete line at the end
+	echo >>actual &&
+	cat <<\EOF >expected &&
+short long  long long
+message ..   A U Thor
+add bar      A U Thor
+initial      A U Thor
+EOF
+	test_cmp expected actual
+'
+
 test_done

t/t4207-log-decoration-colors.sh

@@ -44,15 +44,15 @@ test_expect_success setup '
 '
 
 cat >expected <<EOF
-${c_commit}COMMIT_ID (${c_HEAD}HEAD${c_reset}${c_commit},\
+${c_commit}COMMIT_ID${c_reset}${c_commit} (${c_HEAD}HEAD${c_reset}${c_commit},\
  ${c_tag}tag: v1.0${c_reset}${c_commit},\
  ${c_tag}tag: B${c_reset}${c_commit},\
  ${c_branch}master${c_reset}${c_commit})${c_reset} B
-${c_commit}COMMIT_ID (${c_tag}tag: A1${c_reset}${c_commit},\
+${c_commit}COMMIT_ID${c_reset}${c_commit} (${c_tag}tag: A1${c_reset}${c_commit},\
  ${c_remoteBranch}other/master${c_reset}${c_commit})${c_reset} A1
-${c_commit}COMMIT_ID (${c_stash}refs/stash${c_reset}${c_commit})${c_reset}\
+${c_commit}COMMIT_ID${c_reset}${c_commit} (${c_stash}refs/stash${c_reset}${c_commit})${c_reset}\
  On master: Changes to A.t
-${c_commit}COMMIT_ID (${c_tag}tag: A${c_reset}${c_commit})${c_reset} A
+${c_commit}COMMIT_ID${c_reset}${c_commit} (${c_tag}tag: A${c_reset}${c_commit})${c_reset} A
 EOF
 
 # We want log to show all, but the second parent to refs/stash is irrelevant

t/t6006-rev-list-format.sh

@@ -184,7 +184,7 @@ Test printing of complex bodies
 
 This commit message is much longer than the others,
 and it will be encoded in iso8859-1. We should therefore
-include an iso8859 character: ¡bueno!
+include an iso8859 character: ¡bueno!
 EOF
 test_expect_success 'setup complex body' '
 git config i18n.commitencoding iso8859-1 &&
@@ -192,14 +192,14 @@ git config i18n.commitencoding iso8859-1 &&
 '
 
 test_format complex-encoding %e <<'EOF'
-commit f58db70b055c5718631e5c61528b28b12090cdea
+commit 1ed88da4a5b5ed8c449114ac131efc62178734c3
 iso8859-1
 commit 131a310eb913d107dd3c09a65d1651175898735d
 commit 86c75cfd708a0e5868dc876ed5b8bb66c80b4873
 EOF
 
 test_format complex-subject %s <<'EOF'
-commit f58db70b055c5718631e5c61528b28b12090cdea
+commit 1ed88da4a5b5ed8c449114ac131efc62178734c3
 Test printing of complex bodies
 commit 131a310eb913d107dd3c09a65d1651175898735d
 changed foo
@@ -208,17 +208,17 @@ added foo
 EOF
 
 test_format complex-body %b <<'EOF'
-commit f58db70b055c5718631e5c61528b28b12090cdea
+commit 1ed88da4a5b5ed8c449114ac131efc62178734c3
 This commit message is much longer than the others,
 and it will be encoded in iso8859-1. We should therefore
-include an iso8859 character: ¡bueno!
+include an iso8859 character: ¡bueno!
 
 commit 131a310eb913d107dd3c09a65d1651175898735d
 commit 86c75cfd708a0e5868dc876ed5b8bb66c80b4873
 EOF
 
 test_expect_success '%x00 shows NUL' '
-	echo  >expect commit f58db70b055c5718631e5c61528b28b12090cdea &&
+	echo  >expect commit 1ed88da4a5b5ed8c449114ac131efc62178734c3 &&
 	echo >>expect fooQbar &&
 	git rev-list -1 --format=foo%x00bar HEAD >actual.nul &&
 	nul_to_q <actual.nul >actual &&

utf8.c

@@ -9,6 +9,20 @@ struct interval {
   int last;
 };
 
+size_t display_mode_esc_sequence_len(const char *s)
+{
+	const char *p = s;
+	if (*p++ != '\033')
+		return 0;
+	if (*p++ != '[')
+		return 0;
+	while (isdigit(*p) || *p == ';')
+		p++;
+	if (*p++ != 'm')
+		return 0;
+	return p - s;
+}
+
 /* auxiliary function for binary search in interval table */
 static int bisearch(ucs_char_t ucs, const struct interval *table, int max)
 {
@@ -252,18 +266,26 @@ int utf8_width(const char **start, size_t *remainder_p)
  * string, assuming that the string is utf8.  Returns strlen() instead
  * if the string does not look like a valid utf8 string.
  */
-int utf8_strwidth(const char *string)
+int utf8_strnwidth(const char *string, int len, int skip_ansi)
 {
 	int width = 0;
 	const char *orig = string;
 
-	while (1) {
+	if (len == -1)
-		if (!string)
+		len = strlen(string);
-			return strlen(orig);
+	while (string && string < orig + len) {
-		if (!*string)
+		int skip;
-			return width;
+		while (skip_ansi &&
+		       (skip = display_mode_esc_sequence_len(string)) != 0)
+			string += skip;
 		width += utf8_width(&string, NULL);
 	}
+	return string ? width : len;
+}
+
+int utf8_strwidth(const char *string)
+{
+	return utf8_strnwidth(string, -1, 0);
 }
 
 int is_utf8(const char *text)
@@ -303,20 +325,6 @@ static void strbuf_add_indented_text(struct strbuf *buf, const char *text,
 	}
 }
 
-static size_t display_mode_esc_sequence_len(const char *s)
-{
-	const char *p = s;
-	if (*p++ != '\033')
-		return 0;
-	if (*p++ != '[')
-		return 0;
-	while (isdigit(*p) || *p == ';')
-		p++;
-	if (*p++ != 'm')
-		return 0;
-	return p - s;
-}
-
 /*
  * Wrap the text, if necessary. The variable indent is the indent for the
  * first line, indent2 is the indent for all other lines.
@@ -413,6 +421,52 @@ void strbuf_add_wrapped_bytes(struct strbuf *buf, const char *data, int len,
 	free(tmp);
 }
 
+void strbuf_utf8_replace(struct strbuf *sb_src, int pos, int width,
+			 const char *subst)
+{
+	struct strbuf sb_dst = STRBUF_INIT;
+	char *src = sb_src->buf;
+	char *end = src + sb_src->len;
+	char *dst;
+	int w = 0, subst_len = 0;
+
+	if (subst)
+		subst_len = strlen(subst);
+	strbuf_grow(&sb_dst, sb_src->len + subst_len);
+	dst = sb_dst.buf;
+
+	while (src < end) {
+		char *old;
+		size_t n;
+
+		while ((n = display_mode_esc_sequence_len(src))) {
+			memcpy(dst, src, n);
+			src += n;
+			dst += n;
+		}
+
+		old = src;
+		n = utf8_width((const char**)&src, NULL);
+		if (!src) 	/* broken utf-8, do nothing */
+			return;
+		if (n && w >= pos && w < pos + width) {
+			if (subst) {
+				memcpy(dst, subst, subst_len);
+				dst += subst_len;
+				subst = NULL;
+			}
+			w += n;
+			continue;
+		}
+		memcpy(dst, old, src - old);
+		dst += src - old;
+		w += n;
+	}
+	strbuf_setlen(&sb_dst, dst - sb_dst.buf);
+	strbuf_attach(sb_src, strbuf_detach(&sb_dst, NULL),
+		      sb_dst.len, sb_dst.alloc);
+}
+
 int is_encoding_utf8(const char *name)
 {
 	if (!name)
@@ -460,7 +514,7 @@ int utf8_fprintf(FILE *stream, const char *format, ...)
 #else
 	typedef char * iconv_ibp;
 #endif
-char *reencode_string_iconv(const char *in, size_t insz, iconv_t conv)
+char *reencode_string_iconv(const char *in, size_t insz, iconv_t conv, int *outsz_p)
 {
 	size_t outsz, outalloc;
 	char *out, *outpos;
@@ -494,13 +548,17 @@ char *reencode_string_iconv(const char *in, size_t insz, iconv_t conv)
 		}
 		else {
 			*outpos = '\0';
+			if (outsz_p)
+				*outsz_p = outpos - out;
 			break;
 		}
 	}
 	return out;
 }
 
-char *reencode_string(const char *in, const char *out_encoding, const char *in_encoding)
+char *reencode_string_len(const char *in, int insz,
+			  const char *out_encoding, const char *in_encoding,
+			  int *outsz)
 {
 	iconv_t conv;
 	char *out;
@@ -526,7 +584,7 @@ char *reencode_string(const char *in, const char *out_encoding, const char *in_e
 			return NULL;
 	}
 
-	out = reencode_string_iconv(in, strlen(in), conv);
+	out = reencode_string_iconv(in, insz, conv, outsz);
 	iconv_close(conv);
 	return out;
 }

utf8.h

@@ -3,7 +3,9 @@
 
 typedef unsigned int ucs_char_t;  /* assuming 32bit int */
 
+size_t display_mode_esc_sequence_len(const char *s);
 int utf8_width(const char **start, size_t *remainder_p);
+int utf8_strnwidth(const char *string, int len, int skip_ansi);
 int utf8_strwidth(const char *string);
 int is_utf8(const char *text);
 int is_encoding_utf8(const char *name);
@@ -14,14 +16,29 @@ void strbuf_add_wrapped_text(struct strbuf *buf,
 		const char *text, int indent, int indent2, int width);
 void strbuf_add_wrapped_bytes(struct strbuf *buf, const char *data, int len,
 			     int indent, int indent2, int width);
+void strbuf_utf8_replace(struct strbuf *sb, int pos, int width,
+			 const char *subst);
 
 #ifndef NO_ICONV
-char *reencode_string_iconv(const char *in, size_t insz, iconv_t conv);
+char *reencode_string_iconv(const char *in, size_t insz,
-char *reencode_string(const char *in, const char *out_encoding, const char *in_encoding);
+			    iconv_t conv, int *outsz);
+char *reencode_string_len(const char *in, int insz,
+			  const char *out_encoding,
+			  const char *in_encoding,
+			  int *outsz);
 #else
-#define reencode_string(a,b,c) NULL
+#define reencode_string_len(a,b,c,d,e) NULL
 #endif
 
+static inline char *reencode_string(const char *in,
+				    const char *out_encoding,
+				    const char *in_encoding)
+{
+	return reencode_string_len(in, strlen(in),
+				   out_encoding, in_encoding,
+				   NULL);
+}
+
 int mbs_chrlen(const char **text, size_t *remainder_p, const char *encoding);
 
 #endif