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

Author: gitster

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);
-		fputs(decorate_get_color_opt(&opt->diffopt, decoration->type),
-		      stdout);
+		strbuf_addstr(sb, color_commit);
+		strbuf_addstr(sb, prefix);
+		strbuf_addstr(sb, decorate_get_color(use_color, decoration->type));
 		if (decoration->type == DECORATION_REF_TAG)
-			fputs("tag: ", stdout);
-		printf("%s", decoration->name);
-		fputs(color_reset, stdout);
-		fputs(color_commit, stdout);
+			strbuf_addstr(sb, "tag: ");
+		strbuf_addstr(sb, decoration->name);
+		strbuf_addstr(sb, color_reset);
 		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,