pretty: expand tabs in indented logs to make things line up properly

A commit log message sometimes tries to line things up using tabs,
assuming fixed-width font with the standard 8-place tab settings.
Viewing such a commit however does not work well in "git log", as
we indent the lines by prefixing 4 spaces in front of them.

This should all line up:

  Column 1	Column 2
  --------	--------
  A		B
  ABCD		EFGH
  SPACES        Instead of Tabs

Even with multi-byte UTF8 characters:

  Column 1	Column 2
  --------	--------
  Ä		B
  åäö		100
  A Møøse	once bit my sister..

Tab-expand the lines in "git log --expand-tabs" output before
prefixing 4 spaces.

This is based on the patch by Linus Torvalds, but at this step, we
require an explicit command line option to enable the behaviour.

Signed-off-by: Junio C Hamano <gitster@pobox.com>

1 files changed, 69 insertions, 2 deletions

diff --git a/pretty.c b/pretty.c
index 92b2870a7e..c8b075d91b 100644
--- a/pretty.c
+++ b/pretty.c
@@ -1629,6 +1629,72 @@ void pp_title_line(struct pretty_print_context *pp,
 	strbuf_release(&title);
 }
 
+static int pp_utf8_width(const char *start, const char *end)
+{
+	int width = 0;
+	size_t remain = end - start;
+
+	while (remain) {
+		int n = utf8_width(&start, &remain);
+		if (n < 0 || !start)
+			return -1;
+		width += n;
+	}
+	return width;
+}
+
+static void strbuf_add_tabexpand(struct strbuf *sb,
+				 const char *line, int linelen)
+{
+	const char *tab;
+
+	while ((tab = memchr(line, '\t', linelen)) != NULL) {
+		int width = pp_utf8_width(line, tab);
+
+		/*
+		 * If it wasn't well-formed utf8, or it
+		 * had characters with badly defined
+		 * width (control characters etc), just
+		 * give up on trying to align things.
+		 */
+		if (width < 0)
+			break;
+
+		/* Output the data .. */
+		strbuf_add(sb, line, tab - line);
+
+		/* .. and the de-tabified tab */
+		strbuf_addchars(sb, ' ', 8 - (width % 8));
+
+		/* Skip over the printed part .. */
+		linelen -= tab + 1 - line;
+		line = tab + 1;
+	}
+
+	/*
+	 * Print out everything after the last tab without
+	 * worrying about width - there's nothing more to
+	 * align.
+	 */
+	strbuf_add(sb, line, linelen);
+}
+
+/*
+ * pp_handle_indent() prints out the intendation, and
+ * the whole line (without the final newline), after
+ * de-tabifying.
+ */
+static void pp_handle_indent(struct pretty_print_context *pp,
+			     struct strbuf *sb, int indent,
+			     const char *line, int linelen)
+{
+	strbuf_addchars(sb, ' ', indent);
+	if (pp->expand_tabs_in_log)
+		strbuf_add_tabexpand(sb, line, linelen);
+	else
+		strbuf_add(sb, line, linelen);
+}
+
 void pp_remainder(struct pretty_print_context *pp,
 		  const char **msg_p,
 		  struct strbuf *sb,
@@ -1653,8 +1719,9 @@ void pp_remainder(struct pretty_print_context *pp,
 
 		strbuf_grow(sb, linelen + indent + 20);
 		if (indent)
-			strbuf_addchars(sb, ' ', indent);
-		strbuf_add(sb, line, linelen);
+			pp_handle_indent(pp, sb, indent, line, linelen);
+		else
+			strbuf_add(sb, line, linelen);
 		strbuf_addch(sb, '\n');
 	}
 }