[PATCH 2/4] Do attempt pretty print in ASCII-incompatible encodings

["Nguyễn Thái Ngọc Duy" <pclouds@gmail.com>]

We rely on ASCII everywhere. We print "\n" directly without conversion
for example. The end result would be a mix of some encoding and ASCII
if they are incompatible. Do not do that.

In theory we could convert everything to utf-8 as intermediate medium,
process process process, then convert final output to the desired
encoding. But that's a lot of work (unless we have a pager-like
converter) with little real use. Users can just pipe everything to
iconv instead.

Signed-off-by: Nguyễn Thái Ngọc Duy <pclouds@gmail.com>
---
 It seems half of the encodings "iconv -l" list does not pass
 ascii_superset_encoding() test. I just assume they are either exotic
 or duplicate names.

 pretty.c |    7 +++++++
 utf8.c   |   15 +++++++++++++++
 utf8.h   |    1 +
 3 files changed, 23 insertions(+), 0 deletions(-)

diff --git a/pretty.c b/pretty.c
index 8688b8f..5c433a2 100644
--- a/pretty.c
+++ b/pretty.c
@@ -493,12 +493,19 @@ char *logmsg_reencode(const struct commit *commit,
 		      const char *output_encoding)
 {
 	static const char *utf8 = "UTF-8";
+	static const char *last_output_encoding = NULL;
 	const char *use_encoding;
 	char *encoding;
 	char *out;
 
 	if (!*output_encoding)
 		return NULL;
+	if (last_output_encoding != output_encoding) {
+		if (!ascii_superset_encoding(output_encoding))
+			die("encoding %s is not a superset of ASCII.",
+			    output_encoding);
+		last_output_encoding = output_encoding;
+	}
 	encoding = get_header(commit, "encoding");
 	use_encoding = encoding ? encoding : utf8;
 	if (!strcmp(use_encoding, output_encoding))
diff --git a/utf8.c b/utf8.c
index 8acbc66..def93ee 100644
--- a/utf8.c
+++ b/utf8.c
@@ -482,3 +482,18 @@ char *reencode_string(const char *in, const char *out_encoding, const char *in_e
 	return out;
 }
 #endif
+
+int ascii_superset_encoding(const char *encoding)
+{
+	const char *sample = " !\"#$%&'()*+,-./0123456789:;<=>?@"
+		"ABCDEFGHIJKLMNOPQRSTUVWXYZ[\\]^_`"
+		"abcdefghijklmnopqrstuvwxyz{|}~\n";
+	char *output;
+	int ret;
+	if (!encoding)
+		return 1;
+	output = reencode_string(sample, encoding, "US-ASCII");
+	ret = !output || !strcmp(sample, output);
+	free(output);
+	return ret;
+}
diff --git a/utf8.h b/utf8.h
index 81f2c82..75bc128 100644
--- a/utf8.h
+++ b/utf8.h
@@ -12,6 +12,7 @@ int strbuf_add_wrapped_text(struct strbuf *buf,
 		const char *text, int indent, int indent2, int width);
 int strbuf_add_wrapped_bytes(struct strbuf *buf, const char *data, int len,
 			     int indent, int indent2, int width);
+int ascii_superset_encoding(const char *encoding);
 
 #ifndef NO_ICONV
 char *reencode_string(const char *in, const char *out_encoding, const char *in_encoding);
-- 
1.7.8.36.g69ee2