From 0e18bcd5e937b9e5857892e7f5c80c3c5b1da5d4 Mon Sep 17 00:00:00 2001
From: Junio C Hamano <gitster@pobox.com>
Date: Thu, 18 Oct 2012 22:41:56 -0700
Subject: [PATCH] reencode_string(): introduce and use same_encoding()
Callers of reencode_string() that re-encodes a string from one
encoding to another all used ad-hoc way to bypass the case where the
input and the output encodings are the same. Some did strcmp(),
some did strcasecmp(), yet some others when converting to UTF-8 used
is_encoding_utf8().
Introduce same_encoding() helper function to make these callers use
the same logic. Notably, is_encoding_utf8() has a work-around for
common misconfiguration to use "utf8" to name UTF-8 encoding, which
does not match "UTF-8" hence strcasecmp() would not consider the
same. Make use of it in this helper function.
Signed-off-by: Junio C Hamano <gitster@pobox.com>
---
builtin/mailinfo.c | 2 +-
notes.c | 2 +-
pretty.c | 2 +-
sequencer.c | 2 +-
utf8.c | 7 +++++++
utf8.h | 1 +
6 files changed, 12 insertions(+), 4 deletions(-)
diff --git a/builtin/mailinfo.c b/builtin/mailinfo.c
index fe128572f7..90b158d4f5 100644
--- a/builtin/mailinfo.c
+++ b/builtin/mailinfo.c
@@ -507,7 +507,7 @@ static void convert_to_utf8(struct strbuf *line, const char *charset)
return;
}
- if (!strcasecmp(metainfo_charset, charset))
+ if (same_encoding(metainfo_charset, charset))
return;
out = reencode_string(line->buf, metainfo_charset, charset);
if (!out)
diff --git a/notes.c b/notes.c
index 93e9868d5d..e48f6604d8 100644
--- a/notes.c
+++ b/notes.c
@@ -1221,7 +1221,7 @@ void format_note(struct notes_tree *t, const unsigned char *object_sha1,
}
if (output_encoding && *output_encoding &&
- strcmp(utf8, output_encoding)) {
+ !is_encoding_utf8(output_encoding)) {
char *reencoded = reencode_string(msg, output_encoding, utf8);
if (reencoded) {
free(msg);
diff --git a/pretty.c b/pretty.c
index 8b1ea9ffad..e87fe9fec3 100644
--- a/pretty.c
+++ b/pretty.c
@@ -504,7 +504,7 @@ char *logmsg_reencode(const struct commit *commit,
return NULL;
encoding = get_header(commit, "encoding");
use_encoding = encoding ? encoding : utf8;
- if (!strcmp(use_encoding, output_encoding))
+ if (same_encoding(use_encoding, output_encoding))
if (encoding) /* we'll strip encoding header later */
out = xstrdup(commit->buffer);
else
diff --git a/sequencer.c b/sequencer.c
index bd626806d6..f2f5b137ea 100644
--- a/sequencer.c
+++ b/sequencer.c
@@ -58,7 +58,7 @@ static int get_message(struct commit *commit, struct commit_message *out)
out->reencoded_message = NULL;
out->message = commit->buffer;
- if (strcmp(encoding, git_commit_encoding))
+ if (same_encoding(encoding, git_commit_encoding))
out->reencoded_message = reencode_string(commit->buffer,
git_commit_encoding, encoding);
if (out->reencoded_message)
diff --git a/utf8.c b/utf8.c
index a544f15456..6a52834576 100644
--- a/utf8.c
+++ b/utf8.c
@@ -423,6 +423,13 @@ int is_encoding_utf8(const char *name)
return 0;
}
+int same_encoding(const char *src, const char *dst)
+{
+ if (is_encoding_utf8(src) && is_encoding_utf8(dst))
+ return 1;
+ return !strcasecmp(src, dst);
+}
+
/*
* Given a buffer and its encoding, return it re-encoded
* with iconv. If the conversion fails, returns NULL.
diff --git a/utf8.h b/utf8.h
index 3c0ae7624e..93ef60042c 100644
--- a/utf8.h
+++ b/utf8.h
@@ -7,6 +7,7 @@ int utf8_width(const char **start, size_t *remainder_p);
int utf8_strwidth(const char *string);
int is_utf8(const char *text);
int is_encoding_utf8(const char *name);
+int same_encoding(const char *, const char *);
int strbuf_add_wrapped_text(struct strbuf *buf,
const char *text, int indent, int indent2, int width);
--
2.48.1