char *logmsg_reencode(const struct commit *commit,
const char *output_encoding)
{
static const char *utf8 = "UTF-8";
const char *use_encoding;
char *encoding;
char *out;
if (!output_encoding || !*output_encoding)
return NULL;
encoding = get_header(commit, "encoding");
use_encoding = encoding ? encoding : utf8;
if (same_encoding(use_encoding, output_encoding))
if (encoding) /* we'll strip encoding header later */
out = xstrdup(commit->buffer);
else
return NULL; /* nothing to do */
else
out = reencode_string(commit->buffer,
output_encoding, use_encoding);
if (out)
out = replace_encoding_header(out, output_encoding);
free(encoding);
return out;
}
void format_commit_message(const struct commit *commit,
const char *format, struct strbuf *sb,
const struct pretty_print_context *pretty_ctx)
{
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;
/*
* convert a commit message to UTF-8 first
* as far as 'format_commit_item' assumes it in UTF-8
*/
context.message = logmsg_reencode(commit,
&context.commit_encoding,
utf8);
strbuf_expand(sb, format, format_commit_item, &context);
rewrap_message_tail(sb, &context, 0, 0, 0);
/* then convert a commit message to an actual output encoding */
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);
unuse_commit_buffer(commit, context.message);
free(context.signature_check.gpg_output);
free(context.signature_check.signer);
}
int strbuf_reencode(struct strbuf *sb, const char *from, const char *to)
{
char *out;
int len;
if (same_encoding(from, to))
return 0;
out = reencode_string_len(sb->buf, sb->len, to, from, &len);
if (!out)
return -1;
strbuf_attach(sb, out, len, len);
return 0;
}
static int convert_to_utf8(struct mailinfo *mi,
struct strbuf *line, const char *charset)
{
char *out;
if (!mi->metainfo_charset || !charset || !*charset)
return 0;
if (same_encoding(mi->metainfo_charset, charset))
return 0;
out = reencode_string(line->buf, mi->metainfo_charset, charset);
if (!out) {
mi->input_error = -1;
return error("cannot convert from %s to %s",
charset, mi->metainfo_charset);
}
strbuf_attach(line, out, strlen(out), strlen(out));
return 0;
}
static int get_message(struct commit *commit, struct commit_message *out)
{
const char *encoding;
const char *abbrev, *subject;
int abbrev_len, subject_len;
char *q;
if (!commit->buffer)
return -1;
encoding = get_encoding(commit->buffer);
if (!encoding)
encoding = "UTF-8";
if (!git_commit_encoding)
git_commit_encoding = "UTF-8";
out->reencoded_message = NULL;
out->message = commit->buffer;
if (same_encoding(encoding, git_commit_encoding))
out->reencoded_message = reencode_string(commit->buffer,
git_commit_encoding, encoding);
if (out->reencoded_message)
out->message = out->reencoded_message;
abbrev = find_unique_abbrev(commit->object.sha1, DEFAULT_ABBREV);
abbrev_len = strlen(abbrev);
subject_len = find_commit_subject(out->message, &subject);
out->parent_label = xmalloc(strlen("parent of ") + abbrev_len +
strlen("... ") + subject_len + 1);
q = out->parent_label;
q = mempcpy(q, "parent of ", strlen("parent of "));
out->label = q;
q = mempcpy(q, abbrev, abbrev_len);
q = mempcpy(q, "... ", strlen("... "));
out->subject = q;
q = mempcpy(q, subject, subject_len);
*q = '\0';
return 0;
}
const char *logmsg_reencode(const struct commit *commit,
char **commit_encoding,
const char *output_encoding)
{
static const char *utf8 = "UTF-8";
const char *use_encoding;
char *encoding;
const char *msg = get_commit_buffer(commit, NULL);
char *out;
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)) {
/*
* No encoding work to be done. If we have no encoding header
* at all, then there's nothing to do, and we can return the
* message verbatim (whether newly allocated or not).
*/
if (!encoding)
return msg;
/*
* Otherwise, we still want to munge the encoding header in the
* result, which will be done by modifying the buffer. If we
* are using a fresh copy, we can reuse it. But if we are using
* the cached copy from get_commit_buffer, we need to duplicate it
* to avoid munging the cached copy.
*/
if (msg == get_cached_commit_buffer(commit, NULL))
out = xstrdup(msg);
else
out = (char *)msg;
}
else {
/*
* There's actual encoding work to do. Do the reencoding, which
* still leaves the header to be replaced in the next step. At
* this point, we are done with msg. If we allocated a fresh
* copy, we can free it.
*/
out = reencode_string(msg, output_encoding, use_encoding);
if (out)
unuse_commit_buffer(commit, msg);
}
/*
* This replacement actually consumes the buffer we hand it, so we do
* not have to worry about freeing the old "out" here.
*/
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
* case we just return the commit message verbatim.
*/
return out ? out : msg;
}
