From 0a799424f682071da9f5b632d1394308e9255bb5 Mon Sep 17 00:00:00 2001 From: Julius Plenz Date: Thu, 10 Mar 2011 17:03:23 +0100 Subject: fix two encoding bugs reencode() takes three arguments in the order (txt, from, to), opposed to reencode_string, which will, like iconv, handle the arguments with from and to swapped. Fix that (this makes reencode more intuitive). If src and dst encoding are equivalent, don't do any encoding. If no special encoding parameter is found within the commit, assume UTF-8 and explicitly convert to PAGE_ENCODING. The change to reencode() mentioned above avoids re-encoding a UTF-8 string to UTF-8, for example. Signed-off-by: Julius Plenz Signed-off-by: Lars Hjemli --- parsing.c | 24 +++++++++++++++--------- 1 file changed, 15 insertions(+), 9 deletions(-) diff --git a/parsing.c b/parsing.c index f37c49d..c9e4350 100644 --- a/parsing.c +++ b/parsing.c @@ -106,7 +106,11 @@ const char *reencode(char **txt, const char *src_enc, const char *dst_enc) if (!txt || !*txt || !src_enc || !dst_enc) return *txt; - tmp = reencode_string(*txt, src_enc, dst_enc); + /* no encoding needed if src_enc equals dst_enc */ + if(!strcasecmp(src_enc, dst_enc)) + return *txt; + + tmp = reencode_string(*txt, dst_enc, src_enc); if (tmp) { free(*txt); *txt = tmp; @@ -160,6 +164,10 @@ struct commitinfo *cgit_parse_commit(struct commit *commit) } } + /* if no special encoding is found, assume UTF-8 */ + if(!ret->msg_encoding) + ret->msg_encoding = xstrdup("UTF-8"); + // skip unknown header fields while (p && *p && (*p != '\n')) { p = strchr(p, '\n'); @@ -189,14 +197,12 @@ struct commitinfo *cgit_parse_commit(struct commit *commit) } else ret->subject = xstrdup(p); - if (ret->msg_encoding) { - reencode(&ret->author, PAGE_ENCODING, ret->msg_encoding); - reencode(&ret->author_email, PAGE_ENCODING, ret->msg_encoding); - reencode(&ret->committer, PAGE_ENCODING, ret->msg_encoding); - reencode(&ret->committer_email, PAGE_ENCODING, ret->msg_encoding); - reencode(&ret->subject, PAGE_ENCODING, ret->msg_encoding); - reencode(&ret->msg, PAGE_ENCODING, ret->msg_encoding); - } + reencode(&ret->author, ret->msg_encoding, PAGE_ENCODING); + reencode(&ret->author_email, ret->msg_encoding, PAGE_ENCODING); + reencode(&ret->committer, ret->msg_encoding, PAGE_ENCODING); + reencode(&ret->committer_email, ret->msg_encoding, PAGE_ENCODING); + reencode(&ret->subject, ret->msg_encoding, PAGE_ENCODING); + reencode(&ret->msg, ret->msg_encoding, PAGE_ENCODING); return ret; } -- cgit v1.2.3-57-g22cb