Fixed bug that caused icy header metadata to be not correctly
encoded/converted. Characters above x7F were replaced by '?' character although the rfc defines a ISO−8859−1 encoding for descriptive field-content. According to rfc2616 the field-content is defined as follows: <the OCTETs making up the field-value and consisting of either *TEXT or combinations of token, separators, and quoted-string> The TEXT rule is only used for descriptive field contents and values that are not intended to be interpreted by the message parser. Words of *TEXT MAY contain characters from character sets other than ISO- 8859-1 only when encoded according to the rules of RFC 2047. In the previous implementation the icy metadata was converted based on fromcode "ascii". Following incoming icy header field-values should be encoded as "ISO−8859−1" before adding them to the metadata structure. - misc.c unicode_fixup_string enhanced by an additional parameter to define the fromcode - misc.h unicode_fixup_string prototype updated - filescanner.c function fixup_tags updated to stay compatible to the previous implementation using fromcode "ascii" - db.c function unicode_fixup_mfi updated to stay compatible to the previous implementation using fromcode "ascii" - http.c function metadata_header_get enhanced to encode the header field-content as "ISO−8859−1" to comply with rfc2616
This commit is contained in:
parent
70fea7e459
commit
32727bd296
2
src/db.c
2
src/db.c
|
@ -465,7 +465,7 @@ unicode_fixup_mfi(struct media_file_info *mfi)
|
|||
if (!*field)
|
||||
continue;
|
||||
|
||||
ret = unicode_fixup_string(*field);
|
||||
ret = unicode_fixup_string(*field,"ascii");
|
||||
if (ret != *field)
|
||||
{
|
||||
free(*field);
|
||||
|
|
|
@ -588,7 +588,7 @@ fixup_tags(struct media_file_info *mfi)
|
|||
/* fname is left untouched by unicode_fixup_mfi() for
|
||||
* obvious reasons, so ensure it is proper UTF-8
|
||||
*/
|
||||
mfi->title = unicode_fixup_string(mfi->fname);
|
||||
mfi->title = unicode_fixup_string(mfi->fname,"ascii");
|
||||
if (mfi->title == mfi->fname)
|
||||
mfi->title = strdup(mfi->fname);
|
||||
}
|
||||
|
|
22
src/http.c
22
src/http.c
|
@ -408,6 +408,7 @@ metadata_header_get(struct http_icy_metadata *metadata, AVFormatContext *fmtctx)
|
|||
uint8_t *buffer;
|
||||
char *icy_token;
|
||||
char *ptr;
|
||||
const char *headerenc = "ISO−8859−1";
|
||||
|
||||
av_opt_get(fmtctx, "icy_metadata_headers", AV_OPT_SEARCH_CHILDREN, &buffer);
|
||||
if (!buffer)
|
||||
|
@ -427,12 +428,27 @@ metadata_header_get(struct http_icy_metadata *metadata, AVFormatContext *fmtctx)
|
|||
if (ptr[0] == ' ')
|
||||
ptr++;
|
||||
|
||||
|
||||
/*
|
||||
Reference:
|
||||
http://www.w3.org/Protocols/rfc2616/rfc2616-sec4.html#sec4.2
|
||||
http://www.w3.org/Protocols/rfc2616/rfc2616-sec2.html#sec2.2
|
||||
|
||||
Based on rfc2616 the field-content is defined as follows: <the OCTETs making up the field-value
|
||||
and consisting of either *TEXT or combinations of token, separators, and quoted-string>
|
||||
The TEXT rule is only used for descriptive field contents and values that are not intended to be interpreted
|
||||
by the message parser. Words of *TEXT MAY contain characters from character sets other than ISO- 8859-1
|
||||
only when encoded according to the rules of RFC 2047.
|
||||
|
||||
Incoming icy header field-values should be encoded as "ISO−8859−1" before adding them to the metadata structure.
|
||||
*/
|
||||
|
||||
if ((strncmp(icy_token, "icy-name", strlen("icy-name")) == 0) && !metadata->name)
|
||||
metadata->name = strdup(ptr);
|
||||
metadata->name = strdup(unicode_fixup_string(ptr,headerenc));
|
||||
else if ((strncmp(icy_token, "icy-description", strlen("icy-description")) == 0) && !metadata->description)
|
||||
metadata->description = strdup(ptr);
|
||||
metadata->description = strdup(unicode_fixup_string(ptr,headerenc));
|
||||
else if ((strncmp(icy_token, "icy-genre", strlen("icy-genre")) == 0) && !metadata->genre)
|
||||
metadata->genre = strdup(ptr);
|
||||
metadata->genre = strdup(unicode_fixup_string(ptr,headerenc));
|
||||
|
||||
icy_token = strtok(NULL, "\r\n");
|
||||
}
|
||||
|
|
|
@ -486,8 +486,9 @@ m_realpath(const char *pathname)
|
|||
return ret;
|
||||
}
|
||||
|
||||
|
||||
char *
|
||||
unicode_fixup_string(char *str)
|
||||
unicode_fixup_string(char *str, const char *fromcode)
|
||||
{
|
||||
uint8_t *ret;
|
||||
size_t len;
|
||||
|
@ -510,7 +511,7 @@ unicode_fixup_string(char *str)
|
|||
return str;
|
||||
}
|
||||
|
||||
ret = u8_conv_from_encoding("ascii", iconveh_question_mark, str, len, NULL, NULL, &len);
|
||||
ret = u8_conv_from_encoding(fromcode, iconveh_question_mark, str, len, NULL, NULL, &len);
|
||||
if (!ret)
|
||||
{
|
||||
DPRINTF(E_LOG, L_MISC, "Could not convert string '%s' to UTF-8: %s\n", str, strerror(errno));
|
||||
|
|
|
@ -65,7 +65,7 @@ char *
|
|||
m_realpath(const char *pathname);
|
||||
|
||||
char *
|
||||
unicode_fixup_string(char *str);
|
||||
unicode_fixup_string(char *str, const char *fromcode);
|
||||
|
||||
char *
|
||||
trimwhitespace(const char *str);
|
||||
|
|
Loading…
Reference in New Issue