Some comments inline
On Fri, Mar 09, 2018 at 06:35:32PM +0100, lars.schneider@xxxxxxxxxxxx wrote:
> From: Lars Schneider <larsxschneider@xxxxxxxxx>
>
> Git recognizes files encoded with ASCII or one of its supersets (e.g.
> UTF-8 or ISO-8859-1) as text files. All other encodings are usually
> interpreted as binary and consequently built-in Git text processing
> tools (e.g. 'git diff') as well as most Git web front ends do not
> visualize the content.
>
> Add an attribute to tell Git what encoding the user has defined for a
> given file. If the content is added to the index, then Git converts the
Minor comment:
"Git converts the content"
Everywhere else (?) "encodes or reencodes" is used.
"Git reencodes the content" may be more consistent.
[No comments on the .gitattributes]
>
> diff --git a/convert.c b/convert.c
> index b976eb968c..aa59ecfe49 100644
> --- a/convert.c
> +++ b/convert.c
> @@ -7,6 +7,7 @@
> #include "sigchain.h"
> #include "pkt-line.h"
> #include "sub-process.h"
> +#include "utf8.h"
>
> /*
> * convert.c - convert a file when checking it out and checking it in.
> @@ -265,6 +266,78 @@ static int will_convert_lf_to_crlf(size_t len, struct text_stat *stats,
>
> }
>
> +static const char *default_encoding = "UTF-8";
> +
> +static int encode_to_git(const char *path, const char *src, size_t src_len,
> + struct strbuf *buf, const char *enc, int conv_flags)
> +{
> + char *dst;
> + int dst_len;
> + int die_on_error = conv_flags & CONV_WRITE_OBJECT;
> +
> + /*
> + * No encoding is specified or there is nothing to encode.
> + * Tell the caller that the content was not modified.
> + */
> + if (!enc || (src && !src_len))
> + return 0;
(This may have been discussed before.
As we checked (enc != NULL) I think we can add here:)
if (is_encoding_utf8(enc))
return 0;
> +
> + /*
> + * Looks like we got called from "would_convert_to_git()".
> + * This means Git wants to know if it would encode (= modify!)
> + * the content. Let's answer with "yes", since an encoding was
> + * specified.
> + */
> + if (!buf && !src)
> + return 1;
> +
> + dst = reencode_string_len(src, src_len, default_encoding, enc,
> + &dst_len);
> + if (!dst) {
> + /*
> + * We could add the blob "as-is" to Git. However, on checkout
> + * we would try to reencode to the original encoding. This
> + * would fail and we would leave the user with a messed-up
> + * working tree. Let's try to avoid this by screaming loud.
> + */
> + const char* msg = _("failed to encode '%s' from %s to %s");
> + if (die_on_error)
> + die(msg, path, enc, default_encoding);
> + else {
> + error(msg, path, enc, default_encoding);
> + return 0;
> + }
> + }
> +
> + strbuf_attach(buf, dst, dst_len, dst_len + 1);
> + return 1;
> +}
> +
> +static int encode_to_worktree(const char *path, const char *src, size_t src_len,
> + struct strbuf *buf, const char *enc)
> +{
> + char *dst;
> + int dst_len;
> +
> + /*
> + * No encoding is specified or there is nothing to encode.
> + * Tell the caller that the content was not modified.
> + */
> + if (!enc || (src && !src_len))
> + return 0;
Same as above:
if (is_encoding_utf8(enc))
return 0;
> +
> + dst = reencode_string_len(src, src_len, enc, default_encoding,
> + &dst_len);
> + if (!dst) {
> + error("failed to encode '%s' from %s to %s",
> + path, default_encoding, enc);
> + return 0;
> + }
> +
> + strbuf_attach(buf, dst, dst_len, dst_len + 1);
> + return 1;
> +}
> +
> static int crlf_to_git(const struct index_state *istate,
> const char *path, const char *src, size_t len,
> struct strbuf *buf,
> @@ -978,6 +1051,25 @@ static int ident_to_worktree(const char *path, const char *src, size_t len,
> return 1;
> }
>
> +static const char *git_path_check_encoding(struct attr_check_item *check)
> +{
> + const char *value = check->value;
> +
> + if (ATTR_UNSET(value) || !strlen(value))
> + return NULL;
> +
> + if (ATTR_TRUE(value) || ATTR_FALSE(value)) {
> + error(_("working-tree-encoding attribute requires a value"));
> + return NULL;
> + }
TRUE or false are values, but just wrong ones.
If this test is removed, the user will see "failed to encode "TRUE" to "UTF-8",
which should give enough information to fix it.
> +
> + /* Don't encode to the default encoding */
> + if (!strcasecmp(value, default_encoding))
> + return NULL;
Same as above ?:
if (is_encoding_utf8(value))
return 0;
