Re: [PATCH] Add ls-files --eol-staged, --eol-worktree

> Make it possible to show the line endings of files.
> Files which are staged and/or files in the working tree:
>
> git ls-files --eol-staged
> git ls-files --eol-worktree
>
> Both will show an output like this:
>
> empty    empty_file
> bin      binary_file_or_with_cr_handled_as_binary
> txt-crlf text_file_with_crlf
> txt-mix  text_file_with_crlf_and_lf
> txt-lf   text_file_with_lf
> txt      text_file_with_no_eol_at_all

>
> Implementation details:
> Make struct text_stat, is_binary() and gather_stats() from convert.c
> public, add a new function get_convert_stats_ascii() and use it
> in and use them in ls-files.
> git ls-files --eol-staged will give a line like this:
>
> Signed-off-by: Torsten Bögershausen <tboegi@web.de>
> ---
> This needs to go on top of tb/t0027-crlf
>
> builtin/ls-files.c | 21 +++++++++++++++++++++
> convert.c          | 51 
> +++++++++++++++++++++++++++++++++++++++++----------
> convert.h          | 14 ++++++++++++++
> 3 files changed, 76 insertions(+), 10 deletions(-)
>
> diff --git a/builtin/ls-files.c b/builtin/ls-files.c
> index b6a7cb0..c989e94 100644
> --- a/builtin/ls-files.c
> +++ b/builtin/ls-files.c
> @@ -27,6 +27,8 @@ static int show_killed;
> static int show_valid_bit;
> static int line_terminator = '\n';
> static int debug_mode;
> +static int show_eol_staged;
> +static int show_eol_wt;
>
> static const char *prefix;
> static int max_prefix_len;
> @@ -68,6 +70,11 @@ static void show_dir_entry(const char *tag, struct 
> dir_entry *ent)
> return;
>
> fputs(tag, stdout);
> + if (show_eol_wt) {
> + printf("%s ", get_convert_stats_ascii(ent->name,
> + GET_CONVERT_STATS_ASCII_WT, 0));
> + }
> +
> write_name(ent->name);
> }
>
> @@ -170,6 +177,14 @@ static void show_ce_entry(const char *tag, const 
> struct cache_entry *ce)
>        find_unique_abbrev(ce->sha1,abbrev),
>        ce_stage(ce));
> }
> + if (show_eol_staged) {
> + printf("%s ",
> + get_convert_stats_ascii(ce->name, GET_CONVERT_STATS_ASCII_BLOB, 0));
> + }
> + if (show_eol_wt) {
> + printf("%s ", 
> get_convert_stats_ascii(ce->name,GET_CONVERT_STATS_ASCII_WT,
> + ce->ce_stat_data.sd_size));
> + }
> write_name(ce->name);
> if (debug_mode) {
> const struct stat_data *sd = &ce->ce_stat_data;
> @@ -206,6 +221,10 @@ static void show_ru_info(void)
> printf("%s%06o %s %d\t", tag_resolve_undo, ui->mode[i],
>        find_unique_abbrev(ui->sha1[i], abbrev),
>        i + 1);
> + if (show_eol_wt) {
> + printf("%s ",
> + get_convert_stats_ascii(path, GET_CONVERT_STATS_ASCII_WT, 0));
> + }
> write_name(path);
> }
> }
> @@ -433,6 +452,8 @@ int cmd_ls_files(int argc, const char **argv, const 
> char *cmd_prefix)
> OPT_BIT(0, "directory", &dir.flags,
> N_("show 'other' directories' names only"),
> DIR_SHOW_OTHER_DIRECTORIES),
> + OPT_BOOL(0, "eol-staged", &show_eol_staged, N_("show line endings of the 
> staged file")),
> + OPT_BOOL(0, "eol-worktree", &show_eol_wt, N_("show line endings of the 
> file in work tree")),
> OPT_NEGBIT(0, "empty-directory", &dir.flags,
> N_("don't show empty directories"),
> DIR_HIDE_EMPTY_DIRECTORIES),
> diff --git a/convert.c b/convert.c
> index 814e814..a1c24cd 100644
> --- a/convert.c
> +++ b/convert.c
> @@ -22,15 +22,7 @@ enum crlf_action {
> CRLF_AUTO
> };
>
> -struct text_stat {
> - /* NUL, CR, LF and CRLF counts */
> - unsigned nul, cr, lf, crlf;
> -
> - /* These are just approximations! */
> - unsigned printable, nonprintable;
> -};
> -
> -static void gather_stats(const char *buf, unsigned long size, struct 
> text_stat *stats)
> +void gather_stats(const char *buf, unsigned long size, struct text_stat 
> *stats)
> {
> unsigned long i;
>
> @@ -76,7 +68,7 @@ static void gather_stats(const char *buf, unsigned long 
> size, struct text_stat *
> /*
> * The same heuristics as diff.c::mmfile_is_binary()
> */
> -static int is_binary(unsigned long size, struct text_stat *stats)
> +int is_binary(unsigned long size, struct text_stat *stats)
> {
>
> if (stats->nul)
> @@ -95,6 +87,45 @@ static int is_binary(unsigned long size, struct 
> text_stat *stats)
> return 0;
> }
>
> +
> +const char *gather_stats_ascii(const char *data, unsigned long size)
> +{
> + struct text_stat stats;
> + if (!data || !size)
> + return("empty   ");
> + gather_stats(data, size, &stats);
> + if (is_binary(size, &stats))
> + return("bin     ");
> + else if (stats.cr != stats.crlf)
> + return("bin     ");
> + else if (stats.crlf && (stats.crlf == stats.lf))
> + return("txt-crlf");
> + else if (stats.crlf && stats.lf)
> + return("txt-mix ");
> + else if (stats.lf)
> + return("txt-lf  ");
> + else
> + return("txt     ");
> +}
> +
> +const char *get_convert_stats_ascii(const char *path, int flags, size_t 
> hint)
> +{
> + const char *ret = "";
> + if (flags & GET_CONVERT_STATS_ASCII_BLOB) {
> + unsigned long sz;
> + void *data = read_blob_data_from_cache(path, &sz);
> + ret = gather_stats_ascii(data, sz);
> + if (data)
> + free(data);
> + } else if (flags & GET_CONVERT_STATS_ASCII_WT){
> + struct strbuf sb = STRBUF_INIT;
> + strbuf_read_file(&sb, path, hint);
> + ret = gather_stats_ascii(sb.buf, sb.len);
> + strbuf_release(&sb);
> + }
> + return ret;
> +}
> +
> static enum eol output_eol(enum crlf_action crlf_action)
> {
> switch (crlf_action) {
> diff --git a/convert.h b/convert.h
> index d9d853c..566cf0e 100644
> --- a/convert.h
> +++ b/convert.h
> @@ -31,6 +31,20 @@ enum eol {
> #endif
> };
>
> +struct text_stat {
> + /* NUL, CR, LF and CRLF counts */
> + unsigned nul, cr, lf, crlf;
> +
> + /* These are just approximations! */
> + unsigned printable, nonprintable;
> +};
> +void gather_stats(const char *buf, unsigned long size, struct text_stat 
> *stats);
> +int is_binary(unsigned long size, struct text_stat *stats);
> +const char *gather_stats_ascii(const char *buf, unsigned long size);
> +#define GET_CONVERT_STATS_ASCII_BLOB           (1<<0)
> +#define GET_CONVERT_STATS_ASCII_WT             (1<<1)
> +const char *get_convert_stats_ascii(const char *path, int isBlob, size_t 
> hint);
> +
> extern enum eol core_eol;
>
> /* returns 1 if *dst was used */
> -- 
> 2.6.1.443.g36d7748
>
> --