#include "cache.h"
#include "attr.h"
#include "run-command.h"
#include "quote.h"
#include "sigchain.h"
/*
* convert.c - convert a file when checking it out and checking it in.
*
* This should use the pathname to decide on whether it wants to do some
* more interesting conversions (automatic gzip/unzip, general format
* conversions etc etc), but by default it just does automatic CRLF<->LF
* translation when the "text" attribute or "auto_crlf" option is set.
*/
enum crlf_action {
CRLF_GUESS = -1,
CRLF_BINARY = 0,
CRLF_TEXT,
CRLF_INPUT,
CRLF_CRLF,
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)
{
unsigned long i;
memset(stats, 0, sizeof(*stats));
for (i = 0; i < size; i++) {
unsigned char c = buf[i];
if (c == '\r') {
stats->cr++;
if (i+1 < size && buf[i+1] == '\n')
stats->crlf++;
continue;
}
if (c == '\n') {
stats->lf++;
continue;
}
if (c == 127)
/* DEL */
stats->nonprintable++;
else if (c < 32) {
switch (c) {
/* BS, HT, ESC and FF */
case '\b': case '\t': case '\033': case '\014':
stats->printable++;
break;
case 0:
stats->nul++;
/* fall through */
default:
stats->nonprintable++;
}
}
else
stats->printable++;
}
/* If file ends with EOF then don't count this EOF as non-printable. */
if (size >= 1 && buf[size-1] == '\032')
stats->nonprintable--;
}
/*
* The same heuristics as diff.c::mmfile_is_binary()
*/
static int is_binary(unsigned long size, struct text_stat *stats)
{
if (stats->nul)
return 1;
if ((stats->printable >> 7) < stats->nonprintable)
return 1;
/*
* Other heuristics? Average line length might be relevant,
* as might LF vs CR vs CRLF counts..
*
* NOTE! It might be normal to have a low ratio of CRLF to LF
* (somebody starts with a LF-only file and edits it with an editor
* that adds CRLF only to lines that are added..). But do we
* want to support CR-only? Probably not.
*/
return 0;
}
static enum eol output_eol(enum crlf_action crlf_action)
{
switch (crlf_action) {
case CRLF_BINARY:
return EOL_UNSET;
case CRLF_CRLF:
return EOL_CRLF;
case CRLF_INPUT:
return EOL_LF;
case CRLF_GUESS:
if (!auto_crlf)
return EOL_UNSET;
/* fall through */
case CRLF_TEXT:
case CRLF_AUTO:
if (auto_crlf == AUTO_CRLF_TRUE)
return EOL_CRLF;
else if (auto_crlf == AUTO_CRLF_INPUT)
return EOL_LF;
else if (core_eol == EOL_UNSET)
return EOL_NATIVE;
}
return core_eol;
}
static void check_safe_crlf(const char *path, enum crlf_action crlf_action,
struct text_stat *stats, enum safe_crlf checksafe)
{
if (!checksafe)
return;
if (output_eol(crlf_action) == EOL_LF) {
/*
* CRLFs would not be restored by checkout:
|