git/parse-options.c
Torsten Bögershausen 76759c7dff git on Mac OS and precomposed unicode
Mac OS X mangles file names containing unicode on file systems HFS+,
VFAT or SAMBA.  When a file using unicode code points outside ASCII
is created on a HFS+ drive, the file name is converted into
decomposed unicode and written to disk. No conversion is done if
the file name is already decomposed unicode.

Calling open("\xc3\x84", ...) with a precomposed "Ä" yields the same
result as open("\x41\xcc\x88",...) with a decomposed "Ä".

As a consequence, readdir() returns the file names in decomposed
unicode, even if the user expects precomposed unicode.  Unlike on
HFS+, Mac OS X stores files on a VFAT drive (e.g. an USB drive) in
precomposed unicode, but readdir() still returns file names in
decomposed unicode.  When a git repository is stored on a network
share using SAMBA, file names are send over the wire and written to
disk on the remote system in precomposed unicode, but Mac OS X
readdir() returns decomposed unicode to be compatible with its
behaviour on HFS+ and VFAT.

The unicode decomposition causes many problems:

- The names "git add" and other commands get from the end user may
  often be precomposed form (the decomposed form is not easily input
  from the keyboard), but when the commands read from the filesystem
  to see what it is going to update the index with already is on the
  filesystem, readdir() will give decomposed form, which is different.

- Similarly "git log", "git mv" and all other commands that need to
  compare pathnames found on the command line (often but not always
  precomposed form; a command line input resulting from globbing may
  be in decomposed) with pathnames found in the tree objects (should
  be precomposed form to be compatible with other systems and for
  consistency in general).

- The same for names stored in the index, which should be
  precomposed, that may need to be compared with the names read from
  readdir().

NFS mounted from Linux is fully transparent and does not suffer from
the above.

As Mac OS X treats precomposed and decomposed file names as equal,
we can

 - wrap readdir() on Mac OS X to return the precomposed form, and

 - normalize decomposed form given from the command line also to the
   precomposed form,

to ensure that all pathnames used in Git are always in the
precomposed form.  This behaviour can be requested by setting
"core.precomposedunicode" configuration variable to true.

The code in compat/precomposed_utf8.c implements basically 4 new
functions: precomposed_utf8_opendir(), precomposed_utf8_readdir(),
precomposed_utf8_closedir() and precompose_argv().  The first three
are to wrap opendir(3), readdir(3), and closedir(3) functions.

The argv[] conversion allows to use the TAB filename completion done
by the shell on command line.  It tolerates other tools which use
readdir() to feed decomposed file names into git.

When creating a new git repository with "git init" or "git clone",
"core.precomposedunicode" will be set "false".

The user needs to activate this feature manually.  She typically
sets core.precomposedunicode to "true" on HFS and VFAT, or file
systems mounted via SAMBA.

Helped-by: Junio C Hamano <gitster@pobox.com>
Signed-off-by: Torsten Bögershausen <tboegi@web.de>
Signed-off-by: Junio C Hamano <gitster@pobox.com>
2012-07-08 22:03:46 -07:00

597 lines
15 KiB
C

#include "git-compat-util.h"
#include "parse-options.h"
#include "cache.h"
#include "commit.h"
#include "color.h"
static int parse_options_usage(struct parse_opt_ctx_t *ctx,
const char * const *usagestr,
const struct option *opts, int err);
#define OPT_SHORT 1
#define OPT_UNSET 2
int optbug(const struct option *opt, const char *reason)
{
if (opt->long_name)
return error("BUG: option '%s' %s", opt->long_name, reason);
return error("BUG: switch '%c' %s", opt->short_name, reason);
}
int opterror(const struct option *opt, const char *reason, int flags)
{
if (flags & OPT_SHORT)
return error("switch `%c' %s", opt->short_name, reason);
if (flags & OPT_UNSET)
return error("option `no-%s' %s", opt->long_name, reason);
return error("option `%s' %s", opt->long_name, reason);
}
static int get_arg(struct parse_opt_ctx_t *p, const struct option *opt,
int flags, const char **arg)
{
if (p->opt) {
*arg = p->opt;
p->opt = NULL;
} else if (p->argc == 1 && (opt->flags & PARSE_OPT_LASTARG_DEFAULT)) {
*arg = (const char *)opt->defval;
} else if (p->argc > 1) {
p->argc--;
*arg = *++p->argv;
} else
return opterror(opt, "requires a value", flags);
return 0;
}
static void fix_filename(const char *prefix, const char **file)
{
if (!file || !*file || !prefix || is_absolute_path(*file)
|| !strcmp("-", *file))
return;
*file = xstrdup(prefix_filename(prefix, strlen(prefix), *file));
}
static int get_value(struct parse_opt_ctx_t *p,
const struct option *opt, int flags)
{
const char *s, *arg;
const int unset = flags & OPT_UNSET;
int err;
if (unset && p->opt)
return opterror(opt, "takes no value", flags);
if (unset && (opt->flags & PARSE_OPT_NONEG))
return opterror(opt, "isn't available", flags);
if (!(flags & OPT_SHORT) && p->opt && (opt->flags & PARSE_OPT_NOARG))
return opterror(opt, "takes no value", flags);
switch (opt->type) {
case OPTION_LOWLEVEL_CALLBACK:
return (*(parse_opt_ll_cb *)opt->callback)(p, opt, unset);
case OPTION_BIT:
if (unset)
*(int *)opt->value &= ~opt->defval;
else
*(int *)opt->value |= opt->defval;
return 0;
case OPTION_NEGBIT:
if (unset)
*(int *)opt->value |= opt->defval;
else
*(int *)opt->value &= ~opt->defval;
return 0;
case OPTION_COUNTUP:
*(int *)opt->value = unset ? 0 : *(int *)opt->value + 1;
return 0;
case OPTION_SET_INT:
*(int *)opt->value = unset ? 0 : opt->defval;
return 0;
case OPTION_SET_PTR:
*(void **)opt->value = unset ? NULL : (void *)opt->defval;
return 0;
case OPTION_STRING:
if (unset)
*(const char **)opt->value = NULL;
else if (opt->flags & PARSE_OPT_OPTARG && !p->opt)
*(const char **)opt->value = (const char *)opt->defval;
else
return get_arg(p, opt, flags, (const char **)opt->value);
return 0;
case OPTION_FILENAME:
err = 0;
if (unset)
*(const char **)opt->value = NULL;
else if (opt->flags & PARSE_OPT_OPTARG && !p->opt)
*(const char **)opt->value = (const char *)opt->defval;
else
err = get_arg(p, opt, flags, (const char **)opt->value);
if (!err)
fix_filename(p->prefix, (const char **)opt->value);
return err;
case OPTION_CALLBACK:
if (unset)
return (*opt->callback)(opt, NULL, 1) ? (-1) : 0;
if (opt->flags & PARSE_OPT_NOARG)
return (*opt->callback)(opt, NULL, 0) ? (-1) : 0;
if (opt->flags & PARSE_OPT_OPTARG && !p->opt)
return (*opt->callback)(opt, NULL, 0) ? (-1) : 0;
if (get_arg(p, opt, flags, &arg))
return -1;
return (*opt->callback)(opt, arg, 0) ? (-1) : 0;
case OPTION_INTEGER:
if (unset) {
*(int *)opt->value = 0;
return 0;
}
if (opt->flags & PARSE_OPT_OPTARG && !p->opt) {
*(int *)opt->value = opt->defval;
return 0;
}
if (get_arg(p, opt, flags, &arg))
return -1;
*(int *)opt->value = strtol(arg, (char **)&s, 10);
if (*s)
return opterror(opt, "expects a numerical value", flags);
return 0;
default:
die("should not happen, someone must be hit on the forehead");
}
}
static int parse_short_opt(struct parse_opt_ctx_t *p, const struct option *options)
{
const struct option *numopt = NULL;
for (; options->type != OPTION_END; options++) {
if (options->short_name == *p->opt) {
p->opt = p->opt[1] ? p->opt + 1 : NULL;
return get_value(p, options, OPT_SHORT);
}
/*
* Handle the numerical option later, explicit one-digit
* options take precedence over it.
*/
if (options->type == OPTION_NUMBER)
numopt = options;
}
if (numopt && isdigit(*p->opt)) {
size_t len = 1;
char *arg;
int rc;
while (isdigit(p->opt[len]))
len++;
arg = xmemdupz(p->opt, len);
p->opt = p->opt[len] ? p->opt + len : NULL;
rc = (*numopt->callback)(numopt, arg, 0) ? (-1) : 0;
free(arg);
return rc;
}
return -2;
}
static int parse_long_opt(struct parse_opt_ctx_t *p, const char *arg,
const struct option *options)
{
const char *arg_end = strchr(arg, '=');
const struct option *abbrev_option = NULL, *ambiguous_option = NULL;
int abbrev_flags = 0, ambiguous_flags = 0;
if (!arg_end)
arg_end = arg + strlen(arg);
for (; options->type != OPTION_END; options++) {
const char *rest, *long_name = options->long_name;
int flags = 0, opt_flags = 0;
if (!long_name)
continue;
again:
rest = skip_prefix(arg, long_name);
if (options->type == OPTION_ARGUMENT) {
if (!rest)
continue;
if (*rest == '=')
return opterror(options, "takes no value", flags);
if (*rest)
continue;
p->out[p->cpidx++] = arg - 2;
return 0;
}
if (!rest) {
/* abbreviated? */
if (!strncmp(long_name, arg, arg_end - arg)) {
is_abbreviated:
if (abbrev_option) {
/*
* If this is abbreviated, it is
* ambiguous. So when there is no
* exact match later, we need to
* error out.
*/
ambiguous_option = abbrev_option;
ambiguous_flags = abbrev_flags;
}
if (!(flags & OPT_UNSET) && *arg_end)
p->opt = arg_end + 1;
abbrev_option = options;
abbrev_flags = flags ^ opt_flags;
continue;
}
/* negation allowed? */
if (options->flags & PARSE_OPT_NONEG)
continue;
/* negated and abbreviated very much? */
if (!prefixcmp("no-", arg)) {
flags |= OPT_UNSET;
goto is_abbreviated;
}
/* negated? */
if (prefixcmp(arg, "no-")) {
if (!prefixcmp(long_name, "no-")) {
long_name += 3;
opt_flags |= OPT_UNSET;
goto again;
}
continue;
}
flags |= OPT_UNSET;
rest = skip_prefix(arg + 3, long_name);
/* abbreviated and negated? */
if (!rest && !prefixcmp(long_name, arg + 3))
goto is_abbreviated;
if (!rest)
continue;
}
if (*rest) {
if (*rest != '=')
continue;
p->opt = rest + 1;
}
return get_value(p, options, flags ^ opt_flags);
}
if (ambiguous_option)
return error("Ambiguous option: %s "
"(could be --%s%s or --%s%s)",
arg,
(ambiguous_flags & OPT_UNSET) ? "no-" : "",
ambiguous_option->long_name,
(abbrev_flags & OPT_UNSET) ? "no-" : "",
abbrev_option->long_name);
if (abbrev_option)
return get_value(p, abbrev_option, abbrev_flags);
return -2;
}
static int parse_nodash_opt(struct parse_opt_ctx_t *p, const char *arg,
const struct option *options)
{
for (; options->type != OPTION_END; options++) {
if (!(options->flags & PARSE_OPT_NODASH))
continue;
if (options->short_name == arg[0] && arg[1] == '\0')
return get_value(p, options, OPT_SHORT);
}
return -2;
}
static void check_typos(const char *arg, const struct option *options)
{
if (strlen(arg) < 3)
return;
if (!prefixcmp(arg, "no-")) {
error ("did you mean `--%s` (with two dashes ?)", arg);
exit(129);
}
for (; options->type != OPTION_END; options++) {
if (!options->long_name)
continue;
if (!prefixcmp(options->long_name, arg)) {
error ("did you mean `--%s` (with two dashes ?)", arg);
exit(129);
}
}
}
static void parse_options_check(const struct option *opts)
{
int err = 0;
for (; opts->type != OPTION_END; opts++) {
if ((opts->flags & PARSE_OPT_LASTARG_DEFAULT) &&
(opts->flags & PARSE_OPT_OPTARG))
err |= optbug(opts, "uses incompatible flags "
"LASTARG_DEFAULT and OPTARG");
if (opts->flags & PARSE_OPT_NODASH &&
((opts->flags & PARSE_OPT_OPTARG) ||
!(opts->flags & PARSE_OPT_NOARG) ||
!(opts->flags & PARSE_OPT_NONEG) ||
opts->long_name))
err |= optbug(opts, "uses feature "
"not supported for dashless options");
switch (opts->type) {
case OPTION_COUNTUP:
case OPTION_BIT:
case OPTION_NEGBIT:
case OPTION_SET_INT:
case OPTION_SET_PTR:
case OPTION_NUMBER:
if ((opts->flags & PARSE_OPT_OPTARG) ||
!(opts->flags & PARSE_OPT_NOARG))
err |= optbug(opts, "should not accept an argument");
default:
; /* ok. (usually accepts an argument) */
}
}
if (err)
exit(128);
}
void parse_options_start(struct parse_opt_ctx_t *ctx,
int argc, const char **argv, const char *prefix,
const struct option *options, int flags)
{
memset(ctx, 0, sizeof(*ctx));
ctx->argc = argc - 1;
ctx->argv = argv + 1;
ctx->out = argv;
ctx->prefix = prefix;
ctx->cpidx = ((flags & PARSE_OPT_KEEP_ARGV0) != 0);
ctx->flags = flags;
if ((flags & PARSE_OPT_KEEP_UNKNOWN) &&
(flags & PARSE_OPT_STOP_AT_NON_OPTION))
die("STOP_AT_NON_OPTION and KEEP_UNKNOWN don't go together");
parse_options_check(options);
}
static int usage_with_options_internal(struct parse_opt_ctx_t *,
const char * const *,
const struct option *, int, int);
int parse_options_step(struct parse_opt_ctx_t *ctx,
const struct option *options,
const char * const usagestr[])
{
int internal_help = !(ctx->flags & PARSE_OPT_NO_INTERNAL_HELP);
/* we must reset ->opt, unknown short option leave it dangling */
ctx->opt = NULL;
for (; ctx->argc; ctx->argc--, ctx->argv++) {
const char *arg = ctx->argv[0];
if (*arg != '-' || !arg[1]) {
if (parse_nodash_opt(ctx, arg, options) == 0)
continue;
if (ctx->flags & PARSE_OPT_STOP_AT_NON_OPTION)
return PARSE_OPT_NON_OPTION;
ctx->out[ctx->cpidx++] = ctx->argv[0];
continue;
}
if (arg[1] != '-') {
ctx->opt = arg + 1;
if (internal_help && *ctx->opt == 'h')
return parse_options_usage(ctx, usagestr, options, 0);
switch (parse_short_opt(ctx, options)) {
case -1:
return parse_options_usage(ctx, usagestr, options, 1);
case -2:
if (ctx->opt)
check_typos(arg + 1, options);
goto unknown;
}
if (ctx->opt)
check_typos(arg + 1, options);
while (ctx->opt) {
if (internal_help && *ctx->opt == 'h')
return parse_options_usage(ctx, usagestr, options, 0);
switch (parse_short_opt(ctx, options)) {
case -1:
return parse_options_usage(ctx, usagestr, options, 1);
case -2:
/* fake a short option thing to hide the fact that we may have
* started to parse aggregated stuff
*
* This is leaky, too bad.
*/
ctx->argv[0] = xstrdup(ctx->opt - 1);
*(char *)ctx->argv[0] = '-';
goto unknown;
}
}
continue;
}
if (!arg[2]) { /* "--" */
if (!(ctx->flags & PARSE_OPT_KEEP_DASHDASH)) {
ctx->argc--;
ctx->argv++;
}
break;
}
if (internal_help && !strcmp(arg + 2, "help-all"))
return usage_with_options_internal(ctx, usagestr, options, 1, 0);
if (internal_help && !strcmp(arg + 2, "help"))
return parse_options_usage(ctx, usagestr, options, 0);
switch (parse_long_opt(ctx, arg + 2, options)) {
case -1:
return parse_options_usage(ctx, usagestr, options, 1);
case -2:
goto unknown;
}
continue;
unknown:
if (!(ctx->flags & PARSE_OPT_KEEP_UNKNOWN))
return PARSE_OPT_UNKNOWN;
ctx->out[ctx->cpidx++] = ctx->argv[0];
ctx->opt = NULL;
}
return PARSE_OPT_DONE;
}
int parse_options_end(struct parse_opt_ctx_t *ctx)
{
memmove(ctx->out + ctx->cpidx, ctx->argv, ctx->argc * sizeof(*ctx->out));
ctx->out[ctx->cpidx + ctx->argc] = NULL;
return ctx->cpidx + ctx->argc;
}
int parse_options(int argc, const char **argv, const char *prefix,
const struct option *options, const char * const usagestr[],
int flags)
{
struct parse_opt_ctx_t ctx;
parse_options_start(&ctx, argc, argv, prefix, options, flags);
switch (parse_options_step(&ctx, options, usagestr)) {
case PARSE_OPT_HELP:
exit(129);
case PARSE_OPT_NON_OPTION:
case PARSE_OPT_DONE:
break;
default: /* PARSE_OPT_UNKNOWN */
if (ctx.argv[0][1] == '-') {
error("unknown option `%s'", ctx.argv[0] + 2);
} else {
error("unknown switch `%c'", *ctx.opt);
}
usage_with_options(usagestr, options);
}
precompose_argv(argc, argv);
return parse_options_end(&ctx);
}
static int usage_argh(const struct option *opts, FILE *outfile)
{
const char *s;
int literal = (opts->flags & PARSE_OPT_LITERAL_ARGHELP) || !opts->argh;
if (opts->flags & PARSE_OPT_OPTARG)
if (opts->long_name)
s = literal ? "[=%s]" : "[=<%s>]";
else
s = literal ? "[%s]" : "[<%s>]";
else
s = literal ? " %s" : " <%s>";
return fprintf(outfile, s, opts->argh ? _(opts->argh) : _("..."));
}
#define USAGE_OPTS_WIDTH 24
#define USAGE_GAP 2
static int usage_with_options_internal(struct parse_opt_ctx_t *ctx,
const char * const *usagestr,
const struct option *opts, int full, int err)
{
FILE *outfile = err ? stderr : stdout;
if (!usagestr)
return PARSE_OPT_HELP;
if (!err && ctx && ctx->flags & PARSE_OPT_SHELL_EVAL)
fprintf(outfile, "cat <<\\EOF\n");
fprintf_ln(outfile, _("usage: %s"), _(*usagestr++));
while (*usagestr && **usagestr)
/* TRANSLATORS: the colon here should align with the
one in "usage: %s" translation */
fprintf_ln(outfile, _(" or: %s"), _(*usagestr++));
while (*usagestr) {
if (**usagestr)
fprintf_ln(outfile, _(" %s"), _(*usagestr));
else
putchar('\n');
usagestr++;
}
if (opts->type != OPTION_GROUP)
fputc('\n', outfile);
for (; opts->type != OPTION_END; opts++) {
size_t pos;
int pad;
if (opts->type == OPTION_GROUP) {
fputc('\n', outfile);
if (*opts->help)
fprintf(outfile, "%s\n", _(opts->help));
continue;
}
if (!full && (opts->flags & PARSE_OPT_HIDDEN))
continue;
pos = fprintf(outfile, " ");
if (opts->short_name) {
if (opts->flags & PARSE_OPT_NODASH)
pos += fprintf(outfile, "%c", opts->short_name);
else
pos += fprintf(outfile, "-%c", opts->short_name);
}
if (opts->long_name && opts->short_name)
pos += fprintf(outfile, ", ");
if (opts->long_name)
pos += fprintf(outfile, "--%s", opts->long_name);
if (opts->type == OPTION_NUMBER)
pos += fprintf(outfile, "-NUM");
if ((opts->flags & PARSE_OPT_LITERAL_ARGHELP) ||
!(opts->flags & PARSE_OPT_NOARG))
pos += usage_argh(opts, outfile);
if (pos <= USAGE_OPTS_WIDTH)
pad = USAGE_OPTS_WIDTH - pos;
else {
fputc('\n', outfile);
pad = USAGE_OPTS_WIDTH;
}
fprintf(outfile, "%*s%s\n", pad + USAGE_GAP, "", _(opts->help));
}
fputc('\n', outfile);
if (!err && ctx && ctx->flags & PARSE_OPT_SHELL_EVAL)
fputs("EOF\n", outfile);
return PARSE_OPT_HELP;
}
void NORETURN usage_with_options(const char * const *usagestr,
const struct option *opts)
{
usage_with_options_internal(NULL, usagestr, opts, 0, 1);
exit(129);
}
void NORETURN usage_msg_opt(const char *msg,
const char * const *usagestr,
const struct option *options)
{
fprintf(stderr, "%s\n\n", msg);
usage_with_options(usagestr, options);
}
static int parse_options_usage(struct parse_opt_ctx_t *ctx,
const char * const *usagestr,
const struct option *opts, int err)
{
return usage_with_options_internal(ctx, usagestr, opts, 0, err);
}