| Message ID | 1382058681-14957-10-git-send-email-xiawenc@linux.vnet.ibm.com |
|---|---|
| State | New |
| Headers | show |
Il 18/10/2013 03:11, Wenchao Xia ha scritto: > This remove additional code path about where to print the error, > error_vprintf() is only the controller now, making future change > easier. > > The logic is not changed since when cur_mon = NULL, error_vprintf() > will still print to stderr. > > Signed-off-by: Wenchao Xia <xiawenc@linux.vnet.ibm.com> > --- > util/qemu-error.c | 11 ++++++++++- > 1 files changed, 10 insertions(+), 1 deletions(-) > > diff --git a/util/qemu-error.c b/util/qemu-error.c > index d1e858a..c29fcbd 100644 > --- a/util/qemu-error.c > +++ b/util/qemu-error.c > @@ -151,6 +151,15 @@ const char *error_get_progname(void) > return progname; > } > > +static void error_print_progname(const char *fmt, ...) > +{ > + va_list ap; > + > + va_start(ap, fmt); > + error_vprintf(fmt, ap); > + va_end(ap); > +} > + > /* > * Print current location to current monitor if we have one, else to stderr. > */ > @@ -161,7 +170,7 @@ static void error_print_loc(void) > const char *const *argp; > > if (!cur_mon && progname) { > - fprintf(stderr, "%s: ", progname); > + error_print_progname("%s: ", progname); > } > switch (cur_loc->kind) { > case LOC_CMDLINE: > I agree that using fprintf looks odd, but why not use error_printf directly? Paolo
δΊ 2013/10/18 17:44, Paolo Bonzini ει: > Il 18/10/2013 03:11, Wenchao Xia ha scritto: >> This remove additional code path about where to print the error, >> error_vprintf() is only the controller now, making future change >> easier. >> >> The logic is not changed since when cur_mon = NULL, error_vprintf() >> will still print to stderr. >> >> Signed-off-by: Wenchao Xia <xiawenc@linux.vnet.ibm.com> >> --- >> util/qemu-error.c | 11 ++++++++++- >> 1 files changed, 10 insertions(+), 1 deletions(-) >> >> diff --git a/util/qemu-error.c b/util/qemu-error.c >> index d1e858a..c29fcbd 100644 >> --- a/util/qemu-error.c >> +++ b/util/qemu-error.c >> @@ -151,6 +151,15 @@ const char *error_get_progname(void) >> return progname; >> } >> >> +static void error_print_progname(const char *fmt, ...) >> +{ >> + va_list ap; >> + >> + va_start(ap, fmt); >> + error_vprintf(fmt, ap); >> + va_end(ap); >> +} >> + >> /* >> * Print current location to current monitor if we have one, else to stderr. >> */ >> @@ -161,7 +170,7 @@ static void error_print_loc(void) >> const char *const *argp; >> >> if (!cur_mon && progname) { >> - fprintf(stderr, "%s: ", progname); >> + error_print_progname("%s: ", progname); >> } >> switch (cur_loc->kind) { >> case LOC_CMDLINE: >> > I agree that using fprintf looks odd, but why not use error_printf directly? > > Paolo > I used custom function since I have a following modification in my private branch. Since it is not send, I will use error_printf(), which is more straight.
diff --git a/util/qemu-error.c b/util/qemu-error.c index d1e858a..c29fcbd 100644 --- a/util/qemu-error.c +++ b/util/qemu-error.c @@ -151,6 +151,15 @@ const char *error_get_progname(void) return progname; } +static void error_print_progname(const char *fmt, ...) +{ + va_list ap; + + va_start(ap, fmt); + error_vprintf(fmt, ap); + va_end(ap); +} + /* * Print current location to current monitor if we have one, else to stderr. */ @@ -161,7 +170,7 @@ static void error_print_loc(void) const char *const *argp; if (!cur_mon && progname) { - fprintf(stderr, "%s: ", progname); + error_print_progname("%s: ", progname); } switch (cur_loc->kind) { case LOC_CMDLINE:
This remove additional code path about where to print the error, error_vprintf() is only the controller now, making future change easier. The logic is not changed since when cur_mon = NULL, error_vprintf() will still print to stderr. Signed-off-by: Wenchao Xia <xiawenc@linux.vnet.ibm.com> --- util/qemu-error.c | 11 ++++++++++- 1 files changed, 10 insertions(+), 1 deletions(-)