15 Commits

Author SHA1 Message Date
Ben Gras
2725087880 only check local benchmarks if /usr/local/benchmarks exists 2010-02-04 18:14:48 +00:00
Ben Gras
5795636593 also be able to run benchmarks from packages. 2010-02-04 17:52:52 +00:00
Ben Gras
7ff2ced50a benchmarks makefile. 2010-02-03 16:48:08 +00:00
Ben Gras
a6c6a2b4aa mimic old .sect .end behaviour 2010-02-03 15:30:26 +00:00
Ben Gras
6691830237 benchmarks. 2010-02-03 14:31:35 +00:00
Ben Gras
e0f2607bf0 remove benchmarks. 2010-02-03 14:30:36 +00:00
Ben Gras
0561f59b77 move benchmarks to their own dir. 2010-02-03 14:27:16 +00:00
Ben Gras
a008951e02 check for perl, don't assume Run is executable. 2010-02-03 14:18:25 +00:00
Ben Gras
77ca11d673 no big/small commands any more. 2010-02-03 13:55:48 +00:00
Ben Gras
e4201e90b0 asmconv in /usr/bin, other fixes 2010-02-03 13:32:33 +00:00
Ben Gras
64ab79e5e5 make run-bench executable too. 2010-02-02 15:35:51 +00:00
Ben Gras
ac33a29cf9 Nick's dec21140A fixes 2010-01-30 16:14:24 +00:00
Ben Gras
ca2d58a90c update qemu 2010-01-28 15:22:31 +00:00
Ben Gras
129c16543e updated package versions 2010-01-28 14:24:15 +00:00
Ben Gras
660364e68d include iperf, newer openssh 2010-01-28 14:14:23 +00:00
3354 changed files with 113477 additions and 91249 deletions

View File

@@ -1,6 +1,6 @@
# Master Makefile to compile everything in /usr/src except the system.
MAKE=make
MAKE = exec make -$(MAKEFLAGS)
usage:
@echo ""
@@ -8,15 +8,13 @@ usage:
@echo "Root privileges are required for some actions."
@echo ""
@echo "Usage:"
@echo " make world # Compile everything (libraries & commands)"
@echo " make includes # Install include files from src/"
@echo " make libraries # Compile and install libraries"
@echo " make commands # Compile all, commands, but don't install"
@echo " make install # Compile and install commands"
@echo " make depend # Generate required .depend files"
@echo " make gnu-includes # Install include files for GCC"
@echo " make gnu-libraries # Compile and install libraries for GCC"
@echo " make clean # Remove all compiler results"
@echo " make world # Compile everything (libraries & commands)"
@echo " make includes # Install include files from src/"
@echo " make libraries # Compile and install libraries"
@echo " make cmds # Compile all, commands, but don't install"
@echo " make install # Compile and install commands"
@echo " make depend # Generate required .depend files"
@echo " make clean # Remove all compiler results"
@echo ""
@echo "Run 'make' in tools/ to create a new MINIX configuration."
@echo ""
@@ -29,64 +27,45 @@ usage:
# 'make install' target.
#
# etcfiles has to be done first.
.if ${COMPILER_TYPE} == "ack"
world: mkfiles includes depend libraries install
.elif ${COMPILER_TYPE} == "gnu"
world: mkfiles includes depend gnu-libraries install
.endif
mkfiles:
cp etc/mk/*.mk /etc/mk/
world: includes depend libraries cmds install postinstall
includes:
cd include && $(MAKE) includes
cd include && $(MAKE) install gcc
libraries:
cd lib && sh ack_build.sh obj depend all install
cd lib && $(MAKE) all install
MKHEADERS411=/usr/gnu/libexec/gcc/i386-pc-minix/4.1.1/install-tools/mkheaders
MKHEADERS443=/usr/gnu/libexec/gcc/i686-pc-minix/4.4.3/install-tools/mkheaders
gnu-includes: includes
SHELL=/bin/sh; if [ -f $(MKHEADERS411) ] ; then sh -e $(MKHEADERS411) ; fi
SHELL=/bin/sh; if [ -f $(MKHEADERS443) ] ; then sh -e $(MKHEADERS443) ; fi
cmds:
if [ -f commands/Makefile ] ; then cd commands && $(MAKE) all; fi
gnu-libraries:
cd lib && sh gnu_build.sh obj depend all install
commands:
cd commands && $(MAKE) all
install::
if [ -f commands/Makefile ] ; then cd commands && $(MAKE) install; fi
depend::
cd boot && $(MAKE) depend
cd commands && $(MAKE) depend
cd kernel && $(MAKE) depend
cd servers && $(MAKE) depend
cd drivers && $(MAKE) depend
mkdep kernel
mkdep servers
mkdep drivers
cd kernel && $(MAKE) $@
cd servers && $(MAKE) $@
cd drivers && $(MAKE) $@
clean::
cd lib && $(MAKE) $@
test ! -f commands/Makefile || { cd commands && $(MAKE) $@; }
etcfiles::
cd etc && $(MAKE) install
all::
cd boot && $(MAKE) all
cd commands && $(MAKE) all
cd tools && $(MAKE) all
install::
cd boot && $(MAKE) install
cd man && $(MAKE) install makedb
cd commands && $(MAKE) install
cd share && $(MAKE) install
cd tools && $(MAKE) install
clean::
cd boot && $(MAKE) clean
cd commands && $(MAKE) clean
cd tools && $(MAKE) clean
cd lib && sh ack_build.sh clean
cd lib && sh gnu_build.sh clean
cd test && $(MAKE) clean
cd test && $(MAKE) $@
cleandepend::
cd boot && $(MAKE) cleandepend
cd commands && $(MAKE) cleandepend
cd tools && $(MAKE) cleandepend
all install clean::
cd boot && $(MAKE) $@
cd man && $(MAKE) $@ # First manpages, then commands
test ! -f commands/Makefile || { cd commands && $(MAKE) $@; }
cd tools && $(MAKE) $@
cd servers && $(MAKE) $@
postinstall:
cd etc && $(MAKE) $@

View File

@@ -1,4 +1,8 @@
#!/bin/sh
export CC=cc
export MINIX=1
./Run
if perl -e 'exit 0'
then perl -w Run
else echo "perl not installed. please install perl to run unixbench." >&2
exit 1
fi

View File

@@ -1,79 +1,123 @@
# Makefile for the boot monitor package.
# XXX: Can only be built with ACK currently
CC:=${CC:C/^gcc/cc/}
COMPILER_TYPE:=ack
SYS = ..
PROGS= bootblock cdbootblock bootexec boot masterboot \
jumpboot installboot edparams
CC = exec cc
CC86 = exec cc -mi86 -Was-ncc
CFLAGS = -I$(SYS)
LIBS = -lsys
LD = $(CC) -s -.o
LD86 = $(CC86) -.o
BIN = /usr/bin
MDEC = /usr/mdec
SRCS.bootblock= bootblock.s
CPPFLAGS.bootblock.s= ${I86CPPFLAGS}
LDFLAGS.bootblock= ${I86LDFLAGS}
BINDIR.bootblock= /usr/mdec
MAN.bootblock=
all: bootblock boot edparams masterboot jumpboot installboot addaout
dos: boot.com mkfile.com
SRCS.cdbootblock= cdbootblock.s
CPPFLAGS.cdbootblock.s= ${I86CPPFLAGS} -DCDBOOT
LDFLAGS.cdbootblock= ${I86LDFLAGS}
BINDIR.cdbootblock= /usr/mdec
MAN.cdbootblock=
bootblock: bootblock.s
$(LD86) -com -o $@ bootblock.s
SRCS.bootexec= boothead.s boot.c bootimage.c rawfs86.c
CPPFLAGS.boothead.s= ${I86CPPFLAGS}
CPPFLAGS.boot.c= ${I86CPPFLAGS}
CPPFLAGS.bootimage.c= ${I86CPPFLAGS}
CPPFLAGS.rawfs86.c= ${I86CPPFLAGS}
LDFLAGS.bootexec= ${I86LDFLAGS}
DPADD.bootexec= ${LIBSYS}
LDADD.bootexec= -lsys
BINDIR.bootexec= /usr/mdec
MAN.bootexec=
masterboot: masterboot.s
$(LD86) -com -o $@ masterboot.s
BINDIR.boot= /usr/mdec
MAN.boot=
jumpboot: jumpboot.s
$(LD86) -com -o $@ jumpboot.s
SRCS.masterboot= masterboot.s
CPPFLAGS.masterboot.s= ${I86CPPFLAGS}
LDFLAGS.masterboot= ${I86LDFLAGS}
BINDIR.masterboot= /usr/mdec
MAN.masterboot=
boot.o: boot.c
$(CC86) $(CFLAGS) -c boot.c
SRCS.jumpboot= jumpboot.s
CPPFLAGS.jumpboot.s= ${I86CPPFLAGS}
LDFLAGS.jumpboot= ${I86LDFLAGS}
BINDIR.jumpboot= /usr/mdec
MAN.jumpboot=
bootimage.o: bootimage.c
$(CC86) $(CFLAGS) -c bootimage.c
SRCS.installboot= installboot.c rawfs.c
BINDIR.installboot= /usr/bin
MAN.installboot=
SRCS.edparams= edparams.c rawfs.c
CPPFLAGS.edparams.c= -DUNIX
BINDIR.edparams= /usr/bin
MAN.edparams=
rawfs86.c: rawfs.c
rawfs86.o: rawfs.c rawfs.o
ln -f rawfs.c rawfs86.c
$(CC86) $(CFLAGS) -c rawfs86.c
rm rawfs86.c
-cmp -s rawfs.o rawfs86.o && ln -f rawfs.o rawfs86.o
edparams.c: boot.c
boot: boothead.s boot.o bootimage.o rawfs86.o
$(LD86) -o bootexec \
boothead.s boot.o bootimage.o rawfs86.o $(LIBS)
install -S 12kb bootexec
# This is code that is executed when used on a bootable
# CD, as its entry point is the start of the file then.
# It jumps over the a.out header into the part of the
# code in boothead.s where the code knows it's booting
# from CD if entered there.
( printf '\xeb\x3e ' ; cat bootexec ) >boot
chmod 755 boot
edparams.o: boot.c
ln -f boot.c edparams.c
$(CC) $(CFLAGS) -DUNIX -c edparams.c
rm edparams.c
cdbootblock.s: bootblock.s
ln -f bootblock.s cdbootblock.s
edparams: edparams.o rawfs.o
$(CC) $(CFLAGS) $(STRIP) -o $@ edparams.o rawfs.o
install -S 16kw edparams
boot: bootexec
install -S 22kb bootexec
cp bootexec boot
dosboot.o: boot.c
$(CC86) $(CFLAGS) -DDOS -o $@ -c boot.c
CPPFLAGS= -I${MINIXSRCDIR}
AFLAGS= -I${MINIXSRCDIR}
I86CPPFLAGS= -mi86 -Was-ncc
I86LDFLAGS= -mi86 -Was-ncc -.o -com
doshead.o: doshead.s
$(CC) -mi386 -o $@ -c doshead.s
STRIPFLAG= -s
dosboot: doshead.o dosboot.o bootimage.o rawfs86.o
$(LD86) -com -o $@ \
doshead.o dosboot.o bootimage.o rawfs86.o $(LIBS)
CLEANFILES+= rawfs86.c edparams.c cdbootblock.s
boot.com: dosboot
exec sh a.out2com dosboot boot.com
.include <minix.prog.mk>
mkfile: mkfhead.s mkfile.c
$(LD) -.o -mi86 -com -o $@ mkfhead.s mkfile.c $(LIBS)
mkfile.com: mkfile
exec sh a.out2com mkfile mkfile.com
installboot: installboot.o rawfs.o
$(CC) $(STRIP) -o installboot installboot.o rawfs.o
install -S 6kw installboot
addaout: addaout.o
$(CC) -o addaout addaout.o
installboot.o bootimage.o: image.h
boot.o bootimage.o dosboot.o edparams.o: boot.h
rawfs.o rawfs86.o installboot.o boot.o bootimage.o: rawfs.h
install: $(MDEC)/bootblock $(MDEC)/boot $(MDEC)/masterboot \
$(MDEC)/jumpboot $(BIN)/installboot $(BIN)/edparams
dosinstall: $(MDEC)/boot.com $(MDEC)/mkfile.com
$(MDEC)/bootblock: bootblock
install -cs -o bin -m 644 $? $@
$(MDEC)/boot: boot
install -cs -o bin -m 644 $? $@
$(MDEC)/boot.com: boot.com
install -c -m 644 $? $@
$(MDEC)/mkfile.com: mkfile.com
install -c -m 644 $? $@
$(MDEC)/masterboot: masterboot
install -cs -o bin -m 644 $? $@
$(MDEC)/jumpboot: jumpboot
install -cs -o bin -m 644 $? $@
$(BIN)/installboot: installboot
install -cs -o bin $? $@
$(BIN)/addaout: addaout
install -cs -o bin $? $@
$(BIN)/edparams: edparams
install -cs -o bin $? $@
clean:
rm -f *.bak *.o
rm -f bootblock addaout installboot boot masterboot jumpboot edparams
rm -f dosboot boot.com mkfile mkfile.com

View File

@@ -20,35 +20,34 @@
#define OUTPUT_FILE 2
/* Report problems. */
static void report(const char *problem, const char *message)
void report(char *problem, char *message)
{
fprintf(stderr, "%s:\n", problem);
fprintf(stderr, " %s\n\n", message);
}
static int copy_data(int srcfd, int dstfd)
int copy_data(int srcfd, int dstfd)
{
char buf[8192];
ssize_t n;
int total=0;
/** FIXME: handle error from read() */
/* Copy the little bytes themselves. (Source from cp.c). */
while ((n= read(srcfd, buf, sizeof(buf))) > 0) {
char *bp = buf;
ssize_t r = 0;
ssize_t r;
/** FIXME: handle error from write() */
while (n > 0 && (r= write(dstfd, bp, n)) > 0) {
bp += r;
n -= r;
total += r;
}
if (r == 0) {
fprintf(stderr, "Warning: EOF writing to output file.\n");
return(-1);
if (r <= 0) {
if (r == 0) {
fprintf(stderr, "Warning: EOF writing to output file.\n");
return(-1);
}
}
}
return(total);
@@ -63,7 +62,8 @@ int main(int argc, char **argv)
int fdin, fdout;
char * bp;
int n,r;
int total_size;
int total_size=0;
int result;
/* Check if command line arguments are present, or print usage. */
if (argc!=3) {
@@ -113,13 +113,13 @@ int main(int argc, char **argv)
bp = (char *) &aout;
n = sizeof(aout);
lseek(fdout, 0L, SEEK_SET);
lseek(fdout, 0, SEEK_SET);
while (n > 0 && (r= write(fdout, bp, n)) > 0) {
bp += r;
n -= r;
}
printf("Prepended data file (%d bytes) with a.out header (%u bytes).\n",
printf("Prepended data file (%u bytes) with a.out header (%u bytes).\n",
total_size, sizeof(aout));
printf("Done.\n");

View File

@@ -17,8 +17,8 @@ char version[]= "2.20";
#include <limits.h>
#include <string.h>
#include <errno.h>
#include <machine/partition.h>
#include <machine/bios.h>
#include <ibm/partition.h>
#include <ibm/bios.h>
#include <minix/config.h>
#include <minix/type.h>
#include <minix/dmap.h>
@@ -64,7 +64,7 @@ static int block_size;
*/
unsigned char boot_spec[24];
static const char *bios_err(int err)
char *bios_err(int err)
/* Translate BIOS error code to a readable string. (This is a rare trait
* known as error checking and reporting. Take a good look at it, you won't
* see it often.)
@@ -125,7 +125,7 @@ static const char *bios_err(int err)
* sector addressing, we check if the device is a CD in readsectors() and if so,
* read it into our own buffer first
*/
int readsectors(u32_t bufaddr, u32_t sector, u8_t count)
int readsectors(u32_t bufaddr, u32_t sector, U8_t count)
{
#define CDSECTOR_SIZE 2048
static char cdbuf[CDSECTOR_SIZE];
@@ -168,7 +168,7 @@ char *unix_err(int err)
}
}
static void rwerr(const char *rw, off_t sec, int err)
void rwerr(char *rw, off_t sec, int err)
{
printf("\n%s error 0x%02x (%s) at sector %ld absolute\n",
rw, err, bios_err(err), sec);
@@ -208,8 +208,8 @@ struct biosdev {
int device; /* Device to edit parameters. */
} bootdev;
static struct termios termbuf;
static int istty;
struct termios termbuf;
int istty;
void quit(int status)
{
@@ -219,13 +219,13 @@ void quit(int status)
#define exit(s) quit(s)
void report(const char *label)
void report(char *label)
/* edparams: label: No such file or directory */
{
fprintf(stderr, "edparams: %s: %s\n", label, strerror(errno));
}
void fatal(const char *label)
void fatal(char *label)
{
report(label);
exit(1);
@@ -338,7 +338,7 @@ int getch(void)
#endif /* UNIX */
static char *readline(void)
char *readline(void)
/* Read a line including a newline with echoing. */
{
char *line;
@@ -375,13 +375,13 @@ static char *readline(void)
return line;
}
static int sugar(const char *tok)
int sugar(char *tok)
/* Recognize special tokens. */
{
return strchr("=(){};\n", tok[0]) != nil;
}
static char *onetoken(char **aline)
char *onetoken(char **aline)
/* Returns a string with one token for tokenize. */
{
char *line= *aline;
@@ -429,7 +429,7 @@ typedef struct token {
char *token;
} token;
static token **tokenize(token **acmds, char *line)
token **tokenize(token **acmds, char *line)
/* Takes a line apart to form tokens. The tokens are inserted into a command
* chain at *acmds. Tokenize returns a reference to where another line could
* be added. Tokenize looks at spaces as token separators, and recognizes only
@@ -450,10 +450,10 @@ static token **tokenize(token **acmds, char *line)
return acmds;
}
static token *cmds; /* String of commands to execute. */
static int err; /* Set on an error. */
token *cmds; /* String of commands to execute. */
int err; /* Set on an error. */
static char *poptoken(void)
char *poptoken(void)
/* Pop one token off the command chain. */
{
token *cmd= cmds;
@@ -465,7 +465,7 @@ static char *poptoken(void)
return tok;
}
static void voidtoken(void)
void voidtoken(void)
/* Remove one token from the command chain. */
{
free(poptoken());
@@ -480,7 +480,7 @@ void parse_code(char *code)
(void) tokenize(&cmds, code);
}
static int interrupt(void)
int interrupt(void)
/* Clean up after an ESC has been typed. */
{
if (escape()) {
@@ -493,14 +493,14 @@ static int interrupt(void)
#if BIOS
static int activate;
int activate;
struct biosdev {
char name[8];
int device, primary, secondary;
} bootdev, tmpdev;
static int get_master(char *master, struct part_entry **table, u32_t pos)
int get_master(char *master, struct part_entry **table, u32_t pos)
/* Read a master boot sector and its partition table. */
{
int r, n;
@@ -526,7 +526,7 @@ static int get_master(char *master, struct part_entry **table, u32_t pos)
return 0;
}
static void initialize(void)
void initialize(void)
{
char master[SECTOR_SIZE];
struct part_entry *table[NR_PARTITIONS];
@@ -715,35 +715,35 @@ static void initialize(void)
/* Reserved names: */
enum resnames {
R_NULL, R_BOOT, R_CTTY, R_DELAY, R_ECHO, R_EXIT, R_HELP,
R_LS, R_MENU, R_OFF, R_SAVE, R_SET, R_TRAP, R_UNSET, R_RESET
R_LS, R_MENU, R_OFF, R_SAVE, R_SET, R_TRAP, R_UNSET
};
static char resnames[][6] = {
char resnames[][6] = {
"", "boot", "ctty", "delay", "echo", "exit", "help",
"ls", "menu", "off", "save", "set", "trap", "unset", "reset",
"ls", "menu", "off", "save", "set", "trap", "unset",
};
/* Using this for all null strings saves a lot of memory. */
#define null (resnames[0])
static enum resnames reserved(const char *s)
int reserved(char *s)
/* Recognize reserved strings. */
{
enum resnames r;
int r;
for (r= R_BOOT; r <= R_RESET; r++) {
for (r= R_BOOT; r <= R_UNSET; r++) {
if (strcmp(s, resnames[r]) == 0) return r;
}
return R_NULL;
}
static void sfree(char *s)
void sfree(char *s)
/* Free a non-null string. */
{
if (s != nil && s != null) free(s);
}
static char *copystr(const char *s)
char *copystr(char *s)
/* Copy a non-null string using malloc. */
{
char *c;
@@ -754,12 +754,12 @@ static char *copystr(const char *s)
return c;
}
static int is_default(const environment *e)
int is_default(environment *e)
{
return (e->flags & E_SPECIAL) && e->defval == nil;
}
static environment **searchenv(const char *name)
environment **searchenv(char *name)
{
environment **aenv= &env;
@@ -773,7 +773,7 @@ static environment **searchenv(const char *name)
#define b_getenv(name) (*searchenv(name))
/* Return the environment *structure* belonging to name, or nil if not found. */
char *b_value(const char *name)
char *b_value(char *name)
/* The value of a variable. */
{
environment *e= b_getenv(name);
@@ -781,7 +781,7 @@ char *b_value(const char *name)
return e == nil || !(e->flags & E_VAR) ? nil : e->value;
}
static char *b_body(const char *name)
char *b_body(char *name)
/* The value of a function. */
{
environment *e= b_getenv(name);
@@ -789,8 +789,7 @@ static char *b_body(const char *name)
return e == nil || !(e->flags & E_FUNCTION) ? nil : e->value;
}
static int b_setenv(int flags, const char *name, const char *arg,
const char *value)
int b_setenv(int flags, char *name, char *arg, char *value)
/* Change the value of an environment variable. Returns the flags of the
* variable if you are not allowed to change it, 0 otherwise.
*/
@@ -839,7 +838,7 @@ int b_setvar(int flags, char *name, char *value)
return r;
}
void b_unset(const char *name)
void b_unset(char *name)
/* Remove a variable from the environment. A special variable is reset to
* its default value.
*/
@@ -865,7 +864,7 @@ void b_unset(const char *name)
}
}
long a2l(const char *a)
long a2l(char *a)
/* Cheap atol(). */
{
int sign= 1;
@@ -895,7 +894,7 @@ char *ul2a10(u32_t n)
return ul2a(n, 10);
}
unsigned a2x(const char *a)
unsigned a2x(char *a)
/* Ascii to hex. */
{
unsigned n= 0;
@@ -916,11 +915,11 @@ unsigned a2x(const char *a)
return n;
}
static void get_parameters(void)
void get_parameters(void)
{
char params[SECTOR_SIZE + 1];
token **acmds;
int r, processor;
int r, bus, processor;
memory *mp;
static char bus_type[][4] = {
"xt", "at", "mca"
@@ -998,14 +997,14 @@ static void get_parameters(void)
#endif
}
static char *addptr;
char *addptr;
static void addparm(const char *n)
void addparm(char *n)
{
while (*n != 0 && *addptr != 0) *addptr++ = *n++;
}
static void save_parameters(void)
void save_parameters(void)
/* Save nondefault environment variables to the bootparams sector. */
{
environment *e;
@@ -1046,7 +1045,7 @@ static void save_parameters(void)
}
}
static void show_env(void)
void show_env(void)
/* Show the environment settings. */
{
environment *e;
@@ -1117,6 +1116,7 @@ dev_t name2dev(char *name)
{
dev_t dev;
ino_t ino;
int drive;
struct stat st;
char *n, *s;
@@ -1415,19 +1415,17 @@ int exec_bootstrap(void)
return r;
bootstrap(device, active);
return 0;
}
static void boot_device(char *devname)
void boot_device(char *devname)
/* Boot the device named by devname. */
{
dev_t dev= name2dev(devname);
int save_dev= device;
int r;
const char *err;
char *err;
if (tmpdev.device < 0) {
/* FIXME: clearer error message. */
if (dev != -1) printf("Can't boot from %s\n", devname);
return;
}
@@ -1445,7 +1443,7 @@ static void boot_device(char *devname)
(void) dev_open();
}
static void ctty(char *line)
void ctty(char *line)
{
if (line == nil) {
serial_line = -1;
@@ -1460,13 +1458,13 @@ static void ctty(char *line)
#else /* DOS */
static void boot_device(char *devname)
void boot_device(char *devname)
/* No booting of other devices under DOS. */
{
printf("Can't boot devices under DOS\n");
}
static void ctty(char *line)
void ctty(char *line)
/* Don't know how to handle serial lines under DOS. */
{
printf("No serial line support under DOS\n");
@@ -1475,7 +1473,7 @@ static void ctty(char *line)
#endif /* DOS */
#endif /* BIOS */
static void ls(char *dir)
void ls(char *dir)
/* List the contents of a directory. */
{
ino_t ino;
@@ -1494,24 +1492,24 @@ static void ls(char *dir)
}
(void) r_readdir(name); /* Skip ".." too. */
while (r_readdir(name) != 0) printf("%s/%s\n", dir, name);
while ((ino= r_readdir(name)) != 0) printf("%s/%s\n", dir, name);
}
static u32_t milli_time(void)
u32_t milli_time(void)
{
return get_tick() * MSEC_PER_TICK;
}
static u32_t milli_since(u32_t base)
u32_t milli_since(u32_t base)
{
return (milli_time() + (TICKS_PER_DAY*MSEC_PER_TICK) - base)
% (TICKS_PER_DAY*MSEC_PER_TICK);
}
static char *Thandler;
static u32_t Tbase, Tcount;
char *Thandler;
u32_t Tbase, Tcount;
static void unschedule(void)
void unschedule(void)
/* Invalidate a waiting command. */
{
alarm(0);
@@ -1522,7 +1520,7 @@ static void unschedule(void)
}
}
static void schedule(long msec, char *cmd)
void schedule(long msec, char *cmd)
/* Schedule command at a certain time from now. */
{
unschedule();
@@ -1538,7 +1536,7 @@ int expired(void)
return (Thandler != nil && milli_since(Tbase) >= Tcount);
}
void delay(const char *msec)
void delay(char *msec)
/* Delay for a given time. */
{
u32_t base, count;
@@ -1553,7 +1551,7 @@ void delay(const char *msec)
} while (!interrupt() && !expired() && milli_since(base) < count);
}
static enum whatfun { NOFUN, SELECT, DEFFUN, USERFUN } menufun(const environment *e)
enum whatfun { NOFUN, SELECT, DEFFUN, USERFUN } menufun(environment *e)
{
if (!(e->flags & E_FUNCTION) || e->arg[0] == 0) return NOFUN;
if (e->arg[1] != ',') return SELECT;
@@ -1588,7 +1586,6 @@ void menu(void)
case SELECT:
printf(" %c Select %s kernel\n", e->arg[0],e->name);
break;
case NOFUN:
default:;
}
}
@@ -1657,12 +1654,12 @@ void help(void)
}
}
static void execute(void)
void execute(void)
/* Get one command from the command chain and execute it. */
{
token *second, *third, *fourth, *sep;
char *name;
enum resnames res;
int res;
size_t n= 0;
if (err) {
@@ -1877,7 +1874,6 @@ static void execute(void)
case R_EXIT: exit(0);
case R_OFF: off(); ok= 1; break;
case R_CTTY: ctty(nil); ok= 1; break;
case R_RESET: reset(); ok= 1; break;
}
/* Command to check bootparams: */
@@ -1918,7 +1914,7 @@ int run_trailer(void)
return !err;
}
static void monitor(void)
void monitor(void)
/* Read a line and tokenize it. */
{
char *line;
@@ -2030,9 +2026,6 @@ void main(int argc, char **argv)
}
exit(0);
}
reset() { }
#endif /* UNIX */
/*

View File

@@ -93,7 +93,7 @@ void raw_copy(u32_t dstaddr, u32_t srcaddr, u32_t count);
/* Copy bytes from anywhere to anywhere. */
u16_t get_word(u32_t addr);
/* Get a word from anywhere. */
void put_word(u32_t addr, u16_t word);
void put_word(u32_t addr, U16_t word);
/* Put a word anywhere. */
void relocate(void);
/* Switch to a copy of this program. */
@@ -101,12 +101,12 @@ int dev_open(void), dev_close(void);
/* Open device and determine params / close device. */
int dev_boundary(u32_t sector);
/* True if sector is on a track boundary. */
int readsectors(u32_t bufaddr, u32_t sector, u8_t count);
int readsectors(u32_t bufaddr, u32_t sector, U8_t count);
/* Read 1 or more sectors from "device". */
int writesectors(u32_t bufaddr, u32_t sector, u8_t count);
int writesectors(u32_t bufaddr, u32_t sector, U8_t count);
/* Write 1 or more sectors to "device". */
int biosreadsectors(u32_t bufaddr, u32_t sector, u8_t count);
int biosreadsectors(u32_t bufaddr, u32_t sector, U8_t count);
int getch(void);
/* Read a keypress. */
@@ -167,9 +167,9 @@ typedef struct environment {
EXTERN environment *env; /* Lists the environment. */
char *b_value(const char *name); /* Get/set the value of a variable. */
char *b_value(char *name); /* Get/set the value of a variable. */
int b_setvar(int flags, char *name, char *value);
void b_unset(const char *name);
void b_unset(char *name);
void parse_code(char *code); /* Parse boot monitor commands. */
@@ -187,9 +187,9 @@ void readerr(off_t sec, int err);
/* Report a read error. */
char *ul2a(u32_t n, unsigned b), *ul2a10(u32_t n);
/* Transform u32_t to ASCII at base b or base 10. */
long a2l(const char *a);
long a2l(char *a);
/* Cheap atol(). */
unsigned a2x(const char *a);
unsigned a2x(char *a);
/* ASCII to hex. */
dev_t name2dev(char *name);
/* Translate a device name to a device number. */
@@ -213,7 +213,7 @@ EXTERN char *drun; /* Initial command from DOS command line. */
#endif
void readblock(off_t, char *, int);
void delay(const char *);
void delay(char *);
/*
* $PchId: boot.h,v 1.12 2002/02/27 19:42:45 philip Exp $

View File

@@ -1,4 +1,3 @@
#
! Bootblock 1.5 - Minix boot block. Author: Kees J. Bot
! 21 Dec 1991
!
@@ -19,21 +18,15 @@
LOADOFF = 0x7C00 ! 0x0000:LOADOFF is where this code is loaded
BOOTSEG = 0x1000 ! Secondary boot code segment.
#ifdef CDBOOT
BOOTOFF = 0x0050 ! Offset into /boot above header
#else
BOOTOFF = 0x0030 ! Offset into /boot above header
#endif
BUFFER = 0x0600 ! First free memory
#ifndef CDBOOT /* just constants, but make no sense for CDs */
LOWSEC = 8 ! Offset of logical first sector in partition
! table
! Variables addressed using bp register
device = 0 ! The boot device
lowsec = 2 ! Offset of boot partition within drive
secpcyl = 6 ! Sectors per cylinder = heads * sectors
#endif
device = 0 ! The boot device
.text
@@ -58,21 +51,18 @@ boot:
mov di, #LOADOFF+sectors ! char *di = sectors;
#ifndef CDBOOT
testb dl, dl ! Winchester disks if dl >= 0x80
jge floppy
#endif
winchester:
#ifndef CDBOOT
! Get the offset of the first sector of the boot partition from the partition
! table. The table is found at es:si, the lowsec parameter at offset LOWSEC.
eseg
les ax, LOWSEC(si) ! es:ax = LOWSEC+2(si):LOWSEC(si)
mov lowsec+0(bp), ax ! Low 16 bits of partitions first sector
mov lowsec+2(bp), es ! High 16 bits of partitions first sector
mov lowsec+0(bp), ax ! Low 16 bits of partition's first sector
mov lowsec+2(bp), es ! High 16 bits of partition's first sector
! Get the drive parameters, the number of sectors is bluntly written into the
! floppy disk sectors/track array.
@@ -82,10 +72,8 @@ winchester:
andb cl, #0x3F ! cl = max sector number (1-origin)
movb (di), cl ! Number of sectors per track
incb dh ! dh = 1 + max head number (0-origin)
#endif
jmp loadboot
#ifndef CDBOOT
! Floppy:
! Execute three read tests to determine the drive type. Test for each floppy
! type by reading the last sector on the first track. If it fails, try a type
@@ -113,16 +101,13 @@ floppy: xorb ah, ah ! Reset drive
jc next ! Error, try the next floppy type
success:movb dh, #2 ! Load number of heads for multiply
#endif
loadboot:
! Load /boot from the boot device
#ifndef CDBOOT
movb al, (di) ! al = (di) = sectors per track
mulb dh ! dh = heads, ax = heads * sectors
mov secpcyl(bp), ax ! Sectors per cylinder = heads * sectors
#endif
mov ax, #BOOTSEG ! Segment to load /boot into
mov es, ax
@@ -132,7 +117,6 @@ load:
mov ax, 1(si) ! Get next sector number: low 16 bits
movb dl, 3(si) ! Bits 16-23 for your up to 8GB partition
xorb dh, dh ! dx:ax = sector within partition
#ifndef CDBOOT
add ax, lowsec+0(bp)
adc dx, lowsec+2(bp)! dx:ax = sector within drive
cmp dx, #[1024*255*63-255]>>16 ! Near 8G limit?
@@ -152,14 +136,13 @@ load:
movb al, (di) ! Sectors per track - Sector number (0-origin)
subb al, ah ! = Sectors left on this track
cmpb al, (si) ! Compare with # sectors to read
jbe read ! Cant read past the end of a cylinder?
jbe read ! Can't read past the end of a cylinder?
movb al, (si) ! (si) < sectors left on this track
read: push ax ! Save al = sectors to read
movb ah, #0x02 ! Code for disk read (all registers in use now!)
int 0x13 ! Call the BIOS for a read
pop cx ! Restore al in cl
jmp rdeval
#endif
bigdisk:
movb cl, (si) ! Number of sectors to read
push si ! Save si
@@ -178,14 +161,6 @@ rdeval:
movb al, cl ! Restore al = sectors read
addb bh, al ! bx += 2 * al * 256 (add bytes read)
addb bh, al ! es:bx = where next sector must be read
#ifdef CDBOOT
addb bh, al ! For CDs, a sector is 2048 bytes, so
addb bh, al ! do this 6 more times to get byte count.
addb bh, al
addb bh, al
addb bh, al
addb bh, al
#endif
add 1(si), ax ! Update address by sectors read
adcb 3(si), ah ! Don't forget bits 16-23 (add ah = 0)
subb (si), al ! Decrement sector count by sectors read

View File

@@ -46,29 +46,25 @@
.text
! We assume boot is always linked with a short (32 byte) a.out header and has
! 16 bytes of its own prefix, so 48 bytes to skip. bootblock jumps into us
! at offset 0x30, cd boot code at 0x40
! Set segment registers and stack pointer using the programs own header!
! The header is either 32 bytes (short form) or 48 bytes (long form). The
! bootblock will jump to address 0x10030 in both cases, calling one of the
! two jmpf instructions below.
!
! CD bootblock jumps to address 0x10050 in both cases.
! Set cs right
! (skip short a.out header plus 16 byte preefix)
jmpf boot, LOADSEG+3
.space 11
jmpf boot, LOADSEG+3 ! Set cs right (skipping long a.out header)
.space 11 ! jmpf + 11 = 16 bytes
jmpf boot, LOADSEG+2 ! Set cs right (skipping short a.out header)
.space 11 ! jmpf + 11 = 16 bytes
! entry point when booting from CD
jmpf cdboot, LOADSEG+3
.space 11
jmpf cdboot, LOADSEG+2
.space 11
.space 11
cdboot:
mov bx, #1
jmp commonboot
boot:
mov bx, #0
commonboot:
mov ax, #LOADSEG
mov ax, #LOADSEG+1
mov ds, ax ! ds = header
movb al, a_flags
@@ -133,7 +129,7 @@ sepID:
mov _daddr+0, ax
mov _daddr+2, dx
push ds
mov ax, #LOADSEG
mov ax, #LOADSEG+1
mov ds, ax ! Back to the header once more
mov ax, a_total+0
mov dx, a_total+2 ! dx:ax = data + bss + heap + stack
@@ -301,12 +297,10 @@ smallcopy:
ext_copy:
mov x_dst_desc+2, ax
movb x_dst_desc+4, dl ! Set base of destination segment
movb x_dst_desc+7, dh
mov ax, 8(bp)
mov dx, 10(bp)
mov x_src_desc+2, ax
movb x_src_desc+4, dl ! Set base of source segment
movb x_src_desc+7, dh
mov si, #x_gdt ! es:si = global descriptor table
shr cx, #1 ! Words to move
movb ah, #0x87 ! Code for extended memory move
@@ -1454,11 +1448,6 @@ _scan_keyboard:
outb 0x61
ret
.define _reset
_reset:
lidt idt_zero
int 0x3
.data
.ascii "(null)\0" ! Just in case someone follows a null pointer
.align 2
@@ -1466,8 +1455,6 @@ c60: .data2 60 ! Constants for MUL and DIV
c1024: .data2 1024
c1080: .data2 1080
c19663: .data2 19663
idt_zero:
.data4 0,0
! Global descriptor tables.
UNSET = 0 ! Must be computed

View File

@@ -22,19 +22,12 @@
#include <sys/video.h>
#include <kernel/const.h>
#include <kernel/type.h>
#include <machine/partition.h>
#include <ibm/partition.h>
#include "rawfs.h"
#include "image.h"
#include "boot.h"
static int block_size = 0;
static int verboseboot = VERBOSEBOOT_QUIET;
#define DEBUG_PRINT(params, level) do { \
if (verboseboot >= (level)) printf params; } while (0)
#define DEBUGBASIC(params) DEBUG_PRINT(params, VERBOSEBOOT_BASIC)
#define DEBUGEXTRA(params) DEBUG_PRINT(params, VERBOSEBOOT_EXTRA)
#define DEBUGMAX(params) DEBUG_PRINT(params, VERBOSEBOOT_MAX)
extern int serial_line;
extern u16_t vid_port; /* Video i/o port. */
@@ -53,8 +46,7 @@ extern u32_t vid_mem_size; /* Video memory size. */
#define K_INT86 0x0040 /* Requires generic INT support. */
#define K_MEML 0x0080 /* Pass a list of free memory. */
#define K_BRET 0x0100 /* New monitor code on shutdown in boot parameters. */
#define K_KHIGH 0x0200 /* Load kernel in extended memory. */
#define K_ALL 0x03FF /* All feature bits this monitor supports. */
#define K_ALL 0x01FF /* All feature bits this monitor supports. */
/* Data about the different processes. */
@@ -85,7 +77,7 @@ int n_procs; /* Number of processes. */
#define between(a, c, z) ((unsigned) ((c) - (a)) <= ((z) - (a)))
void pretty_image(const char *image)
void pretty_image(char *image)
/* Pretty print the name of the image to load. Translate '/' and '_' to
* space, first letter goes uppercase. An 'r' before a digit prints as
* 'revision'. E.g. 'minix/1.6.16r10' -> 'Minix 1.6.16 revision 10'.
@@ -110,20 +102,16 @@ void pretty_image(const char *image)
}
}
#define RAW_ALIGN 16
#define BUFSIZE_ZEROS 128
void raw_clear(u32_t addr, u32_t count)
/* Clear "count" bytes at absolute address "addr". */
{
static char zerosdata[BUFSIZE_ZEROS + RAW_ALIGN];
char *zeros = zerosdata + RAW_ALIGN - (unsigned) &zerosdata % RAW_ALIGN;
static char zeros[128];
u32_t dst;
u32_t zct;
zct= BUFSIZE_ZEROS;
zct= sizeof(zeros);
if (zct > count) zct= count;
raw_copy(addr, mon2abs(zeros), zct);
raw_copy(addr, mon2abs(&zeros), zct);
count-= zct;
while (count > 0) {
@@ -235,7 +223,7 @@ void patch_sizes(void)
put_word(process[FS].data + P_INIT_OFF+4, data_size);
}
int selected(const char *name)
int selected(char *name)
/* True iff name has no label or the proper label. */
{
char *colon, *label;
@@ -250,7 +238,7 @@ int selected(const char *name)
return cmp == 0;
}
static u32_t proc_size(const struct image_header *hdr)
u32_t proc_size(struct image_header *hdr)
/* Return the size of a process in sectors as found in an image. */
{
u32_t len= hdr->process.a_text;
@@ -294,10 +282,9 @@ char *get_sector(u32_t vsec)
u32_t sec;
int r;
#define SECBUFS 16
static char bufdata[SECBUFS * SECTOR_SIZE + RAW_ALIGN];
static char buf[SECBUFS * SECTOR_SIZE];
static size_t count; /* Number of sectors in the buffer. */
static u32_t bufsec; /* First Sector now in the buffer. */
char *buf = bufdata + RAW_ALIGN - (unsigned) &bufdata % RAW_ALIGN;
if (vsec == 0) count= 0; /* First sector; initialize. */
@@ -378,20 +365,10 @@ int get_segment(u32_t *vsec, long *size, u32_t *addr, u32_t limit)
if ((buf= get_sector((*vsec)++)) == nil) return 0;
cnt= SECTOR_SIZE;
}
if (*addr + click_size > limit)
{
DEBUGEXTRA(("get_segment: out of memory; "
"addr=0x%lx; limit=0x%lx; size=%lx\n",
*addr, limit, size));
errno= ENOMEM;
return 0;
}
if (*addr + click_size > limit) { errno= ENOMEM; return 0; }
n= click_size;
if (n > cnt) n= cnt;
DEBUGMAX(("raw_copy(0x%lx, 0x%lx/0x%x, 0x%lx)... ",
*addr, mon2abs(buf), buf, n));
raw_copy(*addr, mon2abs(buf), n);
DEBUGMAX(("done\n"));
*addr+= n;
*size-= n;
buf+= n;
@@ -400,9 +377,7 @@ int get_segment(u32_t *vsec, long *size, u32_t *addr, u32_t limit)
/* Zero extend to a click. */
n= align(*addr, click_size) - *addr;
DEBUGMAX(("raw_clear(0x%lx, 0x%lx)... ", *addr, n));
raw_clear(*addr, n);
DEBUGMAX(("done\n"));
*addr+= n;
*size-= n;
return 1;
@@ -425,7 +400,7 @@ static void restore_screen(void)
sizeof(boot_tty_info));
if(boot_tty_info.magic == TTYMAGIC) {
if((boot_tty_info.flags & (BTIF_CONSORIGIN|BTIF_CONSCURSOR)) ==
if(boot_tty_info.flags & (BTIF_CONSORIGIN|BTIF_CONSCURSOR) ==
(BTIF_CONSORIGIN|BTIF_CONSCURSOR)) {
int line;
raw_copy(mon2abs(consolescreen),
@@ -455,17 +430,18 @@ void exec_image(char *image)
long a_text, a_data, a_bss, a_stack;
int banner= 0;
long processor= a2l(b_value("processor"));
u16_t kmagic, mode;
u16_t mode;
char *console;
char params[SECTOR_SIZE];
extern char *sbrk(int);
char *verb;
int verbose = 0;
/* The stack is pretty deep here, so check if heap and stack collide. */
(void) sbrk(0);
if ((verb= b_value(VERBOSEBOOTVARNAME)) != nil)
verboseboot = a2l(verb);
if ((verb= b_value("verbose")) != nil && a2l(verb) > 0)
verbose = 1;
printf("\nLoading ");
pretty_image(image);
@@ -495,7 +471,6 @@ void exec_image(char *image)
procp= &process[i];
/* Read header. */
DEBUGEXTRA(("Reading header... "));
for (;;) {
if ((buf= get_sector(vsec++)) == nil) return;
@@ -509,7 +484,6 @@ void exec_image(char *image)
/* Bad label, skip this process. */
vsec+= proc_size(&hdr);
}
DEBUGEXTRA(("done\n"));
/* Sanity check: an 8086 can't run a 386 kernel. */
if (hdr.process.a_cpu == A_I80386 && processor < 386) {
@@ -523,35 +497,22 @@ void exec_image(char *image)
if (i == KERNEL_IDX) {
if (!get_clickshift(vsec, &hdr)) return;
addr= align(addr, click_size);
/* big kernels must be loaded into extended memory */
if (k_flags & K_KHIGH) {
addr= mem[1].base;
limit= mem[1].base + mem[1].size;
}
}
/* Save a copy of the header for the kernel, with a_syms
* misused as the address where the process is loaded at.
*/
DEBUGEXTRA(("raw_copy(0x%x, 0x%lx, 0x%x)... ",
aout + i * A_MINHDR, mon2abs(&hdr.process), A_MINHDR));
hdr.process.a_syms= addr;
raw_copy(aout + i * A_MINHDR, mon2abs(&hdr.process), A_MINHDR);
DEBUGEXTRA(("done\n"));
if (!banner) {
DEBUGBASIC((" cs ds text data bss"));
if (k_flags & K_CHMEM) DEBUGBASIC((" stack"));
DEBUGBASIC(("\n"));
if (!banner && verbose) {
printf(" cs ds text data bss");
if (k_flags & K_CHMEM) printf(" stack");
putch('\n');
banner= 1;
}
/* Segment sizes. */
DEBUGEXTRA(("a_text=0x%lx; a_data=0x%lx; a_bss=0x%lx; a_flags=0x%x)\n",
hdr.process.a_text, hdr.process.a_data,
hdr.process.a_bss, hdr.process.a_flags));
a_text= hdr.process.a_text;
a_data= hdr.process.a_data;
a_bss= hdr.process.a_bss;
@@ -575,12 +536,7 @@ void exec_image(char *image)
/* Separate I&D: two segments. Common I&D: only one. */
if (hdr.process.a_flags & A_SEP) {
/* Read the text segment. */
DEBUGEXTRA(("get_segment(0x%lx, 0x%lx, 0x%lx, 0x%lx)\n",
vsec, a_text, addr, limit));
if (!get_segment(&vsec, &a_text, &addr, limit)) return;
DEBUGEXTRA(("get_segment done vsec=0x%lx a_text=0x%lx "
"addr=0x%lx\n",
vsec, a_text, addr));
/* The data segment follows. */
procp->ds= addr;
@@ -594,20 +550,19 @@ void exec_image(char *image)
}
/* Read the data segment. */
DEBUGEXTRA(("get_segment(0x%lx, 0x%lx, 0x%lx, 0x%lx)\n",
vsec, a_data, addr, limit));
if (!get_segment(&vsec, &a_data, &addr, limit)) return;
DEBUGEXTRA(("get_segment done vsec=0x%lx a_data=0x%lx "
"addr=0x%lx\n",
vsec, a_data, addr));
/* Make space for bss and stack unless... */
if (i != KERNEL_IDX && (k_flags & K_CLAIM)) a_bss= a_stack= 0;
DEBUGBASIC(("%07lx %07lx %8ld %8ld %8ld",
procp->cs, procp->ds, hdr.process.a_text,
hdr.process.a_data, hdr.process.a_bss));
if (k_flags & K_CHMEM) DEBUGBASIC((" %8ld", a_stack));
if(verbose) {
printf("%07lx %07lx %8ld %8ld %8ld",
procp->cs, procp->ds,
hdr.process.a_text, hdr.process.a_data,
hdr.process.a_bss
);
}
if ((k_flags & K_CHMEM) && verbose) printf(" %8ld", a_stack);
/* Note that a_data may be negative now, but we can look at it
* as -a_data bss bytes.
@@ -619,10 +574,8 @@ void exec_image(char *image)
a_bss-= n;
/* Zero out bss. */
DEBUGEXTRA(("\nraw_clear(0x%lx, 0x%lx); limit=0x%lx... ", addr, n, limit));
if (addr + n > limit) { errno= ENOMEM; return; }
raw_clear(addr, n);
DEBUGEXTRA(("done\n"));
addr+= n;
/* And the number of stack clicks. */
@@ -636,7 +589,7 @@ void exec_image(char *image)
/* Process endpoint. */
procp->end= addr;
if (verboseboot >= VERBOSEBOOT_BASIC)
if(verbose)
printf(" %s\n", hdr.name);
else {
u32_t mem;
@@ -645,14 +598,14 @@ void exec_image(char *image)
totalmem += mem;
}
if (i == 0 && (k_flags & (K_HIGH | K_KHIGH)) == K_HIGH) {
if (i == 0 && (k_flags & K_HIGH)) {
/* Load the rest in extended memory. */
addr= mem[1].base;
limit= mem[1].base + mem[1].size;
}
}
if (verboseboot < VERBOSEBOOT_BASIC)
if(!verbose)
printf("(%dk)\n", totalmem/1024);
if ((n_procs= i) == 0) {
@@ -662,19 +615,14 @@ void exec_image(char *image)
}
/* Check the kernel magic number. */
raw_copy(mon2abs(&kmagic),
process[KERNEL_IDX].data + MAGIC_OFF, sizeof(kmagic));
if (kmagic != KERNEL_D_MAGIC) {
printf("Kernel magic number is incorrect (0x%x@0x%lx)\n",
kmagic, process[KERNEL_IDX].data + MAGIC_OFF);
if (get_word(process[KERNEL_IDX].data + MAGIC_OFF) != KERNEL_D_MAGIC) {
printf("Kernel magic number is incorrect\n");
errno= 0;
return;
}
/* Patch sizes, etc. into kernel data. */
DEBUGEXTRA(("patch_sizes()... "));
patch_sizes();
DEBUGEXTRA(("done\n"));
#if !DOS
if (!(k_flags & K_MEML)) {
@@ -684,33 +632,22 @@ void exec_image(char *image)
#endif
/* Run the trailer function just before starting Minix. */
DEBUGEXTRA(("run_trailer()... "));
if (!run_trailer()) { errno= 0; return; }
DEBUGEXTRA(("done\n"));
/* Translate the boot parameters to what Minix likes best. */
DEBUGEXTRA(("params2params(0x%x, 0x%x)... ", params, sizeof(params)));
if (!params2params(params, sizeof(params))) { errno= 0; return; }
DEBUGEXTRA(("done\n"));
/* Set the video to the required mode. */
if ((console= b_value("console")) == nil || (mode= a2x(console)) == 0) {
mode= strcmp(b_value("chrome"), "color") == 0 ? COLOR_MODE :
MONO_MODE;
}
DEBUGEXTRA(("set_mode(%d)... ", mode));
set_mode(mode);
DEBUGEXTRA(("done\n"));
/* Close the disk. */
DEBUGEXTRA(("dev_close()... "));
(void) dev_close();
DEBUGEXTRA(("done\n"));
/* Minix. */
DEBUGEXTRA(("minix(0x%lx, 0x%lx, 0x%lx, 0x%x, 0x%x, 0x%lx)\n",
process[KERNEL_IDX].entry, process[KERNEL_IDX].cs,
process[KERNEL_IDX].ds, params, sizeof(params), aout));
minix(process[KERNEL_IDX].entry, process[KERNEL_IDX].cs,
process[KERNEL_IDX].ds, params, sizeof(params), aout);

View File

@@ -3,6 +3,7 @@
*
* Either make a device bootable or make an image from kernel, mm, fs, etc.
*/
#define nil 0
#define _POSIX_SOURCE 1
#define _MINIX 1
#include <stdio.h>
@@ -39,13 +40,13 @@
#define BOOT_BLOCK_SIZE 1024
static void report(const char *label)
void report(char *label)
/* installboot: label: No such file or directory */
{
fprintf(stderr, "installboot: %s: %s\n", label, strerror(errno));
}
static void fatal(const char *label)
void fatal(char *label)
{
report(label);
exit(1);
@@ -60,12 +61,12 @@ char *basename(char *name)
static char base[IM_NAME_MAX];
char *p, *bp= base;
if ((p= strchr(name, ':')) != NULL) {
if ((p= strchr(name, ':')) != nil) {
while (name <= p && bp < base + IM_NAME_MAX - 1)
*bp++ = *name++;
}
for (;;) {
if ((p= strrchr(name, '/')) == NULL) { p= name; break; }
if ((p= strrchr(name, '/')) == nil) { p= name; break; }
if (*++p != 0) break;
*--p= 0;
}
@@ -74,7 +75,7 @@ char *basename(char *name)
return base;
}
static void bread(FILE *f, char *name, void *buf, size_t len)
void bread(FILE *f, char *name, void *buf, size_t len)
/* Read len bytes. Don't dare return without them. */
{
if (len > 0 && fread(buf, len, 1, f) != 1) {
@@ -84,7 +85,7 @@ static void bread(FILE *f, char *name, void *buf, size_t len)
}
}
static void bwrite(FILE *f, const char *name, const void *buf, size_t len)
void bwrite(FILE *f, char *name, void *buf, size_t len)
{
if (len > 0 && fwrite(buf, len, 1, f) != 1) fatal(name);
}
@@ -94,14 +95,14 @@ int making_image= 0;
void read_header(int talk, char *proc, FILE *procf, struct image_header *ihdr)
/* Read the a.out header of a program and check it. If procf happens to be
* NULL then the header is already in *image_hdr and need only be checked.
* nil then the header is already in *image_hdr and need only be checked.
*/
{
int n, big= 0;
static int banner= 0;
struct exec *phdr= &ihdr->process;
if (procf == NULL) {
if (procf == nil) {
/* Header already present. */
n= phdr->a_hdrlen;
} else {
@@ -121,7 +122,7 @@ void read_header(int talk, char *proc, FILE *procf, struct image_header *ihdr)
}
/* Get the rest of the exec header. */
if (procf != NULL) {
if (procf != nil) {
bread(procf, proc, ((char *) phdr) + A_MINHDR,
phdr->a_hdrlen - A_MINHDR);
}
@@ -159,7 +160,7 @@ void read_header(int talk, char *proc, FILE *procf, struct image_header *ihdr)
}
}
void padimage(const char *image, FILE *imagef, int n)
void padimage(char *image, FILE *imagef, int n)
/* Add n zeros to image to pad it to a sector boundary. */
{
while (n > 0) {
@@ -205,16 +206,16 @@ void make_image(char *image, char **procv)
making_image= 1;
if ((imagef= fopen(image, "w")) == NULL) fatal(image);
if ((imagef= fopen(image, "w")) == nil) fatal(image);
for (procn= 0; (proc= *procv++) != NULL; procn++) {
for (procn= 0; (proc= *procv++) != nil; procn++) {
/* Remove the label from the file name. */
if ((file= strchr(proc, ':')) != NULL) file++; else file= proc;
if ((file= strchr(proc, ':')) != nil) file++; else file= proc;
/* Real files please, may need to seek. */
if (stat(file, &st) < 0
|| (errno= EISDIR, !S_ISREG(st.st_mode))
|| (procf= fopen(file, "r")) == NULL
|| (procf= fopen(file, "r")) == nil
) fatal(proc);
/* Read a.out header. */
@@ -295,7 +296,7 @@ void extract_image(char *image)
/* Size of the image. */
len= S_ISREG(st.st_mode) ? st.st_size : -1;
if ((imagef= fopen(image, "r")) == NULL) fatal(image);
if ((imagef= fopen(image, "r")) == nil) fatal(image);
while (len != 0) {
/* Extract a program, first sector is an extended header. */
@@ -306,9 +307,9 @@ void extract_image(char *image)
phdr= ihdr.process;
/* Check header. */
read_header(1, ihdr.name, NULL, &ihdr);
read_header(1, ihdr.name, nil, &ihdr);
if ((procf= fopen(ihdr.name, "w")) == NULL) fatal(ihdr.name);
if ((procf= fopen(ihdr.name, "w")) == nil) fatal(ihdr.name);
if (phdr.a_flags & A_PAL) {
/* A page aligned process contains a header in text. */
@@ -332,8 +333,8 @@ void extract_image(char *image)
}
}
static int rawfd; /* File descriptor to open device. */
static const char *rawdev; /* Name of device. */
int rawfd; /* File descriptor to open device. */
char *rawdev; /* Name of device. */
void readblock(off_t blk, char *buf, int block_size)
/* For rawfs, so that it can read blocks. */
@@ -350,7 +351,7 @@ void readblock(off_t blk, char *buf, int block_size)
}
}
void writeblock(off_t blk, const char *buf, int block_size)
void writeblock(off_t blk, char *buf, int block_size)
/* Add a function to write blocks for local use. */
{
if (lseek(rawfd, blk * block_size, SEEK_SET) < 0
@@ -377,7 +378,7 @@ int raw_install(char *file, off_t *start, off_t *len, int block_size)
devsize= -1;
if (ioctl(rawfd, DIOCGETP, &entry) == 0) devsize= cv64ul(entry.size);
if ((f= fopen(file, "r")) == NULL) fatal(file);
if ((f= fopen(file, "r")) == nil) fatal(file);
/* Copy sectors from file onto the boot device. */
sec= *start;
@@ -485,7 +486,7 @@ void make_bootable(enum howto how, char *device, char *bootblock,
*/
if (stat(bootcode, &st) < 0) fatal(bootcode);
if ((bootf= fopen(bootcode, "r")) == NULL) fatal(bootcode);
if ((bootf= fopen(bootcode, "r")) == nil) fatal(bootcode);
} else {
/* Boot code is present in the file system. */
r_stat(ino, &st);
@@ -495,16 +496,17 @@ void make_bootable(enum howto how, char *device, char *bootblock,
boothdr.a_magic[0]= !A_MAGIC0;
} else {
readblock(addr, buf, block_size);
memcpy(&boothdr, buf, sizeof(struct exec));
/* Must skip 16 bytes of 'boot' as that contains code. */
memcpy(&boothdr, buf + 16, sizeof(struct exec));
}
bootf= NULL;
bootf= nil;
dummy.process= boothdr;
}
/* See if it is an executable (read_header does the check). */
read_header(0, bootcode, bootf, &dummy);
boothdr= dummy.process;
if (bootf != NULL) fclose(bootf);
if (bootf != nil) fclose(bootf);
/* Get all the sector addresses of the secondary boot code. */
max_sector= (boothdr.a_hdrlen + boothdr.a_text
@@ -549,7 +551,7 @@ void make_bootable(enum howto how, char *device, char *bootblock,
/* Get the boot block and patch the pieces in. */
readblock(BOOTBLOCK, buf, BOOT_BLOCK_SIZE);
if ((bootf= fopen(bootblock, "r")) == NULL) fatal(bootblock);
if ((bootf= fopen(bootblock, "r")) == nil) fatal(bootblock);
read_header(0, bootblock, bootf, &dummy);
boothdr= dummy.process;
@@ -594,7 +596,7 @@ void make_bootable(enum howto how, char *device, char *bootblock,
* necessary.
*/
for (parmp= buf + SECTOR_SIZE; parmp < buf + 2*SECTOR_SIZE; parmp++) {
if (*imagev != NULL || (control(*parmp) && *parmp != '\n')) {
if (*imagev != nil || (control(*parmp) && *parmp != '\n')) {
/* Param sector must be initialized. */
memset(buf + SECTOR_SIZE, '\n', SECTOR_SIZE);
break;
@@ -627,10 +629,10 @@ void make_bootable(enum howto how, char *device, char *bootblock,
parmp+= strlen(parmp);
}
while ((labels= *imagev++) != NULL) {
while ((labels= *imagev++) != nil) {
/* Place each kernel image on the boot device. */
if ((image= strchr(labels, ':')) != NULL)
if ((image= strchr(labels, ':')) != nil)
*image++= 0;
else {
if (nolabel) {
@@ -640,23 +642,23 @@ void make_bootable(enum howto how, char *device, char *bootblock,
}
nolabel= 1;
image= labels;
labels= NULL;
labels= nil;
}
len= 0;
if (!raw_install(image, &pos, &len, block_size)) exit(1);
if (labels == NULL) {
if (labels == nil) {
/* Let this image be the default. */
sprintf(parmp, "image=%ld:%ld\n", pos-len, len);
parmp+= strlen(parmp);
}
while (labels != NULL) {
while (labels != nil) {
/* Image is prefixed by a comma separated list of
* labels. Define functions to select label and image.
*/
label= labels;
if ((labels= strchr(labels, ',')) != NULL) *labels++ = 0;
if ((labels= strchr(labels, ',')) != nil) *labels++ = 0;
sprintf(parmp,
"%s(%c){label=%s;image=%ld:%ld;echo %s kernel selected;menu}\n",
@@ -683,7 +685,7 @@ void make_bootable(enum howto how, char *device, char *bootblock,
}
}
static void install_master(const char *device, char *masterboot, char **guide)
void install_master(char *device, char *masterboot, char **guide)
/* Booting a hard disk is a two stage process: The master bootstrap in sector
* 0 loads the bootstrap from sector 0 of the active partition which in turn
* starts the operating system. This code installs such a master bootstrap
@@ -700,7 +702,7 @@ static void install_master(const char *device, char *masterboot, char **guide)
if ((rawfd= open(rawdev= device, O_RDWR)) < 0) fatal(device);
/* Open the master boot code. */
if ((masf= fopen(masterboot, "r")) == NULL) fatal(masterboot);
if ((masf= fopen(masterboot, "r")) == nil) fatal(masterboot);
/* See if the user is cloning a device. */
if (fstat(fileno(masf), &st) >=0 && S_ISBLK(st.st_mode))
@@ -723,10 +725,10 @@ static void install_master(const char *device, char *masterboot, char **guide)
memset(buf, 0, PARTPOS);
(void) bread(masf, masterboot, buf, size);
if (guide[0] != NULL) {
if (guide[0] != nil) {
/* Fixate partition to boot. */
const char *keys= guide[0];
const char *logical= guide[1];
char *keys= guide[0];
char *logical= guide[1];
size_t i;
int logfd;
u32_t offset;
@@ -753,7 +755,7 @@ static void install_master(const char *device, char *masterboot, char **guide)
size += i;
buf[size]= '\r';
if (logical != NULL) {
if (logical != nil) {
if ((logfd= open(logical, O_RDONLY)) < 0
|| ioctl(logfd, DIOCGETP, &geometry) < 0
) {
@@ -780,7 +782,7 @@ static void install_master(const char *device, char *masterboot, char **guide)
writeblock(BOOTBLOCK, buf, BOOT_BLOCK_SIZE);
}
static void usage(void)
void usage(void)
{
fprintf(stderr,
"Usage: installboot -i(mage) image kernel mm fs ... init\n"
@@ -791,7 +793,7 @@ static void usage(void)
exit(1);
}
static int isoption(const char *option, const char *test)
int isoption(char *option, char *test)
/* Check if the option argument is equals "test". Also accept -i as short
* for -image, and the special case -x for -extract.
*/

View File

@@ -21,7 +21,7 @@ int printf(const char *fmt, ...);
#define SEEK_END 2
/* Kernel printf requires a putk() function. */
void putk(int c)
int putk(int c)
{
char ch = c;
@@ -72,6 +72,7 @@ char *strerror(int err)
int main(int argc, char **argv)
{
int i;
static char buf[512];
unsigned long size, mul;
off_t offset;

View File

@@ -2,6 +2,7 @@
* 23 Dec 1991
* Based on readfs by Paul Polderman
*/
#define nil 0
#define _POSIX_SOURCE 1
#define _MINIX 1
#include <sys/types.h>
@@ -285,7 +286,7 @@ off_t r_vir2abs(off_t virblk)
return z;
}
ino_t r_lookup(Ino_t cwd, const char *path)
ino_t r_lookup(Ino_t cwd, char *path)
/* Translates a pathname to an inode number. This is just a nice utility
* function, it only needs r_stat and r_readdir.
*/

View File

@@ -17,7 +17,7 @@
* Return next directory entry or 0 if there are no more.
* Returns -1 and sets errno on error.
*
* ino_t r_lookup(ino_t cwd, const char *path);
* ino_t r_lookup(ino_t cwd, char *path);
* A utility function that translates a pathname to an
* inode number. It starts from directory "cwd" unless
* path starts with a '/', then from ROOT_INO.
@@ -30,19 +30,14 @@
* errors.
*/
#ifndef INC_RAWFS_H
#define INC_RAWFS_H
#define ROOT_INO ((ino_t) 1) /* Inode nr of root dir. */
extern off_t r_super(int *);
extern void r_stat(Ino_t file, struct stat *stp);
extern off_t r_vir2abs(off_t virblockno);
extern ino_t r_readdir(char *name);
extern ino_t r_lookup(Ino_t cwd, const char *path);
off_t r_super(int *);
void r_stat(Ino_t file, struct stat *stp);
off_t r_vir2abs(off_t virblockno);
ino_t r_readdir(char *name);
ino_t r_lookup(Ino_t cwd, char *path);
/*
* $PchId: rawfs.h,v 1.4 1996/04/19 08:16:36 philip Exp $
*/
#endif

View File

@@ -1,4 +0,0 @@
SCRIPTS= DESCRIBE.sh
MAN=
.include <minix.prog.mk>

View File

@@ -1,7 +0,0 @@
SCRIPTS= M.sh
BINDIR= /bin
MAN=
LINKS+= ${BINDIR}/M ${BINDIR}/U
.include <minix.prog.mk>

View File

@@ -1,4 +0,0 @@
SCRIPTS= MAKEDEV.sh
MAN=
.include <minix.prog.mk>

View File

@@ -1,44 +1,31 @@
# Makefile for commands.
.include <minix.own.mk>
MAKE = exec make -$(MAKEFLAGS)
BZIP2=bzip2-1.0.3
FLEX=flex-2.5.4
SUBDIR= aal add_route adduser advent arp ash at autil awk \
backup badblocks banner basename bigmake binpackage \
binpackages binsizes bzip2 bzip2recover cal calendar \
cat cawf cd cdiff cdprobe cgrep checkhier chmem \
chmod chown chroot ci cksum cleantmp clear cmp co \
comm compress cp crc cron crontab cut datasizes date \
dd de decomp16 DESCRIBE dev2name devsize df dhcpd \
dhrystone diff dirname dis88 du dumpcore easypack \
ed eject elle elvis env expand factor fgrep file \
find finger fingerd fix fold format fortune fsck \
fsck1 ftp101 ftpd200 getty gomoku grep head host \
hostaddr id ifconfig ifdef indent install \
intr ipcrm ipcs irdpd isoread join kill last leave \
lex life loadkeys loadramdisk logger login look lp \
lpd ls lspci M m4 mail make MAKEDEV makewhatis man \
mdb mesg mined mkdep mkdir mkdist mkfifo mkfs mknod \
mkproto modem mount mt netconf newroot nice nm nohup \
nonamed od packit packman passwd paste patch pax \
ping postinstall poweroff pr prep printf printroot \
profile progressbar proto pr_routes ps pwd pwdauth \
ramdisk rarpd rawspeed rcp rdate readall readclock \
readfs reboot remsync rev rget rlogin rlogind rmdir \
rotate rsh rshd sed service setup shar size \
sleep slip sort spell split srccrc stat strings strip \
stty su sum svclog swapfs swifi sync synctree sysenv \
syslogd tail talk talkd tcpd tcpdp tcpstat tee telnet \
telnetd term termcap tget time tinyhalt top touch tr \
truncate tsort ttt tty udpstat umount uname unexpand \
uniq unstack update urlget uud uue version vol wc \
whatis whereis which who whoami write writeisofs \
xargs yacc yap yes zdump zic zmodem
SMALLPROGRAMS=`arch` aal advent ash autil awk byacc cawf cron de dhcpd dis88 elle elvis ftp101 ftpd200 ibm indent m4 make mdb mined patch pax profile ps reboot rlogind scripts sh simple syslogd talk talkd telnet telnetd urlget yap zoneinfo
usage:
@echo "Usage: make all # Compile all commands" >&2
@echo " make install # Install the result (run as bin!)" >&2
@echo " make clean # Delete .o files and other junk" >&2
all:
cd zmodem && make
cd $(BZIP2) && /bin/sh build build
set -e; for p in $(SMALLPROGRAMS); do ( cd $$p && make all ); done
install:
set -e; for p in $(SMALLPROGRAMS); do ( cd $$p && make install ); done
cd zmodem && make install
cd $(BZIP2) && make install
cd $(FLEX) && sh build
clean::
cd $(BZIP2) && make clean
cd zmodem && make clean
if [ -f $(FLEX)/Makefile ]; then cd $(FLEX) && make distclean ; fi
for p in $(SMALLPROGRAMS); do ( cd $$p && make clean ); done
.if ${ARCH} == "i386"
SUBDIR+= atnormalize dosread fdisk loadfont \
mixer autopart part partition playwave postmort \
recwave repartition screendump
SUBDIR+= acd asmconv gas2ack
.endif
.include <minix.subdir.mk>

View File

@@ -1,2 +0,0 @@
CPPFLAGS+= -D_MINIX -D_POSIX_SOURCE
BINDIR?=/usr/bin

View File

@@ -1,12 +1,56 @@
# Makefile for aal
PROG= aal
SRCS= archiver.c print.c rd.c rd_arhdr.c rd_unsig2.c sprint.c \
wr_arhdr.c wr_bytes.c wr_int2.c wr_long.c wr_ranlib.c \
format.c rd_bytes.c system.c write.c long2str.c
CPPFLAGS+= -I${.CURDIR} -DAAL -DSTB -DNDEBUG -DDISTRIBUTION
CC=exec cc
CFLAGS=-I. -wo -DAAL -DSTB -DNDEBUG -DDISTRIBUTION -D_POSIX_SOURCE -D_MINIX
LDFLAGS=-i
LINKS+= ${BINDIR}/aal ${BINDIR}/ar
MAN=
all: aal
.include <minix.prog.mk>
OFILES= archiver.o \
print.o \
rd.o \
rd_arhdr.o \
rd_unsig2.o \
sprint.o \
wr_arhdr.o \
wr_bytes.o \
wr_int2.o \
wr_long.o \
wr_ranlib.o \
format.o \
rd_bytes.o \
system.o \
write.o \
long2str.o
aal: $(OFILES)
$(CC) $(LDFLAGS) -o aal $(OFILES)
install -S 512k $@
install: /usr/bin/aal /usr/bin/ar
/usr/bin/aal: aal
install -cs -o bin aal $@
/usr/bin/ar: /usr/bin/aal
install -l $? $@
archiver.o:
print.o:
rd.o:
rd_arhdr.o:
rd_unsig2.o:
sprint.o:
wr_arhdr.o:
wr_bytes.o:
wr_int2.o:
wr_long.o:
wr_ranlib.o:
format.o:
rd_bytes.o:
system.o:
write.o:
long2str.o:
clean:
rm -f *.o core *.bak aal

View File

@@ -25,7 +25,6 @@ static char RcsId[] = "$Header$";
#endif
*/
#include <stdlib.h>
#include <sys/types.h>
#include <sys/stat.h>
#ifndef S_IREAD
@@ -48,6 +47,7 @@ struct ranlib *tab;
unsigned int tnum = 0;
char *tstrtab;
unsigned int tssiz = 0;
char *malloc(), *realloc(), *strcpy(), *strncpy();
long time();
unsigned int tabsz, strtabsz;
#else
@@ -68,6 +68,10 @@ typedef char BOOL;
#define MEMBER struct ar_hdr
#define NIL_PTR ((char *) 0)
#define NIL_MEM ((MEMBER *) 0)
#define NIL_LONG ((long *) 0)
#define IO_SIZE (10 * 1024)
#define equal(str1, str2) (!strncmp((str1), (str2), 14))
@@ -132,14 +136,14 @@ char *basename(path)
char *path;
{
register char *ptr = path;
register char *last = NULL;
register char *last = NIL_PTR;
while (*ptr != '\0') {
if (*ptr == '/')
last = ptr;
ptr++;
}
if (last == NULL)
if (last == NIL_PTR)
return path;
if (*(last + 1) == '\0') {
*last = '\0';
@@ -298,7 +302,7 @@ get_member()
again:
if (rd_arhdr(ar_fd, &member) == 0)
return NULL;
return NIL_MEM;
if (member.ar_size < 0) {
error(TRUE, "archive has member with negative size\n");
}
@@ -328,7 +332,7 @@ register char *argv[];
#endif
)
temp_fd = open_archive(temp_arch, CREATE);
while ((member = get_member()) != NULL) {
while ((member = get_member()) != NIL_MEM) {
if (argc > 3) {
for (i = 3; i < argc; i++) {
if (equal(basename(argv[i]), member->ar_name))
@@ -793,4 +797,4 @@ enter_name(namep)
}
tnum++;
}
#endif /* AAL */
#endif AAL

3
commands/aal/build Executable file
View File

@@ -0,0 +1,3 @@
#!/bin/sh
make clean
make && make install

View File

@@ -12,7 +12,7 @@
# define ACKM "minix"
/* size of local machine, either 0 (for 16 bit address space), or 1 */
# undef BIGMACHINE
# undef BIGMACHINE 1
/* operating system, SYS_5, V7, BSD4_1 or BSD4_2; Do NOT delete the comment
in the next line! */

View File

@@ -44,4 +44,4 @@ extern File _sys_ftab[];
/* system's idea of block */
#define BUFSIZ 1024
#endif /* __SYSTEM_INCLUDED__ */
#endif __SYSTEM_INCLUDED__

View File

@@ -1,13 +0,0 @@
# Makefile for acd
.include <minix.own.mk>
PROG= acd
CPPFLAGS+= -DARCH=\"`arch`\" -DDESCR=\"/usr/lib/descr\"
LINKS+= ${BINDIR}/acd ${BINDIR}/cc
FILESDIR= /usr/lib
FILES= acd.descr
FILESNAME= descr
MAN=
.include <minix.prog.mk>

View File

@@ -1,6 +0,0 @@
PROG= add_route
MAN=
LINKS+= ${BINDIR}/add_route ${BINDIR}/del_route
.include <minix.prog.mk>

View File

@@ -1,4 +0,0 @@
SCRIPTS= adduser.sh
MAN=
.include <minix.prog.mk>

View File

@@ -1,28 +1,63 @@
# Makefile for advent
PROG= advent
SRCS= advent.c database.c english.c initial.c itverb.c score.c \
travel.c turn.c utility.c verb.c vocab.c
# Where to put the adventure text files, and the binary executable.
# Need the trailing "/"s.
TEXTDIR = /usr/lib/advent/
BINDIR = /usr/bin
# Where to put the adventure text files
# Need the trailing "/" on TEXTDIR
TEXTDIR= /usr/lib/advent/
FILESDIR= ${TEXTDIR}
DATFILES= advent1.dat advent2.dat advent3.dat advent4.dat
FILES= ${DATFILES}
MAN=
# Flags you may want to add to CFLAGS:
# -DHAS_STDC=0 or 1 We have Standard C. Default=1 iff __STDC__ is nonzero.
database.o: advtext.h
CC = exec cc
CFLAGS = -D_POSIX_SOURCE
LDFLAGS = -i
OBJS = advent.o database.o english.o initial.o itverb.o score.o\
travel.o turn.o utility.o verb.o vocab.o
DAT = advent1.dat advent2.dat advent3.dat advent4.dat
INSTDAT = $(TEXTDIR)advent1.dat $(TEXTDIR)advent2.dat \
$(TEXTDIR)advent3.dat $(TEXTDIR)advent4.dat
all: $(DAT) advent
install: $(TEXTDIR) $(INSTDAT) $(BINDIR)/advent
$(TEXTDIR):
install -d -o bin $(TEXTDIR)
$(TEXTDIR)advent1.dat: advent1.dat
install -c -o bin $? $@
$(TEXTDIR)advent2.dat: advent2.dat
install -c -o bin $? $@
$(TEXTDIR)advent3.dat: advent3.dat
install -c -o bin $? $@
$(TEXTDIR)advent4.dat: advent4.dat
install -c -o bin $? $@
$(BINDIR)/advent: advent
install -cs -o bin $? $@
advent: $(OBJS)
$(CC) $(LDFLAGS) -o advent $(OBJS)
setup: setup.c advent.h
${CC} ${CPPFLAGS} ${LDFLAGS} -o setup setup.c
$(CC) $(CFLAGS) $(LDFLAGS) -o setup setup.c
advtext.h advent1.dat advent2.dat advent3.dat advent4.dat: \
setup advent1.txt advent2.txt advent3.txt advent4.txt
./setup
CPPFLAGS.advent.c= -DTEXTDIR='"${TEXTDIR}"'
advent.o: advent.h advdec.h advent.c
$(CC) -c $(CFLAGS) -DTEXTDIR='"$(TEXTDIR)"' advent.c
CLEANFILES+= ${DATFILES} advtext.h setup
database.o: advent.h advdec.h advtext.h
travel.o: advent.h advdec.h advcave.h
initial.o english.o itverb.o score.o turn.o utility.o\
verb.o vocab.o: advent.h advdec.h
.include <minix.prog.mk>
clean:
@rm -f *.o *.BAK *.dat advtext.h core advent setup

3
commands/advent/build Executable file
View File

@@ -0,0 +1,3 @@
#!/bin/sh
make clean
make && make install

View File

@@ -1,5 +0,0 @@
PROG= arp
BINMODE= 4755
MAN=
.include <minix.prog.mk>

View File

@@ -1,34 +1,33 @@
# Makefile for ash.
.include <minix.own.mk>
SRCS= alias.c builtins.c cd.c error.c eval.c exec.c expand.c histedit.c \
input.c \
jobs.c mail.c main.c memalloc.c miscbltin.c mystring.c nodes.c \
options.c parser.c redir.c setmode.c show.c signames.c syntax.c \
trap.c \
output.c var.c
YHEADER=1
PROG= sh
OBJS= alias.o builtins.o cd.o error.o eval.o exec.o expand.o histedit.o \
input.o \
jobs.o mail.o main.o memalloc.o miscbltin.o mystring.o nodes.o \
options.o parser.o redir.o setmode.o show.o signames.o syntax.o \
trap.o \
output.o var.o init.o \
bltin/echo.o bltin/expr.o bltin/operators.o bltin/regexp.o \
arith.o arith_lex.o
SHSRCS= alias.c arith.y arith_lex.l cd.c echo.c error.c eval.c exec.c expand.c \
histedit.c input.c jobs.c mail.c main.c memalloc.c miscbltin.c \
mystring.c options.c output.c parser.c redir.c show.c \
trap.c var.c setmode.c expr.c regexp.c
GENSRCS= builtins.c init.c nodes.c syntax.c operators.c signames.c
GENHDRS= builtins.h nodes.h syntax.h token.h operators.h signames.h
SRCS= ${SHSRCS} ${GENSRCS}
DPSRCS+=${GENHDRS}
BINDIR= /bin
MAN=
DPADD+= ${LIBL} ${LIBEDIT}
LDADD+= -ll -ledit
LFLAGS= -8 # 8-bit lex scanner for arithmetic
YFLAGS= -d
# The .depend file can get references to these temporary files
.OPTIONAL: lex.yy.c y.tab.c
LEX=flex
YACC=/usr/bin/yacc
.c.o:
$(CC) $(CFLAGS) -c $< -o $@
# Enable this line to disable command line editing
#EDIT=-DNO_HISTORY
# Enable this line to use the editline library instead of libedit
EDIT=-DEDITLINE
EDITLIB=-ledit
FLEXLIB=-lfl
# Enable this line if your system does not have a <paths.h>
NO_PATHS_H=-DNO_PATHS_H
@@ -37,50 +36,88 @@ NO_PATHS_H=-DNO_PATHS_H
NO_JOBS=-DJOBS=0
MKB_NO_JOBS=-j
CPPFLAGS+=-DSHELL -I. -I${.CURDIR}
CPPFLAGS+=${EDIT} ${NO_PATHS_H} ${NO_JOBS}
CPPFLAGS= -DSHELL -I. -D_MINIX $(EDIT) $(NO_PATHS_H) $(NO_JOBS)
CFLAGS= $(OPT) $(CPPFLAGS)
LIBS= $(EDITLIB) $(FLEXLIB)
.PATH: ${.CURDIR}/bltin
CLEANFILES= $(OBJS) \
arith.c arith_y.h arith_lex.c builtins.c builtins.h init.c \
mkinit mknodes mksignames mksyntax \
nodes.c nodes.h signames.c signames.h syntax.c syntax.h token.h \
bltin/operators.h bltin/operators.c
CLEANFILES+= mkinit mkinit.o mknodes mknodes.o \
mksyntax mksyntax.o mksignames mksignames.o
CLEANFILES+= ${GENSRCS} ${GENHDRS} y.tab.h
all: sh
build-tools: mkinit mknodes mksyntax mksignames
sh: $(OBJS)
$(CC) $(CFLAGS) -fnone -o sh $(OBJS) $(LIBS)
install -S 136k sh
.ORDER: builtins.c builtins.h
builtins.c builtins.h: mkbuiltins builtins.def shell.h
cd ${.CURDIR}; sh mkbuiltins ${MKB_NO_JOBS} ${.OBJDIR} shell.h builtins.def
install: /usr/bin/ash /usr/bin/sh /bin/sh /bin/bigsh
init.c: mkinit alias.c eval.c exec.c input.c jobs.c options.c parser.c \
redir.c trap.c var.c
./mkinit ${.ALLSRC:S/^mkinit$//}
/usr/bin/ash: sh
install -cs -o bin $< $@
mkinit: mkinit.o
mknodes: mknodes.o
mksyntax: mksyntax.o
mksignames: mksignames.o
/usr/bin/sh: /usr/bin/ash
install -l $< $@
/bin/sh: /usr/bin/ash
install -lcs $< $@
/bin/bigsh: /usr/bin/ash
install -S 6600k -lcs $< $@
clean:
rm -f $(CLEANFILES) sh core
parser.o: token.def
token.def: mktokens
sh mktokens
arith.c: arith.y
$(YACC) -d $<
mv y.tab.c $@
mv y.tab.h arith_y.h
arith_lex.c: arith_lex.l
builtins.c builtins.h: builtins.def shell.h
sh mkbuiltins $(MKB_NO_JOBS) . shell.h builtins.def
init.c: mkinit $(SRCS)
./mkinit $(SRCS)
mkinit: mkinit.c
$(CC) $(CFLAGS) mkinit.c -o $@
.ORDER: nodes.c nodes.h
nodes.c nodes.h: mknodes nodetypes nodes.c.pat
./mknodes ${.CURDIR}/nodetypes ${.CURDIR}/nodes.c.pat
./mknodes nodetypes nodes.c.pat
.ORDER: syntax.c syntax.h
syntax.c syntax.h: mksyntax
./mksyntax
mknodes: mknodes.c
$(CC) $(CFLAGS) mknodes.c -o $@
token.h: mktokens
sh ${.CURDIR}/mktokens
.ORDER: signames.c signames.h
signames.c signames.h: mksignames
./mksignames
.ORDER: operators.c operators.h
operators.c operators.h: mkexpr unary_op binary_op
sh bltin/mkexpr bltin/unary_op bltin/binary_op
mksignames: mksignames.c
$(CC) $(CFLAGS) mksignames.c -o $@
arith.h: arith.c
arith.c: arith.y
syntax.c syntax.h: mksyntax
./mksyntax
.include <minix.prog.mk>
mksyntax: mksyntax.c parser.h
$(CC) $(CFLAGS) mksyntax.c -o $@
bltin/operators.h: bltin/mkexpr bltin/unary_op bltin/binary_op
cd bltin && sh mkexpr unary_op binary_op
# Dependencies you say? This will have to do.
$(OBJS): error.h eval.h exec.h expand.h init.h input.h \
jobs.h machdep.h mail.h main.h memalloc.h mystring.h options.h \
output.h parser.h redir.h shell.h trap.h var.h \
builtins.h nodes.h signames.h syntax.h
bltin/expr.o bltin/operators.o: bltin/operators.h
#
# $PchId: Makefile,v 1.4 2006/05/22 12:40:46 philip Exp $

View File

@@ -49,18 +49,19 @@ __FBSDID("$FreeBSD: src/bin/sh/alias.c,v 1.18 2004/04/06 20:06:51 markm Exp $");
#include "mystring.h"
#include "alias.h"
#include "options.h" /* XXX for argptr (should remove?) */
#include "builtins.h"
#define ATABSIZE 39
STATIC struct alias *atab[ATABSIZE];
STATIC void setalias(const char *, const char *);
STATIC int unalias(const char *);
STATIC struct alias **hashalias(const char *);
STATIC void setalias(char *, char *);
STATIC int unalias(char *);
STATIC struct alias **hashalias(char *);
STATIC
void
setalias(const char *name, const char *val)
setalias(char *name, char *val)
{
struct alias *ap, **app;
@@ -113,7 +114,7 @@ setalias(const char *name, const char *val)
}
STATIC int
unalias(const char *name)
unalias(char *name)
{
struct alias *ap, **app;
@@ -174,7 +175,7 @@ rmaliases(void)
}
struct alias *
lookupalias(const char *name, int check)
lookupalias(char *name, int check)
{
struct alias *ap = *hashalias(name);
@@ -249,7 +250,7 @@ unaliascmd(int argc __unused, char **argv __unused)
}
STATIC struct alias **
hashalias(const char *p)
hashalias(char *p)
{
unsigned int hashval;

View File

@@ -42,7 +42,7 @@ struct alias {
int flag;
};
struct alias *lookupalias(const char *, int);
struct alias *lookupalias(char *, int);
int aliascmd(int, char **);
int unaliascmd(int, char **);
void rmaliases(void);

View File

@@ -1,6 +1,6 @@
/*
* Copyright (c) 1989, 1993
* The Regents of the University of California. All rights reserved.
/*-
* Copyright (c) 1995
* The Regents of the University of California. All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
* modification, are permitted provided that the following conditions
@@ -10,7 +10,7 @@
* 2. Redistributions in binary form must reproduce the above copyright
* notice, this list of conditions and the following disclaimer in the
* documentation and/or other materials provided with the distribution.
* 3. Neither the name of the University nor the names of its contributors
* 4. Neither the name of the University nor the names of its contributors
* may be used to endorse or promote products derived from this software
* without specific prior written permission.
*
@@ -25,27 +25,15 @@
* LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
* OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
* SUCH DAMAGE.
*
* @(#)arith.h 1.1 (Berkeley) 5/4/95
* $FreeBSD: src/bin/sh/arith.h,v 1.9 2004/04/06 20:06:51 markm Exp $
*/
#include <assert.h>
#include <wchar.h>
int arith(char *);
int arith_assign(char *, arith_t);
int expcmd(int, char **);
int
wcsncmp(const wchar_t *s1, const wchar_t *s2, size_t n)
{
assert(s1 != NULL);
assert(s2 != NULL);
if (n == 0)
return (0);
do {
if (*s1 != *s2++) {
/* XXX assumes wchar_t = int */
return (*s1 - *--s2);
}
if (*s1++ == 0)
break;
} while (--n != 0);
return (0);
}
/*
* $PchId: arith.h,v 1.3 2006/03/31 11:25:25 philip Exp $
*/

View File

@@ -42,11 +42,12 @@ __FBSDID("$FreeBSD: src/bin/sh/arith.y,v 1.19 2004/05/24 10:11:31 stefanf Exp $"
*/
#include <limits.h>
#include <stdlib.h>
#include <stdio.h>
#include "shell.h"
#include "expand.h"
#include "arith.h"
#include "arith_lex.h"
#include "var.h"
%}
%union {
@@ -260,6 +261,7 @@ expr:
#include "error.h"
#include "output.h"
#include "memalloc.h"
#include "builtins.h"
#define lstrlen(var) (3 + (2 + CHAR_BIT * sizeof((var))) / 3)
@@ -358,3 +360,7 @@ error(char *s)
exit(1);
}
#endif
/*
* $PchId: arith.y,v 1.6 2006/05/22 12:41:47 philip Exp $
*/

View File

@@ -44,7 +44,8 @@ __FBSDID("$FreeBSD: src/bin/sh/arith_lex.l,v 1.22 2004/04/06 20:06:51 markm Exp
#include <string.h>
#include "shell.h"
#include "arith.h"
#include "arith_lex.h"
#include "arith_y.h"
#include "error.h"
#include "memalloc.h"
#include "var.h"
@@ -131,3 +132,7 @@ arith_lex_reset(void)
{
YY_NEW_FILE;
}
/*
* $PchId: arith_lex.l,v 1.5 2006/04/10 14:35:29 philip Exp $
*/

View File

@@ -67,11 +67,11 @@ __FBSDID("$FreeBSD: src/bin/sh/cd.c,v 1.34 2004/04/06 20:06:51 markm Exp $");
#include "show.h"
#include "cd.h"
STATIC int cdlogical(const char *);
STATIC int cdphysical(const char *);
STATIC int docd(const char *, int, int);
STATIC int cdlogical(char *);
STATIC int cdphysical(char *);
STATIC int docd(char *, int, int);
STATIC char *getcomponent(void);
STATIC int updatepwd(const char *);
STATIC int updatepwd(char *);
STATIC char *curdir = NULL; /* current working directory */
STATIC char *prevdir; /* previous working directory */
@@ -145,7 +145,7 @@ cdcmd(int argc, char **argv)
* directory name if "print" is nonzero.
*/
STATIC int
docd(const char *dest, int print, int phys)
docd(char *dest, int print, int phys)
{
TRACE(("docd(\"%s\", %d, %d) called\n", dest, print, phys));
@@ -161,7 +161,7 @@ docd(const char *dest, int print, int phys)
}
STATIC int
cdlogical(const char *dest)
cdlogical(char *dest)
{
char *p;
char *q;
@@ -212,7 +212,7 @@ cdlogical(const char *dest)
}
STATIC int
cdphysical(const char *dest)
cdphysical(char *dest)
{
INTOFF;
@@ -255,7 +255,7 @@ getcomponent(void)
* that the current directory has changed.
*/
STATIC int
updatepwd(const char *dir)
updatepwd(char *dir)
{
char *new;
char *p;

View File

@@ -49,10 +49,13 @@ __FBSDID("$FreeBSD: src/bin/sh/error.c,v 1.25 2004/04/06 20:06:51 markm Exp $");
#include "options.h"
#include "output.h"
#include "error.h"
#include "nodes.h" /* show.h needs nodes.h */
#include "show.h"
#include "trap.h"
#include <signal.h>
#include <stdlib.h>
#include <unistd.h>
#include <errno.h>
#include <sys/types.h>

View File

@@ -62,13 +62,6 @@ void rmescapes(char *);
int casematch(union node *, char *);
int wordexpcmd(int, char **);
/* From arith.y */
int arith(char *);
int arith_assign(char *, arith_t);
int expcmd(int , char **);
void arith_lex_reset(void);
/*
* $PchId: expand.h,v 1.4 2006/03/30 14:50:52 philip Exp $
*/

View File

@@ -83,7 +83,7 @@ ckrealloc(pointer p, int nbytes)
*/
char *
savestr(const char *s)
savestr(char *s)
{
char *p;

View File

@@ -48,7 +48,7 @@ extern int herefd;
pointer ckmalloc(int);
pointer ckrealloc(pointer, int);
char *savestr(const char *);
char *savestr(char *);
pointer stalloc(int);
void stunalloc(pointer);
void setstackmark(struct stackmark *);

View File

@@ -1,8 +0,0 @@
# Makefile for asmconv.
PROG= asmconv
SRCS= asm86.c asmconv.c parse_ack.c parse_gnu.c parse_bas.c \
tokenize.c emit_ack.c emit_gnu.c
MAN=
.include <minix.prog.mk>

View File

@@ -1,5 +0,0 @@
PROG= at
BINMODE= 4755
MAN=
.include <minix.prog.mk>

View File

@@ -1,4 +0,0 @@
PROG= atnormalize
MAN=
.include <minix.prog.mk>

View File

@@ -1,10 +1,26 @@
# Makefile for commands/autil
PROGS= anm asize
SRCS.anm= anm.c rd.c rd_arhdr.c rd_bytes.c rd_unsig2.c
SRCS.asize= asize.c
CPPFLAGS+= -I${.CURDIR}
MAN.anm=
MAN.asize=
CC = exec cc
CFLAGS = -I. -D_MINIX -D_POSIX_SOURCE -wo
CCLD = $(CC) -i $(CFLAGS)
.include <minix.prog.mk>
all: anm asize
anm: anm.c rd.c rd_arhdr.c rd_bytes.c rd_unsig2.c
$(CCLD) -o $@ $?
install -S 32kw $@
asize: asize.c
$(CCLD) -o $@ $?
install -S 4kw $@
install: /usr/bin/anm /usr/bin/asize
/usr/bin/anm: anm
install -cs -o bin $? $@
/usr/bin/asize: asize
install -cs -o bin $? $@
clean:
rm -f anm asize core

View File

@@ -2,6 +2,7 @@
* (c) copyright 1987 by the Vrije Universiteit, Amsterdam, The Netherlands.
* See the copyright notice in the ACK home directory, in the file "Copyright".
*/
/* $Id$ */
/*
** print symbol tables for
** ACK object files

View File

@@ -1,3 +1,4 @@
/* $Id$ */
/*
* (c) copyright 1987 by the Vrije Universiteit, Amsterdam, The Netherlands.
* See the copyright notice in the ACK home directory, in the file "Copyright".

3
commands/autil/build Executable file
View File

@@ -0,0 +1,3 @@
#!/bin/sh
make clean
make && make install

View File

@@ -1,3 +1,4 @@
/* $Id$ */
/*
* (c) copyright 1987 by the Vrije Universiteit, Amsterdam, The Netherlands.
* See the copyright notice in the ACK home directory, in the file "Copyright".

View File

@@ -1,3 +1,4 @@
/* $Id$ */
/*
* (c) copyright 1987 by the Vrije Universiteit, Amsterdam, The Netherlands.
* See the copyright notice in the ACK home directory, in the file "Copyright".

View File

@@ -2,6 +2,7 @@
* (c) copyright 1987 by the Vrije Universiteit, Amsterdam, The Netherlands.
* See the copyright notice in the ACK home directory, in the file "Copyright".
*/
/* $Id$ */
#ifndef __RANLIB_H_INCLUDED
#define __RANLIB_H_INCLUDED

View File

@@ -1,3 +1,4 @@
/* $Id$ */
/*
* (c) copyright 1987 by the Vrije Universiteit, Amsterdam, The Netherlands.
* See the copyright notice in the ACK home directory, in the file "Copyright".

View File

@@ -1,3 +1,4 @@
/* $Id$ */
/*
* (c) copyright 1987 by the Vrije Universiteit, Amsterdam, The Netherlands.
* See the copyright notice in the ACK home directory, in the file "Copyright".

View File

@@ -1,3 +1,4 @@
/* $Id$ */
/*
* (c) copyright 1987 by the Vrije Universiteit, Amsterdam, The Netherlands.
* See the copyright notice in the ACK home directory, in the file "Copyright".

View File

@@ -1,3 +1,4 @@
/* $Id$ */
/*
* (c) copyright 1987 by the Vrije Universiteit, Amsterdam, The Netherlands.
* See the copyright notice in the ACK home directory, in the file "Copyright".

View File

@@ -1,4 +0,0 @@
PROG= autopart
MAN=
.include <minix.prog.mk>

View File

@@ -1,961 +0,0 @@
/****************************************************************
Copyright (C) Lucent Technologies 1997
All Rights Reserved
Permission to use, copy, modify, and distribute this software and
its documentation for any purpose and without fee is hereby
granted, provided that the above copyright notice appear in all
copies and that both that the copyright notice and this
permission notice and warranty disclaimer appear in supporting
documentation, and that the name Lucent Technologies or any of
its entities not be used in advertising or publicity pertaining
to distribution of the software without specific, written prior
permission.
LUCENT DISCLAIMS ALL WARRANTIES WITH REGARD TO THIS SOFTWARE,
INCLUDING ALL IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS.
IN NO EVENT SHALL LUCENT OR ANY OF ITS ENTITIES BE LIABLE FOR ANY
SPECIAL, INDIRECT OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES
WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER
IN AN ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION,
ARISING OUT OF OR IN CONNECTION WITH THE USE OR PERFORMANCE OF
THIS SOFTWARE.
****************************************************************/
This file lists all bug fixes, changes, etc., made since the AWK book
was sent to the printers in August, 1987.
Feb 8, 2010:
i give up. replaced isblank with isspace in b.c; there are
no consistent header files.
Nov 26, 2009:
fixed a long-standing issue with when FS takes effect. a
change to FS is now noticed immediately for subsequent splits.
changed the name getline() to awkgetline() to avoid yet another
name conflict somewhere.
Feb 11, 2009:
temporarily for now defined HAS_ISBLANK, since that seems to
be the best way through the thicket. isblank arrived in C99,
but seems to be arriving at different systems at different
times.
Oct 8, 2008:
fixed typo in b.c that set tmpvec wrongly. no one had ever
run into the problem, apparently. thanks to alistair crooks.
Oct 23, 2007:
minor fix in lib.c: increase inputFS to 100, change malloc
for fields to n+1.
fixed memory fault caused by out of order test in setsval.
thanks to david o'brien, freebsd, for both fixes.
May 1, 2007:
fiddle in makefile to fix for BSD make; thanks to igor sobrado.
Mar 31, 2007:
fixed some null pointer refs calling adjbuf.
Feb 21, 2007:
fixed a bug in matching the null RE in sub and gsub. thanks to al aho
who actually did the fix (in b.c), and to wolfgang seeberg for finding
it and providing a very compact test case.
fixed quotation in b.c; thanks to Hal Pratt and the Princeton Dante
Project.
removed some no-effect asserts in run.c.
fiddled maketab.c to not complain about bison-generated values.
removed the obsolete -V argument; fixed --version to print the
version and exit.
fixed wording and an outright error in the usage message; thanks to igor
sobrado and jason mcintyre.
fixed a bug in -d that caused core dump if no program followed.
Jan 1, 2007:
dropped mac.code from makefile; there are few non-MacOSX
mac's these days.
Jan 17, 2006:
system() not flagged as unsafe in the unadvertised -safe option.
found it while enhancing tests before shipping the ;login: article.
practice what you preach.
removed the 9-years-obsolete -mr and -mf flags.
added -version and --version options.
core dump on linux with BEGIN {nextfile}, now fixed.
removed some #ifdef's in run.c and lex.c that appear to no
longer be necessary.
Apr 24, 2005:
modified lib.c so that values of $0 et al are preserved in the END
block, apparently as required by posix. thanks to havard eidnes
for the report and code.
Jan 14, 2005:
fixed infinite loop in parsing, originally found by brian tsang.
thanks to arnold robbins for a suggestion that started me
rethinking it.
Dec 31, 2004:
prevent overflow of -f array in main, head off potential error in
call of SYNTAX(), test malloc return in lib.c, all with thanks to
todd miller.
Dec 22, 2004:
cranked up size of NCHARS; coverity thinks it can be overrun with
smaller size, and i think that's right. added some assertions to b.c
to catch places where it might overrun. the RE code is still fragile.
Dec 5, 2004:
fixed a couple of overflow problems with ridiculous field numbers:
e.g., print $(2^32-1). thanks to ruslan ermilov, giorgos keramidas
and david o'brien at freebsd.org for patches. this really should
be re-done from scratch.
Nov 21, 2004:
fixed another 25-year-old RE bug, in split. it's another failure
to (re-)initialize. thanks to steve fisher for spotting this and
providing a good test case.
Nov 22, 2003:
fixed a bug in regular expressions that dates (so help me) from 1977;
it's been there from the beginning. an anchored longest match that
was longer than the number of states triggered a failure to initialize
the machine properly. many thanks to moinak ghosh for not only finding
this one but for providing a fix, in some of the most mysterious
code known to man.
fixed a storage leak in call() that appears to have been there since
1983 or so -- a function without an explicit return that assigns a
string to a parameter leaked a Cell. thanks to moinak ghosh for
spotting this very subtle one.
Jul 31, 2003:
fixed, thanks to andrey chernov and ruslan ermilov, a bug in lex.c
that mis-handled the character 255 in input. (it was being compared
to EOF with a signed comparison.)
Jul 29, 2003:
fixed (i think) the long-standing botch that included the beginning of
line state ^ for RE's in the set of valid characters; this led to a
variety of odd problems, including failure to properly match certain
regular expressions in non-US locales. thanks to ruslan for keeping
at this one.
Jul 28, 2003:
n-th try at getting internationalization right, with thanks to volker
kiefel, arnold robbins and ruslan ermilov for advice, though they
should not be blamed for the outcome. according to posix, "." is the
radix character in programs and command line arguments regardless of
the locale; otherwise, the locale should prevail for input and output
of numbers. so it's intended to work that way.
i have rescinded the attempt to use strcoll in expanding shorthands in
regular expressions (cclenter). its properties are much too
surprising; for example [a-c] matches aAbBc in locale en_US but abBcC
in locale fr_CA. i can see how this might arise by implementation
but i cannot explain it to a human user. (this behavior can be seen
in gawk as well; we're leaning on the same library.)
the issue appears to be that strcoll is meant for sorting, where
merging upper and lower case may make sense (though note that unix
sort does not do this by default either). it is not appropriate
for regular expressions, where the goal is to match specific
patterns of characters. in any case, the notations [:lower:], etc.,
are available in awk, and they are more likely to work correctly in
most locales.
a moratorium is hereby declared on internationalization changes.
i apologize to friends and colleagues in other parts of the world.
i would truly like to get this "right", but i don't know what
that is, and i do not want to keep making changes until it's clear.
Jul 4, 2003:
fixed bug that permitted non-terminated RE, as in "awk /x".
Jun 1, 2003:
subtle change to split: if source is empty, number of elems
is always 0 and the array is not set.
Mar 21, 2003:
added some parens to isblank, in another attempt to make things
internationally portable.
Mar 14, 2003:
the internationalization changes, somewhat modified, are now
reinstated. in theory awk will now do character comparisons
and case conversions in national language, but "." will always
be the decimal point separator on input and output regardless
of national language. isblank(){} has an #ifndef.
this no longer compiles on windows: LC_MESSAGES isn't defined
in vc6++.
fixed subtle behavior in field and record splitting: if FS is
a single character and RS is not empty, \n is NOT a separator.
this tortuous reading is found in the awk book; behavior now
matches gawk and mawk.
Dec 13, 2002:
for the moment, the internationalization changes of nov 29 are
rolled back -- programs like x = 1.2 don't work in some locales,
because the parser is expecting x = 1,2. until i understand this
better, this will have to wait.
Nov 29, 2002:
modified b.c (with tiny changes in main and run) to support
locales, using strcoll and iswhatever tests for posix character
classes. thanks to ruslan ermilov (ru@freebsd.org) for code.
the function isblank doesn't seem to have propagated to any
header file near me, so it's there explicitly. not properly
tested on non-ascii character sets by me.
Jun 28, 2002:
modified run/format() and tran/getsval() to do a slightly better
job on using OFMT for output from print and CONVFMT for other
number->string conversions, as promised by posix and done by
gawk and mawk. there are still places where it doesn't work
right if CONVFMT is changed; by then the STR attribute of the
variable has been irrevocably set. thanks to arnold robbins for
code and examples.
fixed subtle bug in format that could get core dump. thanks to
Jaromir Dolecek <jdolecek@NetBSD.org> for finding and fixing.
minor cleanup in run.c / format() at the same time.
added some tests for null pointers to debugging printf's, which
were never intended for external consumption. thanks to dave
kerns (dkerns@lucent.com) for pointing this out.
GNU compatibility: an empty regexp matches anything (thanks to
dag-erling smorgrav, des@ofug.org). subject to reversion if
this does more harm than good.
pervasive small changes to make things more const-correct, as
reported by gcc's -Wwrite-strings. as it says in the gcc manual,
this may be more nuisance than useful. provoked by a suggestion
and code from arnaud desitter, arnaud@nimbus.geog.ox.ac.uk
minor documentation changes to note that this now compiles out
of the box on Mac OS X.
Feb 10, 2002:
changed types in posix chars structure to quiet solaris cc.
Jan 1, 2002:
fflush() or fflush("") flushes all files and pipes.
length(arrayname) returns number of elements; thanks to
arnold robbins for suggestion.
added a makefile.win to make it easier to build on windows.
based on dan allen's buildwin.bat.
Nov 16, 2001:
added support for posix character class names like [:digit:],
which are not exactly shorter than [0-9] and perhaps no more
portable. thanks to dag-erling smorgrav for code.
Feb 16, 2001:
removed -m option; no longer needed, and it was actually
broken (noted thanks to volker kiefel).
Feb 10, 2001:
fixed an appalling bug in gettok: any sequence of digits, +,-, E, e,
and period was accepted as a valid number if it started with a period.
this would never have happened with the lex version.
other 1-character botches, now fixed, include a bare $ and a
bare " at the end of the input.
Feb 7, 2001:
more (const char *) casts in b.c and tran.c to silence warnings.
Nov 15, 2000:
fixed a bug introduced in august 1997 that caused expressions
like $f[1] to be syntax errors. thanks to arnold robbins for
noticing this and providing a fix.
Oct 30, 2000:
fixed some nextfile bugs: not handling all cases. thanks to
arnold robbins for pointing this out. new regressions added.
close() is now a function. it returns whatever the library
fclose returns, and -1 for closing a file or pipe that wasn't
opened.
Sep 24, 2000:
permit \n explicitly in character classes; won't work right
if comes in as "[\n]" but ok as /[\n]/, because of multiple
processing of \'s. thanks to arnold robbins.
July 5, 2000:
minor fiddles in tran.c to keep compilers happy about uschar.
thanks to norman wilson.
May 25, 2000:
yet another attempt at making 8-bit input work, with another
band-aid in b.c (member()), and some (uschar) casts to head
off potential errors in subscripts (like isdigit). also
changed HAT to NCHARS-2. thanks again to santiago vila.
changed maketab.c to ignore apparently out of range definitions
instead of halting; new freeBSD generates one. thanks to
jon snader <jsnader@ix.netcom.com> for pointing out the problem.
May 2, 2000:
fixed an 8-bit problem in b.c by making several char*'s into
unsigned char*'s. not clear i have them all yet. thanks to
Santiago Vila <sanvila@unex.es> for the bug report.
Apr 21, 2000:
finally found and fixed a memory leak in function call; it's
been there since functions were added ~1983. thanks to
jon bentley for the test case that found it.
added test in envinit to catch environment "variables" with
names beginning with '='; thanks to Berend Hasselman.
Jul 28, 1999:
added test in defn() to catch function foo(foo), which
otherwise recurses until core dump. thanks to arnold
robbins for noticing this.
Jun 20, 1999:
added *bp in gettok in lex.c; appears possible to exit function
without terminating the string. thanks to russ cox.
Jun 2, 1999:
added function stdinit() to run to initialize files[] array,
in case stdin, etc., are not constants; some compilers care.
May 10, 1999:
replaced the ERROR ... FATAL, etc., macros with functions
based on vprintf, to avoid problems caused by overrunning
fixed-size errbuf array. thanks to ralph corderoy for the
impetus, and for pointing out a string termination bug in
qstring as well.
Apr 21, 1999:
fixed bug that caused occasional core dumps with commandline
variable with value ending in \. (thanks to nelson beebe for
the test case.)
Apr 16, 1999:
with code kindly provided by Bruce Lilly, awk now parses
/=/ and similar constructs more sensibly in more places.
Bruce also provided some helpful test cases.
Apr 5, 1999:
changed true/false to True/False in run.c to make it
easier to compile with C++. Added some casts on malloc
and realloc to be honest about casts; ditto. changed
ltype int to long in struct rrow to reduce some 64-bit
complaints; other changes scattered throughout for the
same purpose. thanks to Nelson Beebe for these portability
improvements.
removed some horrible pointer-int casting in b.c and elsewhere
by adding ptoi and itonp to localize the casts, which are
all benign. fixed one incipient bug that showed up on sgi
in 64-bit mode.
reset lineno for new source file; include filename in error
message. also fixed line number error in continuation lines.
(thanks to Nelson Beebe for both of these.)
Mar 24, 1999:
Nelson Beebe notes that irix 5.3 yacc dies with a bogus
error; use a newer version or switch to bison, since sgi
is unlikely to fix it.
Mar 5, 1999:
changed isnumber to is_number to avoid the problem caused by
versions of ctype.h that include the name isnumber.
distribution now includes a script for building on a Mac,
thanks to Dan Allen.
Feb 20, 1999:
fixed memory leaks in run.c (call) and tran.c (setfval).
thanks to Stephen Nutt for finding these and providing the fixes.
Jan 13, 1999:
replaced srand argument by (unsigned int) in run.c;
avoids problem on Mac and potentially on Unix & Windows.
thanks to Dan Allen.
added a few (int) casts to silence useless compiler warnings.
e.g., errorflag= in run.c jump().
added proctab.c to the bundle outout; one less thing
to have to compile out of the box.
added calls to _popen and _pclose to the win95 stub for
pipes (thanks to Steve Adams for this helpful suggestion).
seems to work, though properties are not well understood
by me, and it appears that under some circumstances the
pipe output is truncated. Be careful.
Oct 19, 1998:
fixed a couple of bugs in getrec: could fail to update $0
after a getline var; because inputFS wasn't initialized,
could split $0 on every character, a misleading diversion.
fixed caching bug in makedfa: LRU was actually removing
least often used.
thanks to ross ridge for finding these, and for providing
great bug reports.
May 12, 1998:
fixed potential bug in readrec: might fail to update record
pointer after growing. thanks to dan levy for spotting this
and suggesting the fix.
Mar 12, 1998:
added -V to print version number and die.
Feb 11, 1998:
subtle silent bug in lex.c: if the program ended with a number
longer than 1 digit, part of the input would be pushed back and
parsed again because token buffer wasn't terminated right.
example: awk 'length($0) > 10'. blush. at least i found it
myself.
Aug 31, 1997:
s/adelete/awkdelete/: SGI uses this in malloc.h.
thanks to nelson beebe for pointing this one out.
Aug 21, 1997:
fixed some bugs in sub and gsub when replacement includes \\.
this is a dark, horrible corner, but at least now i believe that
the behavior is the same as gawk and the intended posix standard.
thanks to arnold robbins for advice here.
Aug 9, 1997:
somewhat regretfully, replaced the ancient lex-based lexical
analyzer with one written in C. it's longer, generates less code,
and more portable; the old one depended too much on mysterious
properties of lex that were not preserved in other environments.
in theory these recognize the same language.
now using strtod to test whether a string is a number, instead of
the convoluted original function. should be more portable and
reliable if strtod is implemented right.
removed now-pointless optimization in makefile that tries to avoid
recompilation when awkgram.y is changed but symbols are not.
removed most fixed-size arrays, though a handful remain, some
of which are unchecked. you have been warned.
Aug 4, 1997:
with some trepidation, replaced the ancient code that managed
fields and $0 in fixed-size arrays with arrays that grow on
demand. there is still some tension between trying to make this
run fast and making it clean; not sure it's right yet.
the ill-conceived -mr and -mf arguments are now useful only
for debugging. previous dynamic string code removed.
numerous other minor cleanups along the way.
Jul 30, 1997:
using code provided by dan levy (to whom profuse thanks), replaced
fixed-size arrays and awkward kludges by a fairly uniform mechanism
to grow arrays as needed for printf, sub, gsub, etc.
Jul 23, 1997:
falling off the end of a function returns "" and 0, not 0.
thanks to arnold robbins.
Jun 17, 1997:
replaced several fixed-size arrays by dynamically-created ones
in run.c; added overflow tests to some previously unchecked cases.
getline, toupper, tolower.
getline code is still broken in that recursive calls may wind
up using the same space. [fixed later]
increased RECSIZE to 8192 to push problems further over the horizon.
added \r to \n as input line separator for programs, not data.
damn CRLFs.
modified format() to permit explicit printf("%c", 0) to include
a null byte in output. thanks to ken stailey for the fix.
added a "-safe" argument that disables file output (print >,
print >>), process creation (cmd|getline, print |, system), and
access to the environment (ENVIRON). this is a first approximation
to a "safe" version of awk, but don't rely on it too much. thanks
to joan feigenbaum and matt blaze for the inspiration long ago.
Jul 8, 1996:
fixed long-standing bug in sub, gsub(/a/, "\\\\&"); thanks to
ralph corderoy.
Jun 29, 1996:
fixed awful bug in new field splitting; didn't get all the places
where input was done.
Jun 28, 1996:
changed field-splitting to conform to posix definition: fields are
split using the value of FS at the time of input; it used to be
the value when the field or NF was first referred to, a much less
predictable definition. thanks to arnold robbins for encouragement
to do the right thing.
May 28, 1996:
fixed appalling but apparently unimportant bug in parsing octal
numbers in reg exprs.
explicit hex in reg exprs now limited to 2 chars: \xa, \xaa.
May 27, 1996:
cleaned up some declarations so gcc -Wall is now almost silent.
makefile now includes backup copies of ytab.c and lexyy.c in case
one makes before looking; it also avoids recreating lexyy.c unless
really needed.
s/aprintf/awkprint, s/asprintf/awksprintf/ to avoid some name clashes
with unwisely-written header files.
thanks to jeffrey friedl for several of these.
May 26, 1996:
an attempt to rationalize the (unsigned) char issue. almost all
instances of unsigned char have been removed; the handful of places
in b.c where chars are used as table indices have been hand-crafted.
added some latin-1 tests to the regression, but i'm not confident;
none of my compilers seem to care much. thanks to nelson beebe for
pointing out some others that do care.
May 2, 1996:
removed all register declarations.
enhanced split(), as in gawk, etc: split(s, a, "") splits s into
a[1]...a[length(s)] with each character a single element.
made the same changes for field-splitting if FS is "".
added nextfile, as in gawk: causes immediate advance to next
input file. (thanks to arnold robbins for inspiration and code).
small fixes to regexpr code: can now handle []], [[], and
variants; [] is now a syntax error, rather than matching
everything; [z-a] is now empty, not z. far from complete
or correct, however. (thanks to jeffrey friedl for pointing out
some awful behaviors.)
Apr 29, 1996:
replaced uchar by uschar everywhere; apparently some compilers
usurp this name and this causes conflicts.
fixed call to time in run.c (bltin); arg is time_t *.
replaced horrible pointer/long punning in b.c by a legitimate
union. should be safer on 64-bit machines and cleaner everywhere.
(thanks to nelson beebe for pointing out some of these problems.)
replaced nested comments by #if 0...#endif in run.c, lib.c.
removed getsval, setsval, execute macros from run.c and lib.c.
machines are 100x faster than they were when these macros were
first used.
revised filenames: awk.g.y => awkgram.y, awk.lx.l => awklex.l,
y.tab.[ch] => ytab.[ch], lex.yy.c => lexyy.c, all in the aid of
portability to nameless systems.
"make bundle" now includes yacc and lex output files for recipients
who don't have yacc or lex.
Aug 15, 1995:
initialized Cells in setsymtab more carefully; some fields
were not set. (thanks to purify, all of whose complaints i
think i now understand.)
fixed at least one error in gsub that looked at -1-th element
of an array when substituting for a null match (e.g., $).
delete arrayname is now legal; it clears the elements but leaves
the array, which may not be the right behavior.
modified makefile: my current make can't cope with the test used
to avoid unnecessary yacc invocations.
Jul 17, 1995:
added dynamically growing strings to awk.lx.l and b.c
to permit regular expressions to be much bigger.
the state arrays can still overflow.
Aug 24, 1994:
detect duplicate arguments in function definitions (mdm).
May 11, 1994:
trivial fix to printf to limit string size in sub().
Apr 22, 1994:
fixed yet another subtle self-assignment problem:
$1 = $2; $1 = $1 clobbered $1.
Regression tests now use private echo, to avoid quoting problems.
Feb 2, 1994:
changed error() to print line number as %d, not %g.
Jul 23, 1993:
cosmetic changes: increased sizes of some arrays,
reworded some error messages.
added CONVFMT as in posix (just replaced OFMT in getsval)
FILENAME is now "" until the first thing that causes a file
to be opened.
Nov 28, 1992:
deleted yyunput and yyoutput from proto.h;
different versions of lex give these different declarations.
May 31, 1992:
added -mr N and -mf N options: more record and fields.
these really ought to adjust automatically.
cleaned up some error messages; "out of space" now means
malloc returned NULL in all cases.
changed rehash so that if it runs out, it just returns;
things will continue to run slow, but maybe a bit longer.
Apr 24, 1992:
remove redundant close of stdin when using -f -.
got rid of core dump with -d; awk -d just prints date.
Apr 12, 1992:
added explicit check for /dev/std(in,out,err) in redirection.
unlike gawk, no /dev/fd/n yet.
added (file/pipe) builtin. hard to test satisfactorily.
not posix.
Feb 20, 1992:
recompile after abortive changes; should be unchanged.
Dec 2, 1991:
die-casting time: converted to ansi C, installed that.
Nov 30, 1991:
fixed storage leak in freefa, failing to recover [N]CCL.
thanks to Bill Jones (jones@cs.usask.ca)
Nov 19, 1991:
use RAND_MAX instead of literal in builtin().
Nov 12, 1991:
cranked up some fixed-size arrays in b.c, and added a test for
overflow in penter. thanks to mark larsen.
Sep 24, 1991:
increased buffer in gsub. a very crude fix to a general problem.
and again on Sep 26.
Aug 18, 1991:
enforce variable name syntax for commandline variables: has to
start with letter or _.
Jul 27, 1991:
allow newline after ; in for statements.
Jul 21, 1991:
fixed so that in self-assignment like $1=$1, side effects
like recomputing $0 take place. (this is getting subtle.)
Jun 30, 1991:
better test for detecting too-long output record.
Jun 2, 1991:
better defense against very long printf strings.
made break and continue illegal outside of loops.
May 13, 1991:
removed extra arg on gettemp, tempfree. minor error message rewording.
May 6, 1991:
fixed silly bug in hex parsing in hexstr().
removed an apparently unnecessary test in isnumber().
warn about weird printf conversions.
fixed unchecked array overwrite in relex().
changed for (i in array) to access elements in sorted order.
then unchanged it -- it really does run slower in too many cases.
left the code in place, commented out.
Feb 10, 1991:
check error status on all writes, to avoid banging on full disks.
Jan 28, 1991:
awk -f - reads the program from stdin.
Jan 11, 1991:
failed to set numeric state on $0 in cmd|getline context in run.c.
Nov 2, 1990:
fixed sleazy test for integrality in getsval; use modf.
Oct 29, 1990:
fixed sleazy buggy code in lib.c that looked (incorrectly) for
too long input lines.
Oct 14, 1990:
fixed the bug on p. 198 in which it couldn't deduce that an
argument was an array in some contexts. replaced the error
message in intest() by code that damn well makes it an array.
Oct 8, 1990:
fixed horrible bug: types and values were not preserved in
some kinds of self-assignment. (in assign().)
Aug 24, 1990:
changed NCHARS to 256 to handle 8-bit characters in strings
presented to match(), etc.
Jun 26, 1990:
changed struct rrow (awk.h) to use long instead of int for lval,
since cfoll() stores a pointer in it. now works better when int's
are smaller than pointers!
May 6, 1990:
AVA fixed the grammar so that ! is uniformly of the same precedence as
unary + and -. This renders illegal some constructs like !x=y, which
now has to be parenthesized as !(x=y), and makes others work properly:
!x+y is (!x)+y, and x!y is x !y, not two pattern-action statements.
(These problems were pointed out by Bob Lenk of Posix.)
Added \x to regular expressions (already in strings).
Limited octal to octal digits; \8 and \9 are not octal.
Centralized the code for parsing escapes in regular expressions.
Added a bunch of tests to T.re and T.sub to verify some of this.
Feb 9, 1990:
fixed null pointer dereference bug in main.c: -F[nothing]. sigh.
restored srand behavior: it returns the current seed.
Jan 18, 1990:
srand now returns previous seed value (0 to start).
Jan 5, 1990:
fix potential problem in tran.c -- something was freed,
then used in freesymtab.
Oct 18, 1989:
another try to get the max number of open files set with
relatively machine-independent code.
small fix to input() in case of multiple reads after EOF.
Oct 11, 1989:
FILENAME is now defined in the BEGIN block -- too many old
programs broke.
"-" means stdin in getline as well as on the commandline.
added a bunch of casts to the code to tell the truth about
char * vs. unsigned char *, a right royal pain. added a
setlocale call to the front of main, though probably no one
has it usefully implemented yet.
Aug 24, 1989:
removed redundant relational tests against nullnode if parse
tree already had a relational at that point.
Aug 11, 1989:
fixed bug: commandline variable assignment has to look like
var=something. (consider the man page for =, in file =.1)
changed number of arguments to functions to static arrays
to avoid repeated malloc calls.
Aug 2, 1989:
restored -F (space) separator
Jul 30, 1989:
added -v x=1 y=2 ... for immediate commandline variable assignment;
done before the BEGIN block for sure. they have to precede the
program if the program is on the commandline.
Modified Aug 2 to require a separate -v for each assignment.
Jul 10, 1989:
fixed ref-thru-zero bug in environment code in tran.c
Jun 23, 1989:
add newline to usage message.
Jun 14, 1989:
added some missing ansi printf conversion letters: %i %X %E %G.
no sensible meaning for h or L, so they may not do what one expects.
made %* conversions work.
changed x^y so that if n is a positive integer, it's done
by explicit multiplication, thus achieving maximum accuracy.
(this should be done by pow() but it seems not to be locally.)
done to x ^= y as well.
Jun 4, 1989:
ENVIRON array contains environment: if shell variable V=thing,
ENVIRON["V"] is "thing"
multiple -f arguments permitted. error reporting is naive.
(they were permitted before, but only the last was used.)
fixed a really stupid botch in the debugging macro dprintf
fixed order of evaluation of commandline assignments to match
what the book claims: an argument of the form x=e is evaluated
at the time it would have been opened if it were a filename (p 63).
this invalidates the suggested answer to ex 4-1 (p 195).
removed some code that permitted -F (space) fieldseparator,
since it didn't quite work right anyway. (restored aug 2)
Apr 27, 1989:
Line number now accumulated correctly for comment lines.
Apr 26, 1989:
Debugging output now includes a version date,
if one compiles it into the source each time.
Apr 9, 1989:
Changed grammar to prohibit constants as 3rd arg of sub and gsub;
prevents class of overwriting-a-constant errors. (Last one?)
This invalidates the "banana" example on page 43 of the book.
Added \a ("alert"), \v (vertical tab), \xhhh (hexadecimal),
as in ANSI, for strings. Rescinded the sloppiness that permitted
non-octal digits in \ooo. Warning: not all compilers and libraries
will be able to deal with \x correctly.
Jan 9, 1989:
Fixed bug that caused tempcell list to contain a duplicate.
The fix is kludgy.
Dec 17, 1988:
Catches some more commandline errors in main.
Removed redundant decl of modf in run.c (confuses some compilers).
Warning: there's no single declaration of malloc, etc., in awk.h
that seems to satisfy all compilers.
Dec 7, 1988:
Added a bit of code to error printing to avoid printing nulls.
(Not clear that it actually would.)
Nov 27, 1988:
With fear and trembling, modified the grammar to permit
multiple pattern-action statements on one line without
an explicit separator. By definition, this capitulation
to the ghost of ancient implementations remains undefined
and thus subject to change without notice or apology.
DO NOT COUNT ON IT.
Oct 30, 1988:
Fixed bug in call() that failed to recover storage.
A warning is now generated if there are more arguments
in the call than in the definition (in lieu of fixing
another storage leak).
Oct 20, 1988:
Fixed %c: if expr is numeric, use numeric value;
otherwise print 1st char of string value. still
doesn't work if the value is 0 -- won't print \0.
Added a few more checks for running out of malloc.
Oct 12, 1988:
Fixed bug in call() that freed local arrays twice.
Fixed to handle deletion of non-existent array right;
complains about attempt to delete non-array element.
Sep 30, 1988:
Now guarantees to evaluate all arguments of built-in
functions, as in C; the appearance is that arguments
are evaluated before the function is called. Places
affected are sub (gsub was ok), substr, printf, and
all the built-in arithmetic functions in bltin().
A warning is generated if a bltin() is called with
the wrong number of arguments.
This requires changing makeprof on p167 of the book.
Aug 23, 1988:
setting FILENAME in BEGIN caused core dump, apparently
because it was freeing space not allocated by malloc.
July 24, 1988:
fixed egregious error in toupper/tolower functions.
still subject to rescinding, however.
July 2, 1988:
flush stdout before opening file or pipe
July 2, 1988:
performance bug in b.c/cgoto(): not freeing some sets of states.
partial fix only right now, and the number of states increased
to make it less obvious.
June 1, 1988:
check error status on close
May 28, 1988:
srand returns seed value it's using.
see 1/18/90
May 22, 1988:
Removed limit on depth of function calls.
May 10, 1988:
Fixed lib.c to permit _ in commandline variable names.
Mar 25, 1988:
main.c fixed to recognize -- as terminator of command-
line options. Illegal options flagged.
Error reporting slightly cleaned up.
Dec 2, 1987:
Newer C compilers apply a strict scope rule to extern
declarations within functions. Two extern declarations in
lib.c and tran.c have been moved to obviate this problem.
Oct xx, 1987:
Reluctantly added toupper and tolower functions.
Subject to rescinding without notice.
Sep 17, 1987:
Error-message printer had printf(s) instead of
printf("%s",s); got core dumps when the message
included a %.
Sep 12, 1987:
Very long printf strings caused core dump;
fixed aprintf, asprintf, format to catch them.
Can still get a core dump in printf itself.

View File

@@ -1,17 +1,30 @@
.include <minix.own.mk>
# Makefile for awk.
PROG= awk
SRCS= awkgram.y b.c lex.c lib.c main.c parse.c proctab.c run.c tran.c
YHEADER= yes
QUIET_YACC= yes
CC = exec cc
CFLAGS = -D_MINIX -D_POSIX_SOURCE -wo -w
LDFLAGS = -i -f
build-tools: maketab
OBJS = m.o e.o n.o l.o r.o v.o y.o regexp.o k.o
proctab.c: maketab
./maketab > proctab.c
all: awk
maketab: awkgram.h maketab.c
awk: $(OBJS)
$(CC) $(LDFLAGS) -o $@ $(OBJS) #-lm
install -S 32kw $@
CLEANFILES= maketab proctab.c
install: /usr/bin/awk
.include <minix.prog.mk>
/usr/bin/awk: awk
install -cs -o bin $? $@
clean:
rm -f awk *.o a.out *.bak core
e.o: awk.h regexp.h
l.o: awk.h
m.o: awk.h
n.o: awk.h
r.o: awk.h regexp.h
regexp.o: regexp.h
v.o: awk.h regexp.h
y.o: awk.h

View File

@@ -1,94 +0,0 @@
# /****************************************************************
# Copyright (C) Lucent Technologies 1997
# All Rights Reserved
#
# Permission to use, copy, modify, and distribute this software and
# its documentation for any purpose and without fee is hereby
# granted, provided that the above copyright notice appear in all
# copies and that both that the copyright notice and this
# permission notice and warranty disclaimer appear in supporting
# documentation, and that the name Lucent Technologies or any of
# its entities not be used in advertising or publicity pertaining
# to distribution of the software without specific, written prior
# permission.
#
# LUCENT DISCLAIMS ALL WARRANTIES WITH REGARD TO THIS SOFTWARE,
# INCLUDING ALL IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS.
# IN NO EVENT SHALL LUCENT OR ANY OF ITS ENTITIES BE LIABLE FOR ANY
# SPECIAL, INDIRECT OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES
# WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER
# IN AN ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION,
# ARISING OUT OF OR IN CONNECTION WITH THE USE OR PERFORMANCE OF
# THIS SOFTWARE.
# ****************************************************************/
CFLAGS = -g
CFLAGS = -O2
CFLAGS =
CC = gcc -Wall -g -Wwrite-strings
CC = gcc -fprofile-arcs -ftest-coverage # then gcov f1.c; cat f1.c.gcov
CC = gcc -Wall -g
CC = cc
CC = gcc -O4
CC = cc -O
YACC = bison -y
YACC = yacc
YFLAGS = -d
OFILES = b.o main.o parse.o proctab.o tran.o lib.o run.o lex.o
SOURCE = awk.h ytab.c ytab.h proto.h awkgram.y lex.c b.c main.c \
maketab.c parse.c lib.c run.c tran.c proctab.c missing95.c
LISTING = awk.h proto.h awkgram.y lex.c b.c main.c maketab.c parse.c \
lib.c run.c tran.c missing95.c
SHIP = README FIXES $(SOURCE) ytab[ch].bak makefile makefile.win \
vcvars32.bat buildwin.bat awk.1
all: awk
install: awk awk.1
install -m 755 -o bin -g operator awk /usr/bin/awk
install -m 644 -o bin -g operator awk.1 /usr/man/man1
awk: ytab.o $(OFILES)
$(CC) $(CFLAGS) ytab.o $(OFILES) $(ALLOC) -lm -o $@
$(OFILES): awk.h ytab.h proto.h
ytab.o ytab.c ytab.h: awk.h proto.h awkgram.y
$(YACC) $(YFLAGS) awkgram.y 2>/dev/null
mv y.tab.c ytab.c
mv y.tab.h ytab.h
$(CC) $(CFLAGS) -c ytab.c
proctab.c: maketab
./maketab >proctab.c
maketab: ytab.h maketab.c
$(CC) $(CFLAGS) maketab.c -o maketab
bundle:
@cp ytab.h ytabh.bak
@cp ytab.c ytabc.bak
@bundle $(SHIP)
tar:
@cp ytab.h ytabh.bak
@cp ytab.c ytabc.bak
@bundle $(SHIP) >awk.shar
@tar cf awk.tar $(SHIP)
gzip awk.tar
ls -l awk.tar.gz
@zip awk.zip $(SHIP)
ls -l awk.zip
names:
@echo $(LISTING)
clean:
rm -f awk *.o *.obj maketab maketab.exe *.bb *.bbg *.da *.gcov *.gcno *.gcda # proctab.c

View File

@@ -1,94 +1,13 @@
/****************************************************************
Copyright (C) Lucent Technologies 1997
All Rights Reserved
A small AWK clone for the 16-bit Minix
Permission to use, copy, modify, and distribute this software and
its documentation for any purpose and without fee is hereby
granted, provided that the above copyright notice appear in all
copies and that both that the copyright notice and this
permission notice and warranty disclaimer appear in supporting
documentation, and that the name Lucent Technologies or any of
its entities not be used in advertising or publicity pertaining
to distribution of the software without specific, written prior
permission.
We have written this program for the Minix 1.2 to fit into 64K+64K
memory. When compiling this program, you need the Peter S. Housel's
Floating Math Package with corrected the atan() function. Original atan()
function has incorrect argument sequence.
LUCENT DISCLAIMS ALL WARRANTIES WITH REGARD TO THIS SOFTWARE,
INCLUDING ALL IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS.
IN NO EVENT SHALL LUCENT OR ANY OF ITS ENTITIES BE LIABLE FOR ANY
SPECIAL, INDIRECT OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES
WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER
IN AN ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION,
ARISING OUT OF OR IN CONNECTION WITH THE USE OR PERFORMANCE OF
THIS SOFTWARE.
****************************************************************/
This program supports Japanese Shift-JIS KANJI code and passes
all the test program of the "AWK programming language" written by original
AWK authors except some programs relied upon the way of regular expression
evaluation.
This is the version of awk described in "The AWK Programming Language",
by Al Aho, Brian Kernighan, and Peter Weinberger
(Addison-Wesley, 1988, ISBN 0-201-07981-X).
Changes, mostly bug fixes and occasional enhancements, are listed
in FIXES. If you distribute this code further, please please please
distribute FIXES with it. If you find errors, please report them
to bwk@bell-labs.com. Thanks.
The program itself is created by
make
which should produce a sequence of messages roughly like this:
yacc -d awkgram.y
conflicts: 43 shift/reduce, 85 reduce/reduce
mv y.tab.c ytab.c
mv y.tab.h ytab.h
cc -c ytab.c
cc -c b.c
cc -c main.c
cc -c parse.c
cc maketab.c -o maketab
./maketab >proctab.c
cc -c proctab.c
cc -c tran.c
cc -c lib.c
cc -c run.c
cc -c lex.c
cc ytab.o b.o main.o parse.o proctab.o tran.o lib.o run.o lex.o -lm
This produces an executable a.out; you will eventually want to
move this to some place like /usr/bin/awk.
If your system does not have yacc or bison (the GNU
equivalent), you must compile the pieces manually. We have
included yacc output in ytab.c and ytab.h, and backup copies in
case you overwrite them. We have also included a copy of
proctab.c so you do not need to run maketab.
NOTE: This version uses ANSI C, as you should also. We have
compiled this without any changes using gcc -Wall and/or local C
compilers on a variety of systems, but new systems or compilers
may raise some new complaint; reports of difficulties are
welcome.
This also compiles with Visual C++ on all flavors of Windows,
*if* you provide versions of popen and pclose. The file
missing95.c contains versions that can be used to get started
with, though the underlying support has mysterious properties,
the symptom of which can be truncated pipe output. Beware. The
file makefile.win gives hints on how to proceed; if you run
vcvars32.bat, it will set up necessary paths and parameters so
you can subsequently run nmake -f makefile.win. Beware also that
when running on Windows under command.com, various quoting
conventions are different from Unix systems: single quotes won't
work around arguments, and various characters like % are
interpreted within double quotes.
This compiles without change on Macintosh OS X using gcc and
the standard developer tools.
This is also said to compile on Macintosh OS 9 systems, using the
file "buildmac" provided by Dan Allen (danallen@microsoft.com),
to whom many thanks.
The version of malloc that comes with some systems is sometimes
astonishly slow. If awk seems slow, you might try fixing that.
More generally, turning on optimization can significantly improve
awk's speed, perhaps by 1/3 for highest levels.
Kouichi Hirabayashi (kh@mogami-wire.co.jp)

View File

@@ -1,529 +0,0 @@
.de EX
.nf
.ft CW
..
.de EE
.br
.fi
.ft 1
..
awk
.TH AWK 1
.CT 1 files prog_other
.SH NAME
awk \- pattern-directed scanning and processing language
.SH SYNOPSIS
.B awk
[
.BI \-F
.I fs
]
[
.BI \-v
.I var=value
]
[
.I 'prog'
|
.BI \-f
.I progfile
]
[
.I file ...
]
.SH DESCRIPTION
.I Awk
scans each input
.I file
for lines that match any of a set of patterns specified literally in
.IR prog
or in one or more files
specified as
.B \-f
.IR progfile .
With each pattern
there can be an associated action that will be performed
when a line of a
.I file
matches the pattern.
Each line is matched against the
pattern portion of every pattern-action statement;
the associated action is performed for each matched pattern.
The file name
.B \-
means the standard input.
Any
.IR file
of the form
.I var=value
is treated as an assignment, not a filename,
and is executed at the time it would have been opened if it were a filename.
The option
.B \-v
followed by
.I var=value
is an assignment to be done before
.I prog
is executed;
any number of
.B \-v
options may be present.
The
.B \-F
.IR fs
option defines the input field separator to be the regular expression
.IR fs.
.PP
An input line is normally made up of fields separated by white space,
or by regular expression
.BR FS .
The fields are denoted
.BR $1 ,
.BR $2 ,
\&..., while
.B $0
refers to the entire line.
If
.BR FS
is null, the input line is split into one field per character.
.PP
A pattern-action statement has the form
.IP
.IB pattern " { " action " }
.PP
A missing
.BI { " action " }
means print the line;
a missing pattern always matches.
Pattern-action statements are separated by newlines or semicolons.
.PP
An action is a sequence of statements.
A statement can be one of the following:
.PP
.EX
.ta \w'\f(CWdelete array[expression]'u
.RS
.nf
.ft CW
if(\fI expression \fP)\fI statement \fP\fR[ \fPelse\fI statement \fP\fR]\fP
while(\fI expression \fP)\fI statement\fP
for(\fI expression \fP;\fI expression \fP;\fI expression \fP)\fI statement\fP
for(\fI var \fPin\fI array \fP)\fI statement\fP
do\fI statement \fPwhile(\fI expression \fP)
break
continue
{\fR [\fP\fI statement ... \fP\fR] \fP}
\fIexpression\fP #\fR commonly\fP\fI var = expression\fP
print\fR [ \fP\fIexpression-list \fP\fR] \fP\fR[ \fP>\fI expression \fP\fR]\fP
printf\fI format \fP\fR[ \fP,\fI expression-list \fP\fR] \fP\fR[ \fP>\fI expression \fP\fR]\fP
return\fR [ \fP\fIexpression \fP\fR]\fP
next #\fR skip remaining patterns on this input line\fP
nextfile #\fR skip rest of this file, open next, start at top\fP
delete\fI array\fP[\fI expression \fP] #\fR delete an array element\fP
delete\fI array\fP #\fR delete all elements of array\fP
exit\fR [ \fP\fIexpression \fP\fR]\fP #\fR exit immediately; status is \fP\fIexpression\fP
.fi
.RE
.EE
.DT
.PP
Statements are terminated by
semicolons, newlines or right braces.
An empty
.I expression-list
stands for
.BR $0 .
String constants are quoted \&\f(CW"\ "\fR,
with the usual C escapes recognized within.
Expressions take on string or numeric values as appropriate,
and are built using the operators
.B + \- * / % ^
(exponentiation), and concatenation (indicated by white space).
The operators
.B
! ++ \-\- += \-= *= /= %= ^= > >= < <= == != ?:
are also available in expressions.
Variables may be scalars, array elements
(denoted
.IB x [ i ] )
or fields.
Variables are initialized to the null string.
Array subscripts may be any string,
not necessarily numeric;
this allows for a form of associative memory.
Multiple subscripts such as
.B [i,j,k]
are permitted; the constituents are concatenated,
separated by the value of
.BR SUBSEP .
.PP
The
.B print
statement prints its arguments on the standard output
(or on a file if
.BI > file
or
.BI >> file
is present or on a pipe if
.BI | cmd
is present), separated by the current output field separator,
and terminated by the output record separator.
.I file
and
.I cmd
may be literal names or parenthesized expressions;
identical string values in different statements denote
the same open file.
The
.B printf
statement formats its expression list according to the format
(see
.IR printf (3)) .
The built-in function
.BI close( expr )
closes the file or pipe
.IR expr .
The built-in function
.BI fflush( expr )
flushes any buffered output for the file or pipe
.IR expr .
.PP
The mathematical functions
.BR exp ,
.BR log ,
.BR sqrt ,
.BR sin ,
.BR cos ,
and
.BR atan2
are built in.
Other built-in functions:
.TF length
.TP
.B length
the length of its argument
taken as a string,
or of
.B $0
if no argument.
.TP
.B rand
random number on (0,1)
.TP
.B srand
sets seed for
.B rand
and returns the previous seed.
.TP
.B int
truncates to an integer value
.TP
.BI substr( s , " m" , " n\fB)
the
.IR n -character
substring of
.I s
that begins at position
.IR m
counted from 1.
.TP
.BI index( s , " t" )
the position in
.I s
where the string
.I t
occurs, or 0 if it does not.
.TP
.BI match( s , " r" )
the position in
.I s
where the regular expression
.I r
occurs, or 0 if it does not.
The variables
.B RSTART
and
.B RLENGTH
are set to the position and length of the matched string.
.TP
.BI split( s , " a" , " fs\fB)
splits the string
.I s
into array elements
.IB a [1] ,
.IB a [2] ,
\&...,
.IB a [ n ] ,
and returns
.IR n .
The separation is done with the regular expression
.I fs
or with the field separator
.B FS
if
.I fs
is not given.
An empty string as field separator splits the string
into one array element per character.
.TP
.BI sub( r , " t" , " s\fB)
substitutes
.I t
for the first occurrence of the regular expression
.I r
in the string
.IR s .
If
.I s
is not given,
.B $0
is used.
.TP
.B gsub
same as
.B sub
except that all occurrences of the regular expression
are replaced;
.B sub
and
.B gsub
return the number of replacements.
.TP
.BI sprintf( fmt , " expr" , " ...\fB )
the string resulting from formatting
.I expr ...
according to the
.IR printf (3)
format
.I fmt
.TP
.BI system( cmd )
executes
.I cmd
and returns its exit status
.TP
.BI tolower( str )
returns a copy of
.I str
with all upper-case characters translated to their
corresponding lower-case equivalents.
.TP
.BI toupper( str )
returns a copy of
.I str
with all lower-case characters translated to their
corresponding upper-case equivalents.
.PD
.PP
The ``function''
.B getline
sets
.B $0
to the next input record from the current input file;
.B getline
.BI < file
sets
.B $0
to the next record from
.IR file .
.B getline
.I x
sets variable
.I x
instead.
Finally,
.IB cmd " | getline
pipes the output of
.I cmd
into
.BR getline ;
each call of
.B getline
returns the next line of output from
.IR cmd .
In all cases,
.B getline
returns 1 for a successful input,
0 for end of file, and \-1 for an error.
.PP
Patterns are arbitrary Boolean combinations
(with
.BR "! || &&" )
of regular expressions and
relational expressions.
Regular expressions are as in
.IR egrep ;
see
.IR grep (1).
Isolated regular expressions
in a pattern apply to the entire line.
Regular expressions may also occur in
relational expressions, using the operators
.BR ~
and
.BR !~ .
.BI / re /
is a constant regular expression;
any string (constant or variable) may be used
as a regular expression, except in the position of an isolated regular expression
in a pattern.
.PP
A pattern may consist of two patterns separated by a comma;
in this case, the action is performed for all lines
from an occurrence of the first pattern
though an occurrence of the second.
.PP
A relational expression is one of the following:
.IP
.I expression matchop regular-expression
.br
.I expression relop expression
.br
.IB expression " in " array-name
.br
.BI ( expr , expr,... ") in " array-name
.PP
where a relop is any of the six relational operators in C,
and a matchop is either
.B ~
(matches)
or
.B !~
(does not match).
A conditional is an arithmetic expression,
a relational expression,
or a Boolean combination
of these.
.PP
The special patterns
.B BEGIN
and
.B END
may be used to capture control before the first input line is read
and after the last.
.B BEGIN
and
.B END
do not combine with other patterns.
.PP
Variable names with special meanings:
.TF FILENAME
.TP
.B CONVFMT
conversion format used when converting numbers
(default
.BR "%.6g" )
.TP
.B FS
regular expression used to separate fields; also settable
by option
.BI \-F fs.
.TP
.BR NF
number of fields in the current record
.TP
.B NR
ordinal number of the current record
.TP
.B FNR
ordinal number of the current record in the current file
.TP
.B FILENAME
the name of the current input file
.TP
.B RS
input record separator (default newline)
.TP
.B OFS
output field separator (default blank)
.TP
.B ORS
output record separator (default newline)
.TP
.B OFMT
output format for numbers (default
.BR "%.6g" )
.TP
.B SUBSEP
separates multiple subscripts (default 034)
.TP
.B ARGC
argument count, assignable
.TP
.B ARGV
argument array, assignable;
non-null members are taken as filenames
.TP
.B ENVIRON
array of environment variables; subscripts are names.
.PD
.PP
Functions may be defined (at the position of a pattern-action statement) thus:
.IP
.B
function foo(a, b, c) { ...; return x }
.PP
Parameters are passed by value if scalar and by reference if array name;
functions may be called recursively.
Parameters are local to the function; all other variables are global.
Thus local variables may be created by providing excess parameters in
the function definition.
.SH EXAMPLES
.TP
.EX
length($0) > 72
.EE
Print lines longer than 72 characters.
.TP
.EX
{ print $2, $1 }
.EE
Print first two fields in opposite order.
.PP
.EX
BEGIN { FS = ",[ \et]*|[ \et]+" }
{ print $2, $1 }
.EE
.ns
.IP
Same, with input fields separated by comma and/or blanks and tabs.
.PP
.EX
.nf
{ s += $1 }
END { print "sum is", s, " average is", s/NR }
.fi
.EE
.ns
.IP
Add up first column, print sum and average.
.TP
.EX
/start/, /stop/
.EE
Print all lines between start/stop pairs.
.PP
.EX
.nf
BEGIN { # Simulate echo(1)
for (i = 1; i < ARGC; i++) printf "%s ", ARGV[i]
printf "\en"
exit }
.fi
.EE
.SH SEE ALSO
.IR lex (1),
.IR sed (1)
.br
A. V. Aho, B. W. Kernighan, P. J. Weinberger,
.I
The AWK Programming Language,
Addison-Wesley, 1988. ISBN 0-201-07981-X
.SH BUGS
There are no explicit conversions between numbers and strings.
To force an expression to be treated as a number add 0 to it;
to force it to be treated as a string concatenate
\&\f(CW""\fP to it.
.br
The scope rules for variables in functions are a botch;
the syntax is worse.

View File

@@ -1,233 +1,186 @@
/****************************************************************
Copyright (C) Lucent Technologies 1997
All Rights Reserved
/*
* a small awk clone
*
* (C) 1989 Saeko Hirabauashi & Kouichi Hirabayashi
*
* Absolutely no warranty. Use this software with your own risk.
*
* Permission to use, copy, modify and distribute this software for any
* purpose and without fee is hereby granted, provided that the above
* copyright and disclaimer notice.
*
* This program was written to fit into 64K+64K memory of the Minix 1.2.
*/
Permission to use, copy, modify, and distribute this software and
its documentation for any purpose and without fee is hereby
granted, provided that the above copyright notice appear in all
copies and that both that the copyright notice and this
permission notice and warranty disclaimer appear in supporting
documentation, and that the name Lucent Technologies or any of
its entities not be used in advertising or publicity pertaining
to distribution of the software without specific, written prior
permission.
/* lexical/parser tokens and executable statements */
LUCENT DISCLAIMS ALL WARRANTIES WITH REGARD TO THIS SOFTWARE,
INCLUDING ALL IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS.
IN NO EVENT SHALL LUCENT OR ANY OF ITS ENTITIES BE LIABLE FOR ANY
SPECIAL, INDIRECT OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES
WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER
IN AN ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION,
ARISING OUT OF OR IN CONNECTION WITH THE USE OR PERFORMANCE OF
THIS SOFTWARE.
****************************************************************/
#define FIRSTP 256
#define ARG 256
#define ARITH 257
#define ARRAY 258
#define ASSIGN 259
#define CALL 260
#define CAT 261
#define COND 262
#define DELETE 263
#define DO 264
#define ELEMENT 265
#define FIELD 266
#define FOR 267
#define FORIN 268
#define GETLINE 269
#define IF 270
#define IN 271
#define JUMP 272
#define MATHFUN 273
#define NULPROC 274
#define P1STAT 275
#define P2STAT 276
#define PRINT 277
#define PRINT0 278
#define STRFUN 279
#define SUBST 280
#define USRFUN 281
#define WHILE 282
#define LASTP 282
/* lexical token */
#include <assert.h>
#define ADD 300 /* + */
#define ADDEQ 301 /* += */
#define AND 302 /* && */
#define BEGIN 303 /* BEGIN */
#define BINAND 304 /* & */
#define BINOR 305 /* | */
#define BREAK 306 /* break */
#define CLOSE 307 /* close */
#define CONTIN 308 /* continue */
#define DEC 309 /* -- */
#define DIV 310 /* / */
#define DIVEQ 311 /* /= */
#define ELSE 312 /* else */
#define END 313 /* END */
#define EOL 314 /* ; or '\n' */
#define EQ 315 /* == */
#define EXIT 316 /* exit */
#define FUNC 317 /* function */
#define GE 318 /* >= */
#define GT 319 /* > */
#define IDENT 320 /* identifier */
#define INC 321 /* ++ */
#define LE 322 /* <= */
#define LT 323 /* < */
#define MATCH 324 /* ~ */
#define MOD 325 /* % */
#define MODEQ 326 /* %= */
#define MULT 327 /* * */
#define MULTEQ 328 /* *= */
#define NE 329 /* != */
#define NEXT 330 /* next */
#define NOMATCH 331 /* !~ */
#define NOT 332 /* ! */
#define NUMBER 333 /* integer or floating number */
#define OR 334 /* || */
#define POWEQ 335 /* ^= */
#define POWER 336 /* ^ */
#define PRINTF 337 /* printf */
#define REGEXP 338 /* /REG/ */
#define RETURN 339 /* return */
#define SHIFTL 340 /* << */
#define SHIFTR 341 /* >> */
#define SPRINT 342 /* sprint */
#define SPRINTF 343 /* sprintf */
#define STRING 344 /* ".." */
#define SUB 345 /* - */
#define SUBEQ 346 /* -= */
#define SYSTEM 347 /* system */
#define UMINUS 348 /* - */
typedef double Awkfloat;
/* tokens in parser */
/* unsigned char is more trouble than it's worth */
#define VALUE 400 /* value node */
#define INCDEC 401 /* ++, -- */
#define PRE 402 /* pre incre/decre */
#define POST 403 /* post incre/decre */
typedef unsigned char uschar;
/* redirect in print(f) statement */
#define xfree(a) { if ((a) != NULL) { free((void *) (a)); (a) = NULL; } }
#define R_OUT 410 /* > */
#define R_APD 411 /* >> */
#define R_PIPE 412 /* | */
#define R_IN 413 /* < */
#define R_PIN 414 /* | getline */
#define R_POUT 415 /* print | */
#define NN(p) ((p) ? (p) : "(null)") /* guaranteed non-null for dprintf
*/
#define DEBUG
#ifdef DEBUG
/* uses have to be doubly parenthesized */
# define dprintf(x) if (dbg) printf x
#else
# define dprintf(x)
#endif
/* function */
extern int compile_time; /* 1 if compiling, 0 if running */
extern int safe; /* 0 => unsafe, 1 => safe */
#define ATAN2 500 /* atan2 */
#define COS 501 /* cos */
#define EXP 502 /* exp */
#define INDEX 503 /* index */
#define INT 504 /* int */
#define LENGTH 505 /* length */
#define LOG 506 /* log */
#define RAND 507 /* rand */
#define RGSUB 508 /* gsub */
#define RMATCH 509 /* match */
#define RSUB 510 /* sub */
#define SIN 511 /* sin */
#define SPLIT 512 /* split */
#define SQRT 513 /* sqrt */
#define SRAND 514 /* srand */
#define SUBSTR 515 /* substr */
#define RECSIZE (8 * 1024) /* sets limit on records, fields, etc., etc. */
extern int recsize; /* size of current record, orig RECSIZE */
/* print(f) options */
extern char **FS;
extern char **RS;
extern char **ORS;
extern char **OFS;
extern char **OFMT;
extern Awkfloat *NR;
extern Awkfloat *FNR;
extern Awkfloat *NF;
extern char **FILENAME;
extern char **SUBSEP;
extern Awkfloat *RSTART;
extern Awkfloat *RLENGTH;
#define FORMAT 1024 /* PRINTF, SPRINTF */
#define STROUT 2048 /* SPRINTF */
#define PRMASK 0x3ff /* ~(FORMAT|STROUT) */
extern char *record; /* points to $0 */
extern int lineno; /* line number in awk program */
extern int errorflag; /* 1 if error has occurred */
extern int donefld; /* 1 if record broken into fields */
extern int donerec; /* 1 if record is valid (no fld has changed */
extern char inputFS[]; /* FS at time of input, for field splitting */
/* node - used in parsed tree */
extern int dbg;
struct node {
int n_type; /* node type */
struct node *n_next; /* pointer to next node */
struct node *n_arg[1]; /* argument (variable length) */
};
extern char *patbeg; /* beginning of pattern matched */
extern int patlen; /* length of pattern matched. set in b.c */
typedef struct node NODE;
/* Cell: all information about a variable or constant */
/* object cell */
typedef struct Cell {
uschar ctype; /* OCELL, OBOOL, OJUMP, etc. */
uschar csub; /* CCON, CTEMP, CFLD, etc. */
char *nval; /* name, for variables only */
char *sval; /* string value */
Awkfloat fval; /* value as number */
int tval; /* type info: STR|NUM|ARR|FCN|FLD|CON|DONTFREE */
struct Cell *cnext; /* ptr to next if chained */
} Cell;
struct cell {
int c_type; /* cell type */
char *c_sval; /* string value */
double c_fval; /* floating value */
};
typedef struct Array { /* symbol table array */
int nelem; /* elements in table right now */
int size; /* size of tab */
Cell **tab; /* hash table pointers */
} Array;
typedef struct cell CELL;
#define NSYMTAB 50 /* initial size of a symbol table */
extern Array *symtab;
/* cell type */
extern Cell *nrloc; /* NR */
extern Cell *fnrloc; /* FNR */
extern Cell *nfloc; /* NF */
extern Cell *rstartloc; /* RSTART */
extern Cell *rlengthloc; /* RLENGTH */
#define UDF 0 /* pass parameter */
#define VAR 1 /* variable */
#define NUM 2 /* number */
#define ARR 4 /* array */
#define STR 8 /* string */
#define REC 16 /* record */
#define FLD 32 /* filed */
#define PAT 64 /* pattern (compiled REGEXPR) */
#define BRK 128 /* break */
#define CNT 256 /* continue */
#define NXT 512 /* next */
#define EXT 1024 /* exit */
#define RTN 2048 /* return */
#define TMP 4096 /* temp cell */
#define POS 8192 /* argument position */
#define FUN 16384 /* function */
/* Cell.tval values: */
#define NUM 01 /* number value is valid */
#define STR 02 /* string value is valid */
#define DONTFREE 04 /* string space is not freeable */
#define CON 010 /* this is a constant */
#define ARR 020 /* this is an array */
#define FCN 040 /* this is a function name */
#define FLD 0100 /* this is a field $1, $2, ... */
#define REC 0200 /* this is $0 */
/* symbol cell - linked to symbol table */
struct symbol {
char *s_name;
CELL *s_val;
struct symbol *s_next;
};
/* function types */
#define FLENGTH 1
#define FSQRT 2
#define FEXP 3
#define FLOG 4
#define FINT 5
#define FSYSTEM 6
#define FRAND 7
#define FSRAND 8
#define FSIN 9
#define FCOS 10
#define FATAN 11
#define FTOUPPER 12
#define FTOLOWER 13
#define FFLUSH 14
/* Node: parse tree is made of nodes, with Cell's at bottom */
typedef struct Node {
int ntype;
struct Node *nnext;
int lineno;
int nobj;
struct Node *narg[1]; /* variable: actual size set by calling malloc */
} Node;
#define NIL ((Node *) 0)
extern Node *winner;
extern Node *nullstat;
extern Node *nullnode;
/* ctypes */
#define OCELL 1
#define OBOOL 2
#define OJUMP 3
/* Cell subtypes: csub */
#define CFREE 7
#define CCOPY 6
#define CCON 5
#define CTEMP 4
#define CNAME 3
#define CVAR 2
#define CFLD 1
#define CUNK 0
/* bool subtypes */
#define BTRUE 11
#define BFALSE 12
/* jump subtypes */
#define JEXIT 21
#define JNEXT 22
#define JBREAK 23
#define JCONT 24
#define JRET 25
#define JNEXTFILE 26
/* node types */
#define NVALUE 1
#define NSTAT 2
#define NEXPR 3
extern int pairstack[], paircnt;
#define notlegal(n) (n <= FIRSTTOKEN || n >= LASTTOKEN || proctab[n-FIRSTTOKEN] == nullproc)
#define isvalue(n) ((n)->ntype == NVALUE)
#define isexpr(n) ((n)->ntype == NEXPR)
#define isjump(n) ((n)->ctype == OJUMP)
#define isexit(n) ((n)->csub == JEXIT)
#define isbreak(n) ((n)->csub == JBREAK)
#define iscont(n) ((n)->csub == JCONT)
#define isnext(n) ((n)->csub == JNEXT || (n)->csub == JNEXTFILE)
#define isret(n) ((n)->csub == JRET)
#define isrec(n) ((n)->tval & REC)
#define isfld(n) ((n)->tval & FLD)
#define isstr(n) ((n)->tval & STR)
#define isnum(n) ((n)->tval & NUM)
#define isarr(n) ((n)->tval & ARR)
#define isfcn(n) ((n)->tval & FCN)
#define istrue(n) ((n)->csub == BTRUE)
#define istemp(n) ((n)->csub == CTEMP)
#define isargument(n) ((n)->nobj == ARG)
/* #define freeable(p) (!((p)->tval & DONTFREE)) */
#define freeable(p) ( ((p)->tval & (STR|DONTFREE)) == STR )
/* structures used by regular expression matching machinery, mostly b.c: */
#define NCHARS (256+3) /* 256 handles 8-bit chars; 128 does 7-bit */
/* watch out in match(), etc. */
#define NSTATES 32
typedef struct rrow {
long ltype; /* long avoids pointer warnings on 64-bit */
union {
int i;
Node *np;
uschar *up;
} lval; /* because Al stores a pointer in it! */
int *lfollow;
} rrow;
typedef struct fa {
uschar gototab[NSTATES][NCHARS];
uschar out[NSTATES];
uschar *restr;
int *posns[NSTATES];
int anchor;
int use;
int initstat;
int curstat;
int accept;
int reset;
struct rrow re[1]; /* variable: actual size set by calling malloc */
} fa;
#include "proto.h"
typedef struct symbol SYMBOL;

View File

@@ -1,486 +0,0 @@
/****************************************************************
Copyright (C) Lucent Technologies 1997
All Rights Reserved
Permission to use, copy, modify, and distribute this software and
its documentation for any purpose and without fee is hereby
granted, provided that the above copyright notice appear in all
copies and that both that the copyright notice and this
permission notice and warranty disclaimer appear in supporting
documentation, and that the name Lucent Technologies or any of
its entities not be used in advertising or publicity pertaining
to distribution of the software without specific, written prior
permission.
LUCENT DISCLAIMS ALL WARRANTIES WITH REGARD TO THIS SOFTWARE,
INCLUDING ALL IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS.
IN NO EVENT SHALL LUCENT OR ANY OF ITS ENTITIES BE LIABLE FOR ANY
SPECIAL, INDIRECT OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES
WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER
IN AN ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION,
ARISING OUT OF OR IN CONNECTION WITH THE USE OR PERFORMANCE OF
THIS SOFTWARE.
****************************************************************/
%{
#include <stdio.h>
#include <string.h>
#include "awk.h"
void checkdup(Node *list, Cell *item);
int yywrap(void) { return(1); }
Node *beginloc = 0;
Node *endloc = 0;
int infunc = 0; /* = 1 if in arglist or body of func */
int inloop = 0; /* = 1 if in while, for, do */
char *curfname = 0; /* current function name */
Node *arglist = 0; /* list of args for current function */
%}
%union {
Node *p;
Cell *cp;
int i;
char *s;
}
%token <i> FIRSTTOKEN /* must be first */
%token <p> PROGRAM PASTAT PASTAT2 XBEGIN XEND
%token <i> NL ',' '{' '(' '|' ';' '/' ')' '}' '[' ']'
%token <i> ARRAY
%token <i> MATCH NOTMATCH MATCHOP
%token <i> FINAL DOT ALL CCL NCCL CHAR OR STAR QUEST PLUS EMPTYRE
%token <i> AND BOR APPEND EQ GE GT LE LT NE IN
%token <i> ARG BLTIN BREAK CLOSE CONTINUE DELETE DO EXIT FOR FUNC
%token <i> SUB GSUB IF INDEX LSUBSTR MATCHFCN NEXT NEXTFILE
%token <i> ADD MINUS MULT DIVIDE MOD
%token <i> ASSIGN ASGNOP ADDEQ SUBEQ MULTEQ DIVEQ MODEQ POWEQ
%token <i> PRINT PRINTF SPRINTF
%token <p> ELSE INTEST CONDEXPR
%token <i> POSTINCR PREINCR POSTDECR PREDECR
%token <cp> VAR IVAR VARNF CALL NUMBER STRING
%token <s> REGEXPR
%type <p> pas pattern ppattern plist pplist patlist prarg term re
%type <p> pa_pat pa_stat pa_stats
%type <s> reg_expr
%type <p> simple_stmt opt_simple_stmt stmt stmtlist
%type <p> var varname funcname varlist
%type <p> for if else while
%type <i> do st
%type <i> pst opt_pst lbrace rbrace rparen comma nl opt_nl and bor
%type <i> subop print
%right ASGNOP
%right '?'
%right ':'
%left BOR
%left AND
%left GETLINE
%nonassoc APPEND EQ GE GT LE LT NE MATCHOP IN '|'
%left ARG BLTIN BREAK CALL CLOSE CONTINUE DELETE DO EXIT FOR FUNC
%left GSUB IF INDEX LSUBSTR MATCHFCN NEXT NUMBER
%left PRINT PRINTF RETURN SPLIT SPRINTF STRING SUB SUBSTR
%left REGEXPR VAR VARNF IVAR WHILE '('
%left CAT
%left '+' '-'
%left '*' '/' '%'
%left NOT UMINUS
%right POWER
%right DECR INCR
%left INDIRECT
%token LASTTOKEN /* must be last */
%%
program:
pas { if (errorflag==0)
winner = (Node *)stat3(PROGRAM, beginloc, $1, endloc); }
| error { yyclearin; bracecheck(); SYNTAX("bailing out"); }
;
and:
AND | and NL
;
bor:
BOR | bor NL
;
comma:
',' | comma NL
;
do:
DO | do NL
;
else:
ELSE | else NL
;
for:
FOR '(' opt_simple_stmt ';' opt_nl pattern ';' opt_nl opt_simple_stmt rparen {inloop++;} stmt
{ --inloop; $$ = stat4(FOR, $3, notnull($6), $9, $12); }
| FOR '(' opt_simple_stmt ';' ';' opt_nl opt_simple_stmt rparen {inloop++;} stmt
{ --inloop; $$ = stat4(FOR, $3, NIL, $7, $10); }
| FOR '(' varname IN varname rparen {inloop++;} stmt
{ --inloop; $$ = stat3(IN, $3, makearr($5), $8); }
;
funcname:
VAR { setfname($1); }
| CALL { setfname($1); }
;
if:
IF '(' pattern rparen { $$ = notnull($3); }
;
lbrace:
'{' | lbrace NL
;
nl:
NL | nl NL
;
opt_nl:
/* empty */ { $$ = 0; }
| nl
;
opt_pst:
/* empty */ { $$ = 0; }
| pst
;
opt_simple_stmt:
/* empty */ { $$ = 0; }
| simple_stmt
;
pas:
opt_pst { $$ = 0; }
| opt_pst pa_stats opt_pst { $$ = $2; }
;
pa_pat:
pattern { $$ = notnull($1); }
;
pa_stat:
pa_pat { $$ = stat2(PASTAT, $1, stat2(PRINT, rectonode(), NIL)); }
| pa_pat lbrace stmtlist '}' { $$ = stat2(PASTAT, $1, $3); }
| pa_pat ',' pa_pat { $$ = pa2stat($1, $3, stat2(PRINT, rectonode(), NIL)); }
| pa_pat ',' pa_pat lbrace stmtlist '}' { $$ = pa2stat($1, $3, $5); }
| lbrace stmtlist '}' { $$ = stat2(PASTAT, NIL, $2); }
| XBEGIN lbrace stmtlist '}'
{ beginloc = linkum(beginloc, $3); $$ = 0; }
| XEND lbrace stmtlist '}'
{ endloc = linkum(endloc, $3); $$ = 0; }
| FUNC funcname '(' varlist rparen {infunc++;} lbrace stmtlist '}'
{ infunc--; curfname=0; defn((Cell *)$2, $4, $8); $$ = 0; }
;
pa_stats:
pa_stat
| pa_stats opt_pst pa_stat { $$ = linkum($1, $3); }
;
patlist:
pattern
| patlist comma pattern { $$ = linkum($1, $3); }
;
ppattern:
var ASGNOP ppattern { $$ = op2($2, $1, $3); }
| ppattern '?' ppattern ':' ppattern %prec '?'
{ $$ = op3(CONDEXPR, notnull($1), $3, $5); }
| ppattern bor ppattern %prec BOR
{ $$ = op2(BOR, notnull($1), notnull($3)); }
| ppattern and ppattern %prec AND
{ $$ = op2(AND, notnull($1), notnull($3)); }
| ppattern MATCHOP reg_expr { $$ = op3($2, NIL, $1, (Node*)makedfa($3, 0)); }
| ppattern MATCHOP ppattern
{ if (constnode($3))
$$ = op3($2, NIL, $1, (Node*)makedfa(strnode($3), 0));
else
$$ = op3($2, (Node *)1, $1, $3); }
| ppattern IN varname { $$ = op2(INTEST, $1, makearr($3)); }
| '(' plist ')' IN varname { $$ = op2(INTEST, $2, makearr($5)); }
| ppattern term %prec CAT { $$ = op2(CAT, $1, $2); }
| re
| term
;
pattern:
var ASGNOP pattern { $$ = op2($2, $1, $3); }
| pattern '?' pattern ':' pattern %prec '?'
{ $$ = op3(CONDEXPR, notnull($1), $3, $5); }
| pattern bor pattern %prec BOR
{ $$ = op2(BOR, notnull($1), notnull($3)); }
| pattern and pattern %prec AND
{ $$ = op2(AND, notnull($1), notnull($3)); }
| pattern EQ pattern { $$ = op2($2, $1, $3); }
| pattern GE pattern { $$ = op2($2, $1, $3); }
| pattern GT pattern { $$ = op2($2, $1, $3); }
| pattern LE pattern { $$ = op2($2, $1, $3); }
| pattern LT pattern { $$ = op2($2, $1, $3); }
| pattern NE pattern { $$ = op2($2, $1, $3); }
| pattern MATCHOP reg_expr { $$ = op3($2, NIL, $1, (Node*)makedfa($3, 0)); }
| pattern MATCHOP pattern
{ if (constnode($3))
$$ = op3($2, NIL, $1, (Node*)makedfa(strnode($3), 0));
else
$$ = op3($2, (Node *)1, $1, $3); }
| pattern IN varname { $$ = op2(INTEST, $1, makearr($3)); }
| '(' plist ')' IN varname { $$ = op2(INTEST, $2, makearr($5)); }
| pattern '|' GETLINE var {
if (safe) SYNTAX("cmd | getline is unsafe");
else $$ = op3(GETLINE, $4, itonp($2), $1); }
| pattern '|' GETLINE {
if (safe) SYNTAX("cmd | getline is unsafe");
else $$ = op3(GETLINE, (Node*)0, itonp($2), $1); }
| pattern term %prec CAT { $$ = op2(CAT, $1, $2); }
| re
| term
;
plist:
pattern comma pattern { $$ = linkum($1, $3); }
| plist comma pattern { $$ = linkum($1, $3); }
;
pplist:
ppattern
| pplist comma ppattern { $$ = linkum($1, $3); }
;
prarg:
/* empty */ { $$ = rectonode(); }
| pplist
| '(' plist ')' { $$ = $2; }
;
print:
PRINT | PRINTF
;
pst:
NL | ';' | pst NL | pst ';'
;
rbrace:
'}' | rbrace NL
;
re:
reg_expr
{ $$ = op3(MATCH, NIL, rectonode(), (Node*)makedfa($1, 0)); }
| NOT re { $$ = op1(NOT, notnull($2)); }
;
reg_expr:
'/' {startreg();} REGEXPR '/' { $$ = $3; }
;
rparen:
')' | rparen NL
;
simple_stmt:
print prarg '|' term {
if (safe) SYNTAX("print | is unsafe");
else $$ = stat3($1, $2, itonp($3), $4); }
| print prarg APPEND term {
if (safe) SYNTAX("print >> is unsafe");
else $$ = stat3($1, $2, itonp($3), $4); }
| print prarg GT term {
if (safe) SYNTAX("print > is unsafe");
else $$ = stat3($1, $2, itonp($3), $4); }
| print prarg { $$ = stat3($1, $2, NIL, NIL); }
| DELETE varname '[' patlist ']' { $$ = stat2(DELETE, makearr($2), $4); }
| DELETE varname { $$ = stat2(DELETE, makearr($2), 0); }
| pattern { $$ = exptostat($1); }
| error { yyclearin; SYNTAX("illegal statement"); }
;
st:
nl
| ';' opt_nl
;
stmt:
BREAK st { if (!inloop) SYNTAX("break illegal outside of loops");
$$ = stat1(BREAK, NIL); }
| CONTINUE st { if (!inloop) SYNTAX("continue illegal outside of loops");
$$ = stat1(CONTINUE, NIL); }
| do {inloop++;} stmt {--inloop;} WHILE '(' pattern ')' st
{ $$ = stat2(DO, $3, notnull($7)); }
| EXIT pattern st { $$ = stat1(EXIT, $2); }
| EXIT st { $$ = stat1(EXIT, NIL); }
| for
| if stmt else stmt { $$ = stat3(IF, $1, $2, $4); }
| if stmt { $$ = stat3(IF, $1, $2, NIL); }
| lbrace stmtlist rbrace { $$ = $2; }
| NEXT st { if (infunc)
SYNTAX("next is illegal inside a function");
$$ = stat1(NEXT, NIL); }
| NEXTFILE st { if (infunc)
SYNTAX("nextfile is illegal inside a function");
$$ = stat1(NEXTFILE, NIL); }
| RETURN pattern st { $$ = stat1(RETURN, $2); }
| RETURN st { $$ = stat1(RETURN, NIL); }
| simple_stmt st
| while {inloop++;} stmt { --inloop; $$ = stat2(WHILE, $1, $3); }
| ';' opt_nl { $$ = 0; }
;
stmtlist:
stmt
| stmtlist stmt { $$ = linkum($1, $2); }
;
subop:
SUB | GSUB
;
term:
term '/' ASGNOP term { $$ = op2(DIVEQ, $1, $4); }
| term '+' term { $$ = op2(ADD, $1, $3); }
| term '-' term { $$ = op2(MINUS, $1, $3); }
| term '*' term { $$ = op2(MULT, $1, $3); }
| term '/' term { $$ = op2(DIVIDE, $1, $3); }
| term '%' term { $$ = op2(MOD, $1, $3); }
| term POWER term { $$ = op2(POWER, $1, $3); }
| '-' term %prec UMINUS { $$ = op1(UMINUS, $2); }
| '+' term %prec UMINUS { $$ = $2; }
| NOT term %prec UMINUS { $$ = op1(NOT, notnull($2)); }
| BLTIN '(' ')' { $$ = op2(BLTIN, itonp($1), rectonode()); }
| BLTIN '(' patlist ')' { $$ = op2(BLTIN, itonp($1), $3); }
| BLTIN { $$ = op2(BLTIN, itonp($1), rectonode()); }
| CALL '(' ')' { $$ = op2(CALL, celltonode($1,CVAR), NIL); }
| CALL '(' patlist ')' { $$ = op2(CALL, celltonode($1,CVAR), $3); }
| CLOSE term { $$ = op1(CLOSE, $2); }
| DECR var { $$ = op1(PREDECR, $2); }
| INCR var { $$ = op1(PREINCR, $2); }
| var DECR { $$ = op1(POSTDECR, $1); }
| var INCR { $$ = op1(POSTINCR, $1); }
| GETLINE var LT term { $$ = op3(GETLINE, $2, itonp($3), $4); }
| GETLINE LT term { $$ = op3(GETLINE, NIL, itonp($2), $3); }
| GETLINE var { $$ = op3(GETLINE, $2, NIL, NIL); }
| GETLINE { $$ = op3(GETLINE, NIL, NIL, NIL); }
| INDEX '(' pattern comma pattern ')'
{ $$ = op2(INDEX, $3, $5); }
| INDEX '(' pattern comma reg_expr ')'
{ SYNTAX("index() doesn't permit regular expressions");
$$ = op2(INDEX, $3, (Node*)$5); }
| '(' pattern ')' { $$ = $2; }
| MATCHFCN '(' pattern comma reg_expr ')'
{ $$ = op3(MATCHFCN, NIL, $3, (Node*)makedfa($5, 1)); }
| MATCHFCN '(' pattern comma pattern ')'
{ if (constnode($5))
$$ = op3(MATCHFCN, NIL, $3, (Node*)makedfa(strnode($5), 1));
else
$$ = op3(MATCHFCN, (Node *)1, $3, $5); }
| NUMBER { $$ = celltonode($1, CCON); }
| SPLIT '(' pattern comma varname comma pattern ')' /* string */
{ $$ = op4(SPLIT, $3, makearr($5), $7, (Node*)STRING); }
| SPLIT '(' pattern comma varname comma reg_expr ')' /* const /regexp/ */
{ $$ = op4(SPLIT, $3, makearr($5), (Node*)makedfa($7, 1), (Node *)REGEXPR); }
| SPLIT '(' pattern comma varname ')'
{ $$ = op4(SPLIT, $3, makearr($5), NIL, (Node*)STRING); } /* default */
| SPRINTF '(' patlist ')' { $$ = op1($1, $3); }
| STRING { $$ = celltonode($1, CCON); }
| subop '(' reg_expr comma pattern ')'
{ $$ = op4($1, NIL, (Node*)makedfa($3, 1), $5, rectonode()); }
| subop '(' pattern comma pattern ')'
{ if (constnode($3))
$$ = op4($1, NIL, (Node*)makedfa(strnode($3), 1), $5, rectonode());
else
$$ = op4($1, (Node *)1, $3, $5, rectonode()); }
| subop '(' reg_expr comma pattern comma var ')'
{ $$ = op4($1, NIL, (Node*)makedfa($3, 1), $5, $7); }
| subop '(' pattern comma pattern comma var ')'
{ if (constnode($3))
$$ = op4($1, NIL, (Node*)makedfa(strnode($3), 1), $5, $7);
else
$$ = op4($1, (Node *)1, $3, $5, $7); }
| SUBSTR '(' pattern comma pattern comma pattern ')'
{ $$ = op3(SUBSTR, $3, $5, $7); }
| SUBSTR '(' pattern comma pattern ')'
{ $$ = op3(SUBSTR, $3, $5, NIL); }
| var
;
var:
varname
| varname '[' patlist ']' { $$ = op2(ARRAY, makearr($1), $3); }
| IVAR { $$ = op1(INDIRECT, celltonode($1, CVAR)); }
| INDIRECT term { $$ = op1(INDIRECT, $2); }
;
varlist:
/* nothing */ { arglist = $$ = 0; }
| VAR { arglist = $$ = celltonode($1,CVAR); }
| varlist comma VAR {
checkdup($1, $3);
arglist = $$ = linkum($1,celltonode($3,CVAR)); }
;
varname:
VAR { $$ = celltonode($1, CVAR); }
| ARG { $$ = op1(ARG, itonp($1)); }
| VARNF { $$ = op1(VARNF, (Node *) $1); }
;
while:
WHILE '(' pattern rparen { $$ = notnull($3); }
;
%%
void setfname(Cell *p)
{
if (isarr(p))
SYNTAX("%s is an array, not a function", p->nval);
else if (isfcn(p))
SYNTAX("you can't define function %s more than once", p->nval);
curfname = p->nval;
}
int constnode(Node *p)
{
return isvalue(p) && ((Cell *) (p->narg[0]))->csub == CCON;
}
char *strnode(Node *p)
{
return ((Cell *)(p->narg[0]))->sval;
}
Node *notnull(Node *n)
{
switch (n->nobj) {
case LE: case LT: case EQ: case NE: case GT: case GE:
case BOR: case AND: case NOT:
return n;
default:
return op2(NE, n, nullnode);
}
}
void checkdup(Node *vl, Cell *cp) /* check if name already in list */
{
char *s = cp->nval;
for ( ; vl; vl = vl->nnext) {
if (strcmp(s, ((Cell *)(vl->narg[0]))->nval) == 0) {
SYNTAX("duplicate argument %s", s);
break;
}
}
}

View File

@@ -1,954 +0,0 @@
/****************************************************************
Copyright (C) Lucent Technologies 1997
All Rights Reserved
Permission to use, copy, modify, and distribute this software and
its documentation for any purpose and without fee is hereby
granted, provided that the above copyright notice appear in all
copies and that both that the copyright notice and this
permission notice and warranty disclaimer appear in supporting
documentation, and that the name Lucent Technologies or any of
its entities not be used in advertising or publicity pertaining
to distribution of the software without specific, written prior
permission.
LUCENT DISCLAIMS ALL WARRANTIES WITH REGARD TO THIS SOFTWARE,
INCLUDING ALL IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS.
IN NO EVENT SHALL LUCENT OR ANY OF ITS ENTITIES BE LIABLE FOR ANY
SPECIAL, INDIRECT OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES
WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER
IN AN ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION,
ARISING OUT OF OR IN CONNECTION WITH THE USE OR PERFORMANCE OF
THIS SOFTWARE.
****************************************************************/
/* lasciate ogne speranza, voi ch'intrate. */
#define DEBUG
#include <ctype.h>
#include <stdio.h>
#include <string.h>
#include <stdlib.h>
#include "awk.h"
#include "awkgram.h"
#define HAT (NCHARS+2) /* matches ^ in regular expr */
/* NCHARS is 2**n */
#define MAXLIN 22
#define type(v) (v)->nobj /* badly overloaded here */
#define info(v) (v)->ntype /* badly overloaded here */
#define left(v) (v)->narg[0]
#define right(v) (v)->narg[1]
#define parent(v) (v)->nnext
#define LEAF case CCL: case NCCL: case CHAR: case DOT: case FINAL: case ALL:
#define ELEAF case EMPTYRE: /* empty string in regexp */
#define UNARY case STAR: case PLUS: case QUEST:
/* encoding in tree Nodes:
leaf (CCL, NCCL, CHAR, DOT, FINAL, ALL, EMPTYRE):
left is index, right contains value or pointer to value
unary (STAR, PLUS, QUEST): left is child, right is null
binary (CAT, OR): left and right are children
parent contains pointer to parent
*/
int *setvec;
int *tmpset;
int maxsetvec = 0;
int rtok; /* next token in current re */
int rlxval;
static uschar *rlxstr;
static uschar *prestr; /* current position in current re */
static uschar *lastre; /* origin of last re */
static int setcnt;
static int poscnt;
char *patbeg;
int patlen;
#define NFA 20 /* cache this many dynamic fa's */
fa *fatab[NFA];
int nfatab = 0; /* entries in fatab */
fa *makedfa(const char *s, int anchor) /* returns dfa for reg expr s */
{
int i, use, nuse;
fa *pfa;
static int now = 1;
if (setvec == 0) { /* first time through any RE */
maxsetvec = MAXLIN;
setvec = (int *) malloc(maxsetvec * sizeof(int));
tmpset = (int *) malloc(maxsetvec * sizeof(int));
if (setvec == 0 || tmpset == 0)
overflo("out of space initializing makedfa");
}
if (compile_time) /* a constant for sure */
return mkdfa(s, anchor);
for (i = 0; i < nfatab; i++) /* is it there already? */
if (fatab[i]->anchor == anchor
&& strcmp((const char *) fatab[i]->restr, s) == 0) {
fatab[i]->use = now++;
return fatab[i];
}
pfa = mkdfa(s, anchor);
if (nfatab < NFA) { /* room for another */
fatab[nfatab] = pfa;
fatab[nfatab]->use = now++;
nfatab++;
return pfa;
}
use = fatab[0]->use; /* replace least-recently used */
nuse = 0;
for (i = 1; i < nfatab; i++)
if (fatab[i]->use < use) {
use = fatab[i]->use;
nuse = i;
}
freefa(fatab[nuse]);
fatab[nuse] = pfa;
pfa->use = now++;
return pfa;
}
fa *mkdfa(const char *s, int anchor) /* does the real work of making a dfa */
/* anchor = 1 for anchored matches, else 0 */
{
Node *p, *p1;
fa *f;
p = reparse(s);
p1 = op2(CAT, op2(STAR, op2(ALL, NIL, NIL), NIL), p);
/* put ALL STAR in front of reg. exp. */
p1 = op2(CAT, p1, op2(FINAL, NIL, NIL));
/* put FINAL after reg. exp. */
poscnt = 0;
penter(p1); /* enter parent pointers and leaf indices */
if ((f = (fa *) calloc(1, sizeof(fa) + poscnt*sizeof(rrow))) == NULL)
overflo("out of space for fa");
f->accept = poscnt-1; /* penter has computed number of positions in re */
cfoll(f, p1); /* set up follow sets */
freetr(p1);
if ((f->posns[0] = (int *) calloc(1, *(f->re[0].lfollow)*sizeof(int))) == NULL)
overflo("out of space in makedfa");
if ((f->posns[1] = (int *) calloc(1, sizeof(int))) == NULL)
overflo("out of space in makedfa");
*f->posns[1] = 0;
f->initstat = makeinit(f, anchor);
f->anchor = anchor;
f->restr = (uschar *) tostring(s);
return f;
}
int makeinit(fa *f, int anchor)
{
int i, k;
f->curstat = 2;
f->out[2] = 0;
f->reset = 0;
k = *(f->re[0].lfollow);
xfree(f->posns[2]);
if ((f->posns[2] = (int *) calloc(1, (k+1)*sizeof(int))) == NULL)
overflo("out of space in makeinit");
for (i=0; i <= k; i++) {
(f->posns[2])[i] = (f->re[0].lfollow)[i];
}
if ((f->posns[2])[1] == f->accept)
f->out[2] = 1;
for (i=0; i < NCHARS; i++)
f->gototab[2][i] = 0;
f->curstat = cgoto(f, 2, HAT);
if (anchor) {
*f->posns[2] = k-1; /* leave out position 0 */
for (i=0; i < k; i++) {
(f->posns[0])[i] = (f->posns[2])[i];
}
f->out[0] = f->out[2];
if (f->curstat != 2)
--(*f->posns[f->curstat]);
}
return f->curstat;
}
void penter(Node *p) /* set up parent pointers and leaf indices */
{
switch (type(p)) {
ELEAF
LEAF
info(p) = poscnt;
poscnt++;
break;
UNARY
penter(left(p));
parent(left(p)) = p;
break;
case CAT:
case OR:
penter(left(p));
penter(right(p));
parent(left(p)) = p;
parent(right(p)) = p;
break;
default: /* can't happen */
FATAL("can't happen: unknown type %d in penter", type(p));
break;
}
}
void freetr(Node *p) /* free parse tree */
{
switch (type(p)) {
ELEAF
LEAF
xfree(p);
break;
UNARY
freetr(left(p));
xfree(p);
break;
case CAT:
case OR:
freetr(left(p));
freetr(right(p));
xfree(p);
break;
default: /* can't happen */
FATAL("can't happen: unknown type %d in freetr", type(p));
break;
}
}
/* in the parsing of regular expressions, metacharacters like . have */
/* to be seen literally; \056 is not a metacharacter. */
int hexstr(char **pp) /* find and eval hex string at pp, return new p */
{ /* only pick up one 8-bit byte (2 chars) */
uschar *p;
int n = 0;
int i;
for (i = 0, p = (uschar *) *pp; i < 2 && isxdigit(*p); i++, p++) {
if (isdigit(*p))
n = 16 * n + *p - '0';
else if (*p >= 'a' && *p <= 'f')
n = 16 * n + *p - 'a' + 10;
else if (*p >= 'A' && *p <= 'F')
n = 16 * n + *p - 'A' + 10;
}
*pp = (char *) p;
return n;
}
#define isoctdigit(c) ((c) >= '0' && (c) <= '7') /* multiple use of arg */
int quoted(char **pp) /* pick up next thing after a \\ */
/* and increment *pp */
{
char *p = *pp;
int c;
if ((c = *p++) == 't')
c = '\t';
else if (c == 'n')
c = '\n';
else if (c == 'f')
c = '\f';
else if (c == 'r')
c = '\r';
else if (c == 'b')
c = '\b';
else if (c == '\\')
c = '\\';
else if (c == 'x') { /* hexadecimal goo follows */
c = hexstr(&p); /* this adds a null if number is invalid */
} else if (isoctdigit(c)) { /* \d \dd \ddd */
int n = c - '0';
if (isoctdigit(*p)) {
n = 8 * n + *p++ - '0';
if (isoctdigit(*p))
n = 8 * n + *p++ - '0';
}
c = n;
} /* else */
/* c = c; */
*pp = p;
return c;
}
char *cclenter(const char *argp) /* add a character class */
{
int i, c, c2;
uschar *p = (uschar *) argp;
uschar *op, *bp;
static uschar *buf = 0;
static int bufsz = 100;
op = p;
if (buf == 0 && (buf = (uschar *) malloc(bufsz)) == NULL)
FATAL("out of space for character class [%.10s...] 1", p);
bp = buf;
for (i = 0; (c = *p++) != 0; ) {
if (c == '\\') {
c = quoted((char **) &p);
} else if (c == '-' && i > 0 && bp[-1] != 0) {
if (*p != 0) {
c = bp[-1];
c2 = *p++;
if (c2 == '\\')
c2 = quoted((char **) &p);
if (c > c2) { /* empty; ignore */
bp--;
i--;
continue;
}
while (c < c2) {
if (!adjbuf((char **) &buf, &bufsz, bp-buf+2, 100, (char **) &bp, "cclenter1"))
FATAL("out of space for character class [%.10s...] 2", p);
*bp++ = ++c;
i++;
}
continue;
}
}
if (!adjbuf((char **) &buf, &bufsz, bp-buf+2, 100, (char **) &bp, "cclenter2"))
FATAL("out of space for character class [%.10s...] 3", p);
*bp++ = c;
i++;
}
*bp = 0;
dprintf( ("cclenter: in = |%s|, out = |%s|\n", op, buf) );
xfree(op);
return (char *) tostring((char *) buf);
}
void overflo(const char *s)
{
FATAL("regular expression too big: %.30s...", s);
}
void cfoll(fa *f, Node *v) /* enter follow set of each leaf of vertex v into lfollow[leaf] */
{
int i;
int *p;
switch (type(v)) {
ELEAF
LEAF
f->re[info(v)].ltype = type(v);
f->re[info(v)].lval.np = right(v);
while (f->accept >= maxsetvec) { /* guessing here! */
maxsetvec *= 4;
setvec = (int *) realloc(setvec, maxsetvec * sizeof(int));
tmpset = (int *) realloc(tmpset, maxsetvec * sizeof(int));
if (setvec == 0 || tmpset == 0)
overflo("out of space in cfoll()");
}
for (i = 0; i <= f->accept; i++)
setvec[i] = 0;
setcnt = 0;
follow(v); /* computes setvec and setcnt */
if ((p = (int *) calloc(1, (setcnt+1)*sizeof(int))) == NULL)
overflo("out of space building follow set");
f->re[info(v)].lfollow = p;
*p = setcnt;
for (i = f->accept; i >= 0; i--)
if (setvec[i] == 1)
*++p = i;
break;
UNARY
cfoll(f,left(v));
break;
case CAT:
case OR:
cfoll(f,left(v));
cfoll(f,right(v));
break;
default: /* can't happen */
FATAL("can't happen: unknown type %d in cfoll", type(v));
}
}
int first(const Node *p) /* collects initially active leaves of p into setvec */
/* returns 0 if p matches empty string */
{
int b, lp;
switch (type(p)) {
ELEAF
LEAF
lp = info(p); /* look for high-water mark of subscripts */
while (setcnt >= maxsetvec || lp >= maxsetvec) { /* guessing here! */
maxsetvec *= 4;
setvec = (int *) realloc(setvec, maxsetvec * sizeof(int));
tmpset = (int *) realloc(tmpset, maxsetvec * sizeof(int));
if (setvec == 0 || tmpset == 0)
overflo("out of space in first()");
}
if (type(p) == EMPTYRE) {
setvec[lp] = 0;
return(0);
}
if (setvec[lp] != 1) {
setvec[lp] = 1;
setcnt++;
}
if (type(p) == CCL && (*(char *) right(p)) == '\0')
return(0); /* empty CCL */
else return(1);
case PLUS:
if (first(left(p)) == 0) return(0);
return(1);
case STAR:
case QUEST:
first(left(p));
return(0);
case CAT:
if (first(left(p)) == 0 && first(right(p)) == 0) return(0);
return(1);
case OR:
b = first(right(p));
if (first(left(p)) == 0 || b == 0) return(0);
return(1);
}
FATAL("can't happen: unknown type %d in first", type(p)); /* can't happen */
return(-1);
}
void follow(Node *v) /* collects leaves that can follow v into setvec */
{
Node *p;
if (type(v) == FINAL)
return;
p = parent(v);
switch (type(p)) {
case STAR:
case PLUS:
first(v);
follow(p);
return;
case OR:
case QUEST:
follow(p);
return;
case CAT:
if (v == left(p)) { /* v is left child of p */
if (first(right(p)) == 0) {
follow(p);
return;
}
} else /* v is right child */
follow(p);
return;
}
}
int member(int c, const char *sarg) /* is c in s? */
{
uschar *s = (uschar *) sarg;
while (*s)
if (c == *s++)
return(1);
return(0);
}
int match(fa *f, const char *p0) /* shortest match ? */
{
int s, ns;
uschar *p = (uschar *) p0;
s = f->reset ? makeinit(f,0) : f->initstat;
if (f->out[s])
return(1);
do {
/* assert(*p < NCHARS); */
if ((ns = f->gototab[s][*p]) != 0)
s = ns;
else
s = cgoto(f, s, *p);
if (f->out[s])
return(1);
} while (*p++ != 0);
return(0);
}
int pmatch(fa *f, const char *p0) /* longest match, for sub */
{
int s, ns;
uschar *p = (uschar *) p0;
uschar *q;
int i, k;
/* s = f->reset ? makeinit(f,1) : f->initstat; */
if (f->reset) {
f->initstat = s = makeinit(f,1);
} else {
s = f->initstat;
}
patbeg = (char *) p;
patlen = -1;
do {
q = p;
do {
if (f->out[s]) /* final state */
patlen = q-p;
/* assert(*q < NCHARS); */
if ((ns = f->gototab[s][*q]) != 0)
s = ns;
else
s = cgoto(f, s, *q);
if (s == 1) { /* no transition */
if (patlen >= 0) {
patbeg = (char *) p;
return(1);
}
else
goto nextin; /* no match */
}
} while (*q++ != 0);
if (f->out[s])
patlen = q-p-1; /* don't count $ */
if (patlen >= 0) {
patbeg = (char *) p;
return(1);
}
nextin:
s = 2;
if (f->reset) {
for (i = 2; i <= f->curstat; i++)
xfree(f->posns[i]);
k = *f->posns[0];
if ((f->posns[2] = (int *) calloc(1, (k+1)*sizeof(int))) == NULL)
overflo("out of space in pmatch");
for (i = 0; i <= k; i++)
(f->posns[2])[i] = (f->posns[0])[i];
f->initstat = f->curstat = 2;
f->out[2] = f->out[0];
for (i = 0; i < NCHARS; i++)
f->gototab[2][i] = 0;
}
} while (*p++ != 0);
return (0);
}
int nematch(fa *f, const char *p0) /* non-empty match, for sub */
{
int s, ns;
uschar *p = (uschar *) p0;
uschar *q;
int i, k;
/* s = f->reset ? makeinit(f,1) : f->initstat; */
if (f->reset) {
f->initstat = s = makeinit(f,1);
} else {
s = f->initstat;
}
patlen = -1;
while (*p) {
q = p;
do {
if (f->out[s]) /* final state */
patlen = q-p;
/* assert(*q < NCHARS); */
if ((ns = f->gototab[s][*q]) != 0)
s = ns;
else
s = cgoto(f, s, *q);
if (s == 1) { /* no transition */
if (patlen > 0) {
patbeg = (char *) p;
return(1);
} else
goto nnextin; /* no nonempty match */
}
} while (*q++ != 0);
if (f->out[s])
patlen = q-p-1; /* don't count $ */
if (patlen > 0 ) {
patbeg = (char *) p;
return(1);
}
nnextin:
s = 2;
if (f->reset) {
for (i = 2; i <= f->curstat; i++)
xfree(f->posns[i]);
k = *f->posns[0];
if ((f->posns[2] = (int *) calloc(1, (k+1)*sizeof(int))) == NULL)
overflo("out of state space");
for (i = 0; i <= k; i++)
(f->posns[2])[i] = (f->posns[0])[i];
f->initstat = f->curstat = 2;
f->out[2] = f->out[0];
for (i = 0; i < NCHARS; i++)
f->gototab[2][i] = 0;
}
p++;
}
return (0);
}
Node *reparse(const char *p) /* parses regular expression pointed to by p */
{ /* uses relex() to scan regular expression */
Node *np;
dprintf( ("reparse <%s>\n", p) );
lastre = prestr = (uschar *) p; /* prestr points to string to be parsed */
rtok = relex();
/* GNU compatibility: an empty regexp matches anything */
if (rtok == '\0') {
/* FATAL("empty regular expression"); previous */
return(op2(EMPTYRE, NIL, NIL));
}
np = regexp();
if (rtok != '\0')
FATAL("syntax error in regular expression %s at %s", lastre, prestr);
return(np);
}
Node *regexp(void) /* top-level parse of reg expr */
{
return (alt(concat(primary())));
}
Node *primary(void)
{
Node *np;
switch (rtok) {
case CHAR:
np = op2(CHAR, NIL, itonp(rlxval));
rtok = relex();
return (unary(np));
case ALL:
rtok = relex();
return (unary(op2(ALL, NIL, NIL)));
case EMPTYRE:
rtok = relex();
return (unary(op2(ALL, NIL, NIL)));
case DOT:
rtok = relex();
return (unary(op2(DOT, NIL, NIL)));
case CCL:
np = op2(CCL, NIL, (Node*) cclenter((char *) rlxstr));
rtok = relex();
return (unary(np));
case NCCL:
np = op2(NCCL, NIL, (Node *) cclenter((char *) rlxstr));
rtok = relex();
return (unary(np));
case '^':
rtok = relex();
return (unary(op2(CHAR, NIL, itonp(HAT))));
case '$':
rtok = relex();
return (unary(op2(CHAR, NIL, NIL)));
case '(':
rtok = relex();
if (rtok == ')') { /* special pleading for () */
rtok = relex();
return unary(op2(CCL, NIL, (Node *) tostring("")));
}
np = regexp();
if (rtok == ')') {
rtok = relex();
return (unary(np));
}
else
FATAL("syntax error in regular expression %s at %s", lastre, prestr);
default:
FATAL("illegal primary in regular expression %s at %s", lastre, prestr);
}
return 0; /*NOTREACHED*/
}
Node *concat(Node *np)
{
switch (rtok) {
case CHAR: case DOT: case ALL: case EMPTYRE: case CCL: case NCCL: case '$': case '(':
return (concat(op2(CAT, np, primary())));
}
return (np);
}
Node *alt(Node *np)
{
if (rtok == OR) {
rtok = relex();
return (alt(op2(OR, np, concat(primary()))));
}
return (np);
}
Node *unary(Node *np)
{
switch (rtok) {
case STAR:
rtok = relex();
return (unary(op2(STAR, np, NIL)));
case PLUS:
rtok = relex();
return (unary(op2(PLUS, np, NIL)));
case QUEST:
rtok = relex();
return (unary(op2(QUEST, np, NIL)));
default:
return (np);
}
}
/*
* Character class definitions conformant to the POSIX locale as
* defined in IEEE P1003.1 draft 7 of June 2001, assuming the source
* and operating character sets are both ASCII (ISO646) or supersets
* thereof.
*
* Note that to avoid overflowing the temporary buffer used in
* relex(), the expanded character class (prior to range expansion)
* must be less than twice the size of their full name.
*/
/* Because isblank doesn't show up in any of the header files on any
* system i use, it's defined here. if some other locale has a richer
* definition of "blank", define HAS_ISBLANK and provide your own
* version.
* the parentheses here are an attempt to find a path through the maze
* of macro definition and/or function and/or version provided. thanks
* to nelson beebe for the suggestion; let's see if it works everywhere.
*/
/* #define HAS_ISBLANK */
#ifndef HAS_ISBLANK
int (xisblank)(int c)
{
return c==' ' || c=='\t';
}
#endif
struct charclass {
const char *cc_name;
int cc_namelen;
int (*cc_func)(int);
} charclasses[] = {
{ "alnum", 5, isalnum },
{ "alpha", 5, isalpha },
{ "blank", 5, isspace }, /* was isblank */
{ "cntrl", 5, iscntrl },
{ "digit", 5, isdigit },
{ "graph", 5, isgraph },
{ "lower", 5, islower },
{ "print", 5, isprint },
{ "punct", 5, ispunct },
{ "space", 5, isspace },
{ "upper", 5, isupper },
{ "xdigit", 6, isxdigit },
{ NULL, 0, NULL },
};
int relex(void) /* lexical analyzer for reparse */
{
int c, n;
int cflag;
static uschar *buf = 0;
static int bufsz = 100;
uschar *bp;
struct charclass *cc;
int i;
switch (c = *prestr++) {
case '|': return OR;
case '*': return STAR;
case '+': return PLUS;
case '?': return QUEST;
case '.': return DOT;
case '\0': prestr--; return '\0';
case '^':
case '$':
case '(':
case ')':
return c;
case '\\':
rlxval = quoted((char **) &prestr);
return CHAR;
default:
rlxval = c;
return CHAR;
case '[':
if (buf == 0 && (buf = (uschar *) malloc(bufsz)) == NULL)
FATAL("out of space in reg expr %.10s..", lastre);
bp = buf;
if (*prestr == '^') {
cflag = 1;
prestr++;
}
else
cflag = 0;
n = 2 * strlen((const char *) prestr)+1;
if (!adjbuf((char **) &buf, &bufsz, n, n, (char **) &bp, "relex1"))
FATAL("out of space for reg expr %.10s...", lastre);
for (; ; ) {
if ((c = *prestr++) == '\\') {
*bp++ = '\\';
if ((c = *prestr++) == '\0')
FATAL("nonterminated character class %.20s...", lastre);
*bp++ = c;
/* } else if (c == '\n') { */
/* FATAL("newline in character class %.20s...", lastre); */
} else if (c == '[' && *prestr == ':') {
/* POSIX char class names, Dag-Erling Smorgrav, des@ofug.org */
for (cc = charclasses; cc->cc_name; cc++)
if (strncmp((const char *) prestr + 1, (const char *) cc->cc_name, cc->cc_namelen) == 0)
break;
if (cc->cc_name != NULL && prestr[1 + cc->cc_namelen] == ':' &&
prestr[2 + cc->cc_namelen] == ']') {
prestr += cc->cc_namelen + 3;
for (i = 0; i < NCHARS; i++) {
if (!adjbuf((char **) &buf, &bufsz, bp-buf+1, 100, (char **) &bp, "relex2"))
FATAL("out of space for reg expr %.10s...", lastre);
if (cc->cc_func(i)) {
*bp++ = i;
n++;
}
}
} else
*bp++ = c;
} else if (c == '\0') {
FATAL("nonterminated character class %.20s", lastre);
} else if (bp == buf) { /* 1st char is special */
*bp++ = c;
} else if (c == ']') {
*bp++ = 0;
rlxstr = (uschar *) tostring((char *) buf);
if (cflag == 0)
return CCL;
else
return NCCL;
} else
*bp++ = c;
}
}
}
int cgoto(fa *f, int s, int c)
{
int i, j, k;
int *p, *q;
assert(c == HAT || c < NCHARS);
while (f->accept >= maxsetvec) { /* guessing here! */
maxsetvec *= 4;
setvec = (int *) realloc(setvec, maxsetvec * sizeof(int));
tmpset = (int *) realloc(tmpset, maxsetvec * sizeof(int));
if (setvec == 0 || tmpset == 0)
overflo("out of space in cgoto()");
}
for (i = 0; i <= f->accept; i++)
setvec[i] = 0;
setcnt = 0;
/* compute positions of gototab[s,c] into setvec */
p = f->posns[s];
for (i = 1; i <= *p; i++) {
if ((k = f->re[p[i]].ltype) != FINAL) {
if ((k == CHAR && c == ptoi(f->re[p[i]].lval.np))
|| (k == DOT && c != 0 && c != HAT)
|| (k == ALL && c != 0)
|| (k == EMPTYRE && c != 0)
|| (k == CCL && member(c, (char *) f->re[p[i]].lval.up))
|| (k == NCCL && !member(c, (char *) f->re[p[i]].lval.up) && c != 0 && c != HAT)) {
q = f->re[p[i]].lfollow;
for (j = 1; j <= *q; j++) {
if (q[j] >= maxsetvec) {
maxsetvec *= 4;
setvec = (int *) realloc(setvec, maxsetvec * sizeof(int));
tmpset = (int *) realloc(tmpset, maxsetvec * sizeof(int));
if (setvec == 0 || tmpset == 0)
overflo("cgoto overflow");
}
if (setvec[q[j]] == 0) {
setcnt++;
setvec[q[j]] = 1;
}
}
}
}
}
/* determine if setvec is a previous state */
tmpset[0] = setcnt;
j = 1;
for (i = f->accept; i >= 0; i--)
if (setvec[i]) {
tmpset[j++] = i;
}
/* tmpset == previous state? */
for (i = 1; i <= f->curstat; i++) {
p = f->posns[i];
if ((k = tmpset[0]) != p[0])
goto different;
for (j = 1; j <= k; j++)
if (tmpset[j] != p[j])
goto different;
/* setvec is state i */
f->gototab[s][c] = i;
return i;
different:;
}
/* add tmpset to current set of states */
if (f->curstat >= NSTATES-1) {
f->curstat = 2;
f->reset = 1;
for (i = 2; i < NSTATES; i++)
xfree(f->posns[i]);
} else
++(f->curstat);
for (i = 0; i < NCHARS; i++)
f->gototab[f->curstat][i] = 0;
xfree(f->posns[f->curstat]);
if ((p = (int *) calloc(1, (setcnt+1)*sizeof(int))) == NULL)
overflo("out of space in cgoto");
f->posns[f->curstat] = p;
f->gototab[s][c] = f->curstat;
for (i = 0; i <= setcnt; i++)
p[i] = tmpset[i];
if (setvec[f->accept])
f->out[f->curstat] = 1;
else
f->out[f->curstat] = 0;
return f->curstat;
}
void freefa(fa *f) /* free a finite automaton */
{
int i;
if (f == NULL)
return;
for (i = 0; i <= f->curstat; i++)
xfree(f->posns[i]);
for (i = 0; i <= f->accept; i++) {
xfree(f->re[i].lfollow);
if (f->re[i].ltype == CCL || f->re[i].ltype == NCCL)
xfree((f->re[i].lval.np));
}
xfree(f->restr);
xfree(f);
}

3
commands/awk/build Executable file
View File

@@ -0,0 +1,3 @@
#!/bin/sh
make clean
make && make install

952
commands/awk/e.c Normal file
View File

@@ -0,0 +1,952 @@
/*
* a small awk clone
*
* (C) 1989 Saeko Hirabauashi & Kouichi Hirabayashi
*
* Absolutely no warranty. Use this software with your own risk.
*
* Permission to use, copy, modify and distribute this software for any
* purpose and without fee is hereby granted, provided that the above
* copyright and disclaimer notice.
*
* This program was written to fit into 64K+64K memory of the Minix 1.2.
*/
#include <stdio.h>
#include <ctype.h>
#include "awk.h"
#include "regexp.h"
extern char **FS, **OFS, **ORS, **OFMT;
extern double *RSTART, *RLENGTH;
extern char record[];
extern CELL *field[];
extern int r_start, r_length;
double getfval(), atof();
char *strsave(), *getsval(), *strcat(), *strstr();
CELL *mkcell(), *mktmp();
CELL *Field(), *Split(), *Forin();
CELL *Arith(), *Assign(), *Stat(), *Mathfun(), *Strfun(), *Cond();
CELL *Print(), *Cat(), *Array(), *Element();
CELL *If(), *While(), *For(), *Do(), *Jump();
CELL *P1stat(), *P2stat(), *Print0();
CELL *Arg(), *Call(), *Ret();
CELL *Subst(), *In(), *Getline(), *Delete(), *Close();
CELL *Nulproc(), *Usrfun();
CELL *_Arg();
FILE *getfp(); /* r.c */
CELL truecell = { NUM, NULL, 1.0 };
CELL falsecell = { NUM, NULL, 0.0 };
static CELL breakcell = { BRK, NULL, 0.0 };
static CELL contcell = { CNT, NULL, 0.0 };
static CELL nextcell = { NXT, NULL, 0.0 };
static CELL retcell = { RTN, NULL, 0.0 };
static CELL *retval; /* function return value */
int pateval; /* used in P1STAT & P2STAT */
static char *r_str; /* STR in 'str ~ STR */
static regexp *r_pat; /* compiled pattern for STR */
CELL *(*proctab[])() = {
Arg, Arith, Array, Assign, Call, Cat, Cond, Delete, Do, Element,
Field, For, Forin, Getline, If, In, Jump, Mathfun, Nulproc, P1stat,
P2stat, Print, Print0, Strfun, Subst, Usrfun, While
};
CELL *
execute(p) NODE *p;
{
int type, i;
CELL *r, *(*proc)();
type = p->n_type;
if (type == VALUE) {
if ((r = (CELL *) p->n_arg[0])->c_type & PAT && pateval) {
i = match(r->c_sval, (char *)record) ? 1 : 0;
r = mktmp(NUM, NULL, (double) i);
}
return r;
}
for ( ; p != NULL; p = p->n_next) {
#if 0
if (p->n_type == VALUE) continue; /* neglect */
#endif
/*
switch ((int) p->n_type) {
case ARRAY:
r = Array(p);
break;
case ARITH:
r = Arith(p);
break;
case ASSIGN:
r = Assign(p);
break;
case PRINT:
r = Print(p);
break;
case PRINT0:
r = Print0(p);
break;
case CAT:
r = Cat(p);
break;
case MATHFUN:
r = Mathfun(p);
break;
case STRFUN:
r = Strfun(p);
break;
case COND:
r = Cond(p);
break;
case IF:
r = If(p);
break;
case P1STAT:
r = P1stat(p);
break;
case P2STAT:
r = P2stat(p);
break;
case WHILE:
r = While(p);
break;
case DO:
r = Do(p);
break;
case FOR:
r = For(p);
break;
case FORIN:
r = Forin(p);
break;
case FIELD:
r = Field(p);
break;
case JUMP:
r = Jump(p);
break;
case ARG:
r = Arg(p);
break;
case CALL:
r = Call(p);
break;
case SUBST:
r = Subst(p);
break;
case ELEMENT:
r = Element(p);
break;
case IN:
r = In(p);
break;
case GETLINE:
r = Getline(p);
break;
case DELETE:
r = Delete(p);
break;
case NULPROC:
r = &truecell;
break;
default:
printf("PROGRAM ERROR ? ILLEGAL NODE TYPE(%d)\n", type);
exit(1);
break;
}
*/
i = (int) p->n_type;
if (i < FIRSTP || i > LASTP)
error("ILLEGAL PROC (%d)", i);
proc = proctab[i - FIRSTP];
r = (*proc)(p);
if (r->c_type & (BRK|CNT|NXT|RTN))
return r;
if (p->n_next != NULL)
c_free(r);
#ifdef DOS
kbhit(); /* needs in MS-DOS */
#endif
}
return r;
}
static CELL *
Arith(p) NODE *p;
{
int op;
CELL *r, *u, *v, *execute();
double x, y, fmod(), pow();
op = (int) p->n_arg[0];
if (op == UMINUS) {
u = execute(p->n_arg[1]);
x = - getfval(u);
}
else if (op == INCDEC) {
u = execute(p->n_arg[1]);
x = getfval(u);
setfval(u, x + (int) p->n_arg[2]);
if ((int) p->n_arg[3] == PRE)
return u;
/* return dummy */
}
else {
u = execute(p->n_arg[1]);
v = execute(p->n_arg[2]);
x = getfval(u);
y = getfval(v);
if (op == DIV || op == MOD) {
if (y == 0.0)
fprintf(stderr, "divid by 0\n");
}
switch (op) {
case SUB: x -= y;break;
case ADD: x += y; break;
case MULT: x *= y; break;
case DIV:
if (y == 0.0)
error("division by zero in \"/\"", (char *)0);
x /= y; break;
case MOD:
if (y == 0.0)
error("division by zero in \"%%\"", (char *)0);
x = fmod(x, y); break;
case POWER: x = pow(x, y); break;
default: printf("UNSUPPORTED ARITH OPERATOR !\n"); break;
}
c_free(v);
}
c_free(u);
r = mktmp(NUM, NULL, x);
return r;
}
static CELL *
Assign(p) NODE *p;
{
CELL *u, *v, *execute();
int op;
double x, y, fmod(), pow();
op = (int) p->n_arg[0];
u = execute(p->n_arg[1]);
#if 0
if (u->c_type == UDF) /* fix up local var */
u->c_type |= VAR|STR;
#endif
if (!(u->c_type & (VAR|FLD|REC)) && (u->c_type != UDF))
fprintf(stderr, "ASSIGN TO NON VARIABLE (%d)\n", u->c_type);
v = execute(p->n_arg[2]);
if (u == v)
goto rtn; /* same node */
if (op == ASSIGN) {
if (v->c_type & NUM/* || isnum(v->c_sval)*/)
setfval(u, getfval(v));
else
setsval(u, getsval(v));
}
else {
x = getfval(u);
y = getfval(v);
switch (op) {
case ADDEQ: x += y; break;
case SUBEQ: x -= y; break;
case MULTEQ: x *= y; break;
case DIVEQ:
if (y == 0.0)
error("division by zero in \"/=\"", (char *)0);
x /= y; break;
case MODEQ:
if (y == 0.0)
error("division by zero in \"%=\"", (char *)0);
x = fmod(x, y); break;
case POWEQ: x = pow(x, y); break;
default:
synerr("illegal assign op (%d)", op);
break;
}
setfval(u, x);
}
rtn:
c_free(v);
return u;
}
static CELL *
Cat(p) NODE *p;
{
CELL *u;
char *s, *t, str[BUFSIZ];
u = execute(p->n_arg[0]);
s = getsval(u);
for (t = str; *s; )
*t++ = *s++;
c_free(u);
u = execute(p->n_arg[1]);
s = getsval(u);
while (*s)
*t++ = *s++;
c_free(u);
*t = '\0';
return mktmp(STR, str, 0.0);
}
static CELL *
Print(p) NODE *p;
{
register int i, redir, typ;
CELL *u;
char *s, str[BUFSIZ];
char *file;
FILE *fp;
redir = (int) p->n_arg[0];
if (typ = redir & PRMASK) { /* redirect */
u = execute(p->n_arg[1]);
file = getsval(u);
if (typ == R_PIPE)
typ = R_POUT;
fp = getfp(file, typ);
c_free(u);
}
else
fp = stdout;
if (redir & FORMAT) /* format */
format(str, p);
else {
*str = '\0';
for (i = 2; p->n_arg[i] != NULL; i++) {
if (i > 2)
strcat(str, *OFS);
u = execute(p->n_arg[i]);
s = getsval(u);
strcat(str, s);
c_free(u);
}
strcat(str, *ORS);
}
if (redir & STROUT) /* sprintf */
return mktmp(STR, str, 0.0);
fputs(str, fp);
fflush(fp);
return &truecell;
}
static CELL *
Mathfun(p) NODE *p;
{
CELL *u, *v;
double x, y;
double atan2(), cos(), exp(), log(), sin(), sqrt(), modf();
if ((int) p->n_arg[1] == 0) {
u = NULL;
x = 0.0;
}
else {
u = execute(p->n_arg[2]);
x = getfval(u);
}
switch ((int) p->n_arg[0]) {
case ATAN2:
if ((int) p->n_arg[1] == 2) {
v = execute(p->n_arg[3]);
y = getfval(v);
x = atan2(x, y);
c_free(v);
}
else
x = 0.0;
break;
case COS: x = cos(x); break;
case EXP: x = exp(x); break;
case INT: y = modf(x, &x); break;
case LOG: x = log(x); break;
case SIN: x = sin(x); break;
case SQRT: x = sqrt(x); break;
case RAND: x = (double) rand() / 32768.0; break;
case SRAND: if (x == 0.0)
x = (double) time(0);
x = (double) srand((int) x);
break;
default:
fprintf(stderr, "unknown math function (%d)\n", p->n_arg[2]);
break;
}
if (u != NULL)
c_free(u);
return mktmp(NUM, NULL, x);
}
static CELL *
Strfun(p) NODE *p;
{
CELL *u, *v, *r;
char *s, *t, str[BUFSIZ];
int i, m, n;
double x;
regexp *pat, *getpat();
n = (int) p->n_arg[1];
if (n > 0 && (int) p->n_arg[0] != SPLIT) {
u = execute(p->n_arg[2]);
s = getsval(u);
}
else {
s = "";
u = NULL;
}
switch ((int) p->n_arg[0]) {
case INDEX:
if (n > 1) {
v = execute(p->n_arg[3]);
t = getsval(v);
i = Index(s, t);
c_free(v);
}
else
i = 0;
r = mktmp(NUM, NULL, (double) i);
break;
case LENGTH:
i = (n > 0) ? jstrlen(s) : jstrlen(record);
r = mktmp(NUM, NULL, (double) i);
break;
case SPLIT:
r = Split(p);
break;
case SUBSTR:
if (n > 1) {
v = execute(p->n_arg[3]);
m = (int) getfval(v) - 1;
c_free(v);
}
else
m = 0;
if (n > 2) {
v = execute(p->n_arg[4]);
n = (int) getfval(v);
c_free(v);
}
else
n = jstrlen(s) - m;
for (t = str; *s && m-- > 0; s++)
if (isKanji(*s))
s++;
while (*s && n-- > 0) {
if (isKanji(*s))
*t++ = *s++;
*t++ = *s++;
}
*t = '\0';
r = mktmp(STR, str, 0.0);
break;
case RMATCH:
if (n > 1) {
v = execute(p->n_arg[3]);
pat = getpat(v);
match(pat, s);
c_free(v);
if (r_start) { /* change only if match */
*RSTART = (double) r_start;
*RLENGTH = (double) r_length;
}
r = mktmp(NUM, NULL, (double) r_start);
}
else
error("missing regexpr in match(str, regexpr)");
break;
case CLOSE:
r = Close(s);
break;
case SYSTEM:
r = mktmp(NUM, NULL, system(s) == -1 ? 0.0 : 1.0);
break;
default:
fprintf(stderr, "unknown string function");
break;
}
c_free(u);
return r;
}
static regexp *
getpat(r) CELL *r;
{
regexp *pat, *mkpat();
if (r->c_type & PAT)
pat = (regexp *) r->c_sval;
else {
if (r_str && strcmp(r_str, r->c_sval) == 0)
pat = r_pat;
else {
sfree(r_str); sfree(r_pat);
r_str = strsave(getsval(r));
pat = r_pat = mkpat(r_str);
}
}
return pat;
}
static CELL *
Subst(p) NODE *p;
{
CELL *u, *v, *w;
char *s, *t, *r, str[BUFSIZ], *strcpy();
int i, n;
n = (int) p->n_arg[1];
if (n > 1) {
u = execute(p->n_arg[3]); /* substitute string */
s = getsval(u);
v = execute(p->n_arg[2]); /* expr */
if (n > 2) {
w = execute(p->n_arg[4]);
t = getsval(w);
r = str;
}
else {
t = r = record;
w = NULL;
}
i = (int) p->n_arg[0] == RGSUB ? 0 : 1;
if (v->c_type & (PAT|STR))
i = Sub(r, v->c_sval, (v->c_type & STR), s, t, i);
else
error("[g]sub(PAT, .. ) must be /../ or string (%d)",
w->c_type);
if (n > 2) {
if (w->c_type & REC) {
strcpy(record, str);
mkfld(record, *FS, field);
}
else
setsval(w, str);
}
else
mkfld(record, *FS, field);
c_free(u);
c_free(v);
c_free(w);
}
else
i = 0;
return mktmp(NUM, NULL, (double) i);
}
static CELL *
Cond(p) NODE *p;
{
CELL *u, *v;
double x, y;
int op, i, j;
char *s;
int save = pateval;
op = (int) p->n_arg[0];
u = execute(p->n_arg[1]);
x = getfval(u);
/*
printf("Cond(%d)(%s)\n", u->c_type, u->c_sval);
*/
if (op == AND || op == OR || op == NOT) {
if (u->c_type & NUM)
i = (x != 0.0);
else {
s = getsval(u);
i = (s != (char *)NULL) && (*s != '\0');
}
}
if (op == AND && !i) {
c_free(u);
return &falsecell;
}
if (op == OR && i) {
c_free(u);
return &truecell;
}
if (op == NOT)
i = i == 0 ? 1 : 0;
else {
if (op == MATCH || op == NOMATCH)
pateval = 0;
v = execute(p->n_arg[2]);
y = getfval(v);
if (op == AND || op == OR || op == BINAND || op == BINOR) {
if (v->c_type & NUM)
j = (y != 0.0);
else {
s = getsval(v);
j = (s != (char *)NULL) && (*s != '\0');
}
switch (op) {
case AND: i = i && j; break;
case OR: i = i || j; break;
case BINAND: i = i & j; break;
case BINOR: i = i | j; break;
}
}
else if (op == MATCH || op == NOMATCH) {
char *s;
regexp *pat, *getpat();
s = getsval(u);
pat = getpat(v);
i = match(pat, s) == 0 ? 0 : 1;
if (op == NOMATCH)
i = i == 0 ? 1 : 0;
}
else { /* relative operator */
/*
printf("Cond(%d)(%d)(%s)(%s)\n", u->c_type, v->c_type, u->c_sval, v->c_sval);
*/
if ((u->c_type & NUM) && (v->c_type & NUM))
i = x < y ? -1 : (x > y ? 1 : 0);
else
i = strcmp(getsval(u), getsval(v));
/*
printf("Cond(%d)(%d)(%g)(%g)(%d)\n", u->c_type, v->c_type, x, y, i);
*/
switch (op) {
case LT: i = i < 0 ? 1 : 0; break;
case LE: i = i <= 0 ? 1 : 0; break;
case EQ: i = i == 0 ? 1 : 0; break;
case NE: i = i != 0 ? 1 : 0; break;
case GT: i = i > 0 ? 1 : 0; break;
case GE: i = i >= 0 ? 1 : 0; break;
default:
fprintf(stderr, "unknown relative operator (%d)\n", op);
break;
}
}
c_free(v);
}
c_free(u);
pateval = save;
return mktmp(NUM, NULL, (double) i);
}
static CELL *
If(p) NODE *p;
{
CELL *u;
int i;
char *s;
u = execute(p->n_arg[0]);
if (u->c_type & NUM)
i = (getfval(u) != 0.0);
else {
s = getsval(u);
i = (s != (char *)NULL) && (*s != '\0');
}
c_free(u);
if (i)
u = execute(p->n_arg[1]);
else if (p->n_arg[2])
u = execute(p->n_arg[2]);
else
u = &truecell;
return u;
}
static CELL *
While(p) NODE *p;
{
CELL *u;
double x;
for (;;) {
u = execute(p->n_arg[0]);
x = getfval(u);
if (x == 0.0)
break;
c_free(u);
u = execute(p->n_arg[1]);
switch (u->c_type) {
case BRK:
goto rtn;
case NXT: case EXT: case RTN:
return u;
}
c_free(u);
}
rtn:
c_free(u);
return &truecell;
}
static CELL *
Do(p) NODE *p;
{
CELL *u;
double x;
for (;;) {
u = execute(p->n_arg[0]);
switch (u->c_type) {
case BRK:
goto rtn;
case NXT: case EXT: case RTN:
return u;
}
c_free(u);
u = execute(p->n_arg[1]);
if(getfval(u) == 0.0)
break;
c_free(u);
}
rtn:
c_free(u);
return &truecell;
}
static CELL *
For(p) NODE *p;
{
CELL *u;
double x;
if (p->n_arg[0] != NULL) {
u = execute(p->n_arg[0]);
c_free(u);
}
for (;;) {
if (p->n_arg[1] != NULL) {
u = execute(p->n_arg[1]);
x = getfval(u);
c_free(u);
if (x == 0.0)
break;
}
u = execute(p->n_arg[3]);
switch (u->c_type) {
case BRK:
c_free(u);
goto rtn;
case NXT: case EXT: case RTN:
return u;
}
if (p->n_arg[2] != NULL) {
u = execute(p->n_arg[2]);
c_free(u);
}
}
rtn:
return &truecell;
}
static CELL *
Jump(p) NODE *p;
{
CELL *u;
int i;
switch ((int) p->n_arg[0]) {
case BREAK: u = &breakcell; break;
case CONTIN: u = &contcell; break;
case EXIT:
if ((int) p->n_arg[1]) {
u = execute(p->n_arg[1]);
i = (int) getfval(u);
}
else
i = 0;
closeall();
exit(i);
case RETURN:
Return(p);
u = &retcell;
break;
case NEXT: u = &nextcell; break;
}
return u;
}
static
Return(p) NODE *p;
{
CELL *u;
int i;
char *s, str[BUFSIZ];
c_free(retval);
if (p->n_arg[1] != NULL) {
if (p->n_arg[2] == NULL) {
/*
if (0) {
*/
u = execute(p->n_arg[1]);
if (u->c_type == UDF)
retval = mktmp(STR, "", 0.0);
else
retval = mktmp(u->c_type, u->c_sval, u->c_fval);
c_free(u);
}
else {
for (i = 1; p->n_arg[i] != NULL; i++) {
if (i == 1)
*str = '\0';
else
strcat(str, *OFS);
u = execute(p->n_arg[i]);
s = getsval(u);
strcat(str, s);
c_free(u);
}
/*
printf("Ret(%s)(%d)\n", str, isnum(str));
*/
if (isnum(str))
retval = mktmp(STR|NUM, str, atof(str));
else
retval = mktmp(STR, str, 0.0);
}
}
else
retval = &truecell;
}
#define MAXFRAME 100
CELL **frame[MAXFRAME];
static int framep;
static CELL *
Arg(p) NODE *p;
{
CELL *u;
int i;
u = (CELL *)p->n_arg[0];
return _Arg((int)u->c_fval);
}
CELL *
_Arg(i)
{
/*
printf("Arg(%d)\n", i);
*/
return frame[framep - 1][i];
}
static CELL *
Call(p) NODE *p;
{
CELL *u, *v, *r, **arg;
NODE *q;
int i, j, k, n;
char *emalloc();
if (framep >= MAXFRAME - 2)
error("stack frame overflow", (char *)0);
retval = &truecell;
r = (CELL *) p->n_arg[0];
if (r->c_type != FUN)
synerr("called function is not declared", (char *)0);
n = (int) r->c_fval; /* # of params */
if (n > 0) {
arg = (CELL **) emalloc(sizeof(u) * n);
for (i = 2, j = 0, k = (int) p->n_arg[1]; j < k; i++) {
u = execute(p->n_arg[i]);
/*
printf("pass, j(%d)typ(%d)\n", j, u->c_type);
*/
if (u->c_type & ARR)
v = u; /* pass by reference */
else { /* pass by value */
v = mkcell(UDF, u->c_sval, u->c_fval);
if (u->c_type != UDF) {
#if 0
v->c_type = u->c_type;
if (v->c_type & (NUM|STR))
v->c_type |= VAR;
v->c_type &= ~TMP; /* dont't free */
#else
v->c_type |= (u->c_type & (NUM|STR))|VAR;
/*v->c_type &= ~TMP;*/
#endif
/* Don't free original */
}
/*
printf("pass1, j(%d)typ(%d)\n", j, v->c_type);
*/
}
arg[j++] = v;
}
for ( ; j < n; ) /* local var */
arg[j++] = mkcell(UDF, NULL, 0.0);
}
else
arg = NULL;
frame[framep] = arg;
framep++;
r = execute(r->c_sval);
c_free(r);
framep--;
if (n > 0) {
for (j = n - 1 ; j > k; j--) { /* local var */
u = arg[j];
if (u->c_type & ARR)
a_free(u);
else
c_free(u);
}
for ( ; j >= 0; j--) {
u = arg[j];
if (!(u->c_type & ARR)) {
/* c_free(u);*/
sfree(u->c_sval);
sfree(u);
}
else {
v = execute(p->n_arg[j + 2]);
if (v->c_type == UDF) { /* copy back */
/*
printf("copy_back_UDF(%d)(%d)\n", j, u->c_type);
*/
v->c_type = u->c_type;
sfree(v->c_sval);
v->c_sval = u->c_sval;
v->c_fval = u->c_fval;
sfree(u);
}
}
}
}
sfree(arg);
/* return retval;*/
u = mktmp(retval->c_type, retval->c_sval, retval->c_fval);
return u;
}
CELL *Nulproc()
{
return &truecell;
}
CELL *
Usrfun(p) NODE *p;
{
CELL *u;
u = execute(p);
return u;
}

43
commands/awk/k.c Normal file
View File

@@ -0,0 +1,43 @@
/*
* a small awk clone
*
* (C) 1989 Saeko Hirabauashi & Kouichi Hirabayashi
*
* Absolutely no warranty. Use this software with your own risk.
*
* Permission to use, copy, modify and distribute this software for any
* purpose and without fee is hereby granted, provided that the above
* copyright and disclaimer notice.
*
* This program was written to fit into 64K+64K memory of the Minix 1.2.
*/
#include <stdio.h>
isKanji(c)
{
c &= 0xff;
return (c > 0x80 && c < 0xa0 || c > 0xdf && c < 0xfd);
}
jstrlen(s) char *s;
{
int i;
for (i = 0; *s; i++, s++)
if (isKanji(*s))
s++;
return i;
}
char *
jStrchr(s, c) char *s;
{
for ( ; *s; s++)
if (isKanji(*s))
s++;
else if (*s == c)
return s;
return NULL;
}

353
commands/awk/l.c Normal file
View File

@@ -0,0 +1,353 @@
/*
* a small awk clone
*
* (C) 1989 Saeko Hirabauashi & Kouichi Hirabayashi
*
* Absolutely no warranty. Use this software with your own risk.
*
* Permission to use, copy, modify and distribute this software for any
* purpose and without fee is hereby granted, provided that the above
* copyright and disclaimer notice.
*
* This program was written to fit into 64K+64K memory of the Minix 1.2.
*/
#include <stdio.h>
#include <ctype.h>
#include "awk.h"
extern char *srcprg; /* inline program */
extern FILE *pfp; /* program file */
int sym; /* lexical token */
int sym1; /* auxiliary lexical token */
int regexflg; /* set by parser (y.c) to indicate parsing REGEXPR */
int funflg; /* set by parser (y.c) to indicate parsing FUNCTION */
int printflg; /* set by parser (y.c) to indicate parsing PRINT */
int getlineflg; /* set by parser (y.c) to indicate parsing GETLINE */
char text[BUFSIZ]; /* lexical word */
char line[BUFSIZ]; /* program line for error message (ring buffer) */
char *linep = line; /* line pointer */
char funnam[128]; /* function name for error message */
int lineno = 1;
lex()
{
int c, d;
char *s;
if (regexflg)
return sym = scanreg();
next:
while ((c = Getc()) == ' ' || c == '\t')
;
while (c == '#')
for (c = Getc(); c != '\n'; c = Getc())
;
switch (c) {
case '\\':
if ((c = Getc()) == '\n') {
lineno++;
goto next;
}
break;
case '\n':
lineno++;
break;
}
switch (c) {
case EOF: return sym = 0;
case '+': return sym = follow2('=', '+', ADDEQ, INC, ADD);
case '-': return sym = follow2('=', '-', SUBEQ, DEC, SUB);
case '*': return sym = follow('=', MULTEQ, MULT);
case '/': return sym = follow('=', DIVEQ, DIV);
case '%': return sym = follow('=', MODEQ, MOD);
case '^': return sym = follow('=', POWEQ, POWER);
case '=': return sym = follow('=', EQ, ASSIGN);
case '!': return sym = follow2('=', '~', NE, NOMATCH, NOT);
case '&': return sym = follow('&', AND, BINAND);
case '|': sym = follow('|', OR, BINOR);
if (printflg && sym == BINOR)
sym = R_POUT;
return sym;
case '<': sym = follow2('=', '<', LE, SHIFTL, LT);
if (getlineflg && sym == LT)
sym = R_IN;
return sym;
case '>': sym = follow2('=', '>', GE, SHIFTR, GT);
if (printflg) {
switch (sym) {
case GT: sym = R_OUT; break;
case SHIFTR: sym = R_APD; break;
}
}
return sym;
case '~': return sym = MATCH; break;
case ';': case '\n': return sym = EOL;
}
if (isalpha(c) || c == '_') {
for (s = text; isalnum(c) || c == '_'; ) {
*s++ = c; c = Getc();
}
Ungetc(c);
*s = '\0';
if ((d = iskeywd(text)) == 0 &&
(d = isbuiltin(text, &sym1)) == 0) {
if (c == '(')
return sym = CALL;
else if (funflg) {
if ((sym1 = isarg(text)) != -1)
return sym = ARG;
}
}
return sym = d ? d : IDENT;
}
else if (c == '.' || (isdigit(c))) {
Ungetc(c);
return sym = scannum(text); /* NUMBER */
}
else if (c == '"')
return sym = scanstr(text); /* STRING */
return sym = c;
}
static
follow(c1, r1, r2)
{
register int c;
if ((c = Getc()) == c1)
return r1;
else {
Ungetc(c);
return r2;
}
}
static
follow2(c1, c2, r1, r2, r3)
{
register int c;
if ((c = Getc()) == c1)
return r1;
else if (c == c2)
return r2;
else {
Ungetc(c);
return r3;
}
}
static
iskeywd(s) char *s;
{
static struct { char *kw; int token; } tab[] = {
"BEGIN", BEGIN,
"END", END,
"break", BREAK,
"continue", CONTIN,
"delete", DELETE,
"do", DO,
"else", ELSE,
"exit", EXIT,
"for", FOR,
"func", FUNC,
"function", FUNC,
"getline", GETLINE,
"if", IF,
"in", IN,
"next", NEXT,
"print", PRINT,
"printf", PRINTF,
"return", RETURN,
"sprint", SPRINT,
"sprintf", SPRINTF,
"while", WHILE,
"", 0, 0
};
register int i;
for (i = 0; tab[i].token; i++)
if (strcmp(tab[i].kw, s) == 0)
break;
return tab[i].token;
}
static
isbuiltin(s, p) char *s; int *p;
{
static struct { char *kw; int type; int token; } tab[] = {
"atan2", MATHFUN, ATAN2,
"close", STRFUN, CLOSE,
"cos", MATHFUN, COS,
"exp", MATHFUN, EXP,
"gsub", SUBST, RGSUB,
"index", STRFUN, INDEX,
"int", MATHFUN, INT,
"length", STRFUN, LENGTH,
"log", MATHFUN, LOG,
"match", STRFUN, RMATCH,
"sin", MATHFUN, SIN,
"sqrt", MATHFUN, SQRT,
"rand", MATHFUN, RAND,
"srand", MATHFUN, SRAND,
"split", STRFUN, SPLIT,
"sub", SUBST, RSUB,
"substr", STRFUN, SUBSTR,
"system", STRFUN, SYSTEM,
"", 0, 0
};
register int i;
for (i = 0; tab[i].token; i++)
if (strcmp(tab[i].kw, s) == 0)
break;
*p = tab[i].token;
return tab[i].type;
}
static
scannum(s) char *s;
{
register int c;
char *strchr();
if ((c = Getc()) && strchr("+-", c) != NULL) {
*s++ = c; c = Getc();
}
while (isdigit(c)) {
*s++ = c; c = Getc();
}
if (c == '.') {
*s++ = c; c = Getc();
while (isdigit(c)) {
*s++ = c; c = Getc();
}
}
if (c && strchr("eE", c) != NULL) {
*s++ = c; c = Getc();
if (c && strchr("+-", c) != NULL) {
*s++ = c; c = Getc();
}
while (isdigit(c)) {
*s++ = c; c = Getc();
}
}
*s = '\0';
Ungetc(c);
return NUMBER;
}
static
scanstr(s) char *s;
{
register int c, i, j;
for (c = Getc(); c != EOF & c != '"'; ) {
if (c == '\\') {
switch (c = Getc()) {
case 'b': c = '\b'; break;
case 'f': c = '\f'; break;
case 'n': c = '\n'; break;
case 'r': c = '\r'; break;
case 't': c = '\t'; break;
default:
if (isdigit(c)) {
for (i = j = 0; i < 3 && isdigit(c); c = Getc(), i++)
j = j * 8 + c - '0';
Ungetc(c);
c = j;
}
break;
}
}
*s++ = c;
if (isKanji(c))
*s++ = Getc();
c = Getc();
}
*s = '\0';
return STRING;
}
static
scanreg()
{
register int c;
register char *s;
for (s = text; (c = Getc()) != '/'; )
if (c == '\n')
error("newline in regular expression");
else {
if (isKanji(c) || c == '\\') {
*s++ = c; c = Getc();
}
*s++ = c;
}
*s = '\0';
return REGEXP;
}
isarrayindex()
{
int c, c2;
next:
while ((c = Getc()) == ' ' || c == '\t')
;
if (c == '\\') {
if ((c2 = Getc()) == '\n') {
lineno++;
goto next;
}
Ungetc(c2);
}
if (c != '[') Ungetc(c);
return (c == '[');
}
#define UNGET_DEPTH 2
static int unget[UNGET_DEPTH], unget_depth;
Ungetc(c)
{
if (unget_depth == UNGET_DEPTH) error("unget buffer overflow");
unget[unget_depth++] = c;
if (linep > line) {
if (--linep < line)
linep == line + BUFSIZ - 1;
}
}
Getc()
{
register int c;
char *s, *t;
if (unget_depth > 0)
c = unget[--unget_depth];
else if (srcprg)
c = *srcprg ? *srcprg++ : EOF;
else
c = fgetc(pfp);
#if 0
if (linep - line == BUFSIZ) {
printf("!!!\n");
for (s = line; *s != '\n' && ((s - line) <BUFSIZ); s++)
;
printf("***(%d)***\n", *s);
for (t = line; s < linep; )
*t++ = *++s;
}
#endif
*linep++ = c;
if ((linep - line) == BUFSIZ)
linep = line;
return c;
}

View File

@@ -1,582 +0,0 @@
/****************************************************************
Copyright (C) Lucent Technologies 1997
All Rights Reserved
Permission to use, copy, modify, and distribute this software and
its documentation for any purpose and without fee is hereby
granted, provided that the above copyright notice appear in all
copies and that both that the copyright notice and this
permission notice and warranty disclaimer appear in supporting
documentation, and that the name Lucent Technologies or any of
its entities not be used in advertising or publicity pertaining
to distribution of the software without specific, written prior
permission.
LUCENT DISCLAIMS ALL WARRANTIES WITH REGARD TO THIS SOFTWARE,
INCLUDING ALL IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS.
IN NO EVENT SHALL LUCENT OR ANY OF ITS ENTITIES BE LIABLE FOR ANY
SPECIAL, INDIRECT OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES
WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER
IN AN ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION,
ARISING OUT OF OR IN CONNECTION WITH THE USE OR PERFORMANCE OF
THIS SOFTWARE.
****************************************************************/
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <ctype.h>
#include "awk.h"
#include "awkgram.h"
extern YYSTYPE yylval;
extern int infunc;
int lineno = 1;
int bracecnt = 0;
int brackcnt = 0;
int parencnt = 0;
typedef struct Keyword {
const char *word;
int sub;
int type;
} Keyword;
Keyword keywords[] ={ /* keep sorted: binary searched */
{ "BEGIN", XBEGIN, XBEGIN },
{ "END", XEND, XEND },
{ "NF", VARNF, VARNF },
{ "atan2", FATAN, BLTIN },
{ "break", BREAK, BREAK },
{ "close", CLOSE, CLOSE },
{ "continue", CONTINUE, CONTINUE },
{ "cos", FCOS, BLTIN },
{ "delete", DELETE, DELETE },
{ "do", DO, DO },
{ "else", ELSE, ELSE },
{ "exit", EXIT, EXIT },
{ "exp", FEXP, BLTIN },
{ "fflush", FFLUSH, BLTIN },
{ "for", FOR, FOR },
{ "func", FUNC, FUNC },
{ "function", FUNC, FUNC },
{ "getline", GETLINE, GETLINE },
{ "gsub", GSUB, GSUB },
{ "if", IF, IF },
{ "in", IN, IN },
{ "index", INDEX, INDEX },
{ "int", FINT, BLTIN },
{ "length", FLENGTH, BLTIN },
{ "log", FLOG, BLTIN },
{ "match", MATCHFCN, MATCHFCN },
{ "next", NEXT, NEXT },
{ "nextfile", NEXTFILE, NEXTFILE },
{ "print", PRINT, PRINT },
{ "printf", PRINTF, PRINTF },
{ "rand", FRAND, BLTIN },
{ "return", RETURN, RETURN },
{ "sin", FSIN, BLTIN },
{ "split", SPLIT, SPLIT },
{ "sprintf", SPRINTF, SPRINTF },
{ "sqrt", FSQRT, BLTIN },
{ "srand", FSRAND, BLTIN },
{ "sub", SUB, SUB },
{ "substr", SUBSTR, SUBSTR },
{ "system", FSYSTEM, BLTIN },
{ "tolower", FTOLOWER, BLTIN },
{ "toupper", FTOUPPER, BLTIN },
{ "while", WHILE, WHILE },
};
#define RET(x) { if(dbg)printf("lex %s\n", tokname(x)); return(x); }
int peek(void)
{
int c = input();
unput(c);
return c;
}
int gettok(char **pbuf, int *psz) /* get next input token */
{
int c, retc;
char *buf = *pbuf;
int sz = *psz;
char *bp = buf;
c = input();
if (c == 0)
return 0;
buf[0] = c;
buf[1] = 0;
if (!isalnum(c) && c != '.' && c != '_')
return c;
*bp++ = c;
if (isalpha(c) || c == '_') { /* it's a varname */
for ( ; (c = input()) != 0; ) {
if (bp-buf >= sz)
if (!adjbuf(&buf, &sz, bp-buf+2, 100, &bp, "gettok"))
FATAL( "out of space for name %.10s...", buf );
if (isalnum(c) || c == '_')
*bp++ = c;
else {
*bp = 0;
unput(c);
break;
}
}
*bp = 0;
retc = 'a'; /* alphanumeric */
} else { /* maybe it's a number, but could be . */
char *rem;
/* read input until can't be a number */
for ( ; (c = input()) != 0; ) {
if (bp-buf >= sz)
if (!adjbuf(&buf, &sz, bp-buf+2, 100, &bp, "gettok"))
FATAL( "out of space for number %.10s...", buf );
if (isdigit(c) || c == 'e' || c == 'E'
|| c == '.' || c == '+' || c == '-')
*bp++ = c;
else {
unput(c);
break;
}
}
*bp = 0;
strtod(buf, &rem); /* parse the number */
if (rem == buf) { /* it wasn't a valid number at all */
buf[1] = 0; /* return one character as token */
retc = buf[0]; /* character is its own type */
unputstr(rem+1); /* put rest back for later */
} else { /* some prefix was a number */
unputstr(rem); /* put rest back for later */
rem[0] = 0; /* truncate buf after number part */
retc = '0'; /* type is number */
}
}
*pbuf = buf;
*psz = sz;
return retc;
}
int word(char *);
int string(void);
int regexpr(void);
int sc = 0; /* 1 => return a } right now */
int reg = 0; /* 1 => return a REGEXPR now */
int yylex(void)
{
int c;
static char *buf = 0;
static int bufsize = 5; /* BUG: setting this small causes core dump! */
if (buf == 0 && (buf = (char *) malloc(bufsize)) == NULL)
FATAL( "out of space in yylex" );
if (sc) {
sc = 0;
RET('}');
}
if (reg) {
reg = 0;
return regexpr();
}
for (;;) {
c = gettok(&buf, &bufsize);
if (c == 0)
return 0;
if (isalpha(c) || c == '_')
return word(buf);
if (isdigit(c)) {
yylval.cp = setsymtab(buf, tostring(buf), atof(buf), CON|NUM, symtab);
/* should this also have STR set? */
RET(NUMBER);
}
yylval.i = c;
switch (c) {
case '\n': /* {EOL} */
RET(NL);
case '\r': /* assume \n is coming */
case ' ': /* {WS}+ */
case '\t':
break;
case '#': /* #.* strip comments */
while ((c = input()) != '\n' && c != 0)
;
unput(c);
break;
case ';':
RET(';');
case '\\':
if (peek() == '\n') {
input();
} else if (peek() == '\r') {
input(); input(); /* \n */
lineno++;
} else {
RET(c);
}
break;
case '&':
if (peek() == '&') {
input(); RET(AND);
} else
RET('&');
case '|':
if (peek() == '|') {
input(); RET(BOR);
} else
RET('|');
case '!':
if (peek() == '=') {
input(); yylval.i = NE; RET(NE);
} else if (peek() == '~') {
input(); yylval.i = NOTMATCH; RET(MATCHOP);
} else
RET(NOT);
case '~':
yylval.i = MATCH;
RET(MATCHOP);
case '<':
if (peek() == '=') {
input(); yylval.i = LE; RET(LE);
} else {
yylval.i = LT; RET(LT);
}
case '=':
if (peek() == '=') {
input(); yylval.i = EQ; RET(EQ);
} else {
yylval.i = ASSIGN; RET(ASGNOP);
}
case '>':
if (peek() == '=') {
input(); yylval.i = GE; RET(GE);
} else if (peek() == '>') {
input(); yylval.i = APPEND; RET(APPEND);
} else {
yylval.i = GT; RET(GT);
}
case '+':
if (peek() == '+') {
input(); yylval.i = INCR; RET(INCR);
} else if (peek() == '=') {
input(); yylval.i = ADDEQ; RET(ASGNOP);
} else
RET('+');
case '-':
if (peek() == '-') {
input(); yylval.i = DECR; RET(DECR);
} else if (peek() == '=') {
input(); yylval.i = SUBEQ; RET(ASGNOP);
} else
RET('-');
case '*':
if (peek() == '=') { /* *= */
input(); yylval.i = MULTEQ; RET(ASGNOP);
} else if (peek() == '*') { /* ** or **= */
input(); /* eat 2nd * */
if (peek() == '=') {
input(); yylval.i = POWEQ; RET(ASGNOP);
} else {
RET(POWER);
}
} else
RET('*');
case '/':
RET('/');
case '%':
if (peek() == '=') {
input(); yylval.i = MODEQ; RET(ASGNOP);
} else
RET('%');
case '^':
if (peek() == '=') {
input(); yylval.i = POWEQ; RET(ASGNOP);
} else
RET(POWER);
case '$':
/* BUG: awkward, if not wrong */
c = gettok(&buf, &bufsize);
if (isalpha(c)) {
if (strcmp(buf, "NF") == 0) { /* very special */
unputstr("(NF)");
RET(INDIRECT);
}
c = peek();
if (c == '(' || c == '[' || (infunc && isarg(buf) >= 0)) {
unputstr(buf);
RET(INDIRECT);
}
yylval.cp = setsymtab(buf, "", 0.0, STR|NUM, symtab);
RET(IVAR);
} else if (c == 0) { /* */
SYNTAX( "unexpected end of input after $" );
RET(';');
} else {
unputstr(buf);
RET(INDIRECT);
}
case '}':
if (--bracecnt < 0)
SYNTAX( "extra }" );
sc = 1;
RET(';');
case ']':
if (--brackcnt < 0)
SYNTAX( "extra ]" );
RET(']');
case ')':
if (--parencnt < 0)
SYNTAX( "extra )" );
RET(')');
case '{':
bracecnt++;
RET('{');
case '[':
brackcnt++;
RET('[');
case '(':
parencnt++;
RET('(');
case '"':
return string(); /* BUG: should be like tran.c ? */
default:
RET(c);
}
}
}
int string(void)
{
int c, n;
char *s, *bp;
static char *buf = 0;
static int bufsz = 500;
if (buf == 0 && (buf = (char *) malloc(bufsz)) == NULL)
FATAL("out of space for strings");
for (bp = buf; (c = input()) != '"'; ) {
if (!adjbuf(&buf, &bufsz, bp-buf+2, 500, &bp, "string"))
FATAL("out of space for string %.10s...", buf);
switch (c) {
case '\n':
case '\r':
case 0:
SYNTAX( "non-terminated string %.10s...", buf );
lineno++;
if (c == 0) /* hopeless */
FATAL( "giving up" );
break;
case '\\':
c = input();
switch (c) {
case '"': *bp++ = '"'; break;
case 'n': *bp++ = '\n'; break;
case 't': *bp++ = '\t'; break;
case 'f': *bp++ = '\f'; break;
case 'r': *bp++ = '\r'; break;
case 'b': *bp++ = '\b'; break;
case 'v': *bp++ = '\v'; break;
case 'a': *bp++ = '\007'; break;
case '\\': *bp++ = '\\'; break;
case '0': case '1': case '2': /* octal: \d \dd \ddd */
case '3': case '4': case '5': case '6': case '7':
n = c - '0';
if ((c = peek()) >= '0' && c < '8') {
n = 8 * n + input() - '0';
if ((c = peek()) >= '0' && c < '8')
n = 8 * n + input() - '0';
}
*bp++ = n;
break;
case 'x': /* hex \x0-9a-fA-F + */
{ char xbuf[100], *px;
for (px = xbuf; (c = input()) != 0 && px-xbuf < 100-2; ) {
if (isdigit(c)
|| (c >= 'a' && c <= 'f')
|| (c >= 'A' && c <= 'F'))
*px++ = c;
else
break;
}
*px = 0;
unput(c);
sscanf(xbuf, "%x", &n);
*bp++ = n;
break;
}
default:
*bp++ = c;
break;
}
break;
default:
*bp++ = c;
break;
}
}
*bp = 0;
s = tostring(buf);
*bp++ = ' '; *bp++ = 0;
yylval.cp = setsymtab(buf, s, 0.0, CON|STR|DONTFREE, symtab);
RET(STRING);
}
int binsearch(const char *w, const Keyword *kp, int n)
{
int cond, low, mid, high;
low = 0;
high = n - 1;
while (low <= high) {
mid = (low + high) / 2;
if ((cond = strcmp(w, kp[mid].word)) < 0)
high = mid - 1;
else if (cond > 0)
low = mid + 1;
else
return mid;
}
return -1;
}
int word(char *w)
{
Keyword *kp;
int c, n;
n = binsearch(w, keywords, sizeof(keywords)/sizeof(keywords[0]));
/* BUG: this ought to be inside the if; in theory could fault (daniel barrett) */
kp = keywords + n;
if (n != -1) { /* found in table */
yylval.i = kp->sub;
switch (kp->type) { /* special handling */
case BLTIN:
if (kp->sub == FSYSTEM && safe)
SYNTAX( "system is unsafe" );
RET(kp->type);
case FUNC:
if (infunc)
SYNTAX( "illegal nested function" );
RET(kp->type);
case RETURN:
if (!infunc)
SYNTAX( "return not in function" );
RET(kp->type);
case VARNF:
yylval.cp = setsymtab("NF", "", 0.0, NUM, symtab);
RET(VARNF);
default:
RET(kp->type);
}
}
c = peek(); /* look for '(' */
if (c != '(' && infunc && (n=isarg(w)) >= 0) {
yylval.i = n;
RET(ARG);
} else {
yylval.cp = setsymtab(w, "", 0.0, STR|NUM|DONTFREE, symtab);
if (c == '(') {
RET(CALL);
} else {
RET(VAR);
}
}
}
void startreg(void) /* next call to yylex will return a regular expression */
{
reg = 1;
}
int regexpr(void)
{
int c;
static char *buf = 0;
static int bufsz = 500;
char *bp;
if (buf == 0 && (buf = (char *) malloc(bufsz)) == NULL)
FATAL("out of space for rex expr");
bp = buf;
for ( ; (c = input()) != '/' && c != 0; ) {
if (!adjbuf(&buf, &bufsz, bp-buf+3, 500, &bp, "regexpr"))
FATAL("out of space for reg expr %.10s...", buf);
if (c == '\n') {
SYNTAX( "newline in regular expression %.10s...", buf );
unput('\n');
break;
} else if (c == '\\') {
*bp++ = '\\';
*bp++ = input();
} else {
*bp++ = c;
}
}
*bp = 0;
if (c == 0)
SYNTAX("non-terminated regular expression %.10s...", buf);
yylval.s = tostring(buf);
unput('/');
RET(REGEXPR);
}
/* low-level lexical stuff, sort of inherited from lex */
char ebuf[300];
char *ep = ebuf;
char yysbuf[100]; /* pushback buffer */
char *yysptr = yysbuf;
FILE *yyin = 0;
int input(void) /* get next lexical input character */
{
int c;
extern char *lexprog;
if (yysptr > yysbuf)
c = (uschar)*--yysptr;
else if (lexprog != NULL) { /* awk '...' */
if ((c = (uschar)*lexprog) != 0)
lexprog++;
} else /* awk -f ... */
c = pgetc();
if (c == '\n')
lineno++;
else if (c == EOF)
c = 0;
if (ep >= ebuf + sizeof ebuf)
ep = ebuf;
return *ep++ = c;
}
void unput(int c) /* put lexical character back on input */
{
if (c == '\n')
lineno--;
if (yysptr >= yysbuf + sizeof(yysbuf))
FATAL("pushed back too much: %.20s...", yysbuf);
*yysptr++ = c;
if (--ep < ebuf)
ep = ebuf + sizeof(ebuf) - 1;
}
void unputstr(const char *s) /* put a string back on input */
{
int i;
for (i = strlen(s)-1; i >= 0; i--)
unput(s[i]);
}

View File

@@ -1,697 +0,0 @@
/****************************************************************
Copyright (C) Lucent Technologies 1997
All Rights Reserved
Permission to use, copy, modify, and distribute this software and
its documentation for any purpose and without fee is hereby
granted, provided that the above copyright notice appear in all
copies and that both that the copyright notice and this
permission notice and warranty disclaimer appear in supporting
documentation, and that the name Lucent Technologies or any of
its entities not be used in advertising or publicity pertaining
to distribution of the software without specific, written prior
permission.
LUCENT DISCLAIMS ALL WARRANTIES WITH REGARD TO THIS SOFTWARE,
INCLUDING ALL IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS.
IN NO EVENT SHALL LUCENT OR ANY OF ITS ENTITIES BE LIABLE FOR ANY
SPECIAL, INDIRECT OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES
WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER
IN AN ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION,
ARISING OUT OF OR IN CONNECTION WITH THE USE OR PERFORMANCE OF
THIS SOFTWARE.
****************************************************************/
#define DEBUG
#include <stdio.h>
#include <string.h>
#include <ctype.h>
#include <errno.h>
#include <stdlib.h>
#include <stdarg.h>
#include "awk.h"
#include "awkgram.h"
FILE *infile = NULL;
char *file = "";
char *record;
int recsize = RECSIZE;
char *fields;
int fieldssize = RECSIZE;
Cell **fldtab; /* pointers to Cells */
char inputFS[100] = " ";
#define MAXFLD 2
int nfields = MAXFLD; /* last allocated slot for $i */
int donefld; /* 1 = implies rec broken into fields */
int donerec; /* 1 = record is valid (no flds have changed) */
int lastfld = 0; /* last used field */
int argno = 1; /* current input argument number */
extern Awkfloat *ARGC;
static Cell dollar0 = { OCELL, CFLD, NULL, "", 0.0, REC|STR|DONTFREE };
static Cell dollar1 = { OCELL, CFLD, NULL, "", 0.0, FLD|STR|DONTFREE };
void recinit(unsigned int n)
{
if ( (record = (char *) malloc(n)) == NULL
|| (fields = (char *) malloc(n+1)) == NULL
|| (fldtab = (Cell **) malloc((nfields+1) * sizeof(Cell *))) == NULL
|| (fldtab[0] = (Cell *) malloc(sizeof(Cell))) == NULL )
FATAL("out of space for $0 and fields");
*fldtab[0] = dollar0;
fldtab[0]->sval = record;
fldtab[0]->nval = tostring("0");
makefields(1, nfields);
}
void makefields(int n1, int n2) /* create $n1..$n2 inclusive */
{
char temp[50];
int i;
for (i = n1; i <= n2; i++) {
fldtab[i] = (Cell *) malloc(sizeof (struct Cell));
if (fldtab[i] == NULL)
FATAL("out of space in makefields %d", i);
*fldtab[i] = dollar1;
sprintf(temp, "%d", i);
fldtab[i]->nval = tostring(temp);
}
}
void initgetrec(void)
{
int i;
char *p;
for (i = 1; i < *ARGC; i++) {
if (!isclvar(p = getargv(i))) { /* find 1st real filename */
setsval(lookup("FILENAME", symtab), getargv(i));
return;
}
setclvar(p); /* a commandline assignment before filename */
argno++;
}
infile = stdin; /* no filenames, so use stdin */
}
static int firsttime = 1;
int getrec(char **pbuf, int *pbufsize, int isrecord) /* get next input record */
{ /* note: cares whether buf == record */
int c;
char *buf = *pbuf;
uschar saveb0;
int bufsize = *pbufsize, savebufsize = bufsize;
if (firsttime) {
firsttime = 0;
initgetrec();
}
dprintf( ("RS=<%s>, FS=<%s>, ARGC=%g, FILENAME=%s\n",
*RS, *FS, *ARGC, *FILENAME) );
if (isrecord) {
donefld = 0;
donerec = 1;
}
saveb0 = buf[0];
buf[0] = 0;
while (argno < *ARGC || infile == stdin) {
dprintf( ("argno=%d, file=|%s|\n", argno, file) );
if (infile == NULL) { /* have to open a new file */
file = getargv(argno);
if (*file == '\0') { /* it's been zapped */
argno++;
continue;
}
if (isclvar(file)) { /* a var=value arg */
setclvar(file);
argno++;
continue;
}
*FILENAME = file;
dprintf( ("opening file %s\n", file) );
if (*file == '-' && *(file+1) == '\0')
infile = stdin;
else if ((infile = fopen(file, "r")) == NULL)
FATAL("can't open file %s", file);
setfval(fnrloc, 0.0);
}
c = readrec(&buf, &bufsize, infile);
if (c != 0 || buf[0] != '\0') { /* normal record */
if (isrecord) {
if (freeable(fldtab[0]))
xfree(fldtab[0]->sval);
fldtab[0]->sval = buf; /* buf == record */
fldtab[0]->tval = REC | STR | DONTFREE;
if (is_number(fldtab[0]->sval)) {
fldtab[0]->fval = atof(fldtab[0]->sval);
fldtab[0]->tval |= NUM;
}
}
setfval(nrloc, nrloc->fval+1);
setfval(fnrloc, fnrloc->fval+1);
*pbuf = buf;
*pbufsize = bufsize;
return 1;
}
/* EOF arrived on this file; set up next */
if (infile != stdin)
fclose(infile);
infile = NULL;
argno++;
}
buf[0] = saveb0;
*pbuf = buf;
*pbufsize = savebufsize;
return 0; /* true end of file */
}
void nextfile(void)
{
if (infile != NULL && infile != stdin)
fclose(infile);
infile = NULL;
argno++;
}
int readrec(char **pbuf, int *pbufsize, FILE *inf) /* read one record into buf */
{
int sep, c;
char *rr, *buf = *pbuf;
int bufsize = *pbufsize;
if (strlen(*FS) >= sizeof(inputFS))
FATAL("field separator %.10s... is too long", *FS);
strcpy(inputFS, *FS); /* for subsequent field splitting */
if ((sep = **RS) == 0) {
sep = '\n';
while ((c=getc(inf)) == '\n' && c != EOF) /* skip leading \n's */
;
if (c != EOF)
ungetc(c, inf);
}
for (rr = buf; ; ) {
for (; (c=getc(inf)) != sep && c != EOF; ) {
if (rr-buf+1 > bufsize)
if (!adjbuf(&buf, &bufsize, 1+rr-buf, recsize, &rr, "readrec 1"))
FATAL("input record `%.30s...' too long", buf);
*rr++ = c;
}
if (**RS == sep || c == EOF)
break;
if ((c = getc(inf)) == '\n' || c == EOF) /* 2 in a row */
break;
if (!adjbuf(&buf, &bufsize, 2+rr-buf, recsize, &rr, "readrec 2"))
FATAL("input record `%.30s...' too long", buf);
*rr++ = '\n';
*rr++ = c;
}
if (!adjbuf(&buf, &bufsize, 1+rr-buf, recsize, &rr, "readrec 3"))
FATAL("input record `%.30s...' too long", buf);
*rr = 0;
dprintf( ("readrec saw <%s>, returns %d\n", buf, c == EOF && rr == buf ? 0 : 1) );
*pbuf = buf;
*pbufsize = bufsize;
return c == EOF && rr == buf ? 0 : 1;
}
char *getargv(int n) /* get ARGV[n] */
{
Cell *x;
char *s, temp[50];
extern Array *ARGVtab;
sprintf(temp, "%d", n);
x = setsymtab(temp, "", 0.0, STR, ARGVtab);
s = getsval(x);
dprintf( ("getargv(%d) returns |%s|\n", n, s) );
return s;
}
void setclvar(char *s) /* set var=value from s */
{
char *p;
Cell *q;
for (p=s; *p != '='; p++)
;
*p++ = 0;
p = qstring(p, '\0');
q = setsymtab(s, p, 0.0, STR, symtab);
setsval(q, p);
if (is_number(q->sval)) {
q->fval = atof(q->sval);
q->tval |= NUM;
}
dprintf( ("command line set %s to |%s|\n", s, p) );
}
void fldbld(void) /* create fields from current record */
{
/* this relies on having fields[] the same length as $0 */
/* the fields are all stored in this one array with \0's */
char *r, *fr, sep;
Cell *p;
int i, j, n;
if (donefld)
return;
if (!isstr(fldtab[0]))
getsval(fldtab[0]);
r = fldtab[0]->sval;
n = strlen(r);
if (n > fieldssize) {
xfree(fields);
if ((fields = (char *) malloc(n+1)) == NULL)
FATAL("out of space for fields in fldbld %d", n);
fieldssize = n;
}
fr = fields;
i = 0; /* number of fields accumulated here */
strcpy(inputFS, *FS);
if (strlen(inputFS) > 1) { /* it's a regular expression */
i = refldbld(r, inputFS);
} else if ((sep = *inputFS) == ' ') { /* default whitespace */
for (i = 0; ; ) {
while (*r == ' ' || *r == '\t' || *r == '\n')
r++;
if (*r == 0)
break;
i++;
if (i > nfields)
growfldtab(i);
if (freeable(fldtab[i]))
xfree(fldtab[i]->sval);
fldtab[i]->sval = fr;
fldtab[i]->tval = FLD | STR | DONTFREE;
do
*fr++ = *r++;
while (*r != ' ' && *r != '\t' && *r != '\n' && *r != '\0');
*fr++ = 0;
}
*fr = 0;
} else if ((sep = *inputFS) == 0) { /* new: FS="" => 1 char/field */
for (i = 0; *r != 0; r++) {
char buf[2];
i++;
if (i > nfields)
growfldtab(i);
if (freeable(fldtab[i]))
xfree(fldtab[i]->sval);
buf[0] = *r;
buf[1] = 0;
fldtab[i]->sval = tostring(buf);
fldtab[i]->tval = FLD | STR;
}
*fr = 0;
} else if (*r != 0) { /* if 0, it's a null field */
/* subtlecase : if length(FS) == 1 && length(RS > 0)
* \n is NOT a field separator (cf awk book 61,84).
* this variable is tested in the inner while loop.
*/
int rtest = '\n'; /* normal case */
if (strlen(*RS) > 0)
rtest = '\0';
for (;;) {
i++;
if (i > nfields)
growfldtab(i);
if (freeable(fldtab[i]))
xfree(fldtab[i]->sval);
fldtab[i]->sval = fr;
fldtab[i]->tval = FLD | STR | DONTFREE;
while (*r != sep && *r != rtest && *r != '\0') /* \n is always a separator */
*fr++ = *r++;
*fr++ = 0;
if (*r++ == 0)
break;
}
*fr = 0;
}
if (i > nfields)
FATAL("record `%.30s...' has too many fields; can't happen", r);
cleanfld(i+1, lastfld); /* clean out junk from previous record */
lastfld = i;
donefld = 1;
for (j = 1; j <= lastfld; j++) {
p = fldtab[j];
if(is_number(p->sval)) {
p->fval = atof(p->sval);
p->tval |= NUM;
}
}
setfval(nfloc, (Awkfloat) lastfld);
if (dbg) {
for (j = 0; j <= lastfld; j++) {
p = fldtab[j];
printf("field %d (%s): |%s|\n", j, p->nval, p->sval);
}
}
}
void cleanfld(int n1, int n2) /* clean out fields n1 .. n2 inclusive */
{ /* nvals remain intact */
Cell *p;
int i;
for (i = n1; i <= n2; i++) {
p = fldtab[i];
if (freeable(p))
xfree(p->sval);
p->sval = "";
p->tval = FLD | STR | DONTFREE;
}
}
void newfld(int n) /* add field n after end of existing lastfld */
{
if (n > nfields)
growfldtab(n);
cleanfld(lastfld+1, n);
lastfld = n;
setfval(nfloc, (Awkfloat) n);
}
Cell *fieldadr(int n) /* get nth field */
{
if (n < 0)
FATAL("trying to access out of range field %d", n);
if (n > nfields) /* fields after NF are empty */
growfldtab(n); /* but does not increase NF */
return(fldtab[n]);
}
void growfldtab(int n) /* make new fields up to at least $n */
{
int nf = 2 * nfields;
size_t s;
if (n > nf)
nf = n;
s = (nf+1) * (sizeof (struct Cell *)); /* freebsd: how much do we need? */
if (s / sizeof(struct Cell *) - 1 == nf) /* didn't overflow */
fldtab = (Cell **) realloc(fldtab, s);
else /* overflow sizeof int */
xfree(fldtab); /* make it null */
if (fldtab == NULL)
FATAL("out of space creating %d fields", nf);
makefields(nfields+1, nf);
nfields = nf;
}
int refldbld(const char *rec, const char *fs) /* build fields from reg expr in FS */
{
/* this relies on having fields[] the same length as $0 */
/* the fields are all stored in this one array with \0's */
char *fr;
int i, tempstat, n;
fa *pfa;
n = strlen(rec);
if (n > fieldssize) {
xfree(fields);
if ((fields = (char *) malloc(n+1)) == NULL)
FATAL("out of space for fields in refldbld %d", n);
fieldssize = n;
}
fr = fields;
*fr = '\0';
if (*rec == '\0')
return 0;
pfa = makedfa(fs, 1);
dprintf( ("into refldbld, rec = <%s>, pat = <%s>\n", rec, fs) );
tempstat = pfa->initstat;
for (i = 1; ; i++) {
if (i > nfields)
growfldtab(i);
if (freeable(fldtab[i]))
xfree(fldtab[i]->sval);
fldtab[i]->tval = FLD | STR | DONTFREE;
fldtab[i]->sval = fr;
dprintf( ("refldbld: i=%d\n", i) );
if (nematch(pfa, rec)) {
pfa->initstat = 2; /* horrible coupling to b.c */
dprintf( ("match %s (%d chars)\n", patbeg, patlen) );
strncpy(fr, rec, patbeg-rec);
fr += patbeg - rec + 1;
*(fr-1) = '\0';
rec = patbeg + patlen;
} else {
dprintf( ("no match %s\n", rec) );
strcpy(fr, rec);
pfa->initstat = tempstat;
break;
}
}
return i;
}
void recbld(void) /* create $0 from $1..$NF if necessary */
{
int i;
char *r, *p;
if (donerec == 1)
return;
r = record;
for (i = 1; i <= *NF; i++) {
p = getsval(fldtab[i]);
if (!adjbuf(&record, &recsize, 1+strlen(p)+r-record, recsize, &r, "recbld 1"))
FATAL("created $0 `%.30s...' too long", record);
while ((*r = *p++) != 0)
r++;
if (i < *NF) {
if (!adjbuf(&record, &recsize, 2+strlen(*OFS)+r-record, recsize, &r, "recbld 2"))
FATAL("created $0 `%.30s...' too long", record);
for (p = *OFS; (*r = *p++) != 0; )
r++;
}
}
if (!adjbuf(&record, &recsize, 2+r-record, recsize, &r, "recbld 3"))
FATAL("built giant record `%.30s...'", record);
*r = '\0';
dprintf( ("in recbld inputFS=%s, fldtab[0]=%p\n", inputFS, fldtab[0]) );
if (freeable(fldtab[0]))
xfree(fldtab[0]->sval);
fldtab[0]->tval = REC | STR | DONTFREE;
fldtab[0]->sval = record;
dprintf( ("in recbld inputFS=%s, fldtab[0]=%p\n", inputFS, fldtab[0]) );
dprintf( ("recbld = |%s|\n", record) );
donerec = 1;
}
int errorflag = 0;
void yyerror(const char *s)
{
SYNTAX("%s", s);
}
void SYNTAX(const char *fmt, ...)
{
extern char *cmdname, *curfname;
static int been_here = 0;
va_list varg;
if (been_here++ > 2)
return;
fprintf(stderr, "%s: ", cmdname);
va_start(varg, fmt);
vfprintf(stderr, fmt, varg);
va_end(varg);
fprintf(stderr, " at source line %d", lineno);
if (curfname != NULL)
fprintf(stderr, " in function %s", curfname);
if (compile_time == 1 && cursource() != NULL)
fprintf(stderr, " source file %s", cursource());
fprintf(stderr, "\n");
errorflag = 2;
eprint();
}
void fpecatch(int n)
{
FATAL("floating point exception %d", n);
}
extern int bracecnt, brackcnt, parencnt;
void bracecheck(void)
{
int c;
static int beenhere = 0;
if (beenhere++)
return;
while ((c = input()) != EOF && c != '\0')
bclass(c);
bcheck2(bracecnt, '{', '}');
bcheck2(brackcnt, '[', ']');
bcheck2(parencnt, '(', ')');
}
void bcheck2(int n, int c1, int c2)
{
if (n == 1)
fprintf(stderr, "\tmissing %c\n", c2);
else if (n > 1)
fprintf(stderr, "\t%d missing %c's\n", n, c2);
else if (n == -1)
fprintf(stderr, "\textra %c\n", c2);
else if (n < -1)
fprintf(stderr, "\t%d extra %c's\n", -n, c2);
}
void FATAL(const char *fmt, ...)
{
extern char *cmdname;
va_list varg;
fflush(stdout);
fprintf(stderr, "%s: ", cmdname);
va_start(varg, fmt);
vfprintf(stderr, fmt, varg);
va_end(varg);
error();
if (dbg > 1) /* core dump if serious debugging on */
abort();
exit(2);
}
void WARNING(const char *fmt, ...)
{
extern char *cmdname;
va_list varg;
fflush(stdout);
fprintf(stderr, "%s: ", cmdname);
va_start(varg, fmt);
vfprintf(stderr, fmt, varg);
va_end(varg);
error();
}
void error()
{
extern Node *curnode;
fprintf(stderr, "\n");
if (compile_time != 2 && NR && *NR > 0) {
fprintf(stderr, " input record number %d", (int) (*FNR));
if (strcmp(*FILENAME, "-") != 0)
fprintf(stderr, ", file %s", *FILENAME);
fprintf(stderr, "\n");
}
if (compile_time != 2 && curnode)
fprintf(stderr, " source line number %d", curnode->lineno);
else if (compile_time != 2 && lineno)
fprintf(stderr, " source line number %d", lineno);
if (compile_time == 1 && cursource() != NULL)
fprintf(stderr, " source file %s", cursource());
fprintf(stderr, "\n");
eprint();
}
void eprint(void) /* try to print context around error */
{
char *p, *q;
int c;
static int been_here = 0;
extern char ebuf[], *ep;
if (compile_time == 2 || compile_time == 0 || been_here++ > 0)
return;
p = ep - 1;
if (p > ebuf && *p == '\n')
p--;
for ( ; p > ebuf && *p != '\n' && *p != '\0'; p--)
;
while (*p == '\n')
p++;
fprintf(stderr, " context is\n\t");
for (q=ep-1; q>=p && *q!=' ' && *q!='\t' && *q!='\n'; q--)
;
for ( ; p < q; p++)
if (*p)
putc(*p, stderr);
fprintf(stderr, " >>> ");
for ( ; p < ep; p++)
if (*p)
putc(*p, stderr);
fprintf(stderr, " <<< ");
if (*ep)
while ((c = input()) != '\n' && c != '\0' && c != EOF) {
putc(c, stderr);
bclass(c);
}
putc('\n', stderr);
ep = ebuf;
}
void bclass(int c)
{
switch (c) {
case '{': bracecnt++; break;
case '}': bracecnt--; break;
case '[': brackcnt++; break;
case ']': brackcnt--; break;
case '(': parencnt++; break;
case ')': parencnt--; break;
}
}
double errcheck(double x, const char *s)
{
if (errno == EDOM) {
errno = 0;
WARNING("%s argument out of domain", s);
x = 1;
} else if (errno == ERANGE) {
errno = 0;
WARNING("%s result out of range", s);
x = 1;
}
return x;
}
int isclvar(const char *s) /* is s of form var=something ? */
{
const char *os = s;
if (!isalpha((uschar) *s) && *s != '_')
return 0;
for ( ; *s; s++)
if (!(isalnum((uschar) *s) || *s == '_'))
break;
return *s == '=' && s > os && *(s+1) != '=';
}
/* strtod is supposed to be a proper test of what's a valid number */
/* appears to be broken in gcc on linux: thinks 0x123 is a valid FP number */
/* wrong: violates 4.10.1.4 of ansi C standard */
#include <math.h>
int is_number(const char *s)
{
double r;
char *ep;
errno = 0;
r = strtod(s, &ep);
if (ep == s || r == HUGE_VAL || errno == ERANGE)
return 0;
while (*ep == ' ' || *ep == '\t' || *ep == '\n')
ep++;
if (*ep == '\0')
return 1;
else
return 0;
}

153
commands/awk/m.c Normal file
View File

@@ -0,0 +1,153 @@
/*
* a small awk clone
*
* (C) 1989 Saeko Hirabauashi & Kouichi Hirabayashi
*
* Absolutely no warranty. Use this software with your own risk.
*
* Permission to use, copy, modify and distribute this software for any
* purpose and without fee is hereby granted, provided that the above
* copyright and disclaimer notice.
*
* This program was written to fit into 64K+64K memory of the Minix 1.2.
*/
#include <stdio.h>
#include <sys/types.h>
#include <signal.h>
#include "awk.h"
extern char **FS, **FILENAME;
extern char record[];
extern FILE *ifp;
NODE *parse();
CELL *execute();
FILE *efopen(), *fopen();
char *strsave();
int xargc;
char **xargv;
char *srcprg;
FILE *pfp;
char *cmd;
#if 0
int iflg; /* interactive mode */
#endif
main(argc, argv, envp) char **argv, *envp;
{
char *s, *strpbrk(), *strchr();
void onint();
#ifdef DOS
_sharg(&argc, &argv);
#endif
signal(SIGINT, onint);
signal(SIGFPE, onint);
cmd = argv[0];
init();
while (--argc > 0 && (*++argv)[0] == '-')
for (s = argv[0]+1; *s; s++)
if (strcmp(argv[0], "-") == 0)
break;
else
switch (*s) {
#if 0
case 'i':
iflg++;
pfp = stdin;
interactive();
/* no return */
#endif
case 'F':
*FS = ++s;
break;
case 'f':
if (*(s+1))
s++;
else {
argc--; s = *++argv;
}
if (s == NULL) usage();
pfp = efopen(s, "r");
s += strlen(s) - 1;
break;
}
xargc = argc; xargv = argv;
if (pfp == NULL && xargc > 0) {
srcprg = *xargv++; xargc--;
}
/*
if (pfp == NULL && xargc > 0) {
if (strpbrk(xargv[0], " !$^()={}[];<>,/~") != NULL) {
sprintf(record, "%s\n", xargv[0]);
srcprg = strsave(record);
}
else {
sprintf(record, "%s.awk", xargv[0]);
if ((pfp = fopen(record, "r")) == NULL)
error("can't open %s", record);
}
xargc--; xargv++;
}
*/
if (pfp == NULL && srcprg == NULL) usage();
while (*xargv != NULL && strchr(*xargv, '=') != NULL) {
setvar(*xargv++);
xargc--;
}
initarg(cmd, xargc, xargv, envp);
if (xargc == 0) {
ifp = stdin; *FILENAME = "-";
}
parse();
closeall();
exit(0);
}
FILE *
efopen(file, mode) char *file, *mode;
{
FILE *fp, *fopen();
if ((fp = fopen(file, mode)) == NULL)
error("cannot open %s", file);
return fp;
}
error(s, t) char *s, *t;
{
extern double *NR;
fprintf(stderr, "awk: ");
fprintf(stderr, s, t);
fprintf(stderr, "\n");
if (NR != NULL) {
fprintf(stderr, "record number %g\n", *NR);
}
#ifdef DOS
closeall();
#endif
exit(1);
}
void
onint(i)
{
closeall();
exit(0x80 | i);
}
void
usage()
{
fprintf(stderr,
"usage: %s [options] [-f <rulefile> | <rules>] [inputfiles]\n", cmd);
closeall();
exit(1);
}

View File

@@ -1,192 +0,0 @@
/****************************************************************
Copyright (C) Lucent Technologies 1997
All Rights Reserved
Permission to use, copy, modify, and distribute this software and
its documentation for any purpose and without fee is hereby
granted, provided that the above copyright notice appear in all
copies and that both that the copyright notice and this
permission notice and warranty disclaimer appear in supporting
documentation, and that the name Lucent Technologies or any of
its entities not be used in advertising or publicity pertaining
to distribution of the software without specific, written prior
permission.
LUCENT DISCLAIMS ALL WARRANTIES WITH REGARD TO THIS SOFTWARE,
INCLUDING ALL IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS.
IN NO EVENT SHALL LUCENT OR ANY OF ITS ENTITIES BE LIABLE FOR ANY
SPECIAL, INDIRECT OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES
WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER
IN AN ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION,
ARISING OUT OF OR IN CONNECTION WITH THE USE OR PERFORMANCE OF
THIS SOFTWARE.
****************************************************************/
const char *version = "version 20100208";
#define DEBUG
#include <stdio.h>
#include <ctype.h>
#include <locale.h>
#include <stdlib.h>
#include <string.h>
#include <signal.h>
#include "awk.h"
#include "awkgram.h"
extern char **environ;
extern int nfields;
int dbg = 0;
char *cmdname; /* gets argv[0] for error messages */
extern FILE *yyin; /* lex input file */
char *lexprog; /* points to program argument if it exists */
extern int errorflag; /* non-zero if any syntax errors; set by yyerror */
int compile_time = 2; /* for error printing: */
/* 2 = cmdline, 1 = compile, 0 = running */
#define MAX_PFILE 20 /* max number of -f's */
char *pfile[MAX_PFILE]; /* program filenames from -f's */
int npfile = 0; /* number of filenames */
int curpfile = 0; /* current filename */
int safe = 0; /* 1 => "safe" mode */
int main(int argc, char *argv[])
{
const char *fs = NULL;
setlocale(LC_CTYPE, "");
setlocale(LC_NUMERIC, "C"); /* for parsing cmdline & prog */
cmdname = argv[0];
if (argc == 1) {
fprintf(stderr,
"usage: %s [-F fs] [-v var=value] [-f progfile | 'prog'] [file ...]\n",
cmdname);
exit(1);
}
signal(SIGFPE, fpecatch);
yyin = NULL;
symtab = makesymtab(NSYMTAB/NSYMTAB);
while (argc > 1 && argv[1][0] == '-' && argv[1][1] != '\0') {
if (strcmp(argv[1],"-version") == 0 || strcmp(argv[1],"--version") == 0) {
printf("awk %s\n", version);
exit(0);
break;
}
if (strncmp(argv[1], "--", 2) == 0) { /* explicit end of args */
argc--;
argv++;
break;
}
switch (argv[1][1]) {
case 's':
if (strcmp(argv[1], "-safe") == 0)
safe = 1;
break;
case 'f': /* next argument is program filename */
argc--;
argv++;
if (argc <= 1)
FATAL("no program filename");
if (npfile >= MAX_PFILE - 1)
FATAL("too many -f options");
pfile[npfile++] = argv[1];
break;
case 'F': /* set field separator */
if (argv[1][2] != 0) { /* arg is -Fsomething */
if (argv[1][2] == 't' && argv[1][3] == 0) /* wart: t=>\t */
fs = "\t";
else if (argv[1][2] != 0)
fs = &argv[1][2];
} else { /* arg is -F something */
argc--; argv++;
if (argc > 1 && argv[1][0] == 't' && argv[1][1] == 0) /* wart: t=>\t */
fs = "\t";
else if (argc > 1 && argv[1][0] != 0)
fs = &argv[1][0];
}
if (fs == NULL || *fs == '\0')
WARNING("field separator FS is empty");
break;
case 'v': /* -v a=1 to be done NOW. one -v for each */
if (argv[1][2] == '\0' && --argc > 1 && isclvar((++argv)[1]))
setclvar(argv[1]);
break;
case 'd':
dbg = atoi(&argv[1][2]);
if (dbg == 0)
dbg = 1;
printf("awk %s\n", version);
break;
default:
WARNING("unknown option %s ignored", argv[1]);
break;
}
argc--;
argv++;
}
/* argv[1] is now the first argument */
if (npfile == 0) { /* no -f; first argument is program */
if (argc <= 1) {
if (dbg)
exit(0);
FATAL("no program given");
}
dprintf( ("program = |%s|\n", argv[1]) );
lexprog = argv[1];
argc--;
argv++;
}
recinit(recsize);
syminit();
compile_time = 1;
argv[0] = cmdname; /* put prog name at front of arglist */
dprintf( ("argc=%d, argv[0]=%s\n", argc, argv[0]) );
arginit(argc, argv);
if (!safe)
envinit(environ);
yyparse();
setlocale(LC_NUMERIC, ""); /* back to whatever it is locally */
if (fs)
*FS = qstring(fs, '\0');
dprintf( ("errorflag=%d\n", errorflag) );
if (errorflag == 0) {
compile_time = 0;
run(winner);
} else
bracecheck();
return(errorflag);
}
int pgetc(void) /* get 1 character from awk program */
{
int c;
for (;;) {
if (yyin == NULL) {
if (curpfile >= npfile)
return EOF;
if (strcmp(pfile[curpfile], "-") == 0)
yyin = stdin;
else if ((yyin = fopen(pfile[curpfile], "r")) == NULL)
FATAL("can't open file %s", pfile[curpfile]);
lineno = 1;
}
if ((c = getc(yyin)) != EOF)
return c;
if (yyin != stdin)
fclose(yyin);
yyin = NULL;
curpfile++;
}
}
char *cursource(void) /* current source file name */
{
if (npfile > 0)
return pfile[curpfile];
else
return NULL;
}

View File

@@ -1,168 +0,0 @@
/****************************************************************
Copyright (C) Lucent Technologies 1997
All Rights Reserved
Permission to use, copy, modify, and distribute this software and
its documentation for any purpose and without fee is hereby
granted, provided that the above copyright notice appear in all
copies and that both that the copyright notice and this
permission notice and warranty disclaimer appear in supporting
documentation, and that the name Lucent Technologies or any of
its entities not be used in advertising or publicity pertaining
to distribution of the software without specific, written prior
permission.
LUCENT DISCLAIMS ALL WARRANTIES WITH REGARD TO THIS SOFTWARE,
INCLUDING ALL IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS.
IN NO EVENT SHALL LUCENT OR ANY OF ITS ENTITIES BE LIABLE FOR ANY
SPECIAL, INDIRECT OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES
WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER
IN AN ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION,
ARISING OUT OF OR IN CONNECTION WITH THE USE OR PERFORMANCE OF
THIS SOFTWARE.
****************************************************************/
/*
* this program makes the table to link function names
* and type indices that is used by execute() in run.c.
* it finds the indices in awkgram.h, produced by yacc.
*/
#include <stdio.h>
#include <string.h>
#include <stdlib.h>
#include "awk.h"
#include "awkgram.h"
struct xx
{ int token;
const char *name;
const char *pname;
} proc[] = {
{ PROGRAM, "program", NULL },
{ BOR, "boolop", " || " },
{ AND, "boolop", " && " },
{ NOT, "boolop", " !" },
{ NE, "relop", " != " },
{ EQ, "relop", " == " },
{ LE, "relop", " <= " },
{ LT, "relop", " < " },
{ GE, "relop", " >= " },
{ GT, "relop", " > " },
{ ARRAY, "array", NULL },
{ INDIRECT, "indirect", "$(" },
{ SUBSTR, "substr", "substr" },
{ SUB, "sub", "sub" },
{ GSUB, "gsub", "gsub" },
{ INDEX, "sindex", "sindex" },
{ SPRINTF, "awksprintf", "sprintf " },
{ ADD, "arith", " + " },
{ MINUS, "arith", " - " },
{ MULT, "arith", " * " },
{ DIVIDE, "arith", " / " },
{ MOD, "arith", " % " },
{ UMINUS, "arith", " -" },
{ POWER, "arith", " **" },
{ PREINCR, "incrdecr", "++" },
{ POSTINCR, "incrdecr", "++" },
{ PREDECR, "incrdecr", "--" },
{ POSTDECR, "incrdecr", "--" },
{ CAT, "cat", " " },
{ PASTAT, "pastat", NULL },
{ PASTAT2, "dopa2", NULL },
{ MATCH, "matchop", " ~ " },
{ NOTMATCH, "matchop", " !~ " },
{ MATCHFCN, "matchop", "matchop" },
{ INTEST, "intest", "intest" },
{ PRINTF, "awkprintf", "printf" },
{ PRINT, "printstat", "print" },
{ CLOSE, "closefile", "closefile" },
{ DELETE, "awkdelete", "awkdelete" },
{ SPLIT, "split", "split" },
{ ASSIGN, "assign", " = " },
{ ADDEQ, "assign", " += " },
{ SUBEQ, "assign", " -= " },
{ MULTEQ, "assign", " *= " },
{ DIVEQ, "assign", " /= " },
{ MODEQ, "assign", " %= " },
{ POWEQ, "assign", " ^= " },
{ CONDEXPR, "condexpr", " ?: " },
{ IF, "ifstat", "if(" },
{ WHILE, "whilestat", "while(" },
{ FOR, "forstat", "for(" },
{ DO, "dostat", "do" },
{ IN, "instat", "instat" },
{ NEXT, "jump", "next" },
{ NEXTFILE, "jump", "nextfile" },
{ EXIT, "jump", "exit" },
{ BREAK, "jump", "break" },
{ CONTINUE, "jump", "continue" },
{ RETURN, "jump", "ret" },
{ BLTIN, "bltin", "bltin" },
{ CALL, "call", "call" },
{ ARG, "arg", "arg" },
{ VARNF, "getnf", "NF" },
{ GETLINE, "awkgetline", "getline" },
{ 0, "", "" },
};
#define SIZE (LASTTOKEN - FIRSTTOKEN + 1)
const char *table[SIZE];
char *names[SIZE];
int main(int argc, char *argv[])
{
const struct xx *p;
int i, n, tok;
char c;
FILE *fp;
char buf[200], name[200], def[200];
printf("#include <stdio.h>\n");
printf("#include \"awk.h\"\n");
printf("#include \"awkgram.h\"\n\n");
for (i = SIZE; --i >= 0; )
names[i] = "";
if ((fp = fopen("awkgram.h", "r")) == NULL) {
fprintf(stderr, "maketab can't open awkgram.h!\n");
exit(1);
}
printf("static char *printname[%d] = {\n", SIZE);
i = 0;
while (fgets(buf, sizeof buf, fp) != NULL) {
n = sscanf(buf, "%1c %s %s %d", &c, def, name, &tok);
if (c != '#' || (n != 4 && strcmp(def,"define") != 0)) /* not a valid #define */
continue;
if (tok < FIRSTTOKEN || tok > LASTTOKEN) {
/* fprintf(stderr, "maketab funny token %d %s ignored\n", tok, buf); */
continue;
}
names[tok-FIRSTTOKEN] = (char *) malloc(strlen(name)+1);
strcpy(names[tok-FIRSTTOKEN], name);
printf("\t(char *) \"%s\",\t/* %d */\n", name, tok);
i++;
}
printf("};\n\n");
for (p=proc; p->token!=0; p++)
table[p->token-FIRSTTOKEN] = p->name;
printf("\nCell *(*proctab[%d])(Node **, int) = {\n", SIZE);
for (i=0; i<SIZE; i++)
if (table[i]==0)
printf("\tnullproc,\t/* %s */\n", names[i]);
else
printf("\t%s,\t/* %s */\n", table[i], names[i]);
printf("};\n\n");
printf("char *tokname(int n)\n"); /* print a tokname() function */
printf("{\n");
printf(" static char buf[100];\n\n");
printf(" if (n < FIRSTTOKEN || n > LASTTOKEN) {\n");
printf(" sprintf(buf, \"token %%d\", n);\n");
printf(" return buf;\n");
printf(" }\n");
printf(" return printname[n-FIRSTTOKEN];\n");
printf("}\n");
return 0;
}

149
commands/awk/n.c Normal file
View File

@@ -0,0 +1,149 @@
/*
* a small awk clone
*
* (C) 1989 Saeko Hirabauashi & Kouichi Hirabayashi
*
* Absolutely no warranty. Use this software with your own risk.
*
* Permission to use, copy, modify and distribute this software for any
* purpose and without fee is hereby granted, provided that the above
* copyright and disclaimer notice.
*
* This program was written to fit into 64K+64K memory of the Minix 1.2.
*/
#include <stdio.h>
#include "awk.h"
NODE *
node0(type)
{
NODE *p;
char *emalloc();
p = (NODE *) emalloc(sizeof(*p) - sizeof(p));
p->n_type = type;
p->n_next = NULL;
return p;
}
NODE *
node1(type, arg0) NODE *arg0;
{
NODE *p;
char *emalloc();
p = (NODE *) emalloc(sizeof(*p));
p->n_type = type;
p->n_next = NULL;
p->n_arg[0] = (NODE *) arg0;
return p;
}
NODE *
node2(type, arg0, arg1) NODE *arg0, *arg1;
{
NODE *p;
char *emalloc();
p = (NODE *) emalloc(sizeof(*p) + sizeof(p) * 1);
p->n_type = type;
p->n_next = NULL;
p->n_arg[0] = (NODE *) arg0;
p->n_arg[1] = (NODE *) arg1;
return p;
}
NODE *
node3(type, arg0, arg1, arg2) NODE *arg0, *arg1, *arg2;
{
NODE *p;
char *emalloc();
p = (NODE *) emalloc(sizeof(*p) + sizeof(p) * 2);
p->n_type = type;
p->n_next = NULL;
p->n_arg[0] = (NODE *) arg0;
p->n_arg[1] = (NODE *) arg1;
p->n_arg[2] = (NODE *) arg2;
return p;
}
NODE *
node4(type, arg0, arg1, arg2, arg3) NODE *arg0, *arg1, *arg2, *arg3;
{
NODE *p;
char *emalloc();
p = (NODE *) emalloc(sizeof(*p) + sizeof(p) * 3);
p->n_type = type;
p->n_next = NULL;
p->n_arg[0] = (NODE *) arg0;
p->n_arg[1] = (NODE *) arg1;
p->n_arg[2] = (NODE *) arg2;
p->n_arg[3] = (NODE *) arg3;
return p;
}
CELL *
mkcell(type, sval, fval) char *sval; double fval;
{
CELL *p;
char *emalloc(), *strsave();
p = (CELL *) emalloc(sizeof(*p));
p->c_type = type;
if (sval == NULL)
p->c_sval = NULL;
else
p->c_sval = strsave(sval);
p->c_fval = fval;
return p;
}
#ifdef TMPCELL
#define MAXTMP 25
CELL tmpcell[MAXTMP];
#endif
CELL *
mktmp(type, sval, fval) char *sval; double fval;
{
register int i;
char *strsave();
#ifdef TMPCELL
for (i = 0; i < MAXTMP; i++)
if (tmpcell[i].c_type == 0) {
tmpcell[i].c_type = type | TMP;
tmpcell[i].c_sval = strsave(sval);
tmpcell[i].c_fval = fval;
return &tmpcell[i];
}
error("formula too complex", (char *) 0);
#else
return mkcell(type | TMP, sval, fval);
#endif
}
c_free(p) CELL *p;
{
if ((p != NULL) && (p->c_type & TMP)) {
#ifdef TMPCELL
p->c_type = 0;
sfree(p->c_sval);
p->c_sval = (char *)NULL;
p->c_fval = 0.0;
#else
if (p->c_sval != NULL) {
Free(p->c_sval);
p->c_sval = NULL;
}
p->c_type = 0;
Free(p);
p = NULL;
#endif
}
}

View File

@@ -1,276 +0,0 @@
/****************************************************************
Copyright (C) Lucent Technologies 1997
All Rights Reserved
Permission to use, copy, modify, and distribute this software and
its documentation for any purpose and without fee is hereby
granted, provided that the above copyright notice appear in all
copies and that both that the copyright notice and this
permission notice and warranty disclaimer appear in supporting
documentation, and that the name Lucent Technologies or any of
its entities not be used in advertising or publicity pertaining
to distribution of the software without specific, written prior
permission.
LUCENT DISCLAIMS ALL WARRANTIES WITH REGARD TO THIS SOFTWARE,
INCLUDING ALL IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS.
IN NO EVENT SHALL LUCENT OR ANY OF ITS ENTITIES BE LIABLE FOR ANY
SPECIAL, INDIRECT OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES
WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER
IN AN ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION,
ARISING OUT OF OR IN CONNECTION WITH THE USE OR PERFORMANCE OF
THIS SOFTWARE.
****************************************************************/
#define DEBUG
#include <stdio.h>
#include <string.h>
#include <stdlib.h>
#include "awk.h"
#include "awkgram.h"
Node *nodealloc(int n)
{
Node *x;
x = (Node *) malloc(sizeof(Node) + (n-1)*sizeof(Node *));
if (x == NULL)
FATAL("out of space in nodealloc");
x->nnext = NULL;
x->lineno = lineno;
return(x);
}
Node *exptostat(Node *a)
{
a->ntype = NSTAT;
return(a);
}
Node *node1(int a, Node *b)
{
Node *x;
x = nodealloc(1);
x->nobj = a;
x->narg[0]=b;
return(x);
}
Node *node2(int a, Node *b, Node *c)
{
Node *x;
x = nodealloc(2);
x->nobj = a;
x->narg[0] = b;
x->narg[1] = c;
return(x);
}
Node *node3(int a, Node *b, Node *c, Node *d)
{
Node *x;
x = nodealloc(3);
x->nobj = a;
x->narg[0] = b;
x->narg[1] = c;
x->narg[2] = d;
return(x);
}
Node *node4(int a, Node *b, Node *c, Node *d, Node *e)
{
Node *x;
x = nodealloc(4);
x->nobj = a;
x->narg[0] = b;
x->narg[1] = c;
x->narg[2] = d;
x->narg[3] = e;
return(x);
}
Node *stat1(int a, Node *b)
{
Node *x;
x = node1(a,b);
x->ntype = NSTAT;
return(x);
}
Node *stat2(int a, Node *b, Node *c)
{
Node *x;
x = node2(a,b,c);
x->ntype = NSTAT;
return(x);
}
Node *stat3(int a, Node *b, Node *c, Node *d)
{
Node *x;
x = node3(a,b,c,d);
x->ntype = NSTAT;
return(x);
}
Node *stat4(int a, Node *b, Node *c, Node *d, Node *e)
{
Node *x;
x = node4(a,b,c,d,e);
x->ntype = NSTAT;
return(x);
}
Node *op1(int a, Node *b)
{
Node *x;
x = node1(a,b);
x->ntype = NEXPR;
return(x);
}
Node *op2(int a, Node *b, Node *c)
{
Node *x;
x = node2(a,b,c);
x->ntype = NEXPR;
return(x);
}
Node *op3(int a, Node *b, Node *c, Node *d)
{
Node *x;
x = node3(a,b,c,d);
x->ntype = NEXPR;
return(x);
}
Node *op4(int a, Node *b, Node *c, Node *d, Node *e)
{
Node *x;
x = node4(a,b,c,d,e);
x->ntype = NEXPR;
return(x);
}
Node *celltonode(Cell *a, int b)
{
Node *x;
a->ctype = OCELL;
a->csub = b;
x = node1(0, (Node *) a);
x->ntype = NVALUE;
return(x);
}
Node *rectonode(void) /* make $0 into a Node */
{
extern Cell *literal0;
return op1(INDIRECT, celltonode(literal0, CUNK));
}
Node *makearr(Node *p)
{
Cell *cp;
if (isvalue(p)) {
cp = (Cell *) (p->narg[0]);
if (isfcn(cp))
SYNTAX( "%s is a function, not an array", cp->nval );
else if (!isarr(cp)) {
xfree(cp->sval);
cp->sval = (char *) makesymtab(NSYMTAB);
cp->tval = ARR;
}
}
return p;
}
#define PA2NUM 50 /* max number of pat,pat patterns allowed */
int paircnt; /* number of them in use */
int pairstack[PA2NUM]; /* state of each pat,pat */
Node *pa2stat(Node *a, Node *b, Node *c) /* pat, pat {...} */
{
Node *x;
x = node4(PASTAT2, a, b, c, itonp(paircnt));
if (paircnt++ >= PA2NUM)
SYNTAX( "limited to %d pat,pat statements", PA2NUM );
x->ntype = NSTAT;
return(x);
}
Node *linkum(Node *a, Node *b)
{
Node *c;
if (errorflag) /* don't link things that are wrong */
return a;
if (a == NULL)
return(b);
else if (b == NULL)
return(a);
for (c = a; c->nnext != NULL; c = c->nnext)
;
c->nnext = b;
return(a);
}
void defn(Cell *v, Node *vl, Node *st) /* turn on FCN bit in definition, */
{ /* body of function, arglist */
Node *p;
int n;
if (isarr(v)) {
SYNTAX( "`%s' is an array name and a function name", v->nval );
return;
}
if (isarg(v->nval) != -1) {
SYNTAX( "`%s' is both function name and argument name", v->nval );
return;
}
v->tval = FCN;
v->sval = (char *) st;
n = 0; /* count arguments */
for (p = vl; p; p = p->nnext)
n++;
v->fval = n;
dprintf( ("defining func %s (%d args)\n", v->nval, n) );
}
int isarg(const char *s) /* is s in argument list for current function? */
{ /* return -1 if not, otherwise arg # */
extern Node *arglist;
Node *p = arglist;
int n;
for (n = 0; p != 0; p = p->nnext, n++)
if (strcmp(((Cell *)(p->narg[0]))->nval, s) == 0)
return n;
return -1;
}
int ptoi(void *p) /* convert pointer to integer */
{
return (int) (long) p; /* swearing that p fits, of course */
}
Node *itonp(int i) /* and vice versa */
{
return (Node *) (long) i;
}

View File

@@ -1,195 +0,0 @@
/****************************************************************
Copyright (C) Lucent Technologies 1997
All Rights Reserved
Permission to use, copy, modify, and distribute this software and
its documentation for any purpose and without fee is hereby
granted, provided that the above copyright notice appear in all
copies and that both that the copyright notice and this
permission notice and warranty disclaimer appear in supporting
documentation, and that the name Lucent Technologies or any of
its entities not be used in advertising or publicity pertaining
to distribution of the software without specific, written prior
permission.
LUCENT DISCLAIMS ALL WARRANTIES WITH REGARD TO THIS SOFTWARE,
INCLUDING ALL IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS.
IN NO EVENT SHALL LUCENT OR ANY OF ITS ENTITIES BE LIABLE FOR ANY
SPECIAL, INDIRECT OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES
WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER
IN AN ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION,
ARISING OUT OF OR IN CONNECTION WITH THE USE OR PERFORMANCE OF
THIS SOFTWARE.
****************************************************************/
extern int yywrap(void);
extern void setfname(Cell *);
extern int constnode(Node *);
extern char *strnode(Node *);
extern Node *notnull(Node *);
extern int yyparse(void);
extern int yylex(void);
extern void startreg(void);
extern int input(void);
extern void unput(int);
extern void unputstr(const char *);
extern int yylook(void);
extern int yyback(int *, int);
extern int yyinput(void);
extern fa *makedfa(const char *, int);
extern fa *mkdfa(const char *, int);
extern int makeinit(fa *, int);
extern void penter(Node *);
extern void freetr(Node *);
extern int hexstr(char **);
extern int quoted(char **);
extern char *cclenter(const char *);
extern void overflo(const char *);
extern void cfoll(fa *, Node *);
extern int first(const Node *);
extern void follow(Node *);
extern int member(int, const char *);
extern int match(fa *, const char *);
extern int pmatch(fa *, const char *);
extern int nematch(fa *, const char *);
extern Node *reparse(const char *);
extern Node *regexp(void);
extern Node *primary(void);
extern Node *concat(Node *);
extern Node *alt(Node *);
extern Node *unary(Node *);
extern int relex(void);
extern int cgoto(fa *, int, int);
extern void freefa(fa *);
extern int pgetc(void);
extern char *cursource(void);
extern Node *nodealloc(int);
extern Node *exptostat(Node *);
extern Node *node1(int, Node *);
extern Node *node2(int, Node *, Node *);
extern Node *node3(int, Node *, Node *, Node *);
extern Node *node4(int, Node *, Node *, Node *, Node *);
extern Node *stat3(int, Node *, Node *, Node *);
extern Node *op2(int, Node *, Node *);
extern Node *op1(int, Node *);
extern Node *stat1(int, Node *);
extern Node *op3(int, Node *, Node *, Node *);
extern Node *op4(int, Node *, Node *, Node *, Node *);
extern Node *stat2(int, Node *, Node *);
extern Node *stat4(int, Node *, Node *, Node *, Node *);
extern Node *celltonode(Cell *, int);
extern Node *rectonode(void);
extern Node *makearr(Node *);
extern Node *pa2stat(Node *, Node *, Node *);
extern Node *linkum(Node *, Node *);
extern void defn(Cell *, Node *, Node *);
extern int isarg(const char *);
extern char *tokname(int);
extern Cell *(*proctab[])(Node **, int);
extern int ptoi(void *);
extern Node *itonp(int);
extern void syminit(void);
extern void arginit(int, char **);
extern void envinit(char **);
extern Array *makesymtab(int);
extern void freesymtab(const Cell *);
extern void freeelem(const Cell *, const char *);
extern Cell *setsymtab(const char *, const char *, double, unsigned int, Array *);
extern int hash(const char *, int);
extern void rehash(Array *);
extern Cell *lookup(const char *, const Array *);
extern double setfval(Cell *, double);
extern void funnyvar(Cell *, const char *);
extern char *setsval(Cell *, const char *);
extern double getfval(Cell *);
extern char *getsval(Cell *);
extern char *getpssval(Cell *); /* for print */
extern char *tostring(const char *);
extern char *qstring(const char *, int);
extern void recinit(unsigned int);
extern void initgetrec(void);
extern void makefields(int, int);
extern void growfldtab(int n);
extern int getrec(char **, int *, int);
extern void nextfile(void);
extern int readrec(char **buf, int *bufsize, FILE *inf);
extern char *getargv(int);
extern void setclvar(char *);
extern void fldbld(void);
extern void cleanfld(int, int);
extern void newfld(int);
extern int refldbld(const char *, const char *);
extern void recbld(void);
extern Cell *fieldadr(int);
extern void yyerror(const char *);
extern void fpecatch(int);
extern void bracecheck(void);
extern void bcheck2(int, int, int);
extern void SYNTAX(const char *, ...);
extern void FATAL(const char *, ...);
extern void WARNING(const char *, ...);
extern void error(void);
extern void eprint(void);
extern void bclass(int);
extern double errcheck(double, const char *);
extern int isclvar(const char *);
extern int is_number(const char *);
extern int adjbuf(char **pb, int *sz, int min, int q, char **pbp, const char *what);
extern void run(Node *);
extern Cell *execute(Node *);
extern Cell *program(Node **, int);
extern Cell *call(Node **, int);
extern Cell *copycell(Cell *);
extern Cell *arg(Node **, int);
extern Cell *jump(Node **, int);
extern Cell *awkgetline(Node **, int);
extern Cell *getnf(Node **, int);
extern Cell *array(Node **, int);
extern Cell *awkdelete(Node **, int);
extern Cell *intest(Node **, int);
extern Cell *matchop(Node **, int);
extern Cell *boolop(Node **, int);
extern Cell *relop(Node **, int);
extern void tfree(Cell *);
extern Cell *gettemp(void);
extern Cell *field(Node **, int);
extern Cell *indirect(Node **, int);
extern Cell *substr(Node **, int);
extern Cell *sindex(Node **, int);
extern int format(char **, int *, const char *, Node *);
extern Cell *awksprintf(Node **, int);
extern Cell *awkprintf(Node **, int);
extern Cell *arith(Node **, int);
extern double ipow(double, int);
extern Cell *incrdecr(Node **, int);
extern Cell *assign(Node **, int);
extern Cell *cat(Node **, int);
extern Cell *pastat(Node **, int);
extern Cell *dopa2(Node **, int);
extern Cell *split(Node **, int);
extern Cell *condexpr(Node **, int);
extern Cell *ifstat(Node **, int);
extern Cell *whilestat(Node **, int);
extern Cell *dostat(Node **, int);
extern Cell *forstat(Node **, int);
extern Cell *instat(Node **, int);
extern Cell *bltin(Node **, int);
extern Cell *printstat(Node **, int);
extern Cell *nullproc(Node **, int);
extern FILE *redirect(int, Node *);
extern FILE *openfile(int, const char *);
extern const char *filename(FILE *);
extern Cell *closefile(Node **, int);
extern void closeall(void);
extern Cell *sub(Node **, int);
extern Cell *gsub(Node **, int);
extern FILE *popen(const char *, const char *);
extern int pclose(FILE *);

627
commands/awk/r.c Normal file
View File

@@ -0,0 +1,627 @@
/*
* a small awk clone
*
* (C) 1989 Saeko Hirabauashi & Kouichi Hirabayashi
*
* Absolutely no warranty. Use this software with your own risk.
*
* Permission to use, copy, modify and distribute this software for any
* purpose and without fee is hereby granted, provided that the above
* copyright and disclaimer notice.
*
* This program was written to fit into 64K+64K memory of the Minix 1.2.
*/
#include <stdio.h>
#include <ctype.h>
#include <sys/types.h>
#include <sys/stat.h>
#include <fcntl.h>
#ifdef DOS
#include <process.h>
#endif
#include "awk.h"
#include "regexp.h"
#define MAXFLD 100
extern char **FS, **RS, **OFS, **ORS, **FILENAME;
extern double *NF, *NR;
extern double *FNR;
extern double *ARGC;
extern SYMBOL *argtab[];
extern CELL *getvar();
char *strsave(), *strcpy(), *getsval(), *jStrchr(), *strchr();
double getfval(), atof();
CELL *mkcell(), *mktmp(), *execute(), *patexec();
FILE *efopen();
extern CELL truecell, falsecell;
extern int pateval;
int infileno = 1;
FILE *ifp;
char record[BUFSIZ];
CELL *field[MAXFLD];
char *fs_str;
regexp *fs_pat;
CELL *
Getline(p) NODE *p;
{
CELL *u;
char *fnam, *s, str[BUFSIZ];
int i;
FILE *fp, *getfp();
if ((int) p->n_arg[0]) /* read into var */
s = str;
else
s = NULL;
if ((int) p->n_arg[1]) { /* file name */
u = execute(p->n_arg[1]);
fnam = getsval(u);
fp = getfp(fnam, (int) p->n_arg[2]);
c_free(u);
i = get1rec(s, fp);
}
else
i = Getrec(s);
if (s == str) {
u = execute(p->n_arg[0]);
setsval(u, str);
}
return mktmp(NUM, NULL, (double) i);
}
static
get1rec(buf, fp) char *buf; FILE *fp;
{
register int c;
register char rs, *s;
int mflg;
if (buf == NULL)
buf = record;
if ((rs = **RS) == '\0') { /* multi line record */
mflg = 1;
rs = '\n';
}
else
mflg = 0;
if (feof(fp) || (c = getc(fp)) == EOF)
return 0;
for (s = buf; ; ) {
for ( ; c != rs && c != EOF; c = getc(fp)) {
if (isKanji(c)) {
*s++ = c; c = getc(fp);
}
*s++ = c;
}
if (mflg) {
if ((c = getc(fp)) == '\n' || c == EOF)
break;
*s++ = '\n';
}
else
break;
}
*s = '\0';
#if 1
if (buf == record) {
#else
if (buf == record && c != EOF) {
#endif
mkfld(record, *FS, field);
(*NR)++;
(*FNR)++;
}
return s > buf || c != EOF ? 1 : 0;
}
Getrec(s) char *s;
{
CELL *u;
char *file, str[8];
while (ifp == stdin || infileno < (int)*ARGC) {
if (ifp == NULL) {
*FNR = 0.0;
if (infileno == (int)*ARGC)
break;
sprintf(str, "%d", infileno);
u = getvar(str, argtab);
file = getsval(u);
if (strchr(file, '=') != NULL) {
setvar(file);
infileno++;
continue;
}
else if (strcmp(file, "") == 0) {
/*
if (infileno == (int)*ARGC - 1)
ifp = stdin;
*/
infileno++;
continue;
}
else {
if (strcmp(file, "-") == 0)
ifp = stdin;
else
ifp = efopen(file, "r");
*FILENAME = file;
}
}
if (get1rec(s, ifp))
return 1;
else {
if (ifp != stdin)
fclose(ifp);
ifp = NULL;
infileno++;
}
}
ifp = stdin; /* for further "getline" */
*FILENAME = "-";
return 0; /* EOF */
}
mkfld(rec, sep, fld) char *rec, *sep; CELL *fld[];
{
char *s, *t;
char str[BUFSIZ];
int i, j, n;
int skip = 0;
if (strlen(sep) > 1)
return r_mkfld(rec, sep, fld);
if (*sep == ' ' || *sep == '\0') {
sep = " \t\n"; skip++;
}
for (i = 1, n = (int) *NF; i <= n; i++) {
sfree(fld[i]->c_sval);
sfree(fld[i]);
fld[i] = NULL;
}
for (i = 0, s = rec; ; ) {
t = str;
if (skip) {
while (*s && strchr(" \t\n", *s))
s++;
if (*s == '\0')
break;
}
while (*s && !jStrchr(sep, *s)) {
if (isKanji(*s))
*t++ = *s++;
*t++ = *s++;
}
*t = '\0';
if (isnum(str))
fld[++i] = mkcell(FLD|STR|NUM, str, atof(str));
else
fld[++i] = mkcell(FLD|STR, str, 0.0);
if (*s)
s++;
else
break;
}
*NF = (double) i;
return i;
}
static
r_mkfld(rec, sep, fld) char *rec, *sep; CELL *fld[];
{
char *s, *t;
char str[BUFSIZ];
int i, n;
regexp *mkpat();
extern int r_start, r_length;
if (strcmp(*FS, fs_str) != 0) {
sfree(fs_str); sfree(fs_pat);
fs_str = strsave(*FS);
fs_pat = mkpat(fs_str);
}
for (i = 1, n = (int) *NF; i <= n; i++) {
sfree(fld[i]->c_sval);
sfree(fld[i]);
fld[i] = NULL;
}
for (i = 0, s = rec, t = str; *s; ) {
if (match(fs_pat, s)) {
for (n = r_start; --n > 0; )
*t++ = *s++;
}
else {
while (*s)
*t++ = *s++;
}
*t = '\0';
t = str;
fld[++i] = mkcell(FLD|STR, str, 0.0);
if (*s)
s += r_length;
}
*NF = (double) i;
return i;
}
mkrec(u) CELL *u;
{
register char *s, *t;
register int i, j;
for (j = (int)*NF, i = 1; i <= j; i++)
if (field[i] == u)
break;
if (i > j) {
for ( ; i < MAXFLD; i++)
if (field[i] == u)
break;
if (i == MAXFLD)
error("too many field (%d)", i);
*NF = (double)i;
}
for (t = record, i = 1, j = (int) *NF; i <= j; i++) {
if (i > 1)
*t++ = **OFS;
for (s = getsval(field[i]); *s; )
*t++ = *s++;
}
*t++ = '\0';
}
CELL *
Field(p) NODE *p;
{
CELL *u;
int i, j;
u = execute(p->n_arg[0]);
i = (int) getfval(u);
c_free(u);
j = (int)*NF;
if (i > j)
for (++j; j <= i; j++) {
if (field[j] == NULL)
field[j] = mkcell(FLD|STR, "", 0.0);
}
return field[i];
}
CELL *
P1stat(p) NODE *p;
{
CELL *u;
double x;
pateval++;
u = execute(p->n_arg[0]);
pateval = 0;
x = getfval(u);
c_free(u);
if (x != 0.0)
u = execute(p->n_arg[1]);
else
u = &truecell;
return u;
}
CELL *
P2stat(p) NODE *p;
{
static stat = 0;
CELL *u, *v;
double x;
switch (stat) {
case 0:
pateval++;
u = execute(p->n_arg[0]);
pateval = 0;
x = getfval(u);
c_free(u);
if (x == 0.0) {
u = &truecell; break;
}
else
stat++;
/* fall through */
case 1:
u = execute(p->n_arg[2]);
c_free(u);
pateval++;
u = execute(p->n_arg[1]);
pateval = 0;
x = getfval(u);
if (x != 0.0)
stat = 0;
break;
default:
u = &truecell;
break;
}
return u;
}
CELL *
Print0()
{
/*
int i, j;
char *s, str[BUFSIZ];
for (*str = '\0', i = 1, j = (int) *NF; i <= j; i++) {
if (i > 1)
strcat(str, *OFS);
s = getsval(field[i]);
strcat(str, s);
}
strcat(str, *ORS);
fputs(str, stdout);
*/
fprintf(stdout, "%s%s", record, *ORS);
return &truecell;
}
char *
format(t, p) char *t; NODE *p;
{
CELL *u, *v;
char *r, *s, *s0, fmt[BUFSIZ];
double x;
int i;
u = execute(p->n_arg[2]);
s = s0 = getsval(u);
/*
printf("fmt(%s)\n", s);
*/
for (i = 3; *s; s++) {
if (isKanji(*s)) {
*t++ = *s++; *t++ = *s; continue;
}
if (*s != '%') {
*t++ = *s; continue;
}
else if (*(s + 1) == '%') {
*t++ = *s++; continue;
}
for (r = fmt, *r++ = *s++; *r++ = *s; s++) {
if (strchr("%cdefgosux", *s))
break;
}
*r = '\0';
if (p->n_arg[i] == NULL)
error("not enough args in printf(%s)", s0);
v = execute(p->n_arg[i++]);
if (*s == 's')
r = getsval(v);
else
x = getfval(v);
/*
printf("val(%d)(%s)\n", v->c_type, v->c_sval);
*/
switch (*s) {
case 'c':
sprintf(t, fmt, (int) x);
break;
case 'd':
if (*(s - 1) != 'l') {
*--r = 'l'; *++r = 'd'; *++r = '\0';
}
sprintf(t, fmt, (long) x);
break;
case 'e': case 'f': case 'g':
sprintf(t, fmt, x);
break;
case 'o': case 'u': case 'x':
if (*(s - 1) == 'l')
sprintf(t, fmt, (long) x);
else
sprintf(t, fmt, (int) x);
break;
case 's':
/*r = getsval(v);*/
sprintf(t, fmt, r);
break;
default:
strcpy(t, fmt);
break;
}
c_free(v);
t += strlen(t);
}
c_free(u);
*t = '\0';
}
#define MAXFILE 10
struct {
char *f_name; /* file name */
FILE *f_fp;
int f_type;
} filetab[MAXFILE];
FILE *
getfp(file, type) char *file;
{
register int i;
register char *name, *mode;
char *awktmp();
FILE *fp, *efopen(), *epopen();
for (i = 0; i < MAXFILE; i++)
if (filetab[i].f_name && strcmp(filetab[i].f_name, file) == 0)
return filetab[i].f_fp;
for (i = 0; i < MAXFILE; i++)
if (!filetab[i].f_fp)
break;
if (i == MAXFILE)
error("too many files to open");
name = file;
switch (type) {
case R_OUT: mode = "w"; break;
case R_APD: mode = "a"; break;
case R_POUT:
#ifdef DOS
name = awktmp(i); mode = "w"; /* MS-DOS */
#else
fp = epopen(file, "w");
goto g1;
#endif
break;
case R_IN: mode = "r"; break;
case R_PIN:
#ifdef DOS
{
int savefd, fd, result;
name = awktmp(i);
if ((fd = open(name,
O_WRONLY|O_TEXT|O_CREAT|O_TRUNC,S_IREAD|S_IWRITE)) == -1)
error("can't open %s", name);
savefd = dup(1); dup2(fd, 1); close(fd);
if ((result =
system(file)) == -1)
error("can't exec %s", file);
dup2(savefd, 1); close(savefd); close(fd);
mode = "r";
}
#else
fp = epopen(file,"r");
goto g1;
#endif
break;
}
fp = efopen(name, mode);
g1:
filetab[i].f_name = strsave(file);
filetab[i].f_type = type;
filetab[i].f_fp = fp;
return fp;
}
closeall()
{
register int i;
for (i = 0; i < MAXFILE; i++)
close1(i);
}
CELL *
Close(s) char *s;
{
register int i;
for (i = 0; i < MAXFILE; i++)
if (strcmp(s, filetab[i].f_name) == 0) {
close1(i);
break;
}
i = (i == MAXFILE) ? 0 : 1;
return mktmp(NUM, NULL, (double) i);
}
static
close1(i)
{
int fd, result, savefd;
char *awktmp();
if (filetab[i].f_fp == NULL)
return;
switch (filetab[i].f_type) {
case R_PIN:
#ifdef DOS
fclose(filetab[i].f_fp);
unlink(awktmp(i));
#else
pclose(filetab[i].f_fp);
#endif
break;
case R_IN: case R_OUT: case R_APD:
fclose(filetab[i].f_fp);
break;
case R_POUT:
#ifdef DOS
fclose(filetab[i].f_fp);
if ((fd = open(awktmp(i), O_RDONLY)) == NULL)
error("can't open %s", awktmp(i));
savefd = dup(0);
dup2(fd, 0);
close(fd);
if ((result =
system(filetab[i].f_name)) == -1)
/*
spawnl(P_WAIT, "/usr/bin/sh", "sh", "-c", filetab[i].f_name, (char *) 0)) == -1)
fprintf(stderr, "can't spawn /bin/sh\n");
*/
error("can't exec %s", filetab[i].f_name);
dup2(savefd, 0);
close(savefd);
unlink(awktmp(i));
#else
pclose(filetab[i].f_fp);
#endif
break;
}
sfree(filetab[i].f_name);
filetab[i].f_type = 0;
filetab[i].f_name = NULL;
filetab[i].f_fp = NULL;
}
#ifndef DOS
FILE *
epopen(file, mod) char *file, *mod;
{
FILE *fp, *popen();
if ((fp = popen(file, mod)) == NULL)
error("can't poen %s", file);
return fp;
}
#endif
static char *
awktmp(i)
{
static char str[16];
sprintf(str, "awk000%02d.tmp", i);
return str;
}
Index(s, t) char *s, *t;
{
register char *u, *v;
register int i;
for (i = 1; *s; s++, i++) {
for (u = s, v = t; *v; u++, v++) {
if (isKanji(*v)) {
if (*u != *v)
break;
u++; v++;
}
if (*u != *v)
break;
}
if (*v == '\0')
return i;
if (isKanji(*s))
s++;
}
return 0;
}

1440
commands/awk/regexp.c Normal file

File diff suppressed because it is too large Load Diff

23
commands/awk/regexp.h Normal file
View File

@@ -0,0 +1,23 @@
/*
* Definitions etc. for regexp(3) routines.
*
* Caveat: this is V8 regexp(3) [actually, a reimplementation thereof],
* not the System V one.
*/
#define ushort unsigned short
#define CHARBITS 0xffff
#define NSUBEXP 10
typedef struct regexp {
ushort *startp[NSUBEXP];
ushort *endp[NSUBEXP];
ushort regstart; /* Internal use only. */
ushort reganch; /* Internal use only. */
ushort *regmust; /* Internal use only. */
int regmlen; /* Internal use only. */
ushort program[1]; /* Unwarranted chumminess with compiler. */
} regexp;
extern regexp *regcomp();
extern int regexec();
extern int regsub();
extern int regerror();

File diff suppressed because it is too large Load Diff

View File

@@ -1,457 +0,0 @@
/****************************************************************
Copyright (C) Lucent Technologies 1997
All Rights Reserved
Permission to use, copy, modify, and distribute this software and
its documentation for any purpose and without fee is hereby
granted, provided that the above copyright notice appear in all
copies and that both that the copyright notice and this
permission notice and warranty disclaimer appear in supporting
documentation, and that the name Lucent Technologies or any of
its entities not be used in advertising or publicity pertaining
to distribution of the software without specific, written prior
permission.
LUCENT DISCLAIMS ALL WARRANTIES WITH REGARD TO THIS SOFTWARE,
INCLUDING ALL IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS.
IN NO EVENT SHALL LUCENT OR ANY OF ITS ENTITIES BE LIABLE FOR ANY
SPECIAL, INDIRECT OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES
WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER
IN AN ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION,
ARISING OUT OF OR IN CONNECTION WITH THE USE OR PERFORMANCE OF
THIS SOFTWARE.
****************************************************************/
#define DEBUG
#include <stdio.h>
#include <math.h>
#include <ctype.h>
#include <string.h>
#include <stdlib.h>
#include "awk.h"
#include "awkgram.h"
#define FULLTAB 2 /* rehash when table gets this x full */
#define GROWTAB 4 /* grow table by this factor */
Array *symtab; /* main symbol table */
char **FS; /* initial field sep */
char **RS; /* initial record sep */
char **OFS; /* output field sep */
char **ORS; /* output record sep */
char **OFMT; /* output format for numbers */
char **CONVFMT; /* format for conversions in getsval */
Awkfloat *NF; /* number of fields in current record */
Awkfloat *NR; /* number of current record */
Awkfloat *FNR; /* number of current record in current file */
char **FILENAME; /* current filename argument */
Awkfloat *ARGC; /* number of arguments from command line */
char **SUBSEP; /* subscript separator for a[i,j,k]; default \034 */
Awkfloat *RSTART; /* start of re matched with ~; origin 1 (!) */
Awkfloat *RLENGTH; /* length of same */
Cell *fsloc; /* FS */
Cell *nrloc; /* NR */
Cell *nfloc; /* NF */
Cell *fnrloc; /* FNR */
Array *ARGVtab; /* symbol table containing ARGV[...] */
Array *ENVtab; /* symbol table containing ENVIRON[...] */
Cell *rstartloc; /* RSTART */
Cell *rlengthloc; /* RLENGTH */
Cell *symtabloc; /* SYMTAB */
Cell *nullloc; /* a guaranteed empty cell */
Node *nullnode; /* zero&null, converted into a node for comparisons */
Cell *literal0;
extern Cell **fldtab;
void syminit(void) /* initialize symbol table with builtin vars */
{
literal0 = setsymtab("0", "0", 0.0, NUM|STR|CON|DONTFREE, symtab);
/* this is used for if(x)... tests: */
nullloc = setsymtab("$zero&null", "", 0.0, NUM|STR|CON|DONTFREE, symtab);
nullnode = celltonode(nullloc, CCON);
fsloc = setsymtab("FS", " ", 0.0, STR|DONTFREE, symtab);
FS = &fsloc->sval;
RS = &setsymtab("RS", "\n", 0.0, STR|DONTFREE, symtab)->sval;
OFS = &setsymtab("OFS", " ", 0.0, STR|DONTFREE, symtab)->sval;
ORS = &setsymtab("ORS", "\n", 0.0, STR|DONTFREE, symtab)->sval;
OFMT = &setsymtab("OFMT", "%.6g", 0.0, STR|DONTFREE, symtab)->sval;
CONVFMT = &setsymtab("CONVFMT", "%.6g", 0.0, STR|DONTFREE, symtab)->sval;
FILENAME = &setsymtab("FILENAME", "", 0.0, STR|DONTFREE, symtab)->sval;
nfloc = setsymtab("NF", "", 0.0, NUM, symtab);
NF = &nfloc->fval;
nrloc = setsymtab("NR", "", 0.0, NUM, symtab);
NR = &nrloc->fval;
fnrloc = setsymtab("FNR", "", 0.0, NUM, symtab);
FNR = &fnrloc->fval;
SUBSEP = &setsymtab("SUBSEP", "\034", 0.0, STR|DONTFREE, symtab)->sval;
rstartloc = setsymtab("RSTART", "", 0.0, NUM, symtab);
RSTART = &rstartloc->fval;
rlengthloc = setsymtab("RLENGTH", "", 0.0, NUM, symtab);
RLENGTH = &rlengthloc->fval;
symtabloc = setsymtab("SYMTAB", "", 0.0, ARR, symtab);
symtabloc->sval = (char *) symtab;
}
void arginit(int ac, char **av) /* set up ARGV and ARGC */
{
Cell *cp;
int i;
char temp[50];
ARGC = &setsymtab("ARGC", "", (Awkfloat) ac, NUM, symtab)->fval;
cp = setsymtab("ARGV", "", 0.0, ARR, symtab);
ARGVtab = makesymtab(NSYMTAB); /* could be (int) ARGC as well */
cp->sval = (char *) ARGVtab;
for (i = 0; i < ac; i++) {
sprintf(temp, "%d", i);
if (is_number(*av))
setsymtab(temp, *av, atof(*av), STR|NUM, ARGVtab);
else
setsymtab(temp, *av, 0.0, STR, ARGVtab);
av++;
}
}
void envinit(char **envp) /* set up ENVIRON variable */
{
Cell *cp;
char *p;
cp = setsymtab("ENVIRON", "", 0.0, ARR, symtab);
ENVtab = makesymtab(NSYMTAB);
cp->sval = (char *) ENVtab;
for ( ; *envp; envp++) {
if ((p = strchr(*envp, '=')) == NULL)
continue;
if( p == *envp ) /* no left hand side name in env string */
continue;
*p++ = 0; /* split into two strings at = */
if (is_number(p))
setsymtab(*envp, p, atof(p), STR|NUM, ENVtab);
else
setsymtab(*envp, p, 0.0, STR, ENVtab);
p[-1] = '='; /* restore in case env is passed down to a shell */
}
}
Array *makesymtab(int n) /* make a new symbol table */
{
Array *ap;
Cell **tp;
ap = (Array *) malloc(sizeof(Array));
tp = (Cell **) calloc(n, sizeof(Cell *));
if (ap == NULL || tp == NULL)
FATAL("out of space in makesymtab");
ap->nelem = 0;
ap->size = n;
ap->tab = tp;
return(ap);
}
void freesymtab(const Cell *ap) /* free a symbol table */
{
Cell *cp, *temp;
Array *tp;
int i;
if (!isarr(ap))
return;
tp = (Array *) ap->sval;
if (tp == NULL)
return;
for (i = 0; i < tp->size; i++) {
for (cp = tp->tab[i]; cp != NULL; cp = temp) {
xfree(cp->nval);
if (freeable(cp))
xfree(cp->sval);
temp = cp->cnext; /* avoids freeing then using */
free(cp);
tp->nelem--;
}
tp->tab[i] = 0;
}
if (tp->nelem != 0)
WARNING("can't happen: inconsistent element count freeing %s", ap->nval);
free(tp->tab);
free(tp);
}
void freeelem(const Cell *ap, const char *s)
/* free elem s from ap (i.e., ap["s"] */
{
Array *tp;
Cell *p, *prev = NULL;
int h;
tp = (Array *) ap->sval;
h = hash(s, tp->size);
for (p = tp->tab[h]; p != NULL; prev = p, p = p->cnext)
if (strcmp(s, p->nval) == 0) {
if (prev == NULL) /* 1st one */
tp->tab[h] = p->cnext;
else /* middle somewhere */
prev->cnext = p->cnext;
if (freeable(p))
xfree(p->sval);
free(p->nval);
free(p);
tp->nelem--;
return;
}
}
Cell *setsymtab(const char *n, const char *s, Awkfloat f, unsigned t, Array *tp)
{
int h;
Cell *p;
if (n != NULL && (p = lookup(n, tp)) != NULL) {
dprintf( ("setsymtab found %p: n=%s s=\"%s\" f=%g t=%o\n",
p, NN(p->nval), NN(p->sval), p->fval, p->tval) );
return(p);
}
p = (Cell *) malloc(sizeof(Cell));
if (p == NULL)
FATAL("out of space for symbol table at %s", n);
p->nval = tostring(n);
p->sval = s ? tostring(s) : tostring("");
p->fval = f;
p->tval = t;
p->csub = CUNK;
p->ctype = OCELL;
tp->nelem++;
if (tp->nelem > FULLTAB * tp->size)
rehash(tp);
h = hash(n, tp->size);
p->cnext = tp->tab[h];
tp->tab[h] = p;
dprintf( ("setsymtab set %p: n=%s s=\"%s\" f=%g t=%o\n",
p, p->nval, p->sval, p->fval, p->tval) );
return(p);
}
int hash(const char *s, int n) /* form hash value for string s */
{
unsigned hashval;
for (hashval = 0; *s != '\0'; s++)
hashval = (*s + 31 * hashval);
return hashval % n;
}
void rehash(Array *tp) /* rehash items in small table into big one */
{
int i, nh, nsz;
Cell *cp, *op, **np;
nsz = GROWTAB * tp->size;
np = (Cell **) calloc(nsz, sizeof(Cell *));
if (np == NULL) /* can't do it, but can keep running. */
return; /* someone else will run out later. */
for (i = 0; i < tp->size; i++) {
for (cp = tp->tab[i]; cp; cp = op) {
op = cp->cnext;
nh = hash(cp->nval, nsz);
cp->cnext = np[nh];
np[nh] = cp;
}
}
free(tp->tab);
tp->tab = np;
tp->size = nsz;
}
Cell *lookup(const char *s, const Array *tp) /* look for s in tp */
{
Cell *p;
int h;
h = hash(s, tp->size);
for (p = tp->tab[h]; p != NULL; p = p->cnext)
if (strcmp(s, p->nval) == 0)
return(p); /* found it */
return(NULL); /* not found */
}
Awkfloat setfval(Cell *vp, Awkfloat f) /* set float val of a Cell */
{
int fldno;
if ((vp->tval & (NUM | STR)) == 0)
funnyvar(vp, "assign to");
if (isfld(vp)) {
donerec = 0; /* mark $0 invalid */
fldno = atoi(vp->nval);
if (fldno > *NF)
newfld(fldno);
dprintf( ("setting field %d to %g\n", fldno, f) );
} else if (isrec(vp)) {
donefld = 0; /* mark $1... invalid */
donerec = 1;
}
if (freeable(vp))
xfree(vp->sval); /* free any previous string */
vp->tval &= ~STR; /* mark string invalid */
vp->tval |= NUM; /* mark number ok */
dprintf( ("setfval %p: %s = %g, t=%o\n", vp, NN(vp->nval), f, vp->tval) );
return vp->fval = f;
}
void funnyvar(Cell *vp, const char *rw)
{
if (isarr(vp))
FATAL("can't %s %s; it's an array name.", rw, vp->nval);
if (vp->tval & FCN)
FATAL("can't %s %s; it's a function.", rw, vp->nval);
WARNING("funny variable %p: n=%s s=\"%s\" f=%g t=%o",
vp, vp->nval, vp->sval, vp->fval, vp->tval);
}
char *setsval(Cell *vp, const char *s) /* set string val of a Cell */
{
char *t;
int fldno;
dprintf( ("starting setsval %p: %s = \"%s\", t=%o, r,f=%d,%d\n",
vp, NN(vp->nval), s, vp->tval, donerec, donefld) );
if ((vp->tval & (NUM | STR)) == 0)
funnyvar(vp, "assign to");
if (isfld(vp)) {
donerec = 0; /* mark $0 invalid */
fldno = atoi(vp->nval);
if (fldno > *NF)
newfld(fldno);
dprintf( ("setting field %d to %s (%p)\n", fldno, s, s) );
} else if (isrec(vp)) {
donefld = 0; /* mark $1... invalid */
donerec = 1;
}
t = tostring(s); /* in case it's self-assign */
if (freeable(vp))
xfree(vp->sval);
vp->tval &= ~NUM;
vp->tval |= STR;
vp->tval &= ~DONTFREE;
dprintf( ("setsval %p: %s = \"%s (%p) \", t=%o r,f=%d,%d\n",
vp, NN(vp->nval), t,t, vp->tval, donerec, donefld) );
return(vp->sval = t);
}
Awkfloat getfval(Cell *vp) /* get float val of a Cell */
{
if ((vp->tval & (NUM | STR)) == 0)
funnyvar(vp, "read value of");
if (isfld(vp) && donefld == 0)
fldbld();
else if (isrec(vp) && donerec == 0)
recbld();
if (!isnum(vp)) { /* not a number */
vp->fval = atof(vp->sval); /* best guess */
if (is_number(vp->sval) && !(vp->tval&CON))
vp->tval |= NUM; /* make NUM only sparingly */
}
dprintf( ("getfval %p: %s = %g, t=%o\n", vp, NN(vp->nval), vp->fval, vp->tval) );
return(vp->fval);
}
static char *get_str_val(Cell *vp, char **fmt)
/* get string val of a Cell */
{
char s[100]; /* BUG: unchecked */
double dtemp;
if ((vp->tval & (NUM | STR)) == 0)
funnyvar(vp, "read value of");
if (isfld(vp) && donefld == 0)
fldbld();
else if (isrec(vp) && donerec == 0)
recbld();
if (isstr(vp) == 0) {
if (freeable(vp))
xfree(vp->sval);
if (modf(vp->fval, &dtemp) == 0) /* it's integral */
sprintf(s, "%.30g", vp->fval);
else
sprintf(s, *fmt, vp->fval);
vp->sval = tostring(s);
vp->tval &= ~DONTFREE;
vp->tval |= STR;
}
dprintf( ("getsval %p: %s = \"%s (%p)\", t=%o\n", vp, NN(vp->nval), vp->sval, vp->sval, vp->tval) );
return(vp->sval);
}
char *getsval(Cell *vp) /* get string val of a Cell */
{
return get_str_val(vp, CONVFMT);
}
char *getpssval(Cell *vp) /* get string val of a Cell for print */
{
return get_str_val(vp, OFMT);
}
char *tostring(const char *s) /* make a copy of string s */
{
char *p;
p = (char *) malloc(strlen(s)+1);
if (p == NULL)
FATAL("out of space in tostring on %s", s);
strcpy(p, s);
return(p);
}
char *qstring(const char *is, int delim) /* collect string up to next delim */
{
const char *os = is;
int c, n;
uschar *s = (uschar *) is;
uschar *buf, *bp;
if ((buf = (uschar *) malloc(strlen(is)+3)) == NULL)
FATAL( "out of space in qstring(%s)", s);
for (bp = buf; (c = *s) != delim; s++) {
if (c == '\n')
SYNTAX( "newline in string %.20s...", os );
else if (c != '\\')
*bp++ = c;
else { /* \something */
c = *++s;
if (c == 0) { /* \ at end */
*bp++ = '\\';
break; /* for loop */
}
switch (c) {
case '\\': *bp++ = '\\'; break;
case 'n': *bp++ = '\n'; break;
case 't': *bp++ = '\t'; break;
case 'b': *bp++ = '\b'; break;
case 'f': *bp++ = '\f'; break;
case 'r': *bp++ = '\r'; break;
default:
if (!isdigit(c)) {
*bp++ = c;
break;
}
n = c - '0';
if (isdigit(s[1])) {
n = 8 * n + *++s - '0';
if (isdigit(s[1]))
n = 8 * n + *++s - '0';
}
*bp++ = n;
break;
}
}
}
*bp++ = 0;
return (char *) buf;
}

703
commands/awk/v.c Normal file
View File

@@ -0,0 +1,703 @@
/*
* a small awk clone
*
* (C) 1989 Saeko Hirabauashi & Kouichi Hirabayashi
*
* Absolutely no warranty. Use this software with your own risk.
*
* Permission to use, copy, modify and distribute this software for any
* purpose and without fee is hereby granted, provided that the above
* copyright and disclaimer notice.
*
* This program was written to fit into 64K+64K memory of the Minix 1.2.
*/
#include <stdio.h>
#include <ctype.h>
#include "awk.h"
#include "regexp.h"
#define PI 3.14159265358979323846
#define HASHSIZE 50
#define MAXFIELD 100
double atof();
char *getsval(), *jStrchar();
extern CELL *execute(), *_Arg();
extern char record[];
extern CELL *field[];
extern CELL truecell, falsecell;
extern prmflg;
SYMBOL *hashtab[HASHSIZE];
SYMBOL *funtab[HASHSIZE];
SYMBOL *argtab[HASHSIZE];
SYMBOL *envtab[HASHSIZE];
char *strsave(), *emalloc(), *strchr();
CELL *lookup(), *install(), *_install(), *mkcell(), *mktmp(), *getvar();
char **FS, **RS, **OFS, **ORS, **OFMT, **FILENAME;
char **SUBSEP;
double *NR, *NF;
double *FNR, *ARGC, *RSTART, *RLENGTH;
init()
{
FS = &install("FS", VAR|STR, " ", 0.0, hashtab)->c_sval;
RS = &install("RS", VAR|STR, "\n", 0.0, hashtab)->c_sval;
OFS = &install("OFS", VAR|STR , " ", 0.0, hashtab)->c_sval;
ORS = &install("ORS", VAR|STR, "\n", 0.0, hashtab)->c_sval;
OFMT = &install("OFMT", VAR|STR, "%.6g", 0.0, hashtab)->c_sval;
NR = &install("NR", VAR|NUM, (char *)NULL, 0.0, hashtab)->c_fval;
NF = &install("NF", VAR|NUM, (char *)NULL, 0.0, hashtab)->c_fval;
FILENAME = &install("FILENAME", VAR|STR, (char *)NULL, 0.0, hashtab)->c_sval;
install("PI", VAR|NUM, (char *)NULL, PI, hashtab);
field[0] = mkcell(REC|STR, (char *)NULL, 0.0); /* $0 */
field[0]->c_sval = record;
SUBSEP = &install("SUBSEP", VAR|STR, "\034", 0.0, hashtab)->c_sval;
FNR = &install("FNR", VAR|NUM, (char *)NULL, 0.0, hashtab)->c_fval;
RSTART = &install("RSTART", VAR|NUM, (char *)NULL, 0.0, hashtab)->c_fval;
RLENGTH = &install("RLENGTH", VAR|NUM, (char *)NULL, 0.0, hashtab)->c_fval;
}
setvar(s) char *s;
{
CELL *u;
char *t;
for (t = s; *t && *t != '='; t++)
;
*t++ = '\0';
if ((u = lookup(s, hashtab)) == (CELL *)NULL) {
if (isnum(t))
install(s, VAR|NUM|STR, t, atof(t), hashtab);
else
install(s, VAR|STR, t, 0.0, hashtab);
}
else {
if (isnum(t))
setfval(u, atof(t));
else
setsval(u, t);
}
}
initarg(arg0, argc, argv, envp) char *arg0, **argv, **envp;
{
CELL *u;
register int i;
register char str[4], *p;
ARGC = &install("ARGC", VAR|NUM, (char *)NULL, (double)argc+1, hashtab)->c_fval;
u = install("ARGV", ARR, (char *)NULL, 0.0, hashtab);
u->c_sval = (char *) argtab;
install("0", VAR|STR, arg0, 0.0, argtab);
for (i = 0; i < argc; i++) {
sprintf(str, "%d", i+1);
if (isnum(argv[i]))
install(str, VAR|STR|NUM, argv[i], atof(argv[i]), argtab);
else
install(str, VAR|STR, argv[i], 0.0, argtab);
}
u = install("ENVIRON", ARR, (char *)NULL, 0.0, hashtab);
u->c_sval = (char *) envtab;
for (i = 0; envp[i] && *envp[i]; i++) {
if ((p = strchr(envp[i], '=')) != NULL) {
*p = 0;
if (isnum(p+1))
install(envp[i], VAR|STR|NUM, p+1, atof(p+1), envtab);
else
install(envp[i], VAR|STR, p+1, 0.0, envtab);
*p = '=';
}
}
}
static
hash(s) unsigned char *s;
{
register unsigned int h;
for (h = 0; *s; )
h += *s++;
return h % HASHSIZE;
}
CELL *
lookup(s, h) char *s; SYMBOL *h[];
{
register SYMBOL *p;
for (p = h[hash(s)]; p; p = p->s_next)
if (strcmp(s, p->s_name) == 0)
return p->s_val;
return (CELL *)NULL;
}
static CELL *
install(name, type, sval, fval, h) char *name, *sval; double fval; SYMBOL *h[];
{
CELL *u;
if ((u = lookup(name, h)) == (CELL *)NULL)
u = _install(name, type, sval, fval, h);
else
error("%s is doubly defined", name);
return u;
}
static CELL *
_install(name, type, sval, fval, h) char *name, *sval; double fval; SYMBOL *h[];{
register SYMBOL *p;
CELL *u;
int hval;
p = (SYMBOL *) emalloc(sizeof(*p));
u = (CELL *) emalloc(sizeof(*u));
p->s_name = strsave(name);
p->s_val = u;
hval = hash(name);
p->s_next = h[hval];
h[hval] = p;
u->c_type = type;
u->c_sval = strsave(sval);
#if 0
if (!(type & NUM) && isnum(sval)) {
u->c_fval = atof(sval);
u->c_type |= NUM;
}
else
#endif
u->c_fval = fval;
return u;
}
CELL *
getvar(s, h, typ) char *s; SYMBOL *h[];
{
CELL *u;
SYMBOL *p;
char *t;
int i, hval;
if ((u = lookup(s, h)) == (CELL *)NULL) {
if (prmflg) {
u = _install(s, UDF, "", 0.0, h);
goto rtn;
}
else if (typ & ARR) {
t = emalloc(sizeof(SYMBOL *) * HASHSIZE);
for (i = 0; i < HASHSIZE; i++)
((SYMBOL **) t)[i] = (SYMBOL *)NULL;
u = (CELL *) emalloc(sizeof(*u));
u->c_type = typ;
u->c_sval = t;
u->c_fval = 0.0;
p = (SYMBOL *) emalloc(sizeof(*p));
p->s_name = strsave(s);
p->s_val = u;
hval = hash(s);
p->s_next = h[hval];
h[hval] = p;
}
else
u = _install(s, typ, "", 0.0, h);
}
else if (!prmflg && (u->c_type == UDF) && (typ != UDF)) {
/* fix up local_var/forward_function */
if (typ == ARR) {
/*
printf("getvar_correct_to_array\n");
*/
u->c_type = typ;
sfree(u->c_sval);
u->c_sval = emalloc(sizeof(SYMBOL *) * HASHSIZE);
for (i = 0; i < HASHSIZE; i++)
((SYMBOL **) u->c_sval)[i] = (SYMBOL *)NULL;
u->c_fval = 0.0;
}
else if (typ != UDF) {
u->c_type = typ;
}
}
rtn:
return u;
}
fixarray(u) CELL *u;
{
int i;
if (u->c_type == UDF) { /* fix up local var */
/*
printf("fixarray\n");
*/
u->c_type = ARR;
sfree(u->c_sval);
u->c_sval = emalloc(sizeof(SYMBOL *) * HASHSIZE);
for (i = 0; i < HASHSIZE; i++)
((SYMBOL **) u->c_sval)[i] = (SYMBOL *)NULL;
u->c_fval = 0.0;
}
}
a_free(u) CELL *u;
{ /* free local array */
SYMBOL **h, *q, *r;
CELL *v;
int i;
if (!(u->c_type & ARR))
error("try to free non array variable", (char *)0);
h = (SYMBOL **) u->c_sval;
for (i = 0; i < HASHSIZE; i++)
for (q = h[i]; q; q = r) {
r = q->s_next;
sfree(q->s_name);
v = q->s_val; /* CELL */
c_free(v);
sfree(q); /* SYMBOL */
}
sfree(u->c_sval); /* symbol table */
c_free(u);
}
CELL *
Array(p) NODE *p;
{
CELL *u;
char str[BUFSIZ];
int i, n;
CELL *v;
u = (CELL *) p->n_arg[0];
if (u->c_type == POS) {
i = (int)u->c_fval;
/*
printf("**ARG_ARRAY(%d)*\n", i);
*/
u = _Arg(i);
if (u->c_type == UDF) { /* fix up local array */
/*
printf("local_var_to_array\n");
*/
fixarray(u);
}
}
else if (!(u->c_type & ARR))
error("non array refference");
arrayelm(p, str);
u = getvar(str, u->c_sval, VAR|NUM|STR); /* "rtsort in AWK book */
return u;
}
static
arrayelm(p, s) NODE *p; char *s;
{
CELL *u;
int i, n;
char *t;
/*
char *tt = s;
*/
n = (int) p->n_arg[1] + 2;
for (i = 2; i < n; i++) {
if (i > 2)
*s++ = **SUBSEP;
u = execute(p->n_arg[i]);
for (t = getsval(u); *t; )
*s++ = *t++;
c_free(u);
}
*s = '\0';
/*
printf("array_elm(%s)\n", tt);
*/
}
CELL *
Element(p) NODE *p;
{
char str[BUFSIZ];
arrayelm(p, str);
return mktmp(STR, str, 0.0);
}
CELL *
Delete(p) NODE *p;
{
CELL *u;
char str[BUFSIZ];
int i;
SYMBOL *q, *r, **h;
u = (CELL *) p->n_arg[0];
if (!(u->c_type & ARR))
error("can't delete non array variable");
arrayelm(p, str);
h = (SYMBOL **) u->c_sval;
for (r = (SYMBOL *)NULL, i = hash(str), q = h[i]; q; r = q, q = q->s_next)
if (strcmp(str, q->s_name) == 0)
break;
if (q) {
sfree(q->s_val->c_sval);
sfree(q->s_name);
if (r)
r->s_next = q->s_next;
if (q == h[i])
h[i] = (SYMBOL *)NULL;
}
return &truecell;
}
CELL *
In(p) NODE *p;
{
SYMBOL **h, *q;
CELL *u, *v;
char *s;
int i;
u = (CELL *) p->n_arg[1]; /* array */
if (!(u->c_type & ARR))
error("%s is not an array", u->c_sval);
h = (SYMBOL **) u->c_sval;
if (u->c_sval != (char *)NULL) {
v = execute(p->n_arg[0]); /* var */
s = getsval(v);
for (i = 0; i < HASHSIZE; i++)
for (q = h[i]; q; q = q->s_next) {
if (strcmp(s, q->s_name) == 0) {
c_free(v);
return &truecell;
}
}
c_free(v);
}
return &falsecell;
}
CELL *
Split(p) NODE *p;
{
CELL *u, *v, *w;
char *s, *t, *h, *name, *sep;
int i, n, skip;
char elm[8], str[BUFSIZ];
static char *s_str;
static regexp *s_pat;
regexp *mkpat();
extern int r_start, r_length;
n = (int) p->n_arg[1];
if (n > 1) {
u = execute(p->n_arg[2]);
s = getsval(u); /* str */
v = execute(p->n_arg[3]); /* array */
if (!(v->c_type & ARR)) {
/*
printf("Split fix_to_array(%d)\n", v->c_type);
*/
if (v->c_type == UDF) /* fix up local array */
fixarray(v);
else
error("split to non array variable", (char *)0);
}
h = v->c_sval;
c_free(v);
if (n > 2) {
v = execute(p->n_arg[4]);
sep = getsval(v);
}
else {
v = (CELL *)NULL;
sep = *FS;
}
if (strlen(sep) > 1) { /* reg_exp */
if (strcmp(sep, s_str) != 0) {
sfree(s_str); sfree(s_pat);
s_str = strsave(sep);
s_pat = mkpat(s_str);
}
for (i = 0, t = str; *s; ) {
if (match(s_pat, s)) {
for (n = r_start; --n > 0; )
*t++ = *s++;
}
else {
while(*s)
*t++ = *s++;
}
*t = '\0';
t = str;
sprintf(elm, "%d", ++i);
w = getvar(elm, h, VAR);
if (isnum(str))
setfval(w, atof(str));
else
setsval(w, str);
if (*s)
s += r_length;
}
}
else {
skip = *sep == ' ';
for (i = 0; t = str, *s; ) {
if (skip)
while (jStrchr(" \t\n", *s))
s++;
if (!(*s))
break;
while (*s && !jStrchr(sep, *s)) {
if (isKanji(*s))
*t++ = *s++;
*t++ = *s++;
}
*t = '\0';
sprintf(elm, "%d", ++i);
w = getvar(elm, h, VAR);
if (isnum(str))
setfval(w, atof(str));
else
setsval(w, str);
if (*s && !skip)
s++;
}
}
c_free(v); /* sep */
c_free(u); /* str may be CATed */
}
else
i = 0;
return mktmp(NUM, (char *)NULL, (double) i);
}
CELL *
Forin(p) NODE *p;
{
CELL *u, *v;
SYMBOL **h, *q;
char *name;
int i;
u = execute(p->n_arg[1]);
if (!(u->c_type & ARR))
synerr(
"non array variable is specified in 'for (. in var)'", (char *)0);
h = (SYMBOL **) u->c_sval;
c_free(u);
u = execute(p->n_arg[0]);
if (u->c_type == UDF) {
/*
printf("Forin_fix_to_VAR|NUM\n");
*/
u->c_type = VAR|NUM;
}
if (!(u->c_type & VAR))
error("'for (VAR in .)' is not variable (%d)", name, u->c_type);
for (i = 0; i < HASHSIZE; i++) {
for (q = h[i]; q; q = q->s_next) {
setsval(u, q->s_name);
v = execute(p->n_arg[2]);
c_free(v);
}
}
c_free(u);
return &truecell;
}
char *
strsave(s) char *s;
{
register int n;
char *emalloc(), *strcpy();
if (s == (char *)NULL)
return (char *)NULL;
n = strlen(s) + 1;
return strcpy(emalloc(n), s);
}
sfree(p) char *p;
{
if (p != (char *)NULL)
Free(p);
}
isnum(s) char *s;
{
char *strchr();
if (s == NULL || *s == '\0' || !strcmp(s, "."))
return 0;
if (*s && strchr("+-", *s) != (char *)NULL)
s++;
if (*s == '\0')
return 0;
while (isdigit(*s))
s++;
if (*s == '.') {
s++;
while (isdigit(*s))
s++;
}
if (*s && strchr("eE", *s) != (char *)NULL) {
s++;
if (*s == '\0')
return 0;
if (*s && strchr("+-", *s) != (char *)NULL)
s++;
while (isdigit(*s))
s++;
}
return *s == '\0';
}
setfval(u, f) CELL *u; double f;
{
if (u->c_type == UDF) { /* fix up local var */
/*
printf("setfval_fix_to_VAR\n");
*/
u->c_type |= VAR;
}
if (u->c_type & (VAR|FLD|REC|TMP)) {
u->c_type &= ~STR;
u->c_type |= NUM;
sfree(u->c_sval);
u->c_sval = (char *)NULL;
u->c_fval = f;
if (u->c_type & FLD)
mkrec(u);
}
else
fprintf(stderr, "assign to nonvariable (%d)\n", u->c_type);
}
setsval(u, s) CELL *u; char *s;
{
double atof();
if (u->c_type == UDF) { /* fix up local var */
/*
printf("setsval_fix_to_VAR\n");
*/
u->c_type |= VAR;
}
if (u->c_type & (VAR|FLD|REC|TMP)) {
u->c_type &= ~NUM;
u->c_type |= STR;
sfree(u->c_sval);
u->c_sval = strsave(s);
#if 0 /* "table2" in AWK book */
if (isnum(u->c_sval)) {
u->c_fval = atof(u->c_sval);
u->c_type |= NUM;
}
else
#endif
u->c_fval = 0.0;
if (u->c_type & FLD)
mkrec(u);
}
else
fprintf(stderr, "assign to constant (%d)\n", u->c_type);
}
double
getfval(u) CELL *u;
{
double x, atof();
if (u->c_type == UDF) { /* local var */
u->c_type |= VAR|STR|NUM;
u->c_sval = strsave("");
x = u->c_fval = 0.0;
}
else if (u->c_type & NUM)
x = u->c_fval;
#if 1
else {
x = atof(u->c_sval);
#else
else {
if (isnum(u->c_sval))
x = atof(u->c_sval);
else
x = 0.0;
#endif
}
return x;
}
char *
getsval(u) CELL *u;
{
char *s, str[80];
if (u->c_type & STR)
s = u->c_sval;
else if (u->c_type & NUM) {
/* if (u->c_fval >= -2147483648.0 && u->c_fval <= 2147483647.0)*/
if ((long)u->c_fval == u->c_fval)
s = "%.16g";
else
s = *OFMT;
sprintf(str, s, u->c_fval);
sfree(u->c_sval);
s = u->c_sval = strsave(str);
}
#if 1
else if (u->c_type == UDF) { /* local var */
/*
printf("getsval_fix_to_VAR|STR\n");
*/
u->c_type |= VAR|STR|NUM;
s = u->c_sval = strsave("");
u->c_fval = 0.0;
}
#endif
else
fprintf(stderr, "abnormal value (STR|NUM == 0)(%d)\n", u->c_type);
return s;
}
char *
emalloc(n) unsigned n;
{
char *p;
#if 0
char far *_fmalloc();
#else
char *malloc();
#endif
#if 0
if ((p = _fmalloc(n)) == (char *)NULL)
#else
if ((p = malloc(n)) == (char *)NULL)
#endif
error("memory over");
return p;
}
Free(s) char *s;
{
#if DOS
void _ffree();
_ffree(s);
#else
free(s);
#endif
}

1086
commands/awk/y.c Normal file

File diff suppressed because it is too large Load Diff

View File

@@ -1,6 +0,0 @@
PROG= backup
MAN=
LINKS+= ${BINDIR}/backup ${BINDIR}/restore
.include <minix.prog.mk>

View File

@@ -1,5 +0,0 @@
PROG= badblocks
CPPFLAGS+= -I${MINIXSRCDIR}/servers
MAN=
.include <minix.prog.mk>

View File

@@ -1,4 +0,0 @@
PROG= banner
MAN=
.include <minix.prog.mk>

View File

@@ -1,4 +0,0 @@
PROG= basename
MAN=
.include <minix.prog.mk>

View File

@@ -1,4 +0,0 @@
SCRIPTS= bigmake.sh
MAN=
.include <minix.prog.mk>

View File

@@ -1,4 +0,0 @@
SCRIPTS= binpackage.sh
MAN=
.include <minix.prog.mk>

View File

@@ -1,4 +0,0 @@
SCRIPTS= binpackages.sh
MAN=
.include <minix.prog.mk>

View File

@@ -1,4 +0,0 @@
SCRIPTS= binsizes.sh
MAN=
.include <minix.prog.mk>

33
commands/byacc/MANIFEST Normal file
View File

@@ -0,0 +1,33 @@
File Name Archive # Description
-----------------------------------------------------------
ACKNOWLEDGEMENTS 1
CSU.diffs 1
MANIFEST 1 This shipping list
Makefile 1
NEW_FEATURES 1
NOTES 1
NO_WARRANTY 1
README 1
closure.c 1
defs.h 1
error.c 1
lalr.c 1
lr0.c 1
main.c 1
mkpar.c 1
output.c 2
reader.c 3
skeleton.c 1
symtab.c 1
test 1
test/error.output 1
test/error.tab.c 1
test/error.tab.h 1
test/error.y 1
test/ftp.output 2
test/ftp.tab.c 3
test/ftp.tab.h 1
test/ftp.y 2
verbose.c 1
warshall.c 1
yacc.1 1

86
commands/byacc/Makefile Normal file
View File

@@ -0,0 +1,86 @@
# Makefile for Berkeley yacc.
BINDIR = /usr/bin
HDRS = defs.h
CFLAGS = -DNDEBUG -D_MINIX -D_POSIX_SOURCE -wo $(OPT)
LDFLAGS = -i
LIBS =
CC = exec cc
LINKER = $(CC)
MAKEFILE = Makefile
OBJS = closure.o \
error.o \
lalr.o \
lr0.o \
main.o \
mkpar.o \
output.o \
reader.o \
skeleton.o \
symtab.o \
verbose.o \
warshall.o
PRINT = pr -f -l88
PROGRAM = yacc
SRCS = closure.c \
error.c \
lalr.c \
lr0.c \
main.c \
mkpar.c \
output.c \
reader.c \
skeleton.c \
symtab.c \
verbose.c \
warshall.c
all: $(PROGRAM)
$(PROGRAM): $(OBJS) $(LIBS)
$(LINKER) $(LDFLAGS) -o $(PROGRAM) $(OBJS) $(LIBS)
install -S 484k $(PROGRAM)
install: $(BINDIR)/yacc
$(BINDIR)/yacc: $(PROGRAM)
install -cs -o bin $(PROGRAM) $@
clean:; rm -f $(OBJS) $(PROGRAM) core
#depend:; @mkmf -f $(MAKEFILE) PROGRAM=$(PROGRAM) DEST=$(DEST)
#
#index:; @ctags -wx $(HDRS) $(SRCS)
#
#listing:; @$(PRINT) Makefile $(HDRS) $(SRCS) | lpr
#
#lint:; @lint $(SRCS)
#
#program: $(PROGRAM)
#
#tags: $(HDRS) $(SRCS); @ctags $(HDRS) $(SRCS)
###
closure.o: defs.h
error.o: defs.h
lalr.o: defs.h
lr0.o: defs.h
main.o: defs.h
mkpar.o: defs.h
output.o: defs.h
reader.o: defs.h
skeleton.o: defs.h
symtab.o: defs.h
verbose.o: defs.h
warshall.o: defs.h

9
commands/byacc/NOTES Normal file
View File

@@ -0,0 +1,9 @@
Berkeley Yacc reflects its origins. The reason so many routines
use exactly six register variables is that Berkeley Yacc was
developed on a VAX using PCC. PCC placed at most six variables
in registers. I went to considerable effort to find which six
variables most belonged in registers. Changes in machines and
compilers make that effort worthless, perhaps even harmful.
The code contains many instances where address calculations are
performed in particular ways to optimize the code for the VAX.

View File

@@ -0,0 +1,3 @@
Berkeley Yacc is distributed with no warranty whatever. The author
and any other contributors take no responsibility for the consequences of
its use.

3
commands/byacc/build Executable file
View File

@@ -0,0 +1,3 @@
#!/bin/sh
make clean
make && make install

View File

@@ -1,46 +1,3 @@
/* $NetBSD: closure.c,v 1.8 2006/05/24 18:01:43 christos Exp $ */
/*
* Copyright (c) 1989 The Regents of the University of California.
* All rights reserved.
*
* This code is derived from software contributed to Berkeley by
* Robert Paul Corbett.
*
* Redistribution and use in source and binary forms, with or without
* modification, are permitted provided that the following conditions
* are met:
* 1. Redistributions of source code must retain the above copyright
* notice, this list of conditions and the following disclaimer.
* 2. Redistributions in binary form must reproduce the above copyright
* notice, this list of conditions and the following disclaimer in the
* documentation and/or other materials provided with the distribution.
* 3. Neither the name of the University nor the names of its contributors
* may be used to endorse or promote products derived from this software
* without specific prior written permission.
*
* THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND
* ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
* IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
* ARE DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE
* FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
* DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
* OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
* HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
* LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
* OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
* SUCH DAMAGE.
*/
#include <sys/cdefs.h>
#if defined(__RCSID) && !defined(lint)
#if 0
static char sccsid[] = "@(#)closure.c 5.3 (Berkeley) 5/24/93";
#else
__RCSID("$NetBSD: closure.c,v 1.8 2006/05/24 18:01:43 christos Exp $");
#endif
#endif /* not lint */
#include "defs.h"
short *itemset;
@@ -50,17 +7,15 @@ unsigned *ruleset;
static unsigned *first_derives;
static unsigned *EFF;
static void set_EFF(void);
static void
set_EFF(void)
set_EFF()
{
unsigned *row;
int symbol;
short *sp;
int rowsize;
int i;
int rule;
register unsigned *row;
register int symbol;
register short *sp;
register int rowsize;
register int i;
register int rule;
rowsize = WORDSIZE(nvars);
EFF = NEW2(nvars * rowsize, unsigned);
@@ -89,23 +44,20 @@ set_EFF(void)
}
void
set_first_derives(void)
set_first_derives()
{
unsigned *rrow;
unsigned *vrow;
int j;
unsigned k;
unsigned cword;
short *rp;
register unsigned *rrow;
register unsigned *vrow;
register int j;
register unsigned k;
register unsigned cword;
register short *rp;
int rule;
int i;
int rulesetsize;
int varsetsize;
cword = 0;
rulesetsize = WORDSIZE(nrules);
varsetsize = WORDSIZE(nvars);
first_derives = NEW2(nvars * rulesetsize, unsigned) - ntokens * rulesetsize;
@@ -147,16 +99,17 @@ set_first_derives(void)
}
void
closure(short *nucleus, int n)
closure(nucleus, n)
short *nucleus;
int n;
{
int ruleno;
unsigned word;
unsigned i;
short *csp;
unsigned *dsp;
unsigned *rsp;
int rulesetsize;
register int ruleno;
register unsigned word;
register unsigned i;
register short *csp;
register unsigned *dsp;
register unsigned *rsp;
register int rulesetsize;
short *csend;
unsigned *rsend;
@@ -215,8 +168,8 @@ closure(short *nucleus, int n)
}
void
finalize_closure(void)
finalize_closure()
{
FREE(itemset);
FREE(ruleset);
@@ -226,10 +179,10 @@ finalize_closure(void)
#ifdef DEBUG
void
print_closure(int n)
print_closure(n)
int n;
{
short *isp;
register short *isp;
printf("\n\nn = %d\n\n", n);
for (isp = itemset; isp < itemsetend; isp++)
@@ -237,13 +190,12 @@ print_closure(int n)
}
void
print_EFF(void)
print_EFF()
{
int i, j;
unsigned *rowp;
unsigned word;
unsigned k;
register int i, j;
register unsigned *rowp;
register unsigned word;
register unsigned k;
printf("\n\nEpsilon Free Firsts\n");
@@ -269,14 +221,13 @@ print_EFF(void)
}
void
print_first_derives(void)
print_first_derives()
{
int i;
int j;
unsigned *rp;
unsigned cword;
unsigned k;
register int i;
register int j;
register unsigned *rp;
register unsigned cword;
register unsigned k;
printf("\n\n\nFirst Derives\n");

View File

@@ -1,48 +1,6 @@
/* $NetBSD: defs.h,v 1.17 2009/04/14 09:41:30 lukem Exp $ */
/*
* Copyright (c) 1989 The Regents of the University of California.
* All rights reserved.
*
* This code is derived from software contributed to Berkeley by
* Robert Paul Corbett.
*
* Redistribution and use in source and binary forms, with or without
* modification, are permitted provided that the following conditions
* are met:
* 1. Redistributions of source code must retain the above copyright
* notice, this list of conditions and the following disclaimer.
* 2. Redistributions in binary form must reproduce the above copyright
* notice, this list of conditions and the following disclaimer in the
* documentation and/or other materials provided with the distribution.
* 3. Neither the name of the University nor the names of its contributors
* may be used to endorse or promote products derived from this software
* without specific prior written permission.
*
* THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND
* ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
* IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
* ARE DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE
* FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
* DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
* OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
* HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
* LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
* OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
* SUCH DAMAGE.
*
* @(#)defs.h 5.6 (Berkeley) 5/24/93
*/
#if HAVE_NBTOOL_CONFIG_H
#include "nbtool_config.h"
#endif
#include <assert.h>
#include <ctype.h>
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
/* machine-dependent definitions */
@@ -60,14 +18,23 @@
/* from r (0-indexed) */
/* SETBIT sets the n-th bit starting from r */
#if !__STDC__
#define MAXCHAR 255
#define MAXSHORT 32767
#define MINSHORT -32768
#define MAXTABLE 32500
#define BITS_PER_WORD 32
#define WORDSIZE(n) (((n)+(BITS_PER_WORD-1)/BITS_PER_WORD))
#define BIT(r, n) ((((r)[(n)>>5])>>((n)&31)&1))
#define SETBIT(r, n) ((r)[(n)>>5]|=((unsigned)1<<((n)&31)))
#else
#include <limits.h>
#define MAXCHAR UCHAR_MAX
#define MAXSHORT SHRT_MAX
#define MINSHORT SHRT_MIN
#define BITS_PER_WORD (INT_MAX == 32767 ? 16 : 32)
#define BITS_PER_BPW (INT_MAX == 32767 ? 4 : 5)
#endif
#define MAXTABLE 32500
#define WORDSIZE(n) (((n)+(BITS_PER_WORD-1))/BITS_PER_WORD)
#define BIT(r, n) ((((r)[(n)>>BITS_PER_BPW])>>((n)&(BITS_PER_WORD-1)))&1)
#define SETBIT(r, n) ((r)[(n)>>BITS_PER_BPW]|=((unsigned)1<<((n)&(BITS_PER_WORD-1))))
/* character names */
@@ -105,7 +72,6 @@
#define START 7
#define UNION 8
#define IDENT 9
#define EXPECT 10
/* symbol classes */
@@ -226,24 +192,24 @@ extern char lflag;
extern char rflag;
extern char tflag;
extern char vflag;
extern const char *symbol_prefix;
extern char *symbol_prefix;
extern const char *myname;
extern char *myname;
extern char *cptr;
extern char *line;
extern int lineno;
extern int outline;
extern const char * const banner[];
extern const char * const tables[];
extern const char * const header[];
extern const char * const body[];
extern const char * const trailer[];
extern char *banner[];
extern char *tables[];
extern char *header[];
extern char *body[];
extern char *trailer[];
extern char *action_file_name;
extern char *code_file_name;
extern char *defines_file_name;
extern const char *input_file_name;
extern char *input_file_name;
extern char *output_file_name;
extern char *text_file_name;
extern char *union_file_name;
@@ -266,6 +232,7 @@ extern int nvars;
extern int ntags;
extern char unionized;
extern char line_format[];
extern int start_symbol;
extern char **symbol_name;
@@ -312,61 +279,20 @@ extern short final_state;
/* global functions */
extern char *allocate(unsigned);
extern bucket *lookup(char *);
extern bucket *make_bucket(const char *);
extern char *allocate();
extern bucket *lookup();
extern bucket *make_bucket();
extern void set_first_derives(void);
extern void closure(short *, int);
extern void finalize_closure(void);
extern __dead void fatal(const char *);
/* system variables */
extern void reflexive_transitive_closure(unsigned *, int);
extern __dead void done(int);
extern int errno;
extern __dead void no_space(void);
extern __dead void open_error(const char *);
extern __dead void unexpected_EOF(void);
extern void print_pos(char *, char *);
extern __dead void syntax_error(int, char *, char *);
extern __dead void unterminated_comment(int, char *, char *);
extern __dead void unterminated_string(int, char *, char *);
extern __dead void unterminated_text(int, char *, char *);
extern __dead void unterminated_union(int, char *, char *);
extern __dead void over_unionized(char *);
extern void illegal_tag(int, char *, char *);
extern void illegal_character(char *);
extern void used_reserved(char *);
extern void tokenized_start(char *);
extern void retyped_warning(char *);
extern void reprec_warning(char *);
extern void revalued_warning(char *);
extern __dead void terminal_start(char *);
extern void restarted_warning(void);
extern __dead void no_grammar(void);
extern __dead void terminal_lhs(int);
extern void prec_redeclared(void);
extern __dead void unterminated_action(int, char *, char *);
extern void dollar_warning(int, int);
extern __dead void dollar_error(int, char *, char *);
extern __dead void untyped_lhs(void);
extern __dead void untyped_rhs(int, char *);
extern __dead void unknown_rhs(int);
extern void default_action_warning(void);
extern __dead void undefined_goal(char *);
extern void undefined_symbol_warning(char *);
extern void lalr(void);
/* system functions */
extern void reader(void);
extern void lr0(void);
extern void make_parser(void);
extern void verbose(void);
extern void output(void);
extern void free_parser(void);
extern void write_section(const char * const []);
extern void create_symbol_table(void);
extern void free_symbol_table(void);
extern void free_symbols(void);
extern void free();
extern char *calloc();
extern char *malloc();
extern char *realloc();
extern char *strcpy();

Some files were not shown because too many files have changed in this diff Show More