cirno/plan9port
1
0
Fork 0
mirror of https://github.com/9fans/plan9port.git synced 2025-01-12 11:10:07 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

awk: import from sources

Browse source
This commit is contained in:
Jeff Sickel 2008-11-03 12:35:56 -06:00
parent d210f09d22
commit 63a686861c
14 changed files with 14513 additions and 0 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

13
src/cmd/awk/README Normal file
View file

@ -0,0 +1,13 @@
This 'awk' source is directly downloaded from the Plan 9 source
http://cm.bell-labs.com/sources/plan9/sys/src/cmd/awk/
as such, it's copyright is held by Lucent Technologies and distributed under the
Lucent Public License version 1.02 [http://www.opensource.org/licenses/lucent1.02.php].
Modifications were made by Jeff Sickel in order to build using Plan 9 from User
Space [http://swtch.com/plan9port/] to the following files:
mkfile
re.c

185
src/cmd/awk/awk.h Normal file
View file

@ -0,0 +1,185 @@
/*
Copyright (c) Lucent Technologies 1997
All Rights Reserved
*/
typedef double Awkfloat;
/* unsigned char is more trouble than it's worth */
typedef unsigned char uschar;
#define xfree(a) { if ((a) != NULL) { free((char *) a); a = NULL; } }
#define DEBUG
#ifdef DEBUG
/* uses have to be doubly parenthesized */
# define dprintf(x) if (dbg) printf x
#else
# define dprintf(x)
#endif
extern char errbuf[];
extern int compile_time; /* 1 if compiling, 0 if running */
extern int safe; /* 0 => unsafe, 1 => safe */
#define RECSIZE (8 * 1024) /* sets limit on records, fields, etc., etc. */
extern int recsize; /* size of current record, orig RECSIZE */
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;
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 */
extern int dbg;
extern char *patbeg; /* beginning of pattern matched */
extern int patlen; /* length of pattern matched. set in b.c */
/* Cell: all information about a variable or constant */
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;
typedef struct Array { /* symbol table array */
int nelem; /* elements in table right now */
int size; /* size of tab */
Cell **tab; /* hash table pointers */
} Array;
#define NSYMTAB 50 /* initial size of a symbol table */
extern Array *symtab;
extern Cell *nrloc; /* NR */
extern Cell *fnrloc; /* FNR */
extern Cell *nfloc; /* NF */
extern Cell *rstartloc; /* RSTART */
extern Cell *rlengthloc; /* RLENGTH */
/* 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 */
/* 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
#define FUTF 15
/* 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)
#define isnextfile(n) ((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 )
#include "proto.h"

489
src/cmd/awk/awkgram.y Normal file
View file

@ -0,0 +1,489 @@
/****************************************************************
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"
#define makedfa(a,b) compre(a)
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
%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); }
| CLOSE pattern st { $$ = stat1(CLOSE, $2); }
| CONTINUE st { if (!inloop) SYNTAX("continue illegal outside of loops");
$$ = 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); }
| 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;
}
}
}

570
src/cmd/awk/lex.c Normal file
View file

@ -0,0 +1,570 @@
/****************************************************************
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 "y.tab.h"
extern YYSTYPE yylval;
extern int infunc;
int lineno = 1;
int bracecnt = 0;
int brackcnt = 0;
int parencnt = 0;
typedef struct Keyword {
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 },
{ "utf", FUTF, BLTIN },
{ "while", WHILE, WHILE },
};
#define DEBUG
#ifdef DEBUG
#define RET(x) { if(dbg)printf("lex %s\n", tokname(x)); return(x); }
#else
#define RET(x) return(x)
#endif
int peek(void)
{
int c = input();
unput(c);
return c;
}
int gettok(char **pbuf, int *psz) /* get next input token */
{
int c;
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, 0))
FATAL( "out of space for name %.10s...", buf );
if (isalnum(c) || c == '_')
*bp++ = c;
else {
*bp = 0;
unput(c);
break;
}
}
} else { /* it's a number */
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, 0))
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 */
unputstr(rem); /* put rest back for later */
rem[0] = 0;
}
*pbuf = buf;
*psz = sz;
return buf[0];
}
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 = 500;
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) || 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 (c == '(' || c == '[' || (infunc && isarg(buf) >= 0)) {
unputstr(buf);
RET(INDIRECT);
} else if (isalpha(c)) {
if (strcmp(buf, "NF") == 0) { /* very special */
unputstr("(NF)");
RET(INDIRECT);
}
yylval.cp = setsymtab(buf, "", 0.0, STR|NUM, symtab);
RET(IVAR);
} 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, 0))
FATAL("out of space for string %.10s...", buf);
switch (c) {
case '\n':
case '\r':
case 0:
SYNTAX( "non-terminated string %.10s...", buf );
lineno++;
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(char *w, 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]));
kp = keywords + n;
if (n != -1) { /* found in table */
yylval.i = kp->sub;
switch (kp->type) { /* special handling */
case FSYSTEM:
if (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 yyles 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, 0))
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;
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 = *--yysptr;
else if (lexprog != NULL) { /* awk '...' */
if ((c = *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(char *s) /* put a string back on input */
{
int i;
for (i = strlen(s)-1; i >= 0; i--)
unput(s[i]);
}

713
src/cmd/awk/lib.c Normal file
View file

@ -0,0 +1,713 @@
/****************************************************************
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 "y.tab.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 200
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)
{
record = (char *) malloc(n);
fields = (char *) malloc(n);
fldtab = (Cell **) malloc((nfields+1) * sizeof(Cell *));
if (record == NULL || fields == NULL || fldtab == NULL)
FATAL("out of space for $0 and fields");
fldtab[0] = (Cell *) malloc(sizeof (Cell));
*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 */
}
int getrec(char **pbuf, int *pbufsize, int isrecord) /* get next input record */
{ /* note: cares whether buf == record */
int c;
static int firsttime = 1;
char *buf = *pbuf;
int bufsize = *pbufsize;
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;
}
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++;
}
*pbuf = buf;
*pbufsize = bufsize;
return 0; /* true end of file */
}
void nextfile(void)
{
if (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 */
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 */
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 != '\n' && *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 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;
if (n > nf)
nf = n;
fldtab = (Cell **) realloc(fldtab, (nf+1) * (sizeof (struct Cell *)));
if (fldtab == NULL)
FATAL("out of space creating %d fields", nf);
makefields(nfields+1, nf);
nfields = nf;
}
int refldbld(char *rec, 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;
void *p;
int i, n;
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;
p = compre(fs);
dprintf( ("into refldbld, rec = <%s>, pat = <%s>\n", rec, fs) );
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(p, rec, rec)) {
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);
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(char *s)
{
SYNTAX(s);
}
void SYNTAX(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);
if(compile_time == 1 && cursource() != NULL)
fprintf(stderr, " at %s:%d", cursource(), lineno);
else
fprintf(stderr, " at line %d", lineno);
if (curfname != NULL)
fprintf(stderr, " in function %s", curfname);
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(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(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;
int line;
fprintf(stderr, "\n");
if (compile_time != 2 && NR && *NR > 0) {
if (strcmp(*FILENAME, "-") != 0)
fprintf(stderr, " input record %s:%d", *FILENAME, (int) (*FNR));
else
fprintf(stderr, " input record number %d", (int) (*FNR));
fprintf(stderr, "\n");
}
if (compile_time != 2 && curnode)
line = curnode->lineno;
else if (compile_time != 2 && lineno)
line = lineno;
else
line = -1;
if (compile_time == 1 && cursource() != NULL){
if(line >= 0)
fprintf(stderr, " source %s:%d", cursource(), line);
else
fprintf(stderr, " source file %s", cursource());
}else if(line >= 0)
fprintf(stderr, " source line %d", line);
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, 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(char *s) /* is s of form var=something ? */
{
char *os = s;
if (!isalpha(*s) && *s != '_')
return 0;
for ( ; *s; s++)
if (!(isalnum(*s) || *s == '_'))
break;
return *s == '=' && s > os && *(s+1) != '=';
}
/* strtod is supposed to be a proper test of what's a valid number */
#include <math.h>
int is_number(char *s)
{
double r;
char *ep;
/*
* fast could-it-be-a-number check before calling strtod,
* which takes a surprisingly long time to reject non-numbers.
*/
switch (*s) {
case '0': case '1': case '2': case '3': case '4':
case '5': case '6': case '7': case '8': case '9':
case '\t':
case '\n':
case '\v':
case '\f':
case '\r':
case ' ':
case '-':
case '+':
case '.':
case 'n': /* nans */
case 'N':
case 'i': /* infs */
case 'I':
break;
default:
return 0; /* can't be a number */
}
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;
}

198
src/cmd/awk/main.c Normal file
View file

@ -0,0 +1,198 @@
/****************************************************************
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.
****************************************************************/
char *version = "version 19990602";
#define DEBUG
#include <stdio.h>
#include <ctype.h>
#include <stdlib.h>
#include <string.h>
#include <signal.h>
#include "awk.h"
#include "y.tab.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 */
char *pfile[20]; /* 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[])
{
char *fs = NULL, *marg;
int temp;
cmdname = argv[0];
if (argc == 1) {
fprintf(stderr, "Usage: %s [-F fieldsep] [-mf n] [-mr n] [-v var=value] [-f programfile | 'program'] [file ...]\n", cmdname);
exit(1);
}
signal(SIGFPE, fpecatch);
yyin = NULL;
symtab = makesymtab(NSYMTAB);
while (argc > 1 && argv[1][0] == '-' && argv[1][1] != '\0') {
if (strcmp(argv[1], "--") == 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");
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 'm': /* more memory: -mr=record, -mf=fields */
/* no longer needed */
marg = argv[1];
if (argv[1][3])
temp = atoi(&argv[1][3]);
else {
argv++; argc--;
temp = atoi(&argv[1][0]);
}
switch (marg[2]) {
case 'r': recsize = temp; break;
case 'f': nfields = temp; break;
default: FATAL("unknown option %s\n", marg);
}
break;
case 'd':
dbg = atoi(&argv[1][2]);
if (dbg == 0)
dbg = 1;
printf("awk %s\n", version);
break;
case 'V': /* added for exptools "standard" */
printf("awk %s\n", version);
exit(0);
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();
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;
}

169
src/cmd/awk/maketab.c Normal file
View file

@ -0,0 +1,169 @@
/****************************************************************
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 y.tab.h, produced by yacc.
*/
#include <stdio.h>
#include <string.h>
#include <stdlib.h>
#include "awk.h"
#include "y.tab.h"
struct xx
{ int token;
char *name;
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, "getline", "getline" },
{ 0, "", "" },
};
#define SIZE (LASTTOKEN - FIRSTTOKEN + 1)
char *table[SIZE];
char *names[SIZE];
int main(int argc, char *argv[])
{
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 \"y.tab.h\"\n\n");
for (i = SIZE; --i >= 0; )
names[i] = "";
if ((fp = fopen("y.tab.h", "r")) == NULL) {
fprintf(stderr, "maketab can't open y.tab.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\n", tok, buf);
exit(1);
}
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;
}

35
src/cmd/awk/mkfile Normal file
View file

@ -0,0 +1,35 @@
<$PLAN9/src/mkhdr
TARG=awk
OFILES=re.$O\
lex.$O\
main.$O\
parse.$O\
proctab.$O\
tran.$O\
lib.$O\
run.$O\
y.tab.$O\
HFILES=awk.h\
y.tab.h\
proto.h\
YFILES=awkgram.y
CLEANFILES=$CLEANFILES proctab.c $O.maketab
<$PLAN9/src/mkone
# CFLAGS=-c -D_REGEXP_EXTENSION -D_RESEARCH_SOURCE -D_BSD_EXTENSION -DUTF
YFLAGS=-S -d -v
proctab.c: $O.maketab
./$O.maketab >proctab.c
maketab.$O: maketab.c
$CC $CFLAGS maketab.c
$O.maketab:V: y.tab.h maketab.$O
$LD -o $O.maketab maketab.$O

272
src/cmd/awk/parse.c Normal file
View file

@ -0,0 +1,272 @@
/****************************************************************
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 "y.tab.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;
}
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(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;
}

178
src/cmd/awk/proto.h Normal file
View file

@ -0,0 +1,178 @@
/****************************************************************
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(char *);
extern int yylook(void);
extern int yyback(int *, int);
extern int yyinput(void);
extern void *compre(char *);
extern int hexstr(char **);
extern void quoted(char **, char **, char *);
extern int match(void *, char *, char *);
extern int pmatch(void *, char *, char *);
extern int nematch(void *, char *, char *);
extern int countposn(char *, int);
extern void overflow(void);
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(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(Cell *);
extern void freeelem(Cell *, char *);
extern Cell *setsymtab(char *, char *, double, unsigned int, Array *);
extern int hash(char *, int);
extern void rehash(Array *);
extern Cell *lookup(char *, Array *);
extern double setfval(Cell *, double);
extern void funnyvar(Cell *, char *);
extern char *setsval(Cell *, char *);
extern double getfval(Cell *);
extern char *getsval(Cell *);
extern char *tostring(char *);
extern char *qstring(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(char *, char *);
extern void recbld(void);
extern Cell *fieldadr(int);
extern void yyerror(char *);
extern void fpecatch(int);
extern void bracecheck(void);
extern void bcheck2(int, int, int);
extern void SYNTAX(char *, ...);
extern void FATAL(char *, ...);
extern void WARNING(char *, ...);
extern void error(void);
extern void eprint(void);
extern void bclass(int);
extern double errcheck(double, char *);
extern int isclvar(char *);
extern int is_number(char *);
extern int adjbuf(char **pb, int *sz, int min, int q, char **pbp, 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 *getline(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 *, 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, char *);
extern 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 *);

325
src/cmd/awk/re.c Normal file
View file

@ -0,0 +1,325 @@
/****************************************************************
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 <u.h>
#include <libc.h>
#include <ctype.h>
#include <bio.h>
#include <regexp.h>
#include "awk.h"
#include "y.tab.h"
/* This file provides the interface between the main body of
* awk and the pattern matching package. It preprocesses
* patterns prior to compilation to provide awk-like semantics
* to character sequences not supported by the pattern package.
* The following conversions are performed:
*
* "()" -> "[]"
* "[-" -> "[\-"
* "[^-" -> "[^\-"
* "-]" -> "\-]"
* "[]" -> "[]*"
* "\xdddd" -> "\z" where 'z' is the UTF sequence
* for the hex value
* "\ddd" -> "\o" where 'o' is a char octal value
* "\b" -> "\B" where 'B' is backspace
* "\t" -> "\T" where 'T' is tab
* "\f" -> "\F" where 'F' is form feed
* "\n" -> "\N" where 'N' is newline
* "\r" -> "\r" where 'C' is cr
*/
#define MAXRE 512
static char re[MAXRE]; /* copy buffer */
char *patbeg;
int patlen; /* number of chars in pattern */
#define NPATS 20 /* number of slots in pattern cache */
static struct pat_list /* dynamic pattern cache */
{
char *re;
int use;
Reprog *program;
} pattern[NPATS];
static int npats; /* cache fill level */
/* Compile a pattern */
void
*compre(char *pat)
{
int i, j, inclass;
char c, *p, *s;
Reprog *program;
if (!compile_time) { /* search cache for dynamic pattern */
for (i = 0; i < npats; i++)
if (!strcmp(pat, pattern[i].re)) {
pattern[i].use++;
return((void *) pattern[i].program);
}
}
/* Preprocess Pattern for compilation */
p = re;
s = pat;
inclass = 0;
while (c = *s++) {
if (c == '\\') {
quoted(&s, &p, re+MAXRE);
continue;
}
else if (!inclass && c == '(' && *s == ')') {
if (p < re+MAXRE-2) { /* '()' -> '[]*' */
*p++ = '[';
*p++ = ']';
c = '*';
s++;
}
else overflow();
}
else if (c == '['){ /* '[-' -> '[\-' */
inclass = 1;
if (*s == '-') {
if (p < re+MAXRE-2) {
*p++ = '[';
*p++ = '\\';
c = *s++;
}
else overflow();
} /* '[^-' -> '[^\-'*/
else if (*s == '^' && s[1] == '-'){
if (p < re+MAXRE-3) {
*p++ = '[';
*p++ = *s++;
*p++ = '\\';
c = *s++;
}
else overflow();
}
else if (*s == '['){ /* skip '[[' */
if (p < re+MAXRE-1)
*p++ = c;
else overflow();
c = *s++;
}
else if (*s == '^' && s[1] == '[') { /* skip '[^['*/
if (p < re+MAXRE-2) {
*p++ = c;
*p++ = *s++;
c = *s++;
}
else overflow();
}
else if (*s == ']') { /* '[]' -> '[]*' */
if (p < re+MAXRE-2) {
*p++ = c;
*p++ = *s++;
c = '*';
inclass = 0;
}
else overflow();
}
}
else if (c == '-' && *s == ']') { /* '-]' -> '\-]' */
if (p < re+MAXRE-1)
*p++ = '\\';
else overflow();
}
else if (c == ']')
inclass = 0;
if (p < re+MAXRE-1)
*p++ = c;
else overflow();
}
*p = 0;
program = regcomp(re); /* compile pattern */
if (!compile_time) {
if (npats < NPATS) /* Room in cache */
i = npats++;
else { /* Throw out least used */
int use = pattern[0].use;
i = 0;
for (j = 1; j < NPATS; j++) {
if (pattern[j].use < use) {
use = pattern[j].use;
i = j;
}
}
xfree(pattern[i].program);
xfree(pattern[i].re);
}
pattern[i].re = tostring(pat);
pattern[i].program = program;
pattern[i].use = 1;
}
return((void *) program);
}
/* T/F match indication - matched string not exported */
int
match(void *p, char *s, char *start)
{
return regexec((Reprog *) p, (char *) s, 0, 0);
}
/* match and delimit the matched string */
int
pmatch(void *p, char *s, char *start)
{
Resub m;
m.s.sp = start;
m.e.ep = 0;
if (regexec((Reprog *) p, (char *) s, &m, 1)) {
patbeg = m.s.sp;
patlen = m.e.ep-m.s.sp;
return 1;
}
patlen = -1;
patbeg = start;
return 0;
}
/* perform a non-empty match */
int
nematch(void *p, char *s, char *start)
{
if (pmatch(p, s, start) == 1 && patlen > 0)
return 1;
patlen = -1;
patbeg = start;
return 0;
}
/* 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 */
{
char c;
int n = 0;
int i;
for (i = 0, c = (*pp)[i]; i < 4 && isxdigit(c); i++, c = (*pp)[i]) {
if (isdigit(c))
n = 16 * n + c - '0';
else if ('a' <= c && c <= 'f')
n = 16 * n + c - 'a' + 10;
else if ('A' <= c && c <= 'F')
n = 16 * n + c - 'A' + 10;
}
*pp += i;
return n;
}
/* look for awk-specific escape sequences */
#define isoctdigit(c) ((c) >= '0' && (c) <= '7') /* multiple use of arg */
void
quoted(char **s, char **to, char *end) /* handle escaped sequence */
{
char *p = *s;
char *t = *to;
wchar_t c;
switch(c = *p++) {
case 't':
c = '\t';
break;
case 'n':
c = '\n';
break;
case 'f':
c = '\f';
break;
case 'r':
c = '\r';
break;
case 'b':
c = '\b';
break;
default:
if (t < end-1) /* all else must be escaped */
*t++ = '\\';
if (c == 'x') { /* hexadecimal goo follows */
c = hexstr(&p);
if (t < end-MB_CUR_MAX)
t += wctomb(t, c);
else overflow();
*to = t;
*s = p;
return;
} else if (isoctdigit(c)) { /* \d \dd \ddd */
c -= '0';
if (isoctdigit(*p)) {
c = 8 * c + *p++ - '0';
if (isoctdigit(*p))
c = 8 * c + *p++ - '0';
}
}
break;
}
if (t < end-1)
*t++ = c;
*s = p;
*to = t;
}
/* count rune positions */
int
countposn(char *s, int n)
{
int i, j;
char *end;
for (i = 0, end = s+n; *s && s < end; i++){
j = mblen(s, n);
if(j <= 0)
j = 1;
s += j;
}
return(i);
}
/* pattern package error handler */
void
regerror(char *s)
{
FATAL("%s", s);
}
void
overflow(void)
{
FATAL("%s", "regular expression too big");
}

1899
src/cmd/awk/run.c Normal file
View file

File diff suppressed because it is too large Load diff

435
src/cmd/awk/tran.c Normal file
View file

@ -0,0 +1,435 @@
/****************************************************************
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 "y.tab.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 *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);
FS = &setsymtab("FS", " ", 0.0, STR|DONTFREE, symtab)->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;
*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(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->tab[i] = 0;
}
free(tp->tab);
free(tp);
}
void freeelem(Cell *ap, 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(char *n, 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, p->nval, 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(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(char *s, 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, vp->nval, f, vp->tval) );
return vp->fval = f;
}
void funnyvar(Cell *vp, 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, char *s) /* set string val of a Cell */
{
char *t;
int fldno;
dprintf( ("starting setsval %p: %s = \"%s\", t=%o\n", vp, vp->nval, s, vp->tval) );
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 */
vp->tval &= ~NUM;
vp->tval |= STR;
if (freeable(vp))
xfree(vp->sval);
vp->tval &= ~DONTFREE;
dprintf( ("setsval %p: %s = \"%s (%p)\", t=%o\n", vp, vp->nval, t,t, vp->tval) );
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, vp->nval, vp->fval, vp->tval) );
return(vp->fval);
}
char *getsval(Cell *vp) /* 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, *CONVFMT, vp->fval);
vp->sval = tostring(s);
vp->tval &= ~DONTFREE;
vp->tval |= STR;
}
dprintf( ("getsval %p: %s = \"%s (%p)\", t=%o\n", vp, vp->nval, vp->sval, vp->sval, vp->tval) );
return(vp->sval);
}
char *tostring(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(char *s, int delim) /* collect string up to next delim */
{
char *os = s;
int c, n;
char *buf, *bp;
if ((buf = (char *) malloc(strlen(s)+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 buf;
}

9032
src/cmd/awk/y.output Normal file
View file

File diff suppressed because it is too large Load diff