ref: ba1c218dc86bf94096fcb18ba292c72a3a737b8d
author: qwx <qwx@sciops.net>
date: Tue Sep 23 19:01:00 EDT 2025
pull awk from 9front
--- /dev/null
+++ b/awk.h
@@ -1,0 +1,183 @@
+/*
+Copyright (c) Lucent Technologies 1997
+ All Rights Reserved
+
+*/
+
+typedef double Awkfloat;
+
+#define xfree(a) { if ((a) != nil) { free((a)); (a) = nil; } }+
+#define DEBUG
+#ifdef DEBUG
+ /* uses have to be doubly parenthesized */
+# define dprint(x) if (dbg) print x
+#else
+# define dprint(x)
+#endif
+
+#define FOPEN_MAX 40 /* max number of open files */
+
+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 Biobuf stdin;
+extern Biobuf stdout;
+extern Biobuf stderr;
+
+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 char *exitstatus; /* exit status string */
+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 {+ uchar ctype; /* OCELL, OBOOL, OJUMP, etc. */
+ uchar 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 nelemt; /* 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 *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"
--- /dev/null
+++ b/awkgram.y
@@ -1,0 +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 <u.h>
+#include <libc.h>
+#include <bio.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 (exitstatus==nil)+ 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;
+ }
+ }
+}
--- /dev/null
+++ b/lex.c
@@ -1,0 +1,571 @@
+/****************************************************************
+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 <u.h>
+#include <libc.h>
+#include <ctype.h>
+#include <bio.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 },+};
+
+#ifdef DEBUG
+#define RET(x) { if(dbg)print("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)) == nil)
+ 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)) == nil)
+ FATAL("out of space for strings");+ for (bp = buf; (c = input()) != '"'; ) {+ if (!adjbuf(&buf, &bufsz, bp-buf+2, 500, &bp, 0)){+ *bp = 0;
+ FATAL("out of space for string %.10s...", buf);+ }
+ switch (c) {+ case '\n':
+ case '\r':
+ case 0:
+ *bp = 0;
+ SYNTAX( "non-terminated string %.10s...", buf );
+ lineno++;
+ RET(0);
+ 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);
+ n = strtol(xbuf, nil, 16);
+ *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)) == nil)
+ 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;
+Biobuf *yyin;
+
+int input(void) /* get next lexical input character */
+{+ int c;
+ extern char *lexprog;
+
+ if (yysptr > yysbuf)
+ c = *--yysptr;
+ else if (lexprog != nil) { /* awk '...' */+ if ((c = *lexprog) != 0)
+ lexprog++;
+ } else /* awk -f ... */
+ c = pgetc();
+ if (c == '\n')
+ lineno++;
+ else if (c == Beof)
+ 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]);
+}
--- /dev/null
+++ b/lib.c
@@ -1,0 +1,709 @@
+/****************************************************************
+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 <u.h>
+#include <libc.h>
+#include <ctype.h>
+#include <bio.h>
+#include "awk.h"
+#include "y.tab.h"
+
+Biobuf *infile;
+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 *AARGC;
+
+static Cell dollar0 = { OCELL, CFLD, nil, "", 0.0, REC|STR|DONTFREE };+static Cell dollar1 = { OCELL, CFLD, nil, "", 0.0, FLD|STR|DONTFREE };+
+void recinit(unsigned int n)
+{+ assert(n > 0);
+ record = (char *) malloc(n);
+ fields = (char *) malloc(n);
+ fldtab = (Cell **) malloc((nfields+1) * sizeof(Cell *));
+ if (record == nil || fields == nil || fldtab == nil)
+ FATAL("out of space for $0 and fields");+ record[0] = '\0';
+ 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] == nil)
+ FATAL("out of space in makefields %d", i);+ *fldtab[i] = dollar1;
+ sprint(temp, "%d", i);
+ fldtab[i]->nval = tostring(temp);
+ }
+}
+
+void initgetrec(void)
+{+ int i;
+ char *p;
+
+ for (i = 1; i < *AARGC; i++) {+ if (!isclvar(p = getargv(i))) { /* find 1st real filename */+ setsval(lookup("FILENAME", symtab), p);+ 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();
+ }
+ dprint( ("RS=<%s>, FS=<%s>, AARGC=%g, FILENAME=%s\n",+ *RS, *FS, *AARGC, *FILENAME) );
+ if (isrecord) {+ donefld = 0;
+ donerec = 1;
+ }
+ buf[0] = 0;
+ while (argno < *AARGC || infile == &stdin) {+ dprint( ("argno=%d, file=|%s|\n", argno, file) );+ if (infile == nil) { /* 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;
+ dprint( ("opening file %s\n", file) );+ if (*file == '-' && *(file+1) == '\0')
+ infile = &stdin;
+ else if ((infile = Bopen(file, OREAD)) == nil)
+ 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;
+ }
+ /* Beof arrived on this file; set up next */
+ nextfile();
+ }
+ *pbuf = buf;
+ *pbufsize = bufsize;
+ return 0; /* true end of file */
+}
+
+void nextfile(void)
+{+ if (infile != nil && infile != &stdin)
+ Bterm(infile);
+ infile = nil;
+ argno++;
+}
+
+int readrec(char **pbuf, int *pbufsize, Biobuf *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=Bgetc(inf)) == '\n' && c != Beof) /* skip leading \n's */
+ ;
+ if (c != Beof)
+ Bungetc(inf);
+ }
+ for (rr = buf; ; ) {+ for (; (c=Bgetc(inf)) != sep && c != Beof; ) {+ 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 == Beof)
+ break;
+ if ((c = Bgetc(inf)) == '\n' || c == Beof) /* 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;
+ dprint( ("readrec saw <%s>, returns %d\n", buf, c == Beof && rr == buf ? 0 : 1) );+ *pbuf = buf;
+ *pbufsize = bufsize;
+ return c == Beof && rr == buf ? 0 : 1;
+}
+
+char *getargv(int n) /* get ARGV[n] */
+{+ Cell *x;
+ char *s, temp[50];
+ extern Array *ARGVtab;
+
+ sprint(temp, "%d", n);
+ x = setsymtab(temp, "", 0.0, STR, ARGVtab);
+ s = getsval(x);
+ dprint( ("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;
+ }
+ dprint( ("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, w;
+
+ 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+2)) == nil) /* possibly 2 final \0s */
+ 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 (*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 += w) {+ char buf[UTFmax + 1];
+ Rune chr;
+
+ i++;
+ if (i > nfields)
+ growfldtab(i);
+ if (freeable(fldtab[i]))
+ xfree(fldtab[i]->sval);
+ w = chartorune(&chr, r);
+ n = runetochar(buf, &chr);
+ buf[n] = 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];
+ print("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 == nil)
+ 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)) == nil)
+ FATAL("out of space for fields in refldbld %d", n);+ fieldssize = n;
+ }
+ fr = fields;
+ *fr = '\0';
+ if (*rec == '\0')
+ return 0;
+ p = compre(fs);
+ dprint( ("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;
+ dprint( ("refldbld: i=%d\n", i) );+ if (nematch(p, rec, rec)) {+ dprint( ("match %s (%d chars)\n", patbeg, patlen) );+ strncpy(fr, rec, patbeg-rec);
+ fr += patbeg - rec + 1;
+ *(fr-1) = '\0';
+ rec = patbeg + patlen;
+ } else {+ dprint( ("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';
+ dprint( ("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;
+
+ dprint( ("in recbld inputFS=%s, fldtab[0]=%p\n", inputFS, fldtab[0]) );+ dprint( ("recbld = |%s|\n", record) );+ donerec = 1;
+}
+
+char *exitstatus = nil;
+
+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;
+ Bprint(&stderr, "%s: ", cmdname);
+ va_start(varg, fmt);
+ Bvprint(&stderr, fmt, varg);
+ va_end(varg);
+ if(compile_time == 1 && cursource() != nil)
+ Bprint(&stderr, " at %s:%d", cursource(), lineno);
+ else
+ Bprint(&stderr, " at line %d", lineno);
+ if (curfname != nil)
+ Bprint(&stderr, " in function %s", curfname);
+ Bprint(&stderr, "\n");
+ exitstatus = "syntax error";
+ eprint();
+}
+
+int handler(void *, char *err)
+{+ Bflush(&stdout);
+ fprint(2, "%s\n", err);
+ return 0;
+}
+
+extern int bracecnt, brackcnt, parencnt;
+
+void bracecheck(void)
+{+ int c;
+ static int beenhere = 0;
+
+ if (beenhere++)
+ return;
+ while ((c = input()) != Beof && c != '\0')
+ bclass(c);
+ bcheck2(bracecnt, '{', '}');+ bcheck2(brackcnt, '[', ']');
+ bcheck2(parencnt, '(', ')');+}
+
+void bcheck2(int n, int, int c2)
+{+ if (n == 1)
+ Bprint(&stderr, "\tmissing %c\n", c2);
+ else if (n > 1)
+ Bprint(&stderr, "\t%d missing %c's\n", n, c2);
+ else if (n == -1)
+ Bprint(&stderr, "\textra %c\n", c2);
+ else if (n < -1)
+ Bprint(&stderr, "\t%d extra %c's\n", -n, c2);
+}
+
+void FATAL(char *fmt, ...)
+{+ extern char *cmdname;
+ va_list varg;
+
+ Bflush(&stdout);
+ Bprint(&stderr, "%s: ", cmdname);
+ va_start(varg, fmt);
+ Bvprint(&stderr, fmt, varg);
+ va_end(varg);
+ error();
+ if (dbg > 1) /* core dump if serious debugging on */
+ abort();
+ exits("FATAL");+}
+
+void WARNING(char *fmt, ...)
+{+ extern char *cmdname;
+ va_list varg;
+
+ Bflush(&stdout);
+ Bprint(&stderr, "%s: ", cmdname);
+ va_start(varg, fmt);
+ Bvprint(&stderr, fmt, varg);
+ va_end(varg);
+ error();
+}
+
+void error()
+{+ extern Node *curnode;
+ int line;
+
+ Bprint(&stderr, "\n");
+ if (compile_time != 2 && NR && *NR > 0) {+ if (strcmp(*FILENAME, "-") != 0)
+ Bprint(&stderr, " input record %s:%d", *FILENAME, (int) (*FNR));
+ else
+ Bprint(&stderr, " input record number %d", (int) (*FNR));
+ Bprint(&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() != nil){+ if(line >= 0)
+ Bprint(&stderr, " source %s:%d", cursource(), line);
+ else
+ Bprint(&stderr, " source file %s", cursource());
+ }else if(line >= 0)
+ Bprint(&stderr, " source line %d", line);
+ Bprint(&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++;
+ Bprint(&stderr, " context is\n\t");
+ for (q=ep-1; q>=p && *q!=' ' && *q!='\t' && *q!='\n'; q--)
+ ;
+ for ( ; p < q; p++)
+ if (*p)
+ Bputc(&stderr, *p);
+ Bprint(&stderr, " >>> ");
+ for ( ; p < ep; p++)
+ if (*p)
+ Bputc(&stderr, *p);
+ Bprint(&stderr, " <<< ");
+ if (*ep)
+ while ((c = input()) != '\n' && c != '\0' && c != Beof) {+ Bputc(&stderr, c);
+ bclass(c);
+ }
+ Bputc(&stderr, '\n');
+ 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 (isNaN(x)) {+ WARNING("%s argument out of domain", s);+ x = 1;
+ } else if (isInf(x, 1) || isInf(x, -1)) {+ 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 */
+
+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 */
+ }
+
+ r = strtod(s, &ep);
+ if (ep == s || isInf(r, 1) || isInf(r, -1) || isNaN(r))
+ return 0;
+ while (*ep == ' ' || *ep == '\t' || *ep == '\n')
+ ep++;
+ if (*ep == '\0')
+ return 1;
+ else
+ return 0;
+}
--- /dev/null
+++ b/main.c
@@ -1,0 +1,204 @@
+/****************************************************************
+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";
+
+#include <u.h>
+#include <libc.h>
+#include <bio.h>
+#include "awk.h"
+#include "y.tab.h"
+
+extern int nfields;
+
+Biobuf stdin;
+Biobuf stdout;
+Biobuf stderr;
+
+int dbg = 0;
+Awkfloat srand_seed = 1;
+char *cmdname; /* gets argv[0] for error messages */
+extern Biobuf *yyin; /* lex input file */
+char *lexprog; /* points to program argument if it exists */
+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 */
+
+void main(int argc, char *argv[])
+{+ char *fs = nil, *marg;
+ int temp;
+
+ setfcr(getfcr() & ~FPINVAL);
+
+ Binit(&stdin, 0, OREAD);
+ Binit(&stdout, 1, OWRITE);
+ Binit(&stderr, 2, OWRITE);
+
+ cmdname = argv[0];
+ if (argc == 1) {+ Bprint(&stderr, "usage: %s [-F fieldsep] [-d] [-mf n] [-mr n] [-safe] [-v var=value] [-f programfile | 'program'] [file ...]\n", cmdname);
+ exits("usage");+ }
+
+ atnotify(handler, 1);
+ srand((unsigned long) srand_seed);
+ yyin = nil;
+ 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 == nil || *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;
+ print("awk %s\n", version);+ break;
+ case 'V': /* added for exptools "standard" */
+ print("awk %s\n", version);+ exits(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)
+ exits(0);
+ FATAL("no program given");+ }
+ dprint( ("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 */
+ dprint( ("argc=%d, argv[0]=%s\n", argc, argv[0]) );+ arginit(argc, argv);
+ quotefmtinstall();
+ yyparse();
+ if (fs)
+ *FS = qstring(fs, '\0');
+ dprint( ("exitstatus=%s\n", exitstatus) );+ if (exitstatus == nil) {+ compile_time = 0;
+ run(winner);
+ } else
+ bracecheck();
+ exits(exitstatus);
+}
+
+int pgetc(void) /* get 1 character from awk program */
+{+ int c;
+
+ for (;;) {+ if (yyin == nil) {+ if (curpfile >= npfile)
+ return Beof;
+ if (strcmp(pfile[curpfile], "-") == 0)
+ yyin = &stdin;
+ else if ((yyin = Bopen(pfile[curpfile], OREAD)) == nil)
+ FATAL("can't open file %s", pfile[curpfile]);+ lineno = 1;
+ }
+ if ((c = Bgetc(yyin)) != Beof)
+ return c;
+ if (yyin != &stdin)
+ Bterm(yyin);
+ yyin = nil;
+ curpfile++;
+ }
+}
+
+char *cursource(void) /* current source file name */
+{+ if (npfile > 0)
+ return pfile[curpfile];
+ else
+ return nil;
+}
--- /dev/null
+++ b/maketab.c
@@ -1,0 +1,171 @@
+/****************************************************************
+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 <u.h>
+#include <libc.h>
+#include <bio.h>
+#include "awk.h"
+#include "y.tab.h"
+
+struct xx
+{ int token;+ char *name;
+ char *pname;
+} proc[] = {+ { PROGRAM, "program", nil },+ { BOR, "boolop", " || " },+ { AND, "boolop", " && " },+ { NOT, "boolop", " !" },+ { NE, "relop", " != " },+ { EQ, "relop", " == " },+ { LE, "relop", " <= " },+ { LT, "relop", " < " },+ { GE, "relop", " >= " },+ { GT, "relop", " > " },+ { ARRAY, "array", nil },+ { 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", nil },+ { PASTAT2, "dopa2", nil },+ { 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];
+
+void main(int, char**)
+{+ struct xx *p;
+ int i, tok;
+ Biobuf *fp;
+ char *buf, *toks[3];
+
+ print("#include <u.h>\n");+ print("#include <libc.h>\n");+ print("#include <bio.h>\n");+ print("#include \"awk.h\"\n");+ print("#include \"y.tab.h\"\n\n");+ for (i = SIZE; --i >= 0; )
+ names[i] = "";
+
+ if ((fp = Bopen("y.tab.h", OREAD)) == nil) {+ fprint(2, "maketab can't open y.tab.h!\n");
+ exits("can't open y.tab.h");+ }
+ print("static char *printname[%d] = {\n", SIZE);+ i = 0;
+ while ((buf = Brdline(fp, '\n')) != nil) {+ buf[Blinelen(fp)-1] = '\0';
+ if (tokenize(buf, toks, 3) != 3
+ || strcmp("#define", toks[0]) != 0) /* not a valid #define */+ continue;
+ tok = strtol(toks[2], nil, 10);
+ if (tok < FIRSTTOKEN || tok > LASTTOKEN) {+ fprint(2, "maketab funny token %d %s\n", tok, buf);
+ exits("funny token");+ }
+ names[tok-FIRSTTOKEN] = (char *) malloc(strlen(toks[1])+1);
+ strcpy(names[tok-FIRSTTOKEN], toks[1]);
+ print("\t(char *) \"%s\",\t/* %d */\n", toks[1], tok);+ i++;
+ }
+ print("};\n\n");+
+ for (p=proc; p->token!=0; p++)
+ table[p->token-FIRSTTOKEN] = p->name;
+ print("\nCell *(*proctab[%d])(Node **, int) = {\n", SIZE);+ for (i=0; i<SIZE; i++)
+ if (table[i]==0)
+ print("\tnullproc,\t/* %s */\n", names[i]);+ else
+ print("\t%s,\t/* %s */\n", table[i], names[i]);+ print("};\n\n");+
+ print("char *tokname(int n)\n"); /* print a tokname() function */+ print("{\n");+ print(" static char buf[100];\n\n");+ print(" if (n < FIRSTTOKEN || n > LASTTOKEN) {\n");+ print(" sprint(buf, \"token %%d\", n);\n");+ print(" return buf;\n");+ print(" }\n");+ print(" return printname[n-FIRSTTOKEN];\n");+ print("}\n");+ exits(0);
+}
--- /dev/null
+++ b/mkfile
@@ -1,0 +1,42 @@
+</$objtype/mkfile
+
+TARG=awk
+OFILES=re.$O\
+ lex.$O\
+ main.$O\
+ parse.$O\
+ proctab.$O\
+ popen.$O\
+ tran.$O\
+ lib.$O\
+ run.$O\
+ awkgram.$O\
+
+HFILES=awk.h\
+ y.tab.h\
+ proto.h\
+
+YFILES=awkgram.y
+
+BIN=/$objtype/bin
+
+</sys/src/cmd/mkone
+
+y.tab.h awkgram.c: $YFILES
+ $YACC -o awkgram.c $YFLAGS $prereq
+
+clean:V:
+ rm -f *.[$OS] [$OS].out *.maketab y.tab.? y.debug y.output $TARG
+
+nuke:V:
+ rm -f *.[$OS] [$OS].out *.maketab y.tab.? y.debug y.output awkgram.c proctab.c $TARG
+
+proctab.c: $cputype.maketab
+ ./$cputype.maketab >proctab.c
+
+$cputype.maketab: y.tab.h maketab.c
+ objtype=$cputype mk maketab.$cputype
+
+maketab.$objtype:V:
+ $CC $CFLAGS maketab.c
+ $LD $LDFLAGS -o $objtype.maketab maketab.$O
--- /dev/null
+++ b/parse.c
@@ -1,0 +1,270 @@
+/****************************************************************
+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 <u.h>
+#include <libc.h>
+#include <bio.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 == nil)
+ FATAL("out of space in nodealloc");+ x->nnext = nil;
+ 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 (exitstatus != nil) /* don't link things that are wrong */
+ return a;
+ if (a == nil)
+ return(b);
+ else if (b == nil)
+ return(a);
+ for (c = a; c->nnext != nil; 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;
+ dprint( ("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) (vlong) p; /* swearing that p fits, of course */
+}
+
+Node *itonp(int i) /* and vice versa */
+{+ return (Node *) (long) i;
+}
--- /dev/null
+++ b/popen.c
@@ -1,0 +1,91 @@
+#include <u.h>
+#include <libc.h>
+#include <bio.h>
+#include "awk.h"
+
+#define MAXFORKS 20
+#define NSYSFILE 3
+#define tst(a,b) (mode == OREAD? (b) : (a))
+#define RDR 0
+#define WTR 1
+
+struct a_fork {+ short done;
+ short fd;
+ int pid;
+ char status[128];
+};
+static struct a_fork the_fork[MAXFORKS];
+
+Biobuf*
+popen(char *cmd, int mode)
+{+ int p[2];
+ int myside, hisside, pid;
+ int i, ind;
+
+ for (ind = 0; ind < MAXFORKS; ind++)
+ if (the_fork[ind].pid == 0)
+ break;
+ if (ind == MAXFORKS)
+ return nil;
+ if(pipe(p) < 0)
+ return nil;
+ myside = tst(p[WTR], p[RDR]);
+ hisside = tst(p[RDR], p[WTR]);
+ switch (pid = fork()) {+ case -1:
+ return nil;
+ case 0:
+ /* myside and hisside reverse roles in child */
+ close(myside);
+ dup(hisside, tst(0, 1));
+ for (i=NSYSFILE; i<FOPEN_MAX; i++)
+ close(i);
+ execl("/bin/rc", "rc", "-c", cmd, nil);+ exits("exec failed");+ default:
+ the_fork[ind].pid = pid;
+ the_fork[ind].fd = myside;
+ the_fork[ind].done = 0;
+ close(hisside);
+ return(Bfdopen(myside, mode));
+ }
+}
+
+int
+pclose(Biobuf *ptr)
+{+ int f, r, ind;
+ Waitmsg *status;
+
+ f = Bfildes(ptr);
+ Bterm(ptr);
+ for (ind = 0; ind < MAXFORKS; ind++)
+ if (the_fork[ind].fd == f && the_fork[ind].pid != 0)
+ break;
+ if (ind == MAXFORKS)
+ return -1;
+ if (!the_fork[ind].done) {+ do {+ if((status = wait()) == nil)
+ r = -1;
+ else
+ r = status->pid;
+ for (f = 0; f < MAXFORKS; f++) {+ if (r == the_fork[f].pid) {+ the_fork[f].done = 1;
+ strecpy(the_fork[f].status, the_fork[f].status+512, status->msg);
+ break;
+ }
+ }
+ free(status);
+ } while(r != the_fork[ind].pid && r != -1);
+ if(r == -1)
+ strcpy(the_fork[ind].status, "No loved ones to wait for");
+ }
+ the_fork[ind].pid = 0;
+ if(the_fork[ind].status[0] != '\0')
+ return 1;
+ return 0;
+}
--- /dev/null
+++ b/proto.h
@@ -1,0 +1,172 @@
+/****************************************************************
+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 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 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(void);
+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, Biobuf *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 int handler(void*, char*);
+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 *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 Biobuf *redirect(int, Node *);
+extern Biobuf *openfile(int, char *);
+extern char *filename(Biobuf *);
+extern Cell *closefile(Node **, int);
+extern void closeall(void);
+extern Cell *sub(Node **, int);
+extern Cell *gsub(Node **, int);
+
+extern Biobuf *popen(char *, int);
+extern int pclose(Biobuf *);
--- /dev/null
+++ b/re.c
@@ -1,0 +1,305 @@
+/****************************************************************
+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 <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 *)
+{+ 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.sp = start;
+ m.ep = 0;
+ if (regexec((Reprog *) p, (char *) s, &m, 1)) {+ patbeg = m.sp;
+ patlen = m.ep-m.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. */
+
+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;
+ Rune 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-UTFmax)
+ t += runelen(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;
+}
+
+ /* pattern package error handler */
+
+void
+regerror(char *s)
+{+ FATAL("%s", s);+}
+
+void
+overflow(void)
+{+ FATAL("%s", "regular expression too big");+}
--- /dev/null
+++ b/run.c
@@ -1,0 +1,2018 @@
+/****************************************************************
+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 <u.h>
+#include <libc.h>
+#include <ctype.h>
+#include <bio.h>
+#include "awk.h"
+#include "y.tab.h"
+
+jmp_buf env;
+extern int pairstack[];
+extern Awkfloat srand_seed;
+
+Node *winner = nil; /* root of parse tree */
+Cell *tmps; /* free temporary cells for execution */
+
+static Cell truecell ={ OBOOL, BTRUE, 0, 0, 1.0, NUM };+Cell *True = &truecell;
+static Cell falsecell ={ OBOOL, BFALSE, 0, 0, 0.0, NUM };+Cell *False = &falsecell;
+static Cell breakcell ={ OJUMP, JBREAK, 0, 0, 0.0, NUM };+Cell *jbreak = &breakcell;
+static Cell contcell ={ OJUMP, JCONT, 0, 0, 0.0, NUM };+Cell *jcont = &contcell;
+static Cell nextcell ={ OJUMP, JNEXT, 0, 0, 0.0, NUM };+Cell *jnext = &nextcell;
+static Cell nextfilecell ={ OJUMP, JNEXTFILE, 0, 0, 0.0, NUM };+Cell *jnextfile = &nextfilecell;
+static Cell exitcell ={ OJUMP, JEXIT, 0, 0, 0.0, NUM };+Cell *jexit = &exitcell;
+static Cell retcell ={ OJUMP, JRET, 0, 0, 0.0, NUM };+Cell *jret = &retcell;
+static Cell tempcell ={ OCELL, CTEMP, 0, "", 0.0, NUM|STR|DONTFREE };+
+Node *curnode = nil; /* the node being executed, for debugging */
+
+int
+system(const char *s)
+{+ Waitmsg *status;
+ int pid;
+
+ if(s == nil)
+ return 1;
+ pid = fork();
+ if(pid == 0) {+ execl("/bin/rc", "rc", "-c", s, nil);+ exits("exec");+ }
+ if(pid < 0){+ return -1;
+ }
+ for(;;) {+ status = wait();
+ if(status == nil)
+ FATAL("Out of memory");+ if(status->pid == pid)
+ break;
+ free(status);
+ }
+
+ if(status->msg[0] != '\0') {+ free(status);
+ return 1;
+ }
+ free(status);
+ return 0;
+}
+
+/* buffer memory management */
+int adjbuf(char **pbuf, int *psiz, int minlen, int quantum, char **pbptr,
+ char *whatrtn)
+/* pbuf: address of pointer to buffer being managed
+ * psiz: address of buffer size variable
+ * minlen: minimum length of buffer needed
+ * quantum: buffer size quantum
+ * pbptr: address of movable pointer into buffer, or 0 if none
+ * whatrtn: name of the calling routine if failure should cause fatal error
+ *
+ * return 0 for realloc failure, !=0 for success
+ */
+{+ if (minlen > *psiz) {+ char *tbuf;
+ int rminlen = quantum ? minlen % quantum : 0;
+ int boff = pbptr ? *pbptr - *pbuf : 0;
+ /* round up to next multiple of quantum */
+ if (rminlen)
+ minlen += quantum - rminlen;
+ tbuf = (char *) realloc(*pbuf, minlen);
+ if (tbuf == nil) {+ if (whatrtn)
+ FATAL("out of memory in %s", whatrtn);+ return 0;
+ }
+ *pbuf = tbuf;
+ *psiz = minlen;
+ if (pbptr)
+ *pbptr = tbuf + boff;
+ }
+ return 1;
+}
+
+void run(Node *a) /* execution of parse tree starts here */
+{+ extern void stdinit(void);
+
+ stdinit();
+ execute(a);
+ closeall();
+}
+
+Cell *execute(Node *u) /* execute a node of the parse tree */
+{+ int nobj;
+ Cell *(*proc)(Node **, int);
+ Cell *x;
+ Node *a;
+
+ if (u == nil)
+ return(True);
+ for (a = u; ; a = a->nnext) {+ curnode = a;
+ if (isvalue(a)) {+ x = (Cell *) (a->narg[0]);
+ if (isfld(x) && !donefld)
+ fldbld();
+ else if (isrec(x) && !donerec)
+ recbld();
+ return(x);
+ }
+ nobj = a->nobj;
+ if (notlegal(nobj)) /* probably a Cell* but too risky to print */
+ FATAL("illegal statement");+ proc = proctab[nobj-FIRSTTOKEN];
+ x = (*proc)(a->narg, nobj);
+ if (isfld(x) && !donefld)
+ fldbld();
+ else if (isrec(x) && !donerec)
+ recbld();
+ if (isexpr(a))
+ return(x);
+ if (isjump(x))
+ return(x);
+ if (a->nnext == nil)
+ return(x);
+ if(istemp(x))
+ tfree(x);
+ }
+}
+
+
+Cell *program(Node **a, int) /* execute an awk program */
+{ /* a[0] = BEGIN, a[1] = body, a[2] = END */+ Cell *x;
+
+ if (setjmp(env) != 0)
+ goto ex;
+ if (a[0]) { /* BEGIN */+ x = execute(a[0]);
+ if (isexit(x))
+ return(True);
+ if (isjump(x))
+ FATAL("illegal break, continue, next or nextfile from BEGIN");+ if (istemp(x))
+ tfree(x);
+ }
+ if (a[1] || a[2])
+ while (getrec(&record, &recsize, 1) > 0) {+ x = execute(a[1]);
+ if (isexit(x))
+ break;
+ if (istemp(x))
+ tfree(x);
+ }
+ ex:
+ if (setjmp(env) != 0) /* handles exit within END */
+ goto ex1;
+ if (a[2]) { /* END */+ x = execute(a[2]);
+ if (isbreak(x) || isnext(x) || iscont(x))
+ FATAL("illegal break, continue, next or nextfile from END");+ if (istemp(x))
+ tfree(x);
+ }
+ ex1:
+ return(True);
+}
+
+struct Frame { /* stack frame for awk function calls */+ int nargs; /* number of arguments in this call */
+ Cell *fcncell; /* pointer to Cell for function */
+ Cell **args; /* pointer to array of arguments after execute */
+ Cell *retval; /* return value */
+};
+
+#define NARGS 50 /* max args in a call */
+
+struct Frame *frame = nil; /* base of stack frames; dynamically allocated */
+int nframe = 0; /* number of frames allocated */
+struct Frame *fp = nil; /* frame pointer. bottom level unused */
+
+Cell *call(Node **a, int) /* function call. very kludgy and fragile */
+{+ static Cell newcopycell = { OCELL, CCOPY, 0, "", 0.0, NUM|STR|DONTFREE };+ int i, ncall, ndef;
+ Node *x;
+ Cell *args[NARGS], *oargs[NARGS]; /* BUG: fixed size arrays */
+ Cell *y, *z, *fcn;
+ char *s;
+
+ fcn = execute(a[0]); /* the function itself */
+ s = fcn->nval;
+ if (!isfcn(fcn))
+ FATAL("calling undefined function %s", s);+ if (frame == nil) {+ fp = frame = (struct Frame *) calloc(nframe += 100, sizeof(struct Frame));
+ if (frame == nil)
+ FATAL("out of space for stack frames calling %s", s);+ }
+ for (ncall = 0, x = a[1]; x != nil; x = x->nnext) /* args in call */
+ ncall++;
+ ndef = (int) fcn->fval; /* args in defn */
+ dprint( ("calling %s, %d args (%d in defn), fp=%d\n", s, ncall, ndef, (int) (fp-frame)) );+ if (ncall > ndef)
+ WARNING("function %s called with %d args, uses only %d",+ s, ncall, ndef);
+ if (ncall + ndef > NARGS)
+ FATAL("function %s has %d arguments, limit %d", s, ncall+ndef, NARGS);+ for (i = 0, x = a[1]; x != nil; i++, x = x->nnext) { /* get call args */+ dprint( ("evaluate args[%d], fp=%d:\n", i, (int) (fp-frame)) );+ y = execute(x);
+ oargs[i] = y;
+ dprint( ("args[%d]: %s %f <%s>, t=%o\n",+ i, y->nval, y->fval, isarr(y) ? "(array)" : y->sval, y->tval) );
+ if (isfcn(y))
+ FATAL("can't use function %s as argument in %s", y->nval, s);+ if (isarr(y))
+ args[i] = y; /* arrays by ref */
+ else
+ args[i] = copycell(y);
+ if (istemp(y))
+ tfree(y);
+ }
+ for ( ; i < ndef; i++) { /* add null args for ones not provided */+ args[i] = gettemp();
+ *args[i] = newcopycell;
+ }
+ fp++; /* now ok to up frame */
+ if (fp >= frame + nframe) {+ int dfp = fp - frame; /* old index */
+ frame = (struct Frame *)
+ realloc((char *) frame, (nframe += 100) * sizeof(struct Frame));
+ if (frame == nil)
+ FATAL("out of space for stack frames in %s", s);+ fp = frame + dfp;
+ }
+ fp->fcncell = fcn;
+ fp->args = args;
+ fp->nargs = ndef; /* number defined with (excess are locals) */
+ fp->retval = gettemp();
+
+ dprint( ("start exec of %s, fp=%d\n", s, (int) (fp-frame)) );+ y = execute((Node *)(fcn->sval)); /* execute body */
+ dprint( ("finished exec of %s, fp=%d\n", s, (int) (fp-frame)) );+
+ for (i = 0; i < ndef; i++) {+ Cell *t = fp->args[i];
+ if (isarr(t)) {+ if (t->csub == CCOPY) {+ if (i >= ncall) {+ freesymtab(t);
+ t->csub = CTEMP;
+ if (istemp(t))
+ tfree(t);
+ } else {+ oargs[i]->tval = t->tval;
+ oargs[i]->tval &= ~(STR|NUM|DONTFREE);
+ oargs[i]->sval = t->sval;
+ if (istemp(t))
+ tfree(t);
+ }
+ }
+ } else if (t != y) { /* kludge to prevent freeing twice */+ t->csub = CTEMP;
+ if (istemp(t))
+ tfree(t);
+ }
+ }
+ if (istemp(fcn))
+ tfree(fcn);
+ if (isexit(y) || isnext(y) || isnextfile(y))
+ return y;
+ if (istemp(y))
+ tfree(y); /* this can free twice! */
+ z = fp->retval; /* return value */
+ dprint( ("%s returns %g |%s| %o\n", s, getfval(z), getsval(z), z->tval) );+ fp--;
+ return(z);
+}
+
+Cell *copycell(Cell *x) /* make a copy of a cell in a temp */
+{+ Cell *y;
+
+ y = gettemp();
+ y->csub = CCOPY; /* prevents freeing until call is over */
+ y->nval = x->nval; /* BUG? */
+ y->sval = x->sval ? tostring(x->sval) : nil;
+ y->fval = x->fval;
+ y->tval = x->tval & ~(CON|FLD|REC|DONTFREE); /* copy is not constant or field */
+ /* is DONTFREE right? */
+ return y;
+}
+
+Cell *arg(Node **a, int n) /* nth argument of a function */
+{+
+ n = ptoi(a[0]); /* argument number, counting from 0 */
+ dprint( ("arg(%d), fp->nargs=%d\n", n, fp->nargs) );+ if (n+1 > fp->nargs)
+ FATAL("argument #%d of function %s was not supplied",+ n+1, fp->fcncell->nval);
+ return fp->args[n];
+}
+
+Cell *jump(Node **a, int n) /* break, continue, next, nextfile, return */
+{+ Cell *y;
+
+ switch (n) {+ case EXIT:
+ if (a[0] != nil) {+ y = execute(a[0]);
+ if((y->tval & (NUM|STR)) == STR) {+ exitstatus = getsval(y);
+ } else if((int) getfval(y) != 0) {+ exitstatus = "error";
+ }
+ }
+ longjmp(env, 1);
+ case RETURN:
+ if (a[0] != nil) {+ y = execute(a[0]);
+ if ((y->tval & (STR|NUM)) == (STR|NUM)) {+ setsval(fp->retval, getsval(y));
+ fp->retval->fval = getfval(y);
+ fp->retval->tval |= NUM;
+ }
+ else if (y->tval & STR)
+ setsval(fp->retval, getsval(y));
+ else if (y->tval & NUM)
+ setfval(fp->retval, getfval(y));
+ else /* can't happen */
+ FATAL("bad type variable %d", y->tval);+ if (istemp(y))
+ tfree(y);
+ }
+ return(jret);
+ case NEXT:
+ return(jnext);
+ case NEXTFILE:
+ nextfile();
+ return(jnextfile);
+ case BREAK:
+ return(jbreak);
+ case CONTINUE:
+ return(jcont);
+ default: /* can't happen */
+ FATAL("illegal jump type %d", n);+ }
+ return 0; /* not reached */
+}
+
+Cell *getline(Node **a, int n) /* get next line from specific input */
+{ /* a[0] is variable, a[1] is operator, a[2] is filename */+ Cell *r, *x;
+ extern Cell **fldtab;
+ Biobuf *fp;
+ char *buf;
+ int bufsize = recsize;
+ int mode;
+
+ if ((buf = (char *) malloc(bufsize)) == nil)
+ FATAL("out of memory in getline");+
+ Bflush(&stdout); /* in case someone is waiting for a prompt */
+ r = gettemp();
+ if (a[1] != nil) { /* getline < file */+ x = execute(a[2]); /* filename */
+ mode = ptoi(a[1]);
+ if (mode == '|') /* input pipe */
+ mode = LE; /* arbitrary flag */
+ fp = openfile(mode, getsval(x));
+ if (istemp(x))
+ tfree(x);
+ if (fp == nil)
+ n = -1;
+ else
+ n = readrec(&buf, &bufsize, fp);
+ if (n <= 0) {+ ;
+ } else if (a[0] != nil) { /* getline var <file */+ x = execute(a[0]);
+ setsval(x, buf);
+ if (istemp(x))
+ tfree(x);
+ } else { /* getline <file */+ setsval(fldtab[0], buf);
+ if (is_number(fldtab[0]->sval)) {+ fldtab[0]->fval = atof(fldtab[0]->sval);
+ fldtab[0]->tval |= NUM;
+ }
+ }
+ } else { /* bare getline; use current input */+ if (a[0] == nil) /* getline */
+ n = getrec(&record, &recsize, 1);
+ else { /* getline var */+ n = getrec(&buf, &bufsize, 0);
+ if (n > 0) {+ x = execute(a[0]);
+ setsval(x, buf);
+ if (istemp(x))
+ tfree(x);
+ }
+ }
+ }
+ setfval(r, (Awkfloat) n);
+ free(buf);
+ return r;
+}
+
+Cell *getnf(Node **a, int) /* get NF */
+{+ if (donefld == 0)
+ fldbld();
+ return (Cell *) a[0];
+}
+
+Cell *array(Node **a, int) /* a[0] is symtab, a[1] is list of subscripts */
+{+ Cell *x, *y, *z;
+ char *s;
+ Node *np;
+ char *buf;
+ int bufsz = recsize;
+ int nsub = strlen(*SUBSEP);
+
+ if ((buf = (char *) malloc(bufsz)) == nil)
+ FATAL("out of memory in array");+
+ x = execute(a[0]); /* Cell* for symbol table */
+ buf[0] = 0;
+ for (np = a[1]; np; np = np->nnext) {+ y = execute(np); /* subscript */
+ s = getsval(y);
+ if (!adjbuf(&buf, &bufsz, strlen(buf)+strlen(s)+nsub+1, recsize, 0, 0))
+ FATAL("out of memory for %s[%s...]", x->nval, buf);+ strcat(buf, s);
+ if (np->nnext)
+ strcat(buf, *SUBSEP);
+ if (istemp(y))
+ tfree(y);
+ }
+ if (!isarr(x)) {+ dprint( ("making %s into an array\n", x->nval) );+ if (freeable(x))
+ xfree(x->sval);
+ x->tval &= ~(STR|NUM|DONTFREE);
+ x->tval |= ARR;
+ x->sval = (char *) makesymtab(NSYMTAB);
+ }
+ z = setsymtab(buf, "", 0.0, STR|NUM, (Array *) x->sval);
+ z->ctype = OCELL;
+ z->csub = CVAR;
+ if (istemp(x))
+ tfree(x);
+ free(buf);
+ return(z);
+}
+
+Cell *awkdelete(Node **a, int) /* a[0] is symtab, a[1] is list of subscripts */
+{+ Cell *x, *y;
+ Node *np;
+ char *s;
+ int nsub = strlen(*SUBSEP);
+
+ x = execute(a[0]); /* Cell* for symbol table */
+ if (!isarr(x))
+ return True;
+ if (a[1] == 0) { /* delete the elements, not the table */+ freesymtab(x);
+ x->tval &= ~STR;
+ x->tval |= ARR;
+ x->sval = (char *) makesymtab(NSYMTAB);
+ } else {+ int bufsz = recsize;
+ char *buf;
+ if ((buf = (char *) malloc(bufsz)) == nil)
+ FATAL("out of memory in adelete");+ buf[0] = 0;
+ for (np = a[1]; np; np = np->nnext) {+ y = execute(np); /* subscript */
+ s = getsval(y);
+ if (!adjbuf(&buf, &bufsz, strlen(buf)+strlen(s)+nsub+1, recsize, 0, 0))
+ FATAL("out of memory deleting %s[%s...]", x->nval, buf);+ strcat(buf, s);
+ if (np->nnext)
+ strcat(buf, *SUBSEP);
+ if (istemp(y))
+ tfree(y);
+ }
+ freeelem(x, buf);
+ free(buf);
+ }
+ if (istemp(x))
+ tfree(x);
+ return True;
+}
+
+Cell *intest(Node **a, int) /* a[0] is index (list), a[1] is symtab */
+{+ Cell *x, *ap, *k;
+ Node *p;
+ char *buf;
+ char *s;
+ int bufsz = recsize;
+ int nsub = strlen(*SUBSEP);
+
+ ap = execute(a[1]); /* array name */
+ if (!isarr(ap)) {+ dprint( ("making %s into an array\n", ap->nval) );+ if (freeable(ap))
+ xfree(ap->sval);
+ ap->tval &= ~(STR|NUM|DONTFREE);
+ ap->tval |= ARR;
+ ap->sval = (char *) makesymtab(NSYMTAB);
+ }
+ if ((buf = (char *) malloc(bufsz)) == nil) {+ FATAL("out of memory in intest");+ }
+ buf[0] = 0;
+ for (p = a[0]; p; p = p->nnext) {+ x = execute(p); /* expr */
+ s = getsval(x);
+ if (!adjbuf(&buf, &bufsz, strlen(buf)+strlen(s)+nsub+1, recsize, 0, 0))
+ FATAL("out of memory deleting %s[%s...]", x->nval, buf);+ strcat(buf, s);
+ if (istemp(x))
+ tfree(x);
+ if (p->nnext)
+ strcat(buf, *SUBSEP);
+ }
+ k = lookup(buf, (Array *) ap->sval);
+ if (istemp(ap))
+ tfree(ap);
+ free(buf);
+ if (k == nil)
+ return(False);
+ else
+ return(True);
+}
+
+
+Cell *matchop(Node **a, int n) /* ~ and match() */
+{+ Cell *x, *y;
+ char *s, *t;
+ int i;
+ void *p;
+
+ x = execute(a[1]); /* a[1] = target text */
+ s = getsval(x);
+ if (a[0] == 0) /* a[1] == 0: already-compiled reg expr */
+ p = (void *) a[2];
+ else {+ y = execute(a[2]); /* a[2] = regular expr */
+ t = getsval(y);
+ p = compre(t);
+ if (istemp(y))
+ tfree(y);
+ }
+ if (n == MATCHFCN)
+ i = pmatch(p, s, s);
+ else
+ i = match(p, s, s);
+ if (istemp(x))
+ tfree(x);
+ if (n == MATCHFCN) {+ int start = utfnlen(s, patbeg-s)+1;
+ if (patlen < 0)
+ start = 0;
+ setfval(rstartloc, (Awkfloat) start);
+ setfval(rlengthloc, (Awkfloat) utfnlen(patbeg, patlen));
+ x = gettemp();
+ x->tval = NUM;
+ x->fval = start;
+ return x;
+ } else if ((n == MATCH && i == 1) || (n == NOTMATCH && i == 0))
+ return(True);
+ else
+ return(False);
+}
+
+
+Cell *boolop(Node **a, int n) /* a[0] || a[1], a[0] && a[1], !a[0] */
+{+ Cell *x, *y;
+ int i;
+
+ x = execute(a[0]);
+ i = istrue(x);
+ if (istemp(x))
+ tfree(x);
+ switch (n) {+ case BOR:
+ if (i) return(True);
+ y = execute(a[1]);
+ i = istrue(y);
+ if (istemp(y))
+ tfree(y);
+ if (i) return(True);
+ else return(False);
+ case AND:
+ if ( !i ) return(False);
+ y = execute(a[1]);
+ i = istrue(y);
+ if (istemp(y))
+ tfree(y);
+ if (i) return(True);
+ else return(False);
+ case NOT:
+ if (i) return(False);
+ else return(True);
+ default: /* can't happen */
+ FATAL("unknown boolean operator %d", n);+ }
+ return 0; /*NOTREACHED*/
+}
+
+Cell *relop(Node **a, int n) /* a[0 < a[1], etc. */
+{+ int i;
+ Cell *x, *y;
+ Awkfloat j;
+
+ x = execute(a[0]);
+ y = execute(a[1]);
+ if (x->tval&NUM && y->tval&NUM) {+ j = x->fval - y->fval;
+ i = j<0? -1: (j>0? 1: 0);
+ } else {+ i = strcmp(getsval(x), getsval(y));
+ }
+ if (istemp(x))
+ tfree(x);
+ if (istemp(y))
+ tfree(y);
+ switch (n) {+ case LT: if (i<0) return(True);
+ else return(False);
+ case LE: if (i<=0) return(True);
+ else return(False);
+ case NE: if (i!=0) return(True);
+ else return(False);
+ case EQ: if (i == 0) return(True);
+ else return(False);
+ case GE: if (i>=0) return(True);
+ else return(False);
+ case GT: if (i>0) return(True);
+ else return(False);
+ default: /* can't happen */
+ FATAL("unknown relational operator %d", n);+ }
+ return 0; /*NOTREACHED*/
+}
+
+void tfree(Cell *a) /* free a tempcell */
+{+ if (freeable(a)) {+ dprint( ("freeing %s %s %o\n", a->nval, a->sval, a->tval) );+ xfree(a->sval);
+ }
+ if (a == tmps)
+ FATAL("tempcell list is curdled");+ a->cnext = tmps;
+ tmps = a;
+}
+
+Cell *gettemp(void) /* get a tempcell */
+{ int i;+ Cell *x;
+
+ if (!tmps) {+ tmps = (Cell *) calloc(100, sizeof(Cell));
+ if (!tmps)
+ FATAL("out of space for temporaries");+ for(i = 1; i < 100; i++)
+ tmps[i-1].cnext = &tmps[i];
+ tmps[i-1].cnext = 0;
+ }
+ x = tmps;
+ tmps = x->cnext;
+ *x = tempcell;
+ return(x);
+}
+
+Cell *indirect(Node **a, int) /* $( a[0] ) */
+{+ Cell *x;
+ int m;
+ char *s;
+
+ x = execute(a[0]);
+ m = (int) getfval(x);
+ if (m == 0 && !is_number(s = getsval(x))) /* suspicion! */
+ FATAL("illegal field $(%s), name \"%s\"", s, x->nval);+ /* BUG: can x->nval ever be null??? */
+ if (istemp(x))
+ tfree(x);
+ x = fieldadr(m);
+ x->ctype = OCELL; /* BUG? why are these needed? */
+ x->csub = CFLD;
+ return(x);
+}
+
+Cell *substr(Node **a, int) /* substr(a[0], a[1], a[2]) */
+{+ int k, m, n;
+ Rune r;
+ char *s, *p;
+ int temp;
+ Cell *x, *y, *z = 0;
+
+ x = execute(a[0]);
+ y = execute(a[1]);
+ if (a[2] != 0)
+ z = execute(a[2]);
+ s = getsval(x);
+ k = utfnlen(s, strlen(s)) + 1;
+ if (k <= 1) {+ if (istemp(x))
+ tfree(x);
+ if (istemp(y))
+ tfree(y);
+ if (a[2] != 0) {+ if (istemp(z))
+ tfree(z);
+ }
+ x = gettemp();
+ setsval(x, "");
+ return(x);
+ }
+ m = (int) getfval(y);
+ if (m <= 0)
+ m = 1;
+ else if (m > k)
+ m = k;
+ if (istemp(y))
+ tfree(y);
+ if (a[2] != 0) {+ n = (int) getfval(z);
+ if (istemp(z))
+ tfree(z);
+ } else
+ n = k - 1;
+ if (n < 0)
+ n = 0;
+ else if (n > k - m)
+ n = k - m;
+ dprint( ("substr: m=%d, n=%d, s=%s\n", m, n, s) );+ y = gettemp();
+ while (*s && --m)
+ s += chartorune(&r, s);
+ for (p = s; *p && n--; p += chartorune(&r, p))
+ ;
+ temp = *p; /* with thanks to John Linderman */
+ *p = '\0';
+ setsval(y, s);
+ *p = temp;
+ if (istemp(x))
+ tfree(x);
+ return(y);
+}
+
+Cell *sindex(Node **a, int) /* index(a[0], a[1]) */
+{+ Cell *x, *y, *z;
+ char *s1, *s2, *p1, *p2, *q;
+ Awkfloat v = 0.0;
+
+ x = execute(a[0]);
+ s1 = getsval(x);
+ y = execute(a[1]);
+ s2 = getsval(y);
+
+ z = gettemp();
+ for (p1 = s1; *p1 != '\0'; p1++) {+ for (q=p1, p2=s2; *p2 != '\0' && *q == *p2; q++, p2++)
+ ;
+ if (*p2 == '\0') {+ v = (Awkfloat) utfnlen(s1, p1-s1) + 1; /* origin 1 */
+ break;
+ }
+ }
+ if (istemp(x))
+ tfree(x);
+ if (istemp(y))
+ tfree(y);
+ setfval(z, v);
+ return(z);
+}
+
+#define MAXNUMSIZE 50
+
+int format(char **pbuf, int *pbufsize, char *s, Node *a) /* printf-like conversions */
+{+ char *fmt;
+ char *p, *t, *os;
+ Cell *x;
+ int flag, n;
+ int fmtwd; /* format width */
+ int fmtsz = recsize;
+ char *buf = *pbuf;
+ int bufsize = *pbufsize;
+
+ os = s;
+ p = buf;
+ if ((fmt = (char *) malloc(fmtsz)) == nil)
+ FATAL("out of memory in format()");+ while (*s) {+ adjbuf(&buf, &bufsize, MAXNUMSIZE+1+p-buf, recsize, &p, "format");
+ if (*s != '%') {+ *p++ = *s++;
+ continue;
+ }
+ if (*(s+1) == '%') {+ *p++ = '%';
+ s += 2;
+ continue;
+ }
+ /* have to be real careful in case this is a huge number, eg, %100000d */
+ fmtwd = atoi(s+1);
+ if (fmtwd < 0)
+ fmtwd = -fmtwd;
+ adjbuf(&buf, &bufsize, fmtwd+1+p-buf, recsize, &p, "format");
+ for (t = fmt; (*t++ = *s) != '\0'; s++) {+ if (!adjbuf(&fmt, &fmtsz, MAXNUMSIZE+1+t-fmt, recsize, &t, 0))
+ FATAL("format item %.30s... ran format() out of memory", os);+ if (isalpha(*s) && *s != 'l' && *s != 'h' && *s != 'L')
+ break; /* the ansi panoply */
+ if (*s == '*') {+ x = execute(a);
+ a = a->nnext;
+ sprint(t-1, "%d", fmtwd=(int) getfval(x));
+ if (fmtwd < 0)
+ fmtwd = -fmtwd;
+ adjbuf(&buf, &bufsize, fmtwd+1+p-buf, recsize, &p, "format");
+ t = fmt + strlen(fmt);
+ if (istemp(x))
+ tfree(x);
+ }
+ }
+ *t = '\0';
+ if (fmtwd < 0)
+ fmtwd = -fmtwd;
+ adjbuf(&buf, &bufsize, fmtwd+1+p-buf, recsize, &p, "format");
+
+ switch (*s) {+ case 'f': case 'e': case 'g': case 'E': case 'G':
+ flag = 1;
+ break;
+ case 'd': case 'i':
+ flag = 2;
+ if(*(s-1) == 'l') break;
+ t[-1] = 'l';
+ *t = 'd';
+ *++t = '\0';
+ break;
+ case 'u':
+ flag = *(s-1) == 'l' ? 2 : 3;
+ t[-1] = 'u';
+ *t++ = 'd';
+ *t = '\0';
+ break;
+ case 'o': case 'x': case 'X':
+ flag = *(s-1) == 'l' ? 2 : 3;
+ t[-1] = 'u';
+ *t++ = *s;
+ *t = '\0';
+ break;
+ case 's': case 'q':
+ flag = 4;
+ break;
+ case 'c':
+ flag = 5;
+ break;
+ default:
+ WARNING("weird printf conversion %s", fmt);+ flag = 0;
+ break;
+ }
+ if (a == nil)
+ FATAL("not enough args in printf(%s)", os);+ x = execute(a);
+ a = a->nnext;
+ n = MAXNUMSIZE;
+ if (fmtwd > n)
+ n = fmtwd;
+ adjbuf(&buf, &bufsize, 1+n+p-buf, recsize, &p, "format");
+ switch (flag) {+ case 0: sprint(p, "%s", fmt); /* unknown, so dump it too */
+ t = getsval(x);
+ n = strlen(t);
+ if (fmtwd > n)
+ n = fmtwd;
+ adjbuf(&buf, &bufsize, 1+strlen(p)+n+p-buf, recsize, &p, "format");
+ p += strlen(p);
+ sprint(p, "%s", t);
+ break;
+ case 1: sprint(p, fmt, getfval(x)); break;
+ case 2: sprint(p, fmt, (long) getfval(x)); break;
+ case 3: sprint(p, fmt, (int) getfval(x)); break;
+ case 4:
+ t = getsval(x);
+ n = strlen(t);
+ if (fmtwd > n)
+ n = fmtwd;
+ if (!adjbuf(&buf, &bufsize, 1+n+p-buf, recsize, &p, 0))
+ FATAL("huge string/format (%d chars) in printf %.30s... ran format() out of memory", n, t);+ sprint(p, fmt, t);
+ break;
+ case 5:
+ if (isnum(x)) {+ if (getfval(x)) {+ *p++ = (uchar)getfval(x);
+ *p = '\0';
+ } else {+ *p++ = '\0';
+ *p = '\0';
+ }
+ } else {+ if((*p = getsval(x)[0]) != '\0')
+ p++;
+ *p = '\0';
+ }
+ break;
+ }
+ if (istemp(x))
+ tfree(x);
+ p += strlen(p);
+ s++;
+ }
+ *p = '\0';
+ free(fmt);
+ for ( ; a; a = a->nnext) { /* evaluate any remaining args */+ x = execute(a);
+ if (istemp(x))
+ tfree(x);
+ }
+ *pbuf = buf;
+ *pbufsize = bufsize;
+ return p - buf;
+}
+
+Cell *awksprintf(Node **a, int) /* sprint(a[0]) */
+{+ Cell *x;
+ Node *y;
+ char *buf;
+ int bufsz=3*recsize;
+
+ if ((buf = (char *) malloc(bufsz)) == nil)
+ FATAL("out of memory in awksprint");+ y = a[0]->nnext;
+ x = execute(a[0]);
+ if (format(&buf, &bufsz, getsval(x), y) == -1)
+ FATAL("sprint string %.30s... too long. can't happen.", buf);+ if (istemp(x))
+ tfree(x);
+ x = gettemp();
+ x->sval = buf;
+ x->tval = STR;
+ return(x);
+}
+
+Cell *awkprintf(Node **a, int) /* printf */
+{ /* a[0] is list of args, starting with format string */+ /* a[1] is redirection operator, a[2] is redirection file */
+ Biobuf *fp;
+ Cell *x;
+ Node *y;
+ char *buf;
+ int len;
+ int bufsz=3*recsize;
+
+ if ((buf = (char *) malloc(bufsz)) == nil)
+ FATAL("out of memory in awkprintf");+ y = a[0]->nnext;
+ x = execute(a[0]);
+ if ((len = format(&buf, &bufsz, getsval(x), y)) == -1)
+ FATAL("printf string %.30s... too long. can't happen.", buf);+ if (istemp(x))
+ tfree(x);
+ fp = a[1]? redirect(ptoi(a[1]), a[2]): &stdout;
+ if(Bwrite(fp, buf, len) < 0)
+ FATAL("write error on %s", filename(fp));+ if(fp != &stdout) Bflush(fp);
+ free(buf);
+ return(True);
+}
+
+Cell *arith(Node **a, int n) /* a[0] + a[1], etc. also -a[0] */
+{+ Awkfloat i, j = 0;
+ double v;
+ Cell *x, *y, *z;
+
+ x = execute(a[0]);
+ i = getfval(x);
+ if (istemp(x))
+ tfree(x);
+ if (n != UMINUS) {+ y = execute(a[1]);
+ j = getfval(y);
+ if (istemp(y))
+ tfree(y);
+ }
+ z = gettemp();
+ switch (n) {+ case ADD:
+ i += j;
+ break;
+ case MINUS:
+ i -= j;
+ break;
+ case MULT:
+ i *= j;
+ break;
+ case DIVIDE:
+ if (j == 0)
+ FATAL("division by zero");+ i /= j;
+ break;
+ case MOD:
+ if (j == 0)
+ FATAL("division by zero in mod");+ modf(i/j, &v);
+ i = i - j * v;
+ break;
+ case UMINUS:
+ i = -i;
+ break;
+ case POWER:
+ if (j >= 0 && modf(j, &v) == 0.0) /* pos integer exponent */
+ i = ipow(i, (int) j);
+ else
+ i = errcheck(pow(i, j), "pow");
+ break;
+ default: /* can't happen */
+ FATAL("illegal arithmetic operator %d", n);+ }
+ setfval(z, i);
+ return(z);
+}
+
+double ipow(double x, int n) /* x**n. ought to be done by pow, but isn't always */
+{+ double v;
+
+ if (n <= 0)
+ return 1;
+ v = ipow(x, n/2);
+ if (n % 2 == 0)
+ return v * v;
+ else
+ return x * v * v;
+}
+
+Cell *incrdecr(Node **a, int n) /* a[0]++, etc. */
+{+ Cell *x, *z;
+ int k;
+ Awkfloat xf;
+
+ x = execute(a[0]);
+ xf = getfval(x);
+ k = (n == PREINCR || n == POSTINCR) ? 1 : -1;
+ if (n == PREINCR || n == PREDECR) {+ setfval(x, xf + k);
+ return(x);
+ }
+ z = gettemp();
+ setfval(z, xf);
+ setfval(x, xf + k);
+ if (istemp(x))
+ tfree(x);
+ return(z);
+}
+
+Cell *assign(Node **a, int n) /* a[0] = a[1], a[0] += a[1], etc. */
+{ /* this is subtle; don't muck with it. */+ Cell *x, *y;
+ Awkfloat xf, yf;
+ double v;
+
+ y = execute(a[1]);
+ x = execute(a[0]);
+ if (n == ASSIGN) { /* ordinary assignment */+ if (x == y && !(x->tval & (FLD|REC))) /* self-assignment: */
+ goto Free; /* leave alone unless it's a field */
+ if ((y->tval & (STR|NUM)) == (STR|NUM)) {+ yf = getfval(y);
+ setsval(x, getsval(y));
+ x->fval = yf;
+ x->tval |= NUM;
+ }
+ else if (isstr(y))
+ setsval(x, getsval(y));
+ else if (isnum(y))
+ setfval(x, getfval(y));
+ else
+ funnyvar(y, "read value of");
+Free:
+ if (istemp(y))
+ tfree(y);
+ return(x);
+ }
+ xf = getfval(x);
+ yf = getfval(y);
+ switch (n) {+ case ADDEQ:
+ xf += yf;
+ break;
+ case SUBEQ:
+ xf -= yf;
+ break;
+ case MULTEQ:
+ xf *= yf;
+ break;
+ case DIVEQ:
+ if (yf == 0)
+ FATAL("division by zero in /=");+ xf /= yf;
+ break;
+ case MODEQ:
+ if (yf == 0)
+ FATAL("division by zero in %%=");+ modf(xf/yf, &v);
+ xf = xf - yf * v;
+ break;
+ case POWEQ:
+ if (yf >= 0 && modf(yf, &v) == 0.0) /* pos integer exponent */
+ xf = ipow(xf, (int) yf);
+ else
+ xf = errcheck(pow(xf, yf), "pow");
+ break;
+ default:
+ FATAL("illegal assignment operator %d", n);+ break;
+ }
+ if (istemp(y))
+ tfree(y);
+ setfval(x, xf);
+ return(x);
+}
+
+Cell *cat(Node **a, int) /* a[0] cat a[1] */
+{+ Cell *x, *y, *z;
+ int n1, n2;
+ char *s;
+
+ x = execute(a[0]);
+ y = execute(a[1]);
+ getsval(x);
+ getsval(y);
+ n1 = strlen(x->sval);
+ n2 = strlen(y->sval);
+ s = (char *) malloc(n1 + n2 + 1);
+ if (s == nil)
+ FATAL("out of space concatenating %.15s... and %.15s...",+ x->sval, y->sval);
+ strcpy(s, x->sval);
+ strcpy(s+n1, y->sval);
+ if (istemp(y))
+ tfree(y);
+ z = gettemp();
+ z->sval = s;
+ z->tval = STR;
+ if (istemp(x))
+ tfree(x);
+ return(z);
+}
+
+Cell *pastat(Node **a, int) /* a[0] { a[1] } */+{+ Cell *x;
+
+ if (a[0] == 0)
+ x = execute(a[1]);
+ else {+ x = execute(a[0]);
+ if (istrue(x)) {+ if (istemp(x))
+ tfree(x);
+ x = execute(a[1]);
+ }
+ }
+ return x;
+}
+
+Cell *dopa2(Node **a, int) /* a[0], a[1] { a[2] } */+{+ Cell *x;
+ int pair;
+
+ pair = ptoi(a[3]);
+ if (pairstack[pair] == 0) {+ x = execute(a[0]);
+ if (istrue(x))
+ pairstack[pair] = 1;
+ if (istemp(x))
+ tfree(x);
+ }
+ if (pairstack[pair] == 1) {+ x = execute(a[1]);
+ if (istrue(x))
+ pairstack[pair] = 0;
+ if (istemp(x))
+ tfree(x);
+ x = execute(a[2]);
+ return(x);
+ }
+ return(False);
+}
+
+Cell *split(Node **a, int) /* split(a[0], a[1], a[2]); a[3] is type */
+{+ Cell *x = 0, *y, *ap;
+ char *s, *t, *fs = 0;
+ char temp, num[50];
+ int n, nb, sep, arg3type;
+
+ y = execute(a[0]); /* source string */
+ s = getsval(y);
+ arg3type = ptoi(a[3]);
+ if (a[2] == 0) /* fs string */
+ fs = *FS;
+ else if (arg3type == STRING) { /* split(str,arr,"string") */+ x = execute(a[2]);
+ fs = getsval(x);
+ } else if (arg3type == REGEXPR)
+ fs = "(regexpr)"; /* split(str,arr,/regexpr/) */
+ else
+ FATAL("illegal type of split");+ sep = *fs;
+ ap = execute(a[1]); /* array name */
+ n = y->tval;
+ y->tval |= DONTFREE; /* split(a[x], a); */
+ freesymtab(ap);
+ y->tval = n;
+ dprint( ("split: s=|%s|, a=%s, sep=|%s|\n", s, ap->nval, fs) );+ ap->tval &= ~STR;
+ ap->tval |= ARR;
+ ap->sval = (char *) makesymtab(NSYMTAB);
+
+ n = 0;
+ if ((*s != '\0' && strlen(fs) > 1) || arg3type == REGEXPR) { /* reg expr */+ void *p;
+ if (arg3type == REGEXPR) { /* it's ready already */+ p = (void *) a[2];
+ } else {+ p = compre(fs);
+ }
+ t = s;
+ if (nematch(p,s,t)) {+ do {+ n++;
+ sprint(num, "%d", n);
+ temp = *patbeg;
+ *patbeg = '\0';
+ if (is_number(t))
+ setsymtab(num, t, atof(t), STR|NUM, (Array *) ap->sval);
+ else
+ setsymtab(num, t, 0.0, STR, (Array *) ap->sval);
+ *patbeg = temp;
+ t = patbeg + patlen;
+ if (t[-1] == 0 || *t == 0) {+ n++;
+ sprint(num, "%d", n);
+ setsymtab(num, "", 0.0, STR, (Array *) ap->sval);
+ goto spdone;
+ }
+ } while (nematch(p,s,t));
+ }
+ n++;
+ sprint(num, "%d", n);
+ if (is_number(t))
+ setsymtab(num, t, atof(t), STR|NUM, (Array *) ap->sval);
+ else
+ setsymtab(num, t, 0.0, STR, (Array *) ap->sval);
+ spdone:
+ p = nil;
+ USED(p);
+ } else if (sep == ' ') {+ for (n = 0; ; ) {+ while (*s == ' ' || *s == '\t' || *s == '\n')
+ s++;
+ if (*s == 0)
+ break;
+ n++;
+ t = s;
+ do
+ s++;
+ while (*s!=' ' && *s!='\t' && *s!='\n' && *s!='\0');
+ temp = *s;
+ *s = '\0';
+ sprint(num, "%d", n);
+ if (is_number(t))
+ setsymtab(num, t, atof(t), STR|NUM, (Array *) ap->sval);
+ else
+ setsymtab(num, t, 0.0, STR, (Array *) ap->sval);
+ *s = temp;
+ if (*s != 0)
+ s++;
+ }
+ } else if (sep == 0) { /* new: split(s, a, "") => 1 char/elem */+ for (n = 0; *s != 0; s += nb) {+ Rune r;
+ char buf[UTFmax+1];
+
+ n++;
+ snprint(num, sizeof num, "%d", n);
+ nb = chartorune(&r, s);
+ memmove(buf, s, nb);
+ buf[nb] = '\0';
+ if (isdigit(buf[0]))
+ setsymtab(num, buf, atof(buf), STR|NUM, (Array *) ap->sval);
+ else
+ setsymtab(num, buf, 0.0, STR, (Array *) ap->sval);
+ }
+ } else if (*s != 0) {+ for (;;) {+ n++;
+ t = s;
+ while (*s != sep && *s != '\n' && *s != '\0')
+ s++;
+ temp = *s;
+ *s = '\0';
+ sprint(num, "%d", n);
+ if (is_number(t))
+ setsymtab(num, t, atof(t), STR|NUM, (Array *) ap->sval);
+ else
+ setsymtab(num, t, 0.0, STR, (Array *) ap->sval);
+ *s = temp;
+ if (*s++ == 0)
+ break;
+ }
+ }
+ if (istemp(ap))
+ tfree(ap);
+ if (istemp(y))
+ tfree(y);
+ if (a[2] != 0 && arg3type == STRING)
+ if (istemp(x))
+ tfree(x);
+ x = gettemp();
+ x->tval = NUM;
+ x->fval = n;
+ return(x);
+}
+
+Cell *condexpr(Node **a, int) /* a[0] ? a[1] : a[2] */
+{+ Cell *x;
+
+ x = execute(a[0]);
+ if (istrue(x)) {+ if (istemp(x))
+ tfree(x);
+ x = execute(a[1]);
+ } else {+ if (istemp(x))
+ tfree(x);
+ x = execute(a[2]);
+ }
+ return(x);
+}
+
+Cell *ifstat(Node **a, int) /* if (a[0]) a[1]; else a[2] */
+{+ Cell *x;
+
+ x = execute(a[0]);
+ if (istrue(x)) {+ if (istemp(x))
+ tfree(x);
+ x = execute(a[1]);
+ } else if (a[2] != 0) {+ if (istemp(x))
+ tfree(x);
+ x = execute(a[2]);
+ }
+ return(x);
+}
+
+Cell *whilestat(Node **a, int) /* while (a[0]) a[1] */
+{+ Cell *x;
+
+ for (;;) {+ x = execute(a[0]);
+ if (!istrue(x))
+ return(x);
+ if (istemp(x))
+ tfree(x);
+ x = execute(a[1]);
+ if (isbreak(x)) {+ x = True;
+ return(x);
+ }
+ if (isnext(x) || isexit(x) || isret(x))
+ return(x);
+ if (istemp(x))
+ tfree(x);
+ }
+}
+
+Cell *dostat(Node **a, int) /* do a[0]; while(a[1]) */
+{+ Cell *x;
+
+ for (;;) {+ x = execute(a[0]);
+ if (isbreak(x))
+ return True;
+ if (isnext(x) || isnextfile(x) || isexit(x) || isret(x))
+ return(x);
+ if (istemp(x))
+ tfree(x);
+ x = execute(a[1]);
+ if (!istrue(x))
+ return(x);
+ if (istemp(x))
+ tfree(x);
+ }
+}
+
+Cell *forstat(Node **a, int) /* for (a[0]; a[1]; a[2]) a[3] */
+{+ Cell *x;
+
+ x = execute(a[0]);
+ if (istemp(x))
+ tfree(x);
+ for (;;) {+ if (a[1]!=0) {+ x = execute(a[1]);
+ if (!istrue(x))
+ return(x);
+ else if (istemp(x))
+ tfree(x);
+ }
+ x = execute(a[3]);
+ if (isbreak(x)) /* turn off break */
+ return True;
+ if (isnext(x) || isexit(x) || isret(x))
+ return(x);
+ if (istemp(x))
+ tfree(x);
+ x = execute(a[2]);
+ if (istemp(x))
+ tfree(x);
+ }
+}
+
+Cell *instat(Node **a, int) /* for (a[0] in a[1]) a[2] */
+{+ Cell *x, *vp, *arrayp, *cp, *ncp;
+ Array *tp;
+ int i;
+
+ vp = execute(a[0]);
+ arrayp = execute(a[1]);
+ if (!isarr(arrayp)) {+ return True;
+ }
+ tp = (Array *) arrayp->sval;
+ if (istemp(arrayp))
+ tfree(arrayp);
+ for (i = 0; i < tp->size; i++) { /* this routine knows too much */+ for (cp = tp->tab[i]; cp != nil; cp = ncp) {+ setsval(vp, cp->nval);
+ ncp = cp->cnext;
+ x = execute(a[2]);
+ if (isbreak(x)) {+ if (istemp(vp))
+ tfree(vp);
+ return True;
+ }
+ if (isnext(x) || isexit(x) || isret(x)) {+ if (istemp(vp))
+ tfree(vp);
+ return(x);
+ }
+ if (istemp(x))
+ tfree(x);
+ }
+ }
+ return True;
+}
+
+Cell *bltin(Node **a, int) /* builtin functions. a[0] is type, a[1] is arg list */
+{+ Cell *x, *y;
+ Awkfloat u, tmp;
+ int t;
+ Rune wc;
+ char *p, *buf;
+ char mbc[50];
+ Node *nextarg;
+ Biobuf *fp;
+ void flush_all(void);
+
+ t = ptoi(a[0]);
+ x = execute(a[1]);
+ nextarg = a[1]->nnext;
+ switch (t) {+ case FLENGTH:
+ if (isarr(x))
+ u = ((Array *) x->sval)->nelemt; /* GROT. should be function*/
+ else {+ p = getsval(x);
+ u = (Awkfloat) utfnlen(p, strlen(p));
+ }
+ break;
+ case FLOG:
+ u = errcheck(log(getfval(x)), "log"); break;
+ case FINT:
+ modf(getfval(x), &u); break;
+ case FEXP:
+ u = errcheck(exp(getfval(x)), "exp"); break;
+ case FSQRT:
+ u = errcheck(sqrt(getfval(x)), "sqrt"); break;
+ case FSIN:
+ u = sin(getfval(x)); break;
+ case FCOS:
+ u = cos(getfval(x)); break;
+ case FATAN:
+ if (nextarg == 0) {+ WARNING("atan2 requires two arguments; returning 1.0");+ u = 1.0;
+ } else {+ y = execute(a[1]->nnext);
+ u = atan2(getfval(x), getfval(y));
+ if (istemp(y))
+ tfree(y);
+ nextarg = nextarg->nnext;
+ }
+ break;
+ case FSYSTEM:
+ Bflush(&stdout); /* in case something is buffered already */
+ u = (Awkfloat) system(getsval(x));
+ break;
+ case FRAND:
+ u = frand();
+ break;
+ case FSRAND:
+ if (isrec(x)) /* no argument provided */
+ tmp = (Awkfloat) (truerand() >> 1);
+ else
+ tmp = getfval(x);
+ srand((unsigned long) tmp);
+ u = srand_seed;
+ srand_seed = tmp;
+ break;
+ case FTOUPPER:
+ case FTOLOWER:
+ buf = tostring(getsval(x));
+ if (t == FTOUPPER) {+ for (p = buf; *p; p++)
+ if (islower(*p))
+ *p = toupper(*p);
+ } else {+ for (p = buf; *p; p++)
+ if (isupper(*p))
+ *p = tolower(*p);
+ }
+ if (istemp(x))
+ tfree(x);
+ x = gettemp();
+ setsval(x, buf);
+ free(buf);
+ return x;
+ case FFLUSH:
+ if (isrec(x) || strlen(getsval(x)) == 0) {+ flush_all(); /* fflush() or fflush("") -> all */+ u = 0;
+ } else if ((fp = openfile(FFLUSH, getsval(x))) == nil)
+ u = Beof;
+ else
+ u = Bflush(fp);
+ break;
+ case FUTF:
+ wc = (int)getfval(x);
+ mbc[runetochar(mbc, &wc)] = 0;
+ if (istemp(x))
+ tfree(x);
+ x = gettemp();
+ setsval(x, mbc);
+ return x;
+ default: /* can't happen */
+ FATAL("illegal function type %d", t);+ break;
+ }
+ if (istemp(x))
+ tfree(x);
+ x = gettemp();
+ setfval(x, u);
+ if (nextarg != 0) {+ WARNING("warning: function has too many arguments");+ for ( ; nextarg; nextarg = nextarg->nnext)
+ execute(nextarg);
+ }
+ return(x);
+}
+
+Cell *printstat(Node **a, int) /* print a[0] */
+{+ int r;
+ Node *x;
+ Cell *y;
+ Biobuf *fp;
+
+ if (a[1] == 0) /* a[1] is redirection operator, a[2] is file */
+ fp = &stdout;
+ else
+ fp = redirect(ptoi(a[1]), a[2]);
+ for (x = a[0]; x != nil; x = x->nnext) {+ y = execute(x);
+ Bwrite(fp, getsval(y), strlen(getsval(y)));
+ if (istemp(y))
+ tfree(y);
+ if (x->nnext == nil)
+ r = Bprint(fp, "%s", *ORS);
+ else
+ r = Bprint(fp, "%s", *OFS);
+ if (r < 0)
+ FATAL("write error on %s", filename(fp));+ }
+ if (Bflush(fp) < 0)
+ FATAL("write error on %s", filename(fp));+ return(True);
+}
+
+Cell *nullproc(Node **, int)
+{+ return 0;
+}
+
+
+Biobuf *redirect(int a, Node *b) /* set up all i/o redirections */
+{+ Biobuf *fp;
+ Cell *x;
+ char *fname;
+
+ x = execute(b);
+ fname = getsval(x);
+ fp = openfile(a, fname);
+ if (fp == nil)
+ FATAL("can't open file %s", fname);+ if (istemp(x))
+ tfree(x);
+ return fp;
+}
+
+struct files {+ Biobuf *fp;
+ char *fname;
+ int mode; /* '|', 'a', 'w' => LE/LT, GT */
+} files[FOPEN_MAX] ={+ { nil, "/dev/stdin", LT }, /* watch out: don't free this! */+ { nil, "/dev/stdout", GT },+ { nil, "/dev/stderr", GT }+};
+
+void stdinit(void) /* in case stdin, etc., are not constants */
+{+ files[0].fp = &stdin;
+ files[1].fp = &stdout;
+ files[2].fp = &stderr;
+}
+#define writing(m) ((m) != LT && (m) != LE)
+
+Biobuf *openfile(int a, char *us)
+{+ char *s = us;
+ int i, m, fd;
+ Biobuf *fp = nil;
+
+ if (*s == '\0')
+ FATAL("null file name in print or getline");+ for (i=0; i < FOPEN_MAX; i++)
+ if (files[i].fname && strcmp(s, files[i].fname) == 0) {+ if (a == files[i].mode || (a==APPEND && files[i].mode==GT))
+ return files[i].fp;
+ if (a == FFLUSH) {+ if(!writing(files[i].mode))
+ return nil;
+ return files[i].fp;
+ }
+ }
+ if (a == FFLUSH) /* didn't find it, so don't create it! */
+ return nil;
+
+ for (i=0; i < FOPEN_MAX; i++)
+ if (files[i].fp == 0)
+ break;
+ if (i >= FOPEN_MAX)
+ FATAL("%s makes too many open files", s);+ Bflush(&stdout); /* force a semblance of order */
+ m = a;
+ if (a == GT) {+ fp = Bopen(s, OWRITE);
+ } else if (a == APPEND) {+ fd = open(s, OWRITE);
+ if (fd < 0)
+ fd = create(s, OWRITE, 0666);
+ if (fd >= 0) {+ fp = Bfdopen(fd, OWRITE);
+ if (fp != nil)
+ Bseek(fp, 0LL, 2);
+ m = GT; /* so can mix > and >> */
+ }
+ } else if (a == '|') { /* output pipe */+ fp = popen(s, OWRITE);
+ } else if (a == LE) { /* input pipe */+ fp = popen(s, OREAD);
+ } else if (a == LT) { /* getline <file */+ fp = strcmp(s, "-") == 0 ? &stdin : Bopen(s, OREAD); /* "-" is stdin */
+ } else /* can't happen */
+ FATAL("illegal redirection %d", a);+ if (fp != nil) {+ files[i].fname = tostring(s);
+ files[i].fp = fp;
+ files[i].mode = m;
+ }
+ return fp;
+}
+
+char *filename(Biobuf *fp)
+{+ int i;
+
+ for (i = 0; i < FOPEN_MAX; i++)
+ if (fp == files[i].fp)
+ return files[i].fname;
+ return "???";
+}
+
+Cell *closefile(Node **a, int)
+{+ Cell *x;
+ int i, stat;
+
+ x = execute(a[0]);
+ getsval(x);
+ for (i = 0; i < FOPEN_MAX; i++)
+ if (files[i].fname && strcmp(x->sval, files[i].fname) == 0) {+ if (files[i].mode == '|' || files[i].mode == LE)
+ stat = pclose(files[i].fp);
+ else
+ stat = Bterm(files[i].fp);
+ if (stat == Beof)
+ WARNING( "i/o error occurred closing %s", files[i].fname );
+ if (i > 2) /* don't do /dev/std... */
+ xfree(files[i].fname);
+ files[i].fname = nil; /* watch out for ref thru this */
+ files[i].fp = nil;
+ }
+ if (istemp(x))
+ tfree(x);
+ return(True);
+}
+
+void closeall(void)
+{+ int i, stat;
+
+ for (i = 0; i < FOPEN_MAX; i++)
+ if (files[i].fp) {+ if (files[i].mode == '|' || files[i].mode == LE)
+ stat = pclose(files[i].fp);
+ else
+ stat = Bterm(files[i].fp);
+ if (stat < -1)
+ WARNING( "i/o error occurred while closing %s", files[i].fname );
+ }
+}
+
+void flush_all(void)
+{+ int i;
+ for (i = 0; i < FOPEN_MAX; i++)
+ if (files[i].fp && writing(files[i].mode))
+ Bflush(files[i].fp);
+}
+void backsub(char **pb_ptr, char **sptr_ptr);
+
+Cell *sub(Node **a, int) /* substitute command */
+{+ char *sptr, *pb, *q;
+ Cell *x, *y, *result;
+ char *t, *buf;
+ void *p;
+ int bufsz = recsize;
+
+ if ((buf = (char *) malloc(bufsz)) == nil)
+ FATAL("out of memory in sub");+ x = execute(a[3]); /* target string */
+ t = getsval(x);
+ if (a[0] == 0) /* 0 => a[1] is already-compiled regexpr */
+ p = (void *) a[1]; /* regular expression */
+ else {+ y = execute(a[1]);
+ p = compre(getsval(y));
+ if (istemp(y))
+ tfree(y);
+ }
+ y = execute(a[2]); /* replacement string */
+ result = False;
+ if (pmatch(p, t, t)) {+ sptr = t;
+ adjbuf(&buf, &bufsz, 1+patbeg-sptr, recsize, 0, "sub");
+ pb = buf;
+ while (sptr < patbeg)
+ *pb++ = *sptr++;
+ sptr = getsval(y);
+ while (*sptr != 0) {+ adjbuf(&buf, &bufsz, 5+pb-buf, recsize, &pb, "sub");
+ if (*sptr == '\\') {+ backsub(&pb, &sptr);
+ } else if (*sptr == '&') {+ sptr++;
+ adjbuf(&buf, &bufsz, 1+patlen+pb-buf, recsize, &pb, "sub");
+ for (q = patbeg; q < patbeg+patlen; )
+ *pb++ = *q++;
+ } else
+ *pb++ = *sptr++;
+ }
+ *pb = '\0';
+ sptr = patbeg + patlen;
+ if ((patlen == 0 && *patbeg) || (patlen && *(sptr-1))) {+ adjbuf(&buf, &bufsz, 1+strlen(sptr)+pb-buf, 0, &pb, "sub");
+ while ((*pb++ = *sptr++) != 0)
+ ;
+ }
+ setsval(x, buf); /* BUG: should be able to avoid copy */
+ result = True;;
+ }
+ if (istemp(x))
+ tfree(x);
+ if (istemp(y))
+ tfree(y);
+ free(buf);
+ return result;
+}
+
+Cell *gsub(Node **a, int) /* global substitute */
+{+ Cell *x, *y;
+ char *rptr, *sptr, *t, *pb, *c, *s;
+ char *buf;
+ void *p;
+ int mflag, num;
+ int bufsz = recsize;
+
+ if ((buf = (char *)malloc(bufsz)) == nil)
+ FATAL("out of memory in gsub");+ mflag = 0; /* if mflag == 0, can replace empty string */
+ num = 0;
+ x = execute(a[3]); /* target string */
+ c = t = getsval(x);
+ if (a[0] == 0) /* 0 => a[1] is already-compiled regexpr */
+ p = (void *) a[1]; /* regular expression */
+ else {+ y = execute(a[1]);
+ s = getsval(y);
+ p = compre(s);
+ if (istemp(y))
+ tfree(y);
+ }
+ y = execute(a[2]); /* replacement string */
+ if (pmatch(p, t, c)) {+ pb = buf;
+ rptr = getsval(y);
+ do {+ if (patlen == 0 && *patbeg != 0) { /* matched empty string */+ if (mflag == 0) { /* can replace empty */+ num++;
+ sptr = rptr;
+ while (*sptr != 0) {+ adjbuf(&buf, &bufsz, 5+pb-buf, recsize, &pb, "gsub");
+ if (*sptr == '\\') {+ backsub(&pb, &sptr);
+ } else if (*sptr == '&') {+ char *q;
+ sptr++;
+ adjbuf(&buf, &bufsz, 1+patlen+pb-buf, recsize, &pb, "gsub");
+ for (q = patbeg; q < patbeg+patlen; )
+ *pb++ = *q++;
+ } else
+ *pb++ = *sptr++;
+ }
+ }
+ if (*c == 0) /* at end */
+ break;
+ adjbuf(&buf, &bufsz, 2+pb-buf, recsize, &pb, "gsub");
+ *pb++ = *c++;
+ mflag = 0;
+ }
+ else { /* matched nonempty string */+ num++;
+ sptr = c;
+ adjbuf(&buf, &bufsz, 1+(patbeg-sptr)+pb-buf, recsize, &pb, "gsub");
+ while (sptr < patbeg)
+ *pb++ = *sptr++;
+ sptr = rptr;
+ while (*sptr != 0) {+ adjbuf(&buf, &bufsz, 5+pb-buf, recsize, &pb, "gsub");
+ if (*sptr == '\\') {+ backsub(&pb, &sptr);
+ } else if (*sptr == '&') {+ char *q;
+ sptr++;
+ adjbuf(&buf, &bufsz, 1+patlen+pb-buf, recsize, &pb, "gsub");
+ for (q = patbeg; q < patbeg+patlen; )
+ *pb++ = *q++;
+ } else
+ *pb++ = *sptr++;
+ }
+ c = patbeg + patlen;
+ if (c[-1] == 0){+ c--;
+ break;
+ }
+ if (*c == 0)
+ break;
+ mflag = 1;
+ }
+ } while (pmatch(p, t, c));
+ sptr = c;
+ adjbuf(&buf, &bufsz, 1+strlen(sptr)+pb-buf, 0, &pb, "gsub");
+ while ((*pb++ = *sptr++) != 0)
+ ;
+ setsval(x, buf); /* BUG: should be able to avoid copy + free */
+ }
+ if (istemp(x))
+ tfree(x);
+ if (istemp(y))
+ tfree(y);
+ x = gettemp();
+ x->tval = NUM;
+ x->fval = num;
+ free(buf);
+ return(x);
+}
+
+void backsub(char **pb_ptr, char **sptr_ptr) /* handle \\& variations */
+{ /* sptr[0] == '\\' */+ char *pb = *pb_ptr, *sptr = *sptr_ptr;
+
+ if (sptr[1] == '\\') {+ if (sptr[2] == '\\' && sptr[3] == '&') { /* \\\& -> \& */+ *pb++ = '\\';
+ *pb++ = '&';
+ sptr += 4;
+ } else if (sptr[2] == '&') { /* \\& -> \ + matched */+ *pb++ = '\\';
+ sptr += 2;
+ } else { /* \\x -> \\x */+ *pb++ = *sptr++;
+ *pb++ = *sptr++;
+ }
+ } else if (sptr[1] == '&') { /* literal & */+ sptr++;
+ *pb++ = *sptr++;
+ } else /* literal \ */
+ *pb++ = *sptr++;
+
+ *pb_ptr = pb;
+ *sptr_ptr = sptr;
+}
--- /dev/null
+++ b/tran.c
@@ -1,0 +1,449 @@
+/****************************************************************
+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 <u.h>
+#include <libc.h>
+#include <ctype.h>
+#include <bio.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 *AARGC; /* 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];
+
+ AARGC = &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++) {+ sprint(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(void) /* set up ENVIRON variable */
+{+ int fd, i, n;
+ char *k, *v;
+ Dir *buf;
+
+ ENVtab = makesymtab(NSYMTAB);
+ if ((fd = open("/env", OREAD)) < 0)+ return;
+
+ buf = nil;
+ while((n = dirread(fd, &buf)) > 0) {+ for (i = 0; i < n; i++) {+ k = buf[i].name;
+ if(strncmp(k, "fn#", 3) == 0)
+ continue;
+ if ((v = getenv(k)) == nil)
+ continue;
+ if (is_number(v))
+ setsymtab(k, v, atof(v), STR|NUM, ENVtab);
+ else
+ setsymtab(k, v, 0.0, STR, ENVtab);
+ free(v);
+ }
+ free(buf);
+ buf = nil;
+ }
+
+ close(fd);
+}
+
+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 == nil || tp == nil)
+ FATAL("out of space in makesymtab");+ ap->nelemt = 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 == nil)
+ return;
+ for (i = 0; i < tp->size; i++) {+ for (cp = tp->tab[i]; cp != nil; 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 = nil;
+ int h;
+
+ tp = (Array *) ap->sval;
+ h = hash(s, tp->size);
+ for (p = tp->tab[h]; p != nil; prev = p, p = p->cnext)
+ if (strcmp(s, p->nval) == 0) {+ if (prev == nil) /* 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->nelemt--;
+ return;
+ }
+}
+
+Cell *setsymtab(char *n, char *s, Awkfloat f, unsigned t, Array *tp)
+{+ int h;
+ Cell *p;
+
+ if (n != nil && (p = lookup(n, tp)) != nil) {+ dprint( ("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 == nil)
+ FATAL("out of space for symbol table at %s", n);+ p->nval = tostring(n);
+ p->fval = f;
+ if(tp == symtab && strcmp(n, "ENVIRON") == 0 && !safe) {+ envinit();
+ p->sval = (char *) ENVtab;
+ p->tval = ARR;
+ } else {+ p->sval = s ? tostring(s) : tostring("");+ p->tval = t;
+ }
+ p->csub = CUNK;
+ p->ctype = OCELL;
+ tp->nelemt++;
+ if (tp->nelemt > FULLTAB * tp->size)
+ rehash(tp);
+ h = hash(n, tp->size);
+ p->cnext = tp->tab[h];
+ tp->tab[h] = p;
+ dprint( ("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 == nil) /* 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 != nil; p = p->cnext)
+ if (strcmp(s, p->nval) == 0)
+ return(p); /* found it */
+ return(nil); /* 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);
+ dprint( ("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 */
+ dprint( ("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;
+
+ dprint( ("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);
+ dprint( ("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;
+ dprint( ("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 */
+ }
+ dprint( ("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 */
+ sprint(s, "%.30g", vp->fval);
+ else
+ sprint(s, *CONVFMT, vp->fval);
+ vp->sval = tostring(s);
+ vp->tval &= ~DONTFREE;
+ vp->tval |= STR;
+ }
+ dprint( ("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 == nil)
+ 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)) == nil)
+ 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;
+}
--
⑨