mirrors/cosmopolitan
1
0
Fork 0
mirror of https://github.com/jart/cosmopolitan.git synced 2025-02-07 06:53:33 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Upgrade the One True Awk

Browse source
This commit is contained in:
Justine Tunney 2024-04-06 19:21:48 -07:00
parent b9d6e6e348
commit 49a32136f8
No known key found for this signature in database
GPG key ID: BE714B4575D6E328
15 changed files with 5280 additions and 4322 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

3
third_party/awk/BUILD.mk vendored
View file

@ -31,8 +31,7 @@ THIRD_PARTY_AWK_A_DEPS := \
$(call uniq,$(foreach x,$(THIRD_PARTY_AWK_A_DIRECTDEPS),$($(x))))
THIRD_PARTY_AWK_CHECKS = \
$(THIRD_PARTY_AWK_A).pkg \
$(THIRD_PARTY_AWK_HDRS:%=o/$(MODE)/%.ok)
$(THIRD_PARTY_AWK_A).pkg
$(THIRD_PARTY_AWK_A): \
third_party/awk/ \

5
third_party/awk/README.cosmo vendored
View file

@ -10,8 +10,7 @@ SOURCE
https://github.com/onetrueawk/awk
commit b92d8cecd132ce8e02a373e28dd42e6be34d3d59
Author: ozan yigit <ozan.yigit@gmail.com>
Date: Mon May 30 11:34:52 2022 -0400
commit 2bab10b60b3f4d3bbefdcb60410655f317d1a452
date Thu Mar 14 14:25:30 2024 +0200
added YACC definition for byacc.

244
third_party/awk/awk.h vendored
View file

@ -1,10 +1,35 @@
#ifndef COSMOPOLITAN_THIRD_PARTY_AWK_AWK_H_
#define COSMOPOLITAN_THIRD_PARTY_AWK_AWK_H_
#include "libc/assert.h"
#include "libc/limits.h"
#include "libc/literal.h"
#include "libc/stdio/stdio.h"
COSMOPOLITAN_C_START_
/****************************************************************
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 <assert.h>
#include <stdint.h>
#include <stdbool.h>
#if __STDC_VERSION__ <= 199901L
#define noreturn
#else
#include <stdnoreturn.h>
#endif
typedef double Awkfloat;
@ -12,7 +37,7 @@ typedef double Awkfloat;
typedef unsigned char uschar;
#define xfree(a) { if ((a) != NULL) { free((void *)(intptr_t)(a)); (a) = NULL; } }
#define xfree(a) { free((void *)(intptr_t)(a)); (a) = NULL; }
/*
* We sometimes cheat writing read-only pointers to NUL-terminate them
* and then put back the original value
@ -39,6 +64,8 @@ extern bool safe; /* false => unsafe, true => safe */
#define RECSIZE (8 * 1024) /* sets limit on records, fields, etc., etc. */
extern int recsize; /* size of current record, orig RECSIZE */
extern size_t awk_mb_cur_max; /* max size of a multi-byte character */
extern char EMPTY[]; /* this avoid -Wwritable-strings issues */
extern char **FS;
extern char **RS;
@ -53,6 +80,8 @@ extern char **SUBSEP;
extern Awkfloat *RSTART;
extern Awkfloat *RLENGTH;
extern bool CSV; /* true for csv input */
extern char *record; /* points to $0 */
extern int lineno; /* line number in awk program */
extern int errorflag; /* 1 if error has occurred */
@ -200,7 +229,8 @@ extern int pairstack[], paircnt;
/* structures used by regular expression matching machinery, mostly b.c: */
#define NCHARS (256+3) /* 256 handles 8-bit chars; 128 does 7-bit */
#define NCHARS (1256+3) /* 256 handles 8-bit chars; 128 does 7-bit */
/* BUG: some overflows (caught) if we use 256 */
/* watch out in match(), etc. */
#define HAT (NCHARS+2) /* matches ^ in regular expr */
#define NSTATES 32
@ -211,12 +241,24 @@ typedef struct rrow {
int i;
Node *np;
uschar *up;
int *rp; /* rune representation of char class */
} lval; /* because Al stores a pointer in it! */
int *lfollow;
} rrow;
typedef struct gtte { /* gototab entry */
unsigned int ch;
unsigned int state;
} gtte;
typedef struct gtt { /* gototab */
size_t allocated;
size_t inuse;
gtte *entries;
} gtt;
typedef struct fa {
unsigned int **gototab;
gtt *gototab;
uschar *out;
uschar *restr;
int **posns;
@ -229,185 +271,5 @@ typedef struct fa {
struct rrow re[1]; /* variable: actual size set by calling malloc */
} fa;
extern int yywrap(void);
extern void setfname(Cell *);
extern int constnode(Node *);
extern char *strnode(Node *);
extern Node *notnull(Node *);
extern int yyparse(void);
extern int yylex(void);
extern void startreg(void);
extern int input(void);
extern void unput(int);
extern void unputstr(const char *);
extern int yylook(void);
extern int yyback(int *, int);
extern int yyinput(void);
extern fa *makedfa(const char *, bool);
extern fa *mkdfa(const char *, bool);
extern int makeinit(fa *, bool);
extern void penter(Node *);
extern void freetr(Node *);
extern int hexstr(const uschar **);
extern int quoted(const uschar **);
extern char *cclenter(const char *);
extern wontreturn void overflo(const char *);
extern void cfoll(fa *, Node *);
extern int first(Node *);
extern void follow(Node *);
extern int member(int, const char *);
extern int match(fa *, const char *);
extern int pmatch(fa *, const char *);
extern int nematch(fa *, const char *);
extern bool fnematch(fa *, FILE *, char **, int *, int);
extern Node *reparse(const char *);
extern Node *regexp(void);
extern Node *primary(void);
extern Node *concat(Node *);
extern Node *alt(Node *);
extern Node *unary(Node *);
extern int relex(void);
extern int cgoto(fa *, int, int);
extern void freefa(fa *);
extern int pgetc(void);
extern char *cursource(void);
extern Node *nodealloc(int);
extern Node *exptostat(Node *);
extern Node *node1(int, Node *);
extern Node *node2(int, Node *, Node *);
extern Node *node3(int, Node *, Node *, Node *);
extern Node *node4(int, Node *, Node *, Node *, Node *);
extern Node *stat3(int, Node *, Node *, Node *);
extern Node *op2(int, Node *, Node *);
extern Node *op1(int, Node *);
extern Node *stat1(int, Node *);
extern Node *op3(int, Node *, Node *, Node *);
extern Node *op4(int, Node *, Node *, Node *, Node *);
extern Node *stat2(int, Node *, Node *);
extern Node *stat4(int, Node *, Node *, Node *, Node *);
extern Node *celltonode(Cell *, int);
extern Node *rectonode(void);
extern Node *makearr(Node *);
extern Node *pa2stat(Node *, Node *, Node *);
extern Node *linkum(Node *, Node *);
extern void defn(Cell *, Node *, Node *);
extern int isarg(const char *);
extern const char *tokname(int);
extern Cell *(*proctab[])(Node **, int);
extern int ptoi(void *);
extern Node *itonp(int);
extern void syminit(void);
extern void arginit(int, char **);
extern void envinit(char **);
extern Array *makesymtab(int);
extern void freesymtab(Cell *);
extern void freeelem(Cell *, const char *);
extern Cell *setsymtab(const char *, const char *, double, unsigned int, Array *);
extern int hash(const char *, int);
extern void rehash(Array *);
extern Cell *lookup(const char *, Array *);
extern double setfval(Cell *, double);
extern void funnyvar(Cell *, const char *);
extern char *setsval(Cell *, const char *);
extern double getfval(Cell *);
extern char *getsval(Cell *);
extern char *getpssval(Cell *); /* for print */
extern char *tostring(const char *);
extern char *tostringN(const char *, size_t);
extern char *qstring(const char *, int);
extern Cell *catstr(Cell *, Cell *);
extern void recinit(unsigned int);
extern void initgetrec(void);
extern void makefields(int, int);
extern void growfldtab(int n);
extern void savefs(void);
extern int getrec(char **, int *, bool);
extern void nextfile(void);
extern int readrec(char **buf, int *bufsize, FILE *inf, bool isnew);
extern char *getargv(int);
extern void setclvar(char *);
extern void fldbld(void);
extern void cleanfld(int, int);
extern void newfld(int);
extern void setlastfld(int);
extern int refldbld(const char *, const char *);
extern void recbld(void);
extern Cell *fieldadr(int);
extern void yyerror(const char *);
extern void bracecheck(void);
extern void bcheck2(int, int, int);
extern void SYNTAX(const char *, ...)
__attribute__((__format__(__printf__, 1, 2)));
extern wontreturn void FATAL(const char *, ...)
__attribute__((__format__(__printf__, 1, 2)));
extern void WARNING(const char *, ...)
__attribute__((__format__(__printf__, 1, 2)));
extern void error(void);
extern void eprint(void);
extern void bclass(int);
extern double errcheck(double, const char *);
extern int isclvar(const char *);
extern bool is_valid_number(const char *s, bool trailing_stuff_ok,
bool *no_trailing, double *result);
#define is_number(s, val) is_valid_number(s, false, NULL, val)
extern int adjbuf(char **pb, int *sz, int min, int q, char **pbp, const char *what);
extern void run(Node *);
extern Cell *execute(Node *);
extern Cell *program(Node **, int);
extern Cell *call(Node **, int);
extern Cell *copycell(Cell *);
extern Cell *arg(Node **, int);
extern Cell *jump(Node **, int);
extern Cell *awkgetline(Node **, int);
extern Cell *getnf(Node **, int);
extern Cell *array(Node **, int);
extern Cell *awkdelete(Node **, int);
extern Cell *intest(Node **, int);
extern Cell *matchop(Node **, int);
extern Cell *boolop(Node **, int);
extern Cell *relop(Node **, int);
extern void tfree(Cell *);
extern Cell *gettemp(void);
extern Cell *field(Node **, int);
extern Cell *indirect(Node **, int);
extern Cell *substr(Node **, int);
extern Cell *sindex(Node **, int);
extern int format(char **, int *, const char *, Node *);
extern Cell *awksprintf(Node **, int);
extern Cell *awkprintf(Node **, int);
extern Cell *arith(Node **, int);
extern double ipow(double, int);
extern Cell *incrdecr(Node **, int);
extern Cell *assign(Node **, int);
extern Cell *cat(Node **, int);
extern Cell *pastat(Node **, int);
extern Cell *dopa2(Node **, int);
extern Cell *split(Node **, int);
extern Cell *condexpr(Node **, int);
extern Cell *ifstat(Node **, int);
extern Cell *whilestat(Node **, int);
extern Cell *dostat(Node **, int);
extern Cell *forstat(Node **, int);
extern Cell *instat(Node **, int);
extern Cell *bltin(Node **, int);
extern Cell *printstat(Node **, int);
extern Cell *nullproc(Node **, int);
extern FILE *redirect(int, Node *);
extern FILE *openfile(int, const char *, bool *);
extern const char *filename(FILE *);
extern Cell *closefile(Node **, int);
extern void closeall(void);
extern Cell *sub(Node **, int);
extern Cell *gsub(Node **, int);
extern const char *flags2str(int flags);
COSMOPOLITAN_C_END_
#endif /* COSMOPOLITAN_THIRD_PARTY_AWK_AWK_H_ */
#include "proto.h"

6663
third_party/awk/awkgram.tab.c vendored
View file

File diff suppressed because it is too large Load diff

252
third_party/awk/awkgram.tab.h vendored
View file

@ -1,113 +1,145 @@
#ifndef COSMOPOLITAN_THIRD_PARTY_AWK_AWKGRAM_TAB_H_
#define COSMOPOLITAN_THIRD_PARTY_AWK_AWKGRAM_TAB_H_
#include "third_party/awk/awk.h"
COSMOPOLITAN_C_START_
#ifndef YY_YY_AWKGRAM_TAB_H_INCLUDED
# define YY_YY_AWKGRAM_TAB_H_INCLUDED
/* Debug traces. */
#ifndef YYDEBUG
# define YYDEBUG 0
#endif
#if YYDEBUG
extern int yydebug;
#endif
/* Token kinds. */
#ifndef YYTOKENTYPE
# define YYTOKENTYPE
enum yytokentype
{
YYEMPTY = -2,
YYEOF = 0, /* "end of file" */
YYerror = 256, /* error */
YYUNDEF = 257, /* "invalid token" */
FIRSTTOKEN = 258, /* FIRSTTOKEN */
PROGRAM = 259, /* PROGRAM */
PASTAT = 260, /* PASTAT */
PASTAT2 = 261, /* PASTAT2 */
XBEGIN = 262, /* XBEGIN */
XEND = 263, /* XEND */
NL = 264, /* NL */
ARRAY = 265, /* ARRAY */
MATCH = 266, /* MATCH */
NOTMATCH = 267, /* NOTMATCH */
MATCHOP = 268, /* MATCHOP */
FINAL = 269, /* FINAL */
DOT = 270, /* DOT */
ALL = 271, /* ALL */
CCL = 272, /* CCL */
NCCL = 273, /* NCCL */
CHAR = 274, /* CHAR */
OR = 275, /* OR */
STAR = 276, /* STAR */
QUEST = 277, /* QUEST */
PLUS = 278, /* PLUS */
EMPTYRE = 279, /* EMPTYRE */
ZERO = 280, /* ZERO */
AND = 281, /* AND */
BOR = 282, /* BOR */
APPEND = 283, /* APPEND */
EQ = 284, /* EQ */
GE = 285, /* GE */
GT = 286, /* GT */
LE = 287, /* LE */
LT = 288, /* LT */
NE = 289, /* NE */
IN = 290, /* IN */
ARG = 291, /* ARG */
BLTIN = 292, /* BLTIN */
BREAK = 293, /* BREAK */
CLOSE = 294, /* CLOSE */
CONTINUE = 295, /* CONTINUE */
DELETE = 296, /* DELETE */
DO = 297, /* DO */
EXIT = 298, /* EXIT */
FOR = 299, /* FOR */
FUNC = 300, /* FUNC */
SUB = 301, /* SUB */
GSUB = 302, /* GSUB */
IF = 303, /* IF */
INDEX = 304, /* INDEX */
LSUBSTR = 305, /* LSUBSTR */
MATCHFCN = 306, /* MATCHFCN */
NEXT = 307, /* NEXT */
NEXTFILE = 308, /* NEXTFILE */
ADD = 309, /* ADD */
MINUS = 310, /* MINUS */
MULT = 311, /* MULT */
DIVIDE = 312, /* DIVIDE */
MOD = 313, /* MOD */
ASSIGN = 314, /* ASSIGN */
ASGNOP = 315, /* ASGNOP */
ADDEQ = 316, /* ADDEQ */
SUBEQ = 317, /* SUBEQ */
MULTEQ = 318, /* MULTEQ */
DIVEQ = 319, /* DIVEQ */
MODEQ = 320, /* MODEQ */
POWEQ = 321, /* POWEQ */
PRINT = 322, /* PRINT */
PRINTF = 323, /* PRINTF */
SPRINTF = 324, /* SPRINTF */
ELSE = 325, /* ELSE */
INTEST = 326, /* INTEST */
CONDEXPR = 327, /* CONDEXPR */
POSTINCR = 328, /* POSTINCR */
PREINCR = 329, /* PREINCR */
POSTDECR = 330, /* POSTDECR */
PREDECR = 331, /* PREDECR */
VAR = 332, /* VAR */
IVAR = 333, /* IVAR */
VARNF = 334, /* VARNF */
CALL = 335, /* CALL */
NUMBER = 336, /* NUMBER */
STRING = 337, /* STRING */
REGEXPR = 338, /* REGEXPR */
GETLINE = 339, /* GETLINE */
RETURN = 340, /* RETURN */
SPLIT = 341, /* SPLIT */
SUBSTR = 342, /* SUBSTR */
WHILE = 343, /* WHILE */
CAT = 344, /* CAT */
NOT = 345, /* NOT */
UMINUS = 346, /* UMINUS */
UPLUS = 347, /* UPLUS */
POWER = 348, /* POWER */
DECR = 349, /* DECR */
INCR = 350, /* INCR */
INDIRECT = 351, /* INDIRECT */
LASTTOKEN = 352 /* LASTTOKEN */
};
typedef enum yytokentype yytoken_kind_t;
#endif
/* Value type. */
#if ! defined YYSTYPE && ! defined YYSTYPE_IS_DECLARED
union YYSTYPE
{
#line 41 "awkgram.y"
Node *p;
Cell *cp;
int i;
char *s;
#line 168 "awkgram.tab.h"
};
typedef union YYSTYPE YYSTYPE;
# define YYSTYPE_IS_TRIVIAL 1
# define YYSTYPE_IS_DECLARED 1
#endif
#define FIRSTTOKEN 257
#define PROGRAM 258
#define PASTAT 259
#define PASTAT2 260
#define XBEGIN 261
#define XEND 262
#define NL 263
#define ARRAY 264
#define MATCH 265
#define NOTMATCH 266
#define MATCHOP 267
#define FINAL 268
#define DOT 269
#define ALL 270
#define CCL 271
#define NCCL 272
#define CHAR 273
#define OR 274
#define STAR 275
#define QUEST 276
#define PLUS 277
#define EMPTYRE 278
#define ZERO 279
#define AND 280
#define BOR 281
#define APPEND 282
#define EQ 283
#define GE 284
#define GT 285
#define LE 286
#define LT 287
#define NE 288
#define IN 289
#define ARG 290
#define BLTIN 291
#define BREAK 292
#define CLOSE 293
#define CONTINUE 294
#define DELETE 295
#define DO 296
#define EXIT 297
#define FOR 298
#define FUNC 299
#define SUB 300
#define GSUB 301
#define IF 302
#define INDEX 303
#define LSUBSTR 304
#define MATCHFCN 305
#define NEXT 306
#define NEXTFILE 307
#define ADD 308
#define MINUS 309
#define MULT 310
#define DIVIDE 311
#define MOD 312
#define ASSIGN 313
#define ASGNOP 314
#define ADDEQ 315
#define SUBEQ 316
#define MULTEQ 317
#define DIVEQ 318
#define MODEQ 319
#define POWEQ 320
#define PRINT 321
#define PRINTF 322
#define SPRINTF 323
#define ELSE 324
#define INTEST 325
#define CONDEXPR 326
#define POSTINCR 327
#define PREINCR 328
#define POSTDECR 329
#define PREDECR 330
#define VAR 331
#define IVAR 332
#define VARNF 333
#define CALL 334
#define NUMBER 335
#define STRING 336
#define REGEXPR 337
#define GETLINE 338
#define RETURN 339
#define SPLIT 340
#define SUBSTR 341
#define WHILE 342
#define CAT 343
#define NOT 344
#define UMINUS 345
#define UPLUS 346
#define POWER 347
#define DECR 348
#define INCR 349
#define INDIRECT 350
#define LASTTOKEN 351
#ifndef YYSTYPE_DEFINED
#define YYSTYPE_DEFINED
typedef union {
Node *p;
Cell *cp;
int i;
char *s;
} YYSTYPE;
#endif /* YYSTYPE_DEFINED */
extern YYSTYPE yylval;
COSMOPOLITAN_C_END_
#endif /* COSMOPOLITAN_THIRD_PARTY_AWK_AWKGRAM_TAB_H_ */
int yyparse (void);
#endif /* !YY_YY_AWKGRAM_TAB_H_INCLUDED */

511
third_party/awk/b.c vendored
View file

@ -1,39 +1,39 @@
/*-*- mode:c;indent-tabs-mode:t;c-basic-offset:8;tab-width:8;coding:utf-8 -*-│
│ vi: set noet ft=c ts=8 sw=8 fenc=utf-8 :vi │
╚──────────────────────────────────────────────────────────────────────────────╝
│ │
│ Copyright (C) Lucent Technologies 1997 │
│ All Rights Reserved │
│ │
│ Permission to use, copy, modify, and distribute this software and │
│ its documentation for any purpose and without fee is hereby │
│ granted, provided that the above copyright notice appear in all │
│ copies and that both that the copyright notice and this │
│ permission notice and warranty disclaimer appear in supporting │
│ documentation, and that the name Lucent Technologies or any of │
│ its entities not be used in advertising or publicity pertaining │
│ to distribution of the software without specific, written prior │
│ permission. │
│ │
│ LUCENT DISCLAIMS ALL WARRANTIES WITH REGARD TO THIS SOFTWARE, │
│ INCLUDING ALL IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS. │
│ IN NO EVENT SHALL LUCENT OR ANY OF ITS ENTITIES BE LIABLE FOR ANY │
│ SPECIAL, INDIRECT OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES │
│ WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER │
│ IN AN ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, │
│ ARISING OUT OF OR IN CONNECTION WITH THE USE OR PERFORMANCE OF │
│ THIS SOFTWARE. │
│ │
╚─────────────────────────────────────────────────────────────────────────────*/
#define DEBUG
#include "libc/calls/calls.h"
#include "libc/mem/mem.h"
#include "libc/str/str.h"
#include "third_party/awk/awk.h"
#include "third_party/awk/awkgram.tab.h"
/****************************************************************
Copyright (C) Lucent Technologies 1997
All Rights Reserved
Permission to use, copy, modify, and distribute this software and
its documentation for any purpose and without fee is hereby
granted, provided that the above copyright notice appear in all
copies and that both that the copyright notice and this
permission notice and warranty disclaimer appear in supporting
documentation, and that the name Lucent Technologies or any of
its entities not be used in advertising or publicity pertaining
to distribution of the software without specific, written prior
permission.
LUCENT DISCLAIMS ALL WARRANTIES WITH REGARD TO THIS SOFTWARE,
INCLUDING ALL IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS.
IN NO EVENT SHALL LUCENT OR ANY OF ITS ENTITIES BE LIABLE FOR ANY
SPECIAL, INDIRECT OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES
WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER
IN AN ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION,
ARISING OUT OF OR IN CONNECTION WITH THE USE OR PERFORMANCE OF
THIS SOFTWARE.
****************************************************************/
/* lasciate ogne speranza, voi ch'intrate. */
#define DEBUG
#include <ctype.h>
#include <limits.h>
#include <stdio.h>
#include <string.h>
#include <stdlib.h>
#include "awk.h"
#include "awkgram.tab.h"
#define MAXLIN 22
#define type(v) (v)->nobj /* badly overloaded here */
@ -80,6 +80,44 @@ int patlen;
fa *fatab[NFA];
int nfatab = 0; /* entries in fatab */
extern int u8_nextlen(const char *s);
/* utf-8 mechanism:
For most of Awk, utf-8 strings just "work", since they look like
null-terminated sequences of 8-bit bytes.
Functions like length(), index(), and substr() have to operate
in units of utf-8 characters. The u8_* functions in run.c
handle this.
Regular expressions are more complicated, since the basic
mechanism of the goto table used 8-bit byte indices into the
gototab entries to compute the next state. Unicode is a lot
bigger, so the gototab entries are now structs with a character
and a next state. These are sorted by code point and binary
searched.
Throughout the RE mechanism in b.c, utf-8 characters are
converted to their utf-32 value. This mostly shows up in
cclenter, which expands character class ranges like a-z and now
alpha-omega. The size of a gototab array is still about 256.
This should be dynamic, but for now things work ok for a single
code page of Unicode, which is the most likely case.
The code changes are localized in run.c and b.c. I have added a
handful of functions to somewhat better hide the implementation,
but a lot more could be done.
*/
static int entry_cmp(const void *l, const void *r);
static int get_gototab(fa*, int, int);
static int set_gototab(fa*, int, int, int);
static void clear_gototab(fa*, int);
extern int u8_rune(int *, const char *);
static int *
intalloc(size_t n, const char *f)
{
@ -105,7 +143,7 @@ resizesetvec(const char *f)
static void
resize_state(fa *f, int state)
{
unsigned int **p;
gtt *p;
uschar *p2;
int **p3;
int i, new_count;
@ -115,7 +153,7 @@ resize_state(fa *f, int state)
new_count = state + 10; /* needs to be tuned */
p = (unsigned int **) realloc(f->gototab, new_count * sizeof(f->gototab[0]));
p = (gtt *) realloc(f->gototab, new_count * sizeof(gtt));
if (p == NULL)
goto out;
f->gototab = p;
@ -131,10 +169,12 @@ resize_state(fa *f, int state)
f->posns = p3;
for (i = f->state_count; i < new_count; ++i) {
f->gototab[i] = (unsigned int *) calloc(NCHARS, sizeof(**f->gototab));
if (f->gototab[i] == NULL)
f->gototab[i].entries = (gtte *) calloc(NCHARS, sizeof(gtte));
if (f->gototab[i].entries == NULL)
goto out;
f->out[i] = 0;
f->gototab[i].allocated = NCHARS;
f->gototab[i].inuse = 0;
f->out[i] = 0;
f->posns[i] = NULL;
}
f->state_count = new_count;
@ -230,8 +270,7 @@ int makeinit(fa *f, bool anchor)
}
if ((f->posns[2])[1] == f->accept)
f->out[2] = 1;
for (i = 0; i < NCHARS; i++)
f->gototab[2][i] = 0;
clear_gototab(f, 2);
f->curstat = cgoto(f, 2, HAT);
if (anchor) {
*f->posns[2] = k-1; /* leave out position 0 */
@ -300,14 +339,14 @@ void freetr(Node *p) /* free parse tree */
/* in the parsing of regular expressions, metacharacters like . have */
/* to be seen literally; \056 is not a metacharacter. */
int hexstr(const uschar **pp) /* find and eval hex string at pp, return new p */
int hexstr(const uschar **pp, int max) /* find and eval hex string at pp, return new p */
{ /* only pick up one 8-bit byte (2 chars) */
const uschar *p;
int n = 0;
int i;
for (i = 0, p = *pp; i < 2 && isxdigit(*p); i++, p++) {
if (isdigit(*p))
for (i = 0, p = *pp; i < max && isxdigit(*p); i++, p++) {
if (isdigit((int) *p))
n = 16 * n + *p - '0';
else if (*p >= 'a' && *p <= 'f')
n = 16 * n + *p - 'a' + 10;
@ -318,6 +357,8 @@ int hexstr(const uschar **pp) /* find and eval hex string at pp, return new p */
return n;
}
#define isoctdigit(c) ((c) >= '0' && (c) <= '7') /* multiple use of arg */
int quoted(const uschar **pp) /* pick up next thing after a \\ */
@ -326,24 +367,28 @@ int quoted(const uschar **pp) /* pick up next thing after a \\ */
const uschar *p = *pp;
int c;
if ((c = *p++) == 't')
/* BUG: should advance by utf-8 char even if makes no sense */
if ((c = *p++) == 't') {
c = '\t';
else if (c == 'n')
} else if (c == 'n') {
c = '\n';
else if (c == 'f')
} else if (c == 'f') {
c = '\f';
else if (c == 'r')
} else if (c == 'r') {
c = '\r';
else if (c == 'b')
} else if (c == 'b') {
c = '\b';
else if (c == 'v')
} else if (c == 'v') {
c = '\v';
else if (c == 'a')
} else if (c == 'a') {
c = '\a';
else if (c == '\\')
} else if (c == '\\') {
c = '\\';
else if (c == 'x') { /* hexadecimal goo follows */
c = hexstr(&p); /* this adds a null if number is invalid */
} else if (c == 'x') { /* 2 hex digits follow */
c = hexstr(&p, 2); /* this adds a null if number is invalid */
} else if (c == 'u') { /* unicode char number up to 8 hex digits */
c = hexstr(&p, 8);
} else if (isoctdigit(c)) { /* \d \dd \ddd */
int n = c - '0';
if (isoctdigit(*p)) {
@ -358,50 +403,67 @@ int quoted(const uschar **pp) /* pick up next thing after a \\ */
return c;
}
char *cclenter(const char *argp) /* add a character class */
int *cclenter(const char *argp) /* add a character class */
{
int i, c, c2;
const uschar *op, *p = (const uschar *) argp;
uschar *bp;
static uschar *buf = NULL;
int n;
const uschar *p = (const uschar *) argp;
int *bp, *retp;
static int *buf = NULL;
static int bufsz = 100;
op = p;
if (buf == NULL && (buf = (uschar *) malloc(bufsz)) == NULL)
if (buf == NULL && (buf = (int *) calloc(bufsz, sizeof(int))) == NULL)
FATAL("out of space for character class [%.10s...] 1", p);
bp = buf;
for (i = 0; (c = *p++) != 0; ) {
for (i = 0; *p != 0; ) {
n = u8_rune(&c, (const char *) p);
p += n;
if (c == '\\') {
c = quoted(&p);
} else if (c == '-' && i > 0 && bp[-1] != 0) {
if (*p != 0) {
c = bp[-1];
c2 = *p++;
/* c2 = *p++; */
n = u8_rune(&c2, (const char *) p);
p += n;
if (c2 == '\\')
c2 = quoted(&p);
c2 = quoted(&p); /* BUG: sets p, has to be u8 size */
if (c > c2) { /* empty; ignore */
bp--;
i--;
continue;
}
while (c < c2) {
if (!adjbuf((char **) &buf, &bufsz, bp-buf+2, 100, (char **) &bp, "cclenter1"))
FATAL("out of space for character class [%.10s...] 2", p);
if (i >= bufsz) {
bufsz *= 2;
buf = (int *) realloc(buf, bufsz * sizeof(int));
if (buf == NULL)
FATAL("out of space for character class [%.10s...] 2", p);
bp = buf + i;
}
*bp++ = ++c;
i++;
}
continue;
}
}
if (!adjbuf((char **) &buf, &bufsz, bp-buf+2, 100, (char **) &bp, "cclenter2"))
FATAL("out of space for character class [%.10s...] 3", p);
if (i >= bufsz) {
bufsz *= 2;
buf = (int *) realloc(buf, bufsz * sizeof(int));
if (buf == NULL)
FATAL("out of space for character class [%.10s...] 2", p);
bp = buf + i;
}
*bp++ = c;
i++;
}
*bp = 0;
DPRINTF("cclenter: in = |%s|, out = |%s|\n", op, buf);
xfree(op);
return (char *) tostring((char *) buf);
/* DPRINTF("cclenter: in = |%s|, out = |%s|\n", op, buf); BUG: can't print array of int */
/* xfree(op); BUG: what are we freeing here? */
retp = (int *) calloc(bp-buf+1, sizeof(int));
for (i = 0; i < bp-buf+1; i++)
retp[i] = buf[i];
return retp;
}
void overflo(const char *s)
@ -468,7 +530,7 @@ int first(Node *p) /* collects initially active leaves of p into setvec */
setvec[lp] = 1;
setcnt++;
}
if (type(p) == CCL && (*(char *) right(p)) == '\0')
if (type(p) == CCL && (*(int *) right(p)) == 0)
return(0); /* empty CCL */
return(1);
case PLUS:
@ -524,9 +586,9 @@ void follow(Node *v) /* collects leaves that can follow v into setvec */
}
}
int member(int c, const char *sarg) /* is c in s? */
int member(int c, int *sarg) /* is c in s? */
{
const uschar *s = (const uschar *) sarg;
int *s = (int *) sarg;
while (*s)
if (c == *s++)
@ -534,11 +596,113 @@ int member(int c, const char *sarg) /* is c in s? */
return(0);
}
static void resize_gototab(fa *f, int state)
{
size_t new_size = f->gototab[state].allocated * 2;
gtte *p = (gtte *) realloc(f->gototab[state].entries, new_size * sizeof(gtte));
if (p == NULL)
overflo(__func__);
// need to initialized the new memory to zero
size_t orig_size = f->gototab[state].allocated; // 2nd half of new mem is this size
memset(p + orig_size, 0, orig_size * sizeof(gtte)); // clean it out
f->gototab[state].allocated = new_size; // update gototab info
f->gototab[state].entries = p;
}
static int get_gototab(fa *f, int state, int ch) /* hide gototab implementation */
{
gtte key;
gtte *item;
key.ch = ch;
key.state = 0; /* irrelevant */
item = (gtte *) bsearch(& key, f->gototab[state].entries,
f->gototab[state].inuse, sizeof(gtte),
entry_cmp);
if (item == NULL)
return 0;
else
return item->state;
}
static int entry_cmp(const void *l, const void *r)
{
const gtte *left, *right;
left = (const gtte *) l;
right = (const gtte *) r;
return left->ch - right->ch;
}
static int set_gototab(fa *f, int state, int ch, int val) /* hide gototab implementation */
{
if (f->gototab[state].inuse == 0) {
f->gototab[state].entries[0].ch = ch;
f->gototab[state].entries[0].state = val;
f->gototab[state].inuse++;
return val;
} else if (ch > f->gototab[state].entries[f->gototab[state].inuse-1].ch) {
// not seen yet, insert and return
gtt *tab = & f->gototab[state];
if (tab->inuse + 1 >= tab->allocated)
resize_gototab(f, state);
f->gototab[state].entries[f->gototab[state].inuse-1].ch = ch;
f->gototab[state].entries[f->gototab[state].inuse-1].state = val;
f->gototab[state].inuse++;
return val;
} else {
// maybe we have it, maybe we don't
gtte key;
gtte *item;
key.ch = ch;
key.state = 0; /* irrelevant */
item = (gtte *) bsearch(& key, f->gototab[state].entries,
f->gototab[state].inuse, sizeof(gtte),
entry_cmp);
if (item != NULL) {
// we have it, update state and return
item->state = val;
return item->state;
}
// otherwise, fall through to insert and reallocate.
}
gtt *tab = & f->gototab[state];
if (tab->inuse + 1 >= tab->allocated)
resize_gototab(f, state);
++tab->inuse;
f->gototab[state].entries[tab->inuse].ch = ch;
f->gototab[state].entries[tab->inuse].state = val;
qsort(f->gototab[state].entries,
f->gototab[state].inuse, sizeof(gtte), entry_cmp);
return val; /* not used anywhere at the moment */
}
static void clear_gototab(fa *f, int state)
{
memset(f->gototab[state].entries, 0,
f->gototab[state].allocated * sizeof(gtte));
f->gototab[state].inuse = 0;
}
int match(fa *f, const char *p0) /* shortest match ? */
{
int s, ns;
int n;
int rune;
const uschar *p = (const uschar *) p0;
/* return pmatch(f, p0); does it matter whether longest or shortest? */
s = f->initstat;
assert (s < f->state_count);
@ -546,19 +710,25 @@ int match(fa *f, const char *p0) /* shortest match ? */
return(1);
do {
/* assert(*p < NCHARS); */
if ((ns = f->gototab[s][*p]) != 0)
n = u8_rune(&rune, (const char *) p);
if ((ns = get_gototab(f, s, rune)) != 0)
s = ns;
else
s = cgoto(f, s, *p);
s = cgoto(f, s, rune);
if (f->out[s])
return(1);
} while (*p++ != 0);
if (*p == 0)
break;
p += n;
} while (1); /* was *p++ != 0 */
return(0);
}
int pmatch(fa *f, const char *p0) /* longest match, for sub */
{
int s, ns;
int n;
int rune;
const uschar *p = (const uschar *) p0;
const uschar *q;
@ -573,10 +743,11 @@ int pmatch(fa *f, const char *p0) /* longest match, for sub */
if (f->out[s]) /* final state */
patlen = q-p;
/* assert(*q < NCHARS); */
if ((ns = f->gototab[s][*q]) != 0)
n = u8_rune(&rune, (const char *) q);
if ((ns = get_gototab(f, s, rune)) != 0)
s = ns;
else
s = cgoto(f, s, *q);
s = cgoto(f, s, rune);
assert(s < f->state_count);
@ -588,7 +759,11 @@ int pmatch(fa *f, const char *p0) /* longest match, for sub */
else
goto nextin; /* no match */
}
} while (*q++ != 0);
if (*q == 0)
break;
q += n;
} while (1);
q++; /* was *q++ */
if (f->out[s])
patlen = q-p-1; /* don't count $ */
if (patlen >= 0) {
@ -597,13 +772,19 @@ int pmatch(fa *f, const char *p0) /* longest match, for sub */
}
nextin:
s = 2;
} while (*p++);
if (*p == 0)
break;
n = u8_rune(&rune, (const char *) p);
p += n;
} while (1); /* was *p++ */
return (0);
}
int nematch(fa *f, const char *p0) /* non-empty match, for sub */
{
int s, ns;
int n;
int rune;
const uschar *p = (const uschar *) p0;
const uschar *q;
@ -618,10 +799,11 @@ int nematch(fa *f, const char *p0) /* non-empty match, for sub */
if (f->out[s]) /* final state */
patlen = q-p;
/* assert(*q < NCHARS); */
if ((ns = f->gototab[s][*q]) != 0)
n = u8_rune(&rune, (const char *) q);
if ((ns = get_gototab(f, s, rune)) != 0)
s = ns;
else
s = cgoto(f, s, *q);
s = cgoto(f, s, rune);
if (s == 1) { /* no transition */
if (patlen > 0) {
patbeg = (const char *) p;
@ -629,7 +811,11 @@ int nematch(fa *f, const char *p0) /* non-empty match, for sub */
} else
goto nnextin; /* no nonempty match */
}
} while (*q++ != 0);
if (*q == 0)
break;
q += n;
} while (1);
q++;
if (f->out[s])
patlen = q-p-1; /* don't count $ */
if (patlen > 0 ) {
@ -661,54 +847,84 @@ int nematch(fa *f, const char *p0) /* non-empty match, for sub */
bool fnematch(fa *pfa, FILE *f, char **pbuf, int *pbufsize, int quantum)
{
char *buf = *pbuf;
char *i, *j, *k, *buf = *pbuf;
int bufsize = *pbufsize;
int c, i, j, k, ns, s;
int c, n, ns, s;
s = pfa->initstat;
patlen = 0;
/*
* All indices relative to buf.
* i <= j <= k <= bufsize
* buf <= i <= j <= k <= buf+bufsize
*
* i: origin of active substring
* j: current character
* k: destination of next getc()
* k: destination of the next getc
*/
i = -1, k = 0;
do {
j = i++;
do {
if (++j == k) {
if (k == bufsize)
if (!adjbuf((char **) &buf, &bufsize, bufsize+1, quantum, 0, "fnematch"))
FATAL("stream '%.30s...' too long", buf);
buf[k++] = (c = getc(f)) != EOF ? c : 0;
}
c = (uschar)buf[j];
/* assert(c < NCHARS); */
if ((ns = pfa->gototab[s][c]) != 0)
s = ns;
else
s = cgoto(pfa, s, c);
i = j = k = buf;
if (pfa->out[s]) { /* final state */
patlen = j - i + 1;
if (c == 0) /* don't count $ */
patlen--;
do {
/*
* Call u8_rune with at least awk_mb_cur_max ahead in
* the buffer until EOF interferes.
*/
if (k - j < awk_mb_cur_max) {
if (k + awk_mb_cur_max > buf + bufsize) {
char *obuf = buf;
adjbuf((char **) &buf, &bufsize,
bufsize + awk_mb_cur_max,
quantum, 0, "fnematch");
/* buf resized, maybe moved. update pointers */
*pbufsize = bufsize;
if (obuf != buf) {
i = buf + (i - obuf);
j = buf + (j - obuf);
k = buf + (k - obuf);
*pbuf = buf;
if (patlen)
patbeg = buf + (patbeg - obuf);
}
}
} while (buf[j] && s != 1);
for (n = awk_mb_cur_max ; n > 0; n--) {
*k++ = (c = getc(f)) != EOF ? c : 0;
if (c == EOF) {
if (ferror(f))
FATAL("fnematch: getc error");
break;
}
}
}
j += u8_rune(&c, j);
if ((ns = get_gototab(pfa, s, c)) != 0)
s = ns;
else
s = cgoto(pfa, s, c);
if (pfa->out[s]) { /* final state */
patbeg = i;
patlen = j - i;
if (c == 0) /* don't count $ */
patlen--;
}
if (c && s != 1)
continue; /* origin i still viable, next j */
if (patlen)
break; /* best match found */
/* no match at origin i, next i and start over */
i += u8_rune(&c, i);
if (c == 0)
break; /* no match */
j = i;
s = 2;
} while (buf[i] && !patlen);
/* adjbuf() may have relocated a resized buffer. Inform the world. */
*pbuf = buf;
*pbufsize = bufsize;
} while (1);
if (patlen) {
patbeg = (char *) buf + i;
/*
* Under no circumstances is the last character fed to
* the automaton part of the match. It is EOF's nullbyte,
@ -721,10 +937,10 @@ bool fnematch(fa *pfa, FILE *f, char **pbuf, int *pbufsize, int quantum)
* terminate the buffer.
*/
do
if (buf[--k] && ungetc(buf[k], f) == EOF)
FATAL("unable to ungetc '%c'", buf[k]);
while (k > i + patlen);
buf[k] = '\0';
if (*--k && ungetc(*k, f) == EOF)
FATAL("unable to ungetc '%c'", *k);
while (k > patbeg + patlen);
*k = '\0';
return true;
}
else
@ -797,7 +1013,7 @@ Node *primary(void)
rtok = relex();
if (rtok == ')') { /* special pleading for () */
rtok = relex();
return unary(op2(CCL, NIL, (Node *) tostring("")));
return unary(op2(CCL, NIL, (Node *) cclenter("")));
}
np = regexp();
if (rtok == ')') {
@ -820,7 +1036,7 @@ Node *concat(Node *np)
return (concat(op2(CAT, np, primary())));
case EMPTYRE:
rtok = relex();
return (concat(op2(CAT, op2(CCL, NIL, (Node *) tostring("")),
return (concat(op2(CAT, op2(CCL, NIL, (Node *) cclenter("")),
primary())));
}
return (np);
@ -866,6 +1082,25 @@ Node *unary(Node *np)
* must be less than twice the size of their full name.
*/
/* Because isblank doesn't show up in any of the header files on any
* system i use, it's defined here. if some other locale has a richer
* definition of "blank", define HAS_ISBLANK and provide your own
* version.
* the parentheses here are an attempt to find a path through the maze
* of macro definition and/or function and/or version provided. thanks
* to nelson beebe for the suggestion; let's see if it works everywhere.
*/
/* #define HAS_ISBLANK */
#ifndef HAS_ISBLANK
int (xisblank)(int c)
{
return c==' ' || c=='\t';
}
#endif
static const struct charclass {
const char *cc_name;
int cc_namelen;
@ -873,7 +1108,11 @@ static const struct charclass {
} charclasses[] = {
{ "alnum", 5, isalnum },
{ "alpha", 5, isalpha },
#ifndef HAS_ISBLANK
{ "blank", 5, xisblank },
#else
{ "blank", 5, isblank },
#endif
{ "cntrl", 5, iscntrl },
{ "digit", 5, isdigit },
{ "graph", 5, isgraph },
@ -1013,6 +1252,12 @@ int relex(void) /* lexical analyzer for reparse */
rescan:
starttok = prestr;
if ((n = u8_rune(&rlxval, (const char *) prestr)) > 1) {
prestr += n;
starttok = prestr;
return CHAR;
}
switch (c = *prestr++) {
case '|': return OR;
case '*': return STAR;
@ -1050,10 +1295,15 @@ rescan:
}
else
cflag = 0;
n = 2 * strlen((const char *) prestr)+1;
n = 5 * strlen((const char *) prestr)+1; /* BUG: was 2. what value? */
if (!adjbuf((char **) &buf, &bufsz, n, n, (char **) &bp, "relex1"))
FATAL("out of space for reg expr %.10s...", lastre);
for (; ; ) {
if ((n = u8_rune(&rlxval, (const char *) prestr)) > 1) {
for (i = 0; i < n; i++)
*bp++ = *prestr++;
continue;
}
if ((c = *prestr++) == '\\') {
*bp++ = '\\';
if ((c = *prestr++) == '\0')
@ -1143,7 +1393,7 @@ rescan:
}
break;
case '{':
if (isdigit(*(prestr))) {
if (isdigit((int) *(prestr))) {
num = 0; /* Process as a repetition */
n = -1; m = -1;
commafound = false;
@ -1213,7 +1463,6 @@ rescan:
}
break;
}
return 0; /* [jart] why wasn't this here? */
}
int cgoto(fa *f, int s, int c)
@ -1221,7 +1470,7 @@ int cgoto(fa *f, int s, int c)
int *p, *q;
int i, j, k;
assert(c == HAT || c < NCHARS);
/* assert(c == HAT || c < NCHARS); BUG: seg fault if disable test */
while (f->accept >= maxsetvec) { /* guessing here! */
resizesetvec(__func__);
}
@ -1237,8 +1486,8 @@ int cgoto(fa *f, int s, int c)
|| (k == DOT && c != 0 && c != HAT)
|| (k == ALL && c != 0)
|| (k == EMPTYRE && c != 0)
|| (k == CCL && member(c, (char *) f->re[p[i]].lval.up))
|| (k == NCCL && !member(c, (char *) f->re[p[i]].lval.up) && c != 0 && c != HAT)) {
|| (k == CCL && member(c, (int *) f->re[p[i]].lval.rp))
|| (k == NCCL && !member(c, (int *) f->re[p[i]].lval.rp) && c != 0 && c != HAT)) {
q = f->re[p[i]].lfollow;
for (j = 1; j <= *q; j++) {
if (q[j] >= maxsetvec) {
@ -1270,7 +1519,7 @@ int cgoto(fa *f, int s, int c)
goto different;
/* setvec is state i */
if (c != HAT)
f->gototab[s][c] = i;
set_gototab(f, s, c, i);
return i;
different:;
}
@ -1278,14 +1527,13 @@ int cgoto(fa *f, int s, int c)
/* add tmpset to current set of states */
++(f->curstat);
resize_state(f, f->curstat);
for (i = 0; i < NCHARS; i++)
f->gototab[f->curstat][i] = 0;
clear_gototab(f, f->curstat);
xfree(f->posns[f->curstat]);
p = intalloc(setcnt + 1, __func__);
f->posns[f->curstat] = p;
if (c != HAT)
f->gototab[s][c] = f->curstat;
set_gototab(f, s, c, f->curstat);
for (i = 0; i <= setcnt; i++)
p[i] = tmpset[i];
if (setvec[f->accept])
@ -1303,7 +1551,8 @@ void freefa(fa *f) /* free a finite automaton */
if (f == NULL)
return;
for (i = 0; i < f->state_count; i++)
xfree(f->gototab[i])
xfree(f->gototab[i].entries);
xfree(f->gototab);
for (i = 0; i <= f->curstat; i++)
xfree(f->posns[i]);
for (i = 0; i <= f->accept; i++) {

129
third_party/awk/lex.c vendored
View file

@ -1,40 +1,35 @@
/*-*- mode:c;indent-tabs-mode:t;c-basic-offset:8;tab-width:8;coding:utf-8 -*-│
│ vi: set noet ft=c ts=8 sw=8 fenc=utf-8 :vi │
╚──────────────────────────────────────────────────────────────────────────────╝
│ │
│ 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 "libc/calls/calls.h"
#include "libc/fmt/conv.h"
#include "libc/mem/mem.h"
#include "libc/runtime/runtime.h"
#include "libc/stdio/stdio.h"
#include "libc/str/str.h"
#include "third_party/awk/awk.h"
#include "third_party/awk/awkgram.tab.h"
#include "third_party/gdtoa/gdtoa.h"
/****************************************************************
Copyright (C) Lucent Technologies 1997
All Rights Reserved
Permission to use, copy, modify, and distribute this software and
its documentation for any purpose and without fee is hereby
granted, provided that the above copyright notice appear in all
copies and that both that the copyright notice and this
permission notice and warranty disclaimer appear in supporting
documentation, and that the name Lucent Technologies or any of
its entities not be used in advertising or publicity pertaining
to distribution of the software without specific, written prior
permission.
LUCENT DISCLAIMS ALL WARRANTIES WITH REGARD TO THIS SOFTWARE,
INCLUDING ALL IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS.
IN NO EVENT SHALL LUCENT OR ANY OF ITS ENTITIES BE LIABLE FOR ANY
SPECIAL, INDIRECT OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES
WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER
IN AN ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION,
ARISING OUT OF OR IN CONNECTION WITH THE USE OR PERFORMANCE OF
THIS SOFTWARE.
****************************************************************/
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <ctype.h>
#include "awk.h"
#include "awkgram.tab.h"
extern YYSTYPE yylval;
extern bool infunc;
int lineno = 1;
@ -373,6 +368,8 @@ int yylex(void)
}
}
extern int runetochar(char *str, int c);
int string(void)
{
int c, n;
@ -420,20 +417,54 @@ int string(void)
*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;
case 'x': /* hex \x0-9a-fA-F (exactly two) */
{
int i;
if (!isxdigit(peek())) {
unput(c);
break;
}
n = 0;
for (i = 0; i < 2; i++) {
c = input();
if (c == 0)
break;
if (isxdigit(c)) {
c = tolower(c);
n *= 16;
if (isdigit(c))
n += (c - '0');
else
n += 10 + (c - 'a');
} else {
unput(c);
break;
}
}
if (i)
*bp++ = n;
break;
}
case 'u': /* utf \u0-9a-fA-F (1..8) */
{
int i;
n = 0;
for (i = 0; i < 8; i++) {
c = input();
if (!isxdigit(c) || c == 0)
break;
c = tolower(c);
n *= 16;
if (isdigit(c))
n += (c - '0');
else
n += 10 + (c - 'a');
}
*px = 0;
unput(c);
sscanf(xbuf, "%x", (unsigned int *) &n);
*bp++ = n;
bp += runetochar(bp, n);
break;
}
@ -530,7 +561,7 @@ int regexpr(void)
char *bp;
if (buf == NULL && (buf = (char *) malloc(bufsz)) == NULL)
FATAL("out of space for rex expr");
FATAL("out of space for reg expr");
bp = buf;
for ( ; (c = input()) != '/' && c != 0; ) {
if (!adjbuf(&buf, &bufsz, bp-buf+3, 500, &bp, "regexpr"))

223
third_party/awk/lib.c vendored
View file

@ -1,43 +1,43 @@
/*-*- mode:c;indent-tabs-mode:t;c-basic-offset:8;tab-width:8;coding:utf-8 -*-│
│ vi: set noet ft=c ts=8 sw=8 fenc=utf-8 :vi │
╚──────────────────────────────────────────────────────────────────────────────╝
│ │
│ 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. │
│ │
╚─────────────────────────────────────────────────────────────────────────────*/
/****************************************************************
Copyright (C) Lucent Technologies 1997
All Rights Reserved
Permission to use, copy, modify, and distribute this software and
its documentation for any purpose and without fee is hereby
granted, provided that the above copyright notice appear in all
copies and that both that the copyright notice and this
permission notice and warranty disclaimer appear in supporting
documentation, and that the name Lucent Technologies or any of
its entities not be used in advertising or publicity pertaining
to distribution of the software without specific, written prior
permission.
LUCENT DISCLAIMS ALL WARRANTIES WITH REGARD TO THIS SOFTWARE,
INCLUDING ALL IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS.
IN NO EVENT SHALL LUCENT OR ANY OF ITS ENTITIES BE LIABLE FOR ANY
SPECIAL, INDIRECT OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES
WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER
IN AN ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION,
ARISING OUT OF OR IN CONNECTION WITH THE USE OR PERFORMANCE OF
THIS SOFTWARE.
****************************************************************/
#define DEBUG
#include "libc/calls/calls.h"
#include "libc/errno.h"
#include "libc/fmt/conv.h"
#include "libc/limits.h"
#include "libc/math.h"
#include "libc/mem/mem.h"
#include "libc/runtime/runtime.h"
#include "libc/str/str.h"
#include "third_party/awk/awk.h"
#include <stdio.h>
#include <string.h>
#include <strings.h>
#include <ctype.h>
#include <errno.h>
#include <stdlib.h>
#include <stdarg.h>
#include <limits.h>
#include <math.h>
#include "awk.h"
extern int u8_nextlen(const char *s);
char EMPTY[] = { '\0' };
static FILE *infile = NULL;
FILE *infile = NULL;
bool innew; /* true = infile has not been read by readrec */
char *file = EMPTY;
char *record;
@ -152,11 +152,6 @@ int getrec(char **pbuf, int *pbufsize, bool isrecord) /* get next input record *
}
DPRINTF("RS=<%s>, FS=<%s>, ARGC=%g, FILENAME=%s\n",
*RS, *FS, *ARGC, *FILENAME);
if (isrecord) {
donefld = false;
donerec = true;
savefs();
}
saveb0 = buf[0];
buf[0] = 0;
while (argno < *ARGC || infile == stdin) {
@ -196,6 +191,9 @@ int getrec(char **pbuf, int *pbufsize, bool isrecord) /* get next input record *
fldtab[0]->fval = result;
fldtab[0]->tval |= NUM;
}
donefld = false;
donerec = true;
savefs();
}
setfval(nrloc, nrloc->fval+1);
setfval(fnrloc, fnrloc->fval+1);
@ -223,16 +221,22 @@ void nextfile(void)
argno++;
}
extern int readcsvrec(char **pbuf, int *pbufsize, FILE *inf, bool newflag);
int readrec(char **pbuf, int *pbufsize, FILE *inf, bool newflag) /* read one record into buf */
{
int sep, c, isrec;
char *rr, *buf = *pbuf;
int sep, c, isrec; // POTENTIAL BUG? isrec is a macro in awk.h
char *rr = *pbuf, *buf = *pbuf;
int bufsize = *pbufsize;
char *rs = getsval(rsloc);
if (*rs && rs[1]) {
if (CSV) {
c = readcsvrec(pbuf, pbufsize, inf, newflag);
isrec = (c == EOF && rr == buf) ? false : true;
} else if (*rs && rs[1]) {
bool found;
memset(buf, 0, bufsize);
fa *pfa = makedfa(rs, 1);
if (newflag)
found = fnematch(pfa, inf, &buf, &bufsize, recsize);
@ -245,6 +249,7 @@ int readrec(char **pbuf, int *pbufsize, FILE *inf, bool newflag) /* read one rec
if (found)
setptr(patbeg, '\0');
isrec = (found == 0 && *buf == '\0') ? false : true;
} else {
if ((sep = *rs) == 0) {
sep = '\n';
@ -282,6 +287,52 @@ int readrec(char **pbuf, int *pbufsize, FILE *inf, bool newflag) /* read one rec
return isrec;
}
/*******************
* loose ends here:
* \r\n should become \n
* what about bare \r? Excel uses that for embedded newlines
* can't have "" in unquoted fields, according to RFC 4180
*/
int readcsvrec(char **pbuf, int *pbufsize, FILE *inf, bool newflag) /* csv can have \n's */
{ /* so read a complete record that might be multiple lines */
int sep, c;
char *rr = *pbuf, *buf = *pbuf;
int bufsize = *pbufsize;
bool in_quote = false;
sep = '\n'; /* the only separator; have to skip over \n embedded in "..." */
rr = buf;
while ((c = getc(inf)) != EOF) {
if (c == sep) {
if (! in_quote)
break;
if (rr > buf && rr[-1] == '\r') // remove \r if was \r\n
rr--;
}
if (rr-buf+1 > bufsize)
if (!adjbuf(&buf, &bufsize, 1+rr-buf,
recsize, &rr, "readcsvrec 1"))
FATAL("input record `%.30s...' too long", buf);
*rr++ = c;
if (c == '"')
in_quote = ! in_quote;
}
if (c == '\n' && rr > buf && rr[-1] == '\r') // remove \r if was \r\n
rr--;
if (!adjbuf(&buf, &bufsize, 1+rr-buf, recsize, &rr, "readcsvrec 4"))
FATAL("input record `%.30s...' too long", buf);
*rr = 0;
*pbuf = buf;
*pbufsize = bufsize;
DPRINTF("readcsvrec saw <%s>, returns %d\n", buf, c);
return c;
}
char *getargv(int n) /* get ARGV[n] */
{
Cell *x;
@ -303,6 +354,9 @@ void setclvar(char *s) /* set var=value from s */
Cell *q;
double result;
/* commit f3d9187d4e0f02294fb1b0e31152070506314e67 broke T.argv test */
/* I don't understand why it was changed. */
for (p=s; *p != '='; p++)
;
e = p;
@ -315,6 +369,7 @@ void setclvar(char *s) /* set var=value from s */
q->tval |= NUM;
}
DPRINTF("command line set %s to |%s|\n", s, p);
free(p);
*e = '=';
}
@ -344,9 +399,9 @@ void fldbld(void) /* create fields from current record */
i = 0; /* number of fields accumulated here */
if (inputFS == NULL) /* make sure we have a copy of FS */
savefs();
if (strlen(inputFS) > 1) { /* it's a regular expression */
if (!CSV && strlen(inputFS) > 1) { /* it's a regular expression */
i = refldbld(r, inputFS);
} else if ((sep = *inputFS) == ' ') { /* default whitespace */
} else if (!CSV && (sep = *inputFS) == ' ') { /* default whitespace */
for (i = 0; ; ) {
while (*r == ' ' || *r == '\t' || *r == '\n')
r++;
@ -365,26 +420,58 @@ void fldbld(void) /* create fields from current record */
*fr++ = 0;
}
*fr = 0;
} else if ((sep = *inputFS) == 0) { /* new: FS="" => 1 char/field */
for (i = 0; *r != '\0'; r += n) {
char buf[MB_LEN_MAX + 1];
} else if (CSV) { /* CSV processing. no error handling */
if (*r != 0) {
for (;;) {
i++;
if (i > nfields)
growfldtab(i);
if (freeable(fldtab[i]))
xfree(fldtab[i]->sval);
fldtab[i]->sval = fr;
fldtab[i]->tval = FLD | STR | DONTFREE;
if (*r == '"' ) { /* start of "..." */
for (r++ ; *r != '\0'; ) {
if (*r == '"' && r[1] != '\0' && r[1] == '"') {
r += 2; /* doubled quote */
*fr++ = '"';
} else if (*r == '"' && (r[1] == '\0' || r[1] == ',')) {
r++; /* skip over closing quote */
break;
} else {
*fr++ = *r++;
}
}
*fr++ = 0;
} else { /* unquoted field */
while (*r != ',' && *r != '\0')
*fr++ = *r++;
*fr++ = 0;
}
if (*r++ == 0)
break;
}
}
*fr = 0;
} else if ((sep = *inputFS) == 0) { /* new: FS="" => 1 char/field */
for (i = 0; *r != '\0'; ) {
char buf[10];
i++;
if (i > nfields)
growfldtab(i);
if (freeable(fldtab[i]))
xfree(fldtab[i]->sval);
n = mblen(r, MB_LEN_MAX);
if (n < 0)
n = 1;
memcpy(buf, r, n);
buf[n] = '\0';
n = u8_nextlen(r);
for (j = 0; j < n; j++)
buf[j] = *r++;
buf[j] = '\0';
fldtab[i]->sval = tostring(buf);
fldtab[i]->tval = FLD | STR;
}
*fr = 0;
} else if (*r != 0) { /* if 0, it's a null field */
/* subtlecase : if length(FS) == 1 && length(RS > 0)
/* subtle case: if length(FS) == 1 && length(RS > 0)
* \n is NOT a field separator (cf awk book 61,84).
* this variable is tested in the inner while loop.
*/
@ -587,11 +674,9 @@ void yyerror(const char *s)
SYNTAX("%s", s);
}
extern char *cmdname;
void SYNTAX(const char *fmt, ...)
{
extern char *curfname;
extern char *cmdname, *curfname;
static int been_here = 0;
va_list varg;
@ -641,6 +726,7 @@ void bcheck2(int n, int c1, int c2)
void FATAL(const char *fmt, ...)
{
extern char *cmdname;
va_list varg;
fflush(stdout);
@ -656,6 +742,7 @@ void FATAL(const char *fmt, ...)
void WARNING(const char *fmt, ...)
{
extern char *cmdname;
va_list varg;
fflush(stdout);
@ -758,10 +845,10 @@ int isclvar(const char *s) /* is s of form var=something ? */
{
const char *os = s;
if (!isalpha((uschar) *s) && *s != '_')
if (!isalpha((int) *s) && *s != '_')
return 0;
for ( ; *s; s++)
if (!(isalnum((uschar) *s) || *s == '_'))
if (!(isalnum((int) *s) || *s == '_'))
break;
return *s == '=' && s > os;
}
@ -796,19 +883,19 @@ bool is_valid_number(const char *s, bool trailing_stuff_ok,
if (no_trailing)
*no_trailing = false;
while (isspace(*s))
while (isspace((int) *s))
s++;
// no hex floating point, sorry
/* no hex floating point, sorry */
if (s[0] == '0' && tolower(s[1]) == 'x')
return false;
// allow +nan, -nan, +inf, -inf, any other letter, no
/* allow +nan, -nan, +inf, -inf, any other letter, no */
if (s[0] == '+' || s[0] == '-') {
is_nan = (strncasecmp(s+1, "nan", 3) == 0);
is_inf = (strncasecmp(s+1, "inf", 3) == 0);
if ((is_nan || is_inf)
&& (isspace(s[4]) || s[4] == '\0'))
&& (isspace((int) s[4]) || s[4] == '\0'))
goto convert;
else if (! isdigit(s[1]) && s[1] != '.')
return false;
@ -831,13 +918,13 @@ convert:
/*
* check for trailing stuff
*/
while (isspace(*ep))
while (isspace((int) *ep))
ep++;
if (no_trailing != NULL)
*no_trailing = (*ep == '\0');
// return true if found the end, or trailing stuff is allowed
/* return true if found the end, or trailing stuff is allowed */
retval = *ep == '\0' || trailing_stuff_ok;
return retval;

147
third_party/awk/main.c vendored
View file

@ -1,46 +1,5 @@
/*-*- mode:c;indent-tabs-mode:t;c-basic-offset:8;tab-width:8;coding:utf-8 -*-│
│ vi: set noet ft=c ts=8 sw=8 fenc=utf-8 :vi │
╚──────────────────────────────────────────────────────────────────────────────╝
│ │
│ Copyright (C) Lucent Technologies 1997 │
│ All Rights Reserved │
│ │
│ Permission to use, copy, modify, and distribute this software and │
│ its documentation for any purpose and without fee is hereby │
│ granted, provided that the above copyright notice appear in all │
│ copies and that both that the copyright notice and this │
│ permission notice and warranty disclaimer appear in supporting │
│ documentation, and that the name Lucent Technologies or any of │
│ its entities not be used in advertising or publicity pertaining │
│ to distribution of the software without specific, written prior │
│ permission. │
│ │
│ LUCENT DISCLAIMS ALL WARRANTIES WITH REGARD TO THIS SOFTWARE, │
│ INCLUDING ALL IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS. │
│ IN NO EVENT SHALL LUCENT OR ANY OF ITS ENTITIES BE LIABLE FOR ANY │
│ SPECIAL, INDIRECT OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES │
│ WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER │
│ IN AN ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, │
│ ARISING OUT OF OR IN CONNECTION WITH THE USE OR PERFORMANCE OF │
│ THIS SOFTWARE. │
│ │
╚─────────────────────────────────────────────────────────────────────────────*/
#define DEBUG
#include "libc/calls/calls.h"
#include "libc/calls/struct/sigaction.h"
#include "libc/calls/struct/siginfo.h"
#include "libc/mem/mem.h"
#include "libc/runtime/runtime.h"
#include "libc/stdio/rand.h"
#include "libc/str/locale.h"
#include "libc/str/str.h"
#include "libc/sysv/consts/sa.h"
#include "libc/sysv/consts/sicode.h"
#include "libc/sysv/consts/sig.h"
#include "third_party/awk/awk.h"
__notice(awk_notice, "\
The One True Awk\n\
__notice(awk_license, "\
/****************************************************************\n\
Copyright (C) Lucent Technologies 1997\n\
All Rights Reserved\n\
\n\
@ -61,9 +20,21 @@ SPECIAL, INDIRECT OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES\n\
WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER\n\
IN AN ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION,\n\
ARISING OUT OF OR IN CONNECTION WITH THE USE OR PERFORMANCE OF\n\
THIS SOFTWARE.");
THIS SOFTWARE.\n\
****************************************************************/");
const char *version = "version 20220530";
const char *version = "version 20240311";
#define DEBUG
#include <stdio.h>
#include <ctype.h>
#include <locale.h>
#include <stdlib.h>
#include <string.h>
#include <signal.h>
#include "awk.h"
extern char **environ;
extern int nfields;
int dbg = 0;
@ -71,6 +42,7 @@ Awkfloat srand_seed = 1;
char *cmdname; /* gets argv[0] for error messages */
extern FILE *yyin; /* lex input file */
char *lexprog; /* points to program argument if it exists */
extern int errorflag; /* non-zero if any syntax errors; set by yyerror */
enum compile_states compile_time = ERROR_PRINTING;
static char **pfile; /* program filenames from -f's */
@ -78,23 +50,37 @@ static size_t maxpfile; /* max program filename */
static size_t npfile; /* number of filenames */
static size_t curpfile; /* current filename */
bool CSV = false; /* true for csv input */
bool safe = false; /* true => "safe" mode */
static wontreturn void fpecatch(int n, siginfo_t *si, void *uc)
size_t awk_mb_cur_max = 1;
static noreturn void fpecatch(int n
#ifdef SA_SIGINFO
, siginfo_t *si, void *uc
#endif
)
{
const char *emsg[10];
emsg[0] = "Unknown error";
emsg[FPE_INTDIV] = "Integer divide by zero";
emsg[FPE_INTOVF] = "Integer overflow";
emsg[FPE_FLTDIV] = "Floating point divide by zero";
emsg[FPE_FLTOVF] = "Floating point overflow";
emsg[FPE_FLTUND] = "Floating point underflow";
emsg[FPE_FLTRES] = "Floating point inexact result";
emsg[FPE_FLTINV] = "Invalid Floating point operation";
emsg[FPE_FLTSUB] = "Subscript out of range";
FATAL("floating point exception: %s",
(size_t)si->si_code < sizeof(emsg) / sizeof(emsg[0]) &&
emsg[si->si_code] ? emsg[si->si_code] : emsg[0]);
#ifdef SA_SIGINFOz
static const char *emsg[] = {
[0] = "Unknown error",
[FPE_INTDIV] = "Integer divide by zero",
[FPE_INTOVF] = "Integer overflow",
[FPE_FLTDIV] = "Floating point divide by zero",
[FPE_FLTOVF] = "Floating point overflow",
[FPE_FLTUND] = "Floating point underflow",
[FPE_FLTRES] = "Floating point inexact result",
[FPE_FLTINV] = "Invalid Floating point operation",
[FPE_FLTSUB] = "Subscript out of range",
};
#endif
FATAL("floating point exception"
#ifdef SA_SIGINFOz
": %s", (size_t)si->si_code < sizeof(emsg) / sizeof(emsg[0]) &&
emsg[si->si_code] ? emsg[si->si_code] : emsg[0]
#endif
);
}
/* Can this work with recursive calls? I don't think so.
@ -129,30 +115,30 @@ getarg(int *argc, char ***argv, const char *msg)
int _awk(int argc, char *argv[])
{
const char *fs = NULL;
struct sigaction sa;
char *fn, *vn;
setlocale(LC_CTYPE, "");
setlocale(LC_NUMERIC, "C"); /* for parsing cmdline & prog */
awk_mb_cur_max = MB_CUR_MAX;
cmdname = argv[0];
if (pledge("stdio rpath wpath cpath proc exec", NULL) == -1) {
fprintf(stderr, "%s: pledge: incorrect arguments\n",
cmdname);
exit(1);
}
if (argc == 1) {
fprintf(stderr,
"usage: %s [-F fs] [-v var=value] [-f progfile | 'prog'] [file ...]\n",
"usage: %s [-F fs | --csv] [-v var=value] [-f progfile | 'prog'] [file ...]\n",
cmdname);
exit(1);
}
sa.sa_sigaction = fpecatch;
sa.sa_flags = SA_SIGINFO;
sigemptyset(&sa.sa_mask);
(void)sigaction(SIGFPE, &sa, NULL);
#ifdef SA_SIGINFO
{
struct sigaction sa;
sa.sa_sigaction = fpecatch;
sa.sa_flags = SA_SIGINFO;
sigemptyset(&sa.sa_mask);
(void)sigaction(SIGFPE, &sa, NULL);
}
#else
(void)signal(SIGFPE, fpecatch);
#endif
/*signal(SIGSEGV, segvcatch); experiment */
/* Set and keep track of the random seed */
srand_seed = 1;
@ -170,6 +156,12 @@ int _awk(int argc, char *argv[])
argv++;
break;
}
if (strcmp(argv[1], "--csv") == 0) { /* turn on csv input processing */
CSV = true;
argc--;
argv++;
continue;
}
switch (argv[1][1]) {
case 's':
if (strcmp(argv[1], "-safe") == 0)
@ -208,6 +200,10 @@ int _awk(int argc, char *argv[])
argc--;
argv++;
}
if (CSV && (fs != NULL || lookup("FS", symtab) != NULL))
WARNING("danger: don't set FS when --csv is in effect");
/* argv[1] is now the first argument */
if (npfile == 0) { /* no -f; first argument is program */
if (argc <= 1) {
@ -229,6 +225,11 @@ int _awk(int argc, char *argv[])
if (!safe)
envinit(environ);
yyparse();
#if 0
// Doing this would comply with POSIX, but is not compatible with
// other awks and with what most users expect. So comment it out.
setlocale(LC_NUMERIC, ""); /* back to whatever it is locally */
#endif
if (fs)
*FS = qstring(fs, '\0');
DPRINTF("errorflag=%d\n", errorflag);

66
third_party/awk/maketab.c vendored
View file

@ -1,36 +1,26 @@
/*-*- mode:c;indent-tabs-mode:t;c-basic-offset:8;tab-width:8;coding:utf-8 -*-│
│ vi: set noet ft=c ts=8 sw=8 fenc=utf-8 :vi │
╚──────────────────────────────────────────────────────────────────────────────╝
│ │
│ 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 "libc/mem/mem.h"
#include "libc/runtime/runtime.h"
#include "libc/stdio/stdio.h"
#include "libc/str/str.h"
#include "third_party/awk/awk.h"
#include "third_party/awk/awkgram.tab.h"
/****************************************************************
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
@ -38,6 +28,12 @@
* it finds the indices in awkgram.tab.h, produced by bison.
*/
#include <stdio.h>
#include <string.h>
#include <stdlib.h>
#include "awk.h"
#include "awkgram.tab.h"
struct xx
{ int token;
const char *name;
@ -56,8 +52,8 @@ struct xx
{ ARRAY, "array", NULL },
{ INDIRECT, "indirect", "$(" },
{ SUBSTR, "substr", "substr" },
{ SUB, "sub", "sub" },
{ GSUB, "gsub", "gsub" },
{ SUB, "dosub", "sub" },
{ GSUB, "dosub", "gsub" },
{ INDEX, "sindex", "sindex" },
{ SPRINTF, "awksprintf", "sprintf " },
{ ADD, "arith", " + " },

64
third_party/awk/parse.c vendored
View file

@ -1,37 +1,35 @@
/*-*- mode:c;indent-tabs-mode:t;c-basic-offset:8;tab-width:8;coding:utf-8 -*-│
│ vi: set noet ft=c ts=8 sw=8 fenc=utf-8 :vi │
╚──────────────────────────────────────────────────────────────────────────────╝
│ │
│ Copyright (C) Lucent Technologies 1997 │
│ All Rights Reserved │
│ │
│ Permission to use, copy, modify, and distribute this software and │
│ its documentation for any purpose and without fee is hereby │
│ granted, provided that the above copyright notice appear in all │
│ copies and that both that the copyright notice and this │
│ permission notice and warranty disclaimer appear in supporting │
│ documentation, and that the name Lucent Technologies or any of │
│ its entities not be used in advertising or publicity pertaining │
│ to distribution of the software without specific, written prior │
│ permission. │
│ │
│ LUCENT DISCLAIMS ALL WARRANTIES WITH REGARD TO THIS SOFTWARE, │
│ INCLUDING ALL IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS. │
│ IN NO EVENT SHALL LUCENT OR ANY OF ITS ENTITIES BE LIABLE FOR ANY │
│ SPECIAL, INDIRECT OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES │
│ WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER │
│ IN AN ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, │
│ ARISING OUT OF OR IN CONNECTION WITH THE USE OR PERFORMANCE OF │
│ THIS SOFTWARE. │
│ │
╚─────────────────────────────────────────────────────────────────────────────*/
#define DEBUG
#include "libc/mem/mem.h"
#include "libc/str/str.h"
#include "third_party/awk/awk.h"
#include "third_party/awk/awkgram.tab.h"
/****************************************************************
Copyright (C) Lucent Technologies 1997
All Rights Reserved
Node *nodealloc(int n)
Permission to use, copy, modify, and distribute this software and
its documentation for any purpose and without fee is hereby
granted, provided that the above copyright notice appear in all
copies and that both that the copyright notice and this
permission notice and warranty disclaimer appear in supporting
documentation, and that the name Lucent Technologies or any of
its entities not be used in advertising or publicity pertaining
to distribution of the software without specific, written prior
permission.
LUCENT DISCLAIMS ALL WARRANTIES WITH REGARD TO THIS SOFTWARE,
INCLUDING ALL IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS.
IN NO EVENT SHALL LUCENT OR ANY OF ITS ENTITIES BE LIABLE FOR ANY
SPECIAL, INDIRECT OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES
WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER
IN AN ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION,
ARISING OUT OF OR IN CONNECTION WITH THE USE OR PERFORMANCE OF
THIS SOFTWARE.
****************************************************************/
#define DEBUG
#include <stdio.h>
#include <string.h>
#include <stdlib.h>
#include "awk.h"
#include "awkgram.tab.h"
Node *nodealloc(size_t n)
{
Node *x;

36
third_party/awk/proctab.c vendored
View file

@ -1,32 +1,6 @@
/*-*- mode:c;indent-tabs-mode:t;c-basic-offset:8;tab-width:8;coding:utf-8 -*-│
│ vi: set noet ft=c ts=8 sw=8 fenc=utf-8 :vi │
╚──────────────────────────────────────────────────────────────────────────────╝
│ │
│ 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 "third_party/awk/awk.h"
#include "third_party/awk/awkgram.tab.h"
#include <stdio.h>
#include "awk.h"
#include "awkgram.tab.h"
static const char * const printname[95] = {
"FIRSTTOKEN", /* 258 */
@ -171,8 +145,8 @@ Cell *(*proctab[95])(Node **, int) = {
jump, /* EXIT */
forstat, /* FOR */
nullproc, /* FUNC */
sub, /* SUB */
gsub, /* GSUB */
dosub, /* SUB */
dosub, /* GSUB */
ifstat, /* IF */
sindex, /* INDEX */
nullproc, /* LSUBSTR */

204
third_party/awk/proto.h vendored Normal file
View file

@ -0,0 +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.
****************************************************************/
extern int yywrap(void);
extern void setfname(Cell *);
extern int constnode(Node *);
extern char *strnode(Node *);
extern Node *notnull(Node *);
extern int yyparse(void);
extern int yylex(void);
extern void startreg(void);
extern int input(void);
extern void unput(int);
extern void unputstr(const char *);
extern int yylook(void);
extern int yyback(int *, int);
extern int yyinput(void);
extern fa *makedfa(const char *, bool);
extern fa *mkdfa(const char *, bool);
extern int makeinit(fa *, bool);
extern void penter(Node *);
extern void freetr(Node *);
extern int quoted(const uschar **);
extern int *cclenter(const char *);
extern noreturn void overflo(const char *);
extern void cfoll(fa *, Node *);
extern int first(Node *);
extern void follow(Node *);
extern int member(int, int *);
extern int match(fa *, const char *);
extern int pmatch(fa *, const char *);
extern int nematch(fa *, const char *);
extern bool fnematch(fa *, FILE *, char **, int *, int);
extern Node *reparse(const char *);
extern Node *regexp(void);
extern Node *primary(void);
extern Node *concat(Node *);
extern Node *alt(Node *);
extern Node *unary(Node *);
extern int relex(void);
extern int cgoto(fa *, int, int);
extern void freefa(fa *);
extern int pgetc(void);
extern char *cursource(void);
extern Node *nodealloc(size_t);
extern Node *exptostat(Node *);
extern Node *node1(int, Node *);
extern Node *node2(int, Node *, Node *);
extern Node *node3(int, Node *, Node *, Node *);
extern Node *node4(int, Node *, Node *, Node *, Node *);
extern Node *stat3(int, Node *, Node *, Node *);
extern Node *op2(int, Node *, Node *);
extern Node *op1(int, Node *);
extern Node *stat1(int, Node *);
extern Node *op3(int, Node *, Node *, Node *);
extern Node *op4(int, Node *, Node *, Node *, Node *);
extern Node *stat2(int, Node *, Node *);
extern Node *stat4(int, Node *, Node *, Node *, Node *);
extern Node *celltonode(Cell *, int);
extern Node *rectonode(void);
extern Node *makearr(Node *);
extern Node *pa2stat(Node *, Node *, Node *);
extern Node *linkum(Node *, Node *);
extern void defn(Cell *, Node *, Node *);
extern int isarg(const char *);
extern const char *tokname(int);
extern Cell *(*proctab[])(Node **, int);
extern int ptoi(void *);
extern Node *itonp(int);
extern void syminit(void);
extern void arginit(int, char **);
extern void envinit(char **);
extern Array *makesymtab(int);
extern void freesymtab(Cell *);
extern void freeelem(Cell *, const char *);
extern Cell *setsymtab(const char *, const char *, double, unsigned int, Array *);
extern int hash(const char *, int);
extern void rehash(Array *);
extern Cell *lookup(const char *, Array *);
extern double setfval(Cell *, double);
extern void funnyvar(Cell *, const char *);
extern char *setsval(Cell *, const char *);
extern double getfval(Cell *);
extern char *getsval(Cell *);
extern char *getpssval(Cell *); /* for print */
extern char *tostring(const char *);
extern char *tostringN(const char *, size_t);
extern char *qstring(const char *, int);
extern Cell *catstr(Cell *, Cell *);
extern void recinit(unsigned int);
extern void initgetrec(void);
extern void makefields(int, int);
extern void growfldtab(int n);
extern void savefs(void);
extern int getrec(char **, int *, bool);
extern void nextfile(void);
extern int readrec(char **buf, int *bufsize, FILE *inf, bool isnew);
extern char *getargv(int);
extern void setclvar(char *);
extern void fldbld(void);
extern void cleanfld(int, int);
extern void newfld(int);
extern void setlastfld(int);
extern int refldbld(const char *, const char *);
extern void recbld(void);
extern Cell *fieldadr(int);
extern void yyerror(const char *);
extern void bracecheck(void);
extern void bcheck2(int, int, int);
extern void SYNTAX(const char *, ...)
__attribute__((__format__(__printf__, 1, 2)));
extern noreturn void FATAL(const char *, ...)
__attribute__((__format__(__printf__, 1, 2)));
extern void WARNING(const char *, ...)
__attribute__((__format__(__printf__, 1, 2)));
extern void error(void);
extern void eprint(void);
extern void bclass(int);
extern double errcheck(double, const char *);
extern int isclvar(const char *);
extern bool is_valid_number(const char *s, bool trailing_stuff_ok,
bool *no_trailing, double *result);
#define is_number(s, val) is_valid_number(s, false, NULL, val)
extern int adjbuf(char **pb, int *sz, int min, int q, char **pbp, const char *what);
extern void run(Node *);
extern Cell *execute(Node *);
extern Cell *program(Node **, int);
extern Cell *call(Node **, int);
extern Cell *copycell(Cell *);
extern Cell *arg(Node **, int);
extern Cell *jump(Node **, int);
extern Cell *awkgetline(Node **, int);
extern Cell *getnf(Node **, int);
extern Cell *array(Node **, int);
extern Cell *awkdelete(Node **, int);
extern Cell *intest(Node **, int);
extern Cell *matchop(Node **, int);
extern Cell *boolop(Node **, int);
extern Cell *relop(Node **, int);
extern void tfree(Cell *);
extern Cell *gettemp(void);
extern Cell *field(Node **, int);
extern Cell *indirect(Node **, int);
extern Cell *substr(Node **, int);
extern Cell *sindex(Node **, int);
extern int format(char **, int *, const char *, Node *);
extern Cell *awksprintf(Node **, int);
extern Cell *awkprintf(Node **, int);
extern Cell *arith(Node **, int);
extern double ipow(double, int);
extern Cell *incrdecr(Node **, int);
extern Cell *assign(Node **, int);
extern Cell *cat(Node **, int);
extern Cell *pastat(Node **, int);
extern Cell *dopa2(Node **, int);
extern Cell *split(Node **, int);
extern Cell *condexpr(Node **, int);
extern Cell *ifstat(Node **, int);
extern Cell *whilestat(Node **, int);
extern Cell *dostat(Node **, int);
extern Cell *forstat(Node **, int);
extern Cell *instat(Node **, int);
extern Cell *bltin(Node **, int);
extern Cell *printstat(Node **, int);
extern Cell *nullproc(Node **, int);
extern FILE *redirect(int, Node *);
extern FILE *openfile(int, const char *, bool *);
extern const char *filename(FILE *);
extern Cell *closefile(Node **, int);
extern void closeall(void);
extern Cell *dosub(Node **, int);
extern FILE *popen(const char *, const char *);
extern int pclose(FILE *);
extern const char *flags2str(int flags);

980
third_party/awk/run.c vendored
View file

File diff suppressed because it is too large Load diff

75
third_party/awk/tran.c vendored
View file

@ -1,36 +1,34 @@
/*-*- mode:c;indent-tabs-mode:t;c-basic-offset:8;tab-width:8;coding:utf-8 -*-│
│ vi: set noet ft=c ts=8 sw=8 fenc=utf-8 :vi │
╚──────────────────────────────────────────────────────────────────────────────╝
│ │
│ Copyright (C) Lucent Technologies 1997 │
│ All Rights Reserved │
│ │
│ Permission to use, copy, modify, and distribute this software and │
│ its documentation for any purpose and without fee is hereby │
│ granted, provided that the above copyright notice appear in all │
│ copies and that both that the copyright notice and this │
│ permission notice and warranty disclaimer appear in supporting │
│ documentation, and that the name Lucent Technologies or any of │
│ its entities not be used in advertising or publicity pertaining │
│ to distribution of the software without specific, written prior │
│ permission. │
│ │
│ LUCENT DISCLAIMS ALL WARRANTIES WITH REGARD TO THIS SOFTWARE, │
│ INCLUDING ALL IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS. │
│ IN NO EVENT SHALL LUCENT OR ANY OF ITS ENTITIES BE LIABLE FOR ANY │
│ SPECIAL, INDIRECT OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES │
│ WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER │
│ IN AN ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, │
│ ARISING OUT OF OR IN CONNECTION WITH THE USE OR PERFORMANCE OF │
│ THIS SOFTWARE. │
│ │
╚─────────────────────────────────────────────────────────────────────────────*/
#define DEBUG
#include "libc/fmt/conv.h"
#include "libc/math.h"
#include "libc/mem/mem.h"
#include "libc/str/str.h"
#include "third_party/awk/awk.h"
/****************************************************************
Copyright (C) Lucent Technologies 1997
All Rights Reserved
Permission to use, copy, modify, and distribute this software and
its documentation for any purpose and without fee is hereby
granted, provided that the above copyright notice appear in all
copies and that both that the copyright notice and this
permission notice and warranty disclaimer appear in supporting
documentation, and that the name Lucent Technologies or any of
its entities not be used in advertising or publicity pertaining
to distribution of the software without specific, written prior
permission.
LUCENT DISCLAIMS ALL WARRANTIES WITH REGARD TO THIS SOFTWARE,
INCLUDING ALL IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS.
IN NO EVENT SHALL LUCENT OR ANY OF ITS ENTITIES BE LIABLE FOR ANY
SPECIAL, INDIRECT OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES
WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER
IN AN ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION,
ARISING OUT OF OR IN CONNECTION WITH THE USE OR PERFORMANCE OF
THIS SOFTWARE.
****************************************************************/
#define DEBUG
#include <stdio.h>
#include <math.h>
#include <ctype.h>
#include <string.h>
#include <stdlib.h>
#include "awk.h"
#define FULLTAB 2 /* rehash when table gets this x full */
#define GROWTAB 4 /* grow table by this factor */
@ -310,7 +308,7 @@ Awkfloat setfval(Cell *vp, Awkfloat f) /* set float val of a Cell */
} else if (&vp->fval == NF) {
donerec = false; /* mark $0 invalid */
setlastfld(f);
DPRINTF("setting NF to %g\n", f);
DPRINTF("setfval: setting NF to %g\n", f);
} else if (isrec(vp)) {
donefld = false; /* mark $1... invalid */
donerec = true;
@ -350,6 +348,10 @@ char *setsval(Cell *vp, const char *s) /* set string val of a Cell */
(void*)vp, NN(vp->nval), s, vp->tval, donerec, donefld);
if ((vp->tval & (NUM | STR)) == 0)
funnyvar(vp, "assign to");
if (CSV && (vp == rsloc))
WARNING("danger: don't set RS when --csv is in effect");
if (CSV && (vp == fsloc))
WARNING("danger: don't set FS when --csv is in effect");
if (isfld(vp)) {
donerec = false; /* mark $0 invalid */
fldno = atoi(vp->nval);
@ -377,7 +379,7 @@ char *setsval(Cell *vp, const char *s) /* set string val of a Cell */
donerec = false; /* mark $0 invalid */
f = getfval(vp);
setlastfld(f);
DPRINTF("setting NF to %g\n", f);
DPRINTF("setsval: setting NF to %g\n", f);
}
return(vp->sval);
@ -565,7 +567,6 @@ Cell *catstr(Cell *a, Cell *b) /* concatenate a and b */
char *qstring(const char *is, int delim) /* collect string up to next delim */
{
const char *os = is;
int c, n;
const uschar *s = (const uschar *) is;
uschar *buf, *bp;
@ -574,7 +575,7 @@ char *qstring(const char *is, int delim) /* collect string up to next delim */
FATAL( "out of space in qstring(%s)", s);
for (bp = buf; (c = *s) != delim; s++) {
if (c == '\n')
SYNTAX( "newline in string %.20s...", os );
SYNTAX( "newline in string %.20s...", is );
else if (c != '\\')
*bp++ = c;
else { /* \something */