/*** $Id: lstrlib.c,v 1.221 2014/12/11 14:03:07 roberto Exp $** Standard library for string operations and pattern-matching** See Copyright Notice in lua.h*/ #define lstrlib_c#define LUA_LIB #include "lprefix.h"  #include <ctype.h>#include <limits.h>#include <stddef.h>#include <stdio.h>#include <stdlib.h>#include <string.h> #include "lua.h" #include "lauxlib.h"#include "lualib.h"  /*** maximum number of captures that a pattern can do during** pattern-matching. This limit is arbitrary.*/#if !defined(LUA_MAXCAPTURES)#define LUA_MAXCAPTURES		32#endif  /* macro to 'unsign' a character */#define uchar(c)	((unsigned char)(c))  /*** Some sizes are better limited to fit in 'int', but must also fit in** 'size_t'. (We assume that 'lua_Integer' cannot be smaller than 'int'.)*/#define MAXSIZE  \	(sizeof(size_t) < sizeof(int) ? (~(size_t)0) : (size_t)(INT_MAX))    static int str_len (lua_State *L) {  size_t l;  luaL_checklstring(L, 1, &l);  lua_pushinteger(L, (lua_Integer)l);  return 1;}  /* translate a relative string position: negative means back from end */static lua_Integer posrelat (lua_Integer pos, size_t len) {  if (pos >= 0) return pos;  else if (0u - (size_t)pos > len) return 0;  else return (lua_Integer)len + pos + 1;}  static int str_sub (lua_State *L) {  size_t l;  const char *s = luaL_checklstring(L, 1, &l);  lua_Integer start = posrelat(luaL_checkinteger(L, 2), l);  lua_Integer end = posrelat(luaL_optinteger(L, 3, -1), l);  if (start < 1) start = 1;  if (end > (lua_Integer)l) end = l;  if (start <= end)    lua_pushlstring(L, s + start - 1, (size_t)(end - start + 1));  else lua_pushliteral(L, "");  return 1;}  static int str_reverse (lua_State *L) {  size_t l, i;  luaL_Buffer b;  const char *s = luaL_checklstring(L, 1, &l);  char *p = luaL_buffinitsize(L, &b, l);  for (i = 0; i < l; i++)    p[i] = s[l - i - 1];  luaL_pushresultsize(&b, l);  return 1;}  static int str_lower (lua_State *L) {  size_t l;  size_t i;  luaL_Buffer b;  const char *s = luaL_checklstring(L, 1, &l);  char *p = luaL_buffinitsize(L, &b, l);  for (i=0; i<l; i++)    p[i] = tolower(uchar(s[i]));  luaL_pushresultsize(&b, l);  return 1;}  static int str_upper (lua_State *L) {  size_t l;  size_t i;  luaL_Buffer b;  const char *s = luaL_checklstring(L, 1, &l);  char *p = luaL_buffinitsize(L, &b, l);  for (i=0; i<l; i++)    p[i] = toupper(uchar(s[i]));  luaL_pushresultsize(&b, l);  return 1;}  static int str_rep (lua_State *L) {  size_t l, lsep;  const char *s = luaL_checklstring(L, 1, &l);  lua_Integer n = luaL_checkinteger(L, 2);  const char *sep = luaL_optlstring(L, 3, "", &lsep);  if (n <= 0) lua_pushliteral(L, "");  else if (l + lsep < l || l + lsep > MAXSIZE / n)  /* may overflow? */    return luaL_error(L, "resulting string too large");  else {    size_t totallen = (size_t)n * l + (size_t)(n - 1) * lsep;    luaL_Buffer b;    char *p = luaL_buffinitsize(L, &b, totallen);    while (n-- > 1) {  /* first n-1 copies (followed by separator) */      memcpy(p, s, l * sizeof(char)); p += l;      if (lsep > 0) {  /* empty 'memcpy' is not that cheap */        memcpy(p, sep, lsep * sizeof(char));        p += lsep;      }    }    memcpy(p, s, l * sizeof(char));  /* last copy (not followed by separator) */    luaL_pushresultsize(&b, totallen);  }  return 1;}  static int str_byte (lua_State *L) {  size_t l;  const char *s = luaL_checklstring(L, 1, &l);  lua_Integer posi = posrelat(luaL_optinteger(L, 2, 1), l);  lua_Integer pose = posrelat(luaL_optinteger(L, 3, posi), l);  int n, i;  if (posi < 1) posi = 1;  if (pose > (lua_Integer)l) pose = l;  if (posi > pose) return 0;  /* empty interval; return no values */  n = (int)(pose -  posi + 1);  if (posi + n <= pose)  /* arithmetic overflow? */    return luaL_error(L, "string slice too long");  luaL_checkstack(L, n, "string slice too long");  for (i=0; i<n; i++)    lua_pushinteger(L, uchar(s[posi+i-1]));  return n;}  static int str_char (lua_State *L) {  int n = lua_gettop(L);  /* number of arguments */  int i;  luaL_Buffer b;  char *p = luaL_buffinitsize(L, &b, n);  for (i=1; i<=n; i++) {    lua_Integer c = luaL_checkinteger(L, i);    luaL_argcheck(L, uchar(c) == c, i, "value out of range");    p[i - 1] = uchar(c);  }  luaL_pushresultsize(&b, n);  return 1;}  static int writer (lua_State *L, const void *b, size_t size, void *B) {  (void)L;  luaL_addlstring((luaL_Buffer *) B, (const char *)b, size);  return 0;}  static int str_dump (lua_State *L) {  luaL_Buffer b;  int strip = lua_toboolean(L, 2);  luaL_checktype(L, 1, LUA_TFUNCTION);  lua_settop(L, 1);  luaL_buffinit(L,&b);  if (lua_dump(L, writer, &b, strip) != 0)    return luaL_error(L, "unable to dump given function");  luaL_pushresult(&b);  return 1;}   /*** {======================================================** PATTERN MATCHING** =======================================================*/  #define CAP_UNFINISHED	(-1)#define CAP_POSITION	(-2)  typedef struct MatchState {  int matchdepth;  /* control for recursive depth (to avoid C stack overflow) */  const char *src_init;  /* init of source string */  const char *src_end;  /* end ('\0') of source string */  const char *p_end;  /* end ('\0') of pattern */  lua_State *L;  int level;  /* total number of captures (finished or unfinished) */  struct {    const char *init;    ptrdiff_t len;  } capture[LUA_MAXCAPTURES];} MatchState;  /* recursive function */static const char *match (MatchState *ms, const char *s, const char *p);  /* maximum recursion depth for 'match' */#if !defined(MAXCCALLS)#define MAXCCALLS	200#endif  #define L_ESC		'%'#define SPECIALS	"^$*+?.([%-"  static int check_capture (MatchState *ms, int l) {  l -= '1';  if (l < 0 || l >= ms->level || ms->capture[l].len == CAP_UNFINISHED)    return luaL_error(ms->L, "invalid capture index %%%d", l + 1);  return l;}  static int capture_to_close (MatchState *ms) {  int level = ms->level;  for (level--; level>=0; level--)    if (ms->capture[level].len == CAP_UNFINISHED) return level;  return luaL_error(ms->L, "invalid pattern capture");}  static const char *classend (MatchState *ms, const char *p) {  switch (*p++) {    case L_ESC: {      if (p == ms->p_end)        luaL_error(ms->L, "malformed pattern (ends with '%%')");      return p+1;    }    case '[': {      if (*p == '^') p++;      do {  /* look for a ']' */        if (p == ms->p_end)          luaL_error(ms->L, "malformed pattern (missing ']')");        if (*(p++) == L_ESC && p < ms->p_end)          p++;  /* skip escapes (e.g. '%]') */      } while (*p != ']');      return p+1;    }    default: {      return p;    }  }}  static int match_class (int c, int cl) {  int res;  switch (tolower(cl)) {    case 'a' : res = isalpha(c); break;    case 'c' : res = iscntrl(c); break;    case 'd' : res = isdigit(c); break;    case 'g' : res = isgraph(c); break;    case 'l' : res = islower(c); break;    case 'p' : res = ispunct(c); break;    case 's' : res = isspace(c); break;    case 'u' : res = isupper(c); break;    case 'w' : res = isalnum(c); break;    case 'x' : res = isxdigit(c); break;    case 'z' : res = (c == 0); break;  /* deprecated option */    default: return (cl == c);  }  return (islower(cl) ? res : !res);}  static int matchbracketclass (int c, const char *p, const char *ec) {  int sig = 1;  if (*(p+1) == '^') {    sig = 0;    p++;  /* skip the '^' */  }  while (++p < ec) {    if (*p == L_ESC) {      p++;      if (match_class(c, uchar(*p)))        return sig;    }    else if ((*(p+1) == '-') && (p+2 < ec)) {      p+=2;      if (uchar(*(p-2)) <= c && c <= uchar(*p))        return sig;    }    else if (uchar(*p) == c) return sig;  }  return !sig;}  static int singlematch (MatchState *ms, const char *s, const char *p,                        const char *ep) {  if (s >= ms->src_end)    return 0;  else {    int c = uchar(*s);    switch (*p) {      case '.': return 1;  /* matches any char */      case L_ESC: return match_class(c, uchar(*(p+1)));      case '[': return matchbracketclass(c, p, ep-1);      default:  return (uchar(*p) == c);    }  }}  static const char *matchbalance (MatchState *ms, const char *s,                                   const char *p) {  if (p >= ms->p_end - 1)    luaL_error(ms->L, "malformed pattern (missing arguments to '%%b')");  if (*s != *p) return NULL;  else {    int b = *p;    int e = *(p+1);    int cont = 1;    while (++s < ms->src_end) {      if (*s == e) {        if (--cont == 0) return s+1;      }      else if (*s == b) cont++;    }  }  return NULL;  /* string ends out of balance */}  static const char *max_expand (MatchState *ms, const char *s,                                 const char *p, const char *ep) {  ptrdiff_t i = 0;  /* counts maximum expand for item */  while (singlematch(ms, s + i, p, ep))    i++;  /* keeps trying to match with the maximum repetitions */  while (i>=0) {    const char *res = match(ms, (s+i), ep+1);    if (res) return res;    i--;  /* else didn't match; reduce 1 repetition to try again */  }  return NULL;}  static const char *min_expand (MatchState *ms, const char *s,                                 const char *p, const char *ep) {  for (;;) {    const char *res = match(ms, s, ep+1);    if (res != NULL)      return res;    else if (singlematch(ms, s, p, ep))      s++;  /* try with one more repetition */    else return NULL;  }}  static const char *start_capture (MatchState *ms, const char *s,                                    const char *p, int what) {  const char *res;  int level = ms->level;  if (level >= LUA_MAXCAPTURES) luaL_error(ms->L, "too many captures");  ms->capture[level].init = s;  ms->capture[level].len = what;  ms->level = level+1;  if ((res=match(ms, s, p)) == NULL)  /* match failed? */    ms->level--;  /* undo capture */  return res;}  static const char *end_capture (MatchState *ms, const char *s,                                  const char *p) {  int l = capture_to_close(ms);  const char *res;  ms->capture[l].len = s - ms->capture[l].init;  /* close capture */  if ((res = match(ms, s, p)) == NULL)  /* match failed? */    ms->capture[l].len = CAP_UNFINISHED;  /* undo capture */  return res;}  static const char *match_capture (MatchState *ms, const char *s, int l) {  size_t len;  l = check_capture(ms, l);  len = ms->capture[l].len;  if ((size_t)(ms->src_end-s) >= len &&      memcmp(ms->capture[l].init, s, len) == 0)    return s+len;  else return NULL;}  static const char *match (MatchState *ms, const char *s, const char *p) {  if (ms->matchdepth-- == 0)    luaL_error(ms->L, "pattern too complex");  init: /* using goto's to optimize tail recursion */  if (p != ms->p_end) {  /* end of pattern? */    switch (*p) {      case '(': {  /* start capture */        if (*(p + 1) == ')')  /* position capture? */          s = start_capture(ms, s, p + 2, CAP_POSITION);        else          s = start_capture(ms, s, p + 1, CAP_UNFINISHED);        break;      }      case ')': {  /* end capture */        s = end_capture(ms, s, p + 1);        break;      }      case '$': {        if ((p + 1) != ms->p_end)  /* is the '$' the last char in pattern? */          goto dflt;  /* no; go to default */        s = (s == ms->src_end) ? s : NULL;  /* check end of string */        break;      }      case L_ESC: {  /* escaped sequences not in the format class[*+?-]? */        switch (*(p + 1)) {          case 'b': {  /* balanced string? */            s = matchbalance(ms, s, p + 2);            if (s != NULL) {              p += 4; goto init;  /* return match(ms, s, p + 4); */            }  /* else fail (s == NULL) */            break;          }          case 'f': {  /* frontier? */            const char *ep; char previous;            p += 2;            if (*p != '[')              luaL_error(ms->L, "missing '[' after '%%f' in pattern");            ep = classend(ms, p);  /* points to what is next */            previous = (s == ms->src_init) ? '\0' : *(s - 1);            if (!matchbracketclass(uchar(previous), p, ep - 1) &&               matchbracketclass(uchar(*s), p, ep - 1)) {              p = ep; goto init;  /* return match(ms, s, ep); */            }            s = NULL;  /* match failed */            break;          }          case '0': case '1': case '2': case '3':          case '4': case '5': case '6': case '7':          case '8': case '9': {  /* capture results (%0-%9)? */            s = match_capture(ms, s, uchar(*(p + 1)));            if (s != NULL) {              p += 2; goto init;  /* return match(ms, s, p + 2) */            }            break;          }          default: goto dflt;        }        break;      }      default: dflt: {  /* pattern class plus optional suffix */        const char *ep = classend(ms, p);  /* points to optional suffix */        /* does not match at least once? */        if (!singlematch(ms, s, p, ep)) {          if (*ep == '*' || *ep == '?' || *ep == '-') {  /* accept empty? */            p = ep + 1; goto init;  /* return match(ms, s, ep + 1); */          }          else  /* '+' or no suffix */            s = NULL;  /* fail */        }        else {  /* matched once */          switch (*ep) {  /* handle optional suffix */            case '?': {  /* optional */              const char *res;              if ((res = match(ms, s + 1, ep + 1)) != NULL)                s = res;              else {                p = ep + 1; goto init;  /* else return match(ms, s, ep + 1); */              }              break;            }            case '+':  /* 1 or more repetitions */

Lines 1–500 of 1430. Load more