/*** $Id: lstrlib.c,v 1.176 2012/05/23 15:37:09 roberto Exp $** Standard library for string operations and pattern-matching** See Copyright Notice in lua.h*/  #include <ctype.h>#include <stddef.h>#include <stdio.h>#include <stdlib.h>#include <string.h> #define lstrlib_c#define LUA_LIB #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))   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 size_t posrelat (ptrdiff_t pos, size_t len) {  if (pos >= 0) return (size_t)pos;  else if (0u - (size_t)pos > len) return 0;  else return len - ((size_t)-pos) + 1;}  static int str_sub (lua_State *L) {  size_t l;  const char *s = luaL_checklstring(L, 1, &l);  size_t start = posrelat(luaL_checkinteger(L, 2), l);  size_t end = posrelat(luaL_optinteger(L, 3, -1), l);  if (start < 1) start = 1;  if (end > l) end = l;  if (start <= end)    lua_pushlstring(L, s + start - 1, 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;}  /* reasonable limit to avoid arithmetic overflow */#define MAXSIZE		((~(size_t)0) >> 1) static int str_rep (lua_State *L) {  size_t l, lsep;  const char *s = luaL_checklstring(L, 1, &l);  int n = luaL_checkint(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 = n * l + (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) {  /* avoid empty 'memcpy' (may be expensive) */        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);  size_t posi = posrelat(luaL_optinteger(L, 2, 1), l);  size_t pose = posrelat(luaL_optinteger(L, 3, posi), l);  int n, i;  if (posi < 1) posi = 1;  if (pose > l) pose = l;  if (posi > pose) return 0;  /* empty interval; return no values */  n = (int)(pose -  posi + 1);  if (posi + n <= pose)  /* (size_t -> int) 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++) {    int c = luaL_checkint(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;  luaL_checktype(L, 1, LUA_TFUNCTION);  lua_settop(L, 1);  luaL_buffinit(L,&b);  if (lua_dump(L, writer, &b) != 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 {  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;  #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 " LUA_QL("%%") ")");      return p+1;    }    case '[': {      if (*p == '^') p++;      do {  /* look for a `]' */        if (p == ms->p_end)          luaL_error(ms->L, "malformed pattern (missing " LUA_QL("]") ")");        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 (int c, const char *p, const char *ep) {  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 *match (MatchState *ms, const char *s, const char *p);  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 " LUA_QL("%%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 ((s+i)<ms->src_end && singlematch(uchar(*(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 (s<ms->src_end && singlematch(uchar(*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) {  init: /* using goto's to optimize tail recursion */  if (p == ms->p_end)  /* end of pattern? */    return s;  /* match succeeded */  switch (*p) {    case '(': {  /* start capture */      if (*(p+1) == ')')  /* position capture? */        return start_capture(ms, s, p+2, CAP_POSITION);      else        return start_capture(ms, s, p+1, CAP_UNFINISHED);    }    case ')': {  /* end capture */      return end_capture(ms, s, p+1);    }    case '$': {      if ((p+1) == ms->p_end)  /* is the `$' the last char in pattern? */        return (s == ms->src_end) ? s : NULL;  /* check end of string */      else goto dflt;    }    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) return NULL;          p+=4; goto init;  /* else return match(ms, s, p+4); */        }        case 'f': {  /* frontier? */          const char *ep; char previous;          p += 2;          if (*p != '[')            luaL_error(ms->L, "missing " LUA_QL("[") " after "                               LUA_QL("%%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)) return NULL;          p=ep; goto init;  /* else return match(ms, s, ep); */        }        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) return NULL;          p+=2; goto init;  /* else return match(ms, s, p+2) */        }        default: goto dflt;      }    }    default: dflt: {  /* pattern class plus optional suffix */      const char *ep = classend(ms, p);  /* points to what is next */      int m = s < ms->src_end && singlematch(uchar(*s), p, ep);      switch (*ep) {        case '?': {  /* optional */          const char *res;          if (m && ((res=match(ms, s+1, ep+1)) != NULL))            return res;          p=ep+1; goto init;  /* else return match(ms, s, ep+1); */        }        case '*': {  /* 0 or more repetitions */          return max_expand(ms, s, p, ep);        }        case '+': {  /* 1 or more repetitions */          return (m ? max_expand(ms, s+1, p, ep) : NULL);        }        case '-': {  /* 0 or more repetitions (minimum) */          return min_expand(ms, s, p, ep);        }        default: {          if (!m) return NULL;          s++; p=ep; goto init;  /* else return match(ms, s+1, ep); */        }      }    }  }}   static const char *lmemfind (const char *s1, size_t l1,                               const char *s2, size_t l2) {  if (l2 == 0) return s1;  /* empty strings are everywhere */  else if (l2 > l1) return NULL;  /* avoids a negative `l1' */  else {    const char *init;  /* to search for a `*s2' inside `s1' */    l2--;  /* 1st char will be checked by `memchr' */    l1 = l1-l2;  /* `s2' cannot be found after that */    while (l1 > 0 && (init = (const char *)memchr(s1, *s2, l1)) != NULL) {      init++;   /* 1st char is already checked */      if (memcmp(init, s2+1, l2) == 0)        return init-1;      else {  /* correct `l1' and `s1' to try again */        l1 -= init-s1;        s1 = init;      }    }    return NULL;  /* not found */  }}  static void push_onecapture (MatchState *ms, int i, const char *s,                                                    const char *e) {  if (i >= ms->level) {    if (i == 0)  /* ms->level == 0, too */      lua_pushlstring(ms->L, s, e - s);  /* add whole match */    else

Lines 1–500 of 972. Load more