/*

** $Id: lstrlib.c,v 1.132.1.4 2008/07/11 17:27:21 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"

/* 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, l);

  return 1;

}

static ptrdiff_t posrelat (ptrdiff_t pos, size_t len) {

  /* relative string position: negative means back from end */

  if (pos < 0) pos += (ptrdiff_t)len + 1;

  return (pos >= 0) ? pos : 0;

}

static int str_sub (lua_State *L) {

  size_t l;

  const char *s = luaL_checklstring(L, 1, &l);

  ptrdiff_t start = posrelat(luaL_checkinteger(L, 2), l);

  ptrdiff_t end = posrelat(luaL_optinteger(L, 3, -1), l);

  if (start < 1) start = 1;

  if (end > (ptrdiff_t)l) end = (ptrdiff_t)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;

  luaL_Buffer b;

  const char *s = luaL_checklstring(L, 1, &l);

  luaL_buffinit(L, &b);

  while (l--) luaL_addchar(&b, s[l]);

  luaL_pushresult(&b);

  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);

  luaL_buffinit(L, &b);

  for (i=0; i<l; i++)

    luaL_addchar(&b, tolower(uchar(s[i])));

  luaL_pushresult(&b);

  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);

  luaL_buffinit(L, &b);

  for (i=0; i<l; i++)

    luaL_addchar(&b, toupper(uchar(s[i])));

  luaL_pushresult(&b);

  return 1;

}

static int str_rep (lua_State *L) {

  size_t l;

  luaL_Buffer b;

  const char *s = luaL_checklstring(L, 1, &l);

  int n = luaL_checkint(L, 2);

  luaL_buffinit(L, &b);

  while (n-- > 0)

    luaL_addlstring(&b, s, l);

  luaL_pushresult(&b);

  return 1;

}

static int str_byte (lua_State *L) {

  size_t l;

  const char *s = luaL_checklstring(L, 1, &l);

  ptrdiff_t posi = posrelat(luaL_optinteger(L, 2, 1), l);

  ptrdiff_t pose = posrelat(luaL_optinteger(L, 3, posi), l);

  int n, i;

  if (posi <= 0) posi = 1;

  if ((size_t)pose > l) pose = l;

  if (posi > pose) return 0;  /* empty interval; return no values */

  n = (int)(pose -  posi + 1);

  if (posi + n <= pose)  /* overflow? */

    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;

  luaL_buffinit(L, &b);

  for (i=1; i<=n; i++) {

    int c = luaL_checkint(L, i);

    luaL_argcheck(L, uchar(c) == c, i, "invalid value");

    luaL_addchar(&b, uchar(c));

  }

  luaL_pushresult(&b);

  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)

    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 */

  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");

  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 == '\0')

        luaL_error(ms->L, "malformed pattern (ends with " LUA_QL("%%") ")");

      return p+1;

    }

    case '[': {

      if (*p == '^') p++;

      do {  /* look for a `]' */

        if (*p == '\0')

          luaL_error(ms->L, "malformed pattern (missing " LUA_QL("]") ")");

        if (*(p++) == L_ESC && *p != '\0')

          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 '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;

    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 == 0 || *(p+1) == 0)

    luaL_error(ms->L, "unbalanced pattern");

  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 */

  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 L_ESC: {

      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); */

        }

        default: {

          if (isdigit(uchar(*(p+1)))) {  /* 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) */

          }

          goto dflt;  /* case default */

        }

      }

    }

    case '\0': {  /* end of pattern */

      return s;  /* match succeeded */

    }

    case '$': {

      if (*(p+1) == '\0')  /* is the `$' the last char in pattern? */

        return (s == ms->src_end) ? s : NULL;  /* check end of string */

      else goto dflt;

    }

    default: dflt: {  /* it is a pattern item */

      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

      luaL_error(ms->L, "invalid capture index");

  }

  else {

    ptrdiff_t l = ms->capture[i].len;

    if (l == CAP_UNFINISHED) luaL_error(ms->L, "unfinished capture");

    if (l == CAP_POSITION)

      lua_pushinteger(ms->L, ms->capture[i].init - ms->src_init + 1);

    else

      lua_pushlstring(ms->L, ms->capture[i].init, l);

  }

}

static int push_captures (MatchState *ms, const char *s, const char *e) {

  int i;

  int nlevels = (ms->level == 0 && s) ? 1 : ms->level;

  luaL_checkstack(ms->L, nlevels, "too many captures");

  for (i = 0; i < nlevels; i++)

    push_onecapture(ms, i, s, e);

  return nlevels;  /* number of strings pushed */

}

static int str_find_aux (lua_State *L, int find) {

  size_t l1, l2;

  const char *s = luaL_checklstring(L, 1, &l1);

  const char *p = luaL_checklstring(L, 2, &l2);

  ptrdiff_t init = posrelat(luaL_optinteger(L, 3, 1), l1) - 1;

  if (init < 0) init = 0;

  else if ((size_t)(init) > l1) init = (ptrdiff_t)l1;

  if (find && (lua_toboolean(L, 4) ||  /* explicit request? */

      strpbrk(p, SPECIALS) == NULL)) {  /* or no special characters? */

    /* do a plain search */

    const char *s2 = lmemfind(s+init, l1-init, p, l2);

    if (s2) {

      lua_pushinteger(L, s2-s+1);

      lua_pushinteger(L, s2-s+l2);

      return 2;

    }

  }

  else {

    MatchState ms;

    int anchor = (*p == '^') ? (p++, 1) : 0;

    const char *s1=s+init;

    ms.L = L;

    ms.src_init = s;

    ms.src_end = s+l1;

    do {

      const char *res;

      ms.level = 0;

      if ((res=match(&ms, s1, p)) != NULL) {

        if (find) {

          lua_pushinteger(L, s1-s+1);  /* start */

          lua_pushinteger(L, res-s);   /* end */

          return push_captures(&ms, NULL, 0) + 2;

        }

        else