Fossil

** second.
**
**  The following regular expression syntax is supported:
**
**     X*      zero or more occurrences of X
**     X+      one or more occurrences of X
**     X?      zero or one occurrences of X
**     X{p,q}  between p and q occurrences of X
**     (X)     match X
**     X|Y     X or Y
**     ^X      X occurring at the beginning of the string
**     X$      X occurring at the end of the string
**     .       Match any single character
**     \c      Character c where c is one of \{}()[]|*+?.
**     \c      C-language escapes for c in afnrtv.  ex: \t or \n

** performance is bounded by O(N*M) where N is the size of the regular
** expression and M is the size of the input string.  The matcher never
** exhibits exponential behavior.  Note that the X{p,q} operator expands
** to p copies of X following by q-p copies of X? and that the size of the
** regular expression in the O(N*M) performance bound is computed after
** this expansion.
**
** To help prevent DoS attacks, the size of the NFA is limit to
** SQLITE_MAX_REGEXP states, default 9999.
*/
#include <string.h>
#include <stdlib.h>
/* #include "sqlite3ext.h" */
SQLITE_EXTENSION_INIT1

#ifndef SQLITE_MAX_REGEXP
# define SQLITE_MAX_REGEXP 9999
#endif

/*
** The following #defines change the names of some functions implemented in
** this file to prevent name collisions with C-library functions of the
** same name.
*/

  char *aOp;                  /* Operators for the virtual machine */
  int *aArg;                  /* Arguments to each operator */
  unsigned (*xNextChar)(ReInput*);  /* Next character function */
  unsigned char zInit[12];    /* Initial text to match */
  int nInit;                  /* Number of bytes in zInit */
  unsigned nState;            /* Number of entries in aOp[] and aArg[] */
  unsigned nAlloc;            /* Slots allocated for aOp[] and aArg[] */
  unsigned mxAlloc;           /* Complexity limit */
};

/* Add a state to the given state set if it is not already there */
static void re_add_state(ReStateSet *pSet, int newState){
  unsigned i;
  for(i=0; i<pSet->nState; i++) if( pSet->aState[i]==newState ) return;
  pSet->aState[pSet->nState++] = (ReStateNumber)newState;

}

/* Resize the opcode and argument arrays for an RE under construction.
*/
static int re_resize(ReCompiled *p, int N){
  char *aOp;
  int *aArg;
  if( N>p->mxAlloc ){ p->zErr = "REGEXP pattern too big"; return 1; }
  aOp = sqlite3_realloc64(p->aOp, N*sizeof(p->aOp[0]));
  if( aOp==0 ){ p->zErr = "out of memory"; return 1; }
  p->aOp = aOp;
  aArg = sqlite3_realloc64(p->aArg, N*sizeof(p->aArg[0]));
  if( aArg==0 ){ p->zErr = "out of memory"; return 1; }
  p->aArg = aArg;
  p->nAlloc = N;
  return 0;
}

/* Insert a new opcode and argument into an RE under construction.  The
** insertion point is just prior to existing opcode iBefore.

      }
      case '{': {
        unsigned int m = 0, n = 0;
        unsigned int sz, j;
        if( iPrev<0 ) return "'{m,n}' without operand";
        while( (c=rePeek(p))>='0' && c<='9' ){
          m = m*10 + c - '0';
          if( m*2>p->mxAlloc ) return "REGEXP pattern too big";
          p->sIn.i++;
        }
        n = m;
        if( c==',' ){
          p->sIn.i++;
          n = 0;
          while( (c=rePeek(p))>='0' && c<='9' ){
            n = n*10 + c-'0';
            if( n*2>p->mxAlloc ) return "REGEXP pattern too big";
            p->sIn.i++;
          }
        }
        if( c!='}' ) return "unmatched '{'";
        if( n<m ) return "n less than m in '{m,n}'";
        p->sIn.i++;
        sz = p->nState - iPrev;
        if( m==0 ){
          if( n==0 ) return "both m and n are zero in '{m,n}'";
          re_insert(p, iPrev, RE_OP_FORK, sz+1);
          iPrev++;
          n--;
        }else{
          for(j=1; j<m; j++) re_copy(p, iPrev, sz);
        }
        for(j=m; j<n; j++){
          re_append(p, RE_OP_FORK, sz+1);
          re_copy(p, iPrev, sz);
        }
        if( n==0 && m>0 ){
          re_append(p, RE_OP_FORK, -(int)sz);
        }
        break;
      }
      case '[': {
        unsigned int iFirst = p->nState;
        if( rePeek(p)=='^' ){
          re_append(p, RE_OP_CC_EXC, 0);

/*
** Compile a textual regular expression in zIn[] into a compiled regular
** expression suitable for us by re_match() and return a pointer to the
** compiled regular expression in *ppRe.  Return NULL on success or an
** error message if something goes wrong.
*/
static const char *re_compile(
  ReCompiled **ppRe,      /* OUT: write compiled NFA here */
  const char *zIn,        /* Input regular expression */
  int mxRe,               /* Complexity limit */
  int noCase              /* True for caseless comparisons */
){
  ReCompiled *pRe;
  const char *zErr;
  int i, j;

  *ppRe = 0;
  pRe = sqlite3_malloc( sizeof(*pRe) );
  if( pRe==0 ){
    return "out of memory";
  }
  memset(pRe, 0, sizeof(*pRe));
  pRe->xNextChar = noCase ? re_next_char_nocase : re_next_char;
  pRe->mxAlloc = mxRe;
  if( re_resize(pRe, 30) ){
    zErr = pRe->zErr;
    re_free(pRe);
    return zErr;
  }
  if( zIn[0]=='^' ){
    zIn++;
  }else{
    re_append(pRe, RE_OP_ANYSTAR, 0);
  }
  pRe->sIn.z = (unsigned char*)zIn;

      }
    }
    if( j>0 && pRe->zInit[j-1]==0 ) j--;
    pRe->nInit = j;
  }
  return pRe->zErr;
}

/*
** Compute a reasonable limit on the length of the REGEXP NFA.
*/
static int re_maxlen(sqlite3_context *context){
  sqlite3 *db = sqlite3_context_db_handle(context);
  return 75 + sqlite3_limit(db, SQLITE_LIMIT_LIKE_PATTERN_LENGTH,-1)/2;
}

/*
** Implementation of the regexp() SQL function.  This function implements
** the build-in REGEXP operator.  The first argument to the function is the
** pattern and the second argument is the string.  So, the SQL statements:
**
**       A REGEXP B

  int setAux = 0;           /* True to invoke sqlite3_set_auxdata() */

  (void)argc;  /* Unused */
  pRe = sqlite3_get_auxdata(context, 0);
  if( pRe==0 ){
    zPattern = (const char*)sqlite3_value_text(argv[0]);
    if( zPattern==0 ) return;
    zErr = re_compile(&pRe, zPattern, re_maxlen(context),
                      sqlite3_user_data(context)!=0);
    if( zErr ){
      re_free(pRe);
      sqlite3_result_error(context, zErr, -1);
      return;
    }
    if( pRe==0 ){
      sqlite3_result_error_nomem(context);

  int i;
  int n;
  char *z;
  (void)argc;

  zPattern = (const char*)sqlite3_value_text(argv[0]);
  if( zPattern==0 ) return;
  zErr = re_compile(&pRe, zPattern, re_maxlen(context),
                    sqlite3_user_data(context)!=0);
  if( zErr ){
    re_free(pRe);
    sqlite3_result_error(context, zErr, -1);
    return;
  }
  if( pRe==0 ){
    sqlite3_result_error_nomem(context);

** the text of this file.  Search for "Begin file sqlite3.h" to find the start
** of the embedded sqlite3.h header file.) Additional code files may be needed
** if you want a wrapper to interface SQLite with your choice of programming
** language. The code for the "sqlite3" command-line shell is also in a
** separate file. This file contains only code for the core SQLite library.
**
** The content in this amalgamation comes from Fossil check-in
** 869c968569b09d05a5b7d587d8fddb3b4611 with changes in files:
**
**    
*/
#ifndef SQLITE_AMALGAMATION
#define SQLITE_CORE 1
#define SQLITE_AMALGAMATION 1
#ifndef SQLITE_PRIVATE

**
** See also: [sqlite3_libversion()],
** [sqlite3_libversion_number()], [sqlite3_sourceid()],
** [sqlite_version()] and [sqlite_source_id()].
*/
#define SQLITE_VERSION        "3.51.0"
#define SQLITE_VERSION_NUMBER 3051000
#define SQLITE_SOURCE_ID      "2025-09-26 15:38:52 869c968569b09d05a5b7d587d8fddb3b4611daf7467dc157701e5dc6c960alt1"
#define SQLITE_SCM_BRANCH     "trunk"
#define SQLITE_SCM_TAGS       ""
#define SQLITE_SCM_DATETIME   "2025-09-26T15:38:52.279Z"

/*
** CAPI3REF: Run-Time Library Version Numbers
** KEYWORDS: sqlite3_version sqlite3_sourceid
**
** These interfaces provide the same information as the [SQLITE_VERSION],
** [SQLITE_VERSION_NUMBER], and [SQLITE_SOURCE_ID] C preprocessor macros

**
** See also: [sqlite3_libversion()],
** [sqlite3_libversion_number()], [sqlite3_sourceid()],
** [sqlite_version()] and [sqlite_source_id()].
*/
#define SQLITE_VERSION        "3.51.0"
#define SQLITE_VERSION_NUMBER 3051000
#define SQLITE_SOURCE_ID      "2025-09-26 15:38:52 869c968569b09d05a5b7d587d8fddb3b4611daf7467dc157701e5dc6c960alt1"
#define SQLITE_SCM_BRANCH     "trunk"
#define SQLITE_SCM_TAGS       ""
#define SQLITE_SCM_DATETIME   "2025-09-26T15:38:52.279Z"

/*
** CAPI3REF: Run-Time Library Version Numbers
** KEYWORDS: sqlite3_version sqlite3_sourceid
**
** These interfaces provide the same information as the [SQLITE_VERSION],
** [SQLITE_VERSION_NUMBER], and [SQLITE_SOURCE_ID] C preprocessor macros