** a legal notice, here is a blessing:
**
**    May you do good and not evil.
**    May you find forgiveness for yourself and forgive others.
**    May you share freely, never taking more than you give.
**
*************************************************************************
** $Id: btree.c,v 1.688 2009/07/15 11:26:44 drh Exp $
**
** This file implements a external (disk-based) database using BTrees.
** See the header comment on "btreeInt.h" for additional information.
** Including a description of file format and an overview of operation.
*/
#include "btreeInt.h"

................................................................................
** optimization 2 above is ommitted if the corresponding bit is already
** set in BtShared.pHasContent. The contents of the bitvec are cleared
** at the end of every transaction.
*/
static int btreeSetHasContent(BtShared *pBt, Pgno pgno){
  int rc = SQLITE_OK;
  if( !pBt->pHasContent ){
    int nPage;
    rc = sqlite3PagerPagecount(pBt->pPager, &nPage);
    if( rc==SQLITE_OK ){

      pBt->pHasContent = sqlite3BitvecCreate((u32)nPage);
      if( !pBt->pHasContent ){
        rc = SQLITE_NOMEM;
      }
    }
  }
  if( rc==SQLITE_OK && pgno<=sqlite3BitvecSize(pBt->pHasContent) ){
    rc = sqlite3BitvecSet(pBt->pHasContent, pgno);
  }
  return rc;
}
................................................................................
  int rc;

  assert( CURSOR_VALID==pCur->eState );
  assert( 0==pCur->pKey );
  assert( cursorHoldsMutex(pCur) );

  rc = sqlite3BtreeKeySize(pCur, &pCur->nKey);


  /* If this is an intKey table, then the above call to BtreeKeySize()
  ** stores the integer key in pCur->nKey. In this case this value is
  ** all that is required. Otherwise, if pCur is not open on an intKey
  ** table, then malloc space for and store the pCur->nKey bytes of key 
  ** data.
  */
  if( rc==SQLITE_OK && 0==pCur->apPage[0]->intKey){
    void *pKey = sqlite3Malloc( (int)pCur->nKey );
    if( pKey ){
      rc = sqlite3BtreeKey(pCur, 0, (int)pCur->nKey, pKey);
      if( rc==SQLITE_OK ){
        pCur->pKey = pKey;
      }else{
        sqlite3_free(pKey);
................................................................................
** saveCursorPosition().
*/
static int btreeRestoreCursorPosition(BtCursor *pCur){
  int rc;
  assert( cursorHoldsMutex(pCur) );
  assert( pCur->eState>=CURSOR_REQUIRESEEK );
  if( pCur->eState==CURSOR_FAULT ){
    return pCur->skip;
  }
  pCur->eState = CURSOR_INVALID;
  rc = btreeMoveto(pCur, pCur->pKey, pCur->nKey, 0, &pCur->skip);
  if( rc==SQLITE_OK ){
    sqlite3_free(pCur->pKey);
    pCur->pKey = 0;
    assert( pCur->eState==CURSOR_VALID || pCur->eState==CURSOR_INVALID );
  }
  return rc;
}
................................................................................
  int rc;

  rc = restoreCursorPosition(pCur);
  if( rc ){
    *pHasMoved = 1;
    return rc;
  }
  if( pCur->eState!=CURSOR_VALID || pCur->skip!=0 ){
    *pHasMoved = 1;
  }else{
    *pHasMoved = 0;
  }
  return SQLITE_OK;
}

................................................................................
    goto trans_begun;
  }
#endif

  /* Any read-only or read-write transaction implies a read-lock on 
  ** page 1. So if some other shared-cache client already has a write-lock 
  ** on page 1, the transaction cannot be opened. */
  if( SQLITE_OK!=(rc = querySharedCacheTableLock(p, MASTER_ROOT, READ_LOCK)) ){
    goto trans_begun;
  }

  do {
    /* Call lockBtree() until either pBt->pPage1 is populated or
    ** lockBtree() returns something other than SQLITE_OK. lockBtree()
    ** may return SQLITE_OK but leave pBt->pPage1 set to 0 if after
    ** reading page 1 it discovers that the page-size of the database 
    ** file is not pBt->pageSize. In this case lockBtree() will update
................................................................................
void sqlite3BtreeTripAllCursors(Btree *pBtree, int errCode){
  BtCursor *p;
  sqlite3BtreeEnter(pBtree);
  for(p=pBtree->pBt->pCursor; p; p=p->pNext){
    int i;
    sqlite3BtreeClearCursor(p);
    p->eState = CURSOR_FAULT;
    p->skip = errCode;
    for(i=0; i<=p->iPage; i++){
      releasePage(p->apPage[i]);
      p->apPage[i] = 0;
    }
  }
  sqlite3BtreeLeave(pBtree);
}
................................................................................

  assert( cursorHoldsMutex(pCur) );
  assert( CURSOR_INVALID < CURSOR_REQUIRESEEK );
  assert( CURSOR_VALID   < CURSOR_REQUIRESEEK );
  assert( CURSOR_FAULT   > CURSOR_REQUIRESEEK );
  if( pCur->eState>=CURSOR_REQUIRESEEK ){
    if( pCur->eState==CURSOR_FAULT ){
      assert( pCur->skip!=SQLITE_OK );
      return pCur->skip;
    }
    sqlite3BtreeClearCursor(pCur);
  }

  if( pCur->iPage>=0 ){
    int i;
    for(i=1; i<=pCur->iPage; i++){
      releasePage(pCur->apPage[i]);
    }
    pCur->iPage = 0;
  }else{
    if( 
      SQLITE_OK!=(rc = getAndInitPage(pBt, pCur->pgnoRoot, &pCur->apPage[0]))
    ){

      pCur->eState = CURSOR_INVALID;
      return rc;
    }
    pCur->iPage = 0;

    /* If pCur->pKeyInfo is not NULL, then the caller that opened this cursor
    ** expected to open it on an index b-tree. Otherwise, if pKeyInfo is
................................................................................
    return rc;
  }
  assert( pRes!=0 );
  if( CURSOR_INVALID==pCur->eState ){
    *pRes = 1;
    return SQLITE_OK;
  }
  if( pCur->skip>0 ){
    pCur->skip = 0;
    *pRes = 0;
    return SQLITE_OK;
  }
  pCur->skip = 0;

  pPage = pCur->apPage[pCur->iPage];
  idx = ++pCur->aiIdx[pCur->iPage];
  assert( pPage->isInit );
  assert( idx<=pPage->nCell );

  pCur->info.nSize = 0;
................................................................................
    return rc;
  }
  pCur->atLast = 0;
  if( CURSOR_INVALID==pCur->eState ){
    *pRes = 1;
    return SQLITE_OK;
  }
  if( pCur->skip<0 ){
    pCur->skip = 0;
    *pRes = 0;
    return SQLITE_OK;
  }
  pCur->skip = 0;

  pPage = pCur->apPage[pCur->iPage];
  assert( pPage->isInit );
  if( !pPage->leaf ){
    int idx = pCur->aiIdx[pCur->iPage];
    rc = moveToChild(pCur, get4byte(findCell(pPage, idx)));
    if( rc ){
................................................................................
      }
      if( rc ){
        pTrunk = 0;
        goto end_allocate_page;
      }

      k = get4byte(&pTrunk->aData[4]);
      testcase( k==(u32)(pBt->usableSize/4 - 2) );
      if( k==0 && !searchList ){
        /* The trunk has no leaves and the list is not being searched. 
        ** So extract the trunk page itself and use it as the newly 
        ** allocated page */
        assert( pPrevTrunk==0 );
        rc = sqlite3PagerWrite(pTrunk->pDbPage);
        if( rc ){
................................................................................
  assert( idx>=0 && idx<pPage->nCell );
  assert( sz==cellSize(pPage, idx) );
  assert( sqlite3PagerIswriteable(pPage->pDbPage) );
  assert( sqlite3_mutex_held(pPage->pBt->mutex) );
  data = pPage->aData;
  ptr = &data[pPage->cellOffset + 2*idx];
  pc = get2byte(ptr);
  if( NEVER(pc<pPage->hdrOffset+6+pPage->childPtrSize)
     || (pc+sz>pPage->pBt->usableSize) ){
    return SQLITE_CORRUPT_BKPT;
  }
  rc = freeSpace(pPage, pc, sz);
  if( rc!=SQLITE_OK ){
    return rc;
  }
................................................................................
  ** cursors open on the row being replaced (assuming this is a replace
  ** operation - if it is not, the following is a no-op).  */
  if( pCur->pKeyInfo==0 ){
    invalidateIncrblobCursors(p, pCur->pgnoRoot, nKey, 0);
  }

  if( pCur->eState==CURSOR_FAULT ){
    assert( pCur->skip!=SQLITE_OK );
    return pCur->skip;
  }

  /* Save the positions of any other cursors open on this table.
  **
  ** In some cases, the call to btreeMoveto() below is a no-op. For
  ** example, when inserting data into a table with auto-generated integer
  ** keys, the VDBE layer invokes sqlite3BtreeLast() to figure out the 
  ** integer key to use. It then calls this function to actually insert the 
  ** data into the intkey B-Tree. In this case btreeMoveto() recognizes
  ** that the cursor is already where it needs to be and returns without
  ** doing any work. To avoid thwarting these optimizations, it is important
  ** not to clear the cursor here.
  */
  if(
    SQLITE_OK!=(rc = saveAllCursors(pBt, pCur->pgnoRoot, pCur)) || (!loc &&
    SQLITE_OK!=(rc = btreeMoveto(pCur, pKey, nKey, appendBias, &loc))
  )){
    return rc;
  }
  assert( pCur->eState==CURSOR_VALID || (pCur->eState==CURSOR_INVALID && loc) );

  pPage = pCur->apPage[pCur->iPage];
  assert( pPage->intKey || nKey>=0 );
  assert( pPage->leaf || !pPage->intKey );

................................................................................
  ** the entry being deleted. This cell will replace the cell being deleted
  ** from the internal node. The 'previous' entry is used for this instead
  ** of the 'next' entry, as the previous entry is always a part of the
  ** sub-tree headed by the child page of the cell being deleted. This makes
  ** balancing the tree following the delete operation easier.  */
  if( !pPage->leaf ){
    int notUsed;
    if( SQLITE_OK!=(rc = sqlite3BtreePrevious(pCur, &notUsed)) ){
      return rc;
    }
  }

  /* Save the positions of any other cursors open on this table before
  ** making any modifications. Make the page containing the entry to be 
  ** deleted writable. Then free any overflow pages associated with the 
  ** entry and finally remove the cell itself from within the page.  
  */

** a legal notice, here is a blessing:
**
**    May you do good and not evil.
**    May you find forgiveness for yourself and forgive others.
**    May you share freely, never taking more than you give.
**
*************************************************************************
** $Id: btree.c,v 1.689 2009/07/15 17:25:46 drh Exp $
**
** This file implements a external (disk-based) database using BTrees.
** See the header comment on "btreeInt.h" for additional information.
** Including a description of file format and an overview of operation.
*/
#include "btreeInt.h"

................................................................................
** optimization 2 above is ommitted if the corresponding bit is already
** set in BtShared.pHasContent. The contents of the bitvec are cleared
** at the end of every transaction.
*/
static int btreeSetHasContent(BtShared *pBt, Pgno pgno){
  int rc = SQLITE_OK;
  if( !pBt->pHasContent ){
    int nPage = 100;
    sqlite3PagerPagecount(pBt->pPager, &nPage);
    /* If sqlite3PagerPagecount() fails there is no harm because the
    ** nPage variable is unchanged from its default value of 100 */
    pBt->pHasContent = sqlite3BitvecCreate((u32)nPage);
    if( !pBt->pHasContent ){
      rc = SQLITE_NOMEM;

    }
  }
  if( rc==SQLITE_OK && pgno<=sqlite3BitvecSize(pBt->pHasContent) ){
    rc = sqlite3BitvecSet(pBt->pHasContent, pgno);
  }
  return rc;
}
................................................................................
  int rc;

  assert( CURSOR_VALID==pCur->eState );
  assert( 0==pCur->pKey );
  assert( cursorHoldsMutex(pCur) );

  rc = sqlite3BtreeKeySize(pCur, &pCur->nKey);
  assert( rc==SQLITE_OK );  /* Cannot fail since pCur->eState==VALID */

  /* If this is an intKey table, then the above call to BtreeKeySize()
  ** stores the integer key in pCur->nKey. In this case this value is
  ** all that is required. Otherwise, if pCur is not open on an intKey
  ** table, then malloc space for and store the pCur->nKey bytes of key 
  ** data.
  */
  if( 0==pCur->apPage[0]->intKey ){
    void *pKey = sqlite3Malloc( (int)pCur->nKey );
    if( pKey ){
      rc = sqlite3BtreeKey(pCur, 0, (int)pCur->nKey, pKey);
      if( rc==SQLITE_OK ){
        pCur->pKey = pKey;
      }else{
        sqlite3_free(pKey);
................................................................................
** saveCursorPosition().
*/
static int btreeRestoreCursorPosition(BtCursor *pCur){
  int rc;
  assert( cursorHoldsMutex(pCur) );
  assert( pCur->eState>=CURSOR_REQUIRESEEK );
  if( pCur->eState==CURSOR_FAULT ){
    return pCur->skipNext;
  }
  pCur->eState = CURSOR_INVALID;
  rc = btreeMoveto(pCur, pCur->pKey, pCur->nKey, 0, &pCur->skipNext);
  if( rc==SQLITE_OK ){
    sqlite3_free(pCur->pKey);
    pCur->pKey = 0;
    assert( pCur->eState==CURSOR_VALID || pCur->eState==CURSOR_INVALID );
  }
  return rc;
}
................................................................................
  int rc;

  rc = restoreCursorPosition(pCur);
  if( rc ){
    *pHasMoved = 1;
    return rc;
  }
  if( pCur->eState!=CURSOR_VALID || pCur->skipNext!=0 ){
    *pHasMoved = 1;
  }else{
    *pHasMoved = 0;
  }
  return SQLITE_OK;
}

................................................................................
    goto trans_begun;
  }
#endif

  /* Any read-only or read-write transaction implies a read-lock on 
  ** page 1. So if some other shared-cache client already has a write-lock 
  ** on page 1, the transaction cannot be opened. */
  rc = querySharedCacheTableLock(p, MASTER_ROOT, READ_LOCK);
  if( SQLITE_OK!=rc ) goto trans_begun;


  do {
    /* Call lockBtree() until either pBt->pPage1 is populated or
    ** lockBtree() returns something other than SQLITE_OK. lockBtree()
    ** may return SQLITE_OK but leave pBt->pPage1 set to 0 if after
    ** reading page 1 it discovers that the page-size of the database 
    ** file is not pBt->pageSize. In this case lockBtree() will update
................................................................................
void sqlite3BtreeTripAllCursors(Btree *pBtree, int errCode){
  BtCursor *p;
  sqlite3BtreeEnter(pBtree);
  for(p=pBtree->pBt->pCursor; p; p=p->pNext){
    int i;
    sqlite3BtreeClearCursor(p);
    p->eState = CURSOR_FAULT;
    p->skipNext = errCode;
    for(i=0; i<=p->iPage; i++){
      releasePage(p->apPage[i]);
      p->apPage[i] = 0;
    }
  }
  sqlite3BtreeLeave(pBtree);
}
................................................................................

  assert( cursorHoldsMutex(pCur) );
  assert( CURSOR_INVALID < CURSOR_REQUIRESEEK );
  assert( CURSOR_VALID   < CURSOR_REQUIRESEEK );
  assert( CURSOR_FAULT   > CURSOR_REQUIRESEEK );
  if( pCur->eState>=CURSOR_REQUIRESEEK ){
    if( pCur->eState==CURSOR_FAULT ){
      assert( pCur->skipNext!=SQLITE_OK );
      return pCur->skipNext;
    }
    sqlite3BtreeClearCursor(pCur);
  }

  if( pCur->iPage>=0 ){
    int i;
    for(i=1; i<=pCur->iPage; i++){
      releasePage(pCur->apPage[i]);
    }
    pCur->iPage = 0;
  }else{

    rc = getAndInitPage(pBt, pCur->pgnoRoot, &pCur->apPage[0]);

    if( rc!=SQLITE_OK ){
      pCur->eState = CURSOR_INVALID;
      return rc;
    }
    pCur->iPage = 0;

    /* If pCur->pKeyInfo is not NULL, then the caller that opened this cursor
    ** expected to open it on an index b-tree. Otherwise, if pKeyInfo is
................................................................................
    return rc;
  }
  assert( pRes!=0 );
  if( CURSOR_INVALID==pCur->eState ){
    *pRes = 1;
    return SQLITE_OK;
  }
  if( pCur->skipNext>0 ){
    pCur->skipNext = 0;
    *pRes = 0;
    return SQLITE_OK;
  }
  pCur->skipNext = 0;

  pPage = pCur->apPage[pCur->iPage];
  idx = ++pCur->aiIdx[pCur->iPage];
  assert( pPage->isInit );
  assert( idx<=pPage->nCell );

  pCur->info.nSize = 0;
................................................................................
    return rc;
  }
  pCur->atLast = 0;
  if( CURSOR_INVALID==pCur->eState ){
    *pRes = 1;
    return SQLITE_OK;
  }
  if( pCur->skipNext<0 ){
    pCur->skipNext = 0;
    *pRes = 0;
    return SQLITE_OK;
  }
  pCur->skipNext = 0;

  pPage = pCur->apPage[pCur->iPage];
  assert( pPage->isInit );
  if( !pPage->leaf ){
    int idx = pCur->aiIdx[pCur->iPage];
    rc = moveToChild(pCur, get4byte(findCell(pPage, idx)));
    if( rc ){
................................................................................
      }
      if( rc ){
        pTrunk = 0;
        goto end_allocate_page;
      }

      k = get4byte(&pTrunk->aData[4]);

      if( k==0 && !searchList ){
        /* The trunk has no leaves and the list is not being searched. 
        ** So extract the trunk page itself and use it as the newly 
        ** allocated page */
        assert( pPrevTrunk==0 );
        rc = sqlite3PagerWrite(pTrunk->pDbPage);
        if( rc ){
................................................................................
  assert( idx>=0 && idx<pPage->nCell );
  assert( sz==cellSize(pPage, idx) );
  assert( sqlite3PagerIswriteable(pPage->pDbPage) );
  assert( sqlite3_mutex_held(pPage->pBt->mutex) );
  data = pPage->aData;
  ptr = &data[pPage->cellOffset + 2*idx];
  pc = get2byte(ptr);
  if( (pc<pPage->hdrOffset+6+pPage->childPtrSize)
     || (pc+sz>pPage->pBt->usableSize) ){
    return SQLITE_CORRUPT_BKPT;
  }
  rc = freeSpace(pPage, pc, sz);
  if( rc!=SQLITE_OK ){
    return rc;
  }
................................................................................
  ** cursors open on the row being replaced (assuming this is a replace
  ** operation - if it is not, the following is a no-op).  */
  if( pCur->pKeyInfo==0 ){
    invalidateIncrblobCursors(p, pCur->pgnoRoot, nKey, 0);
  }

  if( pCur->eState==CURSOR_FAULT ){
    assert( pCur->skipNext!=SQLITE_OK );
    return pCur->skipNext;
  }

  /* Save the positions of any other cursors open on this table.
  **
  ** In some cases, the call to btreeMoveto() below is a no-op. For
  ** example, when inserting data into a table with auto-generated integer
  ** keys, the VDBE layer invokes sqlite3BtreeLast() to figure out the 
  ** integer key to use. It then calls this function to actually insert the 
  ** data into the intkey B-Tree. In this case btreeMoveto() recognizes
  ** that the cursor is already where it needs to be and returns without
  ** doing any work. To avoid thwarting these optimizations, it is important
  ** not to clear the cursor here.
  */
  rc = saveAllCursors(pBt, pCur->pgnoRoot, pCur);
  if( rc ) return rc;
  if( !loc ){
    rc = btreeMoveto(pCur, pKey, nKey, appendBias, &loc);
    if( rc ) return rc;
  }
  assert( pCur->eState==CURSOR_VALID || (pCur->eState==CURSOR_INVALID && loc) );

  pPage = pCur->apPage[pCur->iPage];
  assert( pPage->intKey || nKey>=0 );
  assert( pPage->leaf || !pPage->intKey );

................................................................................
  ** the entry being deleted. This cell will replace the cell being deleted
  ** from the internal node. The 'previous' entry is used for this instead
  ** of the 'next' entry, as the previous entry is always a part of the
  ** sub-tree headed by the child page of the cell being deleted. This makes
  ** balancing the tree following the delete operation easier.  */
  if( !pPage->leaf ){
    int notUsed;
    rc = sqlite3BtreePrevious(pCur, &notUsed);
    if( rc ) return rc;

  }

  /* Save the positions of any other cursors open on this table before
  ** making any modifications. Make the page containing the entry to be 
  ** deleted writable. Then free any overflow pages associated with the 
  ** entry and finally remove the cell itself from within the page.  
  */

** a legal notice, here is a blessing:
**
**    May you do good and not evil.
**    May you find forgiveness for yourself and forgive others.
**    May you share freely, never taking more than you give.
**
*************************************************************************
** $Id: btreeInt.h,v 1.51 2009/07/09 05:07:38 danielk1977 Exp $
**
** This file implements a external (disk-based) database using BTrees.
** For a detailed discussion of BTrees, refer to
**
**     Donald E. Knuth, THE ART OF COMPUTER PROGRAMMING, Volume 3:
**     "Sorting And Searching", pages 473-480. Addison-Wesley
**     Publishing Company, Reading, Massachusetts.
................................................................................
  CellInfo info;            /* A parse of the cell we are pointing at */
  u8 wrFlag;                /* True if writable */
  u8 atLast;                /* Cursor pointing to the last entry */
  u8 validNKey;             /* True if info.nKey is valid */
  u8 eState;                /* One of the CURSOR_XXX constants (see below) */
  void *pKey;      /* Saved key that was cursor's last known position */
  i64 nKey;        /* Size of pKey, or last integer key */
  int skip;        /* (skip<0) -> Prev() is a no-op. (skip>0) -> Next() is */
#ifndef SQLITE_OMIT_INCRBLOB
  u8 isIncrblobHandle;      /* True if this cursor is an incr. io handle */
  Pgno *aOverflow;          /* Cache of overflow page locations */
#endif
  i16 iPage;                            /* Index of current page in apPage */
  MemPage *apPage[BTCURSOR_MAX_DEPTH];  /* Pages from root to current page */
  u16 aiIdx[BTCURSOR_MAX_DEPTH];        /* Current index in apPage[i] */
................................................................................
/*
** Read or write a two- and four-byte big-endian integer values.
*/
#define get2byte(x)   ((x)[0]<<8 | (x)[1])
#define put2byte(p,v) ((p)[0] = (u8)((v)>>8), (p)[1] = (u8)(v))
#define get4byte sqlite3Get4byte
#define put4byte sqlite3Put4byte

** a legal notice, here is a blessing:
**
**    May you do good and not evil.
**    May you find forgiveness for yourself and forgive others.
**    May you share freely, never taking more than you give.
**
*************************************************************************
** $Id: btreeInt.h,v 1.52 2009/07/15 17:25:46 drh Exp $
**
** This file implements a external (disk-based) database using BTrees.
** For a detailed discussion of BTrees, refer to
**
**     Donald E. Knuth, THE ART OF COMPUTER PROGRAMMING, Volume 3:
**     "Sorting And Searching", pages 473-480. Addison-Wesley
**     Publishing Company, Reading, Massachusetts.
................................................................................
  CellInfo info;            /* A parse of the cell we are pointing at */
  u8 wrFlag;                /* True if writable */
  u8 atLast;                /* Cursor pointing to the last entry */
  u8 validNKey;             /* True if info.nKey is valid */
  u8 eState;                /* One of the CURSOR_XXX constants (see below) */
  void *pKey;      /* Saved key that was cursor's last known position */
  i64 nKey;        /* Size of pKey, or last integer key */
  int skipNext;    /* Prev() is noop if negative. Next() is noop if positive */
#ifndef SQLITE_OMIT_INCRBLOB
  u8 isIncrblobHandle;      /* True if this cursor is an incr. io handle */
  Pgno *aOverflow;          /* Cache of overflow page locations */
#endif
  i16 iPage;                            /* Index of current page in apPage */
  MemPage *apPage[BTCURSOR_MAX_DEPTH];  /* Pages from root to current page */
  u16 aiIdx[BTCURSOR_MAX_DEPTH];        /* Current index in apPage[i] */
................................................................................
/*
** Read or write a two- and four-byte big-endian integer values.
*/
#define get2byte(x)   ((x)[0]<<8 | (x)[1])
#define put2byte(p,v) ((p)[0] = (u8)((v)>>8), (p)[1] = (u8)(v))
#define get4byte sqlite3Get4byte
#define put4byte sqlite3Put4byte