btree.c

sqlite的最新源码 This ZIP archive contains preprocessed C code for the SQLite library as individual sour

  hdr = pPage->hdrOffset;
  addr = hdr + 1;
  while( (pbegin = get2byte(&data[addr]))<start && pbegin>0 ){
    assert( pbegin<=pPage->pBt->usableSize-4 );
    if( pbegin<=addr ) {
      return SQLITE_CORRUPT_BKPT;
    }
    addr = pbegin;
  }
  if ( pbegin>pPage->pBt->usableSize-4 ) {
    return SQLITE_CORRUPT_BKPT;
  }
  assert( pbegin>addr || pbegin==0 );
  put2byte(&data[addr], start);
  put2byte(&data[start], pbegin);
  put2byte(&data[start+2], size);
  pPage->nFree += size;

  /* Coalesce adjacent free blocks */
  addr = pPage->hdrOffset + 1;
  while( (pbegin = get2byte(&data[addr]))>0 ){
    int pnext, psize;
    assert( pbegin>addr );
    assert( pbegin<=pPage->pBt->usableSize-4 );
    pnext = get2byte(&data[pbegin]);
    psize = get2byte(&data[pbegin+2]);
    if( pbegin + psize + 3 >= pnext && pnext>0 ){
      int frag = pnext - (pbegin+psize);
      if( (frag<0) || (frag>data[pPage->hdrOffset+7]) ){
        return SQLITE_CORRUPT_BKPT;
      }
      data[pPage->hdrOffset+7] -= frag;
      put2byte(&data[pbegin], get2byte(&data[pnext]));
      put2byte(&data[pbegin+2], pnext+get2byte(&data[pnext+2])-pbegin);
    }else{
      addr = pbegin;
    }
  }

  /* If the cell content area begins with a freeblock, remove it. */
  if( data[hdr+1]==data[hdr+5] && data[hdr+2]==data[hdr+6] ){
    int top;
    pbegin = get2byte(&data[hdr+1]);
    memcpy(&data[hdr+1], &data[pbegin], 2);
    top = get2byte(&data[hdr+5]);
    put2byte(&data[hdr+5], top + get2byte(&data[pbegin+2]));
  }
  return SQLITE_OK;
}

/*
** Decode the flags byte (the first byte of the header) for a page
** and initialize fields of the MemPage structure accordingly.
**
** Only the following combinations are supported.  Anything different
** indicates a corrupt database files:
**
**         PTF_ZERODATA
**         PTF_ZERODATA | PTF_LEAF
**         PTF_LEAFDATA | PTF_INTKEY
**         PTF_LEAFDATA | PTF_INTKEY | PTF_LEAF
*/
static int decodeFlags(MemPage *pPage, int flagByte){
  BtShared *pBt;     /* A copy of pPage->pBt */

  assert( pPage->hdrOffset==(pPage->pgno==1 ? 100 : 0) );
  assert( sqlite3_mutex_held(pPage->pBt->mutex) );
  pPage->leaf = flagByte>>3;  assert( PTF_LEAF == 1<<3 );
  flagByte &= ~PTF_LEAF;
  pPage->childPtrSize = 4-4*pPage->leaf;
  pBt = pPage->pBt;
  if( flagByte==(PTF_LEAFDATA | PTF_INTKEY) ){
    pPage->intKey = 1;
    pPage->hasData = pPage->leaf;
    pPage->maxLocal = pBt->maxLeaf;
    pPage->minLocal = pBt->minLeaf;
  }else if( flagByte==PTF_ZERODATA ){
    pPage->intKey = 0;
    pPage->hasData = 0;
    pPage->maxLocal = pBt->maxLocal;
    pPage->minLocal = pBt->minLocal;
  }else{
    return SQLITE_CORRUPT_BKPT;
  }
  return SQLITE_OK;
}

/*
** Initialize the auxiliary information for a disk block.
**
** Return SQLITE_OK on success.  If we see that the page does
** not contain a well-formed database page, then return 
** SQLITE_CORRUPT.  Note that a return of SQLITE_OK does not
** guarantee that the page is well-formed.  It only shows that
** we failed to detect any corruption.
*/
int sqlite3BtreeInitPage(MemPage *pPage){

  assert( pPage->pBt!=0 );
  assert( sqlite3_mutex_held(pPage->pBt->mutex) );
  assert( pPage->pgno==sqlite3PagerPagenumber(pPage->pDbPage) );
  assert( pPage == sqlite3PagerGetExtra(pPage->pDbPage) );
  assert( pPage->aData == sqlite3PagerGetData(pPage->pDbPage) );

  if( !pPage->isInit ){
    int pc;            /* Address of a freeblock within pPage->aData[] */
    int hdr;           /* Offset to beginning of page header */
    u8 *data;          /* Equal to pPage->aData */
    BtShared *pBt;        /* The main btree structure */
    int usableSize;    /* Amount of usable space on each page */
    int cellOffset;    /* Offset from start of page to first cell pointer */
    int nFree;         /* Number of unused bytes on the page */
    int top;           /* First byte of the cell content area */

    pBt = pPage->pBt;

    hdr = pPage->hdrOffset;
    data = pPage->aData;
    if( decodeFlags(pPage, data[hdr]) ) return SQLITE_CORRUPT_BKPT;
    assert( pBt->pageSize>=512 && pBt->pageSize<=32768 );
    pPage->maskPage = pBt->pageSize - 1;
    pPage->nOverflow = 0;
    usableSize = pBt->usableSize;
    pPage->cellOffset = cellOffset = hdr + 12 - 4*pPage->leaf;
    top = get2byte(&data[hdr+5]);
    pPage->nCell = get2byte(&data[hdr+3]);
    if( pPage->nCell>MX_CELL(pBt) ){
      /* To many cells for a single page.  The page must be corrupt */
      return SQLITE_CORRUPT_BKPT;
    }
  
    /* Compute the total free space on the page */
    pc = get2byte(&data[hdr+1]);
    nFree = data[hdr+7] + top - (cellOffset + 2*pPage->nCell);
    while( pc>0 ){
      int next, size;
      if( pc>usableSize-4 ){
        /* Free block is off the page */
        return SQLITE_CORRUPT_BKPT; 
      }
      next = get2byte(&data[pc]);
      size = get2byte(&data[pc+2]);
      if( next>0 && next<=pc+size+3 ){
        /* Free blocks must be in accending order */
        return SQLITE_CORRUPT_BKPT; 
      }
      nFree += size;
      pc = next;
    }
    pPage->nFree = nFree;
    if( nFree>=usableSize ){
      /* Free space cannot exceed total page size */
      return SQLITE_CORRUPT_BKPT; 
    }

#if 0
  /* Check that all the offsets in the cell offset array are within range. 
  ** 
  ** Omitting this consistency check and using the pPage->maskPage mask
  ** to prevent overrunning the page buffer in findCell() results in a
  ** 2.5% performance gain.
  */
  {
    u8 *pOff;        /* Iterator used to check all cell offsets are in range */
    u8 *pEnd;        /* Pointer to end of cell offset array */
    u8 mask;         /* Mask of bits that must be zero in MSB of cell offsets */
    mask = ~(((u8)(pBt->pageSize>>8))-1);
    pEnd = &data[cellOffset + pPage->nCell*2];
    for(pOff=&data[cellOffset]; pOff!=pEnd && !((*pOff)&mask); pOff+=2);
    if( pOff!=pEnd ){
      return SQLITE_CORRUPT_BKPT;
    }
  }
#endif

    pPage->isInit = 1;
  }
  return SQLITE_OK;
}

/*
** Set up a raw page so that it looks like a database page holding
** no entries.
*/
static void zeroPage(MemPage *pPage, int flags){
  unsigned char *data = pPage->aData;
  BtShared *pBt = pPage->pBt;
  int hdr = pPage->hdrOffset;
  int first;

  assert( sqlite3PagerPagenumber(pPage->pDbPage)==pPage->pgno );
  assert( sqlite3PagerGetExtra(pPage->pDbPage) == (void*)pPage );
  assert( sqlite3PagerGetData(pPage->pDbPage) == data );
  assert( sqlite3PagerIswriteable(pPage->pDbPage) );
  assert( sqlite3_mutex_held(pBt->mutex) );
  /*memset(&data[hdr], 0, pBt->usableSize - hdr);*/
  data[hdr] = flags;
  first = hdr + 8 + 4*((flags&PTF_LEAF)==0);
  memset(&data[hdr+1], 0, 4);
  data[hdr+7] = 0;
  put2byte(&data[hdr+5], pBt->usableSize);
  pPage->nFree = pBt->usableSize - first;
  decodeFlags(pPage, flags);
  pPage->hdrOffset = hdr;
  pPage->cellOffset = first;
  pPage->nOverflow = 0;
  assert( pBt->pageSize>=512 && pBt->pageSize<=32768 );
  pPage->maskPage = pBt->pageSize - 1;
  pPage->nCell = 0;
  pPage->isInit = 1;
}


/*
** Convert a DbPage obtained from the pager into a MemPage used by
** the btree layer.
*/
static MemPage *btreePageFromDbPage(DbPage *pDbPage, Pgno pgno, BtShared *pBt){
  MemPage *pPage = (MemPage*)sqlite3PagerGetExtra(pDbPage);
  pPage->aData = sqlite3PagerGetData(pDbPage);
  pPage->pDbPage = pDbPage;
  pPage->pBt = pBt;
  pPage->pgno = pgno;
  pPage->hdrOffset = pPage->pgno==1 ? 100 : 0;
  return pPage; 
}

/*
** Get a page from the pager.  Initialize the MemPage.pBt and
** MemPage.aData elements if needed.
**
** If the noContent flag is set, it means that we do not care about
** the content of the page at this time.  So do not go to the disk
** to fetch the content.  Just fill in the content with zeros for now.
** If in the future we call sqlite3PagerWrite() on this page, that
** means we have started to be concerned about content and the disk
** read should occur at that point.
*/
int sqlite3BtreeGetPage(
  BtShared *pBt,       /* The btree */
  Pgno pgno,           /* Number of the page to fetch */
  MemPage **ppPage,    /* Return the page in this parameter */
  int noContent        /* Do not load page content if true */
){
  int rc;
  DbPage *pDbPage;

  assert( sqlite3_mutex_held(pBt->mutex) );
  rc = sqlite3PagerAcquire(pBt->pPager, pgno, (DbPage**)&pDbPage, noContent);
  if( rc ) return rc;
  *ppPage = btreePageFromDbPage(pDbPage, pgno, pBt);
  return SQLITE_OK;
}

/*
** Return the size of the database file in pages. If there is any kind of
** error, return ((unsigned int)-1).
*/
static Pgno pagerPagecount(BtShared *pBt){
  int nPage = -1;
  int rc;
  assert( pBt->pPage1 );
  rc = sqlite3PagerPagecount(pBt->pPager, &nPage);
  assert( rc==SQLITE_OK || nPage==-1 );
  return (Pgno)nPage;
}

/*
** Get a page from the pager and initialize it.  This routine
** is just a convenience wrapper around separate calls to
** sqlite3BtreeGetPage() and sqlite3BtreeInitPage().
*/
static int getAndInitPage(
  BtShared *pBt,          /* The database file */
  Pgno pgno,           /* Number of the page to get */
  MemPage **ppPage     /* Write the page pointer here */
){
  int rc;
  DbPage *pDbPage;
  MemPage *pPage;

  assert( sqlite3_mutex_held(pBt->mutex) );
  if( pgno==0 ){
    return SQLITE_CORRUPT_BKPT; 
  }

  /* It is often the case that the page we want is already in cache.
  ** If so, get it directly.  This saves us from having to call
  ** pagerPagecount() to make sure pgno is within limits, which results
  ** in a measureable performance improvements.
  */
  pDbPage = sqlite3PagerLookup(pBt->pPager, pgno);
  if( pDbPage ){
    /* Page is already in cache */
    *ppPage = pPage = btreePageFromDbPage(pDbPage, pgno, pBt);
    rc = SQLITE_OK;
  }else{
    /* Page not in cache.  Acquire it. */
    if( pgno>pagerPagecount(pBt) ){
      return SQLITE_CORRUPT_BKPT; 
    }
    rc = sqlite3BtreeGetPage(pBt, pgno, ppPage, 0);
    if( rc ) return rc;
    pPage = *ppPage;
  }
  if( !pPage->isInit ){
    rc = sqlite3BtreeInitPage(pPage);
  }
  if( rc!=SQLITE_OK ){
    releasePage(pPage);
    *ppPage = 0;
  }
  return rc;
}

/*
** Release a MemPage.  This should be called once for each prior
** call to sqlite3BtreeGetPage.
*/
static void releasePage(MemPage *pPage){
  if( pPage ){
    assert( pPage->aData );
    assert( pPage->pBt );
    assert( sqlite3PagerGetExtra(pPage->pDbPage) == (void*)pPage );
    assert( sqlite3PagerGetData(pPage->pDbPage)==pPage->aData );
    assert( sqlite3_mutex_held(pPage->pBt->mutex) );
    sqlite3PagerUnref(pPage->pDbPage);
  }
}

/*
** During a rollback, when the pager reloads information into the cache
** so that the cache is restored to its original state at the start of
** the transaction, for each page restored this routine is called.
**
** This routine needs to reset the extra data section at the end of the
** page to agree with the restored data.
*/
static void pageReinit(DbPage *pData){
  MemPage *pPage;
  pPage = (MemPage *)sqlite3PagerGetExtra(pData);
  if( pPage->isInit ){
    assert( sqlite3_mutex_held(pPage->pBt->mutex) );
    pPage->isInit = 0;
    if( sqlite3PagerPageRefcount(pData)>0 ){
      sqlite3BtreeInitPage(pPage);
    }
  }
}

/*
** Invoke the busy handler for a btree.
*/
static int btreeInvokeBusyHandler(void *pArg){
  BtShared *pBt = (BtShared*)pArg;
  assert( pBt->db );
  assert( sqlite3_mutex_held(pBt->db->mutex) );
  return sqlite3InvokeBusyHandler(&pBt->db->busyHandler);
}

/*
** Open a database file.
** 
** zFilename is the name of the database file.  If zFilename is NULL
** a new database with a random name is created.  This randomly named
** database file will be deleted when sqlite3BtreeClose() is called.
** If zFilename is ":memory:" then an in-memory database is created
** that is automatically destroyed when it is closed.
*/
int sqlite3BtreeOpen(
  const char *zFilename,  /* Name of the file containing the BTree database */
  sqlite3 *db,            /* Associated database handle */
  Btree **ppBtree,        /* Pointer to new Btree object written here */
  int flags,              /* Options */
  int vfsFlags            /* Flags passed through to sqlite3_vfs.xOpen() */
){
  sqlite3_vfs *pVfs;      /* The VFS to use for this btree */
  BtShared *pBt = 0;      /* Shared part of btree structure */
  Btree *p;               /* Handle to return */
  int rc = SQLITE_OK;
  int nReserve;
  unsigned char zDbHeader[100];

  /* Set the variable isMemdb to true for an in-memory database, or 
  ** false for a file-based database. This symbol is only required if
  ** either of the shared-data or autovacuum features are compiled 
  ** into the library.
  */
#if !defined(SQLITE_OMIT_SHARED_CACHE) || !defined(SQLITE_OMIT_AUTOVACUUM)
  #ifdef SQLITE_OMIT_MEMORYDB
    const int isMemdb = 0;
  #else
    const int isMemdb = zFilename && !strcmp(zFilename, ":memory:");
  #endif
#endif

  assert( db!=0 );
  assert( sqlite3_mutex_held(db->mutex) );

  pVfs = db->pVfs;
  p = sqlite3MallocZero(sizeof(Btree));
  if( !p ){
    return SQLITE_NOMEM;
  }
  p->inTrans = TRANS_NONE;
  p->db = db;

#if !defined(SQLITE_OMIT_SHARED_CACHE) && !defined(SQLITE_OMIT_DISKIO)
  /*
  ** If this Btree is a candidate for shared cache, try to find an
  ** existing BtShared object that we can share with
  */
  if( isMemdb==0
   && (db->flags & SQLITE_Vtab)==0
   && zFilename && zFilename[0]
  ){
    if( sqlite3GlobalConfig.sharedCacheEnabled ){
      int nFullPathname = pVfs->mxPathname+1;
      char *zFullPathname = sqlite3Malloc(nFullPathname);
      sqlite3_mutex *mutexShared;
      p->sharable = 1;
      db->flags |= SQLITE_SharedCache;
      if( !zFullPathname ){
        sqlite3_free(p);
        return SQLITE_NOMEM;
      }
      sqlite3OsFullPathname(pVfs, zFilename, nFullPathname, zFullPathname);
      mutexShared = sqlite3MutexAlloc(SQLITE_MUTEX_STATIC_MASTER);