xmlparse.cpp

C++ class libraries for network-centric, portable applications, integrated perfectly with the C++ St

/* Copyright (c) 1998, 1999, 2000 Thai Open Source Software Center Ltd
   See the file COPYING for copying permission.
*/

#include <stddef.h>
#include <string.h>                     /* memset(), memcpy() */
#include <assert.h>

#define XML_BUILDING_EXPAT 1

#ifdef COMPILED_FROM_DSP
#include "winconfig.h"
#elif defined(MACOS_CLASSIC)
#include "macconfig.h"
#elif defined(__amigaos4__)
#include "amigaconfig.h"
#elif defined(HAVE_EXPAT_CONFIG_H)
#include "expat_config.h"
#endif /* ndef COMPILED_FROM_DSP */

#include "Poco/XML/expat.h"

#ifdef XML_UNICODE
#define XML_ENCODE_MAX XML_UTF16_ENCODE_MAX
#define XmlConvert XmlUtf16Convert
#define XmlGetInternalEncoding XmlGetUtf16InternalEncoding
#define XmlGetInternalEncodingNS XmlGetUtf16InternalEncodingNS
#define XmlEncode XmlUtf16Encode
#define MUST_CONVERT(enc, s) (!(enc)->isUtf16 || (((unsigned long)s) & 1))
typedef unsigned short ICHAR;
#else
#define XML_ENCODE_MAX XML_UTF8_ENCODE_MAX
#define XmlConvert XmlUtf8Convert
#define XmlGetInternalEncoding XmlGetUtf8InternalEncoding
#define XmlGetInternalEncodingNS XmlGetUtf8InternalEncodingNS
#define XmlEncode XmlUtf8Encode
#define MUST_CONVERT(enc, s) (!(enc)->isUtf8)
typedef char ICHAR;
#endif


#ifndef XML_NS

#define XmlInitEncodingNS XmlInitEncoding
#define XmlInitUnknownEncodingNS XmlInitUnknownEncoding
#undef XmlGetInternalEncodingNS
#define XmlGetInternalEncodingNS XmlGetInternalEncoding
#define XmlParseXmlDeclNS XmlParseXmlDecl

#endif

#ifdef XML_UNICODE

#ifdef XML_UNICODE_WCHAR_T
#define XML_T(x) (const wchar_t)x
#define XML_L(x) L ## x
#else
#define XML_T(x) (const unsigned short)x
#define XML_L(x) x
#endif

#else

#define XML_T(x) x
#define XML_L(x) x

#endif

/* Round up n to be a multiple of sz, where sz is a power of 2. */
#define ROUND_UP(n, sz) (((n) + ((sz) - 1)) & ~((sz) - 1))

/* Handle the case where memmove() doesn't exist. */
#ifndef HAVE_MEMMOVE
#ifdef HAVE_BCOPY
#define memmove(d,s,l) bcopy((s),(d),(l))
#else
#error memmove does not exist on this platform, nor is a substitute available
#endif /* HAVE_BCOPY */
#endif /* HAVE_MEMMOVE */

#include "internal.h"
#include "xmltok.h"
#include "xmlrole.h"

typedef const XML_Char *KEY;

typedef struct {
  KEY name;
} NAMED;

typedef struct {
  NAMED **v;
  unsigned char power;
  size_t size;
  size_t used;
  const XML_Memory_Handling_Suite *mem;
} HASH_TABLE;

/* Basic character hash algorithm, taken from Python's string hash:
   h = h * 1000003 ^ character, the constant being a prime number.

*/
#ifdef XML_UNICODE
#define CHAR_HASH(h, c) \
  (((h) * 0xF4243) ^ (unsigned short)(c))
#else
#define CHAR_HASH(h, c) \
  (((h) * 0xF4243) ^ (unsigned char)(c))
#endif

/* For probing (after a collision) we need a step size relative prime
   to the hash table size, which is a power of 2. We use double-hashing,
   since we can calculate a second hash value cheaply by taking those bits
   of the first hash value that were discarded (masked out) when the table
   index was calculated: index = hash & mask, where mask = table->size - 1.
   We limit the maximum step size to table->size / 4 (mask >> 2) and make
   it odd, since odd numbers are always relative prime to a power of 2.
*/
#define SECOND_HASH(hash, mask, power) \
  ((((hash) & ~(mask)) >> ((power) - 1)) & ((mask) >> 2))
#define PROBE_STEP(hash, mask, power) \
  ((unsigned char)((SECOND_HASH(hash, mask, power)) | 1))

typedef struct {
  NAMED **p;
  NAMED **end;
} HASH_TABLE_ITER;

#define INIT_TAG_BUF_SIZE 32  /* must be a multiple of sizeof(XML_Char) */
#define INIT_DATA_BUF_SIZE 1024
#define INIT_ATTS_SIZE 16
#define INIT_ATTS_VERSION 0xFFFFFFFF
#define INIT_BLOCK_SIZE 1024
#define INIT_BUFFER_SIZE 1024

#define EXPAND_SPARE 24

typedef struct binding {
  struct prefix *prefix;
  struct binding *nextTagBinding;
  struct binding *prevPrefixBinding;
  const struct attribute_id *attId;
  XML_Char *uri;
  int uriLen;
  int uriAlloc;
} BINDING;

typedef struct prefix {
  const XML_Char *name;
  BINDING *binding;
} PREFIX;

typedef struct {
  const XML_Char *str;
  const XML_Char *localPart;
  const XML_Char *prefix;
  int strLen;
  int uriLen;
  int prefixLen;
} TAG_NAME;

/* TAG represents an open element.
   The name of the element is stored in both the document and API
   encodings.  The memory buffer 'buf' is a separately-allocated
   memory area which stores the name.  During the XML_Parse()/
   XMLParseBuffer() when the element is open, the memory for the 'raw'
   version of the name (in the document encoding) is shared with the
   document buffer.  If the element is open across calls to
   XML_Parse()/XML_ParseBuffer(), the buffer is re-allocated to
   contain the 'raw' name as well.

   A parser re-uses these structures, maintaining a list of allocated
   TAG objects in a free list.
*/
typedef struct tag {
  struct tag *parent;           /* parent of this element */
  const char *rawName;          /* tagName in the original encoding */
  int rawNameLength;
  TAG_NAME name;                /* tagName in the API encoding */
  char *buf;                    /* buffer for name components */
  char *bufEnd;                 /* end of the buffer */
  BINDING *bindings;
} TAG;

typedef struct {
  const XML_Char *name;
  const XML_Char *textPtr;
  int textLen;                  /* length in XML_Chars */
  int processed;                /* # of processed bytes - when suspended */
  const XML_Char *systemId;
  const XML_Char *base;
  const XML_Char *publicId;
  const XML_Char *notation;
  XML_Bool open;
  XML_Bool is_param;
  XML_Bool is_internal; /* true if declared in internal subset outside PE */
} ENTITY;

typedef struct {
  enum XML_Content_Type         type;
  enum XML_Content_Quant        quant;
  const XML_Char *              name;
  int                           firstchild;
  int                           lastchild;
  int                           childcnt;
  int                           nextsib;
} CONTENT_SCAFFOLD;

#define INIT_SCAFFOLD_ELEMENTS 32

typedef struct block {
  struct block *next;
  int size;
  XML_Char s[1];
} BLOCK;

typedef struct {
  BLOCK *blocks;
  BLOCK *freeBlocks;
  const XML_Char *end;
  XML_Char *ptr;
  XML_Char *start;
  const XML_Memory_Handling_Suite *mem;
} STRING_POOL;

/* The XML_Char before the name is used to determine whether
   an attribute has been specified. */
typedef struct attribute_id {
  XML_Char *name;
  PREFIX *prefix;
  XML_Bool maybeTokenized;
  XML_Bool xmlns;
} ATTRIBUTE_ID;

typedef struct {
  const ATTRIBUTE_ID *id;
  XML_Bool isCdata;
  const XML_Char *value;
} DEFAULT_ATTRIBUTE;

typedef struct {
  unsigned long version;
  unsigned long hash;
  const XML_Char *uriName;
} NS_ATT;

typedef struct {
  const XML_Char *name;
  PREFIX *prefix;
  const ATTRIBUTE_ID *idAtt;
  int nDefaultAtts;
  int allocDefaultAtts;
  DEFAULT_ATTRIBUTE *defaultAtts;
} ELEMENT_TYPE;

typedef struct {
  HASH_TABLE generalEntities;
  HASH_TABLE elementTypes;
  HASH_TABLE attributeIds;
  HASH_TABLE prefixes;
  STRING_POOL pool;
  STRING_POOL entityValuePool;
  /* false once a parameter entity reference has been skipped */
  XML_Bool keepProcessing;
  /* true once an internal or external PE reference has been encountered;
     this includes the reference to an external subset */
  XML_Bool hasParamEntityRefs;
  XML_Bool standalone;
#ifdef XML_DTD
  /* indicates if external PE has been read */
  XML_Bool paramEntityRead;
  HASH_TABLE paramEntities;
#endif /* XML_DTD */
  PREFIX defaultPrefix;
  /* === scaffolding for building content model === */
  XML_Bool in_eldecl;
  CONTENT_SCAFFOLD *scaffold;
  unsigned contentStringLen;
  unsigned scaffSize;
  unsigned scaffCount;
  int scaffLevel;
  int *scaffIndex;
} DTD;

typedef struct open_internal_entity {
  const char *internalEventPtr;
  const char *internalEventEndPtr;
  struct open_internal_entity *next;
  ENTITY *entity;
  int startTagLevel;
  XML_Bool betweenDecl; /* WFC: PE Between Declarations */
} OPEN_INTERNAL_ENTITY;

typedef enum XML_Error PTRCALL Processor(XML_Parser parser,
                                         const char *start,
                                         const char *end,
                                         const char **endPtr);

static Processor prologProcessor;
static Processor prologInitProcessor;
static Processor contentProcessor;
static Processor cdataSectionProcessor;
#ifdef XML_DTD
static Processor ignoreSectionProcessor;
static Processor externalParEntProcessor;
static Processor externalParEntInitProcessor;
static Processor entityValueProcessor;
static Processor entityValueInitProcessor;
#endif /* XML_DTD */
static Processor epilogProcessor;
static Processor errorProcessor;
static Processor externalEntityInitProcessor;
static Processor externalEntityInitProcessor2;
static Processor externalEntityInitProcessor3;
static Processor externalEntityContentProcessor;
static Processor internalEntityProcessor;

static enum XML_Error
handleUnknownEncoding(XML_Parser parser, const XML_Char *encodingName);
static enum XML_Error
processXmlDecl(XML_Parser parser, int isGeneralTextEntity,
               const char *s, const char *next);
static enum XML_Error
initializeEncoding(XML_Parser parser);
static enum XML_Error
doProlog(XML_Parser parser, const ENCODING *enc, const char *s, 
         const char *end, int tok, const char *next, const char **nextPtr, 
         XML_Bool haveMore);
static enum XML_Error
processInternalEntity(XML_Parser parser, ENTITY *entity, 
                      XML_Bool betweenDecl);
static enum XML_Error
doContent(XML_Parser parser, int startTagLevel, const ENCODING *enc,
          const char *start, const char *end, const char **endPtr, 
          XML_Bool haveMore);
static enum XML_Error
doCdataSection(XML_Parser parser, const ENCODING *, const char **startPtr,
               const char *end, const char **nextPtr, XML_Bool haveMore);
#ifdef XML_DTD
static enum XML_Error
doIgnoreSection(XML_Parser parser, const ENCODING *, const char **startPtr,
                const char *end, const char **nextPtr, XML_Bool haveMore);
#endif /* XML_DTD */

static enum XML_Error
storeAtts(XML_Parser parser, const ENCODING *, const char *s,
          TAG_NAME *tagNamePtr, BINDING **bindingsPtr);
static enum XML_Error
addBinding(XML_Parser parser, PREFIX *prefix, const ATTRIBUTE_ID *attId,
           const XML_Char *uri, BINDING **bindingsPtr);
static int
defineAttribute(ELEMENT_TYPE *type, ATTRIBUTE_ID *, XML_Bool isCdata, 
                XML_Bool isId, const XML_Char *dfltValue, XML_Parser parser);
static enum XML_Error
storeAttributeValue(XML_Parser parser, const ENCODING *, XML_Bool isCdata,
                    const char *, const char *, STRING_POOL *);
static enum XML_Error
appendAttributeValue(XML_Parser parser, const ENCODING *, XML_Bool isCdata,
                     const char *, const char *, STRING_POOL *);
static ATTRIBUTE_ID *
getAttributeId(XML_Parser parser, const ENCODING *enc, const char *start,
               const char *end);
static int
setElementTypePrefix(XML_Parser parser, ELEMENT_TYPE *);
static enum XML_Error
storeEntityValue(XML_Parser parser, const ENCODING *enc, const char *start,
                 const char *end);
static int
reportProcessingInstruction(XML_Parser parser, const ENCODING *enc,
                            const char *start, const char *end);
static int
reportComment(XML_Parser parser, const ENCODING *enc, const char *start,
              const char *end);
static void
reportDefault(XML_Parser parser, const ENCODING *enc, const char *start,
              const char *end);

static const XML_Char * getContext(XML_Parser parser);
static XML_Bool
setContext(XML_Parser parser, const XML_Char *context);

static void FASTCALL normalizePublicId(XML_Char *s);

static DTD * dtdCreate(const XML_Memory_Handling_Suite *ms);
/* do not call if parentParser != NULL */
static void dtdReset(DTD *p, const XML_Memory_Handling_Suite *ms);
static void
dtdDestroy(DTD *p, XML_Bool isDocEntity, const XML_Memory_Handling_Suite *ms);
static int
dtdCopy(DTD *newDtd, const DTD *oldDtd, const XML_Memory_Handling_Suite *ms);
static int
copyEntityTable(HASH_TABLE *, STRING_POOL *, const HASH_TABLE *);

static NAMED *
lookup(HASH_TABLE *table, KEY name, size_t createSize);
static void FASTCALL
hashTableInit(HASH_TABLE *, const XML_Memory_Handling_Suite *ms);
static void FASTCALL hashTableClear(HASH_TABLE *);
static void FASTCALL hashTableDestroy(HASH_TABLE *);
static void FASTCALL
hashTableIterInit(HASH_TABLE_ITER *, const HASH_TABLE *);
static NAMED * FASTCALL hashTableIterNext(HASH_TABLE_ITER *);

static void FASTCALL
poolInit(STRING_POOL *, const XML_Memory_Handling_Suite *ms);
static void FASTCALL poolClear(STRING_POOL *);
static void FASTCALL poolDestroy(STRING_POOL *);
static XML_Char *
poolAppend(STRING_POOL *pool, const ENCODING *enc,
           const char *ptr, const char *end);
static XML_Char *
poolStoreString(STRING_POOL *pool, const ENCODING *enc,
                const char *ptr, const char *end);
static XML_Bool FASTCALL poolGrow(STRING_POOL *pool);
static const XML_Char * FASTCALL
poolCopyString(STRING_POOL *pool, const XML_Char *s);
static const XML_Char *
poolCopyStringN(STRING_POOL *pool, const XML_Char *s, int n);
static const XML_Char * FASTCALL
poolAppendString(STRING_POOL *pool, const XML_Char *s);

static int FASTCALL nextScaffoldPart(XML_Parser parser);
static XML_Content * build_model(XML_Parser parser);
static ELEMENT_TYPE *
getElementType(XML_Parser parser, const ENCODING *enc,
               const char *ptr, const char *end);

static XML_Parser
parserCreate(const XML_Char *encodingName,
             const XML_Memory_Handling_Suite *memsuite,
             const XML_Char *nameSep,
             DTD *dtd);
static void
parserInit(XML_Parser parser, const XML_Char *encodingName);

#define poolStart(pool) ((pool)->start)
#define poolEnd(pool) ((pool)->ptr)
#define poolLength(pool) ((pool)->ptr - (pool)->start)
#define poolChop(pool) ((void)--(pool->ptr))
#define poolLastChar(pool) (((pool)->ptr)[-1])
#define poolDiscard(pool) ((pool)->ptr = (pool)->start)