xmlparse.c

《unix/Linux下的Curses库开发指南》综合示例程序

	            ns ? XmlGetInternalEncodingNS() : XmlGetInternalEncoding(),
		    openInternalEntities->internalEventPtr,
		    openInternalEntities->internalEventEndPtr);
    else
      reportDefault(parser, encoding, eventPtr, eventEndPtr);
  }
}

const XML_LChar *XML_ErrorString(int code)
{
  static const XML_LChar *message[] = {
    0,
    XML_T("out of memory"),
    XML_T("syntax error"),
    XML_T("no element found"),
    XML_T("not well-formed"),
    XML_T("unclosed token"),
    XML_T("unclosed token"),
    XML_T("mismatched tag"),
    XML_T("duplicate attribute"),
    XML_T("junk after document element"),
    XML_T("illegal parameter entity reference"),
    XML_T("undefined entity"),
    XML_T("recursive entity reference"),
    XML_T("asynchronous entity"),
    XML_T("reference to invalid character number"),
    XML_T("reference to binary entity"),
    XML_T("reference to external entity in attribute"),
    XML_T("xml processing instruction not at start of external entity"),
    XML_T("unknown encoding"),
    XML_T("encoding specified in XML declaration is incorrect"),
    XML_T("unclosed CDATA section"),
    XML_T("error in processing external entity reference"),
    XML_T("document is not standalone")
  };
  if (code > 0 && code < sizeof(message)/sizeof(message[0]))
    return message[code];
  return 0;
}

static
enum XML_Error contentProcessor(XML_Parser parser,
				const char *start,
				const char *end,
				const char **endPtr)
{
  return doContent(parser, 0, encoding, start, end, endPtr);
}

static
enum XML_Error externalEntityInitProcessor(XML_Parser parser,
					   const char *start,
					   const char *end,
					   const char **endPtr)
{
  enum XML_Error result = initializeEncoding(parser);
  if (result != XML_ERROR_NONE)
    return result;
  processor = externalEntityInitProcessor2;
  return externalEntityInitProcessor2(parser, start, end, endPtr);
}

static
enum XML_Error externalEntityInitProcessor2(XML_Parser parser,
					    const char *start,
					    const char *end,
					    const char **endPtr)
{
  const char *next;
  int tok = XmlContentTok(encoding, start, end, &next);
  switch (tok) {
  case XML_TOK_BOM:
    start = next;
    break;
  case XML_TOK_PARTIAL:
    if (endPtr) {
      *endPtr = start;
      return XML_ERROR_NONE;
    }
    eventPtr = start;
    return XML_ERROR_UNCLOSED_TOKEN;
  case XML_TOK_PARTIAL_CHAR:
    if (endPtr) {
      *endPtr = start;
      return XML_ERROR_NONE;
    }
    eventPtr = start;
    return XML_ERROR_PARTIAL_CHAR;
  }
  processor = externalEntityInitProcessor3;
  return externalEntityInitProcessor3(parser, start, end, endPtr);
}

static
enum XML_Error externalEntityInitProcessor3(XML_Parser parser,
					    const char *start,
					    const char *end,
					    const char **endPtr)
{
  const char *next;
  int tok = XmlContentTok(encoding, start, end, &next);
  switch (tok) {
  case XML_TOK_XML_DECL:
    {
      enum XML_Error result = processXmlDecl(parser, 1, start, next);
      if (result != XML_ERROR_NONE)
	return result;
      start = next;
    }
    break;
  case XML_TOK_PARTIAL:
    if (endPtr) {
      *endPtr = start;
      return XML_ERROR_NONE;
    }
    eventPtr = start;
    return XML_ERROR_UNCLOSED_TOKEN;
  case XML_TOK_PARTIAL_CHAR:
    if (endPtr) {
      *endPtr = start;
      return XML_ERROR_NONE;
    }
    eventPtr = start;
    return XML_ERROR_PARTIAL_CHAR;
  }
  processor = externalEntityContentProcessor;
  tagLevel = 1;
  return doContent(parser, 1, encoding, start, end, endPtr);
}

static
enum XML_Error externalEntityContentProcessor(XML_Parser parser,
					      const char *start,
					      const char *end,
					      const char **endPtr)
{
  return doContent(parser, 1, encoding, start, end, endPtr);
}

static enum XML_Error
doContent(XML_Parser parser,
	  int startTagLevel,
	  const ENCODING *enc,
	  const char *s,
	  const char *end,
	  const char **nextPtr)
{
  const ENCODING *internalEnc = ns ? XmlGetInternalEncodingNS() : XmlGetInternalEncoding();
  const char **eventPP;
  const char **eventEndPP;
  if (enc == encoding) {
    eventPP = &eventPtr;
    eventEndPP = &eventEndPtr;
  }
  else {
    eventPP = &(openInternalEntities->internalEventPtr);
    eventEndPP = &(openInternalEntities->internalEventEndPtr);
  }
  *eventPP = s;
  for (;;) {
    const char *next = s; /* XmlContentTok doesn't always set the last arg */
    int tok = XmlContentTok(enc, s, end, &next);
    *eventEndPP = next;
    switch (tok) {
    case XML_TOK_TRAILING_CR:
      if (nextPtr) {
	*nextPtr = s;
	return XML_ERROR_NONE;
      }
      *eventEndPP = end;
      if (characterDataHandler) {
	XML_Char c = 0xA;
	characterDataHandler(handlerArg, &c, 1);
      }
      else if (defaultHandler)
	reportDefault(parser, enc, s, end);
      if (startTagLevel == 0)
	return XML_ERROR_NO_ELEMENTS;
      if (tagLevel != startTagLevel)
	return XML_ERROR_ASYNC_ENTITY;
      return XML_ERROR_NONE;
    case XML_TOK_NONE:
      if (nextPtr) {
	*nextPtr = s;
	return XML_ERROR_NONE;
      }
      if (startTagLevel > 0) {
	if (tagLevel != startTagLevel)
	  return XML_ERROR_ASYNC_ENTITY;
	return XML_ERROR_NONE;
      }
      return XML_ERROR_NO_ELEMENTS;
    case XML_TOK_INVALID:
      *eventPP = next;
      return XML_ERROR_INVALID_TOKEN;
    case XML_TOK_PARTIAL:
      if (nextPtr) {
	*nextPtr = s;
	return XML_ERROR_NONE;
      }
      return XML_ERROR_UNCLOSED_TOKEN;
    case XML_TOK_PARTIAL_CHAR:
      if (nextPtr) {
	*nextPtr = s;
	return XML_ERROR_NONE;
      }
      return XML_ERROR_PARTIAL_CHAR;
    case XML_TOK_ENTITY_REF:
      {
	const XML_Char *name;
	ENTITY *entity;
	XML_Char ch = XmlPredefinedEntityName(enc,
					      s + enc->minBytesPerChar,
					      next - enc->minBytesPerChar);
	if (ch) {
	  if (characterDataHandler)
	    characterDataHandler(handlerArg, &ch, 1);
	  else if (defaultHandler)
	    reportDefault(parser, enc, s, next);
	  break;
	}
	name = poolStoreString(&dtd.pool, enc,
				s + enc->minBytesPerChar,
				next - enc->minBytesPerChar);
	if (!name)
	  return XML_ERROR_NO_MEMORY;
	entity = (ENTITY *)lookup(&dtd.generalEntities, name, 0);
	poolDiscard(&dtd.pool);
	if (!entity) {
	  if (dtd.complete || dtd.standalone)
	    return XML_ERROR_UNDEFINED_ENTITY;
	  if (defaultHandler)
	    reportDefault(parser, enc, s, next);
	  break;
	}
	if (entity->open)
	  return XML_ERROR_RECURSIVE_ENTITY_REF;
	if (entity->notation)
	  return XML_ERROR_BINARY_ENTITY_REF;
	if (entity) {
	  if (entity->textPtr) {
	    enum XML_Error result;
	    OPEN_INTERNAL_ENTITY openEntity;
	    if (defaultHandler && !defaultExpandInternalEntities) {
	      reportDefault(parser, enc, s, next);
	      break;
	    }
	    entity->open = 1;
	    openEntity.next = openInternalEntities;
	    openInternalEntities = &openEntity;
	    openEntity.entity = entity;
	    openEntity.internalEventPtr = 0;
	    openEntity.internalEventEndPtr = 0;
	    result = doContent(parser,
			       tagLevel,
			       internalEnc,
			       (char *)entity->textPtr,
			       (char *)(entity->textPtr + entity->textLen),
			       0);
	    entity->open = 0;
	    openInternalEntities = openEntity.next;
	    if (result)
	      return result;
	  }
	  else if (externalEntityRefHandler) {
	    const XML_Char *context;
	    entity->open = 1;
	    context = getContext(parser);
	    entity->open = 0;
	    if (!context)
	      return XML_ERROR_NO_MEMORY;
	    if (!externalEntityRefHandler(externalEntityRefHandlerArg,
				          context,
					  dtd.base,
					  entity->systemId,
					  entity->publicId))
	      return XML_ERROR_EXTERNAL_ENTITY_HANDLING;
	    poolDiscard(&tempPool);
	  }
	  else if (defaultHandler)
	    reportDefault(parser, enc, s, next);
	}
	break;
      }
    case XML_TOK_START_TAG_WITH_ATTS:
      if (!startElementHandler) {
	enum XML_Error result = storeAtts(parser, enc, s, 0, 0);
	if (result)
	  return result;
      }
      /* fall through */
    case XML_TOK_START_TAG_NO_ATTS:
      {
	TAG *tag;
	if (freeTagList) {
	  tag = freeTagList;
	  freeTagList = freeTagList->parent;
	}
	else {
	  tag = malloc(sizeof(TAG));
	  if (!tag)
	    return XML_ERROR_NO_MEMORY;
	  tag->buf = malloc(INIT_TAG_BUF_SIZE);
	  if (!tag->buf)
	    return XML_ERROR_NO_MEMORY;
	  tag->bufEnd = tag->buf + INIT_TAG_BUF_SIZE;
	}
	tag->bindings = 0;
	tag->parent = tagStack;
	tagStack = tag;
	tag->name.localPart = 0;
	tag->rawName = s + enc->minBytesPerChar;
	tag->rawNameLength = XmlNameLength(enc, tag->rawName);
	if (nextPtr) {
	  /* Need to guarantee that:
	     tag->buf + ROUND_UP(tag->rawNameLength, sizeof(XML_Char)) <= tag->bufEnd - sizeof(XML_Char) */
	  if (tag->rawNameLength + (int)(sizeof(XML_Char) - 1) + (int)sizeof(XML_Char) > tag->bufEnd - tag->buf) {
	    int bufSize = tag->rawNameLength * 4;
	    bufSize = ROUND_UP(bufSize, sizeof(XML_Char));
	    tag->buf = realloc(tag->buf, bufSize);
	    if (!tag->buf)
	      return XML_ERROR_NO_MEMORY;
	    tag->bufEnd = tag->buf + bufSize;
	  }
	  memcpy(tag->buf, tag->rawName, tag->rawNameLength);
	  tag->rawName = tag->buf;
	}
	++tagLevel;
	if (startElementHandler) {
	  enum XML_Error result;
	  XML_Char *toPtr;
	  for (;;) {
	    const char *rawNameEnd = tag->rawName + tag->rawNameLength;
	    const char *fromPtr = tag->rawName;
	    int bufSize;
	    if (nextPtr)
	      toPtr = (XML_Char *)(tag->buf + ROUND_UP(tag->rawNameLength, sizeof(XML_Char)));
	    else
	      toPtr = (XML_Char *)tag->buf;
	    tag->name.str = toPtr;
	    XmlConvert(enc,
		       &fromPtr, rawNameEnd,
		       (ICHAR **)&toPtr, (ICHAR *)tag->bufEnd - 1);
	    if (fromPtr == rawNameEnd)
	      break;
	    bufSize = (tag->bufEnd - tag->buf) << 1;
	    tag->buf = realloc(tag->buf, bufSize);
	    if (!tag->buf)
	      return XML_ERROR_NO_MEMORY;
	    tag->bufEnd = tag->buf + bufSize;
	    if (nextPtr)
	      tag->rawName = tag->buf;
	  }
	  *toPtr = XML_T('\0');
	  result = storeAtts(parser, enc, s, &(tag->name), &(tag->bindings));
	  if (result)
	    return result;
	  startElementHandler(handlerArg, tag->name.str, (const XML_Char **)atts);
	  poolClear(&tempPool);
	}
	else {
	  tag->name.str = 0;
	  if (defaultHandler)
	    reportDefault(parser, enc, s, next);
	}
	break;
      }
    case XML_TOK_EMPTY_ELEMENT_WITH_ATTS:
      if (!startElementHandler) {
	enum XML_Error result = storeAtts(parser, enc, s, 0, 0);
	if (result)
	  return result;
      }
      /* fall through */
    case XML_TOK_EMPTY_ELEMENT_NO_ATTS:
      if (startElementHandler || endElementHandler) {
	const char *rawName = s + enc->minBytesPerChar;
	enum XML_Error result;
	BINDING *bindings = 0;
	TAG_NAME name;
	name.str = poolStoreString(&tempPool, enc, rawName,
				   rawName + XmlNameLength(enc, rawName));
	if (!name.str)
	  return XML_ERROR_NO_MEMORY;
	poolFinish(&tempPool);
	result = storeAtts(parser, enc, s, &name, &bindings);
	if (result)
	  return result;
	poolFinish(&tempPool);
	if (startElementHandler)
	  startElementHandler(handlerArg, name.str, (const XML_Char **)atts);
	if (endElementHandler) {
	  if (startElementHandler)
	    *eventPP = *eventEndPP;
	  endElementHandler(handlerArg, name.str);
	}
	poolClear(&tempPool);
	while (bindings) {
	  BINDING *b = bindings;
	  if (endNamespaceDeclHandler)
	    endNamespaceDeclHandler(handlerArg, b->prefix->name);
	  bindings = bindings->nextTagBinding;
	  b->nextTagBinding = freeBindingList;
	  freeBindingList = b;
	  b->prefix->binding = b->prevPrefixBinding;
	}
      }
      else if (defaultHandler)
	reportDefault(parser, enc, s, next);
      if (tagLevel == 0)
	return epilogProcessor(parser, next, end, nextPtr);
      break;
    case XML_TOK_END_TAG:
      if (tagLevel == startTagLevel)
        return XML_ERROR_ASYNC_ENTITY;
      else {
	int len;
	const char *rawName;
	TAG *tag = tagStack;
	tagStack = tag->parent;
	tag->parent = freeTagList;
	freeTagList = tag;
	rawName = s + enc->minBytesPerChar*2;
	len = XmlNameLength(enc, rawName);
	if (len != tag->rawNameLength
	    || memcmp(tag->rawName, rawName, len) != 0) {
	  *eventPP = rawName;
	  return XML_ERROR_TAG_MISMATCH;
	}
	--tagLevel;
	if (endElementHandler && tag->name.str) {
	  if (tag->name.localPart) {
	    XML_Char *to = (XML_Char *)tag->name.str + tag->name.uriLen;
	    const XML_Char *from = tag->name.localPart;
	    while ((*to++ = *from++) != 0)
	      ;
	  }
	  endElementHandler(handlerArg, tag->name.str);
	}
	else if (defaultHandler)
	  reportDefault(parser, enc, s, next);
	while (tag->bindings) {
	  BINDING *b = tag->bindings;
	  if (endNamespaceDeclHandler)
	    endNamespaceDeclHandler(handlerArg, b->prefix->name);
	  tag->bindings = tag->bindings->nextTagBinding;
	  b->nextTagBinding = freeBindingList;
	  freeBindingList = b;
	  b->prefix->binding = b->prevPrefixBinding;
	}
	if (tagLevel == 0)
	  return epilogProcessor(parser, next, end, nextPtr);
      }