return (0);
if (ctxt->lastError.code == XML_ERR_ENTITY_LOOP)
return (1);
+
+ /*
+ * This may look absurd but is needed to detect
+ * entities problems
+ */
+ if ((ent != NULL) && (ent->etype != XML_INTERNAL_PREDEFINED_ENTITY) &&
+ (ent->content != NULL) && (ent->checked == 0)) {
+ unsigned long oldnbent = ctxt->nbentities;
+ xmlChar *rep;
+
+ ent->checked = 1;
+
+ rep = xmlStringDecodeEntities(ctxt, ent->content,
+ XML_SUBSTITUTE_REF, 0, 0, 0);
+
+ ent->checked = (ctxt->nbentities - oldnbent + 1) * 2;
+ if (rep != NULL) {
+ if (xmlStrchr(rep, '<'))
+ ent->checked |= 1;
+ xmlFree(rep);
+ rep = NULL;
+ }
+ }
if (replacement != 0) {
if (replacement < XML_MAX_TEXT_LENGTH)
return(0);
return (0);
} else {
/*
- * strange we got no data for checking just return
+ * strange we got no data for checking
*/
- return (0);
+ if (((ctxt->lastError.code != XML_ERR_UNDECLARED_ENTITY) &&
+ (ctxt->lastError.code != XML_WAR_UNDECLARED_ENTITY)) ||
+ (ctxt->nbentities <= 10000))
+ return (0);
}
xmlFatalErr(ctxt, XML_ERR_ENTITY_LOOP, NULL);
return (1);
xmlGROW (ctxt);
static void xmlGROW (xmlParserCtxtPtr ctxt) {
- if ((((ctxt->input->end - ctxt->input->cur) > XML_MAX_LOOKUP_LIMIT) ||
- ((ctxt->input->cur - ctxt->input->base) > XML_MAX_LOOKUP_LIMIT)) &&
+ unsigned long curEnd = ctxt->input->end - ctxt->input->cur;
+ unsigned long curBase = ctxt->input->cur - ctxt->input->base;
+
+ if (((curEnd > (unsigned long) XML_MAX_LOOKUP_LIMIT) ||
+ (curBase > (unsigned long) XML_MAX_LOOKUP_LIMIT)) &&
((ctxt->input->buf) && (ctxt->input->buf->readcallback != (xmlInputReadCallback) xmlNop)) &&
((ctxt->options & XML_PARSE_HUGE) == 0)) {
xmlFatalErr(ctxt, XML_ERR_INTERNAL_ERROR, "Huge input lookup");
while (IS_BLANK_CH(*cur)) {
if (*cur == '\n') {
ctxt->input->line++; ctxt->input->col = 1;
+ } else {
+ ctxt->input->col++;
}
cur++;
res++;
name, NULL);
ctxt->valid = 0;
}
+ xmlParserEntityCheck(ctxt, 0, NULL, 0);
} else if (ctxt->input->free != deallocblankswrapper) {
input = xmlNewBlanksWrapperInputStream(ctxt, entity);
if (xmlPushInput(ctxt, input) < 0)
xmlCharEncoding enc;
/*
+ * Note: external parameter entities will not be loaded, it
+ * is not required for a non-validating parser, unless the
+ * option of validating, or substituting entities were
+ * given. Doing so is far more secure as the parser will
+ * only process data coming from the document entity by
+ * default.
+ */
+ if ((entity->etype == XML_EXTERNAL_PARAMETER_ENTITY) &&
+ ((ctxt->options & XML_PARSE_NOENT) == 0) &&
+ ((ctxt->options & XML_PARSE_DTDVALID) == 0) &&
+ ((ctxt->options & XML_PARSE_DTDLOAD) == 0) &&
+ ((ctxt->options & XML_PARSE_DTDATTR) == 0) &&
+ (ctxt->replaceEntities == 0) &&
+ (ctxt->validate == 0))
+ return;
+
+ /*
* handle the extra spaces added before and after
* c.f. http://www.w3.org/TR/REC-xml#as-PE
* this is done independently.
if ((ctxt->lastError.code == XML_ERR_ENTITY_LOOP) ||
(ctxt->lastError.code == XML_ERR_INTERNAL_ERROR))
goto int_error;
+ xmlParserEntityCheck(ctxt, 0, ent, 0);
if (ent != NULL)
ctxt->nbentities += ent->checked / 2;
if ((ent != NULL) &&
ent = xmlParseStringPEReference(ctxt, &str);
if (ctxt->lastError.code == XML_ERR_ENTITY_LOOP)
goto int_error;
+ xmlParserEntityCheck(ctxt, 0, ent, 0);
if (ent != NULL)
ctxt->nbentities += ent->checked / 2;
if (ent != NULL) {
int len = 0, l;
int c;
int count = 0;
+ const xmlChar *end; /* needed because CUR_CHAR() can move cur on \r\n */
#ifdef DEBUG
nbParseNCNameComplex++;
* Handler for more complex cases
*/
GROW;
+ end = ctxt->input->cur;
c = CUR_CHAR(l);
if ((c == ' ') || (c == '>') || (c == '/') || /* accelerators */
(!xmlIsNameStartChar(ctxt, c) || (c == ':'))) {
}
len += l;
NEXTL(l);
+ end = ctxt->input->cur;
c = CUR_CHAR(l);
if (c == 0) {
count = 0;
GROW;
if (ctxt->instate == XML_PARSER_EOF)
return(NULL);
+ end = ctxt->input->cur;
c = CUR_CHAR(l);
}
}
xmlFatalErr(ctxt, XML_ERR_NAME_TOO_LONG, "NCName");
return(NULL);
}
- return(xmlDictLookup(ctxt->dict, ctxt->input->cur - len, len));
+ return(xmlDictLookup(ctxt->dict, end - len, len));
}
/**
}
if ((name != NULL) && (xmlStrchr(name, ':') != NULL)) {
xmlNsErr(ctxt, XML_NS_ERR_COLON,
- "colon are forbidden from PI names '%s'\n", name, NULL, NULL);
+ "colons are forbidden from PI names '%s'\n", name, NULL, NULL);
}
return(name);
}
}
if (xmlStrchr(name, ':') != NULL) {
xmlNsErr(ctxt, XML_NS_ERR_COLON,
- "colon are forbidden from notation names '%s'\n",
+ "colons are forbidden from notation names '%s'\n",
name, NULL, NULL);
}
SKIP_BLANKS;
}
if (xmlStrchr(name, ':') != NULL) {
xmlNsErr(ctxt, XML_NS_ERR_COLON,
- "colon are forbidden from entities names '%s'\n",
+ "colons are forbidden from entities names '%s'\n",
name, NULL, NULL);
}
skipped = SKIP_BLANKS;
(ret != XML_WAR_UNDECLARED_ENTITY)) {
xmlFatalErrMsgStr(ctxt, XML_ERR_UNDECLARED_ENTITY,
"Entity '%s' failed to parse\n", ent->name);
+ xmlParserEntityCheck(ctxt, 0, ent, 0);
} else if (list != NULL) {
xmlFreeNodeList(list);
list = NULL;
/*
* We are copying here, make sure there is no abuse
*/
- ctxt->sizeentcopy += ent->length;
+ ctxt->sizeentcopy += ent->length + 5;
if (xmlParserEntityCheck(ctxt, 0, ent, ctxt->sizeentcopy))
return;
/*
* We are copying here, make sure there is no abuse
*/
- ctxt->sizeentcopy += ent->length;
+ ctxt->sizeentcopy += ent->length + 5;
if (xmlParserEntityCheck(ctxt, 0, ent, ctxt->sizeentcopy))
return;
ctxt->sax->reference(ctxt->userData, name);
}
}
+ xmlParserEntityCheck(ctxt, 0, ent, 0);
ctxt->valid = 0;
}
else if ((ctxt->instate == XML_PARSER_ATTRIBUTE_VALUE) &&
(ent != NULL) &&
(ent->etype != XML_INTERNAL_PREDEFINED_ENTITY)) {
- if ((ent->checked & 1) || ((ent->checked == 0) &&
- (ent->content != NULL) &&(xmlStrchr(ent->content, '<')))) {
+ if (((ent->checked & 1) || (ent->checked == 0)) &&
+ (ent->content != NULL) && (xmlStrchr(ent->content, '<'))) {
xmlFatalErrMsgStr(ctxt, XML_ERR_LT_IN_ATTRIBUTE,
"'<' in entity '%s' is not allowed in attributes values\n", name);
}
/*
- * Predefined entites override any extra definition
+ * Predefined entities override any extra definition
*/
if ((ctxt->options & XML_PARSE_OLDSAX) == 0) {
ent = xmlGetPredefinedEntity(name);
"Entity '%s' not defined\n",
name);
}
+ xmlParserEntityCheck(ctxt, 0, ent, 0);
/* TODO ? check regressions ctxt->valid = 0; */
}
name, NULL);
ctxt->valid = 0;
}
+ xmlParserEntityCheck(ctxt, 0, NULL, 0);
} else {
/*
* Internal checking in case the entity quest barfed
name, NULL);
ctxt->valid = 0;
}
+ xmlParserEntityCheck(ctxt, 0, NULL, 0);
} else {
/*
* Internal checking in case the entity quest barfed
xmlChar limit = 0;
const xmlChar *in = NULL, *start, *end, *last;
xmlChar *ret = NULL;
+ int line, col;
GROW;
in = (xmlChar *) CUR_PTR;
+ line = ctxt->input->line;
+ col = ctxt->input->col;
if (*in != '"' && *in != '\'') {
xmlFatalErr(ctxt, XML_ERR_ATTRIBUTE_NOT_STARTED, NULL);
return (NULL);
* pure ASCII.
*/
limit = *in++;
+ col++;
end = ctxt->input->end;
start = in;
if (in >= end) {
while ((in < end) && (*in != limit) &&
((*in == 0x20) || (*in == 0x9) ||
(*in == 0xA) || (*in == 0xD))) {
+ if (*in == 0xA) {
+ line++; col = 1;
+ } else {
+ col++;
+ }
in++;
start = in;
if (in >= end) {
}
while ((in < end) && (*in != limit) && (*in >= 0x20) &&
(*in <= 0x7f) && (*in != '&') && (*in != '<')) {
+ col++;
if ((*in++ == 0x20) && (*in == 0x20)) break;
if (in >= end) {
const xmlChar *oldbase = ctxt->input->base;
while ((in < end) && (*in != limit) &&
((*in == 0x20) || (*in == 0x9) ||
(*in == 0xA) || (*in == 0xD))) {
+ if (*in == 0xA) {
+ line++, col = 1;
+ } else {
+ col++;
+ }
in++;
if (in >= end) {
const xmlChar *oldbase = ctxt->input->base;
while ((in < end) && (*in != limit) && (*in >= 0x20) &&
(*in <= 0x7f) && (*in != '&') && (*in != '<')) {
in++;
+ col++;
if (in >= end) {
const xmlChar *oldbase = ctxt->input->base;
GROW;
if (*in != limit) goto need_complex;
}
in++;
+ col++;
if (len != NULL) {
*len = last - start;
ret = (xmlChar *) start;
ret = xmlStrndup(start, last - start);
}
CUR_PTR = in;
+ ctxt->input->line = line;
+ ctxt->input->col = col;
if (alloc) *alloc = 0;
return ret;
need_complex:
const xmlChar *URL = xmlDictLookup(ctxt->dict, attvalue, len);
xmlURIPtr uri;
+ if (URL == NULL) {
+ xmlErrMemory(ctxt, "dictionary allocation failure");
+ if ((attvalue != NULL) && (alloc != 0))
+ xmlFree(attvalue);
+ return(NULL);
+ }
if (*URL != 0) {
uri = xmlParseURI((const char *) URL);
if (uri == NULL) {
if (nsPush(ctxt, NULL, URL) > 0) nbNs++;
skip_default_ns:
if (alloc != 0) xmlFree(attvalue);
+ if ((RAW == '>') || (((RAW == '/') && (NXT(1) == '>'))))
+ break;
+ if (!IS_BLANK_CH(RAW)) {
+ xmlFatalErrMsg(ctxt, XML_ERR_SPACE_REQUIRED,
+ "attributes construct error\n");
+ break;
+ }
SKIP_BLANKS;
continue;
}
if (nsPush(ctxt, attname, URL) > 0) nbNs++;
skip_ns:
if (alloc != 0) xmlFree(attvalue);
+ if ((RAW == '>') || (((RAW == '/') && (NXT(1) == '>'))))
+ break;
+ if (!IS_BLANK_CH(RAW)) {
+ xmlFatalErrMsg(ctxt, XML_ERR_SPACE_REQUIRED,
+ "attributes construct error\n");
+ break;
+ }
SKIP_BLANKS;
if (ctxt->input->base != base) goto base_changed;
continue;
if ((tlen > 0) && (xmlStrncmp(ctxt->input->cur, ctxt->name, tlen) == 0)) {
if (ctxt->input->cur[tlen] == '>') {
ctxt->input->cur += tlen + 1;
+ ctxt->input->col += tlen + 1;
goto done;
}
ctxt->input->cur += tlen;
+ ctxt->input->col += tlen;
name = (xmlChar*)1;
} else {
if (prefix == NULL)
/*
* Non standard parsing, allowing the user to ignore encoding
*/
- if (ctxt->options & XML_PARSE_IGNORE_ENC)
- return(encoding);
+ if (ctxt->options & XML_PARSE_IGNORE_ENC) {
+ xmlFree((xmlChar *) encoding);
+ return(NULL);
+ }
/*
* UTF-16 encoding stwich has already taken place at this stage,
ctxt->sax->startDocument(ctxt->userData);
if (ctxt->instate == XML_PARSER_EOF)
return(-1);
+ if ((ctxt->myDoc != NULL) && (ctxt->input != NULL) &&
+ (ctxt->input->buf != NULL) && (ctxt->input->buf->compressed >= 0)) {
+ ctxt->myDoc->compression = ctxt->input->buf->compressed;
+ }
/*
* The Misc part of the Prolog
return(NULL);
}
+ /* We are loading a DTD */
+ ctxt->options |= XML_PARSE_DTDLOAD;
+
/*
* Set-up the SAX context
*/
return(NULL);
}
+ /* We are loading a DTD */
+ ctxt->options |= XML_PARSE_DTDLOAD;
+
/*
* Set-up the SAX context
*/
xmlFree((xmlChar *) ctxt->encoding);
ctxt->encoding = xmlStrdup((const xmlChar *) doc->encoding);
- hdlr = xmlFindCharEncodingHandler(doc->encoding);
+ hdlr = xmlFindCharEncodingHandler((const char *) doc->encoding);
if (hdlr != NULL) {
xmlSwitchToEncoding(ctxt, hdlr);
} else {
xmlCtxtUseOptionsInternal(ctxt, options, NULL);
xmlDetectSAX2(ctxt);
ctxt->myDoc = doc;
+ /* parsing in context, i.e. as within existing content */
+ ctxt->instate = XML_PARSER_CONTENT;
fake = xmlNewComment(NULL);
if (fake == NULL) {
}
cur = cur->parent;
}
- ctxt->instate = XML_PARSER_CONTENT;
}
if ((ctxt->validate) || (ctxt->replaceEntities != 0)) {
#ifdef LIBXML_XPATH_ENABLED
xmlXPathInit();
#endif
+#ifdef LIBXML_CATALOG_ENABLED
+ xmlInitializeCatalog();
+#endif
xmlParserInitialized = 1;
#ifdef LIBXML_THREAD_ENABLED
}
xmlSchemaCleanupTypes();
xmlRelaxNGCleanupTypes();
#endif
- xmlCleanupGlobals();
xmlResetLastError();
+ xmlCleanupGlobals();
xmlCleanupThreads(); /* must be last if called not from the main thread */
xmlCleanupMemory();
xmlParserInitialized = 0;
if (cur == NULL)
return (NULL);
+ xmlInitParser();
ctxt = xmlCreateDocParserCtxt(cur);
if (ctxt == NULL)
{
xmlParserCtxtPtr ctxt;
+ xmlInitParser();
ctxt = xmlCreateURLParserCtxt(filename, options);
if (ctxt == NULL)
return (NULL);
{
xmlParserCtxtPtr ctxt;
+ xmlInitParser();
ctxt = xmlCreateMemoryParserCtxt(buffer, size);
if (ctxt == NULL)
return (NULL);
if (fd < 0)
return (NULL);
+ xmlInitParser();
input = xmlParserInputBufferCreateFd(fd, XML_CHAR_ENCODING_NONE);
if (input == NULL)
if (ioread == NULL)
return (NULL);
+ xmlInitParser();
input = xmlParserInputBufferCreateIO(ioread, ioclose, ioctx,
XML_CHAR_ENCODING_NONE);
return (NULL);
if (ctxt == NULL)
return (NULL);
+ xmlInitParser();
xmlCtxtReset(ctxt);
return (NULL);
if (ctxt == NULL)
return (NULL);
+ xmlInitParser();
xmlCtxtReset(ctxt);
return (NULL);
if (buffer == NULL)
return (NULL);
+ xmlInitParser();
xmlCtxtReset(ctxt);
return (NULL);
if (ctxt == NULL)
return (NULL);
+ xmlInitParser();
xmlCtxtReset(ctxt);
return (NULL);
if (ctxt == NULL)
return (NULL);
+ xmlInitParser();
xmlCtxtReset(ctxt);