diff options
author | Trent Mick <trentm@activestate.com> | 2006-06-19 23:21:25 (GMT) |
---|---|---|
committer | Trent Mick <trentm@activestate.com> | 2006-06-19 23:21:25 (GMT) |
commit | f08d663a2f9cbd8dd0ca868272f03ad115691df7 (patch) | |
tree | 229b8e5158e39dbf09fcad82b0b2c32f0c5e87bb /Modules/expat/xmlparse.c | |
parent | 3dbc8916f55cb6093ea056962d49b8215de0501f (diff) | |
download | cpython-f08d663a2f9cbd8dd0ca868272f03ad115691df7.zip cpython-f08d663a2f9cbd8dd0ca868272f03ad115691df7.tar.gz cpython-f08d663a2f9cbd8dd0ca868272f03ad115691df7.tar.bz2 |
Upgrade pyexpat to expat 2.0.0 (http://python.org/sf/1462338).
Diffstat (limited to 'Modules/expat/xmlparse.c')
-rw-r--r-- | Modules/expat/xmlparse.c | 333 |
1 files changed, 207 insertions, 126 deletions
diff --git a/Modules/expat/xmlparse.c b/Modules/expat/xmlparse.c index 42d95b7..882470d 100644 --- a/Modules/expat/xmlparse.c +++ b/Modules/expat/xmlparse.c @@ -8,6 +8,8 @@ #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 */ @@ -456,7 +458,7 @@ struct XML_ParserStruct { char *m_bufferEnd; /* allocated end of buffer */ const char *m_bufferLim; - long m_parseEndByteIndex; + XML_Index m_parseEndByteIndex; const char *m_parseEndPtr; XML_Char *m_dataBuf; XML_Char *m_dataBufEnd; @@ -640,8 +642,8 @@ struct XML_ParserStruct { #define groupSize (parser->m_groupSize) #define namespaceSeparator (parser->m_namespaceSeparator) #define parentParser (parser->m_parentParser) -#define parsing (parser->m_parsingStatus.parsing) -#define finalBuffer (parser->m_parsingStatus.finalBuffer) +#define ps_parsing (parser->m_parsingStatus.parsing) +#define ps_finalBuffer (parser->m_parsingStatus.finalBuffer) #ifdef XML_DTD #define isParamEntity (parser->m_isParamEntity) #define useForeignDTD (parser->m_useForeignDTD) @@ -852,7 +854,7 @@ parserInit(XML_Parser parser, const XML_Char *encodingName) unknownEncodingRelease = NULL; unknownEncodingData = NULL; parentParser = NULL; - parsing = XML_INITIALIZED; + ps_parsing = XML_INITIALIZED; #ifdef XML_DTD isParamEntity = XML_FALSE; useForeignDTD = XML_FALSE; @@ -915,7 +917,7 @@ XML_SetEncoding(XML_Parser parser, const XML_Char *encodingName) XXX There's no way for the caller to determine which of the XXX possible error cases caused the XML_STATUS_ERROR return. */ - if (parsing == XML_PARSING || parsing == XML_SUSPENDED) + if (ps_parsing == XML_PARSING || ps_parsing == XML_SUSPENDED) return XML_STATUS_ERROR; if (encodingName == NULL) protocolEncodingName = NULL; @@ -1143,7 +1145,7 @@ XML_UseForeignDTD(XML_Parser parser, XML_Bool useDTD) { #ifdef XML_DTD /* block after XML_Parse()/XML_ParseBuffer() has been called */ - if (parsing == XML_PARSING || parsing == XML_SUSPENDED) + if (ps_parsing == XML_PARSING || ps_parsing == XML_SUSPENDED) return XML_ERROR_CANT_CHANGE_FEATURE_ONCE_PARSING; useForeignDTD = useDTD; return XML_ERROR_NONE; @@ -1156,7 +1158,7 @@ void XMLCALL XML_SetReturnNSTriplet(XML_Parser parser, int do_nst) { /* block after XML_Parse()/XML_ParseBuffer() has been called */ - if (parsing == XML_PARSING || parsing == XML_SUSPENDED) + if (ps_parsing == XML_PARSING || ps_parsing == XML_SUSPENDED) return; ns_triplets = do_nst ? XML_TRUE : XML_FALSE; } @@ -1408,7 +1410,7 @@ XML_SetParamEntityParsing(XML_Parser parser, enum XML_ParamEntityParsing peParsing) { /* block after XML_Parse()/XML_ParseBuffer() has been called */ - if (parsing == XML_PARSING || parsing == XML_SUSPENDED) + if (ps_parsing == XML_PARSING || ps_parsing == XML_SUSPENDED) return 0; #ifdef XML_DTD paramEntityParsing = peParsing; @@ -1421,7 +1423,7 @@ XML_SetParamEntityParsing(XML_Parser parser, enum XML_Status XMLCALL XML_Parse(XML_Parser parser, const char *s, int len, int isFinal) { - switch (parsing) { + switch (ps_parsing) { case XML_SUSPENDED: errorCode = XML_ERROR_SUSPENDED; return XML_STATUS_ERROR; @@ -1429,11 +1431,11 @@ XML_Parse(XML_Parser parser, const char *s, int len, int isFinal) errorCode = XML_ERROR_FINISHED; return XML_STATUS_ERROR; default: - parsing = XML_PARSING; + ps_parsing = XML_PARSING; } if (len == 0) { - finalBuffer = (XML_Bool)isFinal; + ps_finalBuffer = (XML_Bool)isFinal; if (!isFinal) return XML_STATUS_OK; positionPtr = bufferPtr; @@ -1441,19 +1443,19 @@ XML_Parse(XML_Parser parser, const char *s, int len, int isFinal) /* If data are left over from last buffer, and we now know that these data are the final chunk of input, then we have to check them again - to detect errors based on this information. + to detect errors based on that fact. */ errorCode = processor(parser, bufferPtr, parseEndPtr, &bufferPtr); if (errorCode == XML_ERROR_NONE) { - switch (parsing) { + switch (ps_parsing) { case XML_SUSPENDED: XmlUpdatePosition(encoding, positionPtr, bufferPtr, &position); positionPtr = bufferPtr; return XML_STATUS_SUSPENDED; case XML_INITIALIZED: case XML_PARSING: - parsing = XML_FINISHED; + ps_parsing = XML_FINISHED; /* fall through */ default: return XML_STATUS_OK; @@ -1470,7 +1472,7 @@ XML_Parse(XML_Parser parser, const char *s, int len, int isFinal) enum XML_Error result; parseEndByteIndex += len; positionPtr = s; - finalBuffer = (XML_Bool)isFinal; + ps_finalBuffer = (XML_Bool)isFinal; errorCode = processor(parser, s, parseEndPtr = s + len, &end); @@ -1480,7 +1482,7 @@ XML_Parse(XML_Parser parser, const char *s, int len, int isFinal) return XML_STATUS_ERROR; } else { - switch (parsing) { + switch (ps_parsing) { case XML_SUSPENDED: result = XML_STATUS_SUSPENDED; break; @@ -1488,14 +1490,13 @@ XML_Parse(XML_Parser parser, const char *s, int len, int isFinal) case XML_PARSING: result = XML_STATUS_OK; if (isFinal) { - parsing = XML_FINISHED; + ps_parsing = XML_FINISHED; return result; } } } XmlUpdatePosition(encoding, positionPtr, end, &position); - positionPtr = end; nLeftOver = s + len - end; if (nLeftOver) { if (buffer == NULL || nLeftOver > bufferLim - buffer) { @@ -1518,9 +1519,13 @@ XML_Parse(XML_Parser parser, const char *s, int len, int isFinal) bufferLim = buffer + len * 2; } memcpy(buffer, end, nLeftOver); - bufferPtr = buffer; - bufferEnd = buffer + nLeftOver; } + bufferPtr = buffer; + bufferEnd = buffer + nLeftOver; + positionPtr = bufferPtr; + parseEndPtr = bufferEnd; + eventPtr = bufferPtr; + eventEndPtr = bufferPtr; return result; } #endif /* not defined XML_CONTEXT_BYTES */ @@ -1541,7 +1546,7 @@ XML_ParseBuffer(XML_Parser parser, int len, int isFinal) const char *start; enum XML_Status result = XML_STATUS_OK; - switch (parsing) { + switch (ps_parsing) { case XML_SUSPENDED: errorCode = XML_ERROR_SUSPENDED; return XML_STATUS_ERROR; @@ -1549,7 +1554,7 @@ XML_ParseBuffer(XML_Parser parser, int len, int isFinal) errorCode = XML_ERROR_FINISHED; return XML_STATUS_ERROR; default: - parsing = XML_PARSING; + ps_parsing = XML_PARSING; } start = bufferPtr; @@ -1557,7 +1562,7 @@ XML_ParseBuffer(XML_Parser parser, int len, int isFinal) bufferEnd += len; parseEndPtr = bufferEnd; parseEndByteIndex += len; - finalBuffer = (XML_Bool)isFinal; + ps_finalBuffer = (XML_Bool)isFinal; errorCode = processor(parser, start, parseEndPtr, &bufferPtr); @@ -1567,14 +1572,14 @@ XML_ParseBuffer(XML_Parser parser, int len, int isFinal) return XML_STATUS_ERROR; } else { - switch (parsing) { + switch (ps_parsing) { case XML_SUSPENDED: result = XML_STATUS_SUSPENDED; break; case XML_INITIALIZED: case XML_PARSING: if (isFinal) { - parsing = XML_FINISHED; + ps_parsing = XML_FINISHED; return result; } default: ; /* should not happen */ @@ -1589,7 +1594,7 @@ XML_ParseBuffer(XML_Parser parser, int len, int isFinal) void * XMLCALL XML_GetBuffer(XML_Parser parser, int len) { - switch (parsing) { + switch (ps_parsing) { case XML_SUSPENDED: errorCode = XML_ERROR_SUSPENDED; return NULL; @@ -1601,9 +1606,9 @@ XML_GetBuffer(XML_Parser parser, int len) if (len > bufferLim - bufferEnd) { /* FIXME avoid integer overflow */ - int neededSize = len + (bufferEnd - bufferPtr); + int neededSize = len + (int)(bufferEnd - bufferPtr); #ifdef XML_CONTEXT_BYTES - int keep = bufferPtr - buffer; + int keep = (int)(bufferPtr - buffer); if (keep > XML_CONTEXT_BYTES) keep = XML_CONTEXT_BYTES; @@ -1612,7 +1617,7 @@ XML_GetBuffer(XML_Parser parser, int len) if (neededSize <= bufferLim - buffer) { #ifdef XML_CONTEXT_BYTES if (keep < bufferPtr - buffer) { - int offset = (bufferPtr - buffer) - keep; + int offset = (int)(bufferPtr - buffer) - keep; memmove(buffer, &buffer[offset], bufferEnd - bufferPtr + keep); bufferEnd -= offset; bufferPtr -= offset; @@ -1625,7 +1630,7 @@ XML_GetBuffer(XML_Parser parser, int len) } else { char *newBuf; - int bufferSize = bufferLim - bufferPtr; + int bufferSize = (int)(bufferLim - bufferPtr); if (bufferSize == 0) bufferSize = INIT_BUFFER_SIZE; do { @@ -1639,7 +1644,7 @@ XML_GetBuffer(XML_Parser parser, int len) bufferLim = newBuf + bufferSize; #ifdef XML_CONTEXT_BYTES if (bufferPtr) { - int keep = bufferPtr - buffer; + int keep = (int)(bufferPtr - buffer); if (keep > XML_CONTEXT_BYTES) keep = XML_CONTEXT_BYTES; memcpy(newBuf, &bufferPtr[-keep], bufferEnd - bufferPtr + keep); @@ -1668,13 +1673,13 @@ XML_GetBuffer(XML_Parser parser, int len) enum XML_Status XMLCALL XML_StopParser(XML_Parser parser, XML_Bool resumable) { - switch (parsing) { + switch (ps_parsing) { case XML_SUSPENDED: if (resumable) { errorCode = XML_ERROR_SUSPENDED; return XML_STATUS_ERROR; } - parsing = XML_FINISHED; + ps_parsing = XML_FINISHED; break; case XML_FINISHED: errorCode = XML_ERROR_FINISHED; @@ -1687,10 +1692,10 @@ XML_StopParser(XML_Parser parser, XML_Bool resumable) return XML_STATUS_ERROR; } #endif - parsing = XML_SUSPENDED; + ps_parsing = XML_SUSPENDED; } else - parsing = XML_FINISHED; + ps_parsing = XML_FINISHED; } return XML_STATUS_OK; } @@ -1700,11 +1705,11 @@ XML_ResumeParser(XML_Parser parser) { enum XML_Status result = XML_STATUS_OK; - if (parsing != XML_SUSPENDED) { + if (ps_parsing != XML_SUSPENDED) { errorCode = XML_ERROR_NOT_SUSPENDED; return XML_STATUS_ERROR; } - parsing = XML_PARSING; + ps_parsing = XML_PARSING; errorCode = processor(parser, bufferPtr, parseEndPtr, &bufferPtr); @@ -1714,14 +1719,14 @@ XML_ResumeParser(XML_Parser parser) return XML_STATUS_ERROR; } else { - switch (parsing) { + switch (ps_parsing) { case XML_SUSPENDED: result = XML_STATUS_SUSPENDED; break; case XML_INITIALIZED: case XML_PARSING: - if (finalBuffer) { - parsing = XML_FINISHED; + if (ps_finalBuffer) { + ps_parsing = XML_FINISHED; return result; } default: ; @@ -1746,7 +1751,7 @@ XML_GetErrorCode(XML_Parser parser) return errorCode; } -long XMLCALL +XML_Index XMLCALL XML_GetCurrentByteIndex(XML_Parser parser) { if (eventPtr) @@ -1758,7 +1763,7 @@ int XMLCALL XML_GetCurrentByteCount(XML_Parser parser) { if (eventEndPtr && eventPtr) - return eventEndPtr - eventPtr; + return (int)(eventEndPtr - eventPtr); return 0; } @@ -1767,15 +1772,15 @@ XML_GetInputContext(XML_Parser parser, int *offset, int *size) { #ifdef XML_CONTEXT_BYTES if (eventPtr && buffer) { - *offset = eventPtr - buffer; - *size = bufferEnd - buffer; + *offset = (int)(eventPtr - buffer); + *size = (int)(bufferEnd - buffer); return buffer; } #endif /* defined XML_CONTEXT_BYTES */ return (char *) 0; } -int XMLCALL +XML_Size XMLCALL XML_GetCurrentLineNumber(XML_Parser parser) { if (eventPtr && eventPtr >= positionPtr) { @@ -1785,7 +1790,7 @@ XML_GetCurrentLineNumber(XML_Parser parser) return position.lineNumber + 1; } -int XMLCALL +XML_Size XMLCALL XML_GetCurrentColumnNumber(XML_Parser parser) { if (eventPtr && eventPtr >= positionPtr) { @@ -1836,7 +1841,7 @@ XML_DefaultCurrent(XML_Parser parser) const XML_LChar * XMLCALL XML_ErrorString(enum XML_Error code) { - static const XML_LChar *message[] = { + static const XML_LChar* const message[] = { 0, XML_L("out of memory"), XML_L("syntax error"), @@ -1854,7 +1859,7 @@ XML_ErrorString(enum XML_Error code) XML_L("reference to invalid character number"), XML_L("reference to binary entity"), XML_L("reference to external entity in attribute"), - XML_L("xml declaration not at start of external entity"), + XML_L("XML or text declaration not at start of entity"), XML_L("unknown encoding"), XML_L("encoding specified in XML declaration is incorrect"), XML_L("unclosed CDATA section"), @@ -1874,7 +1879,10 @@ XML_ErrorString(enum XML_Error code) XML_L("parser not suspended"), XML_L("parsing aborted"), XML_L("parsing finished"), - XML_L("cannot suspend in external parameter entity") + XML_L("cannot suspend in external parameter entity"), + XML_L("reserved prefix (xml) must not be undeclared or bound to another namespace name"), + XML_L("reserved prefix (xmlns) must not be declared or undeclared"), + XML_L("prefix must not be bound to one of the reserved namespace names") }; if (code > 0 && code < sizeof(message)/sizeof(message[0])) return message[code]; @@ -1916,9 +1924,11 @@ XML_ExpatVersionInfo(void) const XML_Feature * XMLCALL XML_GetFeatureList(void) { - static XML_Feature features[] = { - {XML_FEATURE_SIZEOF_XML_CHAR, XML_L("sizeof(XML_Char)"), 0}, - {XML_FEATURE_SIZEOF_XML_LCHAR, XML_L("sizeof(XML_LChar)"), 0}, + static const XML_Feature features[] = { + {XML_FEATURE_SIZEOF_XML_CHAR, XML_L("sizeof(XML_Char)"), + sizeof(XML_Char)}, + {XML_FEATURE_SIZEOF_XML_LCHAR, XML_L("sizeof(XML_LChar)"), + sizeof(XML_LChar)}, #ifdef XML_UNICODE {XML_FEATURE_UNICODE, XML_L("XML_UNICODE"), 0}, #endif @@ -1935,11 +1945,12 @@ XML_GetFeatureList(void) #ifdef XML_MIN_SIZE {XML_FEATURE_MIN_SIZE, XML_L("XML_MIN_SIZE"), 0}, #endif +#ifdef XML_NS + {XML_FEATURE_NS, XML_L("XML_NS"), 0}, +#endif {XML_FEATURE_END, NULL, 0} }; - features[0].value = sizeof(XML_Char); - features[1].value = sizeof(XML_LChar); return features; } @@ -2000,7 +2011,7 @@ contentProcessor(XML_Parser parser, const char **endPtr) { enum XML_Error result = doContent(parser, 0, encoding, start, end, - endPtr, (XML_Bool)!finalBuffer); + endPtr, (XML_Bool)!ps_finalBuffer); if (result == XML_ERROR_NONE) { if (!storeRawNames(parser)) return XML_ERROR_NO_MEMORY; @@ -2036,21 +2047,21 @@ externalEntityInitProcessor2(XML_Parser parser, doContent (by detecting XML_TOK_NONE) without processing any xml text declaration - causing the error XML_ERROR_MISPLACED_XML_PI in doContent. */ - if (next == end && !finalBuffer) { + if (next == end && !ps_finalBuffer) { *endPtr = next; return XML_ERROR_NONE; } start = next; break; case XML_TOK_PARTIAL: - if (!finalBuffer) { + if (!ps_finalBuffer) { *endPtr = start; return XML_ERROR_NONE; } eventPtr = start; return XML_ERROR_UNCLOSED_TOKEN; case XML_TOK_PARTIAL_CHAR: - if (!finalBuffer) { + if (!ps_finalBuffer) { *endPtr = start; return XML_ERROR_NONE; } @@ -2080,7 +2091,7 @@ externalEntityInitProcessor3(XML_Parser parser, result = processXmlDecl(parser, 1, start, next); if (result != XML_ERROR_NONE) return result; - switch (parsing) { + switch (ps_parsing) { case XML_SUSPENDED: *endPtr = next; return XML_ERROR_NONE; @@ -2092,13 +2103,13 @@ externalEntityInitProcessor3(XML_Parser parser, } break; case XML_TOK_PARTIAL: - if (!finalBuffer) { + if (!ps_finalBuffer) { *endPtr = start; return XML_ERROR_NONE; } return XML_ERROR_UNCLOSED_TOKEN; case XML_TOK_PARTIAL_CHAR: - if (!finalBuffer) { + if (!ps_finalBuffer) { *endPtr = start; return XML_ERROR_NONE; } @@ -2116,7 +2127,7 @@ externalEntityContentProcessor(XML_Parser parser, const char **endPtr) { enum XML_Error result = doContent(parser, 1, encoding, start, end, - endPtr, (XML_Bool)!finalBuffer); + endPtr, (XML_Bool)!ps_finalBuffer); if (result == XML_ERROR_NONE) { if (!storeRawNames(parser)) return XML_ERROR_NO_MEMORY; @@ -2315,12 +2326,12 @@ doContent(XML_Parser parser, XmlConvert(enc, &fromPtr, rawNameEnd, (ICHAR **)&toPtr, (ICHAR *)tag->bufEnd - 1); - convLen = toPtr - (XML_Char *)tag->buf; + convLen = (int)(toPtr - (XML_Char *)tag->buf); if (fromPtr == rawNameEnd) { tag->name.strLen = convLen; break; } - bufSize = (tag->bufEnd - tag->buf) << 1; + bufSize = (int)(tag->bufEnd - tag->buf) << 1; { char *temp = (char *)REALLOC(tag->buf, bufSize); if (temp == NULL) @@ -2508,12 +2519,12 @@ doContent(XML_Parser parser, ICHAR *dataPtr = (ICHAR *)dataBuf; XmlConvert(enc, &s, end, &dataPtr, (ICHAR *)dataBufEnd); characterDataHandler(handlerArg, dataBuf, - dataPtr - (ICHAR *)dataBuf); + (int)(dataPtr - (ICHAR *)dataBuf)); } else characterDataHandler(handlerArg, (XML_Char *)s, - (XML_Char *)end - (XML_Char *)s); + (int)((XML_Char *)end - (XML_Char *)s)); } else if (defaultHandler) reportDefault(parser, enc, s, end); @@ -2538,7 +2549,7 @@ doContent(XML_Parser parser, XmlConvert(enc, &s, next, &dataPtr, (ICHAR *)dataBufEnd); *eventEndPP = s; characterDataHandler(handlerArg, dataBuf, - dataPtr - (ICHAR *)dataBuf); + (int)(dataPtr - (ICHAR *)dataBuf)); if (s == next) break; *eventPP = s; @@ -2547,7 +2558,7 @@ doContent(XML_Parser parser, else characterDataHandler(handlerArg, (XML_Char *)s, - (XML_Char *)next - (XML_Char *)s); + (int)((XML_Char *)next - (XML_Char *)s)); } else if (defaultHandler) reportDefault(parser, enc, s, next); @@ -2566,7 +2577,7 @@ doContent(XML_Parser parser, break; } *eventPP = s = next; - switch (parsing) { + switch (ps_parsing) { case XML_SUSPENDED: *nextPtr = next; return XML_ERROR_NONE; @@ -2822,7 +2833,7 @@ storeAtts(XML_Parser parser, const ENCODING *enc, } if (!step) step = PROBE_STEP(uriHash, mask, nsAttsPower); - j < step ? ( j += nsAttsSize - step) : (j -= step); + j < step ? (j += nsAttsSize - step) : (j -= step); } } @@ -2845,8 +2856,10 @@ storeAtts(XML_Parser parser, const ENCODING *enc, nsAtts[j].hash = uriHash; nsAtts[j].uriName = s; - if (!--nPrefixes) + if (!--nPrefixes) { + i += 2; break; + } } else /* not prefixed */ ((XML_Char *)s)[-1] = 0; /* clear flag */ @@ -2879,14 +2892,14 @@ storeAtts(XML_Parser parser, const ENCODING *enc, prefixLen = 0; if (ns_triplets && binding->prefix->name) { for (; binding->prefix->name[prefixLen++];) - ; + ; /* prefixLen includes null terminator */ } tagNamePtr->localPart = localPart; tagNamePtr->uriLen = binding->uriLen; tagNamePtr->prefix = binding->prefix->name; tagNamePtr->prefixLen = prefixLen; for (i = 0; localPart[i++];) - ; + ; /* i includes null terminator */ n = i + binding->uriLen + prefixLen; if (n > binding->uriAlloc) { TAG *p; @@ -2901,12 +2914,13 @@ storeAtts(XML_Parser parser, const ENCODING *enc, FREE(binding->uri); binding->uri = uri; } + /* if namespaceSeparator != '\0' then uri includes it already */ uri = binding->uri + binding->uriLen; memcpy(uri, localPart, i * sizeof(XML_Char)); + /* we always have a namespace separator between localPart and prefix */ if (prefixLen) { - uri = uri + (i - 1); - if (namespaceSeparator) - *uri = namespaceSeparator; + uri += i - 1; + *uri = namespaceSeparator; /* replace null terminator */ memcpy(uri + 1, binding->prefix->name, prefixLen * sizeof(XML_Char)); } tagNamePtr->str = binding->uri; @@ -2920,6 +2934,26 @@ static enum XML_Error addBinding(XML_Parser parser, PREFIX *prefix, const ATTRIBUTE_ID *attId, const XML_Char *uri, BINDING **bindingsPtr) { + static const XML_Char xmlNamespace[] = { + 'h', 't', 't', 'p', ':', '/', '/', + 'w', 'w', 'w', '.', 'w', '3', '.', 'o', 'r', 'g', '/', + 'X', 'M', 'L', '/', '1', '9', '9', '8', '/', + 'n', 'a', 'm', 'e', 's', 'p', 'a', 'c', 'e', '\0' + }; + static const int xmlLen = + (int)sizeof(xmlNamespace)/sizeof(XML_Char) - 1; + static const XML_Char xmlnsNamespace[] = { + 'h', 't', 't', 'p', ':', '/', '/', + 'w', 'w', 'w', '.', 'w', '3', '.', 'o', 'r', 'g', '/', + '2', '0', '0', '0', '/', 'x', 'm', 'l', 'n', 's', '/', '\0' + }; + static const int xmlnsLen = + (int)sizeof(xmlnsNamespace)/sizeof(XML_Char) - 1; + + XML_Bool mustBeXML = XML_FALSE; + XML_Bool isXML = XML_TRUE; + XML_Bool isXMLNS = XML_TRUE; + BINDING *b; int len; @@ -2927,8 +2961,39 @@ addBinding(XML_Parser parser, PREFIX *prefix, const ATTRIBUTE_ID *attId, if (*uri == XML_T('\0') && prefix->name) return XML_ERROR_UNDECLARING_PREFIX; - for (len = 0; uri[len]; len++) - ; + if (prefix->name + && prefix->name[0] == XML_T('x') + && prefix->name[1] == XML_T('m') + && prefix->name[2] == XML_T('l')) { + + /* Not allowed to bind xmlns */ + if (prefix->name[3] == XML_T('n') + && prefix->name[4] == XML_T('s') + && prefix->name[5] == XML_T('\0')) + return XML_ERROR_RESERVED_PREFIX_XMLNS; + + if (prefix->name[3] == XML_T('\0')) + mustBeXML = XML_TRUE; + } + + for (len = 0; uri[len]; len++) { + if (isXML && (len > xmlLen || uri[len] != xmlNamespace[len])) + isXML = XML_FALSE; + + if (!mustBeXML && isXMLNS + && (len > xmlnsLen || uri[len] != xmlnsNamespace[len])) + isXMLNS = XML_FALSE; + } + isXML = isXML && len == xmlLen; + isXMLNS = isXMLNS && len == xmlnsLen; + + if (mustBeXML != isXML) + return mustBeXML ? XML_ERROR_RESERVED_PREFIX_XML + : XML_ERROR_RESERVED_NAMESPACE_URI; + + if (isXMLNS) + return XML_ERROR_RESERVED_NAMESPACE_URI; + if (namespaceSeparator) len++; if (freeBindingList) { @@ -2985,7 +3050,7 @@ cdataSectionProcessor(XML_Parser parser, const char **endPtr) { enum XML_Error result = doCdataSection(parser, encoding, &start, end, - endPtr, (XML_Bool)!finalBuffer); + endPtr, (XML_Bool)!ps_finalBuffer); if (result != XML_ERROR_NONE) return result; if (start) { @@ -3044,7 +3109,7 @@ doCdataSection(XML_Parser parser, reportDefault(parser, enc, s, next); *startPtr = next; *nextPtr = next; - if (parsing == XML_FINISHED) + if (ps_parsing == XML_FINISHED) return XML_ERROR_ABORTED; else return XML_ERROR_NONE; @@ -3064,7 +3129,7 @@ doCdataSection(XML_Parser parser, XmlConvert(enc, &s, next, &dataPtr, (ICHAR *)dataBufEnd); *eventEndPP = next; characterDataHandler(handlerArg, dataBuf, - dataPtr - (ICHAR *)dataBuf); + (int)(dataPtr - (ICHAR *)dataBuf)); if (s == next) break; *eventPP = s; @@ -3073,7 +3138,7 @@ doCdataSection(XML_Parser parser, else characterDataHandler(handlerArg, (XML_Char *)s, - (XML_Char *)next - (XML_Char *)s); + (int)((XML_Char *)next - (XML_Char *)s)); } else if (defaultHandler) reportDefault(parser, enc, s, next); @@ -3100,7 +3165,7 @@ doCdataSection(XML_Parser parser, } *eventPP = s = next; - switch (parsing) { + switch (ps_parsing) { case XML_SUSPENDED: *nextPtr = next; return XML_ERROR_NONE; @@ -3124,7 +3189,7 @@ ignoreSectionProcessor(XML_Parser parser, const char **endPtr) { enum XML_Error result = doIgnoreSection(parser, encoding, &start, end, - endPtr, (XML_Bool)!finalBuffer); + endPtr, (XML_Bool)!ps_finalBuffer); if (result != XML_ERROR_NONE) return result; if (start) { @@ -3169,7 +3234,7 @@ doIgnoreSection(XML_Parser parser, reportDefault(parser, enc, s, next); *startPtr = next; *nextPtr = next; - if (parsing == XML_FINISHED) + if (ps_parsing == XML_FINISHED) return XML_ERROR_ABORTED; else return XML_ERROR_NONE; @@ -3409,7 +3474,7 @@ entityValueInitProcessor(XML_Parser parser, tok = XmlPrologTok(encoding, start, end, &next); eventEndPtr = next; if (tok <= 0) { - if (!finalBuffer && tok != XML_TOK_INVALID) { + if (!ps_finalBuffer && tok != XML_TOK_INVALID) { *nextPtr = s; return XML_ERROR_NONE; } @@ -3432,7 +3497,7 @@ entityValueInitProcessor(XML_Parser parser, result = processXmlDecl(parser, 0, start, next); if (result != XML_ERROR_NONE) return result; - switch (parsing) { + switch (ps_parsing) { case XML_SUSPENDED: *nextPtr = next; return XML_ERROR_NONE; @@ -3452,7 +3517,7 @@ entityValueInitProcessor(XML_Parser parser, then, when this routine is entered the next time, XmlPrologTok will return XML_TOK_INVALID, since the BOM is still in the buffer */ - else if (tok == XML_TOK_BOM && next == end && !finalBuffer) { + else if (tok == XML_TOK_BOM && next == end && !ps_finalBuffer) { *nextPtr = next; return XML_ERROR_NONE; } @@ -3472,7 +3537,7 @@ externalParEntProcessor(XML_Parser parser, tok = XmlPrologTok(encoding, s, end, &next); if (tok <= 0) { - if (!finalBuffer && tok != XML_TOK_INVALID) { + if (!ps_finalBuffer && tok != XML_TOK_INVALID) { *nextPtr = s; return XML_ERROR_NONE; } @@ -3499,7 +3564,7 @@ externalParEntProcessor(XML_Parser parser, processor = prologProcessor; return doProlog(parser, encoding, s, end, tok, next, - nextPtr, (XML_Bool)!finalBuffer); + nextPtr, (XML_Bool)!ps_finalBuffer); } static enum XML_Error PTRCALL @@ -3516,7 +3581,7 @@ entityValueProcessor(XML_Parser parser, for (;;) { tok = XmlPrologTok(enc, start, end, &next); if (tok <= 0) { - if (!finalBuffer && tok != XML_TOK_INVALID) { + if (!ps_finalBuffer && tok != XML_TOK_INVALID) { *nextPtr = s; return XML_ERROR_NONE; } @@ -3549,7 +3614,7 @@ prologProcessor(XML_Parser parser, const char *next = s; int tok = XmlPrologTok(encoding, s, end, &next); return doProlog(parser, encoding, s, end, tok, next, - nextPtr, (XML_Bool)!finalBuffer); + nextPtr, (XML_Bool)!ps_finalBuffer); } static enum XML_Error @@ -3738,7 +3803,8 @@ doProlog(XML_Parser parser, */ #ifdef XML_DTD if (doctypeSysid || useForeignDTD) { - dtd->hasParamEntityRefs = XML_TRUE; /* when docTypeSysid == NULL */ + XML_Bool hadParamEntityRefs = dtd->hasParamEntityRefs; + dtd->hasParamEntityRefs = XML_TRUE; if (paramEntityParsing && externalEntityRefHandler) { ENTITY *entity = (ENTITY *)lookup(&dtd->paramEntities, externalSubsetName, @@ -3754,11 +3820,17 @@ doProlog(XML_Parser parser, entity->systemId, entity->publicId)) return XML_ERROR_EXTERNAL_ENTITY_HANDLING; - if (dtd->paramEntityRead && - !dtd->standalone && - notStandaloneHandler && - !notStandaloneHandler(handlerArg)) - return XML_ERROR_NOT_STANDALONE; + if (dtd->paramEntityRead) { + if (!dtd->standalone && + notStandaloneHandler && + !notStandaloneHandler(handlerArg)) + return XML_ERROR_NOT_STANDALONE; + } + /* if we didn't read the foreign DTD then this means that there + is no external subset and we must reset dtd->hasParamEntityRefs + */ + else if (!doctypeSysid) + dtd->hasParamEntityRefs = hadParamEntityRefs; /* end of DTD - no need to update dtd->keepProcessing */ } useForeignDTD = XML_FALSE; @@ -3775,6 +3847,7 @@ doProlog(XML_Parser parser, last chance to read the foreign DTD */ if (useForeignDTD) { + XML_Bool hadParamEntityRefs = dtd->hasParamEntityRefs; dtd->hasParamEntityRefs = XML_TRUE; if (paramEntityParsing && externalEntityRefHandler) { ENTITY *entity = (ENTITY *)lookup(&dtd->paramEntities, @@ -3790,11 +3863,17 @@ doProlog(XML_Parser parser, entity->systemId, entity->publicId)) return XML_ERROR_EXTERNAL_ENTITY_HANDLING; - if (dtd->paramEntityRead && - !dtd->standalone && - notStandaloneHandler && - !notStandaloneHandler(handlerArg)) - return XML_ERROR_NOT_STANDALONE; + if (dtd->paramEntityRead) { + if (!dtd->standalone && + notStandaloneHandler && + !notStandaloneHandler(handlerArg)) + return XML_ERROR_NOT_STANDALONE; + } + /* if we didn't read the foreign DTD then this means that there + is no external subset and we must reset dtd->hasParamEntityRefs + */ + else + dtd->hasParamEntityRefs = hadParamEntityRefs; /* end of DTD - no need to update dtd->keepProcessing */ } } @@ -3935,7 +4014,7 @@ doProlog(XML_Parser parser, next - enc->minBytesPerChar); if (declEntity) { declEntity->textPtr = poolStart(&dtd->entityValuePool); - declEntity->textLen = poolLength(&dtd->entityValuePool); + declEntity->textLen = (int)(poolLength(&dtd->entityValuePool)); poolFinish(&dtd->entityValuePool); if (entityDeclHandler) { *eventEndPP = s; @@ -4496,7 +4575,7 @@ doProlog(XML_Parser parser, if (handleDefault && defaultHandler) reportDefault(parser, enc, s, next); - switch (parsing) { + switch (ps_parsing) { case XML_SUSPENDED: *nextPtr = next; return XML_ERROR_NONE; @@ -4527,7 +4606,7 @@ epilogProcessor(XML_Parser parser, case -XML_TOK_PROLOG_S: if (defaultHandler) { reportDefault(parser, encoding, s, next); - if (parsing == XML_FINISHED) + if (ps_parsing == XML_FINISHED) return XML_ERROR_ABORTED; } *nextPtr = next; @@ -4551,13 +4630,13 @@ epilogProcessor(XML_Parser parser, eventPtr = next; return XML_ERROR_INVALID_TOKEN; case XML_TOK_PARTIAL: - if (!finalBuffer) { + if (!ps_finalBuffer) { *nextPtr = s; return XML_ERROR_NONE; } return XML_ERROR_UNCLOSED_TOKEN; case XML_TOK_PARTIAL_CHAR: - if (!finalBuffer) { + if (!ps_finalBuffer) { *nextPtr = s; return XML_ERROR_NONE; } @@ -4566,7 +4645,7 @@ epilogProcessor(XML_Parser parser, return XML_ERROR_JUNK_AFTER_DOC_ELEMENT; } eventPtr = s = next; - switch (parsing) { + switch (ps_parsing) { case XML_SUSPENDED: *nextPtr = next; return XML_ERROR_NONE; @@ -4619,8 +4698,8 @@ processInternalEntity(XML_Parser parser, ENTITY *entity, textEnd, &next, XML_FALSE); if (result == XML_ERROR_NONE) { - if (textEnd != next && parsing == XML_SUSPENDED) { - entity->processed = next - textStart; + if (textEnd != next && ps_parsing == XML_SUSPENDED) { + entity->processed = (int)(next - textStart); processor = internalEntityProcessor; } else { @@ -4665,8 +4744,8 @@ internalEntityProcessor(XML_Parser parser, if (result != XML_ERROR_NONE) return result; - else if (textEnd != next && parsing == XML_SUSPENDED) { - entity->processed = next - (char *)entity->textPtr; + else if (textEnd != next && ps_parsing == XML_SUSPENDED) { + entity->processed = (int)(next - (char *)entity->textPtr); return result; } else { @@ -4683,7 +4762,7 @@ internalEntityProcessor(XML_Parser parser, processor = prologProcessor; tok = XmlPrologTok(encoding, s, end, &next); return doProlog(parser, encoding, s, end, tok, next, nextPtr, - (XML_Bool)!finalBuffer); + (XML_Bool)!ps_finalBuffer); } else #endif /* XML_DTD */ @@ -4691,7 +4770,7 @@ internalEntityProcessor(XML_Parser parser, processor = contentProcessor; /* see externalEntityContentProcessor vs contentProcessor */ return doContent(parser, parentParser ? 1 : 0, encoding, s, end, - nextPtr, (XML_Bool)!finalBuffer); + nextPtr, (XML_Bool)!ps_finalBuffer); } } @@ -4800,9 +4879,8 @@ appendAttributeValue(XML_Parser parser, const ENCODING *enc, XML_Bool isCdata, return XML_ERROR_NO_MEMORY; entity = (ENTITY *)lookup(&dtd->generalEntities, name, 0); poolDiscard(&temp2Pool); - /* first, determine if a check for an existing declaration is needed; - if yes, check that the entity exists, and that it is internal, - otherwise call the default handler (if called from content) + /* First, determine if a check for an existing declaration is needed; + if yes, check that the entity exists, and that it is internal. */ if (pool == &dtd->pool) /* are we called from prolog? */ checkEntityDecl = @@ -4821,13 +4899,16 @@ appendAttributeValue(XML_Parser parser, const ENCODING *enc, XML_Bool isCdata, return XML_ERROR_ENTITY_DECLARED_IN_PE; } else if (!entity) { - /* cannot report skipped entity here - see comments on - skippedEntityHandler + /* Cannot report skipped entity here - see comments on + skippedEntityHandler. if (skippedEntityHandler) skippedEntityHandler(handlerArg, name, 0); */ + /* Cannot call the default handler because this would be + out of sync with the call to the startElementHandler. if ((pool == &tempPool) && defaultHandler) reportDefault(parser, enc, ptr, next); + */ break; } if (entity->open) { @@ -5127,12 +5208,12 @@ reportDefault(XML_Parser parser, const ENCODING *enc, ICHAR *dataPtr = (ICHAR *)dataBuf; XmlConvert(enc, &s, end, &dataPtr, (ICHAR *)dataBufEnd); *eventEndPP = s; - defaultHandler(handlerArg, dataBuf, dataPtr - (ICHAR *)dataBuf); + defaultHandler(handlerArg, dataBuf, (int)(dataPtr - (ICHAR *)dataBuf)); *eventPP = s; } while (s != end); } else - defaultHandler(handlerArg, (XML_Char *)s, (XML_Char *)end - (XML_Char *)s); + defaultHandler(handlerArg, (XML_Char *)s, (int)((XML_Char *)end - (XML_Char *)s)); } @@ -5286,7 +5367,7 @@ getContext(XML_Parser parser) if (!poolAppendChar(&tempPool, XML_T('='))) return NULL; len = dtd->defaultPrefix.binding->uriLen; - if (namespaceSeparator != XML_T('\0')) + if (namespaceSeparator) len--; for (i = 0; i < len; i++) if (!poolAppendChar(&tempPool, dtd->defaultPrefix.binding->uri[i])) @@ -5312,7 +5393,7 @@ getContext(XML_Parser parser) if (!poolAppendChar(&tempPool, XML_T('='))) return NULL; len = prefix->binding->uriLen; - if (namespaceSeparator != XML_T('\0')) + if (namespaceSeparator) len--; for (i = 0; i < len; i++) if (!poolAppendChar(&tempPool, prefix->binding->uri[i])) @@ -6014,7 +6095,7 @@ poolGrow(STRING_POOL *pool) } } if (pool->blocks && pool->start == pool->blocks->s) { - int blockSize = (pool->end - pool->start)*2; + int blockSize = (int)(pool->end - pool->start)*2; pool->blocks = (BLOCK *) pool->mem->realloc_fcn(pool->blocks, (offsetof(BLOCK, s) @@ -6028,7 +6109,7 @@ poolGrow(STRING_POOL *pool) } else { BLOCK *tem; - int blockSize = pool->end - pool->start; + int blockSize = (int)(pool->end - pool->start); if (blockSize < INIT_BLOCK_SIZE) blockSize = INIT_BLOCK_SIZE; else |