📄 xmlparse.c
字号:
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); } break; case XML_TOK_CHAR_REF: { int n = XmlCharRefNumber(enc, s); if (n < 0) return XML_ERROR_BAD_CHAR_REF; if (characterDataHandler) { XML_Char buf[XML_ENCODE_MAX]; characterDataHandler(handlerArg, buf, XmlEncode(n, (ICHAR *)buf)); } else if (defaultHandler) reportDefault(parser, enc, s, next); } break; case XML_TOK_XML_DECL: return XML_ERROR_MISPLACED_XML_PI; case XML_TOK_DATA_NEWLINE: if (characterDataHandler) { XML_Char c = 0xA; characterDataHandler(handlerArg, &c, 1); } else if (defaultHandler) reportDefault(parser, enc, s, next); break; case XML_TOK_CDATA_SECT_OPEN: { enum XML_Error result; if (startCdataSectionHandler) startCdataSectionHandler(handlerArg);#if 0 /* Suppose you doing a transformation on a document that involves changing only the character data. You set up a defaultHandler and a characterDataHandler. The defaultHandler simply copies characters through. The characterDataHandler does the transformation and writes the characters out escaping them as necessary. This case will fail to work if we leave out the following two lines (because & and < inside CDATA sections will be incorrectly escaped). However, now we have a start/endCdataSectionHandler, so it seems easier to let the user deal with this. */ else if (characterDataHandler) characterDataHandler(handlerArg, dataBuf, 0);#endif else if (defaultHandler) reportDefault(parser, enc, s, next); result = doCdataSection(parser, enc, &next, end, nextPtr); if (!next) { processor = cdataSectionProcessor; return result; } } break; case XML_TOK_TRAILING_RSQB: if (nextPtr) { *nextPtr = s; return XML_ERROR_NONE; } if (characterDataHandler) { if (MUST_CONVERT(enc, s)) { ICHAR *dataPtr = (ICHAR *)dataBuf; XmlConvert(enc, &s, end, &dataPtr, (ICHAR *)dataBufEnd); characterDataHandler(handlerArg, dataBuf, dataPtr - (ICHAR *)dataBuf); } else characterDataHandler(handlerArg, (XML_Char *)s, (XML_Char *)end - (XML_Char *)s); } else if (defaultHandler) reportDefault(parser, enc, s, end); if (startTagLevel == 0) { *eventPP = end; return XML_ERROR_NO_ELEMENTS; } if (tagLevel != startTagLevel) { *eventPP = end; return XML_ERROR_ASYNC_ENTITY; } return XML_ERROR_NONE; case XML_TOK_DATA_CHARS: if (characterDataHandler) { if (MUST_CONVERT(enc, s)) { for (;;) { ICHAR *dataPtr = (ICHAR *)dataBuf; XmlConvert(enc, &s, next, &dataPtr, (ICHAR *)dataBufEnd); *eventEndPP = s; characterDataHandler(handlerArg, dataBuf, dataPtr - (ICHAR *)dataBuf); if (s == next) break; *eventPP = s; } } else characterDataHandler(handlerArg, (XML_Char *)s, (XML_Char *)next - (XML_Char *)s); } else if (defaultHandler) reportDefault(parser, enc, s, next); break; case XML_TOK_PI: if (!reportProcessingInstruction(parser, enc, s, next)) return XML_ERROR_NO_MEMORY; break; case XML_TOK_COMMENT: if (!reportComment(parser, enc, s, next)) return XML_ERROR_NO_MEMORY; break; default: if (defaultHandler) reportDefault(parser, enc, s, next); break; } *eventPP = s = next; } /* not reached */}/* If tagNamePtr is non-null, build a real list of attributes,otherwise just check the attributes for well-formedness. */static enum XML_Error storeAtts(XML_Parser parser, const ENCODING *enc, const char *attStr, TAG_NAME *tagNamePtr, BINDING **bindingsPtr){ ELEMENT_TYPE *elementType = 0; int nDefaultAtts = 0; const XML_Char **appAtts; /* the attribute list to pass to the application */ int attIndex = 0; int i; int n; int nPrefixes = 0; BINDING *binding; const XML_Char *localPart; /* lookup the element type name */ if (tagNamePtr) { elementType = (ELEMENT_TYPE *)lookup(&dtd.elementTypes, tagNamePtr->str, 0); if (!elementType) { tagNamePtr->str = poolCopyString(&dtd.pool, tagNamePtr->str); if (!tagNamePtr->str) return XML_ERROR_NO_MEMORY; elementType = (ELEMENT_TYPE *)lookup(&dtd.elementTypes, tagNamePtr->str, sizeof(ELEMENT_TYPE)); if (!elementType) return XML_ERROR_NO_MEMORY; if (ns && !setElementTypePrefix(parser, elementType)) return XML_ERROR_NO_MEMORY; } nDefaultAtts = elementType->nDefaultAtts; } /* get the attributes from the tokenizer */ n = XmlGetAttributes(enc, attStr, attsSize, atts); if (n + nDefaultAtts > attsSize) { int oldAttsSize = attsSize; attsSize = n + nDefaultAtts + INIT_ATTS_SIZE; atts = realloc((void *)atts, attsSize * sizeof(ATTRIBUTE)); if (!atts) return XML_ERROR_NO_MEMORY; if (n > oldAttsSize) XmlGetAttributes(enc, attStr, n, atts); } appAtts = (const XML_Char **)atts; for (i = 0; i < n; i++) { /* add the name and value to the attribute list */ ATTRIBUTE_ID *attId = getAttributeId(parser, enc, atts[i].name, atts[i].name + XmlNameLength(enc, atts[i].name)); if (!attId) return XML_ERROR_NO_MEMORY; /* detect duplicate attributes */ if ((attId->name)[-1]) { if (enc == encoding) eventPtr = atts[i].name; return XML_ERROR_DUPLICATE_ATTRIBUTE; } (attId->name)[-1] = 1; appAtts[attIndex++] = attId->name; if (!atts[i].normalized) { enum XML_Error result; int isCdata = 1; /* figure out whether declared as other than CDATA */ if (attId->maybeTokenized) { int j; for (j = 0; j < nDefaultAtts; j++) { if (attId == elementType->defaultAtts[j].id) { isCdata = elementType->defaultAtts[j].isCdata; break; } } } /* normalize the attribute value */ result = storeAttributeValue(parser, enc, isCdata, atts[i].valuePtr, atts[i].valueEnd, &tempPool); if (result) return result; if (tagNamePtr) { appAtts[attIndex] = poolStart(&tempPool); poolFinish(&tempPool); } else poolDiscard(&tempPool); } else if (tagNamePtr) { /* the value did not need normalizing */ appAtts[attIndex] = poolStoreString(&tempPool, enc, atts[i].valuePtr, atts[i].valueEnd); if (appAtts[attIndex] == 0) return XML_ERROR_NO_MEMORY; poolFinish(&tempPool); } /* handle prefixed attribute names */ if (attId->prefix && tagNamePtr) { if (attId->xmlns) { /* deal with namespace declarations here */ if (!addBinding(parser, attId->prefix, attId, appAtts[attIndex], bindingsPtr)) return XML_ERROR_NO_MEMORY; --attIndex; } else { /* deal with other prefixed names later */ attIndex++; nPrefixes++; (attId->name)[-1] = 2; } } else attIndex++; } if (tagNamePtr) { int j; nSpecifiedAtts = attIndex; if (elementType->idAtt && (elementType->idAtt->name)[-1]) { for (i = 0; i < attIndex; i += 2) if (appAtts[i] == elementType->idAtt->name) { idAttIndex = i; break; } } else idAttIndex = -1; /* do attribute defaulting */ for (j = 0; j < nDefaultAtts; j++) { const DEFAULT_ATTRIBUTE *da = elementType->defaultAtts + j; if (!(da->id->name)[-1] && da->value) { if (da->id->prefix) { if (da->id->xmlns) { if (!addBinding(parser, da->id->prefix, da->id, da->value, bindingsPtr)) return XML_ERROR_NO_MEMORY; } else { (da->id->name)[-1] = 2; nPrefixes++; appAtts[attIndex++] = da->id->name; appAtts[attIndex++] = da->value; } } else { (da->id->name)[-1] = 1; appAtts[attIndex++] = da->id->name; appAtts[attIndex++] = da->value; } } } appAtts[attIndex] = 0; } i = 0; if (nPrefixes) { /* expand prefixed attribute names */ for (; i < attIndex; i += 2) { if (appAtts[i][-1] == 2) { ATTRIBUTE_ID *id; ((XML_Char *)(appAtts[i]))[-1] = 0; id = (ATTRIBUTE_ID *)lookup(&dtd.attributeIds, appAtts[i], 0); if (id->prefix->binding) { int j; const BINDING *b = id->prefix->binding; const XML_Char *s = appAtts[i]; for (j = 0; j < b->uriLen; j++) { if (!poolAppendChar(&tempPool, b->uri[j])) return XML_ERROR_NO_MEMORY; } while (*s++ != ':') ; do { if (!poolAppendChar(&tempPool, *s)) return XML_ERROR_NO_MEMORY; } while (*s++); appAtts[i] = poolStart(&tempPool); poolFinish(&tempPool); } if (!--nPrefixes) break; } else ((XML_Char *)(appAtts[i]))[-1] = 0; } } /* clear the flags that say whether attributes were specified */ for (; i < attIndex; i += 2) ((XML_Char *)(appAtts[i]))[-1] = 0; if (!tagNamePtr) return XML_ERROR_NONE; for (binding = *bindingsPtr; binding; binding = binding->nextTagBinding) binding->attId->name[-1] = 0; /* expand the element type name */ if (elementType->prefix) { binding = elementType->prefix->binding; if (!binding) return XML_ERROR_NONE; localPart = tagNamePtr->str; while (*localPart++ != XML_T(':')) ; } else if (dtd.defaultPrefix.binding) { binding = dtd.defaultPrefix.binding; localPart = tagNamePtr->str; } else return XML_ERROR_NONE;
⌨️ 快捷键说明
复制代码
Ctrl + C
搜索代码
Ctrl + F
全屏模式
F11
切换主题
Ctrl + Shift + D
显示快捷键
?
增大字号
Ctrl + =
减小字号
Ctrl + -