http://git-wip-us.apache.org/repos/asf/nifi-minifi-cpp/blob/7956696e/thirdparty/libxml2/HTMLparser.c ---------------------------------------------------------------------- diff --git a/thirdparty/libxml2/HTMLparser.c b/thirdparty/libxml2/HTMLparser.c new file mode 100644 index 0000000..b729197 --- /dev/null +++ b/thirdparty/libxml2/HTMLparser.c @@ -0,0 +1,7121 @@ +/* + * HTMLparser.c : an HTML 4.0 non-verifying parser + * + * See Copyright for the status of this software. + * + * [email protected] + */ + +#define IN_LIBXML +#include "libxml.h" +#ifdef LIBXML_HTML_ENABLED + +#include <string.h> +#ifdef HAVE_CTYPE_H +#include <ctype.h> +#endif +#ifdef HAVE_STDLIB_H +#include <stdlib.h> +#endif +#ifdef HAVE_SYS_STAT_H +#include <sys/stat.h> +#endif +#ifdef HAVE_FCNTL_H +#include <fcntl.h> +#endif +#ifdef HAVE_UNISTD_H +#include <unistd.h> +#endif +#ifdef HAVE_ZLIB_H +#include <zlib.h> +#endif + +#include <libxml/xmlmemory.h> +#include <libxml/tree.h> +#include <libxml/parser.h> +#include <libxml/parserInternals.h> +#include <libxml/xmlerror.h> +#include <libxml/HTMLparser.h> +#include <libxml/HTMLtree.h> +#include <libxml/entities.h> +#include <libxml/encoding.h> +#include <libxml/valid.h> +#include <libxml/xmlIO.h> +#include <libxml/globals.h> +#include <libxml/uri.h> + +#include "buf.h" +#include "enc.h" + +#define HTML_MAX_NAMELEN 1000 +#define HTML_PARSER_BIG_BUFFER_SIZE 1000 +#define HTML_PARSER_BUFFER_SIZE 100 + +/* #define DEBUG */ +/* #define DEBUG_PUSH */ + +static int htmlOmittedDefaultValue = 1; + +xmlChar * htmlDecodeEntities(htmlParserCtxtPtr ctxt, int len, + xmlChar end, xmlChar end2, xmlChar end3); +static void htmlParseComment(htmlParserCtxtPtr ctxt); + +/************************************************************************ + * * + * Some factorized error routines * + * * + ************************************************************************/ + +/** + * htmlErrMemory: + * @ctxt: an HTML parser context + * @extra: extra informations + * + * Handle a redefinition of attribute error + */ +static void +htmlErrMemory(xmlParserCtxtPtr ctxt, const char *extra) +{ + if ((ctxt != NULL) && (ctxt->disableSAX != 0) && + (ctxt->instate == XML_PARSER_EOF)) + return; + if (ctxt != NULL) { + ctxt->errNo = XML_ERR_NO_MEMORY; + ctxt->instate = XML_PARSER_EOF; + ctxt->disableSAX = 1; + } + if (extra) + __xmlRaiseError(NULL, NULL, NULL, ctxt, NULL, XML_FROM_PARSER, + XML_ERR_NO_MEMORY, XML_ERR_FATAL, NULL, 0, extra, + NULL, NULL, 0, 0, + "Memory allocation failed : %s\n", extra); + else + __xmlRaiseError(NULL, NULL, NULL, ctxt, NULL, XML_FROM_PARSER, + XML_ERR_NO_MEMORY, XML_ERR_FATAL, NULL, 0, NULL, + NULL, NULL, 0, 0, "Memory allocation failed\n"); +} + +/** + * htmlParseErr: + * @ctxt: an HTML parser context + * @error: the error number + * @msg: the error message + * @str1: string infor + * @str2: string infor + * + * Handle a fatal parser error, i.e. violating Well-Formedness constraints + */ +static void +htmlParseErr(xmlParserCtxtPtr ctxt, xmlParserErrors error, + const char *msg, const xmlChar *str1, const xmlChar *str2) +{ + if ((ctxt != NULL) && (ctxt->disableSAX != 0) && + (ctxt->instate == XML_PARSER_EOF)) + return; + if (ctxt != NULL) + ctxt->errNo = error; + __xmlRaiseError(NULL, NULL, NULL, ctxt, NULL, XML_FROM_HTML, error, + XML_ERR_ERROR, NULL, 0, + (const char *) str1, (const char *) str2, + NULL, 0, 0, + msg, str1, str2); + if (ctxt != NULL) + ctxt->wellFormed = 0; +} + +/** + * htmlParseErrInt: + * @ctxt: an HTML parser context + * @error: the error number + * @msg: the error message + * @val: integer info + * + * Handle a fatal parser error, i.e. violating Well-Formedness constraints + */ +static void +htmlParseErrInt(xmlParserCtxtPtr ctxt, xmlParserErrors error, + const char *msg, int val) +{ + if ((ctxt != NULL) && (ctxt->disableSAX != 0) && + (ctxt->instate == XML_PARSER_EOF)) + return; + if (ctxt != NULL) + ctxt->errNo = error; + __xmlRaiseError(NULL, NULL, NULL, ctxt, NULL, XML_FROM_HTML, error, + XML_ERR_ERROR, NULL, 0, NULL, NULL, + NULL, val, 0, msg, val); + if (ctxt != NULL) + ctxt->wellFormed = 0; +} + +/************************************************************************ + * * + * Parser stacks related functions and macros * + * * + ************************************************************************/ + +/** + * htmlnamePush: + * @ctxt: an HTML parser context + * @value: the element name + * + * Pushes a new element name on top of the name stack + * + * Returns 0 in case of error, the index in the stack otherwise + */ +static int +htmlnamePush(htmlParserCtxtPtr ctxt, const xmlChar * value) +{ + if ((ctxt->html < 3) && (xmlStrEqual(value, BAD_CAST "head"))) + ctxt->html = 3; + if ((ctxt->html < 10) && (xmlStrEqual(value, BAD_CAST "body"))) + ctxt->html = 10; + if (ctxt->nameNr >= ctxt->nameMax) { + ctxt->nameMax *= 2; + ctxt->nameTab = (const xmlChar * *) + xmlRealloc((xmlChar * *)ctxt->nameTab, + ctxt->nameMax * + sizeof(ctxt->nameTab[0])); + if (ctxt->nameTab == NULL) { + htmlErrMemory(ctxt, NULL); + return (0); + } + } + ctxt->nameTab[ctxt->nameNr] = value; + ctxt->name = value; + return (ctxt->nameNr++); +} +/** + * htmlnamePop: + * @ctxt: an HTML parser context + * + * Pops the top element name from the name stack + * + * Returns the name just removed + */ +static const xmlChar * +htmlnamePop(htmlParserCtxtPtr ctxt) +{ + const xmlChar *ret; + + if (ctxt->nameNr <= 0) + return (NULL); + ctxt->nameNr--; + if (ctxt->nameNr < 0) + return (NULL); + if (ctxt->nameNr > 0) + ctxt->name = ctxt->nameTab[ctxt->nameNr - 1]; + else + ctxt->name = NULL; + ret = ctxt->nameTab[ctxt->nameNr]; + ctxt->nameTab[ctxt->nameNr] = NULL; + return (ret); +} + +/** + * htmlNodeInfoPush: + * @ctxt: an HTML parser context + * @value: the node info + * + * Pushes a new element name on top of the node info stack + * + * Returns 0 in case of error, the index in the stack otherwise + */ +static int +htmlNodeInfoPush(htmlParserCtxtPtr ctxt, htmlParserNodeInfo *value) +{ + if (ctxt->nodeInfoNr >= ctxt->nodeInfoMax) { + if (ctxt->nodeInfoMax == 0) + ctxt->nodeInfoMax = 5; + ctxt->nodeInfoMax *= 2; + ctxt->nodeInfoTab = (htmlParserNodeInfo *) + xmlRealloc((htmlParserNodeInfo *)ctxt->nodeInfoTab, + ctxt->nodeInfoMax * + sizeof(ctxt->nodeInfoTab[0])); + if (ctxt->nodeInfoTab == NULL) { + htmlErrMemory(ctxt, NULL); + return (0); + } + } + ctxt->nodeInfoTab[ctxt->nodeInfoNr] = *value; + ctxt->nodeInfo = &ctxt->nodeInfoTab[ctxt->nodeInfoNr]; + return (ctxt->nodeInfoNr++); +} + +/** + * htmlNodeInfoPop: + * @ctxt: an HTML parser context + * + * Pops the top element name from the node info stack + * + * Returns 0 in case of error, the pointer to NodeInfo otherwise + */ +static htmlParserNodeInfo * +htmlNodeInfoPop(htmlParserCtxtPtr ctxt) +{ + if (ctxt->nodeInfoNr <= 0) + return (NULL); + ctxt->nodeInfoNr--; + if (ctxt->nodeInfoNr < 0) + return (NULL); + if (ctxt->nodeInfoNr > 0) + ctxt->nodeInfo = &ctxt->nodeInfoTab[ctxt->nodeInfoNr - 1]; + else + ctxt->nodeInfo = NULL; + return &ctxt->nodeInfoTab[ctxt->nodeInfoNr]; +} + +/* + * Macros for accessing the content. Those should be used only by the parser, + * and not exported. + * + * Dirty macros, i.e. one need to make assumption on the context to use them + * + * CUR_PTR return the current pointer to the xmlChar to be parsed. + * CUR returns the current xmlChar value, i.e. a 8 bit value if compiled + * in ISO-Latin or UTF-8, and the current 16 bit value if compiled + * in UNICODE mode. This should be used internally by the parser + * only to compare to ASCII values otherwise it would break when + * running with UTF-8 encoding. + * NXT(n) returns the n'th next xmlChar. Same as CUR is should be used only + * to compare on ASCII based substring. + * UPP(n) returns the n'th next xmlChar converted to uppercase. Same as CUR + * it should be used only to compare on ASCII based substring. + * SKIP(n) Skip n xmlChar, and must also be used only to skip ASCII defined + * strings without newlines within the parser. + * + * Clean macros, not dependent of an ASCII context, expect UTF-8 encoding + * + * CURRENT Returns the current char value, with the full decoding of + * UTF-8 if we are using this mode. It returns an int. + * NEXT Skip to the next character, this does the proper decoding + * in UTF-8 mode. It also pop-up unfinished entities on the fly. + * NEXTL(l) Skip the current unicode character of l xmlChars long. + * COPY(to) copy one char to *to, increment CUR_PTR and to accordingly + */ + +#define UPPER (toupper(*ctxt->input->cur)) + +#define SKIP(val) ctxt->nbChars += (val),ctxt->input->cur += (val),ctxt->input->col+=(val) + +#define NXT(val) ctxt->input->cur[(val)] + +#define UPP(val) (toupper(ctxt->input->cur[(val)])) + +#define CUR_PTR ctxt->input->cur + +#define SHRINK if ((ctxt->input->cur - ctxt->input->base > 2 * INPUT_CHUNK) && \ + (ctxt->input->end - ctxt->input->cur < 2 * INPUT_CHUNK)) \ + xmlParserInputShrink(ctxt->input) + +#define GROW if ((ctxt->progressive == 0) && \ + (ctxt->input->end - ctxt->input->cur < INPUT_CHUNK)) \ + xmlParserInputGrow(ctxt->input, INPUT_CHUNK) + +#define CURRENT ((int) (*ctxt->input->cur)) + +#define SKIP_BLANKS htmlSkipBlankChars(ctxt) + +/* Inported from XML */ + +/* #define CUR (ctxt->token ? ctxt->token : (int) (*ctxt->input->cur)) */ +#define CUR ((int) (*ctxt->input->cur)) +#define NEXT xmlNextChar(ctxt) + +#define RAW (ctxt->token ? -1 : (*ctxt->input->cur)) + + +#define NEXTL(l) do { \ + if (*(ctxt->input->cur) == '\n') { \ + ctxt->input->line++; ctxt->input->col = 1; \ + } else ctxt->input->col++; \ + ctxt->token = 0; ctxt->input->cur += l; ctxt->nbChars++; \ + } while (0) + +/************ + \ + if (*ctxt->input->cur == '%') xmlParserHandlePEReference(ctxt); \ + if (*ctxt->input->cur == '&') xmlParserHandleReference(ctxt); + ************/ + +#define CUR_CHAR(l) htmlCurrentChar(ctxt, &l) +#define CUR_SCHAR(s, l) xmlStringCurrentChar(ctxt, s, &l) + +#define COPY_BUF(l,b,i,v) \ + if (l == 1) b[i++] = (xmlChar) v; \ + else i += xmlCopyChar(l,&b[i],v) + +/** + * htmlFindEncoding: + * @the HTML parser context + * + * Ty to find and encoding in the current data available in the input + * buffer this is needed to try to switch to the proper encoding when + * one face a character error. + * That's an heuristic, since it's operating outside of parsing it could + * try to use a meta which had been commented out, that's the reason it + * should only be used in case of error, not as a default. + * + * Returns an encoding string or NULL if not found, the string need to + * be freed + */ +static xmlChar * +htmlFindEncoding(xmlParserCtxtPtr ctxt) { + const xmlChar *start, *cur, *end; + + if ((ctxt == NULL) || (ctxt->input == NULL) || + (ctxt->input->encoding != NULL) || (ctxt->input->buf == NULL) || + (ctxt->input->buf->encoder != NULL)) + return(NULL); + if ((ctxt->input->cur == NULL) || (ctxt->input->end == NULL)) + return(NULL); + + start = ctxt->input->cur; + end = ctxt->input->end; + /* we also expect the input buffer to be zero terminated */ + if (*end != 0) + return(NULL); + + cur = xmlStrcasestr(start, BAD_CAST "HTTP-EQUIV"); + if (cur == NULL) + return(NULL); + cur = xmlStrcasestr(cur, BAD_CAST "CONTENT"); + if (cur == NULL) + return(NULL); + cur = xmlStrcasestr(cur, BAD_CAST "CHARSET="); + if (cur == NULL) + return(NULL); + cur += 8; + start = cur; + while (((*cur >= 'A') && (*cur <= 'Z')) || + ((*cur >= 'a') && (*cur <= 'z')) || + ((*cur >= '0') && (*cur <= '9')) || + (*cur == '-') || (*cur == '_') || (*cur == ':') || (*cur == '/')) + cur++; + if (cur == start) + return(NULL); + return(xmlStrndup(start, cur - start)); +} + +/** + * htmlCurrentChar: + * @ctxt: the HTML parser context + * @len: pointer to the length of the char read + * + * The current char value, if using UTF-8 this may actually span multiple + * bytes in the input buffer. Implement the end of line normalization: + * 2.11 End-of-Line Handling + * If the encoding is unspecified, in the case we find an ISO-Latin-1 + * char, then the encoding converter is plugged in automatically. + * + * Returns the current char value and its length + */ + +static int +htmlCurrentChar(xmlParserCtxtPtr ctxt, int *len) { + if (ctxt->instate == XML_PARSER_EOF) + return(0); + + if (ctxt->token != 0) { + *len = 0; + return(ctxt->token); + } + if (ctxt->charset == XML_CHAR_ENCODING_UTF8) { + /* + * We are supposed to handle UTF8, check it's valid + * From rfc2044: encoding of the Unicode values on UTF-8: + * + * UCS-4 range (hex.) UTF-8 octet sequence (binary) + * 0000 0000-0000 007F 0xxxxxxx + * 0000 0080-0000 07FF 110xxxxx 10xxxxxx + * 0000 0800-0000 FFFF 1110xxxx 10xxxxxx 10xxxxxx + * + * Check for the 0x110000 limit too + */ + const unsigned char *cur = ctxt->input->cur; + unsigned char c; + unsigned int val; + + c = *cur; + if (c & 0x80) { + if (cur[1] == 0) { + xmlParserInputGrow(ctxt->input, INPUT_CHUNK); + cur = ctxt->input->cur; + } + if ((cur[1] & 0xc0) != 0x80) + goto encoding_error; + if ((c & 0xe0) == 0xe0) { + + if (cur[2] == 0) { + xmlParserInputGrow(ctxt->input, INPUT_CHUNK); + cur = ctxt->input->cur; + } + if ((cur[2] & 0xc0) != 0x80) + goto encoding_error; + if ((c & 0xf0) == 0xf0) { + if (cur[3] == 0) { + xmlParserInputGrow(ctxt->input, INPUT_CHUNK); + cur = ctxt->input->cur; + } + if (((c & 0xf8) != 0xf0) || + ((cur[3] & 0xc0) != 0x80)) + goto encoding_error; + /* 4-byte code */ + *len = 4; + val = (cur[0] & 0x7) << 18; + val |= (cur[1] & 0x3f) << 12; + val |= (cur[2] & 0x3f) << 6; + val |= cur[3] & 0x3f; + } else { + /* 3-byte code */ + *len = 3; + val = (cur[0] & 0xf) << 12; + val |= (cur[1] & 0x3f) << 6; + val |= cur[2] & 0x3f; + } + } else { + /* 2-byte code */ + *len = 2; + val = (cur[0] & 0x1f) << 6; + val |= cur[1] & 0x3f; + } + if (!IS_CHAR(val)) { + htmlParseErrInt(ctxt, XML_ERR_INVALID_CHAR, + "Char 0x%X out of allowed range\n", val); + } + return(val); + } else { + if ((*ctxt->input->cur == 0) && + (ctxt->input->cur < ctxt->input->end)) { + htmlParseErrInt(ctxt, XML_ERR_INVALID_CHAR, + "Char 0x%X out of allowed range\n", 0); + *len = 1; + return(' '); + } + /* 1-byte code */ + *len = 1; + return((int) *ctxt->input->cur); + } + } + /* + * Assume it's a fixed length encoding (1) with + * a compatible encoding for the ASCII set, since + * XML constructs only use < 128 chars + */ + *len = 1; + if ((int) *ctxt->input->cur < 0x80) + return((int) *ctxt->input->cur); + + /* + * Humm this is bad, do an automatic flow conversion + */ + { + xmlChar * guess; + xmlCharEncodingHandlerPtr handler; + + guess = htmlFindEncoding(ctxt); + if (guess == NULL) { + xmlSwitchEncoding(ctxt, XML_CHAR_ENCODING_8859_1); + } else { + if (ctxt->input->encoding != NULL) + xmlFree((xmlChar *) ctxt->input->encoding); + ctxt->input->encoding = guess; + handler = xmlFindCharEncodingHandler((const char *) guess); + if (handler != NULL) { + xmlSwitchToEncoding(ctxt, handler); + } else { + htmlParseErr(ctxt, XML_ERR_INVALID_ENCODING, + "Unsupported encoding %s", guess, NULL); + } + } + ctxt->charset = XML_CHAR_ENCODING_UTF8; + } + + return(xmlCurrentChar(ctxt, len)); + +encoding_error: + /* + * If we detect an UTF8 error that probably mean that the + * input encoding didn't get properly advertized in the + * declaration header. Report the error and switch the encoding + * to ISO-Latin-1 (if you don't like this policy, just declare the + * encoding !) + */ + { + char buffer[150]; + + if (ctxt->input->end - ctxt->input->cur >= 4) { + snprintf(buffer, 149, "Bytes: 0x%02X 0x%02X 0x%02X 0x%02X\n", + ctxt->input->cur[0], ctxt->input->cur[1], + ctxt->input->cur[2], ctxt->input->cur[3]); + } else { + snprintf(buffer, 149, "Bytes: 0x%02X\n", ctxt->input->cur[0]); + } + htmlParseErr(ctxt, XML_ERR_INVALID_ENCODING, + "Input is not proper UTF-8, indicate encoding !\n", + BAD_CAST buffer, NULL); + } + + ctxt->charset = XML_CHAR_ENCODING_8859_1; + *len = 1; + return((int) *ctxt->input->cur); +} + +/** + * htmlSkipBlankChars: + * @ctxt: the HTML parser context + * + * skip all blanks character found at that point in the input streams. + * + * Returns the number of space chars skipped + */ + +static int +htmlSkipBlankChars(xmlParserCtxtPtr ctxt) { + int res = 0; + + while (IS_BLANK_CH(*(ctxt->input->cur))) { + if ((*ctxt->input->cur == 0) && + (xmlParserInputGrow(ctxt->input, INPUT_CHUNK) <= 0)) { + xmlPopInput(ctxt); + } else { + if (*(ctxt->input->cur) == '\n') { + ctxt->input->line++; ctxt->input->col = 1; + } else ctxt->input->col++; + ctxt->input->cur++; + ctxt->nbChars++; + if (*ctxt->input->cur == 0) + xmlParserInputGrow(ctxt->input, INPUT_CHUNK); + } + res++; + } + return(res); +} + + + +/************************************************************************ + * * + * The list of HTML elements and their properties * + * * + ************************************************************************/ + +/* + * Start Tag: 1 means the start tag can be ommited + * End Tag: 1 means the end tag can be ommited + * 2 means it's forbidden (empty elements) + * 3 means the tag is stylistic and should be closed easily + * Depr: this element is deprecated + * DTD: 1 means that this element is valid only in the Loose DTD + * 2 means that this element is valid only in the Frameset DTD + * + * Name,Start Tag,End Tag,Save End,Empty,Deprecated,DTD,inline,Description + , subElements , impliedsubelt , Attributes, userdata + */ + +/* Definitions and a couple of vars for HTML Elements */ + +#define FONTSTYLE "tt", "i", "b", "u", "s", "strike", "big", "small" +#define NB_FONTSTYLE 8 +#define PHRASE "em", "strong", "dfn", "code", "samp", "kbd", "var", "cite", "abbr", "acronym" +#define NB_PHRASE 10 +#define SPECIAL "a", "img", "applet", "embed", "object", "font", "basefont", "br", "script", "map", "q", "sub", "sup", "span", "bdo", "iframe" +#define NB_SPECIAL 16 +#define INLINE FONTSTYLE, PHRASE, SPECIAL, FORMCTRL +#define NB_INLINE NB_PCDATA + NB_FONTSTYLE + NB_PHRASE + NB_SPECIAL + NB_FORMCTRL +#define BLOCK HEADING, LIST, "pre", "p", "dl", "div", "center", "noscript", "noframes", "blockquote", "form", "isindex", "hr", "table", "fieldset", "address" +#define NB_BLOCK NB_HEADING + NB_LIST + 14 +#define FORMCTRL "input", "select", "textarea", "label", "button" +#define NB_FORMCTRL 5 +#define PCDATA +#define NB_PCDATA 0 +#define HEADING "h1", "h2", "h3", "h4", "h5", "h6" +#define NB_HEADING 6 +#define LIST "ul", "ol", "dir", "menu" +#define NB_LIST 4 +#define MODIFIER +#define NB_MODIFIER 0 +#define FLOW BLOCK,INLINE +#define NB_FLOW NB_BLOCK + NB_INLINE +#define EMPTY NULL + + +static const char* const html_flow[] = { FLOW, NULL } ; +static const char* const html_inline[] = { INLINE, NULL } ; + +/* placeholders: elts with content but no subelements */ +static const char* const html_pcdata[] = { NULL } ; +#define html_cdata html_pcdata + + +/* ... and for HTML Attributes */ + +#define COREATTRS "id", "class", "style", "title" +#define NB_COREATTRS 4 +#define I18N "lang", "dir" +#define NB_I18N 2 +#define EVENTS "onclick", "ondblclick", "onmousedown", "onmouseup", "onmouseover", "onmouseout", "onkeypress", "onkeydown", "onkeyup" +#define NB_EVENTS 9 +#define ATTRS COREATTRS,I18N,EVENTS +#define NB_ATTRS NB_NB_COREATTRS + NB_I18N + NB_EVENTS +#define CELLHALIGN "align", "char", "charoff" +#define NB_CELLHALIGN 3 +#define CELLVALIGN "valign" +#define NB_CELLVALIGN 1 + +static const char* const html_attrs[] = { ATTRS, NULL } ; +static const char* const core_i18n_attrs[] = { COREATTRS, I18N, NULL } ; +static const char* const core_attrs[] = { COREATTRS, NULL } ; +static const char* const i18n_attrs[] = { I18N, NULL } ; + + +/* Other declarations that should go inline ... */ +static const char* const a_attrs[] = { ATTRS, "charset", "type", "name", + "href", "hreflang", "rel", "rev", "accesskey", "shape", "coords", + "tabindex", "onfocus", "onblur", NULL } ; +static const char* const target_attr[] = { "target", NULL } ; +static const char* const rows_cols_attr[] = { "rows", "cols", NULL } ; +static const char* const alt_attr[] = { "alt", NULL } ; +static const char* const src_alt_attrs[] = { "src", "alt", NULL } ; +static const char* const href_attrs[] = { "href", NULL } ; +static const char* const clear_attrs[] = { "clear", NULL } ; +static const char* const inline_p[] = { INLINE, "p", NULL } ; + +static const char* const flow_param[] = { FLOW, "param", NULL } ; +static const char* const applet_attrs[] = { COREATTRS , "codebase", + "archive", "alt", "name", "height", "width", "align", + "hspace", "vspace", NULL } ; +static const char* const area_attrs[] = { "shape", "coords", "href", "nohref", + "tabindex", "accesskey", "onfocus", "onblur", NULL } ; +static const char* const basefont_attrs[] = + { "id", "size", "color", "face", NULL } ; +static const char* const quote_attrs[] = { ATTRS, "cite", NULL } ; +static const char* const body_contents[] = { FLOW, "ins", "del", NULL } ; +static const char* const body_attrs[] = { ATTRS, "onload", "onunload", NULL } ; +static const char* const body_depr[] = { "background", "bgcolor", "text", + "link", "vlink", "alink", NULL } ; +static const char* const button_attrs[] = { ATTRS, "name", "value", "type", + "disabled", "tabindex", "accesskey", "onfocus", "onblur", NULL } ; + + +static const char* const col_attrs[] = { ATTRS, "span", "width", CELLHALIGN, CELLVALIGN, NULL } ; +static const char* const col_elt[] = { "col", NULL } ; +static const char* const edit_attrs[] = { ATTRS, "datetime", "cite", NULL } ; +static const char* const compact_attrs[] = { ATTRS, "compact", NULL } ; +static const char* const dl_contents[] = { "dt", "dd", NULL } ; +static const char* const compact_attr[] = { "compact", NULL } ; +static const char* const label_attr[] = { "label", NULL } ; +static const char* const fieldset_contents[] = { FLOW, "legend" } ; +static const char* const font_attrs[] = { COREATTRS, I18N, "size", "color", "face" , NULL } ; +static const char* const form_contents[] = { HEADING, LIST, INLINE, "pre", "p", "div", "center", "noscript", "noframes", "blockquote", "isindex", "hr", "table", "fieldset", "address", NULL } ; +static const char* const form_attrs[] = { ATTRS, "method", "enctype", "accept", "name", "onsubmit", "onreset", "accept-charset", NULL } ; +static const char* const frame_attrs[] = { COREATTRS, "longdesc", "name", "src", "frameborder", "marginwidth", "marginheight", "noresize", "scrolling" , NULL } ; +static const char* const frameset_attrs[] = { COREATTRS, "rows", "cols", "onload", "onunload", NULL } ; +static const char* const frameset_contents[] = { "frameset", "frame", "noframes", NULL } ; +static const char* const head_attrs[] = { I18N, "profile", NULL } ; +static const char* const head_contents[] = { "title", "isindex", "base", "script", "style", "meta", "link", "object", NULL } ; +static const char* const hr_depr[] = { "align", "noshade", "size", "width", NULL } ; +static const char* const version_attr[] = { "version", NULL } ; +static const char* const html_content[] = { "head", "body", "frameset", NULL } ; +static const char* const iframe_attrs[] = { COREATTRS, "longdesc", "name", "src", "frameborder", "marginwidth", "marginheight", "scrolling", "align", "height", "width", NULL } ; +static const char* const img_attrs[] = { ATTRS, "longdesc", "name", "height", "width", "usemap", "ismap", NULL } ; +static const char* const embed_attrs[] = { COREATTRS, "align", "alt", "border", "code", "codebase", "frameborder", "height", "hidden", "hspace", "name", "palette", "pluginspace", "pluginurl", "src", "type", "units", "vspace", "width", NULL } ; +static const char* const input_attrs[] = { ATTRS, "type", "name", "value", "checked", "disabled", "readonly", "size", "maxlength", "src", "alt", "usemap", "ismap", "tabindex", "accesskey", "onfocus", "onblur", "onselect", "onchange", "accept", NULL } ; +static const char* const prompt_attrs[] = { COREATTRS, I18N, "prompt", NULL } ; +static const char* const label_attrs[] = { ATTRS, "for", "accesskey", "onfocus", "onblur", NULL } ; +static const char* const legend_attrs[] = { ATTRS, "accesskey", NULL } ; +static const char* const align_attr[] = { "align", NULL } ; +static const char* const link_attrs[] = { ATTRS, "charset", "href", "hreflang", "type", "rel", "rev", "media", NULL } ; +static const char* const map_contents[] = { BLOCK, "area", NULL } ; +static const char* const name_attr[] = { "name", NULL } ; +static const char* const action_attr[] = { "action", NULL } ; +static const char* const blockli_elt[] = { BLOCK, "li", NULL } ; +static const char* const meta_attrs[] = { I18N, "http-equiv", "name", "scheme", "charset", NULL } ; +static const char* const content_attr[] = { "content", NULL } ; +static const char* const type_attr[] = { "type", NULL } ; +static const char* const noframes_content[] = { "body", FLOW MODIFIER, NULL } ; +static const char* const object_contents[] = { FLOW, "param", NULL } ; +static const char* const object_attrs[] = { ATTRS, "declare", "classid", "codebase", "data", "type", "codetype", "archive", "standby", "height", "width", "usemap", "name", "tabindex", NULL } ; +static const char* const object_depr[] = { "align", "border", "hspace", "vspace", NULL } ; +static const char* const ol_attrs[] = { "type", "compact", "start", NULL} ; +static const char* const option_elt[] = { "option", NULL } ; +static const char* const optgroup_attrs[] = { ATTRS, "disabled", NULL } ; +static const char* const option_attrs[] = { ATTRS, "disabled", "label", "selected", "value", NULL } ; +static const char* const param_attrs[] = { "id", "value", "valuetype", "type", NULL } ; +static const char* const width_attr[] = { "width", NULL } ; +static const char* const pre_content[] = { PHRASE, "tt", "i", "b", "u", "s", "strike", "a", "br", "script", "map", "q", "span", "bdo", "iframe", NULL } ; +static const char* const script_attrs[] = { "charset", "src", "defer", "event", "for", NULL } ; +static const char* const language_attr[] = { "language", NULL } ; +static const char* const select_content[] = { "optgroup", "option", NULL } ; +static const char* const select_attrs[] = { ATTRS, "name", "size", "multiple", "disabled", "tabindex", "onfocus", "onblur", "onchange", NULL } ; +static const char* const style_attrs[] = { I18N, "media", "title", NULL } ; +static const char* const table_attrs[] = { ATTRS, "summary", "width", "border", "frame", "rules", "cellspacing", "cellpadding", "datapagesize", NULL } ; +static const char* const table_depr[] = { "align", "bgcolor", NULL } ; +static const char* const table_contents[] = { "caption", "col", "colgroup", "thead", "tfoot", "tbody", "tr", NULL} ; +static const char* const tr_elt[] = { "tr", NULL } ; +static const char* const talign_attrs[] = { ATTRS, CELLHALIGN, CELLVALIGN, NULL} ; +static const char* const th_td_depr[] = { "nowrap", "bgcolor", "width", "height", NULL } ; +static const char* const th_td_attr[] = { ATTRS, "abbr", "axis", "headers", "scope", "rowspan", "colspan", CELLHALIGN, CELLVALIGN, NULL } ; +static const char* const textarea_attrs[] = { ATTRS, "name", "disabled", "readonly", "tabindex", "accesskey", "onfocus", "onblur", "onselect", "onchange", NULL } ; +static const char* const tr_contents[] = { "th", "td", NULL } ; +static const char* const bgcolor_attr[] = { "bgcolor", NULL } ; +static const char* const li_elt[] = { "li", NULL } ; +static const char* const ul_depr[] = { "type", "compact", NULL} ; +static const char* const dir_attr[] = { "dir", NULL} ; + +#define DECL (const char**) + +static const htmlElemDesc +html40ElementTable[] = { +{ "a", 0, 0, 0, 0, 0, 0, 1, "anchor ", + DECL html_inline , NULL , DECL a_attrs , DECL target_attr, NULL +}, +{ "abbr", 0, 0, 0, 0, 0, 0, 1, "abbreviated form", + DECL html_inline , NULL , DECL html_attrs, NULL, NULL +}, +{ "acronym", 0, 0, 0, 0, 0, 0, 1, "", + DECL html_inline , NULL , DECL html_attrs, NULL, NULL +}, +{ "address", 0, 0, 0, 0, 0, 0, 0, "information on author ", + DECL inline_p , NULL , DECL html_attrs, NULL, NULL +}, +{ "applet", 0, 0, 0, 0, 1, 1, 2, "java applet ", + DECL flow_param , NULL , NULL , DECL applet_attrs, NULL +}, +{ "area", 0, 2, 2, 1, 0, 0, 0, "client-side image map area ", + EMPTY , NULL , DECL area_attrs , DECL target_attr, DECL alt_attr +}, +{ "b", 0, 3, 0, 0, 0, 0, 1, "bold text style", + DECL html_inline , NULL , DECL html_attrs, NULL, NULL +}, +{ "base", 0, 2, 2, 1, 0, 0, 0, "document base uri ", + EMPTY , NULL , NULL , DECL target_attr, DECL href_attrs +}, +{ "basefont", 0, 2, 2, 1, 1, 1, 1, "base font size " , + EMPTY , NULL , NULL, DECL basefont_attrs, NULL +}, +{ "bdo", 0, 0, 0, 0, 0, 0, 1, "i18n bidi over-ride ", + DECL html_inline , NULL , DECL core_i18n_attrs, NULL, DECL dir_attr +}, +{ "big", 0, 3, 0, 0, 0, 0, 1, "large text style", + DECL html_inline , NULL , DECL html_attrs, NULL, NULL +}, +{ "blockquote", 0, 0, 0, 0, 0, 0, 0, "long quotation ", + DECL html_flow , NULL , DECL quote_attrs , NULL, NULL +}, +{ "body", 1, 1, 0, 0, 0, 0, 0, "document body ", + DECL body_contents , "div" , DECL body_attrs, DECL body_depr, NULL +}, +{ "br", 0, 2, 2, 1, 0, 0, 1, "forced line break ", + EMPTY , NULL , DECL core_attrs, DECL clear_attrs , NULL +}, +{ "button", 0, 0, 0, 0, 0, 0, 2, "push button ", + DECL html_flow MODIFIER , NULL , DECL button_attrs, NULL, NULL +}, +{ "caption", 0, 0, 0, 0, 0, 0, 0, "table caption ", + DECL html_inline , NULL , DECL html_attrs, NULL, NULL +}, +{ "center", 0, 3, 0, 0, 1, 1, 0, "shorthand for div align=center ", + DECL html_flow , NULL , NULL, DECL html_attrs, NULL +}, +{ "cite", 0, 0, 0, 0, 0, 0, 1, "citation", + DECL html_inline , NULL , DECL html_attrs, NULL, NULL +}, +{ "code", 0, 0, 0, 0, 0, 0, 1, "computer code fragment", + DECL html_inline , NULL , DECL html_attrs, NULL, NULL +}, +{ "col", 0, 2, 2, 1, 0, 0, 0, "table column ", + EMPTY , NULL , DECL col_attrs , NULL, NULL +}, +{ "colgroup", 0, 1, 0, 0, 0, 0, 0, "table column group ", + DECL col_elt , "col" , DECL col_attrs , NULL, NULL +}, +{ "dd", 0, 1, 0, 0, 0, 0, 0, "definition description ", + DECL html_flow , NULL , DECL html_attrs, NULL, NULL +}, +{ "del", 0, 0, 0, 0, 0, 0, 2, "deleted text ", + DECL html_flow , NULL , DECL edit_attrs , NULL, NULL +}, +{ "dfn", 0, 0, 0, 0, 0, 0, 1, "instance definition", + DECL html_inline , NULL , DECL html_attrs, NULL, NULL +}, +{ "dir", 0, 0, 0, 0, 1, 1, 0, "directory list", + DECL blockli_elt, "li" , NULL, DECL compact_attrs, NULL +}, +{ "div", 0, 0, 0, 0, 0, 0, 0, "generic language/style container", + DECL html_flow, NULL, DECL html_attrs, DECL align_attr, NULL +}, +{ "dl", 0, 0, 0, 0, 0, 0, 0, "definition list ", + DECL dl_contents , "dd" , DECL html_attrs, DECL compact_attr, NULL +}, +{ "dt", 0, 1, 0, 0, 0, 0, 0, "definition term ", + DECL html_inline, NULL, DECL html_attrs, NULL, NULL +}, +{ "em", 0, 3, 0, 0, 0, 0, 1, "emphasis", + DECL html_inline, NULL, DECL html_attrs, NULL, NULL +}, +{ "embed", 0, 1, 0, 0, 1, 1, 1, "generic embedded object ", + EMPTY, NULL, DECL embed_attrs, NULL, NULL +}, +{ "fieldset", 0, 0, 0, 0, 0, 0, 0, "form control group ", + DECL fieldset_contents , NULL, DECL html_attrs, NULL, NULL +}, +{ "font", 0, 3, 0, 0, 1, 1, 1, "local change to font ", + DECL html_inline, NULL, NULL, DECL font_attrs, NULL +}, +{ "form", 0, 0, 0, 0, 0, 0, 0, "interactive form ", + DECL form_contents, "fieldset", DECL form_attrs , DECL target_attr, DECL action_attr +}, +{ "frame", 0, 2, 2, 1, 0, 2, 0, "subwindow " , + EMPTY, NULL, NULL, DECL frame_attrs, NULL +}, +{ "frameset", 0, 0, 0, 0, 0, 2, 0, "window subdivision" , + DECL frameset_contents, "noframes" , NULL , DECL frameset_attrs, NULL +}, +{ "h1", 0, 0, 0, 0, 0, 0, 0, "heading ", + DECL html_inline, NULL, DECL html_attrs, DECL align_attr, NULL +}, +{ "h2", 0, 0, 0, 0, 0, 0, 0, "heading ", + DECL html_inline, NULL, DECL html_attrs, DECL align_attr, NULL +}, +{ "h3", 0, 0, 0, 0, 0, 0, 0, "heading ", + DECL html_inline, NULL, DECL html_attrs, DECL align_attr, NULL +}, +{ "h4", 0, 0, 0, 0, 0, 0, 0, "heading ", + DECL html_inline, NULL, DECL html_attrs, DECL align_attr, NULL +}, +{ "h5", 0, 0, 0, 0, 0, 0, 0, "heading ", + DECL html_inline, NULL, DECL html_attrs, DECL align_attr, NULL +}, +{ "h6", 0, 0, 0, 0, 0, 0, 0, "heading ", + DECL html_inline, NULL, DECL html_attrs, DECL align_attr, NULL +}, +{ "head", 1, 1, 0, 0, 0, 0, 0, "document head ", + DECL head_contents, NULL, DECL head_attrs, NULL, NULL +}, +{ "hr", 0, 2, 2, 1, 0, 0, 0, "horizontal rule " , + EMPTY, NULL, DECL html_attrs, DECL hr_depr, NULL +}, +{ "html", 1, 1, 0, 0, 0, 0, 0, "document root element ", + DECL html_content , NULL , DECL i18n_attrs, DECL version_attr, NULL +}, +{ "i", 0, 3, 0, 0, 0, 0, 1, "italic text style", + DECL html_inline, NULL, DECL html_attrs, NULL, NULL +}, +{ "iframe", 0, 0, 0, 0, 0, 1, 2, "inline subwindow ", + DECL html_flow, NULL, NULL, DECL iframe_attrs, NULL +}, +{ "img", 0, 2, 2, 1, 0, 0, 1, "embedded image ", + EMPTY, NULL, DECL img_attrs, DECL align_attr, DECL src_alt_attrs +}, +{ "input", 0, 2, 2, 1, 0, 0, 1, "form control ", + EMPTY, NULL, DECL input_attrs , DECL align_attr, NULL +}, +{ "ins", 0, 0, 0, 0, 0, 0, 2, "inserted text", + DECL html_flow, NULL, DECL edit_attrs, NULL, NULL +}, +{ "isindex", 0, 2, 2, 1, 1, 1, 0, "single line prompt ", + EMPTY, NULL, NULL, DECL prompt_attrs, NULL +}, +{ "kbd", 0, 0, 0, 0, 0, 0, 1, "text to be entered by the user", + DECL html_inline, NULL, DECL html_attrs, NULL, NULL +}, +{ "label", 0, 0, 0, 0, 0, 0, 1, "form field label text ", + DECL html_inline MODIFIER, NULL, DECL label_attrs , NULL, NULL +}, +{ "legend", 0, 0, 0, 0, 0, 0, 0, "fieldset legend ", + DECL html_inline, NULL, DECL legend_attrs , DECL align_attr, NULL +}, +{ "li", 0, 1, 1, 0, 0, 0, 0, "list item ", + DECL html_flow, NULL, DECL html_attrs, NULL, NULL +}, +{ "link", 0, 2, 2, 1, 0, 0, 0, "a media-independent link ", + EMPTY, NULL, DECL link_attrs, DECL target_attr, NULL +}, +{ "map", 0, 0, 0, 0, 0, 0, 2, "client-side image map ", + DECL map_contents , NULL, DECL html_attrs , NULL, DECL name_attr +}, +{ "menu", 0, 0, 0, 0, 1, 1, 0, "menu list ", + DECL blockli_elt , NULL, NULL, DECL compact_attrs, NULL +}, +{ "meta", 0, 2, 2, 1, 0, 0, 0, "generic metainformation ", + EMPTY, NULL, DECL meta_attrs , NULL , DECL content_attr +}, +{ "noframes", 0, 0, 0, 0, 0, 2, 0, "alternate content container for non frame-based rendering ", + DECL noframes_content, "body" , DECL html_attrs, NULL, NULL +}, +{ "noscript", 0, 0, 0, 0, 0, 0, 0, "alternate content container for non script-based rendering ", + DECL html_flow, "div", DECL html_attrs, NULL, NULL +}, +{ "object", 0, 0, 0, 0, 0, 0, 2, "generic embedded object ", + DECL object_contents , "div" , DECL object_attrs, DECL object_depr, NULL +}, +{ "ol", 0, 0, 0, 0, 0, 0, 0, "ordered list ", + DECL li_elt , "li" , DECL html_attrs, DECL ol_attrs, NULL +}, +{ "optgroup", 0, 0, 0, 0, 0, 0, 0, "option group ", + DECL option_elt , "option", DECL optgroup_attrs, NULL, DECL label_attr +}, +{ "option", 0, 1, 0, 0, 0, 0, 0, "selectable choice " , + DECL html_pcdata, NULL, DECL option_attrs, NULL, NULL +}, +{ "p", 0, 1, 0, 0, 0, 0, 0, "paragraph ", + DECL html_inline, NULL, DECL html_attrs, DECL align_attr, NULL +}, +{ "param", 0, 2, 2, 1, 0, 0, 0, "named property value ", + EMPTY, NULL, DECL param_attrs, NULL, DECL name_attr +}, +{ "pre", 0, 0, 0, 0, 0, 0, 0, "preformatted text ", + DECL pre_content, NULL, DECL html_attrs, DECL width_attr, NULL +}, +{ "q", 0, 0, 0, 0, 0, 0, 1, "short inline quotation ", + DECL html_inline, NULL, DECL quote_attrs, NULL, NULL +}, +{ "s", 0, 3, 0, 0, 1, 1, 1, "strike-through text style", + DECL html_inline, NULL, NULL, DECL html_attrs, NULL +}, +{ "samp", 0, 0, 0, 0, 0, 0, 1, "sample program output, scripts, etc.", + DECL html_inline, NULL, DECL html_attrs, NULL, NULL +}, +{ "script", 0, 0, 0, 0, 0, 0, 2, "script statements ", + DECL html_cdata, NULL, DECL script_attrs, DECL language_attr, DECL type_attr +}, +{ "select", 0, 0, 0, 0, 0, 0, 1, "option selector ", + DECL select_content, NULL, DECL select_attrs, NULL, NULL +}, +{ "small", 0, 3, 0, 0, 0, 0, 1, "small text style", + DECL html_inline, NULL, DECL html_attrs, NULL, NULL +}, +{ "span", 0, 0, 0, 0, 0, 0, 1, "generic language/style container ", + DECL html_inline, NULL, DECL html_attrs, NULL, NULL +}, +{ "strike", 0, 3, 0, 0, 1, 1, 1, "strike-through text", + DECL html_inline, NULL, NULL, DECL html_attrs, NULL +}, +{ "strong", 0, 3, 0, 0, 0, 0, 1, "strong emphasis", + DECL html_inline, NULL, DECL html_attrs, NULL, NULL +}, +{ "style", 0, 0, 0, 0, 0, 0, 0, "style info ", + DECL html_cdata, NULL, DECL style_attrs, NULL, DECL type_attr +}, +{ "sub", 0, 3, 0, 0, 0, 0, 1, "subscript", + DECL html_inline, NULL, DECL html_attrs, NULL, NULL +}, +{ "sup", 0, 3, 0, 0, 0, 0, 1, "superscript ", + DECL html_inline, NULL, DECL html_attrs, NULL, NULL +}, +{ "table", 0, 0, 0, 0, 0, 0, 0, "", + DECL table_contents , "tr" , DECL table_attrs , DECL table_depr, NULL +}, +{ "tbody", 1, 0, 0, 0, 0, 0, 0, "table body ", + DECL tr_elt , "tr" , DECL talign_attrs, NULL, NULL +}, +{ "td", 0, 0, 0, 0, 0, 0, 0, "table data cell", + DECL html_flow, NULL, DECL th_td_attr, DECL th_td_depr, NULL +}, +{ "textarea", 0, 0, 0, 0, 0, 0, 1, "multi-line text field ", + DECL html_pcdata, NULL, DECL textarea_attrs, NULL, DECL rows_cols_attr +}, +{ "tfoot", 0, 1, 0, 0, 0, 0, 0, "table footer ", + DECL tr_elt , "tr" , DECL talign_attrs, NULL, NULL +}, +{ "th", 0, 1, 0, 0, 0, 0, 0, "table header cell", + DECL html_flow, NULL, DECL th_td_attr, DECL th_td_depr, NULL +}, +{ "thead", 0, 1, 0, 0, 0, 0, 0, "table header ", + DECL tr_elt , "tr" , DECL talign_attrs, NULL, NULL +}, +{ "title", 0, 0, 0, 0, 0, 0, 0, "document title ", + DECL html_pcdata, NULL, DECL i18n_attrs, NULL, NULL +}, +{ "tr", 0, 0, 0, 0, 0, 0, 0, "table row ", + DECL tr_contents , "td" , DECL talign_attrs, DECL bgcolor_attr, NULL +}, +{ "tt", 0, 3, 0, 0, 0, 0, 1, "teletype or monospaced text style", + DECL html_inline, NULL, DECL html_attrs, NULL, NULL +}, +{ "u", 0, 3, 0, 0, 1, 1, 1, "underlined text style", + DECL html_inline, NULL, NULL, DECL html_attrs, NULL +}, +{ "ul", 0, 0, 0, 0, 0, 0, 0, "unordered list ", + DECL li_elt , "li" , DECL html_attrs, DECL ul_depr, NULL +}, +{ "var", 0, 0, 0, 0, 0, 0, 1, "instance of a variable or program argument", + DECL html_inline, NULL, DECL html_attrs, NULL, NULL +} +}; + +/* + * start tags that imply the end of current element + */ +static const char * const htmlStartClose[] = { +"form", "form", "p", "hr", "h1", "h2", "h3", "h4", "h5", "h6", + "dl", "ul", "ol", "menu", "dir", "address", "pre", + "listing", "xmp", "head", NULL, +"head", "p", NULL, +"title", "p", NULL, +"body", "head", "style", "link", "title", "p", NULL, +"frameset", "head", "style", "link", "title", "p", NULL, +"li", "p", "h1", "h2", "h3", "h4", "h5", "h6", "dl", "address", + "pre", "listing", "xmp", "head", "li", NULL, +"hr", "p", "head", NULL, +"h1", "p", "head", NULL, +"h2", "p", "head", NULL, +"h3", "p", "head", NULL, +"h4", "p", "head", NULL, +"h5", "p", "head", NULL, +"h6", "p", "head", NULL, +"dir", "p", "head", NULL, +"address", "p", "head", "ul", NULL, +"pre", "p", "head", "ul", NULL, +"listing", "p", "head", NULL, +"xmp", "p", "head", NULL, +"blockquote", "p", "head", NULL, +"dl", "p", "dt", "menu", "dir", "address", "pre", "listing", + "xmp", "head", NULL, +"dt", "p", "menu", "dir", "address", "pre", "listing", "xmp", + "head", "dd", NULL, +"dd", "p", "menu", "dir", "address", "pre", "listing", "xmp", + "head", "dt", NULL, +"ul", "p", "head", "ol", "menu", "dir", "address", "pre", + "listing", "xmp", NULL, +"ol", "p", "head", "ul", NULL, +"menu", "p", "head", "ul", NULL, +"p", "p", "head", "h1", "h2", "h3", "h4", "h5", "h6", FONTSTYLE, NULL, +"div", "p", "head", NULL, +"noscript", "p", NULL, +"center", "font", "b", "i", "p", "head", NULL, +"a", "a", "head", NULL, +"caption", "p", NULL, +"colgroup", "caption", "colgroup", "col", "p", NULL, +"col", "caption", "col", "p", NULL, +"table", "p", "head", "h1", "h2", "h3", "h4", "h5", "h6", "pre", + "listing", "xmp", "a", NULL, +"th", "th", "td", "p", "span", "font", "a", "b", "i", "u", NULL, +"td", "th", "td", "p", "span", "font", "a", "b", "i", "u", NULL, +"tr", "th", "td", "tr", "caption", "col", "colgroup", "p", NULL, +"thead", "caption", "col", "colgroup", NULL, +"tfoot", "th", "td", "tr", "caption", "col", "colgroup", "thead", + "tbody", "p", NULL, +"tbody", "th", "td", "tr", "caption", "col", "colgroup", "thead", + "tfoot", "tbody", "p", NULL, +"optgroup", "option", NULL, +"option", "option", NULL, +"fieldset", "legend", "p", "head", "h1", "h2", "h3", "h4", "h5", "h6", + "pre", "listing", "xmp", "a", NULL, +/* most tags in in FONTSTYLE, PHRASE and SPECIAL should close <head> */ +"tt", "head", NULL, +"i", "head", NULL, +"b", "head", NULL, +"u", "head", NULL, +"s", "head", NULL, +"strike", "head", NULL, +"big", "head", NULL, +"small", "head", NULL, + +"em", "head", NULL, +"strong", "head", NULL, +"dfn", "head", NULL, +"code", "head", NULL, +"samp", "head", NULL, +"kbd", "head", NULL, +"var", "head", NULL, +"cite", "head", NULL, +"abbr", "head", NULL, +"acronym", "head", NULL, + +/* "a" */ +"img", "head", NULL, +/* "applet" */ +/* "embed" */ +/* "object" */ +"font", "head", NULL, +/* "basefont" */ +"br", "head", NULL, +/* "script" */ +"map", "head", NULL, +"q", "head", NULL, +"sub", "head", NULL, +"sup", "head", NULL, +"span", "head", NULL, +"bdo", "head", NULL, +"iframe", "head", NULL, +NULL +}; + +/* + * The list of HTML elements which are supposed not to have + * CDATA content and where a p element will be implied + * + * TODO: extend that list by reading the HTML SGML DTD on + * implied paragraph + */ +static const char *const htmlNoContentElements[] = { + "html", + "head", + NULL +}; + +/* + * The list of HTML attributes which are of content %Script; + * NOTE: when adding ones, check htmlIsScriptAttribute() since + * it assumes the name starts with 'on' + */ +static const char *const htmlScriptAttributes[] = { + "onclick", + "ondblclick", + "onmousedown", + "onmouseup", + "onmouseover", + "onmousemove", + "onmouseout", + "onkeypress", + "onkeydown", + "onkeyup", + "onload", + "onunload", + "onfocus", + "onblur", + "onsubmit", + "onreset", + "onchange", + "onselect" +}; + +/* + * This table is used by the htmlparser to know what to do with + * broken html pages. By assigning different priorities to different + * elements the parser can decide how to handle extra endtags. + * Endtags are only allowed to close elements with lower or equal + * priority. + */ + +typedef struct { + const char *name; + int priority; +} elementPriority; + +static const elementPriority htmlEndPriority[] = { + {"div", 150}, + {"td", 160}, + {"th", 160}, + {"tr", 170}, + {"thead", 180}, + {"tbody", 180}, + {"tfoot", 180}, + {"table", 190}, + {"head", 200}, + {"body", 200}, + {"html", 220}, + {NULL, 100} /* Default priority */ +}; + +static const char** htmlStartCloseIndex[100]; +static int htmlStartCloseIndexinitialized = 0; + +/************************************************************************ + * * + * functions to handle HTML specific data * + * * + ************************************************************************/ + +/** + * htmlInitAutoClose: + * + * Initialize the htmlStartCloseIndex for fast lookup of closing tags names. + * This is not reentrant. Call xmlInitParser() once before processing in + * case of use in multithreaded programs. + */ +void +htmlInitAutoClose(void) { + int indx, i = 0; + + if (htmlStartCloseIndexinitialized) return; + + for (indx = 0;indx < 100;indx ++) htmlStartCloseIndex[indx] = NULL; + indx = 0; + while ((htmlStartClose[i] != NULL) && (indx < 100 - 1)) { + htmlStartCloseIndex[indx++] = (const char**) &htmlStartClose[i]; + while (htmlStartClose[i] != NULL) i++; + i++; + } + htmlStartCloseIndexinitialized = 1; +} + +/** + * htmlTagLookup: + * @tag: The tag name in lowercase + * + * Lookup the HTML tag in the ElementTable + * + * Returns the related htmlElemDescPtr or NULL if not found. + */ +const htmlElemDesc * +htmlTagLookup(const xmlChar *tag) { + unsigned int i; + + for (i = 0; i < (sizeof(html40ElementTable) / + sizeof(html40ElementTable[0]));i++) { + if (!xmlStrcasecmp(tag, BAD_CAST html40ElementTable[i].name)) + return((htmlElemDescPtr) &html40ElementTable[i]); + } + return(NULL); +} + +/** + * htmlGetEndPriority: + * @name: The name of the element to look up the priority for. + * + * Return value: The "endtag" priority. + **/ +static int +htmlGetEndPriority (const xmlChar *name) { + int i = 0; + + while ((htmlEndPriority[i].name != NULL) && + (!xmlStrEqual((const xmlChar *)htmlEndPriority[i].name, name))) + i++; + + return(htmlEndPriority[i].priority); +} + + +/** + * htmlCheckAutoClose: + * @newtag: The new tag name + * @oldtag: The old tag name + * + * Checks whether the new tag is one of the registered valid tags for + * closing old. + * Initialize the htmlStartCloseIndex for fast lookup of closing tags names. + * + * Returns 0 if no, 1 if yes. + */ +static int +htmlCheckAutoClose(const xmlChar * newtag, const xmlChar * oldtag) +{ + int i, indx; + const char **closed = NULL; + + if (htmlStartCloseIndexinitialized == 0) + htmlInitAutoClose(); + + /* inefficient, but not a big deal */ + for (indx = 0; indx < 100; indx++) { + closed = htmlStartCloseIndex[indx]; + if (closed == NULL) + return (0); + if (xmlStrEqual(BAD_CAST * closed, newtag)) + break; + } + + i = closed - htmlStartClose; + i++; + while (htmlStartClose[i] != NULL) { + if (xmlStrEqual(BAD_CAST htmlStartClose[i], oldtag)) { + return (1); + } + i++; + } + return (0); +} + +/** + * htmlAutoCloseOnClose: + * @ctxt: an HTML parser context + * @newtag: The new tag name + * @force: force the tag closure + * + * The HTML DTD allows an ending tag to implicitly close other tags. + */ +static void +htmlAutoCloseOnClose(htmlParserCtxtPtr ctxt, const xmlChar * newtag) +{ + const htmlElemDesc *info; + int i, priority; + + priority = htmlGetEndPriority(newtag); + + for (i = (ctxt->nameNr - 1); i >= 0; i--) { + + if (xmlStrEqual(newtag, ctxt->nameTab[i])) + break; + /* + * A missplaced endtag can only close elements with lower + * or equal priority, so if we find an element with higher + * priority before we find an element with + * matching name, we just ignore this endtag + */ + if (htmlGetEndPriority(ctxt->nameTab[i]) > priority) + return; + } + if (i < 0) + return; + + while (!xmlStrEqual(newtag, ctxt->name)) { + info = htmlTagLookup(ctxt->name); + if ((info != NULL) && (info->endTag == 3)) { + htmlParseErr(ctxt, XML_ERR_TAG_NAME_MISMATCH, + "Opening and ending tag mismatch: %s and %s\n", + newtag, ctxt->name); + } + if ((ctxt->sax != NULL) && (ctxt->sax->endElement != NULL)) + ctxt->sax->endElement(ctxt->userData, ctxt->name); + htmlnamePop(ctxt); + } +} + +/** + * htmlAutoCloseOnEnd: + * @ctxt: an HTML parser context + * + * Close all remaining tags at the end of the stream + */ +static void +htmlAutoCloseOnEnd(htmlParserCtxtPtr ctxt) +{ + int i; + + if (ctxt->nameNr == 0) + return; + for (i = (ctxt->nameNr - 1); i >= 0; i--) { + if ((ctxt->sax != NULL) && (ctxt->sax->endElement != NULL)) + ctxt->sax->endElement(ctxt->userData, ctxt->name); + htmlnamePop(ctxt); + } +} + +/** + * htmlAutoClose: + * @ctxt: an HTML parser context + * @newtag: The new tag name or NULL + * + * The HTML DTD allows a tag to implicitly close other tags. + * The list is kept in htmlStartClose array. This function is + * called when a new tag has been detected and generates the + * appropriates closes if possible/needed. + * If newtag is NULL this mean we are at the end of the resource + * and we should check + */ +static void +htmlAutoClose(htmlParserCtxtPtr ctxt, const xmlChar * newtag) +{ + while ((newtag != NULL) && (ctxt->name != NULL) && + (htmlCheckAutoClose(newtag, ctxt->name))) { + if ((ctxt->sax != NULL) && (ctxt->sax->endElement != NULL)) + ctxt->sax->endElement(ctxt->userData, ctxt->name); + htmlnamePop(ctxt); + } + if (newtag == NULL) { + htmlAutoCloseOnEnd(ctxt); + return; + } + while ((newtag == NULL) && (ctxt->name != NULL) && + ((xmlStrEqual(ctxt->name, BAD_CAST "head")) || + (xmlStrEqual(ctxt->name, BAD_CAST "body")) || + (xmlStrEqual(ctxt->name, BAD_CAST "html")))) { + if ((ctxt->sax != NULL) && (ctxt->sax->endElement != NULL)) + ctxt->sax->endElement(ctxt->userData, ctxt->name); + htmlnamePop(ctxt); + } +} + +/** + * htmlAutoCloseTag: + * @doc: the HTML document + * @name: The tag name + * @elem: the HTML element + * + * The HTML DTD allows a tag to implicitly close other tags. + * The list is kept in htmlStartClose array. This function checks + * if the element or one of it's children would autoclose the + * given tag. + * + * Returns 1 if autoclose, 0 otherwise + */ +int +htmlAutoCloseTag(htmlDocPtr doc, const xmlChar *name, htmlNodePtr elem) { + htmlNodePtr child; + + if (elem == NULL) return(1); + if (xmlStrEqual(name, elem->name)) return(0); + if (htmlCheckAutoClose(elem->name, name)) return(1); + child = elem->children; + while (child != NULL) { + if (htmlAutoCloseTag(doc, name, child)) return(1); + child = child->next; + } + return(0); +} + +/** + * htmlIsAutoClosed: + * @doc: the HTML document + * @elem: the HTML element + * + * The HTML DTD allows a tag to implicitly close other tags. + * The list is kept in htmlStartClose array. This function checks + * if a tag is autoclosed by one of it's child + * + * Returns 1 if autoclosed, 0 otherwise + */ +int +htmlIsAutoClosed(htmlDocPtr doc, htmlNodePtr elem) { + htmlNodePtr child; + + if (elem == NULL) return(1); + child = elem->children; + while (child != NULL) { + if (htmlAutoCloseTag(doc, elem->name, child)) return(1); + child = child->next; + } + return(0); +} + +/** + * htmlCheckImplied: + * @ctxt: an HTML parser context + * @newtag: The new tag name + * + * The HTML DTD allows a tag to exists only implicitly + * called when a new tag has been detected and generates the + * appropriates implicit tags if missing + */ +static void +htmlCheckImplied(htmlParserCtxtPtr ctxt, const xmlChar *newtag) { + int i; + + if (ctxt->options & HTML_PARSE_NOIMPLIED) + return; + if (!htmlOmittedDefaultValue) + return; + if (xmlStrEqual(newtag, BAD_CAST"html")) + return; + if (ctxt->nameNr <= 0) { + htmlnamePush(ctxt, BAD_CAST"html"); + if ((ctxt->sax != NULL) && (ctxt->sax->startElement != NULL)) + ctxt->sax->startElement(ctxt->userData, BAD_CAST"html", NULL); + } + if ((xmlStrEqual(newtag, BAD_CAST"body")) || (xmlStrEqual(newtag, BAD_CAST"head"))) + return; + if ((ctxt->nameNr <= 1) && + ((xmlStrEqual(newtag, BAD_CAST"script")) || + (xmlStrEqual(newtag, BAD_CAST"style")) || + (xmlStrEqual(newtag, BAD_CAST"meta")) || + (xmlStrEqual(newtag, BAD_CAST"link")) || + (xmlStrEqual(newtag, BAD_CAST"title")) || + (xmlStrEqual(newtag, BAD_CAST"base")))) { + if (ctxt->html >= 3) { + /* we already saw or generated an <head> before */ + return; + } + /* + * dropped OBJECT ... i you put it first BODY will be + * assumed ! + */ + htmlnamePush(ctxt, BAD_CAST"head"); + if ((ctxt->sax != NULL) && (ctxt->sax->startElement != NULL)) + ctxt->sax->startElement(ctxt->userData, BAD_CAST"head", NULL); + } else if ((!xmlStrEqual(newtag, BAD_CAST"noframes")) && + (!xmlStrEqual(newtag, BAD_CAST"frame")) && + (!xmlStrEqual(newtag, BAD_CAST"frameset"))) { + if (ctxt->html >= 10) { + /* we already saw or generated a <body> before */ + return; + } + for (i = 0;i < ctxt->nameNr;i++) { + if (xmlStrEqual(ctxt->nameTab[i], BAD_CAST"body")) { + return; + } + if (xmlStrEqual(ctxt->nameTab[i], BAD_CAST"head")) { + return; + } + } + + htmlnamePush(ctxt, BAD_CAST"body"); + if ((ctxt->sax != NULL) && (ctxt->sax->startElement != NULL)) + ctxt->sax->startElement(ctxt->userData, BAD_CAST"body", NULL); + } +} + +/** + * htmlCheckParagraph + * @ctxt: an HTML parser context + * + * Check whether a p element need to be implied before inserting + * characters in the current element. + * + * Returns 1 if a paragraph has been inserted, 0 if not and -1 + * in case of error. + */ + +static int +htmlCheckParagraph(htmlParserCtxtPtr ctxt) { + const xmlChar *tag; + int i; + + if (ctxt == NULL) + return(-1); + tag = ctxt->name; + if (tag == NULL) { + htmlAutoClose(ctxt, BAD_CAST"p"); + htmlCheckImplied(ctxt, BAD_CAST"p"); + htmlnamePush(ctxt, BAD_CAST"p"); + if ((ctxt->sax != NULL) && (ctxt->sax->startElement != NULL)) + ctxt->sax->startElement(ctxt->userData, BAD_CAST"p", NULL); + return(1); + } + if (!htmlOmittedDefaultValue) + return(0); + for (i = 0; htmlNoContentElements[i] != NULL; i++) { + if (xmlStrEqual(tag, BAD_CAST htmlNoContentElements[i])) { + htmlAutoClose(ctxt, BAD_CAST"p"); + htmlCheckImplied(ctxt, BAD_CAST"p"); + htmlnamePush(ctxt, BAD_CAST"p"); + if ((ctxt->sax != NULL) && (ctxt->sax->startElement != NULL)) + ctxt->sax->startElement(ctxt->userData, BAD_CAST"p", NULL); + return(1); + } + } + return(0); +} + +/** + * htmlIsScriptAttribute: + * @name: an attribute name + * + * Check if an attribute is of content type Script + * + * Returns 1 is the attribute is a script 0 otherwise + */ +int +htmlIsScriptAttribute(const xmlChar *name) { + unsigned int i; + + if (name == NULL) + return(0); + /* + * all script attributes start with 'on' + */ + if ((name[0] != 'o') || (name[1] != 'n')) + return(0); + for (i = 0; + i < sizeof(htmlScriptAttributes)/sizeof(htmlScriptAttributes[0]); + i++) { + if (xmlStrEqual(name, (const xmlChar *) htmlScriptAttributes[i])) + return(1); + } + return(0); +} + +/************************************************************************ + * * + * The list of HTML predefined entities * + * * + ************************************************************************/ + + +static const htmlEntityDesc html40EntitiesTable[] = { +/* + * the 4 absolute ones, plus apostrophe. + */ +{ 34, "quot", "quotation mark = APL quote, U+0022 ISOnum" }, +{ 38, "amp", "ampersand, U+0026 ISOnum" }, +{ 39, "apos", "single quote" }, +{ 60, "lt", "less-than sign, U+003C ISOnum" }, +{ 62, "gt", "greater-than sign, U+003E ISOnum" }, + +/* + * A bunch still in the 128-255 range + * Replacing them depend really on the charset used. + */ +{ 160, "nbsp", "no-break space = non-breaking space, U+00A0 ISOnum" }, +{ 161, "iexcl","inverted exclamation mark, U+00A1 ISOnum" }, +{ 162, "cent", "cent sign, U+00A2 ISOnum" }, +{ 163, "pound","pound sign, U+00A3 ISOnum" }, +{ 164, "curren","currency sign, U+00A4 ISOnum" }, +{ 165, "yen", "yen sign = yuan sign, U+00A5 ISOnum" }, +{ 166, "brvbar","broken bar = broken vertical bar, U+00A6 ISOnum" }, +{ 167, "sect", "section sign, U+00A7 ISOnum" }, +{ 168, "uml", "diaeresis = spacing diaeresis, U+00A8 ISOdia" }, +{ 169, "copy", "copyright sign, U+00A9 ISOnum" }, +{ 170, "ordf", "feminine ordinal indicator, U+00AA ISOnum" }, +{ 171, "laquo","left-pointing double angle quotation mark = left pointing guillemet, U+00AB ISOnum" }, +{ 172, "not", "not sign, U+00AC ISOnum" }, +{ 173, "shy", "soft hyphen = discretionary hyphen, U+00AD ISOnum" }, +{ 174, "reg", "registered sign = registered trade mark sign, U+00AE ISOnum" }, +{ 175, "macr", "macron = spacing macron = overline = APL overbar, U+00AF ISOdia" }, +{ 176, "deg", "degree sign, U+00B0 ISOnum" }, +{ 177, "plusmn","plus-minus sign = plus-or-minus sign, U+00B1 ISOnum" }, +{ 178, "sup2", "superscript two = superscript digit two = squared, U+00B2 ISOnum" }, +{ 179, "sup3", "superscript three = superscript digit three = cubed, U+00B3 ISOnum" }, +{ 180, "acute","acute accent = spacing acute, U+00B4 ISOdia" }, +{ 181, "micro","micro sign, U+00B5 ISOnum" }, +{ 182, "para", "pilcrow sign = paragraph sign, U+00B6 ISOnum" }, +{ 183, "middot","middle dot = Georgian comma Greek middle dot, U+00B7 ISOnum" }, +{ 184, "cedil","cedilla = spacing cedilla, U+00B8 ISOdia" }, +{ 185, "sup1", "superscript one = superscript digit one, U+00B9 ISOnum" }, +{ 186, "ordm", "masculine ordinal indicator, U+00BA ISOnum" }, +{ 187, "raquo","right-pointing double angle quotation mark right pointing guillemet, U+00BB ISOnum" }, +{ 188, "frac14","vulgar fraction one quarter = fraction one quarter, U+00BC ISOnum" }, +{ 189, "frac12","vulgar fraction one half = fraction one half, U+00BD ISOnum" }, +{ 190, "frac34","vulgar fraction three quarters = fraction three quarters, U+00BE ISOnum" }, +{ 191, "iquest","inverted question mark = turned question mark, U+00BF ISOnum" }, +{ 192, "Agrave","latin capital letter A with grave = latin capital letter A grave, U+00C0 ISOlat1" }, +{ 193, "Aacute","latin capital letter A with acute, U+00C1 ISOlat1" }, +{ 194, "Acirc","latin capital letter A with circumflex, U+00C2 ISOlat1" }, +{ 195, "Atilde","latin capital letter A with tilde, U+00C3 ISOlat1" }, +{ 196, "Auml", "latin capital letter A with diaeresis, U+00C4 ISOlat1" }, +{ 197, "Aring","latin capital letter A with ring above = latin capital letter A ring, U+00C5 ISOlat1" }, +{ 198, "AElig","latin capital letter AE = latin capital ligature AE, U+00C6 ISOlat1" }, +{ 199, "Ccedil","latin capital letter C with cedilla, U+00C7 ISOlat1" }, +{ 200, "Egrave","latin capital letter E with grave, U+00C8 ISOlat1" }, +{ 201, "Eacute","latin capital letter E with acute, U+00C9 ISOlat1" }, +{ 202, "Ecirc","latin capital letter E with circumflex, U+00CA ISOlat1" }, +{ 203, "Euml", "latin capital letter E with diaeresis, U+00CB ISOlat1" }, +{ 204, "Igrave","latin capital letter I with grave, U+00CC ISOlat1" }, +{ 205, "Iacute","latin capital letter I with acute, U+00CD ISOlat1" }, +{ 206, "Icirc","latin capital letter I with circumflex, U+00CE ISOlat1" }, +{ 207, "Iuml", "latin capital letter I with diaeresis, U+00CF ISOlat1" }, +{ 208, "ETH", "latin capital letter ETH, U+00D0 ISOlat1" }, +{ 209, "Ntilde","latin capital letter N with tilde, U+00D1 ISOlat1" }, +{ 210, "Ograve","latin capital letter O with grave, U+00D2 ISOlat1" }, +{ 211, "Oacute","latin capital letter O with acute, U+00D3 ISOlat1" }, +{ 212, "Ocirc","latin capital letter O with circumflex, U+00D4 ISOlat1" }, +{ 213, "Otilde","latin capital letter O with tilde, U+00D5 ISOlat1" }, +{ 214, "Ouml", "latin capital letter O with diaeresis, U+00D6 ISOlat1" }, +{ 215, "times","multiplication sign, U+00D7 ISOnum" }, +{ 216, "Oslash","latin capital letter O with stroke latin capital letter O slash, U+00D8 ISOlat1" }, +{ 217, "Ugrave","latin capital letter U with grave, U+00D9 ISOlat1" }, +{ 218, "Uacute","latin capital letter U with acute, U+00DA ISOlat1" }, +{ 219, "Ucirc","latin capital letter U with circumflex, U+00DB ISOlat1" }, +{ 220, "Uuml", "latin capital letter U with diaeresis, U+00DC ISOlat1" }, +{ 221, "Yacute","latin capital letter Y with acute, U+00DD ISOlat1" }, +{ 222, "THORN","latin capital letter THORN, U+00DE ISOlat1" }, +{ 223, "szlig","latin small letter sharp s = ess-zed, U+00DF ISOlat1" }, +{ 224, "agrave","latin small letter a with grave = latin small letter a grave, U+00E0 ISOlat1" }, +{ 225, "aacute","latin small letter a with acute, U+00E1 ISOlat1" }, +{ 226, "acirc","latin small letter a with circumflex, U+00E2 ISOlat1" }, +{ 227, "atilde","latin small letter a with tilde, U+00E3 ISOlat1" }, +{ 228, "auml", "latin small letter a with diaeresis, U+00E4 ISOlat1" }, +{ 229, "aring","latin small letter a with ring above = latin small letter a ring, U+00E5 ISOlat1" }, +{ 230, "aelig","latin small letter ae = latin small ligature ae, U+00E6 ISOlat1" }, +{ 231, "ccedil","latin small letter c with cedilla, U+00E7 ISOlat1" }, +{ 232, "egrave","latin small letter e with grave, U+00E8 ISOlat1" }, +{ 233, "eacute","latin small letter e with acute, U+00E9 ISOlat1" }, +{ 234, "ecirc","latin small letter e with circumflex, U+00EA ISOlat1" }, +{ 235, "euml", "latin small letter e with diaeresis, U+00EB ISOlat1" }, +{ 236, "igrave","latin small letter i with grave, U+00EC ISOlat1" }, +{ 237, "iacute","latin small letter i with acute, U+00ED ISOlat1" }, +{ 238, "icirc","latin small letter i with circumflex, U+00EE ISOlat1" }, +{ 239, "iuml", "latin small letter i with diaeresis, U+00EF ISOlat1" }, +{ 240, "eth", "latin small letter eth, U+00F0 ISOlat1" }, +{ 241, "ntilde","latin small letter n with tilde, U+00F1 ISOlat1" }, +{ 242, "ograve","latin small letter o with grave, U+00F2 ISOlat1" }, +{ 243, "oacute","latin small letter o with acute, U+00F3 ISOlat1" }, +{ 244, "ocirc","latin small letter o with circumflex, U+00F4 ISOlat1" }, +{ 245, "otilde","latin small letter o with tilde, U+00F5 ISOlat1" }, +{ 246, "ouml", "latin small letter o with diaeresis, U+00F6 ISOlat1" }, +{ 247, "divide","division sign, U+00F7 ISOnum" }, +{ 248, "oslash","latin small letter o with stroke, = latin small letter o slash, U+00F8 ISOlat1" }, +{ 249, "ugrave","latin small letter u with grave, U+00F9 ISOlat1" }, +{ 250, "uacute","latin small letter u with acute, U+00FA ISOlat1" }, +{ 251, "ucirc","latin small letter u with circumflex, U+00FB ISOlat1" }, +{ 252, "uuml", "latin small letter u with diaeresis, U+00FC ISOlat1" }, +{ 253, "yacute","latin small letter y with acute, U+00FD ISOlat1" }, +{ 254, "thorn","latin small letter thorn with, U+00FE ISOlat1" }, +{ 255, "yuml", "latin small letter y with diaeresis, U+00FF ISOlat1" }, + +{ 338, "OElig","latin capital ligature OE, U+0152 ISOlat2" }, +{ 339, "oelig","latin small ligature oe, U+0153 ISOlat2" }, +{ 352, "Scaron","latin capital letter S with caron, U+0160 ISOlat2" }, +{ 353, "scaron","latin small letter s with caron, U+0161 ISOlat2" }, +{ 376, "Yuml", "latin capital letter Y with diaeresis, U+0178 ISOlat2" }, + +/* + * Anything below should really be kept as entities references + */ +{ 402, "fnof", "latin small f with hook = function = florin, U+0192 ISOtech" }, + +{ 710, "circ", "modifier letter circumflex accent, U+02C6 ISOpub" }, +{ 732, "tilde","small tilde, U+02DC ISOdia" }, + +{ 913, "Alpha","greek capital letter alpha, U+0391" }, +{ 914, "Beta", "greek capital letter beta, U+0392" }, +{ 915, "Gamma","greek capital letter gamma, U+0393 ISOgrk3" }, +{ 916, "Delta","greek capital letter delta, U+0394 ISOgrk3" }, +{ 917, "Epsilon","greek capital letter epsilon, U+0395" }, +{ 918, "Zeta", "greek capital letter zeta, U+0396" }, +{ 919, "Eta", "greek capital letter eta, U+0397" }, +{ 920, "Theta","greek capital letter theta, U+0398 ISOgrk3" }, +{ 921, "Iota", "greek capital letter iota, U+0399" }, +{ 922, "Kappa","greek capital letter kappa, U+039A" }, +{ 923, "Lambda", "greek capital letter lambda, U+039B ISOgrk3" }, +{ 924, "Mu", "greek capital letter mu, U+039C" }, +{ 925, "Nu", "greek capital letter nu, U+039D" }, +{ 926, "Xi", "greek capital letter xi, U+039E ISOgrk3" }, +{ 927, "Omicron","greek capital letter omicron, U+039F" }, +{ 928, "Pi", "greek capital letter pi, U+03A0 ISOgrk3" }, +{ 929, "Rho", "greek capital letter rho, U+03A1" }, +{ 931, "Sigma","greek capital letter sigma, U+03A3 ISOgrk3" }, +{ 932, "Tau", "greek capital letter tau, U+03A4" }, +{ 933, "Upsilon","greek capital letter upsilon, U+03A5 ISOgrk3" }, +{ 934, "Phi", "greek capital letter phi, U+03A6 ISOgrk3" }, +{ 935, "Chi", "greek capital letter chi, U+03A7" }, +{ 936, "Psi", "greek capital letter psi, U+03A8 ISOgrk3" }, +{ 937, "Omega","greek capital letter omega, U+03A9 ISOgrk3" }, + +{ 945, "alpha","greek small letter alpha, U+03B1 ISOgrk3" }, +{ 946, "beta", "greek small letter beta, U+03B2 ISOgrk3" }, +{ 947, "gamma","greek small letter gamma, U+03B3 ISOgrk3" }, +{ 948, "delta","greek small letter delta, U+03B4 ISOgrk3" }, +{ 949, "epsilon","greek small letter epsilon, U+03B5 ISOgrk3" }, +{ 950, "zeta", "greek small letter zeta, U+03B6 ISOgrk3" }, +{ 951, "eta", "greek small letter eta, U+03B7 ISOgrk3" }, +{ 952, "theta","greek small letter theta, U+03B8 ISOgrk3" }, +{ 953, "iota", "greek small letter iota, U+03B9 ISOgrk3" }, +{ 954, "kappa","greek small letter kappa, U+03BA ISOgrk3" }, +{ 955, "lambda","greek small letter lambda, U+03BB ISOgrk3" }, +{ 956, "mu", "greek small letter mu, U+03BC ISOgrk3" }, +{ 957, "nu", "greek small letter nu, U+03BD ISOgrk3" }, +{ 958, "xi", "greek small letter xi, U+03BE ISOgrk3" }, +{ 959, "omicron","greek small letter omicron, U+03BF NEW" }, +{ 960, "pi", "greek small letter pi, U+03C0 ISOgrk3" }, +{ 961, "rho", "greek small letter rho, U+03C1 ISOgrk3" }, +{ 962, "sigmaf","greek small letter final sigma, U+03C2 ISOgrk3" }, +{ 963, "sigma","greek small letter sigma, U+03C3 ISOgrk3" }, +{ 964, "tau", "greek small letter tau, U+03C4 ISOgrk3" }, +{ 965, "upsilon","greek small letter upsilon, U+03C5 ISOgrk3" }, +{ 966, "phi", "greek small letter phi, U+03C6 ISOgrk3" }, +{ 967, "chi", "greek small letter chi, U+03C7 ISOgrk3" }, +{ 968, "psi", "greek small letter psi, U+03C8 ISOgrk3" }, +{ 969, "omega","greek small letter omega, U+03C9 ISOgrk3" }, +{ 977, "thetasym","greek small letter theta symbol, U+03D1 NEW" }, +{ 978, "upsih","greek upsilon with hook symbol, U+03D2 NEW" }, +{ 982, "piv", "greek pi symbol, U+03D6 ISOgrk3" }, + +{ 8194, "ensp", "en space, U+2002 ISOpub" }, +{ 8195, "emsp", "em space, U+2003 ISOpub" }, +{ 8201, "thinsp","thin space, U+2009 ISOpub" }, +{ 8204, "zwnj", "zero width non-joiner, U+200C NEW RFC 2070" }, +{ 8205, "zwj", "zero width joiner, U+200D NEW RFC 2070" }, +{ 8206, "lrm", "left-to-right mark, U+200E NEW RFC 2070" }, +{ 8207, "rlm", "right-to-left mark, U+200F NEW RFC 2070" }, +{ 8211, "ndash","en dash, U+2013 ISOpub" }, +{ 8212, "mdash","em dash, U+2014 ISOpub" }, +{ 8216, "lsquo","left single quotation mark, U+2018 ISOnum" }, +{ 8217, "rsquo","right single quotation mark, U+2019 ISOnum" }, +{ 8218, "sbquo","single low-9 quotation mark, U+201A NEW" }, +{ 8220, "ldquo","left double quotation mark, U+201C ISOnum" }, +{ 8221, "rdquo","right double quotation mark, U+201D ISOnum" }, +{ 8222, "bdquo","double low-9 quotation mark, U+201E NEW" }, +{ 8224, "dagger","dagger, U+2020 ISOpub" }, +{ 8225, "Dagger","double dagger, U+2021 ISOpub" }, + +{ 8226, "bull", "bullet = black small circle, U+2022 ISOpub" }, +{ 8230, "hellip","horizontal ellipsis = three dot leader, U+2026 ISOpub" }, + +{ 8240, "permil","per mille sign, U+2030 ISOtech" }, + +{ 8242, "prime","prime = minutes = feet, U+2032 ISOtech" }, +{ 8243, "Prime","double prime = seconds = inches, U+2033 ISOtech" }, + +{ 8249, "lsaquo","single left-pointing angle quotation mark, U+2039 ISO proposed" }, +{ 8250, "rsaquo","single right-pointing angle quotation mark, U+203A ISO proposed" }, + +{ 8254, "oline","overline = spacing overscore, U+203E NEW" }, +{ 8260, "frasl","fraction slash, U+2044 NEW" }, + +{ 8364, "euro", "euro sign, U+20AC NEW" }, + +{ 8465, "image","blackletter capital I = imaginary part, U+2111 ISOamso" }, +{ 8472, "weierp","script capital P = power set = Weierstrass p, U+2118 ISOamso" }, +{ 8476, "real", "blackletter capital R = real part symbol, U+211C ISOamso" }, +{ 8482, "trade","trade mark sign, U+2122 ISOnum" }, +{ 8501, "alefsym","alef symbol = first transfinite cardinal, U+2135 NEW" }, +{ 8592, "larr", "leftwards arrow, U+2190 ISOnum" }, +{ 8593, "uarr", "upwards arrow, U+2191 ISOnum" }, +{ 8594, "rarr", "rightwards arrow, U+2192 ISOnum" }, +{ 8595, "darr", "downwards arrow, U+2193 ISOnum" }, +{ 8596, "harr", "left right arrow, U+2194 ISOamsa" }, +{ 8629, "crarr","downwards arrow with corner leftwards = carriage return, U+21B5 NEW" }, +{ 8656, "lArr", "leftwards double arrow, U+21D0 ISOtech" }, +{ 8657, "uArr", "upwards double arrow, U+21D1 ISOamsa" }, +{ 8658, "rArr", "rightwards double arrow, U+21D2 ISOtech" }, +{ 8659, "dArr", "downwards double arrow, U+21D3 ISOamsa" }, +{ 8660, "hArr", "left right double arrow, U+21D4 ISOamsa" }, + +{ 8704, "forall","for all, U+2200 ISOtech" }, +{ 8706, "part", "partial differential, U+2202 ISOtech" }, +{ 8707, "exist","there exists, U+2203 ISOtech" }, +{ 8709, "empty","empty set = null set = diameter, U+2205 ISOamso" }, +{ 8711, "nabla","nabla = backward difference, U+2207 ISOtech" }, +{ 8712, "isin", "element of, U+2208 ISOtech" }, +{ 8713, "notin","not an element of, U+2209 ISOtech" }, +{ 8715, "ni", "contains as member, U+220B ISOtech" }, +{ 8719, "prod", "n-ary product = product sign, U+220F ISOamsb" }, +{ 8721, "sum", "n-ary summation, U+2211 ISOamsb" }, +{ 8722, "minus","minus sign, U+2212 ISOtech" }, +{ 8727, "lowast","asterisk operator, U+2217 ISOtech" }, +{ 8730, "radic","square root = radical sign, U+221A ISOtech" }, +{ 8733, "prop", "proportional to, U+221D ISOtech" }, +{ 8734, "infin","infinity, U+221E ISOtech" }, +{ 8736, "ang", "angle, U+2220 ISOamso" }, +{ 8743, "and", "logical and = wedge, U+2227 ISOtech" }, +{ 8744, "or", "logical or = vee, U+2228 ISOtech" }, +{ 8745, "cap", "intersection = cap, U+2229 ISOtech" }, +{ 8746, "cup", "union = cup, U+222A ISOtech" }, +{ 8747, "int", "integral, U+222B ISOtech" }, +{ 8756, "there4","therefore, U+2234 ISOtech" }, +{ 8764, "sim", "tilde operator = varies with = similar to, U+223C ISOtech" }, +{ 8773, "cong", "approximately equal to, U+2245 ISOtech" }, +{ 8776, "asymp","almost equal to = asymptotic to, U+2248 ISOamsr" }, +{ 8800, "ne", "not equal to, U+2260 ISOtech" }, +{ 8801, "equiv","identical to, U+2261 ISOtech" }, +{ 8804, "le", "less-than or equal to, U+2264 ISOtech" }, +{ 8805, "ge", "greater-than or equal to, U+2265 ISOtech" }, +{ 8834, "sub", "subset of, U+2282 ISOtech" }, +{ 8835, "sup", "superset of, U+2283 ISOtech" }, +{ 8836, "nsub", "not a subset of, U+2284 ISOamsn" }, +{ 8838, "sube", "subset of or equal to, U+2286 ISOtech" }, +{ 8839, "supe", "superset of or equal to, U+2287 ISOtech" }, +{ 8853, "oplus","circled plus = direct sum, U+2295 ISOamsb" }, +{ 8855, "otimes","circled times = vector product, U+2297 ISOamsb" }, +{ 8869, "perp", "up tack = orthogonal to = perpendicular, U+22A5 ISOtech" }, +{ 8901, "sdot", "dot operator, U+22C5 ISOamsb" }, +{ 8968, "lceil","left ceiling = apl upstile, U+2308 ISOamsc" }, +{ 8969, "rceil","right ceiling, U+2309 ISOamsc" }, +{ 8970, "lfloor","left floor = apl downstile, U+230A ISOamsc" }, +{ 8971, "rfloor","right floor, U+230B ISOamsc" }, +{ 9001, "lang", "left-pointing angle bracket = bra, U+2329 ISOtech" }, +{ 9002, "rang", "right-pointing angle bracket = ket, U+232A ISOtech" }, +{ 9674, "loz", "lozenge, U+25CA ISOpub" }, + +{ 9824, "spades","black spade suit, U+2660 ISOpub" }, +{ 9827, "clubs","black club suit = shamrock, U+2663 ISOpub" }, +{ 9829, "hearts","black heart suit = valentine, U+2665 ISOpub" }, +{ 9830, "diams","black diamond suit, U+2666 ISOpub" }, + +}; + +/************************************************************************ + * * + * Commodity functions to handle entities * + * * + ************************************************************************/ + +/* + * Macro used to grow the current buffer. + */ +#define growBuffer(buffer) { \ + xmlChar *tmp; \ + buffer##_size *= 2; \ + tmp = (xmlChar *) xmlRealloc(buffer, buffer##_size * sizeof(xmlChar)); \ + if (tmp == NULL) { \ + htmlErrMemory(ctxt, "growing buffer\n"); \ + xmlFree(buffer); \ + return(NULL); \ + } \ + buffer = tmp; \ +} + +/** + * htmlEntityLookup: + * @name: the entity name + * + * Lookup the given entity in EntitiesTable + * + * TODO: the linear scan is really ugly, an hash table is really needed. + * + * Returns the associated htmlEntityDescPtr if found, NULL otherwise. + */ +const htmlEntityDesc * +htmlEntityLookup(const xmlChar *name) { + unsigned int i; + + for (i = 0;i < (sizeof(html40EntitiesTable)/ + sizeof(html40EntitiesTable[0]));i++) { + if (xmlStrEqual(name, BAD_CAST html40EntitiesTable[i].name)) { + return((htmlEntityDescPtr) &html40EntitiesTable[i]); + } + } + return(NULL); +} + +/** + * htmlEntityValueLookup: + * @value: the entity's unicode value + * + * Lookup the given entity in EntitiesTable + * + * TODO: the linear scan is really ugly, an hash table is really needed. + * + * Returns the associated htmlEntityDescPtr if found, NULL otherwise. + */ +const htmlEntityDesc * +htmlEntityValueLookup(unsigned int value) { + unsigned int i; + + for (i = 0;i < (sizeof(html40EntitiesTable)/ + sizeof(html40EntitiesTable[0]));i++) { + if (html40EntitiesTable[i].value >= value) { + if (html40EntitiesTable[i].value > value) + break; + return((htmlEntityDescPtr) &html40EntitiesTable[i]); + } + } + return(NULL); +} + +/** + * UTF8ToHtml: + * @out: a pointer to an array of bytes to store the result + * @outlen: the length of @out + * @in: a pointer to an array of UTF-8 chars + * @inlen: the length of @in + * + * Take a block of UTF-8 chars in and try to convert it to an ASCII + * plus HTML entities block of chars out. + * + * Returns 0 if success, -2 if the transcoding fails, or -1 otherwise + * The value of @inlen after return is the number of octets consumed + * as the return value is positive, else unpredictable. + * The value of @outlen after return is the number of octets consumed. + */ +int +UTF8ToHtml(unsigned char* out, int *outlen, + const unsigned char* in, int *inlen) { + const unsigned char* processed = in; + const unsigned char* outend; + const unsigned char* outstart = out; + const unsigned char* instart = in; + const unsigned char* inend; + unsigned int c, d; + int trailing; + + if ((out == NULL) || (outlen == NULL) || (inlen == NULL)) return(-1); + if (in == NULL) { + /* + * initialization nothing to do + */ + *outlen = 0; + *inlen = 0; + return(0); + } + inend = in + (*inlen); + outend = out + (*outlen); + while (in < inend) { + d = *in++; + if (d < 0x80) { c= d; trailing= 0; } + else if (d < 0xC0) { + /* trailing byte in leading position */ + *outlen = out - outstart; + *inlen = processed - instart; + return(-2); + } else if (d < 0xE0) { c= d & 0x1F; trailing= 1; } + else if (d < 0xF0) { c= d & 0x0F; trailing= 2; } + else if (d < 0xF8) { c= d & 0x07; trailing= 3; } + else { + /* no chance for this in Ascii */ + *outlen = out - outstart; + *inlen = processed - instart; + return(-2); + } + + if (inend - in < trailing) { + break; + } + + for ( ; trailing; trailing--) { + if ((in >= inend) || (((d= *in++) & 0xC0) != 0x80)) + break; + c <<= 6; + c |= d & 0x3F; + } + + /* assertion: c is a single UTF-4 value */ + if (c < 0x80) { + if (out + 1 >= outend) + break; + *out++ = c; + } else { + int len; + const htmlEntityDesc * ent; + const char *cp; + char nbuf[16]; + + /* + * Try to lookup a predefined HTML entity for it + */ + + ent = htmlEntityValueLookup(c); + if (ent == NULL) { + snprintf(nbuf, sizeof(nbuf), "#%u", c); + cp = nbuf; + } + else + cp = ent->name; + len = strlen(cp); + if (out + 2 + len >= outend) + break; + *out++ = '&'; + memcpy(out, cp, len); + out += len; + *out++ = ';'; + } + processed = in; + } + *outlen = out - outstart; + *inlen = processed - instart; + return(0); +} + +/** + * htmlEncodeEntities: + * @out: a pointer to an array of bytes to store the result + * @outlen: the length of @out + * @in: a pointer to an array of UTF-8 chars + * @inlen: the length of @in + * @quoteChar: the quote character to escape (' or ") or zero. + * + * Take a block of UTF-8 chars in and try to convert it to an ASCII + * plus HTML entities block of chars out. + * + * Returns 0 if success, -2 if the transcoding fails, or -1 otherwise + * The value of @inlen after return is the number of octets consumed + * as the return value is positive, else unpredictable. + * The value of @outlen after return is the number of octets consumed. + */ +int +htmlEncodeEntities(unsigned char* out, int *outlen, + const unsigned char* in, int *inlen, int quoteChar) { + const unsigned char* processed = in; + const unsigned char* outend; + const unsigned char* outstart = out; + const unsigned char* instart = in; + const unsigned char* inend; + unsigned int c, d; + int trailing; + + if ((out == NULL) || (outlen == NULL) || (inlen == NULL) || (in == NULL)) + return(-1); + outend = out + (*outlen); + inend = in + (*inlen); + while (in < inend) { + d = *in++; + if (d < 0x80) { c= d; trailing= 0; } + else if (d < 0xC0) { + /* trailing byte in leading position */ + *outlen = out - outstart; + *inlen = processed - instart; + return(-2); + } else if (d < 0xE0) { c= d & 0x1F; trailing= 1; } + else if (d < 0xF0) { c= d & 0x0F; trailing= 2; } + else if (d < 0xF8) { c= d & 0x07; trailing= 3; } + else { + /* no chance for this in Ascii */ + *outlen = out - outstart; + *inlen = processed - instart; + return(-2); + } + + if (inend - in < trailing) + break; + + while (trailing--) { + if (((d= *in++) & 0xC0) != 0x80) { + *outlen = out - outstart; + *inlen = processed - instart; + return(-2); + } + c <<= 6; + c |= d & 0x3F; + } + + /* assertion: c is a single UTF-4 value */ + if ((c < 0x80) && (c != (unsigned int) quoteChar) && + (c != '&') && (c != '<') && (c != '>')) { + if (out >= outend) + break; + *out++ = c; + } else { + const htmlEntityDesc * ent; + const char *cp; + char nbuf[16]; + int len; + + /* + * Try to lookup a predefined HTML entity for it + */ + ent = htmlEntityValueLookup(c); + if (ent == NULL) { + snprintf(nbuf, sizeof(nbuf), "#%u", c); + cp = nbuf; + } + else + cp = ent->name; + len = strlen(cp); + if (out + 2 + len > outend) + break; + *out++ = '&'; + memcpy(out, cp, len); + out += len; + *out++ = ';'; + } + processed = in; + } + *outlen = out - outstart; + *inlen = processed - instart; + return(0); +} + +/************************************************************************ + * * + * Commodity functions to handle streams * + * * + ************************************************************************/ + +/** + * htmlNewInputStream: + * @ctxt: an HTML parser context + * + * Create a new input stream structure + * Returns the new input stream or NULL + */ +static htmlParserInputPtr +htmlNewInputStream(htmlParserCtxtPtr ctxt) { + htmlParserInputPtr input; + + input = (xmlParserInputPtr) xmlMalloc(sizeof(htmlParserInput)); + if (input == NULL) { + htmlErrMemory(ctxt, "couldn't allocate a new input stream\n"); + return(NULL); + } + memset(input, 0, sizeof(htmlParserInput)); + input->filename = NULL; + input->directory = NULL; + input->base = NULL; + input->cur = NULL; + input->buf = NULL; + input->line = 1; + input->col = 1; + input->buf = NULL; + input->free = NULL; + input->version = NULL; + input->consumed = 0; + input->length = 0; + return(input); +} + + +/************************************************************************ + * * + * Commodity functions, cleanup needed ? * + * * + ************************************************************************/ +/* + * all tags allowing pc data from the html 4.01 loose dtd + * NOTE: it might be more apropriate to integrate this information + * into the html40ElementTable array but I don't want to risk any + * binary incomptibility + */ +static const char *allowPCData[] = { + "a", "abbr", "acronym", "address", "applet", "b", "bdo", "big", + "blockquote", "body", "button", "caption", "center", "cite", "code", + "dd", "del", "dfn", "div", "dt", "em", "font", "form", "h1", "h2", + "h3", "h4", "h5", "h6", "i", "iframe", "ins", "kbd", "label", "legend", + "li", "noframes", "noscript", "object", "p", "pre", "q", "s", "samp", + "small", "span", "strike", "strong", "td", "th", "tt", "u", "var" +}; + +/** + * areBlanks: + * @ctxt: an HTML parser context + * @str: a xmlChar * + * @len: the size of @str + * + * Is this a sequence of blank chars that one can ignore ? + * + * Returns 1 if ignorable 0 otherwise. + */ + +static int areBlanks(htmlParserCtxtPtr ctxt, const xmlChar *str, int len) { + unsigned int i; + int j; + xmlNodePtr lastChild; + xmlDtdPtr dtd; + + for (j = 0;j < len;j++) + if (!(IS_BLANK_CH(str[j]))) return(0); + + if (CUR == 0) return(1); + if (CUR != '<') return(0); + if (ctxt->name == NULL) + return(1); + if (xmlStrEqual(ctxt->name, BAD_CAST"html")) + return(1); + if (xmlStrEqual(ctxt->name, BAD_CAST"head")) + return(1); + + /* Only strip CDATA children of the body tag for strict HTML DTDs */ + if (xmlStrEqual(ctxt->name, BAD_CAST "body") && ctxt->myDoc != NULL) { + dtd = xmlGetIntSubset(ctxt->myDoc); + if (dtd != NULL && dtd->ExternalID != NULL) { + if (!xmlStrcasecmp(dtd->ExternalID, BAD_CAST "-//W3C//DTD HTML 4.01//EN") || + !xmlStrcasecmp(dtd->ExternalID, BAD_CAST "-//W3C//DTD HTML 4//EN")) + return(1); + } + } + + if (ctxt->node == NULL) return(0); + lastChild = xmlGetLastChild(ctxt->node); + while ((lastChild) && (lastChild->type == XML_COMMENT_NODE)) + lastChild = lastChild->prev; + if (lastChild == NULL) { + if ((ctxt->node->type != XML_ELEMENT_NODE) && + (ctxt->node->content != NULL)) return(0); + /* keep ws in constructs like ...<b> </b>... + for all tags "b" allowing PCDATA */ + for ( i = 0; i < sizeof(allowPCData)/sizeof(allowPCData[0]); i++ ) { + if ( xmlStrEqual(ctxt->name, BAD_CAST allowPCData[i]) ) { + return(0); + } + } + } else if (xmlNodeIsText(lastChild)) { + return(0); + } else { + /* keep ws in constructs like <p><b>xy</b> <i>z</i><p> + for all tags "p" allowing PCDATA */ + for ( i = 0; i < sizeof(allowPCData)/sizeof(allowPCData[0]); i++ ) { + if ( xmlStrEqual(lastChild->name, BAD_CAST allowPCData[i]) ) { + return(0); + } + } + } + return(1); +} + +/** + * htmlNewDocNoDtD: + * @URI: URI for the dtd, or NULL + * @ExternalID: the external ID of the DTD, or NULL + * + * Creates a new HTML document without a DTD node if @URI and @ExternalID + * are NULL + * + * Returns a new document, do not initialize the DTD if not provided + */ +htmlDocPtr +htmlNewDocNoDtD(const xmlChar *URI, const xmlChar *ExternalID) { + xmlDocPtr cur; + + /* + * Allocate a new document and fill the fields. + */ + cur = (xmlDocPtr) xmlMalloc(sizeof(xmlDoc)); + if (cur == NULL) { + htmlErrMemory(NULL, "HTML document creation failed\n"); + return(NULL); + } + memset(cur, 0, sizeof(xmlDoc)); + + cur->type = XML_HTML_DOCUMENT_NODE; + cur->version = NULL; + cur->intSubset = NULL; + cur->doc = cur; + cur->name = NULL; + cur->children = NULL; + cur->extSubset = NULL; + cur->oldNs = NULL; + cur->encoding = NULL; + cur->standalone = 1; + cur->compression = 0; + cur->ids = NULL; + cur->refs = NULL; + cur->_private = NULL; + cur->charset = XML_CHAR_ENCODING_UTF8; + cur->properties = XML_DOC_HTML | XML_DOC_USERBUILT; + if ((ExternalID != NULL) || + (URI != NULL)) + xmlCreateIntSubset(cur, BAD_CAST "html", ExternalID, URI); + return(cur); +} + +/** + * htmlNewDoc: + * @URI: URI for the dtd, or NULL + * @ExternalID: the external ID of the DTD, or NULL + * + * Creates a new HTML document + * + * Returns a new document + */ +htmlDocPtr +htmlNewDoc(const xmlChar *URI, const xmlChar *ExternalID) { + if ((URI == NULL) && (ExternalID == NULL)) + return(htmlNewDocNoDtD( + BAD_CAST "http://www.w3.org/TR/REC-html40/loose.dtd";, + BAD_CAST "-//W3C//DTD HTML 4.0 Transitional//EN")); + + return(htmlNewDocNoDtD(URI, ExternalID)); +} + + +/************************************************************************ + * * + * The parser itself * + * Relates to http://www.w3.org/TR/html40 * + * * + ************************************************************************/ + +/************************************************************************ + * * + * The parser itself * + * * + ************************************************************************/ + +static const xmlChar * htmlParseNameComplex(xmlParserCtxtPtr ctxt); + +/** + * htmlParseHTMLName: + * @ctxt: an HTML parser context + * + * parse an HTML tag or attribute name, note that we convert it to lowercase + * since HTML names are not case-sensitive. + * + * Returns the Tag Name parsed or NULL + */ + +static const xmlChar * +htmlParseHTMLName(htmlParserCtxtPtr ctxt) { + int i = 0; + xmlChar loc[HTML_PARSER_BUFFER_SIZE]; + + if (!IS_ASCII_LETTER(CUR) && (CUR != '_') && + (CUR != ':') && (CUR != '.')) return(NULL); + + while ((i < HTML_PARSER_BUFFER_SIZE) && + ((IS_ASCII_LETTER(CUR)) || (IS_ASCII_DIGIT(CUR)) || + (CUR == ':') || (CUR == '-') || (CUR == '_') || + (CUR == '.'))) { + if ((CUR >= 'A') && (CUR <= 'Z')) loc[i] = CUR + 0x20; + else loc[i] = CUR; + i++; + + NEXT; + } + + return(xmlDictLookup(ctxt->dict, loc, i)); +} + + +/** + * htmlParseHTMLName_nonInvasive: + * @ctxt: an HTML parser context + * + * parse an HTML tag or attribute name, note that we convert it to lowercase + * since HTML names are not case-sensitive, this doesn't consume the data + * from the stream, it's a look-ahead + * + * Returns the Tag Name parsed or NULL + */ + +static const xmlChar * +htmlParseHTMLName_nonInvasive(htmlParserCtxtPtr ctxt) { + int i = 0; + xmlChar loc[HTML_PARSER_BUFFER_SIZE]; + + if (!IS_ASCII_LETTER(NXT(1)) && (NXT(1) != '_') && + (NXT(1) != ':')) return(NULL); + + while ((i < HTML_PARSER_BUFFER_SIZE) && + ((IS_ASCII_LETTER(NXT(1+i))) || (IS_ASCII_DIGIT(NXT(1+i))) || + (NXT(1+i) == ':') || (NXT(1+i) == '-') || (NXT(1+i) == '_'))) { + if ((NXT(1+i) >= 'A') && (NXT(1+i) <= 'Z')) loc[i] = NXT(1+i) + 0x20; + else loc[i] = NXT(1+i); + i++; + } + + return(xmlDictLookup(ctxt->dict, loc, i)); +} + + +/** + * htmlParseName: + * @ctxt: an HTML parser context + * + * parse an HTML name, this routine is case sensitive. + * + * Returns the Name parsed or NULL + */ + +static const xmlChar * +htmlParseName(htmlParserCtxtPtr ctxt) { + const xmlChar *in; + const xmlChar *ret; + int count = 0; + + GROW; + + /* + * Accelerator for simple ASCII names + */ + in = ctxt->input->cur; + if (((*in >= 0x61) && (*
<TRUNCATED>
