diff --git a/ChangeLog b/ChangeLog index 700a90b7..38a1fba9 100644 --- a/ChangeLog +++ b/ChangeLog @@ -1,3 +1,10 @@ +Tue Aug 29 11:24:48 CEST 2000 Daniel Veillard + + * HTMLparser.c testHTML.c: applied two new patches from + Wayne Davison + * result/HTML/*.sax: regenerated HTML SAX output + * parser.c: more cleanup. + Mon Aug 28 11:58:12 CEST 2000 Daniel Veillard * HTMLparser.[ch] testHTML.c: applied the second set of diff --git a/HTMLparser.c b/HTMLparser.c index 709be8dc..b0b43bd6 100644 --- a/HTMLparser.c +++ b/HTMLparser.c @@ -1650,6 +1650,8 @@ static int areBlanks(htmlParserCtxtPtr ctxt, const xmlChar *str, int len) { if (CUR != '<') return(0); if (ctxt->name == NULL) return(1); + if (!xmlStrcmp(ctxt->name, BAD_CAST"html")) + return(1); if (!xmlStrcmp(ctxt->name, BAD_CAST"head")) return(1); if (!xmlStrcmp(ctxt->name, BAD_CAST"body")) diff --git a/parser.c b/parser.c index 0964881f..dd9b98ff 100644 --- a/parser.c +++ b/parser.c @@ -4292,7 +4292,7 @@ xmlParseEntityValue(xmlParserCtxtPtr ctxt, xmlChar **orig) { * xmlStringDecodeEntities() */ cur = buf; - while (*cur != 0) { + while (*cur != 0) { /* non input consuming */ if ((*cur == '%') || ((*cur == '&') && (cur[1] != '#'))) { xmlChar *name; xmlChar tmp = *cur; @@ -4428,7 +4428,8 @@ xmlParseAttValue(xmlParserCtxtPtr ctxt) { * Ok loop until we reach one of the ending char or a size limit. */ c = CUR_CHAR(l); - while (((NXT(0) != limit) && (c != '<')) || (ctxt->token != 0)) { + while (((NXT(0) != limit) && /* checked */ + (c != '<')) || (ctxt->token != 0)) { if (c == 0) break; if (ctxt->token == '&') { static xmlChar buffer[6] = "&"; @@ -4437,7 +4438,7 @@ xmlParseAttValue(xmlParserCtxtPtr ctxt) { growBuffer(buf); } current = &buffer[0]; - while (*current != 0) { + while (*current != 0) { /* non input consuming */ buf[len++] = *current++; } ctxt->token = 0; @@ -4456,7 +4457,7 @@ xmlParseAttValue(xmlParserCtxtPtr ctxt) { XML_SUBSTITUTE_REF, 0, 0, 0); if (rep != NULL) { current = rep; - while (*current != 0) { + while (*current != 0) { /* non input consuming */ buf[len++] = *current++; if (len > buf_size - 10) { growBuffer(buf); @@ -4551,6 +4552,7 @@ xmlParseSystemLiteral(xmlParserCtxtPtr ctxt) { int cur, l; xmlChar stop; int state = ctxt->instate; + int count = 0; SHRINK; if (RAW == '"') { @@ -4576,7 +4578,7 @@ xmlParseSystemLiteral(xmlParserCtxtPtr ctxt) { } ctxt->instate = XML_PARSER_SYSTEM_LITERAL; cur = CUR_CHAR(l); - while ((IS_CHAR(cur)) && (cur != stop)) { + while ((IS_CHAR(cur)) && (cur != stop)) { /* checked */ if (len + 5 >= size) { size *= 2; buf = (xmlChar *) xmlRealloc(buf, size * sizeof(xmlChar)); @@ -4586,6 +4588,11 @@ xmlParseSystemLiteral(xmlParserCtxtPtr ctxt) { return(NULL); } } + count++; + if (count > 50) { + GROW; + count = 0; + } COPY_BUF(l,buf,len,cur); NEXTL(l); cur = CUR_CHAR(l); @@ -4627,6 +4634,7 @@ xmlParsePubidLiteral(xmlParserCtxtPtr ctxt) { int size = XML_PARSER_BUFFER_SIZE; xmlChar cur; xmlChar stop; + int count = 0; SHRINK; if (RAW == '"') { @@ -4650,7 +4658,7 @@ xmlParsePubidLiteral(xmlParserCtxtPtr ctxt) { return(NULL); } cur = CUR; - while ((IS_PUBIDCHAR(cur)) && (cur != stop)) { + while ((IS_PUBIDCHAR(cur)) && (cur != stop)) { /* checked */ if (len + 1 >= size) { size *= 2; buf = (xmlChar *) xmlRealloc(buf, size * sizeof(xmlChar)); @@ -4660,6 +4668,11 @@ xmlParsePubidLiteral(xmlParserCtxtPtr ctxt) { } } buf[len++] = cur; + count++; + if (count > 50) { + GROW; + count = 0; + } NEXT; cur = CUR; if (cur == 0) { @@ -4702,10 +4715,12 @@ xmlParseCharData(xmlParserCtxtPtr ctxt, int cdata) { xmlChar buf[XML_PARSER_BIG_BUFFER_SIZE + 5]; int nbchar = 0; int cur, l; + int count = 0; SHRINK; + GROW; cur = CUR_CHAR(l); - while (((cur != '<') || (ctxt->token == '<')) && + while (((cur != '<') || (ctxt->token == '<')) && /* checked */ ((cur != '&') || (ctxt->token == '&')) && (IS_CHAR(cur))) { if ((cur == ']') && (NXT(1) == ']') && @@ -4738,6 +4753,11 @@ xmlParseCharData(xmlParserCtxtPtr ctxt, int cdata) { } nbchar = 0; } + count++; + if (count > 50) { + GROW; + count = 0; + } NEXTL(l); cur = CUR_CHAR(l); } @@ -4852,7 +4872,7 @@ xmlParseExternalID(xmlParserCtxtPtr ctxt, xmlChar **publicID, int strict) { ptr = CUR_PTR; if (!IS_BLANK(*ptr)) return(NULL); - while (IS_BLANK(*ptr)) ptr++; + while (IS_BLANK(*ptr)) ptr++; /* TODO: dangerous, fix ! */ if ((*ptr != '\'') && (*ptr != '"')) return(NULL); } SKIP_BLANKS; @@ -4889,6 +4909,7 @@ xmlParseComment(xmlParserCtxtPtr ctxt) { int cur, l; xmlParserInputState state; xmlParserInputPtr input = ctxt->input; + int count = 0; /* * Check that there is a comment right here. @@ -4912,7 +4933,7 @@ xmlParseComment(xmlParserCtxtPtr ctxt) { NEXTL(rl); cur = CUR_CHAR(l); len = 0; - while (IS_CHAR(cur) && + while (IS_CHAR(cur) && /* checked */ ((cur != '>') || (r != '-') || (q != '-'))) { if ((r == '-') && (q == '-') && (len > 1)) { @@ -4937,6 +4958,12 @@ xmlParseComment(xmlParserCtxtPtr ctxt) { ql = rl; r = cur; rl = l; + + count++; + if (count > 50) { + GROW; + count = 0; + } NEXTL(l); cur = CUR_CHAR(l); if (cur == 0) { @@ -5043,6 +5070,7 @@ xmlParsePI(xmlParserCtxtPtr ctxt) { int cur, l; xmlChar *target; xmlParserInputState state; + int count = 0; if ((RAW == '<') && (NXT(1) == '?')) { xmlParserInputPtr input = ctxt->input; @@ -5099,7 +5127,7 @@ xmlParsePI(xmlParserCtxtPtr ctxt) { } SKIP_BLANKS; cur = CUR_CHAR(l); - while (IS_CHAR(cur) && + while (IS_CHAR(cur) && /* checked */ ((cur != '?') || (NXT(1) != '>'))) { if (len + 5 >= size) { size *= 2; @@ -5110,6 +5138,11 @@ xmlParsePI(xmlParserCtxtPtr ctxt) { return; } } + count++; + if (count > 50) { + GROW; + count = 0; + } COPY_BUF(l,buf,len,cur); NEXTL(l); cur = CUR_CHAR(l); diff --git a/result/HTML/Down.html.sax b/result/HTML/Down.html.sax index defeff15..a8c32c9b 100644 --- a/result/HTML/Down.html.sax +++ b/result/HTML/Down.html.sax @@ -1,11 +1,8 @@ SAX.setDocumentLocator() SAX.startDocument() SAX.startElement(html) -SAX.startElement(body) -SAX.startElement(p) -SAX.characters( +SAX.ignorableWhitespace( , 1) -SAX.endElement(p) SAX.startElement(head) SAX.ignorableWhitespace( , 3) @@ -22,11 +19,11 @@ SAX.startElement(body, bgcolor='#FFFFFF') SAX.ignorableWhitespace( , 1) SAX.startElement(h1, align='center') -SAX.characters(Sorry, this service is tempora, 30) +SAX.characters(Sorry, this service is tempora, 37) SAX.endElement(h1) SAX.startElement(p) SAX.characters( -We are doing our best to get , 30) +We are doing our best to get , 48) SAX.endElement(p) SAX.startElement(p) SAX.characters(The W3C system administrators, 29) @@ -36,7 +33,6 @@ SAX.ignorableWhitespace( SAX.endElement(body) SAX.ignorableWhitespace( , 1) -SAX.endElement(body) SAX.endElement(html) SAX.ignorableWhitespace( , 1) diff --git a/result/HTML/doc2.htm.sax b/result/HTML/doc2.htm.sax index edd2b2a6..1a23b28e 100644 --- a/result/HTML/doc2.htm.sax +++ b/result/HTML/doc2.htm.sax @@ -12,7 +12,7 @@ SAX.ignorableWhitespace( , 1) SAX.startElement(script, language='javascript') SAX.characters( - NS_ActualOpen=windo, 30) + NS_ActualOpen=windo, 194) SAX.endElement(script) SAX.ignorableWhitespace( , 1) @@ -55,7 +55,7 @@ SAX.startElement(body, bgcolor='#FFFFFF', text='#000000', link='#000080', vlink= SAX.ignorableWhitespace( , 3) SAX.startElement(p) -SAX.characters(This page uses frames, but you, 30) +SAX.characters(This page uses frames, but you, 61) SAX.endElement(p) SAX.ignorableWhitespace( , 3) diff --git a/result/HTML/doc3.htm.sax b/result/HTML/doc3.htm.sax index c810f35c..0f26df0c 100644 --- a/result/HTML/doc3.htm.sax +++ b/result/HTML/doc3.htm.sax @@ -6,13 +6,13 @@ SAX.comment( BEGIN Naviscope Javascript ) SAX.startElement(html) SAX.startElement(head) SAX.startElement(title) -SAX.characters(BP6.com #1 online resource for, 30) +SAX.characters(BP6.com #1 online resource for, 47) SAX.endElement(title) SAX.ignorableWhitespace( , 2) SAX.startElement(script, language='javascript') SAX.characters( - NS_ActualOpen=wind, 30) + NS_ActualOpen=wind, 199) SAX.endElement(script) SAX.ignorableWhitespace( , 2) @@ -32,7 +32,7 @@ SAX.ignorableWhitespace( , 2) SAX.startElement(style, type='text/css') SAX.characters(A.nav { - COLOR: #003399; TEXT, 30) + COLOR: #003399; TEXT, 115) SAX.endElement(style) SAX.ignorableWhitespace( @@ -70,11 +70,8 @@ SAX.ignorableWhitespace( SAX.startElement(meta, content='MSHTML 5.00.3103.1000', name='GENERATOR') SAX.endElement(meta) SAX.endElement(head) -SAX.startElement(body) -SAX.startElement(p) -SAX.characters( +SAX.ignorableWhitespace( , 2) -SAX.endElement(p) SAX.startElement(body, aLink='red', bgColor='black', link='red', text='white', vLink='red') SAX.ignorableWhitespace( , 2) @@ -793,7 +790,7 @@ SAX.endElement(br) SAX.startElement(font, face='arial', size='1') SAX.startElement(a, class='nav', href='http://bp6.gamesquad.net/index.phtml#newsitem965012956,78924,') SAX.characters(Chat - with ABIT -, 30) + with ABIT -, 41) SAX.endElement(a) SAX.endElement(font) SAX.startElement(br) @@ -801,7 +798,7 @@ SAX.endElement(br) SAX.startElement(font, face='arial', size='1') SAX.startElement(a, class='nav', href='http://bp6.gamesquad.net/index.phtml#newsitem964766837,26344,') SAX.characters(Fixed - wallpaper , 30) + wallpaper , 43) SAX.endElement(a) SAX.endElement(font) SAX.startElement(br) @@ -809,7 +806,7 @@ SAX.endElement(br) SAX.startElement(font, face='arial', size='1') SAX.startElement(a, class='nav', href='http://bp6.gamesquad.net/index.phtml#newsitem964762841,25865,') SAX.characters(Seti - update - 10, 30) + update - 10, 39) SAX.endElement(a) SAX.endElement(font) SAX.startElement(br) @@ -817,7 +814,7 @@ SAX.endElement(br) SAX.startElement(font, face='arial', size='1') SAX.startElement(a, class='nav', href='http://bp6.gamesquad.net/index.phtml#newsitem964732235,45502,') SAX.characters(Judge - gives Naps, 30) + gives Naps, 57) SAX.endElement(a) SAX.endElement(font) SAX.startElement(br) @@ -825,7 +822,7 @@ SAX.endElement(br) SAX.startElement(font, face='arial', size='1') SAX.startElement(a, class='nav', href='http://bp6.gamesquad.net/index.phtml#newsitem964713289,83675,') SAX.characters(Ram - Sinks.. more, 30) + Sinks.. more, 83) SAX.endElement(a) SAX.endElement(font) SAX.startElement(br) @@ -833,7 +830,7 @@ SAX.endElement(br) SAX.startElement(font, face='arial', size='1') SAX.startElement(a, class='nav', href='http://bp6.gamesquad.net/index.phtml#newsitem964671589,7831,') SAX.characters(is - it [H]ard? - , 30) + it [H]ard? - , 40) SAX.endElement(a) SAX.endElement(font) SAX.startElement(br) @@ -841,7 +838,7 @@ SAX.endElement(br) SAX.startElement(font, face='arial', size='1') SAX.startElement(a, class='nav', href='http://bp6.gamesquad.net/index.phtml#newsitem964644047,60218,') SAX.characters(WiLd - CaSe!! - 1:, 30) + CaSe!! - 1:, 38) SAX.endElement(a) SAX.endElement(font) SAX.startElement(br) @@ -849,7 +846,7 @@ SAX.endElement(br) SAX.startElement(font, face='arial', size='1') SAX.startElement(a, class='nav', href='http://bp6.gamesquad.net/index.phtml#newsitem964631110,84122,') SAX.characters(What - the heck is, 30) + the heck is, 58) SAX.endElement(a) SAX.endElement(font) SAX.startElement(br) @@ -857,7 +854,7 @@ SAX.endElement(br) SAX.startElement(font, face='arial', size='1') SAX.startElement(a, class='nav', href='http://bp6.gamesquad.net/index.phtml#newsitem964587833,74573,') SAX.characters(HELLO - EVERYONE!!, 30) + EVERYONE!!, 45) SAX.endElement(a) SAX.endElement(font) SAX.startElement(br) @@ -865,7 +862,7 @@ SAX.endElement(br) SAX.startElement(font, face='arial', size='1') SAX.startElement(a, class='nav', href='http://bp6.gamesquad.net/index.phtml#newsitem964429577,13375,') SAX.characters(BP6 - Q3 server up, 30) + Q3 server up, 57) SAX.endElement(a) SAX.endElement(font) SAX.startElement(br) @@ -890,7 +887,7 @@ SAX.startElement(td) SAX.startElement(font, color='#ffffff', face='Verdana,arial', size='2') SAX.startElement(b) SAX.characters(Sunday, - Ju, 30) + Ju, 41) SAX.endElement(b) SAX.endElement(font) SAX.endElement(td) @@ -941,20 +938,20 @@ SAX.endElement(br) SAX.startElement(font, color='black', face='Arial', size='2') SAX.characters(I, 1) SAX.characters(’, 3) -SAX.characters(m slacking a little. All game , 30) +SAX.characters(m slacking a little. All game , 83) SAX.startElement(br) SAX.endElement(br) SAX.startElement(br) SAX.endElement(br) SAX.characters(Wallpaper update: I got - , 30) + , 130) SAX.startElement(br) SAX.endElement(br) SAX.startElement(br) SAX.endElement(br) SAX.startElement(b) SAX.startElement(a, href='http://fullon3d.com/chat/abit/', target='3d') -SAX.characters(Fullon3d had a live chat with , 30) +SAX.characters(Fullon3d had a live chat with , 69) SAX.endElement(a) SAX.endElement(b) SAX.characters(Submitted by: MJS, 17) @@ -971,14 +968,14 @@ SAX.characters([Falcon] BP6-2??, 30) SAX.startElement(br) SAX.endElement(br) -SAX.characters([EricBoeing] We already have a, 30) +SAX.characters([EricBoeing] We already have a, 75) SAX.startElement(br) SAX.endElement(br) SAX.characters([EricBoeing] but it's OEM only, 30) SAX.startElement(br) SAX.endElement(br) SAX.characters([EricBoeing] the full ATX - , 30) + , 74) SAX.startElement(br) SAX.endElement(br) SAX.endElement(font) @@ -1003,7 +1000,7 @@ SAX.startElement(td) SAX.startElement(font, color='#ffffff', face='Verdana,arial', size='2') SAX.startElement(b) SAX.characters(Thursday, - , 30) + , 43) SAX.endElement(b) SAX.endElement(font) SAX.endElement(td) @@ -1058,39 +1055,39 @@ SAX.endElement(b) SAX.startElement(br) SAX.endElement(br) SAX.characters(This is a - fixed , 30) + fixed , 106) SAX.startElement(br) SAX.endElement(br) SAX.startElement(img, height='180', src='doc3_files/3-800.jpg', width='240') SAX.endElement(img) SAX.startElement(br) SAX.endElement(br) -SAX.characters(It's still the Intels Inside o, 30) +SAX.characters(It's still the Intels Inside o, 104) SAX.startElement(br) SAX.endElement(br) SAX.startElement(br) SAX.endElement(br) SAX.characters(Thanks to Matt for - , 30) + , 57) SAX.startElement(br) SAX.endElement(br) -SAX.characters(I would also like to thank Kev, 30) +SAX.characters(I would also like to thank Kev, 133) SAX.startElement(br) SAX.endElement(br) -SAX.characters(And 1 more person, THANK YOU T, 30) +SAX.characters(And 1 more person, THANK YOU T, 90) SAX.startElement(br) SAX.endElement(br) SAX.startElement(br) SAX.endElement(br) -SAX.characters(If you need a weird resolution, 30) +SAX.characters(If you need a weird resolution, 59) SAX.startElement(a, href='mailto:Holodeck2@home.com') SAX.characters(e-mail, 6) SAX.endElement(a) SAX.characters( me requesting - f, 30) + f, 37) SAX.startElement(br) SAX.endElement(br) -SAX.characters(If you have ideas or more erro, 30) +SAX.characters(If you have ideas or more erro, 47) SAX.startElement(a, href='mailto:Holodeck2@home.com') SAX.characters(mailto:Holodeck2@home.com, 25) SAX.endElement(a) @@ -1139,7 +1136,7 @@ SAX.endElement(a) SAX.startElement(br) SAX.endElement(br) SAX.characters([H]ard at - work o, 30) + work o, 65) SAX.startElement(br) SAX.endElement(br) SAX.endElement(p) @@ -1193,7 +1190,7 @@ SAX.endElement(img) SAX.startElement(br) SAX.endElement(br) SAX.characters(You like the - pic, 30) + pic, 31) SAX.startElement(br) SAX.endElement(br) SAX.startElement(br) @@ -1202,26 +1199,26 @@ SAX.characters(Bp6 User Group Update:, 22) SAX.startElement(br) SAX.endElement(br) SAX.characters(Completed 61531 - , 30) + , 37) SAX.startElement(br) SAX.endElement(br) SAX.startElement(b) SAX.characters(#168 on Top 200 All Groups, 26) SAX.endElement(b) SAX.characters( (Going to pass CLRC in - , 30) + , 49) SAX.startElement(br) SAX.endElement(br) SAX.startElement(b) SAX.characters(#74 on Top 200 Teams, 20) SAX.endElement(b) SAX.characters( (Gaining fast on - , 30) + , 42) SAX.startElement(br) SAX.endElement(br) SAX.startElement(br) SAX.endElement(br) -SAX.characters(We are flying though at the sp, 30) +SAX.characters(We are flying though at the sp, 82) SAX.startElement(br) SAX.endElement(br) SAX.characters(Good job everyone!!, 19) @@ -1230,7 +1227,7 @@ SAX.endElement(br) SAX.startElement(br) SAX.endElement(br) SAX.characters(Check this page at - , 30) + , 67) SAX.startElement(br) SAX.endElement(br) SAX.endElement(font) @@ -1244,7 +1241,7 @@ SAX.startElement(b) SAX.startElement(u) SAX.startElement(font, color='#003366', face='Verdana, Arial', size='2') SAX.characters(Judge gives Napster the - , 30) + , 44) SAX.endElement(font) SAX.endElement(u) SAX.endElement(b) @@ -1279,17 +1276,17 @@ SAX.characters( , 1) SAX.startElement(br) SAX.endElement(br) SAX.startElement(font, color='black', face='Arial', size='2') -SAX.characters(Good afternoon for everyone li, 30) +SAX.characters(Good afternoon for everyone li, 135) SAX.startElement(br) SAX.endElement(br) -SAX.characters(I woke up and thought about po, 30) +SAX.characters(I woke up and thought about po, 488) SAX.startElement(br) SAX.endElement(br) SAX.startElement(br) SAX.endElement(br) SAX.startElement(a, href='http://www.msnbc.com/news/437532.asp', target='Judge vs Napster') SAX.characters(Judge shuts Napster down - , 30) + , 38) SAX.startElement(p) SAX.startElement(img, height='143', src='doc3_files/669915.jpg', width='200') SAX.endElement(img) @@ -1297,11 +1294,11 @@ SAX.endElement(p) SAX.endElement(a) SAX.startElement(br) SAX.endElement(br) -SAX.characters(Check out the Goofy guy in the, 30) +SAX.characters(Check out the Goofy guy in the, 35) SAX.startElement(br) SAX.endElement(br) SAX.characters(He's Sean - Fannin, 30) + Fannin, 52) SAX.startElement(br) SAX.endElement(br) SAX.startElement(br) @@ -1322,7 +1319,7 @@ SAX.endElement(a) SAX.startElement(b) SAX.startElement(u) SAX.startElement(font, color='#003366', face='Verdana, Arial', size='2') -SAX.characters(Ram Sinks.. more cooling for s, 30) +SAX.characters(Ram Sinks.. more cooling for s, 56) SAX.endElement(font) SAX.endElement(u) SAX.endElement(b) @@ -1356,12 +1353,12 @@ SAX.characters( , 1) SAX.startElement(br) SAX.endElement(br) SAX.startElement(font, color='black', face='Arial', size='2') -SAX.characters(Need some cooling for your Vid, 30) +SAX.characters(Need some cooling for your Vid, 106) SAX.startElement(a, href='http://www.overclockershideout.com/RamSinks.html', target='_BLANK') SAX.characters(Overclockers Hiedout Ram Sinks, 30) SAX.endElement(a) SAX.characters( They just notified - , 30) + , 57) SAX.startElement(br) SAX.endElement(br) SAX.startElement(img, border='1', src='doc3_files/ramsink.jpg') @@ -1388,7 +1385,7 @@ SAX.startElement(td) SAX.startElement(font, color='#ffffff', face='Verdana,arial', size='2') SAX.startElement(b) SAX.characters(Wednesday, July 26, - , 30) + , 38) SAX.endElement(b) SAX.endElement(font) SAX.endElement(td) @@ -1437,10 +1434,10 @@ SAX.characters( , 1) SAX.startElement(br) SAX.endElement(br) SAX.startElement(font, color='black', face='Arial', size='2') -SAX.characters(Big heatsinks are good, very g, 30) +SAX.characters(Big heatsinks are good, very g, 71) SAX.startElement(br) SAX.endElement(br) -SAX.characters(You can never can have a too b, 30) +SAX.characters(You can never can have a too b, 99) SAX.startElement(br) SAX.endElement(br) SAX.startElement(br) @@ -1450,14 +1447,14 @@ SAX.endElement(img) SAX.startElement(br) SAX.endElement(br) SAX.characters(My overclocked - V, 30) + V, 74) SAX.startElement(br) SAX.endElement(br) SAX.characters(Peltier and - wate, 30) + wate, 50) SAX.startElement(br) SAX.endElement(br) -SAX.characters((if you pry off the heatsink y, 30) +SAX.characters((if you pry off the heatsink y, 66) SAX.startElement(br) SAX.endElement(br) SAX.startElement(br) @@ -1471,7 +1468,7 @@ SAX.endElement(br) SAX.characters(I, 1) SAX.characters(’, 3) SAX.characters(m not only a - BP6, 30) + BP6, 55) SAX.startElement(br) SAX.endElement(br) SAX.endElement(font) @@ -1519,7 +1516,7 @@ SAX.characters( , 1) SAX.startElement(br) SAX.endElement(br) SAX.startElement(font, color='black', face='Arial', size='2') -SAX.characters(Now this person really knows h, 30) +SAX.characters(Now this person really knows h, 70) SAX.startElement(br) SAX.endElement(br) SAX.characters(Addin an 18" Fan!! WOW!!, 24) @@ -1534,7 +1531,7 @@ SAX.endElement(a) SAX.startElement(br) SAX.endElement(br) SAX.characters(Click to go to his - , 30) + , 38) SAX.startElement(br) SAX.endElement(br) SAX.endElement(font) @@ -1548,7 +1545,7 @@ SAX.startElement(b) SAX.startElement(u) SAX.startElement(font, color='#003366', face='Verdana, Arial', size='2') SAX.characters(What the heck is a - , 30) + , 44) SAX.endElement(font) SAX.endElement(u) SAX.endElement(b) @@ -1583,13 +1580,13 @@ SAX.characters( , 1) SAX.startElement(br) SAX.endElement(br) SAX.startElement(font, color='black', face='Arial', size='2') -SAX.characters(This is for all you people who, 30) +SAX.characters(This is for all you people who, 78) SAX.startElement(br) SAX.endElement(br) SAX.startElement(br) SAX.endElement(br) SAX.characters(The quest fo the Perfect - , 30) + , 46) SAX.startElement(br) SAX.endElement(br) SAX.startElement(a, href='http://www.tweakmax.com/html/peltier/peltier-1.cfm', target='_blank') @@ -1610,13 +1607,13 @@ SAX.startElement(br) SAX.endElement(br) SAX.startElement(br) SAX.endElement(br) -SAX.characters(Note: Today morning when I wok, 30) +SAX.characters(Note: Today morning when I wok, 397) SAX.startElement(img, src='doc3_files/smile.gif') SAX.endElement(img) SAX.startElement(br) SAX.endElement(br) SAX.characters(I'm not angry at anyone... - , 30) + , 71) SAX.startElement(img, src='doc3_files/tongue.gif') SAX.endElement(img) SAX.startElement(br) @@ -1643,7 +1640,7 @@ SAX.startElement(td) SAX.startElement(font, color='#ffffff', face='Verdana,arial', size='2') SAX.startElement(b) SAX.characters(Tuesday, - J, 30) + J, 42) SAX.endElement(b) SAX.endElement(font) SAX.endElement(td) @@ -1657,7 +1654,7 @@ SAX.startElement(b) SAX.startElement(u) SAX.startElement(font, color='#003366', face='Verdana, Arial', size='2') SAX.characters(HELLO - EVERYONE!!, 30) + EVERYONE!!, 31) SAX.endElement(font) SAX.endElement(u) SAX.endElement(b) @@ -1678,37 +1675,37 @@ SAX.startElement(br) SAX.endElement(br) SAX.startElement(font, color='black', face='Arial', size='2') SAX.characters(Hello - everyone, , 30) + everyone, , 47) SAX.startElement(br) SAX.endElement(br) -SAX.characters(Who is this Holodeck2 person , 30) +SAX.characters(Who is this Holodeck2 person , 66) SAX.startElement(br) SAX.endElement(br) SAX.characters(I, 1) SAX.characters(’, 3) -SAX.characters(m a regular on the bp6 message, 30) +SAX.characters(m a regular on the bp6 message, 97) SAX.startElement(br) SAX.endElement(br) SAX.characters(I, 1) SAX.characters(’, 3) SAX.characters(m the - self-procl, 30) + self-procl, 85) SAX.characters(’, 3) SAX.characters(ve - probably alre, 30) + probably alre, 68) SAX.startElement(br) SAX.endElement(br) SAX.characters(My computer - is a, 30) + is a, 200) SAX.startElement(br) SAX.endElement(br) -SAX.characters(Any Questions or comments, you, 30) +SAX.characters(Any Questions or comments, you, 98) SAX.startElement(br) SAX.endElement(br) SAX.startElement(br) SAX.endElement(br) SAX.characters(Ways to contact - , 30) + , 33) SAX.startElement(br) SAX.endElement(br) SAX.characters(E-mail: , 8) @@ -1716,27 +1713,27 @@ SAX.startElement(a, href='mailto:Holodeck2@home.com') SAX.characters(Holodeck2@home.com, 18) SAX.endElement(a) SAX.characters( (All E-mails - wi, 30) + wi, 82) SAX.startElement(br) SAX.endElement(br) SAX.characters(When you - write m, 30) + write m, 163) SAX.startElement(br) SAX.endElement(br) SAX.startElement(a, href='http://www.aol.com/aim') SAX.characters(AIM: , 5) SAX.endElement(a) SAX.characters(Holodeck2 (instant response -, 30) +, 46) SAX.characters(’, 3) -SAX.characters(m in front of my comp and not , 30) +SAX.characters(m in front of my comp and not , 53) SAX.startElement(br) SAX.endElement(br) SAX.startElement(a, href='http://www.icq.com/download') SAX.characters(ICQ: , 5) SAX.endElement(a) SAX.characters(82640218 (rarely - , 30) + , 34) SAX.startElement(br) SAX.endElement(br) SAX.startElement(br) @@ -1746,7 +1743,7 @@ SAX.characters(“, 3) SAX.characters(Digital Vortex, 14) SAX.characters(”, 3) SAX.characters( on either Quake 3 - , 30) + , 51) SAX.characters(’, 3) SAX.characters(s probably me. ;-), 18) SAX.startElement(br) @@ -1773,7 +1770,7 @@ SAX.startElement(td) SAX.startElement(font, color='#ffffff', face='Verdana,arial', size='2') SAX.startElement(b) SAX.characters(Monday, - Ju, 30) + Ju, 41) SAX.endElement(b) SAX.endElement(font) SAX.endElement(td) @@ -1787,7 +1784,7 @@ SAX.startElement(b) SAX.startElement(u) SAX.startElement(font, color='#003366', face='Verdana, Arial', size='2') SAX.characters(BP6 Q3 server up and - , 30) + , 44) SAX.endElement(font) SAX.endElement(u) SAX.endElement(b) @@ -1821,11 +1818,11 @@ SAX.characters( , 1) SAX.startElement(br) SAX.endElement(br) SAX.startElement(font, color='black', face='Arial', size='2') -SAX.characters(Setup a Q3 server for anyone w, 30) +SAX.characters(Setup a Q3 server for anyone w, 355) SAX.startElement(br) SAX.endElement(br) SAX.characters((BTW- - there are , 30) + there are , 68) SAX.endElement(font) SAX.startElement(br) SAX.endElement(br) @@ -1837,7 +1834,7 @@ SAX.startElement(b) SAX.startElement(u) SAX.startElement(font, color='#003366', face='Verdana, Arial', size='2') SAX.characters(BIOS Savior to the - , 30) + , 43) SAX.endElement(font) SAX.endElement(u) SAX.endElement(b) @@ -1871,12 +1868,12 @@ SAX.characters( , 1) SAX.startElement(br) SAX.endElement(br) SAX.startElement(font, color='black', face='Arial', size='2') -SAX.characters(Do you sweat during the BIOS f, 30) +SAX.characters(Do you sweat during the BIOS f, 167) SAX.startElement(b) SAX.characters(RD1 BIOS Savior, 15) SAX.endElement(b) SAX.characters(" and it - plugs i, 30) + plugs i, 520) SAX.startElement(br) SAX.endElement(br) SAX.startElement(a, href='http://www.ioss.com.tw/eg/rd1/RD1info0004.PDF', target='_NEW') @@ -1921,7 +1918,7 @@ SAX.startElement(td) SAX.startElement(font, color='#ffffff', face='Verdana,arial', size='2') SAX.startElement(b) SAX.characters(Monday, - Ju, 30) + Ju, 41) SAX.endElement(b) SAX.endElement(font) SAX.endElement(td) @@ -1970,7 +1967,7 @@ SAX.characters( , 1) SAX.startElement(br) SAX.endElement(br) SAX.startElement(font, color='black', face='Arial', size='2') -SAX.characters(For those of you who are new t, 30) +SAX.characters(For those of you who are new t, 209) SAX.startElement(br) SAX.endElement(br) SAX.startElement(br) @@ -1990,7 +1987,7 @@ SAX.startElement(b) SAX.startElement(u) SAX.startElement(font, color='#003366', face='Verdana, Arial', size='2') SAX.characters(The Cardcooler - X, 30) + X, 31) SAX.endElement(font) SAX.endElement(u) SAX.endElement(b) @@ -2025,14 +2022,14 @@ SAX.characters( , 1) SAX.startElement(br) SAX.endElement(br) SAX.startElement(font, color='black', face='Arial', size='2') -SAX.characters(Wow! I am impressed! Nevermind, 30) +SAX.characters(Wow! I am impressed! Nevermind, 98) SAX.startElement(br) SAX.endElement(br) SAX.startElement(br) SAX.endElement(br) SAX.startElement(i) SAX.characters(Even if your - not, 30) + not, 345) SAX.endElement(i) SAX.startElement(br) SAX.endElement(br) @@ -2044,7 +2041,7 @@ SAX.endElement(br) SAX.startElement(br) SAX.endElement(br) SAX.startElement(a, href='http://www.brokenpixel.com/articles/coolerXT/cardcoolerXT_1.shtml', target='_blank') -SAX.characters(http://www.brokenpixel.com/art, 30) +SAX.characters(http://www.brokenpixel.com/art, 65) SAX.endElement(a) SAX.characters( , 15) @@ -2094,7 +2091,7 @@ SAX.characters( , 1) SAX.startElement(br) SAX.endElement(br) SAX.startElement(font, color='black', face='Arial', size='2') -SAX.characters(We all need to have some fun , 30) +SAX.characters(We all need to have some fun , 181) SAX.startElement(br) SAX.endElement(br) SAX.startElement(br) @@ -2117,7 +2114,7 @@ SAX.endElement(a) SAX.startElement(b) SAX.startElement(u) SAX.startElement(font, color='#003366', face='Verdana, Arial', size='2') -SAX.characters(Dual PSU Wiring diagram... (pr, 30) +SAX.characters(Dual PSU Wiring diagram... (pr, 81) SAX.endElement(font) SAX.endElement(u) SAX.endElement(b) @@ -2151,7 +2148,7 @@ SAX.characters( , 1) SAX.startElement(br) SAX.endElement(br) SAX.startElement(font, color='black', face='Arial', size='2') -SAX.characters(When is comes to overclocking , 30) +SAX.characters(When is comes to overclocking , 848) SAX.startElement(br) SAX.endElement(br) SAX.startElement(br) @@ -2172,7 +2169,7 @@ SAX.startElement(br) SAX.endElement(br) SAX.startElement(br) SAX.endElement(br) -SAX.characters(I used Tap-In Squeeze Connecto, 30) +SAX.characters(I used Tap-In Squeeze Connecto, 150) SAX.startElement(a, href='http://www.radioshack.com/ProductCatalog/ProductDetail/Index/1,2098,,00.html?SKUString1=64&SKUString2=3053', target='_blank') SAX.characters(click here, 10) SAX.endElement(a) @@ -2199,7 +2196,7 @@ SAX.startElement(td) SAX.startElement(font, color='#ffffff', face='Verdana,arial', size='2') SAX.startElement(b) SAX.characters(Sunday, - Ju, 30) + Ju, 41) SAX.endElement(b) SAX.endElement(font) SAX.endElement(td) @@ -2213,7 +2210,7 @@ SAX.startElement(b) SAX.startElement(u) SAX.startElement(font, color='#003366', face='Verdana, Arial', size='2') SAX.characters(RAM Overclocking? - , 30) + , 39) SAX.endElement(font) SAX.endElement(u) SAX.endElement(b) @@ -2248,18 +2245,18 @@ SAX.characters( , 1) SAX.startElement(br) SAX.endElement(br) SAX.startElement(font, color='black', face='Arial', size='2') -SAX.characters(I know we're pretty big overcl, 30) +SAX.characters(I know we're pretty big overcl, 636) SAX.startElement(br) SAX.endElement(br) SAX.startElement(br) SAX.endElement(br) -SAX.characters(Extreme Overclocking has teste, 30) +SAX.characters(Extreme Overclocking has teste, 145) SAX.startElement(br) SAX.endElement(br) SAX.startElement(br) SAX.endElement(br) SAX.startElement(i) -SAX.characters(Well, the guys at Extreme Over, 30) +SAX.characters(Well, the guys at Extreme Over, 344) SAX.endElement(i) SAX.startElement(br) SAX.endElement(br) @@ -2320,7 +2317,7 @@ SAX.characters( , 1) SAX.startElement(br) SAX.endElement(br) SAX.startElement(font, color='black', face='Arial', size='2') -SAX.characters(A follow up on the 'Weekly CPU, 30) +SAX.characters(A follow up on the 'Weekly CPU, 203) SAX.startElement(br) SAX.endElement(br) SAX.startElement(br) @@ -2329,7 +2326,7 @@ SAX.characters( , 14) SAX.startElement(li) SAX.startElement(a, href='http://www6.tomshardware.com/howto/00q2/000412/index.html', target='_blank') -SAX.characters(http://www6.tomshardware.com/h, 30) +SAX.characters(http://www6.tomshardware.com/h, 57) SAX.endElement(a) SAX.endElement(li) SAX.endElement(font) @@ -2354,7 +2351,7 @@ SAX.startElement(td) SAX.startElement(font, color='#ffffff', face='Verdana,arial', size='2') SAX.startElement(b) SAX.characters(Saturday, - , 30) + , 43) SAX.endElement(b) SAX.endElement(font) SAX.endElement(td) @@ -2368,7 +2365,7 @@ SAX.startElement(b) SAX.startElement(u) SAX.startElement(font, color='#003366', face='Verdana, Arial', size='2') SAX.characters(Weekly CPU - Price, 30) + Price, 31) SAX.endElement(font) SAX.endElement(u) SAX.endElement(b) @@ -2403,7 +2400,7 @@ SAX.characters( , 1) SAX.startElement(br) SAX.endElement(br) SAX.startElement(font, color='black', face='Arial', size='2') -SAX.characters(Wow, found this very useful! W, 30) +SAX.characters(Wow, found this very useful! W, 104) SAX.startElement(br) SAX.endElement(br) SAX.startElement(br) @@ -2417,7 +2414,7 @@ SAX.endElement(br) SAX.startElement(br) SAX.endElement(br) SAX.characters(Thanks Sharky - Ex, 30) + Ex, 36) SAX.endElement(font) SAX.startElement(br) SAX.endElement(br) @@ -2463,26 +2460,26 @@ SAX.characters( , 1) SAX.startElement(br) SAX.endElement(br) SAX.startElement(font, color='black', face='Arial', size='2') -SAX.characters(FAST-MHz has released some wal, 30) +SAX.characters(FAST-MHz has released some wal, 53) SAX.startElement(a, href='http://64.29.18.111/wallpaper/index.html', target='_blank') SAX.characters(Click here, 10) SAX.endElement(a) -SAX.characters( to view them. They come in si, 30) +SAX.characters( to view them. They come in si, 241) SAX.startElement(br) SAX.endElement(br) SAX.startElement(br) SAX.endElement(br) SAX.characters(In other news, we want to - , 30) + , 135) SAX.startElement(a, href='http://bp6.gamesquad.net/uc.phtml', target='_blank') SAX.characters(Picture Gallery, 15) SAX.endElement(a) -SAX.characters(. To help us out, you can send, 30) +SAX.characters(. To help us out, you can send, 103) SAX.startElement(a, href='mailto:thedaredevil@bp6.com') SAX.characters(thedaredevil@bp6.com, 20) SAX.endElement(a) SAX.characters(. (The - topic bei, 30) + topic bei, 186) SAX.startElement(br) SAX.endElement(br) SAX.startElement(br) @@ -2516,7 +2513,7 @@ SAX.startElement(td) SAX.startElement(font, color='#ffffff', face='Verdana,arial', size='2') SAX.startElement(b) SAX.characters(Friday, - Ju, 30) + Ju, 41) SAX.endElement(b) SAX.endElement(font) SAX.endElement(td) @@ -2565,7 +2562,7 @@ SAX.characters( , 1) SAX.startElement(br) SAX.endElement(br) SAX.startElement(font, color='black', face='Arial', size='2') -SAX.characters(Hey guys, just wanted to intro, 30) +SAX.characters(Hey guys, just wanted to intro, 312) SAX.startElement(br) SAX.endElement(br) SAX.startElement(br) @@ -2898,7 +2895,7 @@ SAX.characters( SAX.startElement(p, align='center') SAX.startElement(font, color='#999999', face='verdana,arial', size='1') SAX.characters(Copyright - ©1999-2, 26) + ©1999-2, 59) SAX.startElement(br) SAX.endElement(br) SAX.characters(Got news? Send it to , 21) @@ -2924,7 +2921,6 @@ SAX.endElement(script) SAX.ignorableWhitespace( , 2) SAX.endElement(body) -SAX.endElement(body) SAX.endElement(html) SAX.ignorableWhitespace( , 2) diff --git a/result/HTML/fp40.htm.sax b/result/HTML/fp40.htm.sax index 03142761..3859458d 100644 --- a/result/HTML/fp40.htm.sax +++ b/result/HTML/fp40.htm.sax @@ -2,12 +2,9 @@ SAX.setDocumentLocator() SAX.startDocument() SAX.internalSubset(html, -//IETF//DTD HTML//EN, ) SAX.startElement(html) -SAX.startElement(body) -SAX.startElement(p) -SAX.characters( +SAX.ignorableWhitespace( , 2) -SAX.endElement(p) SAX.startElement(head) SAX.ignorableWhitespace( , 1) @@ -16,7 +13,7 @@ SAX.endElement(meta) SAX.ignorableWhitespace( , 1) SAX.startElement(title) -SAX.characters(README - Microsoft FrontPage 2, 30) +SAX.characters(README - Microsoft FrontPage 2, 51) SAX.endElement(title) SAX.ignorableWhitespace( , 1) @@ -36,7 +33,7 @@ SAX.characters( , 1) SAX.startElement(h1) SAX.startElement(a, name='top') -SAX.characters(Microsoft FrontPage 2000 Serve, 30) +SAX.characters(Microsoft FrontPage 2000 Serve, 48) SAX.endElement(a) SAX.endElement(h1) SAX.characters( @@ -44,7 +41,7 @@ SAX.characters( , 2) SAX.startElement(font, size='2') SAX.startElement(i) -SAX.characters(© Copyright Microsoft Cor, 26) +SAX.characters(© Copyright Microsoft Cor, 40) SAX.characters( , 2) SAX.endElement(i) SAX.endElement(font) @@ -53,7 +50,7 @@ SAX.characters( , 3) SAX.startElement(p) -SAX.characters(The FrontPage Server Extension, 30) +SAX.characters(The FrontPage Server Extension, 88) SAX.endElement(p) SAX.startElement(ul) SAX.characters( @@ -69,7 +66,7 @@ SAX.endElement(li) SAX.characters( , 3) SAX.startElement(li) -SAX.characters(Browse-time FrontPage web func, 30) +SAX.characters(Browse-time FrontPage web func, 39) SAX.endElement(li) SAX.characters( , 1) @@ -115,7 +112,7 @@ SAX.characters( , 2) SAX.startElement(p) -SAX.characters(This section provides compleme, 30) +SAX.characters(This section provides compleme, 136) SAX.endElement(p) SAX.characters( @@ -129,14 +126,14 @@ SAX.endElement(br) SAX.characters( , 1) SAX.startElement(a, href='#upgrading') -SAX.characters(Upgrading from previous versio, 30) +SAX.characters(Upgrading from previous versio, 62) SAX.endElement(a) SAX.startElement(br) SAX.endElement(br) SAX.characters( , 1) SAX.startElement(a, href='#executables') -SAX.characters(Uploading files into executabl, 30) +SAX.characters(Uploading files into executabl, 39) SAX.endElement(a) SAX.endElement(p) SAX.characters( @@ -163,7 +160,7 @@ SAX.characters( , 2) SAX.startElement(p) -SAX.characters(You need to take some special , 30) +SAX.characters(You need to take some special , 360) SAX.endElement(p) SAX.characters( @@ -195,13 +192,13 @@ SAX.characters( , 3) SAX.startElement(p) -SAX.characters(If you have some settings stor, 30) +SAX.characters(If you have some settings stor, 90) SAX.endElement(p) SAX.characters( , 2) SAX.startElement(p) -SAX.characters(You must stop and restart the , 30) +SAX.characters(You must stop and restart the , 86) SAX.endElement(p) SAX.characters( @@ -222,26 +219,26 @@ SAX.characters( , 4) SAX.startElement(h3) SAX.startElement(a, name='upgrading') -SAX.characters(Upgrading from previous versio, 30) +SAX.characters(Upgrading from previous versio, 62) SAX.endElement(a) SAX.endElement(h3) SAX.characters( , 2) SAX.startElement(p) -SAX.characters(Custom entries in frontpage.cn, 30) +SAX.characters(Custom entries in frontpage.cn, 67) SAX.endElement(p) SAX.characters( , 2) SAX.startElement(p) -SAX.characters(When you install FrontPage 200, 30) +SAX.characters(When you install FrontPage 200, 359) SAX.endElement(p) SAX.characters( , 2) SAX.startElement(p) -SAX.characters(Do not overwrite the FrontPage, 30) +SAX.characters(Do not overwrite the FrontPage, 141) SAX.endElement(p) SAX.characters( @@ -262,7 +259,7 @@ SAX.characters( , 4) SAX.startElement(h3) SAX.startElement(a, name='executables') -SAX.characters(Uploading files into executabl, 30) +SAX.characters(Uploading files into executabl, 39) SAX.endElement(a) SAX.endElement(h3) SAX.characters( @@ -270,15 +267,15 @@ SAX.characters( , 3) SAX.startElement(p) -SAX.characters(After upgrading to FrontPage 2, 30) +SAX.characters(After upgrading to FrontPage 2, 385) SAX.endElement(p) SAX.characters( , 3) SAX.startElement(p) -SAX.characters(To allow FrontPage authors to , 30) +SAX.characters(To allow FrontPage authors to , 249) SAX.startElement(a, href='http://officeupdate.microsoft.com/frontpage/wpp/serk/') -SAX.characters(http://officeupdate.microsoft., 30) +SAX.characters(http://officeupdate.microsoft., 53) SAX.endElement(a) SAX.characters(., 1) SAX.endElement(p) @@ -315,7 +312,7 @@ SAX.characters( , 2) SAX.startElement(p) -SAX.characters(This section lists sources of , 30) +SAX.characters(This section lists sources of , 85) SAX.endElement(p) SAX.characters( @@ -329,7 +326,7 @@ SAX.endElement(br) SAX.characters( , 1) SAX.startElement(a, href='#serkupdate') -SAX.characters(Server Extensions Resource Kit, 30) +SAX.characters(Server Extensions Resource Kit, 37) SAX.endElement(a) SAX.startElement(br) SAX.endElement(br) @@ -363,13 +360,13 @@ SAX.characters( , 2) SAX.startElement(p) -SAX.characters(The FrontPage 2000 Server Exte, 30) +SAX.characters(The FrontPage 2000 Server Exte, 339) SAX.endElement(p) SAX.characters( , 2) SAX.startElement(p) -SAX.characters(The Server Extensions Resource, 30) +SAX.characters(The Server Extensions Resource, 312) SAX.endElement(p) SAX.characters( @@ -387,16 +384,16 @@ SAX.characters( , 3) SAX.startElement(h3) SAX.startElement(a, name='serkupdate') -SAX.characters(Server Extensions Resource Kit, 30) +SAX.characters(Server Extensions Resource Kit, 37) SAX.endElement(a) SAX.endElement(h3) SAX.characters( , 2) SAX.startElement(p) -SAX.characters(For updated information about , 30) +SAX.characters(For updated information about , 157) SAX.startElement(a, href='http://officeupdate.microsoft.com/frontpage/wpp/serk/') -SAX.characters(http://officeupdate.microsoft., 30) +SAX.characters(http://officeupdate.microsoft., 53) SAX.endElement(a) SAX.characters(., 1) SAX.endElement(p) @@ -424,13 +421,13 @@ SAX.characters( , 2) SAX.startElement(p) -SAX.characters(For further technical informat, 30) +SAX.characters(For further technical informat, 254) SAX.error: htmlParseEntityRef: no name SAX.characters(&, 1) SAX.characters( troubleshooters to find -fast, 30) +fast, 302) SAX.startElement(a, href='http://support.microsoft.com/support/') -SAX.characters(http://support.microsoft.com/s, 30) +SAX.characters(http://support.microsoft.com/s, 37) SAX.endElement(a) SAX.characters(., 1) SAX.endElement(p) @@ -460,7 +457,6 @@ SAX.ignorableWhitespace( SAX.endElement(body) SAX.ignorableWhitespace( , 1) -SAX.endElement(body) SAX.endElement(html) SAX.ignorableWhitespace( , 1) diff --git a/result/HTML/liclose.html.sax b/result/HTML/liclose.html.sax index 5e37aa81..30f26c0f 100644 --- a/result/HTML/liclose.html.sax +++ b/result/HTML/liclose.html.sax @@ -2,11 +2,8 @@ SAX.setDocumentLocator() SAX.startDocument() SAX.internalSubset(HTML, -//W3C//DTD HTML 4.0 Transitional//EN, http://www.w3.org/TR/REC-html40/loose.dtd) SAX.startElement(html) -SAX.startElement(body) -SAX.startElement(p) -SAX.characters( +SAX.ignorableWhitespace( , 1) -SAX.endElement(p) SAX.startElement(head) SAX.ignorableWhitespace( , 3) @@ -28,14 +25,13 @@ SAX.characters(First item , 11) SAX.endElement(li) SAX.startElement(li) -SAX.characters(Second item, closes the first , 30) +SAX.characters(Second item, closes the first , 34) SAX.endElement(li) SAX.endElement(ul) SAX.ignorableWhitespace( , 2) SAX.endElement(body) -SAX.endElement(body) SAX.endElement(html) SAX.ignorableWhitespace( , 1) diff --git a/result/HTML/reg1.html.sax b/result/HTML/reg1.html.sax index 516c0226..1ca02716 100644 --- a/result/HTML/reg1.html.sax +++ b/result/HTML/reg1.html.sax @@ -1,11 +1,8 @@ SAX.setDocumentLocator() SAX.startDocument() SAX.startElement(html) -SAX.startElement(body) -SAX.startElement(p) -SAX.characters( +SAX.ignorableWhitespace( , 1) -SAX.endElement(p) SAX.startElement(head) SAX.ignorableWhitespace( , 1) @@ -33,7 +30,6 @@ SAX.endElement(p) SAX.endElement(body) SAX.ignorableWhitespace( , 1) -SAX.endElement(body) SAX.endElement(html) SAX.ignorableWhitespace( , 1) diff --git a/result/HTML/reg2.html.sax b/result/HTML/reg2.html.sax index 79a0d275..63acfd42 100644 --- a/result/HTML/reg2.html.sax +++ b/result/HTML/reg2.html.sax @@ -1,11 +1,8 @@ SAX.setDocumentLocator() SAX.startDocument() SAX.startElement(html) -SAX.startElement(body) -SAX.startElement(p) -SAX.characters( +SAX.ignorableWhitespace( , 1) -SAX.endElement(p) SAX.startElement(head) SAX.ignorableWhitespace( , 1) @@ -38,7 +35,6 @@ SAX.endElement(p) SAX.endElement(body) SAX.ignorableWhitespace( , 1) -SAX.endElement(body) SAX.endElement(html) SAX.ignorableWhitespace( , 1) diff --git a/result/HTML/reg3.html.sax b/result/HTML/reg3.html.sax index 441a9e2d..5d498b25 100644 --- a/result/HTML/reg3.html.sax +++ b/result/HTML/reg3.html.sax @@ -1,11 +1,8 @@ SAX.setDocumentLocator() SAX.startDocument() SAX.startElement(html) -SAX.startElement(body) -SAX.startElement(p) -SAX.characters( +SAX.ignorableWhitespace( , 1) -SAX.endElement(p) SAX.startElement(head) SAX.ignorableWhitespace( , 1) @@ -42,7 +39,6 @@ SAX.endElement(p) SAX.endElement(body) SAX.ignorableWhitespace( , 1) -SAX.endElement(body) SAX.endElement(html) SAX.ignorableWhitespace( , 1) diff --git a/result/HTML/reg4.html.sax b/result/HTML/reg4.html.sax index d2d386b5..5a4eacfd 100644 --- a/result/HTML/reg4.html.sax +++ b/result/HTML/reg4.html.sax @@ -1,11 +1,8 @@ SAX.setDocumentLocator() SAX.startDocument() SAX.startElement(html) -SAX.startElement(body) -SAX.startElement(p) -SAX.characters( +SAX.ignorableWhitespace( , 1) -SAX.endElement(p) SAX.startElement(head) SAX.ignorableWhitespace( , 1) @@ -40,7 +37,6 @@ SAX.ignorableWhitespace( SAX.endElement(body) SAX.ignorableWhitespace( , 1) -SAX.endElement(body) SAX.endElement(html) SAX.ignorableWhitespace( , 1) diff --git a/result/HTML/test2.html.sax b/result/HTML/test2.html.sax index 351080a5..191b3236 100644 --- a/result/HTML/test2.html.sax +++ b/result/HTML/test2.html.sax @@ -8,11 +8,8 @@ SAX.startElement(title) SAX.characters(Linux Today, 11) SAX.endElement(title) SAX.endElement(head) -SAX.startElement(body) -SAX.startElement(p) -SAX.characters( +SAX.ignorableWhitespace( , 1) -SAX.endElement(p) SAX.startElement(body, bgcolor='White', link='Blue', text='Black', VLINK='Black', ALINK='Red') SAX.ignorableWhitespace( @@ -142,7 +139,6 @@ SAX.endElement(p) SAX.endElement(body) SAX.ignorableWhitespace( , 1) -SAX.endElement(body) SAX.endElement(html) SAX.ignorableWhitespace( , 1) diff --git a/result/HTML/test3.html.sax b/result/HTML/test3.html.sax index f88b7df8..1f76e50f 100644 --- a/result/HTML/test3.html.sax +++ b/result/HTML/test3.html.sax @@ -1,11 +1,8 @@ SAX.setDocumentLocator() SAX.startDocument() SAX.startElement(html) -SAX.startElement(body) -SAX.startElement(p) -SAX.characters( +SAX.ignorableWhitespace( , 2) -SAX.endElement(p) SAX.startElement(head) SAX.ignorableWhitespace( , 2) @@ -16,9 +13,10 @@ SAX.ignorableWhitespace( SAX.endElement(head) SAX.ignorableWhitespace( , 2) +SAX.startElement(body) SAX.startElement(a, name='ProblemDomain.Package') SAX.startElement(h2) -SAX.characters(Component Package diagram Prob, 30) +SAX.characters(Component Package diagram Prob, 39) SAX.endElement(h2) SAX.characters( , 2) @@ -55,9 +53,9 @@ SAX.characters(Note , 5) SAX.endElement(b) SAX.endElement(dt) SAX.startElement(dd) -SAX.characters(The Problem Domain package is , 30) +SAX.characters(The Problem Domain package is , 59) SAX.startElement(dd) -SAX.characters(Interface, thats stores and ma, 30) +SAX.characters(Interface, thats stores and ma, 58) SAX.endElement(dd) SAX.endElement(dd) SAX.endElement(dl) diff --git a/result/HTML/wired.html.sax b/result/HTML/wired.html.sax index 3760a64e..bf4695ed 100644 --- a/result/HTML/wired.html.sax +++ b/result/HTML/wired.html.sax @@ -4,7 +4,7 @@ SAX.comment( Vignette StoryServer 4 Fri Oct 15 11:37:12 1999 ) SAX.startElement(html) SAX.startElement(head) SAX.startElement(title) -SAX.characters(Top Stories News from Wired Ne, 30) +SAX.characters(Top Stories News from Wired Ne, 32) SAX.endElement(title) SAX.endElement(head) SAX.startElement(body, bgcolor='#FFFFFF', text='#000000', link='#333399', vlink='#660066', alink='#666699') @@ -1051,7 +1051,7 @@ SAX.characters( Web Business , 16) SAX.startElement(option, value='2800') SAX.characters( Bargain Books - , 30) + , 40) SAX.startElement(option, value='4') SAX.characters(Other @@ -1105,7 +1105,7 @@ SAX.characters( SAX.endElement(td) SAX.characters( - , 30) + , 35) SAX.endElement(tr) SAX.characters( , 17) @@ -1534,7 +1534,7 @@ SAX.characters(8:15 a.m., 9) SAX.endElement(font) SAX.characters( , 2) SAX.startElement(font, face='Verdana, Arial, Geneva, sans-serif', size='2') -SAX.characters(The city council approves a pl, 30) +SAX.characters(The city council approves a pl, 180) SAX.endElement(font) SAX.startElement(br) SAX.endElement(br) @@ -1624,7 +1624,7 @@ SAX.startElement(br) SAX.endElement(br) SAX.startElement(font, size='2', face='Arial, Helvetica, sans-serif') SAX.startElement(font, size='1', face='Arial, Geneva, sans-serif', color='#000000') -SAX.characters(Readers on Apple's G4 ... AOL', 30) +SAX.characters(Readers on Apple's G4 ... AOL', 59) SAX.endElement(font) SAX.startElement(br) SAX.endElement(br) @@ -2087,7 +2087,7 @@ SAX.endElement(br) SAX.startElement(font, size='1', face='Arial, Geneva, sans-serif', color='#000000') SAX.startElement(p) SAX.characters( -Contruction workers in Berli, 30) +Contruction workers in Berli, 637) SAX.startElement(br) SAX.endElement(br) SAX.endElement(p) @@ -2168,7 +2168,7 @@ SAX.characters(10:15 a.m., 10) SAX.endElement(font) SAX.characters( , 2) SAX.startElement(font, face='Verdana, Arial, Geneva, sans-serif', size='2') -SAX.characters(The Dow and Nasdaq suffer size, 30) +SAX.characters(The Dow and Nasdaq suffer size, 180) SAX.endElement(font) SAX.startElement(br) SAX.endElement(br) @@ -2200,7 +2200,7 @@ SAX.characters(9:10 a.m., 9) SAX.endElement(font) SAX.characters( , 2) SAX.startElement(font, face='Verdana, Arial, Geneva, sans-serif', size='2') -SAX.characters(The bulls and the bears are in, 30) +SAX.characters(The bulls and the bears are in, 128) SAX.endElement(font) SAX.startElement(br) SAX.endElement(br) @@ -2221,7 +2221,7 @@ SAX.comment( IBD_SUBJECT:'Want a Loan? What's Your Race?' ) SAX.startElement(font, face='Arial, Helvetica, sans-serif', size='3') SAX.startElement(b) SAX.startElement(a, href='/news/politics/0,1283,31533,00.html') -SAX.characters('Want a Loan? What's Your Race, 30) +SAX.characters('Want a Loan? What's Your Race, 32) SAX.endElement(a) SAX.endElement(b) SAX.endElement(font) @@ -2232,7 +2232,7 @@ SAX.characters(3:00 a.m., 9) SAX.endElement(font) SAX.characters( , 2) SAX.startElement(font, face='Verdana, Arial, Geneva, sans-serif', size='2') -SAX.characters(The Federal Reserve is in the , 30) +SAX.characters(The Federal Reserve is in the , 184) SAX.endElement(font) SAX.startElement(br) SAX.endElement(br) @@ -2264,7 +2264,7 @@ SAX.characters(3:00 a.m., 9) SAX.endElement(font) SAX.characters( , 2) SAX.startElement(font, face='Verdana, Arial, Geneva, sans-serif', size='2') -SAX.characters(The struggle to come up with a, 30) +SAX.characters(The struggle to come up with a, 171) SAX.endElement(font) SAX.startElement(br) SAX.endElement(br) @@ -2296,7 +2296,7 @@ SAX.characters(3:00 a.m., 9) SAX.endElement(font) SAX.characters( , 2) SAX.startElement(font, face='Verdana, Arial, Geneva, sans-serif', size='2') -SAX.characters(High-tech companies are notori, 30) +SAX.characters(High-tech companies are notori, 186) SAX.endElement(font) SAX.startElement(br) SAX.endElement(br) @@ -2328,7 +2328,7 @@ SAX.characters(3:00 a.m., 9) SAX.endElement(font) SAX.characters( , 2) SAX.startElement(font, face='Verdana, Arial, Geneva, sans-serif', size='2') -SAX.characters(Windows NT sales remain strong, 30) +SAX.characters(Windows NT sales remain strong, 165) SAX.endElement(font) SAX.startElement(br) SAX.endElement(br) @@ -2365,7 +2365,7 @@ SAX.characters(3:00 a.m., 9) SAX.endElement(font) SAX.characters( , 2) SAX.startElement(font, face='Verdana, Arial, Geneva, sans-serif', size='2') -SAX.characters(Different cancer patients need, 30) +SAX.characters(Different cancer patients need, 207) SAX.endElement(font) SAX.startElement(br) SAX.endElement(br) @@ -2397,7 +2397,7 @@ SAX.characters(3:00 a.m., 9) SAX.endElement(font) SAX.characters( , 2) SAX.startElement(font, face='Verdana, Arial, Geneva, sans-serif', size='2') -SAX.characters(It's not just another round of, 30) +SAX.characters(It's not just another round of, 196) SAX.endElement(font) SAX.startElement(br) SAX.endElement(br) @@ -2429,7 +2429,7 @@ SAX.characters(3:00 a.m., 9) SAX.endElement(font) SAX.characters( , 2) SAX.startElement(font, face='Verdana, Arial, Geneva, sans-serif', size='2') -SAX.characters(The far-flung databases on glo, 30) +SAX.characters(The far-flung databases on glo, 196) SAX.endElement(font) SAX.startElement(br) SAX.endElement(br) @@ -2501,7 +2501,7 @@ SAX.endElement(br) SAX.startElement(font, face='helvetica, arial', size='3') SAX.startElement(b) SAX.startElement(a, href='http://news.lycos.com/stories/TopNews/19991014RTNEWS-ARMS-TREATY.asp') -SAX.characters(White House Lashes Out on Trea, 30) +SAX.characters(White House Lashes Out on Trea, 32) SAX.endElement(a) SAX.endElement(b) SAX.endElement(font) @@ -2551,7 +2551,7 @@ SAX.endElement(br) SAX.startElement(font, face='helvetica, arial', size='3') SAX.startElement(b) SAX.startElement(a, href='http://www.nytimes.com/library/tech/99/10/biztech/articles/14free.html') -SAX.characters(Much Is Free in the Wired Worl, 30) +SAX.characters(Much Is Free in the Wired Worl, 31) SAX.endElement(a) SAX.endElement(b) SAX.endElement(font) @@ -2588,7 +2588,7 @@ SAX.endElement(br) SAX.startElement(font, face='helvetica, arial', size='3') SAX.startElement(b) SAX.startElement(a, href='http://www.msnbc.com/news/322926.asp') -SAX.characters(Domain Owners Surrender Privac, 30) +SAX.characters(Domain Owners Surrender Privac, 31) SAX.endElement(a) SAX.endElement(b) SAX.endElement(font) @@ -2765,7 +2765,7 @@ SAX.characters(Copyright, 9) SAX.endElement(a) SAX.characters( , 1) SAX.characters(©, 2) -SAX.characters( 1994-99 Wired Digital Inc. Al, 30) +SAX.characters( 1994-99 Wired Digital Inc. Al, 48) SAX.endElement(font) SAX.characters( @@ -2841,12 +2841,8 @@ SAX.endElement(br) SAX.ignorableWhitespace( , 1) SAX.endElement(body) -SAX.startElement(body) -SAX.startElement(p) -SAX.characters( +SAX.ignorableWhitespace( , 1) -SAX.endElement(p) -SAX.endElement(body) SAX.endElement(html) SAX.ignorableWhitespace( diff --git a/testHTML.c b/testHTML.c index af088b5c..0bd7fee8 100644 --- a/testHTML.c +++ b/testHTML.c @@ -412,9 +412,9 @@ void charactersDebug(void *ctx, const xmlChar *ch, int len) { unsigned char output[40]; - int outlen = 30; + int inlen = len, outlen = 30; - htmlEncodeEntities(output, &outlen, ch, &len, 0); + htmlEncodeEntities(output, &outlen, ch, &inlen, 0); output[outlen] = 0; fprintf(stdout, "SAX.characters(%s, %d)\n", output, len);