diff options
author | dimitri <dimitri@afe2bf4a-e733-0410-8a33-86f594647bc7> | 2005-06-15 19:21:39 (GMT) |
---|---|---|
committer | dimitri <dimitri@afe2bf4a-e733-0410-8a33-86f594647bc7> | 2005-06-15 19:21:39 (GMT) |
commit | cf0e414d83f34ebf877abbe43a15c350876669d4 (patch) | |
tree | 3f2be46d34910503ef3532aa95aa0422e86cd993 /src/doctokenizer.l | |
parent | ad65c6e23de430b2c4f0ef732b95834c87a28c20 (diff) | |
download | Doxygen-cf0e414d83f34ebf877abbe43a15c350876669d4.zip Doxygen-cf0e414d83f34ebf877abbe43a15c350876669d4.tar.gz Doxygen-cf0e414d83f34ebf877abbe43a15c350876669d4.tar.bz2 |
Release-1.4.3-20050615
Diffstat (limited to 'src/doctokenizer.l')
-rw-r--r-- | src/doctokenizer.l | 180 |
1 files changed, 97 insertions, 83 deletions
diff --git a/src/doctokenizer.l b/src/doctokenizer.l index 640c562..b2be204 100644 --- a/src/doctokenizer.l +++ b/src/doctokenizer.l @@ -136,72 +136,6 @@ static int computeIndent(const char *str,int length) return indent; } -/*! converts input string \a opt into a list of Html Attributes. Each - * attribute is a name, value pair. The result is stored in g_token->attribs - */ -static void parseHtmlAttribs(const char *att) -{ - //printf("parseHtmlAttribs(%s)\n",att); - QCString attribs=att; - int len = attribs.length(); - char c; - int i=0,startName,endName,startAttrib,endAttrib; - while (i<len) - { - c=attribs.at(i); - // skip spaces - while (i<len && c==' ') { c=attribs.at(++i); } - startName=i; - // search for end of name - while (i<len && c!=' ' && c!='=') { c=attribs.at(++i); } - endName=i; - HtmlAttrib opt; - opt.name = attribs.mid(startName,endName-startName).lower(); - // skip spaces - while (i<len && c==' ') { c=attribs.at(++i); } - if (attribs.at(i)=='=') // option has value - { - c=attribs.at(++i); - // skip spaces - while (i<len && c==' ') { c=attribs.at(++i); } - if (attribs.at(i)=='\'') // option '...' - { - c=attribs.at(++i); - startAttrib=i; - - // search for matching quote - while (i<len && c!='\'') { c=attribs.at(++i); } - endAttrib=i; - if (i<len) c=attribs.at(++i); - } - else if (attribs.at(i)=='"') // option "..." - { - c=attribs.at(++i); - startAttrib=i; - // search for matching quote - while (i<len && c!='"') { c=attribs.at(++i); } - endAttrib=i; - if (i<len) c=attribs.at(++i); - } - else // value without any quotes - { - startAttrib=i; - // search for separator - while (i<len && c!=' ') { c=attribs.at(++i); } - endAttrib=i; - if (i<len) c=attribs.at(++i); - } - opt.value = attribs.mid(startAttrib,endAttrib-startAttrib); - } - else // start next option - { - } - //printf("=====> Adding option name=<%s> value=<%s>\n", - // opt.name.data(),opt.value.data()); - g_token->attribs.append(&opt); - } -} - //-------------------------------------------------------------------------- static void processSection() @@ -231,27 +165,96 @@ static void processSection() static void handleHtmlTag() { - g_token->name = yytext; + QCString tagText=yytext; g_token->attribs.clear(); + g_token->endTag = FALSE; + g_token->emptyTag = FALSE; + + // Check for end tag int startNamePos=1; - if (g_token->name.at(1)=='/') startNamePos++; - int attSep=0; - while (attSep<yyleng && !isspace(yytext[attSep])) + if (tagText.at(1)=='/') { - attSep++; + g_token->endTag = TRUE; + startNamePos++; } - if (attSep!=yyleng) // tag has one or more options + + // Parse the name portion + int i = startNamePos; + for (i=startNamePos; i < yyleng; i++) { - parseHtmlAttribs(g_token->name.mid(attSep+1,g_token->name.length()-attSep-2)); - g_token->name=g_token->name.mid(startNamePos,attSep-1).lower(); + // Check for valid HTML/XML name chars (including namespaces) + char c = tagText.at(i); + if (!(isalnum(c) || c=='-' || c=='_' || c==':')) break; } - else // tag without options, strip brackets + g_token->name = tagText.mid(startNamePos,i-startNamePos); + + // Parse the attributes. Each attribute is a name, value pair + // The result is stored in g_token->attribs. + int startName,endName,startAttrib,endAttrib; + while (i<yyleng) { - g_token->name=g_token->name.mid(startNamePos,g_token->name.length()-startNamePos-1).lower(); + char c=tagText.at(i); + // skip spaces + while (i<yyleng && c==' ') { c=tagText.at(++i); } + // check for end of the tag + if (c == '>') break; + // Check for XML style "empty" tag. + if (c == '/') + { + g_token->emptyTag = TRUE; + break; + } + startName=i; + // search for end of name + while (i<yyleng && c!=' ' && c!='=') { c=tagText.at(++i); } + endName=i; + HtmlAttrib opt; + opt.name = tagText.mid(startName,endName-startName).lower(); + // skip spaces + while (i<yyleng && c==' ') { c=tagText.at(++i); } + if (tagText.at(i)=='=') // option has value + { + c=tagText.at(++i); + // skip spaces + while (i<yyleng && c==' ') { c=tagText.at(++i); } + if (tagText.at(i)=='\'') // option '...' + { + c=tagText.at(++i); + startAttrib=i; + + // search for matching quote + while (i<yyleng && c!='\'') { c=tagText.at(++i); } + endAttrib=i; + if (i<yyleng) c=tagText.at(++i); + } + else if (tagText.at(i)=='"') // option "..." + { + c=tagText.at(++i); + startAttrib=i; + // search for matching quote + while (i<yyleng && c!='"') { c=tagText.at(++i); } + endAttrib=i; + if (i<yyleng) c=tagText.at(++i); + } + else // value without any quotes + { + startAttrib=i; + // search for separator + while (i<yyleng && c!=' ') { c=tagText.at(++i); } + endAttrib=i; + if (i<yyleng) c=tagText.at(++i); + } + opt.value = tagText.mid(startAttrib,endAttrib-startAttrib); + } + else // start next option + { + } + //printf("=====> Adding option name=<%s> value=<%s>\n", + // opt.name.data(),opt.value.data()); + g_token->attribs.append(&opt); } - g_token->endTag = startNamePos==2; } - + static QString stripEmptyLines(const char *s) { int result=0,p=0; @@ -287,6 +290,7 @@ WS [ \t\r\n] NONWS [^ \t\r\n] BLANK [ \t\r] ID [a-z_A-Z][a-z_A-Z0-9]* +MAILADR [a-z_A-Z0-9.+-]+"@"[a-z_A-Z0-9-]+("."[a-z_A-Z0-9\-]+)+[a-z_A-Z0-9\-]+ OPTSTARS ("//"{BLANK}*)?"*"*{BLANK}* LISTITEM {BLANK}*{OPTSTARS}"-"("#")?{WS} ENDLIST {BLANK}*{OPTSTARS}"."{BLANK}*\n @@ -326,7 +330,7 @@ WORD1 "%"?{CHARWORD}+|"{"|"}"|("\""[^"\n]*"\"") WORD2 "."|","|"("|")"|"["|"]"|":"|";"|"\?" WORD1NQ "%"?{CHARWORDQ}+ WORD2NQ "."|","|"("|")"|"["|"]"|":"|";"|"\?" -HTMLTAG "<"(("/")?){ID}({WS}+{ATTRIB})*{WS}*">" +HTMLTAG "<"(("/")?){ID}({WS}+{ATTRIB})*{WS}*(("/")?)">" HTMLKEYL "strong"|"center"|"table"|"caption"|"small"|"code"|"dfn"|"var"|"img"|"pre"|"sub"|"sup"|"tr"|"td"|"th"|"ol"|"ul"|"li"|"tt"|"kbd"|"em"|"hr"|"dl"|"dt"|"dd"|"br"|"i"|"a"|"b"|"p" HTMLKEYU "STRONG"|"CENTER"|"TABLE"|"CAPTION"|"SMALL"|"CODE"|"DFN"|"VAR"|"IMG"|"PRE"|"SUB"|"SUP"|"TR"|"TD"|"TH"|"OL"|"UL"|"LI"|"TT"|"KBD"|"EM"|"HR"|"DL"|"DT"|"DD"|"BR"|"I"|"A"|"B"|"P" HTMLKEYW {HTMLKEYL}|{HTMLKEYU} @@ -344,6 +348,7 @@ REFWORD ("#"|"::")?({ID}("."|"#"|"::"|"-"))*({ID}(":")?){FUNCARG}? %x St_TitleA %x St_TitleV %x St_Code +%x St_XmlCode %x St_HtmlOnly %x St_ManOnly %x St_LatexOnly @@ -445,7 +450,7 @@ REFWORD ("#"|"::")?({ID}("."|"#"|"::"|"-"))*({ID}(":")?){FUNCARG}? g_token->isEMailAddr=FALSE; return TK_URL; } -<St_Para>[a-z_A-Z0-9.+-]+"@"[a-z_A-Z0-9-]+("."[a-z_A-Z0-9\-]+)+[a-z_A-Z0-9\-]+ { // Mail address +<St_Para>{MAILADR} { // Mail address g_token->name=yytext; g_token->isEMailAddr=TRUE; return TK_URL; @@ -539,9 +544,12 @@ REFWORD ("#"|"::")?({ID}("."|"#"|"::"|"-"))*({ID}(":")?){FUNCARG}? <St_Code>{WS}*{CMD}"endcode" { return RetVal_OK; } -<St_Code>[^\\@\n]+ | -<St_Code>\n | -<St_Code>. { +<St_XmlCode>{WS}*"</code>" { + return RetVal_OK; + } +<St_Code,St_XmlCode>[^\\@\n]+ | +<St_Code,St_XmlCode>\n | +<St_Code,St_XmlCode>. { g_token->verb+=yytext; } <St_HtmlOnly>{CMD}"endhtmlonly" { @@ -942,6 +950,12 @@ void doctokenizerYYsetStateCode() BEGIN(St_Code); } +void doctokenizerYYsetStateXmlCode() +{ + g_token->verb=""; + BEGIN(St_XmlCode); +} + void doctokenizerYYsetStateHtmlOnly() { g_token->verb=""; |