diff options
Diffstat (limited to 'src/doctokenizer.l')
| -rw-r--r-- | src/doctokenizer.l | 100 |
1 files changed, 83 insertions, 17 deletions
diff --git a/src/doctokenizer.l b/src/doctokenizer.l index 7f43614..1ec3e44 100644 --- a/src/doctokenizer.l +++ b/src/doctokenizer.l @@ -235,7 +235,11 @@ OPCAST {BLANK}+[^(\r\n.,]+ OPMASK ({BLANK}*{OPNORM}({FUNCARG}?))|({OPCAST}{FUNCARG}) LNKWORD1 {SCOPEMASK}({FUNCARG}({BLANK}*("const"|"volatile"))?)? LNKWORD2 {SCOPEPRE}*"operator"{OPMASK} -WORD [^ \t\n\r\\@<>&$#,.]+ +WORD1 [^ \t\n\r\\@<>&$#,.]+ +WORD2 "."|"," +WORD1NQ [^ \t\n\r\\@<>&$#,."]+ +WORD2NQ "."|"," +HTMLTAG "<"(("/")?){ID}({BLANK}+{ATTRIB})*">" %option noyywrap %option yylineno @@ -243,6 +247,10 @@ WORD [^ \t\n\r\\@<>&$#,.]+ %x St_Para %x St_Comment %x St_Title +%x St_TitleN +%x St_TitleQ +%x St_TitleA +%x St_TitleV %x St_Code %x St_HtmlOnly %x St_LatexOnly @@ -317,13 +325,13 @@ WORD [^ \t\n\r\\@<>&$#,.]+ g_token->text = tagName.mid(i+1,tagName.length()-i-2); return TK_RCSTAG; } -<St_Para>"$("{ID}")" { /* environment variable */ +<St_Para,St_HtmlOnly>"$("{ID}")" { /* environment variable */ QCString name = &yytext[2]; name = name.left(name.length()-1); QCString value = getenv(name); for (int i=value.length()-1;i>=0;i--) unput(value.at(i)); } -<St_Para>"<"(("/")?){ID}({BLANK}+{ATTRIB})*">" { /* html tag */ +<St_Para>{HTMLTAG} { /* html tag */ g_token->name = yytext; int startNamePos=1; if (g_token->name.at(1)=='/') startNamePos++; @@ -349,11 +357,8 @@ WORD [^ \t\n\r\\@<>&$#,.]+ g_token->name = yytext; return TK_LNKWORD; } -<St_Para>"."|"," { - g_token->name = yytext; - return TK_WORD; - } -<St_Para>{WORD} { /* function call */ +<St_Para>{WORD1} | +<St_Para>{WORD2} { /* function call */ g_token->name = yytext; return TK_WORD; @@ -383,7 +388,7 @@ WORD [^ \t\n\r\\@<>&$#,.]+ <St_HtmlOnly>{CMD}"endhtmlonly" { return RetVal_OK; } -<St_HtmlOnly>[^\\@\n]+ | +<St_HtmlOnly>[^\\@\n$]+ | <St_HtmlOnly>\n | <St_HtmlOnly>. { g_token->verb+=yytext; @@ -404,26 +409,87 @@ WORD [^ \t\n\r\\@<>&$#,.]+ <St_Verbatim>. { /* Verbatim text */ g_token->verb+=yytext; } -<St_Title>"&"{ID}";" { /* symbol */ +<St_Title>"\"" { // quoted title + BEGIN(St_TitleQ); + } +<St_Title>[ \t]+ { + g_token->chars=yytext; + return TK_WHITESPACE; + } +<St_Title>. { // non-quoted title + unput(*yytext); + BEGIN(St_TitleN); + } +<St_Title>\n { + return 0; + } +<St_TitleN>"&"{ID}";" { /* symbol */ g_token->name = yytext; return TK_SYMBOL; } -<St_Title>{SPCMD1} | -<St_Title>{SPCMD2} { /* special command */ +<St_TitleN>{SPCMD1} | +<St_TitleN>{SPCMD2} { /* special command */ g_token->name = yytext+1; return TK_COMMAND; } -<St_Title>{WORD} { /* word */ +<St_TitleN>{WORD1} | +<St_TitleN>{WORD2} { /* word */ g_token->name = yytext; return TK_WORD; } -<St_Title>[ \t]+ { +<St_TitleN>[ \t]+ { + g_token->chars=yytext; + return TK_WHITESPACE; + } +<St_TitleN>\n { /* new line => end of title */ + unput(*yytext); + return 0; + } +<St_TitleQ>"&"{ID}";" { /* symbol */ + g_token->name = yytext; + return TK_SYMBOL; + } +<St_TitleQ>{SPCMD1} | +<St_TitleQ>{SPCMD2} { /* special command */ + g_token->name = yytext+1; + return TK_COMMAND; + } +<St_TitleQ>{WORD1NQ} | +<St_TitleQ>{WORD2NQ} { /* word */ + g_token->name = yytext; + return TK_WORD; + } +<St_TitleQ>[ \t]+ { g_token->chars=yytext; return TK_WHITESPACE; } -<St_Title>\n { /* new line => end of title */ +<St_TitleQ>"\"" { /* closing quote => end of title */ + BEGIN(St_TitleA); + return 0; + } +<St_TitleQ>\n { /* new line => end of title */ + unput(*yytext); return 0; } +<St_TitleA>{BLANK}*{ID}{BLANK}*"="{BLANK}* { // title attribute + g_token->name = yytext; + g_token->name = g_token->name.left( + g_token->name.find('=')).stripWhiteSpace(); + BEGIN(St_TitleV); + } +<St_TitleV>[^ \t\r\n]+ { // attribute value + g_token->chars = yytext; + BEGIN(St_TitleN); + return TK_WORD; + } +<St_TitleV,St_TitleA>. { + unput(*yytext); + return 0; + } +<St_TitleV,St_TitleA>\n { + return 0; + } + <St_Ref>{ID} { g_token->name=yytext; return TK_WORD; @@ -458,8 +524,8 @@ WORD [^ \t\n\r\\@<>&$#,.]+ g_token->name = yytext+1; return TK_COMMAND; } -<St_Ref2>[^ \t\n\r\\@<&$"]+ | -<St_Ref2>[^ \t\n\r\\@<&$"]+"("[^\n")]*")"({BLANK}*("const"|"volatile"))? { +<St_Ref2>{WORD1NQ} | +<St_Ref2>{WORD2NQ} { /* word */ g_token->name = yytext; return TK_WORD; |