summaryrefslogtreecommitdiffstats
path: root/src/doctokenizer.l
diff options
context:
space:
mode:
Diffstat (limited to 'src/doctokenizer.l')
-rw-r--r--src/doctokenizer.l170
1 files changed, 143 insertions, 27 deletions
diff --git a/src/doctokenizer.l b/src/doctokenizer.l
index 3772807..765e6c8 100644
--- a/src/doctokenizer.l
+++ b/src/doctokenizer.l
@@ -23,6 +23,7 @@
#include <qstring.h>
#include <qstack.h>
#include <qdict.h>
+#include <qregexp.h>
#include "doctokenizer.h"
#include "cmdmapper.h"
@@ -257,17 +258,44 @@ static void handleHtmlTag()
}
}
-static QCString stripEmptyLines(const char *s)
+static QCString stripEmptyLines(const QCString &s)
{
- if (s==0) return QCString();
- int result=0,p=0;
+ if (s.isEmpty()) return QCString();
+ int end=s.length();
+ int start=0,p=0;
+ // skip leading empty lines
for (;;)
{
int c;
- while ((c=s[p]) && isspace(c)) p++;
- if (s[p]=='\n') result=++p; else break;
+ while ((c=s[p]) && (c==' ' || c=='\t')) p++;
+ if (s[p]=='\n')
+ {
+ start=++p;
+ }
+ else
+ {
+ break;
+ }
+ }
+ // skip trailing empty lines
+ p=end-1;
+ if (p>=start && s.at(p)=='\n') p--;
+ while (p>=start)
+ {
+ int c;
+ while ((c=s[p]) && (c==' ' || c=='\t')) p--;
+ if (s[p]=='\n')
+ {
+ end=p;
+ }
+ else
+ {
+ break;
+ }
+ p--;
}
- return &s[result];
+ //printf("stripEmptyLines(%d-%d)\n",start,end);
+ return s.mid(start,end-start);
}
//--------------------------------------------------------------------------
@@ -288,18 +316,20 @@ static int yyread(char *buf,int max_size)
%}
-CMD ("\\"|"@")
-WS [ \t\r\n]
-NONWS [^ \t\r\n]
-BLANK [ \t\r]
-ID "$"?[a-z_A-Z\x80-\xFF][a-z_A-Z0-9\x80-\xFF]*
-LABELID [a-z_A-Z\x80-\xFF][a-z_A-Z0-9\x80-\xFF\-]*
-CITEID [a-z_A-Z\x80-\xFF][a-z_A-Z0-9\x80-\xFF\-:/]*
-MAILADR [a-z_A-Z0-9.+-]+"@"[a-z_A-Z0-9-]+("."[a-z_A-Z0-9\-]+)+[a-z_A-Z0-9\-]+
-OPTSTARS ("//"{BLANK}*)?"*"*{BLANK}*
-LISTITEM {BLANK}*{OPTSTARS}"-"("#")?{WS}
-ENDLIST {BLANK}*{OPTSTARS}"."{BLANK}*\n
-ATTRIB {ID}{WS}*("="{WS}*(("\""[^\"]*"\"")|("'"[^\']*"'")|[^ \t\r\n'"><]+))?
+CMD ("\\"|"@")
+WS [ \t\r\n]
+NONWS [^ \t\r\n]
+BLANK [ \t\r]
+ID "$"?[a-z_A-Z\x80-\xFF][a-z_A-Z0-9\x80-\xFF]*
+LABELID [a-z_A-Z\x80-\xFF][a-z_A-Z0-9\x80-\xFF\-]*
+CITEID [a-z_A-Z\x80-\xFF][a-z_A-Z0-9\x80-\xFF\-:/]*
+MAILADR ("mailto:")?[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}*[-]("#")?{WS}
+MLISTITEM {BLANK}*[+*]{WS}
+OLISTITEM {BLANK}*[1-9][0-9]*"."{WS}
+ENDLIST {BLANK}*"."{BLANK}*\n
+ATTRIB {ID}{WS}*("="{WS}*(("\""[^\"]*"\"")|("'"[^\']*"'")|[^ \t\r\n'"><]+))?
URLCHAR [a-z_A-Z0-9\!\~\,\:\;\'\$\?\@\&\%\#\.\-\+\/\=]
URLMASK ({URLCHAR}+([({]{URLCHAR}*[)}])?)+
FILESCHAR [a-z_A-Z0-9\\:\\\/\-\+]
@@ -309,7 +339,7 @@ FILEMASK ({FILESCHAR}*{FILEECHAR}+("."{FILESCHAR}*{FILEECHAR}+)*)|{HFILEMASK}
LINKMASK [^ \t\n\r\\@<&${}]+("("[^\n)]*")")?({BLANK}*("const"|"volatile"){BLANK}+)?
VERBATIM "verbatim"{BLANK}*
SPCMD1 {CMD}([a-z_A-Z][a-z_A-Z0-9]*|{VERBATIM})
-SPCMD2 {CMD}[\\@<>&$#%~"]
+SPCMD2 {CMD}[\\@<>&$#%~".]
SPCMD3 {CMD}form#[0-9]+
SPCMD4 {CMD}"::"
INOUT "in"|"out"|("in"{BLANK}*","{BLANK}*"out")|("out"{BLANK}*","{BLANK}*"in")
@@ -389,14 +419,44 @@ REFWORD {LABELID}|{REFWORD2}|{REFWORD3}
%x St_SecSkip
%%
-<St_Para>\r /* skip carriage return */
-<St_Para>^{LISTITEM} { /* list item */
+<St_Para>\r /* skip carriage return */
+<St_Para>^{LISTITEM} { /* list item */
QCString text=yytext;
int dashPos = text.findRev('-');
g_token->isEnumList = text.at(dashPos+1)=='#';
g_token->indent = computeIndent(yytext,dashPos);
return TK_LISTITEM;
}
+<St_Para>^{MLISTITEM} { /* list item */
+ if (!Doxygen::markdownSupport)
+ {
+ REJECT;
+ }
+ else
+ {
+ QCString text=yytext;
+ static QRegExp re("[*+]");
+ int listPos = text.findRev(re);
+ g_token->isEnumList = FALSE;
+ g_token->indent = computeIndent(yytext,listPos);
+ return TK_LISTITEM;
+ }
+ }
+<St_Para>^{OLISTITEM} { /* numbered list item */
+ if (!Doxygen::markdownSupport)
+ {
+ REJECT;
+ }
+ else
+ {
+ QCString text=yytext;
+ static QRegExp re("[1-9]");
+ int digitPos = text.find(re);
+ g_token->isEnumList = TRUE;
+ g_token->indent = computeIndent(yytext,digitPos);
+ return TK_LISTITEM;
+ }
+ }
<St_Para>{BLANK}*\n{LISTITEM} { /* list item on next line */
QCString text=yytext;
text=text.right(text.length()-text.find('\n')-1);
@@ -405,6 +465,38 @@ REFWORD {LABELID}|{REFWORD2}|{REFWORD3}
g_token->indent = computeIndent(text,dashPos);
return TK_LISTITEM;
}
+<St_Para>{BLANK}*\n{MLISTITEM} { /* list item on next line */
+ if (!Doxygen::markdownSupport)
+ {
+ REJECT;
+ }
+ else
+ {
+ QCString text=yytext;
+ static QRegExp re("[*+]");
+ text=text.right(text.length()-text.find('\n')-1);
+ int markPos = text.findRev(re);
+ g_token->isEnumList = FALSE;
+ g_token->indent = computeIndent(text,markPos);
+ return TK_LISTITEM;
+ }
+ }
+<St_Para>{BLANK}*\n{OLISTITEM} { /* list item on next line */
+ if (!Doxygen::markdownSupport)
+ {
+ REJECT;
+ }
+ else
+ {
+ QCString text=yytext;
+ text=text.right(text.length()-text.find('\n')-1);
+ static QRegExp re("[1-9]");
+ int digitPos = text.find(re);
+ g_token->isEnumList = TRUE;
+ g_token->indent = computeIndent(text,digitPos);
+ return TK_LISTITEM;
+ }
+ }
<St_Para>^{ENDLIST} { /* end list */
int dotPos = QCString(yytext).findRev('.');
g_token->indent = computeIndent(yytext,dotPos);
@@ -479,8 +571,22 @@ REFWORD {LABELID}|{REFWORD2}|{REFWORD3}
g_token->isEMailAddr=FALSE;
return TK_URL;
}
+<St_Para>"<"("http:"|"https:"|"ftp:"|"file:"|"news:"){URLMASK}">" { // URL
+ g_token->name=yytext;
+ g_token->name = g_token->name.mid(1,g_token->name.length()-2);
+ g_token->isEMailAddr=FALSE;
+ return TK_URL;
+ }
<St_Para>{MAILADR} { // Mail address
g_token->name=yytext;
+ g_token->name.stripPrefix("mailto:");
+ g_token->isEMailAddr=TRUE;
+ return TK_URL;
+ }
+<St_Para>"<"{MAILADR}">" { // Mail address
+ g_token->name=yytext;
+ g_token->name = g_token->name.mid(1,g_token->name.length()-2);
+ g_token->name.stripPrefix("mailto:");
g_token->isEMailAddr=TRUE;
return TK_URL;
}
@@ -565,7 +671,7 @@ REFWORD {LABELID}|{REFWORD2}|{REFWORD3}
g_token->name = yytext;
return TK_COMMAND;
}
-<St_Para>({BLANK}*\n)+{BLANK}*\n {
+<St_Para>({BLANK}*\n)+{BLANK}*\n{BLANK}* {
if (g_insidePre)
{
/* Inside a <pre>..</pre> blank lines are treated
@@ -574,9 +680,19 @@ REFWORD {LABELID}|{REFWORD2}|{REFWORD3}
g_token->chars=yytext;
return TK_WHITESPACE;
}
- else
+ else // found end of a paragraph
{
- /* start of a new paragraph */
+ g_token->indent=computeIndent(yytext,yyleng-1);
+ int i;
+ // put back the indentation (needed for list items)
+ for (i=0;i<g_token->indent;i++)
+ {
+ unput(' ');
+ }
+ // tell flex that after putting the last indent
+ // back we are at the beginning of the line
+ YY_CURRENT_BUFFER->yy_at_bol=1;
+ // start of a new paragraph
return TK_NEWPARA;
}
}
@@ -618,9 +734,9 @@ REFWORD {LABELID}|{REFWORD2}|{REFWORD3}
<St_XmlOnly>{CMD}"endxmlonly" {
return RetVal_OK;
}
-<St_XmlOnly>[^\\@\n]+ |
-<St_XmlOnly>\n |
-<St_XmlOnly>. {
+<St_XmlOnly>[^\\@\n]+ |
+<St_XmlOnly>\n |
+<St_XmlOnly>. {
g_token->verb+=yytext;
}
<St_Verbatim>{CMD}"endverbatim" {
generated by cgit v0.12 at 2024-07-03 00:04:40 (GMT)