diff --git a/utils/HtmlOutputDev.cc b/utils/HtmlOutputDev.cc
index dbf677f..22acbd7 100644
--- a/utils/HtmlOutputDev.cc
+++ b/utils/HtmlOutputDev.cc
@@ -27,6 +27,7 @@
// Copyright (C) 2009 Reece Dunn
// Copyright (C) 2010 Adrian Johnson
// Copyright (C) 2010 Hib Eris
+// Copyright (C) 2010 Raphael Monrouzeau
//
// To see a description of the changes please see the Changelog file that
// came with your tarball or type make ChangeLog if you are building from git
@@ -641,6 +642,16 @@ void HtmlPage::dumpAsXML(FILE* f,int page){
delete fontCSStyle;
}
+ // Loop over the list of image names on this page
+ int listlen=HtmlOutputDev::imgList->getLength();
+ for (int i = 0; i < listlen; i++) {
+ GooString *fName= (GooString *)HtmlOutputDev::imgList->del(0);
+ fprintf(f,"%s\n",fName->getCString());
+ delete fName;
+ }
+ HtmlOutputDev::imgNum=1;
+
+ // Loop over the preprocessed text output commands on this page
GooString *str, *str1 = NULL;
for(HtmlString *tmp=yxStrings;tmp;tmp=tmp->yxNext){
if (tmp->htext){
@@ -759,26 +770,33 @@ void HtmlPage::dump(FILE *f, int pageNum)
}
else
{
- fprintf(f,"",pageNum);
- // Loop over the list of image names on this page
- int listlen=HtmlOutputDev::imgList->getLength();
- for (int i = 0; i < listlen; i++) {
- GooString *fName= (GooString *)HtmlOutputDev::imgList->del(0);
- fprintf(f,"
\n",fName->getCString());
- delete fName;
+ if (xml)
+ {
+ dumpAsXML(f, pageNum);
}
- HtmlOutputDev::imgNum=1;
-
- GooString* str;
- for(HtmlString *tmp=yxStrings;tmp;tmp=tmp->yxNext){
- if (tmp->htext){
- str=new GooString(tmp->htext);
- fputs(str->getCString(),f);
- delete str;
- fputs("
\n",f);
+ else
+ {
+ fprintf(f,"",pageNum);
+ // Loop over the list of image names on this page
+ int listlen=HtmlOutputDev::imgList->getLength();
+ for (int i = 0; i < listlen; i++) {
+ GooString *fName= (GooString *)HtmlOutputDev::imgList->del(0);
+ fprintf(f,"
\n",fName->getCString());
+ delete fName;
+ }
+ HtmlOutputDev::imgNum=1;
+
+ GooString* str;
+ for(HtmlString *tmp=yxStrings;tmp;tmp=tmp->yxNext){
+ if (tmp->htext){
+ str=new GooString(tmp->htext);
+ fputs(str->getCString(),f);
+ delete str;
+ fputs("
\n",f);
+ }
}
+ fputs("
\n",f);
}
- fputs("
\n",f);
}
}
diff --git a/utils/pdf2xml.dtd b/utils/pdf2xml.dtd
index 1afa4fe..2a5ed22 100644
--- a/utils/pdf2xml.dtd
+++ b/utils/pdf2xml.dtd
@@ -26,3 +26,4 @@
>
+
diff --git a/utils/pdftohtml.cc b/utils/pdftohtml.cc
index 3c74c6e..aea28ce 100644
--- a/utils/pdftohtml.cc
+++ b/utils/pdftohtml.cc
@@ -256,7 +256,7 @@ int main(int argc, char *argv[]) {
if (complexMode) {
//noframes=gFalse;
stout=gFalse;
- }
+ }
if (stout) {
noframes=gTrue;
@@ -264,8 +264,10 @@ int main(int argc, char *argv[]) {
}
if (xml)
- {
- complexMode = gTrue;
+ {
+ // complexMode is not anymore activated by default in xml
+ // output mode.
+ //complexMode = gTrue;
noframes = gTrue;
noMerge = gTrue;
}