1) Since I sent my last diff, I've:
a) added some string processing to make sure no HTML reserved
characters are placed into the output. I process each word.
b) altered the html a bit so that XML parsers can deal with it.
I've put in a title tag or an empty title tag and added end tags to the
meta tags.
2) Addressing your concerns:
a) I've removed the initialization of stdout.
b) I close f now and reopen it. This also removes the warning.
c) If a user is running with the -bbox option, they want word
bounding boxes. If there are no words, I think a line to stderr is
appropriate.
-KB
On Wed, 26 May 2010, Albert Astals Cid wrote:
A Dimecres, 26 de maig de 2010, Kenneth Berland va escriure:
I get a compiler warning without it.
pdftotext.cc: In function ‘int main(int, char**)’:
pdftotext.cc:164: warning: ‘f’ may be used uninitialized in this function
That change will not get accepted, sorry, initializing f to stdout is not a
solution.
Also i do not like the fact that you do not close f if you are writing the
bbox? Can't you just open it again like the code already does?
Also i do not understand why the code considers a page having no text an
error.
Albert
-KB
On Wed, 26 May 2010, Albert Astals Cid wrote:
> A Diumenge, 9 de maig de 2010, Kenneth Berland va escriure:
>> List,
>>
>> I've attached a small addition to pdftotext that outputs bounding box
>> information to html like this:
>>
>> <doc>
>>
>> <page width="612.000000" height="792.000000"/>
>>
>> <word xMin="56.800000" yMin="57.208000" xMax="75.412000"
>>
>> yMax="70.492000">The</word> </page>
>> </doc>
>>
>> I had a need, maybe others will too.
>>
>> -KB
>
> Why is this change necessary?
>
> - FILE *f;
> + FILE *f = stdout;
>
> Albert
_______________________________________________
poppler mailing list
[email protected]
http://lists.freedesktop.org/mailman/listinfo/poppler
diff --git a/utils/pdftotext.cc b/utils/pdftotext.cc
index d4e004b..dcf4802 100644
--- a/utils/pdftotext.cc
+++ b/utils/pdftotext.cc
@@ -49,6 +49,7 @@
#include "CharTypes.h"
#include "UnicodeMap.h"
#include "Error.h"
+#include <string>
static void printInfoString(FILE *f, Dict *infoDict, char *key,
char *text1, char *text2, UnicodeMap *uMap);
@@ -61,6 +62,7 @@ static int x = 0;
static int y = 0;
static int w = 0;
static int h = 0;
+static int bbox = 0;
static GBool physLayout = gFalse;
static GBool rawOrder = gFalse;
static GBool htmlMeta = gFalse;
@@ -103,6 +105,8 @@ static const ArgDesc argDesc[] = {
"output end-of-line convention (unix, dos, or mac)"},
{"-nopgbrk", argFlag, &noPageBreaks, 0,
"don't insert page breaks between pages"},
+ {"-bbox", argFlag, &bbox, 0,
+ "output bounding box for each word and page size to html. Sets -htmlmeta"},
{"-opw", argString, ownerPassword, sizeof(ownerPassword),
"owner password (for encrypted files)"},
{"-upw", argString, userPassword, sizeof(userPassword),
@@ -122,6 +126,34 @@ static const ArgDesc argDesc[] = {
{NULL}
};
+using namespace std;
+
+string myStringReplace( string inString, string oldToken, string newToken ){
+
+ size_t foundLoc;
+ int advance = 0;
+ do {
+ foundLoc = inString.find(oldToken, advance);
+ if (foundLoc != string::npos){
+ inString.replace( foundLoc, oldToken.length(), newToken );
+ advance = foundLoc + newToken.length();
+ }
+ } while (foundLoc != string::npos );
+ return(inString);
+}
+
+string myXmlTokenReplace( char* inString ){
+ string myString(inString);
+ myString = myStringReplace(myString,string("&"),string("&") );
+ myString = myStringReplace(myString,string("'"),string("'") );
+ myString = myStringReplace(myString,string("\""),string(""") );
+ myString = myStringReplace(myString,string("<"),string("<") );
+ myString = myStringReplace(myString,string(">"),string(">") );
+ return(myString);
+}
+
+
+
int main(int argc, char *argv[]) {
PDFDoc *doc;
GooString *fileName;
@@ -139,6 +171,9 @@ int main(int argc, char *argv[]) {
// parse args
ok = parseArgs(argDesc, &argc, argv);
+ if (bbox){
+ htmlMeta = gTrue;
+ }
if (!ok || (argc < 2 && !printEnc) || argc > 3 || printVersion || printHelp)
{
fprintf(stderr, "pdftotext version %s\n", PACKAGE_VERSION);
fprintf(stderr, "%s\n", popplerCopyright);
@@ -257,57 +292,98 @@ int main(int argc, char *argv[]) {
goto err3;
}
}
- fputs("<html>\n", f);
+ fputs("<!DOCTYPE html PUBLIC \"-//W3C//DTD XHTML 1.0 Transitional//EN\"
\"http://www.w3.org/TR/xhtml1/DTD/xhtml1-transitional.dtd\";>",f);
+ fputs("<html xmlns=\"http://www.w3.org/1999/xhtml\";>\n", f);
fputs("<head>\n", f);
doc->getDocInfo(&info);
if (info.isDict()) {
- printInfoString(f, info.getDict(), "Title", "<title>", "</title>\n",
- uMap);
+ Object obj;
+ if (info.getDict()->lookup("Title", &obj)->isString()) {
+ printInfoString(f, info.getDict(), "Title", "<title>", "</title>\n",
+ uMap);
+ } else {
+ fputs("<title></title>\n", f);
+ }
printInfoString(f, info.getDict(), "Subject",
- "<meta name=\"Subject\" content=\"", "\">\n", uMap);
+ "<meta name=\"Subject\" content=\"", "\"/>\n", uMap);
printInfoString(f, info.getDict(), "Keywords",
- "<meta name=\"Keywords\" content=\"", "\">\n", uMap);
+ "<meta name=\"Keywords\" content=\"", "\"/>\n", uMap);
printInfoString(f, info.getDict(), "Author",
- "<meta name=\"Author\" content=\"", "\">\n", uMap);
+ "<meta name=\"Author\" content=\"", "\"/>\n", uMap);
printInfoString(f, info.getDict(), "Creator",
- "<meta name=\"Creator\" content=\"", "\">\n", uMap);
+ "<meta name=\"Creator\" content=\"", "\"/>\n", uMap);
printInfoString(f, info.getDict(), "Producer",
- "<meta name=\"Producer\" content=\"", "\">\n", uMap);
+ "<meta name=\"Producer\" content=\"", "\"/>\n", uMap);
printInfoDate(f, info.getDict(), "CreationDate",
- "<meta name=\"CreationDate\" content=\"\">\n");
+ "<meta name=\"CreationDate\" content=\"\"/>\n");
printInfoDate(f, info.getDict(), "LastModifiedDate",
- "<meta name=\"ModDate\" content=\"\">\n");
+ "<meta name=\"ModDate\" content=\"\"/>\n");
}
info.free();
fputs("</head>\n", f);
fputs("<body>\n", f);
- fputs("<pre>\n", f);
+ if (!bbox) fputs("<pre>\n", f);
if (f != stdout) {
fclose(f);
}
}
// write text file
- textOut = new TextOutputDev(textFileName->getCString(),
- physLayout, rawOrder, htmlMeta);
- if (textOut->isOk()) {
- if ((w==0) && (h==0) && (x==0) && (y==0)) {
- doc->displayPages(textOut, firstPage, lastPage, resolution, resolution,
0,
- gTrue, gFalse, gFalse);
- } else {
- int page;
-
- for (page = firstPage; page <= lastPage; ++page) {
+ if (bbox) {
+ textOut = new TextOutputDev("/dev/null",
+ physLayout, rawOrder, htmlMeta);
+ if (!(f = fopen(textFileName->getCString(), "ab"))) {
+ error(-1, "Couldn't open text file '%s' for append",
textFileName->getCString());
+ exitCode = 2;
+ goto err3;
+ }
+
+ if (textOut->isOk()) {
+ fprintf(f, "<doc>\n");
+ for (int page = firstPage; page <= lastPage; ++page) {
+ fprintf(f, " <page width=\"%f\"
height=\"%f\">\n",doc->getPageCropWidth(page), doc->getPageCropHeight(page) );
+ doc->displayPage(textOut, page, resolution, resolution, 0,
+ gTrue, gFalse, gFalse);
+ TextWordList *wordlist;
+ wordlist = textOut->makeWordList();
+ int word_length = wordlist->getLength();
+ TextWord *word;
+ double xMinA, yMinA, xMaxA, yMaxA;
+ if (!word_length)
+ fprintf(stderr, "no word list\n");
+
+ for (int i=0; i < word_length; i++){
+ word = wordlist->get(i);
+ word->getBBox (&xMinA, &yMinA, &xMaxA, &yMaxA);
+ string myString = myXmlTokenReplace( (char*) word->getText() );
+ fprintf(f," <word xMin=\"%f\" yMin=\"%f\" xMax=\"%f\"
yMax=\"%f\">%s</word>\n", xMinA, yMinA, xMaxA, yMaxA, (char*) myString.c_str()
);
+ }
+ fprintf(f, " </page>\n");
+ }
+ fprintf(f, "</doc>\n");
+ }
+ fclose(f);
+
+ } else {
+ textOut = new TextOutputDev(textFileName->getCString(),
+ physLayout, rawOrder, htmlMeta);
+ if (textOut->isOk()) {
+ if ((w==0) && (h==0) && (x==0) && (y==0)) {
+ doc->displayPages(textOut, firstPage, lastPage, resolution, resolution,
0,
+ gTrue, gFalse, gFalse);
+ } else {
+
+ for (int page = firstPage; page <= lastPage; ++page) {
doc->displayPageSlice(textOut, page, resolution, resolution, 0,
gTrue, gFalse, gFalse,
x, y, w, h);
- }
- }
-
- } else {
+ }
+ }
+ } else {
delete textOut;
exitCode = 2;
goto err3;
+ }
}
delete textOut;
@@ -322,7 +398,7 @@ int main(int argc, char *argv[]) {
goto err3;
}
}
- fputs("</pre>\n", f);
+ if (!bbox) fputs("</pre>\n", f);
fputs("</body>\n", f);
fputs("</html>\n", f);
if (f != stdout) {
_______________________________________________
poppler mailing list
[email protected]
http://lists.freedesktop.org/mailman/listinfo/poppler
