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
diff --git a/utils/pdftotext.cc b/utils/pdftotext.cc
index d4e004b..c15667e 100644
--- a/utils/pdftotext.cc
+++ b/utils/pdftotext.cc
@@ -61,6 +61,7 @@ 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 +104,8 @@ 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),
@@ -128,7 +131,7 @@ int main(int argc, char *argv[]) {
GooString *textFileName;
GooString *ownerPW, *userPW;
TextOutputDev *textOut;
- FILE *f;
+ FILE *f = stdout;
UnicodeMap *uMap;
Object info;
GBool ok;
@@ -139,6 +142,9 @@ 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);
@@ -281,33 +287,61 @@ int main(int argc, char *argv[]) {
info.free();
fputs("</head>\n", f);
fputs("<body>\n", f);
- fputs("<pre>\n", f);
- if (f != stdout) {
+ if (!bbox) fputs("<pre>\n", f);
+ if (f != stdout && !bbox) { // if writing bbox, f remains open
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 (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);
+ fprintf(f," <word xMin=\"%f\" yMin=\"%f\" xMax=\"%f\"
yMax=\"%f\">%s</word>\n", xMinA, yMinA, xMaxA, yMaxA, (char *) word->getText());
+ }
+ 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;
_______________________________________________
poppler mailing list
[email protected]
http://lists.freedesktop.org/mailman/listinfo/poppler
