[poppler] Re: [Patch] Info about document fonts
Marco Pesenti Gritti
mpgritti at gmail.com
Sat Jun 4 10:04:36 PDT 2005
Slightly updated patch, I implemented evince font properties page with this.
Marco
On 6/4/05, Marco Pesenti Gritti <mpgritti at gmail.com> wrote:
> Hi,
>
> here is a patch that allows to retrieve fonts information from the
> document. It's based on xpdf pdffonts code. It's not complete yet but
> if it make sense I'd like to check it in so that we start playing with
> the user interface in evince and see what we need more...
> Suggestions welcome, my c++/xpdf knowledge is not that great.
>
> Marco
>
-------------- next part --------------
? dump.txt
? slice.png
? glib/poppler-enums.c
? glib/poppler-enums.h
? poppler/FontInfo.cc
? poppler/FontInfo.h
Index: glib/poppler-document.cc
===================================================================
RCS file: /cvs/poppler/poppler/glib/poppler-document.cc,v
retrieving revision 1.17
diff -u -r1.17 poppler-document.cc
--- glib/poppler-document.cc 29 May 2005 14:59:34 -0000 1.17
+++ glib/poppler-document.cc 4 Jun 2005 17:02:14 -0000
@@ -26,6 +26,7 @@
#include <GfxState.h>
#include <SplashOutputDev.h>
#include <Stream.h>
+#include <FontInfo.h>
#include "poppler.h"
#include "poppler-private.h"
@@ -745,6 +746,92 @@
}
+struct _PopplerFontsIter
+{
+ PopplerDocument *document;
+ GooList *items;
+ int index;
+};
+
+GType
+poppler_fonts_iter_get_type (void)
+{
+ static GType our_type = 0;
+
+ if (our_type == 0)
+ our_type = g_boxed_type_register_static ("PopplerFontsIter",
+ (GBoxedCopyFunc) poppler_fonts_iter_copy,
+ (GBoxedFreeFunc) poppler_fonts_iter_free);
+
+ return our_type;
+}
+
+PopplerFontsIter *
+poppler_fonts_iter_copy (PopplerFontsIter *iter)
+{
+ PopplerFontsIter *new_iter;
+
+ g_return_val_if_fail (iter != NULL, NULL);
+
+ new_iter = g_new0 (PopplerFontsIter, 1);
+ *new_iter = *iter;
+ new_iter->document = (PopplerDocument *) g_object_ref (new_iter->document);
+
+ return new_iter;
+}
+
+PopplerFontsIter *
+poppler_fonts_iter_new (PopplerDocument *document)
+{
+ PopplerFontsIter *iter;
+ GooList *items;
+
+ items = FontInfo::scan(document->doc);
+ if (items == NULL)
+ return NULL;
+
+ iter = g_new0 (PopplerFontsIter, 1);
+ iter->document = (PopplerDocument *) g_object_ref (document);
+ iter->items = items;
+ iter->index = 0;
+
+ return iter;
+}
+
+const char *
+poppler_fonts_iter_get_name (PopplerFontsIter *iter)
+{
+ FontInfo *info;
+
+ info = (FontInfo *)iter->items->get (iter->index);
+
+ return info->getName()->getCString();
+}
+
+gboolean
+poppler_fonts_iter_next (PopplerFontsIter *iter)
+{
+ g_return_val_if_fail (iter != NULL, FALSE);
+
+ iter->index++;
+ if (iter->index >= iter->items->getLength())
+ return FALSE;
+
+ return TRUE;
+}
+
+void
+poppler_fonts_iter_free (PopplerFontsIter *iter)
+{
+ if (iter == NULL)
+ return;
+
+ deleteGooList (iter->items, FontInfo);
+
+ g_object_unref (iter->document);
+ g_free (iter);
+}
+
/**
* poppler_ps_file_new:
* @document: a #PopplerDocument
Index: glib/poppler-document.h
===================================================================
RCS file: /cvs/poppler/poppler/glib/poppler-document.h,v
retrieving revision 1.11
diff -u -r1.11 poppler-document.h
--- glib/poppler-document.h 23 May 2005 04:23:53 -0000 1.11
+++ glib/poppler-document.h 4 Jun 2005 17:02:15 -0000
@@ -103,6 +103,15 @@
PopplerAction *poppler_index_iter_get_action (PopplerIndexIter *iter);
gboolean poppler_index_iter_next (PopplerIndexIter *iter);
+/* Interface for getting the Fonts of a poppler_document */
+GType poppler_fonts_iter_get_type (void) G_GNUC_CONST;
+PopplerFontsIter *poppler_fonts_iter_new (PopplerDocument *document);
+PopplerFontsIter *poppler_fonts_iter_copy (PopplerFontsIter *iter);
+void poppler_fonts_iter_free (PopplerFontsIter *iter);
+
+const char *poppler_fonts_iter_get_name (PopplerFontsIter *iter);
+gboolean poppler_fonts_iter_next (PopplerFontsIter *iter);
+
/* Export to ps */
PopplerPSFile *poppler_ps_file_new (PopplerDocument *document,
const char *filename,
Index: glib/poppler.h
===================================================================
RCS file: /cvs/poppler/poppler/glib/poppler.h,v
retrieving revision 1.7
diff -u -r1.7 poppler.h
--- glib/poppler.h 11 May 2005 20:01:43 -0000 1.7
+++ glib/poppler.h 4 Jun 2005 17:02:15 -0000
@@ -45,6 +45,7 @@
typedef struct _PopplerDocument PopplerDocument;
typedef struct _PopplerIndexIter PopplerIndexIter;
+typedef struct _PopplerFontsIter PopplerFontsIter;
typedef struct _PopplerRectangle PopplerRectangle;
typedef struct _PopplerLinkMapping PopplerLinkMapping;
typedef struct _PopplerPage PopplerPage;
Index: glib/test-poppler-glib.c
===================================================================
RCS file: /cvs/poppler/poppler/glib/test-poppler-glib.c,v
retrieving revision 1.11
diff -u -r1.11 test-poppler-glib.c
--- glib/test-poppler-glib.c 29 May 2005 14:59:34 -0000 1.11
+++ glib/test-poppler-glib.c 4 Jun 2005 17:02:16 -0000
@@ -15,6 +15,7 @@
PopplerPageLayout layout;
PopplerPageMode mode;
PopplerViewerPreferences view_prefs;
+ PopplerFontsIter *fonts_iter;
GEnumValue *enum_value;
g_object_get (document,
@@ -53,6 +54,13 @@
g_print ("\tcreation date:\t%d\n", creation_date);
g_print ("\tmodified date:\t%d\n", mod_date);
+ g_print ("\tfonts:\n");
+ fonts_iter = poppler_fonts_iter_new (document);
+ do {
+ g_print ("\t\t\t%s\n", poppler_fonts_iter_get_name (fonts_iter));
+ } while (poppler_fonts_iter_next (fonts_iter));
+ poppler_fonts_iter_free (fonts_iter);
+
/* FIXME: print out the view prefs when we support it */
g_free (title);
Index: poppler/Makefile.am
===================================================================
RCS file: /cvs/poppler/poppler/poppler/Makefile.am,v
retrieving revision 1.6
diff -u -r1.6 Makefile.am
--- poppler/Makefile.am 27 Apr 2005 20:56:18 -0000 1.6
+++ poppler/Makefile.am 4 Jun 2005 17:02:17 -0000
@@ -92,6 +92,7 @@
Dict.h \
Error.h \
FontEncodingTables.h \
+ FontInfo.h \
Function.cc \
Function.h \
Gfx.h \
@@ -143,6 +144,7 @@
Dict.cc \
Error.cc \
FontEncodingTables.cc \
+ FontInfo.cc \
Function.cc \
Gfx.cc \
GfxFont.cc \
--- /dev/null 2005-06-04 19:35:04.067058504 +0200
+++ poppler/FontInfo.cc 2005-06-04 14:16:21.000000000 +0200
@@ -0,0 +1,163 @@
+#include <stdio.h>
+#include <stdlib.h>
+#include <stddef.h>
+#include <string.h>
+#include <math.h>
+#include "GlobalParams.h"
+#include "Error.h"
+#include "Object.h"
+#include "Dict.h"
+#include "GfxFont.h"
+#include "Annot.h"
+#include "PDFDoc.h"
+#include "config.h"
+#include "FontInfo.h"
+
+static char *fontTypeNames[] = {
+ "unknown",
+ "Type 1",
+ "Type 1C",
+ "Type 3",
+ "TrueType",
+ "CID Type 0",
+ "CID Type 0C",
+ "CID TrueType"
+};
+
+GooList *FontInfo::scan(PDFDoc *doc) {
+ GooList *result;
+ Page *page;
+ Dict *resDict;
+ Annots *annots;
+ Object obj1, obj2;
+ int pg, i;
+
+ result = new GooList();
+
+ for (pg = 1; pg <= doc->getNumPages(); ++pg) {
+ page = doc->getCatalog()->getPage(pg);
+ if ((resDict = page->getResourceDict())) {
+ scanFonts(resDict, doc, result);
+ }
+ annots = new Annots(doc->getXRef(), page->getAnnots(&obj1));
+ obj1.free();
+ for (i = 0; i < annots->getNumAnnots(); ++i) {
+ if (annots->getAnnot(i)->getAppearance(&obj1)->isStream()) {
+ obj1.streamGetDict()->lookup("Resources", &obj2);
+ if (obj2.isDict()) {
+ scanFonts(obj2.getDict(), doc, result);
+ }
+ obj2.free();
+ }
+ obj1.free();
+ }
+ delete annots;
+ }
+
+ return result;
+}
+
+void FontInfo::scanFonts(Dict *resDict, PDFDoc *doc, GooList *fontsList) {
+ Object obj1, obj2, xObjDict, xObj, resObj;
+ Ref r;
+ GfxFontDict *gfxFontDict;
+ GfxFont *font;
+ int i;
+
+ // scan the fonts in this resource dictionary
+ gfxFontDict = NULL;
+ resDict->lookupNF("Font", &obj1);
+ if (obj1.isRef()) {
+ obj1.fetch(doc->getXRef(), &obj2);
+ if (obj2.isDict()) {
+ r = obj1.getRef();
+ gfxFontDict = new GfxFontDict(doc->getXRef(), &r, obj2.getDict());
+ }
+ obj2.free();
+ } else if (obj1.isDict()) {
+ gfxFontDict = new GfxFontDict(doc->getXRef(), NULL, obj1.getDict());
+ }
+ if (gfxFontDict) {
+ for (i = 0; i < gfxFontDict->getNumFonts(); ++i) {
+ if ((font = gfxFontDict->getFont(i))) {
+ Ref fontRef = *font->getID();
+ GBool already_seen = gFalse;
+
+ // check for an already-seen font
+ for (int k = 0; k < fontsList->getLength(); ++k) {
+ FontInfo *info = (FontInfo *)fontsList->get(k);
+ if (fontRef.num == info->fontRef.num && fontRef.gen == info->fontRef.gen) {
+ already_seen = gTrue;
+ }
+ }
+
+ // add this font to the list
+ if (!already_seen) {
+ fontsList->append(new FontInfo(font, doc));
+ }
+ }
+ }
+ delete gfxFontDict;
+ }
+ obj1.free();
+
+ // recursively scan any resource dictionaries in objects in this
+ // resource dictionary
+ resDict->lookup("XObject", &xObjDict);
+ if (xObjDict.isDict()) {
+ for (i = 0; i < xObjDict.dictGetLength(); ++i) {
+ xObjDict.dictGetVal(i, &xObj);
+ if (xObj.isStream()) {
+ xObj.streamGetDict()->lookup("Resources", &resObj);
+ if (resObj.isDict()) {
+ scanFonts(resObj.getDict(), doc, fontsList);
+ }
+ resObj.free();
+ }
+ xObj.free();
+ }
+ }
+ xObjDict.free();
+}
+
+FontInfo::FontInfo(GfxFont *font, PDFDoc *doc) {
+ Ref embRef;
+ Object fontObj, toUnicodeObj;
+ int i;
+
+ fontRef = *font->getID();
+
+ // font name
+ name = font->getOrigName()->copy();
+
+ // check for an embedded font
+ if (font->getType() == fontType3) {
+ emb = gTrue;
+ } else {
+ emb = font->getEmbeddedFontID(&embRef);
+ }
+
+ // look for a ToUnicode map
+ hasToUnicode = gFalse;
+ if (doc->getXRef()->fetch(fontRef.num, fontRef.gen, &fontObj)->isDict()) {
+ hasToUnicode = fontObj.dictLookup("ToUnicode", &toUnicodeObj)->isStream();
+ toUnicodeObj.free();
+ }
+ fontObj.free();
+
+ // check for a font subset name: capital letters followed by a '+'
+ // sign
+ subset = gFalse;
+ if (name) {
+ for (i = 0; i < name->getLength(); ++i) {
+ if (name->getChar(i) < 'A' || name->getChar(i) > 'Z') {
+ break;
+ }
+ }
+ subset = i > 0 && i < name->getLength() && name->getChar(i) == '+';
+ }
+}
+
+FontInfo::~FontInfo() {
+ delete name;
+}
--- /dev/null 2005-06-04 19:35:04.067058504 +0200
+++ poppler/FontInfo.h 2005-06-04 14:20:43.000000000 +0200
@@ -0,0 +1,32 @@
+#ifndef FONT_INFO_H
+#define FONT_INFO_H
+
+#include "goo/gtypes.h"
+#include "goo/GooList.h"
+
+class FontInfo {
+public:
+
+ // Constructor.
+ FontInfo(GfxFont *fontA, PDFDoc *doc);
+ // Destructor.
+ ~FontInfo();
+
+ static GooList *scan(PDFDoc *doc);
+
+ GooString *getName() { return name; };
+ GBool getEmbedded() { return emb; };
+ GBool getSubset() { return subset; };
+ GBool getToUnicode() { return hasToUnicode; };
+
+private:
+ GooString *name;
+ GBool emb;
+ GBool subset;
+ GBool hasToUnicode;
+ Ref fontRef;
+
+ static void FontInfo::scanFonts(Dict *resDict, PDFDoc *doc, GooList *fontsList);
+};
+
+#endif
More information about the poppler
mailing list