Hi,
I implemented a patch which supports CJK fonts in the postscript output
device and on Windows platforms in general. It consists mainly of three
parts:
1. Adapt bug fix for bug 11413 to the postscript device
2. A small bug fix when locateFont doesn't find a suitable font and
returns a null pointer
3. CJK substitute implementation on WIndows platforms.
to 1.:
Adapting the implementation of the bug fix for splash and cairo to the
postscript device was quite easy. But my first proofs of the output with
ghostscript 8.71 shows some regressions where the CJK chars have a
smaller height than the default square of the font. But the "48" in the
output of bug-poppler11413.pdf which is set in a "normal" font but
rotated was at the right position. Then I stepped to ghostscript 9.04,
and now the CJK chars were shown correctly, but the 48 was positioned
wrong. But because of these different tests I think that it is still a
problem in ghostscript when using a mix of CJK fonts and "normal" fonts.
BTW, also Acrobat X distiller has problems with the position of the "48"!
to 2.:
On my first tests with PDF which uses non embedded CJK fonts on Windows
I got crashes. Reason for it was that GlobalParamWin returns Helvetica,
which is not a CID font, but locateFont accepts here only CID fonts and
therefore returns a NULL pointer. I first fixed that and then decided to
return as default MS Mincho if a CID font is expected.
to 3.:
When You install ghostscript on WIndows You're able to switch on CJK
support. This will create a cidfmap file in the gs-lib directory. The
ps file which creates it (mkcidfm.ps) runs over the windows font
directory and tries to create a suitable substitution table for missing
CJK fonts. The cidfmap file is more or less PDF like, so it's quite easy
to parse it with our parser and create a substitution table in
GlobalParamsWin and use that table. But I expect it in the poppler data
dir instead of searching for ghostscript installation. If it is not
there, it always returns the default CID font of point 2.
You can either copy it from the gs lib directory or create it with the
ghostscript tool calling
gswin32c -q -dBATCH -sFONTDIR=<windows font directory>
-sCIDFMAP=<popper data dir>/cidfmap mkcidfm.ps
To clearify the format of cidfmap I attach the file produced on my
installation. Keep care: I have not a default windows installation with
windows on c:/windows, my windows installation is on drive f!
Cheers,
Thomas
diff --git a/poppler/GlobalParams.cc b/poppler/GlobalParams.cc
index 72448bf..53aaebe 100644
--- a/poppler/GlobalParams.cc
+++ b/poppler/GlobalParams.cc
@@ -550,6 +550,7 @@ GlobalParams::GlobalParams(const char *customPopplerDataDir)
#ifdef _WIN32
// baseDir will be set by a call to setBaseDir
baseDir = new GooString();
+ substFiles = new GooHash(gTrue);
#else
baseDir = appendToPath(getHomeDir(), ".xpdf");
#endif
@@ -787,6 +788,9 @@ GlobalParams::~GlobalParams() {
deleteGooHash(fontFiles, GooString);
deleteGooList(fontDirs, GooString);
deleteGooHash(ccFontFiles, GooString);
+#ifdef _WIN32
+ deleteGooHash(substFiles, GooString);
+#endif
delete sysFonts;
if (psFile) {
delete psFile;
diff --git a/poppler/GlobalParams.h b/poppler/GlobalParams.h
index 7e23cff..dbefae3 100644
--- a/poppler/GlobalParams.h
+++ b/poppler/GlobalParams.h
@@ -289,6 +289,7 @@ private:
GooList *toUnicodeDirs; // list of ToUnicode CMap dirs
[GooString]
#ifdef _WIN32
GBool baseFontsInitialized;
+ GooHash *substFiles; // windows font substitutes (for CID fonts)
#endif
GooHash *fontFiles; // font files: font name mapped to path
// [GString]
diff --git a/poppler/GlobalParamsWin.cc b/poppler/GlobalParamsWin.cc
index c62e2cd..3a454ab 100644
--- a/poppler/GlobalParamsWin.cc
+++ b/poppler/GlobalParamsWin.cc
@@ -40,6 +40,11 @@ description for all fonts available in Windows. That's how
MuPDF works.
#include "FontEncodingTables.h"
#include "GlobalParams.h"
#include "GfxFont.h"
+#include <sys/stat.h>
+#include "Object.h"
+#include "Stream.h"
+#include "Lexer.h"
+#include "Parser.h"
#if MULTITHREADED
# define lockGlobalParams gLockMutex(&mutex)
@@ -58,6 +63,7 @@ description for all fonts available in Windows. That's how
MuPDF works.
#endif
#define DEFAULT_SUBSTITUTE_FONT "Helvetica"
+#define DEFAULT_CID_FONT "MS-Mincho"
static struct {
const char *name;
@@ -147,7 +153,8 @@ static struct {
{"Georgia-Bold", NULL, "georgiab.ttf"},
{"Georgia-Italic", NULL, "georgiai.ttf"},
{"Georgia-BoldItalic", NULL, "georgiaz.ttf"},
-
+ // default CID font:
+ {"MS-Mincho", NULL, "msmincho.ttf"},
{NULL}
};
@@ -346,6 +353,12 @@ SysFontInfo *SysFontList::makeWindowsFont(char *name, int
fontNum,
void GlobalParams::setupBaseFonts(char * dir)
{
+ const char *dataRoot = popplerDataDir ? popplerDataDir :
POPPLER_DATADIR;
+ GooString *fileName = NULL;
+ struct stat buf;
+ FILE *file;
+ int size = 0;
+
if (baseFontsInitialized)
return;
baseFontsInitialized = true;
@@ -381,20 +394,85 @@ void GlobalParams::setupBaseFonts(char * dir)
if (winFontDir[0]) {
sysFonts->scanWindowsFonts(new GooString(winFontDir));
}
+
+ fileName = new GooString(dataRoot);
+ fileName->append("/cidfmap");
+ if (stat(fileName->getCString(), &buf) == 0) {
+ size = buf.st_size;
+ }
+ // try to open file
+#ifdef VMS
+ file = fopen(fileName->getCString(), "rb", "ctx=stm");
+#else
+ file = fopen(fileName->getCString(), "rb");
+#endif
+
+ if (file != NULL) {
+ Parser *parser;
+ Object obj1, obj2;
+
+ obj1.initNull();
+ parser = new Parser(NULL,
+ new Lexer(NULL,
+ new FileStream(file, 0, gFalse, size, &obj1)),
+ gTrue);
+ obj1.free();
+ parser->getObj(&obj1);
+ while (!obj1.isEOF()) {
+ parser->getObj(&obj2);
+ if (obj1.isName()) {
+ // Substitutions
+ if (obj2.isDict()) {
+ Object obj3;
+ obj2.getDict()->lookup("Path", &obj3);
+ if (obj3.isString())
+ addFontFile(new
GooString(obj1.getName()), obj3.getString()->copy());
+ obj3.free();
+ // Aliases
+ } else if (obj2.isName()) {
+ substFiles->add(new
GooString(obj1.getName()), new GooString(obj2.getName()));
+ }
+ }
+ obj2.free();
+ obj1.free();
+ parser->getObj(&obj1);
+ // skip trailing ';'
+ while (obj1.isCmd(";")) {
+ obj1.free();
+ parser->getObj(&obj1);
+ }
+ }
+ fclose(file);
+ delete parser;
+ }
}
-static char *findSubstituteName(const char *origName)
+static char *findSubstituteName(GfxFont *font, GooHash *substFiles, const char
*origName)
{
assert(origName);
if (!origName) return NULL;
+ GooString *name2 = new GooString(origName);
+ int n = strlen(origName);
+ // remove trailing "-Identity-H"
+ if (n > 11 && !strcmp(name2->getCString() + n - 11, "-Identity-H")) {
+ name2->del(n - 11, 11);
+ n -= 11;
+ }
+ GooString *substName = (GooString *)substFiles->lookup(name2);
+ if (substName != NULL) {
+ delete name2;
+ return substName->getCString();
+ }
+
/* TODO: try to at least guess bold/italic/bolditalic from the name */
- return DEFAULT_SUBSTITUTE_FONT;
+ delete name2;
+ return (font->isCIDFont()) ? DEFAULT_CID_FONT: DEFAULT_SUBSTITUTE_FONT;
}
/* Windows implementation of external font matching code */
GooString *GlobalParams::findSystemFontFile(GfxFont *font,
SysFontType *type,
- int *fontNum, GooString *
/*substituteFontName*/) {
+ int *fontNum, GooString
*substituteFontName) {
SysFontInfo *fi;
GooString *path = NULL;
GooString *fontName = font->getName();
@@ -406,14 +484,21 @@ GooString *GlobalParams::findSystemFontFile(GfxFont *font,
*type = fi->type;
*fontNum = fi->fontNum;
} else {
- GooString *substFontName = new
GooString(findSubstituteName(fontName->getCString()));
+ GooString *substFontName = new GooString(findSubstituteName(font,
substFiles, fontName->getCString()));
+ GooString *path2 = NULL;
error(errSyntaxError, -1, "Couldn't find a font for '{0:t}', subst is
'{1:t}'", fontName, substFontName);
- if ((fi = sysFonts->find(substFontName, gFalse))) {
- path = fi->path->copy();
- *type = fi->type;
- *fontNum = fi->fontNum;
- }
- }
+ if ((path2 = (GooString *)fontFiles->lookup(substFontName))) {
+ path = new GooString(path2);
+ if (substituteFontName)
+ substituteFontName->Set(path->getCString());
+ if (!strcasecmp(path->getCString() + path->getLength() - 4,
".ttc")) {
+ *type = sysFontTTC;
+ } else {
+ *type = sysFontTTF;
+ }
+ *fontNum = 0;
+ }
+ }
unlockGlobalParams;
return path;
}
diff --git a/poppler/PSOutputDev.cc b/poppler/PSOutputDev.cc
index 0c48b5a..1d0f7f2 100644
--- a/poppler/PSOutputDev.cc
+++ b/poppler/PSOutputDev.cc
@@ -1816,6 +1816,7 @@ void PSOutputDev::setupFont(GfxFont *font, Dict
*parentResDict) {
setupType3Font(font, psName, parentResDict);
} else {
fontLoc = font->locateFont(xref, gTrue);
+ if (fontLoc != NULL) {
switch (fontLoc->locType) {
case gfxFontLocEmbedded:
switch (fontLoc->fontType) {
@@ -1887,6 +1888,7 @@ void PSOutputDev::setupFont(GfxFont *font, Dict
*parentResDict) {
psName = fontLoc->path->copy();
break;
}
+ }
if (!psName) {
if (font->isCIDFont()) {
@@ -2364,9 +2366,6 @@ void PSOutputDev::setupExternalCIDTrueTypeFont(GfxFont
*font,
FoFiTrueType *ffTT;
int *codeToGID;
int codeToGIDLen;
- CharCodeToUnicode *ctu;
- Unicode *uBuf;
- int cmap, code;
// beginning comment
writePSFmt("%%BeginResource: font {0:t}\n", psName);
@@ -2381,54 +2380,37 @@ void PSOutputDev::setupExternalCIDTrueTypeFont(GfxFont
*font,
// check for embedding permission
if (ffTT->getEmbeddingRights() >= 1) {
- // create a CID-to-GID mapping, via Unicode
- if ((ctu = ((GfxCIDFont *)font)->getToUnicode())) {
- // look for a Unicode cmap
- for (cmap = 0; cmap < ffTT->getNumCmaps(); ++cmap) {
- if ((ffTT->getCmapPlatform(cmap) == 3 &&
- ffTT->getCmapEncoding(cmap) == 1) ||
- ffTT->getCmapPlatform(cmap) == 0) {
- break;
- }
- }
- if (cmap < ffTT->getNumCmaps()) {
- // map CID -> Unicode -> GID
- codeToGIDLen = ctu->getLength();
- codeToGID = (int *)gmallocn(codeToGIDLen, sizeof(int));
- for (code = 0; code < codeToGIDLen; ++code) {
- int n = ctu->mapToUnicode(code, &uBuf);
- if (n > 0) {
- codeToGID[code] = ffTT->mapCodeToGID(cmap, uBuf[0]);
- } else {
- codeToGID[code] = 0;
- }
- }
- if (ffTT->isOpenTypeCFF()) {
- ffTT->convertToCIDType0(psName->getCString(),
- codeToGID, codeToGIDLen,
- outputFunc, outputStream);
- } else if (globalParams->getPSLevel() >= psLevel3) {
- // Level 3: use a CID font
- ffTT->convertToCIDType2(psName->getCString(),
- codeToGID, codeToGIDLen,
- needVerticalMetrics,
- outputFunc, outputStream);
- } else {
- // otherwise: use a non-CID composite font
- ffTT->convertToType0(psName->getCString(),
- codeToGID, codeToGIDLen,
- needVerticalMetrics,
- outputFunc, outputStream);
- }
- gfree(codeToGID);
- }
- ctu->decRefCnt();
- } else {
- error(errSyntaxError, -1,
- "Couldn't find a mapping to Unicode for font '{0:s}'",
- font->getName() ? font->getName()->getCString() : "(unnamed)");
- }
- } else {
+ codeToGID = NULL;
+ codeToGIDLen = 0;
+ if (((GfxCIDFont *)font)->getCIDToGID()) {
+ codeToGIDLen = ((GfxCIDFont *)font)->getCIDToGIDLen();
+ if (codeToGIDLen) {
+ codeToGID = (int *)gmallocn(codeToGIDLen,
sizeof(int));
+ memcpy(codeToGID, ((GfxCIDFont
*)font)->getCIDToGID(),
+ codeToGIDLen * sizeof(int));
+ }
+ } else {
+ codeToGID = ((GfxCIDFont
*)font)->getCodeToGIDMap(ffTT, &codeToGIDLen);
+ }
+ if (ffTT->isOpenTypeCFF()) {
+ ffTT->convertToCIDType0(psName->getCString(),
+ codeToGID, codeToGIDLen,
+ outputFunc, outputStream);
+ } else if (globalParams->getPSLevel() >= psLevel3) {
+ // Level 3: use a CID font
+ ffTT->convertToCIDType2(psName->getCString(),
+ codeToGID, codeToGIDLen,
+ needVerticalMetrics,
+ outputFunc, outputStream);
+ } else {
+ // otherwise: use a non-CID composite font
+ ffTT->convertToType0(psName->getCString(),
+ codeToGID, codeToGIDLen,
+ needVerticalMetrics,
+ outputFunc, outputStream);
+ }
+ gfree(codeToGID);
+ } else {
error(errSyntaxError, -1,
"TrueType font '%s' does not allow embedding",
font->getName() ? font->getName()->getCString() : "(unnamed)");
%!
% cidfmap generated automatically by mkcidfm.ps from fonts found in
% F:/WINDOWS/Fonts
% Substitutions
/ArialUnicodeMS-CNS << /SubfontID 0 /CSI [(CNS1) 2] /Path
(F:/WINDOWS/Fonts/arialuni.ttf) /FileType /TrueType >> ;
/ArialUnicodeMS-KR << /SubfontID 0 /CSI [(Korea1) 3] /Path
(F:/WINDOWS/Fonts/arialuni.ttf) /FileType /TrueType >> ;
/ArialUnicodeMS-GB << /SubfontID 0 /CSI [(GB1) 2] /Path
(F:/WINDOWS/Fonts/arialuni.ttf) /FileType /TrueType >> ;
/MS-Mincho-oldttf << /SubfontID 0 /CSI [(Japan1) 3] /Path
(F:/WINDOWS/Fonts/msmincho.ttf) /FileType /TrueType >> ;
/ArialUnicodeMS-JP << /SubfontID 0 /CSI [(Japan1) 3] /Path
(F:/WINDOWS/Fonts/arialuni.ttf) /FileType /TrueType >> ;
% Aliases
/Ryumin-Medium /ArialUnicodeMS-JP ;
/AdobeHeitiStd-Regular /ArialUnicodeMS-GB ;
/HeiseiKakuGo-W5 /ArialUnicodeMS-JP ;
/AdobeMingStd-Light /ArialUnicodeMS-CNS ;
/MKai-Medium /ArialUnicodeMS-CNS ;
/MHei-Medium /ArialUnicodeMS-CNS ;
/MSung-Light /ArialUnicodeMS-CNS ;
/HYRGoThic-Medium /ArialUnicodeMS-KR ;
/GothicBBB-Medium /ArialUnicodeMS-JP ;
/AdobeSongStd-Light /ArialUnicodeMS-GB ;
/AdobeMyungjoStd-Medium /ArialUnicodeMS-KR ;
/HYSMyeongJo-Medium /ArialUnicodeMS-KR ;
/HYGoThic-Medium /ArialUnicodeMS-KR ;
/STSong-Light /ArialUnicodeMS-GB ;
/STKaiti-Regular /ArialUnicodeMS-GB ;
/KozMinPr6N-Regular /ArialUnicodeMS-JP ;
/STHeiti-Regular /ArialUnicodeMS-GB ;
/STFangsong-Light /ArialUnicodeMS-GB ;
/MSung-Medium /ArialUnicodeMS-CNS ;
/Ryumin-Light /ArialUnicodeMS-JP ;
/HeiseiMin-W3 /ArialUnicodeMS-JP ;
_______________________________________________
poppler mailing list
[email protected]
http://lists.freedesktop.org/mailman/listinfo/poppler
