[poppler] poppler/GfxFont.cc poppler/UnicodeTypeTable.cc poppler/UnicodeTypeTable.h

[Albert Astals Cid]

 poppler/GfxFont.cc          |   14 +++++++++++++-
 poppler/UnicodeTypeTable.cc |    9 +++++++++
 poppler/UnicodeTypeTable.h  |    3 +++
 3 files changed, 25 insertions(+), 1 deletion(-)

New commits:
commit 3361564364a1799fc3d6c6df9f208c5531c407dc
Author: Adrian Johnson <ajohnson at redneon.com>
Date:   Tue Feb 21 22:20:02 2012 +0100

    Expand glyph name ligatures such as "ff", "ffi" etc to normal form
    
    Bug 7002

diff --git a/poppler/GfxFont.cc b/poppler/GfxFont.cc
index 4e29c36..cc0f092 100644
--- a/poppler/GfxFont.cc
+++ b/poppler/GfxFont.cc
@@ -26,7 +26,7 @@
 // Copyright (C) 2009 Peter Kerzum <kerzum at yandex-team.ru>
 // Copyright (C) 2009, 2010 David Benjamin <davidben at mit.edu>
 // Copyright (C) 2011 Axel Strübing <axel.struebing at freenet.de>
-// Copyright (C) 2011 Adrian Johnson <ajohnson at redneon.com>
+// Copyright (C) 2011, 2012 Adrian Johnson <ajohnson at redneon.com>
 //
 // 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
@@ -55,6 +55,7 @@
 #include "CharCodeToUnicode.h"
 #include "FontEncodingTables.h"
 #include "BuiltinFontTables.h"
+#include "UnicodeTypeTable.h"
 #include <fofi/FoFiIdentifier.h>
 #include <fofi/FoFiType1.h>
 #include <fofi/FoFiType1C.h>
@@ -1228,6 +1229,17 @@ Gfx8BitFont::Gfx8BitFont(XRef *xref, const char *tagA, Ref idA, GooString *nameA
   // construct the char code -> Unicode mapping object
   ctu = CharCodeToUnicode::make8BitToUnicode(toUnicode);
 
+  // pass 1a: Expand ligatures in the Alphabetic Presentation Form
+  // block (eg "fi", "ffi") to normal form
+  for (code = 0; code < 256; ++code) {
+    if (unicodeIsAlphabeticPresentationForm(toUnicode[code])) {
+      Unicode *normalized = unicodeNormalizeNFKC(&toUnicode[code], 1, &len, NULL);
+      if (len > 1)
+        ctu->setMapping((CharCode)code, normalized, len);
+      gfree(normalized);
+    }
+  }
+
   // pass 2: try to fill in the missing chars, looking for ligatures, numeric
   // references and variants
   if (missing) {
diff --git a/poppler/UnicodeTypeTable.cc b/poppler/UnicodeTypeTable.cc
index d620025..721af9d 100644
--- a/poppler/UnicodeTypeTable.cc
+++ b/poppler/UnicodeTypeTable.cc
@@ -16,6 +16,7 @@
 // Copyright (C) 2006, 2007 Ed Catmur <ed at catmur.co.uk>
 // Copyright (C) 2007 Jeff Muizelaar <jeff at infidigm.net>
 // Copyright (C) 2008 Albert Astals Cid <aacid at kde.org>
+// Copyright (C) 2012 Adrian Johnson <ajohnson at redneon.com>
 //
 // 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
@@ -962,6 +963,14 @@ GBool unicodeTypeAlphaNum(Unicode c) {
   return t == 'L' || t == 'R' || t == '#';
 }
 
+#define UNICODE_ALPHABETIC_PRESENTATION_BLOCK_BEGIN 0xFB00
+#define UNICODE_ALPHABETIC_PRESENTATION_BLOCK_END   0xFB4F
+
+GBool unicodeIsAlphabeticPresentationForm(Unicode c) {
+  return c >= UNICODE_ALPHABETIC_PRESENTATION_BLOCK_BEGIN
+    && c <= UNICODE_ALPHABETIC_PRESENTATION_BLOCK_END;
+}
+
 Unicode unicodeToUpper(Unicode c) {
   int i;
 
diff --git a/poppler/UnicodeTypeTable.h b/poppler/UnicodeTypeTable.h
index 0dfbd98..869aad9 100644
--- a/poppler/UnicodeTypeTable.h
+++ b/poppler/UnicodeTypeTable.h
@@ -14,6 +14,7 @@
 // under GPL version 2 or later
 //
 // Copyright (C) 2006 Ed Catmur <ed at catmur.co.uk>
+// Copyright (C) 2012 Adrian Johnson <ajohnson at redneon.com>
 //
 // 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
@@ -33,6 +34,8 @@ extern GBool unicodeTypeNum(Unicode c);
 
 extern GBool unicodeTypeAlphaNum(Unicode c);
 
+extern GBool unicodeIsAlphabeticPresentationForm(Unicode c);
+
 extern Unicode unicodeToUpper(Unicode c);
 
 extern Unicode *unicodeNormalizeNFKC(Unicode *in, int len,