From 31131d377df4f3a5aa49c10e34d5bd2b9b60e5de Mon Sep 17 00:00:00 2001
From: Adrian Johnson <ajohnson@redneon.com>
Date: Sun, 19 Feb 2012 21:31:05 +1030
Subject: [PATCH] Expand glyph name ligatures such as "ff", "ffi" etc to
 normal form

Bug 7002
---
 poppler/GfxFont.cc          |   12 ++++++++++++
 poppler/UnicodeTypeTable.cc |    8 ++++++++
 poppler/UnicodeTypeTable.h  |    2 ++
 3 files changed, 22 insertions(+), 0 deletions(-)

diff --git a/poppler/GfxFont.cc b/poppler/GfxFont.cc
index 4e29c36..3125093 100644
--- a/poppler/GfxFont.cc
+++ b/poppler/GfxFont.cc
@@ -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..98e04a7 100644
--- a/poppler/UnicodeTypeTable.cc
+++ b/poppler/UnicodeTypeTable.cc
@@ -962,6 +962,14 @@ 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..c3906d8 100644
--- a/poppler/UnicodeTypeTable.h
+++ b/poppler/UnicodeTypeTable.h
@@ -33,6 +33,8 @@ 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, 
-- 
1.7.5.4