X-Git-Url: https://git.donarmstrong.com/?a=blobdiff_plain;f=lily%2Fpdf-scheme.cc;fp=lily%2Fpdf-scheme.cc;h=e813e08ec327c25713bdccbb85f94778378238d1;hb=e90f0536f9be39ada0bef0aeb0d275dec3b2fb5b;hp=0000000000000000000000000000000000000000;hpb=a8c9e8a7ca320ab0df5fd32e717fd62cd7635ce6;p=lilypond.git

diff --git a/lily/pdf-scheme.cc b/lily/pdf-scheme.cc
new file mode 100644
index 0000000000..e813e08ec3
--- /dev/null
+++ b/lily/pdf-scheme.cc
@@ -0,0 +1,83 @@
+/*
+  This file is part of LilyPond, the GNU music typesetter.
+
+  Copyright (C) 2011 Reinhold Kainhofer <reinhold@kainhofer.com>
+
+  LilyPond is free software: you can redistribute it and/or modify
+  it under the terms of the GNU General Public License as published by
+  the Free Software Foundation, either version 3 of the License, or
+  (at your option) any later version.
+
+  LilyPond is distributed in the hope that it will be useful,
+  but WITHOUT ANY WARRANTY; without even the implied warranty of
+  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+  GNU General Public License for more details.
+
+  You should have received a copy of the GNU General Public License
+  along with LilyPond.  If not, see <http://www.gnu.org/licenses/>.
+*/
+
+#include <glib.h>
+using namespace std;
+
+#include "international.hh"
+#include "warn.hh"
+#include "lily-guile.hh"
+
+
+LY_DEFINE (ly_encode_string_for_pdf, "ly:encode-string-for-pdf",
+	   1, 0, 0, (SCM str),
+	   "Encode the given string to either Latin1 (which is a subset of"
+	   " the PDFDocEncoding) or if that's not possible to full UTF-16BE"
+	   " with Byte-Order-Mark (BOM).")
+{
+  LY_ASSERT_TYPE (scm_is_string, str, 1);
+  char *p = ly_scm2str0 (str);
+  char *g = NULL;
+  char const *charset="UTF-8"; // Input is ALWAYS UTF-8!
+  gsize bytes_written = 0;
+
+  /* First, try to convert to ISO-8859-1 (no encodings required). This will
+   * fail, if the string contains accented characters, so we do not check
+   * for errors. */
+  g = g_convert (p, -1, "ISO-8859-1", charset, 0, &bytes_written, 0);
+  /* If that fails, we have to resolve to full UTF-16BE */
+  if (!g) 
+    {
+      GError *e = NULL;
+      char *g_without_BOM = g_convert (p, -1,  "UTF-16BE", charset, 0, &bytes_written, &e);
+      if (e != NULL) 
+        {
+          warning (_f("Conversion of string `%s' to UTF-16be failed: %s", p, e->message));
+          g_error_free (e);
+        }
+      /* UTF-16BE allows/recommends a byte-order-mark (BOM) of two bytes 
+       * \xFE\xFF at the begin of the string. The pdfmark specification 
+       * requires it and depends on it to distinguish PdfDocEncoding from
+       * UTF-16BE. As g_convert does not automatically prepend this BOM 
+       * for UTF-16BE (only for UTF-16, which uses lower endian by default, 
+       * though), we have to prepend it manually. */
+      if (g_without_BOM) // conversion to UTF-16be might have failed (shouldn't!)
+        { 
+          g = new char[bytes_written+3];
+          char const *BOM = "\xFE\xFF";
+          strcpy (g, BOM);
+          memcpy (&g[2], g_without_BOM, bytes_written+1); // Copy string + \0
+          free (g_without_BOM);
+          bytes_written += 2;
+        }
+    }
+  free (p);
+
+  /* Convert back to SCM object and return it */
+  /* FIXME guile-2.0: With guile 2.0 the internal representation of a string
+   *                  has changed (char vector rather than binary bytes in 
+   *                  UTF-8). However, with guile 2.0, ly:encode-string-for-pdf
+   *                  is no longer needed and can be replaced by the new 
+   *                  (string->utf16 str 'big)
+   */
+  if (g) 
+    return scm_take_str (g, bytes_written); // scm_take_str eventually frees g!
+  else
+    return str;
+}