From 5a18fc83e6abb29bd795b8a65dc9a320fb20be64 Mon Sep 17 00:00:00 2001
From: Behdad Esfahbod <behdad@behdad.org>
Date: Sun, 19 Apr 2015 03:50:55 -0700
Subject: [PATCH] Add getEncoding() to cmap subtables

---
 Lib/fontTools/ttLib/tables/_c_m_a_p.py      | 13 +++++++
 Lib/fontTools/ttLib/tables/_c_m_a_p_test.py | 40 +++++++++++++++++++++
 2 files changed, 53 insertions(+)
 create mode 100644 Lib/fontTools/ttLib/tables/_c_m_a_p_test.py

diff --git a/Lib/fontTools/ttLib/tables/_c_m_a_p.py b/Lib/fontTools/ttLib/tables/_c_m_a_p.py
index 29f5a1977..9f94035eb 100644
--- a/Lib/fontTools/ttLib/tables/_c_m_a_p.py
+++ b/Lib/fontTools/ttLib/tables/_c_m_a_p.py
@@ -1,6 +1,7 @@
 from __future__ import print_function, division, absolute_import
 from fontTools.misc.py23 import *
 from fontTools.misc.textTools import safeEval, readHex
+from fontTools.misc.encodingTools import getEncoding
 from fontTools.ttLib import getSearchRange
 from fontTools.unicode import Unicode
 from . import DefaultTable
@@ -139,6 +140,18 @@ class CmapSubtable(object):
 		writer.endtag(self.__class__.__name__)
 		writer.newline()
 
+	def getEncoding(self, default=None):
+		"""Returns the Python encoding name for this cmap subtable based on its platformID,
+		platEncID, and language.  If encoding for these values is not known, by default
+		None is returned.  That can be overriden by passing a value to the default
+		argument.
+
+		Note that if you want to choose a "preferred" cmap subtable, most of the time
+		self.isUnicode() is what you want as that one only returns true for the modern,
+		commonly used, Unicode-compatible triplets, not the legacy ones.
+		"""
+		return getEncoding(self.platformID, self.platEncID, self.language, default)
+
 	def isUnicode(self):
 		return (self.platformID == 0 or
 			(self.platformID == 3 and self.platEncID in [0, 1, 10]))
diff --git a/Lib/fontTools/ttLib/tables/_c_m_a_p_test.py b/Lib/fontTools/ttLib/tables/_c_m_a_p_test.py
new file mode 100644
index 000000000..1ae5202b7
--- /dev/null
+++ b/Lib/fontTools/ttLib/tables/_c_m_a_p_test.py
@@ -0,0 +1,40 @@
+from __future__ import print_function, division, absolute_import, unicode_literals
+from fontTools.misc.py23 import *
+import unittest
+from ._c_m_a_p import CmapSubtable
+
+class CmapSubtableTest(unittest.TestCase):
+
+	def makeSubtable(self, platformID, platEncID, langID):
+		subtable = CmapSubtable(None)
+		subtable.platformID, subtable.platEncID, subtable.language = (platformID, platEncID, langID)
+		return subtable
+
+	def test_toUnicode_utf16be(self):
+		subtable = self.makeSubtable(0, 2, 7)
+		self.assertEqual("utf-16be", subtable.getEncoding())
+		self.assertEqual(True, subtable.isUnicode())
+
+	def test_toUnicode_macroman(self):
+		subtable = self.makeSubtable(1, 0, 7)  # MacRoman
+		self.assertEqual("mac-roman", subtable.getEncoding())
+		self.assertEqual(False, subtable.isUnicode())
+
+	def test_toUnicode_macromanian(self):
+		subtable = self.makeSubtable(1, 0, 37)  # Mac Romanian
+		self.assertNotEqual(None, subtable.getEncoding())
+		self.assertEqual(False, subtable.isUnicode())
+
+	def test_extended_mac_encodings(self):
+		subtable = self.makeSubtable(1, 1, 0) # Mac Japanese
+		self.assertNotEqual(None, subtable.getEncoding())
+		self.assertEqual(False, subtable.isUnicode())
+
+	def test_extended_unknown(self):
+		subtable = self.makeSubtable(10, 11, 12)
+		self.assertEqual(subtable.getEncoding(), None)
+		self.assertEqual(subtable.getEncoding("ascii"), "ascii")
+		self.assertEqual(subtable.getEncoding(default="xyz"), "xyz")
+
+if __name__ == "__main__":
+	unittest.main()