From 988350586f607c7a46bbb658a2abecfd004f41fb Mon Sep 17 00:00:00 2001
From: Khaled Hosny <khaledhosny@eglug.org>
Date: Sat, 18 Jun 2016 21:12:19 +0200
Subject: [PATCH 1/2] =?UTF-8?q?[tests]=20Workaround=20Python=202=20?=
 =?UTF-8?q?=E2=80=9Cnarrow=E2=80=9D=20builds?=
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The so-called Python 2 “narrow” builds support UCS2 only, this is a
workaround to allow unichr to work with any Unicode character in such
builds. This fixes Travis-CI failure as it has narrow Python 2 builds.

Copied from:
https://github.com/behdad/fonttools/blob/master/Lib/fontTools/misc/py23.py
---
 test/shaping/hb_test_tools.py | 38 ++++++++++++++++++++++++++++++++++-
 1 file changed, 37 insertions(+), 1 deletion(-)

diff --git a/test/shaping/hb_test_tools.py b/test/shaping/hb_test_tools.py
index 747699b87..747398299 100644
--- a/test/shaping/hb_test_tools.py
+++ b/test/shaping/hb_test_tools.py
@@ -7,7 +7,43 @@ from itertools import *
 diff_symbols = "-+=*&^%$#@!~/"
 diff_colors = ['red', 'green', 'blue']
 
-if sys.version_info[0] >= 3:
+try:
+	unichr = unichr
+
+	if sys.maxunicode < 0x10FFFF:
+		# workarounds for Python 2 "narrow" builds with UCS2-only support.
+
+		_narrow_unichr = unichr
+
+		def unichr(i):
+			"""
+			Return the unicode character whose Unicode code is the integer 'i'.
+			The valid range is 0 to 0x10FFFF inclusive.
+
+			>>> _narrow_unichr(0xFFFF + 1)
+			Traceback (most recent call last):
+			  File "<stdin>", line 1, in ?
+			ValueError: unichr() arg not in range(0x10000) (narrow Python build)
+			>>> unichr(0xFFFF + 1) == u'\U00010000'
+			True
+			>>> unichr(1114111) == u'\U0010FFFF'
+			True
+			>>> unichr(0x10FFFF + 1)
+			Traceback (most recent call last):
+			  File "<stdin>", line 1, in ?
+			ValueError: unichr() arg not in range(0x110000)
+			"""
+			try:
+				return _narrow_unichr(i)
+			except ValueError:
+				try:
+					padded_hex_str = hex(i)[2:].zfill(8)
+					escape_str = "\\U" + padded_hex_str
+					return escape_str.decode("unicode-escape")
+				except UnicodeDecodeError:
+					raise ValueError('unichr() arg not in range(0x110000)')
+
+except NameError:
 	unichr = chr
 
 class ColorFormatter:

From 07461d06d242cd5cfda7ccb891189f074a89b460 Mon Sep 17 00:00:00 2001
From: Kelvin <kelvinsthirteen@gmail.com>
Date: Sat, 18 Jun 2016 22:46:38 +0000
Subject: [PATCH 2/2] Use UTF-32  in Python sample

---
 src/sample.py | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/src/sample.py b/src/sample.py
index 19a4fdcbc..cfbc12265 100755
--- a/src/sample.py
+++ b/src/sample.py
@@ -20,6 +20,7 @@ def tounicode(s, encoding='utf-8'):
 
 fontdata = open (sys.argv[1], 'rb').read ()
 text = tounicode(sys.argv[2])
+codepoints = list(map(ord, text))
 # Need to create GLib.Bytes explicitly until this bug is fixed:
 # https://bugzilla.gnome.org/show_bug.cgi?id=729541
 blob = hb.glib_blob_create (GLib.Bytes.new (fontdata))
@@ -39,7 +40,7 @@ class Debugger(object):
 		return True
 debugger = Debugger()
 hb.buffer_set_message_func (buf, debugger.message, 1, 0)
-hb.buffer_add_utf8 (buf, text.encode('utf-8'), 0, -1)
+hb.buffer_add_utf32 (buf, codepoints, 0, len(codepoints))
 hb.buffer_guess_segment_properties (buf)
 
 hb.shape (font, buf, [])