Add big endian support

scripts/make_data_assembly.py

Index: scripts/make_data_assembly.py
diff --git a/scripts/make_data_assembly.py b/scripts/make_data_assembly.py
new file mode 100755
index 0000000000000000000000000000000000000000..2981e3dd8fb10bf9cfb6d64ea959b734fcc6bdb5
--- /dev/null
+++ b/scripts/make_data_assembly.py
@@ -0,0 +1,74 @@
+#!/usr/bin/python2
+# Copyright 2016 The Chromium Authors. All rights reserved.

[jungshik at Google, 2016/05/18 20:51:24]

Sorry that I forgot to mention. Please, insert a new line between line 1 and
line 2 (Copyright...). 

[miran.karic, 2016/05/19 11:46:33]

Done.

+# Use of this source code is governed by a BSD-style license that can be
+# found in the LICENSE file.
+
+import binascii
+import sys
+
+if len(sys.argv) < 2:
+  sys.exit("Usage: %s icu_data_file [output_assembly_file]" % sys.argv[0])
+
+input_file = sys.argv[1]
+n = input_file.find(".dat")
+if n == -1:
+  sys.exit("%s is not an ICU .dat file." % input_file)
+
+if len(sys.argv) < 3:
+  output_file = input_file[0:n] + "_dat.S"
+else:
+  output_file = sys.argv[2]
+
+n = input_file.find("l.dat")
+if n == -1:

[jungshik at Google, 2016/05/18 20:51:24]

nit: if input_file.find("l.dat") == -1:

[miran.karic, 2016/05/19 11:46:33]

Done.

+  n = input_file.find("b.dat")
+  if n == -1:

[jungshik at Google, 2016/05/18 20:51:24]

same here

[miran.karic, 2016/05/19 11:46:33]

Done.

+    sys.exit("%s has no endianness marker." % input_file)
+  else:
+    step = 1;

[jungshik at Google, 2016/05/18 20:51:24]

You don't need 'else' here because of sys.exit() above. 

[miran.karic, 2016/05/19 11:46:33]

sys.exit() exits only if there is no 'l' or 'b' before ".dat" in the file name,
still need else to initialize step value for BE and other else for LE. Also
removed semicolons here.

+else:
+  step = -1;
+
+input_data = open(input_file, 'rb').read()
+n = input_data.find("icudt")
+if n == -1:

[jungshik at Google, 2016/05/18 20:51:24]

again, just |if input_data.find("icudt") == -1:| would be better.(imho) :-) 

[miran.karic, 2016/05/19 11:46:33]

Here I use n below to extract version number

+  sys.exit("Cannot find a version number in %s." % input_file)
+
+version_number = input_data[n + 5:n + 7]
+
+output = open(output_file, 'w')
+output.write(".globl icudt" + version_number + "_dat\n"
+             "\t.section .note.GNU-stack,\"\",%progbits\n"
+             "\t.section .rodata\n"
+             "\t.balign 16\n"
+             "#ifdef U_HIDE_DATA_SYMBOL\n"
+             "\t.hidden icudt" + version_number + "_dat\n"
+             "#endif\n"
+             "\t.type icudt" + version_number + "_dat,%object\n"
+             "icudt" + version_number + "_dat:\n")
+
+split = [binascii.hexlify(input_data[i:i + 4][::step]).upper().lstrip('0') \
+  for i in range(0, len(input_data), 4)]

[jungshik at Google, 2016/05/18 20:51:24]

nit: You don't need '\' at the end. 
Please, line up 'for i in' with |binascii.hex....|. 

[miran.karic, 2016/05/19 11:46:33]

Done.

+
+for i in range(len(split)):
+  if (len(split[i]) == 0):
+    value = '0'
+  elif (len(split[i]) == 1):
+    if not any((c in '123456789') for c in split[i]):
+      value = '0x0' + split[i]
+    else:
+      value = split[i]
+  elif (len(split[i]) % 2 == 1):
+    value = '0x0' + split[i]
+  else:
+    value = '0x' + split[i]
+
+  if (i % 32 == 0):
+    output.write("\n.long ")
+  else:
+    output.write(",")
+  output.write(value)
+
+output.write("\n")
+output.close()
+print "Generated " + output_file