Compile ICU for [P]NaCl

icu_data_to_c.py

Index: icu_data_to_c.py
diff --git a/icu_data_to_c.py b/icu_data_to_c.py
new file mode 100755
index 0000000000000000000000000000000000000000..dc10f4a208e11ffe74542cf3e2a29a4326e5b329
--- /dev/null
+++ b/icu_data_to_c.py
@@ -0,0 +1,45 @@
+#!/usr/bin/env python
+# Copyright 2013 The Chromium Authors. All rights reserved.
+# Use of this source code is governed by a BSD-style license that can be
+# found in the LICENSE file.
+
+# This scripts generates a compilable .c file from ICU data files. Currently
+# it's used to compile ICU for PNaCl. It's necessary because, unlike other
+# platforms, .S files can't be compiled on PNaCl.
+
+import struct
+import sys
+
+def main():
+  if len(sys.argv) != 3:
+    print "Usage: %s <input> <output>" % sys.argv[0]
+    return 1
+
+  input_file = file(sys.argv[1])
+  output_file = file(sys.argv[2], "w")
+
+  output_file.write(
+"""#include <stdint.h>
+#ifndef U_HIDE_DATA_SYMBOL
+__attribute__((visibility("default")))
+#endif

[Mark Mentovai, 2013/12/19 18:26:47]

#else __attribute__((visibility("hidden")))

[Sergey Ulanov, 2013/12/20 00:55:21]

Removed this script.

+uint32_t icudt46_dat[] = {

[Mark Mentovai, 2013/12/19 18:26:47]

This should absolutely 100% be const.

+""")
+  line_pos = 0
+  while True:
+    data = input_file.read(4096)
+    if len(data) == 0:
+      break
+    for pos in xrange(0, len(data), 4):
+      bytes = data[pos:pos+4]

[Mark Mentovai, 2013/12/19 18:26:47]

Uh-oh! If len(data) % 4 != 0, the last one of these will silently have fewer
than four bytes.

+      output_file.write(hex(struct.unpack("I", bytes)[0]) + ",")
+      line_pos += 1
+      if line_pos >= 8:

[Mark Mentovai, 2013/12/19 18:26:47]

Make this |if line_pos % 8 == 0:|. Then you can get rid of the |line_pos = 0|
reassignment on line 39.

+        output_file.write("\n")
+        line_pos = 0
+
+  output_file.write("\n};")
+  output_file.close()
+
+if __name__ == "__main__":
+  sys.exit(main())