python: Rework bytes/unicode string handling

In both Python 2 and 3, opening a file without specifying the mode will
open it for reading in text mode ('r').

On Python 2, the read() method of a file object opened in mode 'r' will
return byte strings, while on Python 3 it will return unicode strings.

Explicitly specifying the binary mode ('rb') then decoding the byte
string means we always handle unicode strings on both Python 2 and 3.

Which in turns means all re.match(line) will return unicode strings as
well.

If we also make expandCString return unicode strings, we don't need the
call to the unicode() constructor any more.

We were using the ugettext() method because it always returns unicode
strings in Python 2, contrarily to the gettext() one which returns
byte strings. The ugettext() method doesn't exist on Python 3, so we
must use the right method on each version of Python.

The last hurdles are that Python 3 doesn't let us concatenate unicode
and byte strings directly, and that Python 2's stdout wants encoded byte
strings while Python 3's want unicode strings.

With these changes, the script gives the same output on both Python 2
and 3.

Signed-off-by: Mathieu Bridon <bochecha@daitauha.fr>
Reviewed-by: Dylan Baker <dylan@pnwbakers.com>

diff --git a/src/util/xmlpool/gen_xmlpool.py b/src/util/xmlpool/gen_xmlpool.py
index b0db183854a85604855290db4a47d5734bda2dc9..327709c7f8ddac063b4235ad052f2ef4178e092f 100644 (file)
--- a/src/util/xmlpool/gen_xmlpool.py
+++ b/src/util/xmlpool/gen_xmlpool.py
@@ -13,6 +13,12 @@ import sys
 import gettext
 import re
 
+
+if sys.version_info < (3, 0):
+    gettext_method = 'ugettext'
+else:
+    gettext_method = 'gettext'
+
 # Path to t_options.h
 template_header_path = sys.argv[1]
 
@@ -60,7 +66,7 @@ def expandCString (s):
     octa = False
     num = 0
     digits = 0
-    r = ''
+    r = u''
     while i < len(s):
         if not escape:
             if s[i] == '\\':
@@ -128,16 +134,29 @@ def expandMatches (matches, translations, end=None):
         if len(matches) == 1 and i < len(translations) and \
                not matches[0].expand (r'\7').endswith('\\'):
             suffix = ' \\'
-        # Expand the description line. Need to use ugettext in order to allow
-        # non-ascii unicode chars in the original English descriptions.
-        text = escapeCString (trans.ugettext (unicode (expandCString (
-            matches[0].expand (r'\5')), "utf-8"))).encode("utf-8")
-        print(matches[0].expand (r'\1' + lang + r'\3"' + text + r'"\7') + suffix)
+        text = escapeCString (getattr(trans, gettext_method) (expandCString (
+            matches[0].expand (r'\5'))))
+        text = (matches[0].expand (r'\1' + lang + r'\3"' + text + r'"\7') + suffix)
+
+        # In Python 2, stdout expects encoded byte strings, or else it will
+        # encode them with the ascii 'codec'
+        if sys.version_info.major == 2:
+            text = text.encode('utf-8')
+
+        print(text)
+
         # Expand any subsequent enum lines
         for match in matches[1:]:
-            text = escapeCString (trans.ugettext (unicode (expandCString (
-                match.expand (r'\3')), "utf-8"))).encode("utf-8")
-            print(match.expand (r'\1"' + text + r'"\5'))
+            text = escapeCString (getattr(trans, gettext_method) (expandCString (
+                match.expand (r'\3'))))
+            text = match.expand (r'\1"' + text + r'"\5')
+
+            # In Python 2, stdout expects encoded byte strings, or else it will
+            # encode them with the ascii 'codec'
+            if sys.version_info.major == 2:
+                text = text.encode('utf-8')
+
+            print(text)
 
         # Expand description end
         if end:
@@ -168,9 +187,11 @@ print("/***********************************************************************\
 
 # Process the options template and generate options.h with all
 # translations.
-template = open (template_header_path, "r")
+template = open (template_header_path, "rb")
 descMatches = []
 for line in template:
+    line = line.decode('utf-8')
+
     if len(descMatches) > 0:
         matchENUM     = reENUM    .match (line)
         matchDESC_END = reDESC_END.match (line)