1 files changed, 45 insertions, 43 deletions

diff --git a/bin/rebuild-script.py b/bin/rebuild-script.py
index 44fb129..a816af3 100755
--- a/bin/rebuild-script.py
+++ b/bin/rebuild-script.py
@@ -2,70 +2,72 @@
 """
 Helper script to rebuild virtualenv.py from virtualenv_support
 """
+from __future__ import print_function
 
-import re
 import os
-import sys
+import re
+import codecs
+from zlib import crc32
 
 here = os.path.dirname(__file__)
 script = os.path.join(here, '..', 'virtualenv.py')
 
+gzip = codecs.lookup('zlib')
+b64 = codecs.lookup('base64')
+
 file_regex = re.compile(
-    r'##file (.*?)\n([a-zA-Z][a-zA-Z0-9_]+)\s*=\s*convert\("""(.*?)"""\)',
+    br'##file (.*?)\n([a-zA-Z][a-zA-Z0-9_]+)\s*=\s*convert\("""\n(.*?)"""\)',
     re.S)
-file_template = '##file %(filename)s\n%(varname)s = convert("""\n%(data)s""")'
+file_template = b'##file %(filename)s\n%(varname)s = convert("""\n%(data)s""")'
 
-def rebuild():
-    f = open(script, 'rb')
-    content = f.read()
-    f.close()
+def rebuild(script_path):
+    with open(script_path, 'rb') as f:
+        script_content = f.read()
     parts = []
     last_pos = 0
     match = None
-    for match in file_regex.finditer(content):
-        parts.append(content[last_pos:match.start()])
+    for match in file_regex.finditer(script_content):
+        parts += [script_content[last_pos:match.start()]]
         last_pos = match.end()
-        filename = match.group(1)
+        filename, fn_decoded = match.group(1), match.group(1).decode()
         varname = match.group(2)
         data = match.group(3)
-        print('Found reference to file %s' % filename)
-        pathname = os.path.join(here, '..', 'virtualenv_embedded', filename)
-        f = open(pathname, 'rb')
-        c = f.read()
-        f.close()
-        new_data = c.encode('zlib').encode('base64')
+
+        print('Found file %s' % fn_decoded)
+        pathname = os.path.join(here, '..', 'virtualenv_embedded', fn_decoded)
+
+        with open(pathname, 'rb') as f:
+            embedded = f.read()
+        new_crc = crc32(embedded)
+        new_data = b64.encode(gzip.encode(embedded)[0])[0]
+
         if new_data == data:
-            print('  Reference up to date (%s bytes)' % len(c))
-            parts.append(match.group(0))
+            print('  File up to date (crc: %s)' % new_crc)
+            parts += [match.group(0)]
             continue
-        print('  Content changed (%s bytes -> %s bytes)' % (
-            zipped_len(data), len(c)))
-        new_match = file_template % dict(
-            filename=filename,
-            varname=varname,
-            data=new_data)
-        parts.append(new_match)
-    parts.append(content[last_pos:])
-    new_content = ''.join(parts)
-    if new_content != content:
-        sys.stdout.write('Content updated; overwriting... ')
-        f = open(script, 'wb')
-        f.write(new_content)
-        f.close()
+        # Else: content has changed
+        crc = crc32(gzip.decode(b64.decode(data)[0])[0])
+        print('  Content changed (crc: %s -> %s)' %
+              (crc, new_crc))
+        new_match = file_template % {
+            b'filename': filename,
+            b'varname': varname,
+            b'data': new_data
+        }
+        parts += [new_match]
+
+    parts += [script_content[last_pos:]]
+    new_content = b''.join(parts)
+
+    if new_content != script_content:
+        print('Content updated; overwriting... ', end='')
+        with open(script_path, 'wb') as f:
+            f.write(new_content)
         print('done.')
     else:
         print('No changes in content')
     if match is None:
         print('No variables were matched/found')
 
-def zipped_len(data):
-    if not data:
-        return 'no data'
-    try:
-        return len(data.decode('base64').decode('zlib'))
-    except:
-        return 'unknown'
-
 if __name__ == '__main__':
-    rebuild()
-    
+    rebuild(script)