[Python-checkins] cpython: Issue #10419, issue #6011: port 6ad356525381 fix from distutils to packaging

Thu May 19 15:18:46 CEST 2011

http://hg.python.org/cpython/rev/cc5cfeaa4a8d
changeset: 70199:cc5cfeaa4a8d
user: Victor Stinner <victor.stinner at haypocalc.com>
date: Thu May 19 15:18:36 2011 +0200
summary:
 Issue #10419, issue #6011: port 6ad356525381 fix from distutils to packaging
build_scripts command of packaging now handles correctly non-ASCII path (path
to the Python executable). Open and write the script in binary mode, but ensure
that the shebang is decodable from UTF-8 and from the encoding of the script.
files:
 Lib/distutils/command/build_scripts.py | 7 +-
 Lib/packaging/command/build_scripts.py | 48 ++++++++++---
 2 files changed, 38 insertions(+), 17 deletions(-)

diff --git a/Lib/distutils/command/build_scripts.py b/Lib/distutils/command/build_scripts.py
--- a/Lib/distutils/command/build_scripts.py
+++ b/Lib/distutils/command/build_scripts.py
@@ -128,10 +128,9 @@
 "The shebang ({!r}) is not decodable "
 "from the script encoding ({})"
 .format(shebang, encoding))
- outf = open(outfile, "wb")
- outf.write(shebang)
- outf.writelines(f.readlines())
- outf.close()
+ with open(outfile, "wb") as outf:
+ outf.write(shebang)
+ outf.writelines(f.readlines())
 if f:
 f.close()
 else:
diff --git a/Lib/packaging/command/build_scripts.py b/Lib/packaging/command/build_scripts.py
--- a/Lib/packaging/command/build_scripts.py
+++ b/Lib/packaging/command/build_scripts.py
@@ -3,6 +3,7 @@
 import os
 import re
 import sysconfig
+import tokenize
 
 from packaging.command.cmd import Command
 from packaging.util import convert_path, newer
@@ -11,7 +12,7 @@
 
 
 # check if Python is called on the first line with this expression
-first_line_re = re.compile('^#!.*python[0-9.]*([ \t].*)?$')
+first_line_re = re.compile(b'^#!.*python[0-9.]*([ \t].*)?$')
 
 class build_scripts(Command, Mixin2to3):
 
@@ -76,12 +77,14 @@
 # that way, we'll get accurate feedback if we can read the
 # script.
 try:
- f = open(script, "r")
+ f = open(script, "rb")
 except IOError:
 if not self.dry_run:
 raise
 f = None
 else:
+ encoding, lines = tokenize.detect_encoding(f.readline)
+ f.seek(0)
 first_line = f.readline()
 if not first_line:
 logger.warning('%s: %s is an empty file (skipping)',
@@ -91,26 +94,45 @@
 match = first_line_re.match(first_line)
 if match:
 adjust = True
- post_interp = match.group(1) or ''
+ post_interp = match.group(1) or b''
 
 if adjust:
 logger.info("copying and adjusting %s -> %s", script,
 self.build_dir)
 if not self.dry_run:
- outf = open(outfile, "w")
 if not sysconfig.is_python_build():
- outf.write("#!%s%s\n" %
- (self.executable,
- post_interp))
+ executable = self.executable
 else:
- outf.write("#!%s%s\n" %
- (os.path.join(
+ executable = os.path.join(
 sysconfig.get_config_var("BINDIR"),
 "python%s%s" % (sysconfig.get_config_var("VERSION"),
- sysconfig.get_config_var("EXE"))),
- post_interp))
- outf.writelines(f.readlines())
- outf.close()
+ sysconfig.get_config_var("EXE")))
+ executable = os.fsencode(executable)
+ shebang = b"#!" + executable + post_interp + b"\n"
+ # Python parser starts to read a script using UTF-8 until
+ # it gets a #coding:xxx cookie. The shebang has to be the
+ # first line of a file, the #coding:xxx cookie cannot be
+ # written before. So the shebang has to be decodable from
+ # UTF-8.
+ try:
+ shebang.decode('utf-8')
+ except UnicodeDecodeError:
+ raise ValueError(
+ "The shebang ({!r}) is not decodable "
+ "from utf-8".format(shebang))
+ # If the script is encoded to a custom encoding (use a
+ # #coding:xxx cookie), the shebang has to be decodable from
+ # the script encoding too.
+ try:
+ shebang.decode(encoding)
+ except UnicodeDecodeError:
+ raise ValueError(
+ "The shebang ({!r}) is not decodable "
+ "from the script encoding ({})"
+ .format(shebang, encoding))
+ with open(outfile, "wb") as outf:
+ outf.write(shebang)
+ outf.writelines(f.readlines())
 if f:
 f.close()
 else:
-- 
Repository URL: http://hg.python.org/cpython
