# HG changeset patch # Parent 98a57845c8ccdc9b587304f7c6c8571762261409 Issue #27952: Get fixcid.py working with the re module diff -r 98a57845c8cc Lib/test/test_tools/test_fixcid.py --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/Lib/test/test_tools/test_fixcid.py Sat Sep 10 03:20:35 2016 +0000 @@ -0,0 +1,92 @@ +'''Test Tools/scripts/fixcid.py.''' + +from io import StringIO +import os, os.path +import runpy +import sys +from test import support +from test.test_tools import skip_if_missing, scriptsdir +import unittest + +skip_if_missing() + +class Test(unittest.TestCase): + def test_parse_strings(self): + substfile = "xx yy\n" + old1 = 'int xx = "xx\\"xx"[xx];\n' + old2 = "int xx = 'x\\'xx' + xx;\n" + output = self.run_script(old1 + old2) + new1 = 'int yy = "xx\\"xx"[yy];\n' + new2 = "int yy = 'x\\'xx' + yy;\n" + self.assertMultiLineEqual(output, + "1\n" + "< {old1}" + "> {new1}" + "{new1}" + "2\n" + "< {old2}" + "> {new2}" + "{new2}".format(old1=old1, old2=old2, new1=new1, new2=new2) + ) + + def test_alter_comments(self): + output = self.run_script( + substfile= + "xx yy\n" + "*aa bb\n", + args=("-c", "-",), + input= + "/* xx altered */\n" + "int xx;\n" + "/* aa unaltered */\n" + "int aa;\n", + ) + self.assertMultiLineEqual(output, + "1\n" + "< /* xx altered */\n" + "> /* yy altered */\n" + "/* yy altered */\n" + "2\n" + "< int xx;\n" + "> int yy;\n" + "int yy;\n" + "/* aa unaltered */\n" + "4\n" + "< int aa;\n" + "> int bb;\n" + "int bb;\n" + ) + + def test_directory(self): + os.mkdir(support.TESTFN) + self.addCleanup(support.rmtree, support.TESTFN) + c_filename = os.path.join(support.TESTFN, "file.c") + with open(c_filename, "w") as file: + file.write("int xx;\n") + with open(os.path.join(support.TESTFN, "file.py"), "w") as file: + file.write("xx = 'unaltered'\n") + script = os.path.join(scriptsdir, "fixcid.py") + output = self.run_script(args=(support.TESTFN,)) + self.assertMultiLineEqual(output, + "{}:\n" + "1\n" + '< int xx;\n' + '> int yy;\n'.format(c_filename) + ) + + def run_script(self, input="", *, args=("-",), substfile="xx yy\n"): + substfilename = support.TESTFN + ".subst" + with open(substfilename, "w") as file: + file.write(substfile) + self.addCleanup(support.unlink, substfilename) + + argv = ["fixcid.py", "-s", substfilename] + list(args) + script = os.path.join(scriptsdir, "fixcid.py") + with support.swap_attr(sys, "argv", argv), \ + support.swap_attr(sys, "stdin", StringIO(input)), \ + support.captured_stdout() as output: + try: + runpy.run_path(script, run_name="__main__") + except SystemExit as exit: + self.assertEqual(exit.code, 0) + return output.getvalue() diff -r 98a57845c8cc Misc/NEWS --- a/Misc/NEWS Fri Sep 09 07:38:50 2016 +0000 +++ b/Misc/NEWS Sat Sep 10 03:20:35 2016 +0000 @@ -329,6 +329,13 @@ - Issue #27883: Update sqlite to 3.14.1.0 on Windows. +Tools/Demos +----------- + +- Issue #27952: Get Tools/scripts/fixcid.py working with Python 3 and the + current "re" module, avoid deprecated Python backslash escaping, and fix a + bug parsing escaped C quote signs. + What's New in Python 3.6.0 alpha 4 ================================== diff -r 98a57845c8cc Tools/scripts/fixcid.py --- a/Tools/scripts/fixcid.py Fri Sep 09 07:38:50 2016 +0000 +++ b/Tools/scripts/fixcid.py Sat Sep 10 03:20:35 2016 +0000 @@ -88,9 +88,9 @@ sys.exit(bad) # Change this regular expression to select a different set of files -Wanted = '^[a-zA-Z0-9_]+\.[ch]$' +Wanted = r'^[a-zA-Z0-9_]+\.[ch]$' def wanted(name): - return re.match(Wanted, name) >= 0 + return re.match(Wanted, name) def recursedown(dirname): dbg('recursedown(%r)\n' % (dirname,)) @@ -168,6 +168,7 @@ if filename == '-': return 0 # Done in filter mode f.close() if not g: return 0 # No changes + g.close() # Finishing touch -- move files @@ -193,21 +194,21 @@ # Tokenizing ANSI C (partly) -Identifier = '\(struct \)?[a-zA-Z_][a-zA-Z0-9_]+' -String = '"\([^\n\\"]\|\\\\.\)*"' -Char = '\'\([^\n\\\']\|\\\\.\)*\'' -CommentStart = '/\*' -CommentEnd = '\*/' +Identifier = '(struct )?[a-zA-Z_][a-zA-Z0-9_]+' +String = r'"([^\n\\"]|\\.)*"' +Char = r"'([^\n\\']|\\.)*'" +CommentStart = r'/\*' +CommentEnd = r'\*/' Hexnumber = '0[xX][0-9a-fA-F]*[uUlL]*' Octnumber = '0[0-7]*[uUlL]*' Decnumber = '[1-9][0-9]*[uUlL]*' -Intnumber = Hexnumber + '\|' + Octnumber + '\|' + Decnumber +Intnumber = Hexnumber + '|' + Octnumber + '|' + Decnumber Exponent = '[eE][-+]?[0-9]+' -Pointfloat = '\([0-9]+\.[0-9]*\|\.[0-9]+\)\(' + Exponent + '\)?' +Pointfloat = r'([0-9]+\.[0-9]*|\.[0-9]+)(' + Exponent + r')?' Expfloat = '[0-9]+' + Exponent -Floatnumber = Pointfloat + '\|' + Expfloat -Number = Floatnumber + '\|' + Intnumber +Floatnumber = Pointfloat + '|' + Expfloat +Number = Floatnumber + '|' + Intnumber # Anything else is an operator -- don't list this explicitly because of '/*' @@ -225,15 +226,16 @@ def fixline(line): global Program -## print '-->', repr(line) +## print('-->', repr(line)) i = 0 while i < len(line): - i = Program.search(line, i) - if i < 0: break - found = Program.group(0) -## if Program is InsideCommentProgram: print '...', -## else: print ' ', -## print found + match = Program.search(line, i) + if match is None: break + i = match.start() + found = match.group(0) +## if Program is InsideCommentProgram: print(end='... ') +## else: print(end=' ') +## print(found) if len(found) == 2: if found == '/*': Program = InsideCommentProgram @@ -247,15 +249,15 @@ print('Found in comment:', found) i = i + n continue - if NotInComment.has_key(found): -## print 'Ignored in comment:', -## print found, '-->', subst -## print 'Line:', line, + if found in NotInComment: +## print(end='Ignored in comment: ') +## print(found, '-->', subst) +## print('Line:', line, end='') subst = found ## else: -## print 'Substituting in comment:', -## print found, '-->', subst -## print 'Line:', line, +## print(end='Substituting in comment: ') +## print(found, '-->', subst) +## print('Line:', line, end='') line = line[:i] + subst + line[i+n:] n = len(subst) i = i + n