Issue #15539: Fix a number of bugs in Tools/scripts/pindent.py.

Now pindent.py works with a "with" statement.  pindent.py no longer produces
improper indentation.  pindent.py now works with continued lines broken after
"class" or "def" keywords and with continuations at the start of line.  Added
regression tests for pindent.py.  Modernized pindent.py.
This commit is contained in:
Serhiy Storchaka 2013-01-11 12:12:32 +02:00
commit 9942e5a9cf
3 changed files with 392 additions and 105 deletions

View File

@ -9,10 +9,13 @@ import sys
import importlib.machinery import importlib.machinery
import unittest import unittest
from unittest import mock from unittest import mock
import shutil
import subprocess
import sysconfig import sysconfig
import tempfile import tempfile
import textwrap
from test import support from test import support
from test.script_helper import assert_python_ok from test.script_helper import assert_python_ok, temp_dir
if not sysconfig.is_python_build(): if not sysconfig.is_python_build():
# XXX some installers do contain the tools, should we detect that # XXX some installers do contain the tools, should we detect that
@ -36,6 +39,327 @@ class ReindentTests(unittest.TestCase):
self.assertGreater(err, b'') self.assertGreater(err, b'')
class PindentTests(unittest.TestCase):
script = os.path.join(scriptsdir, 'pindent.py')
def assertFileEqual(self, fn1, fn2):
with open(fn1) as f1, open(fn2) as f2:
self.assertEqual(f1.readlines(), f2.readlines())
def pindent(self, source, *args):
with subprocess.Popen(
(sys.executable, self.script) + args,
stdin=subprocess.PIPE, stdout=subprocess.PIPE,
universal_newlines=True) as proc:
out, err = proc.communicate(source)
self.assertIsNone(err)
return out
def lstriplines(self, data):
return '\n'.join(line.lstrip() for line in data.splitlines()) + '\n'
def test_selftest(self):
with temp_dir() as directory:
data_path = os.path.join(directory, '_test.py')
with open(self.script) as f:
closed = f.read()
with open(data_path, 'w') as f:
f.write(closed)
rc, out, err = assert_python_ok(self.script, '-d', data_path)
self.assertEqual(out, b'')
self.assertEqual(err, b'')
backup = data_path + '~'
self.assertTrue(os.path.exists(backup))
with open(backup) as f:
self.assertEqual(f.read(), closed)
with open(data_path) as f:
clean = f.read()
compile(clean, '_test.py', 'exec')
self.assertEqual(self.pindent(clean, '-c'), closed)
self.assertEqual(self.pindent(closed, '-d'), clean)
rc, out, err = assert_python_ok(self.script, '-c', data_path)
self.assertEqual(out, b'')
self.assertEqual(err, b'')
with open(backup) as f:
self.assertEqual(f.read(), clean)
with open(data_path) as f:
self.assertEqual(f.read(), closed)
broken = self.lstriplines(closed)
with open(data_path, 'w') as f:
f.write(broken)
rc, out, err = assert_python_ok(self.script, '-r', data_path)
self.assertEqual(out, b'')
self.assertEqual(err, b'')
with open(backup) as f:
self.assertEqual(f.read(), broken)
with open(data_path) as f:
indented = f.read()
compile(indented, '_test.py', 'exec')
self.assertEqual(self.pindent(broken, '-r'), indented)
def pindent_test(self, clean, closed):
self.assertEqual(self.pindent(clean, '-c'), closed)
self.assertEqual(self.pindent(closed, '-d'), clean)
broken = self.lstriplines(closed)
self.assertEqual(self.pindent(broken, '-r', '-e', '-s', '4'), closed)
def test_statements(self):
clean = textwrap.dedent("""\
if a:
pass
if a:
pass
else:
pass
if a:
pass
elif:
pass
else:
pass
while a:
break
while a:
break
else:
pass
for i in a:
break
for i in a:
break
else:
pass
try:
pass
finally:
pass
try:
pass
except TypeError:
pass
except ValueError:
pass
else:
pass
try:
pass
except TypeError:
pass
except ValueError:
pass
finally:
pass
with a:
pass
class A:
pass
def f():
pass
""")
closed = textwrap.dedent("""\
if a:
pass
# end if
if a:
pass
else:
pass
# end if
if a:
pass
elif:
pass
else:
pass
# end if
while a:
break
# end while
while a:
break
else:
pass
# end while
for i in a:
break
# end for
for i in a:
break
else:
pass
# end for
try:
pass
finally:
pass
# end try
try:
pass
except TypeError:
pass
except ValueError:
pass
else:
pass
# end try
try:
pass
except TypeError:
pass
except ValueError:
pass
finally:
pass
# end try
with a:
pass
# end with
class A:
pass
# end class A
def f():
pass
# end def f
""")
self.pindent_test(clean, closed)
def test_multilevel(self):
clean = textwrap.dedent("""\
def foobar(a, b):
if a == b:
a = a+1
elif a < b:
b = b-1
if b > a: a = a-1
else:
print 'oops!'
""")
closed = textwrap.dedent("""\
def foobar(a, b):
if a == b:
a = a+1
elif a < b:
b = b-1
if b > a: a = a-1
# end if
else:
print 'oops!'
# end if
# end def foobar
""")
self.pindent_test(clean, closed)
def test_preserve_indents(self):
clean = textwrap.dedent("""\
if a:
if b:
pass
""")
closed = textwrap.dedent("""\
if a:
if b:
pass
# end if
# end if
""")
self.assertEqual(self.pindent(clean, '-c'), closed)
self.assertEqual(self.pindent(closed, '-d'), clean)
broken = self.lstriplines(closed)
self.assertEqual(self.pindent(broken, '-r', '-e', '-s', '9'), closed)
clean = textwrap.dedent("""\
if a:
\tif b:
\t\tpass
""")
closed = textwrap.dedent("""\
if a:
\tif b:
\t\tpass
\t# end if
# end if
""")
self.assertEqual(self.pindent(clean, '-c'), closed)
self.assertEqual(self.pindent(closed, '-d'), clean)
broken = self.lstriplines(closed)
self.assertEqual(self.pindent(broken, '-r'), closed)
def test_escaped_newline(self):
clean = textwrap.dedent("""\
class\\
\\
A:
def\
\\
f:
pass
""")
closed = textwrap.dedent("""\
class\\
\\
A:
def\
\\
f:
pass
# end def f
# end class A
""")
self.assertEqual(self.pindent(clean, '-c'), closed)
self.assertEqual(self.pindent(closed, '-d'), clean)
def test_empty_line(self):
clean = textwrap.dedent("""\
if a:
pass
""")
closed = textwrap.dedent("""\
if a:
pass
# end if
""")
self.pindent_test(clean, closed)
def test_oneline(self):
clean = textwrap.dedent("""\
if a: pass
""")
closed = textwrap.dedent("""\
if a: pass
# end if
""")
self.pindent_test(clean, closed)
class TestSundryScripts(unittest.TestCase): class TestSundryScripts(unittest.TestCase):
# At least make sure the rest don't have syntax errors. When tests are # At least make sure the rest don't have syntax errors. When tests are
# added for a script it should be added to the whitelist below. # added for a script it should be added to the whitelist below.

View File

@ -621,6 +621,8 @@ Extension Modules
Tests Tests
----- -----
- Issue #15539: Added regression tests for Tools/scripts/pindent.py.
- Issue #16836: Enable IPv6 support even if IPv6 is disabled on the build host. - Issue #16836: Enable IPv6 support even if IPv6 is disabled on the build host.
- Issue #16925: test_configparser now works with unittest test discovery. - Issue #16925: test_configparser now works with unittest test discovery.
@ -777,6 +779,11 @@ Documentation
Tools/Demos Tools/Demos
----------- -----------
- Issue #15539: Fix a number of bugs in Tools/scripts/pindent.py. Now
pindent.py works with a "with" statement. pindent.py no longer produces
improper indentation. pindent.py now works with continued lines broken after
"class" or "def" keywords and with continuations at the start of line.
- Issue #11797: Add a 2to3 fixer that maps reload() to imp.reload(). - Issue #11797: Add a 2to3 fixer that maps reload() to imp.reload().
- Issue #10966: Remove the concept of unexpected skipped tests. - Issue #10966: Remove the concept of unexpected skipped tests.

View File

@ -79,8 +79,9 @@
# Defaults # Defaults
STEPSIZE = 8 STEPSIZE = 8
TABSIZE = 8 TABSIZE = 8
EXPANDTABS = 0 EXPANDTABS = False
import io
import re import re
import sys import sys
@ -89,7 +90,8 @@ next['if'] = next['elif'] = 'elif', 'else', 'end'
next['while'] = next['for'] = 'else', 'end' next['while'] = next['for'] = 'else', 'end'
next['try'] = 'except', 'finally' next['try'] = 'except', 'finally'
next['except'] = 'except', 'else', 'finally', 'end' next['except'] = 'except', 'else', 'finally', 'end'
next['else'] = next['finally'] = next['def'] = next['class'] = 'end' next['else'] = next['finally'] = next['with'] = \
next['def'] = next['class'] = 'end'
next['end'] = () next['end'] = ()
start = 'if', 'while', 'for', 'try', 'with', 'def', 'class' start = 'if', 'while', 'for', 'try', 'with', 'def', 'class'
@ -105,11 +107,11 @@ class PythonIndenter:
self.expandtabs = expandtabs self.expandtabs = expandtabs
self._write = fpo.write self._write = fpo.write
self.kwprog = re.compile( self.kwprog = re.compile(
r'^\s*(?P<kw>[a-z]+)' r'^(?:\s|\\\n)*(?P<kw>[a-z]+)'
r'(\s+(?P<id>[a-zA-Z_]\w*))?' r'((?:\s|\\\n)+(?P<id>[a-zA-Z_]\w*))?'
r'[^\w]') r'[^\w]')
self.endprog = re.compile( self.endprog = re.compile(
r'^\s*#?\s*end\s+(?P<kw>[a-z]+)' r'^(?:\s|\\\n)*#?\s*end\s+(?P<kw>[a-z]+)'
r'(\s+(?P<id>[a-zA-Z_]\w*))?' r'(\s+(?P<id>[a-zA-Z_]\w*))?'
r'[^\w]') r'[^\w]')
self.wsprog = re.compile(r'^[ \t]*') self.wsprog = re.compile(r'^[ \t]*')
@ -125,7 +127,7 @@ class PythonIndenter:
def readline(self): def readline(self):
line = self.fpi.readline() line = self.fpi.readline()
if line: self.lineno = self.lineno + 1 if line: self.lineno += 1
# end if # end if
return line return line
# end def readline # end def readline
@ -143,27 +145,24 @@ class PythonIndenter:
line2 = self.readline() line2 = self.readline()
if not line2: break if not line2: break
# end if # end if
line = line + line2 line += line2
# end while # end while
return line return line
# end def getline # end def getline
def putline(self, line, indent = None): def putline(self, line, indent):
if indent is None:
self.write(line)
return
# end if
tabs, spaces = divmod(indent*self.indentsize, self.tabsize) tabs, spaces = divmod(indent*self.indentsize, self.tabsize)
i = 0 i = self.wsprog.match(line).end()
m = self.wsprog.match(line) line = line[i:]
if m: i = m.end() if line[:1] not in ('\n', '\r', ''):
line = '\t'*tabs + ' '*spaces + line
# end if # end if
self.write('\t'*tabs + ' '*spaces + line[i:]) self.write(line)
# end def putline # end def putline
def reformat(self): def reformat(self):
stack = [] stack = []
while 1: while True:
line = self.getline() line = self.getline()
if not line: break # EOF if not line: break # EOF
# end if # end if
@ -173,10 +172,9 @@ class PythonIndenter:
kw2 = m.group('kw') kw2 = m.group('kw')
if not stack: if not stack:
self.error('unexpected end') self.error('unexpected end')
elif stack[-1][0] != kw2: elif stack.pop()[0] != kw2:
self.error('unmatched end') self.error('unmatched end')
# end if # end if
del stack[-1:]
self.putline(line, len(stack)) self.putline(line, len(stack))
continue continue
# end if # end if
@ -208,23 +206,23 @@ class PythonIndenter:
def delete(self): def delete(self):
begin_counter = 0 begin_counter = 0
end_counter = 0 end_counter = 0
while 1: while True:
line = self.getline() line = self.getline()
if not line: break # EOF if not line: break # EOF
# end if # end if
m = self.endprog.match(line) m = self.endprog.match(line)
if m: if m:
end_counter = end_counter + 1 end_counter += 1
continue continue
# end if # end if
m = self.kwprog.match(line) m = self.kwprog.match(line)
if m: if m:
kw = m.group('kw') kw = m.group('kw')
if kw in start: if kw in start:
begin_counter = begin_counter + 1 begin_counter += 1
# end if # end if
# end if # end if
self.putline(line) self.write(line)
# end while # end while
if begin_counter - end_counter < 0: if begin_counter - end_counter < 0:
sys.stderr.write('Warning: input contained more end tags than expected\n') sys.stderr.write('Warning: input contained more end tags than expected\n')
@ -234,17 +232,12 @@ class PythonIndenter:
# end def delete # end def delete
def complete(self): def complete(self):
self.indentsize = 1
stack = [] stack = []
todo = [] todo = []
thisid = '' currentws = thisid = firstkw = lastkw = topid = ''
current, firstkw, lastkw, topid = 0, '', '', '' while True:
while 1:
line = self.getline() line = self.getline()
i = 0 i = self.wsprog.match(line).end()
m = self.wsprog.match(line)
if m: i = m.end()
# end if
m = self.endprog.match(line) m = self.endprog.match(line)
if m: if m:
thiskw = 'end' thiskw = 'end'
@ -269,7 +262,9 @@ class PythonIndenter:
thiskw = '' thiskw = ''
# end if # end if
# end if # end if
indent = len(line[:i].expandtabs(self.tabsize)) indentws = line[:i]
indent = len(indentws.expandtabs(self.tabsize))
current = len(currentws.expandtabs(self.tabsize))
while indent < current: while indent < current:
if firstkw: if firstkw:
if topid: if topid:
@ -278,11 +273,11 @@ class PythonIndenter:
else: else:
s = '# end %s\n' % firstkw s = '# end %s\n' % firstkw
# end if # end if
self.putline(s, current) self.write(currentws + s)
firstkw = lastkw = '' firstkw = lastkw = ''
# end if # end if
current, firstkw, lastkw, topid = stack[-1] currentws, firstkw, lastkw, topid = stack.pop()
del stack[-1] current = len(currentws.expandtabs(self.tabsize))
# end while # end while
if indent == current and firstkw: if indent == current and firstkw:
if thiskw == 'end': if thiskw == 'end':
@ -297,18 +292,18 @@ class PythonIndenter:
else: else:
s = '# end %s\n' % firstkw s = '# end %s\n' % firstkw
# end if # end if
self.putline(s, current) self.write(currentws + s)
firstkw = lastkw = topid = '' firstkw = lastkw = topid = ''
# end if # end if
# end if # end if
if indent > current: if indent > current:
stack.append((current, firstkw, lastkw, topid)) stack.append((currentws, firstkw, lastkw, topid))
if thiskw and thiskw not in start: if thiskw and thiskw not in start:
# error # error
thiskw = '' thiskw = ''
# end if # end if
current, firstkw, lastkw, topid = \ currentws, firstkw, lastkw, topid = \
indent, thiskw, thiskw, thisid indentws, thiskw, thiskw, thisid
# end if # end if
if thiskw: if thiskw:
if thiskw in start: if thiskw in start:
@ -326,7 +321,6 @@ class PythonIndenter:
self.write(line) self.write(line)
# end while # end while
# end def complete # end def complete
# end class PythonIndenter # end class PythonIndenter
# Simplified user interface # Simplified user interface
@ -352,76 +346,34 @@ def reformat_filter(input = sys.stdin, output = sys.stdout,
pi.reformat() pi.reformat()
# end def reformat_filter # end def reformat_filter
class StringReader:
def __init__(self, buf):
self.buf = buf
self.pos = 0
self.len = len(self.buf)
# end def __init__
def read(self, n = 0):
if n <= 0:
n = self.len - self.pos
else:
n = min(n, self.len - self.pos)
# end if
r = self.buf[self.pos : self.pos + n]
self.pos = self.pos + n
return r
# end def read
def readline(self):
i = self.buf.find('\n', self.pos)
return self.read(i + 1 - self.pos)
# end def readline
def readlines(self):
lines = []
line = self.readline()
while line:
lines.append(line)
line = self.readline()
# end while
return lines
# end def readlines
# seek/tell etc. are left as an exercise for the reader
# end class StringReader
class StringWriter:
def __init__(self):
self.buf = ''
# end def __init__
def write(self, s):
self.buf = self.buf + s
# end def write
def getvalue(self):
return self.buf
# end def getvalue
# end class StringWriter
def complete_string(source, stepsize = STEPSIZE, tabsize = TABSIZE, expandtabs = EXPANDTABS): def complete_string(source, stepsize = STEPSIZE, tabsize = TABSIZE, expandtabs = EXPANDTABS):
input = StringReader(source) input = io.StringIO(source)
output = StringWriter() output = io.StringIO()
pi = PythonIndenter(input, output, stepsize, tabsize, expandtabs) pi = PythonIndenter(input, output, stepsize, tabsize, expandtabs)
pi.complete() pi.complete()
return output.getvalue() return output.getvalue()
# end def complete_string # end def complete_string
def delete_string(source, stepsize = STEPSIZE, tabsize = TABSIZE, expandtabs = EXPANDTABS): def delete_string(source, stepsize = STEPSIZE, tabsize = TABSIZE, expandtabs = EXPANDTABS):
input = StringReader(source) input = io.StringIO(source)
output = StringWriter() output = io.StringIO()
pi = PythonIndenter(input, output, stepsize, tabsize, expandtabs) pi = PythonIndenter(input, output, stepsize, tabsize, expandtabs)
pi.delete() pi.delete()
return output.getvalue() return output.getvalue()
# end def delete_string # end def delete_string
def reformat_string(source, stepsize = STEPSIZE, tabsize = TABSIZE, expandtabs = EXPANDTABS): def reformat_string(source, stepsize = STEPSIZE, tabsize = TABSIZE, expandtabs = EXPANDTABS):
input = StringReader(source) input = io.StringIO(source)
output = StringWriter() output = io.StringIO()
pi = PythonIndenter(input, output, stepsize, tabsize, expandtabs) pi = PythonIndenter(input, output, stepsize, tabsize, expandtabs)
pi.reformat() pi.reformat()
return output.getvalue() return output.getvalue()
# end def reformat_string # end def reformat_string
def complete_file(filename, stepsize = STEPSIZE, tabsize = TABSIZE, expandtabs = EXPANDTABS): def complete_file(filename, stepsize = STEPSIZE, tabsize = TABSIZE, expandtabs = EXPANDTABS):
source = open(filename, 'r').read() with open(filename, 'r') as f:
source = f.read()
# end with
result = complete_string(source, stepsize, tabsize, expandtabs) result = complete_string(source, stepsize, tabsize, expandtabs)
if source == result: return 0 if source == result: return 0
# end if # end if
@ -429,14 +381,16 @@ def complete_file(filename, stepsize = STEPSIZE, tabsize = TABSIZE, expandtabs =
try: os.rename(filename, filename + '~') try: os.rename(filename, filename + '~')
except OSError: pass except OSError: pass
# end try # end try
f = open(filename, 'w') with open(filename, 'w') as f:
f.write(result) f.write(result)
f.close() # end with
return 1 return 1
# end def complete_file # end def complete_file
def delete_file(filename, stepsize = STEPSIZE, tabsize = TABSIZE, expandtabs = EXPANDTABS): def delete_file(filename, stepsize = STEPSIZE, tabsize = TABSIZE, expandtabs = EXPANDTABS):
source = open(filename, 'r').read() with open(filename, 'r') as f:
source = f.read()
# end with
result = delete_string(source, stepsize, tabsize, expandtabs) result = delete_string(source, stepsize, tabsize, expandtabs)
if source == result: return 0 if source == result: return 0
# end if # end if
@ -444,14 +398,16 @@ def delete_file(filename, stepsize = STEPSIZE, tabsize = TABSIZE, expandtabs = E
try: os.rename(filename, filename + '~') try: os.rename(filename, filename + '~')
except OSError: pass except OSError: pass
# end try # end try
f = open(filename, 'w') with open(filename, 'w') as f:
f.write(result) f.write(result)
f.close() # end with
return 1 return 1
# end def delete_file # end def delete_file
def reformat_file(filename, stepsize = STEPSIZE, tabsize = TABSIZE, expandtabs = EXPANDTABS): def reformat_file(filename, stepsize = STEPSIZE, tabsize = TABSIZE, expandtabs = EXPANDTABS):
source = open(filename, 'r').read() with open(filename, 'r') as f:
source = f.read()
# end with
result = reformat_string(source, stepsize, tabsize, expandtabs) result = reformat_string(source, stepsize, tabsize, expandtabs)
if source == result: return 0 if source == result: return 0
# end if # end if
@ -459,9 +415,9 @@ def reformat_file(filename, stepsize = STEPSIZE, tabsize = TABSIZE, expandtabs =
try: os.rename(filename, filename + '~') try: os.rename(filename, filename + '~')
except OSError: pass except OSError: pass
# end try # end try
f = open(filename, 'w') with open(filename, 'w') as f:
f.write(result) f.write(result)
f.close() # end with
return 1 return 1
# end def reformat_file # end def reformat_file
@ -474,7 +430,7 @@ usage: pindent (-c|-d|-r) [-s stepsize] [-t tabsize] [-e] [file] ...
-r : reformat a completed program (use #end directives) -r : reformat a completed program (use #end directives)
-s stepsize: indentation step (default %(STEPSIZE)d) -s stepsize: indentation step (default %(STEPSIZE)d)
-t tabsize : the worth in spaces of a tab (default %(TABSIZE)d) -t tabsize : the worth in spaces of a tab (default %(TABSIZE)d)
-e : expand TABs into spaces (defailt OFF) -e : expand TABs into spaces (default OFF)
[file] ... : files are changed in place, with backups in file~ [file] ... : files are changed in place, with backups in file~
If no files are specified or a single - is given, If no files are specified or a single - is given,
the program acts as a filter (reads stdin, writes stdout). the program acts as a filter (reads stdin, writes stdout).
@ -517,7 +473,7 @@ def test():
elif o == '-t': elif o == '-t':
tabsize = int(a) tabsize = int(a)
elif o == '-e': elif o == '-e':
expandtabs = 1 expandtabs = True
# end if # end if
# end for # end for
if not action: if not action: