Skip to content

#72 - wc.py gives different answers than /usr/bin/wc #75

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
glanois merged 4 commits into from
Mar 15, 2026
Merged

#72 - wc.py gives different answers than /usr/bin/wc #75

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
196284a
#72 Work in progress - aligning wc.py with Gnu wc.
glanois Mar 9, 2026
94514fe
#72 Work in progress - debugged and tested reading from stdin.
glanois Mar 9, 2026
230bd74
#72 Work in progress. First apparently working version.
glanois Mar 9, 2026
66497dd
#72 Use underscores in function names for readability.
glanois Mar 15, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
26 changes: 14 additions & 12 deletions python/ppt/tests/testwc.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -86,14 +86,14 @@ def test_wc_file(self):
# Run all options on the file in turn.
# Can't test the help options (-h, --help) because argparse exits after printing the help.
fixture = [
{ 'sw' : '-c', 'val' : 1456 },
{ 'sw' : '--bytes', 'val' : 1456 },
{ 'sw' : '-c', 'val' : 1464 },
{ 'sw' : '--bytes', 'val' : 1464 },
{ 'sw' : '-m', 'val' : 1456 },
{ 'sw' : '--chars', 'val' : 1456 },
{ 'sw' : '-l', 'val' : 25 },
{ 'sw' : '--lines', 'val' : 25 },
{ 'sw' : '-w', 'val' : 302 },
{ 'sw' : '--words', 'val' : 302 }]
{ 'sw' : '-w', 'val' : 264 },
{ 'sw' : '--words', 'val' : 264 }]

for f in fixture:
# Capture stdout when running.
Expand All @@ -114,16 +114,16 @@ def test_wc_file2(self):
warnings.simplefilter('ignore', ResourceWarning)

# Capture stdout when running.
out = io.StringIO()
with redirect_stdout(out):
io_out = io.StringIO()
with redirect_stdout(io_out):
parser = ppt.wc.get_parser()
options = parser.parse_args([DATA_FILE])
ppt.wc.main(options)

# Compare the results.
captured_stdout = out.getvalue()
captured_stdout = io_out.getvalue()
vals_int = [int(v) for v in captured_stdout.split()[0:3]]
expected_vals = [25, 302, 1456]
expected_vals = [25, 264, 1464]
self.assertEqual(vals_int, expected_vals)


Expand All @@ -142,18 +142,20 @@ def test_wc_stdin(self):
# TypeError: expected string or bytes-like object, got 'MagicMock'
#
# Therefore, this reads the whole file in (frown) and passes that.

with unittest.mock.patch('sys.stdin') as mock_stdin, open(DATA_FILE, 'r', encoding='utf-8') as data_file:
data_file_contents = data_file.read()

mock_stdin.read.return_value = data_file_contents

# Capture stdout when running.
out = io.StringIO()
with redirect_stdout(out):
io_out = io.StringIO()
with redirect_stdout(io_out):
ppt.wc.main(options)

# Compare the results.
captured_stdout = out.getvalue()
captured_stdout = io_out.getvalue()
vals_int = [int(v) for v in captured_stdout.split()[0:3]]
expected_vals = [25, 302, 1456]
expected_vals = [25, 264, 1456]
self.assertEqual(vals_int, expected_vals)

195 changes: 140 additions & 55 deletions python/ppt/wc.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -29,64 +29,132 @@
import re
import sys

def wordcounttext(options, text, filepath):

def count_requested(count):
num_requested = 0
for (k, v) in list(count['requests'].items()):
if v['requested']:
num_requested += 1
return num_requested


def word_count_text(options, text, filepath):
# For stdin (filepath == ''), just use the length of
# the incoming text.
bytes_count = len(text)

# For actual files, use the size on disk.
if os.path.isfile(filepath):
bytes_count = os.stat(filepath).st_size

# Note that the size on disk will be greater than the
# the length of the text when there are unicode characters.
# (eg, em dash instead of plain ASCII minus '-')

count = {
'chars' : 0,
'lines' : 0,
'words' : 0 }
count['chars'] = len(text)
count['lines'] = text.count('\n')
count['words'] = len(re.findall(r"[\w']+|[.,!?;]", text))

if options.bytes or options.chars:
print('%7d %s' % (count['chars'], filepath))
elif options.lines:
print('%7d %s' % (count['lines'], filepath))
elif options.words:
print('%7d %s' % (count['words'], filepath))
else:
print('%7d %7d %7d %s' % (count['lines'], count['words'], count['chars'], filepath))
'requests' : {
'bytes' : {
'count' : bytes_count,
'requested' : options.bytes },
'chars' : {
'count' : len(text),
'requested' : options.chars },
'lines' : {
'count' : text.count('\n'),
'requested' : options.lines },
'words' : {
'count' : len(re.findall(r'[^\s]+', text)),
'requested' : options.words} },
'filepath' : filepath }

if count_requested(count) == 0:
# Nothing explicitly requested. Therefore, request lines,
# words, and bytes.
count['requests']['lines']['requested'] = True
count['requests']['words']['requested'] = True
count['requests']['bytes']['requested'] = True

return count


def wordcountfile(options, filepath):
count = {
'chars' : 0,
'lines' : 0,
'words' : 0 }
try:
fin = open(filepath, 'r')

def word_count_file(options, filepath):
with open(filepath, 'r', encoding='utf-8') as fin:
text = fin.read()
fin.close()
except IOError:
print('Error reading file %s.' % (filepath))
raise
else:
count = wordcounttext(options, text, filepath)
return count

return word_count_text(options, text, filepath)


def wordcountfilenames(options):
def measure_width(count):
width = 0
# Find the width of the widest requested count.
for v in count['requests'].values():
if v['requested'] and len(str(v['count'])) > width:
width = len(str(v['count']))
return width


def word_count_filenames(options):
total = {
'chars' : 0,
'lines' : 0,
'words' : 0 }

for path in options.filenames:
count = wordcountfile(options, path)
total = {k: total[k] + v for (k, v) in list(count.items())}

if len(options.filenames) > 1:
if options.bytes or options.chars:
print('%7d %s' % (total['chars'], 'total'))
elif options.lines:
print('%7d %s' % (total['lines'], 'total'))
elif options.words:
print('%7d %s' % (total['words'], 'total'))
else:
print('%7d %7d %7d %s' % (total['lines'], total['words'], total['chars'], 'total'))

'bytes' : {
'count' : 0,
'requested' : False },
'chars' : {
'count' : 0,
'requested' : False },
'lines' : {
'count' : 0,
'requested' : False },
'words' : {
'count' : 0,
'requested' : False } }

# Find the width of the widest requested count.
widths = []
counts = []
for filepath in options.filenames:
count = word_count_file(options, filepath)
width = measure_width(count)
counts.append(count)
widths.append(width)
for k in count['requests'].keys():
if count['requests'][k]['requested']:
total[k]['count'] = total[k]['count'] + count['requests'][k]['count']
total[k]['requested'] = count['requests'][k]['requested']

return counts, widths, total


def print_counts_by_file(count, width):

# Have to do some work to duplicate the way wc spaces the numbers.
if count_requested(count) == 1:
# 1. When only one command line switch count requested, there are no leading spaces.
if count['requests']['lines']['requested']:
print(f"{count['requests']['lines']['count']} {count['filepath']}")
elif count['requests']['bytes']['requested']:
print(f"{count['requests']['bytes']['count']} {count['filepath']}")
elif count['requests']['chars']['requested']:
print(f"{count['requests']['chars']['count']} {count['filepath']}")
elif count['requests']['words']['requested']:
print(f"{count['requests']['words']['count']} {count['filepath']}")
else:
# 2. When there are
# a) no requested values (which means print all counts), or
# b) more than one requested value,
#
# wc uses the width of the widest requested number
# (plus one space between as a separator), and always
# prints them in this order: lines, words, characters, bytes.

# Assemble them in the specific order: lines, words, characters, bytes.
counts = []
for c in ('lines', 'words', 'chars', 'bytes'):
if count['requests'][c]['requested']:
counts.append(f"{count['requests'][c]['count']:>{width}}")

# Print it out.
print(f"{' '.join(counts)} {count['filepath']}")


def main(options):
if len(options.filenames) == 0:
# No filenames given on the command line.
Expand All @@ -95,14 +163,31 @@ def main(options):
filenames = sys.stdin.read()
# Split on NUL and throw away last one due to last NUL terminator.
options.filenames = filenames.split('\x00')[:-1]
wordcountfilenames(options)
counts, widths, total = word_count_filenames(options)
else:
# Process data directly from stdin.
text = sys.stdin.read()
wordcounttext(options, text, '')
count = word_count_text(options, text, '')
width = measure_width(count)
print_counts_by_file(count, width)
elif len(options.filenames) == 1:
# Just one file on the command line.
count = word_count_file(options, options.filenames[0])
width = measure_width(count)
print_counts_by_file(count, width)
else:
wordcountfilenames(options)

# Multiple files.
counts, widths, total = word_count_filenames(options)
for count in counts:
print_counts_by_file(count, max(widths))

totals = []
for c in ('lines', 'words', 'chars', 'bytes'):
if total[c]['requested']:
totals.append(f"{total[c]['count']:>{max(widths)}}")

print(f"{' '.join(totals)} total")


def get_parser():
parser = argparse.ArgumentParser()
Expand Down
Loading