def shellExtractor(file):
"""
Extract comments from Shell file.
:param file: File to scan
:type file: string
:return: Scan output
:rtype: ScanOutput
"""
result = CommentSyntax()
single_line_comment = result.hash(file)
cont_single_line_comment = contSingleLines(single_line_comment)
file = file.split("/")
output = ScanOutput()
output.filename = file[-1]
output.lang = "Shell"
output.total_lines = single_line_comment[1]
output.total_lines_of_comments = single_line_comment[3]
output.blank_lines = single_line_comment[2]
if cont_single_line_comment:
single_line_comment = cont_single_line_comment[0]
for i in single_line_comment[0]:
output.single_line_comment.append(SingleLine(i[0], i[1]))
for idx, _ in enumerate(cont_single_line_comment[1]):
output.cont_single_line_comment.append(
MultiLine(
cont_single_line_comment[1][idx],
cont_single_line_comment[2][idx],
cont_single_line_comment[3][idx],
))
return output
def test_outputFormat(self):
"""
Check for the output format correctness.
"""
regex = r"""(?<!["'`])#+\s*(.*)"""
syntax_start = "=begin"
syntax_end = "=cut"
expected = perl.perlExtractor(self.testfile).get_dict()
comment_single = readSingleLine(self.testfile, regex)
comment_multiline = readMultiLineDiff(self.testfile, syntax_start, syntax_end)
comment_contSingleline = contSingleLines(comment_single)
file = self.testfile.split("/")
output = {
"metadata": {
"filename": file[-1],
"lang": "Perl",
"total_lines": comment_single[1],
"total_lines_of_comments": comment_single[3] + comment_multiline[3],
"blank_lines": comment_single[2],
"sloc": comment_single[1] - (comment_single[3] + comment_multiline[3] + comment_single[2]),
},
"single_line_comment": [],
"cont_single_line_comment": [],
"multi_line_comment": [],
}
if comment_contSingleline:
comment_single = comment_contSingleline[0]
if comment_single:
for i in comment_single[0]:
output["single_line_comment"].append(
{"line_number": i[0], "comment": i[1]}
)
if comment_contSingleline:
for idx, _ in enumerate(comment_contSingleline[1]):
output["cont_single_line_comment"].append(
{
"start_line": comment_contSingleline[1][idx],
"end_line": comment_contSingleline[2][idx],
"comment": comment_contSingleline[3][idx],
}
)
if comment_multiline:
for idx, _ in enumerate(comment_multiline[0]):
output["multi_line_comment"].append(
{
"start_line": comment_multiline[0][idx],
"end_line": comment_multiline[1][idx],
"comment": comment_multiline[2][idx],
}
)
self.assertEqual(output, expected)
def test_output(self):
"""
Check for the scan correctness.
"""
regex = r"""(?<!["'`])#+\s*(.*)"""
syntax_start = "=begin"
syntax_end = "=cut"
comment_single = readSingleLine(self.testfile, regex)
comment_multiline = readMultiLineDiff(self.testfile, syntax_start, syntax_end)
comment_contSingleline = contSingleLines(comment_single)
self.assertTrue(comment_single)
self.assertTrue(comment_multiline)
self.assertTrue(comment_contSingleline)
def test_output(self):
"""
Check for the scan correctness.
"""
regex = r"""(?<![pst'"`]:)\/\/\s*(.*)"""
syntax_start = "/*"
syntax_end = "*/"
comment_single = readSingleLine(self.testfile, regex)
comment_multiline = readMultiLineDiff(self.testfile, syntax_start,
syntax_end)
comment_contSinglelines = contSingleLines(comment_single)
self.assertTrue(comment_single)
self.assertTrue(comment_multiline)
self.assertTrue(comment_contSinglelines)
def test_output(self):
"""
Check for the scan correctness.
"""
regex = r"""(?<!["'`])#+\s*(.*)"""
syntax_single = "'''"
syntax_double = '"""'
comment_multi_single = readMultiLineSame(self.testfile, syntax_single)
comment_single = readSingleLine(self.testfile, regex)
comment_multi_double = readMultiLineSame(self.testfile, syntax_double)
comment_contSingleline = contSingleLines(comment_single)
self.assertTrue(comment_single)
self.assertTrue(comment_multi_single)
self.assertTrue(comment_multi_double)
self.assertTrue(comment_contSingleline)
def cExtractor(file):
"""
Extract comments from C file.
:param file: File to scan
:type file: string
:return: Scan output
:rtype: ScanOutput
"""
result = CommentSyntax()
single_line_comment = result.doubleSlash(file)
multiline_comment = result.slashStar(file)
cont_single_line_comment = contSingleLines(single_line_comment)
file = file.split("/")
output = ScanOutput()
output.filename = file[-1]
output.lang = "C"
output.total_lines = single_line_comment[1]
output.total_lines_of_comments = single_line_comment[
3] + multiline_comment[3]
output.blank_lines = single_line_comment[2]
if cont_single_line_comment:
single_line_comment = cont_single_line_comment[0]
for i in single_line_comment[0]:
output.single_line_comment.append(SingleLine(i[0], i[1]))
for idx, _ in enumerate(cont_single_line_comment[1]):
output.cont_single_line_comment.append(
MultiLine(
cont_single_line_comment[1][idx],
cont_single_line_comment[2][idx],
cont_single_line_comment[3][idx],
))
try:
for idx, _ in enumerate(multiline_comment[0]):
output.multi_line_comment.append(
MultiLine(
multiline_comment[0][idx],
multiline_comment[1][idx],
multiline_comment[2][idx],
))
except BaseException:
pass
return output
def matlabExtractor(file):
"""
Extract comments from MATLAB file.
:param file: File to scan
:type file: string
:return: Scan output
:rtype: ScanOutput
"""
result = CommentSyntax()
single_line_comment = result.percentage(file)
multiline_comment = result.percentageCurlybraces(file)
cont_single_line_comment = contSingleLines(single_line_comment)
file = file.split("/")
output = ScanOutput()
output.filename = file[-1]
output.lang = "MATLAB"
output.total_lines = single_line_comment[1]
output.total_lines_of_comments = single_line_comment[3] + multiline_comment[3]
output.blank_lines = single_line_comment[2]
if cont_single_line_comment:
single_line_comment = cont_single_line_comment[0]
for i in single_line_comment[0]:
output.single_line_comment.append(SingleLine(i[0], i[1]))
for idx, _ in enumerate(cont_single_line_comment[1]):
output.cont_single_line_comment.append(
MultiLine(
cont_single_line_comment[1][idx],
cont_single_line_comment[2][idx],
cont_single_line_comment[3][idx],
)
)
for idx, _ in enumerate(multiline_comment[0]):
output.multi_line_comment.append(
MultiLine(
multiline_comment[0][idx],
multiline_comment[1][idx],
multiline_comment[2][idx],
)
)
return output
def test_outputFormat(self):
regex = r'''(\/\/\s*[\w #\.()@+-_*\d]*)'''
self.syntax_start = "/*"
self.syntax_end ='*/'
sign = '//'
expected = cpp.cppExtractor(self.testfile)
comment_single = readSingleLine(self.testfile,regex,sign)
comment_multiline = readMultiLineDiff(self.testfile,self.syntax_start,self.syntax_end)
comment_contSingleline = contSingleLines(comment_single)
file = self.testfile.split("/")
output = {
"metadata": [{
"filename": file[-1],
"lang": "C++",
"total_lines": comment_single[1],
"total_lines_of_comments": comment_single[3]+comment_multiline[3],
"blank_lines": comment_single[2],
"sloc": comment_single[1]-(comment_single[3]+comment_multiline[3]+comment_single[2])
}],
"single_line_comment": [],
"cont_single_line_comment": [],
"multi_line_comment": []
}
if comment_contSingleline:
comment_single = comment_contSingleline[0]
if comment_single:
for i in comment_single[0]:
output['single_line_comment'].append({"line_number" :i[0],"comment": i[1]})
if comment_contSingleline:
for idx,i in enumerate(comment_contSingleline[1]):
output['cont_single_line_comment'].append({"start_line": comment_contSingleline[1][idx], "end_line": comment_contSingleline[2][idx], "comment": comment_contSingleline[3][idx]})
if comment_multiline:
try:
for idx,i in enumerate(comment_multiline[0]):
output['multi_line_comment'].append({"start_line": comment_multiline[0][idx], "end_line": comment_multiline[1][idx], "comment": comment_multiline[2][idx]})
except:
pass
self.assertEqual(output,expected)
