CLOCBear: Add CLOCBear

This bear gives statistics about number of lines,
number of comment lines, and total number of lines.

Closes coala#1577

.ci/deps.sh

@@ -13,7 +13,7 @@ esac
 # apt-get commands
 export DEBIAN_FRONTEND=noninteractive
 
-deps="libclang1-3.4 indent mono-mcs chktex r-base julia golang-go luarocks verilator cppcheck flawfinder devscripts"
+deps="libclang1-3.4 indent mono-mcs chktex r-base julia golang-go luarocks verilator cppcheck flawfinder devscripts cloc"
 deps_infer="m4 opam"
 
 case $CIRCLE_BUILD_IMAGE in

.travis.yml

@@ -43,6 +43,7 @@ addons:
       - opam
       - php-codesniffer
       - verilator
+      - cloc
 
 cache:
   pip: true

bears/general/CLOCBear.py

@@ -0,0 +1,52 @@
+import re
+
+from coalib.bearlib.abstractions.Linter import linter
+from coalib.results.Result import Result
+from dependency_management.requirements.DistributionRequirement import (
+    DistributionRequirement)
+
+
+@linter(executable='cloc',
+        use_stdout=True,
+        use_stderr=False)
+class CLOCBear:
+    """
+    Summarises file of or number of files in directory structure
+    with total lines, number comment lines, actual code lines using tool cloc
+    """
+    LANGUAGES = {'All'}
+    REQUIREMENTS = {DistributionRequirement(apt_get='cloc')}
+    AUTHORS = {'The coala developers'}
+    AUTHORS_EMAILS = {'[email protected]'}
+    LICENSE = 'AGPL-3.0'
+    CAN_DETECT = {'Comment lines','Empty lines'}
+
+    @staticmethod
+    def create_arguments(filename, file, config_file):
+        return ('', filename)
+
+    def process_output(self, output, filename, file):
+        out = output
+        lines = out.split('\n')
+        files = (int)(re.search(r'(\d+)', lines[1]).group(1))
+        ignored_files = (int)(re.search(r'(\d+)', lines[2]).group(1))
+        if(files == ignored_files):
+            msg = 'No valid files. File should belong to valid programming language.'
+            yield Result.from_values(origin = self,
+                                     message = msg,
+                                     file=filename)
+        else:
+            regex = r'(^\S+)\s+(\d+)\s+(\d+)\s+(\d+)\s+(\d+)'
+            for row in lines[8:-2]:
+                match = re.search(regex, row)
+                lang = match.group(1)
+                nfiles = match.group(2)
+                blank = (int)(match.group(3))
+                comment = (int)(match.group(4))
+                code = (int)(match.group(5))
+                total = blank + comment + code
+                report = 'Language: {0}\nTotal files: {1}\nTotal lines: {2}\nCode lines: {3}({4:.2f}%)\nComment lines: {5}({6:.2f}%)\nBlank lines: {7}({8:.2f}%)\n'\
+                         .format(lang, nfiles, total, code, code*100./total, comment, comment*100./total, blank, blank*100./total)
+                yield Result.from_values(origin = self,
+                                         message = report,
+                                         file = filename)

tests/general/CLOCBearTest.py

@@ -0,0 +1,93 @@
+import unittest
+import os
+from queue import Queue
+
+from coalib.settings.Section import Section
+from coalib.testing.LocalBearTestHelper import LocalBearTestHelper
+from coalib.testing.BearTestHelper import generate_skip_decorator
+from coalib.results.Result import Result
+
+from bears.general.CLOCBear import CLOCBear
+
+
+def get_absolute_test_path(file):
+    return os.path.join(os.path.dirname(__file__),
+                        'cloc_test_files', file)
+
+def load_testfile(name):
+    return open(get_absolute_test_path(name)).readlines()
+
+@generate_skip_decorator(CLOCBear)
+class CLOCBearTest(LocalBearTestHelper):
+
+    def setUp(self):
+        self.uut = CLOCBear(Section('name'), Queue())
+        self.test_files = ['example1.cpp', 'example2.py', 'example3.cpp']
+        self.message_format = 'd'
+        self.expected_results = {self.test_files[0] : {'LANGUAGE': 'C++', 'FILES': 1, 'CODE': 6, 'COMMENTS': 5, 'BLANK': 3},
+                                 self.test_files[1] : {'LANGUAGE': 'Python', 'FILES': 1, 'CODE': 3, 'COMMENTS': 2, 'BLANK': 3},
+                                 self.test_files[2] : {'LANGUAGE': 'C++', 'FILES': 1, 'CODE': 10, 'COMMENTS': 0, 'BLANK': 3}
+                                }
+
+    def build_message(self, filename):
+        result = self.expected_results[filename]
+        lang = result['LANGUAGE']
+        nfiles = result['FILES']
+        code = result['CODE']
+        comment = result['COMMENTS']
+        blank = result['BLANK']
+        total = code + comment + blank
+        message = "\n".join(["Language: {0}".format(lang),
+                             "Total files: {0}".format(nfiles),
+                             "Total lines: {0}".format(total),
+                             "Code lines: {0}({1:.2f}%)".format(code, code * 100. / total),
+                             "Comment lines: {0}({1:.2f}%)".format(comment, comment * 100. / total),
+                             "Blank lines: {0}({1:.2f}%)".format(blank, blank * 100. / total),
+                             ""
+                             ])
+        return((str)(message))
+
+    def test_all(self):
+        for filename in self.test_files:
+            file_contents = load_testfile(filename)
+            self.check_results(
+                self.uut,
+                file_contents,
+                [Result.from_values('CLOCBear',
+                                    self.build_message(filename),
+                                    file=get_absolute_test_path(filename))],
+                filename=get_absolute_test_path(filename))
+
+    # def test_license_without_copyright(self):
+    #     file_contents = load_testfile('apache_license_without_copyright.py')
+    #     self.check_results(
+    #         self.uut,
+    #         file_contents,
+    #         [],
+    #         filename=get_testfile_path('apache_license_without_copyright.py'),
+    #         settings={'licensecheck_lines': 70,
+    #                   'licensecheck_tail': 0})
+    #
+    # def copyright_without_license(self):
+    #     file_contents = load_testfile('copyright_without_license.py')
+    #     self.check_results(
+    #         self.uut,
+    #         file_contents,
+    #         [Result.from_values('LicenseCheckBear',
+    #                             'No license found.',
+    #                             file=get_testfile_path('copyright_without_'
+    #                                                    'license.py'))],
+    #         filename=get_testfile_path('copyright_without_license.py'),
+    #         settings={'licensecheck_lines': 0,
+    #                   'licensecheck_tail': 0})  # Parse entire file
+    #
+    # def no_license(self):
+    #     file_contents = load_testfile('no_license.py')
+    #     self.check_results(
+    #         self.uut,
+    #         file_contents,
+    #         [Result.from_values('LicenseCheckBear',
+    #                             'No license found.',
+    #                             file=get_testfile_path('no_license.py'))],
+    #         filename=get_testfile_path('no_license.py'),
+    #         settings={'licensecheck_lines': 10})

tests/general/cloc_test_files/example1.cpp

@@ -0,0 +1,14 @@
+// This comments are for testing purpose.
+
+/*
+Just like any other programmer,
+This example file will also try to print only two words
+*/
+
+#include <cstdio>
+
+int main
+{
+    std::cout << "Hello World!" << std::endl;
+    return 0;
+}

tests/general/cloc_test_files/example2.py

@@ -0,0 +1,8 @@
+# This comments are for testing purpose
+# This program will just try to add two static numbers
+
+first = 5 # First number
+second = 10 # Second number
+
+sum = first + second
+

tests/general/cloc_test_files/example3.cpp

@@ -0,0 +1,13 @@
+#include <cstdio>
+
+#define PI 3.1415926
+using namespace std;
+
+
+int main()
+{
+	const double radii = 1.0;
+	const double area = PI * radii * radii;
+	cout << "Area for the circle with radii " << radii << " is " << area << endl;
+	return 0;
+}