Added support for Julia language

nirjas/languages/__init__.py

@@ -46,4 +46,5 @@
     "swift",
     "text",
     "typescript",
+    "julia",
 ]

nirjas/languages/julia.py

@@ -0,0 +1,140 @@
+#!/usr/bin/env python3
+# -*- coding: utf-8 -*-
+"""
+Copyright (C) 2020  Soham Banerjee (sohambanerjee4abc@hotmail.com),
+
+SPDX-License-Identifier: LGPL-2.1
+
+This library is free software; you can redistribute it and/or
+modify it under the terms of the GNU Lesser General Public
+License as published by the Free Software Foundation; either
+version 2.1 of the License, or (at your option) any later version.
+
+This library is distributed in the hope that it will be useful,
+but WITHOUT ANY WARRANTY; without even the implied warranty of
+MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+Lesser General Public License for more details.
+
+You should have received a copy of the GNU Lesser General Public
+License along with this library; if not, write to the Free Software
+Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA  02110-1301  USA
+"""
+
+from nirjas.binder import CommentSyntax, contSingleLines
+from nirjas.output import ScanOutput, SingleLine, MultiLine
+
+
+def juliaExtractor(file):
+    """
+    Extract comments from julia file.
+    :param file: File to scan
+    :type file: string
+    :return: Scan output
+    :rtype: ScanOutput
+    """
+    result = CommentSyntax()
+    single_line_comment = result.hash(file)
+    multiline_single_comment = result.singleQuotes(file)
+    multiline_double_comment = result.doubleQuotes(file)
+    cont_single_line_comment = contSingleLines(single_line_comment)
+    file = file.split("/")
+    output = ScanOutput()
+    output.filename = file[-1]
+    output.lang = "Julia"
+    output.total_lines = single_line_comment[1]
+    output.total_lines_of_comments = (
+        single_line_comment[3] + multiline_single_comment[3] + multiline_double_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_single_comment[0]):
+            output.multi_line_comment.append(
+                MultiLine(
+                    multiline_single_comment[0][idx],
+                    multiline_single_comment[1][idx],
+                    multiline_single_comment[2][idx],
+                )
+            )
+    except BaseException:
+        pass
+
+    try:
+        for idx, _ in enumerate(multiline_double_comment[0]):
+            output.multi_line_comment.append(
+                MultiLine(
+                    multiline_double_comment[0][idx],
+                    multiline_double_comment[1][idx],
+                    multiline_double_comment[2][idx],
+                )
+            )
+    except BaseException:
+        pass
+
+    return output
+
+
+def juliaSource(file, new_file: str):
+    """
+    Extract source from Julia file and put at new_file.
+    :param file: File to process
+    :type file: string
+    :param new_file: File to put source at
+    :type new_file: string
+    :return: Path to new file
+    :rtype: string
+    """
+    copy = True
+    with open(new_file, "w+") as f1:
+        with open(file) as f:
+            for line in f:
+                content = ""
+                found = False
+                if '"""' in line:
+                    if copy:
+                        pos = line.find('"""')
+                        content = line[:pos].rstrip()
+                        line = line[pos:]
+                        copy = False
+                        found = True
+                    else:
+                        content = content + line[line.rfind('"""') + 3:]
+                        line = content
+                        copy = True
+                        found = True
+                if "'''" in line:
+                    if copy:
+                        pos = line.find("'''")
+                        content = line[:pos].rstrip()
+                        line = line[pos:]
+                        copy = False
+                        found = True
+                    else:
+                        content = content + line[line.rfind("'''") + 3:]
+                        line = content
+                        copy = True
+                        found = True
+                if "#" in line:
+                    content = line[: line.find("#")].rstrip() + "\n"
+                    found = True
+                if not found:
+                    content = line
+                if copy and content.strip() != "":
+                    f1.write(content)
+    f.close()
+    f1.close()
+    return new_file

nirjas/languages/tests/test_julia.py

@@ -0,0 +1,131 @@
+#!/usr/bin/env python3
+# -*- coding: utf-8 -*-
+"""
+SPDX-License-Identifier: LGPL-2.1
+
+This library is free software; you can redistribute it and/or
+modify it under the terms of the GNU Lesser General Public
+License as published by the Free Software Foundation; either
+version 2.1 of the License, or (at your option) any later version.
+
+This library is distributed in the hope that it will be useful,
+but WITHOUT ANY WARRANTY; without even the implied warranty of
+MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+Lesser General Public License for more details.
+
+You should have received a copy of the GNU Lesser General Public
+License along with this library; if not, write to the Free Software
+Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA  02110-1301  USA
+"""
+
+import unittest
+import os
+from nirjas.languages import julia
+from nirjas.binder import readSingleLine, readMultiLineSame, contSingleLines
+
+
+class JuliaTest(unittest.TestCase):
+    """
+    Test cases for Julia language.
+    :ivar testfile: Location of test file
+    """
+
+    testfile = os.path.join(
+        os.path.abspath(os.path.dirname(__file__)), "TestFiles/textcomment.jl"
+    )
+
+    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 test_outputFormat(self):
+        """
+        Check for the output format correctness.
+        """
+        regex = r"""(?<!["'`])#+\s*(.*)"""
+        syntax_single = "'''"
+        syntax_double = '"""'
+        expected = julia.juliaExtractor(self.testfile).get_dict()
+        comment_single = readSingleLine(self.testfile, regex)
+        comment_multi_single = readMultiLineSame(self.testfile, syntax_single)
+        comment_multi_double = readMultiLineSame(self.testfile, syntax_double)
+        comment_contSingleline = contSingleLines(comment_single)
+        file = self.testfile.split("/")
+        output = {
+            "metadata": {
+                "filename": file[-1],
+                "lang": "Julia",
+                "total_lines": comment_single[1],
+                "total_lines_of_comments": comment_single[3] + comment_multi_single[3] + comment_multi_double[3],
+                "blank_lines": comment_single[2],
+                "sloc": comment_single[1] - (
+                    comment_single[3] + comment_multi_single[3] + comment_multi_double[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_multi_single:
+            for idx, _ in enumerate(comment_multi_single[0]):
+                output["multi_line_comment"].append(
+                    {
+                        "start_line": comment_multi_single[0][idx],
+                        "end_line": comment_multi_single[1][idx],
+                        "comment": comment_multi_single[2][idx],
+                    }
+                )
+
+        if comment_multi_double:
+            for idx, _ in enumerate(comment_multi_double[0]):
+                output["multi_line_comment"].append(
+                    {
+                        "start_line": comment_multi_double[0][idx],
+                        "end_line": comment_multi_double[1][idx],
+                        "comment": comment_multi_double[2][idx],
+                    }
+                )
+
+        self.assertEqual(output, expected)
+
+    def test_Source(self):
+        """
+        Test the source code extraction.
+        Call the source function and check if new file exists.
+        """
+        name = "source.txt"
+        newfile = julia.juliaSource(self.testfile, name)
+
+        self.assertTrue(newfile)

nirjas/main.py

@@ -86,6 +86,7 @@ class LanguageMapper:
         ".install": "text",
         ".OSS": "text",
         ".gl": "text",
+        ".jl": "julia",
     }
 
     @staticmethod

testScript.py

@@ -56,7 +56,8 @@ def download_files(cwd):
         "https://raw.githubusercontent.com/flutter/plugins/e61e9d45bcaadc3e409d529d30735cb4db75c5c5/packages/android_alarm_manager/lib/android_alarm_manager.dart",
         "https://raw.githubusercontent.com/microsoft/TypeScript/c33a14d66d0a452673ce77256e178bf84e875d2b/tests/cases/user/formik/index.tsx",
         "https://raw.githubusercontent.com/twbs/bootstrap/9488978fb55286ba83e8193a871d1ff9815045b9/scss/_reboot.scss",
-        "https://raw.githubusercontent.com/its-sushant/SQL/a4bf2972905c8df89d6a60752a2c60920a4b9465/check.sql"
+        "https://raw.githubusercontent.com/svaksha/Julia.jl/898f3d46c79a3b1fe939416fa96a8db9b2069596/src/scrape.jl",
+        "https://raw.githubusercontent.com/its-sushant/SQL/a4bf2972905c8df89d6a60752a2c60920a4b9465/check.sql",
     ]
 
     directory = os.path.join(cwd, "nirjas/languages/tests/TestFiles")