DocBaseClass: Add DocBaseClass

Add DocBaseClass
Merge DocumentationExtraction with DocBaseClass
Closes #2659

Author: damngamerz

…documentation/DocumentationExtraction.py …/languages/documentation/DocBaseClass.pycoalib/bearlib/languages/documentation/DocumentationExtraction.py renamed to coalib/bearlib/languages/documentation/DocBaseClass.py coalib/bearlib/languages/documentation/DocumentationExtraction.py renamed to coalib/bearlib/languages/documentation/DocBaseClass.py

@@ -4,6 +4,8 @@
     DocstyleDefinition)
 from coalib.bearlib.languages.documentation.DocumentationComment import (
     DocumentationComment)
+from coalib.results.Diff import Diff
+from coalib.results.TextRange import TextRange
 from coalib.results.TextPosition import TextPosition
 
 
@@ -254,31 +256,81 @@ def extract_documentation_with_markers(content, docstyle_definition):
             yield doc
 
 
-def extract_documentation(content, language, docstyle):
+class DocBaseClass:
     """
-    Extracts all documentation texts inside the given source-code-string using
-    the coala docstyle definition files.
-
-    The documentation texts are sorted by their order appearing in ``content``.
-
-    For more information about how documentation comments are identified and
-    extracted, see DocstyleDefinition.doctypes enumeration.
-
-    :param content:            The source-code-string where to extract
-                               documentation from. Needs to be a list or tuple
-                               where each string item is a single line
-                               (including ending whitespaces like ``\\n``).
-    :param language:           The programming language used.
-    :param docstyle:           The documentation style/tool used
-                               (e.g. doxygen).
-    :raises FileNotFoundError: Raised when the docstyle definition file was not
-                               found.
-    :raises KeyError:          Raised when the given language is not defined in
-                               given docstyle.
-    :raises ValueError:        Raised when a docstyle definition setting has an
-                               invalid format.
-    :return:                   An iterator returning each DocumentationComment
-                               found in the content.
+    DocBaseClass holds important functions which will extract, parse
+    and generates diffs for documentation. All bears that processes
+    documentation should inherit from this.
     """
-    docstyle_definition = DocstyleDefinition.load(language, docstyle)
-    return extract_documentation_with_markers(content, docstyle_definition)
+
+    @staticmethod
+    def extract(content, language, docstyle):
+        """
+        Extracts all documentation texts inside the given source-code-string
+        using the coala docstyle definition files.
+
+        The documentation texts are sorted by their order appearing in
+        ``content``.
+
+        For more information about how documentation comments are
+        identified and extracted, see DocstyleDefinition.doctypes enumeration.
+
+        :param content:            The source-code-string where to extract
+                                   documentation from. Needs to be a list
+                                   or tuple where each string item is a
+                                   single line(including ending whitespaces
+                                   like ``\\n``).
+        :param language:           The programming language used.
+        :param docstyle:           The documentation style/tool used
+                                   (e.g. doxygen).
+        :raises FileNotFoundError: Raised when the docstyle definition file
+                                   was not found.
+        :raises KeyError:          Raised when the given language is not
+                                   defined in given docstyle.
+        :raises ValueError:        Raised when a docstyle definition setting
+                                   has an invalid format.
+        :return:                   An iterator returning each
+                                   DocumentationComment found in the content.
+        """
+        docstyle_definition = DocstyleDefinition.load(language, docstyle)
+        return extract_documentation_with_markers(
+                        content, docstyle_definition)
+
+    @staticmethod
+    def generate_diff(file, doc_comment, new_comment):
+        """
+        Generates diff between the original doc_comment and its fix
+        new_comment which are instances of DocumentationComment.
+
+        :param doc_comment:
+            Original instance of DocumentationComment.
+        :param new_comment:
+            Fixed instance of DocumentationComment.
+        :return:
+            Diff instance.
+        """
+        diff = Diff(file)
+
+        # We need to update old comment positions, as `assemble()`
+        # prepends indentation for first line.
+        old_range = TextRange.from_values(
+            doc_comment.range.start.line,
+            1,
+            doc_comment.range.end.line,
+            doc_comment.range.end.column)
+
+        # Clearing cached assemble() so a fresh one is fetched.
+        new_comment.assemble.cache_clear()
+
+        diff.replace(old_range, new_comment.assemble())
+        return diff
+
+    def process_documentation(self, *args, **kwargs):
+        """
+        Checks and handles the fixing part of documentation.
+
+        :return:
+            A tuple of processed documentation and warning_desc.
+        """
+        raise NotImplementedError('This function has to be implemented for a '
+                                  'documentation bear.')

…mentation/DocumentationExtractionTest.py …guages/documentation/DocBaseClassTest.pytests/bearlib/languages/documentation/DocumentationExtractionTest.py renamed to tests/bearlib/languages/documentation/DocBaseClassTest.py tests/bearlib/languages/documentation/DocumentationExtractionTest.py renamed to tests/bearlib/languages/documentation/DocBaseClassTest.py

@@ -4,25 +4,28 @@
     DocstyleDefinition)
 from coalib.bearlib.languages.documentation.DocumentationComment import (
     DocumentationComment)
-from coalib.bearlib.languages.documentation.DocumentationExtraction import (
-    extract_documentation)
+from coalib.bearlib.languages.documentation.DocBaseClass import (
+    DocBaseClass)
 from tests.bearlib.languages.documentation.TestUtils import (
     load_testdata)
 from coalib.results.TextPosition import TextPosition
+from coalib.results.TextRange import TextRange
+from coalib.results.Diff import Diff
 
 
-class DocumentationExtractionTest(unittest.TestCase):
+class DocBaseClassTest(unittest.TestCase):
+
+    def test_DocBaseClass_extraction_invalid_input(self):
 
-    def test_extract_documentation_invalid_input(self):
         with self.assertRaises(FileNotFoundError):
-            tuple(extract_documentation('', 'PYTHON', 'INVALID'))
+            tuple(DocBaseClass.extract('', 'PYTHON', 'INVALID'))
 
-    def test_extract_documentation_C(self):
+    def test_DocBaseClass_extraction_C(self):
         data = load_testdata('data.c')
 
         # No built-in documentation for C.
         with self.assertRaises(KeyError):
-            tuple(extract_documentation(data, 'C', 'default'))
+            tuple(DocBaseClass.extract(data, 'C', 'default'))
 
         docstyle_C_doxygen = DocstyleDefinition.load('C', 'doxygen')
 
@@ -59,31 +62,31 @@ def test_extract_documentation_C(self):
                                 TextPosition(28, 1)))
 
         self.assertEqual(tuple(
-            extract_documentation(data, 'C', 'doxygen')),
+            DocBaseClass.extract(data, 'C', 'doxygen')),
             expected_results)
 
-    def test_extract_documentation_C_2(self):
+    def test_DocBaseClass_extraction_C_2(self):
         data = ['/** my main description\n', ' * continues here */']
 
         docstyle_C_doxygen = DocstyleDefinition.load('C', 'doxygen')
 
         self.assertEqual(
-            list(extract_documentation(data, 'C', 'doxygen')),
+            list(DocBaseClass.extract(data, 'C', 'doxygen')),
             [DocumentationComment(' my main description\n continues here',
                                   docstyle_C_doxygen, '',
                                   docstyle_C_doxygen.markers[0],
                                   TextPosition(1, 1))])
 
-    def test_extract_documentation_CPP(self):
+    def test_DocBaseClass_extraction_CPP(self):
         data = load_testdata('data.cpp')
 
         # No built-in documentation for C++.
         with self.assertRaises(KeyError):
-            tuple(extract_documentation(data, 'CPP', 'default'))
+            tuple(DocBaseClass.extract(data, 'CPP', 'default'))
 
         docstyle_CPP_doxygen = DocstyleDefinition.load('CPP', 'doxygen')
 
-        self.assertEqual(tuple(extract_documentation(data, 'CPP', 'doxygen')),
+        self.assertEqual(tuple(DocBaseClass.extract(data, 'CPP', 'doxygen')),
                          (DocumentationComment(
                               ('\n'
                                ' This is the main function.\n'
@@ -118,20 +121,20 @@ def test_extract_documentation_CPP(self):
                               docstyle_CPP_doxygen.markers[4],
                               TextPosition(32, 1))))
 
-    def test_extract_documentation_CPP_2(self):
+    def test_DocBaseClass_CPP_2(self):
         data = load_testdata('data2.cpp')
 
         docstyle_CPP_doxygen = DocstyleDefinition.load('CPP', 'doxygen')
 
-        self.assertEqual(tuple(extract_documentation(data, 'CPP', 'doxygen')),
+        self.assertEqual(tuple(DocBaseClass.extract(data, 'CPP', 'doxygen')),
                          (DocumentationComment(
                           ('module comment\n'
                            ' hello world\n'),
                           docstyle_CPP_doxygen, '',
                           docstyle_CPP_doxygen.markers[0],
                           TextPosition(1, 1)),))
 
-    def test_extract_documentation_PYTHON3(self):
+    def test_DocBaseClass_PYTHON3(self):
         data = load_testdata('data.py')
         docstyle_PYTHON3_default = DocstyleDefinition.load('PYTHON3',
                                                            'default')
@@ -192,9 +195,8 @@ def test_extract_documentation_PYTHON3(self):
                     )
 
         self.assertEqual(
-            tuple(extract_documentation(data, 'PYTHON3', 'default')),
+            tuple(DocBaseClass.extract(data, 'PYTHON3', 'default')),
             expected)
-
         # Change only the docstyle in expected results.
         expected = list(DocumentationComment(r.documentation,
                                              docstyle_PYTHON3_doxygen,
@@ -214,37 +216,37 @@ def test_extract_documentation_PYTHON3(self):
             TextPosition(30, 1)))
 
         self.assertEqual(
-            list(extract_documentation(data, 'PYTHON3', 'doxygen')),
+            list(DocBaseClass.extract(data, 'PYTHON3', 'doxygen')),
             expected)
 
-    def test_extract_documentation_PYTHON3_2(self):
+    def test_DocBaseClass_extraction_PYTHON3_2(self):
         data = ['\n', '""" documentation in single line  """\n', 'print(1)\n']
 
         docstyle_PYTHON3_default = DocstyleDefinition.load('PYTHON3',
                                                            'default')
 
         self.assertEqual(
-            list(extract_documentation(data, 'PYTHON3', 'default')),
+            list(DocBaseClass.extract(data, 'PYTHON3', 'default')),
             [DocumentationComment(' documentation in single line  ',
                                   docstyle_PYTHON3_default, '',
                                   docstyle_PYTHON3_default.markers[0],
                                   TextPosition(2, 1))])
 
-    def test_extract_documentation_PYTHON3_3(self):
+    def test_DocBaseClass_extraction_PYTHON3_3(self):
         data = ['## documentation in single line without return at end.']
 
         docstyle_PYTHON3_doxygen = DocstyleDefinition.load('PYTHON3',
                                                            'doxygen')
 
         self.assertEqual(
-            list(extract_documentation(data, 'PYTHON3', 'doxygen')),
+            list(DocBaseClass.extract(data, 'PYTHON3', 'doxygen')),
             [DocumentationComment(' documentation in single line without '
                                   'return at end.',
                                   docstyle_PYTHON3_doxygen, '',
                                   docstyle_PYTHON3_doxygen.markers[1],
                                   TextPosition(1, 1))])
 
-    def test_extract_documentation_PYTHON3_4(self):
+    def test_DocBaseClass_extraction_PYTHON3_4(self):
         data = ['\n', 'triple_quote_string_test = """\n',
                 'This is not a docstring\n', '"""\n']
 
@@ -254,5 +256,35 @@ def test_extract_documentation_PYTHON3_4(self):
         # Nothing is yielded as triple quote string literals are being
         # ignored.
         self.assertEqual(
-            list(extract_documentation(data, 'PYTHON3', 'default')),
+            list(DocBaseClass.extract(data, 'PYTHON3', 'default')),
             [])
+
+    def test_generate_diff(self):
+        data_old = ['\n', '""" documentation in single line  """\n']
+        for doc_comment in DocBaseClass.extract(
+                                data_old, 'PYTHON3', 'default'):
+            old_doc_comment = doc_comment
+
+        old_range = TextRange.from_values(
+            old_doc_comment.range.start.line,
+            1,
+            old_doc_comment.range.end.line,
+            old_doc_comment.range.end.column)
+
+        data_new = ['\n', '"""\n documentation in single line\n"""\n']
+        for doc_comment in DocBaseClass.extract(
+                                data_new, 'PYTHON3', 'default'):
+            new_doc_comment = doc_comment
+
+        diff = DocBaseClass.generate_diff(
+                        data_old, old_doc_comment, new_doc_comment)
+
+        diff_expected = Diff(data_old)
+        diff_expected.replace(old_range, new_doc_comment.assemble())
+
+        self.assertEqual(diff, diff_expected)
+
+    def test_DocBaseClass_process_documentation_not_implemented(self):
+        test_object = DocBaseClass()
+        self.assertRaises(NotImplementedError,
+                          test_object.process_documentation)

tests/bearlib/languages/documentation/DocumentationCommentTest.py

@@ -4,8 +4,8 @@
     DocstyleDefinition)
 from coalib.bearlib.languages.documentation.DocumentationComment import (
     DocumentationComment)
-from coalib.bearlib.languages.documentation.DocumentationExtraction import (
-    extract_documentation)
+from coalib.bearlib.languages.documentation.DocBaseClass import (
+    DocBaseClass)
 from tests.bearlib.languages.documentation.TestUtils import (
     load_testdata)
 from coalib.results.TextPosition import TextPosition
@@ -72,7 +72,7 @@ def test_not_implemented(self):
     def test_from_metadata(self):
         data = load_testdata('default.py')
 
-        original = list(extract_documentation(data, 'python', 'default'))
+        original = list(DocBaseClass.extract(data, 'python', 'default'))
 
         parsed_docs = [(doc.parse(), doc.marker, doc.indent, doc.position)
                        for doc in original]
@@ -109,7 +109,8 @@ def test_empty_docstring(self):
 
     def test_description(self):
         doc = ' description only '
-        self.check_docstring(doc, [self.Description(desc=' description only ')])
+        self.check_docstring(
+            doc, [self.Description(desc=' description only ')])
 
     def test_params_default(self):
         self.maxDiff = None
@@ -139,7 +140,7 @@ def test_python_default(self):
         data = load_testdata('default.py')
 
         parsed_docs = [doc.parse() for doc in
-                       extract_documentation(data, 'python', 'default')]
+                       DocBaseClass.extract(data, 'python', 'default')]
 
         expected = [
             [self.Description(desc='\nModule description.\n\n'
@@ -188,7 +189,7 @@ def test_python_doxygen(self):
         data = load_testdata('doxygen.py')
 
         parsed_docs = [doc.parse() for doc in
-                       extract_documentation(data, 'python', 'doxygen')]
+                       DocBaseClass.extract(data, 'python', 'doxygen')]
 
         expected = [
             [self.Description(desc=' @package pyexample\n  Documentation for'
@@ -232,7 +233,7 @@ def test_java_default(self):
         data = load_testdata('default.java')
 
         parsed_docs = [doc.parse() for doc in
-                       extract_documentation(data, 'java', 'default')]
+                       DocBaseClass.extract(data, 'java', 'default')]
 
         expected = [[self.Description(
                      desc='\n Returns an String that says Hello with the name'
@@ -253,7 +254,7 @@ def test_go_default(self):
         data = load_testdata('default.go')
 
         parsed_docs = [doc.parse() for doc in
-                       extract_documentation(data, 'golang', 'golang')]
+                       DocBaseClass.extract(data, 'golang', 'golang')]
 
         expected = [['\n',
                      'Comments may span\n',
@@ -272,19 +273,19 @@ def test_python_assembly(self):
         data = load_testdata('default.py')
         docs = ''.join(data)
 
-        for doc in extract_documentation(data, 'python', 'default'):
+        for doc in DocBaseClass.extract(data, 'python', 'default'):
             self.assertIn(doc.assemble(), docs)
 
     def test_doxygen_assembly(self):
         data = load_testdata('doxygen.py')
         docs = ''.join(data)
 
-        for doc in extract_documentation(data, 'python', 'doxygen'):
+        for doc in DocBaseClass.extract(data, 'python', 'doxygen'):
             self.assertIn(doc.assemble(), docs)
 
     def test_c_assembly(self):
         data = load_testdata('default.c')
         docs = ''.join(data)
 
-        for doc in extract_documentation(data, 'c', 'doxygen'):
+        for doc in DocBaseClass.extract(data, 'c', 'doxygen'):
             self.assertIn(doc.assemble(), docs)