fixed some linting errors detected by pylint

.vscode/settings.json

@@ -2,8 +2,12 @@
 	"python.defaultInterpreterPath": "pymusco.venv/bin/python",
 	"pylint.args": [
 		"--disable=C0301",
+		"--disable=C0114",
 		"--disable=C0115",
 		"--disable=C0116",
 		"--generated-members=cv2.*"
+	],
+	"flake8.args": [
+		"--per-file-ignores=\"__init__.py:F401\""
 	]
 }

src/pymusco/core.py

@@ -30,7 +30,7 @@ def dict_raise_on_duplicates(ordered_pairs):
 
 def load_commented_json(commented_json_file_path):
     uncommented_json_contents = ''
-    with open(commented_json_file_path, 'rt') as file:
+    with open(commented_json_file_path, 'rt', encoding='utf-8') as file:
 
         for line in file.readlines():
             uncommented_line = re.sub('//.*$', '', line)
@@ -229,11 +229,9 @@ def load_orchestra(orchestra_file_path):
     return dict_to_orchestra(load_commented_json(orchestra_file_path))
 
 
-"""
-class Clef(Enum):
-    TREBLE = 1
-    BASS = 2
-"""
+# class Clef(Enum):
+#     TREBLE = 1
+#     BASS = 2
 
 
 class Track(object):
@@ -525,7 +523,7 @@ def find_page_number(page_contents_id: int, pdf_reader: PyPDF2.PdfReader):
         # print('looking for page with id %d' % page_contents_id)
         for page_index in range(len(pdf_reader.pages)):
             page_object = pdf_reader.pages[page_index]
-            assert isinstance(page_object, PyPDF2._page.PageObject)
+            assert isinstance(page_object, PyPDF2._page.PageObject)  # pylint: disable=protected-access
             # at this point, a page_object of the table of contents (with 23 links) looks like :
             # {'/Contents': IndirectObject(196, 0), '/Parent': IndirectObject(203, 0), '/Type': '/Page', '/Resources': IndirectObject(195, 0), '/MediaBox': [0, 0, 612, 792], '/Annots': [IndirectObject(171, 0), IndirectObject(172, 0), IndirectObject(173, 0), IndirectObject(174, 0), IndirectObject(175, 0), IndirectObject(176, 0), IndirectObject(177, 0), IndirectObject(178, 0), IndirectObject(179, 0), IndirectObject(180, 0), IndirectObject(181, 0), IndirectObject(182, 0), IndirectObject(183, 0), IndirectObject(184, 0), IndirectObject(185, 0), IndirectObject(186, 0), IndirectObject(187, 0), IndirectObject(188, 0), IndirectObject(189, 0), IndirectObject(190, 0), IndirectObject(191, 0), IndirectObject(192, 0), IndirectObject(193, 0)]}
             # while a normal page_object looks like

src/pymusco/main.py

@@ -40,7 +40,7 @@ def is_locked(filepath):
             print("Trying to open %s." % filepath)
             buffer_size = 8
             # Opening file in append mode and read the first 8 characters.
-            file_object = open(filepath, 'a', buffer_size)
+            file_object = open(filepath, 'a', buffer_size)  # pylint: disable=unspecified-encoding
             if file_object:
                 print("%s is not locked." % filepath)
                 locked = False
@@ -123,7 +123,7 @@ def get_image_file_paths(self):
 
 
 class StubContents(PdfContents):
-    def __init__(self, image_file_paths, toc, title, stamp_descs=[], page_info_line_y_pos=2.7):
+    def __init__(self, image_file_paths, toc, title, stamp_descs=None, page_info_line_y_pos=2.7):
         """
         creates a pdf file from a set of pages (either)
 
@@ -135,7 +135,7 @@ def __init__(self, image_file_paths, toc, title, stamp_descs=[], page_info_line_
         self.image_file_paths = image_file_paths
         self.toc = toc
         self._title = title
-        self._stamp_descs = stamp_descs
+        self._stamp_descs = stamp_descs if stamp_descs is not None else []
         self.page_footers = {}
         self.page_to_section = {}
         self.page_info_line_y_pos = page_info_line_y_pos
@@ -192,7 +192,7 @@ def images_to_pdf(pdf_contents, dst_pdf_file_path):
     tmp_dir.mkdir(parents=True, exist_ok=True)
 
     latex_file_path = tmp_dir / 'stub.tex'
-    with open(latex_file_path, 'w') as latex_file:
+    with open(latex_file_path, 'w', encoding='utf-8') as latex_file:
         page_to_footers = pdf_contents.get_page_footers()
         page_to_section = pdf_contents.get_sections()
         has_toc = len(page_to_section) > 0
@@ -307,7 +307,7 @@ def images_to_pdf(pdf_contents, dst_pdf_file_path):
         check_pdf(dst_pdf_file_path)
 
 
-def scan_to_stub(src_scanned_pdf_file_path, dst_stub_pdf_file_path, toc, title, orchestra, stamp_descs=[], page_info_line_y_pos=1.0):
+def scan_to_stub(src_scanned_pdf_file_path, dst_stub_pdf_file_path, toc, title, orchestra, stamp_descs=None, page_info_line_y_pos=1.0):
     """
     creates musical score stub from a musical score raw scan :
     - adds a table of contents
@@ -330,7 +330,7 @@ def scan_to_stub(src_scanned_pdf_file_path, dst_stub_pdf_file_path, toc, title,
         try:
             track = Track(track_id, orchestra)  # noqa:F841 @UnusedVariable  pylint: disable=unused-variable
         except KeyError as e:  # noqa:F841 pylint: disable=unused-variable
-            raise Exception("Failed to identify track id '%s'. Either its syntax is incorrect or the related instrument in not yet registered in the orchestra." % (track_id))
+            raise KeyError("Failed to identify track id '%s'. Either its syntax is incorrect or the related instrument in not yet registered in the orchestra." % (track_id)) from e
 
     # tmp_dir = tempfile.mkdtemp()
     tmp_dir = Path('/tmp/pymusco')
@@ -345,11 +345,11 @@ def scan_to_stub(src_scanned_pdf_file_path, dst_stub_pdf_file_path, toc, title,
             print('page_index = %d' % page_index)
             page = pdf_reader.pages[page_index]
             # image_file_path = extract_pdf_page_main_image(page, image_dir=tmp_dir, image_name=('page%03d' % page_index))
-            image_file_path = extract_pdf_page(page, image_dir=tmp_dir, image_name=('page%03d' % page_index))
+            image_file_path = extract_pdf_page(page, image_dir=tmp_dir, image_name='page%03d' % page_index)
 
             scanned_image_file_paths.append(image_file_path)
             # break
-
+    stamp_descs = stamp_descs if stamp_descs is not None else []
     images_to_pdf(StubContents(image_file_paths=scanned_image_file_paths, toc=toc, title=title, stamp_descs=stamp_descs, page_info_line_y_pos=page_info_line_y_pos), dst_stub_pdf_file_path)
 
 
@@ -369,7 +369,7 @@ def stub_to_print(src_stub_file_path, dst_print_file_path, track_selector, orche
     print(track_to_print_count)
     dst_print_file_path.parent.mkdir(parents=True, exist_ok=True)
 
-    with open(dst_print_file_path, 'wb') as print_file, open(dst_print_file_path.with_suffix('.log'), 'wt') as log_file:
+    with open(dst_print_file_path, 'wb') as print_file, open(dst_print_file_path.with_suffix('.log'), 'wt', encoding='utf-8') as log_file:
         print_pdf = PyPDF2.PdfWriter()
         log_file.write("contents of print file %s :\n\n" % dst_print_file_path)
         with open(src_stub_file_path, 'rb') as stub_file:
@@ -435,7 +435,7 @@ def stub_to_print(src_stub_file_path, dst_print_file_path, track_selector, orche
             print_pdf.write(print_file)
 
 
-def split_double_pages(src_scanned_pdf_file_path, dst_scanned_pdf_file_path, split_pos=[0.5]):
+def split_double_pages(src_scanned_pdf_file_path, dst_scanned_pdf_file_path, split_pos=[0.5]):  # pylint: disable=dangerous-default-value
     """
     :param list(float) split_pos: where to split the pages (ratio of the width of the double page). If this list contains more than one element, the positions are used sequencially and in a cyclic way
     """
@@ -520,14 +520,14 @@ def pdf_is_readable_by_pypdf2(src_pdf_path):
     with open(src_pdf_path, 'rb') as src_pdf_file:
         try:
             src_pdf = PyPDF2.PdfReader(src_pdf_file)
-            num_pages = len(src_pdf.pages)  # noqa:F841
+            num_pages = len(src_pdf.pages)  # noqa:F841 pylint: disable=unused-variable
             return True
         except NotImplementedError as error:
-            if error.message == "only algorithm code 1 and 2 are supported":
+            if str(error) == "only algorithm code 1 and 2 are supported":
                 return False
             else:
                 raise error
-        except PyPDF2.utils.PdfReadError as error:  # noqa:F841
+        except PyPDF2.errors.PdfReadError as error:  # noqa:F841 pylint: disable=unused-variable
             return False
 
 
@@ -555,7 +555,7 @@ def merge_pdf(dst_pdf_path, src_pdf_paths):
 
 
 def pdftk_is_available():
-    completed_process = subprocess.run(['pdftk'], stdout=subprocess.PIPE)
+    completed_process = subprocess.run(['pdftk'], stdout=subprocess.PIPE, check=False)
     return completed_process.returncode == 0
 
 
@@ -581,6 +581,6 @@ def remove_unneeded_pdf_password(src_pdf_path, dst_pdf_path):
     assert pdftk_is_available(), 'the pdftk command is missing. Please install it as it is required.'
 
     command = ['pdftk', src_pdf_path, 'input_pw', '', 'output', dst_pdf_path]
-    completed_process = subprocess.run(command, stdout=subprocess.PIPE, stderr=subprocess.PIPE)
+    completed_process = subprocess.run(command, stdout=subprocess.PIPE, stderr=subprocess.PIPE, check=False)
     assert completed_process.returncode == 0, "command failed : %s" % command
     # pdftk ./215-avengers-age-of-ultron/avengers-the-age-of-ultron-main-theme---piccolo.pdf input_pw '' output ~/toto/unsecured.pdf

src/pymusco/pdf.py

@@ -65,7 +65,7 @@ def extract_pdf_stream_image(pdf_stream, image_dir, image_name):
             CCITT_group = 4
         else:
             CCITT_group = 3
-        data = pdf_stream._data  # sorry, getData() does not work for CCITTFaxDecode
+        data = pdf_stream._data  # sorry, getData() does not work for CCITTFaxDecode pylint: disable=protected-access
         img_size = len(data)
         tiff_header = tiff_header_for_CCITT(width, height, img_size, CCITT_group)
         saved_image_file_path = (image_dir / image_name).with_suffix('.tiff')
@@ -392,14 +392,14 @@ def check_pdf(src_pdf_file_path):
                                 CCITT_group = 4
                             else:
                                 CCITT_group = 3
-                            data = pdf_stream._data  # sorry, getData() does not work for CCITTFaxDecode
+                            data = pdf_stream._data  # sorry, getData() does not work for CCITTFaxDecode  pylint: disable=protected-access
                             img_size = len(data)
-                            tiff_header = tiff_header_for_CCITT(width, height, img_size, CCITT_group)  # @UnusedVariable
+                            tiff_header = tiff_header_for_CCITT(width, height, img_size, CCITT_group)  # pylint: disable=unused-variable
                         else:
                             try:
                                 data = pdf_stream.getData()
                                 # on corrupt file, gives : raise utils.PdfReadError("Unable to find 'endstream' marker after stream at byte %s." % utils.hexStr(stream.tell()))
-                            except NotImplementedError as e:
+                            except NotImplementedError as e:  # pylint: disable=unused-variable
                                 continue
                             except AssertionError as e:
                                 _, _, tb = sys.exc_info()

src/pymusco/piece.py

@@ -54,9 +54,9 @@ def dict_to_stamp_desc(stamp_desc_as_dict, piece_desc_file_path):
     else:
         abs_stamp_file_path = piece_desc_file_path.parent.resolve() / stamp_file_path
     if not abs_stamp_file_path.exists():
-        raise Exception("The stamp file '%s' is missing (file not found)." % (abs_stamp_file_path))
+        raise FileNotFoundError("The stamp file '%s' is missing (file not found)." % (abs_stamp_file_path))
     if abs_stamp_file_path.suffix not in allowed_image_suffixes:
-        raise Exception("Unsupported image format for stamp '%s' (allowed formats : %s) " % (abs_stamp_file_path, str(allowed_image_suffixes)))
+        raise TypeError("Unsupported image format for stamp '%s' (allowed formats : %s) " % (abs_stamp_file_path, str(allowed_image_suffixes)))
     return StampDesc(file_path=abs_stamp_file_path,
                      scale=stamp_desc_as_dict['scale'],
                      tx=stamp_desc_as_dict['tx'],
@@ -132,7 +132,7 @@ def save_piece_description(piece, piece_desc_file_path):
         the path to the file describing the scanned pdf sheet music
     """
     piece_as_dict = piece_to_dict(piece)
-    with open(piece_desc_file_path, 'w') as file:
+    with open(piece_desc_file_path, 'w', encoding='utf-8') as file:
         json.dump(piece_as_dict, file)
 
 
@@ -147,7 +147,7 @@ def __init__(self, x, y):
 
 class Piece(object):
 
-    def __init__(self, uid, title, orchestra, scan_toc, missing_tracks={}, stamp_descs=[], page_info_line_y_pos=1.0):
+    def __init__(self, uid, title, orchestra, scan_toc, missing_tracks=None, stamp_descs=None, page_info_line_y_pos=1.0):
         """
         Parameters
         ----------
@@ -164,8 +164,8 @@ def __init__(self, uid, title, orchestra, scan_toc, missing_tracks={}, stamp_des
         self.title = title  # match.group('title')
         self.orchestra = orchestra
         self.scan_toc = scan_toc
-        self.missing_tracks = missing_tracks
-        self.stamp_descs = stamp_descs
+        self.missing_tracks = missing_tracks if missing_tracks is not None else {}
+        self.stamp_descs = stamp_descs if stamp_descs is not None else []
         self.page_info_line_y_pos = page_info_line_y_pos
         # self.stamp_scale = 0.5
         # self.stamp_pos = Vector2(14.0, 4.0)

test.py

@@ -191,4 +191,3 @@ def test(src_pdf_file_path, dst_pdf_file_path):
 stub_toc.shift_page_indices(NUM_TOC_PAGES)
 
 pymusco.stub_to_print(os.getcwd() + '/results/stubs/666-japanese-tango.pdf', os.getcwd() + '/results/prints/666-japanese-tango.pdf', track_selector, orchestra, stub_toc=stub_toc)
-