Video sort ignores punctuation #611

README.rst

@@ -46,7 +46,7 @@ Problems can be reported at `our GitHub page <https://github.com/axcore/tartube/
 
 Stable release: **v2.5.0 (3 Jan 2024)**
 
-Development release: **v2.5.0 (3 Jan 2024)**
+Development release: **v2.5.003 (8 Jan 2024)**
 
 Official packages (also available from the `Github release page <https://github.com/axcore/tartube/releases>`__):
 

VERSION

@@ -1 +1 @@
-2.5.0
+2.5.003

nsis/tartube_install_64bit.nsi

@@ -1,4 +1,4 @@
-# Tartube v2.5.0 installer script for MS Windows
+# Tartube v2.5.003 installer script for MS Windows
 #
 # Copyright (C) 2019-2024 A S Lewis
 #
@@ -294,7 +294,7 @@
 
     ;Name and file
     Name "Tartube"
-    OutFile "install-tartube-2.5.0-64bit.exe"
+    OutFile "install-tartube-2.5.003-64bit.exe"
 
     ;Default installation folder
     InstallDir "$LOCALAPPDATA\Tartube"
@@ -397,7 +397,7 @@ Section "Tartube" SecClient
 #        "Publisher" "A S Lewis"
 #    WriteRegStr HKLM \
 #        "Software\Microsoft\Windows\CurrentVersion\Uninstall\Tartube" \
-#        "DisplayVersion" "2.5.0"
+#        "DisplayVersion" "2.5.003"
 
     # Create uninstaller
     WriteUninstaller "$INSTDIR\Uninstall.exe"

pack/bin/no_download/tartube

@@ -44,8 +44,8 @@ import mainapp
 
 # 'Global' variables
 __packagename__ = 'tartube'
-__version__ = '2.5.0'
-__date__ = '3 Jan 2024'
+__version__ = '2.5.003'
+__date__ = '8 Jan 2024'
 __copyright__ = 'Copyright \xa9 2019-2024 A S Lewis'
 __license__ = """
 Copyright \xa9 2019-2024 A S Lewis.

pack/bin/pkg/tartube

@@ -44,8 +44,8 @@ import mainapp
 
 # 'Global' variables
 __packagename__ = 'tartube'
-__version__ = '2.5.0'
-__date__ = '3 Jan 2024'
+__version__ = '2.5.003'
+__date__ = '8 Jan 2024'
 __copyright__ = 'Copyright \xa9 2019-2024 A S Lewis'
 __license__ = """
 Copyright \xa9 2019-2024 A S Lewis.

pack/bin/strict/tartube

@@ -44,8 +44,8 @@ import mainapp
 
 # 'Global' variables
 __packagename__ = 'tartube'
-__version__ = '2.5.0'
-__date__ = '3 Jan 2024'
+__version__ = '2.5.003'
+__date__ = '8 Jan 2024'
 __copyright__ = 'Copyright \xa9 2019-2024 A S Lewis'
 __license__ = """
 Copyright \xa9 2019-2024 A S Lewis.

pack/tartube.1

@@ -1,4 +1,4 @@
-.TH man 1 "3 Jan 2024" "2.5.0" "tartube man page"
+.TH man 1 "8 Jan 2024" "2.5.003" "tartube man page"
 .SH NAME
 tartube \- GUI front-end for youtube-dl and yt-dlp
 .SH SYNOPSIS

setup.py

@@ -164,7 +164,7 @@
 # Setup
 setuptools.setup(
     name = 'tartube',
-    version = '2.5.0',
+    version = '2.5.003',
     description = 'GUI front-end for youtube-dl and yt-dlp',
     long_description = long_description,
     long_description_content_type = 'text/plain',

tartube/mainapp.py

@@ -37,6 +37,7 @@
 import platform
 import re
 import shutil
+import string
 import sys
 import threading
 import time
@@ -8267,6 +8268,22 @@ def update_db(self, version):
             for options_obj in self.ffmpeg_reg_dict.values():
                 options_obj.options_dict['extra_override_flag'] = False
 
+        if version < 2005002:       # v2.5.002
+
+            # This version updates each media.Video's .natname, to remove
+            #   punctuation and leading/trailing zeroes
+            for media_data_obj in self.media_reg_dict.values():
+                if isinstance(media_data_obj, media.Video):
+
+                    natname = media_data_obj.natname
+                    natname = natname.translate(
+                        str.maketrans('', '', string.punctuation)
+                    )
+                    natname = natname.strip()
+                    natname = re.sub(r'^[\s]+', ' ', natname)
+
+                    media_data_obj.natname = natname
+
         # --- Do this last, or the call to .check_integrity_db() fails -------
         # --------------------------------------------------------------------
 

tartube/media.py

@@ -29,6 +29,7 @@
 import functools
 import os
 import re
+import string
 import time
 
 
@@ -55,8 +56,9 @@ class GenericMedia(object):
     def get_natural_name(self, name):
 
         """Converts the specified name so it is suitable for so-called
-        'natural' sorting, adding leading zeroes and reducing to all-lower
-        case.
+        'natural' sorting, removing leading/trailing whitespace, remove
+        punctuation, adding leading zeroes to numbers, and reducing to
+        all-lower case.
 
         Based on the algorithm by Stephen Quan:
             https://stackoverflow.com/questions/4836710/
@@ -67,6 +69,10 @@ def get_natural_name(self, name):
 
         """
 
+        name = name.translate(str.maketrans('', '', string.punctuation))
+        name = name.strip()
+        name = re.sub(r'^[\s]+', ' ', name)
+
         return re.sub(
             r'\d+',
             lambda m: m.group(0).rjust(10, '0'), name
@@ -1892,7 +1898,8 @@ def __init__(self, app_obj, dbid, name, parent_obj=None, options_obj=None,
         # If the video's JSON data has not been fetched, self.name and
         #   self.nickname are the same
         self.nickname = name
-        # Modified version of self.nickname, padded with leading zeroes and
+        # Modified version of self.nickname, with leading/trailing whitespace
+        #   removed, punctuation removed, padded with leading zeroes and
         #   reduced to lower case; used in so-called 'natural' sorting of names
         self.natname = name
         # Download source (a URL)
@@ -3457,7 +3464,8 @@ def __init__(self, app_obj, dbid, name, parent_obj=None, options_obj=None):
         # Channel nickname (displayed in the Video Index; the same as .name,
         #   unless the user changes it)
         self.nickname = name
-        # Modified version of self.nickname, padded with leading zeroes and
+        # Modified version of self.nickname, with leading/trailing whitespace
+        #   removed, punctuation removed, padded with leading zeroes and
         #   reduced to lower case; used in so-called 'natural' sorting of names
         self.natname = name
         # Download source (a URL)
@@ -3802,7 +3810,8 @@ def __init__(self, app_obj, dbid, name, parent_obj=None, options_obj=None):
         # Playlist nickname (displayed in the Video Index; the same as .name,
         #   unless the user changes it)
         self.nickname = name
-        # Modified version of self.nickname, padded with leading zeroes and
+        # Modified version of self.nickname, with leading/trailing whitespace
+        #   removed, punctuation removed, padded with leading zeroes and
         #   reduced to lower case; used in so-called 'natural' sorting of names
         self.natname = name
         # Download source (a URL)
@@ -4167,7 +4176,8 @@ def __init__(self, app_obj, dbid, name, parent_obj=None, options_obj=None,
         #   unless the user changes it). Note that the nickname of a fixed
         #   folder can't be changed
         self.nickname = name
-        # Modified version of self.nickname, padded with leading zeroes and
+        # Modified version of self.nickname, with leading/trailing whitespace
+        #   removed, punctuation removed, padded with leading zeroes and
         #   reduced to lower case; used in so-called 'natural' sorting of names
         self.natname = name
 

tartube/tartube

@@ -44,8 +44,8 @@ import mainapp
 
 # 'Global' variables
 __packagename__ = 'tartube'
-__version__ = '2.5.0'
-__date__ = '3 Jan 2024'
+__version__ = '2.5.003'
+__date__ = '8 Jan 2024'
 __copyright__ = 'Copyright \xa9 2019-2024 A S Lewis'
 __license__ = """
 Copyright \xa9 2019-2024 A S Lewis.

tartube/utils.py

@@ -34,6 +34,7 @@
 import re
 import requests
 import shutil
+import string
 import subprocess
 import sys
 import time
@@ -2008,9 +2009,11 @@ def extract_timestamps_from_descrip(app_obj, descrip):
             # Remove punctuation in the title, such as the hyphen in a line
             #   like 'Intro - 15.52', and strip leading/trailing whitespace
             if title != '':
-                # !!! DEBUG This is not yet tested on other alphabets
-                title = re.sub(r'\s\W+\s', ' ', title)
-                title = strip_whitespace(title)
+                title = title.translate(
+                    str.maketrans('', '', string.punctuation),
+                )
+                title = title.strip()
+                title = re.sub(r'^[\s]+', ' ', title)
 
             # Use None as the title, rather than an empty string
             if title == '':