Add usage of NZB-meta data and X-headers for Sorting.

Meta records: "episodename", "propername" and "year".
X-headers: "x-dnzb-episodename", "x-dnzb-propername" and "x-dnzb-year".
Controlled by an option.

sabnzbd/cfg.py

@@ -128,6 +128,7 @@ folder_rename = OptionBool('misc', 'folder_rename', True)
 folder_max_length = OptionNumber('misc', 'folder_max_length', DEF_FOLDER_MAX, 20, 65000)
 pause_on_pwrar = OptionBool('misc', 'pause_on_pwrar', True)
 prio_sort_list = OptionList('misc', 'prio_sort_list')
+enable_meta = OptionBool('misc', 'enable_meta', True)
 
 safe_postproc = OptionBool('misc', 'safe_postproc', True)
 empty_postproc = OptionBool('misc', 'empty_postproc', False)

sabnzbd/interface.py

@@ -1231,8 +1231,8 @@ SPECIAL_BOOL_LIST = \
               'never_repair', 'allow_streaming', 'ignore_unrar_dates', 'rss_filenames',
               'osx_menu', 'osx_speed', 'win_menu', 'uniconfig', 'use_pickle', 'allow_incomplete_nzb',
               'randomize_server_ip', 'no_ipv6', 'keep_awake', 'overwrite_files', 'empty_postproc',
-              'web_watchdog', 'wait_for_dfolder', 'warn_empty_nzb', 'enable_recursive', 'sanitize_safe'
+              'web_watchdog', 'wait_for_dfolder', 'warn_empty_nzb', 'enable_recursive', 'sanitize_safe',
-
+              'enable_meta'
             )
 SPECIAL_VALUE_LIST = \
             ( 'size_limit', 'folder_max_length', 'fsys_type', 'movie_rename_limit', 'nomedia_marker',

sabnzbd/postproc.py

@@ -307,7 +307,10 @@ def process_job(nzo):
                 complete_dir = real_path(cfg.complete_dir.get_path(), catdir)
 
             ## TV/Movie/Date Renaming code part 1 - detect and construct paths
-            file_sorter = Sorter(cat)
+            if cfg.enable_meta():
+                file_sorter = Sorter(nzo, cat)
+            else:
+                file_sorter = Sorter(None, cat)
             complete_dir = file_sorter.detect(dirname, complete_dir)
             if file_sorter.sort_file:
                 one_folder = False

sabnzbd/tvsort.py

@@ -31,7 +31,7 @@ from sabnzbd.misc import move_to_path, cleanup_empty_directories, get_unique_pat
                          get_unique_filename, get_ext, renamer, sanitize_foldername
 from sabnzbd.constants import series_match, date_match, year_match, sample_match
 import sabnzbd.cfg as cfg
-from sabnzbd.encoding import titler
+from sabnzbd.encoding import titler, latin1
 
 RE_SAMPLE = re.compile(sample_match, re.I)
 # Do not rename .vob files as they are usually DVD's
@@ -96,31 +96,32 @@ def move_to_parent_folder(workdir):
 class Sorter(object):
     """ Generic Sorter class
     """
-    def __init__(self, cat):
+    def __init__(self, nzo, cat):
         self.sorter = None
         self.type = None
         self.sort_file = False
+        self.nzo = nzo
         self.cat = cat
         self.ext = ''
 
     def detect(self, dirname, complete_dir):
         """ Detect which kind of sort applies
         """
-        self.sorter = SeriesSorter(dirname, complete_dir, self.cat)
+        self.sorter = SeriesSorter(self.nzo, dirname, complete_dir, self.cat)
         if self.sorter.matched:
             complete_dir = self.sorter.get_final_path()
             self.type = 'tv'
             self.sort_file = True
             return complete_dir
 
-        self.sorter = DateSorter(dirname, complete_dir, self.cat)
+        self.sorter = DateSorter(self.nzo, dirname, complete_dir, self.cat)
         if self.sorter.matched:
             complete_dir = self.sorter.get_final_path()
             self.type = 'date'
             self.sort_file = True
             return complete_dir
 
-        self.sorter = GenericSorter(dirname, complete_dir, self.cat)
+        self.sorter = GenericSorter(self.nzo, dirname, complete_dir, self.cat)
         if self.sorter.matched:
             complete_dir = self.sorter.get_final_path()
             self.type = 'movie'
@@ -182,11 +183,12 @@ class Sorter(object):
 class SeriesSorter(object):
     """ Methods for Series Sorting
     """
-    def __init__(self, dirname, path, cat):
+    def __init__(self, nzo, dirname, path, cat):
         self.matched = False
 
         self.original_dirname = dirname
         self.original_path = path
+        self.nzo = nzo
         self.cat = cat
         self.sort_string = cfg.tv_sort_string()
         self.cats = cfg.tv_categories()
@@ -252,8 +254,8 @@ class SeriesSorter(object):
     def get_shownames(self):
         ''' Get the show name from the match object and format it '''
         # Get the formatted title and alternate title formats
-        self.show_info['show_tname'], self.show_info['show_tname_two'], self.show_info['show_tname_three'] = get_titles(self.match_obj, self.original_dirname, True)
+        self.show_info['show_tname'], self.show_info['show_tname_two'], self.show_info['show_tname_three'] = get_titles(self.nzo, self.match_obj, self.original_dirname, True)
-        self.show_info['show_name'], self.show_info['show_name_two'], self.show_info['show_name_three'] = get_titles(self.match_obj, self.original_dirname)
+        self.show_info['show_name'], self.show_info['show_name_two'], self.show_info['show_name_three'] = get_titles(self.nzo, self.match_obj, self.original_dirname)
 
 
     def get_seasons(self):
@@ -302,7 +304,7 @@ class SeriesSorter(object):
 
     def get_showdescriptions(self):
         ''' Get the show descriptions from the match object and format them '''
-        self.show_info['ep_name'], self.show_info['ep_name_two'], self.show_info['ep_name_three'] = get_descriptions(self.match_obj, self.original_dirname)
+        self.show_info['ep_name'], self.show_info['ep_name_two'], self.show_info['ep_name_three'] = get_descriptions(self.nzo, self.match_obj, self.original_dirname)
 
 
     def get_values(self):
@@ -518,7 +520,7 @@ def check_for_sequence(regex, files):
 class GenericSorter(object):
     """ Methods for Generic Sorting
     """
-    def __init__(self, dirname, path, cat):
+    def __init__(self, nzo, dirname, path, cat):
         self.matched = False
 
         self.original_dirname = dirname
@@ -527,6 +529,7 @@ class GenericSorter(object):
         self.extra = cfg.movie_sort_extra()
         self.cats = cfg.movie_categories()
         self.cat = cat
+        self.nzo = nzo
         self.filename_set = ''
         self.fname = '' # Value for %fn substitution in folders
         self.final_path = ''
@@ -567,23 +570,30 @@ class GenericSorter(object):
         """ Collect and construct all the values needed for path replacement
         """
         ## - Get Year
-        dirname = self.original_dirname.replace('_', ' ')
+        if self.nzo:
-        RE_YEAR = re.compile(year_match, re.I)
+            year = self.nzo.nzo_info.get('year') or self.nzo.meta.get('year')[0]
-        year_m = RE_YEAR.search(dirname)
-        if year_m:
-            # Find the last matched date
-            # Keep year_m to use in get_titles
-            year = RE_YEAR.findall(dirname)[-1][0]
-            self.movie_info['year'] = year
         else:
-            self.movie_info['year'] = ''
+            year = ''
+        if year:
+            year_m = None
+        else:
+            dirname = self.original_dirname.replace('_', ' ')
+            RE_YEAR = re.compile(year_match, re.I)
+            year_m = RE_YEAR.search(dirname)
+            if year_m:
+                # Find the last matched date
+                # Keep year_m to use in get_titles
+                year = RE_YEAR.findall(dirname)[-1][0]
+            else:
+                year = ''
+        self.movie_info['year'] = year
 
         ## - Get Decades
-        self.movie_info['decade'], self.movie_info['decade_two'] = get_decades(self.movie_info['year'])
+        self.movie_info['decade'], self.movie_info['decade_two'] = get_decades(year)
 
         ## - Get Title
-        self.movie_info['ttitle'], self.movie_info['ttitle_two'], self.movie_info['ttitle_three'] = get_titles(year_m, self.original_dirname, True)
+        self.movie_info['ttitle'], self.movie_info['ttitle_two'], self.movie_info['ttitle_three'] = get_titles(self.nzo, year_m, self.original_dirname, True)
-        self.movie_info['title'], self.movie_info['title_two'], self.movie_info['title_three'] = get_titles(year_m, self.original_dirname)
+        self.movie_info['title'], self.movie_info['title_two'], self.movie_info['title_three'] = get_titles(self.nzo, year_m, self.original_dirname)
 
         return True
 
@@ -721,7 +731,7 @@ class GenericSorter(object):
 class DateSorter(object):
     """ Methods for Date Sorting
     """
-    def __init__(self, dirname, path, cat):
+    def __init__(self, nzo, dirname, path, cat):
         self.matched = False
 
         self.original_dirname = dirname
@@ -729,6 +739,7 @@ class DateSorter(object):
         self.sort_string = cfg.date_sort_string()
         self.cats = cfg.date_categories()
         self.cat = cat
+        self.nzo = nzo
         self.filename_set = ''
         self.fname = '' # Value for %fn substitution in folders
 
@@ -791,10 +802,10 @@ class DateSorter(object):
         self.date_info['decade'], self.date_info['decade_two'] = get_decades(self.date_info['year'])
 
         ## - Get Title
-        self.date_info['ttitle'], self.date_info['ttitle_two'], self.date_info['ttitle_three'] = get_titles(self.match_obj, self.original_dirname, True)
+        self.date_info['ttitle'], self.date_info['ttitle_two'], self.date_info['ttitle_three'] = get_titles(self.nzo, self.match_obj, self.original_dirname, True)
-        self.date_info['title'], self.date_info['title_two'], self.date_info['title_three'] = get_titles(self.match_obj, self.original_dirname)
+        self.date_info['title'], self.date_info['title_two'], self.date_info['title_three'] = get_titles(self.nzo, self.match_obj, self.original_dirname)
 
-        self.date_info['ep_name'], self.date_info['ep_name_two'], self.date_info['ep_name_three'] = get_descriptions(self.match_obj, self.original_dirname)
+        self.date_info['ep_name'], self.date_info['ep_name_two'], self.date_info['ep_name_three'] = get_descriptions(self.nzo, self.match_obj, self.original_dirname)
 
         return True
 
@@ -927,7 +938,7 @@ def path_subst(path, mapping):
     return ''.join(newpath)
 
 
-def get_titles(match, name, titleing=False):
+def get_titles(nzo, match, name, titleing=False):
     '''
     The title will be the part before the match
     Clean it up and title() it
@@ -935,59 +946,64 @@ def get_titles(match, name, titleing=False):
     ''.title() isn't very good under python so this contains
     a lot of little hacks to make it better and for more control
     '''
-    if match:
+    if nzo:
-        name = name[:match.start()]
+        title = latin1(nzo.nzo_info.get('propername') or nzo.meta.get('propername')[0])
-
+    else:
-    # Replace .US. with (US)
+        title = ''
-    if cfg.tv_sort_countries() == 1:
+    if not title:
-        for rep in COUNTRY_REP:
+        if match:
-            # (us) > (US)
+            name = name[:match.start()]
-            name = replace_word(name, rep.lower(), rep)
+    
-            # (Us) > (US)
+        # Replace .US. with (US)
-            name = replace_word(name, titler(rep), rep)
-            # .US. > (US)
-            dotted_country = '.%s.' % (rep.strip('()'))
-            name = replace_word(name, dotted_country, rep)
-    # Remove .US. and (US)
-    elif cfg.tv_sort_countries() == 2:
-        for rep in COUNTRY_REP:
-            # Remove (US)
-            name = replace_word(name, rep, '')
-            dotted_country = '.%s.' % (rep.strip('()'))
-            # Remove .US.
-            name = replace_word(name, dotted_country, '.')
-
-    title = name.replace('.', ' ').replace('_', ' ')
-    title = title.strip().strip('(').strip('_').strip('-').strip().strip('_')
-
-    if titleing:
-        title = titler(title) # title the show name so it is in a consistant letter case
-
-        #title applied uppercase to 's Python bug?
-        title = title.replace("'S", "'s")
-
-        # Replace titled country names, (Us) with (US) and so on
         if cfg.tv_sort_countries() == 1:
             for rep in COUNTRY_REP:
-                title = title.replace(titler(rep), rep)
+                # (us) > (US)
-        # Remove country names, ie (Us)
+                name = replace_word(name, rep.lower(), rep)
+                # (Us) > (US)
+                name = replace_word(name, titler(rep), rep)
+                # .US. > (US)
+                dotted_country = '.%s.' % (rep.strip('()'))
+                name = replace_word(name, dotted_country, rep)
+        # Remove .US. and (US)
         elif cfg.tv_sort_countries() == 2:
             for rep in COUNTRY_REP:
-                title = title.replace(titler(rep), '').strip()
+                # Remove (US)
-
+                name = replace_word(name, rep, '')
-        # Make sure some words such as 'and' or 'of' stay lowercased.
+                dotted_country = '.%s.' % (rep.strip('()'))
-        for x in LOWERCASE:
+                # Remove .US.
-            xtitled = titler(x)
+                name = replace_word(name, dotted_country, '.')
-            title = replace_word(title, xtitled, x)
+    
-
+        title = name.replace('.', ' ').replace('_', ' ')
-        # Make sure some words such as 'III' or 'IV' stay uppercased.
+        title = title.strip().strip('(').strip('_').strip('-').strip().strip('_')
-        for x in UPPERCASE:
+
-            xtitled = titler(x)
+        if titleing:
-            title = replace_word(title, xtitled, x)
+            title = titler(title) # title the show name so it is in a consistant letter case
-
+    
-        # Make sure the first letter of the title is always uppercase
+            #title applied uppercase to 's Python bug?
-        if title:
+            title = title.replace("'S", "'s")
-            title = titler(title[0]) + title[1:]
+    
+            # Replace titled country names, (Us) with (US) and so on
+            if cfg.tv_sort_countries() == 1:
+                for rep in COUNTRY_REP:
+                    title = title.replace(titler(rep), rep)
+            # Remove country names, ie (Us)
+            elif cfg.tv_sort_countries() == 2:
+                for rep in COUNTRY_REP:
+                    title = title.replace(titler(rep), '').strip()
+    
+            # Make sure some words such as 'and' or 'of' stay lowercased.
+            for x in LOWERCASE:
+                xtitled = titler(x)
+                title = replace_word(title, xtitled, x)
+    
+            # Make sure some words such as 'III' or 'IV' stay uppercased.
+            for x in UPPERCASE:
+                xtitled = titler(x)
+                title = replace_word(title, xtitled, x)
+    
+            # Make sure the first letter of the title is always uppercase
+            if title:
+                title = titler(title[0]) + title[1:]
 
     # The title with spaces replaced by dots
     dots = title.replace(" - ", "-").replace(' ','.').replace('_','.')
@@ -1007,22 +1023,27 @@ def replace_word(input, one, two):
             input = input.replace(one, two)
     return input
 
-def get_descriptions(match, name):
+def get_descriptions(nzo, match, name):
     '''
     If present, get a description from the nzb name.
     A description has to be after the matched item, seperated either
     like ' - Description' or '_-_Description'
     '''
-    if match:
+    if nzo:
-        ep_name = name[match.end():] # Need to improve for multi ep support
+        ep_name = latin1(nzo.nzo_info.get('episodename') or nzo.meta.get('episodename')[0])
     else:
-        ep_name = name
+        ep_name = ''
-    ep_name = ep_name.strip(' _.')
+    if not ep_name:
-    if ep_name.startswith('-'):
+        if match:
-        ep_name = ep_name.strip('- _.')
+            ep_name = name[match.end():] # Need to improve for multi ep support
-    if '.' in ep_name and ' ' not in ep_name:
+        else:
-        ep_name = ep_name.replace('.', ' ')
+            ep_name = name
-    ep_name = ep_name.replace('_', ' ')
+        ep_name = ep_name.strip(' _.')
+        if ep_name.startswith('-'):
+            ep_name = ep_name.strip('- _.')
+        if '.' in ep_name and ' ' not in ep_name:
+            ep_name = ep_name.replace('.', ' ')
+        ep_name = ep_name.replace('_', ' ')
     ep_name2 = ep_name.replace(" - ", "-").replace(" ", ".")
     ep_name3 = ep_name.replace(" ", "_")
     return ep_name, ep_name2, ep_name3
@@ -1189,13 +1210,13 @@ def eval_sort(sorttype, expression, name=None, multipart=''):
     name = sanitize_foldername(name)
     if sorttype == 'series':
         name = name or ('%s S01E05 - %s [DTS]' % (Ttemplate('show-name'), Ttemplate('ep-name')))
-        sorter = sabnzbd.tvsort.SeriesSorter(name, path, 'tv')
+        sorter = sabnzbd.tvsort.SeriesSorter(None, name, path, 'tv')
     elif sorttype == 'generic':
         name = name or (Ttemplate('movie-sp-name') + ' (2009)')
-        sorter = sabnzbd.tvsort.GenericSorter(name, path, 'tv')
+        sorter = sabnzbd.tvsort.GenericSorter(None, name, path, 'tv')
     elif sorttype == 'date':
         name = name or (Ttemplate('show-name') + ' 2009-01-02')
-        sorter = sabnzbd.tvsort.DateSorter(name, path, 'tv')
+        sorter = sabnzbd.tvsort.DateSorter(None, name, path, 'tv')
     else:
         return None
     sorter.sort_string = expression

sabnzbd/urlgrabber.py

@@ -147,6 +147,12 @@ class URLGrabber(Thread):
                             filename = value
                             if not filename.endswith('.nzb'):
                                 filename += '.nzb'
+                        elif item == 'x-dnzb-propername':
+                            nzo_info['propername'] = value
+                        elif item == 'x-dnzb-episodename':
+                            nzo_info['episodename'] = value
+                        elif item == 'x-dnzb-year':
+                            nzo_info['year'] = value
                         elif item in ('content-length',):
                             length = misc.int_conv(value)