[YoutubeDL] Add support for string formatting operations in output template

2 files changed, 49 insertions, 1 deletions

diff --git a/test/test_YoutubeDL.py b/test/test_YoutubeDL.py
index 2cfcf743a..8491a88bd 100644
--- a/test/test_YoutubeDL.py
+++ b/test/test_YoutubeDL.py
@@ -526,6 +526,7 @@ class TestYoutubeDL(unittest.TestCase):
             'id': '1234',
             'ext': 'mp4',
             'width': None,
+            'height': 1080,
         }
 
         def fname(templ):
@@ -535,6 +536,19 @@ class TestYoutubeDL(unittest.TestCase):
         self.assertEqual(fname('%(id)s-%(width)s.%(ext)s'), '1234-NA.mp4')
         # Replace missing fields with 'NA'
         self.assertEqual(fname('%(uploader_date)s-%(id)s.%(ext)s'), 'NA-1234.mp4')
+        self.assertEqual(fname('%(height)d.%(ext)s'), '1080.mp4')
+        self.assertEqual(fname('%(height)6d.%(ext)s'), '  1080.mp4')
+        self.assertEqual(fname('%(height)-6d.%(ext)s'), '1080  .mp4')
+        self.assertEqual(fname('%(height)06d.%(ext)s'), '001080.mp4')
+        self.assertEqual(fname('%(height) 06d.%(ext)s'), ' 01080.mp4')
+        self.assertEqual(fname('%(height)   06d.%(ext)s'), ' 01080.mp4')
+        self.assertEqual(fname('%(height)0 6d.%(ext)s'), ' 01080.mp4')
+        self.assertEqual(fname('%(height)0   6d.%(ext)s'), ' 01080.mp4')
+        self.assertEqual(fname('%(height)   0   6d.%(ext)s'), ' 01080.mp4')
+        self.assertEqual(fname('%%(height)06d.%(ext)s'), '%(height)06d.mp4')
+        self.assertEqual(fname('%(width)06d.%(ext)s'), 'NA.mp4')
+        self.assertEqual(fname('%(width)06d.%%(ext)s'), 'NA.%(ext)s')
+        self.assertEqual(fname('%%(width)06d.%(ext)s'), '%(width)06d.mp4')
 
     def test_format_note(self):
         ydl = YoutubeDL()
diff --git a/youtube_dl/YoutubeDL.py b/youtube_dl/YoutubeDL.py
index 68000dea2..bdaf06e62 100755
--- a/youtube_dl/YoutubeDL.py
+++ b/youtube_dl/YoutubeDL.py
@@ -33,6 +33,7 @@ from .compat import (
     compat_get_terminal_size,
     compat_http_client,
     compat_kwargs,
+    compat_numeric_types,
     compat_os_name,
     compat_str,
     compat_tokenize_tokenize,
@@ -609,12 +610,45 @@ class YoutubeDL(object):
                 compat_str(v),
                 restricted=self.params.get('restrictfilenames'),
                 is_id=(k == 'id'))
-            template_dict = dict((k, sanitize(k, v))
+            template_dict = dict((k, v if isinstance(v, compat_numeric_types) else sanitize(k, v))
                                  for k, v in template_dict.items()
                                  if v is not None and not isinstance(v, (list, tuple, dict)))
             template_dict = collections.defaultdict(lambda: 'NA', template_dict)
 
             outtmpl = self.params.get('outtmpl', DEFAULT_OUTTMPL)
+
+            NUMERIC_FIELDS = set((
+                'width', 'height', 'tbr', 'abr', 'asr', 'vbr', 'fps', 'filesize', 'filesize_approx',
+                'upload_year', 'upload_month', 'upload_day',
+                'duration', 'view_count', 'like_count', 'dislike_count', 'repost_count',
+                'average_rating', 'comment_count', 'age_limit',
+                'start_time', 'end_time',
+                'chapter_number', 'season_number', 'episode_number',
+            ))
+
+            # Missing numeric fields used together with integer presentation types
+            # in format specification will break the argument substitution since
+            # string 'NA' is returned for missing fields. We will patch output
+            # template for missing fields to meet string presentation type.
+            for numeric_field in NUMERIC_FIELDS:
+                if numeric_field not in template_dict:
+                    # As of [1] format syntax is:
+                    #  %[mapping_key][conversion_flags][minimum_width][.precision][length_modifier]type
+                    # 1. https://docs.python.org/2/library/stdtypes.html#string-formatting
+                    FORMAT_RE = r'''(?x)
+                        (?<!%)
+                        %
+                        \({0}\)  # mapping key
+                        (?:[#0\-+ ]+)?  # conversion flags (optional)
+                        (?:\d+)?  # minimum field width (optional)
+                        (?:\.\d+)?  # precision (optional)
+                        [hlL]?  # length modifier (optional)
+                        [diouxXeEfFgGcrs%]  # conversion type
+                    '''
+                    outtmpl = re.sub(
+                        FORMAT_RE.format(numeric_field),
+                        r'%({0})s'.format(numeric_field), outtmpl)
+
             tmpl = compat_expanduser(outtmpl)
             filename = tmpl % template_dict
             # Temporary fix for #4787