X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;f=youtube_dl%2Futils.py;h=a2746b2d1f0106ab9d9e651250a070df34af2d11;hb=aa5740fb61d388754e9278a3e38de12203c1b89d;hp=52f0dd09aac2ef0103212086a280fc317b36b82d;hpb=af14ded75e10653b4713c23f8c428c6cd88610ad;p=youtube-dl

diff --git a/youtube_dl/utils.py b/youtube_dl/utils.py
index 52f0dd09a..a2746b2d1 100644
--- a/youtube_dl/utils.py
+++ b/youtube_dl/utils.py
@@ -37,6 +37,7 @@ from .compat import (
     compat_chr,
     compat_html_entities,
     compat_http_client,
+    compat_kwargs,
     compat_parse_qs,
     compat_socket_create_connection,
     compat_str,
@@ -114,7 +115,7 @@ def write_json_file(obj, fn):
             'encoding': 'utf-8',
         })
 
-    tf = tempfile.NamedTemporaryFile(**args)
+    tf = tempfile.NamedTemporaryFile(**compat_kwargs(args))
 
     try:
         with tf:
@@ -312,27 +313,20 @@ def sanitize_path(s):
     """Sanitizes and normalizes path on Windows"""
     if sys.platform != 'win32':
         return s
-    drive, _ = os.path.splitdrive(s)
-    unc, _ = os.path.splitunc(s)
-    unc_or_drive = unc or drive
-    norm_path = os.path.normpath(remove_start(s, unc_or_drive)).split(os.path.sep)
-    if unc_or_drive:
+    drive_or_unc, _ = os.path.splitdrive(s)
+    if sys.version_info < (2, 7) and not drive_or_unc:
+        drive_or_unc, _ = os.path.splitunc(s)
+    norm_path = os.path.normpath(remove_start(s, drive_or_unc)).split(os.path.sep)
+    if drive_or_unc:
         norm_path.pop(0)
     sanitized_path = [
         path_part if path_part in ['.', '..'] else re.sub('(?:[/<>:"\\|\\\\?\\*]|\.$)', '#', path_part)
         for path_part in norm_path]
-    if unc_or_drive:
-        sanitized_path.insert(0, unc_or_drive + os.path.sep)
+    if drive_or_unc:
+        sanitized_path.insert(0, drive_or_unc + os.path.sep)
     return os.path.join(*sanitized_path)
 
 
-def sanitize_url_path_consecutive_slashes(url):
-    """Collapses consecutive slashes in URLs' path"""
-    parsed_url = list(compat_urlparse.urlparse(url))
-    parsed_url[2] = re.sub(r'/{2,}', '/', parsed_url[2])
-    return compat_urlparse.urlunparse(parsed_url)
-
-
 def orderedSet(iterable):
     """ Remove all duplicates from the input iterable """
     res = []
@@ -371,6 +365,18 @@ def unescapeHTML(s):
         r'&([^;]+);', lambda m: _htmlentity_transform(m.group(1)), s)
 
 
+def get_subprocess_encoding():
+    if sys.platform == 'win32' and sys.getwindowsversion()[0] >= 5:
+        # For subprocess calls, encode with locale encoding
+        # Refer to http://stackoverflow.com/a/9951851/35070
+        encoding = preferredencoding()
+    else:
+        encoding = sys.getfilesystemencoding()
+    if encoding is None:
+        encoding = 'utf-8'
+    return encoding
+
+
 def encodeFilename(s, for_subprocess=False):
     """
     @param s The name of the file
@@ -382,21 +388,24 @@ def encodeFilename(s, for_subprocess=False):
     if sys.version_info >= (3, 0):
         return s
 
-    if sys.platform == 'win32' and sys.getwindowsversion()[0] >= 5:
-        # Pass '' directly to use Unicode APIs on Windows 2000 and up
-        # (Detecting Windows NT 4 is tricky because 'major >= 4' would
-        # match Windows 9x series as well. Besides, NT 4 is obsolete.)
-        if not for_subprocess:
-            return s
-        else:
-            # For subprocess calls, encode with locale encoding
-            # Refer to http://stackoverflow.com/a/9951851/35070
-            encoding = preferredencoding()
-    else:
-        encoding = sys.getfilesystemencoding()
-    if encoding is None:
-        encoding = 'utf-8'
-    return s.encode(encoding, 'ignore')
+    # Pass '' directly to use Unicode APIs on Windows 2000 and up
+    # (Detecting Windows NT 4 is tricky because 'major >= 4' would
+    # match Windows 9x series as well. Besides, NT 4 is obsolete.)
+    if not for_subprocess and sys.platform == 'win32' and sys.getwindowsversion()[0] >= 5:
+        return s
+
+    return s.encode(get_subprocess_encoding(), 'ignore')
+
+
+def decodeFilename(b, for_subprocess=False):
+
+    if sys.version_info >= (3, 0):
+        return b
+
+    if not isinstance(b, bytes):
+        return b
+
+    return b.decode(get_subprocess_encoding(), 'ignore')
 
 
 def encodeArgument(s):
@@ -408,6 +417,10 @@ def encodeArgument(s):
     return encodeFilename(s, True)
 
 
+def decodeArgument(b):
+    return decodeFilename(b, True)
+
+
 def decodeOption(optval):
     if optval is None:
         return optval
@@ -452,6 +465,17 @@ def make_HTTPS_handler(params, **kwargs):
         return YoutubeDLHTTPSHandler(params, context=context, **kwargs)
 
 
+def bug_reports_message():
+    if ytdl_is_updateable():
+        update_cmd = 'type  youtube-dl -U  to update'
+    else:
+        update_cmd = 'see  https://yt-dl.org/update  on how to update'
+    msg = '; please report this issue on https://yt-dl.org/bug .'
+    msg += ' Make sure you are using the latest version; %s.' % update_cmd
+    msg += ' Be sure to call youtube-dl with the --verbose flag and include its complete output.'
+    return msg
+
+
 class ExtractorError(Exception):
     """Error during info extraction."""
 
@@ -467,13 +491,7 @@ class ExtractorError(Exception):
         if cause:
             msg += ' (caused by %r)' % cause
         if not expected:
-            if ytdl_is_updateable():
-                update_cmd = 'type  youtube-dl -U  to update'
-            else:
-                update_cmd = 'see  https://yt-dl.org/update  on how to update'
-            msg += '; please report this issue on https://yt-dl.org/bug .'
-            msg += ' Make sure you are using the latest version; %s.' % update_cmd
-            msg += ' Be sure to call youtube-dl with the --verbose flag and include its complete output.'
+            msg += bug_reports_message()
         super(ExtractorError, self).__init__(msg)
 
         self.traceback = tb
@@ -1104,15 +1122,6 @@ def shell_quote(args):
     return ' '.join(quoted_args)
 
 
-def takewhile_inclusive(pred, seq):
-    """ Like itertools.takewhile, but include the latest evaluated element
-        (the first element so that Not pred(e)) """
-    for e in seq:
-        yield e
-        if not pred(e):
-            return
-
-
 def smuggle_url(url, data):
     """ Pass additional data in a URL for internal use. """
 
@@ -1333,9 +1342,19 @@ def parse_duration(s):
     return res
 
 
-def prepend_extension(filename, ext):
+def prepend_extension(filename, ext, expected_real_ext=None):
+    name, real_ext = os.path.splitext(filename)
+    return (
+        '{0}.{1}{2}'.format(name, ext, real_ext)
+        if not expected_real_ext or real_ext[1:] == expected_real_ext
+        else '{0}.{1}'.format(filename, ext))
+
+
+def replace_extension(filename, ext, expected_real_ext=None):
     name, real_ext = os.path.splitext(filename)
-    return '{0}.{1}{2}'.format(name, ext, real_ext)
+    return '{0}.{1}'.format(
+        name if not expected_real_ext or real_ext[1:] == expected_real_ext else filename,
+        ext)
 
 
 def check_executable(exe, args=[]):
@@ -1354,7 +1373,7 @@ def get_exe_version(exe, args=['--version'],
     or False if the executable is not present """
     try:
         out, _ = subprocess.Popen(
-            [exe] + args,
+            [encodeArgument(exe)] + args,
             stdout=subprocess.PIPE, stderr=subprocess.STDOUT).communicate()
     except OSError:
         return False
@@ -1460,6 +1479,14 @@ def uppercase_escape(s):
         s)
 
 
+def lowercase_escape(s):
+    unicode_escape = codecs.getdecoder('unicode_escape')
+    return re.sub(
+        r'\\u[0-9a-fA-F]{4}',
+        lambda m: unicode_escape(m.group(0))[0],
+        s)
+
+
 def escape_rfc3986(s):
     """Escape non-ASCII characters as suggested by RFC 3986"""
     if sys.version_info < (3, 0) and isinstance(s, compat_str):
@@ -1638,6 +1665,7 @@ def mimetype2ext(mt):
     return {
         'x-ms-wmv': 'wmv',
         'x-mp4-fragmented': 'mp4',
+        'ttml+xml': 'ttml',
     }.get(res, res)
 
 
@@ -1795,6 +1823,267 @@ def match_filter_func(filter_str):
     return _match_func
 
 
+def parse_dfxp_time_expr(time_expr):
+    if not time_expr:
+        return 0.0
+
+    mobj = re.match(r'^(?P<time_offset>\d+(?:\.\d+)?)s?$', time_expr)
+    if mobj:
+        return float(mobj.group('time_offset'))
+
+    mobj = re.match(r'^(\d+):(\d\d):(\d\d(?:\.\d+)?)$', time_expr)
+    if mobj:
+        return 3600 * int(mobj.group(1)) + 60 * int(mobj.group(2)) + float(mobj.group(3))
+
+
+def srt_subtitles_timecode(seconds):
+    return '%02d:%02d:%02d,%03d' % (seconds / 3600, (seconds % 3600) / 60, seconds % 60, (seconds % 1) * 1000)
+
+
+def dfxp2srt(dfxp_data):
+    _x = functools.partial(xpath_with_ns, ns_map={
+        'ttml': 'http://www.w3.org/ns/ttml',
+        'ttaf1': 'http://www.w3.org/2006/10/ttaf1',
+    })
+
+    def parse_node(node):
+        str_or_empty = functools.partial(str_or_none, default='')
+
+        out = str_or_empty(node.text)
+
+        for child in node:
+            if child.tag in (_x('ttml:br'), _x('ttaf1:br'), 'br'):
+                out += '\n' + str_or_empty(child.tail)
+            elif child.tag in (_x('ttml:span'), _x('ttaf1:span'), 'span'):
+                out += str_or_empty(parse_node(child))
+            else:
+                out += str_or_empty(xml.etree.ElementTree.tostring(child))
+
+        return out
+
+    dfxp = xml.etree.ElementTree.fromstring(dfxp_data.encode('utf-8'))
+    out = []
+    paras = dfxp.findall(_x('.//ttml:p')) or dfxp.findall(_x('.//ttaf1:p')) or dfxp.findall('.//p')
+
+    if not paras:
+        raise ValueError('Invalid dfxp/TTML subtitle')
+
+    for para, index in zip(paras, itertools.count(1)):
+        begin_time = parse_dfxp_time_expr(para.attrib['begin'])
+        end_time = parse_dfxp_time_expr(para.attrib.get('end'))
+        if not end_time:
+            end_time = begin_time + parse_dfxp_time_expr(para.attrib['dur'])
+        out.append('%d\n%s --> %s\n%s\n\n' % (
+            index,
+            srt_subtitles_timecode(begin_time),
+            srt_subtitles_timecode(end_time),
+            parse_node(para)))
+
+    return ''.join(out)
+
+
+class ISO639Utils(object):
+    # See http://www.loc.gov/standards/iso639-2/ISO-639-2_utf-8.txt
+    _lang_map = {
+        'aa': 'aar',
+        'ab': 'abk',
+        'ae': 'ave',
+        'af': 'afr',
+        'ak': 'aka',
+        'am': 'amh',
+        'an': 'arg',
+        'ar': 'ara',
+        'as': 'asm',
+        'av': 'ava',
+        'ay': 'aym',
+        'az': 'aze',
+        'ba': 'bak',
+        'be': 'bel',
+        'bg': 'bul',
+        'bh': 'bih',
+        'bi': 'bis',
+        'bm': 'bam',
+        'bn': 'ben',
+        'bo': 'bod',
+        'br': 'bre',
+        'bs': 'bos',
+        'ca': 'cat',
+        'ce': 'che',
+        'ch': 'cha',
+        'co': 'cos',
+        'cr': 'cre',
+        'cs': 'ces',
+        'cu': 'chu',
+        'cv': 'chv',
+        'cy': 'cym',
+        'da': 'dan',
+        'de': 'deu',
+        'dv': 'div',
+        'dz': 'dzo',
+        'ee': 'ewe',
+        'el': 'ell',
+        'en': 'eng',
+        'eo': 'epo',
+        'es': 'spa',
+        'et': 'est',
+        'eu': 'eus',
+        'fa': 'fas',
+        'ff': 'ful',
+        'fi': 'fin',
+        'fj': 'fij',
+        'fo': 'fao',
+        'fr': 'fra',
+        'fy': 'fry',
+        'ga': 'gle',
+        'gd': 'gla',
+        'gl': 'glg',
+        'gn': 'grn',
+        'gu': 'guj',
+        'gv': 'glv',
+        'ha': 'hau',
+        'he': 'heb',
+        'hi': 'hin',
+        'ho': 'hmo',
+        'hr': 'hrv',
+        'ht': 'hat',
+        'hu': 'hun',
+        'hy': 'hye',
+        'hz': 'her',
+        'ia': 'ina',
+        'id': 'ind',
+        'ie': 'ile',
+        'ig': 'ibo',
+        'ii': 'iii',
+        'ik': 'ipk',
+        'io': 'ido',
+        'is': 'isl',
+        'it': 'ita',
+        'iu': 'iku',
+        'ja': 'jpn',
+        'jv': 'jav',
+        'ka': 'kat',
+        'kg': 'kon',
+        'ki': 'kik',
+        'kj': 'kua',
+        'kk': 'kaz',
+        'kl': 'kal',
+        'km': 'khm',
+        'kn': 'kan',
+        'ko': 'kor',
+        'kr': 'kau',
+        'ks': 'kas',
+        'ku': 'kur',
+        'kv': 'kom',
+        'kw': 'cor',
+        'ky': 'kir',
+        'la': 'lat',
+        'lb': 'ltz',
+        'lg': 'lug',
+        'li': 'lim',
+        'ln': 'lin',
+        'lo': 'lao',
+        'lt': 'lit',
+        'lu': 'lub',
+        'lv': 'lav',
+        'mg': 'mlg',
+        'mh': 'mah',
+        'mi': 'mri',
+        'mk': 'mkd',
+        'ml': 'mal',
+        'mn': 'mon',
+        'mr': 'mar',
+        'ms': 'msa',
+        'mt': 'mlt',
+        'my': 'mya',
+        'na': 'nau',
+        'nb': 'nob',
+        'nd': 'nde',
+        'ne': 'nep',
+        'ng': 'ndo',
+        'nl': 'nld',
+        'nn': 'nno',
+        'no': 'nor',
+        'nr': 'nbl',
+        'nv': 'nav',
+        'ny': 'nya',
+        'oc': 'oci',
+        'oj': 'oji',
+        'om': 'orm',
+        'or': 'ori',
+        'os': 'oss',
+        'pa': 'pan',
+        'pi': 'pli',
+        'pl': 'pol',
+        'ps': 'pus',
+        'pt': 'por',
+        'qu': 'que',
+        'rm': 'roh',
+        'rn': 'run',
+        'ro': 'ron',
+        'ru': 'rus',
+        'rw': 'kin',
+        'sa': 'san',
+        'sc': 'srd',
+        'sd': 'snd',
+        'se': 'sme',
+        'sg': 'sag',
+        'si': 'sin',
+        'sk': 'slk',
+        'sl': 'slv',
+        'sm': 'smo',
+        'sn': 'sna',
+        'so': 'som',
+        'sq': 'sqi',
+        'sr': 'srp',
+        'ss': 'ssw',
+        'st': 'sot',
+        'su': 'sun',
+        'sv': 'swe',
+        'sw': 'swa',
+        'ta': 'tam',
+        'te': 'tel',
+        'tg': 'tgk',
+        'th': 'tha',
+        'ti': 'tir',
+        'tk': 'tuk',
+        'tl': 'tgl',
+        'tn': 'tsn',
+        'to': 'ton',
+        'tr': 'tur',
+        'ts': 'tso',
+        'tt': 'tat',
+        'tw': 'twi',
+        'ty': 'tah',
+        'ug': 'uig',
+        'uk': 'ukr',
+        'ur': 'urd',
+        'uz': 'uzb',
+        've': 'ven',
+        'vi': 'vie',
+        'vo': 'vol',
+        'wa': 'wln',
+        'wo': 'wol',
+        'xh': 'xho',
+        'yi': 'yid',
+        'yo': 'yor',
+        'za': 'zha',
+        'zh': 'zho',
+        'zu': 'zul',
+    }
+
+    @classmethod
+    def short2long(cls, code):
+        """Convert language code from ISO 639-1 to ISO 639-2/T"""
+        return cls._lang_map.get(code[:2])
+
+    @classmethod
+    def long2short(cls, code):
+        """Convert language code from ISO 639-2/T to ISO 639-1"""
+        for short_name, long_name in cls._lang_map.items():
+            if long_name == code:
+                return short_name
+
+
 class PerRequestProxyHandler(compat_urllib_request.ProxyHandler):
     def __init__(self, proxies=None):
         # Set default handlers