remove debugprint

[youtube-dl.git] / youtube_dl / compat.py

diff --git a/youtube_dl/compat.py b/youtube_dl/compat.py
index 973bcd32074107f70c1b781e95b97ef34501b88f..554e3d5db899d1b5d7aff78e08f49286e279ccfd 100644 (file)
--- a/youtube_dl/compat.py
+++ b/youtube_dl/compat.py
@@ -9,6 +9,7 @@ import shutil
 import socket
 import subprocess
 import sys
+import itertools
 
 
 try:
@@ -46,11 +47,6 @@ try:
 except ImportError:  # Python 2
     import htmlentitydefs as compat_html_entities
 
-try:
-    import html.parser as compat_html_parser
-except ImportError:  # Python 2
-    import HTMLParser as compat_html_parser
-
 try:
     import http.client as compat_http_client
 except ImportError:  # Python 2
@@ -81,7 +77,72 @@ except ImportError:
 try:
     from urllib.parse import unquote as compat_urllib_parse_unquote
 except ImportError:
-    def compat_urllib_parse_unquote(string, encoding='utf-8', errors='replace'):
+    def compat_urllib_parse_unquote_to_bytes(string):
+        """unquote_to_bytes('abc%20def') -> b'abc def'."""
+        # Note: strings are encoded as UTF-8. This is only an issue if it contains
+        # unescaped non-ASCII characters, which URIs should not.
+        if not string:
+            # Is it a string-like object?
+            string.split
+            return b''
+        if isinstance(string, str):
+            string = string.encode('utf-8')
+            # string = encode('utf-8')
+
+        # python3 -> 2: must implicitly convert to bits
+        bits = bytes(string).split(b'%')
+
+        if len(bits) == 1:
+            return string
+        res = [bits[0]]
+        append = res.append
+
+        for item in bits[1:]:
+            try:
+                append(item[:2].decode('hex'))
+                append(item[2:])
+            except:
+                append(b'%')
+                append(item)
+        return b''.join(res)
+
+    compat_urllib_parse_asciire = re.compile('([\x00-\x7f]+)')
+
+    def new_compat_urllib_parse_unquote(string, encoding='utf-8', errors='replace'):
+        """Replace %xx escapes by their single-character equivalent. The optional
+        encoding and errors parameters specify how to decode percent-encoded
+        sequences into Unicode characters, as accepted by the bytes.decode()
+        method.
+        By default, percent-encoded sequences are decoded with UTF-8, and invalid
+        sequences are replaced by a placeholder character.
+
+        unquote('abc%20def') -> 'abc def'.
+        """
+
+        if '%' not in string:
+            string.split
+            return string
+        if encoding is None:
+            encoding = 'utf-8'
+        if errors is None:
+            errors = 'replace'
+
+        bits = compat_urllib_parse_asciire.split(string)
+        res = [bits[0]]
+        append = res.append
+        for i in range(1, len(bits), 2):
+            foo = compat_urllib_parse_unquote_to_bytes(bits[i])
+            foo = foo.decode(encoding, errors)
+            append(foo)
+
+            if bits[i + 1]:
+                bar = bits[i + 1]
+                if not isinstance(bar, unicode):
+                    bar = bar.decode('utf-8')
+                append(bar)
+        return ''.join(res)
+
+    def old_compat_urllib_parse_unquote(string, encoding='utf-8', errors='replace'):
         if string == '':
             return string
         res = string.split('%')
@@ -98,6 +159,8 @@ except ImportError:
             try:
                 if not item:
                     raise ValueError
+                if not re.match('[0-9a-fA-F][0-9a-fA-F]',item[:2]):
+                    raise ValueError
                 pct_sequence += item[:2].decode('hex')
                 rest = item[2:]
                 if not rest:
@@ -116,6 +179,8 @@ except ImportError:
             string += pct_sequence.decode(encoding, errors)
         return string
 
+    compat_urllib_parse_unquote = new_compat_urllib_parse_unquote
+
 try:
     compat_str = unicode  # Python 2
 except NameError:
@@ -393,6 +458,15 @@ else:
             pass
         return _terminal_size(columns, lines)
 
+try:
+    itertools.count(start=0, step=1)
+    compat_itertools_count = itertools.count
+except TypeError:  # Python 2.6
+    def compat_itertools_count(start=0, step=1):
+        n = start
+        while True:
+            yield n
+            n += step
 
 __all__ = [
     'compat_HTTPError',
@@ -404,9 +478,9 @@ __all__ = [
     'compat_getenv',
     'compat_getpass',
     'compat_html_entities',
-    'compat_html_parser',
     'compat_http_client',
     'compat_http_server',
+    'compat_itertools_count',
     'compat_kwargs',
     'compat_ord',
     'compat_parse_qs',