Merge nturl2path implementation into urllib.request

Author: barneygale

Lib/urllib/request.py

@@ -1647,35 +1647,63 @@ def data_open(self, req):
 # Code move from the old urllib module
 
 # Helper for non-unix systems
-if os.name == 'nt':
-    from nturl2path import url2pathname, pathname2url
-else:
-    def url2pathname(pathname):
-        """OS-specific conversion from a relative URL of the 'file' scheme
-        to a file system path; not recommended for general use."""
-        if pathname[:3] == '///':
-            # URL has an empty authority section, so the path begins on the
-            # third character.
-            pathname = pathname[2:]
-        elif pathname[:12] == '//localhost/':
-            # Skip past 'localhost' authority.
-            pathname = pathname[11:]
-        encoding = sys.getfilesystemencoding()
-        errors = sys.getfilesystemencodeerrors()
-        return unquote(pathname, encoding=encoding, errors=errors)
-
-    def pathname2url(pathname):
-        """OS-specific conversion from a file system path to a relative URL
-        of the 'file' scheme; not recommended for general use."""
-        if pathname[:1] == '/':
-            # Add explicitly empty authority to absolute path. If the path
-            # starts with exactly one slash then this change is mostly
-            # cosmetic, but if it begins with two or more slashes then this
-            # avoids interpreting the path as a URL authority.
-            pathname = '//' + pathname
-        encoding = sys.getfilesystemencoding()
-        errors = sys.getfilesystemencodeerrors()
-        return quote(pathname, encoding=encoding, errors=errors)
+def url2pathname(url):
+    """OS-specific conversion from a relative URL of the 'file' scheme
+    to a file system path; not recommended for general use."""
+    if url[:3] == '///':
+        # Empty authority section, so the path begins on the third character.
+        url = url[2:]
+    elif url[:12] == '//localhost/':
+        # Skip past 'localhost' authority.
+        url = url[11:]
+
+    if os.name == 'nt':
+        if url[:3] == '///':
+            # Skip past extra slash before UNC drive in URL path.
+            url = url[1:]
+        else:
+            if url[:1] == '/' and url[2:3] in (':', '|'):
+                # Skip past extra slash before DOS drive in URL path.
+                url = url[1:]
+            if url[1:2] == '|':
+                # Older URLs use a pipe after a drive letter
+                url = url[:1] + ':' + url[2:]
+        url = url.replace('/', '\\')
+    encoding = sys.getfilesystemencoding()
+    errors = sys.getfilesystemencodeerrors()
+    return unquote(url, encoding=encoding, errors=errors)
+
+
+def pathname2url(pathname):
+    """OS-specific conversion from a file system path to a relative URL
+    of the 'file' scheme; not recommended for general use."""
+    if os.name == 'nt':
+        pathname = pathname.replace('\\', '/')
+    encoding = sys.getfilesystemencoding()
+    errors = sys.getfilesystemencodeerrors()
+    prefix = ''
+    drive, root, tail = os.path.splitroot(pathname)
+    if drive:
+        # First, clean up some special forms. We are going to sacrifice the
+        # additional information anyway
+        if drive[:4] == '//?/':
+            drive = drive[4:]
+            if drive[:4].upper() == 'UNC/':
+                drive = '//' + drive[4:]
+        if drive[1:] == ':':
+            # DOS drive specified. Add three slashes to the start, producing
+            # an authority section with a zero-length authority, and a path
+            # section starting with a single slash.
+            prefix += '///'
+        drive = quote(drive, encoding=encoding, errors=errors, safe='/:')
+    elif root:
+        # Add explicitly empty authority to absolute path. If the path
+        # starts with exactly one slash then this change is mostly
+        # cosmetic, but if it begins with two or more slashes then this
+        # avoids interpreting the path as a URL authority.
+        prefix += '//'
+    tail = quote(tail, encoding=encoding, errors=errors)
+    return prefix + drive + root + tail
 
 
 # Utility functions