From: Victor Stinner <victor.stinner@haypocalc.com>
Date: Fri, 14 Jan 2011 12:52:12 +0000 (+0000)
Subject: Add encoding and errors arguments to urllib.parse_qs() and urllib.parse_qsl()
X-Git-Tag: v3.2rc1~28
X-Git-Url: https://granicus.if.org/sourcecode?a=commitdiff_plain;h=ac71c54b88b916e05e4279e9c4306d227f3a6dfe;p=python

Add encoding and errors arguments to urllib.parse_qs() and urllib.parse_qsl()
---

diff --git a/Doc/library/urllib.parse.rst b/Doc/library/urllib.parse.rst
index e7a75ce4a6..01ac444444 100644
--- a/Doc/library/urllib.parse.rst
+++ b/Doc/library/urllib.parse.rst
@@ -116,7 +116,7 @@ or on combining URL components into a URL string.
       Added IPv6 URL parsing capabilities.
 
 
-.. function:: parse_qs(qs, keep_blank_values=False, strict_parsing=False)
+.. function:: parse_qs(qs, keep_blank_values=False, strict_parsing=False, encoding='utf-8', errors='replace')
 
    Parse a query string given as a string argument (data of type
    :mimetype:`application/x-www-form-urlencoded`).  Data are returned as a
@@ -133,11 +133,15 @@ or on combining URL components into a URL string.
    parsing errors.  If false (the default), errors are silently ignored.  If true,
    errors raise a :exc:`ValueError` exception.
 
+   The optional *encoding* and *errors* parameters specify how to decode
+   percent-encoded sequences into Unicode characters, as accepted by the
+   :meth:`bytes.decode` method.
+
    Use the :func:`urllib.parse.urlencode` function to convert such
    dictionaries into query strings.
 
 
-.. function:: parse_qsl(qs, keep_blank_values=False, strict_parsing=False)
+.. function:: parse_qsl(qs, keep_blank_values=False, strict_parsing=False, encoding='utf-8', errors='replace')
 
    Parse a query string given as a string argument (data of type
    :mimetype:`application/x-www-form-urlencoded`).  Data are returned as a list of
@@ -153,6 +157,10 @@ or on combining URL components into a URL string.
    parsing errors.  If false (the default), errors are silently ignored.  If true,
    errors raise a :exc:`ValueError` exception.
 
+   The optional *encoding* and *errors* parameters specify how to decode
+   percent-encoded sequences into Unicode characters, as accepted by the
+   :meth:`bytes.decode` method.
+
    Use the :func:`urllib.parse.urlencode` function to convert such lists of pairs into
    query strings.
 
diff --git a/Lib/urllib/parse.py b/Lib/urllib/parse.py
index 42f8193682..9a3e42ee78 100644
--- a/Lib/urllib/parse.py
+++ b/Lib/urllib/parse.py
@@ -523,7 +523,8 @@ def unquote(string, encoding='utf-8', errors='replace'):
         string += pct_sequence.decode(encoding, errors)
     return string
 
-def parse_qs(qs, keep_blank_values=False, strict_parsing=False):
+def parse_qs(qs, keep_blank_values=False, strict_parsing=False,
+             encoding='utf-8', errors='replace'):
     """Parse a query given as a string argument.
 
         Arguments:
@@ -540,16 +541,22 @@ def parse_qs(qs, keep_blank_values=False, strict_parsing=False):
         strict_parsing: flag indicating what to do with parsing errors.
             If false (the default), errors are silently ignored.
             If true, errors raise a ValueError exception.
+
+        encoding and errors: specify how to decode percent-encoded sequences
+            into Unicode characters, as accepted by the bytes.decode() method.
     """
     dict = {}
-    for name, value in parse_qsl(qs, keep_blank_values, strict_parsing):
+    pairs = parse_qsl(qs, keep_blank_values, strict_parsing,
+                      encoding=encoding, errors=errors)
+    for name, value in pairs:
         if name in dict:
             dict[name].append(value)
         else:
             dict[name] = [value]
     return dict
 
-def parse_qsl(qs, keep_blank_values=False, strict_parsing=False):
+def parse_qsl(qs, keep_blank_values=False, strict_parsing=False,
+              encoding='utf-8', errors='replace'):
     """Parse a query given as a string argument.
 
     Arguments:
@@ -566,6 +573,9 @@ def parse_qsl(qs, keep_blank_values=False, strict_parsing=False):
         false (the default), errors are silently ignored. If true,
         errors raise a ValueError exception.
 
+    encoding and errors: specify how to decode percent-encoded sequences
+        into Unicode characters, as accepted by the bytes.decode() method.
+
     Returns a list, as G-d intended.
     """
     qs, _coerce_result = _coerce_args(qs)
@@ -584,8 +594,12 @@ def parse_qsl(qs, keep_blank_values=False, strict_parsing=False):
             else:
                 continue
         if len(nv[1]) or keep_blank_values:
-            name = _coerce_result(unquote(nv[0].replace('+', ' ')))
-            value = _coerce_result(unquote(nv[1].replace('+', ' ')))
+            name = nv[0].replace('+', ' ')
+            name = unquote(name, encoding=encoding, errors=errors)
+            name = _coerce_result(name)
+            value = nv[1].replace('+', ' ')
+            value = unquote(value, encoding=encoding, errors=errors)
+            value = _coerce_result(value)
             r.append((name, value))
     return r
 
diff --git a/Misc/NEWS b/Misc/NEWS
index 3ff1326aae..3b0e81389f 100644
--- a/Misc/NEWS
+++ b/Misc/NEWS
@@ -43,6 +43,8 @@ Core and Builtins
 Library
 -------
 
+- Add encoding and errors arguments to urllib.parse_qs() and urllib.parse_qsl()
+
 - Issue #10899: No function type annotations in the standard library.
   Removed function type annotations from _pyio.py.