[Python-checkins] cpython (merge 3.5 -> default): Issue #26045: Merge http.client error addition from 3.5

[martin.panter]

https://hg.python.org/cpython/rev/9896ead3cc1d
changeset:   100184:9896ead3cc1d
parent:      100182:a9c9e4054f3f
parent:      100183:966bd147ccb5
user:        Martin Panter <vadmium+py at gmail.com>
date:        Tue Feb 09 11:57:11 2016 +0000
summary:
  Issue #26045: Merge http.client error addition from 3.5

files:
  Lib/http/client.py       |  17 ++++++++++++++++-
  Lib/test/test_httplib.py |   2 +-
  Misc/NEWS                |   3 +++
  3 files changed, 20 insertions(+), 2 deletions(-)


diff --git a/Lib/http/client.py b/Lib/http/client.py
--- a/Lib/http/client.py
+++ b/Lib/http/client.py
@@ -146,6 +146,21 @@
 _METHODS_EXPECTING_BODY = {'PATCH', 'POST', 'PUT'}
 
 
+def _encode(data, name='data'):
+    """Call data.encode("latin-1") but show a better error message."""
+    try:
+        return data.encode("latin-1")
+    except UnicodeEncodeError as err:
+        raise UnicodeEncodeError(
+            err.encoding,
+            err.object,
+            err.start,
+            err.end,
+            "%s (%.20r) is not valid Latin-1. Use %s.encode('utf-8') "
+            "if you want to send it encoded in UTF-8." %
+            (name.title(), data[err.start:err.end], name)) from None
+
+
 class HTTPMessage(email.message.Message):
     # XXX The only usage of this method is in
     # http.server.CGIHTTPRequestHandler.  Maybe move the code there so
@@ -1173,7 +1188,7 @@
         if isinstance(body, str):
             # RFC 2616 Section 3.7.1 says that text default has a
             # default charset of iso-8859-1.
-            body = body.encode('iso-8859-1')
+            body = _encode(body, 'body')
         self.endheaders(body)
 
     def getresponse(self):
diff --git a/Lib/test/test_httplib.py b/Lib/test/test_httplib.py
--- a/Lib/test/test_httplib.py
+++ b/Lib/test/test_httplib.py
@@ -1042,7 +1042,7 @@
         # intentionally omitted for simplicity
         blacklist = {"HTTPMessage", "parse_headers"}
         for name in dir(client):
-            if name in blacklist:
+            if name.startswith("_") or name in blacklist:
                 continue
             module_object = getattr(client, name)
             if getattr(module_object, "__module__", None) == "http.client":
diff --git a/Misc/NEWS b/Misc/NEWS
--- a/Misc/NEWS
+++ b/Misc/NEWS
@@ -170,6 +170,9 @@
 Library
 -------
 
+- Issue #26045: Add UTF-8 suggestion to error message when posting a
+  non-Latin-1 string with http.client.
+
 - Issue #26039: Added zipfile.ZipInfo.from_file() and zipinfo.ZipInfo.is_dir().
   Patch by Thomas Kluyver.
 

-- 
Repository URL: https://hg.python.org/cpython