[Python-checkins] cpython (merge default -> default): Merge heads

Fri Feb 28 15:49:42 CET 2014

http://hg.python.org/cpython/rev/c781843c4cbb
changeset: 89425:c781843c4cbb
parent: 89422:ec42ab5e0cb3
parent: 89424:8ebd0f382f9d
user: Martin v. Löwis <martin at v.loewis.de>
date: Fri Feb 28 15:47:15 2014 +0100
summary:
 Merge heads
files:
 .hgeol | 2 ++
 Lib/test/coding20731.py | 4 ++++
 Lib/test/test_source_encoding.py | 9 +++++++++
 Misc/NEWS | 3 +++
 Parser/tokenizer.c | 14 ++++++++++++--
 5 files changed, 30 insertions(+), 2 deletions(-)

diff --git a/.hgeol b/.hgeol
--- a/.hgeol
+++ b/.hgeol
@@ -38,6 +38,8 @@
 
 Lib/venv/scripts/nt/* = BIN
 
+Lib/test/coding20731.py = BIN
+
 # All other files (which presumably are human-editable) are "native".
 # This must be the last rule!
 
diff --git a/Lib/test/coding20731.py b/Lib/test/coding20731.py
new file mode 100644
--- /dev/null
+++ b/Lib/test/coding20731.py
@@ -0,0 +1,4 @@
+#coding:latin1
+
+
+
diff --git a/Lib/test/test_source_encoding.py b/Lib/test/test_source_encoding.py
--- a/Lib/test/test_source_encoding.py
+++ b/Lib/test/test_source_encoding.py
@@ -5,6 +5,7 @@
 import importlib
 import os
 import sys
+import subprocess
 
 class SourceEncodingTest(unittest.TestCase):
 
@@ -58,6 +59,14 @@
 # two bytes in common with the UTF-8 BOM
 self.assertRaises(SyntaxError, eval, b'\xef\xbb\x20')
 
+ def test_20731(self):
+ sub = subprocess.Popen([sys.executable, 
+ os.path.join(os.path.dirname(__file__),
+ 'coding20731.py')],
+ stderr=subprocess.PIPE)
+ err = sub.communicate()[1]
+ self.assertEquals(err, b'')
+
 def test_error_message(self):
 compile(b'# -*- coding: iso-8859-15 -*-\n', 'dummy', 'exec')
 compile(b'\xef\xbb\xbf\n', 'dummy', 'exec')
diff --git a/Misc/NEWS b/Misc/NEWS
--- a/Misc/NEWS
+++ b/Misc/NEWS
@@ -8,6 +8,9 @@
 Core and Builtins
 -----------------
 
+- Issue #20731: Properly position in source code files even if they
+ are opened in text mode. Patch by Serhiy Storchaka.
+
 - Issue #20637: Key-sharing now also works for instance dictionaries of
 subclasses. Patch by Peter Ingebretson.
 
diff --git a/Parser/tokenizer.c b/Parser/tokenizer.c
--- a/Parser/tokenizer.c
+++ b/Parser/tokenizer.c
@@ -498,9 +498,13 @@
 
 fd = fileno(tok->fp);
 /* Due to buffering the file offset for fd can be different from the file
- * position of tok->fp. */
+ * position of tok->fp. If tok->fp was opened in text mode on Windows,
+ * its file position counts CRLF as one char and can't be directly mapped
+ * to the file offset for fd. Instead we step back one byte and read to
+ * the end of line.*/
 pos = ftell(tok->fp);
- if (pos == -1 || lseek(fd, (off_t)pos, SEEK_SET) == (off_t)-1) {
+ if (pos == -1 ||
+ lseek(fd, (off_t)(pos > 0 ? pos - 1 : pos), SEEK_SET) == (off_t)-1) {
 PyErr_SetFromErrnoWithFilename(PyExc_OSError, NULL);
 goto cleanup;
 }
@@ -513,6 +517,12 @@
 Py_XDECREF(tok->decoding_readline);
 readline = _PyObject_GetAttrId(stream, &PyId_readline);
 tok->decoding_readline = readline;
+ if (pos > 0) {
+ if (PyObject_CallObject(readline, NULL) == NULL) {
+ readline = NULL;
+ goto cleanup;
+ }
+ }
 
 cleanup:
 Py_XDECREF(stream);
-- 
Repository URL: http://hg.python.org/cpython
