#15927: Fix cvs.reader parsing of escaped \r\n with quoting off.

This fix means that such values are correctly roundtripped, since
cvs.writer already does the correct escaping.

Patch by Michael Johnson.

diff --git a/Lib/test/test_csv.py b/Lib/test/test_csv.py
index 3dc3836015546a0461528393da7e301790a3f32a..974d73d02fc41305ea283a21a202a2b63ebaa40e 100644 (file)
--- a/Lib/test/test_csv.py
+++ b/Lib/test/test_csv.py
@@ -308,6 +308,15 @@ class Test_Csv(unittest.TestCase):
             for i, row in enumerate(csv.reader(fileobj)):
                 self.assertEqual(row, rows[i])
 
+    def test_roundtrip_escaped_unquoted_newlines(self):
+        with TemporaryFile("w+", newline='') as fileobj:
+            writer = csv.writer(fileobj,quoting=csv.QUOTE_NONE,escapechar="\\")
+            rows = [['a\nb','b'],['c','x\r\nd']]
+            writer.writerows(rows)
+            fileobj.seek(0)
+            for i, row in enumerate(csv.reader(fileobj,quoting=csv.QUOTE_NONE,escapechar="\\")):
+                self.assertEqual(row,rows[i])
+
 class TestDialectRegistry(unittest.TestCase):
     def test_registry_badargs(self):
         self.assertRaises(TypeError, csv.list_dialects, None)

diff --git a/Misc/ACKS b/Misc/ACKS
index 976fc56e0d4075ce5374519398a77abf826a1eff..600e0bf03c5129c650080391d288c1e21191d801 100644 (file)
--- a/Misc/ACKS
+++ b/Misc/ACKS
@@ -591,6 +591,7 @@ Orjan Johansen
 Fredrik Johansson
 Gregory K. Johnson
 Kent Johnson
+Michael Johnson
 Simon Johnston
 Matt Joiner
 Thomas Jollans

diff --git a/Misc/NEWS b/Misc/NEWS
index d3e98b3e8664b4014218472cc41a8f5835e7a774..792b62f8fb3475dbbb03a97f711aa4b5ce2bf834 100644 (file)
--- a/Misc/NEWS
+++ b/Misc/NEWS
@@ -289,6 +289,9 @@ Core and Builtins
 Library
 -------
 
+- Issue #15927: CVS now correctly parses escaped newlines and carriage
+  when parsing with quoting turned off.
+
 - Issue #17467: add readline and readlines support to mock_open in
   unittest.mock.
 

diff --git a/Modules/_csv.c b/Modules/_csv.c
index 48a5cf809420129566b90d7ccad0e5a642745bf1..39f9d7d377e607903e19937958759a6c84c90d3b 100644 (file)
--- a/Modules/_csv.c
+++ b/Modules/_csv.c
@@ -51,7 +51,7 @@ static struct PyModuleDef _csvmodule;
 typedef enum {
     START_RECORD, START_FIELD, ESCAPED_CHAR, IN_FIELD,
     IN_QUOTED_FIELD, ESCAPE_IN_QUOTED_FIELD, QUOTE_IN_QUOTED_FIELD,
-    EAT_CRNL
+    EAT_CRNL,AFTER_ESCAPED_CRNL
 } ParserState;
 
 typedef enum {
@@ -644,6 +644,12 @@ parse_process_char(ReaderObj *self, Py_UCS4 c)
         break;
 
     case ESCAPED_CHAR:
+        if (c == '\n' | c=='\r') {
+            if (parse_add_char(self, c) < 0)
+                return -1;
+            self->state = AFTER_ESCAPED_CRNL;
+            break;
+        }
         if (c == '\0')
             c = '\n';
         if (parse_add_char(self, c) < 0)
@@ -651,6 +657,11 @@ parse_process_char(ReaderObj *self, Py_UCS4 c)
         self->state = IN_FIELD;
         break;
 
+    case AFTER_ESCAPED_CRNL:
+        if (c == '\0')
+            break;
+        /*fallthru*/
+
     case IN_FIELD:
         /* in unquoted field */
         if (c == '\n' || c == '\r' || c == '\0') {