cpython: 940748853712 (original) (raw)

Mercurial > cpython

changeset 82815:940748853712

#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. [#15927]

R David Murray rdmurray@bitdance.com
date	Tue, 19 Mar 2013 22:41:47 -0400
parents	684b75600fa9
children	01372117a5b4
files	Lib/test/test_csv.py Misc/ACKS Misc/NEWS Modules/_csv.c
diffstat	4 files changed, 25 insertions(+), 1 deletions(-)[+] [-] Lib/test/test_csv.py 9 Misc/ACKS 1 Misc/NEWS 3 Modules/_csv.c 13

line wrap: on

line diff

--- 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:[](#l1.8)

       writer = csv.writer(fileobj,quoting=csv.QUOTE_NONE,escapechar="\\")[](#l1.9)

       rows = [['a\nb','b'],['c','x\r\nd']][](#l1.10)

```
       writer.writerows(rows)[](#l1.11)
```
```
       fileobj.seek(0)[](#l1.12)
```

       for i, row in enumerate(csv.reader(fileobj,quoting=csv.QUOTE_NONE,escapechar="\\")):[](#l1.13)

           self.assertEqual(row,rows[i])[](#l1.14)

+ class TestDialectRegistry(unittest.TestCase): def test_registry_badargs(self): self.assertRaises(TypeError, csv.list_dialects, None)

--- 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

--- 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.

--- 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_U break; case ESCAPED_CHAR:

```
   if (c == '\n' | c=='\r') {[](#l4.16)
```

       if (parse_add_char(self, c) < 0)[](#l4.17)

```
           return -1;[](#l4.18)
```

       self->state = AFTER_ESCAPED_CRNL;[](#l4.19)

```
       break;[](#l4.20)
```

   }[](#l4.21)
   if (c == '\0')[](#l4.22)
       c = '\n';[](#l4.23)
   if (parse_add_char(self, c) < 0)[](#l4.24)

@@ -651,6 +657,11 @@ parse_process_char(ReaderObj *self, Py_U self->state = IN_FIELD; break;

case AFTER_ESCAPED_CRNL:
```
   if (c == '\0')[](#l4.30)
```
```
       break;[](#l4.31)
```
```
   /*fallthru*/[](#l4.32)
```

+ case IN_FIELD: /* in unquoted field */ if (c == '\n' || c == '\r' || c == '\0') {