Make the fieldnames argument optional in the DictReader. If self.fieldnames

Skip Montanaro · Skip Montanaro · commit dffeed3ffa74 · 2003-10-03T14:03:01.000Z
is None, the next row read is used as the fieldnames.  In the common case,
this means the programmer doesn't need to know the fieldnames ahead of time.
The first row of the file will be used.  In the uncommon case, this means
the programmer can set the reader's fieldnames attribute to None at any time
and have the next row read as the next set of fieldnames, so a csv file can
contain several "sections", each with different fieldnames.
diff --git a/Doc/lib/libcsv.tex b/Doc/lib/libcsv.tex
@@ -117,14 +117,18 @@ \subsection{Module Contents \label{csv-contents}}
 
 The \module{csv} module defines the following classes:
 
-\begin{classdesc}{DictReader}{csvfile, fieldnames\optional{,
+\begin{classdesc}{DictReader}{csvfile\optional{,
+			      fieldnames=\constant{None},\optional{,
                               restkey=\constant{None}\optional{,
 			      restval=\constant{None}\optional{,
                               dialect=\code{'excel'}\optional{,
-			      fmtparam}}}}}
+			      fmtparam}}}}}}
 Create an object which operates like a regular reader but maps the
-information read into a dict whose keys are given by the \var{fieldnames}
-parameter.  If the row read has fewer fields than the fieldnames sequence,
+information read into a dict whose keys are given by the optional
+{} \var{fieldnames}
+parameter.  If the \var{fieldnames} parameter is omitted, the values in
+the first row of the \var{csvfile} will be used as the fieldnames.
+If the row read has fewer fields than the fieldnames sequence,
 the value of \var{restval} will be used as the default value.  If the row
 read has more fields than the fieldnames sequence, the remaining data is
 added as a sequence keyed by the value of \var{restkey}.  If the row read
@@ -149,6 +153,13 @@ \subsection{Module Contents \label{csv-contents}}
 to \code{'raise'} a \exception{ValueError} is raised.  If it is set to
 \code{'ignore'}, extra values in the dictionary are ignored.  All other
 parameters are interpreted as for \class{writer} objects.
+
+Note that unlike the \class{DictReader} class, the \var{fieldnames}
+parameter of the \class{DictWriter} is not optional.  Since Python's
+\class{dict} objects are not ordered, there is not enough information
+available to deduce the order in which the row should be written to the
+\var{csvfile}.
+
 \end{classdesc}
 
 \begin{classdesc*}{Dialect}{}
diff --git a/Lib/csv.py b/Lib/csv.py
@@ -92,7 +92,7 @@ class excel_tab(excel):
 
 
 class DictReader:
-    def __init__(self, f, fieldnames, restkey=None, restval=None,
+    def __init__(self, f, fieldnames=None, restkey=None, restval=None,
                  dialect="excel", *args, **kwds):
         self.fieldnames = fieldnames    # list of keys for the dict
         self.restkey = restkey          # key to catch long rows
@@ -104,6 +104,10 @@ def __iter__(self):
 
     def next(self):
         row = self.reader.next()
+        if self.fieldnames is None:
+            self.fieldnames = row
+            row = self.reader.next()
+
         # unlike the basic reader, we prefer not to return blanks,
         # because we will typically wind up with a dict full of None
         # values
diff --git a/Lib/test/test_csv.py b/Lib/test/test_csv.py
@@ -382,7 +382,6 @@ def test_write_escape_fieldsep(self):
     def test_read_escape_fieldsep(self):
         self.readerAssertEqual('"abc\\,def"\r\n', [['abc,def']])
 
-# Disabled, pending support in csv.utils module
 class TestDictFields(unittest.TestCase):
     ### "long" means the row is longer than the number of fieldnames
     ### "short" means there are fewer elements in the row than fieldnames
@@ -401,6 +400,10 @@ def test_read_dict_fields(self):
                                 fieldnames=["f1", "f2", "f3"])
         self.assertEqual(reader.next(), {"f1": '1', "f2": '2', "f3": 'abc'})
 
+    def test_read_dict_no_fieldnames(self):
+        reader = csv.DictReader(StringIO("f1,f2,f3\r\n1,2,abc\r\n"))
+        self.assertEqual(reader.next(), {"f1": '1', "f2": '2', "f3": 'abc'})
+
     def test_read_long(self):
         reader = csv.DictReader(StringIO("1,2,abc,4,5,6\r\n"),
                                 fieldnames=["f1", "f2"])
@@ -413,6 +416,12 @@ def test_read_long_with_rest(self):
         self.assertEqual(reader.next(), {"f1": '1', "f2": '2',
                                          "_rest": ["abc", "4", "5", "6"]})
 
+    def test_read_long_with_rest_no_fieldnames(self):
+        reader = csv.DictReader(StringIO("f1,f2\r\n1,2,abc,4,5,6\r\n"),
+                                restkey="_rest")
+        self.assertEqual(reader.next(), {"f1": '1', "f2": '2',
+                                         "_rest": ["abc", "4", "5", "6"]})
+
     def test_read_short(self):
         reader = csv.DictReader(["1,2,abc,4,5,6\r\n","1,2,abc\r\n"],
                                 fieldnames="1 2 3 4 5 6".split(),
