Fix parsing and formatting of statements containing EXCEPT keyword.

andialbrecht · andialbrecht · commit d74ea26ec3a7 · 2014-01-28T15:16:12.000+01:00
diff --git a/CHANGES b/CHANGES
@@ -5,6 +5,7 @@ Bug Fixes
 * Fix incorrect parsing of string literals containing line breaks (issue118).
 * Fix typo in keywords, add MERGE, COLLECT keywords (issue122/124, by Cristian Orellana).
 * Improve parsing of string literals in columns.
+* Fix parsing and formatting of statements containing EXCEPT keyword.
 
 Enhancements
 * Classify DML keywords (issue116, by Victor Hahn).
diff --git a/sqlparse/engine/grouping.py b/sqlparse/engine/grouping.py
@@ -297,7 +297,7 @@ def group_where(tlist):
      if not isinstance(sgroup, sql.Where)]
     idx = 0
     token = tlist.token_next_match(idx, T.Keyword, 'WHERE')
-    stopwords = ('ORDER', 'GROUP', 'LIMIT', 'UNION')
+    stopwords = ('ORDER', 'GROUP', 'LIMIT', 'UNION', 'EXCEPT')
     while token:
         tidx = tlist.token_index(token)
         end = tlist.token_next_match(tidx + 1, T.Keyword, stopwords)
diff --git a/sqlparse/filters.py b/sqlparse/filters.py
@@ -301,7 +301,7 @@ def nl(self):
     def _split_kwds(self, tlist):
         split_words = ('FROM', 'STRAIGHT_JOIN$', 'JOIN$', 'AND', 'OR',
                        'GROUP', 'ORDER', 'UNION', 'VALUES',
-                       'SET', 'BETWEEN')
+                       'SET', 'BETWEEN', 'EXCEPT')
 
         def _next_token(i):
             t = tlist.token_next_match(i, T.Keyword, split_words,
diff --git a/tests/test_regressions.py b/tests/test_regressions.py
@@ -218,3 +218,18 @@ def test_issue90():
                             '    "price" = 1,',
                             '    "description" = NULL'])
     assert formatted == tformatted
+
+
+def test_except_formatting():
+    sql = 'SELECT 1 FROM foo WHERE 2 = 3 EXCEPT SELECT 2 FROM bar WHERE 1 = 2'
+    formatted = sqlparse.format(sql, reindent=True)
+    tformatted = '\n'.join([
+        'SELECT 1',
+        'FROM foo',
+        'WHERE 2 = 3',
+        'EXCEPT',
+        'SELECT 2',
+        'FROM bar',
+        'WHERE 1 = 2'
+    ])
+    assert formatted == tformatted
