jupyter-duckdb 1.4.0__py3-none-any.whl → 1.4.105__py3-none-any.whl

duckdb_kernel/kernel.py

@@ -13,6 +13,7 @@ from .db import Connection, DatabaseError, Table
 from .db.error import *
 from .magics import *
 from .parser import RAParser, DCParser, ParserError
+from .parser.util.QuerySplitter import split_queries, get_last_query
 from .util.ResultSetComparator import ResultSetComparator
 from .util.SQL import SQL_KEYWORDS
 from .util.TestError import TestError
@@ -27,9 +28,11 @@ class DuckDBKernel(Kernel):
     implementation_version = '1.0'
     banner = 'DuckDB Kernel'
     language_info = {
-        'name': 'duckdb',
-        'mimetype': 'application/sql',
+        'name': 'sql',
         'file_extension': '.sql',
+        'mimetype': 'text/x-sql',
+        'codemirror_mode': 'sql',
+        'pygments_lexer': 'sql',
     }
 
     def __init__(self, **kwargs):
@@ -166,7 +169,9 @@ class DuckDBKernel(Kernel):
         # print result if not silent
         if not silent:
             # print EXPLAIN queries as raw text if using DuckDB
-            if query.strip().startswith('EXPLAIN') and state.db.plain_explain():
+            last_query = get_last_query(query, remove_comments=True).strip()
+
+            if last_query.startswith('EXPLAIN') and state.db.plain_explain():
                 for ekey, evalue in rows:
                     html = f'<b>{ekey}</b><br><pre>{evalue}</pre>'
                     break
@@ -273,8 +278,7 @@ class DuckDBKernel(Kernel):
 
                     # You can only execute one statement at a time using SQLite.
                     if not state.db.multiple_statements_per_query():
-                        statements = re.split(r';\r?\n', content)
-                        for statement in statements:
+                        for statement in split_queries(content):
                             try:
                                 state.db.execute(statement)
                             except EmptyResultError:

duckdb_kernel/parser/RAParser.py

@@ -2,6 +2,7 @@ from .LogicParser import LogicParser
 from .ParserError import RAParserError
 from .elements import *
 from .tokenizer import *
+from .util.QuerySplitter import get_last_query
 
 
 # Instead of multiple nested loops, a tree with rotation can
@@ -10,6 +11,10 @@ from .tokenizer import *
 class RAParser:
     @staticmethod
     def parse_query(query: str) -> RAElement:
+        # remove comments from query
+        query = get_last_query(query, split_at=None, remove_comments=True)
+
+        # parse query
         initial_token = Token(query)
         return RAParser.parse_tokens(initial_token, depth=0)
 

duckdb_kernel/parser/elements/RAElement.py

@@ -36,10 +36,13 @@ class RAElement:
         # if all columns are from the same relation we can skip the relation name
         if len(set(c.table for c in columns)) == 1:
             column_names = ', '.join(f'{c.current_name} AS "{c.name}"' for c in columns)
+            order_names = ', '.join(f'"{c.name}" ASC' for c in columns)
         else:
             column_names = ', '.join(f'{c.current_name} AS "{c.full_name}"' for c in columns)
+            order_names = ', '.join(f'"{c.full_name}" ASC' for c in columns)
 
-        return f'SELECT {column_names} FROM ({sql}) {self._name()}'
+        # create sql
+        return f'SELECT {column_names} FROM ({sql}) {self._name()} ORDER BY {order_names}'
 
     def to_sql_with_count(self, tables: Dict[str, Table]) -> str:
         sql, _ = self.to_sql(tables)

duckdb_kernel/parser/elements/binary/ConditionalSet.py

@@ -347,7 +347,13 @@ class ConditionalSet:
             sql_join_filters += f' AND {join_filter}'
 
         sql_condition = condition.to_sql(joined_columns) if condition is not None else '1=1'
-        sql_query = f'SELECT DISTINCT {sql_select} FROM {sql_tables} WHERE ({sql_join_filters}) AND ({sql_condition})'
+
+        if self.projection == ('*',):
+            sql_order = ', '.join(f'{rc.name} ASC' for rcl in rcls for rc in rcl)
+        else:
+            sql_order = ', '.join(f'{col} ASC' for col in self.projection)
+
+        sql_query = f'SELECT DISTINCT {sql_select} FROM {sql_tables} WHERE ({sql_join_filters}) AND ({sql_condition}) ORDER BY {sql_order}'
 
         # Create a mapping from intermediate column names to constant values.
         column_name_mapping = {

duckdb_kernel/parser/util/QuerySplitter.py

@@ -0,0 +1,87 @@
+from typing import Iterator
+
+
+def split_queries(query: str, split_at: str | None = ';', remove_comments: bool = False) -> Iterator[str]:
+    quotes = '\'"`'
+
+    escaped = False
+    in_quotes = None
+    in_singleline_comment = False
+    in_multiline_comment = False
+
+    previous = None
+    current_query = []
+
+    for symbol in query:
+        keep_symbol = True
+
+        # escaped symbol
+        if escaped:
+            escaped = False
+
+        # backslash (escape)
+        elif symbol == '\\':
+            escaped = True
+
+        # if in quotes
+        elif in_quotes is not None:
+            if symbol == in_quotes:
+                in_quotes = False
+
+        # if in single line comment
+        elif in_singleline_comment:
+            if symbol == '\n':
+                in_singleline_comment = False
+            elif remove_comments:
+                keep_symbol = False
+
+        # if in multiline comment
+        elif in_multiline_comment:
+            if previous == '*' and symbol == '/':
+                in_multiline_comment = False
+
+            if remove_comments:
+                keep_symbol = False
+
+        # start of quotes
+        elif symbol in quotes:
+            in_quotes = symbol
+
+        # start of single line comment
+        elif previous == '-' and symbol == '-':
+            in_singleline_comment = True
+
+            if remove_comments:
+                keep_symbol = False
+                current_query.pop()
+
+        # start of multiline comment
+        elif previous == '/' and symbol == '*':
+            in_multiline_comment = True
+
+            if remove_comments:
+                keep_symbol = False
+                current_query.pop()
+
+        # semicolon
+        elif split_at is not None and symbol == split_at:
+            yield ''.join(current_query)
+
+            current_query = []
+            keep_symbol = False
+
+        # store symbol
+        if keep_symbol:
+            current_query.append(symbol)
+
+        previous = symbol
+
+    # yield remaining symbols
+    yield ''.join(current_query)
+
+
+def get_last_query(query: str, split_at: str | None = ';', remove_comments: bool = False) -> str:
+    for query in split_queries(query, split_at, remove_comments):
+        pass
+
+    return query

duckdb_kernel/tests/__init__.py

@@ -56,7 +56,7 @@ class Connection:
         sql = root.to_sql_with_renamed_columns(self.tables)
         cols, rows = self.execute_sql_return_cols(sql)
 
-        return cols, sorted(rows, key=lambda t: tuple(-1 if x is None else x for x in t))
+        return cols, rows  # sorted(rows, key=lambda t: tuple(-1 if x is None else x for x in t))
 
     def execute_ra(self, root: RAElement) -> List:
         _, rows = self.execute_ra_return_cols(root)
@@ -66,7 +66,7 @@ class Connection:
         sql, cnm = root.to_sql_with_renamed_columns(self.tables)
         cols, rows = self.execute_sql_return_cols(sql)
 
-        return [cnm.get(c, c) for c in cols], sorted(rows)
+        return [cnm.get(c, c) for c in cols], rows  # sorted(rows)
 
     def execute_dc(self, root: ConditionalSet) -> List:
         _, rows = self.execute_dc_return_cols(root)

duckdb_kernel/tests/test_ra.py

@@ -79,6 +79,29 @@ def test_case_insensitivity():
             ]
 
 
+def test_comments():
+    for query in (
+            # single line
+            'Shows -- x Users\n x Seasons',
+            'Shows x Seasons -- x Users',
+            'Shows x Seasons--',
+            'Shows x Seasons--\n',
+            # multi line
+            'Shows /* x Users */ x Seasons',
+            'Shows /* x Users */\n x Seasons',
+            'Shows /* x Users\n */ x Seasons',
+            'Shows x Seasons/**/',
+            'Shows x Seasons/*\n*/',
+            'Shows x Seasons\n/**/',
+            'Shows x Seasons/* x Users'
+    ):
+        root = RAParser.parse_query(query)
+
+        assert isinstance(root, BinaryOperators.Cross)
+        assert isinstance(root.left, RAOperand) and root.left.name == 'Shows'
+        assert isinstance(root.right, RAOperand) and root.right.name == 'Seasons'
+
+
 def test_binary_operator_cross():
     for query in (
             r'Shows x Seasons',

{jupyter_duckdb-1.4.0.dist-info → jupyter_duckdb-1.4.105.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: jupyter-duckdb
-Version: 1.4.0
+Version: 1.4.105
 Summary: a basic wrapper kernel for DuckDB
 Home-page: https://github.com/erictroebs/jupyter-duckdb
 Author: Eric Tröbs
@@ -14,7 +14,7 @@ Description-Content-Type: text/markdown
 Requires-Dist: jupyter
 Requires-Dist: graphviz==0.21
 Requires-Dist: checkmarkandcross
-Requires-Dist: duckdb==1.4.0
+Requires-Dist: duckdb==1.4.1
 Dynamic: author
 Dynamic: author-email
 Dynamic: classifier
@@ -45,6 +45,7 @@ There are some magic commands that make teaching easier with this kernel.
     - [Ship Tests With Your Notebook](#ship-tests-with-your-notebooks)
     - [Relational Algebra](#relational-algebra)
     - [Domain Calculus](#domain-calculus)
+    - [Automated Parser Selection](#automated-parser-selection)
 
 ## Setup
 
@@ -281,6 +282,8 @@ The supported operations are:
 The optional flag `ANALYZE` can be used to add an execution diagram to the
 output.
 
+You can also add comments to queries using `--` or `/* */`, just like in SQL.
+
 The Dockerfile also installs the Jupyter Lab plugin
 [jupyter-ra-extension](https://pypi.org/project/jupyter-ra-extension/). It adds
 the symbols mentioned above and some other supported symbols to the toolbar for
@@ -304,4 +307,3 @@ executed cells.
 If the magic command `%AUTO_PARSER` is added to a cell, a parser is
 automatically selected. If `%GUESS_PARSER` is executed, the parser is
 automatically selected for all subsequent cells.
-

{jupyter_duckdb-1.4.0.dist-info → jupyter_duckdb-1.4.105.dist-info}/RECORD

@@ -1,7 +1,7 @@
 duckdb_kernel/__init__.py,sha256=6auU6zeJrsA4fxPSr2PYamS8fG-SMXTn5YQFXF2cseo,33
 duckdb_kernel/__main__.py,sha256=Z3GwHEBWoQjNm2Y84ijnbA0Lk66L7nsFREuqhZ_ptk0,165
 duckdb_kernel/kernel.json,sha256=_7E8Ci2FSdCvnzCjsOaue8QE8AvpS5JLQuxORO5IGtA,127
-duckdb_kernel/kernel.py,sha256=jgmFdxNfv89_r6pbDMK1F5azjhCz7ABJRlS_Nn9hq1s,28237
+duckdb_kernel/kernel.py,sha256=pn7I_mZj910A1o_RF2_n1fU2aIRIU0fKgvUzU0GdxUw,28386
 duckdb_kernel/db/Column.py,sha256=GM5P6sFdlYK92hiKln5-6038gIDOTxh1AYbR4kiga_w,559
 duckdb_kernel/db/Connection.py,sha256=tBXQBYt9c52RLbpl9sakNuAm0Z84--fhZ4efo8ACz-U,670
 duckdb_kernel/db/Constraint.py,sha256=1YgUHk7s8mHCVedbcuJKyXDykj7_ybbwT3Dk9p2VMis,287
@@ -27,14 +27,14 @@ duckdb_kernel/magics/__init__.py,sha256=ggxzDzDEsKMZzYsWw9JqYVJhciJPvPVYGV7oNo9Y
 duckdb_kernel/parser/DCParser.py,sha256=16c1mxa494KP9OreUKQHsSQKoDGZ7NNp2u_gi_D-dkw,2293
 duckdb_kernel/parser/LogicParser.py,sha256=_vZwE5OPRUEN8aEC_fSZAYKR_dpexqNthXog9OFHYRY,1233
 duckdb_kernel/parser/ParserError.py,sha256=qJQVloFtID1HgVDQ1Io247bODT1ic3oO9Z1ZrWR-2Mk,321
-duckdb_kernel/parser/RAParser.py,sha256=vLR2X8zJIJ3cPKdLvU3PKjNakEOvsoFuoK8pr4bA-Fg,3102
+duckdb_kernel/parser/RAParser.py,sha256=YiXjJGdofnajqDbL3UYofIEj3mXll8Hb6dc2bX58ZNY,3284
 duckdb_kernel/parser/__init__.py,sha256=nTmDm1ADvNPDHhVJQLxKYmArNJk6967EUXqn5AkT8FM,126
 duckdb_kernel/parser/elements/DCOperand.py,sha256=qEg_6Us4WV1eK4Bq6oUsmFt_L_x5pJPGce_wSapzIYA,1149
 duckdb_kernel/parser/elements/LogicElement.py,sha256=YasKHxWLDDP8UdyLIKbXzqIRA8-XaakjmvTj-1Iuzyc,280
 duckdb_kernel/parser/elements/LogicOperand.py,sha256=B9NvriloQE5eP734dNMZBZwrdaaIfsuAmZlG1t2eMhs,1021
 duckdb_kernel/parser/elements/LogicOperator.py,sha256=lkM4TAGkXUhsO4w4PLKVA0bgCRGPQQFpNA1FcWWOW9Q,1028
 duckdb_kernel/parser/elements/RABinaryOperator.py,sha256=XN41stGc1e-a4dZ1AQVtQ3lEgjUGNt3dMfYXp85LEeE,538
-duckdb_kernel/parser/elements/RAElement.py,sha256=d6QWO8KlWcwhA4tXtWsf8K4oT3OMMjTvEnUD4yaWQ_c,1468
+duckdb_kernel/parser/elements/RAElement.py,sha256=3qf-ZLQU5WAH_3TvEnfXUg8Y9lE2Fg01D82XutIfgjg,1661
 duckdb_kernel/parser/elements/RAOperand.py,sha256=pghnTYCrrT6MkvynJRgVFPRoMvxIGNB3FTjaq-uCpDQ,1078
 duckdb_kernel/parser/elements/RAOperator.py,sha256=rtqMFBIBBqT-Bwg7Qm4WQwbDrE28Nb74F_7XMeR3ks4,255
 duckdb_kernel/parser/elements/RAUnaryOperator.py,sha256=XC1nphkSm88JaEu5V_HKnb_8JNoeBfE3EvNL4o0qh2c,654
@@ -42,7 +42,7 @@ duckdb_kernel/parser/elements/__init__.py,sha256=t5H6SVOm3z8r6UWRYOI7HmMIuB4Yh6T
 duckdb_kernel/parser/elements/binary/Add.py,sha256=XGkZMfab01huk9EaI6JUfzkd2STbV1C_-TyC2guKE8I,190
 duckdb_kernel/parser/elements/binary/And.py,sha256=0jgetTG8yo5TJSeK70Kj-PI9ERyek1eyMQXX5HBxa4Y,274
 duckdb_kernel/parser/elements/binary/ArrowLeft.py,sha256=u4fZSoyT9lfvWXBwuhUl4DdjVZAOqyVIKmMVbpElLD4,203
-duckdb_kernel/parser/elements/binary/ConditionalSet.py,sha256=sZ3qrxPux7pb3fMrlyBg4Hw7n4-Ln-AeN70_Jp5dAPo,17652
+duckdb_kernel/parser/elements/binary/ConditionalSet.py,sha256=yzUPWO4KL8BEIQ-SiV00bdLulwHoxgoJRxebyhsRSPU,17884
 duckdb_kernel/parser/elements/binary/Cross.py,sha256=jVY3cvD6qDWZkJ7q74lFUPO2VdDt4aAjdk2YAfg-ZC4,687
 duckdb_kernel/parser/elements/binary/Difference.py,sha256=4nyHhjo09UmYjtGNC3xGQxV5ROzCGOpPkyerUN-AlF4,746
 duckdb_kernel/parser/elements/binary/Divide.py,sha256=ubekU4C1wkCTidUSMLEj5neheRx0QjhWSrsPGuXTa1g,265
@@ -71,12 +71,13 @@ duckdb_kernel/parser/elements/unary/__init__.py,sha256=48EDygy0pD7l3J_BlXGc-b7HY
 duckdb_kernel/parser/tokenizer/Token.py,sha256=gsCzgU_zLiA-yD0FWvd2qS9LQUXbivESYH-34Glffqs,2404
 duckdb_kernel/parser/tokenizer/Tokenizer.py,sha256=PWGgS7gYgpULiKGDho842UbaXuqmwEkccixuF10oi5g,5081
 duckdb_kernel/parser/tokenizer/__init__.py,sha256=EOSmfc2RJwtB5cE1Hhj1JAra97tckxxS8-legybPy60,58
+duckdb_kernel/parser/util/QuerySplitter.py,sha256=CXpF--muxC5NuSr1xc6-EVaP-ZBXLCkDNZb6zYkRTJk,2222
 duckdb_kernel/parser/util/RenamableColumn.py,sha256=LxJhFDMUv_OxYYDLwKn63QGpBRfs08jVvhuJTzRtc9c,704
 duckdb_kernel/parser/util/RenamableColumnList.py,sha256=5oEDbtvl4YfHbkxu_Ny2pc0EYnhCZsf7EeoNQvftbrU,3281
 duckdb_kernel/parser/util/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-duckdb_kernel/tests/__init__.py,sha256=MxC-m85ZyYQVn5_AJyEtXX1T5oQPngjW-Zxa_gpfXLE,2715
+duckdb_kernel/tests/__init__.py,sha256=-BoPfo1FNQKnvAYt22Ioc21dbuO67QVFaV_SmS1zQw8,2731
 duckdb_kernel/tests/test_dc.py,sha256=HPJ6JGB7yXVKIOnDHB8KwX1A16ljU0I5Y8VFcJs-KVI,15192
-duckdb_kernel/tests/test_ra.py,sha256=UENizwUqSnaObrvfliwkOakBQqNIh8tsQsgtYQ807MY,52371
+duckdb_kernel/tests/test_ra.py,sha256=YEL-Jwc9tIvCT-UGOaqfXJZZH0FAok3cj9sXK59xzkQ,53172
 duckdb_kernel/tests/test_result_comparison.py,sha256=TQVLPKKNyV2k3i4jCfasetPfVfCzgYZr92wxQmlzPnA,3859
 duckdb_kernel/tests/test_sql.py,sha256=p7UEokoJs2xc-url7xQ4PmWKxtExrDDYnMeoyR1JD0A,1208
 duckdb_kernel/util/ResultSetComparator.py,sha256=RZDIfjJyx8-eR-HIqQlEYgZd_V1ympbszpVRF4TlA7o,2262
@@ -93,7 +94,7 @@ duckdb_kernel/visualization/lib/__init__.py,sha256=LYi0YPtn5fXOejbLIqbt_3KzP-Xrw
 duckdb_kernel/visualization/lib/plotly-3.0.1.min.js,sha256=oy6Be7Eh6eiQFs5M7oXuPxxm9qbJXEtTpfSI93dW16Q,4653932
 duckdb_kernel/visualization/lib/ra.css,sha256=foz1v69EQ117BDduB9QyHH978PbRs2TG1kBS4VGqZbI,57
 duckdb_kernel/visualization/lib/ra.js,sha256=VzMRn55ztcd5Kfu2B6gdRPARpi8n-fvs8oNFnfp55Ec,1845
-jupyter_duckdb-1.4.0.dist-info/METADATA,sha256=j9NzAabdqOabEew9oJrboOxxHUnURZqE0FQx0N6maU4,9128
-jupyter_duckdb-1.4.0.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-jupyter_duckdb-1.4.0.dist-info/top_level.txt,sha256=KvRRPMnmkQNuhyBsXoPmwyt26LRDp0O-0HN6u0Dm5jA,14
-jupyter_duckdb-1.4.0.dist-info/RECORD,,
+jupyter_duckdb-1.4.105.dist-info/METADATA,sha256=uuenj_81-ZaSUb0TQ2Sy8-rcrtZsa7GHfZQ7nElAzZ0,9272
+jupyter_duckdb-1.4.105.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+jupyter_duckdb-1.4.105.dist-info/top_level.txt,sha256=KvRRPMnmkQNuhyBsXoPmwyt26LRDp0O-0HN6u0Dm5jA,14
+jupyter_duckdb-1.4.105.dist-info/RECORD,,