jupyter-duckdb 1.2.0.3__py3-none-any.whl → 1.2.0.4__py3-none-any.whl

duckdb_kernel/kernel.py

@@ -14,6 +14,7 @@ from .db.error import *
 from .magics import *
 from .parser import RAParser, DCParser
 from .util.ResultSetComparator import ResultSetComparator
+from .util.TestError import TestError
 from .util.formatting import row_count, rows_table, wrap_image
 from .visualization import *
 
@@ -139,6 +140,7 @@ class DuckDBKernel(Kernel):
             return False
 
     def _execute_stmt(self, query: str, silent: bool,
+                      column_name_mapping: Dict[str, str],
                       max_rows: Optional[int]) -> Tuple[Optional[List[str]], Optional[List[List]]]:
         if self._db is None:
             raise AssertionError('load a database first')
@@ -168,7 +170,8 @@ class DuckDBKernel(Kernel):
         else:
             if columns is not None:
                 # table header
-                table_header = ''.join(f'<th>{c}</th>' for c in columns)
+                mapped_columns = (column_name_mapping.get(c, c) for c in columns)
+                table_header = ''.join(f'<th>{c}</th>' for c in mapped_columns)
 
                 # table data
                 if max_rows is not None and len(rows) > max_rows:
@@ -302,12 +305,23 @@ class DuckDBKernel(Kernel):
         result_columns = [col.rsplit('.', 1)[-1] for col in result_columns]
 
         # extract data for test
-        data = self._tests[name]
+        test_data = self._tests[name]
 
+        # execute test
+        try:
+            self._execute_test(test_data, result_columns, result)
+            self.print_data(wrap_image(True))
+        except TestError as e:
+            self.print_data(wrap_image(False, e.message))
+            if os.environ.get('DUCKDB_TESTS_RAISE_EXCEPTION', 'false').lower() in ('true', '1'):
+                raise e
+
+    @staticmethod
+    def _execute_test(test_data: Dict, result_columns: List[str], result: List[List]):
         # check columns if required
-        if isinstance(data['equals'], dict):
+        if isinstance(test_data['equals'], dict):
             # get column order
-            data_columns = list(data['equals'].keys())
+            data_columns = list(test_data['equals'].keys())
             column_order = []
 
             for dc in data_columns:
@@ -318,39 +332,37 @@ class DuckDBKernel(Kernel):
                         found += 1
 
                 if found == 0:
-                    return self.print_data(wrap_image(False, f'attribute {dc} missing'))
+                    raise TestError(f'attribute {dc} missing')
                 if found >= 2:
-                    return self.print_data(wrap_image(False, f'ambiguous attribute {dc}'))
+                    raise TestError(f'ambiguous attribute {dc}')
 
             # abort if columns from result are unnecessary
             for i, rc in enumerate(result_columns):
                 if i not in column_order:
-                    return self.print_data(wrap_image(False, f'unnecessary attribute {rc}'))
+                    raise TestError(f'unnecessary attribute {rc}')
 
             # reorder columns and transform to list of lists
             sorted_columns = [x for _, x in sorted(zip(column_order, data_columns))]
             rows = []
 
-            for row in zip(*(data['equals'][col] for col in sorted_columns)):
+            for row in zip(*(test_data['equals'][col] for col in sorted_columns)):
                 rows.append(row)
 
         else:
-            rows = data['equals']
+            rows = test_data['equals']
 
         # ordered test
-        if data['ordered']:
+        if test_data['ordered']:
             # calculate diff
             rsc = ResultSetComparator(result, rows)
 
             missing = len(rsc.ordered_right_only)
             if missing > 0:
-                return self.print_data(wrap_image(False, f'{row_count(missing)} missing'))
+                raise TestError(f'{row_count(missing)} missing')
 
             missing = len(rsc.ordered_left_only)
             if missing > 0:
-                return self.print_data(wrap_image(False, f'{row_count(missing)} more than required'))
-
-            return self.print_data(wrap_image(True))
+                raise TestError(f'{row_count(missing)} more than required')
 
         # unordered test
         else:
@@ -362,13 +374,11 @@ class DuckDBKernel(Kernel):
 
             # print result
             if below > 0 and above > 0:
-                self.print_data(wrap_image(False, f'{row_count(below)} missing, {row_count(above)} unnecessary'))
+                raise TestError(f'{row_count(below)} missing, {row_count(above)} unnecessary')
             elif below > 0:
-                self.print_data(wrap_image(False, f'{row_count(below)} missing'))
+                raise TestError(f'{row_count(below)} missing')
             elif above > 0:
-                self.print_data(wrap_image(False, f'{row_count(above)} unnecessary'))
-            else:
-                self.print_data(wrap_image(True))
+                raise TestError(f'{row_count(above)} unnecessary')
 
     def _all_magic(self, silent: bool):
         return {
@@ -503,10 +513,11 @@ class DuckDBKernel(Kernel):
         root_node = DCParser.parse_query(code)
 
         # generate sql
-        sql = root_node.to_sql(tables)
+        sql, cnm = root_node.to_sql_with_renamed_columns(tables)
 
         return {
-            'generated_code': sql
+            'generated_code': sql,
+            'column_name_mapping': cnm
         }
 
     # jupyter related functions
@@ -530,6 +541,10 @@ class DuckDBKernel(Kernel):
                 clean_code = execution_args['generated_code']
                 del execution_args['generated_code']
 
+            # set default column name mapping if none provided
+            if 'column_name_mapping' not in execution_args:
+                execution_args['column_name_mapping'] = {}
+
             # execute statement if needed
             if clean_code.strip():
                 cols, rows = self._execute_stmt(clean_code, silent, **execution_args)

duckdb_kernel/parser/elements/binary/ConditionalSet.py

@@ -42,7 +42,7 @@ class ConditionalSet:
 
                 # If a constant was found, we store the value and replace it with a random attribute name.
                 constant = le.names[i]
-                new_token = Token.random()
+                new_token = Token.random(constant)
                 new_operand = DCOperand(le.relation, le.names[:i] + (new_token,) + le.names[i + 1:], skip_comma=True)
 
                 # We now need an equality comparison to ensure the introduced attribute is equal to the constant.
@@ -103,7 +103,7 @@ class ConditionalSet:
         # The default case is to return the LogicElement with not DCOperands.
         return le, []
 
-    def to_sql(self, tables: Dict[str, Table]) -> str:
+    def to_sql_with_renamed_columns(self, tables: Dict[str, Table]) -> Tuple[str, Dict[str, str]]:
         # First we have to find and remove all DCOperands from the operator tree.
         condition, dc_operands = self.split_tree(self.condition)
 
@@ -339,5 +339,18 @@ 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})'
+
+        # Create a mapping from intermediate column names to constant values.
+        column_name_mapping = {
+            p: p.constant
+            for o in dc_operands
+            for p in o.names
+            if p.constant is not None
+        }
 
-        return f'SELECT DISTINCT {sql_select} FROM {sql_tables} WHERE ({sql_join_filters}) AND ({sql_condition})'
+        return sql_query, column_name_mapping
+
+    def to_sql(self, tables: Dict[str, Table]) -> str:
+        sql, _ = self.to_sql_with_renamed_columns(tables)
+        return sql

duckdb_kernel/parser/tokenizer/Token.py

@@ -1,8 +1,9 @@
+from typing import Optional
 from uuid import uuid4
 
 
 class Token(str):
-    def __new__(cls, value: str):
+    def __new__(cls, value: str, constant: 'Token' = None):
         while True:
             # strip whitespaces
             value = value.strip()
@@ -38,20 +39,40 @@ class Token(str):
 
         return super().__new__(cls, value)
 
+    def __init__(self, value: str, constant: 'Token' = None):
+        self.constant: Optional[Token] = constant
+
     @staticmethod
-    def random() -> 'Token':
-        return Token('__' + str(uuid4()).replace('-', '_'))
+    def random(constant: 'Token' = None) -> 'Token':
+        return Token('__' + str(uuid4()).replace('-', '_'), constant)
 
     @property
     def empty(self) -> bool:
         return len(self) == 0
 
+    @property
+    def is_temporary(self) -> bool:
+        return self.startswith('__')
+
     @property
     def is_constant(self) -> bool:
         return ((self[0] == '"' and self[-1] == '"') or
                 (self[0] == "'" and self[-1] == "'") or
                 self.replace('.', '', 1).isnumeric())
 
+    @property
+    def no_quotes(self) -> str:
+        quotes = ('"', "'")
+
+        if self[0] in quotes and self[-1] in quotes:
+            return self[1:-1]
+        if self[0] in quotes:
+            return self[1:]
+        if self[-1] in quotes:
+            return self[:-1]
+        else:
+            return self
+
     @property
     def single_quotes(self) -> str:
         # TODO Is this comparison useless because tokens are cleaned automatically?

duckdb_kernel/util/TestError.py

@@ -0,0 +1,4 @@
+class TestError(Exception):
+    @property
+    def message(self) -> str:
+        return str(self)

{jupyter_duckdb-1.2.0.3.dist-info → jupyter_duckdb-1.2.0.4.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.2
 Name: jupyter-duckdb
-Version: 1.2.0.3
+Version: 1.2.0.4
 Summary: a basic wrapper kernel for DuckDB
 Home-page: https://github.com/erictroebs/jupyter-duckdb
 Author: Eric Tröbs
@@ -32,10 +32,6 @@ This is a simple DuckDB wrapper kernel which accepts SQL as input, executes it
 using a previously loaded DuckDB instance and formats the output as a table.
 There are some magic commands that make teaching easier with this kernel.
 
-## Quick Start
-
-[![Binder](https://mybinder.org/badge_logo.svg)](https://mybinder.org/v2/git/https%3A%2F%2Fdbgit.prakinf.tu-ilmenau.de%2Fertr8623%2Fjupyter-duckdb.git/master)
-
 ## Table of Contents
 
 - [Setup](#setup)
@@ -85,6 +81,12 @@ Execute the following command to pull and run a prepared image.
 docker run -p 8888:8888 troebs/jupyter-duckdb
 ```
 
+There is also a second image. It contains an additional instance of PostgreSQL:
+
+```bash
+docker run -p 8888:8888 troebs/jupyter-duckdb:postgresql
+```
+
 This image can also be used with JupyterHub and the
 [DockerSpawner / SwarmSpawner](https://github.com/jupyterhub/dockerspawner)
 and probably with the
@@ -138,6 +140,13 @@ Please note that `:memory:` is also a valid file path for DuckDB. The data is
 then stored exclusively in the main memory. In combination with `CREATE`
 and `OF` this makes it possible to work on a temporary copy in memory.
 
+Although the name suggests otherwise, the kernel can also be used with other
+databases:
+- **SQLite** is automatically used as a fallback if the DuckDB dependency is
+  missing.
+- To connect to a **PostgreSQL** instance, you need to specify a database URI
+  starting with `(postgresql|postgres|pgsql|psql|pg)://`.
+
 ### Schema Diagrams
 
 The magic command `SCHEMA` can be used to create a simple schema diagram of the
@@ -153,6 +162,10 @@ representation requires more space, but can improve readability.
 %SCHEMA TD
 ```
 
+The optional argument `ONLY`, followed by one or more table names separated by a
+comma, can be used to display only the named tables and all those connected with
+a foreign key.
+
 Graphviz (`dot` in PATH) is required to render schema diagrams.
 
 ### Number of Rows
@@ -234,6 +247,11 @@ UNION
 SELECT 1, 'Name 1'
 ```
 
+By default, failed tests will display an explanation, but the notebook will
+continue to run. Set the `DUCKDB_TESTS_RAISE_EXCEPTION` environment variable to
+`true` to raise an exception when a test fails. This can be useful for automated
+testing in CI environments.
+
 Disclaimer: The integrated testing is work-in-progress and thus subject to
 potentially incompatible changes and enhancements.
 
@@ -259,6 +277,9 @@ The supported operations are:
 - Cross Product `×`
 - Division `÷`
 
+The optional flag `ANALYZE` can be used to add an execution diagram to the
+output.
+
 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

{jupyter_duckdb-1.2.0.3.dist-info → jupyter_duckdb-1.2.0.4.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=Td6S4qWDC9uuqgAhSllXwR-JHHdnGfT14RHkfYLzXxI,19441
+duckdb_kernel/kernel.py,sha256=KjuYperzwFe21x-vjKHIkVjBlQ348Jlfb7C3H5ua7Sg,20061
 duckdb_kernel/db/Column.py,sha256=GM5P6sFdlYK92hiKln5-6038gIDOTxh1AYbR4kiga_w,559
 duckdb_kernel/db/Connection.py,sha256=5pH-CwGh-r9Q2QwJKGSxvoINBU-sqmvZyG4Q1digfeE,599
 duckdb_kernel/db/Constraint.py,sha256=1YgUHk7s8mHCVedbcuJKyXDykj7_ybbwT3Dk9p2VMis,287
@@ -40,7 +40,7 @@ duckdb_kernel/parser/elements/__init__.py,sha256=4DA2M43hh9d1fZb5Z6YnTTI-IBkDyhC
 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=4KzvUTls2bodJw9ejCKx8se32PR5VFJbVupDZVx2NHE,16671
+duckdb_kernel/parser/elements/binary/ConditionalSet.py,sha256=L3X1o_C55ibD0tHLmJWqyR5yuGgxAb_FDT2_mgPjnqo,17154
 duckdb_kernel/parser/elements/binary/Cross.py,sha256=jVY3cvD6qDWZkJ7q74lFUPO2VdDt4aAjdk2YAfg-ZC4,687
 duckdb_kernel/parser/elements/binary/Difference.py,sha256=ZVRgJHYVMOFwnc97oPvGtKvLvHsjSCsn2Aao6ymxY8Y,742
 duckdb_kernel/parser/elements/binary/Divide.py,sha256=d7mzaOeRYSRO1F-2IHsv_C939TuYtLppbf4-5GSRJXs,265
@@ -63,20 +63,21 @@ duckdb_kernel/parser/elements/unary/Projection.py,sha256=CJ-MIf1-__1ewTjNZVy5hOz
 duckdb_kernel/parser/elements/unary/Rename.py,sha256=Zr2n9EJ3nA476lND0Djz2b6493nnsbSpJ9kkEgk5B_Y,1273
 duckdb_kernel/parser/elements/unary/Selection.py,sha256=TKykDMw0QGQcMFp0r7g6ye4CkjshBTNq14c7qtMkqs4,955
 duckdb_kernel/parser/elements/unary/__init__.py,sha256=48EDygy0pD7l3J_BlXGc-b7HYPaiHQa1-0Mcsj9Xzr0,270
-duckdb_kernel/parser/tokenizer/Token.py,sha256=vwN5hHg11kqzOHLeL5GO1c1BbCTZzYDTuy0QR4kDzew,1800
+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/RenamableColumn.py,sha256=LxJhFDMUv_OxYYDLwKn63QGpBRfs08jVvhuJTzRtc9c,704
 duckdb_kernel/parser/util/RenamableColumnList.py,sha256=GfhdGv4KYT64Z9YA9TCn-7hhcEcc3Gu3vI2zMZ52w-8,3015
 duckdb_kernel/parser/util/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 duckdb_kernel/util/ResultSetComparator.py,sha256=RZDIfjJyx8-eR-HIqQlEYgZd_V1ympbszpVRF4TlA7o,2262
+duckdb_kernel/util/TestError.py,sha256=iwlGHr9j6pFDa2cGxqGyvJ-exrFUtPJjVm_OhHi4n3g,97
 duckdb_kernel/util/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 duckdb_kernel/util/formatting.py,sha256=cbt0CtERnqtzd97mLrOjeJpqM2Lo6pW96BjAYqrOTD8,793
 duckdb_kernel/visualization/Drawer.py,sha256=D0LkiGMvuJ2v6cQSg_axLTGaM4VXAJEQJAynvedQ3So,296
 duckdb_kernel/visualization/RATreeDrawer.py,sha256=j-Vy1zpYMzwZ3CsphyfPW-J7ou9a9tM6aXXgAlQTgDI,2128
 duckdb_kernel/visualization/SchemaDrawer.py,sha256=9K-TUUmyeGdMYMTFQJ7evIU3p8p2KyMKeizUc7-y8co,3015
 duckdb_kernel/visualization/__init__.py,sha256=5eMJmxJ01XAXcgWDn3t70eSZF2PGaXdNo6GK-x-0H3s,78
-jupyter_duckdb-1.2.0.3.dist-info/METADATA,sha256=O4AGOi_-WpenZIFXf6ZGNNPFGDWAHTNOYOA2CdEB4g0,7980
-jupyter_duckdb-1.2.0.3.dist-info/WHEEL,sha256=In9FTNxeP60KnTkGw7wk6mJPYd_dQSjEZmXdBdMCI-8,91
-jupyter_duckdb-1.2.0.3.dist-info/top_level.txt,sha256=KvRRPMnmkQNuhyBsXoPmwyt26LRDp0O-0HN6u0Dm5jA,14
-jupyter_duckdb-1.2.0.3.dist-info/RECORD,,
+jupyter_duckdb-1.2.0.4.dist-info/METADATA,sha256=lS30HHPD2YAmrAJ7IKUzkGXUpKIwe00JDszpd08bVjI,8796
+jupyter_duckdb-1.2.0.4.dist-info/WHEEL,sha256=In9FTNxeP60KnTkGw7wk6mJPYd_dQSjEZmXdBdMCI-8,91
+jupyter_duckdb-1.2.0.4.dist-info/top_level.txt,sha256=KvRRPMnmkQNuhyBsXoPmwyt26LRDp0O-0HN6u0Dm5jA,14
+jupyter_duckdb-1.2.0.4.dist-info/RECORD,,