pyspark-explorer 0.0.11__tar.gz

pyspark_explorer-0.0.11/.gitignore

@@ -0,0 +1,163 @@
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+cover/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+# .python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# poetry
+#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
+#poetry.lock
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#pdm.lock
+#   pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
+#   in version control.
+#   https://pdm.fming.dev/latest/usage/project/#working-with-version-control
+.pdm.toml
+.pdm-python
+.pdm-build/
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+# PyCharm
+#  JetBrains specific template is maintained in a separate JetBrains.gitignore that can
+#  be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
+#  and can be added to the global gitignore or merged into this file.  For a more nuclear
+#  option (not recommended) you can uncomment the following to ignore the entire idea folder.
+.idea/
+ignore/

pyspark_explorer-0.0.11/LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2024 Krzysztof Ruta
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

pyspark_explorer-0.0.11/PKG-INFO

@@ -0,0 +1,103 @@
+Metadata-Version: 2.4
+Name: pyspark-explorer
+Version: 0.0.11
+Summary: Explore data files with pyspark
+Project-URL: Homepage, https://github.com/krzys9876/pyspark_explorer
+Project-URL: Repository, https://github.com/krzys9876/pyspark_explorer
+Author-email: Krzysztof Ruta <krzys9876@gmail.com>
+Maintainer-email: Krzysztof Ruta <krzys9876@gmail.com>
+License: MIT License
+        
+        Copyright (c) 2024 Krzysztof Ruta
+        
+        Permission is hereby granted, free of charge, to any person obtaining a copy
+        of this software and associated documentation files (the "Software"), to deal
+        in the Software without restriction, including without limitation the rights
+        to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+        copies of the Software, and to permit persons to whom the Software is
+        furnished to do so, subject to the following conditions:
+        
+        The above copyright notice and this permission notice shall be included in all
+        copies or substantial portions of the Software.
+        
+        THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+        IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+        FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+        AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+        LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+        OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+        SOFTWARE.
+License-File: LICENSE
+Keywords: data,explorer,pyspark,spark
+Classifier: Development Status :: 3 - Alpha
+Classifier: Programming Language :: Python
+Requires-Python: >=3.11
+Requires-Dist: pyspark>=3.5.1
+Requires-Dist: textual>=1.0.0
+Description-Content-Type: text/markdown
+
+# Spark File Explorer
+When developing spark applications I came across the growing number of data files that I create. 
+
+## CSVs are fine but what about JSON and complex PARQUET files?
+
+To open and explore a file I used Excel to view CSV files, text editors with plugins to view JSON files, 
+but there was nothing handy to view PARQUETs. Event formatted JSONs were not always readable. What about viewing schemas? 
+
+Each time I had to use spark and write simple apps which was not a problem itself but was tedious and boring.
+
+## Why not a database?
+
+Well, for tabular data there problems is already solved - just use your preferred database.
+Quite often we can load text files or even parquets directly to the database. 
+
+So what's the big deal?
+
+## Hierarchical data sets
+
+Unfortunately the files I often deal with have hierarchical structure. They cannot be simply visualized as tables
+or rather some fields contain tables of other structures. Each of these structures is a table itself but how to load 
+and explore such embedded tables in a database?
+
+## For Spark files use... Spark! 
+
+Hold on - since I generate files using Apache Spark, why can't I use it to explore them?
+I can easily handle complex structures and file types using built-in features. So all I need is to build a use interface 
+to display directories, files and their contents.
+
+## Why console?
+
+I use Kubernetes in production environment, I develop Spark applications locally or in VM. 
+In all environments I would like to have _one tool to rule them all_.  
+
+I like console tools a lot, they require some sort of simplicity. They can run locally or over SSH connection on 
+the remote cluster. Sounds perfect. All I needed was a console UI library, so I wouldn't have to reinvent the wheel.
+
+## Textual
+
+What a great project [_textual_](https://textual.textualize.io/) is! 
+
+Years ago I used [_curses_](https://docs.python.org/3/library/curses.html) but 
+[_textual_](https://textual.textualize.io/) is so superior to what I used back then. It has so many features packed in
+a friendly form of simple to use components. Highly recommended.
+
+# Usage
+
+Install package with pip:
+    
+    pip install pyspark-explorer
+
+Run:
+
+    pyspark-explorer
+
+I recommend that you provide a base path. For local files that could be for example:
+
+    # Linux
+    pyspark-explorer file:///home/myuser/datafiles/base_path
+    # Windows
+    pyspark-explorer file:///c:/datafiles/base_path
+    # Remote hdfs cluster
+    pyspark-explorer hdfs://somecluster/datafiles/base_path
+
+Default path is set to /, which represents local root filesystem and works fine even in Windows thanks to Spark logics.

pyspark_explorer-0.0.11/README.md

@@ -0,0 +1,65 @@
+# Spark File Explorer
+When developing spark applications I came across the growing number of data files that I create. 
+
+## CSVs are fine but what about JSON and complex PARQUET files?
+
+To open and explore a file I used Excel to view CSV files, text editors with plugins to view JSON files, 
+but there was nothing handy to view PARQUETs. Event formatted JSONs were not always readable. What about viewing schemas? 
+
+Each time I had to use spark and write simple apps which was not a problem itself but was tedious and boring.
+
+## Why not a database?
+
+Well, for tabular data there problems is already solved - just use your preferred database.
+Quite often we can load text files or even parquets directly to the database. 
+
+So what's the big deal?
+
+## Hierarchical data sets
+
+Unfortunately the files I often deal with have hierarchical structure. They cannot be simply visualized as tables
+or rather some fields contain tables of other structures. Each of these structures is a table itself but how to load 
+and explore such embedded tables in a database?
+
+## For Spark files use... Spark! 
+
+Hold on - since I generate files using Apache Spark, why can't I use it to explore them?
+I can easily handle complex structures and file types using built-in features. So all I need is to build a use interface 
+to display directories, files and their contents.
+
+## Why console?
+
+I use Kubernetes in production environment, I develop Spark applications locally or in VM. 
+In all environments I would like to have _one tool to rule them all_.  
+
+I like console tools a lot, they require some sort of simplicity. They can run locally or over SSH connection on 
+the remote cluster. Sounds perfect. All I needed was a console UI library, so I wouldn't have to reinvent the wheel.
+
+## Textual
+
+What a great project [_textual_](https://textual.textualize.io/) is! 
+
+Years ago I used [_curses_](https://docs.python.org/3/library/curses.html) but 
+[_textual_](https://textual.textualize.io/) is so superior to what I used back then. It has so many features packed in
+a friendly form of simple to use components. Highly recommended.
+
+# Usage
+
+Install package with pip:
+    
+    pip install pyspark-explorer
+
+Run:
+
+    pyspark-explorer
+
+I recommend that you provide a base path. For local files that could be for example:
+
+    # Linux
+    pyspark-explorer file:///home/myuser/datafiles/base_path
+    # Windows
+    pyspark-explorer file:///c:/datafiles/base_path
+    # Remote hdfs cluster
+    pyspark-explorer hdfs://somecluster/datafiles/base_path
+
+Default path is set to /, which represents local root filesystem and works fine even in Windows thanks to Spark logics.

pyspark_explorer-0.0.11/main.py

@@ -0,0 +1,5 @@
+from pyspark_explorer.run import run
+
+
+if __name__ == "__main__":
+    run()

pyspark_explorer-0.0.11/pyproject.toml

@@ -0,0 +1,33 @@
+[build-system]
+requires = ["hatchling"]
+build-backend = "hatchling.build"
+
+[project]
+name = "pyspark-explorer"
+version = "0.0.11"
+dependencies = [
+  "pyspark>=3.5.1",
+  "textual>=1.0.0"
+]
+requires-python = ">=3.11"
+authors = [
+  {name = "Krzysztof Ruta", email = "krzys9876@gmail.com"}
+]
+maintainers = [
+  {name = "Krzysztof Ruta", email = "krzys9876@gmail.com"}
+]
+description = "Explore data files with pyspark"
+readme = "README.md"
+license = {file = "LICENSE"}
+keywords = ["pyspark", "spark", "explorer", "data"]
+classifiers = [
+  "Development Status :: 3 - Alpha",
+  "Programming Language :: Python"
+]
+
+[project.urls]
+Homepage = "https://github.com/krzys9876/pyspark_explorer"
+Repository = "https://github.com/krzys9876/pyspark_explorer"
+
+[project.scripts]
+pyspark-explorer = "pyspark_explorer.run:run"

pyspark_explorer-0.0.11/pyspark_explorer/data_table.py

@@ -0,0 +1,217 @@
+from typing import Any
+
+from pyspark.sql.types import StructField, Row, StructType, ArrayType, DataType
+import copy
+
+
+class DataFrameTable:
+    TEXT_LEN = 50
+
+    # allow original rows (Row type) or previously transformed rows (when drilling to details)
+    def __init__(self, schema: [StructField], data=None, transformed_data=None, expand_structs: bool = False):
+        if transformed_data is None:
+            transformed_data = []
+        if data is None:
+            data = []
+        self._schema: [StructField] = schema
+        self._data: [Row] = data
+        self._expand_structs: bool = expand_structs
+
+        self.columns = []
+        self.column_names = []
+        self.schema_tree = []
+        self.rows = []
+        self.row_values = []
+        self.__extract_columns__()
+
+        if len(data):
+            self.__extract_rows__()
+        else:
+            self.__set_rows__(transformed_data)
+
+        if self._expand_structs:
+            self.__expand_structs__()
+
+
+    @staticmethod
+    def __extract_kind__(field: StructField) -> str:
+        if type(field.dataType) == StructType:
+            kind = "struct"
+        elif type(field.dataType) == ArrayType:
+            kind = "array"
+        else:
+            kind = "simple"
+        return kind
+
+
+    def __expand_structs__(self):
+        new_cols = [] # NOTE: we cannot modify self.columns on the fly in the loop below, we would modify the loop
+        new_rows = copy.deepcopy(self.rows)
+        col_index = 0
+        existing_columns = copy.deepcopy(self.columns)
+        for ci, col in enumerate(existing_columns):
+            col["col_index"] = col_index
+            new_cols.append(col)
+            col_index += 1
+            if col["kind"] == "struct":
+                for fi,field in enumerate(col["field_type"].fields):
+                    kind = self.__extract_kind__(field)
+                    field_type = self.__extract_type__(field)
+                    new_col = {"col_index": col_index, "name": f"*{field.name}", "kind": kind, "type": type(field.dataType).__name__, "field_type": field_type}
+                    new_cols.append(new_col)
+
+                    for row in new_rows:
+                        struct_value = row["row"][ci]["value"]
+                        row["row"].insert(col_index, struct_value["row"][fi])
+
+                    col_index += 1
+
+        self.columns = new_cols
+        self.rows = new_rows
+        self.__extract_column_names__()
+        self.__extract_row_values__()
+
+
+    @staticmethod
+    def __extract_type__(field) -> StructType:
+        # extract inner type from ArrayType, return field type otherwise
+        if type(field.dataType) == ArrayType:
+            return field.dataType.elementType
+
+        return field.dataType
+
+
+    @staticmethod
+    def __extract_embedded_schema_tree__(fields: [StructField]) -> []:
+        subfields = []
+        for f in fields:
+            subfield = {"name": f.name, "kind": DataFrameTable.__extract_kind__(f), "type": type(f.dataType).__name__}
+            if subfield["kind"] == "array":
+                embedded_subfields = DataFrameTable.__extract_embedded_array_to_tree__(f.dataType)
+            elif subfield["kind"] == "struct":
+                embedded_subfields = DataFrameTable.__extract_embedded_schema_tree__(f.dataType.fields)
+            else:
+                embedded_subfields = []
+            subfield["subfields"] = embedded_subfields
+            subfields.append(subfield)
+        return subfields
+
+
+    @staticmethod
+    def __extract_embedded_array_to_tree__(subfield: DataType) -> []:
+        if type(subfield) == StructType:
+            subfields = DataFrameTable.__extract_embedded_schema_tree__(subfield.fields)
+        elif type(subfield) == ArrayType:
+            subfields = DataFrameTable.__extract_embedded_array_to_tree__(subfield.elementType)
+        else:
+            subfields = [{"name": "", "kind": "simple", "type": type(subfield).__name__, "subfields": []}]
+
+        return subfields
+
+    def __extract_schema_tree__(self) -> None:
+        tree = []
+        for col in self.columns:
+            tree_field = {"name": col["name"], "kind": col["kind"], "type": col["type"]}
+            if col["kind"] == "array":
+                subfields = self.__extract_embedded_array_to_tree__(col["field_type"])
+            elif col["kind"] == "struct":
+                subfields = self.__extract_embedded_schema_tree__(col["field_type"])
+            else:
+                subfields = []
+            tree_field["subfields"] = subfields
+            tree.append(tree_field)
+
+        self.schema_tree = tree
+
+
+    def __extract_columns__(self) -> None:
+        cols = []
+        for i,field in enumerate(self._schema):
+            field_type = self.__extract_type__(field)
+
+            kind = self.__extract_kind__(field)
+            cols.append({"col_index": i, "name": field.name, "kind": kind, "type": type(field.dataType).__name__, "field_type": field_type})
+
+        self.columns = cols
+        self.__extract_column_names__()
+        self.__extract_schema_tree__()
+
+
+    def __extract_column_names__(self) -> None:
+        self.column_names = [c["name"] for c in self.columns]
+
+
+    def __extract_rows__(self) -> None:
+        assert len(self.columns) > 0  # ensure columns are calculated BEFORE rows
+
+        rows = []
+        for ri,data_row in enumerate(self._data):
+            row=[]
+            for fi, field in enumerate(data_row.__fields__):
+                if self.columns[fi]["kind"] == "array":
+                    # create internal schema as a single field
+                    column = StructField(self.columns[fi]["name"], self.columns[fi]["field_type"])
+                    # specify row schema in a form of name = value
+                    values_as_row = list(map(lambda r: Row(**{self.columns[fi]["name"] : r}), data_row[field])) if data_row[field] is not None else None
+                    value = DataFrameTable([column], values_as_row).rows
+                    display_value = self.disp_value(data_row[field]) if data_row[field] is not None else "[]"
+                elif self.columns[fi]["kind"] == "struct":
+                    # extract internal schema as an array of fields
+                    inner_schema = self.columns[fi]["field_type"].fields
+                    # a value is just a single Row, so we must pack it as an array and then unpack it
+                    value = DataFrameTable(inner_schema, [data_row[field]]).rows[0]
+                    display_value = self.disp_value(data_row[field])
+                else:
+                    value = data_row[field]
+                    display_value = self.disp_value(value)
+
+                row.append({"display_value": display_value, "value": value})
+
+            rows.append({"row_index": ri, "row": row})
+
+        self.__set_rows__(rows)
+
+
+    def __set_rows__(self, rows: []) -> None:
+        self.rows = rows
+        self.__extract_row_values__()
+
+
+    def __extract_row_values__(self) -> None:
+        # maybe it is not very readable but still it's one-liner
+        self.row_values = [[c["display_value"][:DataFrameTable.TEXT_LEN] for c in r["row"]] for r in self.rows]
+
+
+    def select(self, x: int, y: int) -> ({}, {}):
+        return self.columns[x], self.rows[y]["row"][x]
+
+
+    @staticmethod
+    def disp_value(value: Any) -> str:
+        disp_value = str(value)
+        # remove single "Row(...)"
+        disp_value = disp_value[4:-1] if disp_value.startswith("Row(") and disp_value.endswith(")") else disp_value
+        # remove "Row" from array "[Row(...), ... , Row(...)]"
+        disp_value = disp_value[4:-1].replace("), Row(", "), (") if disp_value.startswith("[Row(") and disp_value.endswith(")]") else disp_value
+        return disp_value
+
+
+def extract_embedded_table(tab: DataFrameTable, x: int, y: int, expand_structs: bool = False) -> DataFrameTable | None:
+    # check for kind=array but field_type=StructType - this means that we want to drill down from array to structs
+    column, cell = tab.select(x,y)
+    kind = column["kind"]
+    if kind == "struct": # or type(column["field_type"]) == StructType:
+        columns = copy.deepcopy(column["field_type"].fields)
+        rows = copy.deepcopy([cell["value"]])
+        new_tab = DataFrameTable(columns, data= [], transformed_data=rows, expand_structs= expand_structs)
+        return new_tab
+
+    # other case for array
+    if kind=="array":
+        col_name = column["name"][1:] if column["name"].startswith("*") else column["name"]
+        columns = copy.deepcopy([StructField(col_name, column["field_type"])])
+        rows = copy.deepcopy(cell["value"])
+        new_tab = DataFrameTable(columns, data= [], transformed_data=rows, expand_structs= expand_structs)
+        return new_tab
+
+    return None

pyspark_explorer-0.0.11/pyspark_explorer/explorer.py

@@ -0,0 +1,81 @@
+import math
+
+from pyspark.sql import SparkSession
+
+from pyspark_explorer.data_table import DataFrameTable
+
+
+def __ensure_path_separator__(path: str) -> str:
+    res = path.strip()
+    return res + ("" if res.endswith("/") else "/")
+
+
+def __human_readable_size__(size: int) -> str:
+    formats = [".0f", ".1f", ".3f", ".3f", ".3f"]
+    units = ["B", "k", "M", "G", "T"]
+    exp = math.log(size,10) if size>0 else 0
+    ref_exp = math.log(10.24,10)
+    #  -2 to scale properly and avoid too early rounding
+    scale = max(0, min(round((exp / ref_exp - 2) / 3), 4))
+    text = "{val:" + formats[scale]+"}" + units[scale]
+    return format(text.format(val = size / math.pow(1024, scale)))
+
+
+class Explorer:
+    def __init__(self, spark: SparkSession) -> None:
+        self.spark = spark
+        self.fs = spark._jvm.org.apache.hadoop.fs.FileSystem.get(spark._jsc.hadoopConfiguration())
+        self.params = {
+            "auto_refresh": True,
+            "file_limit": 300,
+            "take_rows": 1000,
+            "sort_file_desc": False
+        }
+
+
+    def __file_info__(self, path) -> {}:
+        file_status = self.fs.getFileStatus(path)
+        file_name = path.getName()
+        is_file = file_status.isFile()
+        file = {"name": file_name, "full_path": path.toString(), "is_dir": not is_file,
+                "size": 0, "hr_size": "", "type": ""}
+        if is_file:
+            file_info = self.fs.getContentSummary(path)
+            file["size"] = file_info.getLength()
+            file["hr_size"] = __human_readable_size__(file_info.getLength())
+            file["type"] = "CSV" if file_name.lower().endswith(".csv") \
+                else "JSON" if file_name.lower().endswith(".json") \
+                else "PARQUET" if file_name.lower().endswith(".parquet") \
+                else "OTHER"
+
+        return file
+
+
+    def read_directory(self, path: str) -> []:
+        files: [dict] = []
+        st = self.fs.getFileStatus(self.spark._jvm.org.apache.hadoop.fs.Path(path))
+        if st.isFile():
+            return []
+
+        l = self.fs.listStatus(self.spark._jvm.org.apache.hadoop.fs.Path(path))
+        if self.params["sort_file_desc"]:
+            l = list(reversed(l))
+        for f in l[:self.params["file_limit"]]:
+            file = self.__file_info__(f.getPath())
+            files.append(file)
+
+        return files
+
+
+    def file_info(self, path: str) -> {}:
+        return self.__file_info__(self.spark._jvm.org.apache.hadoop.fs.Path(path))
+
+
+    def read_file(self, file_format: str, path: str) -> DataFrameTable | None:
+        try:
+            df = self.spark.read.format(file_format).load(path)
+            tab = DataFrameTable(df.schema.fields, df.take(self.params["take_rows"]), True)
+        except Exception as e:
+            tab = None
+
+        return tab