feat: add DataObject, DataAdapters and DataPrinters classes

.circleci/config.yml

@@ -8,8 +8,7 @@ jobs:
       - checkout
       - run: sudo apt update && sudo apt install -y freetds-dev libssl-dev python-dev freetds-bin
       - run: sudo pip install --upgrade pip
-      - run: sudo pip install cython
-      - run: sudo pip install pymssql
+      - run: sudo pip install "Cython<3"
       - run: sudo pip install numpy
       - run: sudo pip install pandas
       - run: sudo python setup.py install

.readthedocs.yaml

@@ -0,0 +1,35 @@
+# Read the Docs configuration file for Sphinx projects
+# See https://docs.readthedocs.io/en/stable/config-file/v2.html for details
+
+# Required
+version: 2
+
+# Set the OS, Python version and other tools you might need
+build:
+  os: ubuntu-22.04
+  tools:
+    python: "3.11"
+    # You can also specify other tool versions:
+    # nodejs: "20"
+    # rust: "1.70"
+    # golang: "1.20"
+
+# Build documentation in the "docs/" directory with Sphinx
+sphinx:
+  configuration: docs/source/conf.py
+  # You can configure Sphinx to use a different builder, for instance use the dirhtml builder for simpler URLs
+  # builder: "dirhtml"
+  # Fail on all warnings to avoid broken references
+  # fail_on_warning: true
+
+# Optionally build your docs in additional formats such as PDF and ePub
+# formats:
+#   - pdf
+#   - epub
+
+# Optional but recommended, declare the Python requirements required
+# to build your documentation
+# See https://docs.readthedocs.io/en/stable/guides/reproducible-builds.html
+python:
+  install:
+    - requirements: docs/requirements.txt

CHANGES.md

@@ -1,5 +1,28 @@
 # Release notes
 
+## 1.7.0
+Apr 19, 2024
+
+- Remove **pymssql** support
+- Add **DataObject** class
+- Add **DataAdapters** class
+- Add **DataPrinters** class
+- Add **aggregate** into _DataAdapters_ class
+- Add **merge** method into _DataAdapters_ class
+- Add **counter** method into _DataAdapters_ class
+- Add **chunks** method into _DataAdapters_ class
+- Add **deduplicate** method into _DataAdapters_ class
+- Add **iter** method into _DataAdapters_ class
+- Add **getitem** method into _DataAdapters_ class
+- Add **getitem** method into _DataAdapters_ class
+- Add **repr** and **str** function into _DataPrinters_ class
+- Add **average** method into _DataPrinters_ class
+- Add **most_common** method into _DataPrinters_ class
+- Add **percentage** method into _DataPrinters_ class
+- Add **len** method into _DataPrinters_ class
+- Add **DataAdapters** and **DataPrinters** classes into _Report_ class
+- Add **DataObjectError** exception class
+
 ## 1.6.0
 Jul 14, 2023
 

docs/requirements.txt

@@ -1,5 +1,4 @@
 ldap3
-pymssql
 mysql-connector-python
 psycopg2-binary
 tablib

docs/source/conf.py

@@ -15,28 +15,27 @@
 # sys.path.insert(0, os.path.abspath('.'))
 import os
 import sys
-sys.path.insert(0, os.path.abspath('../..'))
 
-import __info__
+sys.path.insert(0, os.path.abspath("../.."))
 
 # -- Project information -----------------------------------------------------
 
-project = 'pyreports'
-copyright = '2021, Matteo Guadrini'
-author = __info__.__author__
+project = "pyreports"
+copyright = "2024, Matteo Guadrini"
+author = "Matteo Guadrini"
 
 # The full version, including alpha/beta/rc tags
-release = __info__.__version__
+release = "1.7.0"
 
 # -- General configuration ---------------------------------------------------
 
 # Add any Sphinx extension module names here, as strings. They can be
 # extensions coming with Sphinx (named 'sphinx.ext.*') or your custom
 # ones.
-extensions = ['sphinx.ext.autodoc', 'sphinx.ext.doctest']
+extensions = ["sphinx.ext.autodoc", "sphinx.ext.doctest"]
 
 # Add any paths that contain templates here, relative to this directory.
-templates_path = ['_templates']
+templates_path = ["_templates"]
 
 # List of patterns, relative to source directory, that match files and
 # directories to ignore when looking for source files.
@@ -53,11 +52,9 @@
 # Add any paths that contain custom static files (such as style sheets) here,
 # relative to this directory. They are copied after the builtin static files,
 # so a file named "default.css" will overwrite the builtin "default.css".
-html_static_path = ['_static']
+html_static_path = ["_static"]
 
-html_theme_options = {
-    'logo_only': False
-}
+html_theme_options = {"logo_only": False}
 html_logo = "_static/pyreports.svg"
 
-master_doc = 'index'
+master_doc = "index"

docs/source/datatools.rst

@@ -8,6 +8,107 @@ In this section we will see all these functions contained in the **datatools** m
 .. toctree::
 
 
+DataObject
+----------
+
+**DataObject** class represents a pure *Dataset*.
+
+.. autoclass:: pyreports.DataObject
+   :members:
+
+.. code-block:: python
+
+    import pyreports, tablib
+
+    data = pyreports.DataObject(tablib.Dataset(*[("Arthur", "Dent", 42)]))
+    assert isinstance(data.data, tablib.Dataset) == True
+
+
+
+DataAdapters
+------------
+
+**DataAdapters** class is an object that contains methods that modifying *Dataset*.
+
+.. code-block:: python
+
+    import pyreports, tablib
+
+    data = pyreports.DataAdapters(tablib.Dataset(*[("Arthur", "Dent", 42)]))
+    assert isinstance(data.data, tablib.Dataset) == True
+
+
+    # Aggregate
+    planets = tablib.Dataset(*[("Heart",)])
+    data.aggregate(planets)
+
+    # Merge
+    others = tablib.Dataset(*[("Betelgeuse", "Ford", "Prefect", 42)])
+    data.merge(others)
+
+    # Counter
+    data = pyreports.DataAdapters(Dataset(*[("Heart", "Arthur", "Dent", 42)]))
+    data.merge(self.data)
+    counter = data.counter()
+    assert counter["Arthur"] == 2
+
+    # Chunks
+    data.data.headers = ["planet", "name", "surname", "age"]
+    assert list(data.chunks(4))[0][0] == ("Heart", "Arthur", "Dent", 42)
+
+    # Deduplicate
+    data.deduplicate()
+    assert len(data.data) == 2
+
+    # Get items
+    assert data[1] == ("Betelgeuse", "Ford", "Prefect", 42)
+
+    # Iter items
+    for item in data:
+        print(item)
+
+
+.. autoclass:: pyreports.DataAdapters
+   :members:
+
+DataPrinters
+------------
+
+**DataPrinters** class is an object that contains methods that printing *Dataset*'s information.
+
+.. code-block:: python
+
+    import pyreports, tablib
+
+    data = pyreports.DataPrinters(tablib.Dataset(*[("Arthur", "Dent", 42), ("Ford", "Prefect", 42)], headers=["name", "surname", "age"]))
+    assert isinstance(data.data, tablib.Dataset) == True
+
+    # Print
+    data.print()
+
+    # Average
+    assert data.average(2) == 42
+    assert data.average("age") == 42
+
+    # Most common
+    data.data.append(("Ford", "Prefect", 42))
+    assert data.most_common(0) == "Ford"
+    assert data.most_common("name") == "Ford"
+
+    # Percentage
+    assert data.percentage("Ford") == 66.66666666666666
+
+    # Representation
+    assert repr(data) == "<DataObject, headers=['name', 'surname', 'age'], rows=3>"
+
+    # String
+    assert str(data) == 'name  |surname|age\n------|-------|---\nArthur|Dent   |42 \nFord  |Prefect|42 \nFord  |Prefect|42 '
+
+    # Length
+    assert len(data) == 3
+
+.. autoclass:: pyreports.DataPrinters
+   :members:
 
 
 Average
@@ -137,4 +238,20 @@ The **chunks** function divides a *Dataset* into pieces from *N* (``int``). This
     print(list(new_data))     # [[('Arthur', 'Dent', 55000), ('Ford', 'Prefect', 65000)], [('Tricia', 'McMillian', 55000), ('Zaphod', 'Beeblebrox', 65000)]]
 
 .. note::
-    If the division does not result zero, the last tuple of elements will be a smaller number.
+    If the division does not result zero, the last tuple of elements will be a smaller number.
+
+Deduplicate
+-----------
+
+The **deduplicate** function remove duplicated rows into *Dataset* objects.
+
+.. code-block:: python
+
+    import pyreports
+
+    # Build a datasets
+    employee1 = tablib.Dataset([('Arthur', 'Dent', 55000), ('Ford', 'Prefect', 65000), ('Ford', 'Prefect', 65000)], headers=['name', 'surname', 'salary'])
+
+    # Remove duplicated rows (removed the last ('Ford', 'Prefect', 65000))
+    pyreports.deduplicate(employee1)
+    print(len(employee1))     # 2

docs/source/example.rst

@@ -99,7 +99,7 @@ In this example, we will take two different inputs, and combine them to export a
     # Config Unix application file: this is a FileManager object
     config_file = pyreports.manager('yaml', '/home/myapp.yml')
     # Console admin: this is a DatabaseManager object
-    mydb = pyreports.manager('mssql', server='mssql1.local', database='admins', user='sa', password='sa0000')
+    mydb = pyreports.manager('mysql', server='mysql1.local', database='admins', user='sa', password='sa0000')
     # Get data
     admin_app = config_file.read()                  # return Dataset object: three column (name, shell, login)
     mydb.execute('SELECT * FROM console_admins')

docs/source/managers.rst

@@ -16,7 +16,6 @@ Each type of manager is managed by micro types; Below is the complete list:
 
 #. Database
     #. sqlite (SQLite)
-    #. mssql (Microsoft SQL)
     #. mysql (MySQL or MariaDB)
     #. postgresql (PostgreSQL or EnterpriseDB)
 #. File
@@ -41,7 +40,6 @@ Each type of manager is managed by micro types; Below is the complete list:
 
     # DatabaseManager object
     sqlite_db = pyreports.manager('sqlite', database='/tmp/mydb.db')
-    mssql_db = pyreports.manager('mssql', server='mssql1.local', database='test', user='dba', password='dba0000')
     mysql_db = pyreports.manager('mysql', host='mysql1.local', database='test', user='dba', password='dba0000')
     postgresql_db = pyreports.manager('postgresql', host='postgresql1.local', database='test', user='dba', password='dba0000')
 

index.html

@@ -245,24 +245,24 @@ <h3 class="sub-title text-center">Shell CLI</h3>
                     <pre><code class="language-shell">
 $ cat car.yml
 reports:
-- report:
-  title: 'Red ford machine'
-  input:
-    manager: 'mysql'
-    source:
-    # Connection parameters of my mysql database
-      host: 'mysql1.local'
-      database: 'cars'
-      user: 'admin'
-      password: 'dba0000'
-    params:
-      query: 'SELECT * FROM cars WHERE brand = %s AND color = %s'
-      params: ['ford', 'red']
-  # Filter km
-  filters: [40000, 45000]
-  output:
-    manager: 'csv'
-    filename: '/tmp/car_csv.csv'
+  - report:
+    title: 'Red ford machine'
+    input:
+      manager: 'mysql'
+      source:
+      # Connection parameters of my mysql database
+        host: 'mysql1.local'
+        database: 'cars'
+        user: 'admin'
+        password: 'dba0000'
+      params:
+        query: 'SELECT * FROM cars WHERE brand = %s AND color = %s'
+        params: ['ford', 'red']
+    # Filter km
+    filters: [40000, 45000]
+    output:
+      manager: 'csv'
+      filename: '/tmp/car_csv.csv'
 
 $ report car.yaml
                     </code></pre>

pyproject.toml

@@ -4,11 +4,11 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "pyreports"
-version = "1.6.0"
+version = "1.7.0"
 readme = "README.md"
-license = {text = "GNU General Public License v3.0"}
+license = { text = "GNU General Public License v3.0" }
 keywords = ['pyreports', 'reports', 'report', 'csv', 'yaml', 'export',
-            'excel', 'database', 'ldap', 'dataset', 'file', 'executor', 'book']
+    'excel', 'database', 'ldap', 'dataset', 'file', 'executor', 'book']
 authors = [{ name = "Matteo Guadrini", email = "matteo.guadrini@hotmail.it" }]
 maintainers = [
     { name = "Matteo Guadrini", email = "matteo.guadrini@hotmail.it" },
@@ -20,14 +20,14 @@ classifiers = [
     "License :: OSI Approved :: GNU General Public License v3 (GPLv3)",
     "Operating System :: OS Independent",
 ]
-dependencies = ['ldap3', 'pymssql', 'mysql-connector-python',
-                'psycopg2-binary', 'tablib', 'tablib[all]', 'nosqlapi', 'pyyaml']
+dependencies = ['ldap3', 'mysql-connector-python',
+    'psycopg2-binary', 'tablib', 'tablib[all]', 'nosqlapi', 'pyyaml']
 
 [project.scripts]
 reports = "pyreports.cli:main"
 
 [project.urls]
 homepage = "https://github.com/MatteoGuadrini/pyreports'"
 documentation = "https://pyreports.readthedocs.io/en/latest/"
-repository = "https://github.com/MatteoGuadrini/pyreports/pyreports.git"
-changelog = "https://github.com/MatteoGuadrini/pyreports/blob/master/CHANGES.md"
+repository = "https://github.com/MatteoGuadrini/pyreports.git"
+changelog = "https://github.com/MatteoGuadrini/pyreports/blob/master/CHANGES.md"