Batman

.gitignore

@@ -0,0 +1,176 @@
+# https://github.com/github/gitignore/blob/main/Python.gitignore
+
+# 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
+
+# UV
+#   Similar to Pipfile.lock, it is generally recommended to include uv.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#uv.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/
+
+# Ruff stuff:
+.ruff_cache/
+
+# PyPI configuration file
+.pypirc

README.md

@@ -0,0 +1,3 @@
+# DocGen is an application to normalise and automate documentation for Data Engineers.
+
+## still WIP

docgen.py

@@ -0,0 +1,143 @@
+import logging
+from logging.handlers import RotatingFileHandler
+
+class DocGen:
+    def __init__(self,file):
+        self.details = file
+        self.logging = self.configure_logging()
+        self.logging.info('Starting DocGen')
+
+    def configure_logging(self):
+        # Configure logger with rotating file handler and custom log levels
+        logger = logging.getLogger(__name__)
+        logger.setLevel(logging.DEBUG)
+
+        console_handler = logging.StreamHandler()
+        console_handler.setLevel(logging.INFO)
+        formatter = logging.Formatter('[%(levelname)s] %(name)s.%(funcName)s: %(message)s')
+        console_handler.setFormatter(formatter)
+        logger.addHandler(console_handler)
+
+        # Rotate logs every 10 MB, keeping 5 backups
+        file_handler = RotatingFileHandler('DocGen.log', maxBytes=1024*1024*10, backupCount=5)
+        file_handler.setLevel(logging.DEBUG)
+        formatter = logging.Formatter('%(asctime)s [%(levelname)s] %(name)s.%(funcName)s: %(message)s')
+        file_handler.setFormatter(formatter)
+        logger.addHandler(file_handler)
+
+        return logger
+
+    def wiki_on_a_page(self) -> str:
+        self.logging.info('Building Wiki on a page markdown file')
+        master_file = ''
+        self.logging.debug('Generating overview')
+        overview = self.generate_overview()
+        self.logging.debug('Generating md tables')
+        md_tables = self.generate_md_tables()
+        self.logging.debug('Generating entity relationship diagram')
+        entity_relationship = self.generate_erd()
+        self.logging.debug('Generating lineage report')
+        lineage = self.generate_lineage()
+        self.logging.debug('Generating markdown file')
+        master_file += overview
+        master_file += '\n## Table overview\n\n'
+        master_file += md_tables
+        master_file += '\n\n## Entity Relationship Diagram\n\n```mermaid\n'
+        master_file += entity_relationship
+        master_file += '\n```\n'
+        master_file += '\n\n## Lineage Report\n\n```mermaid\n'
+        master_file += lineage
+        master_file += '\n```\n'
+        self.logging.debug('Generating markdown file complete')
+        return master_file
+
+    def generate_erd(self) -> str:
+        self.logging.info('starting erd generation')
+        mermaid_erd = self._generate_erd_tables()
+        self.logging.info('tables generated, generating relationships')
+        relationships = self._generate_erd_relationships()
+        self.logging.info('Relationships generated, combining and returning')
+        mermaid_erd.extend(relationships)
+        erd_code = "\n".join(mermaid_erd)
+        return erd_code
+
+    def generate_md_tables(self) -> str:
+        self.logging.info('starting table generation')
+        md_table = [
+            "| Entity ID | Entity Name | Description | Entity Type | Primary Key(s) |",
+            "|-----------|-------------|-------------|-------------|----------------|",
+        ]
+        for entity in self.details['entities']:
+            if not entity.get('entity_columns',None):
+                primary_key_string = ''
+            else:
+                pk_list = [column['column_name'] for column in entity['entity_columns'] if column['is_pk'] is True]
+                primary_key_string = ", ".join(pk_list)
+            md_table.append(
+                f"| {entity['entity_id']} | {entity['entity_name']} | {entity.get('entity_description','')} | {entity['entity_type']} | {primary_key_string} |"
+            )
+        md_output = "\n".join(md_table)
+        return md_output
+
+    def generate_overview(self) -> str:
+        self.logging.info('Generating Overview String')
+        self.logging.debug(f'overview Product {self.details.get('product_name',"Missing Product Name")}')
+        self.logging.debug(f'overview Team {self.details.get('responsible_team',"Missing Responsible Team")}')
+        overview = f'''# {self.details.get('product_name',"Missing Product Name")}
+
+## Maintained by: {self.details.get('responsible_team',"Missing Responsible Team")}
+'''
+        return overview
+
+    def generate_lineage(self):
+        mermaid_lines = [r'''%%{init: {"flowchart": {"defaultRenderer": "elk"}} }%%
+flowchart LR
+''']
+        for entity in self.details['entities']:
+            mermaid_lines.append(f"{entity['entity_id']}[{entity['entity_id']} {entity['entity_type']} {entity['entity_name']}]")
+
+        mermaid_lines.append("\n")
+
+        for entity in self.details['entities']:
+            for dependant in entity.get('entity_dependencies',[]):
+                mermaid_lines.append(f"{dependant} --> {entity['entity_id']}")
+
+        mermaid = "\n".join(mermaid_lines)
+        return mermaid
+
+    def _generate_erd_tables(self) -> list:
+        mermaid_erd = ["erDiagram"]
+        self.logging.info('getting gold entity information')
+        for entity in self.details['entities']:
+            self.logging.debug(f'looking at {entity.get('entity_id')}, {entity.get('entity_name')}, {entity.get('entity_type')}')
+            if entity.get('entity_type') != 'gold':
+                continue
+            self.logging.debug(f'entity {entity.get('entity_id')} is golden, getting column information')
+            mermaid_erd.append(f"    {entity.get('entity_name')} {{")
+            for column in entity.get('entity_columns'):
+                self.logging.debug(column)
+                col_name_with_pk = f'{column['column_name']} PK' if column['is_pk'] is True else column['column_name']
+                mermaid_erd.append(f"        {
+                    column['datatype']} {col_name_with_pk}")
+            mermaid_erd.append("    }")
+        return mermaid_erd
+    
+    def _generate_erd_relationships(self) -> set:
+        relationships = set()
+        for entity_a in self.details['entities']:
+            self.logging.debug(f'looking at {entity_a.get('entity_id')}, {entity_a.get('entity_name')}, {entity_a.get('entity_type')}')
+            if entity_a.get('entity_type') != 'gold':
+                continue
+            entity_a_columns = [column['column_name'] for column in entity_a['entity_columns']]
+            for entity_b in self.details['entities']:
+                self.logging.debug(f'looking at {entity_b.get('entity_id')}, {entity_b.get('entity_name')}, {entity_b.get('entity_type')}')
+                if entity_b.get('entity_type') != 'gold':
+                    continue
+                if entity_a['entity_id'] == entity_b['entity_id']:
+                    self.logging.debug('not handling self joins right now. 🫢')
+                    continue
+                entity_b_columns = [column['column_name'] for column in entity_b['entity_columns'] if column['is_pk'] is True]
+                for column in entity_a_columns:
+                    if column in entity_b_columns:
+                        relationships.add(f'    {entity_a["entity_name"]} ||--|| {entity_b["entity_name"]} : "{column}"')
+        return relationships

example_use.py

@@ -0,0 +1,16 @@
+import yaml
+import os
+
+from docgen import DocGen
+
+
+input_file_path = os.path.join('examples', 'example_docgen_product.yaml')
+output_file_path = os.path.join('examples', 'example_docgen_output.md')
+
+with open(input_file_path) as f:
+    file = yaml.safe_load(f)
+
+with open(output_file_path,'w') as md:
+    md.write(DocGen(file).wiki_on_a_page())
+
+# DocGen(file).release_notes_idea()

examples/example_docgen_output.md

@@ -0,0 +1,139 @@
+# The aiimi Data Product
+
+## Maintained by: The aiimi Data Engineers
+
+## Table overview
+
+| Entity ID | Entity Name | Description | Entity Type | Primary Key(s) |
+|-----------|-------------|-------------|-------------|----------------|
+| 1 | transactions | Transaction Fact Table One line per transaction, but only transactions that have actually happened. | gold | transaction_id |
+| 2 | scheduled_transactions | Scheduled Transaction Fact Table One line per transaction, but only transactions that have not actually happened. | gold | scheduled_transaction_id |
+| 3 | accounts | Accounts Dimension Table Holds all the information relating to an account, type 1, 1 line per account. | gold | account_id |
+| 4 | categories | Categories Dimension Table Holds all the information relating to a category, type 1, 1 line per category. | gold | category_id |
+| 5 | payees | Payees Dimension Table Holds all the information relating to a payee, type 1, 1 line per payee. | gold | payee_id |
+| 6 | dates | Good old fashioned Date Dimension | gold | date_id |
+| 7 | accounts | Silver Accounts Table Other random information. | silver |  |
+| 8 | categories | Silver Categories Table Other random information. | silver |  |
+| 9 | payees | Silver Payees Table Other random information. | silver |  |
+| 10 | scheduled_transactions | Silver Scheduled Transactions Table Other random information. | silver |  |
+| 11 | transactions | Silver Transactions Table Other random information. | silver |  |
+| 12 | accounts |  | bronze |  |
+| 13 | categories |  | bronze |  |
+| 14 | payees |  | bronze |  |
+| 15 | scheduled_transactions |  | bronze |  |
+| 16 | transactions |  | bronze |  |
+
+## Entity Relationship Diagram
+
+```mermaid
+erDiagram
+    transactions {
+        string transaction_id PK
+        int account_id
+        int category_id
+        int payee_id
+        int date_id
+        decimal amount
+        boolean cleared
+        boolean approved
+        boolean deleted
+        string memo
+        string flag_color
+        string transfer_account_id
+    }
+    scheduled_transactions {
+        int scheduled_transaction_id PK
+        int account_id
+        int category_id
+        int payee_id
+        str date_first
+        str date_next
+        decimal amount
+        string frequency
+        boolean deleted
+        text memo
+        string flag_color
+        str transfer_account_id
+    }
+    accounts {
+        int account_id PK
+        string account_name
+        string account_type
+        boolean on_budget
+        boolean closed
+        text note
+        decimal balance
+        decimal cleared_balance
+        decimal uncleared_balance
+        boolean deleted
+    }
+    categories {
+        int category_id PK
+        string category_name
+        string category_group_name
+        boolean hidden
+        text note
+        decimal budgeted
+        decimal activity
+        decimal balance
+        boolean deleted
+    }
+    payees {
+        int payee_id PK
+        string payee_name
+        boolean deleted
+    }
+    dates {
+        string date_id PK
+        date date
+        int year
+        int month
+        int day
+        boolean is_weekday
+        int weekday
+    }
+    scheduled_transactions ||--|| payees : "payee_id"
+    transactions ||--|| categories : "category_id"
+    scheduled_transactions ||--|| accounts : "account_id"
+    transactions ||--|| dates : "date_id"
+    scheduled_transactions ||--|| categories : "category_id"
+    transactions ||--|| payees : "payee_id"
+    transactions ||--|| accounts : "account_id"
+```
+
+
+## Lineage Report
+
+```mermaid
+%%{init: {"flowchart": {"defaultRenderer": "elk"}} }%%
+flowchart LR
+
+1[1 gold transactions]
+2[2 gold scheduled_transactions]
+3[3 gold accounts]
+4[4 gold categories]
+5[5 gold payees]
+6[6 gold dates]
+7[7 silver accounts]
+8[8 silver categories]
+9[9 silver payees]
+10[10 silver scheduled_transactions]
+11[11 silver transactions]
+12[12 bronze accounts]
+13[13 bronze categories]
+14[14 bronze payees]
+15[15 bronze scheduled_transactions]
+16[16 bronze transactions]
+
+
+11 --> 1
+10 --> 2
+7 --> 3
+8 --> 4
+9 --> 5
+12 --> 7
+13 --> 8
+14 --> 9
+15 --> 10
+16 --> 11
+```

examples/example_docgen_product.yaml

@@ -0,0 +1,537 @@
+product_name: The aiimi Data Product
+responsible_team: The aiimi Data Engineers
+entities:
+  - entity_name: transactions
+    entity_id: 1
+    entity_type: gold
+    entity_columns:
+      - column_name: transaction_id
+        is_pk: True
+        datatype: string
+      - column_name: account_id
+        is_pk: False
+        datatype: int
+      - column_name: category_id
+        is_pk: False
+        datatype: int
+      - column_name: payee_id
+        is_pk: False
+        datatype: int
+      - column_name: date_id
+        is_pk: False
+        datatype: int
+      - column_name: amount
+        is_pk: False
+        datatype: decimal
+      - column_name: cleared
+        is_pk: False
+        datatype: boolean
+      - column_name: approved
+        is_pk: False
+        datatype: boolean
+      - column_name: deleted
+        is_pk: False
+        datatype: boolean
+      - column_name: memo
+        is_pk: False
+        datatype: string
+      - column_name: flag_color
+        is_pk: False
+        datatype: string
+      - column_name: transfer_account_id
+        is_pk: False
+        datatype: string
+    entity_dependencies:
+      - 11
+    entity_description: >- 
+      Transaction Fact Table
+      One line per transaction, but only transactions that have actually happened.
+  - entity_name: scheduled_transactions
+    entity_id: 2
+    entity_type: gold
+    entity_columns:
+      - column_name: scheduled_transaction_id
+        is_pk: True
+        datatype: int
+      - column_name: account_id
+        is_pk: False
+        datatype: int
+      - column_name: category_id
+        is_pk: False
+        datatype: int
+      - column_name: payee_id
+        is_pk: False
+        datatype: int
+      - column_name: date_first
+        is_pk: False
+        datatype: str
+      - column_name: date_next
+        is_pk: False
+        datatype: str
+      - column_name: amount
+        is_pk: False
+        datatype: decimal
+      - column_name: frequency
+        is_pk: False
+        datatype: string
+      - column_name: deleted
+        is_pk: False
+        datatype: boolean
+      - column_name: memo
+        is_pk: False
+        datatype: text
+      - column_name: flag_color
+        is_pk: False
+        datatype: string
+      - column_name: transfer_account_id
+        is_pk: False
+        datatype: str
+    entity_dependencies:
+      - 10
+    entity_description: >- 
+      Scheduled Transaction Fact Table
+      One line per transaction, but only transactions that have not actually happened.
+  - entity_name: accounts
+    entity_id: 3
+    entity_type: gold
+    entity_columns:
+      - column_name: account_id
+        is_pk: True
+        datatype: int
+      - column_name: account_name
+        is_pk: False
+        datatype: string
+      - column_name: account_type
+        is_pk: False
+        datatype: string
+      - column_name: on_budget
+        is_pk: False
+        datatype: boolean
+      - column_name: closed
+        is_pk: False
+        datatype: boolean
+      - column_name: note
+        is_pk: False
+        datatype: text
+      - column_name: balance
+        is_pk: False
+        datatype: decimal
+      - column_name: cleared_balance
+        is_pk: False
+        datatype: decimal
+      - column_name: uncleared_balance
+        is_pk: False
+        datatype: decimal
+      - column_name: deleted
+        is_pk: False
+        datatype: boolean
+    entity_dependencies:
+      - 7
+    entity_description: >- 
+      Accounts Dimension Table
+      Holds all the information relating to an account, type 1, 1 line per account.
+  - entity_name: categories
+    entity_id: 4
+    entity_type: gold
+    entity_columns:
+      - column_name: category_id
+        is_pk: True
+        datatype: int
+      - column_name: category_name
+        is_pk: False
+        datatype: string
+      - column_name: category_group_name
+        is_pk: False
+        datatype: string
+      - column_name: hidden
+        is_pk: False
+        datatype: boolean
+      - column_name: note
+        is_pk: False
+        datatype: text
+      - column_name: budgeted
+        is_pk: False
+        datatype: decimal
+      - column_name: activity
+        is_pk: False
+        datatype: decimal
+      - column_name: balance
+        is_pk: False
+        datatype: decimal
+      - column_name: deleted
+        is_pk: False
+        datatype: boolean
+    entity_dependencies:
+      - 8
+    entity_description: >- 
+      Categories Dimension Table
+      Holds all the information relating to a category, type 1, 1 line per category.
+  - entity_name: payees
+    entity_id: 5
+    entity_type: gold
+    entity_columns:
+      - column_name: payee_id
+        is_pk: True
+        datatype: int
+      - column_name: payee_name
+        is_pk: False
+        datatype: string
+      - column_name: deleted
+        is_pk: False
+        datatype: boolean
+    entity_dependencies:
+      - 9
+    entity_description: >- 
+      Payees Dimension Table
+      Holds all the information relating to a payee, type 1, 1 line per payee.
+  - entity_name: dates
+    entity_id: 6
+    entity_type: gold
+    entity_columns:
+      - column_name: date_id
+        is_pk: True
+        datatype: string
+      - column_name: date
+        is_pk: False
+        datatype: date
+      - column_name: year
+        is_pk: False
+        datatype: int
+      - column_name: month
+        is_pk: False
+        datatype: int
+      - column_name: day
+        is_pk: False
+        datatype: int
+      - column_name: is_weekday
+        is_pk: False
+        datatype: boolean
+      - column_name: weekday
+        is_pk: False
+        datatype: int
+    entity_description: >- 
+      Good old fashioned Date Dimension
+  - entity_name: accounts
+    entity_id: 7
+    entity_type: silver
+    entity_columns:
+      - column_name: id
+        is_pk: False
+        datatype: String
+      - column_name: name
+        is_pk: False
+        datatype: String
+      - column_name: type
+        is_pk: False
+        datatype: String
+      - column_name: on_budget
+        is_pk: False
+        datatype: Boolean
+      - column_name: closed
+        is_pk: False
+        datatype: Boolean
+      - column_name: note
+        is_pk: False
+        datatype: String
+      - column_name: balance
+        is_pk: False
+        datatype: Int64
+      - column_name: cleared_balance
+        is_pk: False
+        datatype: Int64
+      - column_name: uncleared_balance
+        is_pk: False
+        datatype: Int64
+      - column_name: transfer_payee_id
+        is_pk: False
+        datatype: String
+      - column_name: direct_import_linked
+        is_pk: False
+        datatype: Boolean
+      - column_name: direct_import_in_error
+        is_pk: False
+        datatype: Boolean
+      - column_name: last_reconciled_at
+        is_pk: False
+        datatype: String
+      - column_name: deleted
+        is_pk: False
+        datatype: Boolean
+      - column_name: ingestion_date
+        is_pk: False
+        datatype: Date
+    entity_dependencies:
+      - 12
+    entity_description: >- 
+      Silver Accounts Table
+      Other random information.
+  - entity_name: categories
+    entity_id: 8
+    entity_type: silver
+    entity_columns:
+      - column_name: id
+        is_pk: False
+        datatype: String
+      - column_name: category_group_id
+        is_pk: False
+        datatype: String
+      - column_name: category_group_name
+        is_pk: False
+        datatype: String
+      - column_name: name
+        is_pk: False
+        datatype: String
+      - column_name: hidden
+        is_pk: False
+        datatype: Boolean
+      - column_name: original_category_group_id
+        is_pk: False
+        datatype: Null
+      - column_name: note
+        is_pk: False
+        datatype: String
+      - column_name: budgeted
+        is_pk: False
+        datatype: Int64
+      - column_name: activity
+        is_pk: False
+        datatype: Int64
+      - column_name: balance
+        is_pk: False
+        datatype: Int64
+      - column_name: goal_type
+        is_pk: False
+        datatype: String
+      - column_name: goal_needs_whole_amount
+        is_pk: False
+        datatype: Boolean
+      - column_name: goal_day
+        is_pk: False
+        datatype: Int64
+      - column_name: goal_cadence
+        is_pk: False
+        datatype: Int64
+      - column_name: goal_cadence_frequency
+        is_pk: False
+        datatype: Int64
+      - column_name: goal_creation_month
+        is_pk: False
+        datatype: String
+      - column_name: goal_target
+        is_pk: False
+        datatype: Int64
+      - column_name: goal_target_month
+        is_pk: False
+        datatype: String
+      - column_name: goal_percentage_complete
+        is_pk: False
+        datatype: Int64
+      - column_name: goal_months_to_budget
+        is_pk: False
+        datatype: Int64
+      - column_name: goal_under_funded
+        is_pk: False
+        datatype: Int64
+      - column_name: goal_overall_funded
+        is_pk: False
+        datatype: Int64
+      - column_name: goal_overall_left
+        is_pk: False
+        datatype: Int64
+      - column_name: deleted
+        is_pk: False
+        datatype: Boolean
+      - column_name: ingestion_date
+        is_pk: False
+        datatype: Date
+    entity_dependencies:
+      - 13
+    entity_description: >- 
+      Silver Categories Table
+      Other random information.
+  - entity_name: payees
+    entity_id: 9
+    entity_type: silver
+    entity_columns:
+      - column_name: id
+        is_pk: False
+        datatype: String
+      - column_name: name
+        is_pk: False
+        datatype: String
+      - column_name: transfer_account_id
+        is_pk: False
+        datatype: String
+      - column_name: deleted
+        is_pk: False
+        datatype: Boolean
+      - column_name: ingestion_date
+        is_pk: False
+        datatype: Date
+    entity_dependencies:
+      - 14
+    entity_description: >- 
+      Silver Payees Table
+      Other random information.
+  - entity_name: scheduled_transactions
+    entity_id: 10
+    entity_type: silver
+    entity_columns:
+      - column_name: id
+        is_pk: False
+        datatype: String
+      - column_name: date_first
+        is_pk: False
+        datatype: String
+      - column_name: date_next
+        is_pk: False
+        datatype: String
+      - column_name: frequency
+        is_pk: False
+        datatype: String
+      - column_name: amount
+        is_pk: False
+        datatype: Int64
+      - column_name: memo
+        is_pk: False
+        datatype: Null
+      - column_name: flag_color
+        is_pk: False
+        datatype: Null
+      - column_name: flag_name
+        is_pk: False
+        datatype: Null
+      - column_name: account_id
+        is_pk: False
+        datatype: String
+      - column_name: account_name
+        is_pk: False
+        datatype: String
+      - column_name: payee_id
+        is_pk: False
+        datatype: String
+      - column_name: payee_name
+        is_pk: False
+        datatype: String
+      - column_name: category_id
+        is_pk: False
+        datatype: String
+      - column_name: category_name
+        is_pk: False
+        datatype: String
+      - column_name: transfer_account_id
+        is_pk: False
+        datatype: Null
+      - column_name: deleted
+        is_pk: False
+        datatype: Boolean
+      - column_name: subtransactions
+        is_pk: False
+        datatype: List(Null)
+      - column_name: ingestion_date
+        is_pk: False
+        datatype: Date
+    entity_dependencies:
+      - 15
+    entity_description: >- 
+      Silver Scheduled Transactions Table
+      Other random information.
+  - entity_name: transactions
+    entity_id: 11
+    entity_type: silver
+    entity_columns:
+      - column_name: id
+        is_pk: False
+        datatype: String
+      - column_name: date
+        is_pk: False
+        datatype: String
+      - column_name: amount
+        is_pk: False
+        datatype: Int64
+      - column_name: memo
+        is_pk: False
+        datatype: String
+      - column_name: cleared
+        is_pk: False
+        datatype: String
+      - column_name: approved
+        is_pk: False
+        datatype: Boolean
+      - column_name: flag_color
+        is_pk: False
+        datatype: Null
+      - column_name: flag_name
+        is_pk: False
+        datatype: Null
+      - column_name: account_id
+        is_pk: False
+        datatype: String
+      - column_name: account_name
+        is_pk: False
+        datatype: String
+      - column_name: payee_id
+        is_pk: False
+        datatype: String
+      - column_name: payee_name
+        is_pk: False
+        datatype: String
+      - column_name: category_id
+        is_pk: False
+        datatype: String
+      - column_name: category_name
+        is_pk: False
+        datatype: String
+      - column_name: transfer_account_id
+        is_pk: False
+        datatype: String
+      - column_name: transfer_transaction_id
+        is_pk: False
+        datatype: String
+      - column_name: matched_transaction_id
+        is_pk: False
+        datatype: String
+      - column_name: import_id
+        is_pk: False
+        datatype: String
+      - column_name: import_payee_name
+        is_pk: False
+        datatype: String
+      - column_name: import_payee_name_original
+        is_pk: False
+        datatype: String
+      - column_name: deleted
+        is_pk: False
+        datatype: Boolean
+      - column_name: subtransactions
+        is_pk: False
+        datatype: List(Null)
+      - column_name: ingestion_date
+        is_pk: False
+        datatype: Date
+    entity_dependencies:
+      - 16
+    entity_description: >- 
+      Silver Transactions Table
+      Other random information.
+  - entity_name: accounts
+    entity_id: 12
+    entity_type: bronze
+  - entity_name: categories
+    entity_id: 13
+    entity_type: bronze
+  - entity_name: payees
+    entity_id: 14
+    entity_type: bronze
+  - entity_name: scheduled_transactions
+    entity_id: 15
+    entity_type: bronze
+  - entity_name: transactions
+    entity_id: 16
+    entity_type: bronze
+other_relationships:
+  - entity_name: other_transactions
+    entity_id: 21
+    entity_type: gold
+    entity_dependencies:
+      - 22

examples/example_release_notes.yaml

@@ -0,0 +1,15 @@
+- release_number: 0.0.3
+  release_date: 2025-03-12
+  changes:
+    - added fhj table
+    - changed column a in 372 table
+- release_number: 0.0.2
+  release_date: 2025-03-07
+  changes:
+    - added abc table
+    - changed column a in 678 table
+- release_number: 0.0.1
+  release_date: 2025-03-03
+  changes:
+    - added xyz table
+    - changed column a in 123 table