1st commit

.gitignore

@@ -0,0 +1,169 @@
+# 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/#use-with-ide
+.pdm.toml
+
+# 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/
+
+# Configuration file
+config.json
+
+# UML diagram
+.puml
+
+# OS specific
+.DS_Store

.vscode/settings.json

@@ -0,0 +1,13 @@
+{
+    "python.testing.pytestArgs": [
+        "-s",
+        "--cov=.",
+        "tests"
+    ],
+    "python.testing.unittestEnabled": false,
+    "python.testing.pytestEnabled": true,
+    "[python]": {
+        "editor.defaultFormatter": "ms-python.black-formatter"
+    },
+    "python.formatting.provider": "none"
+}

LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2023 Francesco Lumachi <[email protected]>
+
+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.

README.md

@@ -0,0 +1,24 @@
+# salesforce-erd
+A tool to build your Salesforce instance Entity-Relationship Diagram.
+
+## How to use
+This tool is designed as a script to produce a [plantuml](https://plantuml.com/) text diagram based on Salesforce metadata. To achieve an actual drawing (an svg/png/pdf file) use the produced txt file as input for [plantuml tool](https://plantuml.com/starting).
+
+## How to run
+1. This project use [poetry](https://python-poetry.org/) to organize dependencies. Install it in your system before use.
+2. Duplicate `config.json.template` and rename it in `config.json`. Then fill the requested variables:  
+    a. `user`, `password`, `token` to connect to your Salesforce instance,  
+    b. `diagram_name` is the name that you want to give to the UML diagram,  
+    c. `tables` is the subset of entities that you want in your diagram (the full Salesforce instance it will have easily too much entities to be shown).  
+3. Run `poetry run python build_erd.py` to execute the script. The first run will be longer because [poetry](https://python-poetry.org/) will create a dedicated environment with the necessary dependencies. Follow the provided instruction in order to build your diagram.
+4. Output will be written into `salesforce_erd.puml` file. From here, you can invoke [plantuml](https://plantuml.com/) to transform the diagram in a visual format. 
+
+### Example
+Refer to [plantuml](https://plantuml.com/) documentation, but you probably need to tweak some option, like the maximum file size:
+```bash
+export PLANTUML_LIMIT_SIZE=32767
+plantuml -tsvg salesforce_erd.puml
+```
+
+## Contributing
+This tool is just a POC and needs lot of improvements in testing and usability. If this software do not satisfy you "as-is", consider improve it and send a pull request. Thank you! 

build_erd.py

@@ -0,0 +1,128 @@
+import click
+import pandas as pd
+
+from salesforce_erd import (
+    fields_of,
+    filter_tables,
+    get_instance,
+    read_config,
+    show_tables,
+)
+
+
+@click.command()
+@click.option(
+    "--config-file",
+    "-c",
+    default="config.json",
+    help="Path to the JSON configuration file",
+)
+def build_erd(config_file):
+    conf = read_config(config_file)
+
+    # Read Salesforce metadata
+    sf = get_instance(conf.get("user"), conf.get("password"), conf.get("token"))
+    tables_meta = show_tables(sf)
+
+    # Filter tables
+    tables = conf.get("tables", [])
+    if len(tables) > 0:
+        tables_meta = filter_tables(tables_meta, names=tables)
+
+    # Generate PlantUML text for class diagram
+    plantuml_code = write_header(conf.get("diagram_name"))
+
+    for table in tables_meta.name:
+        # Get entity attributes
+        columns_meta = fields_of(table, sf, metadata=True)
+        columns_meta.soapType = columns_meta.soapType.str[4:]
+
+        # Extract relations
+        relation_meta = get_relations(columns_meta)
+
+        # Entity
+        plantuml_code += write_entity(table, columns_meta, relation_meta)
+
+        # Relationship
+        plantuml_code += write_relationship(tables, table, relation_meta)
+
+        # Close E-R loop
+        plantuml_code += "\n"
+
+    # Footer
+    plantuml_code += "@enduml"
+
+    # Write output to file
+    with open("salesforce_erd.puml", "w") as file:
+        file.write(plantuml_code)
+
+
+def write_relationship(tables, table, relation_meta) -> str:
+    plantuml_code = ""
+    relation_meta = (
+        relation_meta.groupby("referenceTo")["relationshipName"]
+        .agg(list)
+        .str.join(", ")
+        .reset_index()
+    )  # Aggregate relations targetting same entity
+    for _, relation in relation_meta.explode("referenceTo").iterrows():
+        # Drop recursive relation and only specified table
+        if (table != relation["referenceTo"]) and (
+            relation["referenceTo"] in tables if len(tables) > 0 else True
+        ):
+            plantuml_code += f"{table} -left-> {relation['referenceTo']}\n"
+    return plantuml_code
+
+
+def write_entity(table, columns_meta, relation_meta) -> str:
+    plantuml_code = f"class {table} {{\n"
+
+    # Attributes loop
+    for _, attribute in columns_meta.sort_values(by="name").iterrows():
+        method_or_field = "{method} #" if attribute["calculated"] else "{field} +"
+        bold_open_if_ID = "<b>" if attribute["soapType"] == "ID" else ""
+        attribute_type = (
+            attribute["soapType"]
+            if attribute["type"].lower() == attribute["soapType"].lower()
+            else f"{attribute['type']}<{attribute['soapType']}>"
+        )
+        bold_close_if_ID = "</b>" if attribute["soapType"] == "ID" else ""
+        references = relation_meta.loc[
+            relation_meta["name"] == attribute["name"], "referenceTo"
+        ]
+        if len(references) == 0:
+            references = ["No reference found."]
+        reference_to = (
+            ":\n" + ", \n".join(map(lambda r: f"<b>{r}</b>", references))
+            if attribute["type"].lower() == "reference"
+            else ""
+        )
+        plantuml_code += f"  {method_or_field}{bold_open_if_ID}{attribute['name']}: {attribute_type}{bold_close_if_ID}{reference_to}\n"
+
+    plantuml_code += f"}}\n"
+    return plantuml_code
+
+
+def get_relations(columns_meta) -> pd.DataFrame:
+    relation_meta = columns_meta.loc[
+        columns_meta.referenceTo.apply(len) > 0,
+        ["name", "relationshipName", "referenceTo"],
+    ]
+    # Drop relationship with no name
+    relation_meta = relation_meta.dropna(subset="relationshipName")
+    # Flatten polymorphic relations
+    relation_meta = relation_meta.explode("referenceTo")
+    return relation_meta
+
+
+def write_header(diagram_name) -> str:
+    plantuml_code = (
+        f"@startuml {diagram_name} - {pd.Timestamp.now().isoformat()[:10]}\n"
+    )
+    plantuml_code += "skinparam linetype ortho\n"  # °90 degree angle only for arrows
+    plantuml_code += "hide empty methods\n"
+    return plantuml_code
+
+
+if __name__ == "__main__":
+    build_erd()

config.json.template

@@ -0,0 +1,7 @@
+{
+    "user": "",
+    "password": "",
+    "token": "",
+    "diagram_name": "",
+    "tables": []
+}