Merge pull request #139 from rwnx/use-typer

CLI refactor

Author: rwnx

.github/workflows/pypi.yml

@@ -43,7 +43,7 @@ jobs:
       - uses: actions/checkout@v2
       - uses: actions/setup-python@v2
         with:
-          python-version: '3.8' 
+          python-version: '3.12' 
       - name: Setup MSSQL
         run: bash tests_integration/mssql/install_mssql.sh
       - name: Setup test env
@@ -62,7 +62,7 @@ jobs:
         options: --health-cmd="mysqladmin ping" --health-interval=10s --health-timeout=5s --health-retries=3
 
     runs-on: ubuntu-latest
-    container: python:3.8
+    container: python:3.12
     env:
       PYNONYMIZER_DB_HOST: db
       PYNONYMIZER_DB_USER: root
@@ -88,7 +88,7 @@ jobs:
         options: --health-cmd pg_isready --health-interval 10s --health-timeout 5s --health-retries 5
 
     runs-on: ubuntu-latest
-    container: python:3.8
+    container: python:3.12
     env:
       PYNONYMIZER_DB_HOST: db
       PYNONYMIZER_DB_USER: postgres
@@ -104,7 +104,7 @@ jobs:
 
   package: 
     runs-on: ubuntu-latest
-    container: python:3.8
+    container: python:3.12
     needs: 
       - test
       - integration-mysql
@@ -125,7 +125,7 @@ jobs:
     needs: 
       - package
     runs-on: ubuntu-latest
-    container: python:3.8
+    container: python:3.12
     steps:
     - uses: actions/download-artifact@v2
       with:

CHANGELOG.md

@@ -20,6 +20,16 @@ and this project adheres to [Semantic Versioning](http://semver.org/spec/v2.0.0.
 - Better error messages for unsupported fake types - the error should now explain the problem and link to the docs in the right section. [#133]
 - Error message for when a fake_type is used with the wrong config kwargs (these would have previously been caught under "unsupported fake types")
 
+### Removed
+- Positional INPUT. Use the -i/--input option instead
+- Positional STRATEGYFILE. Use the -s/--strategy option instead
+- Positional OUTPUT. Use the -o/--output option instead
+- Deprecated environment keys: `DB_TYPE, DB_HOST, DB_NAME, DB_USER, DB_PASS`.
+- `--fake-locale` `-l` `$PYNONYMIZER_FAKE_LOCALE` cli option. Use the `locale:` key in your strategyfile instead
+
+### Changed
+- environment vars
+
 ## [1.25.0] 2023-03-29
 ### Changed
 - Postgres FAKE_UPDATE strategy now uses an id-based randomization to pick from the seed table. 

README.md

@@ -104,104 +104,9 @@ If this workflow doesnt work for you, see [process control](https://github.com/r
 ## Usage
 ### CLI
 1. Write a [strategyfile](https://github.com/rwnx/pynonymizer/blob/main/doc/strategyfiles.md) for your database
+1. Check out the help for a description of options `pynonymizer --help`
 1. Start Anonymizing!
-```
-usage: pynonymizer [-h] [--input INPUT] [--strategy STRATEGYFILE]
-                   [--output OUTPUT] [--db-type DB_TYPE] [--db-host DB_HOST]
-                   [--db-port DB_PORT] [--db-name DB_NAME] [--db-user DB_USER]
-                   [--db-password DB_PASSWORD] [--fake-locale FAKE_LOCALE]
-                   [--start-at STEP] [--only-step STEP]
-                   [--skip-steps STEP [STEP ...]] [--stop-at STEP]
-                   [--seed-rows SEED_ROWS] [--mssql-driver MSSQL_DRIVER]
-                   [--mssql-backup-compression]
-                   [--mysql-cmd-opts MYSQL_CMD_OPTS]
-                   [--mysql-dump-opts MYSQL_DUMP_OPTS]
-                   [--postgres-cmd-opts POSTGRES_CMD_OPTS]
-                   [--postgres-dump-opts POSTGRES_DUMP_OPTS] [-v] [--verbose]
-                   [--dry-run] [--ignore-anonymization-errors]
-
-A tool for writing better anonymization strategies for your production
-databases.
-
-optional arguments:
-  -h, --help            show this help message and exit
-  --input INPUT, -i INPUT
-                        The source dump filepath to read from. Use `-` for
-                        stdin. [$PYNONYMIZER_INPUT]
-  --strategy STRATEGYFILE, -s STRATEGYFILE
-                        A strategyfile to use during anonymization.
-                        [$PYNONYMIZER_STRATEGY]
-  --output OUTPUT, -o OUTPUT
-                        The destination filepath to write the dumped output
-                        to. Use `-` for stdout. [$PYNONYMIZER_OUTPUT]
-  --db-type DB_TYPE, -t DB_TYPE
-                        Type of database to interact with. More databases will
-                        be supported in future versions. default: mysql
-                        [$PYNONYMIZER_DB_TYPE]
-  --db-host DB_HOST, -d DB_HOST
-                        Database hostname or IP address.
-                        [$PYNONYMIZER_DB_HOST]
-  --db-port DB_PORT, -P DB_PORT
-                        Database port. Defaults to provider default.
-                        [$PYNONYMIZER_DB_PORT]
-  --db-name DB_NAME, -n DB_NAME
-                        Name of database to restore and anonymize in. If not
-                        provided, a unique name will be generated from the
-                        strategy name. This will be dropped at the end of the
-                        run. [$PYNONYMIZER_DB_NAME]
-  --db-user DB_USER, -u DB_USER
-                        Database credentials: username. [$PYNONYMIZER_DB_USER]
-  --db-password DB_PASSWORD, -p DB_PASSWORD
-                        Database credentials: password.
-                        [$PYNONYMIZER_DB_PASSWORD]
-  --fake-locale FAKE_LOCALE, -l FAKE_LOCALE
-                        Locale setting to initialize fake data generation.
-                        Affects Names, addresses, formats, etc.
-                        [$PYNONYMIZER_FAKE_LOCALE]
-  --start-at STEP       Choose a step to begin the process (inclusive).
-                        [$PYNONYMIZER_START_AT]
-  --only-step STEP      Choose one step to perform. [$PYNONYMIZER_ONLY_STEP]
-  --skip-steps STEP [STEP ...]
-                        Choose one or more steps to skip.
-                        [$PYNONYMIZER_SKIP_STEPS]
-  --stop-at STEP        Choose a step to stop at (inclusive).
-                        [$PYNONYMIZER_STOP_AT]
-  --seed-rows SEED_ROWS
-                        Specify a number of rows to populate the fake data
-                        table used during anonymization. Defaults to 150.
-                        [$PYNONYMIZER_SEED_ROWS]
-  --mssql-driver MSSQL_DRIVER
-                        [MSSQL] ODBC driver to use for database connection
-                        [$PYNONYMIZER_MSSQL_DRIVER]
-  --mssql-backup-compression
-                        [MSSQL] Use compression when backing up the database.
-                        [$PYNONYMIZER_MSSQL_BACKUP_COMPRESSION]
-  --mysql-cmd-opts MYSQL_CMD_OPTS
-                        [MYSQL] pass additional arguments to the restore
-                        process (advanced use only!).
-                        [$PYNONYMIZER_MYSQL_CMD_OPTS]
-  --mysql-dump-opts MYSQL_DUMP_OPTS
-                        [MYSQL] pass additional arguments to the dump process
-                        (advanced use only!). [$PYNONYMIZER_MYSQL_DUMP_OPTS]
-  --postgres-cmd-opts POSTGRES_CMD_OPTS
-                        [POSTGRES] pass additional arguments to the restore
-                        process (advanced use only!).
-                        [$PYNONYMIZER_POSTGRES_CMD_OPTS]
-  --postgres-dump-opts POSTGRES_DUMP_OPTS
-                        [POSTGRES] pass additional arguments to the dump
-                        process (advanced use only!).
-                        [$PYNONYMIZER_POSTGRES_DUMP_OPTS]
-  -v, --version         show program's version number and exit
-  --verbose             Increases the verbosity of the logging feature, to
-                        help when troubleshooting issues.
-                        [$PYNONYMIZER_VERBOSE]
-  --dry-run             Instruct pynonymizer to skip all process steps. Useful
-                        for testing safely. [$PYNONYMIZER_DRY_RUN]
-  --ignore-anonymization-errors
-                        Instruct pynonymizer to ignore errors during the
-                        anonymization process and continue as normal.
-                        [$PYNONYMIZER_IGNORE_ANONYMIZATION_ERRORS]
-```
+
 ### Package
 Pynonymizer can also be invoked programmatically / from other python code. See the module entrypoint [pynonymizer](pynonymizer/__init__.py) or [pynonymizer/pynonymize.py](pynonymizer/pynonymize.py)