v0.9.2 Release Preparation

.github/workflows/prepare_release.yml

@@ -0,0 +1,57 @@
+name: Release Prep
+
+on:
+  workflow_dispatch:
+    inputs:
+      branch:
+        description: 'Branch to merge release notes and code analysis into.'
+        required: true
+        default: 'main'
+      version:
+        description:
+          'Version to use for the release. Must be in format: X.Y.Z.'
+      date:
+        description:
+          'Date of the release. Must be in format YYYY-MM-DD.'
+
+jobs:
+  preparerelease:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+      - name: Set up Python 3.10
+        uses: actions/setup-python@v5
+        with:
+          python-version: '3.10'
+
+      - name: Install dependencies
+        run: |
+            python -m pip install --upgrade pip
+            python -m pip install requests==2.31.0
+            python -m pip install bandit==1.7.7
+            python -m pip install .[test]
+
+      - name: Generate release notes
+        env:
+            GH_ACCESS_TOKEN: ${{ secrets.GH_ACCESS_TOKEN }}
+        run: >
+            python scripts/release_notes_generator.py
+            -v ${{ inputs.version }}
+            -d ${{ inputs.date }}
+
+      - name: Save static code analysis
+        run: bandit -r . -x ./tests,./scripts,./build -f txt -o static_code_analysis.txt --exit-zero
+
+      - name: Create pull request
+        id: cpr
+        uses: peter-evans/create-pull-request@v4
+        with:
+          token: ${{ secrets.GH_ACCESS_TOKEN }}
+          commit-message: Prepare release for v${{ inputs.version }}
+          author: "github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>"
+          committer: "github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>"
+          title: v${{ inputs.version }} Release Preparation
+          body: "This is an auto-generated PR to prepare the release."
+          branch: prepared-release
+          branch-suffix: short-commit-hash
+          base: ${{ inputs.branch }}

HISTORY.md

@@ -1,5 +1,20 @@
 # History
 
+## v0.9.2 - 2025-01-09
+
+### Maintenance
+
+* Create Prepare Release workflow - Issue [#364](https://github.com/sdv-dev/SDGym/issues/364) by @R-Palazzo
+
+### Bugs Fixed
+
+* Minimum tests failing because of broken action - Issue [#351](https://github.com/sdv-dev/SDGym/issues/351) by @amontanez24
+
+### New Features
+
+* Add integration with 3rd party synthesizer (REalTabFormer) - Issue [#347](https://github.com/sdv-dev/SDGym/issues/347) by @cristid9
+* Add support for numpy 2.0.0 - Issue [#315](https://github.com/sdv-dev/SDGym/issues/315) by @R-Palazzo
+
 ## v0.9.1 - 2024-08-29
 
 ### Bugs Fixed

scripts/release_notes_generator.py

@@ -0,0 +1,128 @@
+"""Script to generate release notes."""
+
+import argparse
+import os
+from collections import defaultdict
+
+import requests
+
+LABEL_TO_HEADER = {
+    'feature request': 'New Features',
+    'bug': 'Bugs Fixed',
+    'internal': 'Internal',
+    'maintenance': 'Maintenance',
+    'customer success': 'Customer Success',
+    'documentation': 'Documentation',
+    'misc': 'Miscellaneous',
+}
+ISSUE_LABELS = [
+    'documentation',
+    'maintenance',
+    'internal',
+    'bug',
+    'feature request',
+    'customer success',
+]
+NEW_LINE = '\n'
+GITHUB_URL = 'https://api.github.com/repos/sdv-dev/sdgym'
+GITHUB_TOKEN = os.getenv('GH_ACCESS_TOKEN')
+
+
+def _get_milestone_number(milestone_title):
+    url = f'{GITHUB_URL}/milestones'
+    headers = {'Authorization': f'Bearer {GITHUB_TOKEN}'}
+    query_params = {'milestone': milestone_title, 'state': 'all', 'per_page': 100}
+    response = requests.get(url, headers=headers, params=query_params)
+    body = response.json()
+    if response.status_code != 200:
+        raise Exception(str(body))
+    milestones = body
+    for milestone in milestones:
+        if milestone.get('title') == milestone_title:
+            return milestone.get('number')
+    raise ValueError(f'Milestone {milestone_title} not found in past 100 milestones.')
+
+
+def _get_issues_by_milestone(milestone):
+    headers = {'Authorization': f'Bearer {GITHUB_TOKEN}'}
+    # get milestone number
+    milestone_number = _get_milestone_number(milestone)
+    url = f'{GITHUB_URL}/issues'
+    page = 1
+    query_params = {'milestone': milestone_number, 'state': 'all'}
+    issues = []
+    while True:
+        query_params['page'] = page
+        response = requests.get(url, headers=headers, params=query_params)
+        body = response.json()
+        if response.status_code != 200:
+            raise Exception(str(body))
+        issues_on_page = body
+        if not issues_on_page:
+            break
+        issues.extend(issues_on_page)
+        page += 1
+    return issues
+
+
+def _get_issues_by_category(release_issues):
+    category_to_issues = defaultdict(list)
+    for issue in release_issues:
+        issue_title = issue['title']
+        issue_number = issue['number']
+        issue_url = issue['html_url']
+        line = f'* {issue_title} - Issue [#{issue_number}]({issue_url})'
+        assignee = issue.get('assignee')
+        if assignee:
+            login = assignee['login']
+            line += f' by @{login}'
+        # Check if any known label is marked on the issue
+        labels = [label['name'] for label in issue['labels']]
+        found_category = False
+        for category in ISSUE_LABELS:
+            if category in labels:
+                category_to_issues[category].append(line)
+                found_category = True
+                break
+        if not found_category:
+            category_to_issues['misc'].append(line)
+    return category_to_issues
+
+
+def _create_release_notes(issues_by_category, version, date):
+    title = f'## v{version} - {date}'
+    release_notes = f'{title}{NEW_LINE}{NEW_LINE}'
+    for category in ISSUE_LABELS + ['misc']:
+        issues = issues_by_category.get(category)
+        if issues:
+            section_text = (
+                f'### {LABEL_TO_HEADER[category]}{NEW_LINE}{NEW_LINE}'
+                f'{NEW_LINE.join(issues)}{NEW_LINE}{NEW_LINE}'
+            )
+            release_notes += section_text
+    return release_notes
+
+
+def update_release_notes(release_notes):
+    """Add the release notes for the new release to the ``HISTORY.md``."""
+    file_path = 'HISTORY.md'
+    with open(file_path, 'r') as history_file:
+        history = history_file.read()
+    token = '# HISTORY\n\n'
+    split_index = history.find(token) + len(token) + 1
+    header = history[:split_index]
+    new_notes = f'{header}{release_notes}{history[split_index:]}'
+    with open(file_path, 'w') as new_history_file:
+        new_history_file.write(new_notes)
+
+
+if __name__ == '__main__':
+    parser = argparse.ArgumentParser()
+    parser.add_argument('-v', '--version', type=str, help='Release version number (ie. v1.0.1)')
+    parser.add_argument('-d', '--date', type=str, help='Date of release in format YYYY-MM-DD')
+    args = parser.parse_args()
+    release_number = args.version
+    release_issues = _get_issues_by_milestone(release_number)
+    issues_by_category = _get_issues_by_category(release_issues)
+    release_notes = _create_release_notes(issues_by_category, release_number, args.date)
+    update_release_notes(release_notes)

static_code_analysis.txt

@@ -1,4 +1,4 @@
-Run started:2024-08-29 15:51:04.711485
+Run started:2025-01-09 15:17:21.988086
 
 Test results:
 >> Issue: [B403:blacklist] Consider possible security implications associated with pickle module.
@@ -15,53 +15,53 @@ Test results:
    Severity: Low   Confidence: High
    CWE: CWE-703 (https://cwe.mitre.org/data/definitions/703.html)
    More Info: https://bandit.readthedocs.io/en/1.7.7/plugins/b101_assert_used.html
-   Location: ./sdgym/benchmark.py:152:8
-151	    if isinstance(synthesizer, type):
-152	        assert issubclass(
-153	            synthesizer, BaselineSynthesizer
-154	        ), '`synthesizer` must be a synthesizer class'
-155	        synthesizer = synthesizer()
+   Location: ./sdgym/benchmark.py:151:8
+150	    if isinstance(synthesizer, type):
+151	        assert issubclass(synthesizer, BaselineSynthesizer), (
+152	            '`synthesizer` must be a synthesizer class'
+153	        )
+154	        synthesizer = synthesizer()
 
 --------------------------------------------------
 >> Issue: [B101:assert_used] Use of assert detected. The enclosed code will be removed when compiling to optimised byte code.
    Severity: Low   Confidence: High
    CWE: CWE-703 (https://cwe.mitre.org/data/definitions/703.html)
    More Info: https://bandit.readthedocs.io/en/1.7.7/plugins/b101_assert_used.html
-   Location: ./sdgym/benchmark.py:157:8
-156	    else:
-157	        assert issubclass(
-158	            type(synthesizer), BaselineSynthesizer
-159	        ), '`synthesizer` must be an instance of a synthesizer class.'
-160	
+   Location: ./sdgym/benchmark.py:156:8
+155	    else:
+156	        assert issubclass(type(synthesizer), BaselineSynthesizer), (
+157	            '`synthesizer` must be an instance of a synthesizer class.'
+158	        )
+159	
 
 --------------------------------------------------
 >> Issue: [B608:hardcoded_sql_expressions] Possible SQL injection vector through string-based query construction.
    Severity: Medium   Confidence: Low
    CWE: CWE-89 (https://cwe.mitre.org/data/definitions/89.html)
    More Info: https://bandit.readthedocs.io/en/1.7.7/plugins/b608_hardcoded_sql_expressions.html
-   Location: ./sdgym/benchmark.py:675:23
-674	    # User data script to install the library
-675	    user_data_script = f"""#!/bin/bash
-676	    sudo apt update -y
-677	    sudo apt install python3-pip -y
-678	    echo "======== Install Dependencies ============"
-679	    sudo pip3 install sdgym
-680	    sudo pip3 install anyio
-681	    pip3 list
-682	    sudo apt install awscli -y
-683	    aws configure set aws_access_key_id {credentials.access_key}
-684	    aws configure set aws_secret_access_key {credentials.secret_key}
-685	    aws configure set region {session.region_name}
-686	    echo "======== Write Script ==========="
-687	    sudo touch ~/sdgym_script.py
-688	    echo "{script_content}" > ~/sdgym_script.py
-689	    echo "======== Run Script ==========="
-690	    sudo python3 ~/sdgym_script.py
-691	    echo "======== Complete ==========="
-692	    INSTANCE_ID=$(curl -s http://169.254.169.254/latest/meta-data/instance-id)
-693	    aws ec2 terminate-instances --instance-ids $INSTANCE_ID
-694	    """
-695	
+   Location: ./sdgym/benchmark.py:674:23
+673	    # User data script to install the library
+674	    user_data_script = f"""#!/bin/bash
+675	    sudo apt update -y
+676	    sudo apt install python3-pip -y
+677	    echo "======== Install Dependencies ============"
+678	    sudo pip3 install sdgym
+679	    sudo pip3 install anyio
+680	    pip3 list
+681	    sudo apt install awscli -y
+682	    aws configure set aws_access_key_id {credentials.access_key}
+683	    aws configure set aws_secret_access_key {credentials.secret_key}
+684	    aws configure set region {session.region_name}
+685	    echo "======== Write Script ==========="
+686	    sudo touch ~/sdgym_script.py
+687	    echo "{script_content}" > ~/sdgym_script.py
+688	    echo "======== Run Script ==========="
+689	    sudo python3 ~/sdgym_script.py
+690	    echo "======== Complete ==========="
+691	    INSTANCE_ID=$(curl -s http://169.254.169.254/latest/meta-data/instance-id)
+692	    aws ec2 terminate-instances --instance-ids $INSTANCE_ID
+693	    """
+694	
 
 --------------------------------------------------
 >> Issue: [B404:blacklist] Consider possible security implications associated with the subprocess module.
@@ -96,7 +96,7 @@ Test results:
 --------------------------------------------------
 
 Code scanned:
-	Total lines of code: 2735
+	Total lines of code: 2769
 	Total lines skipped (#nosec): 0
 	Total potential issues skipped due to specifically being disabled (e.g., #nosec BXXX): 0