AMW-590 Collection spelling and grammar checking for PRs

.github/vale-lint/action.yml

@@ -0,0 +1,47 @@
+---
+name: Vale Prose Lint
+description: Spell and grammar checks for ansible-middleware collections using Vale
+
+inputs:
+  vale-version:
+    description: Vale version to install
+    required: false
+    default: '3.15.1'
+  min-alert-level:
+    description: Minimum alert level to report (suggestion, warning, error)
+    required: false
+    default: warning
+
+runs:
+  using: composite
+  steps:
+    - name: Install Vale
+      shell: bash
+      run: |
+        wget -qO- "https://github.com/errata-ai/vale/releases/download/v${{ inputs.vale-version }}/vale_${{ inputs.vale-version }}_Linux_64-bit.tar.gz" \
+          | tar xz -C /usr/local/bin vale
+
+    - name: Merge shared vocabulary
+      shell: bash
+      run: |
+        mkdir -p .github/styles/config/vocabularies/Base
+        cat "${{ github.action_path }}/vocabularies/accept.txt" \
+          >> .github/styles/config/vocabularies/Base/accept.txt
+
+    - name: Download Vale styles
+      shell: bash
+      run: vale sync
+
+    - name: Lint prose files
+      shell: bash
+      run: vale --minAlertLevel "${{ inputs.min-alert-level }}" .
+
+    - name: Install Python dependencies
+      shell: bash
+      run: |
+        sudo apt-get install -y python3-docutils hunspell hunspell-en-us
+        pip install pyyaml
+
+    - name: Lint Ansible YAML name fields
+      shell: bash
+      run: python3 "${{ github.action_path }}/scripts/check_grammar_spelling.py"

.github/vale-lint/scripts/check_grammar_spelling.py

@@ -0,0 +1,204 @@
+"""Check grammar and spelling in Ansible YAML prose fields using Vale."""
+import glob
+import os
+import re
+import subprocess
+import sys
+import tempfile
+
+try:
+    import yaml
+except ImportError:
+    print("PyYAML not available, skipping YAML prose check.", file=sys.stderr)
+    sys.exit(0)
+
+PROJECT_ROOT = os.getcwd()
+ACCEPT_TXT = os.path.join(
+    PROJECT_ROOT, ".github", "styles", "config", "vocabularies", "Base", "accept.txt"
+)
+
+
+def _find_vale_config():
+    """Walk up from the working directory to find .vale.ini, mirroring Vale's own discovery."""
+    current = PROJECT_ROOT
+    while True:
+        candidate = os.path.join(current, '.vale.ini')
+        if os.path.exists(candidate):
+            return candidate
+        parent = os.path.dirname(current)
+        if parent == current:
+            return os.path.join(PROJECT_ROOT, '.vale.ini')
+        current = parent
+
+
+VALE_CONFIG = _find_vale_config()
+
+JINJA2_RE = re.compile(r'\{\{[^}]+\}\}')
+
+# Prose-bearing keys extracted from task/handler/playbook/molecule YAML files.
+TASK_KEYS = frozenset({'name', 'msg', 'fail_msg', 'success_msg'})
+
+# Prose-bearing keys extracted from galaxy.yml and role meta/argument_specs files.
+META_KEYS = frozenset({'description', 'short_description'})
+
+# Task-specific Vale config: project override takes precedence over action default.
+_ACTION_DIR = os.path.dirname(os.path.dirname(os.path.abspath(__file__)))
+_PROJECT_TASKS_INI = os.path.join(PROJECT_ROOT, '.github', 'vale-tasks.ini')
+_ACTION_TASKS_INI = os.path.join(_ACTION_DIR, 'vale-tasks.ini')
+TASKS_INI = _PROJECT_TASKS_INI if os.path.exists(_PROJECT_TASKS_INI) else _ACTION_TASKS_INI
+
+
+def _load_accepted_terms():
+    """Load accepted spelling terms from the merged Vale vocabulary file."""
+    try:
+        with open(ACCEPT_TXT) as f:
+            return {line.strip() for line in f if line.strip()}
+    except FileNotFoundError:
+        return set()
+
+
+ACCEPTED_TERMS = _load_accepted_terms()
+
+
+def _build_tasks_config():
+    """Return path to a temp Vale config: project base merged with task suppressions."""
+    try:
+        with open(VALE_CONFIG) as f:
+            base = f.read()
+    except FileNotFoundError:
+        base = ''
+    extra = ''
+    if os.path.exists(TASKS_INI):
+        with open(TASKS_INI) as f:
+            extra = f.read()
+    config_dir = os.path.dirname(os.path.abspath(VALE_CONFIG))
+    with tempfile.NamedTemporaryFile(
+        mode='w', suffix='.ini', dir=config_dir, delete=False
+    ) as f:
+        f.write(base)
+        if extra:
+            f.write('\n' + extra)
+        return f.name
+
+
+def get_prose_fields(filepath, keys):
+    results = []
+    try:
+        with open(filepath) as f:
+            raw = f.read()
+        data = yaml.safe_load(raw)
+        lines = raw.splitlines()
+
+        def _collect(obj):
+            if isinstance(obj, dict):
+                for k, v in obj.items():
+                    if k in keys:
+                        texts = [v] if isinstance(v, str) else (v if isinstance(v, list) else [])
+                        for text in texts:
+                            if not isinstance(text, str) or not text.strip():
+                                continue
+                            text = text.strip().strip('"\'')
+                            needle = text.split('{{', maxsplit=1)[0].strip()[:30]
+                            lineno = next(
+                                (i + 1 for i, l in enumerate(lines)
+                                 if f'{k}:' in l and needle and needle in l),
+                                0,
+                            )
+                            results.append((lineno, text))
+                    else:
+                        _collect(v)
+            elif isinstance(obj, list):
+                for item in obj:
+                    _collect(item)
+
+        _collect(data)
+    except Exception:
+        pass
+    return results
+
+
+def is_accepted(message, rule):
+    """Return True if the finding should be suppressed."""
+    if rule == "Vale.Spelling":
+        # Extract the flagged word from "Did you really mean 'X'?"
+        m = re.search(r"'([^']+)'", message)
+        if m and m.group(1) in ACCEPTED_TERMS:
+            return True
+    return False
+
+
+def vale_check(text, config):
+    """Run Vale on a single string using the given config, returning filtered findings."""
+    clean = JINJA2_RE.sub('VALUE', text)
+    # Skip tokens that look like Ansible variable names (underscore-separated)
+    clean = re.sub(r'\b(?:[a-z][a-z\d]*_)+[a-z\d_]+\b', 'VARNAME', clean)
+
+    with tempfile.NamedTemporaryFile(
+        mode='w', suffix='.md', dir=PROJECT_ROOT, delete=False
+    ) as tmp:
+        tmp.write(clean + '\n')
+        tmp_path = tmp.name
+
+    findings = []
+    try:
+        result = subprocess.run(
+            ['vale', '--config', config, '--output=line',
+             '--minAlertLevel=warning', tmp_path],
+            capture_output=True, text=True, check=False,
+        )
+        for line in result.stdout.strip().splitlines():
+            # Format: "path:line:col:rule:message"
+            parts = line.split(':')
+            if len(parts) < 5:
+                continue
+            rule = parts[3].strip()
+            message = ':'.join(parts[4:]).strip()
+            if not is_accepted(message, rule):
+                findings.append((rule, message))
+    finally:
+        os.unlink(tmp_path)
+
+    return findings
+
+
+def _check_files(file_list, keys, config):
+    found_issues = False
+    for filepath in file_list:
+        for lineno, text in get_prose_fields(filepath, keys):
+            for rule, message in vale_check(text, config):
+                found_issues = True
+                print(f"{filepath}:{lineno}: {message} [{text!r}]")
+    return found_issues
+
+
+def main():
+    task_files = sorted(set(
+        glob.glob('roles/**/tasks/**/*.yml', recursive=True) +
+        glob.glob('roles/**/tasks/*.yml', recursive=True) +
+        glob.glob('roles/**/handlers/**/*.yml', recursive=True) +
+        glob.glob('roles/**/handlers/*.yml', recursive=True) +
+        glob.glob('playbooks/**/*.yml', recursive=True) +
+        glob.glob('playbooks/*.yml') +
+        glob.glob('molecule/**/*.yml', recursive=True) +
+        glob.glob('molecule/*.yml')
+    ))
+
+    meta_files = sorted(set(
+        glob.glob('galaxy.yml') +
+        glob.glob('roles/*/meta/main.yml') +
+        glob.glob('roles/*/meta/argument_specs.yml')
+    ))
+
+    tasks_config = _build_tasks_config()
+    try:
+        found_issues = _check_files(task_files, TASK_KEYS, tasks_config)
+        found_issues = _check_files(meta_files, META_KEYS, tasks_config) or found_issues
+    finally:
+        os.unlink(tasks_config)
+
+    if found_issues:
+        sys.exit(1)
+
+
+if __name__ == '__main__':
+    main()

.github/vale-lint/vale-tasks.ini

@@ -0,0 +1,8 @@
+# Rule suppressions applied only when Vale checks Ansible YAML prose fields
+# (task names, handler names, descriptions, etc.).
+# These rules generate too many false positives for short imperative strings.
+#
+# Projects can override this file by creating .github/vale-tasks.ini in their
+# repository. The project file takes precedence over this shared default.
+write-good.TooWordy = NO
+write-good.Weasel = NO

.github/vale-lint/vocabularies/accept.txt

@@ -0,0 +1,106 @@
+Ranabir
+Chakraborty
+Harsha
+Cherukuri
+Ingo
+Weiss
+Martin
+Cihlar
+Cihlář
+Romain
+Pelisse
+Guido
+Grazioli
+WildFly
+wildfly
+JBoss
+jboss
+EAP
+eap
+Keycloak
+keycloak
+Prospero
+prospero
+Temurin
+OpenJDK
+openjdk
+Ansible
+ansible
+GitHub
+github
+RHEL
+rhel
+DNF
+RPM
+systemd
+firewalld
+POSIX
+JVM
+JDK
+JDBC
+JEE
+JGroups
+jgroup
+YAML
+yaml
+JSON
+json
+XML
+xml
+SSL
+API
+CLI
+cli
+WAR
+RHN
+rhn
+FQCN
+Jinja
+jinja
+playbook
+playbooks
+middleware
+prereqs
+prereq
+argspec
+Argspec
+uninstall
+appserver
+colocated
+multicast
+infinispan
+idempotency
+idempotence
+selinux
+autostart
+bugfix
+Bugfixes
+bugfixes
+pidfile
+elytron
+bugzilla
+wfly
+iface
+mcast
+utils
+repo
+repos
+boolean
+env
+nodeId
+Hostname
+hostname
+pre
+readme
+varname
+zipfile
+fixup
+restorecon
+Overridable
+overridable
+Systemd
+Multicast
+Firewalld
+Yaml
+Config
+config