recipe-maintainer/recipe-info/lasuite-docs/tests/upload_conversion.py

#!/usr/bin/env python3
"""Upload + conversion test for La Suite Docs.

Verifies the end-to-end conversion path:
- `.md` upload → backend → y-provider (yjs)
- `.docx` upload → backend → docspec (BlockNote JSON) → y-provider (yjs)

Exercises CONVERSION_UPLOAD_ENABLED on the backend, backend→y-provider auth
(Y_PROVIDER_API_KEY_FILE) and routing (Y_PROVIDER_API_BASE_URL), and
DOCSPEC_API_URL for the .docx import path.
"""
import argparse
import io
import json
import os
import sys
import urllib.error
import urllib.request
import uuid
import zipfile

sys.path.insert(0, os.path.join(os.path.dirname(__file__), '..', '..', '..'))
from utils.tests.helpers import (
    http_post, load_toml_credentials, resolve_domain,
)


def build_minimal_docx() -> bytes:
    """Build a minimal valid .docx (OOXML) in memory."""
    buf = io.BytesIO()
    with zipfile.ZipFile(buf, 'w', zipfile.ZIP_DEFLATED) as z:
        z.writestr('[Content_Types].xml',
            '<?xml version="1.0" encoding="UTF-8" standalone="yes"?>'
            '<Types xmlns="http://schemas.openxmlformats.org/package/2006/content-types">'
            '<Default Extension="rels" ContentType="application/vnd.openxmlformats-package.relationships+xml"/>'
            '<Default Extension="xml" ContentType="application/xml"/>'
            '<Override PartName="/word/document.xml" '
            'ContentType="application/vnd.openxmlformats-officedocument.wordprocessingml.document.main+xml"/>'
            '</Types>')
        z.writestr('_rels/.rels',
            '<?xml version="1.0" encoding="UTF-8" standalone="yes"?>'
            '<Relationships xmlns="http://schemas.openxmlformats.org/package/2006/relationships">'
            '<Relationship Id="rId1" '
            'Type="http://schemas.openxmlformats.org/officeDocument/2006/relationships/officeDocument" '
            'Target="word/document.xml"/>'
            '</Relationships>')
        z.writestr('word/document.xml',
            '<?xml version="1.0" encoding="UTF-8" standalone="yes"?>'
            '<w:document xmlns:w="http://schemas.openxmlformats.org/wordprocessingml/2006/main">'
            '<w:body><w:p><w:r><w:t>Upload conversion test</w:t></w:r></w:p></w:body>'
            '</w:document>')
    return buf.getvalue()


def get_oidc_token(kc_url, creds):
    """Direct grant flow against the lasuite-docs realm."""
    status, data = http_post(
        f"{kc_url}/realms/{creds['kc_realm']}/protocol/openid-connect/token",
        data={
            "grant_type": "password",
            "client_id": creds["kc_client_id"],
            "client_secret": creds["kc_client_secret"],
            "username": creds["kc_test_user"],
            "password": creds["kc_test_pass"],
            "scope": "openid email",
        },
        content_type="application/x-www-form-urlencoded",
    )
    return (data or {}).get("access_token", "")


def multipart_upload(url, token, filename, content_type, body):
    """POST a file via multipart/form-data with a Bearer token."""
    boundary = uuid.uuid4().hex
    parts = [
        f"--{boundary}\r\n".encode(),
        b'Content-Disposition: form-data; name="title"\r\n\r\n',
        b"upload-conversion-test\r\n",
        f"--{boundary}\r\n".encode(),
        f'Content-Disposition: form-data; name="file"; filename="{filename}"\r\n'.encode(),
        f"Content-Type: {content_type}\r\n\r\n".encode(),
        body,
        f"\r\n--{boundary}--\r\n".encode(),
    ]
    req_body = b"".join(parts)
    req = urllib.request.Request(
        url,
        data=req_body,
        headers={
            "Authorization": f"Bearer {token}",
            "Content-Type": f"multipart/form-data; boundary={boundary}",
        },
        method="POST",
    )
    try:
        with urllib.request.urlopen(req, timeout=30) as resp:
            return resp.status, resp.read().decode()
    except urllib.error.HTTPError as e:
        return e.code, e.read().decode()


def upload_step(label, docs_url, token, filename, content_type, body):
    print(f"Step: Upload {label} ...")
    status, raw = multipart_upload(
        f"{docs_url}/api/v1.0/documents/", token, filename, content_type, body,
    )
    if status != 201:
        print(f"  FAIL: {label} upload returned HTTP {status}: {raw[:200]}")
        sys.exit(1)
    try:
        doc = json.loads(raw)
    except json.JSONDecodeError:
        print(f"  FAIL: {label} response not JSON: {raw[:200]}")
        sys.exit(1)
    doc_id = doc.get('id')
    if not doc_id:
        print(f"  FAIL: {label} response missing 'id': {raw[:200]}")
        sys.exit(1)
    print(f"  PASS: {label} converted and persisted (document id {doc_id})")


def main():
    parser = argparse.ArgumentParser()
    parser.add_argument('--domain', default=os.environ.get('TEST_DOMAIN'))
    args = parser.parse_args()

    recipe_dir = os.path.join(os.path.dirname(__file__), '..')
    creds = load_toml_credentials(recipe_dir, 'keycloak')
    if creds is None:
        print("FAIL: Credentials file not found: keycloak-test-credentials.<domain_suffix>.toml")
        print("Run setup_keycloak_integration.py first.")
        sys.exit(1)

    docs_domain = args.domain or resolve_domain('lasuite-docs')
    kc_domain = resolve_domain('keycloak')
    docs_url = f"https://{docs_domain}"
    kc_url = f"https://{kc_domain}"

    print("Testing file upload + conversion (CONVERSION_UPLOAD_ENABLED + Y_PROVIDER)")
    print()

    print("Step 1: Obtaining access token from Keycloak ...")
    token = get_oidc_token(kc_url, creds)
    if not token:
        print("  FAIL: Could not obtain access token from Keycloak")
        sys.exit(1)
    print(f"  PASS: Obtained access token ({len(token)} chars)")

    upload_step(
        ".md file", docs_url, token,
        "upload-test.md", "text/markdown",
        b"# Upload Conversion Test\n\nValidating **CONVERSION_UPLOAD_ENABLED** end-to-end.\n",
    )

    upload_step(
        ".docx file", docs_url, token,
        "upload-test.docx",
        "application/vnd.openxmlformats-officedocument.wordprocessingml.document",
        build_minimal_docx(),
    )

    print()
    print("PASS: Upload + conversion working end-to-end (.md and .docx)")


if __name__ == '__main__':
    main()