Skip to content

Add XSD ingestion and schema-driven XML generation #1458

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
Paul Lizer (paullizer) merged 3 commits into from
Sep 7, 2026
Merged

Add XSD ingestion and schema-driven XML generation #1458

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
535556c
Add XSD ingestion and schema-driven XML generation
paullizer Sep 7, 2026
7068182
Merge Development into XSD support branch
paullizer Sep 7, 2026
cf20679
Harden XSD upload error responses
paullizer Sep 7, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
13 changes: 11 additions & 2 deletions application/single_app/config.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -22,6 +22,7 @@
mimetypes.add_type('font/ttf', '.ttf')
mimetypes.add_type('font/otf', '.otf')
mimetypes.add_type('application/vnd.ms-outlook', '.msg')
mimetypes.add_type('application/xml', '.xsd')
import openpyxl
import xlrd
import traceback
Expand Down Expand Up @@ -97,7 +98,7 @@
EXECUTOR_TYPE = 'thread'
EXECUTOR_MAX_WORKERS = 30
SESSION_TYPE = 'filesystem'
VERSION = "0.261.021"
VERSION = "0.261.023"
IS_DEVELOPMENT = is_development_env_enabled()

# Opt-out for deployments where App Service Easy Auth is active but the platform
Expand Down Expand Up @@ -184,6 +185,7 @@ def _split_env_list(raw_value, lowercase=False):
BASE_ALLOWED_EXTENSIONS = {'txt', 'doc', 'docm', 'html', 'md', 'json', 'xml', 'yaml', 'yml', 'log'}
DOCUMENT_EXTENSIONS = {'pdf', 'docx', 'pptx', 'ppt'}
TABULAR_EXTENSIONS = {'csv', 'xlsx', 'xls', 'xlsm'}
SCHEMA_EXTENSIONS = {'xsd'}
VISIO_EXTENSIONS = {'vsdx'}
EMAIL_EXTENSIONS = {'msg'}

Expand Down Expand Up @@ -217,6 +219,7 @@ def get_allowed_extensions(enable_video=False, enable_audio=False):
extensions.update(DOCUMENT_EXTENSIONS)
extensions.update(IMAGE_EXTENSIONS)
extensions.update(TABULAR_EXTENSIONS)
extensions.update(SCHEMA_EXTENSIONS)
extensions.update(VISIO_EXTENSIONS)
extensions.update(EMAIL_EXTENSIONS)

Expand All @@ -228,7 +231,7 @@ def get_allowed_extensions(enable_video=False, enable_audio=False):

return extensions

def get_allowed_extension_categories(enable_video=False, enable_audio=False):
def get_allowed_extension_categories(enable_video=False, enable_audio=False, enable_xsd=False):
"""
Get allowed file extensions grouped for display in workspace upload dialogs.
"""
Expand Down Expand Up @@ -263,6 +266,12 @@ def get_allowed_extension_categories(enable_video=False, enable_audio=False):
'extensions': VIDEO_EXTENSIONS,
})

if enable_xsd:
categories.append({
'name': 'XML schemas',
'extensions': SCHEMA_EXTENSIONS,
})

return [
{
'name': category['name'],
Expand Down
34 changes: 33 additions & 1 deletion application/single_app/functions_document_access_index.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -38,7 +38,7 @@
DOCUMENT_ACCESS_BACKFILL_STATE_DOC_ID = 'document_access_index_backfill_state'
DOCUMENT_ACCESS_SHADOW_STATE_TYPE = 'document_access_index_shadow_validation_state'
DOCUMENT_ACCESS_SHADOW_STATE_DOC_ID = 'document_access_index_shadow_validation_state'
DOCUMENT_ACCESS_INDEX_SCHEMA_VERSION = 2
DOCUMENT_ACCESS_INDEX_SCHEMA_VERSION = 3

DOCUMENT_ACCESS_SCOPE_PERSONAL = 'personal'
DOCUMENT_ACCESS_SCOPE_GROUP = 'group'
Expand Down Expand Up @@ -1738,6 +1738,22 @@ def _build_base_row(document_item, source_scope, scope_type, scope_id, access_ro
'number_of_pages': document_item.get('number_of_pages'),
'publication_date': document_item.get('publication_date'),
'enhanced_citations': _has_persisted_blob_reference(document_item),
'document_kind': document_item.get('document_kind'),
'xsd_logical_path': document_item.get('xsd_logical_path'),
'xsd_schema_status': document_item.get('xsd_schema_status'),
'xsd_profile': document_item.get('xsd_profile'),
'xsd_validator_id': document_item.get('xsd_validator_id'),
'xsd_dialect': document_item.get('xsd_dialect'),
'xsd_effective_dialect': document_item.get('xsd_effective_dialect'),
'xsd_target_namespace': document_item.get('xsd_target_namespace'),
'xsd_sha256': document_item.get('xsd_sha256'),
'xsd_byte_size': document_item.get('xsd_byte_size'),
'xsd_author_version': document_item.get('xsd_author_version'),
'xsd_global_elements': document_item.get('xsd_global_elements'),
'xsd_global_types': document_item.get('xsd_global_types'),
'xsd_dependencies': document_item.get('xsd_dependencies'),
'xsd_dependency_count': document_item.get('xsd_dependency_count'),
'xsd_diagnostics': document_item.get('xsd_diagnostics'),
'document_intelligence_extraction_mode': document_item.get('document_intelligence_extraction_mode'),
'extraction_engine': document_item.get('extraction_engine'),
'extraction_engine_reason': document_item.get('extraction_engine_reason'),
Expand Down Expand Up @@ -2410,6 +2426,22 @@ def _projection_row_to_document(row, source_scope):
'number_of_pages': row.get('number_of_pages'),
'publication_date': row.get('publication_date'),
'enhanced_citations': row.get('enhanced_citations'),
'document_kind': row.get('document_kind'),
'xsd_logical_path': row.get('xsd_logical_path'),
'xsd_schema_status': row.get('xsd_schema_status'),
'xsd_profile': row.get('xsd_profile'),
'xsd_validator_id': row.get('xsd_validator_id'),
'xsd_dialect': row.get('xsd_dialect'),
'xsd_effective_dialect': row.get('xsd_effective_dialect'),
'xsd_target_namespace': row.get('xsd_target_namespace'),
'xsd_sha256': row.get('xsd_sha256'),
'xsd_byte_size': row.get('xsd_byte_size'),
'xsd_author_version': row.get('xsd_author_version'),
'xsd_global_elements': row.get('xsd_global_elements'),
'xsd_global_types': row.get('xsd_global_types'),
'xsd_dependencies': row.get('xsd_dependencies'),
'xsd_dependency_count': row.get('xsd_dependency_count'),
'xsd_diagnostics': row.get('xsd_diagnostics'),
'document_intelligence_extraction_mode': row.get('document_intelligence_extraction_mode'),
'extraction_engine': row.get('extraction_engine'),
'extraction_engine_reason': row.get('extraction_engine_reason'),
Expand Down
Loading
Loading