add rich output support for slide notes

python/packages/server/src/officeconvert_server/models.py

@@ -23,6 +23,7 @@ class ConversionSession:
     thumbnail_resolution: conversion_pb2.ConversionResolution
     full_jpeg_quality: int
     thumbnail_jpeg_quality: int
+    notes: conversion_pb2.NotesOptions | None = None
     bucket_name: str
     upload_object_key: str
     status: conversion_pb2.ConversionStatus

python/packages/server/src/officeconvert_server/service.py

@@ -18,6 +18,9 @@ from google.protobuf.timestamp_pb2 import Timestamp
 from officeconvert import SlideArtifact, convert_pptx_to_slidedeck
 from officeconvert.conversion import (
     ConversionTimeoutError,
+    HtmlFormattingPolicy,
+    NotesFormat,
+    NotesOptions,
     PHASE_EXTRACTING_NOTES,
     PHASE_PDF_TO_IMAGES,
     PHASE_PPTX_TO_PDF,
@@ -49,6 +52,37 @@ _DEFAULT_FULL_RESOLUTION = conversion_pb2.CONVERSION_RESOLUTION_FHD
 _DEFAULT_THUMBNAIL_RESOLUTION = conversion_pb2.CONVERSION_RESOLUTION_SD
 _DEFAULT_FULL_JPEG_QUALITY = 85
 _DEFAULT_THUMBNAIL_JPEG_QUALITY = 75
+_DEFAULT_NOTES_FORMAT = conversion_pb2.NOTES_FORMAT_PLAIN
+_DEFAULT_HTML_USE_PARAGRAPH_TAGS = True
+
+
+def _to_library_notes_options(
+    notes: conversion_pb2.NotesOptions | None,
+) -> NotesOptions | None:
+    if notes is None:
+        return None
+
+    fmt = notes.format or _DEFAULT_NOTES_FORMAT
+    library_format = NotesFormat.HTML if fmt == conversion_pb2.NOTES_FORMAT_HTML else NotesFormat.PLAIN
+
+    html_use_paragraph_tags = _DEFAULT_HTML_USE_PARAGRAPH_TAGS
+    if notes.HasField("html_use_paragraph_tags"):
+        html_use_paragraph_tags = bool(notes.html_use_paragraph_tags)
+
+    policy_proto = notes.html_policy
+    policy = HtmlFormattingPolicy(
+        ignore_bold=bool(policy_proto.ignore_bold),
+        ignore_italic=bool(policy_proto.ignore_italic),
+        ignore_underline=bool(policy_proto.ignore_underline),
+        ignore_strikethrough=bool(policy_proto.ignore_strikethrough),
+        ignore_font_size=bool(policy_proto.ignore_font_size),
+        ignore_color=bool(policy_proto.ignore_color),
+    )
+    return NotesOptions(
+        format=library_format,
+        html_use_paragraph_tags=html_use_paragraph_tags,
+        html_policy=policy,
+    )
 
 
 class ConversionServiceImpl(conversion_connect.ConversionService):
@@ -124,6 +158,7 @@ class ConversionServiceImpl(conversion_connect.ConversionService):
             thumbnail_resolution=thumbnail_resolution,
             full_jpeg_quality=full_jpeg_quality,
             thumbnail_jpeg_quality=thumbnail_jpeg_quality,
+            notes=request.notes if request.HasField("notes") else None,
             bucket_name=bucket_name,
             upload_object_key=upload_key,
             status=conversion_pb2.CONVERSION_STATUS_PENDING,
@@ -280,6 +315,7 @@ class ConversionServiceImpl(conversion_connect.ConversionService):
                 pptx_to_pdf_per_slide_timeout_s=self._config.conversion_pptx_to_pdf_per_slide_timeout_seconds,
                 pdf_to_images_base_timeout_s=self._config.conversion_pdf_to_images_base_timeout_seconds,
                 pdf_to_images_per_slide_timeout_s=self._config.conversion_pdf_to_images_per_slide_timeout_seconds,
+                notes_options=_to_library_notes_options(session.notes),
                 progress_callback=lambda phase_name, current, max_value: self._set_session_progress_from_name(
                     session,
                     phase_name=phase_name,
@@ -428,6 +464,7 @@ class ConversionServiceImpl(conversion_connect.ConversionService):
                 conversion_pb2.Slide(
                     index=slide.index,
                     notes_plain=slide.notes_plain,
+                    notes_html=slide.notes_html,
                     image_url=image_url,
                     thumbnail_image_url=thumbnail_image_url,
                 )