Merge pull request #593 from rtibbles/automatic_for_the_people

Allow ContentNode class to take a uri argument for its default file

Author: rtibbles

ricecooker/classes/files.py

@@ -55,6 +55,7 @@ class File(object):
     is_primary = False
     duration = None
     skip_upload = False
+    default_preset = None
 
     def __init__(
         self,
@@ -91,8 +92,11 @@ def validate(self):
     def get_preset(self):
         if self.preset:
             return self.preset
+        if self.default_preset:
+            return self.default_preset
         raise NotImplementedError(
-            "preset must be set if preset isn't specified when creating File object"
+            f"preset must be set if preset and default_preset isn't specified when creating {self.__class__.__name__} "
+            f"object for file {self.filename} ({self.original_filename})"
         )
 
     def get_filename(self):
@@ -195,13 +199,16 @@ def process_file(self):
         self.validate()
         pipeline = config.FILE_PIPELINE or fallback_pipeline
         try:
-            metadata = pipeline.execute(self.path, context=self.context)[0]
+            metadata = pipeline.execute(
+                self.path, context=self.context, skip_cache=config.UPDATE
+            )[0]
             metadata = metadata.to_dict()
             for key in metadata:
                 if key == "path":
                     # Don't overwrite the input path.
                     continue
                 setattr(self, key, metadata[key])
+            self.validate()
             if not self.filename:
                 raise InvalidFileException("File could not be processed by pipeline")
             return super().process_file()
@@ -219,15 +226,13 @@ class ImageDownloadFile(DownloadFile):
 class SlideImageFile(ImageDownloadFile):
     default_ext = file_formats.PNG
     is_primary = True
+    default_preset = format_presets.SLIDESHOW_IMAGE
 
     def __init__(self, path, caption="", descriptive_text="", **kwargs):
         self.caption = caption
         self.descriptive_text = descriptive_text
         super(ImageDownloadFile, self).__init__(path, **kwargs)
 
-    def get_preset(self):
-        return format_presets.SLIDESHOW_IMAGE
-
 
 class ThumbnailFile(ThumbnailPresetMixin, ImageDownloadFile):
     default_ext = file_formats.PNG
@@ -237,58 +242,46 @@ class AudioFile(DownloadFile):
     default_ext = file_formats.MP3
     allowed_formats = AudioCompressionHandler.EXTENSIONS
     is_primary = True
+    default_preset = format_presets.AUDIO
 
     def __init__(self, path, ffmpeg_settings=None, **kwargs):
         super(AudioFile, self).__init__(path, **kwargs)
         self.context["audio_settings"] = ffmpeg_settings or {}
 
-    def get_preset(self):
-        return self.preset or format_presets.AUDIO
-
 
 class DocumentFile(DownloadFile):
     default_ext = file_formats.PDF
     allowed_formats = {file_formats.PDF}
     is_primary = True
-
-    def get_preset(self):
-        return self.preset or format_presets.DOCUMENT
+    default_preset = format_presets.DOCUMENT
 
 
 class EPubFile(DownloadFile):
     default_ext = file_formats.EPUB
     allowed_formats = {file_formats.EPUB}
     is_primary = True
-
-    def get_preset(self):
-        return self.preset or format_presets.EPUB
+    default_preset = format_presets.EPUB
 
 
 class BloomPubFile(DownloadFile):
     default_ext = file_formats.BLOOMPUB
     allowed_formats = {file_formats.BLOOMPUB, file_formats.BLOOMD}
     is_primary = True
-
-    def get_preset(self):
-        return self.preset or format_presets.BLOOMPUB
+    default_preset = format_presets.BLOOMPUB
 
 
 class HTMLZipFile(DownloadFile):
     default_ext = file_formats.HTML5
     allowed_formats = {file_formats.HTML5}
     is_primary = True
-
-    def get_preset(self):
-        return self.preset or format_presets.HTML5_ZIP
+    default_preset = format_presets.HTML5_ZIP
 
 
 class H5PFile(DownloadFile):
     default_ext = file_formats.H5P
     allowed_formats = {file_formats.H5P}
     is_primary = True
-
-    def get_preset(self):
-        return self.preset or format_presets.H5P_ZIP
+    default_preset = format_presets.H5P_ZIP
 
 
 class VideoFile(DownloadFile):
@@ -300,9 +293,6 @@ def __init__(self, path, ffmpeg_settings=None, **kwargs):
         super(VideoFile, self).__init__(path, **kwargs)
         self.context["video_settings"] = ffmpeg_settings or {}
 
-    def get_preset(self):
-        return self.preset
-
 
 class WebVideoFile(DownloadFile):
     is_primary = True
@@ -323,9 +313,6 @@ def __init__(
             self.context["max_height"] = maxheight
         self.context["high_resolution"] = high_resolution
 
-    def get_preset(self):
-        return self.preset
-
 
 class YouTubeVideoFile(WebVideoFile):
     def __init__(self, youtube_id, **kwargs):
@@ -335,6 +322,7 @@ def __init__(self, youtube_id, **kwargs):
 
 
 class YouTubeSubtitleFile(File):
+    default_preset = format_presets.VIDEO_SUBTITLE
     """
     Helper class for downloading youtube subtitles.
     Args:
@@ -360,13 +348,11 @@ def __init__(self, youtube_id, language=None, **kwargs):
         }
         assert self.language, "Subtitles must have a language"
 
-    def get_preset(self):
-        return self.preset or format_presets.VIDEO_SUBTITLE
-
 
 class SubtitleFile(DownloadFile):
     default_ext = file_formats.VTT
     allowed_formats = SubtitleConversionHandler.EXTENSIONS
+    default_preset = format_presets.VIDEO_SUBTITLE
 
     def __init__(self, path, **kwargs):
         """
@@ -384,9 +370,6 @@ def __init__(self, path, **kwargs):
             "default_ext": self.subtitlesformat,
         }
 
-    def get_preset(self):
-        return self.preset or format_presets.VIDEO_SUBTITLE
-
 
 class Base64ImageFile(ThumbnailPresetMixin, DownloadFile):
     default_ext = file_formats.PNG
@@ -396,23 +379,22 @@ def __init__(self, encoding, **kwargs):
 
 
 class _ExerciseBase64ImageFile(Base64ImageFile):
-    def get_preset(self):
-        return self.preset or format_presets.EXERCISE_IMAGE
+    default_preset = format_presets.EXERCISE_IMAGE
 
     def get_replacement_str(self):
         return self.get_filename() or self.path
 
 
 class _ExerciseImageFile(ImageDownloadFile):
+    default_preset = format_presets.EXERCISE_IMAGE
+
     def get_replacement_str(self):
         return self.get_filename() or self.path
 
-    def get_preset(self):
-        return self.preset or format_presets.EXERCISE_IMAGE
-
 
 class _ExerciseGraphieFile(File):
     default_ext = file_formats.GRAPHIE
+    default_preset = format_presets.EXERCISE_GRAPHIE
 
     def __init__(self, path):
         self.original_filename = path.split("/")[-1].split(".")[0]
@@ -426,9 +408,6 @@ def validate(self):
         except ValueError:
             raise ValueError("_ExerciseGraphieFile must have a valid URL")
 
-    def get_preset(self):
-        return self.preset or format_presets.EXERCISE_GRAPHIE
-
     def get_replacement_str(self):
         if "http" in self.path:
             return self.path.split("/")[-1].split(".")[0] or self.path
@@ -523,27 +502,31 @@ def extractor_fun(self, fpath_in, thumbpath_out, **kwargs):
 
 class ExtractedPdfThumbnailFile(ExtractedThumbnailFile):
     extractor_kwargs = {"page_number": 0, "crop": None}
+    allowed_formats = DocumentFile.allowed_formats
 
     def extractor_fun(self, fpath_in, thumbpath_out, **kwargs):
         create_image_from_pdf_page(fpath_in, thumbpath_out, **kwargs)
 
 
 class ExtractedEPubThumbnailFile(ExtractedThumbnailFile):
     extractor_kwargs = {"crop": None}
+    allowed_formats = EPubFile.allowed_formats
 
     def extractor_fun(self, fpath_in, thumbpath_out, **kwargs):
         create_image_from_epub(fpath_in, thumbpath_out, **kwargs)
 
 
 class ExtractedHTMLZipThumbnailFile(ExtractedThumbnailFile):
     extractor_kwargs = {"crop": "smart"}
+    allowed_formats = HTMLZipFile.allowed_formats
 
     def extractor_fun(self, fpath_in, thumbpath_out, **kwargs):
         create_image_from_zip(fpath_in, thumbpath_out, **kwargs)
 
 
 class ExtractedVideoThumbnailFile(ExtractedThumbnailFile):
     extractor_kwargs = {"overwrite": True}
+    allowed_formats = VideoFile.allowed_formats
 
     def extractor_fun(self, fpath_in, thumbpath_out, **kwargs):
         extract_thumbnail_from_video(fpath_in, thumbpath_out, **kwargs)

ricecooker/classes/licenses.py

@@ -52,12 +52,10 @@ def get_id(self):
     def validate(self):
         assert (
             not self.require_copyright_holder or self.copyright_holder != ""
-        ), "Assertion Failed: {} License requires a copyright holder".format(
-            self.license_id
-        )
+        ), "{} License requires a copyright holder".format(self.license_id)
         assert isinstance(
             self.copyright_holder, str
-        ), "Assertion Failed: Copyright holder must be a string"
+        ), "Copyright holder must be a string"
 
     def truncate_fields(self):
         if (