document.page_for_id: catch empty imageFilename case

Makefile

@@ -8,7 +8,7 @@ PYTHONIOENCODING=utf8
 SHARE_DIR=~/.local/share
 
 deps-ubuntu:
-	apt install -y libcairo2-dev libgtk-3-dev libglib2.0-dev libgtksourceview-3.0-dev libgirepository1.0-dev pkg-config cmake
+	apt install -y libcairo2-dev libgtk-3-dev libglib2.0-dev libgtksourceview-3.0-dev libgirepository1.0-dev gir1.2-webkit2-4.0 pkg-config cmake
 
 deps-dev:
 	$(PIP) --use-feature=2020-resolver install -r requirements-dev.txt

README.md

@@ -1,6 +1,6 @@
 # OCR-D Browser
 
-An extensible viewer for [OCR-D](https://ocr-d.de/) mets.xml files 
+An extensible viewer for [OCR-D](https://ocr-d.de/) [mets.xml](https://ocr-d.de/en/spec/mets) files
 
 ## Screenshot
 
@@ -9,16 +9,25 @@ An extensible viewer for [OCR-D](https://ocr-d.de/) mets.xml files
 ## Installation on Ubuntu 18.04
 
 ```
-sudo apt install libcairo2-dev libgtk-3-dev libglib2.0-dev libgtksourceview-3.0-dev libgirepository1.0-dev pkg-config cmake
+sudo make deps-ubuntu
 pip install browse-ocrd
 ```
 
 
 ## Usage
 ```
-browse-ocrd ./path/to/mets.xml
+browse-ocrd ./path/to/mets.xml # or open interactively
 ```
 
+## Features
+
+- Browse fileGrps and pages, arranging views next to each other for comparison
+- Show original or derived images (`AlternativeImage` on any level of the structural hierarchy)
+- Show multiple images at once for different pages (horizontally) or different segments (vertically), zooming freely
+- Show raw [PAGE-XML](https://ocr-d.de/en/spec/page) with syntax highlighting, open with [PageViewer](https://github.com/PRImA-Research-Lab/prima-page-viewer)
+- Show concatenated [PAGE-XML](https://ocr-d.de/en/spec/page) text annotation
+- Show rendered HTML comparison from [dinglehopper](https://github.com/qurator-spk/dinglehopper) evaluations
+
 ## Configuration
 
 ### Configuration file locations
@@ -53,3 +62,4 @@ The `commandline` string will be used as a python format string with the keyword
 * `workspace` : The current `ocrd.Workspace`, all properties get shell escaped (by `shlex.quote`) automatically.
 * `file` : The current `ocrd_models.OcrdFile`, all properties get shell escaped (by `shlex.quote`) automatically, also there is an additional property `path` with the properties `absolute` and `relative`, so `{file.path.absolute}` will be replaced by the shell quoted absolute path of the file. 
 
+> Note: You can get PRImA's PageViewer at [Github](https://github.com/PRImA-Research-Lab/prima-page-viewer/releases).

ocrd_browser/model/document.py

@@ -73,7 +73,7 @@ def load(cls, mets_url: Union[Path, str] = None, emitter: EventCallBack = None)
             return cls.create(emitter=emitter)
         mets_url = cls._strip_local(mets_url)
 
-        workspace = Resolver().workspace_from_url(mets_url, download=True)
+        workspace = Resolver().workspace_from_url(mets_url, download=False)
         doc = cls(workspace, emitter=emitter, original_url=mets_url)
         doc._empty = False
         return doc
@@ -357,7 +357,10 @@ def page_for_id(self, page_id: str, file_group: str = None) -> Optional['Page']:
             return None
         file = next(iter(page_files + image_files))
         pcgts = self.page_for_file(file)
-        if not image_files:
+        if not pcgts.get_Page().get_imageFilename():
+            log.warning("PAGE-XML with empty image path for page '{}' in fileGrp '{}'".format(
+                page_id, file_group))
+        elif not image_files:
             image, _, _ = self.workspace.image_from_page(pcgts.get_Page(), page_id)
             image_files = [file]
             images = [image]

ocrd_browser/view/__init__.py

@@ -1,7 +1,8 @@
 from .base import View
 from .registry import ViewRegistry
+from .html import ViewHtml
 from .images import ViewImages
 from .text import ViewText
 from .xml import ViewXml
 
-__all__ = ['View', 'ViewRegistry', 'ViewImages', 'ViewText', 'ViewXml']
+__all__ = ['View', 'ViewRegistry', 'ViewImages', 'ViewText', 'ViewXml', 'ViewHtml']

ocrd_browser/view/base.py

@@ -249,7 +249,11 @@ class FileGroupModel(Gtk.ListStore):
     def __init__(self, document: Document):
         super().__init__(str, str, str, str)
         for group, mime in document.file_groups_and_mimetypes:
-            self.append(('{}|{}'.format(group, mime), group, mime, MIME_TO_EXT.get(mime, '.???')))
+            if mime == 'text/html':
+                ext = '.html'
+            else:
+                ext = MIME_TO_EXT.get(mime, '.???')
+            self.append(('{}|{}'.format(group, mime), group, mime, ext))
 
     @classmethod
     def build(cls, document: Document, filter_: 'FileGroupFilter' = None) -> 'FileGroupModel':
@@ -267,6 +271,11 @@ def page_filter(model: Gtk.TreeModel, it: Gtk.TreeIter, _data: None) -> bool:
         # str casts for mypy
         return str(model[it][FileGroupComboBox.COLUMN_MIME]) == str(MIMETYPE_PAGE)
 
+    @staticmethod
+    def html_filter(model: Gtk.TreeModel, it: Gtk.TreeIter, _data: None) -> bool:
+        # str casts for mypy
+        return str(model[it][FileGroupComboBox.COLUMN_MIME]) == 'text/html'
+
     @staticmethod
     def all_filter(_model: Gtk.TreeModel, _it: Gtk.TreeIter, _data: None) -> bool:
         return True
@@ -275,6 +284,7 @@ def all_filter(_model: Gtk.TreeModel, _it: Gtk.TreeIter, _data: None) -> bool:
 class FileGroupFilter(Enum):
     IMAGE = FileGroupModel.image_filter
     PAGE = FileGroupModel.page_filter
+    HTML = FileGroupModel.html_filter
     ALL = FileGroupModel.all_filter
 
 

ocrd_browser/view/html.py

@@ -0,0 +1,55 @@
+import gi
+gi.require_version('WebKit2', '4.0')
+from gi.repository import GObject, Gtk, WebKit2
+
+from typing import Optional, Tuple, Any
+
+from ocrd_browser.view import View
+from ocrd_browser.view.base import FileGroupSelector, FileGroupFilter
+from ocrd_browser.model import Page
+
+GObject.type_register(WebKit2.WebView)
+
+
+class ViewHtml(View):
+    """
+    A view of the HTML+CSS annotation (as produced by ocrd-dinglehopper reports).
+    """
+
+    label = 'HTML'
+
+    def __init__(self, name: str, window: Gtk.Window):
+        super().__init__(name, window)
+        self.file_group: Tuple[Optional[str], Optional[str]] = (None, 'text/html')
+        # noinspection PyTypeChecker
+        self.web_view: WebKit2.WebView = None
+
+    def build(self) -> None:
+        super().build()
+        self.add_configurator('file_group', FileGroupSelector(FileGroupFilter.HTML))
+
+        self.web_view = WebKit2.WebView()
+
+        self.scroller.add(self.web_view)
+
+    @property
+    def use_file_group(self) -> str:
+        return self.file_group[0]
+
+    def config_changed(self, name: str, value: Any) -> None:
+        super().config_changed(name, value)
+        self.reload()
+
+    def reload(self) -> None:
+        files = self.document.files_for_page_id(self.page_id, self.use_file_group, mimetype='text/html')
+        if files:
+            self.current = Page(self.page_id, files[0], None, [], [], None)
+        self.redraw()
+
+    def redraw(self) -> None:
+        if self.current:
+            self.web_view.set_tooltip_text(self.page_id)
+            self.web_view.load_uri('file://' + str(self.document.path(self.current.file.local_filename)))
+            self.web_view.show()
+
+

setup.py

@@ -49,6 +49,7 @@
         ],
         'ocrd_browser_view': [
             'xml = ocrd_browser.view:ViewXml',
+            'html = ocrd_browser.view:ViewHtml',
             'text = ocrd_browser.view:ViewText',
             'images = ocrd_browser.view:ViewImages'
         ],