Merge branch 'feature/override-pdf-ids' into develop

 [SVCS-847]

mfr/extensions/pdf/export.py

@@ -4,7 +4,6 @@
 from http import HTTPStatus
 
 from PIL import Image, TiffImagePlugin
-from pdfrw import PdfReader, PdfWriter
 from reportlab.pdfgen import canvas
 
 from mfr.core import extension
@@ -67,13 +66,6 @@ def tiff_to_pdf(self, tiff_img, max_size):
         c.save()
 
     def export(self):
-        if self.ext.lower() == '.pdf':
-            pdf = PdfReader(self.source_file_path)
-            pdf.ID[0] = self.metadata.stable_id
-            pdf.ID[1] = self.metadata.unique_key
-            PdfWriter(self.output_file_path, trailer=pdf).write()
-            return
-
         logger.debug('pdf-export: format::{}'.format(self.format))
         parts = self.format.split('.')
         export_type = parts[-1].lower()

mfr/extensions/pdf/render.py

@@ -28,21 +28,23 @@ def render(self):
             return self.TEMPLATE.render(
                 base=self.assets_url,
                 url=escape_url_for_template(download_url.geturl()),
+                stable_id=self.metadata.stable_id,
                 enable_hypothesis=settings.ENABLE_HYPOTHESIS,
             )
 
         logger.debug('Extension found in supported list!')
         exported_url = furl.furl(self.export_url)
-        if self.metadata.ext.lower() in settings.EXPORT_NEEDS_SCALING:
+        if settings.EXPORT_MAXIMUM_SIZE:
             exported_url.args['format'] = '{}.{}'.format(settings.EXPORT_MAXIMUM_SIZE,
                                                          settings.EXPORT_TYPE)
         else:
-            exported_url.args['format'] = 'export.{}'.format(settings.EXPORT_TYPE)
+            exported_url.args['format'] = settings.EXPORT_TYPE
 
         self.metrics.add('needs_export', True)
         return self.TEMPLATE.render(
             base=self.assets_url,
             url=escape_url_for_template(exported_url.url),
+            stable_id=self.metadata.stable_id,
             enable_hypothesis=settings.ENABLE_HYPOTHESIS
         )
 

mfr/extensions/pdf/settings.py

@@ -5,16 +5,10 @@
 
 EXPORT_TYPE = config.get('EXPORT_TYPE', 'pdf')
 assert EXPORT_TYPE  # mandatory config
+EXPORT_MAXIMUM_SIZE = config.get('EXPORT_MAXIMUM_SIZE', '1200x1200')
 
 ENABLE_HYPOTHESIS = config.get_bool('ENABLE_HYPOTHESIS', False)
 
 # supports multiple files in the form of a space separated string
-EXPORT_SUPPORTED = config.get('EXPORT_SUPPORTED', '.pdf .tiff .tif').split(' ')
-EXPORT_NEEDS_SCALING = config.get('EXPORT_NEEDS_SCALING', '.tiff .tif').split(' ')
+EXPORT_SUPPORTED = config.get('EXPORT_SUPPORTED', '.tiff .tif').split(' ')
 EXPORT_MAX_PAGES = int(config.get('EXPORT_MAX_PAGES', 40))
-EXPORT_MAXIMUM_SIZE = config.get('EXPORT_MAXIMUM_SIZE', '1200x1200')
-
-# scaling requires page and size limits
-if EXPORT_NEEDS_SCALING:
-    assert EXPORT_MAX_PAGES
-    assert EXPORT_MAXIMUM_SIZE

mfr/extensions/pdf/templates/viewer.mako

@@ -424,6 +424,9 @@ http://sourceforge.net/adobe/cmap/wiki/License/
         window.pymChild.sendMessage('embed', 'embed-responsive-pdf');
     </script>
     % if enable_hypothesis:
+    <script>
+        window.MFR_STABLE_ID = '${stable_id}';
+    </script>
     <script src="/static/js/mfr.child.hypothesis.js"></script>
     % endif
   </body>

mfr/extensions/unoconv/export.py

@@ -1,12 +1,6 @@
 import os
 import subprocess
 
-from pdfrw import (
-    PdfReader,
-    PdfWriter
-)
-
-
 from mfr.core import extension
 from mfr.core import exceptions
 
@@ -39,8 +33,3 @@ def export(self):
                 extension=extension or '',
                 exporter_class='unoconv',
             )
-
-        pdf = PdfReader(self.output_file_path)
-        pdf.ID[0] = self.metadata.stable_id
-        pdf.ID[1] = self.metadata.unique_key
-        PdfWriter(self.output_file_path, trailer=pdf).write()

mfr/server/static/js/mfr.child.hypothesis.js

@@ -16,6 +16,13 @@
             return;
         }
 
+        // If a pdf is being rendered and MFR has provided a stable identifier, override the
+        // documentFingerprint with it before loading the hypothes.is client.  The client
+        // will use this ID to identify the document when fetching/saving annotations.
+        if (window.MFR_STABLE_ID && window.PDFViewerApplication) {
+            window.PDFViewerApplication.documentFingerprint = window.MFR_STABLE_ID;
+        }
+
         var script = window.document.createElement('script');
         script.type = 'text/javascript';
         script.src = 'https://hypothes.is/embed.js';

requirements.txt

@@ -37,7 +37,6 @@ mistune==0.7
 
 # Pdf
 reportlab==3.4.0
-pdfrw==0.4.0
 
 # Pptx
 # python-pptx==0.5.7

setup.py

@@ -57,16 +57,13 @@ def parse_requirements(requirements):
             '.bmp = mfr.extensions.image:ImageExporter',
             '.gif = mfr.extensions.image:ImageExporter',
             '.psd = mfr.extensions.image:ImageExporter',
+            '.tif = mfr.extensions.pdf:PdfExporter',
+            '.tiff = mfr.extensions.pdf:PdfExporter',
 
             # jsc3d
             '.stp = mfr.extensions.jsc3d:JSC3DExporter',
             '.step = mfr.extensions.jsc3d:JSC3DExporter',
 
-            # pdf
-            '.pdf = mfr.extensions.pdf:PdfExporter',
-            '.tif = mfr.extensions.pdf:PdfExporter',
-            '.tiff = mfr.extensions.pdf:PdfExporter',
-
             # unoconv
             # '.bib = mfr.extensions.unoconv:UnoconvExporter',
             # '.bmp = mfr.extensions.unoconv:UnoconvExporter',

tests/extensions/pdf/test_renderer.py

@@ -45,7 +45,7 @@ def assets_url():
 
 @pytest.fixture
 def export_url():
-    return 'http://mfr.osf.io/export?url=http://osf.io/file/test.pdf&format=export.pdf'
+    return 'http://mfr.osf.io/export?url=http://osf.io/file/test.pdf'
 
 
 @pytest.fixture
@@ -60,22 +60,18 @@ def tif_renderer(tif_metadata, tif_file_path, tif_url, assets_url, export_url):
 
 class TestPdfRenderer:
 
-    def test_render_pdf(self, renderer, assets_url, export_url):
+    def test_render_pdf(self, renderer, metadata, assets_url):
         body = renderer.render()
         assert '<base href="{}/{}/web/" target="_blank">'.format(assets_url, 'pdf') in body
         assert '<div id="viewer" class="pdfViewer"></div>' in body
-        assert 'DEFAULT_URL = \'{}\''.format(export_url) in body
+        assert 'DEFAULT_URL = \'{}\''.format(metadata.download_url) in body
 
     def test_render_pdf_with_single_quote_in_name(self, assets_url):
 
-        bad_download_url = 'http://osf.io/file/te\'st.pdf'
-        safe_download_url = 'http://osf.io/file/te%27st.pdf'
+        download_url = 'http://wb.osf.io/file/te\'st.pdf?token=1234'
+        safe_download_url = 'http://wb.osf.io/file/te%27st.pdf?token=1234'
 
-        base_export_url = 'http://mfr.osf.io/export?url={}&format=export.pdf'
-        bad_export_url = base_export_url.format(bad_download_url)
-        safe_export_url = base_export_url.format(safe_download_url)
-
-        metadata = ProviderMetadata('te\'st', '.pdf', 'text/plain', '1234', bad_download_url)
+        metadata = ProviderMetadata('te\'st', '.pdf', 'text/plain', '1234', download_url)
         renderer = PdfRenderer(metadata, '/tmp/te\'st.pdf', 'http://osf.io/file/te\'st.pdf',
                                assets_url,
                                'http://mfr.osf.io/export?url=http://osf.io/file/te\'st.pdf')
@@ -84,13 +80,13 @@ def test_render_pdf_with_single_quote_in_name(self, assets_url):
 
         assert '<base href="{}/{}/web/" target="_blank">'.format(assets_url, 'pdf') in body
         assert '<div id="viewer" class="pdfViewer"></div>' in body
-        assert 'DEFAULT_URL = \'{}\''.format(bad_export_url) not in body
-        assert 'DEFAULT_URL = \'{}\''.format(safe_export_url) in body
+        assert 'DEFAULT_URL = \'{}\''.format(download_url) not in body
+        assert 'DEFAULT_URL = \'{}\''.format(safe_download_url) in body
 
     def test_render_tif(self, tif_renderer, assets_url):
         exported_url = furl.furl(tif_renderer.export_url)
         exported_url.args['format'] = '{}.{}'.format(settings.EXPORT_MAXIMUM_SIZE,
-                                                     settings.EXPORT_TYPE)
+                                                            settings.EXPORT_TYPE)
 
         body = tif_renderer.render()
         assert '<base href="{}/{}/web/" target="_blank">'.format(assets_url, 'pdf') in body