Added document extractor

app/library/views/__init__.py

@@ -19,7 +19,7 @@ import re
 from interface.views import EnsembleMixin, ProjectMixin, AuthorizedResourceMixin
 from interface.models import Project
 from library.models import Collection, Work, Document, Section
-from library.music_tags import MUSIC_TAGS, MUSIC_TAG_BY_NAME
+from library.music_tags import MUSIC_TAGS, MUSIC_TAG_BY_NAME, MusicTag
 from library import forms, models
 from library.pdf_utils import extract_pages, extract_and_concat
 
@@ -308,6 +308,38 @@ class WorkPartSetView(CollectionMixin, DetailView):
             works = works.filter(collection__allowed_ensembles__ensemble=self.request.ensemble_id)
         return works
 
+class WorkDownloadView(CollectionMixin, SingleObjectMixin, View):
+    model = models.Work
+
+    def get(self, request, *args, **kwargs):
+        self.object = self.get_object()
+
+        tags = request.GET.getlist('tag')
+
+        if not tags:
+            raise Http404("No tags given")
+        
+        sections = list(self.object.tagged_sections(*tags))
+        print(sections)
+
+        if len(sections) == 0:
+            raise Http404("No matching sections")
+
+        if len(sections) == 1 and sections[0].start == 0:
+            # bypass extraction and redirect to the url
+            logger.debug("Redirecting to url")
+            return redirect(sections[0].upload.url)
+
+        result = extract_and_concat([ (s.upload.path, s.upload.name, s.start, s.end, 1) for s in sections ])
+
+        tag_names = " - ".join([ str(MusicTag.from_tag(tag)) for tag in tags ])
+
+        download_name = f'{self.object.name} - {tag_names}.pdf'
+
+        response = FileResponse(result, content_type="application/pdf")
+        response['Content-Disposition'] = f'inline; filename="{download_name}"'
+        return response
+
 class WorkAddDocumentView(CollectionMixin, CreateView):
     template_name = "interface/default_form.html"
     model = Document

app/library/views/api.py

@@ -35,6 +35,7 @@ class WorkExportView(EnsembleMixin, WorkMixin, View):
 from interface.views import AuthorizedResourceMixin
 
 from rest_framework import routers, serializers, viewsets
+from rest_framework.exceptions import APIException
 
 from library.models import Collection, Work, Document, Section, WorkMeta
 
@@ -72,14 +73,12 @@ class SectionSerializer(serializers.ModelSerializer):
 
     def to_internal_value(self, data):
         tag, start, end = data.split(":")
-        try:
-            start = int(start)
-        except:
-            start = 0
-        try:
-            end = int(end)
-        except:
-            end = 0
+        start = int(start)
+        end = int(end)
+        if start < 1:
+            start = None
+        if end < 1:
+            end = None
         return super().to_internal_value({'tag': tag, 'start': start, 'end': end})
 
 class DocumentSerializer(serializers.ModelSerializer):
@@ -139,7 +138,9 @@ class WorkSerializer(serializers.ModelSerializer):
                 filename = os.path.basename(url.path)
 
                 r = requests.get(d['upload'], stream=True)
-                f = TemporaryUploadedFile(filename, r.headers['content-type'], r.headers['content-length'], r.encoding)
+                if r.status_code != 200:
+                    raise APIException("Failed to download file")
+                f = TemporaryUploadedFile(filename, r.headers['content-type'], r.headers.get('content-length'), r.encoding)
                 shutil.copyfileobj(r.raw, f.file)
                 r.close()
                 d['upload'] = f