make sure the metadataonly parse option is respected for all offtryck…

… derived sources
staffanm · Jun 18, 2017 · a4695f4 · a4695f4
1 parent c2c0218
commit a4695f4
Show file tree

Hide file tree

Showing 2 changed files with 5 additions and 3 deletions.
diff --git a/ferenda/sources/legal/se/offtryck.py b/ferenda/sources/legal/se/offtryck.py
@@ -332,8 +332,9 @@ def parse_body(self, fp, basefile):
         if options == "skip":
             raise DocumentSkippedError("%s: Skipped because of options.py" % basefile,
                                        dummyfile=self.store.parsed_path(basefile))
-        # elif options == "metadataonly":
-        #     do something smart
+        elif options == "metadataonly":
+            return Preformatted("Dokumentttext saknas (se originaldokument)")
+
         # elif options == "simple":
         #     do something else smart
 

diff --git a/ferenda/sources/legal/se/riksdagen.py b/ferenda/sources/legal/se/riksdagen.py
@@ -323,8 +323,9 @@ def extract_body(self, fp, basefile):
         # fp can now be a pointer to a hocr file, a pdf2xml file,
         # a html file or a StringIO object containing html taken
         # from index.xml
+        options = self.get_parse_options(basefile)
         if (os.path.exists(pdffile) and
-            self.get_parse_options(basefile) != "metadataonly"):
+            options != "metadataonly"):
             fp = self.parse_open(basefile)
             parser = "ocr" if ".hocr." in util.name_from_fp(fp) else "xml"
             reader = StreamingPDFReader().read(fp, parser=parser)