feat: Add extractor cli choice

Can only choose pdf for the time being, but allows additional
extractors to be added in the future.

papis_extract/__init__.py

@@ -50,6 +50,18 @@ papis.config.register_default_settings(DEFAULT_OPTIONS)
     ),
     help="Choose an output template to format annotations with.",
 )
+@click.option(
+    "--extractor",
+    "-e",
+    "extractors",
+    type=click.Choice(
+        list(extractor.extractors.keys()),
+        case_sensitive=False,
+    ),
+    default=list(extractor.extractors.keys()),
+    multiple=True,
+    help="Choose an extractor to apply to the selected documents.",
+)
 @click.option(
     "--force/--no-force",
     "-f",
@@ -64,6 +76,7 @@ def main(
     doc_folder: str,
     manual: bool,
     write: bool,
+    extractors: str,
     template: str,
     git: bool,
     force: bool,
@@ -86,6 +99,7 @@ def main(
         logger.warning(papis.strings.no_documents_retrieved_message)
         return
 
+    print(extractors)
     formatter = formatters.get(template)
 
     run(documents, edit=manual, write=write, git=git, formatter=formatter, force=force)

papis_extract/extractor.py

@@ -34,23 +34,26 @@ def start(
     pdf_extractor: Extractor = PdfExtractor()
 
     annotations: list[Annotation] = []
-    found_pdf: bool = False
+    file_available: bool = False
     for file in document.get_files():
         fname = Path(file)
         if not pdf_extractor.can_process(fname):
-            break
-        found_pdf = True
+            continue
+        file_available = True
 
         try:
             annotations.extend(pdf_extractor.run(fname))
         except fitz.FileDataError as e:
             print(f"File structure errors for {file}.\n{e}")
 
-    if not found_pdf:
+    if not file_available:
         # have to remove curlys or papis logger gets upset
         desc = re.sub("[{}]", "", papis.document.describe(document))
-        logger.warning("Did not find suitable PDF file for document: " f"{desc}")
+        logger.warning("Did not find suitable file for document: " f"{desc}")
 
     return annotations
 
 
+extractors: dict[str, Extractor] = {
+    "pdf": PdfExtractor(),
+}