Add PDF.path & fix .to_image() for zipped files

These are related changes, since the previous approach of using
`PDF.stream.name` to distinguish between on-path and filelike-object PDFs
doesn't work for zipped files (and possibly other filelike-objects that
have a `name` property).

pdfplumber/display.py

@@ -1,5 +1,5 @@
+import pathlib
 from io import BufferedReader, BytesIO
-from pathlib import Path
 from typing import TYPE_CHECKING, Any, List, Optional, Tuple, Union
 
 import PIL.Image
@@ -35,14 +35,18 @@ T_contains_points = Union[Tuple[T_point, ...], List[T_point], T_obj]
 
 def get_page_image(
     stream: Union[BufferedReader, BytesIO],
+    path: Optional[pathlib.Path],
     page_ix: int,
     resolution: Union[int, float],
     password: Optional[str],
     antialias: bool = False,
 ) -> PIL.Image.Image:
+
+    src: Union[pathlib.Path, BufferedReader, BytesIO]
+
     # If we are working with a file object saved to disk
-    if hasattr(stream, "name"):
-        src = stream.name
+    if path:
+        src = path
 
     # If we instead are working with a BytesIO stream
     else:
@@ -79,6 +83,7 @@ class PageImage:
         if original is None:
             self.original = get_page_image(
                 stream=page.pdf.stream,
+                path=page.pdf.path,
                 page_ix=page.page_number - 1,
                 resolution=resolution,
                 antialias=antialias,
@@ -133,7 +138,7 @@ class PageImage:
 
     def save(
         self,
-        dest: Union[str, Path, BytesIO],
+        dest: Union[str, pathlib.Path, BytesIO],
         format: str = "PNG",
         quantize: bool = True,
         colors: int = 256,

pdfplumber/pdf.py

@@ -28,6 +28,7 @@ class PDF(Container):
         self,
         stream: Union[BufferedReader, BytesIO],
         stream_is_external: bool = False,
+        path: Optional[pathlib.Path] = None,
         pages: Optional[Union[List[int], Tuple[int]]] = None,
         laparams: Optional[Dict[str, Any]] = None,
         password: Optional[str] = None,
@@ -35,6 +36,7 @@ class PDF(Container):
     ):
         self.stream = stream
         self.stream_is_external = stream_is_external
+        self.path = path
         self.pages_to_parse = pages
         self.laparams = None if laparams is None else LAParams(**laparams)
         self.password = password
@@ -70,20 +72,27 @@ class PDF(Container):
         repair: bool = False,
     ) -> "PDF":
 
-        stream: Union[str, pathlib.Path, BufferedReader, BytesIO]
+        stream: Union[BufferedReader, BytesIO]
+
         if repair:
             stream = _repair(path_or_fp, password=password)
             stream_is_external = False
+            # Although the original file has a path,
+            # the repaired version does not
+            path = None
         elif isinstance(path_or_fp, (str, pathlib.Path)):
             stream = open(path_or_fp, "rb")
             stream_is_external = False
+            path = pathlib.Path(path_or_fp)
         else:
             stream = path_or_fp
             stream_is_external = True
+            path = None
 
         try:
             return cls(
                 stream,
+                path=path,
                 pages=pages,
                 laparams=laparams,
                 password=password,

tests/test_display.py

@@ -3,6 +3,7 @@ import io
 import logging
 import os
 import unittest
+from zipfile import ZipFile
 
 import PIL.Image
 import pytest
@@ -112,3 +113,13 @@ class Test(unittest.TestCase):
         path = os.path.join(HERE, "pdfs/password-example.pdf")
         with pdfplumber.open(path, password="test") as pdf:
             pdf.pages[0].to_image()
+
+    def test_zip(self):
+        # See https://github.com/jsvine/pdfplumber/issues/948
+        # reproducer.py
+        path = os.path.join(HERE, "pdfs/issue-948.zip")
+        with ZipFile(path) as zip_file:
+            with zip_file.open("dummy.pdf") as pdf_file:
+                with pdfplumber.open(pdf_file) as pdf:
+                    page = pdf.pages[0]
+                    page.to_image()