Change default .repair(...) setting h/t @Laubeee

Now passes "default" rather than "prepress" to Ghostscript's
`-dPDFSETTINGS` parameter.

Also makes that setting modifiable via `.repair(setting=...)`, where the
value is one of `"default"`, `"prepress"`, `"printer"`, or `"ebook"`.

See #874 and https://ghostscript.com/docs/9.54.0/VectorDevices.htm

CHANGELOG.md

@@ -4,6 +4,10 @@ All notable changes to this project will be documented in this file. The format
 
 ## [0.11.3] - Unreleased
 
+### Changed
+
+- Change default setting `pdfplumber.repair(...)` passes to Ghostscript's `-dPDFSETTINGS` parameter, from `prepress` to `default`, and make that setting modifiable via `.repair(setting=...)`, where the value is one of `"default"`, `"prepress"`, `"printer"`, or `"ebook"` (h/t @Laubeee). ([#874](https://github.com/jsvine/pdfplumber/issues/874))
+
 ### Fixed
 
 - Fix error on getting `.annots`/`.hyperlinks` from `CroppedPage` (due to missing `.rotation` and `.initial_doctop` attributes) (h/t @Safrone). ([#1171](https://github.com/jsvine/pdfplumber/issues/1171) + [e5737d2](https://github.com/jsvine/pdfplumber/commit/e5737d2))

pdfplumber/pdf.py

@@ -15,7 +15,7 @@
 from ._typing import T_num, T_obj_list
 from .container import Container
 from .page import Page
-from .repair import _repair
+from .repair import T_repair_setting, _repair
 from .structure import PDFStructTree, StructTreeMissing
 from .utils import resolve_and_decode
 
@@ -72,12 +72,15 @@ def open(
         strict_metadata: bool = False,
         repair: bool = False,
         gs_path: Optional[Union[str, pathlib.Path]] = None,
+        repair_setting: T_repair_setting = "default",
     ) -> "PDF":
 
         stream: Union[BufferedReader, BytesIO]
 
         if repair:
-            stream = _repair(path_or_fp, password=password, gs_path=gs_path)
+            stream = _repair(
+                path_or_fp, password=password, gs_path=gs_path, setting=repair_setting
+            )
             stream_is_external = False
             # Although the original file has a path,
             # the repaired version does not

pdfplumber/repair.py

@@ -2,13 +2,16 @@
 import shutil
 import subprocess
 from io import BufferedReader, BytesIO
-from typing import Optional, Union
+from typing import Literal, Optional, Union
+
+T_repair_setting = Literal["default", "prepress", "printer", "ebook", "screen"]
 
 
 def _repair(
     path_or_fp: Union[str, pathlib.Path, BufferedReader, BytesIO],
     password: Optional[str] = None,
     gs_path: Optional[Union[str, pathlib.Path]] = None,
+    setting: T_repair_setting = "default",
 ) -> BytesIO:
 
     executable = (
@@ -29,7 +32,7 @@ def _repair(
         "-o",
         "-",
         "-sDEVICE=pdfwrite",
-        "-dPDFSETTINGS=/prepress",
+        f"-dPDFSETTINGS=/{setting}",
     ]
 
     if password:
@@ -62,8 +65,9 @@ def repair(
     outfile: Optional[Union[str, pathlib.Path]] = None,
     password: Optional[str] = None,
     gs_path: Optional[Union[str, pathlib.Path]] = None,
+    setting: T_repair_setting = "default",
 ) -> Optional[BytesIO]:
-    repaired = _repair(path_or_fp, password, gs_path=gs_path)
+    repaired = _repair(path_or_fp, password, gs_path=gs_path, setting=setting)
     if outfile:
         with open(outfile, "wb") as f:
             f.write(repaired.read())

tests/test_repair.py

@@ -53,6 +53,18 @@ def test_repair_to_file(self):
                 char = page.chars[0]
                 assert char["bottom"] < page.height
 
+    def test_repair_setting(self):
+        path = os.path.join(HERE, "pdfs/malformed-from-issue-932.pdf")
+        with tempfile.NamedTemporaryFile("wb") as out:
+            pdfplumber.repair(path, outfile=out.name)
+            size_default = os.stat(out.name).st_size
+
+        with tempfile.NamedTemporaryFile("wb") as out:
+            pdfplumber.repair(path, outfile=out.name, setting="prepress")
+            size_prepress = os.stat(out.name).st_size
+
+        assert size_default > size_prepress
+
     def test_repair_password(self):
         path = os.path.join(HERE, "pdfs/password-example.pdf")
         with pdfplumber.open(path, repair=True, password="test") as pdf: