Add GVision OCR engine support

Author: aka964

misc/pdf_text_diff.py

@@ -18,7 +18,6 @@ def main(
     engine: Annotated[str, typer.Option()] = 'pdftotext',
 ):
     """Compare text in PDFs."""
-
     text1 = run(
         ['pdftotext', '-layout', '-', '-'], stdin=pdf1, capture_output=True, check=True
     )

pyproject.toml

@@ -21,6 +21,7 @@ dependencies = [
   "Pillow>=10.0.1",
   "pluggy>=1",
   "rich>=13",
+  "google-cloud-vision>=3.4.2",
 ]
 authors = [{ name = "James R. Barlow", email = "james@purplerock.ca" }]
 classifiers = [

src/ocrmypdf/_exec/ghostscript.py

@@ -9,7 +9,6 @@
 import os
 import re
 from collections import deque
-from io import BytesIO
 from os import fspath
 from pathlib import Path
 from subprocess import PIPE, CalledProcessError

src/ocrmypdf/_metadata.py

@@ -15,7 +15,6 @@
 from pikepdf import __version__ as PIKEPDF_VERSION
 from pikepdf.models.metadata import PdfMetadata, encode_pdf_date
 
-from ocrmypdf._annots import remove_broken_goto_annotations
 from ocrmypdf._defaults import PROGRAM_NAME
 from ocrmypdf._jobcontext import PdfContext
 from ocrmypdf._version import __version__ as OCRMYPF_VERSION

src/ocrmypdf/_progressbar.py

@@ -48,9 +48,11 @@ class ProgressBar(Protocol):
             A brief description of the current step (e.g. "Scanning contents",
             "OCR", "PDF/A conversion"). OCRmyPDF updates this before each major step.
         unit (str | None):
-            A short label for the type of work being tracked (e.g. "page", "%", "image").
+            A short label for the type of work being tracked
+            (e.g. "page", "%", "image").
         disable (bool):
-            If ``True``, progress updates are suppressed (no output). Defaults to ``False``.
+            If ``True``, progress updates are suppressed (no output).
+             Defaults to ``False``.
         **kwargs:
             Future or extra parameters that OCRmyPDF might pass. Implementations
             should accept and ignore unrecognized keywords gracefully.
@@ -64,7 +66,9 @@ class ProgressBar(Protocol):
             from ocrmypdf import hookimpl
 
             class ConsoleProgressBar(ProgressBar):
-                def __init__(self, *, total=None, desc=None, unit=None, disable=False, **kwargs):
+                def __init__(
+                self, *, total=None, desc=None, unit=None, disable=False, **kwargs
+                ):
                     self.total = total
                     self.desc = desc
                     self.unit = unit
@@ -73,7 +77,10 @@ def __init__(self, *, total=None, desc=None, unit=None, disable=False, **kwargs)
 
                 def __enter__(self):
                     if not self.disable:
-                        print(f"Starting {self.desc or 'an OCR task'} (total={self.total} {self.unit})")
+                        print(
+                            f"Starting {self.desc or 'an OCR task'} "
+                            f"(total={self.total} {self.unit})"
+                        )
                     return self
 
                 def __exit__(self, exc_type, exc_value, traceback):
@@ -86,15 +93,19 @@ def __exit__(self, exc_type, exc_value, traceback):
 
                 def update(self, n=1, *, completed=None):
                     if completed is not None:
-                        # If 'completed' is given, you could set self.current = completed
+                        # If 'completed' is given, you could set
+                        # self.current = completed
                         # but let's just read it to show usage
                         print(f"Absolute completion reported: {completed}")
                     # Otherwise, we increment by 'n'
                     self.current += n
                     if not self.disable:
                         if self.total:
                             percent = (self.current / self.total) * 100
-                            print(f"{self.desc}: {self.current}/{self.total} ({percent:.1f}%)")
+                            print(
+                                f"{self.desc}: {self.current}/{self.total}"
+                                f"({percent:.1f}%)"
+                            )
                         else:
                             print(f"{self.desc}: {self.current} units done")