Bump version: v17.4.0

The inter-word Tz calculation stretched "word " to span from the current
word to the next, producing extreme horizontal scaling (300-500%) for
words far apart (e.g. in tables). Use per-word Tz instead — Td
positioning already handles inter-word gaps correctly.

Fixes #1635

docs/releasenotes/version17.md

@@ -3,6 +3,20 @@
 
 # v17
 
+## v17.4.0
+
+- Added ``--no-overwrite`` / ``-n`` option to prevent overwriting output files.
+  If the destination file already exists, OCRmyPDF exits with code 5
+  (``OutputFileAccessError``). {issue}`1642`
+- Fixed text layer stretching in the fpdf2 renderer for widely-spaced words.
+  The horizontal scaling (Tz) was incorrectly stretched to fill inter-word gaps
+  instead of relying on Td positioning, causing text selection to highlight far
+  beyond the actual word boundaries. {issue}`1635`
+- Fixed ``optimize=2`` or ``optimize=3`` crash when using the Python API without
+  explicitly setting ``jpg_quality`` or ``png_quality``. {issue}`1641`
+- Fixed ``verapdf`` availability check crashing with ``NotADirectoryError`` on
+  some platforms. {issue}`1638`
+
 ## v17.3.0
 
 - Fixed Python API ignoring the ``language`` parameter, always defaulting to

pyproject.toml

@@ -6,7 +6,7 @@ build-backend = "hatchling.build"
 
 [project]
 name = "ocrmypdf"
-version = "17.3.0"
+version = "17.4.0"
 description = "OCRmyPDF adds an OCR text layer to scanned PDF files, allowing them to be searched"
 readme = "README.md"
 license = "MPL-2.0"
@@ -156,7 +156,12 @@ quote-style = "preserve"
 
 [dependency-groups]
 # Developer-only tools - use `uv sync --group <name>`
-dev = ["mypy>=1.13.0", "ipykernel>=6.29.5", "reportlab>=4.4.4"]
+dev = [
+    "mypy>=1.13.0",
+    "ipykernel>=6.29.5",
+    "reportlab>=4.4.4",
+    "cyclopts>=4.5.1",
+]
 test = [
   # Core testing framework
   "coverage[toml]>=6.2",

src/ocrmypdf/_exec/verapdf.py

@@ -36,7 +36,7 @@ def available() -> bool:
     """Check if verapdf is available."""
     try:
         version()
-    except MissingDependencyError:
+    except (MissingDependencyError, OSError):
         return False
     return True
 

src/ocrmypdf/_options.py

@@ -188,6 +188,9 @@ class OcrOptions(BaseModel):
         """Compatibility alias for jpg_quality."""
         self.jpg_quality = value
 
+    # Output behavior
+    no_overwrite: bool = False
+
     # Advanced options
     max_image_mpixels: float = 250.0
     pdf_renderer: str = 'auto'

src/ocrmypdf/_validation.py

@@ -217,6 +217,17 @@ def check_requested_output_file(options: OcrOptions) -> None:
             f"Output file location ({options.output_file}) is not a writable file."
         )
 
+    if (
+        options.no_overwrite
+        and not hasattr(options.output_file, 'writable')
+        and options.output_file != '-'
+        and Path(str(options.output_file)).exists()
+    ):
+        raise OutputFileAccessError(
+            f"Output file already exists: {options.output_file}\n"
+            "To overwrite it, omit the --no-overwrite / -n option."
+        )
+
 
 def report_output_file_size(
     options: OcrOptions,

src/ocrmypdf/_version.py

@@ -1,3 +1,3 @@
 # SPDX-FileCopyrightText: 2022 James R. Barlow
 # SPDX-License-Identifier: MPL-2.0
-__version__ = "17.3.0"
+__version__ = "17.4.0"

src/ocrmypdf/api.py

@@ -440,6 +440,7 @@ def ocr(
     continue_on_soft_render_error: bool | None = None,
     invalidate_digital_signatures: bool | None = None,
     tagged_pdf_mode: str | None = None,
+    no_overwrite: bool | None = None,
     plugins: Iterable[Path | str] | None = None,
     plugin_manager: OcrmypdfPluginManager | None = None,
     keep_temporary_files: bool | None = None,
@@ -502,6 +503,7 @@ def ocr(  # noqa: D417
     continue_on_soft_render_error: bool | None = None,
     invalidate_digital_signatures: bool | None = None,
     tagged_pdf_mode: str | None = None,
+    no_overwrite: bool | None = None,
     plugins: Iterable[Path | str] | None = None,
     plugin_manager: OcrmypdfPluginManager | None = None,
     keep_temporary_files: bool | None = None,

src/ocrmypdf/cli.py

@@ -137,8 +137,9 @@ Online documentation is located at:
         'output_file',
         metavar="output_pdf",
         help="Output searchable PDF file (or '-' to write to standard output). "
-        "Existing files will be overwritten. If same as input file, the "
-        "input file will be updated only if processing is successful.",
+        "Existing files will be overwritten (use --no-overwrite to prevent this). "
+        "If same as input file, the input file will be updated only if "
+        "processing is successful.",
     )
     parser.add_argument(
         '-l',
@@ -190,6 +191,15 @@ Online documentation is located at:
         "may not both use stdout at the same time.",
     )
 
+    parser.add_argument(
+        '-n',
+        '--no-overwrite',
+        action='store_true',
+        default=False,
+        help="If the output file already exists, exit with an error instead of "
+        "overwriting it.",
+    )
+
     parser.add_argument(
         '--version',
         action='version',

src/ocrmypdf/fpdf_renderer/renderer.py

@@ -677,12 +677,12 @@ class Fpdf2PdfRenderer:
                     dy_pdf = -(py_curr_f - py_prev_f)
                     ops.append(f'{dx_pdf:.2f} {dy_pdf:.2f} Td')
 
-            # Determine text to render and compute Tz
+            # Determine text to render
             if not is_last:
                 next_text, next_x_baseline, _, _ = word_render_data[i + 1]
                 advance = next_x_baseline - x_baseline
 
-                # Add trailing space unless both words are CJK-only
+                # Add trailing space for text extraction unless both are CJK
                 if (
                     advance > 0
                     and not (
@@ -691,18 +691,14 @@ class Fpdf2PdfRenderer:
                     )
                 ):
                     text_to_render = text + ' '
-                    natural_w = pdf.get_string_width(text_to_render)
-                    render_tz = (
-                        (advance / natural_w) * 100
-                        if natural_w > 0
-                        else word_tz
-                    )
                 else:
                     text_to_render = text
-                    render_tz = word_tz
             else:
                 text_to_render = text
-                render_tz = word_tz
+
+            # Use word_tz (fits word into its hOCR bbox) — Td handles
+            # inter-word gaps, so Tz should not stretch to fill them.
+            render_tz = word_tz
 
             ops.append(f'{render_tz:.2f} Tz')
             ops.append(self._encode_shaped_text(pdf, text_to_render))

src/ocrmypdf/optimize.py

@@ -681,9 +681,9 @@ def optimize(
         safe_symlink(input_file, output_file)
         return output_file
 
-    if options.jpg_quality == 0:
+    if not options.jpg_quality:
         options.jpg_quality = DEFAULT_JPEG_QUALITY if options.optimize < 3 else 40
-    if options.png_quality == 0:
+    if not options.png_quality:
         options.png_quality = DEFAULT_PNG_QUALITY if options.optimize < 3 else 30
 
     with Pdf.open(input_file) as pdf:

uv.lock

@@ -1283,7 +1283,7 @@ wheels = [
 
 [[package]]
 name = "ocrmypdf"
-version = "17.2.0"
+version = "17.3.0"
 source = { editable = "." }
 dependencies = [
     { name = "deprecation" },
@@ -1313,6 +1313,7 @@ webservice = [
 
 [package.dev-dependencies]
 dev = [
+    { name = "cyclopts" },
     { name = "ipykernel" },
     { name = "mypy" },
     { name = "reportlab" },
@@ -1367,6 +1368,7 @@ provides-extras = ["watcher", "webservice"]
 
 [package.metadata.requires-dev]
 dev = [
+    { name = "cyclopts", specifier = ">=4.5.1" },
     { name = "ipykernel", specifier = ">=6.29.5" },
     { name = "mypy", specifier = ">=1.13.0" },
     { name = "reportlab", specifier = ">=4.4.4" },