MAINT: Upgrade from PyPDF2 to pypdf + add system metadata (#16)

Author: MartinThoma

.isort.cfg

@@ -5,4 +5,4 @@ multi_line_output=3
 length_sort=0
 include_trailing_comma=True
 skip=docs
-known_third_party = PIL,PyPDF2,pydantic,setuptools,typer
+known_third_party = PIL,pypdf,pydantic,setuptools,typer

.pre-commit-config.yaml

@@ -1,7 +1,7 @@
 # pre-commit run --all-files
 repos:
 -   repo: https://github.com/pre-commit/pre-commit-hooks
-    rev: v4.2.0
+    rev: v4.4.0
     hooks:
     -   id: check-ast
     -   id: check-byte-order-marker
@@ -10,39 +10,38 @@ repos:
     -   id: check-yaml
     -   id: debug-statements
     -   id: end-of-file-fixer
+        exclude: "resources/.*|docs/make.bat"
     -   id: trailing-whitespace
     -   id: mixed-line-ending
+        args: ['--fix=lf']
+        exclude: "docs/make.bat"
     -   id: check-added-large-files
         args: ['--maxkb=1000']
+# -   repo: https://github.com/pre-commit/mirrors-mypy
+#     rev: v0.942
+#     hooks:
+#     -   id: mypy
 -   repo: https://github.com/psf/black
-    rev: 22.3.0
+    rev: 23.1.0
     hooks:
     -   id: black
+        args: [--target-version, py36]
 -   repo: https://github.com/asottile/blacken-docs
-    rev: v1.12.1
+    rev: 1.13.0
     hooks:
     -   id: blacken-docs
         additional_dependencies: [black==22.1.0]
--   repo: https://gitlab.com/pycqa/flake8
-    rev: 3.9.2
+-   repo: https://github.com/charliermarsh/ruff-pre-commit
+    rev: 'v0.0.254'
     hooks:
-    -   id: flake8
--   repo: https://github.com/pre-commit/mirrors-mypy
-    rev: v0.942
-    hooks:
-    -   id: mypy
-        additional_dependencies:
-          - 'pydantic'
--   repo: https://github.com/asottile/seed-isort-config
-    rev: v2.2.0
-    hooks:
-    -   id: seed-isort-config
--   repo: https://github.com/pre-commit/mirrors-isort
-    rev: v5.10.1
-    hooks:
-    -   id: isort
+    -   id: ruff
 -   repo: https://github.com/asottile/pyupgrade
-    rev: v2.32.0
+    rev: v3.3.1
     hooks:
     -   id: pyupgrade
         args: [--py36-plus]
+-   repo: https://github.com/pycqa/flake8
+    rev: 6.0.0
+    hooks:
+    -   id: flake8
+        args: ["--ignore", "E,W,F"]

Makefile

@@ -10,7 +10,7 @@ upload:
 clean:
 	python setup.py clean --all
 	pyclean .
-	rm -rf Tests/__pycache__ PyPDF2/__pycache__ Image9.png htmlcov docs/_build dist dont_commit_merged.pdf dont_commit_writer.pdf PyPDF2.egg-info PyPDF2_pdfLocation.txt
+	rm -rf Tests/__pycache__ pypdf/__pycache__ Image9.png htmlcov docs/_build dist dont_commit_merged.pdf dont_commit_writer.pdf pypdf.egg-info pypdf_pdfLocation.txt
 
 test:
 	pytest Tests --cov --cov-report term-missing -vv --cov-report html --durations=3 --timeout=30

pdfly/cat.py

@@ -41,7 +41,7 @@
 """
 # Copyright (c) 2014, Steve Witham <[email protected]>.
 # All rights reserved. This software is available under a BSD license;
-# see https://github.com/py-pdf/PyPDF2/LICENSE
+# see https://github.com/py-pdf/pypdf/LICENSE
 
 
 import os
@@ -50,7 +50,7 @@
 from sys import exit, stderr, stdout
 from typing import List
 
-from PyPDF2 import PdfMerger, parse_filename_page_ranges
+from pypdf import PdfMerger, parse_filename_page_ranges
 
 
 def main(filename: Path, fn_pgrgs: List[str], output: Path, verbose: bool) -> None:
@@ -66,7 +66,7 @@ def main(filename: Path, fn_pgrgs: List[str], output: Path, verbose: bool) -> No
     merger = PdfMerger()
     in_fs = {}
     try:
-        for (filename, page_range) in filename_page_ranges:  # type: ignore
+        for filename, page_range in filename_page_ranges:  # type: ignore
             if verbose:
                 print(filename, page_range, file=stderr)
             if filename not in in_fs:

pdfly/cli.py

@@ -71,7 +71,7 @@ def metadata(
 @entry_point.command(name="extract-text")  # type: ignore[misc]
 def extract_text(pdf: Path):
     """Extract text from a PDF file."""
-    from PyPDF2 import PdfReader
+    from pypdf import PdfReader
 
     reader = PdfReader(str(pdf))
     for page in reader.pages:

pdfly/compress.py

@@ -3,7 +3,7 @@
 import os
 from pathlib import Path
 
-from PyPDF2 import PdfReader, PdfWriter
+from pypdf import PdfReader, PdfWriter
 
 
 def main(pdf: Path, output: Path):

pdfly/extract_images.py

@@ -8,7 +8,7 @@
 from pathlib import Path
 
 from PIL import Image
-from PyPDF2 import PdfReader
+from pypdf import PdfReader
 
 
 def main(pdf: Path) -> None:

pdfly/metadata.py

@@ -1,25 +1,33 @@
 """Show metadata of a PDF file"""
 
-import os
+import stat
+from datetime import datetime
 from enum import Enum
 from pathlib import Path
 from typing import Optional, Set, Tuple
 
 from pydantic import BaseModel
-from PyPDF2 import PdfReader
+from pypdf import PdfReader
 
 
 class MetaInfo(BaseModel):
     title: Optional[str] = None
     producer: Optional[str] = None
+    author: Optional[str] = None
     pages: int
     encrypted: bool
-    file_size: int  # in bytes
     page_size: Tuple[float, float]  # (width, height)
     pdf_file_version: str
     page_mode: Optional[str]
     page_layout: Optional[str]
 
+    # OS Information
+    file_permissions: str
+    file_size: int  # in bytes
+    creation_time: datetime
+    modification_time: datetime
+    access_time: datetime
+
 
 class OutputOptions(Enum):
     json = "json"
@@ -33,35 +41,41 @@ def main(pdf: Path, output: OutputOptions) -> None:
 
     reader.stream.seek(0)
     pdf_file_version = reader.stream.read(8).decode("utf-8")
+    pdf_stat = pdf.stat()
     meta = MetaInfo(
         pages=len(reader.pages),
         encrypted=reader.is_encrypted,
-        file_size=pdf.stat().st_size,
         page_size=(x2 - x1, y2 - y1),
         page_mode=reader.page_mode,
         pdf_file_version=pdf_file_version,
         page_layout=reader.page_layout,
+        # OS Info
+        file_permissions=f"{stat.filemode(pdf_stat.st_mode)}",
+        file_size=pdf_stat.st_size,
+        creation_time=datetime.fromtimestamp(pdf_stat.st_ctime),
+        modification_time=datetime.fromtimestamp(pdf_stat.st_mtime),
+        access_time=datetime.fromtimestamp(pdf_stat.st_atime),
     )
     if info is not None:
         meta.title = info.title
         meta.producer = info.producer
+        meta.author = info.author
 
     if output == OutputOptions.json:
         print(meta.json())
     else:
         from rich.console import Console
         from rich.table import Table
 
-        table = Table(title=f"{pdf}")
+        table = Table(title="PDF Data")
         table.add_column("Attribute", justify="right", style="cyan", no_wrap=True)
         table.add_column("Value", style="white")
 
-        table.add_row("File Size", f"{os.path.getsize(pdf):,} Bytes")
         table.add_row("Title", meta.title)
         table.add_row("Producer", meta.producer)
+        table.add_row("Author", meta.author)
         table.add_row("Pages", f"{meta.pages:,}")
         table.add_row("Encrypted", f"{meta.encrypted}")
-        table.add_row("File size", f"{meta.file_size:,} bytes")
         table.add_row(
             "Page size", f"{meta.page_size[0]} x {meta.page_size[1]} pts (w x h)"
         )
@@ -77,5 +91,18 @@ def main(pdf: Path, output: OutputOptions) -> None:
         table.add_row("Fonts (unembedded)", ", ".join(sorted(unemedded_fonts)))
         table.add_row("Fonts (embedded)", ", ".join(sorted(embedded_fonts)))
 
+        os_table = Table(title="Operating System Data")
+        os_table.add_column("Attribute", justify="right", style="cyan", no_wrap=True)
+        os_table.add_column("Value", style="white")
+        os_table.add_row("File Name", f"{pdf}")
+        os_table.add_row("File Permissions", f"{meta.file_permissions}")
+        os_table.add_row("File Size", f"{meta.file_size:,} bytes")
+        os_table.add_row("Creation Time", f"{meta.creation_time:%Y-%m-%d %H:%M:%S}")
+        os_table.add_row(
+            "Modification Time", f"{meta.modification_time:%Y-%m-%d %H:%M:%S}"
+        )
+        os_table.add_row("Access Time", f"{meta.access_time:%Y-%m-%d %H:%M:%S}")
+
         console = Console()
+        console.print(os_table)
         console.print(table)

pdfly/up2.py

@@ -9,7 +9,7 @@
 import sys
 from pathlib import Path
 
-from PyPDF2 import PdfReader, PdfWriter
+from pypdf import PdfReader, PdfWriter
 
 
 def main(pdf: Path, output: Path) -> None:

pypproject.toml

@@ -1,2 +1,77 @@
 [tool.black]
 line-length = 79
+
+[tool.ruff]
+line-length = 120
+select = ["ALL"]
+ignore = [
+    "D404",  # First word of the docstring should not be "This"
+    # I would like to have it, but there are a few annoying exceptions:
+    "D401", # First line of docstring should be in imperative mood - false positives
+    "ERA001",
+    "UP031",
+    "D205",  # 1 blank line required between summary line and description
+    "D400",  # First line should end with a period
+    "D415",  # First line should end with a period
+    # Introduces bugs
+    "RUF001", "RUF002", "RUF005",
+    "ARG",
+    "DTZ001", # The use of `datetime.datetime()` without `tzinfo` is necessary
+    # Personal preference
+    "D406", # Section name should end with a newline ("Returns")
+    "D212",  # I want multiline-docstrings to start at the second line
+    "D407",  # google-style docstrings don't have dashses
+    "N806",  # Variable `NO` in function should be lowercase
+    "N814", # Camelcase `PageAttributes` imported as constant `PG`
+    "N817",  # CamelCase `PagesAttributes` imported as acronym `PA`
+    "ANN101",  # annotating 'self' seems weird (at least before 3.11)
+    "ANN102",  # Missing type annotation for `cls` in classmethod
+    "ANN204", # Missing return type annotation for special method `__init__`
+    "ANN401",  # Dynamically typed expressions (typing.Any) are disallowed
+    "BLE",  # we want to capture Exception sometimes
+    "COM812",  # yes, they make the diff smaller
+    "D105",  # Missing docstring in magic method
+    "D106",  # Missing docstring in public nested class
+    "D107",  # Missing docstring in `__init__`
+    "D203", # one-blank-line-before-class
+    "EM",  # exception messages
+    "G004",  # f-string in logging statement
+    "RET",
+    "S110", # `try`-`except`-`pass` detected, consider logging the exception
+    "SIM105",  # contextlib.suppress
+    "SIM108",  # don't enforce ternary operators
+    "SIM300",  # yoda conditions
+    "TID252",  # we want relative imports
+    "TRY", # I don't know what this is about
+    # As long as we are not on Python 3.9+
+    "UP035", # PEP 585
+    # As long as we are not on Python 3.10+
+    "UP038",  # Use `X | Y` in `isinstance` call instead of `(X, Y)` - PEP 604
+    # As long as we are not on Python 3.11+
+    "UP006", "UP007",
+    # for the moment, fix it later:
+    "A",  # Variable is shadowing a built-in
+    "B904", # Within an `except` clause, raise exceptions with
+    "B905",  # `zip()` without an explicit `strict=` parameter
+    "C901",
+    "D101",  # Missing docstring in public class
+    "D102", # Missing docstring in public method
+    "D103",  # Missing docstring in public function
+    "D417",  # Missing argument descriptions in the docstring
+    "FBT001", # Boolean positional arg in function definition
+    "FBT002", # Boolean default value in function definition
+    "FBT003", # Boolean positional value in function call
+    "PGH", # Use specific error messages
+    "PLE",  # too many arguments for logging
+    "PLR0911",  # Too many return statements
+    "PLR0912", # Too many branches
+    "PLR0913",  # Too many arguments to function call
+    "PLR0915", # Too many statements
+    "PLR2004", # Magic value
+    "PLW",  # global variables
+    "PT011", # `pytest.raises(ValueError)` is too broad, set the `match`
+    "PT012",  # `pytest.raises()` block should contain a single simple statement
+    "PTH123", # `open()` should be replaced by `Path.open()`
+    "S101",  # Use of `assert` detected
+    "SLF001",  # Private member accessed
+]

setup.cfg

@@ -34,7 +34,7 @@ classifiers =
 [options]
 python_requires = >=3.6.1
 install_requires =
-    PyPDF2
+    pypdf>3.0.0
     typer
     pillow
     pydantic