pdfly 0.3.3__tar.gz → 0.4.0__tar.gz

{pdfly-0.3.3 → pdfly-0.4.0}/.github/workflows/create-github-release.yaml

@@ -32,7 +32,7 @@ jobs:
           git --no-pager tag -l "${latest_tag}" --format='%(contents:body)' >> "$GITHUB_ENV"
           echo "$EOF" >> "$GITHUB_ENV"
       - name: Create GitHub Release 🚀
-        uses: softprops/action-gh-release@v1
+        uses: softprops/action-gh-release@v2
         with:
           tag_name: ${{ env.latest_tag }}
           name: Version ${{ env.latest_tag }}, ${{ env.date }}

{pdfly-0.3.3 → pdfly-0.4.0}/.github/workflows/github-ci.yaml

@@ -22,7 +22,7 @@ jobs:
     runs-on: ubuntu-20.04
     strategy:
       matrix:
-        python-version: ["3.8", "3.9", "3.10", "3.11"]
+        python-version: ["3.8", "3.9", "3.10", "3.11", "3.12"]
 
     steps:
     - name: Checkout Code
@@ -73,7 +73,7 @@ jobs:
     - name: Test with ruff
       run: |
         echo `ruff --version`
-        ruff pdfly/
+        ruff check pdfly/
 
   package:
     name: Build & verify package

{pdfly-0.3.3 → pdfly-0.4.0}/.pre-commit-config.yaml

@@ -1,7 +1,7 @@
 # pre-commit run --all-files
 repos:
 -   repo: https://github.com/pre-commit/pre-commit-hooks
-    rev: v4.5.0
+    rev: v5.0.0
     hooks:
     -   id: check-ast
     -   id: check-byte-order-marker
@@ -18,34 +18,34 @@ repos:
     -   id: check-added-large-files
         args: ['--maxkb=1000']
 -   repo: https://github.com/psf/black
-    rev: 23.12.0
+    rev: 24.10.0
     hooks:
     -   id: black
         args: [--target-version, py36]
 -   repo: https://github.com/asottile/blacken-docs
-    rev: 1.16.0
+    rev: 1.19.1
     hooks:
     -   id: blacken-docs
         additional_dependencies: [black==22.1.0]
 -   repo: https://github.com/astral-sh/ruff-pre-commit
-    rev: v0.1.8
+    rev: v0.7.4
     hooks:
     -   id: ruff
         args: ['--fix']
         exclude: "tests/"
 -   repo: https://github.com/asottile/pyupgrade
-    rev: v3.15.0
+    rev: v3.19.0
     hooks:
     -   id: pyupgrade
         args: [--py36-plus]
 -   repo: https://github.com/pycqa/flake8
-    rev: 6.1.0
+    rev: 7.1.1
     hooks:
     -   id: flake8
         args: ["--ignore", "E,W,F"]
 
 -   repo: https://github.com/pre-commit/mirrors-mypy
-    rev: 'v1.7.1'
+    rev: 'v1.13.0'
     hooks:
       - id: mypy
         files: ^pdfly/.*

{pdfly-0.3.3 → pdfly-0.4.0}/.readthedocs.yaml

@@ -5,7 +5,7 @@ version: 2
 build:
   os: ubuntu-22.04
   tools:
-    python: "3.11"
+    python: "3.12"
 
 # Build documentation in the docs/ directory with Sphinx
 sphinx:

{pdfly-0.3.3 → pdfly-0.4.0}/CHANGELOG.md

@@ -1,11 +1,28 @@
 # CHANGELOG
 
+## Version 0.4.0, 2024-12-08
+
+### New Features (ENH)
+- New `booklet` command to adjust offsets and lengths ([PR #77](https://github.com/py-pdf/pdfly/pull/77))
+- New `uncompress` command ([PR #75](https://github.com/py-pdf/pdfly/pull/75))
+- New `update-offsets` command to adjust offsets and lengths ([PR #15](https://github.com/py-pdf/pdfly/pull/15))
+- New `rm` command ([PR #59](https://github.com/py-pdf/pdfly/pull/59))
+- `metadata`: now also displaying CreationDate, Creator, Keywords & Subject ([PR #73](https://github.com/py-pdf/pdfly/pull/73))
+- Add warning for out-of-bounds page range in pdfly `cat` command ([PR #58](https://github.com/py-pdf/pdfly/pull/58))
+
+### Bug Fixes (BUG)
+- `2-up` command, that only showed one page per sheet, on the left side, with blank space on the right ([PR #78](https://github.com/py-pdf/pdfly/pull/78))
+
+[Full Changelog](https://github.com/py-pdf/pdfly/compare/0.3.3...0.4.0)
+
+
 ## Version 0.3.3, 2024-04-14
 
 ### Developer Experience (DEV)
 -  Chain workflows
 
-[Full Changelog](https://github.com/py-pdf/pdfly/compare/0.3.1...0.3.2)
+[Full Changelog](https://github.com/py-pdf/pdfly/compare/0.3.2...0.3.3)
+
 
 ## Version 0.3.2, 2024-04-14
 

{pdfly-0.3.3 → pdfly-0.4.0}/Makefile

@@ -15,10 +15,10 @@ upload:
 clean:
 	python setup.py clean --all
 	pyclean .
-	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
+	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
+	pytest tests --cov --cov-report term-missing -vv --cov-report html --durations=3 --timeout=30
 
 mutation-test:
 	mutmut run

{pdfly-0.3.3 → pdfly-0.4.0}/PKG-INFO

@@ -1,6 +1,6 @@
-Metadata-Version: 2.1
+Metadata-Version: 2.3
 Name: pdfly
-Version: 0.3.3
+Version: 0.4.0
 Summary: A pure-python CLI application to manipulate PDF files
 Author-email: Martin Thoma <info@martin-thoma.de>
 Maintainer-email: Martin Thoma <info@martin-thoma.de>
@@ -18,6 +18,8 @@ Classifier: Programming Language :: Python :: 3.7
 Classifier: Programming Language :: Python :: 3.8
 Classifier: Programming Language :: Python :: 3.9
 Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
 Requires-Dist: pypdf>=3.8.2
 Requires-Dist: typer>=0.9.0
 Requires-Dist: pillow
@@ -62,10 +64,13 @@ $ pdfly --help
 │ 2-up             Create a booklet-style PDF from a single input.            │
 │ cat              Concatenate pages from PDF files into a single PDF file.   │
 │ compress         Compress a PDF.                                            │
+| uncompress       Uncompresses a PDF.                                        │
 │ extract-images   Extract images from PDF without resampling or altering.    │
 │ extract-text     Extract text from a PDF file.                              │
 │ meta             Show metadata of a PDF file                                │
 │ pagemeta         Give details about a single page.                          │
+│ rm               Remove pages from PDF files.                               │
+│ update-offsets   Updates offsets and lengths in a simple PDF file.          │
 │ x2pdf            Convert one or more files to PDF. Each file is a page.     │
 ╰─────────────────────────────────────────────────────────────────────────────╯
 ```

{pdfly-0.3.3 → pdfly-0.4.0}/README.md

@@ -34,10 +34,13 @@ $ pdfly --help
 │ 2-up             Create a booklet-style PDF from a single input.            │
 │ cat              Concatenate pages from PDF files into a single PDF file.   │
 │ compress         Compress a PDF.                                            │
+| uncompress       Uncompresses a PDF.                                        │
 │ extract-images   Extract images from PDF without resampling or altering.    │
 │ extract-text     Extract text from a PDF file.                              │
 │ meta             Show metadata of a PDF file                                │
 │ pagemeta         Give details about a single page.                          │
+│ rm               Remove pages from PDF files.                               │
+│ update-offsets   Updates offsets and lengths in a simple PDF file.          │
 │ x2pdf            Convert one or more files to PDF. Each file is a page.     │
 ╰─────────────────────────────────────────────────────────────────────────────╯
 ```

{pdfly-0.3.3 → pdfly-0.4.0}/docs/conf.py

@@ -5,6 +5,7 @@ This file only contains a selection of the most common options.
 For a full list see the documentation:
 https://www.sphinx-doc.org/en/master/usage/configuration.html
 """
+
 # -- Path setup --------------------------------------------------------------
 
 # If extensions (or modules to document with autodoc) are in another directory,

{pdfly-0.3.3 → pdfly-0.4.0}/make_release.py

@@ -1,4 +1,4 @@
-"""Internal tool to update the changelog."""
+"""Internal tool to update the CHANGELOG."""
 
 import json
 import subprocess
@@ -9,6 +9,11 @@ from typing import Any, Dict, List, Tuple
 
 from rich.prompt import Prompt
 
+GH_ORG = "py-pdf"
+GH_PROJECT = "pdfly"
+VERSION_FILE_PATH = "pdfly/_version.py"
+CHANGELOG_FILE_PATH = "CHANGELOG.md"
+
 
 @dataclass(frozen=True)
 class Change:
@@ -27,6 +32,7 @@ def main(changelog_path: str) -> None:
 
     Args:
         changelog_path: The location of the CHANGELOG file
+
     """
     changelog = get_changelog(changelog_path)
     git_tag = get_most_recent_git_tag()
@@ -41,7 +47,7 @@ def main(changelog_path: str) -> None:
 
     today = datetime.now(tz=timezone.utc)
     header = f"## Version {new_version}, {today:%Y-%m-%d}\n"
-    url = f"https://github.com/py-pdf/pdfly/compare/{git_tag}...{new_version}"
+    url = f"https://github.com/{GH_ORG}/{GH_PROJECT}/compare/{git_tag}...{new_version}"
     trailer = f"\n[Full Changelog]({url})\n\n"
     new_entry = header + changes + trailer
     print(new_entry)
@@ -61,9 +67,9 @@ def main(changelog_path: str) -> None:
 def print_instructions(new_version: str) -> None:
     """Print release instructions."""
     print("=" * 80)
-    print(f"☑  _version.py was adjusted to '{new_version}'")
-    print("☑  CHANGELOG.md was adjusted")
-    print("")
+    print(f"☑  {VERSION_FILE_PATH} was adjusted to '{new_version}'")
+    print(f"☑  {CHANGELOG_FILE_PATH} was adjusted")
+    print()
     print("Now run:")
     print("  git commit -eF RELEASE_COMMIT_MSG.md")
     print(f"  git tag -s {new_version} -eF RELEASE_TAG_MSG.md")
@@ -73,7 +79,7 @@ def print_instructions(new_version: str) -> None:
 
 def adjust_version_py(version: str) -> None:
     """Adjust the __version__ string."""
-    with open("pdfly/_version.py", "w") as fp:
+    with open(VERSION_FILE_PATH, "w") as fp:
         fp.write(f'__version__ = "{version}"\n')
 
 
@@ -93,8 +99,7 @@ def get_version_interactive(new_version: str, changes: str) -> str:
 
 def is_semantic_version(version: str) -> bool:
     """Check if the given version is a semantic version."""
-    # It's not so important to cover the edge-cases like pre-releases
-    # This is meant for pdfly only and we don't make pre-releases
+    # This doesn't cover the edge-cases like pre-releases
     if version.count(".") != 2:
         return False
     try:
@@ -147,6 +152,7 @@ def version_bump(git_tag: str) -> str:
 
     Returns:
         The new version where the patch version is bumped.
+
     """
     # just assume a patch version change
     major, minor, patch = git_tag.split(".")
@@ -162,6 +168,7 @@ def get_changelog(changelog_path: str) -> str:
 
     Returns:
         Data of the CHANGELOG
+
     """
     with open(changelog_path) as fh:
         changelog = fh.read()
@@ -175,6 +182,7 @@ def write_changelog(new_changelog: str, changelog_path: str) -> None:
     Args:
         new_changelog: Contents of the new CHANGELOG
         changelog_path: Path where the CHANGELOG file is
+
     """
     with open(changelog_path, "w") as fh:
         fh.write(new_changelog)
@@ -189,6 +197,7 @@ def get_formatted_changes(git_tag: str) -> Tuple[str, str]:
 
     Returns:
         Changes done since git_tag
+
     """
     commits = get_git_commits_since_tag(git_tag)
 
@@ -249,8 +258,11 @@ def get_formatted_changes(git_tag: str) -> Tuple[str, str]:
 
     if grouped:
         output += "\n### Other\n"
+        output_with_user += "\n### Other\n"
         for prefix in grouped:
-            output += f"- {prefix}: {grouped[prefix]}\n"
+            for commit_dict in grouped[prefix]:
+                output += f"- {prefix}: {commit_dict['msg']}\n"
+                output_with_user += f"- {prefix}: {commit_dict['msg']} by @{commit_dict['author']}\n"
 
     return output, output_with_user
 
@@ -261,6 +273,7 @@ def get_most_recent_git_tag() -> str:
 
     Returns:
         Most recently created git tag.
+
     """
     git_tag = str(
         subprocess.check_output(
@@ -280,18 +293,18 @@ def get_author_mapping(line_count: int) -> Dict[str, str]:
 
     Returns:
         A mapping of long commit hashes to author login handles.
+
     """
     per_page = min(line_count, 100)
     page = 1
     mapping: Dict[str, str] = {}
     for _ in range(0, line_count, per_page):
-        with urllib.request.urlopen(  # noqa: S310
-            f"https://api.github.com/repos/py-pdf/pdfly/commits?per_page={per_page}&page={page}"
+        with urllib.request.urlopen(
+            f"https://api.github.com/repos/{GH_ORG}/{GH_PROJECT}/commits?per_page={per_page}&page={page}"
         ) as response:
             commits = json.loads(response.read())
         page += 1
         for commit in commits:
-            print(commit)
             if commit["author"]:
                 gh_handle = commit["author"]["login"]
             else:
@@ -311,8 +324,9 @@ def get_git_commits_since_tag(git_tag: str) -> List[Change]:
 
     Returns:
         List of all changes since git_tag.
+
     """
-    commits = str(
+    commits = (
         subprocess.check_output(
             [
                 "git",
@@ -323,8 +337,10 @@ def get_git_commits_since_tag(git_tag: str) -> List[Change]:
             ],
             stderr=subprocess.STDOUT,
         )
-    ).strip("'b\\n")
-    lines = commits.split("\\n")
+        .decode("UTF-8")
+        .strip()
+    )
+    lines = commits.splitlines()
     authors = get_author_mapping(len(lines))
     return [parse_commit_line(line, authors) for line in lines if line != ""]
 
@@ -341,13 +357,14 @@ def parse_commit_line(line: str, authors: Dict[str, str]) -> Change:
 
     Raises:
         ValueError: The commit line is not well-structured
+
     """
     parts = line.split(":::")
     if len(parts) != 3:
         raise ValueError(f"Invalid commit line: '{line}'")
     commit_hash, rest, author = parts
     if ":" in rest:
-        prefix, message = rest.split(":", 1)
+        prefix, message = rest.split(": ", 1)
     else:
         prefix = ""
         message = rest
@@ -374,4 +391,4 @@ def parse_commit_line(line: str, authors: Dict[str, str]) -> Change:
 
 
 if __name__ == "__main__":
-    main("CHANGELOG.md")
+    main(CHANGELOG_FILE_PATH)

{pdfly-0.3.3 → pdfly-0.4.0}/pdfly/__init__.py

@@ -1,4 +1,5 @@
 """pdfly is a command line utility for manipulating PDFs and getting information about them."""
+
 from ._version import __version__
 
 __all__ = [

pdfly-0.4.0/pdfly/_version.py

@@ -0,0 +1 @@
+__version__ = "0.4.0"

pdfly-0.4.0/pdfly/booklet.py

@@ -0,0 +1,159 @@
+"""
+Reorder and two-up PDF pages for booklet printing.
+
+If the number of pages is not a multiple of four, pages are
+added until it is a multiple of four. This includes a centerfold
+in the middle of the booklet and a single page on the inside
+back cover. The content of those pages are from the
+centerfold-file and blank-page-file files, if specified, otherwise
+they are blank pages.
+
+Example:
+    pdfly booklet input.pdf output.pdf
+
+"""
+
+# Copyright (c) 2014, Steve Witham <switham_github@mac-guyver.com>.
+# All rights reserved. This software is available under a BSD license;
+# see https://github.com/py-pdf/pypdf/LICENSE
+
+import sys
+import traceback
+from pathlib import Path
+from typing import Generator, Optional, Tuple
+
+from pypdf import (
+    PageObject,
+    PdfReader,
+    PdfWriter,
+)
+from pypdf.generic import RectangleObject
+
+
+def main(
+    filename: Path,
+    output: Path,
+    inside_cover_file: Optional[Path],
+    centerfold_file: Optional[Path],
+) -> None:
+    try:
+        # Set up the streams
+        reader = PdfReader(filename)
+        pages = list(reader.pages)
+        writer = PdfWriter()
+
+        # Add blank pages to make the number of pages a multiple of 4
+        # If the user specified an inside-back-cover file, use it.
+        blank_page = PageObject.create_blank_page(
+            width=pages[0].mediabox.width, height=pages[0].mediabox.height
+        )
+        if len(pages) % 2 == 1:
+            if inside_cover_file:
+                ic_reader_page = fetch_first_page(inside_cover_file)
+                pages.insert(-1, ic_reader_page)
+            else:
+                pages.insert(-1, blank_page)
+        if len(pages) % 4 == 2:
+            pages.insert(len(pages) // 2, blank_page)
+            pages.insert(len(pages) // 2, blank_page)
+            requires_centerfold = True
+        else:
+            requires_centerfold = False
+
+        # Reorder the pages and place two pages side by side (2-up) on each sheet
+        for lhs, rhs in page_iter(len(pages)):
+            pages[lhs].merge_translated_page(
+                page2=pages[rhs],
+                tx=pages[lhs].mediabox.width,
+                ty=0,
+                expand=True,
+                over=True,
+            )
+            writer.add_page(pages[lhs])
+
+        # If a centerfold was required, it is already
+        # present as a pair of blank pages. If the user
+        # specified a centerfold file, use it instead.
+        if requires_centerfold and centerfold_file:
+            centerfold_page = fetch_first_page(centerfold_file)
+            last_page = writer.pages[-1]
+            if centerfold_page.rotation != 0:
+                centerfold_page.transfer_rotation_to_content()
+            if requires_rotate(centerfold_page.mediabox, last_page.mediabox):
+                centerfold_page = centerfold_page.rotate(270)
+            if centerfold_page.rotation != 0:
+                centerfold_page.transfer_rotation_to_content()
+            last_page.merge_page(centerfold_page)
+
+        # Everything looks good! Write the output file.
+        with open(output, "wb") as output_fh:
+            writer.write(output_fh)
+
+    except Exception:
+        print(traceback.format_exc(), file=sys.stderr)
+        print(f"Error while reading {filename}", file=sys.stderr)
+        sys.exit(1)
+
+
+def requires_rotate(a: RectangleObject, b: RectangleObject) -> bool:
+    """
+    Return True if a and b are rotated relative to each other.
+
+    Args:
+        a (RectangleObject): The first rectangle.
+        b (RectangleObject): The second rectangle.
+
+    """
+    a_portrait = a.height > a.width
+    b_portrait = b.height > b.width
+    return a_portrait != b_portrait
+
+
+def fetch_first_page(filename: Path) -> PageObject:
+    """
+    Fetch the first page of a PDF file.
+
+    Args:
+        filename (Path): The path to the PDF file.
+
+    Returns:
+        PageObject: The first page of the PDF file.
+
+    """
+    return PdfReader(filename).pages[0]
+
+
+# This function written with inspiration, assistance, and code
+# from claude.ai & Github Copilot
+def page_iter(num_pages: int) -> Generator[Tuple[int, int], None, None]:
+    """
+    Generate pairs of page numbers for printing a booklet.
+    This function assumes that the total number of pages is divisible by 4.
+    It yields tuples of page numbers that should be printed on the same sheet
+    of paper to create a booklet.
+
+    Args:
+        num_pages (int): The total number of pages in the document. Must be divisible by 4.
+
+    Yields:
+        Generator[Tuple[int, int], None, None]: Tuples containing pairs of page numbers.
+            Each tuple represents the page numbers to be printed on one side of a sheet.
+
+    Raises:
+        ValueError: If the number of pages is not divisible by 4.
+
+    """
+    if num_pages % 4 != 0:
+        raise ValueError("Number of pages must be divisible by 4")
+
+    for sheet in range(num_pages // 4):
+        # Outside the fold
+        last_page = num_pages - sheet * 2 - 1
+        first_page = sheet * 2
+
+        # Inside the fold
+        second_page = sheet * 2 + 1
+        second_to_last_page = num_pages - sheet * 2 - 2
+
+        yield last_page, first_page
+        yield second_page, second_to_last_page

{pdfly-0.3.3 → pdfly-0.4.0}/pdfly/cat.py

@@ -37,11 +37,11 @@ Examples
         In case you don't want chapter 10 before chapter 2.
 
 """
+
 # Copyright (c) 2014, Steve Witham <switham_github@mac-guyver.com>.
 # All rights reserved. This software is available under a BSD license;
 # see https://github.com/py-pdf/pypdf/LICENSE
 
-
 import os
 import sys
 import traceback
@@ -52,7 +52,11 @@ from pypdf import PageRange, PdfReader, PdfWriter, parse_filename_page_ranges
 
 
 def main(
-    filename: Path, fn_pgrgs: List[str], output: Path, verbose: bool
+    filename: Path,
+    fn_pgrgs: List[str],
+    output: Path,
+    verbose: bool,
+    inverted_page_selection: bool = False,
 ) -> None:
     filename_page_ranges = parse_filepaths_and_pagerange_args(
         filename, fn_pgrgs
@@ -66,15 +70,35 @@ def main(
     writer = PdfWriter()
     in_fs = {}
     try:
-        for filename, page_range in filename_page_ranges:  # type: ignore
+        for filepath, page_range in filename_page_ranges:  # type: ignore
             if verbose:
-                print(filename, page_range, file=sys.stderr)
-            if filename not in in_fs:
-                in_fs[filename] = open(filename, "rb")
-
-            reader = PdfReader(in_fs[filename])
-            for page_num in range(*page_range.indices(len(reader.pages))):
-                writer.add_page(reader.pages[page_num])
+                print(filepath, page_range, file=sys.stderr)
+            if filepath not in in_fs:
+                in_fs[filepath] = open(filepath, "rb")
+
+            reader = PdfReader(in_fs[filepath])
+            num_pages = len(reader.pages)
+            start, end, step = page_range.indices(num_pages)
+            if (
+                start < 0
+                or end < 0
+                or start >= num_pages
+                or end > num_pages
+                or start > end
+            ):
+                print(
+                    f"WARNING: Page range {page_range} is out of bounds",
+                    file=sys.stderr,
+                )
+            if inverted_page_selection:
+                all_page_nums = set(range(len(reader.pages)))
+                page_nums = set(range(*page_range.indices(len(reader.pages))))
+                inverted_page_nums = all_page_nums - page_nums
+                for page_num in inverted_page_nums:
+                    writer.add_page(reader.pages[page_num])
+            else:
+                for page_num in range(*page_range.indices(len(reader.pages))):
+                    writer.add_page(reader.pages[page_num])
         writer.write(output_fh)
     except Exception:
         print(traceback.format_exc(), file=sys.stderr)
@@ -92,11 +116,11 @@ def parse_filepaths_and_pagerange_args(
     fn_pgrgs_l = list(fn_pgrgs)
     fn_pgrgs_l.insert(0, str(filename))
     filename_page_ranges, invalid_filepaths = [], []
-    for filename, page_range in parse_filename_page_ranges(fn_pgrgs_l):  # type: ignore
-        if Path(filename).is_file():
-            filename_page_ranges.append((filename, page_range))
+    for filepath, page_range in parse_filename_page_ranges(fn_pgrgs_l):  # type: ignore
+        if Path(filepath).is_file():
+            filename_page_ranges.append((Path(filepath), page_range))
         else:
-            invalid_filepaths.append(str(filename))
+            invalid_filepaths.append(str(filepath))
     if invalid_filepaths:
         print(
             f"Invalid file path or page range provided: {' '.join(invalid_filepaths)}",