Merge branch 'main' into ENH-py-pdf#2613-integration-of-images-inside-patterns

Author: 0xNath

.github/workflows/github-ci.yaml

@@ -57,7 +57,7 @@ jobs:
     runs-on: ubuntu-20.04
     strategy:
       matrix:
-        python-version: ["3.7", "3.8", "3.9", "3.10", "3.11", "3.12"]
+        python-version: ["3.7", "3.8", "3.9", "3.10", "3.11", "3.12", "3.13-dev"]
         use-crypto-lib: ["cryptography"]
         include:
           - python-version: "3.7"
@@ -90,7 +90,7 @@ jobs:
         cache-dependency-path: '**/requirements/ci.txt'
     - name: Setup Python (3.11+)
       uses: actions/setup-python@v5
-      if: matrix.python-version == '3.11' || matrix.python-version == '3.12'
+      if: matrix.python-version == '3.11' || matrix.python-version == '3.12' || matrix.python-version == '3.13-dev'
       with:
         python-version: ${{ matrix.python-version }}
         allow-prereleases: true
@@ -106,7 +106,7 @@ jobs:
     - name: Install requirements (Python 3.11+)
       run: |
         pip install -r requirements/ci-3.11.txt
-      if: matrix.python-version == '3.11' || matrix.python-version == '3.12'
+      if: matrix.python-version == '3.11' || matrix.python-version == '3.12' || matrix.python-version == '3.13-dev'
     - name: Remove pycryptodome and cryptography
       run: |
         pip uninstall pycryptodome cryptography -y
@@ -215,8 +215,8 @@ jobs:
       - name: Check Number of Downloaded Files
         run: |
           downloaded_files_count=$(find \.coverage* -type f | wc -l)
-          if [ $downloaded_files_count -eq 8 ]; then
-            echo "The expected number of files (8) were downloaded."
+          if [ $downloaded_files_count -eq 9 ]; then
+            echo "The expected number of files (9) were downloaded."
           else
             echo "ERROR: Expected 8 files, but found $downloaded_files_count files."
             exit 1

.github/workflows/release.yaml

@@ -12,6 +12,9 @@ on:
 permissions:
   contents: write
 
+env:
+  HEAD_COMMIT_MESSAGE: ${{ github.event.head_commit.message }}
+
 jobs:
   build_and_publish:
     name: Publish a new version
@@ -24,15 +27,15 @@ jobs:
       - name: Extract version from commit message
         id: extract_version
         run: |
-          VERSION=$(echo "${{ github.event.head_commit.message }}" | grep -oP '(?<=REL: )\d+\.\d+\.\d+')
+          VERSION=$(echo "$HEAD_COMMIT_MESSAGE" | grep -oP '(?<=REL: )\d+\.\d+\.\d+')
           echo "version=$VERSION" >> $GITHUB_OUTPUT
 
       - name: Extract tag message from commit message
         id: extract_message
         run: |
           VERSION="${{ steps.extract_version.outputs.version }}"
           delimiter="$(openssl rand -hex 8)"
-          MESSAGE=$(echo "${{ github.event.head_commit.message }}" | sed "0,/REL: $VERSION/s///" )
+          MESSAGE=$(echo "$HEAD_COMMIT_MESSAGE" | sed "0,/REL: $VERSION/s///" )
           echo "message<<${delimiter}" >> $GITHUB_OUTPUT
           echo "$MESSAGE" >> $GITHUB_OUTPUT
           echo "${delimiter}" >> $GITHUB_OUTPUT

CHANGELOG.md

@@ -1,5 +1,55 @@
 # CHANGELOG
 
+## Version 4.3.1, 2024-07-21
+
+### Bug Fixes (BUG)
+- Cope with Matrix entry in field annotations (#2736)
+
+### Robustness (ROB)
+- Cope with fields with upside down box/rectangle (#2729)
+
+### Maintenance (MAINT)
+- Add deprecate_with_replacement to StreamObject.initializeFromD… (#2728)
+- Deal with cryptography>=43 moving ARC4 (#2765)
+
+[Full Changelog](https://github.com/py-pdf/pypdf/compare/4.3.0...4.3.1)
+
+## Version 4.3.0, 2024-06-23
+
+### New Features (ENH)
+- Accept ETen-B5 and UniCNS-UTF16 encodings (#2721)
+- Add decode_as_image() to ContentStreams (#2615)
+- context manager for PdfReader (#2666)
+- Add capability to set font and size in fields (#2636)
+- Allow to pass input file without named argument (#2576)
+
+### Bug Fixes (BUG)
+- Fix deprecation for Ressources when using old constants (#2705)
+- Fix images issue 4 bits encoding and LUT starting with UTF16_BOM (#2675)
+- Reading large compressed images takes huge time to process (#2644)
+- Highlighted Text Cannot Be Printed (#2604)
+- Fix UnboundLocalError on malformed pdf (#2619)
+
+### Robustness (ROB)
+- Cope with missing Standard 14 fonts in fields (#2677)
+- Improve inline image extraction (#2622)
+- Cope with loops in Fields tree (#2656)
+- Discard /I in choice fields for compatibility with Acrobat (#2614)
+- Cope with some issues in pillow (#2595)
+- Cope with some image extraction issues (#2591)
+
+### Documentation (DOC)
+- Various improvements on docstrings and examples
+
+### Maintenance (MAINT)
+- Deprecate interiour_color with replacement interior_color (#2706)
+- Add deprecate_with_replacement to PdfWriter.find_bookmark (#2674)
+
+### Code Style (STY)
+- Change Link to be a non-markup annotation (#2714)
+
+[Full Changelog](https://github.com/py-pdf/pypdf/compare/4.2.0...4.3.0)
+
 ## Version 4.2.0, 2024-04-07
 
 ### New Features (ENH)

CONTRIBUTING.md

@@ -15,9 +15,9 @@ Please use the templates provided.
 We appreciate if people make PRs, but please be aware that pypdf is used by many
 people. That means:
 
-* We rarely make breaking changes and have a [deprecation process](https://pypdf.readthedocs.io/en/latest/dev/deprecations.html)
+* We rarely make breaking changes and have a [deprecation process](https://pypdf.readthedocs.io/en/latest/dev/deprecations.html).
 * New features, especially adding to the public interface, typically need to be
   discussed first.
 
-Before you make bigger changes, rather open an issue to make the suggestion.
+Before you make bigger changes, open an issue to make the suggestion.
 Note which interface changes you want to make.

CONTRIBUTORS.md

@@ -1,13 +1,13 @@
 # Contributors
 
-pypdf had a lot of contributors since it started with pyPdf in 2005. We are
+pypdf had a lot of contributors since it started as pyPdf in 2005. We are
 a free software project without any company affiliation. We cannot pay
 contributors, but we do value their contributions. A lot of time, effort, and
-expertise went into this project. With this list, we recognize those awesome
+expertise went into this project. With this list, we recognize these awesome
 people 🤗
 
 The list is definitely not complete. You can find more contributors via the git
-history and [GitHubs 'Contributors' feature](https://github.com/py-pdf/pypdf/graphs/contributors).
+history and [GitHub's 'Contributors' feature](https://github.com/py-pdf/pypdf/graphs/contributors).
 
 ## Contributors to the pypdf (formerly pyPdf / PyPDF2) project
 
@@ -19,6 +19,7 @@ history and [GitHubs 'Contributors' feature](https://github.com/py-pdf/pypdf/gra
 * [ediamondscience](https://github.com/ediamondscience)
 * [Ermeson, Felipe](https://github.com/FelipeErmeson)
 * [Freitag, François](https://github.com/francoisfreitag)
+* [Gagnon, William G.](https://github.com/williamgagnon)
 * [Górny, Michał](https://github.com/mgorny)
 * [Grillo, Miguel](https://github.com/Ineffable22)
 * [Gutteridge, David H.](https://github.com/dhgutteridge)

docs/conf.py

@@ -10,6 +10,7 @@
 # If extensions (or modules to document with autodoc) are in another directory,
 # add these directories to sys.path here. If the directory is relative to the
 # documentation root, use os.path.abspath to make it absolute, like shown here.
+import datetime
 import os
 import shutil
 import sys
@@ -25,7 +26,7 @@
 # -- Project information -----------------------------------------------------
 
 project = py_pkg.__name__
-copyright = "2006 - 2023, Mathieu Fenniak and pypdf contributors"
+copyright = f"2006 - {datetime.datetime.now(tz=datetime.timezone.utc).year}, Mathieu Fenniak and pypdf contributors"
 author = "Mathieu Fenniak"
 
 # The version info for the project you're documenting, acts as replacement for
@@ -93,13 +94,13 @@
 
 # -- Options for HTML output -------------------------------------------------
 
-# The theme to use for HTML and HTML Help pages.  See the documentation for
+# The theme to use for HTML and HTML Help pages. See the documentation for
 # a list of builtin themes.
 #
 html_theme = "sphinx_rtd_theme"
 
 # Theme options are theme-specific and customize the look and feel of a theme
-# further.  For a list of options available for each theme, see the
+# further. For a list of options available for each theme, see the
 # documentation.
 html_theme_options = {
     "canonical_url": "",

docs/dev/cmaps.md

@@ -40,7 +40,7 @@ It defines a starting point:
 That means that `1B` (Hex for 27) maps to the unicode character [`FB00`](https://unicode-table.com/en/FB00/) - the ligature ff (two lowercase f's).
 
 The two numbers in `begincodespacerange` mean that it starts with an offset of
-0 (hence from `1B ➜ FB00`) upt to an offset of FF (dec: 255), hence 1B+FF = 282
+0 (hence from `1B ➜ FB00`) up to an offset of FF (dec: 255), hence 1B+FF = 282
 ➜ [FBFF](https://www.compart.com/de/unicode/U+FBFF).
 
 Within the text stream, there is

docs/dev/testing.md

@@ -19,26 +19,6 @@ You can even disable all of them: `pytest -m "not enable_socket" -m "not samples
 
 Please note that this reduces test coverage. The CI will always test all files.
 
-## Creating a Coverage Report
-
-If you want to get a coverage report that considers the Python version specific
-code, you can run [`tox`](https://tox.wiki/en/latest/).
-
-As a prerequisite, we recommend using [`pyenv`](https://github.com/pyenv/pyenv)
-so that you can install the different Python versions:
-
-```
-pyenv install pypy3.8-7.3.7
-pyenv install 3.7.15
-pyenv install 3.8.12
-pyenv install 3.9.10
-pyenv install 3.10.2
-```
-
-Then you can execute `tox` which will create a coverage report in HTML form
-in the end. The execution takes about 30 minutes.
-
-
 ## Docstrings in Unit tests
 
 The first line of a docstring in a unit test should be written in a way that

docs/index.rst

@@ -32,9 +32,10 @@ You can contribute to `pypdf on GitHub <https://github.com/py-pdf/pypdf>`_.
    user/encryption-decryption
    user/merging-pdfs
    user/cropping-and-transforming
-   user/add-watermark
    user/reading-pdf-annotations
    user/adding-pdf-annotations
+   user/add-watermark
+   user/add-javascript
    user/viewer-preferences
    user/forms
    user/streaming-data

docs/meta/faq.md

@@ -1,4 +1,4 @@
-# Frequently-Asked Questions
+# Frequently Asked Questions
 
 ## How is pypdf related to PyPDF2?
 

docs/modules/constants.rst

@@ -20,3 +20,9 @@ Constants
     :members:
     :undoc-members:
     :show-inheritance:
+
+.. autoclass:: pypdf.constants.FieldDictionaryAttributes
+       :members:
+       :undoc-members:
+       :exclude-members: FT, Parent, Kids, T, TU, TM, V, DV, AA, Opt, attributes, attributes_dict
+       :show-inheritance:

docs/user/add-javascript.md

@@ -0,0 +1,21 @@
+# Adding JavaScript to a PDF
+
+PDF readers vary in the extent they support JavaScript, with some not supporting it at all.
+
+Adobe has documentation on its support here:
+https://opensource.adobe.com/dc-acrobat-sdk-docs/library/jsapiref/index.html
+
+## Launch print window on opening
+
+```python
+from pypdf import PdfWriter
+
+writer = PdfWriter(clone_from="example.pdf")
+
+# Add JavaScript to launch the print window on opening this PDF.
+writer.add_js("this.print({bUI:true,bSilent:false,bShrinkToFit:true});")
+
+# Write to pypdf-output.pdf.
+with open("pypdf-output.pdf", "wb") as fp:
+    writer.write(fp)
+```

docs/user/add-watermark.md

@@ -11,7 +11,7 @@ The process of stamping and watermarking is the same, you just need to set `over
 You can use `merge_page()` if you don't need to transform the stamp:
 
 ```python
-from pypdf import PdfWriter, PdfReader
+from pypdf import PdfReader, PdfWriter
 
 stamp = PdfReader("bg.pdf").pages[0]
 writer = PdfWriter(clone_from="source.pdf")

docs/user/adding-pdf-annotations.md

@@ -215,14 +215,12 @@ with open("annotated-pdf.pdf", "wb") as fp:
 
 ## Popup
 
-Manage the Popup windows for markups. looks like this:
+Manage the Popup windows for markups, looks like this:
 
 ![](annotation-popup.png)
 
 you can use the {py:class}`Popup <pypdf.annotations.Popup>`:
 
-you have to use the returned result from add_annotation() to fill-up the
-
 ```python
 from pypdf.annotations import Popup, Text
 
@@ -249,6 +247,9 @@ popup_annotation = Popup(
 writer.write("annotated-pdf-popup.pdf")
 ```
 
+You have to use the returned result from add_annotation() as it is
+the parent annotation with which this popup annotation shall be associated.
+
 ## Link
 
 If you want to add a link, you can use
@@ -264,7 +265,7 @@ page = reader.pages[0]
 writer = PdfWriter()
 writer.add_page(page)
 
-# Add the line
+# Add the link
 annotation = Link(
     rect=(50, 550, 200, 650),
     url="https://martin-thoma.com/",
@@ -281,16 +282,19 @@ You can also add internal links:
 ```python
 from pypdf import PdfReader, PdfWriter
 from pypdf.annotations import Link
+from pypdf.generic import Fit
 
 pdf_path = os.path.join(RESOURCE_ROOT, "crazyones.pdf")
 reader = PdfReader(pdf_path)
 page = reader.pages[0]
 writer = PdfWriter()
 writer.add_page(page)
 
-# Add the line
+# Add the link
 annotation = Link(
-    rect=(50, 550, 200, 650), target_page_index=3, fit="/FitH", fit_args=(123,)
+    rect=(50, 550, 200, 650),
+    target_page_index=3,
+    fit=Fit(fit_type="/FitH", fit_args=(123,)),
 )
 writer.add_annotation(page_number=0, annotation=annotation)
 
@@ -303,7 +307,7 @@ with open("annotated-pdf.pdf", "wb") as fp:
 
 Text markup annotations refer to a specific piece of text within the document.
 
-Those are a bit more complicated as you need to know exactly where the text
+These are a bit more complicated as you need to know exactly where the text
 is, the so-called "Quad points".
 
 ### Highlighting