pypdfium2-team · mara004 · Apr 4, 2024 · Apr 4, 2024 · Apr 4, 2024 · Apr 4, 2024
diff --git a/.github/workflows/conda.yaml b/.github/workflows/conda.yaml
@@ -121,7 +121,7 @@ jobs:
         run: |
           conda install -y pytest pillow numpy
           conda install -y pypdfium2_${{ inputs.package }} --override-channels -c ./conda_dist/ -c pypdfium2-team -c bblanchon -c defaults
-          pytest tests/ tests_old/
+          pytest tests/
 
   publish:
 

diff --git a/.github/workflows/trigger_conda_raw.yaml b/.github/workflows/trigger_conda_raw.yaml
@@ -3,10 +3,9 @@
 
 name: Trigger conda_raw release
 on:
-  # NOTE temporarily commented out, awaiting merge of the v5 branch
-  # schedule:
-  #   # pdfium-binaries triggers conda on the first Monday of month at 4 o'clock UTC, so we'll want to rebuild after that, but before the next main release where we want to use the package
-  #   - cron: '0 4 8 * *'  # monthly, 8th day
+  schedule:
+    # pdfium-binaries triggers conda on the first Monday of month at 4 o'clock UTC, so we'll want to rebuild after that, but before the next main release where we want to use the package
+    - cron: '0 4 8 * *'  # monthly, 8th day
   workflow_dispatch:
 
 jobs:

diff --git a/.github/workflows/trigger_main.yaml b/.github/workflows/trigger_main.yaml
@@ -5,12 +5,11 @@
 
 name: Trigger main release
 on:
-  # NOTE temporarily commented out, awaiting merge of the v5 branch
-  # # https://github.com/bblanchon/pdfium-binaries/blob/master/.github/workflows/trigger.yml
-  # # https://docs.github.com/en/actions/using-workflows/events-that-trigger-workflows#schedule
-  # # https://crontab.guru/
-  # schedule:
-  #   - cron: '0 4 10 * *'  # monthly, 10th day
+  # https://github.com/bblanchon/pdfium-binaries/blob/master/.github/workflows/trigger.yml
+  # https://docs.github.com/en/actions/using-workflows/events-that-trigger-workflows#schedule
+  # https://crontab.guru/
+  schedule:
+    - cron: '0 4 10 * *'  # monthly, 10th day
   workflow_dispatch:
 
 jobs:

diff --git a/.gitignore b/.gitignore
@@ -5,7 +5,6 @@ build/
 dist/
 conda/*/out/
 tests/output/
-tests_old/output/
 
 data/
 !data/.gitkeep

diff --git a/.reuse/dep5 b/.reuse/dep5
@@ -51,7 +51,7 @@ Files:
     tests/resources/attachments.pdf
     tests/resources/mona_lisa.jpg
 Copyright: 2022 PDFium developers
-License: BSD-3-Clause OR Apache-2.0
+License: BSD-3-Clause, Apache-2.0
 Comment:
     Obtained from:
     https://pdfium.googlesource.com/pdfium/+/refs/heads/main/testing/resources/bookmarks_circular.pdf
@@ -67,7 +67,7 @@ Files:
 Copyright:
     2022 PDFium developers
     2024 geisserml <[email protected]>
-License: BSD-3-Clause OR Apache-2.0
+License: BSD-3-Clause, Apache-2.0
 
 Files: tests/resources/images.pdf
 Copyright:

diff --git a/.reuse/dep5-wheel b/.reuse/dep5-wheel
@@ -26,4 +26,4 @@ Copyright:
     2024 PDFium developers
     2024 Developers of projects mentioned in PdfiumThirdParty
     2024 Benoît Blanchon and pdfium-binaries contributors
-License: (Apache-2.0 OR BSD-3-Clause) AND LicenseRef-PdfiumThirdParty
+License: (BSD-3-Clause, Apache-2.0) AND LicenseRef-PdfiumThirdParty
diff --git a/README.md b/README.md
diff --git a/autorelease/config.json b/autorelease/config.json
@@ -1,5 +1,5 @@
 {
-  "beta": false,
-  "major": false,
+  "beta": true,
+  "major": true,
   "humble": null
-}
+}
diff --git a/conda/helpers/recipe/meta.yaml b/conda/helpers/recipe/meta.yaml
@@ -51,10 +51,10 @@ about:
   description: |
     This package provides python helpers around pdfium.
     Dependants are suggested to pin to a major version, but any tighter pinning is discouraged since it increases the risk for conflicts, and would lock you out from future fixes.
-  license: Apache-2.0 OR BSD-3-Clause
+  license: BSD-3-Clause, Apache-2.0
   license_file:
-    - LICENSES/Apache-2.0.txt
     - LICENSES/BSD-3-Clause.txt
+    - LICENSES/Apache-2.0.txt
     - LICENSES/CC-BY-4.0.txt
   dev_url: https://github.com/pypdfium2-team/pypdfium2
   doc_url: https://pypdfium2.readthedocs.io

diff --git a/conda/raw/recipe/meta.yaml b/conda/raw/recipe/meta.yaml
@@ -52,10 +52,10 @@ about:
   description: |
     This package provides raw ctypes bindings to pdfium.
     Important: DO NOT PIN to an exact version, as pypdfium2_raw itself pins pdfium-binaries to achieve ABI safety.
-  license: Apache-2.0 OR BSD-3-Clause
+  license: BSD-3-Clause, Apache-2.0
   license_file:
-    - LICENSES/Apache-2.0.txt
     - LICENSES/BSD-3-Clause.txt
+    - LICENSES/Apache-2.0.txt
     - LICENSES/CC-BY-4.0.txt
   dev_url: https://github.com/pypdfium2-team/pypdfium2
   doc_url: https://pypdfium2.readthedocs.io

diff --git a/docs/devel/changelog.md b/docs/devel/changelog.md
@@ -39,7 +39,7 @@
 ## 4.26.0 (2024-01-10)
 
 - Updated PDFium from `6164` to `6233`.
-- Pin ctypesgen in sdist to prevent reoccurrence of {issue}`264` / {issue}`286`. As a drawback, the pin is never committed, so the sdist is not simply reproducible at this time due to dependence on the latest commit hash of the ctypesgen fork at build time.
+- Pin ctypesgen in sdist to prevent re-occurrence of {issue}`264` / {issue}`286`. As a drawback, the pin is never committed, so the sdist is not simply reproducible at this time due to dependence on the latest commit hash of the ctypesgen fork at build time.
 - Wheel tags: Added back `manylinux2014` in addition to `manylinux_{glibc_ver}` to be on the safe side. Suspected relation to the above issues.
 
 
@@ -59,10 +59,10 @@
 #### Rationale for `PdfDocument.render()` deprecation
 
 - The parallel rendering API unfortunately was an inherent design mistake: Multiprocessing is not meant to transfer large amounts of pixel data from workers to the main process.
-- This was such a heavy drawback that it basically outweighed the parallelization, so there was no real performance advantage, only higher memory load.
-- As a related problem, the worker pool produces bitmaps at an indepedent speed, regardless of where the receiving iteration might be, so bitmaps could queue up in memory, possibly causing an enormeous rise in memory consumption over time. This effect was pronounced e.g. with PNG saving via PIL, as exhibited in Facebook's `nougat` project.
+- Bitmap transfer is so expensive that it essentially outweighed parallelization, so there was no real performance advantage, only higher memory load.
+- As a related problem, the worker pool produces bitmaps at an independent speed, regardless of where the receiving iteration might be, so bitmaps could queue up in memory, possibly causing an enormeous rise in memory consumption over time. This effect was pronounced e.g. with PNG saving via PIL, as seen in Facebook's `nougat` project.
 - Instead, each bitmap should be processed (e.g. saved) in the job which created it. Only a minimal, final result should be sent back to the main process (e.g. a file path).
-- This means we cannot reasonably provide a generic parallel renderer, instead it needs to be implemented by callers.
+- This means we cannot reasonably provide a generic parallel renderer; instead it needs to be implemented by callers.
 - Historically, note that there had been even more faults in the implementation:
   * Prior to `4.22.0`, the pool was always initialized with `os.cpu_count()` processes by default, even when rendering less pages.
   * Prior to `4.20.0`, a full-scale input transfer was conducted on each job (rendering it unusable with bytes input). However, this can and should be done only once on process creation.

diff --git a/docs/devel/changelog_staging.md b/docs/devel/changelog_staging.md
@@ -4,7 +4,38 @@
 <!-- List character: dash (-) -->
 
 # Changelog for next release
-- `PdfPage.get_objects()`: Don't register pageobjects as children, because they don't need to be closed by the caller when part of a page. This avoids excessive caching of weakrefs that are not cleaned up with the object they refer to.
-- Autorelease: Swapped default condition for minor/patch update, as pypdfium2 changes are likely more API-significant than pdfium updates. Added ability for manual override.
-- Fixed conda packaging: It is now required to explicitly specify `-c defaults` with `--override-channels`, presumably due to an upstream change.
-- Bumped workflows to Python 3.12.
+
+*API changes*
+- Rendering / Bitmap
+  * Removed `PdfDocument.render()` (see deprecation rationale in v4.25 changelog). Instead, use `PdfPage.render()` with a loop or process pool.
+  * Removed `PdfBitmap.get_info()` and `PdfBitmapInfo`, which existed only on behalf of data transfer with `PdfDocument.render()`.
+  * `PdfBitmap.to_numpy()`: If the bitmap is single-channel (grayscale), use a 2d shape to avoid needlessly wrapping each pixel value in a list.
+  * `PdfBitmap.from_pil()`: Removed `recopy` param.
+  * Removed pdfium color scheme param from rendering, as it's not really useful: one can only set colors for certain object types, which are then forced on all instances of that type. This may flatten different colors into one, leading to a loss of visual information. To achieve a "dark theme" for light PDFs, we suggest to instead post-process rendered images with selective lightness inversion, as is now implemented in pypdfium2's rendering CLI.
+- Pageobjects
+  * Renamed `PdfObject.get_pos()` to `.get_bounds()`.
+  * Renamed `PdfImage.get_size()` to `.get_px_size()`.
+  * `PdfImage.extract()`: Removed `fb_render` param because it does not fit in this API. If the image's rendered bitmap is desired, use `.get_bitmap(render=True)` in the first place.
+- Renamed misleading `PdfMatrix.mirror()` parameters `v, h` to `invert_x, invert_y`, as the terms horizontal/vertical flip commonly refer to the transformation applied, not the axis around which is being flipped (i.e. the previous `v` meant flipping around the Y axis, which is vertical, but the resulting transform is inverting the X coordinates and thus actually horizontal). No behavior change if you did not use keyword arguments.
+- `PdfDocument.get_toc()`: Replaced `PdfOutlineItem` namedtuple with method-oriented wrapper classes `PdfBookmark` and `PdfDest`, so callers may retrieve only the properties they actually need. This is closer to pdfium's original API and exposes the underlying raw objects. Provides signed count as-is rather than splitting in `n_kids` and `is_closed`. Also distinguishes between `dest is None` and a dest with unknown mode.
+- `get_text_range()`: Removed implicit translation of default calls to `get_text_bounded()`, as pdfium reverted `FPDFText_GetText()` to UCS-2, which resolves the allocation concern. However, callers are encouraged to explicitly use `get_text_bounded()` for full Unicode support.
+- Removed legacy version flags.
+
+*Improvements and new features*
+- Added `PdfPosConv` helper and `PdfBitmap.get_posconv(page)` for bidirectional translation between page and bitmap coordinates.
+- Added `PdfObject.get_quad_points()` to get the corner points of an image or text object.
+- Exposed `PdfPage.flatten()` (previously semi-private `_flatten()`), after having found out how to correctly use it. Added check and updated docs accordingly.
+- Added context manager support to `PdfDocument`, so it can be used in a `with`-statement, because opening from a file path binds a file descriptor, which should be released explicitly, given OS limits on the number of open FDs.
+- If document loading failed, `err_code` is now assigned to the `PdfiumError` instance so callers may programmatically handle the error subtype.
+- Corrected some null pointer checks: we have to use `bool(ptr)` rather than `ptr is None`.
+- Improved startup performance by deferring imports of optional dependencies to the point where they are actually needed, to avoid overhead if you do not use them.
+- Simplified version classes (no API change expected).
+
+*Project*
+- Merged `tests_old/` back into `tests/`.
+- Docs: Improved logic when to include the unreleased version warning and upcoming changelog.
+
+<!-- TODO
+See https://github.com/pypdfium2-team/pypdfium2/blob/devel_old/docs/devel/changelog_staging.md
+for how to proceed. Note that some things have already been backported, and some rejected.
+-->
diff --git a/docs/source/changelog.rst b/docs/source/changelog.rst
@@ -4,7 +4,7 @@
 Changelog
 =========
 
-.. ifconfig:: build_type == 'latest'
+.. ifconfig:: have_changes
 
     .. warning::
          This is a documentation build for an unreleased version of pypdfium2, so it is possible that new changes are not logged yet.

diff --git a/docs/source/conf.py b/docs/source/conf.py
@@ -8,32 +8,21 @@
 import os
 import sys
 import time
-import collections
+# import collections
 from pathlib import Path
 
 sys.path.insert(0, str(Path(__file__).parents[2] / "setupsrc"))
 from pypdfium2_setup.packaging_base import (
-    run_cmd,
-    ProjectDir,
+    parse_git_tag,
+    get_next_changelog,
 )
 
-
-def _get_build_type():
-
-    # RTD uses git checkout --force origin/... which results in a detached HEAD state, so we cannot easily get the branch name
-    # Thus query for an RTD-specific environment variable instead
-    rtd_vn = os.environ.get("READTHEDOCS_VERSION_NAME", None)
-    if rtd_vn:
-        return rtd_vn
-
-    branch = run_cmd(["git", "branch", "--show-current"], cwd=ProjectDir, capture=True)
-    if branch == "main":
-        return "latest"
-    else:
-        return branch
-
-
-build_type = _get_build_type()
+# RTD modifies conf.py, so we have to ignore dirty state if on RTD
+is_rtd = os.environ.get("READTHEDOCS", "").lower() == "true"
+tag_info = parse_git_tag()
+have_changes = tag_info["n_commits"] > 0 or (tag_info["dirty"] and not is_rtd)
+if get_next_changelog():
+    assert have_changes
 
 project = "pypdfium2"
 author = "pypdfium2-team"
@@ -70,7 +59,6 @@ def _get_build_type():
     "members": True,
     "undoc-members": True,
     "show-inheritance": True,
-    # "inherited-members": True,
     "member-order": "bysource",
 }
 intersphinx_mapping = {
@@ -81,21 +69,16 @@ def _get_build_type():
 
 # https://www.sphinx-doc.org/en/master/usage/configuration.html#confval-rst_prolog
 # .. |br| raw:: html
-
 #    <br/>
-rst_prolog = """
-.. |build_type| replace:: %(build_type)s
-""" % dict(
-    build_type = build_type,
-)
-
-
-def remove_namedtuple_aliases(app, what, name, obj, skip, options):
-    if type(obj) is collections._tuplegetter:
-        return True
-    return skip
+rst_prolog = f"""
+.. |have_changes| replace:: {have_changes}
+"""
 
+# def remove_namedtuple_aliases(app, what, name, obj, skip, options):
+#     if type(obj) is collections._tuplegetter:
+#         return True
+#     return skip
 
 def setup(app):
-    app.connect('autodoc-skip-member', remove_namedtuple_aliases)
-    app.add_config_value("build_type", "latest", "env")
+    # app.connect('autodoc-skip-member', remove_namedtuple_aliases)
+    app.add_config_value("have_changes", True, "env")
diff --git a/docs/source/index.rst b/docs/source/index.rst
@@ -4,7 +4,7 @@
 pypdfium2
 =========
 
-Welcome to the documentation for the support model of pypdfium2 (|build_type| build).
+Welcome to the documentation for the support model of pypdfium2.
 
 .. toctree::
    :maxdepth: 2
@@ -16,9 +16,8 @@ Welcome to the documentation for the support model of pypdfium2 (|build_type| bu
 
 .. toctree::
    :maxdepth: 1
-   :caption: Progress
+   :caption: Release Notes
 
-   planned_changes
    changelog
 
 

diff --git a/docs/source/planned_changes.md b/docs/source/planned_changes.md
diff --git a/docs/source/python_api.rst b/docs/source/python_api.rst
@@ -76,9 +76,6 @@ Version
 
 .. automodule:: pypdfium2.version
 
-.. deprecated:: 4.22
-   The legacy members ``V_PYPDFIUM2, V_LIBPDFIUM, V_BUILDNAME, V_PDFIUM_IS_V8, V_LIBPDFIUM_FULL`` will be removed in version 5.
-
 Document
 ********
 .. automodule:: pypdfium2._helpers.document
@@ -87,8 +84,8 @@ Page
 ****
 .. automodule:: pypdfium2._helpers.page
 
-Page Objects
-************
+Pageobjects
+***********
 .. automodule:: pypdfium2._helpers.pageobjects
 
 Text Page

diff --git a/docs/source/shell_api.rst b/docs/source/shell_api.rst
@@ -46,8 +46,8 @@ Image Converter
 .. command-output:: pypdfium2 imgtopdf --help
 
 
-Page Objects Info
-*****************
+Pageobjects Info
+****************
 .. command-output:: pypdfium2 pageobjects --help
 
 

diff --git a/req/converters.txt b/req/converters.txt
@@ -1,3 +1,3 @@
-# NOTE In order to use numpy, the rendering CLI further needs `opencv-python`, but we don't currently cover that internally. As the import is guarded, we don't have to require it here.
+# NOTE In order to use numpy, the rendering CLI further needs `opencv-python[-headless]`, but we don't currently cover that internally. As the import is guarded, we don't have to require it here.
 pillow
 numpy
diff --git a/run b/run
@@ -8,13 +8,13 @@
 args="${@:2}"
 
 function check() {
-    autoflake src/ setupsrc/ tests/ tests_old/ setup.py docs/source/conf.py --recursive --remove-all-unused-imports --ignore-pass-statements --ignore-init-module-imports
-    codespell --skip="./docs/build,./tests/resources,./tests/output,./tests_old/output,./data,./sourcebuild,./dist,./.git,__pycache__,.mypy_cache,.hypothesis" -L "tabe,splitted,fith,flate"
+    autoflake src/ setupsrc/ tests/ setup.py docs/source/conf.py --recursive --remove-all-unused-imports --ignore-pass-statements --ignore-init-module-imports
+    codespell --skip="./docs/build,./tests/resources,./tests/output,./data,./sourcebuild,./dist,./.git,__pycache__,.mypy_cache,.hypothesis" -L "tabe,splitted,fith,flate"
     reuse lint
 }
 
 function clean() {
-    rm -rf pypdfium2*.egg-info/ src/pypdfium2*.egg-info/ build/ dist/ data/* tests/output/* tests_old/output/* conda/bundle/out/ conda/helpers/out/ conda/raw/out/
+    rm -rf pypdfium2*.egg-info/ src/pypdfium2*.egg-info/ build/ dist/ data/* tests/output/* conda/bundle/out/ conda/helpers/out/ conda/raw/out/
 }
 
 function packaging_pypi() {
@@ -35,10 +35,10 @@ set -x
 case $1 in
 
 test)
-    python3 -m pytest tests/ tests_old/ $args;;
+    python3 -m pytest tests/ $args;;
 
 coverage)
-    python3 -m coverage run --omit "tests/*,tests_old/*,src/pypdfium2_raw/bindings.py,setupsrc/*" -m pytest tests/ tests_old/ $args
+    python3 -m coverage run --omit "tests/*,src/pypdfium2_raw/bindings.py,setupsrc/*" -m pytest tests/ $args
     python3 -m coverage report;;
 
 docs-build)

diff --git a/setup.py b/setup.py
@@ -81,7 +81,7 @@ def run_setup(modnames, pl_name, pdfium_ver):
     kwargs = dict(
         name = "pypdfium2",
         description = "Python bindings to PDFium",
-        license = "Apache-2.0 OR BSD-3-Clause",
+        license = "BSD-3-Clause, Apache-2.0, PdfiumThirdParty",
         license_files = LICENSES_SHARED,
         python_requires = ">= 3.6",
         cmdclass = {},
@@ -132,7 +132,6 @@ def run_setup(modnames, pl_name, pdfium_ver):
         kwargs["package_data"]["pypdfium2_raw"] = [VersionFN, BindingsFN, libname]
         kwargs["cmdclass"]["bdist_wheel"] = bdist_factory(pl_name)
         kwargs["distclass"] = BinaryDistribution
-        kwargs["license"] = f"({kwargs['license']}) AND LicenseRef-PdfiumThirdParty"
         kwargs["license_files"] += LICENSES_WHEEL
 
     if "pypdfium2" in kwargs["package_data"]: