Merge commit '8f52578e85b27831ab8a68a6d86721ea3348a553' into develop

* commit '8f52578e85b27831ab8a68a6d86721ea3348a553': Run black locally with nox (pdfminer#776) Install typing_extensions on Python 3.6 and 3.7 (pdfminer#775) Fix `TypeError` by Ignoring null characters in PSBaseParser (pdfminer#768) Fix `ValueError` with unencrypted metadata values (Fixes pdfminer#766). (pdfminer#774) Fix `TypeError` when getting default width of font (pdfminer#772) Deprecate usage of `if __name__ == "__main__"` in scripts that are not documented. Also deprecate usage of scripts that are only there for testing purposes. (pdfminer#756) Fix Sphinx warnings and error (pdfminer#760) Update CHANGELOG.md for pdfminer#755 Remove upper version bounds (pdfminer#755) Ignore path constructors that do not begin with m (pdfminer#749) Bump version 20220506 & fix small issue with types
HiTalentAlgorithms · Aug 5, 2022 · 7c7568c · 7c7568c
2 parents 766b787 + 8f52578
commit 7c7568c
Show file tree

Hide file tree

Showing 27 changed files with 302 additions and 64 deletions.
diff --git a/.github/pull_request_template.md b/.github/pull_request_template.md
@@ -1,25 +1,15 @@
 **Pull request**
 
-Please remove this paragraph and replace it with a description of your PR.
-Also include links to the issues that it fixes. 
+Please *remove* this paragraph and replace it with a description of your PR. Also include the issue that it fixes. 
 
 **How Has This Been Tested?**
 
-Please repalce this paragraph with a description of how this PR has been 
-tested. Include the necessary instructions and files such that other can
-reproduce it.
+Please *remove* this paragraph with a description of how this PR has been tested.
 
 **Checklist**
 
-- [ ] I have formatted my code with [black](https://github.com/psf/black).
-- [ ] I have added tests that prove my fix is effective or that my feature 
-  works
-- [ ] I have added docstrings to newly created methods and classes
-- [ ] I have optimized the code at least one time after creating the initial 
-  version
-- [ ] I have updated the [README.md](../README.md) or verified that this
-  is not necessary
-- [ ] I have updated the [readthedocs](../docs/source) documentation or
-  verified that this is not necessary
-- [ ] I have added a concise human-readable description of the change to
-  [CHANGELOG.md](../CHANGELOG.md)
+- [ ] I have read [CONTRIBUTING.md](../CONTRIBUTING.md). 
+- [ ] I have added a concise human-readable description of the change to [CHANGELOG.md](../CHANGELOG.md).
+- [ ] I have tested that this fix is effective or that this feature works.
+- [ ] I have added docstrings to newly created methods and classes.
+- [ ] I have updated the [README.md](../README.md) and the [readthedocs](../docs/source) documentation. Or verified that this is not necessary.
diff --git a/.github/workflows/actions.yml b/.github/workflows/actions.yml
@@ -14,6 +14,61 @@ env:
   default-python: "3.10"
 
 jobs:
+
+  check-code-formatting:
+    name: Check coding style
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v2
+      - name: Set up Python ${{ env.default-python }}
+        uses: actions/setup-python@v2
+        with:
+          python-version: ${{ env.default-python }}
+      - name: Upgrade pip, Install nox
+        run: |
+          python -m pip install --upgrade pip
+          python -m pip install nox
+      - name: Check coding style
+        run: |
+          nox --error-on-missing-interpreters --non-interactive --session format
+
+  check-coding-style:
+    name: Check coding style
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v2
+      - name: Set up Python ${{ env.default-python }}
+        uses: actions/setup-python@v2
+        with:
+          python-version: ${{ env.default-python }}
+      - name: Upgrade pip, Install nox
+        run: |
+          python -m pip install --upgrade pip
+          python -m pip install nox
+      - name: Check coding style
+        run: |
+          nox --error-on-missing-interpreters --non-interactive --session lint
+
+  check-static-types:
+    name: Check static types
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v2
+      - name: Set up Python ${{ env.default-python }}
+        uses: actions/setup-python@v2
+        with:
+          python-version: ${{ env.default-python }}
+      - name: Upgrade pip, Install nox
+        run: |
+          python -m pip install --upgrade pip
+          python -m pip install nox
+      - name: Check static types
+        run: |
+          nox --error-on-missing-interpreters --non-interactive --session types
+
   tests:
     name: Run tests
     runs-on: ${{ matrix.os }}

diff --git a/CHANGELOG.md b/CHANGELOG.md
@@ -3,6 +3,29 @@
 All notable changes in pdfminer.six will be documented in this file.
 
 The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/).
+## [20220805]
+
+### Fixed
+
+- `ValueError` when trying to decrypt empty metadata values ([#766](https://github.com/pdfminer/pdfminer.six/issues/766))
+- Sphinx errors during building of documentation ([#760](https://github.com/pdfminer/pdfminer.six/pull/760))
+- `TypeError` when getting default width of font ([#720](https://github.com/pdfminer/pdfminer.six/issues/720))
+- Install typing-extensions on Python 3.6 and 3.7 ([#775](https://github.com/pdfminer/pdfminer.six/pull/775))
+- `TypeError` in cmapdb.py when parsing null characters ([#768](https://github.com/pdfminer/pdfminer.six/pull/768))
+- `ValueError` when trying to convert `str` to `int` in
+### Deprecated
+
+- Usage of `if __name__ == "__main__"` where it was only intended for testing purposes ([#756](https://github.com/pdfminer/pdfminer.six/pull/756))
+
+## [20220524]
+
+### Fixed
+
+- Ignoring (invalid) path constructors that do not begin with `m` ([#749](https://github.com/pdfminer/pdfminer.six/pull/749))
+
+### Changed
+
+- Removed upper version bounds ([#755](https://github.com/pdfminer/pdfminer.six/pull/755))
 
 ## [20220426]
 
@@ -225,13 +248,13 @@ The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/).
 
 - Group text lines if they are centered ([#384](https://github.com/pdfminer/pdfminer.six/pull/384))
 
-## [20200124] - 2020-01-24
+## [20200124]
 
 ### Security
 
 - Removed samples/issue-00152-embedded-pdf.pdf because it contains a possible security thread; a javascript enabled object ([#364](https://github.com/pdfminer/pdfminer.six/pull/364))
 
-## [20200121] - 2020-01-21
+## [20200121]
 
 ### Fixed
 
@@ -244,23 +267,23 @@ The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/).
 
 - The command-line utility latin2ascii.py ([#360](https://github.com/pdfminer/pdfminer.six/pull/360))
 
-## [20200104] - 2019-01-04
+## [20200104]
 
-## Removed
+### Removed
 
 - Support for Python 2 ([#346](https://github.com/pdfminer/pdfminer.six/pull/346))
 
 ### Changed
 
 - Enforce pep8 coding style by adding flake8 to CI ([#345](https://github.com/pdfminer/pdfminer.six/pull/345))
 
-## [20191110] - 2019-11-10
+## [20191110]
 
 ### Fixed
 
 - Wrong order of text box grouping introduced by PR #315 ([#335](https://github.com/pdfminer/pdfminer.six/pull/335))
 
-## [20191107] - 2019-11-07
+## [20191107]
 
 ### Deprecated
 
@@ -290,7 +313,7 @@ The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/).
 
 - Files for external applications such as django, cgi and pyinstaller ([#320](https://github.com/pdfminer/pdfminer.six/pull/320))
 
-## [20191020] - 2019-10-20
+## [20191020]
 
 ### Deprecated
 
@@ -316,7 +339,7 @@ The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/).
 
 - All dependencies are managed in `setup.py` ([#306](https://github.com/pdfminer/pdfminer.six/pull/306) and [#219](https://github.com/pdfminer/pdfminer.six/pull/219))
 
-## [20181108] - 2018-11-08
+## [20181108]
 
 ### Changed
 

diff --git a/CONTRIBUTING.md b/CONTRIBUTING.md
@@ -26,20 +26,25 @@ Any contribution is appreciated! You might want to:
 
 ## Guideline for creating pull request
 
-* A pull request should close an existing issue.
-* Pull requests should be merged to master. Version tags are used indicate the releases.
+* A pull request should close an existing issue. For example, use "Fix #123" to indicate that your PR fixes issue 123. 
+* Pull requests should be merged to master.
 * Include unit tests when possible. In case of bugs, this will help to prevent the same mistake in the future. In case
   of features, this will show that your code works correctly.
 * Code should work for Python 3.6+.
-* Code should be formatted with [black](https://github.com/psf/black). 
+* Test your code by using nox (see below). 
 * New features should be well documented using docstrings.
+* Check if the [README.md](../README.md) or [readthedocs](../docs/source) documentation needs to be updated. 
 * Check spelling and grammar.
-* Don't forget to update the [CHANGELOG.md](CHANGELOG.md#[Unreleased])
+* Don't forget to update the [CHANGELOG.md](CHANGELOG.md#[Unreleased]). 
 
 ## Guidelines for posting comments
 
 * [Be cordial and positive](https://www.kennethreitz.org/essays/be-cordial-or-be-on-your-way)
 
+## Guidelines for publishing
+
+* Publishing is automated. Add a YYYYMMDD version tag and GitHub workflows will do the rest. 
+
 ## Getting started
 
 1. Clone the repository
@@ -68,9 +73,3 @@ Any contribution is appreciated! You might want to:
    ```sh
     nox -e py36
     ```
-
-4. After changing the code, run the black formatter.
-
-    ```sh
-    black .
-    ```
diff --git a/docs/source/howto/acro_forms.rst b/docs/source/howto/acro_forms.rst
@@ -1,7 +1,7 @@
 .. _acro_forms:
 
 How to extract AcroForm interactive form fields from a PDF using PDFMiner
-********************************
+*************************************************************************
 
 Before you start, make sure you have :ref:`installed pdfminer.six<install>`.
 
@@ -78,14 +78,16 @@ How it works:
     doc = PDFDocument(parser)
 
 - Get the catalog
-(the catalog contains references to other objects defining the document structure, see section 7.7.2 of PDF 32000-1:2008 specs: https://www.adobe.com/devnet/pdf/pdf_reference.html)
+
+  (the catalog contains references to other objects defining the document structure, see section 7.7.2 of PDF 32000-1:2008 specs: https://www.adobe.com/devnet/pdf/pdf_reference.html)
 
 .. code-block:: python
 
     res = resolve1(doc.catalog)
 
 - Check if the catalog contains the AcroForm key and raise ValueError if not 
-(the PDF does not contain Acroform type of interactive forms if this key is missing in the catalog, see section 12.7.2 of PDF 32000-1:2008 specs)
+
+  (the PDF does not contain Acroform type of interactive forms if this key is missing in the catalog, see section 12.7.2 of PDF 32000-1:2008 specs)
 
 .. code-block:: python
 
@@ -119,7 +121,8 @@ How it works:
     values = resolve1(value)
 
 - Call the value(s) decoding method as needed
-(a single field can hold multiple values, for example a combo box can hold more than one value at time)
+
+  (a single field can hold multiple values, for example a combo box can hold more than one value at time)
 
 .. code-block:: python
 

diff --git a/docs/source/reference/commandline.rst b/docs/source/reference/commandline.rst
@@ -11,7 +11,7 @@ pdf2txt.py
 
 .. argparse::
     :module: tools.pdf2txt
-    :func: maketheparser
+    :func: create_parser
     :prog: python tools/pdf2txt.py
 
 .. _api_dumppdf:

diff --git a/docs/source/reference/highlevel.rst b/docs/source/reference/highlevel.rst
@@ -21,10 +21,10 @@ extract_text_to_fp
 .. autofunction:: extract_text_to_fp
 
 
+.. _api_extract_pages:
+
 extract_pages
 =============
 
 .. currentmodule:: pdfminer.high_level
 .. autofunction:: extract_pages
-
-.. _api_extract_pages:
diff --git a/noxfile.py b/noxfile.py
@@ -1,20 +1,37 @@
+import os
+
 import nox
 
 
 PYTHON_ALL_VERSIONS = ["3.6", "3.7", "3.8", "3.9", "3.10"]
+PYTHON_MODULES = ["pdfminer", "tools", "tests", "noxfile.py", "setup.py"]
+
+
+@nox.session
+def format(session):
+    session.install("black")
+    # Format files locally with black, but only check in cicd
+    if "CI" in os.environ:
+        session.run("black", "--check", *PYTHON_MODULES)
+    else:
+        session.run("black", *PYTHON_MODULES)
 
 
 @nox.session
 def lint(session):
     session.install("flake8")
-    session.run("flake8", "pdfminer/", "tools/", "tests/", "--count", "--statistics")
+    session.run("flake8", *PYTHON_MODULES, "--count", "--statistics")
 
 
 @nox.session
 def types(session):
     session.install("mypy")
     session.run(
-        "mypy", "--install-types", "--non-interactive", "--show-error-codes", "."
+        "mypy",
+        "--install-types",
+        "--non-interactive",
+        "--show-error-codes",
+        *PYTHON_MODULES,
     )
 
 

diff --git a/pdfminer/cmapdb.py b/pdfminer/cmapdb.py
@@ -481,6 +481,15 @@ def _warn_once(self, msg: str) -> None:
 
 
 def main(argv: List[str]) -> None:
+    from warnings import warn
+
+    warn(
+        "The function main() from cmapdb.py will be removed in 2023. It was probably "
+        "introduced for testing purposes a long time ago, and no longer relevant. "
+        "Feel free to create a GitHub issue if you disagree.",
+        DeprecationWarning,
+    )
+
     args = argv[1:]
     for fname in args:
         fp = open(fname, "rb")

diff --git a/pdfminer/converter.py b/pdfminer/converter.py
@@ -109,7 +109,16 @@ def paint_path(
         """Paint paths described in section 4.4 of the PDF reference manual"""
         shape = "".join(x[0] for x in path)
 
-        if shape.count("m") > 1:
+        if shape[:1] != "m":
+            # Per PDF Reference Section 4.4.1, "path construction operators may
+            # be invoked in any sequence, but the first one invoked must be m
+            # or re to begin a new subpath." Since pdfminer.six already
+            # converts all `re` (rectangle) operators to their equivelent
+            # `mlllh` representation, paths ingested by `.paint_path(...)` that
+            # do not begin with the `m` operator are invalid.
+            pass
+
+        elif shape.count("m") > 1:
             # recurse if there are multiple m's in this shape
             for m in re.finditer(r"m[^m]+", shape):
                 subpath = path[m.start(0): m.end(0)]