dir-content-diff 1.11.0__tar.gz → 1.12.1__tar.gz

{dir_content_diff-1.11.0 → dir_content_diff-1.12.1}/.copier-answers.yml

@@ -21,7 +21,7 @@ setup_codeql: false
 ssh_url: git@github.com:BlueBrain/dir-content-diff.git
 team_name: ''
 tracker_url: https://github.com/BlueBrain/dir-content-diff/issues
-use_pyproject_toml: false
+use_pyproject_toml: true
 version: 1.1.0
 
 # End of Copier answers

dir_content_diff-1.12.1/.copyright.tmpl

@@ -0,0 +1,6 @@
+Copyright (c) 2023-${edit_year} Blue Brain Project, EPFL.
+
+This file is part of dir-content-diff.
+See https://github.com/BlueBrain/dir-content-diff for further info.
+
+SPDX-License-Identifier: Apache-2.0

{dir_content_diff-1.11.0 → dir_content_diff-1.12.1}/.github/workflows/run-tox.yml

@@ -6,6 +6,8 @@ on:
     branches:
       - main
   workflow_dispatch:
+  schedule:
+    - cron: "0 2 15 1,7 *"
 
 jobs:
   build:
@@ -30,12 +32,9 @@ jobs:
     - name: Get current month
       id: date
       run: echo "date=$(date +'%Y-%m')" >> $GITHUB_OUTPUT
-    - name: Cache APT Packages
-      uses: awalsh128/cache-apt-pkgs-action@latest
-      with:
-        packages: poppler-utils imagemagick
-        version: 1.0
-        execute_install_scripts: true
+    - name: Install APT Packages
+      run: |
+        sudo apt-get install -y poppler-utils imagemagick
     - name: Cache tox and precommit environments
       uses: actions/cache@v4
       with:
@@ -64,13 +63,23 @@ jobs:
       with:
         report_paths: 'reports/pytest-*.xml'
     - name: Upload to codecov
-      uses: codecov/codecov-action@v4
+      uses: codecov/codecov-action@v5
       with:
         fail_ci_if_error: false
         directory: ./reports
         flags: pytest
         name: "dir-content-diff-py${{ matrix.python-version }}-${{ matrix.min_versions }}"
         token: ${{ secrets.CODECOV_TOKEN }}
+    - name: Upload to codecov results
+      uses: codecov/test-results-action@v1
+      with:
+        fail_ci_if_error: false
+        flags: pytest
+        directory: ./reports
+        name: "dir-content-diff-py${{ matrix.python-version }}-${{ matrix.min_versions }}-test-results"
+        token: ${{ secrets.CODECOV_TOKEN }}
+      env:
+        CODECOV_TOKEN: ${{ secrets.CODECOV_TOKEN }}
     - name: Upload test artifacts
       uses: actions/upload-artifact@v4
       if: always()

{dir_content_diff-1.11.0 → dir_content_diff-1.12.1}/.pre-commit-config.yaml

@@ -1,4 +1,10 @@
 repos:
+  - repo: https://github.com/astral-sh/ruff-pre-commit
+    rev: v0.7.0
+    hooks:
+      - id: ruff
+        args: ["--fix", "--exit-non-zero-on-fix"]
+      - id: ruff-format
   - repo: https://github.com/pre-commit/pre-commit-hooks
     rev: v5.0.0
     hooks:
@@ -21,10 +27,6 @@ repos:
     rev: 5.13.2
     hooks:
       - id: isort
-  - repo: https://github.com/psf/black
-    rev: 24.10.0
-    hooks:
-      - id: black
   - repo: https://github.com/codespell-project/codespell
     rev: v2.3.0
     hooks:
@@ -39,3 +41,13 @@ repos:
     rev: 7.1.1
     hooks:
       - id: flake8
+        additional_dependencies: ['flake8-pyproject']
+  - repo: https://github.com/arkinmodi/add-license-header
+    rev: v2.2.0
+    hooks:
+      - id: add-license-header
+        args:
+            - --unmanaged
+            - --license-file
+            - .copyright.tmpl
+        files: \.py$

{dir_content_diff-1.11.0 → dir_content_diff-1.12.1}/CHANGELOG.md

@@ -1,5 +1,34 @@
 # Changelog
 
+## [1.12.1](https://github.com/BlueBrain/dir-content-diff/compare/1.12.0..1.12.1)
+
+> 3 July 2025
+
+### Fixes
+
+- Properly update the verbosity in PDF comparator (Adrien Berchet - [#75](https://github.com/BlueBrain/dir-content-diff/pull/75))
+
+### CI Improvements
+
+- Schedule CI every 6 months (Adrien Berchet - [#76](https://github.com/BlueBrain/dir-content-diff/pull/76))
+
+## [1.12.0](https://github.com/BlueBrain/dir-content-diff/compare/1.11.0..1.12.0)
+
+> 18 November 2024
+
+### New Features
+
+- Add CLI (Adrien Berchet - [#70](https://github.com/BlueBrain/dir-content-diff/pull/70))
+- Intercept 'tempfile' argument of the PdfComparator to improve it (Adrien Berchet - [#69](https://github.com/BlueBrain/dir-content-diff/pull/69))
+
+### Chores And Housekeeping
+
+- Add license headers, use pyproject.toml file and migrate docs to MyST parser (Adrien Berchet - [#68](https://github.com/BlueBrain/dir-content-diff/pull/68))
+
+### CI Improvements
+
+- Push test results to Codecov (Adrien Berchet - [#73](https://github.com/BlueBrain/dir-content-diff/pull/73))
+
 ## [1.11.0](https://github.com/BlueBrain/dir-content-diff/compare/1.10.0..1.11.0)
 
 > 6 November 2024

{dir_content_diff-1.11.0/dir_content_diff.egg-info → dir_content_diff-1.12.1}/PKG-INFO

@@ -1,12 +1,12 @@
-Metadata-Version: 2.1
+Metadata-Version: 2.4
 Name: dir-content-diff
-Version: 1.11.0
+Version: 1.12.1
 Summary: Simple tool to compare directory contents.
-Home-page: https://dir-content-diff.readthedocs.io
 Author: Blue Brain Project, EPFL
 License: Apache License 2.0
+Project-URL: Homepage, https://dir-content-diff.readthedocs.io
+Project-URL: Repository, https://github.com/BlueBrain/dir-content-diff
 Project-URL: Tracker, https://github.com/BlueBrain/dir-content-diff/issues
-Project-URL: Source, https://github.com/BlueBrain/dir-content-diff
 Classifier: Development Status :: 5 - Production/Stable
 Classifier: Intended Audience :: Developers
 Classifier: License :: OSI Approved :: Apache Software License
@@ -16,15 +16,17 @@ Classifier: Programming Language :: Python :: 3.9
 Classifier: Programming Language :: Python :: 3.10
 Classifier: Programming Language :: Python :: 3.11
 Classifier: Programming Language :: Python :: 3.12
-Classifier: Topic :: Scientific/Engineering :: Bio-Informatics
+Classifier: Topic :: Software Development :: Libraries :: Python Modules
 Requires-Python: >=3.9
 Description-Content-Type: text/markdown
 License-File: LICENSE.txt
 License-File: AUTHORS.md
+Requires-Dist: click>=8
 Requires-Dist: dictdiffer>=0.8
 Requires-Dist: dicttoxml>=1.7.12
 Requires-Dist: diff_pdf_visually>=1.7
 Requires-Dist: jsonpath-ng>=1.5
+Requires-Dist: packaging>=20
 Requires-Dist: PyYaml>=6
 Provides-Extra: all-comparators
 Requires-Dist: pandas>=1.4; extra == "all-comparators"
@@ -33,19 +35,20 @@ Requires-Dist: tables>=3.7; extra == "all-comparators"
 Requires-Dist: morphio>=3.3.6; extra == "all-comparators"
 Requires-Dist: morph_tool>=2.9; extra == "all-comparators"
 Requires-Dist: voxcell>=3.1.1; extra == "all-comparators"
+Requires-Dist: pynrrd<1.1,>=0.4; extra == "all-comparators"
 Provides-Extra: docs
-Requires-Dist: docutils<0.21; extra == "docs"
-Requires-Dist: m2r2; extra == "docs"
+Requires-Dist: myst_parser; extra == "docs"
 Requires-Dist: sphinx; extra == "docs"
 Requires-Dist: sphinx-bluebrain-theme; extra == "docs"
 Provides-Extra: test
-Requires-Dist: coverage>=7.2; extra == "test"
 Requires-Dist: dicttoxml>=1.7.16; extra == "test"
 Requires-Dist: matplotlib>=3.4; extra == "test"
 Requires-Dist: rst2pdf>=0.99; extra == "test"
-Requires-Dist: packaging>=20; extra == "test"
 Requires-Dist: pandas>=1.4; extra == "test"
 Requires-Dist: pytest>=6.2; extra == "test"
+Requires-Dist: pytest-click>=1.1; extra == "test"
+Requires-Dist: pytest-console-scripts>=1.4; extra == "test"
+Requires-Dist: pytest-cov>=4.1; extra == "test"
 Requires-Dist: pytest-html>=3.2; extra == "test"
 Provides-Extra: pandas
 Requires-Dist: pandas>=1.4; extra == "pandas"
@@ -56,6 +59,9 @@ Requires-Dist: morphio>=3.3.6; extra == "morphio"
 Requires-Dist: morph_tool>=2.9; extra == "morphio"
 Provides-Extra: voxcell
 Requires-Dist: voxcell>=3.1.1; extra == "voxcell"
+Requires-Dist: pynrrd<1.1,>=0.4; extra == "voxcell"
+Dynamic: license-file
+Dynamic: provides-extra
 
 [![Version](https://img.shields.io/pypi/v/dir-content-diff)](https://github.com/BlueBrain/dir-content-diff/releases)
 [![Build status](https://github.com/BlueBrain/dir-content-diff/actions/workflows/run-tox.yml/badge.svg?branch=main)](https://github.com/BlueBrain/dir-content-diff/actions)

{dir_content_diff-1.11.0 → dir_content_diff-1.12.1}/dir_content_diff/__init__.py

@@ -3,11 +3,21 @@
 Simple tool to compare directory contents.
 """
 
+# LICENSE HEADER MANAGED BY add-license-header
+# Copyright (c) 2023-2025 Blue Brain Project, EPFL.
+#
+# This file is part of dir-content-diff.
+# See https://github.com/BlueBrain/dir-content-diff for further info.
+#
+# SPDX-License-Identifier: Apache-2.0
+# LICENSE HEADER MANAGED BY add-license-header
+
 import copy
 import importlib.metadata
 import re
 from pathlib import Path
 
+from dir_content_diff.base_comparators import BaseComparator
 from dir_content_diff.base_comparators import DefaultComparator
 from dir_content_diff.base_comparators import IniComparator
 from dir_content_diff.base_comparators import JsonComparator
@@ -20,7 +30,6 @@ from dir_content_diff.util import format_ext
 
 __version__ = importlib.metadata.version("dir-content-diff")
 
-
 _DEFAULT_COMPARATORS = {
     None: DefaultComparator(),
     ".cfg": IniComparator(),  # luigi config files
@@ -106,7 +115,9 @@ def unregister_comparator(ext, quiet=False):
     return _COMPARATORS.pop(ext, None)
 
 
-def compare_files(ref_file, comp_file, comparator, *args, return_raw_diffs=False, **kwargs):
+def compare_files(
+    ref_file, comp_file, comparator, *args, return_raw_diffs=False, **kwargs
+):
     """Compare 2 files and return the difference.
 
     Args:
@@ -127,7 +138,9 @@ def compare_files(ref_file, comp_file, comparator, *args, return_raw_diffs=False
     LOGGER.debug("Compare: %s and %s", ref_file, comp_file)
 
     try:
-        return comparator(ref_file, comp_file, *args, return_raw_diffs=return_raw_diffs, **kwargs)
+        return comparator(
+            ref_file, comp_file, *args, return_raw_diffs=return_raw_diffs, **kwargs
+        )
     except Exception as exception:  # pylint: disable=broad-except
         load_kwargs = kwargs.pop("load_kwargs", None)
         format_data_kwargs = kwargs.pop("format_data_kwargs", None)
@@ -139,7 +152,9 @@ def compare_files(ref_file, comp_file, comparator, *args, return_raw_diffs=False
         try:
             exception_args = "\n".join(str(i) for i in exception.args)
         except Exception:  # pylint: disable=broad-exception-caught
-            exception_args = "UNKNOWN ERROR: Could not get information from the exception"
+            exception_args = (
+                "UNKNOWN ERROR: Could not get information from the exception"
+            )
         exc_type = type(exception).__name__
         return diff_msg_formatter(
             ref_file,
@@ -209,9 +224,32 @@ def export_formatted_file(file, formatted_file, comparator, **kwargs):
             ),
         )
     else:
-        LOGGER.info(
-            "Skip formatting for '%s' because the comparator has no saving capability.", file
+        LOGGER.debug(
+            "Skip formatting for '%s' because the comparator has no saving capability.",
+            file,
+        )
+
+
+def pick_comparator(comparator=None, suffix=None, comparators=None):
+    """Pick a comparator based on its name or a file suffix."""
+    if isinstance(comparator, BaseComparator):
+        return comparator
+    if comparators is None:
+        comparators = get_comparators()
+    if comparator is not None:
+        for i in comparators.values():  # pragma: no branch
+            if i.__class__.__name__ == comparator:
+                return i
+        LOGGER.debug(
+            "Could not find the comparator named '%s' in the given comparators",
+            comparator,
         )
+    if suffix is not None:
+        if suffix in comparators:
+            return comparators.get(suffix)
+        LOGGER.debug("Could not find the comparator for the '%s' suffix", suffix)
+    LOGGER.debug("Returning the default comparator")
+    return _COMPARATORS.get(None)
 
 
 def compare_trees(
@@ -274,9 +312,6 @@ def compare_trees(
         difference messages. If the directories are considered as equal, an empty ``dict`` is
         returned.
     """
-    if comparators is None:
-        comparators = _COMPARATORS
-
     ref_path = Path(ref_path)
     comp_path = Path(comp_path)
     formatted_data_path = comp_path.with_name(
@@ -316,12 +351,10 @@ def compare_trees(
                         break
             if specific_file_args is None:
                 specific_file_args = {}
-            comparator = specific_file_args.pop(
-                "comparator",
-                comparators.get(
-                    ref_file.suffix,
-                    _COMPARATORS.get(None),
-                ),
+            comparator = pick_comparator(
+                comparator=specific_file_args.pop("comparator", None),
+                suffix=ref_file.suffix,
+                comparators=comparators,
             )
             comparator_args = specific_file_args.pop("args", [])
             res = compare_files(
@@ -376,7 +409,9 @@ def assert_equal_trees(*args, export_formatted_files=False, **kwargs):
         if export_formatted_files is True and assert_equal_trees._pytest_export_suffix:
             export_formatted_files = assert_equal_trees._pytest_export_suffix
 
-    different_files = compare_trees(*args, export_formatted_files=export_formatted_files, **kwargs)
+    different_files = compare_trees(
+        *args, export_formatted_files=export_formatted_files, **kwargs
+    )
 
     # Sort the files according to their relative paths
     sorted_items = sorted(different_files.items(), key=lambda x: x[0])

{dir_content_diff-1.11.0 → dir_content_diff-1.12.1}/dir_content_diff/base_comparators.py

@@ -1,18 +1,29 @@
 """Module containing the base comparators."""
 
+# LICENSE HEADER MANAGED BY add-license-header
+# Copyright (c) 2023-2025 Blue Brain Project, EPFL.
+#
+# This file is part of dir-content-diff.
+# See https://github.com/BlueBrain/dir-content-diff for further info.
+#
+# SPDX-License-Identifier: Apache-2.0
+# LICENSE HEADER MANAGED BY add-license-header
+
 import configparser
 import filecmp
 import json
 import re
 from abc import ABC
 from abc import abstractmethod
+from pathlib import Path
 from xml.etree import ElementTree
 
 import dictdiffer
+import diff_pdf_visually
 import jsonpath_ng
 import yaml
 from dicttoxml import dicttoxml
-from diff_pdf_visually import pdf_similar
+from diff_pdf_visually import pdfdiff_pages
 
 from dir_content_diff.util import diff_msg_formatter
 
@@ -222,7 +233,10 @@ class BaseComparator(ABC):
             if hasattr(filtered_diffs, "items"):
                 formatted_diffs = self.concatenate(
                     self.sort(
-                        [self.format_diff(i, **format_diff_kwargs) for i in filtered_diffs.items()],
+                        [
+                            self.format_diff(i, **format_diff_kwargs)
+                            for i in filtered_diffs.items()
+                        ],
                         **sort_kwargs,
                     ),
                     **concat_kwargs,
@@ -230,7 +244,10 @@ class BaseComparator(ABC):
             else:
                 formatted_diffs = self.concatenate(
                     self.sort(
-                        [self.format_diff(i, **format_diff_kwargs) for i in filtered_diffs],
+                        [
+                            self.format_diff(i, **format_diff_kwargs)
+                            for i in filtered_diffs
+                        ],
                         **sort_kwargs,
                     ),
                     **concat_kwargs,
@@ -254,7 +271,10 @@ class BaseComparator(ABC):
 
     def __eq__(self, other):
         """Compare 2 :class:`dir_content_diff.base_comparators.BaseComparator` instances."""
-        if type(self) is not type(other) or self.__dict__.keys() != other.__dict__.keys():
+        if (
+            type(self) is not type(other)
+            or self.__dict__.keys() != other.__dict__.keys()
+        ):
             return False
 
         for k, v in self.__dict__.items():
@@ -363,7 +383,8 @@ class DictComparator(BaseComparator):
                         for i in path.find(data):
                             if isinstance(i.value, str):
                                 i.full_path.update(
-                                    data, re.sub(pattern, new_value, i.value, count, flags)
+                                    data,
+                                    re.sub(pattern, new_value, i.value, count, flags),
                                 )
         return data
 
@@ -510,7 +531,13 @@ class XmlComparator(DictComparator):
     def add_to_output(obj, child):
         """Add entry from :class:`xml.etree.ElementTree.Element` object into the given object."""
         if isinstance(obj, dict):
-            obj.update({child.tag: XmlComparator._cast_from_attribute(child.text, child.attrib)})
+            obj.update(
+                {
+                    child.tag: XmlComparator._cast_from_attribute(
+                        child.text, child.attrib
+                    )
+                }
+            )
             for sub in child:
                 XmlComparator.add_to_output(obj[child.tag], sub)
         elif isinstance(obj, list):
@@ -592,7 +619,8 @@ class PdfComparator(BaseComparator):
 
         Keyword Args:
             threshold (int): The threshold used to compare the images.
-            tempdir (pathlib.Path): Empty directory where the temporary images will be exported.
+            tempdir (pathlib.Path): Directory in which a new ``dir-diff`` directory will be created
+                to export the debug images.
             dpi (int): The resolution used to convert the PDF files into images.
             verbosity (int): The log verbosity.
             max_report_pagenos (int): Only this number of the different pages will be logged (only
@@ -600,4 +628,98 @@ class PdfComparator(BaseComparator):
             num_threads (int): If set to 2 (the default), the image conversion are processed in
                 parallel. If set to 1 it is processed sequentially.
         """
-        return not pdf_similar(ref, comp, *args, **kwargs)
+        res = pdfdiff_pages(ref, comp, *args, **kwargs)
+        if not res:
+            return False
+        return res
+
+    def __call__(self, ref_file, comp_file, *args, **kwargs):
+        """Process arguments before calling the diff method."""
+        tempdir = kwargs.pop("tempdir", None)
+        if tempdir is not None:
+            relative_parts = []
+            for i, j in zip(
+                ref_file.parts[::-1], comp_file.parts[::-1]
+            ):  # pragma: no branch
+                if i != j:
+                    break
+                relative_parts.append(i)
+            if relative_parts and relative_parts[-1] == Path(tempdir).root:
+                relative_parts.pop()
+            if not relative_parts:
+                relative_parts.append(comp_file.name)
+            relative_parts.append("diff-pdf")
+            new_tempdir = Path(tempdir) / Path(*relative_parts[::-1])
+
+            # Deduplicate name if needed
+            last_part = str(relative_parts[-1])
+            num = 1
+            while True:
+                root = Path(tempdir) / relative_parts[-1]
+                if not root.exists():
+                    new_tempdir.mkdir(parents=True, exist_ok=False)
+                    break
+                relative_parts[-1] = last_part + f"_{num}"
+                new_tempdir = Path(tempdir) / Path(*relative_parts[::-1])
+                num += 1
+
+            kwargs["tempdir"] = new_tempdir
+
+        # Update default verbosity
+        current_default_verbosity = diff_pdf_visually.constants.DEFAULT_VERBOSITY
+        try:
+            if "verbosity" not in kwargs:  # pragma: no branch
+                if (
+                    diff_pdf_visually.diff.pdfdiff_pages.__defaults__[1] is None
+                ):  # pragma: no cover
+                    diff_pdf_visually.constants.DEFAULT_VERBOSITY = 0
+                else:
+                    kwargs["verbosity"] = 0  # pragma: no cover
+            return super().__call__(ref_file, comp_file, *args, **kwargs)
+        finally:
+            diff_pdf_visually.constants.DEFAULT_VERBOSITY = current_default_verbosity
+
+    def report(
+        self,
+        ref_file,
+        comp_file,
+        formatted_differences,
+        diff_args,
+        diff_kwargs,
+        load_kwargs=None,
+        format_data_kwargs=None,
+        filter_kwargs=None,
+        format_diff_kwargs=None,
+        sort_kwargs=None,
+        concat_kwargs=None,
+        **kwargs,
+    ):  # pylint: disable=too-many-arguments
+        """Add specific information before calling the default method."""
+        if formatted_differences and isinstance(formatted_differences, str):
+            formatted_differences = (
+                "The following pages are the most different: "
+                + formatted_differences.replace("\n", ", ")
+            )
+            if "tempdir" in diff_kwargs:
+                formatted_differences += (
+                    "\nThe visual differences can be found here: "
+                    + str(diff_kwargs["tempdir"])
+                )
+        return super().report(
+            ref_file,
+            comp_file,
+            formatted_differences,
+            diff_args,
+            diff_kwargs,
+            load_kwargs=load_kwargs,
+            format_data_kwargs=format_data_kwargs,
+            filter_kwargs=filter_kwargs,
+            format_diff_kwargs=format_diff_kwargs,
+            sort_kwargs=sort_kwargs,
+            concat_kwargs=concat_kwargs,
+            **kwargs,
+        )
+
+    def format_diff(self, difference, **kwargs):
+        """Format one element difference."""
+        return str(difference)