initial commit

.gitignore

@@ -0,0 +1,290 @@
+# Created by https://www.toptal.com/developers/gitignore/api/pycharm,python
+# Edit at https://www.toptal.com/developers/gitignore?templates=pycharm,python
+
+### PyCharm ###
+# Covers JetBrains IDEs: IntelliJ, RubyMine, PhpStorm, AppCode, PyCharm, CLion, Android Studio, WebStorm and Rider
+# Reference: https://intellij-support.jetbrains.com/hc/en-us/articles/206544839
+
+# User-specific stuff
+.idea/**/workspace.xml
+.idea/**/tasks.xml
+.idea/**/usage.statistics.xml
+.idea/**/dictionaries
+.idea/**/shelf
+
+# AWS User-specific
+.idea/**/aws.xml
+
+# Generated files
+.idea/**/contentModel.xml
+
+# Sensitive or high-churn files
+.idea/**/dataSources/
+.idea/**/dataSources.ids
+.idea/**/dataSources.local.xml
+.idea/**/sqlDataSources.xml
+.idea/**/dynamic.xml
+.idea/**/uiDesigner.xml
+.idea/**/dbnavigator.xml
+
+# Gradle
+.idea/**/gradle.xml
+.idea/**/libraries
+
+# Gradle and Maven with auto-import
+# When using Gradle or Maven with auto-import, you should exclude module files,
+# since they will be recreated, and may cause churn.  Uncomment if using
+# auto-import.
+# .idea/artifacts
+# .idea/compiler.xml
+# .idea/jarRepositories.xml
+# .idea/modules.xml
+# .idea/*.iml
+# .idea/modules
+# *.iml
+# *.ipr
+
+# CMake
+cmake-build-*/
+
+# Mongo Explorer plugin
+.idea/**/mongoSettings.xml
+
+# File-based project format
+*.iws
+
+# IntelliJ
+out/
+
+# mpeltonen/sbt-idea plugin
+.idea_modules/
+
+# JIRA plugin
+atlassian-ide-plugin.xml
+
+# Cursive Clojure plugin
+.idea/replstate.xml
+
+# SonarLint plugin
+.idea/sonarlint/
+
+# Crashlytics plugin (for Android Studio and IntelliJ)
+com_crashlytics_export_strings.xml
+crashlytics.properties
+crashlytics-build.properties
+fabric.properties
+
+# Editor-based Rest Client
+.idea/httpRequests
+
+# Android studio 3.1+ serialized cache file
+.idea/caches/build_file_checksums.ser
+
+### PyCharm Patch ###
+# Comment Reason: https://github.com/joeblau/gitignore.io/issues/186#issuecomment-215987721
+
+# *.iml
+# modules.xml
+# .idea/misc.xml
+# *.ipr
+
+# Sonarlint plugin
+# https://plugins.jetbrains.com/plugin/7973-sonarlint
+.idea/**/sonarlint/
+
+# SonarQube Plugin
+# https://plugins.jetbrains.com/plugin/7238-sonarqube-community-plugin
+.idea/**/sonarIssues.xml
+
+# Markdown Navigator plugin
+# https://plugins.jetbrains.com/plugin/7896-markdown-navigator-enhanced
+.idea/**/markdown-navigator.xml
+.idea/**/markdown-navigator-enh.xml
+.idea/**/markdown-navigator/
+
+# Cache file creation bug
+# See https://youtrack.jetbrains.com/issue/JBR-2257
+.idea/$CACHE_FILE$
+
+# CodeStream plugin
+# https://plugins.jetbrains.com/plugin/12206-codestream
+.idea/codestream.xml
+
+# Azure Toolkit for IntelliJ plugin
+# https://plugins.jetbrains.com/plugin/8053-azure-toolkit-for-intellij
+.idea/**/azureSettings.xml
+
+### Python ###
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+cover/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+# .python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# poetry
+#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
+#poetry.lock
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#pdm.lock
+#   pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
+#   in version control.
+#   https://pdm.fming.dev/#use-with-ide
+.pdm.toml
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+# PyCharm
+#  JetBrains specific template is maintained in a separate JetBrains.gitignore that can
+#  be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
+#  and can be added to the global gitignore or merged into this file.  For a more nuclear
+#  option (not recommended) you can uncomment the following to ignore the entire idea folder.
+#.idea/
+
+### Python Patch ###
+# Poetry local configuration file - https://python-poetry.org/docs/configuration/#local-configuration
+poetry.toml
+
+# ruff
+.ruff_cache/
+
+# LSP config files
+pyrightconfig.json
+.my_test_data
+my_test_data/
+# End of https://www.toptal.com/developers/gitignore/api/pycharm,python

.idea/.gitignore

@@ -0,0 +1,8 @@
+# Default ignored files
+/shelf/
+/workspace.xml
+# Editor-based HTTP Client requests
+/httpRequests/
+# Datasource local storage ignored files
+/dataSources/
+/dataSources.local.xml

.idea/inspectionProfiles/profiles_settings.xml

@@ -0,0 +1,6 @@
+<component name="InspectionProjectProfileManager">
+  <settings>
+    <option name="USE_PROJECT_PROFILE" value="false" />
+    <version value="1.0" />
+  </settings>
+</component>

.idea/jekyll-to-hugo.iml

@@ -0,0 +1,10 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<module type="PYTHON_MODULE" version="4">
+  <component name="NewModuleRootManager">
+    <content url="file://$MODULE_DIR$">
+      <excludeFolder url="file://$MODULE_DIR$/venv" />
+    </content>
+    <orderEntry type="jdk" jdkName="Python 3.11 (jekyll-to-hugo)" jdkType="Python SDK" />
+    <orderEntry type="sourceFolder" forTests="false" />
+  </component>
+</module>

.idea/misc.xml

@@ -0,0 +1,4 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<project version="4">
+  <component name="ProjectRootManager" version="2" project-jdk-name="Python 3.11 (jekyll-to-hugo)" project-jdk-type="Python SDK" />
+</project>

.idea/modules.xml

@@ -0,0 +1,8 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<project version="4">
+  <component name="ProjectModuleManager">
+    <modules>
+      <module fileurl="file://$PROJECT_DIR$/.idea/jekyll-to-hugo.iml" filepath="$PROJECT_DIR$/.idea/jekyll-to-hugo.iml" />
+    </modules>
+  </component>
+</project>

.idea/vcs.xml

@@ -0,0 +1,6 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<project version="4">
+  <component name="VcsDirectoryMappings">
+    <mapping directory="" vcs="Git" />
+  </component>
+</project>

Makefile

@@ -0,0 +1,6 @@
+# Formats the code
+format:
+	black . && isort -r .
+# Run tests
+test:
+	pytest .

app/converter/__init__.py

@@ -0,0 +1,2 @@
+from converter import Converter
+from wordpress_markdown import WordpressMarkdownConverter

app/converter/converter.py

@@ -0,0 +1,45 @@
+import os
+from pathlib import Path
+
+from app import utils
+from app.converter.wordpress_markdown import WordpressMarkdownConverter
+
+
+class Converter:
+    """
+    Convert Jekyll posts to Hugo posts
+    """
+
+    def __init__(self, jekyll_posts_path: str, hugo_posts_path: str):
+        """
+        Initializes the converter
+
+        Parameters
+        ----------
+        jekyll_posts_path : str
+            The path to the Jekyll posts
+        hugo_posts_path : str
+            The path to the Hugo posts
+        """
+        utils.guard_against_none_or_empty_str(jekyll_posts_path, "jekyll_posts_path")
+        utils.guard_against_none_or_empty_str(hugo_posts_path, "hugo_posts_path")
+
+        self._jekyll_posts_path = jekyll_posts_path
+        self._hugo_posts_path = hugo_posts_path
+
+        # The converter that converts the markdown
+        self.markdown_converter = WordpressMarkdownConverter()
+
+    def convert(self):
+        """
+        Converts the Jekyll posts to Hugo posts
+        """
+        source_path = self._jekyll_posts_path
+        output_path = Path(self._hugo_posts_path)
+        _, _, files = next(os.walk(source_path))
+        for file in files:
+            source_abs_path = source_path / Path(file)
+            self.markdown_converter.convert_jekyll_to_hugo(
+                source_abs_path,
+                output_path,
+            )

app/converter/wordpress_markdown.py

@@ -0,0 +1,145 @@
+from pathlib import Path
+
+import yaml
+from bs4 import BeautifulSoup, Tag
+
+from app.utils import key_error_silence
+
+
+class WordpressMarkdownConverter:
+    """
+    Markdown converter that converts jekyll posts to hugo posts.
+    """
+
+    def fix_hugo_header(self, header: dict) -> dict:
+        """
+        Fix the Hugo header
+
+        Parameters
+        ----------
+        header : dict
+            The header to fix
+
+        Returns
+        -------
+        dict
+            The fixed header
+        """
+        with key_error_silence():
+            del header["restapi_import_id"]
+        with key_error_silence():
+            del header["original_post_id"]
+        with key_error_silence():
+            del header["timeline_notification"]
+        with key_error_silence():
+            del header["wordads_ufa"]
+        header["guid"] = header["guid"].replace("http://localhost", "")
+        header["author"] = "Denis Nuțiu"
+        return header
+
+    def remove_html_tags(self, post_lines):
+        fixed_lines = []
+        for line in post_lines:
+            if line == "":
+                fixed_lines.append("\n")
+                continue
+            soup = BeautifulSoup(line)
+            for content in soup.contents:
+                if isinstance(content, Tag):
+                    if "is-provider-youtube" in content.attrs.get("class", []):
+                        video_link = content.findNext("iframe").attrs["src"]
+                        video_id_part = video_link.rsplit("/")
+                        video_id = video_id_part[-1].split("?")[0]
+                        fixed_lines.append(f"{{{{< youtube {video_id} >}}}}\n")
+                    else:
+                        tags = list(map(str, content.contents))
+                        if tags:
+                            fixed_tags = self.remove_html_tags(tags)
+                            if fixed_tags:
+                                fixed_lines.extend(fixed_tags)
+                else:
+                    fixed_lines.append(str(content))
+        return fixed_lines
+
+    def convert_post_content(self, post_content: str) -> str:
+        """
+        Converts the post content
+
+        Parameters
+        ----------
+        post_content : str
+            The post content
+
+        Returns
+        -------
+        str
+            The converted post content
+        """
+        # fix  link
+        post_content = post_content.replace("http://localhost/", "/")
+        post_content = post_content.replace(
+            "https://nuculabs.wordpress.com/", "https://nuculabs.dev/posts/"
+        )
+        # fix unknown tags
+        post_lines = post_content.split("\n")
+        fixed_lines = self.remove_html_tags(post_lines)
+
+        return "\n".join(fixed_lines)
+
+    def read_jekyll_post(self, path: Path):
+        """
+        Read a Jekyll post from the specified path
+
+        Parameters
+        ----------
+        path : Path
+            The path to the Jekyll post
+        """
+        # read source
+        with open(path, "r") as fh:
+            contents = fh.read()
+        return contents
+
+    def write_hugo_post(self, output_path, post_header: dict, post_content: str):
+        """
+        Write a Hugo post to the specified path
+
+        Parameters
+        ----------
+        output_path : Path
+            The path to the Hugo post
+        post_header : dict
+            The post header
+        post_content : str
+            The post content
+        """
+        with open(output_path, "w") as fo:
+            header = ["---\n", yaml.dump(post_header), "---\n"]
+            fo.writelines(header)
+            fo.write(post_content)
+
+    def convert_jekyll_to_hugo(self, jekyll_post_path: Path, hugo_post_output: Path):
+        """
+        Convert a Jekyll post to a Hugo post
+
+        Parameters
+        ----------
+        jekyll_post_path : Path
+            The path to the Jekyll post
+        hugo_post_output : Path
+            The path to the Hugo post
+        """
+        contents = self.read_jekyll_post(jekyll_post_path)
+
+        # fix header
+        header = yaml.safe_load(contents.split("---")[1])
+        fixed_header = self.fix_hugo_header(header)
+        # fix content
+        post_content = contents.split("---", 2)[2].lstrip()
+        fixed_post_content = self.convert_post_content(post_content)
+
+        self.write_hugo_post(
+            hugo_post_output.joinpath(jekyll_post_path.name),
+            fixed_header,
+            fixed_post_content,
+        )

app/tests/utils_test.py

@@ -0,0 +1,35 @@
+import pytest
+
+from app.utils import key_error_silence, guard_against_none_or_empty_str
+
+
+def test_key_error_silence():
+    # Test that the context manager silences the exception
+    with key_error_silence():
+        raise KeyError
+    # Test that the context manager does not silence other exceptions
+    with pytest.raises(ValueError):
+        with key_error_silence():
+            raise ValueError
+
+
+@pytest.mark.parametrize(
+    "input_data",
+    [
+        (""),
+        (None),
+        (1),
+        (True),
+        (False),
+        ({}),
+        ([]),
+        ({"a": 1}),
+    ],
+)
+def test_guard_against_none_or_empty_str(input_data):
+    with pytest.raises(ValueError):
+        guard_against_none_or_empty_str(input_data, "test")
+
+
+def test_guard_against_none_or_empty_str_happy():
+    guard_against_none_or_empty_str("a", "test")

app/utils.py

@@ -0,0 +1,28 @@
+import contextlib
+
+
+@contextlib.contextmanager
+def key_error_silence():
+    """
+    Context manager that silences key errors exceptions.
+    """
+    try:
+        yield
+    except KeyError:
+        pass
+
+
+def guard_against_none_or_empty_str(value: str, name: str):
+    """
+    Guard against None or empty string.
+
+    Parameters:
+    ----------
+    value: str
+        The value to check.
+    name: str
+        The name of the value.
+    """
+
+    if value is None or not isinstance(value, str) or value == "":
+        raise ValueError(f"{name} cannot be None or empty")

main.py

@@ -0,0 +1,29 @@
+import logging
+import sys
+
+from app.converter import Converter
+
+
+def main():
+    # Logging configuration
+    logging.basicConfig(
+        format="%(asctime)s %(process)d %(levelname)s %(message)s",
+        level=logging.INFO,
+        datefmt="%Y-%m-%d %H:%M:%S",
+    )
+    logger = logging.getLogger(__name__)
+
+    if len(sys.argv) != 3:
+        logger.error(
+            "Usage: python main.py <source path to jekyll posts> <output path to hugo posts>"
+        )
+        sys.exit(1)
+
+    # Converter
+    converter = Converter(sys.argv[1], sys.argv[2])
+    converter.convert()
+
+
+# Press the green button in the gutter to run the script.
+if __name__ == "__main__":
+    main()

readme.md

@@ -0,0 +1,15 @@
+# Jekyll to Hugo Converter
+
+Jekyll to Hugo Converter is a simple tool to convert Jekyll posts to Hugo posts.
+
+You can also use it to convert your WordPress blog into a Hugo blog. Tutorial coming soon.
+
+## Usage
+
+```bash
+pip install -r requirements.txt
+python3 jekyll-to-hugo.py <jekyll_post_path> <hugo_post_path>
+```
+
+---
+Made with ❤️ by [NucuLabs.dev](https://nuculabs.dev)

requirements-dev.txt

@@ -0,0 +1,2 @@
+black==23.3.0
+pdoc==13.1.1

requirements-test.txt

@@ -0,0 +1 @@
+pytest==7.3.1

requirements.txt

@@ -0,0 +1,3 @@
+beautifulsoup4==4.12.2
+PyYAML==6.0
+soupsieve==2.4.1