From 49f51bf5d4032658c5ff35755c98a60ef69ce7a4 Mon Sep 17 00:00:00 2001
From: Bin Yang <bin.yang@algotune.com>
Date: Thu, 18 Mar 2021 21:40:42 -0400
Subject: [PATCH] initial commit on new branch

---
 .gitignore           | 133 +++++++++++++++++++++++++++++++++++++++++++
 conf.py              |   2 +
 git_status.py        |  37 ++++++++++++
 raw_data/__init__.py |   0
 requirements.txt     |   1 +
 5 files changed, 173 insertions(+)
 create mode 100644 .gitignore
 create mode 100644 conf.py
 create mode 100644 git_status.py
 create mode 100644 raw_data/__init__.py
 create mode 100644 requirements.txt

diff --git a/.gitignore b/.gitignore
new file mode 100644
index 00000000..0ff3bae8
--- /dev/null
+++ b/.gitignore
@@ -0,0 +1,133 @@
+# 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/
+pip-wheel-metadata/
+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/
+
+# 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
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+.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
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow
+__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/
+.idea/
+
+.DS_Store
+.editorconfig
diff --git a/conf.py b/conf.py
new file mode 100644
index 00000000..ac75995f
--- /dev/null
+++ b/conf.py
@@ -0,0 +1,2 @@
+import os
+PROJECT_ROOT_DIR = os.path.dirname(os.path.abspath(__file__))
diff --git a/git_status.py b/git_status.py
new file mode 100644
index 00000000..dafc60e9
--- /dev/null
+++ b/git_status.py
@@ -0,0 +1,37 @@
+import os
+from conf import PROJECT_ROOT_DIR
+import re
+
+@DeprecationWarning
+def parse_readme_md():
+    file_path = os.path.join(PROJECT_ROOT_DIR, 'README.md')
+    with open(file_path) as f:
+        lines = f.readlines()[11:] # skip heading
+        for line_num in range(len(lines)):
+            line = lines[line_num]
+            if line.strip().startswith('#'):
+                # find a heading
+                heading = line.strip().replace('#', '').replace('\n', '').strip()
+                # parse until next # or eof
+                parsed_list = []
+                line_num += 1
+                while line_num < len(lines) and not lines[line_num].strip().startswith('#'):
+                    link_line = lines[line_num].replace('\n', '').strip()
+                    print(link_line)
+                    if len(link_line) > 0:
+                        # usually in the format of '- [NAME](link) - comment
+                        split_sections = link_line.split('- ')
+                        if len(split_sections) == 2:
+                            title_and_link = split_sections[1].strip()
+                            title = re.search(r'\[(.*?)\]', title_and_link).group(1)
+                            m_link = re.search(r'\((.*?)\)', title_and_link)
+                            link_str = ''
+                            if m_link is not None:
+                                link_str = m_link.group(1)
+
+                            pass
+                        elif len(split_sections) == 3:
+                            pass
+
+                        print(split_sections)
+                    line_num += 1
diff --git a/raw_data/__init__.py b/raw_data/__init__.py
new file mode 100644
index 00000000..e69de29b
diff --git a/requirements.txt b/requirements.txt
new file mode 100644
index 00000000..d78a3a82
--- /dev/null
+++ b/requirements.txt
@@ -0,0 +1 @@
+pandas==1.2.1
\ No newline at end of file