This commit is contained in:
Fred Boniface 2024-10-25 21:15:56 +01:00
commit 3c58645eba
5 changed files with 235 additions and 0 deletions

165
.gitignore vendored Normal file
View File

@ -0,0 +1,165 @@
*.pdf
output
# 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/latest/usage/project/#working-with-version-control
.pdm.toml
.pdm-python
.pdm-build/
# 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/

3
README.md Normal file
View File

@ -0,0 +1,3 @@
# dgp2
Parses PDF schedule cards, extracting PIS codes and headcodes before using the OwlBoard API to build a list of PIS codes. Submitting the completed list to Git.

11
main.py Normal file
View File

@ -0,0 +1,11 @@
# Open all PDF files in the working directory.
# Loop through data and remove duplicate codes.
# Check for existing codes via OwlBoard API.
# Validate existing codes and submit issue if not correct.
# Use the train list to search for stopping pattern of any absent codes.
# Format file and commit to git

55
parse_pdf.py Normal file
View File

@ -0,0 +1,55 @@
import PyPDF2
import re
## re Patterns
schedule_pattern = r"(?<=NOTES)(.*?)(?=NOTES|$)" # Split Schedule Cards
train_start_pattern = r"\b\d[A-Z]\d{2}\s+\d{5}\s+\d{2}\.\d{2}(?:\s+\d{2}\.\d{2})?\s+[A-Za-z &]+" # Defines start of train section
train_first_line_pattern = r"(?P<headcode>\d[A-Z]\d{2})\s+(?P<gsmr_code>\d{5})\s+(?P<time0>\d{2}\.\d{2})(?:\s+(?P<time1>\d{2}\.\d{2}))?\s+(?P<location>[A-Za-z0-9& ]+)" # Extracts Train Data
train_pis_line_pattern = r"\(PIS Code\s*:\s*(?P<pis_code>\d+)\s*\)" # Extracts PIS Code
# Extract Schedule Cards to list of strings
def extract_pdf_text(file_path):
with open(file_path, 'rb') as file:
pdf_reader = PyPDF2.PdfReader(file)
page_texts = []
for page in pdf_reader.pages:
text = page.extract_text()
if text:
page_texts.append(text)
full_text = " ".join(page_texts)
return full_text
# Does everything - should be split in to functional functions
def parse_pdf_file(filename):
pdf_text = extract_pdf_text(filename)
schedule_cards = re.findall(schedule_pattern, pdf_text, re.DOTALL)
print(f"{len(schedule_cards)} Schedule Cards parsed")
# Split into individual trains
parsed_schedule_cards = []
for schedule_card in schedule_cards:
train_sections = re.split(f"(?={train_start_pattern})", schedule_cards[0])
train_sections = [section.strip() for section in train_sections if section.strip()]
parsed_schedule_cards.append(train_sections)
# Process data from each individual train
train_data = []
for parsed_schedule_card in parsed_schedule_cards:
for train in parsed_schedule_card:
first_line_match = re.match(train_first_line_pattern, train)
if first_line_match:
train_entry = first_line_match.groupdict()
pis_code_match = re.search(train_pis_line_pattern, train)
train_entry["pis_code"] = pis_code_match.group("pis_code") if pis_code_match else None
train_data.append(train_entry)
return train_data

1
requirements.txt Normal file
View File

@ -0,0 +1 @@
PyPDF2==3.0.1