sample_config.yml

# Copyright (c) 2024-2025, Center for Digital Humanities, Princeton University
# SPDX-License-Identifier: Apache-2.0

# corppa configuration
# copy this file to corppa_config.yml and edit as needed

# to compile found poems v0.5 dataset, copy the following
# from tigerdata prosody project under poetry-detection/2026-05-foundpoems-v0.5/
#.     ref-corpora/
#      ppa-corpus_2026-01-07/
#.     excerpt-data/
# Copy to a local directory, preserving relative paths. Set that local directory
# as your top-level base_dir below.

# top-level path for excerpt dataset ingredients
base_dir: data/tigerdata-foundpoems-v0.5/

# local path to compiled poem dataset files
compiled_dataset_dir: /path/to/ppa-found-poems/data/

# source excerpt data; relative to base_dir unless absolute
excerpt_data_dir: excerpt-data

# PPA full-text corpus and metadata; relative to base_dir unless absolute
ppa_corpus:
  base_dir: ppa_corpus_20XX-XX-XX/

# poem cluster ids
# poem_clusters_path: https://

# paths to reference corpora metadata and text
reference_corpora:
  # default base_dir is data_ingredients_dir / ref-corpora
  # uncomment to override; assumed relative to base_dir if not absolute
  # base_dir: ref-corpora/

  # Paths for individual corpora are assumed relative to reference_corpora.base_dir
  # unless absolute; uncomment to override.
  # text_path can be a tar.gz directory of text files or expanded directory.

  internet_poems:
    # base_dir: internet_poems
    # text_path: internet_poems_texts.tar.gz
    # metadata_path: internet-poems-metadata.csv

  chadwyck-healey:
    # base_dir: chadwyck-healey
    # text_path: "chadwyck-healey/chadwyck-healey_texts.tar.gz"
    # metadata_path: "chadwyck-healey/chadwyck-healey.csv"
  other:
    # URL or local path to "Other Poems" metadata
    # Use a URL if you want to pull directly from google sheets as CSV or
    metadata_path: "https://docs.google.com/spreadsheets/d/..."  # or "/path/to/other.csv"