{
  "corpus": "bronte-charlotte-v1",
  "built_at": "2026-09-10",
  "source": "Project Gutenberg (public domain)",
  "normalisation": "no-break space -> space; `--` -> em dash; straight quotes -> curly, paired per paragraph. Decided from the survey: Shirley was transcribed with straight quotes and zero em-dashes while Jane Eyre and Villette use curly and em-dash, a transcriber split rather than the author's punctuation.",
  "works": [
    {
      "slug": "jane-eyre",
      "gutenberg_id": 1260,
      "title": "Jane Eyre: An Autobiography",
      "chapters": 38,
      "words": 184452,
      "chars": 1022193,
      "path": "works/jane-eyre.jsonl"
    },
    {
      "slug": "villette",
      "gutenberg_id": 9182,
      "title": "Villette",
      "chapters": 42,
      "words": 192411,
      "chars": 1092741,
      "path": "works/villette.jsonl"
    },
    {
      "slug": "shirley",
      "gutenberg_id": 30486,
      "title": "Shirley",
      "chapters": 37,
      "words": 216016,
      "chars": 1226278,
      "path": "works/shirley.jsonl"
    },
    {
      "slug": "the-professor",
      "gutenberg_id": 1028,
      "title": "The Professor",
      "chapters": 25,
      "words": 87412,
      "chars": 500054,
      "path": "works/the-professor.jsonl"
    }
  ],
  "total_words": 680291,
  "total_chapters": 142
}