What Are the Supported Languages for Chapter Detection in book-to-skill?

book-to-skill supports chapter detection in seven natural languages: English, French, German, Spanish, Italian, Dutch, plus an abbreviated form (ch.), through language-specific keyword matching in its core regex.

The book-to-skill library extracts structured content from books by identifying chapter boundaries automatically. Understanding which languages the chapter detection supports helps users determine if their documents will be parsed correctly without manual preprocessing. According to the virgiliojr94/book-to-skill source code, the detection system recognizes diverse linguistic conventions through a carefully crafted regular expression.

How Chapter Detection Works in book-to-skill

The chapter detection logic resides in book_to_skill/utils.py at line 109. The implementation uses a regex-based approach that matches language-specific chapter keywords regardless of case or formatting variants.

The detection captures:

• Full chapter keywords in multiple languages
• Abbreviated forms (ch. or ch)
• Associated chapter numbers (Arabic numerals, Roman numerals, or other numeral systems)

Detecting Structure with detect_structure

The primary entry point for chapter detection is the detect_structure() function in utils.py. This function processes raw text and returns identified structural elements including chapters.

Complete List of Supported Languages for Chapter Detection

Language	Keyword Matched	Notes
English	chapter	Standard form
French	chapitre	Common in French-language publications
German	kapitel	Used in German academic and trade books
Spanish	capítulo	Regex pattern cap[ií]tulo handles both capitulo and capítulo with accented í
Italian	capitolo	Standard Italian chapter designation
Dutch	hoofdstuk	Used in Dutch and Flemish books
Abbreviation	ch. / ch	Universal shorthand across languages

These keywords trigger chapter detection whether they appear as standalone headings or embedded in longer text sequences.

Code Examples: Chapter Detection in Practice

Basic Chapter Detection

from book_to_skill.utils import detect_structure

# English chapter heading

text_en = "# Chapter 3\nContent of the third chapter."

print(detect_structure(text_en))

# → detects chapter 3

German Language Detection

from book_to_skill.utils import detect_structure

text_de = "# Kapitel 5\nInhalt des fünften Kapitels."

print(detect_structure(text_de))

# → detects chapter 5

Spanish with Accented Character

from book_to_skill.utils import detect_structure

text_es = "# Capítulo 2\nContenido del segundo capítulo."

print(detect_structure(text_es))

# → detects chapter 2

Abbreviated Chapter Form

from book_to_skill.utils import detect_structure

text_abbr = "# Ch. 7\nSome content."

print(detect_structure(text_abbr))

# → detects chapter 7

Where Chapter Detection Is Used

The supported languages for chapter detection power multiple components throughout the book-to-skill codebase:

• book_to_skill/utils.py — Contains the core regex and detect_structure() helper
• book_to_skill/parsers/text.py — Applies detection when processing plain-text book files
• tools/discovery_tax.py — Invokes split_chapters(), which relies on the same language-aware detection rules

Summary

• Seven language variants are supported for chapter detection: English (chapter), French (chapitre), German (kapitel), Spanish (capítulo/capitulo), Italian (capitolo), Dutch (hoofdstuk), and abbreviated ch./ch
• The detection regex in book_to_skill/utils.py (line 109) handles case-insensitive matching and numeral variations
• Spanish detection specifically accommodates both accented (í) and unaccented (i) forms via pattern cap[ií]tulo
• All chapter numbers—Arabic, Roman, or other systems—are captured alongside the detected keyword
• The detect_structure() function provides the primary API for chapter identification

Frequently Asked Questions

Can I use book-to-skill with books in languages not on the supported list?

Currently, book-to-skill only recognizes the seven language variants explicitly defined in the regex. Books in Portuguese (capítulo), Russian, Chinese, or other languages will likely require manual chapter splitting or preprocessing to insert recognizable keywords. You can inspect the detection logic in book_to_skill/utils.py to understand the matching constraints.

Does the Spanish detection require the accented í in capítulo?

No. The regex pattern cap[ií]tulo explicitly matches both capitulo (without accent) and capítulo (with accented í). This accommodates encoding variations and different input source formats without failing detection.

Is the abbreviated "ch." form case-sensitive?

No. The chapter detection regex operates case-insensitively, so CH., Ch., ch., and CH all trigger successful chapter identification. This flexibility handles diverse formatting conventions across publishers and document sources.

How does book-to-skill handle Roman numerals in chapter headings?

The detection regex captures chapter numbers following the keyword regardless of numeral system. Both Arabic numerals (Chapter 5) and Roman numerals (Chapter V) are recognized and extracted as part of the chapter identifier, enabling consistent structural parsing across document styles.

{
  "mcpServers": {
    "instagit": {
      "command": "npx",
      "args": ["-y", "instagit@latest"]
    }
  }
}