Skip to content

Turn any technical book PDF into a Claude Code skill — ready to study, reference, and use while you work.

feat(extractor): detect Hindi (Devanagari) chapter headings (#186)

Shubham Srivastavafc9b1c458eeb
diff --git a/book_to_skill/utils.py b/book_to_skill/utils.py
index 2b2d7ee..f0ac2b2 100644
--- a/book_to_skill/utils.py
+++ b/book_to_skill/utils.py
@@ -157,6 +157,18 @@ _TH_CHAPTER = re.compile(
rf"^\s*(?:#{{1,6}}\s+)?(?:บทที่|ตอนที่|ภาคที่|บท|ตอน|ภาค)\s*([0-9{_TH_DIGITS}]+)\b"
)
+# Hindi (Devanagari) chapter headings: "अध्याय 1", "अध्याय १", "## अध्याय 2".
+# अध्याय ("chapter") + a number. Devanagari digits (U+0966-U+096F) are positional
+# like Arabic, so — as with Thai — only a digit remap is needed, no composition.
+# Optional Markdown "#" prefix so "## अध्याय १" is recognized in converted ebooks.
+# Scoped to the digit form (not word ordinals like "पहला अध्याय") and requiring a
+# number keeps prose that merely uses the word अध्याय from matching.
+_HI_DIGITS = "०-९"
+_HI_DIGIT_MAP = str.maketrans("०१२३४५६७८९", "0123456789")
+_HI_CHAPTER = re.compile(
+ rf"^\s*(?:#{{1,6}}\s+)?अध्याय\s*([0-9{_HI_DIGITS}]+)\b"
+)
+
# Korean chapter headings: "제1장 총칙", "## 제4장 근로시간과 휴식", "제6장의2 …".
# 제 + Arabic numeral + a classifier (장 chapter / 편 part / 절 section / 관
# subsection), with an optional "의N" branch suffix that Korean statutes use for
@@ -497,6 +509,9 @@ def _match_chapter_number(line: str) -> int | None:
tm = _TH_CHAPTER.match(s)
if tm:
return int(tm.group(1).translate(_TH_DIGIT_MAP))
+ hm = _HI_CHAPTER.match(s)
+ if hm:
+ return int(hm.group(1).translate(_HI_DIGIT_MAP))
km = _KO_CHAPTER.match(s)
if km:
return int(km.group(1))
@@ -512,7 +527,8 @@ def _chapter_number(line: str) -> int | None:
Handles Arabic ("Chapter 5", "Capítulo 5: ..."), Roman-numeral
("I: Loomings", "## i. introduction", "II. The Carpet-Bag"),
Chinese ("第三章 …", "## 一 · …", "## 第一讲"), Thai ("บทที่ 3",
- "## บทที่ ๑"), Korean ("제1장 총칙", "## 제4장 근로시간과 휴식"), and
+ "## บทที่ ๑"), Hindi ("अध्याय 1", "अध्याय १", "## अध्याय 2"),
+ Korean ("제1장 총칙", "## 제4장 근로시간과 휴식"), and
Persian ("فصل ۱", "فصل اول", "فصل بیست و یکم", "بخش ۲: مفاهیم",
"## فصل ۱: مقدمه", PDF-glued "فصل سی و چهارمخداحافظ…") heading styles — each
optionally preceded by a Markdown/AsciiDoc heading marker
diff --git a/tests/test_book_to_skill.py b/tests/test_book_to_skill.py
index b985f16..42dcce7 100644
--- a/tests/test_book_to_skill.py
+++ b/tests/test_book_to_skill.py
@@ -627,6 +627,27 @@ class TestDetectStructure:
assert _chapter_number("บทความนี้ยาวมากและมีรายละเอียดเยอะ") is None
assert _chapter_number("ตอนนี้เรามาดูกันว่าเกิดอะไรขึ้น") is None
+ # ── Hindi (Devanagari) chapter headings ────────────────────────────────
+ def test_detects_hindi_chapters(self):
+ """Hindi headings: `अध्याय N`, with Devanagari or Arabic digits."""
+ text = (
+ "अध्याय १ प्रस्तावना\nसामग्री\n"
+ "अध्याय २ विधियाँ\nसामग्री\n"
+ "अध्याय 3 परिणाम\nसामग्री"
+ )
+ assert detect_structure(text)["chapters_detected"] == 3
+
+ def test_hindi_markdown_prefix(self):
+ text = "## अध्याय १ पहला\nसामग्री\n## अध्याय २ दूसरा\nसामग्री"
+ assert detect_structure(text)["chapters_detected"] == 2
+
+ def test_hindi_prose_is_not_a_chapter_heading(self):
+ """`अध्याय` used in prose (no number, or not at the start) is not a heading."""
+ from book_to_skill.utils import _chapter_number
+
+ assert _chapter_number("इस अध्याय में हम चर्चा करेंगे") is None
+ assert _chapter_number("अध्याय") is None
+
# ── Korean chapter headings ────────────────────────────────────────────
def test_korean_je_n_jang(self):