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 Telugu (అధ్యాయము) chapter headings (#223)

Shubham Srivastava2057f07cecd5
diff --git a/book_to_skill/utils.py b/book_to_skill/utils.py
index 6e53257..5d40424 100644
--- a/book_to_skill/utils.py
+++ b/book_to_skill/utils.py
@@ -210,6 +210,18 @@ _TA_CHAPTER = re.compile(
rf"^\s*(?:#{{1,6}}\s+)?அத்தியாயம்\s*([0-9{_TA_DIGITS}]+)\b"
)
+# Telugu chapter headings: "అధ్యాయము 1", "అధ్యాయం ౧", "## అధ్యాయం 2".
+# The chapter word has two common spellings — అధ్యాయము (formal) and అధ్యాయం
+# (modern), sharing the stem అధ్యాయ — so both endings are matched. Telugu digits
+# (U+0C66-U+0C6F) are positional like the other Indic blocks above, so only a
+# digit remap is needed. Requiring the full word then a number keeps prose (or an
+# inflected form like "అధ్యాయంలో", a different suffix) from matching.
+_TE_DIGITS = "౦-౯"
+_TE_DIGIT_MAP = str.maketrans("౦౧౨౩౪౫౬౭౮౯", "0123456789")
+_TE_CHAPTER = re.compile(
+ rf"^\s*(?:#{{1,6}}\s+)?అధ్యాయ(?:ము|ం)\s*([0-9{_TE_DIGITS}]+)\b"
+)
+
# Russian (Cyrillic) chapter headings: "Глава 1", "ГЛАВА 12", "## Глава 2".
# "Глава" ("chapter") + a number. Cyrillic uses ordinary Arabic digits, so —
# unlike the Devanagari/Bengali blocks above — no digit remap is needed. A
@@ -596,6 +608,9 @@ def _match_chapter_number(line: str) -> int | None:
tam = _TA_CHAPTER.match(s)
if tam:
return int(tam.group(1).translate(_TA_DIGIT_MAP))
+ tem = _TE_CHAPTER.match(s)
+ if tem:
+ return int(tem.group(1).translate(_TE_DIGIT_MAP))
rum = _RU_CHAPTER.match(s)
if rum:
return int(rum.group(1))
@@ -623,6 +638,7 @@ def _chapter_number(line: str) -> int | None:
"## บทที่ ๑"), Hindi ("अध्याय 1", "अध्याय १", "## अध्याय 2"),
Bengali ("অধ্যায় 1", "অধ্যায় ১", "## অধ্যায় 2"),
Tamil ("அத்தியாயம் 1", "அத்தியாயம் ௧", "## அத்தியாயம் 2"),
+ Telugu ("అధ్యాయము 1", "అధ్యాయం ౧", "## అధ్యాయం 2"),
Russian ("Глава 1", "ГЛАВА 12", "## Глава 2"),
Greek ("Κεφάλαιο 1", "ΚΕΦΑΛΑΙΟ 12", "## Κεφάλαιο 2"),
Korean ("제1장 총칙", "## 제4장 근로시간과 휴식"), and
diff --git a/tests/test_book_to_skill.py b/tests/test_book_to_skill.py
index 98faa75..e125296 100644
--- a/tests/test_book_to_skill.py
+++ b/tests/test_book_to_skill.py
@@ -688,6 +688,26 @@ class TestDetectStructure:
assert _chapter_number("இந்த அத்தியாயத்தில் நாம் பார்ப்போம்") is None
assert _chapter_number("அத்தியாயம்") is None
+ def test_detects_telugu_chapters(self):
+ """Telugu headings: both spellings (అధ్యాయము/అధ్యాయం), Telugu or Arabic digits."""
+ text = (
+ "అధ్యాయము ౧ పరిచయం\nసారాంశం\n"
+ "అధ్యాయం ౨ పద్ధతులు\nసారాంశం\n"
+ "అధ్యాయం 3 ఫలితాలు\nసారాంశం"
+ )
+ assert detect_structure(text)["chapters_detected"] == 3
+
+ def test_telugu_markdown_prefix(self):
+ text = "## అధ్యాయం ౧ మొదటి\nసారాంశం\n## అధ్యాయం ౨ రెండవ\nసారాంశం"
+ assert detect_structure(text)["chapters_detected"] == 2
+
+ def test_telugu_prose_is_not_a_chapter_heading(self):
+ """An inflected form (అధ్యాయంలో) or a bare word is not a heading."""
+ from book_to_skill.utils import _chapter_number
+
+ assert _chapter_number("ఈ అధ్యాయంలో మనం చర్చిస్తాము") is None
+ assert _chapter_number("అధ్యాయం") is None
+
def test_detects_russian_chapters(self):
"""Russian headings: `Глава N`, case-insensitive, with Arabic digits."""
text = (