Files
Enterprise-Knowledge-Base/internal/infrastructure/chunker/tokens_test.go
T
Claude ae6fde2310 feat(chunker): foundation for adaptive 3-tier chunking
Adds the building blocks for tiered chunking strategies — multilingual
patterns, token approximation, document profiling, validation, and a
strategy resolver that today still falls through to the legacy
SplitText. Default Strategy is empty/legacy so existing knowledge bases
continue to chunk identically.

- tokens.go: char/token approximation per language (en/de/zh/mixed)
  and a coarse DetectLanguage heuristic
- patterns.go: source-of-truth regex bibliothek for headings, numbered
  sections, multilingual chapter markers, visual separators, etc.
- profiler.go: single-pass document scan + SelectStrategy chain
- validator.go: rejects obviously broken chunk-sets to drive fallbacks
- strategy.go: public Split / SplitParentChild entry points; resolves
  StrategyAuto via the profiler, anything else maps to a fixed tier
- splitter.go: SplitterConfig gains Strategy / TokenLimit / Languages
  fields and DefaultChunkSize / DefaultChunkOverlap constants (overlap
  raised to 80 ≈ 15%)
- knowledge.go: switches both call sites to chunker.Split /
  SplitParentChild — behavior unchanged for empty Strategy

https://claude.ai/code/session_01XADhx6mtu2ZYW3DE9Lun6k
2026-05-06 17:17:07 +08:00

79 lines
2.4 KiB
Go

package chunker
import "testing"
func TestApproxTokenCount_English(t *testing.T) {
got := ApproxTokenCount("The quick brown fox jumps over the lazy dog.", LangEnglish)
// 44 chars / 4 ≈ 11 tokens
if got < 9 || got > 13 {
t.Errorf("English token estimate out of range: got %d, want 9..13", got)
}
}
func TestApproxTokenCount_Chinese(t *testing.T) {
got := ApproxTokenCount("这是一段中文测试内容用于检验分词估算", LangChinese)
// 18 runes / 1.7 ≈ 10
if got < 9 || got > 12 {
t.Errorf("Chinese token estimate out of range: got %d, want 9..12", got)
}
}
func TestApproxTokenCount_Empty(t *testing.T) {
if got := ApproxTokenCount("", LangEnglish); got != 0 {
t.Errorf("empty string should return 0 tokens, got %d", got)
}
}
func TestApproxTokenCount_UnknownLang(t *testing.T) {
got := ApproxTokenCount("Hello world hello world", "xx")
if got <= 0 {
t.Errorf("unknown lang should fall back to mixed, got %d", got)
}
}
func TestDetectLanguage_English(t *testing.T) {
if got := DetectLanguage("The quick brown fox jumps over the lazy dog."); got != LangEnglish {
t.Errorf("expected English, got %s", got)
}
}
func TestDetectLanguage_German(t *testing.T) {
if got := DetectLanguage("Der schnelle braune Fuchs springt über den faulen Hund."); got != LangGerman {
t.Errorf("expected German, got %s", got)
}
}
func TestDetectLanguage_GermanByStopwords(t *testing.T) {
// No umlauts but plenty of German function words.
if got := DetectLanguage("Das ist ein Test und nicht mit Umlauten."); got != LangGerman {
t.Errorf("expected German via stopwords, got %s", got)
}
}
func TestDetectLanguage_Chinese(t *testing.T) {
if got := DetectLanguage("这是一段中文测试内容"); got != LangChinese {
t.Errorf("expected Chinese, got %s", got)
}
}
func TestDetectLanguage_Mixed(t *testing.T) {
got := DetectLanguage("This 这是 mixed 测试 content with 多语言 inside")
if got != LangMixed {
t.Errorf("expected Mixed, got %s", got)
}
}
func TestCharsForTokenLimit_AppliesSafetyMargin(t *testing.T) {
got := CharsForTokenLimit(1000, LangEnglish)
// 1000 * 4 * 0.9 = 3600
if got < 3500 || got > 3700 {
t.Errorf("char budget for 1000 EN tokens out of range: got %d", got)
}
}
func TestCharsForTokenLimit_ZeroTokens(t *testing.T) {
if got := CharsForTokenLimit(0, LangEnglish); got != 0 {
t.Errorf("zero tokens should give zero chars, got %d", got)
}
}