fix to feedback

This commit is contained in:
Badgerbees 2026-03-17 20:42:34 +07:00
parent f66ee8f306
commit 3efadac453
2 changed files with 23 additions and 53 deletions

View file

@ -207,56 +207,15 @@ func (c *TelegramChannel) Send(ctx context.Context, msg bus.OutboundMessage) err
continue
}
// Seek a natural break point (space or newline) to avoid splitting mid-word.
splitIdx := smallerLen
foundBreak := false
// Use the estimated smaller length as a guide for SplitMessage.
// SplitMessage will find natural break points (newlines/spaces) and respect code blocks.
subChunks := channels.SplitMessage(chunk, smallerLen)
// Scan backwards from the target point to find the nearest whitespace.
for i := smallerLen; i >= 0; i-- {
if runeChunk[i] == ' ' || runeChunk[i] == '\n' || runeChunk[i] == '\t' || runeChunk[i] == '\r' {
splitIdx = i
foundBreak = true
break
}
}
// If no space was found behind, scan forward to find the next word boundary.
if !foundBreak {
for i := smallerLen; i < len(runeChunk); i++ {
if runeChunk[i] == ' ' || runeChunk[i] == '\n' || runeChunk[i] == '\t' || runeChunk[i] == '\r' {
splitIdx = i
foundBreak = true
break
}
}
}
// Fall back to a hard split if the entire block is monolithic (no spaces found).
if !foundBreak {
splitIdx = smallerLen
}
// Ensure we split at a valid index to guarantee forward progress.
if splitIdx <= 0 {
splitIdx = 1
}
// Attempt to split using the determined index, ensuring code block integrity is maintained.
subChunks := channels.SplitMessage(chunk, splitIdx)
// Safety fallback: If SplitMessage failed to shorten the chunk, force a manual split.
// Safety fallback: If SplitMessage failed to shorten the chunk, force a manual hard split.
if len(subChunks) == 1 && subChunks[0] == chunk {
part1 := string(runeChunk[:splitIdx])
subChunks = []string{part1}
nextStart := splitIdx
if foundBreak && nextStart < len(runeChunk) {
nextStart++
}
if nextStart < len(runeChunk) {
part2 := string(runeChunk[nextStart:])
subChunks = append(subChunks, part2)
}
part1 := string(runeChunk[:smallerLen])
part2 := string(runeChunk[smallerLen:])
subChunks = []string{part1, part2}
}
// Filter out empty chunks to avoid sending empty messages to Telegram.

View file

@ -39,7 +39,10 @@ func (s *stubCaller) Call(ctx context.Context, url string, data *ta.RequestData)
type stubConstructor struct{}
func (s *stubConstructor) JSONRequest(parameters any) (*ta.RequestData, error) {
b, _ := json.Marshal(parameters)
b, err := json.Marshal(parameters)
if err != nil {
return nil, err
}
return &ta.RequestData{
ContentType: "application/json",
BodyRaw: b,
@ -247,14 +250,21 @@ func TestSend_HTMLOverflow_WordBoundary(t *testing.T) {
}
ch := newTestChannel(t, caller)
// We want to force a split near index ~2600.
// We want to force a split near index ~2600 while keeping markdown length <= 4000.
// Prefix of 430 bold units (6 chars each) = 2580 chars.
// Expansion per unit is 3 chars. 2580 + 430*3 = 3870.
// Expansion per unit is +3 chars when converted to HTML, so 2580 + 430*3 = 3870.
prefix := strings.Repeat("**a** ", 430)
targetWord := "TARGETWORDTHATSTAYSTOGETHER"
suffix := strings.Repeat(" **b**", 250)
// Suffix of 230 bold units (6 chars each) = 1380 chars.
// Total markdown length: 2580 (prefix) + 27 (target word) + 1380 (suffix) = 3987 <= 4000.
// HTML expansion adds ~3 chars per bold unit: (430 + 230)*3 = 1980 extra chars,
// so total HTML length comfortably exceeds 4096.
suffix := strings.Repeat(" **b**", 230)
content := prefix + targetWord + suffix
// Ensure the test content matches the intended boundary conditions.
assert.LessOrEqual(t, len([]rune(content)), 4000, "markdown content must not exceed chunk size for this test")
err := ch.Send(context.Background(), bus.OutboundMessage{
ChatID: "123456",
Content: content,
@ -265,7 +275,8 @@ func TestSend_HTMLOverflow_WordBoundary(t *testing.T) {
foundFullWord := false
for i, call := range caller.calls {
var params map[string]any
_ = json.Unmarshal(call.Data.BodyRaw, &params)
err := json.Unmarshal(call.Data.BodyRaw, &params)
require.NoError(t, err)
text, _ := params["text"].(string)
hasWord := strings.Contains(text, targetWord)