mirror of
https://github.com/sipeed/picoclaw.git
synced 2026-06-12 18:08:54 +00:00
refactor: extract message splitting logic to shared utils
- Move FindLast, findLast, and SplitMessage from discord.go to pkg/utils/message.go - Update discord.go to use utils.SplitMessage() - Makes splitting logic reusable across other channels
This commit is contained in:
Hua
+1
-128
@@ -4,7 +4,6 @@ import (
|
||||
"context"
|
||||
"fmt"
|
||||
"os"
|
||||
"strings"
|
||||
"time"
|
||||
|
||||
"github.com/bwmarrin/discordgo"
|
||||
@@ -106,7 +105,7 @@ func (c *DiscordChannel) Send(ctx context.Context, msg bus.OutboundMessage) erro
|
||||
return nil
|
||||
}
|
||||
|
||||
chunks := splitMessage(msg.Content, 1500) // Discord has a limit of 2000 characters per message, leave 500 for natural split e.g. code blocks
|
||||
chunks := utils.SplitMessage(msg.Content, 1500) // Discord has a limit of 2000 characters per message, leave 500 for natural split e.g. code blocks
|
||||
|
||||
for _, chunk := range chunks {
|
||||
if err := c.sendChunk(ctx, channelID, chunk); err != nil {
|
||||
@@ -117,132 +116,6 @@ func (c *DiscordChannel) Send(ctx context.Context, msg bus.OutboundMessage) erro
|
||||
return nil
|
||||
}
|
||||
|
||||
// splitMessage splits long messages into chunks, preserving code block integrity
|
||||
// Uses natural boundaries (newlines, spaces) and extends messages slightly to avoid breaking code blocks
|
||||
func splitMessage(content string, limit int) []string {
|
||||
var messages []string
|
||||
|
||||
for len(content) > 0 {
|
||||
if len(content) <= limit {
|
||||
messages = append(messages, content)
|
||||
break
|
||||
}
|
||||
|
||||
msgEnd := limit
|
||||
|
||||
// Find natural split point within the limit
|
||||
msgEnd = findLastNewline(content[:limit], 200)
|
||||
if msgEnd <= 0 {
|
||||
msgEnd = findLastSpace(content[:limit], 100)
|
||||
}
|
||||
if msgEnd <= 0 {
|
||||
msgEnd = limit
|
||||
}
|
||||
|
||||
// Check if this would end with an incomplete code block
|
||||
candidate := content[:msgEnd]
|
||||
unclosedIdx := findLastUnclosedCodeBlock(candidate)
|
||||
|
||||
if unclosedIdx >= 0 {
|
||||
// Message would end with incomplete code block
|
||||
// Try to extend to include the closing ``` (with some buffer)
|
||||
extendedLimit := limit + 500 // Allow 500 char buffer for code blocks
|
||||
if len(content) > extendedLimit {
|
||||
closingIdx := findNextClosingCodeBlock(content, msgEnd)
|
||||
if closingIdx > 0 && closingIdx <= extendedLimit {
|
||||
// Extend to include the closing ```
|
||||
msgEnd = closingIdx
|
||||
} else {
|
||||
// Can't find closing, split before the code block
|
||||
msgEnd = findLastNewline(content[:unclosedIdx], 200)
|
||||
if msgEnd <= 0 {
|
||||
msgEnd = findLastSpace(content[:unclosedIdx], 100)
|
||||
}
|
||||
if msgEnd <= 0 {
|
||||
msgEnd = unclosedIdx
|
||||
}
|
||||
}
|
||||
} else {
|
||||
// Remaining content fits within extended limit
|
||||
msgEnd = len(content)
|
||||
}
|
||||
}
|
||||
|
||||
if msgEnd <= 0 {
|
||||
msgEnd = limit
|
||||
}
|
||||
|
||||
messages = append(messages, content[:msgEnd])
|
||||
content = strings.TrimSpace(content[msgEnd:])
|
||||
}
|
||||
|
||||
return messages
|
||||
}
|
||||
|
||||
// findLastUnclosedCodeBlock finds the last opening ``` that doesn't have a closing ```
|
||||
// Returns the position of the opening ``` or -1 if all code blocks are complete
|
||||
func findLastUnclosedCodeBlock(text string) int {
|
||||
count := 0
|
||||
lastOpenIdx := -1
|
||||
|
||||
for i := 0; i < len(text); i++ {
|
||||
if i+2 < len(text) && text[i] == '`' && text[i+1] == '`' && text[i+2] == '`' {
|
||||
if count == 0 {
|
||||
lastOpenIdx = i
|
||||
}
|
||||
count++
|
||||
i += 2
|
||||
}
|
||||
}
|
||||
|
||||
// If odd number of ``` markers, last one is unclosed
|
||||
if count%2 == 1 {
|
||||
return lastOpenIdx
|
||||
}
|
||||
return -1
|
||||
}
|
||||
|
||||
// findNextClosingCodeBlock finds the next closing ``` starting from a position
|
||||
// Returns the position after the closing ``` or -1 if not found
|
||||
func findNextClosingCodeBlock(text string, startIdx int) int {
|
||||
for i := startIdx; i < len(text); i++ {
|
||||
if i+2 < len(text) && text[i] == '`' && text[i+1] == '`' && text[i+2] == '`' {
|
||||
return i + 3
|
||||
}
|
||||
}
|
||||
return -1
|
||||
}
|
||||
|
||||
// findLastNewline finds the last newline character within the last N characters
|
||||
// Returns the position of the newline or -1 if not found
|
||||
func findLastNewline(s string, searchWindow int) int {
|
||||
searchStart := len(s) - searchWindow
|
||||
if searchStart < 0 {
|
||||
searchStart = 0
|
||||
}
|
||||
for i := len(s) - 1; i >= searchStart; i-- {
|
||||
if s[i] == '\n' {
|
||||
return i
|
||||
}
|
||||
}
|
||||
return -1
|
||||
}
|
||||
|
||||
// findLastSpace finds the last space character within the last N characters
|
||||
// Returns the position of the space or -1 if not found
|
||||
func findLastSpace(s string, searchWindow int) int {
|
||||
searchStart := len(s) - searchWindow
|
||||
if searchStart < 0 {
|
||||
searchStart = 0
|
||||
}
|
||||
for i := len(s) - 1; i >= searchStart; i-- {
|
||||
if s[i] == ' ' || s[i] == '\t' {
|
||||
return i
|
||||
}
|
||||
}
|
||||
return -1
|
||||
}
|
||||
|
||||
func (c *DiscordChannel) sendChunk(ctx context.Context, channelID, content string) error {
|
||||
// 使用传入的 ctx 进行超时控制
|
||||
sendCtx, cancel := context.WithTimeout(ctx, sendTimeout)
|
||||
|
||||
@@ -0,0 +1,131 @@
|
||||
package utils
|
||||
|
||||
import (
|
||||
"strings"
|
||||
)
|
||||
|
||||
// SplitMessage splits long messages into chunks, preserving code block integrity
|
||||
// Uses natural boundaries (newlines, spaces) and extends messages slightly to avoid breaking code blocks
|
||||
func SplitMessage(content string, limit int) []string {
|
||||
var messages []string
|
||||
|
||||
for len(content) > 0 {
|
||||
if len(content) <= limit {
|
||||
messages = append(messages, content)
|
||||
break
|
||||
}
|
||||
|
||||
msgEnd := limit
|
||||
|
||||
// Find natural split point within the limit
|
||||
msgEnd = FindLastNewline(content[:limit], 200)
|
||||
if msgEnd <= 0 {
|
||||
msgEnd = FindLastSpace(content[:limit], 100)
|
||||
}
|
||||
if msgEnd <= 0 {
|
||||
msgEnd = limit
|
||||
}
|
||||
|
||||
// Check if this would end with an incomplete code block
|
||||
candidate := content[:msgEnd]
|
||||
unclosedIdx := FindLastUnclosedCodeBlock(candidate)
|
||||
|
||||
if unclosedIdx >= 0 {
|
||||
// Message would end with incomplete code block
|
||||
// Try to extend to include the closing ``` (with some buffer)
|
||||
extendedLimit := limit + 500 // Allow 500 char buffer for code blocks
|
||||
if len(content) > extendedLimit {
|
||||
closingIdx := FindNextClosingCodeBlock(content, msgEnd)
|
||||
if closingIdx > 0 && closingIdx <= extendedLimit {
|
||||
// Extend to include the closing ```
|
||||
msgEnd = closingIdx
|
||||
} else {
|
||||
// Can't find closing, split before the code block
|
||||
msgEnd = FindLastNewline(content[:unclosedIdx], 200)
|
||||
if msgEnd <= 0 {
|
||||
msgEnd = FindLastSpace(content[:unclosedIdx], 100)
|
||||
}
|
||||
if msgEnd <= 0 {
|
||||
msgEnd = unclosedIdx
|
||||
}
|
||||
}
|
||||
} else {
|
||||
// Remaining content fits within extended limit
|
||||
msgEnd = len(content)
|
||||
}
|
||||
}
|
||||
|
||||
if msgEnd <= 0 {
|
||||
msgEnd = limit
|
||||
}
|
||||
|
||||
messages = append(messages, content[:msgEnd])
|
||||
content = strings.TrimSpace(content[msgEnd:])
|
||||
}
|
||||
|
||||
return messages
|
||||
}
|
||||
|
||||
// FindLastUnclosedCodeBlock finds the last opening ``` that doesn't have a closing ```
|
||||
// Returns the position of the opening ``` or -1 if all code blocks are complete
|
||||
func FindLastUnclosedCodeBlock(text string) int {
|
||||
count := 0
|
||||
lastOpenIdx := -1
|
||||
|
||||
for i := 0; i < len(text); i++ {
|
||||
if i+2 < len(text) && text[i] == '`' && text[i+1] == '`' && text[i+2] == '`' {
|
||||
if count == 0 {
|
||||
lastOpenIdx = i
|
||||
}
|
||||
count++
|
||||
i += 2
|
||||
}
|
||||
}
|
||||
|
||||
// If odd number of ``` markers, last one is unclosed
|
||||
if count%2 == 1 {
|
||||
return lastOpenIdx
|
||||
}
|
||||
return -1
|
||||
}
|
||||
|
||||
// FindNextClosingCodeBlock finds the next closing ``` starting from a position
|
||||
// Returns the position after the closing ``` or -1 if not found
|
||||
func FindNextClosingCodeBlock(text string, startIdx int) int {
|
||||
for i := startIdx; i < len(text); i++ {
|
||||
if i+2 < len(text) && text[i] == '`' && text[i+1] == '`' && text[i+2] == '`' {
|
||||
return i + 3
|
||||
}
|
||||
}
|
||||
return -1
|
||||
}
|
||||
|
||||
// FindLastNewline finds the last newline character within the last N characters
|
||||
// Returns the position of the newline or -1 if not found
|
||||
func FindLastNewline(s string, searchWindow int) int {
|
||||
searchStart := len(s) - searchWindow
|
||||
if searchStart < 0 {
|
||||
searchStart = 0
|
||||
}
|
||||
for i := len(s) - 1; i >= searchStart; i-- {
|
||||
if s[i] == '\n' {
|
||||
return i
|
||||
}
|
||||
}
|
||||
return -1
|
||||
}
|
||||
|
||||
// FindLastSpace finds the last space character within the last N characters
|
||||
// Returns the position of the space or -1 if not found
|
||||
func FindLastSpace(s string, searchWindow int) int {
|
||||
searchStart := len(s) - searchWindow
|
||||
if searchStart < 0 {
|
||||
searchStart = 0
|
||||
}
|
||||
for i := len(s) - 1; i >= searchStart; i-- {
|
||||
if s[i] == ' ' || s[i] == '\t' {
|
||||
return i
|
||||
}
|
||||
}
|
||||
return -1
|
||||
}
|
||||
Reference in New Issue
Block a user