Implement language detection in AI response generation and enhance message content extraction

This commit is contained in:
2025-03-01 14:48:57 +01:00
parent 1be345b07f
commit d326705b1d
2 changed files with 131 additions and 84 deletions

View File

@@ -268,7 +268,6 @@ func (ic *IMAPClient) SaveDraft(email Email, response string) error {
// by removing email headers and MIME boundaries
func extractMessageContent(body string) string {
logger.WithField("bodyLength", len(body)).Debug("Starting message content extraction")
msg, err := mail.ReadMessage(strings.NewReader(body))
if err != nil {
logger.WithFields(logrus.Fields{
@@ -295,89 +294,106 @@ func extractMessageContent(body string) string {
"params": params,
}).Debug("Parsed message Content-Type")
var content string
if strings.HasPrefix(mediaType, "multipart/") {
boundary := params["boundary"]
if boundary == "" {
logger.WithField("mediaType", mediaType).Debug("No boundary found in multipart message, falling back to simple extraction")
return fallbackExtractContent(body)
}
logger.WithFields(logrus.Fields{
"mediaType": mediaType,
"boundary": boundary,
}).Debug("Processing multipart message")
reader := multipart.NewReader(msg.Body, boundary)
var textContent string
partIndex := 0
for {
part, err := reader.NextPart()
if err == io.EOF {
logger.Debug("Finished processing all multipart parts")
break
}
if err != nil {
logger.WithFields(logrus.Fields{
"error": err,
"partIndex": partIndex,
}).Debug("Error reading multipart part, falling back to simple extraction")
return fallbackExtractContent(body)
}
contentType := part.Header.Get("Content-Type")
logger.WithFields(logrus.Fields{
"partIndex": partIndex,
"contentType": contentType,
}).Debug("Processing message part")
if strings.HasPrefix(contentType, "text/plain") {
buf := new(bytes.Buffer)
_, err := buf.ReadFrom(part)
if err != nil {
logger.WithFields(logrus.Fields{
"error": err,
"partIndex": partIndex,
}).Debug("Failed to read text/plain part")
continue
}
textContent = buf.String()
logger.WithFields(logrus.Fields{
"partIndex": partIndex,
"contentLength": len(textContent),
}).Debug("Successfully extracted text/plain content")
textContent = strings.ReplaceAll(textContent, "\n", "<br>\n")
textContent = strings.ReplaceAll(textContent, "\r\n", "<br>\n")
break
}
partIndex++
}
if textContent != "" {
logger.WithField("contentLength", len(textContent)).Debug("Successfully extracted content from multipart message")
return textContent
}
logger.Debug("No text/plain content found in multipart message, trying to read body directly")
content = handleMultipartMessage(msg.Body, params["boundary"])
} else {
content = handleSinglePartMessage(msg.Body)
}
buf := new(bytes.Buffer)
_, err = buf.ReadFrom(msg.Body)
if err != nil {
logger.WithFields(logrus.Fields{
"error": err,
"mediaType": mediaType,
}).Debug("Failed to read message body, falling back to simple extraction")
if content == "" {
logger.Debug("No content extracted, falling back to simple extraction")
return fallbackExtractContent(body)
}
content := buf.String()
// Clean up the content
content = cleanMessageContent(content)
logger.WithField("contentLength", len(content)).Debug("Successfully extracted and cleaned message content")
return content
}
func handleMultipartMessage(reader io.Reader, boundary string) string {
if boundary == "" {
logger.Debug("No boundary found in multipart message")
return ""
}
mReader := multipart.NewReader(reader, boundary)
var textContent string
partIndex := 0
for {
part, err := mReader.NextPart()
if err == io.EOF {
break
}
if err != nil {
logger.WithError(err).Debug("Error reading multipart part")
return ""
}
contentType := part.Header.Get("Content-Type")
if strings.HasPrefix(contentType, "text/plain") {
buf := new(bytes.Buffer)
if _, err := buf.ReadFrom(part); err != nil {
continue
}
textContent = buf.String()
break
}
partIndex++
}
return textContent
}
func handleSinglePartMessage(reader io.Reader) string {
buf := new(bytes.Buffer)
if _, err := buf.ReadFrom(reader); err != nil {
logger.WithError(err).Debug("Failed to read message body")
return ""
}
return buf.String()
}
func cleanMessageContent(content string) string {
// Remove any remaining email headers that might be in the body
lines := strings.Split(content, "\n")
var cleanLines []string
headerSection := true
for _, line := range lines {
trimmed := strings.TrimSpace(line)
// Empty line marks the end of headers
if headerSection && trimmed == "" {
headerSection = false
continue
}
// Skip header lines
if headerSection && (strings.Contains(trimmed, ":") || trimmed == "") {
continue
}
// Add non-header lines
if !headerSection {
cleanLines = append(cleanLines, line)
}
}
content = strings.Join(cleanLines, "\n")
// Convert newlines to HTML breaks for display
content = strings.ReplaceAll(content, "\r\n", "<br>\n")
content = strings.ReplaceAll(content, "\n", "<br>\n")
logger.WithFields(logrus.Fields{
"contentLength": len(content),
"mediaType": mediaType,
}).Debug("Successfully extracted content from message body")
return content
// Remove any remaining email signature markers
content = strings.Split(content, "\n-- ")[0]
content = strings.Split(content, "<br>-- ")[0]
return strings.TrimSpace(content)
}
// fallbackExtractContent is the previous implementation used as fallback