feat: Enhance AI response generation and improve email content extraction with detailed logging
This commit is contained in:
@@ -6,6 +6,7 @@ import (
|
||||
"io"
|
||||
"mime"
|
||||
"mime/multipart"
|
||||
"mime/quotedprintable"
|
||||
"net/mail"
|
||||
"paraclub-ai-mailer/config"
|
||||
"paraclub-ai-mailer/internal/logger"
|
||||
@@ -73,6 +74,7 @@ type Email struct {
|
||||
ID string
|
||||
Subject string
|
||||
From string
|
||||
Date time.Time
|
||||
Body string
|
||||
}
|
||||
|
||||
@@ -194,6 +196,7 @@ func (ic *IMAPClient) FetchUnprocessedEmails() ([]Email, error) {
|
||||
ID: msg.Envelope.MessageId,
|
||||
Subject: msg.Envelope.Subject,
|
||||
From: from,
|
||||
Date: msg.Envelope.Date,
|
||||
Body: bodyBuilder.String(),
|
||||
})
|
||||
}
|
||||
@@ -259,7 +262,7 @@ func (ic *IMAPClient) SaveDraft(email Email, response string) (err error) {
|
||||
response,
|
||||
email.From,
|
||||
email.Subject,
|
||||
time.Now().Format("Mon, 02 Jan 2006 15:04:05 -0700"),
|
||||
email.Date.Format("Mon, 02 Jan 2006 15:04:05 -0700"),
|
||||
extractMessageContent(email.Body))
|
||||
|
||||
literal := &MessageLiteral{
|
||||
@@ -285,6 +288,7 @@ func (ic *IMAPClient) SaveDraft(email Email, response string) (err error) {
|
||||
// by removing email headers and MIME boundaries
|
||||
func extractMessageContent(body string) string {
|
||||
logger.WithField("bodyLength", len(body)).Debug("Starting message content extraction")
|
||||
logger.WithField("rawInputBody", body).Debug("extractMessageContent: Raw input body")
|
||||
msg, err := mail.ReadMessage(strings.NewReader(body))
|
||||
if err != nil {
|
||||
logger.WithFields(logrus.Fields{
|
||||
@@ -296,6 +300,7 @@ func extractMessageContent(body string) string {
|
||||
|
||||
contentTypeHeader := msg.Header.Get("Content-Type")
|
||||
logger.WithField("contentTypeHeader", contentTypeHeader).Debug("Got Content-Type header")
|
||||
logger.WithField("parsedContentTypeHeader", contentTypeHeader).Debug("extractMessageContent: Parsed Content-Type header")
|
||||
|
||||
mediaType, params, err := mime.ParseMediaType(contentTypeHeader)
|
||||
if err != nil {
|
||||
@@ -310,27 +315,50 @@ func extractMessageContent(body string) string {
|
||||
"mediaType": mediaType,
|
||||
"params": params,
|
||||
}).Debug("Parsed message Content-Type")
|
||||
logger.WithFields(logrus.Fields{
|
||||
"mediaType": mediaType,
|
||||
"params": params,
|
||||
}).Debug("extractMessageContent: Parsed mediaType and params")
|
||||
|
||||
var content string
|
||||
if strings.HasPrefix(mediaType, "multipart/") {
|
||||
// For multipart, the handling of Content-Transfer-Encoding will be done within handleMultipartMessage for each part
|
||||
logger.Debug("extractMessageContent: Handling as multipart message")
|
||||
content = handleMultipartMessage(msg.Body, params["boundary"])
|
||||
logger.WithField("contentFromMultipart", content).Debug("extractMessageContent: Content after handleMultipartMessage")
|
||||
} else {
|
||||
content = handleSinglePartMessage(msg.Body)
|
||||
// For single part, handle Content-Transfer-Encoding here
|
||||
var partReader io.Reader = msg.Body
|
||||
transferEncoding := strings.ToLower(msg.Header.Get("Content-Transfer-Encoding"))
|
||||
if transferEncoding == "quoted-printable" {
|
||||
partReader = quotedprintable.NewReader(msg.Body)
|
||||
}
|
||||
// Add handling for "base64" if needed in the future
|
||||
// else if transferEncoding == "base64" {
|
||||
// partReader = base64.NewDecoder(base64.StdEncoding, msg.Body)
|
||||
// }
|
||||
logger.Debug("extractMessageContent: Handling as single part message")
|
||||
content = handleSinglePartMessage(partReader)
|
||||
logger.WithField("contentFromSinglePart", content).Debug("extractMessageContent: Content after handleSinglePartMessage")
|
||||
}
|
||||
|
||||
if content == "" {
|
||||
logger.Debug("No content extracted, falling back to simple extraction")
|
||||
logger.Debug("extractMessageContent: No content from primary extraction, falling back.")
|
||||
return fallbackExtractContent(body)
|
||||
}
|
||||
|
||||
// Clean up the content
|
||||
logger.WithField("contentBeforeClean", content).Debug("extractMessageContent: Content before cleanMessageContent")
|
||||
content = cleanMessageContent(content)
|
||||
logger.WithField("contentAfterClean", content).Debug("extractMessageContent: Content after cleanMessageContent")
|
||||
|
||||
logger.WithField("contentLength", len(content)).Debug("Successfully extracted and cleaned message content")
|
||||
return content
|
||||
}
|
||||
|
||||
func handleMultipartMessage(reader io.Reader, boundary string) string {
|
||||
logger.WithField("boundary", boundary).Debug("handleMultipartMessage: Starting with boundary")
|
||||
if boundary == "" {
|
||||
logger.Debug("No boundary found in multipart message")
|
||||
return ""
|
||||
@@ -351,30 +379,55 @@ func handleMultipartMessage(reader io.Reader, boundary string) string {
|
||||
}
|
||||
|
||||
contentType := part.Header.Get("Content-Type")
|
||||
contentTransferEncoding := strings.ToLower(part.Header.Get("Content-Transfer-Encoding"))
|
||||
logger.WithFields(logrus.Fields{
|
||||
"partIndex": partIndex,
|
||||
"partContentType": contentType,
|
||||
"partTransferEncoding": contentTransferEncoding,
|
||||
"partHeaders": part.Header,
|
||||
}).Debug("handleMultipartMessage: Processing part")
|
||||
|
||||
if strings.HasPrefix(contentType, "text/plain") {
|
||||
var partReader io.Reader = part
|
||||
if contentTransferEncoding == "quoted-printable" {
|
||||
partReader = quotedprintable.NewReader(part)
|
||||
}
|
||||
// Add handling for "base64" if needed in the future
|
||||
// else if contentTransferEncoding == "base64" {
|
||||
// partReader = base64.NewDecoder(base64.StdEncoding, part)
|
||||
// }
|
||||
|
||||
buf := new(bytes.Buffer)
|
||||
if _, err := buf.ReadFrom(part); err != nil {
|
||||
continue
|
||||
if _, err := buf.ReadFrom(partReader); err != nil {
|
||||
logger.WithError(err).WithField("partIndex", partIndex).Debug("Failed to read from partReader in multipart")
|
||||
continue // Or handle error more robustly
|
||||
}
|
||||
textContent = buf.String()
|
||||
// Assuming we only care about the first text/plain part found
|
||||
// If multiple text/plain parts could exist and need concatenation, this logic would need adjustment.
|
||||
break
|
||||
}
|
||||
partIndex++
|
||||
}
|
||||
|
||||
logger.WithField("textContentResult", textContent).Debug("handleMultipartMessage: Returning textContent")
|
||||
return textContent
|
||||
}
|
||||
|
||||
func handleSinglePartMessage(reader io.Reader) string {
|
||||
logger.Debug("handleSinglePartMessage: Starting")
|
||||
buf := new(bytes.Buffer)
|
||||
if _, err := buf.ReadFrom(reader); err != nil {
|
||||
logger.WithError(err).Debug("Failed to read message body")
|
||||
return ""
|
||||
}
|
||||
return buf.String()
|
||||
content := buf.String()
|
||||
logger.WithField("readContent", content).Debug("handleSinglePartMessage: Content read from reader")
|
||||
return content
|
||||
}
|
||||
|
||||
func cleanMessageContent(content string) string {
|
||||
logger.WithField("inputContentLength", len(content)).Debug("cleanMessageContent: Starting")
|
||||
// Remove any remaining email headers that might be in the body
|
||||
lines := strings.Split(content, "\n")
|
||||
var cleanLines []string
|
||||
@@ -401,21 +454,26 @@ func cleanMessageContent(content string) string {
|
||||
}
|
||||
|
||||
content = strings.Join(cleanLines, "\n")
|
||||
logger.WithField("contentAfterHeaderStripLength", len(content)).Debug("cleanMessageContent: Content after header stripping")
|
||||
|
||||
// Convert newlines to HTML breaks for display
|
||||
content = strings.ReplaceAll(content, "\r\n", "<br>\n")
|
||||
content = strings.ReplaceAll(content, "\n", "<br>\n")
|
||||
logger.WithField("contentAfterNewlineConversionLength", len(content)).Debug("cleanMessageContent: Content after newline conversion")
|
||||
|
||||
// Remove any remaining email signature markers
|
||||
content = strings.Split(content, "\n-- ")[0]
|
||||
content = strings.Split(content, "<br>-- ")[0]
|
||||
|
||||
return strings.TrimSpace(content)
|
||||
finalContent := strings.TrimSpace(content)
|
||||
logger.WithField("finalCleanedContentLength", len(finalContent)).Debug("cleanMessageContent: Returning final cleaned content")
|
||||
return finalContent
|
||||
}
|
||||
|
||||
// fallbackExtractContent is the previous implementation used as fallback
|
||||
func fallbackExtractContent(body string) string {
|
||||
logger.WithField("bodyLength", len(body)).Debug("Using fallback content extraction method")
|
||||
logger.WithField("rawInputBodyFallbackLength", len(body)).Debug("fallbackExtractContent: Raw input body")
|
||||
parts := strings.Split(body, "\r\n\r\n")
|
||||
if len(parts) > 1 {
|
||||
content := strings.Join(parts[1:], "\r\n\r\n")
|
||||
@@ -425,6 +483,7 @@ func fallbackExtractContent(body string) string {
|
||||
"contentLength": len(content),
|
||||
"partsCount": len(parts),
|
||||
}).Debug("Successfully extracted content using fallback method")
|
||||
logger.WithField("extractedContentFallbackLength", len(content)).Debug("fallbackExtractContent: Content from splitting parts")
|
||||
return content
|
||||
}
|
||||
content := body
|
||||
@@ -434,6 +493,7 @@ func fallbackExtractContent(body string) string {
|
||||
"contentLength": len(content),
|
||||
"fullBody": true,
|
||||
}).Debug("Using full body as content in fallback method")
|
||||
logger.WithField("finalContentFallbackLength", len(content)).Debug("fallbackExtractContent: Final content from full body")
|
||||
return content
|
||||
}
|
||||
|
||||
|
||||
Reference in New Issue
Block a user