[Feature] Enchance text_part:get_content method

This method now supports otional `type` attribute which could be
following:

- `content` (default): utf8 content with HTML tags stripped and newlines preserved
- `content_oneline`: utf8 content with HTML tags and newlines stripped
- `raw`: raw content, not mime decoded nor utf8 converted
- `raw_parsed`: raw content, mime decoded, not utf8 converted
- `raw_utf`: raw content, mime decoded, utf8 converted (but with HTML tags and newlines)

2 files changed, 3 insertions, 0 deletions

diff --git a/src/libmime/message.c b/src/libmime/message.c
index a4f3be5ca..40769037b 100644
--- a/src/libmime/message.c
+++ b/src/libmime/message.c
@@ -497,6 +497,7 @@ rspamd_message_process_text_part (struct rspamd_task *task,
 				&text_part->exceptions,
 				task->urls,
 				task->emails);
+		text_part->utf_raw_content = part_content;
 
 		if (text_part->content->len == 0) {
 			text_part->flags |= RSPAMD_MIME_TEXT_PART_FLAG_EMPTY;
@@ -526,6 +527,7 @@ rspamd_message_process_text_part (struct rspamd_task *task,
 
 		text_part->content = rspamd_mime_text_part_maybe_convert (task,
 				text_part);
+		text_part->utf_raw_content = text_part->content;
 
 		if (text_part->content != NULL) {
 			/*
diff --git a/src/libmime/message.h b/src/libmime/message.h
index 8c0f919ea..15fcfcccc 100644
--- a/src/libmime/message.h
+++ b/src/libmime/message.h
@@ -82,6 +82,7 @@ struct rspamd_mime_text_part {
 	rspamd_ftok_t raw;
 	rspamd_ftok_t parsed;
 	GByteArray *content;
+	GByteArray *utf_raw_content;
 	GByteArray *stripped_content;
 	GPtrArray *newlines;	/**< positions of newlines in text					*/
 	struct html_content *html;