imfile: support LF escaping in read mode 2

2 files changed, 29 insertions, 6 deletions

diff --git a/ChangeLog b/ChangeLog
index 0264f895..cbfbec5c 100644
--- a/ChangeLog
+++ b/ChangeLog
@@ -1,5 +1,18 @@
 ---------------------------------------------------------------------------
 Version 7.5.3 [devel] 2013-07-??
+- imfile: support for escaping LF characters added
+  embedded LF in syslog messages cause a lot of trouble. imfile now has
+  the capability to escape them to "#012" (just like the regular control
+  character escape option). This requires new-style input statements to be
+  used. If legacy configuration statements are used, LF escaping is always
+  turned off to preserve compatibility.
+  NOTE: if input() statements were already used, there is a CHANGE OF
+        BEHAVIOUR: starting with this version, escaping is enabled by
+	default. So if you do not want it, you need to add
+	escapeLF="off"
+	to the input statement. Given the trouble LFs cause and the fact
+	that the majority of installations still use legacy config, we
+	considered this behaviour change acceptable and useful.
 - bugfix: queue file size was not correctly processed
   this could lead to using one queue file per message for sizes >2GiB
   Thanks to Tomas Heinrich for the patch.
diff --git a/runtime/stream.c b/runtime/stream.c
index 5ffbf10a..b35d6a11 100644
--- a/runtime/stream.c
+++ b/runtime/stream.c
@@ -745,6 +745,7 @@ strmReadLine(strm_t *pThis, cstr_t **ppCStr, uint8_t mode, sbool bEscapeLF)
 	} else if(mode == 2) {
 		/* indented follow-up lines */
 		finished=0;
+		bPrevWasNL = 0;
 		while(finished == 0){
 			if ((*ppCStr)->iStrLen == 0){
         			if(c != '\n') {
@@ -755,22 +756,31 @@ strmReadLine(strm_t *pThis, cstr_t **ppCStr, uint8_t mode, sbool bEscapeLF)
 					finished=1;  /* this is a blank line, a \n with nothing since the last complete record */
 				}
 			} else {
-				if ((*ppCStr)->pBuf[(*ppCStr)->iStrLen -1 ] != '\n'){
-				/* not the first character after a newline, add it to the buffer */
-               				CHKiRet(cstrAppendChar(*ppCStr, c));
-               				CHKiRet(strmReadChar(pThis, &c));
-				} else {
+				if(bPrevWasNL) {
 					if ((c == ' ') || (c == '\t')){
                					CHKiRet(cstrAppendChar(*ppCStr, c));
                					CHKiRet(strmReadChar(pThis, &c));
+						bPrevWasNL = 0;
 					} else {
 						/* clean things up by putting the character we just read back into
 						 * the input buffer and removing the LF character that is currently at the
 						 * end of the output string */
 						CHKiRet(strmUnreadChar(pThis, c));
-						rsCStrTruncate(*ppCStr,1);
+						rsCStrTruncate(*ppCStr, (bEscapeLF) ? 4 : 1);
 						finished=1;
 					}
+				} else { /* not the first character after a newline, add it to the buffer */
+					if(c == '\n') {
+						bPrevWasNL = 1;
+						if(bEscapeLF) {
+							CHKiRet(rsCStrAppendStrWithLen(*ppCStr, (uchar*)"#012", sizeof("#012")-1));
+						} else {
+							CHKiRet(cstrAppendChar(*ppCStr, c));
+						}
+					} else {
+						CHKiRet(cstrAppendChar(*ppCStr, c));
+					}
+               				CHKiRet(strmReadChar(pThis, &c));
 				}
 			}
 		}