mailinfo: More carefully parse header lines in read_one_header_line()

We exited prematurely from header parsing loop when the header
field did not have a space after the colon but we insisted on
it, and we got the check wrong because we forgot that we strip
the trailing whitespace before we do the check.

The space after the colon is not even required by RFC2822, so
stop requiring it.  While we are at it, the header line is
specified to be more strict than "anything with a colon in it"
(there must be one or more characters before the colon, and they
must not be controls, SP or non US-ASCII), so implement that
check as well, lest we mistakenly think something like:

Bogus not a header line: this is not.

as a header line.

Signed-off-by: Junio C Hamano <junkio@cox.net>

diff --git a/mailinfo.c b/mailinfo.c
index 241bfb9e25d54ab2620c456830ad622db9405023..88f9fbb198a7343715fb01c64c72044a7abaedab 100644 (file)
--- a/mailinfo.c
+++ b/mailinfo.c
@@ -382,19 +382,40 @@ static void check_header_line(char *line)
        check_header(line, header);
 }
 
        check_header(line, header);
 }
 

+static int is_rfc2822_header(char *line)
+{
+       /*
+        * The section that defines the loosest possible
+        * field name is "3.6.8 Optional fields".
+        *
+        * optional-field = field-name ":" unstructured CRLF
+        * field-name = 1*ftext
+        * ftext = %d33-57 / %59-126
+        */
+       int ch;
+       char *cp = line;
+       while ((ch = *cp++)) {
+               if (ch == ':')
+                       return cp != line;
+               if ((33 <= ch && ch <= 57) ||
+                   (59 <= ch && ch <= 126))
+                       continue;
+               break;
+       }
+       return 0;
+}
+

 static int read_one_header_line(char *line, int sz, FILE *in)
 {
        int ofs = 0;
        while (ofs < sz) {
 static int read_one_header_line(char *line, int sz, FILE *in)
 {
        int ofs = 0;
        while (ofs < sz) {

-               const char *colon;

                int peek, len;
                if (fgets(line + ofs, sz - ofs, in) == NULL)
                        break;
                len = eatspace(line + ofs);
                if (len == 0)
                        break;
                int peek, len;
                if (fgets(line + ofs, sz - ofs, in) == NULL)
                        break;
                len = eatspace(line + ofs);
                if (len == 0)
                        break;

-               colon = strchr(line, ':');
-               if (!colon || !isspace(colon[1])) {
+               if (!is_rfc2822_header(line)) {

                        /* Re-add the newline */
                        line[ofs + len] = '\n';
                        line[ofs + len + 1] = '\0';
                        /* Re-add the newline */
                        line[ofs + len] = '\n';
                        line[ofs + len + 1] = '\0';