Drop HTML tags when indexing

Wed Mar 22 04:22:59 PDT 2017

Steven Allen pointed out [2] that the previous scanner [1] was a
little too simplistic. This version handles (or claims to) quoted
strings in attributes, which can apparently contain '>'and '<'
characters. This required generalizing the state machine runner a bit
[3] to handle states with out-degree more than two.


[1]: id:20170321131549.19557-1-david at tethera.net
[2]: id:87wpbipl9z.fsf at tesseract.cs.unb.ca
[3]:

diff --git a/lib/index.cc b/lib/index.cc
index 03223f7d..324e6e79 100644
--- a/lib/index.cc
+++ b/lib/index.cc
@@ -122,23 +122,25 @@ do_filter (const scanner_state_t states[],
     register const char *inptr = inbuf;
     const char *inend = inbuf + inlen;
     char *outptr;
-    int next;
+    int next, current;
     (void) prespace;
 
 
     g_mime_filter_set_size (gmime_filter, inlen, FALSE);
     outptr = gmime_filter->outbuf;
 
+    current = filter->state;
     while (inptr < inend) {
-	if (*inptr >= states[filter->state].a &&
-	    *inptr <= states[filter->state].b)
-	{
-	    next = states[filter->state].next_if_match;
-	}
-	else
-	{
-	    next = states[filter->state].next_if_not_match;
-	}
+	/* do "fake transitions" until we fire a rule, or run out of rules */
+	do {
+	    if (*inptr >= states[current].a && *inptr <= states[current].b)  {
+		next = states[current].next_if_match;
+	    } else  {
+		next = states[current].next_if_not_match;
+	    }
+
+	    current = next;
+	} while (next != states[next].state);
 
 	if (filter->state < first_skipping_state)
 	    *outptr++ = *inptr;
@@ -209,7 +211,11 @@ filter_filter_html (GMimeFilter *gmime_filter, char *inbuf, size_t inlen, size_t
 {
     static const scanner_state_t states[] = {
 	{0,  '<',  '<',  1,  0},
+	{1,  '\'', '\'', 4,  2},  /* scanning for quote or > */
+	{1,  '"',  '"',  5,  3},
 	{1,  '>',  '>',  0,  1},
+	{4,  '\'', '\'', 1,  4},  /* inside single quotes */
+	{5,  '"', '"',   1,  5},  /* inside double quotes */
     };
     do_filter(states, 1,
 	      gmime_filter, inbuf, inlen, prespace, outbuf, outlen, outprespace);
diff --git a/test/T680-html-indexing.sh b/test/T680-html-indexing.sh
index ee69209c..74f33708 100755
--- a/test/T680-html-indexing.sh
+++ b/test/T680-html-indexing.sh
@@ -8,4 +8,15 @@ test_begin_subtest 'embedded images should not be indexed'
 notmuch search kwpza7svrgjzqwi8fhb2msggwtxtwgqcxp4wbqr4wjddstqmeqa7 > OUTPUT
 test_expect_equal_file /dev/null OUTPUT
 
+test_begin_subtest 'ignore > in attribute text'
+notmuch search swordfish | notmuch_search_sanitize > OUTPUT
+test_expect_equal_file /dev/null OUTPUT
+
+test_begin_subtest 'non tag text should be indexed'
+notmuch search hunter2 | notmuch_search_sanitize > OUTPUT
+cat <<EOF > EXPECTED
+thread:XXX   2009-11-17 [1/1] David Bremner; test html attachment (inbox unread)
+EOF
+test_expect_equal_file EXPECTED OUTPUT
+
 test_done
diff --git a/test/corpora/html/attribute-text b/test/corpora/html/attribute-text
new file mode 100644
index 00000000..6dae8194
--- /dev/null
+++ b/test/corpora/html/attribute-text
@@ -0,0 +1,15 @@
+From: David Bremner <david at example.net>
+To: David Bremner <david at example.net>
+Subject: test html attachment
+Date: Tue, 17 Nov 2009 21:28:38 +0600
+Message-ID: <87d1dajhgf.fsf at example.net>
+MIME-Version: 1.0
+Content-Type: text/html
+Content-Disposition: inline; filename=test.html
+
+<html>
+  <body>
+    <input value="a>swordfish">
+  </body>
+  hunter2
+</html>

