search: Add stable queries to thread search results

These queries will match exactly the set of messages currently in the
thread, even if more messages later arrive.  Two queries are provided:
one for matched messages and one for unmatched messages.

This can be used to fix race conditions with tagging threads from
search results.  While tagging based on a thread: query can affect
messages that arrived after the search, tagging based on stable
queries affects only the messages the user was shown in the search UI.

Since we want clients to be able to depend on the presence of these
queries, this ushers in schema version 2.

6 files changed, 88 insertions, 7 deletions

diff --git a/devel/schemata b/devel/schemata
index cdd0e433..41dc4a60 100644
--- a/devel/schemata
+++ b/devel/schemata
@@ -14,7 +14,17 @@ are interleaved. Keys are printed as keywords (symbols preceded by a
 colon), e.g. (:id "123" :time 54321 :from "foobar"). Null is printed as
 nil, true as t and false as nil.
 
-This is version 1 of the structured output format.
+This is version 2 of the structured output format.
+
+Version history
+---------------
+
+v1
+- First versioned schema release.
+- Added part.content-length and part.content-transfer-encoding fields.
+
+v2
+- Added the thread_summary.query field.
 
 Common non-terminals
 --------------------
@@ -145,7 +155,15 @@ thread_summary = {
     authors:        string,   # comma-separated names with | between
                               # matched and unmatched
     subject:        string,
-    tags:           [string*]
+    tags:           [string*],
+
+    # Two stable query strings identifying exactly the matched and
+    # unmatched messages currently in this thread.  The messages
+    # matched by these queries will not change even if more messages
+    # arrive in the thread.  If there are no matched or unmatched
+    # messages, the corresponding query will be null (there is no
+    # query that matches nothing).  (Added in schema version 2.)
+    query:          [string|null, string|null],
 }
 
 notmuch reply schema
diff --git a/notmuch-client.h b/notmuch-client.h
index 4ecb3ae9..278b498a 100644
--- a/notmuch-client.h
+++ b/notmuch-client.h
@@ -138,7 +138,7 @@ chomp_newline (char *str)
  * this.  New (required) map fields can be added without increasing
  * this.
  */
-#define NOTMUCH_FORMAT_CUR 1
+#define NOTMUCH_FORMAT_CUR 2
 /* The minimum supported structured output format version.  Requests
  * for format versions below this will return an error. */
 #define NOTMUCH_FORMAT_MIN 1
diff --git a/notmuch-search.c b/notmuch-search.c
index d9d39ec3..7c973b3d 100644
--- a/notmuch-search.c
+++ b/notmuch-search.c
@@ -20,6 +20,7 @@
 
 #include "notmuch-client.h"
 #include "sprinter.h"
+#include "string-util.h"
 
 typedef enum {
     OUTPUT_SUMMARY,
@@ -46,6 +47,45 @@ sanitize_string (const void *ctx, const char *str)
     return out;
 }
 
+/* Return two stable query strings that identify exactly the matched
+ * and unmatched messages currently in thread.  If there are no
+ * matched or unmatched messages, the returned buffers will be
+ * NULL. */
+static int
+get_thread_query (notmuch_thread_t *thread,
+		  char **matched_out, char **unmatched_out)
+{
+    notmuch_messages_t *messages;
+    char *escaped = NULL;
+    size_t escaped_len = 0;
+
+    *matched_out = *unmatched_out = NULL;
+
+    for (messages = notmuch_thread_get_messages (thread);
+	 notmuch_messages_valid (messages);
+	 notmuch_messages_move_to_next (messages))
+    {
+	notmuch_message_t *message = notmuch_messages_get (messages);
+	const char *mid = notmuch_message_get_message_id (message);
+	/* Determine which query buffer to extend */
+	char **buf = notmuch_message_get_flag (
+	    message, NOTMUCH_MESSAGE_FLAG_MATCH) ? matched_out : unmatched_out;
+	/* Add this message's id: query.  Since "id" is an exclusive
+	 * prefix, it is implicitly 'or'd together, so we only need to
+	 * join queries with a space. */
+	if (make_boolean_term (thread, "id", mid, &escaped, &escaped_len) < 0)
+	    return -1;
+	if (*buf)
+	    *buf = talloc_asprintf_append_buffer (*buf, " %s", escaped);
+	else
+	    *buf = talloc_strdup (thread, escaped);
+	if (!*buf)
+	    return -1;
+    }
+    talloc_free (escaped);
+    return 0;
+}
+
 static int
 do_search_threads (sprinter_t *format,
 		   notmuch_query_t *query,
@@ -131,6 +171,25 @@ do_search_threads (sprinter_t *format,
 		format->string (format, authors);
 		format->map_key (format, "subject");
 		format->string (format, subject);
+		if (notmuch_format_version >= 2) {
+		    char *matched_query, *unmatched_query;
+		    if (get_thread_query (thread, &matched_query,
+					  &unmatched_query) < 0) {
+			fprintf (stderr, "Out of memory\n");
+			return 1;
+		    }
+		    format->map_key (format, "query");
+		    format->begin_list (format);
+		    if (matched_query)
+			format->string (format, matched_query);
+		    else
+			format->null (format);
+		    if (unmatched_query)
+			format->string (format, unmatched_query);
+		    else
+			format->null (format);
+		    format->end (format);
+		}
 	    }
 
 	    talloc_free (ctx_quote);
diff --git a/test/json b/test/json
index b87b7f6d..e07a2904 100755
--- a/test/json
+++ b/test/json
@@ -26,6 +26,7 @@ test_expect_equal_json "$output" "[{\"thread\": \"XXX\",
  \"total\": 1,
  \"authors\": \"Notmuch Test Suite\",
  \"subject\": \"json-search-subject\",
+ \"query\": [\"id:$gen_msg_id\", null],
  \"tags\": [\"inbox\",
  \"unread\"]}]"
 
@@ -59,6 +60,7 @@ test_expect_equal_json "$output" "[{\"thread\": \"XXX\",
  \"total\": 1,
  \"authors\": \"Notmuch Test Suite\",
  \"subject\": \"json-search-utf8-body-sübjéct\",
+ \"query\": [\"id:$gen_msg_id\", null],
  \"tags\": [\"inbox\",
  \"unread\"]}]"
 
diff --git a/test/missing-headers b/test/missing-headers
index f14b8784..43e861bc 100755
--- a/test/missing-headers
+++ b/test/missing-headers
@@ -43,7 +43,8 @@ test_expect_equal_json "$output" '
         ],
         "thread": "XXX",
         "timestamp": 978709437,
-        "total": 1
+        "total": 1,
+        "query": ["id:notmuch-sha1-7a6e4eac383ef958fcd3ebf2143db71b8ff01161", null]
     },
     {
         "authors": "Notmuch Test Suite",
@@ -56,7 +57,8 @@ test_expect_equal_json "$output" '
         ],
         "thread": "XXX",
         "timestamp": 0,
-        "total": 1
+        "total": 1,
+        "query": ["id:notmuch-sha1-ca55943aff7a72baf2ab21fa74fab3d632401334", null]
     }
 ]'
 
diff --git a/test/sexp b/test/sexp
index 492a82f7..be815e12 100755
--- a/test/sexp
+++ b/test/sexp
@@ -19,7 +19,7 @@ test_expect_equal "$output" "((((:id \"${gen_msg_id}\" :match t :excluded nil :f
 test_begin_subtest "Search message: sexp"
 add_message "[subject]=\"sexp-search-subject\"" "[date]=\"Sat, 01 Jan 2000 12:00:00 -0000\"" "[body]=\"sexp-search-message\""
 output=$(notmuch search --format=sexp "sexp-search-message" | notmuch_search_sanitize)
-test_expect_equal "$output" "((:thread \"0000000000000002\" :timestamp 946728000 :date_relative \"2000-01-01\" :matched 1 :total 1 :authors \"Notmuch Test Suite\" :subject \"sexp-search-subject\" :tags (\"inbox\" \"unread\")))"
+test_expect_equal "$output" "((:thread \"0000000000000002\" :timestamp 946728000 :date_relative \"2000-01-01\" :matched 1 :total 1 :authors \"Notmuch Test Suite\" :subject \"sexp-search-subject\" :query (\"id:$gen_msg_id\" nil) :tags (\"inbox\" \"unread\")))"
 
 test_begin_subtest "Show message: sexp, utf-8"
 add_message "[subject]=\"sexp-show-utf8-body-sübjéct\"" "[date]=\"Sat, 01 Jan 2000 12:00:00 -0000\"" "[body]=\"jsön-show-méssage\""
@@ -44,7 +44,7 @@ test_expect_equal "$output" "((((:id \"$id\" :match t :excluded nil :filename \"
 test_begin_subtest "Search message: sexp, utf-8"
 add_message "[subject]=\"sexp-search-utf8-body-sübjéct\"" "[date]=\"Sat, 01 Jan 2000 12:00:00 -0000\"" "[body]=\"jsön-search-méssage\""
 output=$(notmuch search --format=sexp "jsön-search-méssage" | notmuch_search_sanitize)
-test_expect_equal "$output" "((:thread \"0000000000000005\" :timestamp 946728000 :date_relative \"2000-01-01\" :matched 1 :total 1 :authors \"Notmuch Test Suite\" :subject \"sexp-search-utf8-body-sübjéct\" :tags (\"inbox\" \"unread\")))"
+test_expect_equal "$output" "((:thread \"0000000000000005\" :timestamp 946728000 :date_relative \"2000-01-01\" :matched 1 :total 1 :authors \"Notmuch Test Suite\" :subject \"sexp-search-utf8-body-sübjéct\" :query (\"id:$gen_msg_id\" nil) :tags (\"inbox\" \"unread\")))"
 
 
 test_done