util: Factor out boolean term quoting routine

This is now a generic boolean term quoting function.  It performs
minimal quoting to produce user-friendly queries.

This could live in tag-util as well, but it is really nothing specific
to tags (although the conventions are specific to Xapian).

The API is changed from "caller-allocates" to "readline-like".  The
scan for max tag length is pushed down into the quoting routine.
Furthermore, this now combines the term prefix with the quoted term;
arguably this is just as easy to do in the caller, but this will
nicely parallel the boolean term parsing function to be introduced
shortly.

This is an amalgamation of code written by David Bremner and myself.

diff --git a/notmuch-tag.c b/notmuch-tag.c
index 88d559be77cd6bb12349e2a12238bfb7090b0f38..fc9d43a7cb21dc2187bea3ca2544495ff496c414 100644 (file)
--- a/notmuch-tag.c
+++ b/notmuch-tag.c
@@ -19,6 +19,7 @@
  */
 
 #include "notmuch-client.h"
+#include "string-util.h"
 
 static volatile sig_atomic_t interrupted;
 
@@ -35,25 +36,6 @@ handle_sigint (unused (int sig))
     interrupted = 1;
 }
 
-static char *
-_escape_tag (char *buf, const char *tag)
-{
-    const char *in = tag;
-    char *out = buf;
-
-    /* Boolean terms surrounded by double quotes can contain any
-     * character.  Double quotes are quoted by doubling them. */
-    *out++ = '"';
-    while (*in) {
-       if (*in == '"')
-           *out++ = '"';
-       *out++ = *in++;
-    }
-    *out++ = '"';
-    *out = 0;
-    return buf;
-}
-
 typedef struct {
     const char *tag;
     notmuch_bool_t remove;
@@ -71,25 +53,16 @@ _optimize_tag_query (void *ctx, const char *orig_query_string,
      * parenthesize and the exclusion part of the query must not use
      * the '-' operator (though the NOT operator is fine). */
 
-    char *escaped, *query_string;
+    char *escaped = NULL;
+    size_t escaped_len = 0;
+    char *query_string;
     const char *join = "";
-    int i;
-    unsigned int max_tag_len = 0;
+    size_t i;
 
     /* Don't optimize if there are no tag changes. */
     if (tag_ops[0].tag == NULL)
        return talloc_strdup (ctx, orig_query_string);
 
-    /* Allocate a buffer for escaping tags.  This is large enough to
-     * hold a fully escaped tag with every character doubled plus
-     * enclosing quotes and a NUL. */
-    for (i = 0; tag_ops[i].tag; i++)
-       if (strlen (tag_ops[i].tag) > max_tag_len)
-           max_tag_len = strlen (tag_ops[i].tag);
-    escaped = talloc_array (ctx, char, max_tag_len * 2 + 3);
-    if (! escaped)
-       return NULL;
-
     /* Build the new query string */
     if (strcmp (orig_query_string, "*") == 0)
        query_string = talloc_strdup (ctx, "(");
@@ -97,10 +70,17 @@ _optimize_tag_query (void *ctx, const char *orig_query_string,
        query_string = talloc_asprintf (ctx, "( %s ) and (", orig_query_string);
 
     for (i = 0; tag_ops[i].tag && query_string; i++) {
+       /* XXX in case of OOM, query_string will be deallocated when
+        * ctx is, which might be at shutdown */
+       if (make_boolean_term (ctx,
+                              "tag", tag_ops[i].tag,
+                              &escaped, &escaped_len))
+           return NULL;
+
        query_string = talloc_asprintf_append_buffer (
-           query_string, "%s%stag:%s", join,
+           query_string, "%s%s%s", join,
            tag_ops[i].remove ? "" : "not ",
-           _escape_tag (escaped, tag_ops[i].tag));
+           escaped);
        join = " or ";
     }
 

diff --git a/util/string-util.c b/util/string-util.c
index 44f8cd3a252ae2ba409ad1861202398a76e56c6f..7a71049a098d70d7788e13098ac6c28c3d33f6e3 100644 (file)
--- a/util/string-util.c
+++ b/util/string-util.c
@@ -20,6 +20,9 @@
 
 
 #include "string-util.h"
+#include "talloc.h"
+
+#include <errno.h>
 
 char *
 strtok_len (char *s, const char *delim, size_t *len)
@@ -32,3 +35,75 @@ strtok_len (char *s, const char *delim, size_t *len)
 
     return *len ? s : NULL;
 }
+
+static int
+is_unquoted_terminator (unsigned char c)
+{
+    return c == 0 || c <= ' ' || c == ')';
+}
+
+int
+make_boolean_term (void *ctx, const char *prefix, const char *term,
+                  char **buf, size_t *len)
+{
+    const char *in;
+    char *out;
+    size_t needed = 3;
+    int need_quoting = 0;
+
+    /* Do we need quoting?  To be paranoid, we quote anything
+     * containing a quote, even though it only matters at the
+     * beginning, and anything containing non-ASCII text. */
+    for (in = term; *in && !need_quoting; in++)
+       if (is_unquoted_terminator (*in) || *in == '"'
+           || (unsigned char)*in > 127)
+           need_quoting = 1;
+
+    if (need_quoting)
+       for (in = term; *in; in++)
+           needed += (*in == '"') ? 2 : 1;
+    else
+       needed = strlen (term) + 1;
+
+    /* Reserve space for the prefix */
+    if (prefix)
+       needed += strlen (prefix) + 1;
+
+    if ((*buf == NULL) || (needed > *len)) {
+       *len = 2 * needed;
+       *buf = talloc_realloc (ctx, *buf, char, *len);
+    }
+
+    if (! *buf) {
+       errno = ENOMEM;
+       return -1;
+    }
+
+    out = *buf;
+
+    /* Copy in the prefix */
+    if (prefix) {
+       strcpy (out, prefix);
+       out += strlen (prefix);
+       *out++ = ':';
+    }
+
+    if (! need_quoting) {
+       strcpy (out, term);
+       return 0;
+    }
+
+    /* Quote term by enclosing it in double quotes and doubling any
+     * internal double quotes. */
+    *out++ = '"';
+    in = term;
+    while (*in) {
+       if (*in == '"')
+           *out++ = '"';
+       *out++ = *in++;
+    }
+    *out++ = '"';
+    *out = '\0';
+
+    return 0;
+}

diff --git a/util/string-util.h b/util/string-util.h
index ac7676c883d742febbbcc3614f2f6a35a57eefe1..719c276a1da908df967e392774f01cd0d6218683 100644 (file)
--- a/util/string-util.h
+++ b/util/string-util.h
@@ -19,4 +19,19 @@
 
 char *strtok_len (char *s, const char *delim, size_t *len);
 
+/* Construct a boolean term query with the specified prefix (e.g.,
+ * "id") and search term, quoting term as necessary.  Specifically, if
+ * term contains any non-printable ASCII characters, non-ASCII
+ * characters, close parenthesis or double quotes, it will be enclosed
+ * in double quotes and any internal double quotes will be doubled
+ * (e.g. a"b -> "a""b").  The result will be a valid notmuch query and
+ * can be parsed by parse_boolean_term.
+ *
+ * Output is into buf; it may be talloc_realloced.
+ * Return: 0 on success, -1 on error.  errno will be set to ENOMEM if
+ * there is an allocation failure.
+ */
+int make_boolean_term (void *talloc_ctx, const char *prefix, const char *term,
+                      char **buf, size_t *len);
+
 #endif