util: Function to parse boolean term queries

This parses the subset of Xapian's boolean term quoting rules that are
used by make_boolean_term.  This is provided as a generic string
utility, but will be used shortly in notmuch restore to parse and
optimize for ID queries.

diff --git a/util/string-util.c b/util/string-util.c
index 7a71049a098d70d7788e13098ac6c28c3d33f6e3..aba9aa836e6522c7c51be56458dfee6fd48618cb 100644 (file)
--- a/util/string-util.c
+++ b/util/string-util.c
@@ -22,6 +22,7 @@
 #include "string-util.h"
 #include "talloc.h"
 
+#include <ctype.h>
 #include <errno.h>
 
 char *
@@ -107,3 +108,84 @@ make_boolean_term (void *ctx, const char *prefix, const char *term,
 
     return 0;
 }
+
+static const char*
+skip_space (const char *str)
+{
+    while (*str && isspace ((unsigned char) *str))
+       ++str;
+    return str;
+}
+
+int
+parse_boolean_term (void *ctx, const char *str,
+                   char **prefix_out, char **term_out)
+{
+    int err = EINVAL;
+    *prefix_out = *term_out = NULL;
+
+    /* Parse prefix */
+    str = skip_space (str);
+    const char *pos = strchr (str, ':');
+    if (! pos)
+       goto FAIL;
+    *prefix_out = talloc_strndup (ctx, str, pos - str);
+    if (! *prefix_out) {
+       err = ENOMEM;
+       goto FAIL;
+    }
+    ++pos;
+
+    /* Implement de-quoting compatible with make_boolean_term. */
+    if (*pos == '"') {
+       char *out = talloc_array (ctx, char, strlen (pos));
+       int closed = 0;
+       if (! out) {
+           err = ENOMEM;
+           goto FAIL;
+       }
+       *term_out = out;
+       /* Skip the opening quote, find the closing quote, and
+        * un-double doubled internal quotes. */
+       for (++pos; *pos; ) {
+           if (*pos == '"') {
+               ++pos;
+               if (*pos != '"') {
+                   /* Found the closing quote. */
+                   closed = 1;
+                   pos = skip_space (pos);
+                   break;
+               }
+           }
+           *out++ = *pos++;
+       }
+       /* Did the term terminate without a closing quote or is there
+        * trailing text after the closing quote? */
+       if (!closed || *pos)
+           goto FAIL;
+       *out = '\0';
+    } else {
+       const char *start = pos;
+       /* Check for text after the boolean term. */
+       while (! is_unquoted_terminator (*pos))
+           ++pos;
+       if (*skip_space (pos)) {
+           err = EINVAL;
+           goto FAIL;
+       }
+       /* No trailing text; dup the string so the caller can free
+        * it. */
+       *term_out = talloc_strndup (ctx, start, pos - start);
+       if (! *term_out) {
+           err = ENOMEM;
+           goto FAIL;
+       }
+    }
+    return 0;
+
+ FAIL:
+    talloc_free (*prefix_out);
+    talloc_free (*term_out);
+    errno = err;
+    return -1;
+}

diff --git a/util/string-util.h b/util/string-util.h
index 719c276a1da908df967e392774f01cd0d6218683..0194607ee52877b9c1adcfc96933d84aab9658f1 100644 (file)
--- a/util/string-util.h
+++ b/util/string-util.h
@@ -34,4 +34,20 @@ char *strtok_len (char *s, const char *delim, size_t *len);
 int make_boolean_term (void *talloc_ctx, const char *prefix, const char *term,
                       char **buf, size_t *len);
 
+/* Parse a boolean term query consisting of a prefix, a colon, and a
+ * term that may be quoted as described for make_boolean_term.  If the
+ * term is not quoted, then it ends at the first whitespace or close
+ * parenthesis.  str may containing leading or trailing whitespace,
+ * but anything else is considered a parse error.  This is compatible
+ * with anything produced by make_boolean_term, and supports a subset
+ * of the quoting styles supported by Xapian (and hence notmuch).
+ * *prefix_out and *term_out will be talloc'd with context ctx.
+ *
+ * Return: 0 on success, -1 on error.  errno will be set to EINVAL if
+ * there is a parse error or ENOMEM if there is an allocation failure.
+ */
+int
+parse_boolean_term (void *ctx, const char *str,
+                   char **prefix_out, char **term_out);
+
 #endif