[PATCH 2/5] util: Function to parse boolean term queries

[Austin Clements <amdragon@MIT.EDU>]

This reproduces Xapian's parsing rules for boolean term queries.  This
is provided as a generic string utility, but will be used shortly in
notmuch restore to parse and optimize for ID queries.
---
 util/string-util.c |   63 ++++++++++++++++++++++++++++++++++++++++++++++++++++
 util/string-util.h |   11 +++++++++
 2 files changed, 74 insertions(+)

diff --git a/util/string-util.c b/util/string-util.c
index 161a4dd..eaa6c99 100644
--- a/util/string-util.c
+++ b/util/string-util.c
@@ -94,3 +94,66 @@ make_boolean_term (void *ctx, const char *prefix, const char *term,
 
     return 0;
 }
+
+static int
+consume_double_quote (const char **str)
+{
+    if (**str == '"') {
+	++*str;
+	return 1;
+    } else if (strncmp(*str, "\xe2\x80\x9c", 3) == 0 || /* UTF8 0x201c */
+	       strncmp(*str, "\xe2\x80\x9d", 3) == 0) { /* UTF8 0x201d */
+	*str += 3;
+	return 3;
+    } else {
+	return 0;
+    }
+}
+
+int
+parse_boolean_term (void *ctx, const char *str,
+		    char **prefix_out, char **term_out)
+{
+    *prefix_out = *term_out = NULL;
+
+    /* Parse prefix */
+    const char *pos = strchr (str, ':');
+    if (! pos)
+	goto FAIL;
+    *prefix_out = talloc_strndup (ctx, str, pos - str);
+    ++pos;
+
+    /* Implement Xapian's boolean term de-quoting.  This is a nearly
+     * direct translation of QueryParser::Internal::parse_query. */
+    pos = *term_out = talloc_strdup (ctx, pos);
+    if (consume_double_quote (&pos)) {
+	char *out = talloc_strdup (ctx, pos);
+	pos = *term_out = out;
+	while (1) {
+	    if (! *pos) {
+		/* Premature end of string */
+		goto FAIL;
+	    } else if (*pos == '"') {
+		if (*++pos != '"')
+		    break;
+	    } else if (consume_double_quote (&pos)) {
+		break;
+	    }
+	    *out++ = *pos++;
+	}
+	if (*pos)
+	    goto FAIL;
+	*out = '\0';
+    } else {
+	while (*pos > ' ' && *pos != ')')
+	    ++pos;
+	if (*pos)
+	    goto FAIL;
+    }
+    return 0;
+
+ FAIL:
+    talloc_free (*prefix_out);
+    talloc_free (*term_out);
+    return 1;
+}
diff --git a/util/string-util.h b/util/string-util.h
index 7475e2c..e4e4c42 100644
--- a/util/string-util.h
+++ b/util/string-util.h
@@ -28,4 +28,15 @@ 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, returning the prefix in *prefix_out and
+ * the term in *term_out.  *prefix_out and *term_out will be talloc'd
+ * with context ctx.
+ *
+ * Return: 0 on success, non-zero on parse error (including trailing
+ * data in str).
+ */
+int
+parse_boolean_term (void *ctx, const char *str,
+		    char **prefix_out, char **term_out);
+
 #endif
-- 
1.7.10.4