From: Austin Clements <amdragon@MIT.EDU>
To: notmuch@notmuchmail.org
Subject: [PATCH v2 2/5] util: Function to parse boolean term queries
Date: Tue, 25 Dec 2012 22:48:40 -0500
Message-Id: <1356493723-11085-3-git-send-email-amdragon@mit.edu>
In-Reply-To: <1356493723-11085-1-git-send-email-amdragon@mit.edu>
References: <1356493723-11085-1-git-send-email-amdragon@mit.edu>
Precedence: list

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.
---
 util/string-util.c |   51 +++++++++++++++++++++++++++++++++++++++++++++++++++
 util/string-util.h |   11 +++++++++++
 2 files changed, 62 insertions(+)

diff --git a/util/string-util.c b/util/string-util.c
index e4bea21..db01b4b 100644
--- a/util/string-util.c
+++ b/util/string-util.c
@@ -96,3 +96,54 @@ make_boolean_term (void *ctx, const char *prefix, const char *term,
 
     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 de-quoting compatible with make_boolean_term. */
+    if (*pos == '"') {
+	char *out = talloc_strdup (ctx, pos + 1);
+	int closed = 0;
+	/* Find the closing quote and un-double doubled internal
+	 * quotes. */
+	for (pos = *term_out = out; *pos; ) {
+	    if (*pos == '"') {
+		++pos;
+		if (*pos != '"') {
+		    /* Found the closing quote. */
+		    closed = 1;
+		    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 {
+	*term_out = talloc_strdup (ctx, pos);
+	/* Check for text after the boolean term. */
+	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..aff2d65 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 produced by make_boolean_term, 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