[Patch v9 06/17] unhex_and_quote: new function to quote hex-decoded queries

[david at tethera.net]

From: David Bremner <bremner at debian.org>

Space delimited tokens are hex decoded and then quoted according to
Xapian rules. Prefixes and '*' are passed through unquoted, as is
anything that hex-decoding would not change.
---
 tag-util.c |   94 ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 94 insertions(+)

diff --git a/tag-util.c b/tag-util.c
index 935c8d9..b9b6099 100644
--- a/tag-util.c
+++ b/tag-util.c
@@ -56,6 +56,100 @@ illegal_tag (const char *tag, notmuch_bool_t remove)
     return NULL;
 }
 
+/* Factor out the boilerplate to append a token to the query string.
+ * For use in unhex_and_quote */
+
+static tag_parse_status_t
+append_tok (const char *tok, size_t tok_len,
+	    const char *line_for_error, char **query_string)
+{
+
+    *query_string = talloc_strndup_append_buffer (*query_string, tok, tok_len);
+    if (*query_string == NULL)
+	return line_error (TAG_PARSE_OUT_OF_MEMORY, line_for_error, "aborting");
+
+    return TAG_PARSE_SUCCESS;
+}
+
+/* Input is a hex encoded string, presumed to be a query for Xapian.
+ *
+ * Space delimited tokens are decoded and quoted, with '*' and prefixes
+ * of the form "foo:" passed through unquoted.
+ */
+static tag_parse_status_t
+unhex_and_quote (void *ctx, char *encoded, const char *line_for_error,
+		 char **query_string)
+{
+    char *tok = encoded;
+    size_t tok_len = 0;
+    size_t delim_len = 0;
+    char *buf = NULL;
+    size_t buf_len = 0;
+    tag_parse_status_t ret = TAG_PARSE_SUCCESS;
+
+    *query_string = talloc_strdup (ctx, "");
+
+    while ((tok = strtok_len2 (tok + tok_len + delim_len, " ()",
+			       &tok_len, &delim_len)) != NULL) {
+
+	size_t prefix_len;
+	char delim = *(tok + tok_len);
+
+	*(tok + tok_len) = '\0';
+
+	/* The following matches a superset of prefixes currently
+	 * used by notmuch */
+	prefix_len = strspn (tok, "abcdefghijklmnopqrstuvwxyz");
+
+	if ((strcmp (tok, "*") == 0) || prefix_len == tok_len) {
+
+	    /* pass some things through without quoting or decoding.
+	     * Note for '*' this is mandatory.
+	     */
+
+	    ret = append_tok (tok, tok_len, line_for_error, query_string);
+	    if (ret) goto DONE;
+
+	} else {
+	    /* potential prefix: one for ':', then something after */
+	    if ((tok_len - prefix_len >= 2) && *(tok + prefix_len) == ':') {
+		ret = append_tok (tok, prefix_len + 1,
+				  line_for_error, query_string);
+		if (ret) goto DONE;
+
+		tok += prefix_len + 1;
+		tok_len -= prefix_len + 1;
+	    }
+
+	    if (hex_decode_inplace (tok) != HEX_SUCCESS) {
+		ret = line_error (TAG_PARSE_INVALID, line_for_error,
+				  "hex decoding of token '%s' failed", tok);
+		goto DONE;
+	    }
+
+	    if (double_quote_str (ctx, tok, &buf, &buf_len)) {
+		ret = line_error (TAG_PARSE_OUT_OF_MEMORY,
+				  line_for_error, "aborting");
+		goto DONE;
+	    }
+
+	    ret = append_tok (buf, buf_len, line_for_error, query_string);
+	    if (ret) goto DONE;
+	}
+	/* restore the string */
+	*(tok + tok_len) = delim;
+
+	/* copy any delimiters */
+	ret = append_tok (tok + tok_len, delim_len, line_for_error, query_string);
+	if (ret) goto DONE;
+    }
+
+  DONE:
+    if (ret != TAG_PARSE_SUCCESS && *query_string)
+	talloc_free (*query_string);
+    return ret;
+}
+
 tag_parse_status_t
 parse_tag_line (void *ctx, char *line,
 		tag_op_flag_t flags,
-- 
1.7.10.4