diff options
| author | Daniel Eklöf <daniel@ekloef.se> | 2025-04-02 06:41:46 +0000 |
|---|---|---|
| committer | Daniel Eklöf <daniel@ekloef.se> | 2025-04-07 07:11:16 +0000 |
| commit | 1760cb6ab82b355a0751f614f3b45c7446e23e95 (patch) | |
| tree | 564bd91d079224003886bdfac807a265f822223d /config.c | |
| parent | Merge branch 'kbd-no-virtual-modifiers' (diff) | |
config: update default URL regex
The old one is in some cases too liberal. The new one is stricter in
two ways:
1. The protocol list is now explicit, rather than matching anything://
2. Allowed characters are now limited to the "safe character set", the
"reserved character set", and some from the "unsafe character set"
Furthermore, some of the characters are restricted in how/when they
are allowed:
1. Periods, commas, question marks etc are allowed inside an URL, but
not at the end.
2. [ ], ( ), " " and ' ' are allowed but only when balanced. This
allows us to match e.g. [http://foo.bar/foo[bar]] correctly.
Closes #2016
Diffstat (limited to 'config.c')
| -rw-r--r-- | config.c | 69 |
1 files changed, 38 insertions, 31 deletions
@@ -3446,39 +3446,46 @@ config_load(struct config *conf, const char *conf_path, tokenize_cmdline("xdg-open ${url}", &conf->url.launch.argv.args); { - /* - * Based on https://gist.github.com/gruber/249502, but modified: - * - Do not allow {} at all - * - Do allow matched [] - */ - const char *url_regex_string = + const char *url_regex_string = + "(" + "(" + "(https?://|mailto:|ftp://|file:|ssh:|ssh://|git://|tel:|magnet:|ipfs://|ipns://|gemini://|gopher://|news:)" + "|" + "www\\." + ")" + "(" + /* Safe + reserved + some unsafe characters parenthesis and double quotes omitted (we only allow them when balanced) */ + "[0-9a-zA-Z:/?#@!$&*+,;=.~_%^\\-]+" + "|" + /* Balanced "(...)". Content is same as above, plus all _other_ characters we require to be balanced */ + "\\([]\\[\"0-9a-zA-Z:/?#@!$&'*+,;=.~_%^\\-]*\\)" + "|" + /* Balanced "[...]". Content is same as above, plus all _other_ characters we require to be balanced */ + "\\[[\\(\\)\"0-9a-zA-Z:/?#@!$&'*+,;=.~_%^\\-]*\\]" + "|" + /* Balanced '"..."'. Content is same as above, plus all _other_ characters we require to be balanced */ + "\"[]\\[\\(\\)0-9a-zA-Z:/?#@!$&'*+,;=.~_%^\\-]*\"" + "|" + /* Balanced "'...'". Content is same as above, plus all _other_ characters we require to be balanced */ + "'[]\\[\\(\\)0-9a-zA-Z:/?#@!$&*+,;=.~_%^\\-]*'" + ")+" "(" - "(" - "[a-z][[:alnum:]-]+:" // protocol - "(" - "/{1,3}|[a-z0-9%]" // slashes (what's the OR part for?) - ")" - "|" - "www[:digit:]{0,3}[.]" - //"|" - //"[a-z0-9.\\-]+[.][a-z]{2,4}/" /* "looks like domain name followed by a slash" - remove? */ - ")" - "(" - "[^[:space:](){}<>]+" - "|" - "\\(([^[:space:](){}<>]+|(\\([^[:space:](){}<>]+\\)))*\\)" - "|" - "\\[([^]\\[[:space:](){}<>]+|(\\[[^]\\[[:space:](){}<>]+\\]))*\\]" - ")+" - "(" - "\\(([^[:space:](){}<>]+|(\\([^[:space:](){}<>]+\\)))*\\)" - "|" - "\\[([^]\\[[:space:](){}<>]+|(\\[[^]\\[[:space:](){}<>]+\\]))*\\]" - "|" - "[^]\\[[:space:]`!(){};:'\".,<>?«»“”‘’]" - ")" + /* Same as above, except :?!,;. are excluded */ + "[0-9a-zA-Z/#@$&*+=~_%^\\-]" + "|" + /* Balanced "(...)". Content is same as above, plus all _other_ characters we require to be balanced */ + "\\([]\\[\"0-9a-zA-Z:/?#@!$&'*+,;=.~_%^\\-]*\\)" + "|" + /* Balanced "[...]". Content is same as above, plus all _other_ characters we require to be balanced */ + "\\[[\\(\\)\"0-9a-zA-Z:/?#@!$&'*+,;=.~_%^\\-]*\\]" + "|" + /* Balanced '"..."'. Content is same as above, plus all _other_ characters we require to be balanced */ + "\"[]\\[\\(\\)0-9a-zA-Z:/?#@!$&'*+,;=.~_%^\\-]*\"" + "|" + /* Balanced "'...'". Content is same as above, plus all _other_ characters we require to be balanced */ + "'[]\\[\\(\\)0-9a-zA-Z:/?#@!$&*+,;=.~_%^\\-]*'" ")" - ; + ")"; int r = regcomp(&conf->url.preg, url_regex_string, REG_EXTENDED); xassert(r == 0); |
