diff options
Diffstat (limited to 'src/url.rs')
| -rw-r--r-- | src/url.rs | 141 |
1 files changed, 86 insertions, 55 deletions
@@ -12,7 +12,7 @@ // See the License for the specific language governing permissions and // limitations under the License. -use url::Url; +use url; // See https://tools.ietf.org/html/rfc3987#page-13 const URL_SEPARATOR_CHARS: [char; 10] = ['<', '>', '"', ' ', '{', '}', '|', '\\', '^', '`']; @@ -21,21 +21,35 @@ const URL_SCHEMES: [&str; 8] = [ "http", "https", "mailto", "news", "file", "git", "ssh", "ftp", ]; -// Parser for streaming inside-out detection of URLs. +/// URL text and origin of the original click position. +#[derive(Debug, PartialEq)] +pub struct Url { + pub text: String, + pub origin: usize, +} + +/// Parser for streaming inside-out detection of URLs. pub struct UrlParser { state: String, + origin: usize, } impl UrlParser { pub fn new() -> Self { UrlParser { state: String::new(), + origin: 0, } } /// Advance the parser one character to the left. pub fn advance_left(&mut self, c: char) -> bool { - self.advance(c, 0) + if self.advance(c, 0) { + true + } else { + self.origin += 1; + false + } } /// Advance the parser one character to the right. @@ -44,7 +58,7 @@ impl UrlParser { } /// Returns the URL if the parser has found any. - pub fn url(mut self) -> Option<String> { + pub fn url(mut self) -> Option<Url> { // Remove non-alphabetical characters before the scheme // https://tools.ietf.org/html/rfc3986#section-3.1 if let Some(index) = self.state.find("://") { @@ -57,6 +71,7 @@ impl UrlParser { match c { 'a'...'z' | 'A'...'Z' => (), _ => { + self.origin = self.origin.saturating_sub(byte_index + 1); self.state = self.state.split_off(byte_index + c.len_utf8()); break; } @@ -97,10 +112,13 @@ impl UrlParser { } // Check if string is valid url - match Url::parse(&self.state) { + match url::Url::parse(&self.state) { Ok(url) => { - if URL_SCHEMES.contains(&url.scheme()) { - Some(self.state) + if URL_SCHEMES.contains(&url.scheme()) && self.origin > 0 { + Some(Url { + text: self.state, + origin: self.origin - 1, + }) } else { None } @@ -155,12 +173,10 @@ mod tests { term } - fn url_test(input: &str, expected: &str, click_index: usize) { + fn url_test(input: &str, expected: &str) { let term = url_create_term(input); - - let url = term.url_search(Point::new(0, Column(click_index))); - - assert_eq!(url, Some(expected.into())); + let url = term.url_search(Point::new(0, Column(15))); + assert_eq!(url.map(|u| u.text), Some(expected.into())); } #[test] @@ -168,72 +184,87 @@ mod tests { let term = url_create_term("no url here"); let url = term.url_search(Point::new(0, Column(4))); assert_eq!(url, None); + + let term = url_create_term(" https://example.org"); + let url = term.url_search(Point::new(0, Column(0))); + assert_eq!(url, None); + } + + #[test] + fn url_origin() { + let term = url_create_term(" test https://example.org "); + let url = term.url_search(Point::new(0, Column(10))); + assert_eq!(url.map(|u| u.origin), Some(4)); + + let term = url_create_term("https://example.org"); + let url = term.url_search(Point::new(0, Column(0))); + assert_eq!(url.map(|u| u.origin), Some(0)); } #[test] fn url_matching_chars() { - url_test("(https://example.org/test(ing))", "https://example.org/test(ing)", 5); - url_test("https://example.org/test(ing)", "https://example.org/test(ing)", 5); - url_test("((https://example.org))", "https://example.org", 5); - url_test(")https://example.org(", "https://example.org", 5); - url_test("https://example.org)", "https://example.org", 5); - url_test("https://example.org(", "https://example.org", 5); - url_test("(https://one.org/)(https://two.org/)", "https://one.org", 5); - - url_test("https://[2001:db8:a0b:12f0::1]:80", "https://[2001:db8:a0b:12f0::1]:80", 5); - url_test("([(https://example.org/test(ing))])", "https://example.org/test(ing)", 5); - url_test("https://example.org/]()", "https://example.org", 5); - url_test("[https://example.org]", "https://example.org", 5); - - url_test("'https://example.org/test'ing'''", "https://example.org/test'ing'", 5); - url_test("https://example.org/test'ing'", "https://example.org/test'ing'", 5); - url_test("'https://example.org'", "https://example.org", 5); - url_test("'https://example.org", "https://example.org", 5); - url_test("https://example.org'", "https://example.org", 5); + url_test("(https://example.org/test(ing))", "https://example.org/test(ing)"); + url_test("https://example.org/test(ing)", "https://example.org/test(ing)"); + url_test("((https://example.org))", "https://example.org"); + url_test(")https://example.org(", "https://example.org"); + url_test("https://example.org)", "https://example.org"); + url_test("https://example.org(", "https://example.org"); + url_test("(https://one.org/)(https://two.org/)", "https://one.org"); + + url_test("https://[2001:db8:a0b:12f0::1]:80", "https://[2001:db8:a0b:12f0::1]:80"); + url_test("([(https://example.org/test(ing))])", "https://example.org/test(ing)"); + url_test("https://example.org/]()", "https://example.org"); + url_test("[https://example.org]", "https://example.org"); + + url_test("'https://example.org/test'ing'''", "https://example.org/test'ing'"); + url_test("https://example.org/test'ing'", "https://example.org/test'ing'"); + url_test("'https://example.org'", "https://example.org"); + url_test("'https://example.org", "https://example.org"); + url_test("https://example.org'", "https://example.org"); } #[test] fn url_detect_end() { - url_test("https://example.org/test\u{00}ing", "https://example.org/test", 5); - url_test("https://example.org/test\u{1F}ing", "https://example.org/test", 5); - url_test("https://example.org/test\u{7F}ing", "https://example.org/test", 5); - url_test("https://example.org/test\u{9F}ing", "https://example.org/test", 5); - url_test("https://example.org/test\ting", "https://example.org/test", 5); - url_test("https://example.org/test ing", "https://example.org/test", 5); + url_test("https://example.org/test\u{00}ing", "https://example.org/test"); + url_test("https://example.org/test\u{1F}ing", "https://example.org/test"); + url_test("https://example.org/test\u{7F}ing", "https://example.org/test"); + url_test("https://example.org/test\u{9F}ing", "https://example.org/test"); + url_test("https://example.org/test\ting", "https://example.org/test"); + url_test("https://example.org/test ing", "https://example.org/test"); } #[test] fn url_remove_end_chars() { - url_test("https://example.org/test?ing", "https://example.org/test?ing", 5); - url_test("https://example.org.,;:)'!/?", "https://example.org", 5); - url_test("https://example.org'.", "https://example.org", 5); + url_test("https://example.org/test?ing", "https://example.org/test?ing"); + url_test("https://example.org.,;:)'!/?", "https://example.org"); + url_test("https://example.org'.", "https://example.org"); } #[test] fn url_remove_start_chars() { - url_test("complicated:https://example.org", "https://example.org", 15); - url_test("test.https://example.org", "https://example.org", 10); - url_test(",https://example.org", "https://example.org", 5); - url_test("\u{2502}https://example.org", "https://example.org", 5); + url_test("complicated:https://example.org", "https://example.org"); + url_test("test.https://example.org", "https://example.org"); + url_test(",https://example.org", "https://example.org"); + url_test("\u{2502}https://example.org", "https://example.org"); } #[test] fn url_unicode() { - url_test("https://xn--example-2b07f.org", "https://xn--example-2b07f.org", 5); - url_test("https://example.org/\u{2008A}", "https://example.org/\u{2008A}", 5); - url_test("https://example.org/\u{f17c}", "https://example.org/\u{f17c}", 5); - url_test("https://üñîçøðé.com/ä", "https://üñîçøðé.com/ä", 5); + url_test("https://xn--example-2b07f.org", "https://xn--example-2b07f.org"); + url_test("https://example.org/\u{2008A}", "https://example.org/\u{2008A}"); + url_test("https://example.org/\u{f17c}", "https://example.org/\u{f17c}"); + url_test("https://üñîçøðé.com/ä", "https://üñîçøðé.com/ä"); } #[test] fn url_schemes() { - url_test("mailto://example.org", "mailto://example.org", 5); - url_test("https://example.org", "https://example.org", 5); - url_test("http://example.org", "http://example.org", 5); - url_test("news://example.org", "news://example.org", 5); - url_test("file://example.org", "file://example.org", 5); - url_test("git://example.org", "git://example.org", 5); - url_test("ssh://example.org", "ssh://example.org", 5); - url_test("ftp://example.org", "ftp://example.org", 5); + url_test("mailto://example.org", "mailto://example.org"); + url_test("https://example.org", "https://example.org"); + url_test("http://example.org", "http://example.org"); + url_test("news://example.org", "news://example.org"); + url_test("file://example.org", "file://example.org"); + url_test("git://example.org", "git://example.org"); + url_test("ssh://example.org", "ssh://example.org"); + url_test("ftp://example.org", "ftp://example.org"); } } |