summaryrefslogtreecommitdiff
path: root/lib
diff options
context:
space:
mode:
authorKoni Marti <koni.marti@gmail.com>2022-06-14 21:10:48 +0200
committerRobin Jarry <robin@jarry.cc>2022-06-14 22:12:48 +0200
commite1d8bc4d17cb7bd79e19fdf866d1da2fedda4de5 (patch)
treeececff85e82e42a2b95b27b03e53c79768ad0709 /lib
parent4753cfd3e33f985ec22c5600a8d7e68b72175607 (diff)
downloadaerc-e1d8bc4d17cb7bd79e19fdf866d1da2fedda4de5.zip
msgviewer: open http links from messages
Parse http links from a message and display them as completions in the :open-link command. Add the following binds to the [view] section in your binds.conf: <C-l> = :open-link <space> Parsing can be disabled in aerc.conf by setting parse-http-links to false in the viewer section. Thanks to Moritz for the help with the regular expression. Signed-off-by: Koni Marti <koni.marti@gmail.com> Reviewed-by: Moritz Poldrack <git@moritz.sh> Acked-by: Robin Jarry <robin@jarry.cc>
Diffstat (limited to 'lib')
-rw-r--r--lib/parse/hyperlinks.go44
-rw-r--r--lib/parse/hyperlinks_test.go99
2 files changed, 143 insertions, 0 deletions
diff --git a/lib/parse/hyperlinks.go b/lib/parse/hyperlinks.go
new file mode 100644
index 0000000..7a00538
--- /dev/null
+++ b/lib/parse/hyperlinks.go
@@ -0,0 +1,44 @@
+package parse
+
+import (
+ "bufio"
+ "bytes"
+ "io"
+ "regexp"
+ "strings"
+)
+
+var submatch = `(https?:\/\/[-a-zA-Z0-9@:%._\+~#=]{1,256}\.[a-zA-Z0-9()]{1,10}\b(?:[-a-zA-Z0-9()@:%_\+.~#?&\/=]*))`
+var httpRe = regexp.MustCompile("\"" + submatch + "\"" + "|" + "\\(" + submatch + "\\)" + "|" + "<" + submatch + ">" + "|" + submatch)
+
+// HttpLinks searches a reader for a http link and returns a copy of the
+// reader and a slice with links.
+func HttpLinks(r io.Reader) (io.Reader, []string) {
+ var buf bytes.Buffer
+ tr := io.TeeReader(r, &buf)
+
+ scanner := bufio.NewScanner(tr)
+ linkMap := make(map[string]struct{})
+ for scanner.Scan() {
+ line := scanner.Text()
+ if !strings.Contains(line, "http") {
+ continue
+ }
+ for _, word := range strings.Fields(line) {
+ if links := httpRe.FindStringSubmatch(word); len(links) > 0 {
+ for _, l := range links[1:] {
+ if l != "" {
+ linkMap[strings.TrimSpace(l)] = struct{}{}
+ }
+ }
+ }
+ }
+ }
+
+ results := []string{}
+ for link, _ := range linkMap {
+ results = append(results, link)
+ }
+
+ return &buf, results
+}
diff --git a/lib/parse/hyperlinks_test.go b/lib/parse/hyperlinks_test.go
new file mode 100644
index 0000000..f16392a
--- /dev/null
+++ b/lib/parse/hyperlinks_test.go
@@ -0,0 +1,99 @@
+package parse_test
+
+import (
+ "io/ioutil"
+ "strings"
+ "testing"
+
+ "git.sr.ht/~rjarry/aerc/lib/parse"
+)
+
+func TestHyperlinks(t *testing.T) {
+ tests := []struct {
+ text string
+ links []string
+ }{
+ {
+ text: "http://aerc-mail.org",
+ links: []string{"http://aerc-mail.org"},
+ },
+ {
+ text: "https://aerc-mail.org",
+ links: []string{"https://aerc-mail.org"},
+ },
+ {
+ text: "text https://aerc-mail.org more text",
+ links: []string{"https://aerc-mail.org"},
+ },
+ {
+ text: "text (https://aerc-mail.org) more text",
+ links: []string{"https://aerc-mail.org"},
+ },
+ {
+ text: "text \"https://aerc-mail.org\" more text",
+ links: []string{"https://aerc-mail.org"},
+ },
+ {
+ text: "text <https://aerc-mail.org> more text",
+ links: []string{"https://aerc-mail.org"},
+ },
+ {
+ text: "<a href=\"https://aerc-mail.org\">",
+ links: []string{"https://aerc-mail.org"},
+ },
+ {
+ text: "text https://aerc-mail.org more text https://aerc-mail.org more text",
+ links: []string{"https://aerc-mail.org"},
+ },
+ {
+ text: "text https://aerc-mail.org more text http://git.sr.ht/~rjarry/aerc more text",
+ links: []string{"https://aerc-mail.org", "http://git.sr.ht/~rjarry/aerc"},
+ },
+ {
+ text: "text http://www.ietf.org/rfc/rfc2396.txt more text",
+ links: []string{"http://www.ietf.org/rfc/rfc2396.txt"},
+ },
+ {
+ text: "text <http://example.com:8042/over/there?name=ferret#nose> more text",
+ links: []string{"http://example.com:8042/over/there?name=ferret#nose"},
+ },
+ {
+ text: "text http://cnn.example.com&story=breaking_news@10.0.0.1/top_story.htm more text",
+ links: []string{"http://cnn.example.com&story=breaking_news@10.0.0.1/top_story.htm"},
+ },
+ {
+ text: "text https://www.ics.uci.edu/pub/ietf/uri/#Related more text",
+ links: []string{"https://www.ics.uci.edu/pub/ietf/uri/#Related"},
+ },
+ {
+ text: "text https://www.example.com/index.php?id_sezione=360&sid=3a5ebc944f41daa6f849f730f1 more text",
+ links: []string{"https://www.example.com/index.php?id_sezione=360&sid=3a5ebc944f41daa6f849f730f1"},
+ },
+ }
+
+ for _, test := range tests {
+
+ // make sure reader is exact copy of input reader
+ reader, links := parse.HttpLinks(strings.NewReader(test.text))
+ if data, err := ioutil.ReadAll(reader); err != nil {
+ t.Errorf("could not read text: %v", err)
+ } else if string(data) != test.text {
+ t.Errorf("did not copy input reader correctly")
+ }
+
+ // check correct parsed links
+ if len(links) != len(test.links) {
+ t.Errorf("different number of links: got %d but expected %d", len(links), len(test.links))
+ }
+ linkMap := make(map[string]struct{})
+ for _, got := range links {
+ linkMap[got] = struct{}{}
+ }
+ for _, expected := range test.links {
+ if _, ok := linkMap[expected]; !ok {
+ t.Errorf("link not parsed: %s", expected)
+ }
+ }
+
+ }
+}