Applies new UrlDetector to the RichTextViewer

This commit is contained in:
Vitor Pamplona
2026-03-07 16:38:25 -05:00
parent 030921c963
commit e3f99051db
12 changed files with 178 additions and 73 deletions
@@ -79,7 +79,7 @@ object CachedUrlParser {
cached cached
} else { } else {
val urlSet = UrlParser().parseValidUrls(content) val urlSet = UrlParser().parseValidUrls(content)
val newUrls = urlSet.withScheme.filter { it.startsWith("http") } + urlSet.withoutScheme.map { "http://$it" } val newUrls = urlSet.withScheme.filter { it.startsWith("http") } + urlSet.withoutScheme.map { "http://$it" } + urlSet.bech32s.map { "http://$it" }
parsedUrlsCache.put(key, newUrls) parsedUrlsCache.put(key, newUrls)
newUrls newUrls
} }
@@ -81,6 +81,7 @@ import com.vitorpamplona.amethyst.commons.richtext.PhoneSegment
import com.vitorpamplona.amethyst.commons.richtext.RegularTextSegment import com.vitorpamplona.amethyst.commons.richtext.RegularTextSegment
import com.vitorpamplona.amethyst.commons.richtext.RelayUrlSegment import com.vitorpamplona.amethyst.commons.richtext.RelayUrlSegment
import com.vitorpamplona.amethyst.commons.richtext.RichTextViewerState import com.vitorpamplona.amethyst.commons.richtext.RichTextViewerState
import com.vitorpamplona.amethyst.commons.richtext.SchemelessUrlSegment
import com.vitorpamplona.amethyst.commons.richtext.SecretEmoji import com.vitorpamplona.amethyst.commons.richtext.SecretEmoji
import com.vitorpamplona.amethyst.commons.richtext.Segment import com.vitorpamplona.amethyst.commons.richtext.Segment
import com.vitorpamplona.amethyst.commons.richtext.VideoSegment import com.vitorpamplona.amethyst.commons.richtext.VideoSegment
@@ -168,6 +169,10 @@ fun RenderStrangeNamePreview() {
is RelayUrlSegment -> { is RelayUrlSegment -> {
ClickableRelayUrl(word.segmentText, EmptyNav()) ClickableRelayUrl(word.segmentText, EmptyNav())
} }
is SchemelessUrlSegment -> {
NoProtocolUrlRenderer(word.segmentText)
}
} }
} }
} }
@@ -225,6 +230,10 @@ fun RenderRegularPreview() {
is RegularTextSegment -> { is RegularTextSegment -> {
Text(word.segmentText) Text(word.segmentText)
} }
is SchemelessUrlSegment -> {
NoProtocolUrlRenderer(word.segmentText)
}
} }
} }
} }
@@ -261,6 +270,8 @@ fun RenderRegularPreview2() {
is RegularTextSegment -> Text(word.segmentText) is RegularTextSegment -> Text(word.segmentText)
is RelayUrlSegment -> ClickableRelayUrl(word.segmentText, EmptyNav()) is RelayUrlSegment -> ClickableRelayUrl(word.segmentText, EmptyNav())
is SchemelessUrlSegment -> NoProtocolUrlRenderer(word.segmentText)
} }
} }
} }
@@ -310,6 +321,8 @@ fun RenderRegularPreview3() {
is RegularTextSegment -> Text(word.segmentText) is RegularTextSegment -> Text(word.segmentText)
is RelayUrlSegment -> ClickableRelayUrl(word.segmentText, EmptyNav()) is RelayUrlSegment -> ClickableRelayUrl(word.segmentText, EmptyNav())
is SchemelessUrlSegment -> NoProtocolUrlRenderer(word.segmentText)
} }
} }
} }
@@ -486,6 +499,8 @@ private fun RenderWordWithoutPreview(
is RegularTextSegment -> Text(word.segmentText) is RegularTextSegment -> Text(word.segmentText)
is RelayUrlSegment -> ClickableRelayUrl(word.segmentText, nav) is RelayUrlSegment -> ClickableRelayUrl(word.segmentText, nav)
is SchemelessUrlSegment -> NoProtocolUrlRenderer(word.segmentText)
} }
} }
@@ -517,6 +532,7 @@ private fun RenderWordWithPreview(
is RegularTextSegment -> Text(word.segmentText) is RegularTextSegment -> Text(word.segmentText)
is Base64Segment -> ZoomableContentView(word.segmentText, state, accountViewModel) is Base64Segment -> ZoomableContentView(word.segmentText, state, accountViewModel)
is RelayUrlSegment -> ClickableRelayUrl(word.segmentText, nav) is RelayUrlSegment -> ClickableRelayUrl(word.segmentText, nav)
is SchemelessUrlSegment -> NoProtocolUrlRenderer(word.segmentText)
} }
} }
@@ -533,6 +549,11 @@ private fun ZoomableContentView(
} }
} }
@Composable
private fun NoProtocolUrlRenderer(url: String) {
ClickableUrl(url, "https://$url")
}
@Composable @Composable
fun RenderCustomEmoji( fun RenderCustomEmoji(
word: String, word: String,
@@ -38,7 +38,7 @@ import com.vitorpamplona.amethyst.commons.model.emphChat.EphemeralChatChannel
import com.vitorpamplona.amethyst.commons.model.nip28PublicChats.PublicChatChannel import com.vitorpamplona.amethyst.commons.model.nip28PublicChats.PublicChatChannel
import com.vitorpamplona.amethyst.commons.model.nip30CustomEmojis.EmojiPackState import com.vitorpamplona.amethyst.commons.model.nip30CustomEmojis.EmojiPackState
import com.vitorpamplona.amethyst.commons.model.nip53LiveActivities.LiveActivitiesChannel import com.vitorpamplona.amethyst.commons.model.nip53LiveActivities.LiveActivitiesChannel
import com.vitorpamplona.amethyst.commons.richtext.RichTextParser import com.vitorpamplona.amethyst.commons.richtext.UrlParser
import com.vitorpamplona.amethyst.model.Account import com.vitorpamplona.amethyst.model.Account
import com.vitorpamplona.amethyst.model.LocalCache import com.vitorpamplona.amethyst.model.LocalCache
import com.vitorpamplona.amethyst.model.Note import com.vitorpamplona.amethyst.model.Note
@@ -517,7 +517,7 @@ open class ChannelNewMessageViewModel :
emojiSuggestions?.reset() emojiSuggestions?.reset()
} }
open fun findUrlInMessage(): String? = RichTextParser().parseValidUrls(message.text).firstOrNull() open fun findUrlInMessage(): String? = UrlParser().parseValidUrls(message.text).withScheme.firstOrNull()
open fun addToMessage(it: String) { open fun addToMessage(it: String) {
updateMessage(TextFieldValue(message.text + " " + it)) updateMessage(TextFieldValue(message.text + " " + it))
@@ -161,7 +161,7 @@ class RichTextParser {
val emojiMap = CustomEmoji.createEmojiMap(tags.lists) val emojiMap = CustomEmoji.createEmojiMap(tags.lists)
val allUrls = urlSet.withScheme + urlSet.withoutScheme + urlSet.emails val allUrls = urlSet.withScheme + urlSet.withoutScheme + urlSet.emails + urlSet.bech32s + urlSet.relayUrls
val newContent = fixMissingSpaces(content, allUrls) val newContent = fixMissingSpaces(content, allUrls)
@@ -280,13 +280,17 @@ class RichTextParser {
} }
} }
if (word.startsWith("ws://") || word.startsWith("wss://")) return RelayUrlSegment(word) if (urls.withoutScheme.contains(word)) return SchemelessUrlSegment(word)
if (urls.withoutScheme.contains(word)) { if (urls.withScheme.contains(word)) return LinkSegment(word)
return LinkSegment("https://$word")
} else if (urls.withScheme.contains(word)) { if (urls.emails.contains(word)) return EmailSegment(word)
return LinkSegment(word)
} if (urls.bech32s.contains(word)) return BechSegment(word)
if (urls.relayUrls.contains(word)) return RelayUrlSegment(word)
if (startsWithNIP19Scheme(word)) return BechSegment(word)
if (CustomEmoji.fastMightContainEmoji(word, emojis) && emojis.any { word.contains(it.key) }) return EmojiSegment(word) if (CustomEmoji.fastMightContainEmoji(word, emojis) && emojis.any { word.contains(it.key) }) return EmojiSegment(word)
@@ -300,10 +304,6 @@ class RichTextParser {
if (EmojiCoder.isCoded(word)) return SecretEmoji(word) if (EmojiCoder.isCoded(word)) return SecretEmoji(word)
if (urls.emails.contains(word)) return EmailSegment(word)
if (startsWithNIP19Scheme(word)) return BechSegment(word)
if (isPotentialPhoneNumber(word) && !isDate(word)) { if (isPotentialPhoneNumber(word) && !isDate(word)) {
if (Patterns.PHONE.matches(word)) return PhoneSegment(word) if (Patterns.PHONE.matches(word)) return PhoneSegment(word)
} }
@@ -143,6 +143,11 @@ class RelayUrlSegment(
segment: String, segment: String,
) : Segment(segment) ) : Segment(segment)
@Immutable
class SchemelessUrlSegment(
segment: String,
) : Segment(segment)
@Immutable @Immutable
class RegularTextSegment( class RegularTextSegment(
segment: String, segment: String,
@@ -27,6 +27,8 @@ class Urls(
val withScheme: Set<String> = emptySet(), val withScheme: Set<String> = emptySet(),
val withoutScheme: Set<String> = emptySet(), val withoutScheme: Set<String> = emptySet(),
val emails: Set<String> = emptySet(), val emails: Set<String> = emptySet(),
val bech32s: Set<String> = emptySet(),
val relayUrls: Set<String> = emptySet(),
) )
class UrlParser { class UrlParser {
@@ -45,7 +47,7 @@ class UrlParser {
} }
} }
fun Url.wroteWithSchema(): Boolean = originalUrl.startsWith(scheme) fun Url.wroteWithSchema(): Boolean = urlMarker.hasScheme()
fun Url.isEmail(): Boolean = fun Url.isEmail(): Boolean =
urlMarker.hasUsernamePassword() && urlMarker.hasUsernamePassword() &&
@@ -54,33 +56,24 @@ class UrlParser {
originalUrl.contains('@') && originalUrl.contains('@') &&
path == "/" path == "/"
fun Char.isValidLastHostnameChar(): Boolean = (this in 'a'..'z' || this in 'A'..'Z' || this in '0'..'9')
fun Url.isValidLastHostnameChar(): Boolean = host[host.length - 1].isValidLastHostnameChar()
fun Url.endsWithHost(): Boolean = originalUrl.endsWith(host)
val notAHostNameChar = "[^a-zA-Z0-9.-]".toRegex()
fun parseValidUrls(content: String): Urls { fun parseValidUrls(content: String): Urls {
val urls = UrlDetector(content).detect() val urls = UrlDetector(content).detect()
val completeUrls = mutableSetOf<String>() val completeUrls = mutableSetOf<String>()
val urlsWithoutScheme = mutableSetOf<String>() val urlsWithoutScheme = mutableSetOf<String>()
val emails = mutableSetOf<String>() val emails = mutableSetOf<String>()
val bech32 = mutableSetOf<String>()
val relays = mutableSetOf<String>()
urls.forEach { urls.forEach {
if (it.isValidTopLevelDomain()) { if (it.isValidTopLevelDomain()) {
if (it.wroteWithSchema()) { if (it.wroteWithSchema()) {
if (it.isValidLastHostnameChar()) { if (it.originalUrl.startsWith("nostr")) {
bech32.add(it.originalUrl)
} else if (it.originalUrl.startsWith("ws")) {
relays.add(it.originalUrl)
} else {
completeUrls.add(it.originalUrl) completeUrls.add(it.originalUrl)
} else if (it.endsWithHost()) {
val match = notAHostNameChar.find(it.host)
if (match != null) {
completeUrls.add(it.originalUrl.substring(0, (it.originalUrl.length - it.host.length) + match.range.first))
} else {
completeUrls.add(it.originalUrl)
}
} }
} else { } else {
// emails are understood as urls from the detector. // emails are understood as urls from the detector.
@@ -99,6 +92,8 @@ class UrlParser {
withScheme = completeUrls, withScheme = completeUrls,
withoutScheme = urlsWithoutScheme, withoutScheme = urlsWithoutScheme,
emails = emails, emails = emails,
bech32s = bech32,
relayUrls = relays,
) )
} }
} }
@@ -70,7 +70,7 @@ class RichTextParserMultibyteTest {
.parseText(text, EmptyTagList, null) .parseText(text, EmptyTagList, null)
assertEquals( assertEquals(
"Vitor, você http://test.com? \uD83E\uDD7A", "Vitor, você http://test.com ? \uD83E\uDD7A",
state.paragraphs.joinToString("\n") { it.words.joinToString(" ") { it.segmentText } }, state.paragraphs.joinToString("\n") { it.words.joinToString(" ") { it.segmentText } },
) )
} }
@@ -157,9 +157,9 @@ class RichTextParserMultibyteTest {
val state = RichTextParser().parseText(text, EmptyTagList, null) val state = RichTextParser().parseText(text, EmptyTagList, null)
val allSegments = state.paragraphs.flatMap { it.words } val allSegments = state.paragraphs.flatMap { it.words }
val urlSegments = allSegments.filterIsInstance<LinkSegment>() val urlSegments = allSegments.filterIsInstance<SchemelessUrlSegment>()
assertTrue("Should have SchemelessUrlSegment", urlSegments.isNotEmpty()) assertTrue("Should have SchemelessUrlSegment", urlSegments.isNotEmpty())
assertTrue("URL should be example.com", urlSegments.any { it.segmentText == "https://example.com" }) assertTrue("URL should be example.com", urlSegments.any { it.segmentText == "example.com" })
val textSegments = allSegments.filterIsInstance<RegularTextSegment>() val textSegments = allSegments.filterIsInstance<RegularTextSegment>()
assertTrue("Should have prefix ああ", textSegments.any { it.segmentText == "ああ" }) assertTrue("Should have prefix ああ", textSegments.any { it.segmentText == "ああ" })
@@ -172,9 +172,9 @@ class RichTextParserMultibyteTest {
val state = RichTextParser().parseText(text, EmptyTagList, null) val state = RichTextParser().parseText(text, EmptyTagList, null)
val allSegments = state.paragraphs.flatMap { it.words } val allSegments = state.paragraphs.flatMap { it.words }
val urlSegments = allSegments.filterIsInstance<LinkSegment>() val urlSegments = allSegments.filterIsInstance<SchemelessUrlSegment>()
assertTrue("Should have SchemelessUrlSegment", urlSegments.isNotEmpty()) assertTrue("Should have SchemelessUrlSegment", urlSegments.isNotEmpty())
assertTrue("URL should be example.com", urlSegments.any { it.segmentText == "https://example.com" }) assertTrue("URL should be example.com", urlSegments.any { it.segmentText == "example.com" })
val textSegments = allSegments.filterIsInstance<RegularTextSegment>() val textSegments = allSegments.filterIsInstance<RegularTextSegment>()
assertTrue("Should have suffix ああ", textSegments.any { it.segmentText == "ああ" }) assertTrue("Should have suffix ああ", textSegments.any { it.segmentText == "ああ" })
@@ -749,52 +749,52 @@ class RichTextParserTest {
"RegularText(Events (%) Relay)", "RegularText(Events (%) Relay)",
"RegularText(33.4K)", "RegularText(33.4K)",
"RegularText((4.6%))", "RegularText((4.6%))",
"Link(https://relay.shitforce.one)", "SchemelessUrl(relay.shitforce.one)",
"RegularText(32.9K)", "RegularText(32.9K)",
"RegularText((4.6%))", "RegularText((4.6%))",
"Link(https://relayable.org)", "SchemelessUrl(relayable.org)",
"RegularText(26.6K)", "RegularText(26.6K)",
"RegularText((3.7%))", "RegularText((3.7%))",
"Link(https://universe.nostrich.land)", "SchemelessUrl(universe.nostrich.land)",
"RegularText(22.8K)", "RegularText(22.8K)",
"RegularText((3.2%))", "RegularText((3.2%))",
"Link(https://nos.lol)", "SchemelessUrl(nos.lol)",
"RegularText(22.7K)", "RegularText(22.7K)",
"RegularText((3.1%))", "RegularText((3.1%))",
"Link(https://universe.nostrich.land?lang=zh)", "SchemelessUrl(universe.nostrich.land?lang=zh)",
"RegularText(22.5K)", "RegularText(22.5K)",
"RegularText((3.1%))", "RegularText((3.1%))",
"Link(https://universe.nostrich.land?lang=en)", "SchemelessUrl(universe.nostrich.land?lang=en)",
"RegularText(21.2K)", "RegularText(21.2K)",
"RegularText((2.9%))", "RegularText((2.9%))",
"Link(https://relay.damus.io)", "SchemelessUrl(relay.damus.io)",
"RegularText(20.6K)", "RegularText(20.6K)",
"RegularText((2.9%))", "RegularText((2.9%))",
"Link(https://relay.nostr.wirednet.jp)", "SchemelessUrl(relay.nostr.wirednet.jp)",
"RegularText(20.1K)", "RegularText(20.1K)",
"RegularText((2.8%))", "RegularText((2.8%))",
"Link(https://offchain.pub)", "SchemelessUrl(offchain.pub)",
"RegularText(19.9K)", "RegularText(19.9K)",
"RegularText((2.8%))", "RegularText((2.8%))",
"Link(https://nostr.rocks)", "SchemelessUrl(nostr.rocks)",
"RegularText(19.5K)", "RegularText(19.5K)",
"RegularText((2.7%))", "RegularText((2.7%))",
"Link(https://relay.wellorder.net)", "SchemelessUrl(relay.wellorder.net)",
"RegularText(19.4K)", "RegularText(19.4K)",
"RegularText((2.7%))", "RegularText((2.7%))",
"Link(https://nostr.oxtr.dev)", "SchemelessUrl(nostr.oxtr.dev)",
"RegularText(19K)", "RegularText(19K)",
"RegularText((2.6%))", "RegularText((2.6%))",
"Link(https://universe.nostrich.land?lang=ja)", "SchemelessUrl(universe.nostrich.land?lang=ja)",
"RegularText(18.4K)", "RegularText(18.4K)",
"RegularText((2.6%))", "RegularText((2.6%))",
"Link(https://relay.mostr.pub)", "SchemelessUrl(relay.mostr.pub)",
"RegularText(17.5K)", "RegularText(17.5K)",
"RegularText((2.4%))", "RegularText((2.4%))",
"Link(https://universe.nostrich.land?lang=zh)", "SchemelessUrl(universe.nostrich.land?lang=zh)",
"RegularText(16.3K)", "RegularText(16.3K)",
"RegularText((2.3%))", "RegularText((2.3%))",
"Link(https://nostr.bitcoiner.social)", "SchemelessUrl(nostr.bitcoiner.social)",
"RegularText()", "RegularText()",
"RegularText(30 day global new events)", "RegularText(30 day global new events)",
"RegularText()", "RegularText()",
@@ -1633,7 +1633,7 @@ class RichTextParserTest {
"RegularText(eb3b94533dafeb8ebd58a4947a3dce11d83a9931c622bdf30a4257d3347ee1bf)", "RegularText(eb3b94533dafeb8ebd58a4947a3dce11d83a9931c622bdf30a4257d3347ee1bf)",
"HashTag(#109)", "HashTag(#109)",
"RegularText(3%)", "RegularText(3%)",
"Link(https://Nostr-Check.com)", "SchemelessUrl(Nostr-Check.com)",
"RegularText(,)", "RegularText(,)",
"Email(freeverification@Nostr-Check.com)", "Email(freeverification@Nostr-Check.com)",
"RegularText(-)", "RegularText(-)",
@@ -1910,7 +1910,7 @@ class RichTextParserTest {
"RegularText(d162a53c3b0bfb5c3ebd787d7b08feab206b112362eca25aa291251cd70fe225)", "RegularText(d162a53c3b0bfb5c3ebd787d7b08feab206b112362eca25aa291251cd70fe225)",
"HashTag(#154)", "HashTag(#154)",
"RegularText(3%)", "RegularText(3%)",
"Link(https://MR.Rabbit)", "SchemelessUrl(MR.Rabbit)",
"RegularText(,)", "RegularText(,)",
"Email(Mr.Rabbit@BitcoinNostr.com)", "Email(Mr.Rabbit@BitcoinNostr.com)",
"RegularText(-)", "RegularText(-)",
@@ -2087,7 +2087,7 @@ class RichTextParserTest {
"RegularText(39ed0aea2338477103e0b5a820532ded27dbfe4f203e7270392d55f63e60271a)", "RegularText(39ed0aea2338477103e0b5a820532ded27dbfe4f203e7270392d55f63e60271a)",
"HashTag(#183)", "HashTag(#183)",
"RegularText(2%)", "RegularText(2%)",
"Link(https://Ancap.su)", "SchemelessUrl(Ancap.su)",
"RegularText(,)", "RegularText(,)",
"Email(ancapsu@getalby.com)", "Email(ancapsu@getalby.com)",
"RegularText(-)", "RegularText(-)",
@@ -2488,7 +2488,7 @@ class RichTextParserTest {
"HashTag(#249)", "HashTag(#249)",
"RegularText(2%)", "RegularText(2%)",
"RegularText(micmad,)", "RegularText(micmad,)",
"Link(https://miceliomad@miceliomad.github.io/nostr/)", "SchemelessUrl(miceliomad@miceliomad.github.io/nostr/)",
"RegularText(-)", "RegularText(-)",
"RegularText(cd806edcf8ff40ea94fa574ea9cd97da16e5beb2b85aac6e1d648b8388504343)", "RegularText(cd806edcf8ff40ea94fa574ea9cd97da16e5beb2b85aac6e1d648b8388504343)",
"HashTag(#250)", "HashTag(#250)",
@@ -2667,7 +2667,7 @@ class RichTextParserTest {
"HashTag(#278)", "HashTag(#278)",
"RegularText(2%)", "RegularText(2%)",
"RegularText(𝕬𝖓𝖔𝖓𝖞𝖒𝖔𝖚𝖘,)", "RegularText(𝕬𝖓𝖔𝖓𝖞𝖒𝖔𝖚𝖘,)",
"Link(https://zapper.lol)", "SchemelessUrl(zapper.lol)",
"RegularText(-)", "RegularText(-)",
"RegularText(96aceca84aa381eeda084167dd317e1bf7a45d874cd14147f0a9e0df86fb44c2)", "RegularText(96aceca84aa381eeda084167dd317e1bf7a45d874cd14147f0a9e0df86fb44c2)",
"HashTag(#279)", "HashTag(#279)",
@@ -3125,7 +3125,7 @@ class RichTextParserTest {
"RegularText(c4a9caef93e93f484274c04cd981d1de1424902451aca2f5602bd0835fe4393d)", "RegularText(c4a9caef93e93f484274c04cd981d1de1424902451aca2f5602bd0835fe4393d)",
"HashTag(#354)", "HashTag(#354)",
"RegularText(2%)", "RegularText(2%)",
"Link(https://smies.me)", "SchemelessUrl(smies.me)",
"RegularText(,)", "RegularText(,)",
"Email(jacksmies@iris.to)", "Email(jacksmies@iris.to)",
"RegularText(-)", "RegularText(-)",
@@ -4006,7 +4006,7 @@ class RichTextParserTest {
"RegularText(21a7014db2ba17acc8bbb9496645084866b46e1ba0062a80513afda405450183)", "RegularText(21a7014db2ba17acc8bbb9496645084866b46e1ba0062a80513afda405450183)",
"HashTag(#499)", "HashTag(#499)",
"RegularText(1%)", "RegularText(1%)",
"Link(https://baller.hodl)", "SchemelessUrl(baller.hodl)",
"RegularText(,)", "RegularText(,)",
"RegularText()", "RegularText()",
"RegularText(-)", "RegularText(-)",
@@ -4287,7 +4287,8 @@ class RichTextParserTest {
listOf<String>( listOf<String>(
"RegularText(Thats)", "RegularText(Thats)",
"RegularText(it!)", "RegularText(it!)",
"Link(http://vitorpamplona.com/.)", "Link(http://vitorpamplona.com/)",
"RegularText(.)",
"RegularText(Thats)", "RegularText(Thats)",
"RegularText(the)", "RegularText(the)",
"RegularText(note)", "RegularText(note)",
@@ -166,7 +166,7 @@ class UrlParserTest {
fun testNostrUrls() = fun testNostrUrls() =
test( test(
"nostr:npub1aabbcc", "nostr:npub1aabbcc",
Urls(withScheme = setOf("nostr:npub1aabbcc")), Urls(bech32s = setOf("nostr:npub1aabbcc")),
) )
@Test @Test
@@ -261,14 +261,14 @@ class UrlParserTest {
fun testRelayUrl() = fun testRelayUrl() =
test( test(
"wss://test.com", "wss://test.com",
Urls(withScheme = setOf("wss://test.com")), Urls(relayUrls = setOf("wss://test.com")),
) )
@Test @Test
fun testBech12() = fun testBech12() =
test( test(
"nostr:npub1aabbcc", "nostr:npub1aabbcc",
Urls(withScheme = setOf("nostr:npub1aabbcc")), Urls(bech32s = setOf("nostr:npub1aabbcc")),
) )
@Test @Test
@@ -220,6 +220,15 @@ class DomainNameReader(
// done = true // done = true
lastWasAscii = isAscii lastWasAscii = isAscii
} else if (index == 0) {
println("First Char: $curr ${curr in UrlDetector.CANNOT_BEGIN_URLS_WITH}")
if (curr in UrlDetector.CANNOT_BEGIN_URLS_WITH) {
newStart = index + 1
currentLabelLength = 0
topLevelLength = 0
numeric = true
dots = 0
}
} }
index++ index++
} }
@@ -650,7 +650,9 @@ class UrlDetector(
if (state == ReadEndState.ValidUrl && buffer.isNotEmpty()) { if (state == ReadEndState.ValidUrl && buffer.isNotEmpty()) {
// Add the url to the list of good urls. // Add the url to the list of good urls.
if (buffer.isNotEmpty()) { if (buffer.isNotEmpty()) {
urlList.add(currentUrlMarker.createUrl(buffer.toString())) var url = buffer.toString()
if (url.lastOrNull() in CANNOT_END_URLS_WITH) url = url.dropLast(1)
urlList.add(currentUrlMarker.createUrl(url))
} }
} }
@@ -669,7 +671,7 @@ class UrlDetector(
} }
companion object { companion object {
private val VALID_SCHEMES_NO_SLASHES: List<String> = val VALID_SCHEMES_NO_SLASHES: List<String> =
listOf( listOf(
"http:", "http:",
"https:", "https:",
@@ -681,9 +683,42 @@ class UrlDetector(
"blossom:", "blossom:",
) )
private val VALID_SCHEMES = val VALID_SCHEMES =
VALID_SCHEMES_NO_SLASHES.map { VALID_SCHEMES_NO_SLASHES.map {
"$it//" "$it//"
} }
val CANNOT_BEGIN_URLS_WITH =
setOf(
',',
'.',
';',
'?',
'!',
')',
'}',
'(',
'{',
'\u3002',
'\uFF0E',
'\uFF61',
)
val CANNOT_END_URLS_WITH =
setOf(
',',
'.',
';',
'?',
'!',
':',
')',
'}',
'(',
'{',
'\u3002',
'\uFF0E',
'\uFF61',
)
} }
} }
@@ -58,7 +58,7 @@ class UriDetectionTest {
runTest( runTest(
"the url google.com is a lot better then www.google.com.", "the url google.com is a lot better then www.google.com.",
"google.com", "google.com",
"www.google.com.", "www.google.com",
) )
} }
@@ -76,7 +76,7 @@ class UriDetectionTest {
"this is an international domain: http://\u043F\u0440\u0438\u043c\u0435\u0440.\u0438\u0441\u043f\u044b" + "this is an international domain: http://\u043F\u0440\u0438\u043c\u0435\u0440.\u0438\u0441\u043f\u044b" +
"\u0442\u0430\u043d\u0438\u0435 so is this: \u4e94\u7926\u767c\u5c55.\u4e2d\u570b.", "\u0442\u0430\u043d\u0438\u0435 so is this: \u4e94\u7926\u767c\u5c55.\u4e2d\u570b.",
"http://\u043F\u0440\u0438\u043c\u0435\u0440.\u0438\u0441\u043f\u044b\u0442\u0430\u043d\u0438\u0435", "http://\u043F\u0440\u0438\u043c\u0435\u0440.\u0438\u0441\u043f\u044b\u0442\u0430\u043d\u0438\u0435",
"\u4e94\u7926\u767c\u5c55.\u4e2d\u570b.", "\u4e94\u7926\u767c\u5c55.\u4e2d\u570b",
) )
} }
@@ -215,7 +215,7 @@ class UriDetectionTest {
"www.www", "www.www",
"yahoo.com", "yahoo.com",
"yahoo.com.br", "yahoo.com.br",
"hello.hello.", "hello.hello",
"hello.com", "hello.com",
) )
} }
@@ -395,7 +395,7 @@ class UriDetectionTest {
runTest("%2ewtfismyip") runTest("%2ewtfismyip")
runTest("wtfismyip%2e") runTest("wtfismyip%2e")
runTest("wtfismyip%2ecom%2e", "wtfismyip%2ecom%2e") runTest("wtfismyip%2ecom%2e", "wtfismyip%2ecom%2e")
runTest("wtfismyip%2ecom.", "wtfismyip%2ecom.") runTest("wtfismyip%2ecom.", "wtfismyip%2ecom")
runTest("%2ewtfismyip%2ecom", "wtfismyip%2ecom") runTest("%2ewtfismyip%2ecom", "wtfismyip%2ecom")
} }
@@ -662,7 +662,7 @@ class UriDetectionTest {
runTest("hello:password@go12//", "hello:password@go12//") runTest("hello:password@go12//", "hello:password@go12//")
runTest("hello:password@go12", "hello:password@go12") runTest("hello:password@go12", "hello:password@go12")
runTest("hello:password@go12 lala", "hello:password@go12") runTest("hello:password@go12 lala", "hello:password@go12")
runTest("hello.com..", "hello.com.") runTest("hello.com..", "hello.com")
runTest("a/") runTest("a/")
runTest("4/5") runTest("4/5")
runTest("concerns/worries") runTest("concerns/worries")
@@ -694,7 +694,7 @@ class UriDetectionTest {
@Test @Test
fun testNostr() { fun testNostr() {
runTest("Check this post nostr:somethingsomething . I think it is really cool", "nostr:somethingsomething") runTest("Check this post nostr:npub1048qg5p6kfnpth2l98kq3dffg097tutm4npsz2exygx25ge2k9xqf5x3nf . I think it is really cool", "nostr:npub1048qg5p6kfnpth2l98kq3dffg097tutm4npsz2exygx25ge2k9xqf5x3nf")
} }
@Test @Test
@@ -704,7 +704,7 @@ class UriDetectionTest {
@Test @Test
fun testNostrSlashes() { fun testNostrSlashes() {
runTest("Check this post nostr://somethingsomething . I think it is really cool", "nostr://somethingsomething") runTest("Check this post nostr://npub1048qg5p6kfnpth2l98kq3dffg097tutm4npsz2exygx25ge2k9xqf5x3nf . I think it is really cool", "nostr://npub1048qg5p6kfnpth2l98kq3dffg097tutm4npsz2exygx25ge2k9xqf5x3nf")
} }
@Test @Test
@@ -742,6 +742,45 @@ class UriDetectionTest {
runTest("ほtest.comほ", "test.com") runTest("ほtest.comほ", "test.com")
} }
@Test
fun testBeginsAndEndsWithPunctuation() {
UrlDetector.CANNOT_END_URLS_WITH.forEach { punctuation ->
runTest("${punctuation}http://test.com?s=dd", "http://test.com?s=dd")
runTest("http://test.com?s=dd$punctuation", "http://test.com?s=dd")
runTest("${punctuation}http://test.com?s=dd$punctuation", "http://test.com?s=dd")
runTest("${punctuation}http://test.com/", "http://test.com/")
runTest("http://test.com/.", "http://test.com/")
runTest("${punctuation}http://test.com/$punctuation", "http://test.com/")
runTest("${punctuation}http://test.com", "http://test.com")
runTest("http://test.com$punctuation", "http://test.com")
runTest("${punctuation}http://test.com$punctuation", "http://test.com")
runTest("${punctuation}test.com", "test.com")
runTest("test.com$punctuation", "test.com")
runTest("${punctuation}test.com$punctuation", "test.com")
}
UrlDetector.CANNOT_BEGIN_URLS_WITH.forEach { punctuation ->
runTest("${punctuation}http://test.com?s=dd", "http://test.com?s=dd")
runTest("http://test.com?s=dd$punctuation", "http://test.com?s=dd")
runTest("${punctuation}http://test.com?s=dd$punctuation", "http://test.com?s=dd")
runTest("${punctuation}http://test.com/", "http://test.com/")
runTest("http://test.com/.", "http://test.com/")
runTest("${punctuation}http://test.com/$punctuation", "http://test.com/")
runTest("${punctuation}http://test.com", "http://test.com")
runTest("http://test.com$punctuation", "http://test.com")
runTest("${punctuation}http://test.com$punctuation", "http://test.com")
runTest("${punctuation}test.com", "test.com")
runTest("test.com$punctuation", "test.com")
runTest("${punctuation}test.com$punctuation", "test.com")
}
}
private fun runTest( private fun runTest(
text: String, text: String,
vararg expected: String?, vararg expected: String?,