Merge pull request #22 from fleeksoft/develop

test files html to gz
fleeksoft · Dec 20, 2023 · 96b0c84 · 96b0c84
2 parents abb866d + c6abc56
commit 96b0c84
Show file tree

Hide file tree

Showing 8 changed files with 12 additions and 4,078 deletions.
diff --git a/ksoup/src/commonTest/kotlin/com/fleeksoft/ksoup/helper/DataUtilTest.kt b/ksoup/src/commonTest/kotlin/com/fleeksoft/ksoup/helper/DataUtilTest.kt
@@ -283,7 +283,7 @@ class DataUtilTest {
 
     @Test
     fun handlesChunkedInputStream() {
-        val inputFile: String = TestHelper.getResourceAbsolutePath("htmltests/large.html")
+        val inputFile: String = TestHelper.getResourceAbsolutePath("htmltests/large.html.gz")
         val input: String = TestHelper.getFileAsString(inputFile.toPath())
 //        val stream = VaryingBufferReader(BufferReader(input))
         val expected = Ksoup.parse(input, "https://example.com")
@@ -295,7 +295,7 @@ class DataUtilTest {
 
     @Test
     fun handlesUnlimitedRead() {
-        val inputFile: String = TestHelper.getResourceAbsolutePath("htmltests/large.html")
+        val inputFile: String = TestHelper.getResourceAbsolutePath("htmltests/large.html.gz")
         val input: String = TestHelper.getFileAsString(inputFile.toPath())
         val byteBuffer: ByteArray = DataUtil.readToByteBuffer(BufferReader(input.toBuffer()), 0)
         val read = byteBuffer.decodeToString()

diff --git a/ksoup/src/commonTest/kotlin/com/fleeksoft/ksoup/issues/GithubIssue19.kt b/ksoup/src/commonTest/kotlin/com/fleeksoft/ksoup/issues/GithubIssue19.kt
@@ -14,7 +14,7 @@ class GithubIssue19 {
 
     @Test
     fun testAttributeIncorrectMixCharsetIssue() {
-        val document: Document = Ksoup.parseFile(TestHelper.getResourceAbsolutePath("htmltests/issue19.html"))
+        val document: Document = Ksoup.parseFile(TestHelper.getResourceAbsolutePath("htmltests/issue19.html.gz"))
         val imagesEls: Elements = document.select("img")
         for (imagesEl in imagesEls) {
             val attr: String = imagesEl.attr("src")

diff --git a/ksoup/src/commonTest/kotlin/com/fleeksoft/ksoup/issues/GithubIssuesTests.kt b/ksoup/src/commonTest/kotlin/com/fleeksoft/ksoup/issues/GithubIssuesTests.kt
@@ -10,7 +10,7 @@ class GithubIssuesTests {
     @Test
     fun testIssue20DuplicateElements() {
         //    https://github.com/fleeksoft/ksoup/issues/20
-        Ksoup.parse(TestHelper.getFileAsString(TestHelper.getResourceAbsolutePath("htmltests/issue20.html").toPath()))
+        Ksoup.parse(TestHelper.getFileAsString(TestHelper.getResourceAbsolutePath("htmltests/issue20.html.gz").toPath()))
             .apply {
                 body().select("div[class=firs l]")
                     .firstOrNull()?.let { element ->

diff --git a/ksoup/src/commonTest/kotlin/com/fleeksoft/ksoup/parser/CharacterReaderTest.kt b/ksoup/src/commonTest/kotlin/com/fleeksoft/ksoup/parser/CharacterReaderTest.kt
@@ -522,7 +522,7 @@ class CharacterReaderTest {
     fun linenumbersAgreeWithEditor() {
         val content: String =
             TestHelper.getFileAsString(
-                TestHelper.getResourceAbsolutePath("htmltests/large.html").toPath(),
+                TestHelper.getResourceAbsolutePath("htmltests/large.html.gz").toPath(),
             )
         val reader = CharacterReader(content)
         reader.trackNewlines(true)

diff --git a/ksoup/src/commonTest/resources/htmltests/issue19.html b/ksoup/src/commonTest/resources/htmltests/issue19.html
diff --git a/ksoup/src/commonTest/resources/htmltests/issue20.html b/ksoup/src/commonTest/resources/htmltests/issue20.html
diff --git a/ksoup/src/commonTest/resources/htmltests/large.html b/ksoup/src/commonTest/resources/htmltests/large.html
diff --git a/ksoup/src/jvmAndroidCommonTest/kotlin/com/fleeksoft/ksoup/DataUtilTestJvm.kt b/ksoup/src/jvmAndroidCommonTest/kotlin/com/fleeksoft/ksoup/DataUtilTestJvm.kt
@@ -5,6 +5,7 @@ import com.fleeksoft.ksoup.nodes.Document
 import com.fleeksoft.ksoup.parser.Parser
 import com.fleeksoft.ksoup.ported.BufferReader
 import io.ktor.utils.io.charsets.*
+import okio.gzip
 import okio.source
 import java.io.*
 import java.nio.charset.StandardCharsets
@@ -53,7 +54,7 @@ class DataUtilTestJvm {
 
     @Test
     fun testHandlesChunkedInputStream() {
-        val file = File(TestHelper.getResourceAbsolutePath("htmltests/large.html"))
+        val file = File(TestHelper.getResourceAbsolutePath("htmltests/large.html.gz"))
         val input = getFileAsString(file)
         val expected =
             Ksoup.parse(
@@ -62,14 +63,14 @@ class DataUtilTestJvm {
             )
         val doc: Document =
             Ksoup.parse(
-                bufferReader = BufferReader(FileInputStream(file).source()),
+                bufferReader = BufferReader(FileInputStream(file).source().gzip()),
                 charsetName = null,
                 baseUri = "https://example.com",
             )
 
         val doc2: Document =
             Ksoup.parseInputStream(
-                inputStream = FileInputStream(file),
+                inputStream = GZIPInputStream(FileInputStream(file)),
                 charsetName = null,
                 baseUri = "https://example.com",
             )
@@ -81,7 +82,7 @@ class DataUtilTestJvm {
 
     @Test
     fun testHandlesUnlimitedRead() {
-        val file = File(TestHelper.getResourceAbsolutePath("htmltests/large.html"))
+        val file = File(TestHelper.getResourceAbsolutePath("htmltests/large.html.gz"))
         val input: String = getFileAsString(file)
 
         //        VaryingReadInputStream stream = new VaryingReadInputStream(ParseTest.inputStreamFrom(input));
@@ -94,13 +95,13 @@ class DataUtilTestJvm {
             )
         val doc2: Document =
             Ksoup.parseInputStream(
-                inputStream = FileInputStream(file),
+                inputStream = GZIPInputStream(FileInputStream(file)),
                 charsetName = null,
                 baseUri = "https://example.com",
             )
         val docThree: Document =
             Ksoup.parse(
-                bufferReader = BufferReader(FileInputStream(file).source()),
+                bufferReader = BufferReader(FileInputStream(file).source().gzip()),
                 charsetName = null,
                 baseUri = "https://example.com",
             )