Switch from MD4C to CommonMark for markdown parsing

I wanted to use MD4C for the performance but unfortunately there seem to be issues with how it handles UTF-8 and how the JNI handles it. CommonMark will have to do for now at least

.gitmodules

@@ -1,3 +0,0 @@
-[submodule "md4k/lib/md4c"]
-	path = md4k/lib/md4c
-	url = https://github.com/mity/md4c

app/build.gradle.kts

@@ -111,7 +111,6 @@ play {
 }
 
 dependencies {
-    implementation(project(":md4k"))
     implementation("androidx.compose.material3:material3-window-size-class-android:1.2.0")
     val navigationVersion = "2.7.2"
     implementation("androidx.navigation:navigation-fragment-ktx:$navigationVersion")
@@ -138,6 +137,15 @@ dependencies {
     implementation("com.jakewharton.timber:timber:5.0.1")
     implementation("androidx.core:core-ktx:1.12.0")
     implementation("androidx.browser:browser:1.6.0")
+    val commonMarkVersion = "0.22.0"
+    implementation("org.commonmark:commonmark:$commonMarkVersion")
+    implementation("org.commonmark:commonmark-ext-gfm-tables:$commonMarkVersion")
+    implementation("org.commonmark:commonmark-ext-gfm-strikethrough:$commonMarkVersion")
+    implementation("org.commonmark:commonmark-ext-autolink:$commonMarkVersion")
+    implementation("org.commonmark:commonmark-ext-task-list-items:$commonMarkVersion")
+    implementation("org.commonmark:commonmark-ext-yaml-front-matter:$commonMarkVersion")
+    implementation("org.commonmark:commonmark-ext-image-attributes:$commonMarkVersion")
+    implementation("org.commonmark:commonmark-ext-heading-anchor:$commonMarkVersion")
     val composeBom = platform("androidx.compose:compose-bom:2023.08.00")
     implementation(composeBom)
     androidTestImplementation(composeBom)

app/src/main/java/com/wbrawner/simplemarkdown/ui/MarkdownText.kt

@@ -12,17 +12,46 @@ import androidx.compose.ui.Modifier
 import androidx.compose.ui.graphics.Color
 import androidx.compose.ui.graphics.toArgb
 import androidx.compose.ui.viewinterop.AndroidView
-import com.wbrawner.md4k.MD4K
 import com.wbrawner.simplemarkdown.BuildConfig
 import kotlinx.coroutines.Dispatchers
 import kotlinx.coroutines.withContext
+import org.commonmark.ext.autolink.AutolinkExtension
+import org.commonmark.ext.front.matter.YamlFrontMatterExtension
+import org.commonmark.ext.gfm.strikethrough.StrikethroughExtension
+import org.commonmark.ext.gfm.tables.TablesExtension
+import org.commonmark.ext.heading.anchor.HeadingAnchorExtension
+import org.commonmark.ext.image.attributes.ImageAttributesExtension
+import org.commonmark.ext.task.list.items.TaskListItemsExtension
+import org.commonmark.parser.Parser
+import org.commonmark.renderer.html.HtmlRenderer
+
+private val markdownExtensions = listOf(
+    AutolinkExtension.create(),
+    StrikethroughExtension.create(),
+    TablesExtension.create(),
+    HeadingAnchorExtension.create(),
+    YamlFrontMatterExtension.create(),
+    ImageAttributesExtension.create(),
+    TaskListItemsExtension.create(),
+)
+
+private val markdownParser = Parser.builder()
+    .extensions(markdownExtensions)
+    .build()
+
+private val renderer = HtmlRenderer.builder()
+    .extensions(markdownExtensions)
+    .build()
 
 @Composable
 fun MarkdownText(modifier: Modifier = Modifier, markdown: String) {
     val (html, setHtml) = remember { mutableStateOf("") }
     LaunchedEffect(markdown) {
         withContext(Dispatchers.IO) {
-            setHtml(MD4K.toHtml(markdown))
+            val parsedHtml = renderer.render(
+                markdownParser.parse(markdown)
+            )
+            setHtml(parsedHtml)
         }
     }
     HtmlText(modifier = modifier, html = html)
@@ -42,7 +71,6 @@ fun HtmlText(html: String, modifier: Modifier = Modifier) {
             |   color: #${materialColors.onSurfaceVariant.toArgb().toHexString().substring(2)};
             |}""".trimMargin().wrapTag("style")
     }
-
     AndroidView(
         modifier = modifier,
         factory = { context ->

md4k/.gitignore

@@ -1,2 +0,0 @@
-/build
-/.cxx

md4k/CMakeLists.txt

@@ -1,18 +0,0 @@
-cmake_minimum_required(VERSION 3.22.1)
-
-project("md4k")
-
-add_subdirectory("lib/md4c")
-set(BUILD_MD2HTML_EXECUTABLE OFF)
-
-add_library(${CMAKE_PROJECT_NAME} SHARED
-        src/main/cpp/md4k.c)
-
-target_link_libraries(${CMAKE_PROJECT_NAME}
-        md4c
-        md4c-html
-)
-
-target_include_directories(${CMAKE_PROJECT_NAME} PUBLIC
-        ${PROJECT_SOURCE_DIR}/lib/md4c/src
-)

md4k/build.gradle.kts

@@ -1,46 +0,0 @@
-plugins {
-    id("com.android.library")
-    id("org.jetbrains.kotlin.android")
-}
-
-android {
-    namespace = "com.wbrawner.md4k"
-    compileSdk = 34
-
-    defaultConfig {
-        minSdk = 23
-
-        testInstrumentationRunner = "androidx.test.runner.AndroidJUnitRunner"
-        consumerProguardFiles("consumer-rules.pro")
-        externalNativeBuild {
-            cmake {
-                cppFlags("")
-            }
-        }
-    }
-
-    buildTypes {
-        release {
-            isMinifyEnabled = false
-            proguardFiles(getDefaultProguardFile("proguard-android-optimize.txt"), "proguard-rules.pro")
-        }
-    }
-    externalNativeBuild {
-        cmake {
-            path("CMakeLists.txt")
-            version = "3.22.1"
-        }
-    }
-    compileOptions {
-        sourceCompatibility = JavaVersion.VERSION_1_8
-        targetCompatibility = JavaVersion.VERSION_1_8
-    }
-    kotlinOptions {
-        jvmTarget = "1.8"
-    }
-}
-
-dependencies {
-    androidTestImplementation("androidx.test.ext:junit:1.1.5")
-    androidTestImplementation("androidx.test:runner:1.5.2")
-}

md4k/lib/md4c

@@ -1 +0,0 @@
-Subproject commit 481fbfbdf72daab2912380d62bb5f2187d438408

md4k/proguard-rules.pro

@@ -1,21 +0,0 @@
-# Add project specific ProGuard rules here.
-# You can control the set of applied configuration files using the
-# proguardFiles setting in build.gradle.
-#
-# For more details, see
-#   http://developer.android.com/guide/developing/tools/proguard.html
-
-# If your project uses WebView with JS, uncomment the following
-# and specify the fully qualified class name to the JavaScript interface
-# class:
-#-keepclassmembers class fqcn.of.javascript.interface.for.webview {
-#   public *;
-#}
-
-# Uncomment this to preserve the line number information for
-# debugging stack traces.
-#-keepattributes SourceFile,LineNumberTable
-
-# If you keep the line number information, uncomment this to
-# hide the original source file name.
-#-renamesourcefileattribute SourceFile

md4k/src/androidTest/kotlin/com/wbrawner/md4k/MarkdownParserTest.kt

@@ -1,28 +0,0 @@
-package com.wbrawner.md4k
-
-import org.junit.Test
-import org.junit.runner.RunWith
-import org.junit.runners.Parameterized
-import org.junit.runners.Parameterized.Parameters
-
-@RunWith(Parameterized::class)
-class MarkdownParserTest(private val markdown: String, private val html: String) {
-
-    @Test
-    fun testMarkdownToHtmlConversion() {
-        val parsedHtml = markdown.toHtml()
-        assert(parsedHtml == html) {
-            """expected "$html", got "$parsedHtml""""
-        }
-    }
-
-    companion object {
-        @JvmStatic
-        @Parameters(name = "Markdown: {0}")
-        fun data(): Array<Array<String>> = arrayOf(
-                arrayOf("# Test", "<h1>Test</h1>\n"),
-                arrayOf("- [ ] Check this", "<ul>\n<li class=\"task-list-item\"><input type=\"checkbox\" class=\"task-list-item-checkbox\" disabled>Check this</li>\n</ul>\n"),
-                arrayOf("- [x] Checked!", "<ul>\n<li class=\"task-list-item\"><input type=\"checkbox\" class=\"task-list-item-checkbox\" disabled checked>Checked!</li>\n</ul>\n"),
-        )
-    }
-}

md4k/src/main/AndroidManifest.xml

@@ -1,4 +0,0 @@
-<?xml version="1.0" encoding="utf-8"?>
-<manifest xmlns:android="http://schemas.android.com/apk/res/android">
-
-</manifest>

md4k/src/main/cpp/md4k.c

@@ -1,41 +0,0 @@
-#include <jni.h>
-#include "md4c.h"
-#include "md4c-html.h"
-#include <stdlib.h>
-#include <string.h>
-
-typedef struct {
-    char *data;
-    size_t length;
-} HtmlBuffer;
-
-void process_output(const MD_CHAR *output, MD_SIZE size, void *userdata) {
-    HtmlBuffer *buffer = (HtmlBuffer *) userdata;
-    buffer->data = realloc(buffer->data, buffer->length + size);
-    memcpy(buffer->data + buffer->length, output, size);
-    buffer->length += size;
-}
-
-jstring Java_com_wbrawner_md4k_MD4K_toHtml(
-        JNIEnv *env,
-        jobject this,
-        jstring markdown
-) {
-    const char *nativeString = (*env)->GetStringUTFChars(env, markdown, NULL);
-    HtmlBuffer buffer;
-    buffer.data = malloc(0);
-    buffer.length = 0;
-    md_html(
-            nativeString,
-            strlen(nativeString),
-            &process_output,
-            &buffer,
-            MD_FLAG_PERMISSIVEAUTOLINKS | MD_FLAG_TABLES | MD_FLAG_STRIKETHROUGH |
-            MD_FLAG_TASKLISTS | MD_FLAG_LATEXMATHSPANS | MD_FLAG_WIKILINKS | MD_FLAG_UNDERLINE,
-            0
-    );
-    (*env)->ReleaseStringUTFChars(env, markdown, nativeString);
-    jstring html = (*env)->NewStringUTF(env, buffer.data);
-    free(buffer.data);
-    return html;
-}

md4k/src/main/java/com/wbrawner/md4k/MD4K.kt

@@ -1,12 +0,0 @@
-package com.wbrawner.md4k
-
-object MD4K {
-
-    init {
-        System.loadLibrary("md4k")
-    }
-
-    external fun toHtml(markdown: String): String
-}
-
-fun String.toHtml() = MD4K.toHtml(this)

settings.gradle.kts

@@ -1 +1 @@
-include(":app", ":md4k")
+include(":app")