Merge pull request #1768 from asger-semmle/ts-debugging

Approved by esben-semmle, xiemaisi

javascript/extractor/lib/typescript/README.md

@@ -0,0 +1,18 @@
+TypeScript parser wrapper
+-------------------------
+
+The TypeScript "parser wrapper" is a Node.js program launched from the JavaScript
+extractor in order to extract TypeScript code.
+
+The two processes communicate via a command/response protocol via stdin/stdout.
+
+Debugging
+---------
+
+To debug the parser script:
+
+1. Launch an extraction process with the environment variable `SEMMLE_TYPESCRIPT_NODE_FLAGS`
+   set to `--inspect`, or `--inspect-brk` if you wish to pause on entry.
+
+2. Open VSCode and choose "Debug: Attach to Node process" from the command palette, and
+   choose the process that looks like the parser-wrapper.

javascript/extractor/src/com/semmle/js/parser/TypeScriptParser.java

@@ -1,6 +1,21 @@
 package com.semmle.js.parser;
 
-import ch.qos.logback.classic.Level;
+import java.io.BufferedReader;
+import java.io.BufferedWriter;
+import java.io.ByteArrayOutputStream;
+import java.io.Closeable;
+import java.io.File;
+import java.io.IOException;
+import java.io.InputStream;
+import java.io.InputStreamReader;
+import java.io.OutputStream;
+import java.io.OutputStreamWriter;
+import java.lang.ProcessBuilder.Redirect;
+import java.util.ArrayList;
+import java.util.Arrays;
+import java.util.Collections;
+import java.util.List;
+
 import com.google.gson.JsonArray;
 import com.google.gson.JsonElement;
 import com.google.gson.JsonObject;
@@ -21,21 +36,8 @@ import com.semmle.util.logging.LogbackUtils;
 import com.semmle.util.process.AbstractProcessBuilder;
 import com.semmle.util.process.Builder;
 import com.semmle.util.process.Env;
-import java.io.BufferedReader;
+
-import java.io.BufferedWriter;
+import ch.qos.logback.classic.Level;
-import java.io.ByteArrayOutputStream;
-import java.io.Closeable;
-import java.io.File;
-import java.io.IOException;
-import java.io.InputStream;
-import java.io.InputStreamReader;
-import java.io.OutputStream;
-import java.io.OutputStreamWriter;
-import java.lang.ProcessBuilder.Redirect;
-import java.util.ArrayList;
-import java.util.Arrays;
-import java.util.Collections;
-import java.util.List;
 
 /**
  * The Java half of our wrapper for invoking the TypeScript parser.
@@ -98,6 +100,13 @@ public class TypeScriptParser {
    */
   public static final String TYPESCRIPT_RAM_RESERVE_SUFFIX = "TYPESCRIPT_RAM_RESERVE";
 
+  /**
+   * An environment variable with additional VM arguments to pass to the Node process.
+   * <p>
+   * Only <code>--inspect</code> or <code>--inspect-brk</code> may be used at the moment.
+   */
+  public static final String TYPESCRIPT_NODE_FLAGS = "SEMMLE_TYPESCRIPT_NODE_FLAGS";
+
   /** The Node.js parser wrapper process, if it has been started already. */
   private Process parserWrapperProcess;
 
@@ -237,10 +246,23 @@ public class TypeScriptParser {
 
     File parserWrapper = getParserWrapper();
 
-    List<String> cmd = getNodeJsRuntimeInvocation(
+    String debugFlagString = Env.systemEnv().getNonEmpty(TYPESCRIPT_NODE_FLAGS);
-        "--max_old_space_size=" + (mainMemoryMb + reserveMemoryMb),
+    List<String> debugFlags = new ArrayList<>();
-        parserWrapper.getAbsolutePath()
+    if (debugFlagString != null) {
-    );
+      for (String flag : debugFlagString.split(" ")) {
+        if (!flag.startsWith("--inspect") || flag.contains(":")) {
+          System.err.println("Ignoring unrecognized Node flag: '" + flag + "'");
+        } else {
+          debugFlags.add(flag);
+        }
+      }
+    }
+
+    List<String> cmd = getNodeJsRuntimeInvocation();
+    cmd.add("--max_old_space_size=" + (mainMemoryMb + reserveMemoryMb));
+    cmd.addAll(debugFlags);
+    cmd.add(parserWrapper.getAbsolutePath());
+
     ProcessBuilder pb = new ProcessBuilder(cmd);
     parserWrapperCommand = StringUtil.glue(" ", cmd);
     pb.environment().put("SEMMLE_TYPESCRIPT_MEMORY_THRESHOLD", "" + mainMemoryMb);