TIKA-4734 -- address copilot feedback

Author: tballison

tika-app/src/main/java/org/apache/tika/cli/TikaCLI.java

@@ -402,8 +402,9 @@ private boolean testForAsync(String[] args) {
             }
         }
 
-        // Single .json file is a config file for async mode
-        if (args.length == 1 && args[0].endsWith(".json")) {
+        // Single .json file is a config file for async mode.
+        // Reject option-style args like `--config=foo.json` so they fall through to process().
+        if (args.length == 1 && !args[0].startsWith("-") && args[0].endsWith(".json")) {
             return true;
         }
 
@@ -623,8 +624,12 @@ private void convertConfigXmlToJson(String inputPath) throws Exception {
 
         Path xmlPath = Paths.get(inputPath.trim());
 
-        if (!Files.exists(xmlPath)) {
-            System.err.println("Error: Input XML file not found: " + xmlPath);
+        if (!Files.isRegularFile(xmlPath)) {
+            System.err.println("Error: Input XML path is not a regular file: " + xmlPath);
+            return;
+        }
+        if (!Files.isReadable(xmlPath)) {
+            System.err.println("Error: Input XML file is not readable: " + xmlPath);
             return;
         }
 
@@ -782,7 +787,7 @@ private void usage() {
         out.println("    -g  or --gui           Start the Apache Tika GUI");
         out.println();
         out.println("    --config=<tika-config.json>");
-        out.println("        TikaConfig file (JSON as of Tika 4.x). Must be specified before -g, -s or -f !");
+        out.println("        TikaConfig file (JSON as of Tika 4.x). Must be specified before -g or -f !");
         // TODO: TIKA-XXXX - Re-enable config dump options once JSON serialization is complete
         // These options are not yet implemented in 4.x due to the migration from XML to JSON config
         // out.println("    --dump-minimal-config  Print minimal TikaConfig");

tika-app/src/test/java/org/apache/tika/cli/TikaCLITest.java

@@ -38,6 +38,8 @@
 import java.util.List;
 import java.util.Set;
 
+import com.fasterxml.jackson.databind.JsonNode;
+import com.fasterxml.jackson.databind.ObjectMapper;
 import org.junit.jupiter.api.AfterEach;
 import org.junit.jupiter.api.BeforeEach;
 import org.junit.jupiter.api.Disabled;
@@ -772,11 +774,23 @@ public void testConvertConfigXmlToJson() throws Exception {
         String xmlPath = Paths.get(getClass().getResource("/xml-configs/tika-config-simple.xml").toURI()).toString();
         String content = getParamOutContent("--convert-config-xml-to-json=" + xmlPath);
 
-        // stdout should contain the converted JSON (and only the JSON)
-        assertTrue(content.contains("\"parsers\""), "Expected JSON parsers section, got: " + content);
-        assertTrue(content.contains("pdf-parser"), "Expected pdf-parser in output, got: " + content);
-        assertTrue(content.contains("\"sortByPosition\" : true"), "Expected converted param, got: " + content);
-        assertTrue(content.trim().startsWith("{"), "Output should be pure JSON, got: " + content);
+        // stdout should be pure JSON; parse and assert on structure, not formatting
+        JsonNode root = new ObjectMapper().readTree(content.trim());
+        JsonNode parsers = root.get("parsers");
+        assertNotNull(parsers, "Expected parsers section, got: " + content);
+        assertTrue(parsers.isArray() && parsers.size() > 0, "Expected non-empty parsers array, got: " + content);
+
+        JsonNode pdfEntry = null;
+        for (JsonNode entry : parsers) {
+            if (entry.has("pdf-parser")) {
+                pdfEntry = entry.get("pdf-parser");
+                break;
+            }
+        }
+        assertNotNull(pdfEntry, "Expected pdf-parser entry, got: " + content);
+        JsonNode sortByPosition = pdfEntry.findValue("sortByPosition");
+        assertNotNull(sortByPosition, "Expected sortByPosition under pdf-parser, got: " + content);
+        assertTrue(sortByPosition.asBoolean(), "Expected sortByPosition=true, got: " + sortByPosition);
     }
 
     /**