You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@tika.apache.org by ta...@apache.org on 2026/05/21 10:34:40 UTC
(tika) branch TIKA-4734 created (now 0b0dc4f75c)
This is an automated email from the ASF dual-hosted git repository.
tballison pushed a change to branch TIKA-4734
in repository https://gitbox.apache.org/repos/asf/tika.git
at 0b0dc4f75c TIKA-4734 -- fix xml config converter
This branch includes the following new commits:
new 0b0dc4f75c TIKA-4734 -- fix xml config converter
The 1 revisions listed above as "new" are entirely new to this
repository and will be described in separate emails. The revisions
listed as "add" were already present in the repository and have only
been added to this reference.
(tika) 01/01: TIKA-4734 -- fix xml config converter
Posted by ta...@apache.org.
This is an automated email from the ASF dual-hosted git repository.
tballison pushed a commit to branch TIKA-4734
in repository https://gitbox.apache.org/repos/asf/tika.git
commit 0b0dc4f75c5adbc3bf014c8796e609512572b917
Author: tallison <ta...@apache.org>
AuthorDate: Thu May 21 06:34:08 2026 -0400
TIKA-4734 -- fix xml config converter
---
.../pages/migration-to-4x/migrating-to-4x.adoc | 5 ++-
.../src/main/java/org/apache/tika/cli/TikaCLI.java | 44 ++++++++++++++--------
.../test/java/org/apache/tika/cli/TikaCLITest.java | 19 ++++++++++
3 files changed, 51 insertions(+), 17 deletions(-)
diff --git a/docs/modules/ROOT/pages/migration-to-4x/migrating-to-4x.adoc b/docs/modules/ROOT/pages/migration-to-4x/migrating-to-4x.adoc
index 34ef91d778..7cca66ec39 100644
--- a/docs/modules/ROOT/pages/migration-to-4x/migrating-to-4x.adoc
+++ b/docs/modules/ROOT/pages/migration-to-4x/migrating-to-4x.adoc
@@ -36,9 +36,12 @@ Tika provides a conversion tool in `tika-app` to help migrate your XML configura
[source,bash]
----
-java -jar tika-app.jar --convert-config-xml-to-json=tika-config.xml,tika-config.json
+java -jar tika-app.jar --convert-config-xml-to-json=tika-config.xml > tika-config.json
----
+The converted JSON is written to standard output, so redirect it to the file of your choice
+(as shown above). No separate `--config` argument is needed.
+
The converter currently supports:
* **Parsers section** - parser declarations with parameters and exclusions
diff --git a/tika-app/src/main/java/org/apache/tika/cli/TikaCLI.java b/tika-app/src/main/java/org/apache/tika/cli/TikaCLI.java
index 82be748314..80999eee21 100644
--- a/tika-app/src/main/java/org/apache/tika/cli/TikaCLI.java
+++ b/tika-app/src/main/java/org/apache/tika/cli/TikaCLI.java
@@ -56,6 +56,7 @@ import javax.xml.transform.sax.TransformerHandler;
import javax.xml.transform.stream.StreamResult;
import org.apache.commons.io.input.CloseShieldInputStream;
+import org.apache.commons.io.output.CloseShieldOutputStream;
import org.apache.logging.log4j.Level;
import org.slf4j.Logger;
import org.slf4j.LoggerFactory;
@@ -364,6 +365,15 @@ public class TikaCLI {
private boolean testForAsync(String[] args) {
+ // Standalone utility flags are handled directly by process(), never via async mode.
+ // (Without this guard, --convert-config-xml-to-json=in.xml would be misread as a
+ // ".json"/batch arg and routed to async, failing with a TikaConfigException - TIKA-4734.)
+ for (String arg : args) {
+ if (arg.startsWith("--convert-config-xml-to-json=")) {
+ return false;
+ }
+ }
+
// Single .json file is a config file for async mode
if (args.length == 1 && args[0].endsWith(".json")) {
return true;
@@ -576,27 +586,27 @@ public class TikaCLI {
System.out.println(localConfig.getConfig().toString());
}*/
- private void convertConfigXmlToJson(String paths) throws Exception {
- String[] parts = paths.split(",");
- if (parts.length != 2) {
- System.err.println("Error: --convert-config-xml-to-json requires input and output paths separated by comma");
- System.err.println("Usage: --convert-config-xml-to-json=<input.xml>,<output.json>");
+ private void convertConfigXmlToJson(String inputPath) throws Exception {
+ if (inputPath == null || inputPath.trim().isEmpty()) {
+ System.err.println("Error: --convert-config-xml-to-json requires an input XML path");
+ System.err.println("Usage: --convert-config-xml-to-json=<input.xml> > <output.json>");
return;
}
- Path xmlPath = Paths.get(parts[0].trim());
- Path jsonPath = Paths.get(parts[1].trim());
+ Path xmlPath = Paths.get(inputPath.trim());
if (!Files.exists(xmlPath)) {
System.err.println("Error: Input XML file not found: " + xmlPath);
return;
}
- try {
- XmlToJsonConfigConverter.convert(xmlPath, jsonPath);
- System.out.println("Successfully converted XML config to JSON:");
- System.out.println(" Input: " + xmlPath.toAbsolutePath());
- System.out.println(" Output: " + jsonPath.toAbsolutePath());
+ // Write JSON to stdout so the user can redirect it (e.g. > tika-config.json).
+ // Informational/diagnostic output from the converter goes to the logger (stderr),
+ // keeping stdout clean for the JSON payload. The converter closes the stream it
+ // is handed, so shield System.out from being closed out from under us.
+ try (InputStream in = Files.newInputStream(xmlPath)) {
+ XmlToJsonConfigConverter.convert(in, CloseShieldOutputStream.wrap(System.out));
+ System.out.flush();
} catch (Exception e) {
System.err.println("Error converting config: " + e.getMessage());
throw e;
@@ -743,16 +753,18 @@ public class TikaCLI {
out.println();
out.println(" -g or --gui Start the Apache Tika GUI");
out.println();
- out.println(" --config=<tika-config.xml>");
- out.println(" TikaConfig file. Must be specified before -g, -s, -f or the dump-x-config !");
+ out.println(" --config=<tika-config.json>");
+ out.println(" TikaConfig file (JSON as of Tika 4.x). Must be specified before -g, -s 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");
// out.println(" --dump-current-config Print current TikaConfig");
// out.println(" --dump-static-config Print static config");
// out.println(" --dump-static-full-config Print static explicit config");
- out.println(" --convert-config-xml-to-json=<input.xml>,<output.json>");
- out.println(" Convert legacy XML config to JSON format (parsers section only)");
+ out.println(" --convert-config-xml-to-json=<input.xml>");
+ out.println(" Convert a legacy 3.x XML config to 4.x JSON format (parsers section only),");
+ out.println(" writing the JSON to stdout. Redirect to save, e.g.:");
+ out.println(" --convert-config-xml-to-json=tika-config.xml > tika-config.json");
out.println("");
out.println(" -x or --xml Output XHTML content (default)");
out.println(" -h or --html Output HTML content");
diff --git a/tika-app/src/test/java/org/apache/tika/cli/TikaCLITest.java b/tika-app/src/test/java/org/apache/tika/cli/TikaCLITest.java
index 5498f3f056..396e174057 100644
--- a/tika-app/src/test/java/org/apache/tika/cli/TikaCLITest.java
+++ b/tika-app/src/test/java/org/apache/tika/cli/TikaCLITest.java
@@ -764,6 +764,25 @@ public class TikaCLITest {
* reset outContent and errContent if they are not empty
* run given params in TikaCLI and return outContent String with UTF-8
*/
+ /**
+ * Tests --convert-config-xml-to-json with no separate config file.
+ * Regression test for TIKA-4734: the flag used to be misrouted to async
+ * mode (the input arg ended in ".json"), failing with a TikaConfigException
+ * unless a --config was also passed. It must now run standalone and write
+ * the converted JSON to stdout.
+ */
+ @Test
+ 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);
+ }
+
String getParamOutContent(String... params) throws Exception {
resetContent();
TikaCLI.main(params);