TIKA-4739

docs/modules/ROOT/pages/advanced/integration-testing/tika-app.adoc

@@ -291,10 +291,14 @@ Create `/tmp/tika-app-test/my-config.json`:
       "emitterId": "fse"
     }
   },
+  "parse-context": {
+    "timeout-limits": {
+      "progressTimeoutMillis": 60000
+    }
+  },
   "pipes": {
     "parseMode": "RMETA",
-    "numClients": 2,
-    "timeoutMillis": 60000
+    "numClients": 2
   },
   "plugin-roots": "/tmp/tika-app-test/plugins"
 }

docs/modules/ROOT/pages/migration-to-4x/migrating-tika-server-4x.adoc

@@ -101,7 +101,7 @@ The `/tika` endpoint no longer routes based on `Accept` headers. Use explicit pa
 
 The following `TikaServerConfig` options have been removed:
 
-* `taskTimeoutMillis` - Now configured via `pipes.timeoutMillis`
+* `taskTimeoutMillis` - Now configured via `parse-context.timeout-limits.progressTimeoutMillis` (and optionally `totalTaskTimeoutMillis`); see xref:pipes/timeouts.adoc[Timeouts].
 * `taskPulseMillis` - No longer needed
 * `minimumTimeoutMillis` - No longer needed
 
@@ -125,9 +125,13 @@ All tika-server configurations must now include a `pipes` section and a `file-sy
       }
     }
   },
+  "parse-context": {
+    "timeout-limits": {
+      "progressTimeoutMillis": 30000
+    }
+  },
   "pipes": {
-    "numClients": 2,
-    "timeoutMillis": 30000
+    "numClients": 2
   },
   "plugin-roots": "path/to/plugins"
 }

docs/modules/ROOT/pages/migration-to-4x/migrating-to-4x.adoc

@@ -83,7 +83,7 @@ The converter currently supports:
 
 NOTE: When you configure a parser with specific settings in JSON, the loader automatically
 excludes it from SPI loading. The parser (e.g., `pdf-parser`) is not even instantiated in
-`default-parser` if there's a definition for it in the tika-config.json. Explicit `_exclude`
+`default-parser` if there's a definition for it in the tika-config.json. Explicit `exclude`
 directives are only needed when you want to disable a parser entirely without providing
 custom configuration.
 
@@ -103,7 +103,7 @@ custom configuration.
 
 |Exclusions
 |`<parser-exclude class="..."/>`
-|`"_exclude": ["component-name"]` (only needed to disable a parser entirely)
+|`"exclude": ["component-name"]` (only needed to disable a parser entirely)
 |===
 
 === Limitations

docs/modules/ROOT/pages/pipes/configuration.adoc

@@ -77,10 +77,6 @@ See also xref:pipes/timeouts.adoc[Timeouts] for the full timeout model.
 |`1000`
 |Interval (ms) between heartbeats sent from the forked process. Must be significantly less than `socketTimeoutMs`.
 
-|`startupTimeoutMillis`
-|`240000`
-|Maximum time (ms) to wait for a forked process to start up.
-
 |`shutdownClientAfterMillis`
 |`300000`
 |Shut down an idle forked process after this many milliseconds of inactivity.

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

@@ -118,7 +118,7 @@
  *     },
  *     {
  *       "default-parser": {
- *         "_exclude": ["pdf-parser"]
+ *         "exclude": ["pdf-parser"]
  *       }
  *     }
  *   ]
@@ -257,9 +257,9 @@ private static void checkForRedundantExclusions(List<Map<String, Object>> parser
         for (Map<String, Object> parserEntry : parsersList) {
             if (parserEntry.containsKey("default-parser")) {
                 Map<?, ?> config = (Map<?, ?>) parserEntry.get("default-parser");
-                if (config.containsKey("_exclude")) {
+                if (config.containsKey("exclude")) {
                     @SuppressWarnings("unchecked")
-                    List<String> excludes = (List<String>) config.get("_exclude");
+                    List<String> excludes = (List<String>) config.get("exclude");
                     excludedParsers.addAll(excludes);
                 }
             }
@@ -364,7 +364,7 @@ private static Map<String, Object> convertParserElement(Element parserElement,
         }
 
         if (excludes != null && !excludes.isEmpty()) {
-            config.put("_exclude", excludes);
+            config.put("exclude", excludes);
         }
 
         Map<String, Object> result = new LinkedHashMap<>();

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

@@ -89,8 +89,8 @@ public void testParserWithExcludes(@TempDir Path tempDir) throws Exception {
 
         String json = new String(Files.readAllBytes(jsonPath), StandardCharsets.UTF_8);
 
-        // Verify exclude is at the correct level (with underscore prefix)
-        assertTrue(json.contains("\"_exclude\""), "Should have _exclude array");
+        // Verify exclude is at the correct level (no underscore prefix; SPI loader reads "exclude")
+        assertTrue(json.contains("\"exclude\""), "Should have exclude array");
         assertFalse(json.contains("\"_decorate\""), "_decorate should not be used for parser excludes");
         assertTrue(json.contains("\"jsoup-parser\""), "Should exclude jsoup-parser");
         assertTrue(json.contains("\"pdf-parser\""), "Should exclude pdf-parser");
@@ -218,7 +218,7 @@ public void testRedundantExclusionWarning(@TempDir Path tempDir) throws Exceptio
         String json = new String(Files.readAllBytes(jsonPath), StandardCharsets.UTF_8);
 
         // Verify the JSON still contains the exclusions (we don't remove them, just inform)
-        assertTrue(json.contains("\"_exclude\""), "Should still have _exclude array");
+        assertTrue(json.contains("\"exclude\""), "Should still have exclude array");
         assertTrue(json.contains("\"pdf-parser\""), "Should have pdf-parser configured");
         assertTrue(json.contains("\"jsoup-parser\""), "Should have jsoup-parser configured");
 

tika-app/src/test/resources/configs/config-template.json

@@ -45,8 +45,6 @@
     "queueSize": 10000,
     "numEmitters": 1,
     "emitIntermediateResults": false,
-    "startupTimeoutMillis": 240000,
-    "sleepOnStartupTimeoutMillis": 240000,
     "shutdownClientAfterMillis": 300000,
     "numClients": 4,
     "maxFilesProcessedPerProcess": 10000,

tika-app/src/test/resources/configs/tika-config2.json

@@ -2,7 +2,7 @@
   "parsers": [
     {
       "default-parser": {
-        "_exclude": ["executable-parser"],
+        "exclude": ["executable-parser"],
         "_mime-exclude": ["image/jpeg", "application/pdf"]
       }
     },

tika-e2e-tests/tika-grpc/src/test/resources/tika-config-ignite-local.json

@@ -30,23 +30,5 @@
       "--add-opens=java.management/sun.management=ALL-UNNAMED",
       "--add-opens=java.desktop/java.awt.font=ALL-UNNAMED"
     ]
-  },
-  "fetchers": [
-    {
-      "fs": {
-        "staticFetcher": {
-          "basePath": "target/govdocs1"
-        }
-      }
-    }
-  ],
-  "emitters": [
-    {
-      "fs": {
-        "defaultEmitter": {
-          "basePath": "/tmp/output"
-        }
-      }
-    }
-  ]
+  }
 }

tika-e2e-tests/tika-grpc/src/test/resources/tika-config-ignite.json

@@ -30,23 +30,5 @@
       "--add-opens=java.management/sun.management=ALL-UNNAMED",
       "--add-opens=java.desktop/java.awt.font=ALL-UNNAMED"
     ]
-  },
-  "fetchers": [
-    {
-      "fs": {
-        "staticFetcher": {
-          "basePath": "/tika/govdocs1"
-        }
-      }
-    }
-  ],
-  "emitters": [
-    {
-      "fs": {
-        "defaultEmitter": {
-          "basePath": "/tmp/output"
-        }
-      }
-    }
-  ]
+  }
 }

tika-integration-tests/tika-pipes-s3-integration-tests/src/test/resources/s3/tika-config-s3.json

@@ -2,7 +2,7 @@
   "parsers": [
     {
       "default-parser": {
-        "_exclude": [
+        "exclude": [
           "tesseract-ocr-parser"
         ]
       }

tika-parsers/tika-parsers-standard/tika-parsers-standard-integration-tests/src/test/resources/configs/tika-config-rendering.json

@@ -2,7 +2,7 @@
   "parsers": [
     {
       "default-parser": {
-        "parser-excludes": ["pdf-parser"]
+        "exclude": ["pdf-parser"]
       }
     },
     {

tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-microsoft-module/src/test/resources/configs/tika-libpst-config.json

@@ -2,7 +2,7 @@
   "parsers": [
     {
       "default-parser": {
-        "_exclude": [
+        "exclude": [
           "outlook-pst-parser",
           "pst-mail-item-parser"
         ]

tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-microsoft-module/src/test/resources/configs/tika-libpst-eml-config.json

@@ -2,7 +2,7 @@
   "parsers": [
     {
       "default-parser": {
-        "_exclude": [
+        "exclude": [
           "outlook-pst-parser",
           "pst-mail-item-parser"
         ]