(accumulo) 01/01: Merge branch '2.1'

[ddanielr]

This is an automated email from the ASF dual-hosted git repository.

ddanielr pushed a commit to branch main
in repository https://gitbox.apache.org/repos/asf/accumulo.git

commit 171a1e144caa9d2eb382846d2dc45a424487d3ec
Merge: 162b8effb1 92331ea113
Author: Daniel Roberts <ddani...@gmail.com>
AuthorDate: Tue Mar 12 15:17:40 2024 +0000

    Merge branch '2.1'

 .../accumulo/core/file/rfile/GenerateSplits.java   | 32 +++++++++--
 .../core/file/rfile/GenerateSplitsTest.java        | 64 +++++++++++++++++++---
 2 files changed, 82 insertions(+), 14 deletions(-)

diff --cc 
core/src/main/java/org/apache/accumulo/core/file/rfile/GenerateSplits.java
index 5928ade21d,865210a970..7ee151f0a2
--- a/core/src/main/java/org/apache/accumulo/core/file/rfile/GenerateSplits.java
+++ b/core/src/main/java/org/apache/accumulo/core/file/rfile/GenerateSplits.java
@@@ -137,19 -143,33 +144,33 @@@ public class GenerateSplits implements 
        Path path = new Path(file);
        fs = PrintInfo.resolveFS(log, hadoopConf, path);
        // get all the files in the directory
 -      filePaths.addAll(getFiles(fs, path));
 +      files.addAll(getFiles(fs, path));
      }
  
 -    if (filePaths.isEmpty()) {
 +    if (files.isEmpty()) {
        throw new IllegalArgumentException("No files were found in " + 
opts.files);
      } else {
 -      log.trace("Found the following files: {}", filePaths);
 +      log.trace("Found the following files: {}", files);
      }
  
+     if (!encode) {
+       // Generate the allowed Character set
+       for (int i = 0; i < 10; i++) {
+         // 0-9
+         allowedChars.add((char) (i + 48));
+       }
+       for (int i = 0; i < 26; i++) {
+         // Uppercase A-Z
+         allowedChars.add((char) (i + 65));
+         // Lowercase a-z
+         allowedChars.add((char) (i + 97));
+       }
+     }
+ 
      // if no size specified look at indexed keys first
      if (opts.splitSize == 0) {
 -      splits = getIndexKeys(siteConf, hadoopConf, fs, filePaths, 
requestedNumSplits, encode,
 -          cryptoService);
 +      splits =
 +          getIndexKeys(siteConf, hadoopConf, fs, files, requestedNumSplits, 
encode, cryptoService);
        // if there weren't enough splits indexed, try again with size = 0
        if (splits.size() < requestedNumSplits) {
          log.info("Only found {} indexed keys but need {}. Doing a full scan 
on files {}",