Store the Harbormaster log chunk format on the log record

Summary: Depends on D19137. Ref T13088. This allows `rebuild-log` to skip work if the chunks are already compressed. It also prepares for a future GC which is looking for "text" or "gzip" chunks to throw away in favor of archival into Files; such a GC can use this column to find collectable logs and then write "file" to it, meaning "chunks are gone, this data is only available in Files".

Test Plan: Ran migration, saw logs populate as "text". Ran `rebuild-log`, saw logs rebuild as "gzip".

Subscribers: PHID-OPKG-gm6ozazyms6q6i22gyam

Maniphest Tasks: T13088

Differential Revision: https://secure.phabricator.com/D19138

resources/sql/autopatches/20180223.log.02.chunkformat.sql

@@ -0,0 +1,2 @@
+ALTER TABLE {$NAMESPACE}_harbormaster.harbormaster_buildlog
+  ADD chunkFormat VARCHAR(32) NOT NULL COLLATE {$COLLATE_TEXT};

resources/sql/autopatches/20180223.log.03.chunkdefault.sql

@@ -0,0 +1,2 @@
+UPDATE {$NAMESPACE}_harbormaster.harbormaster_buildlog
+  SET chunkFormat = 'text' WHERE chunkFormat = '';

src/applications/harbormaster/storage/build/HarbormasterBuildLog.php

@@ -13,6 +13,7 @@ final class HarbormasterBuildLog
   protected $live;
   protected $filePHID;
   protected $byteLength;
+  protected $chunkFormat;
 
   private $buildTarget = self::ATTACHABLE;
   private $rope;
@@ -44,7 +45,8 @@ final class HarbormasterBuildLog
       ->setBuildTargetPHID($build_target->getPHID())
       ->setDuration(null)
       ->setLive(1)
-      ->setByteLength(0);
+      ->setByteLength(0)
+      ->setChunkFormat(HarbormasterBuildLogChunk::CHUNK_ENCODING_TEXT);
   }
 
   public function scheduleRebuild($force) {
@@ -73,6 +75,7 @@ final class HarbormasterBuildLog
         'live' => 'bool',
         'filePHID' => 'phid?',
         'byteLength' => 'uint64',
+        'chunkFormat' => 'text32',
       ),
       self::CONFIG_KEY_SCHEMA => array(
         'key_buildtarget' => array(
@@ -105,6 +108,11 @@ final class HarbormasterBuildLog
       ->setPageSize(8);
   }
 
+  public function newDataIterator() {
+    return $this->newChunkIterator()
+      ->setAsString(true);
+  }
+
   private function loadLastChunkInfo() {
     $chunk_table = new HarbormasterBuildLogChunk();
     $conn_w = $chunk_table->establishConnection('w');
@@ -188,6 +196,10 @@ final class HarbormasterBuildLog
       $this->writeEncodedChunk($rope, $byte_limit, $mode);
     }
 
+    $this
+      ->setChunkFormat($mode)
+      ->save();
+
     $this->saveTransaction();
   }
 

src/applications/harbormaster/worker/HarbormasterLogWorker.php

@@ -58,20 +58,23 @@ final class HarbormasterLogWorker extends HarbormasterWorker {
     $is_force = idx($data, 'force');
 
     if (!$log->getByteLength() || $is_force) {
-      $iterator = $log->newChunkIterator()
-        ->setAsString(true);
+      $iterator = $log->newDataIterator();
 
       $byte_length = 0;
       foreach ($iterator as $block) {
         $byte_length += strlen($block);
       }
+
       $log
         ->setByteLength($byte_length)
         ->save();
     }
 
-    if ($log->canCompressLog()) {
-      $log->compressLog();
+    $format_text = HarbormasterBuildLogChunk::CHUNK_ENCODING_TEXT;
+    if (($log->getChunkFormat() === $format_text) || $is_force) {
+      if ($log->canCompressLog()) {
+        $log->compressLog();
+      }
     }
 
     if ($is_force) {
@@ -79,8 +82,7 @@ final class HarbormasterLogWorker extends HarbormasterWorker {
     }
 
     if (!$log->getFilePHID()) {
-      $iterator = $log->newChunkIterator()
-        ->setAsString(true);
+      $iterator = $log->newDataIterator();
 
       $source = id(new PhabricatorIteratorFileUploadSource())
         ->setName('harbormaster-log-'.$log->getID().'.log')