From 3cfa6dcee8d438c67a3a45ace3897a53344fddbd Mon Sep 17 00:00:00 2001
From: orangain <orangain@gmail.com>
Date: Thu, 13 Aug 2015 00:31:23 +0900
Subject: [PATCH] Fix progress report

Reported count and rate of processing were wrong:

* Reported number of extracted articles was fewer than the true value by 1.
* Reported rate of processing was completely different from the true value.
---
 WikiExtractor.py | 9 +++++----
 1 file changed, 5 insertions(+), 4 deletions(-)

diff --git a/WikiExtractor.py b/WikiExtractor.py
index 1b36acd..d5de23c 100755
--- a/WikiExtractor.py
+++ b/WikiExtractor.py
@@ -2405,11 +2405,12 @@ def output_process(ordering_queue, docs_queue, out_file, file_size, file_compres
             if next_ordinal in ordering_buffer:
                 output.write(ordering_buffer.pop(next_ordinal))
                 ordering_queue.task_done()
-                if (next_ordinal+1) % 100000 == 0:
-                    interval_rate = (next_ordinal-interval_count) / (default_timer()/interval_start)
-                    logging.info("Extracted %d articles (%.1f/s)", next_ordinal, interval_rate)
+                count_done = next_ordinal + 1
+                if count_done % 100000 == 0:
+                    interval_rate = (count_done - interval_count) / (default_timer() - interval_start)
+                    logging.info("Extracted %d articles (%.1f/s)", count_done, interval_rate)
                     interval_start = default_timer()
-                    interval_count = next_ordinal
+                    interval_count = count_done
                 break
             ordinal, text = docs_queue.get()
             ordering_buffer[ordinal] = text