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 2019/05/07 16:44:24 UTC

[tika] branch master updated: TIKA-2863 -- add reports for time details; add real for use w pg

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

tallison pushed a commit to branch master
in repository https://gitbox.apache.org/repos/asf/tika.git


The following commit(s) were added to refs/heads/master by this push:
     new 1c07dc9  TIKA-2863 -- add reports for time details; add real for use w pg
1c07dc9 is described below

commit 1c07dc9c2a03cd59f41a73420a568abfaacc7b5d
Author: TALLISON <ta...@apache.org>
AuthorDate: Tue May 7 12:44:13 2019 -0400

    TIKA-2863 -- add reports for time details; add real for use w pg
---
 .../java/org/apache/tika/eval/reports/Report.java  |  1 +
 .../src/main/resources/comparison-reports.xml      | 29 +++++++++++++++++++---
 2 files changed, 26 insertions(+), 4 deletions(-)

diff --git a/tika-eval/src/main/java/org/apache/tika/eval/reports/Report.java b/tika-eval/src/main/java/org/apache/tika/eval/reports/Report.java
index 8ac7fca..41a1424 100644
--- a/tika-eval/src/main/java/org/apache/tika/eval/reports/Report.java
+++ b/tika-eval/src/main/java/org/apache/tika/eval/reports/Report.java
@@ -164,6 +164,7 @@ public class Report {
             case Types.DOUBLE:
             case Types.FLOAT:
             case Types.DECIMAL:
+            case Types.REAL:
             case Types.NUMERIC:
                 double dbl = rs.getDouble(colIndex);
                 if (rs.wasNull()) {
diff --git a/tika-eval/src/main/resources/comparison-reports.xml b/tika-eval/src/main/resources/comparison-reports.xml
index d3e2329..e84454a 100644
--- a/tika-eval/src/main/resources/comparison-reports.xml
+++ b/tika-eval/src/main/resources/comparison-reports.xml
@@ -1711,19 +1711,40 @@
     </report>
 
     <report reportName="Parse Time (Millis) Compared"
-            reportFilename="content/parse_time_millis_compared.xlsx"
+            reportFilename="parse_times/parse_time_millis_by_mime_compared.xlsx"
             format="xlsx"
             includeSql="true">
         <sql>
-            select ma.mime_string as mime_string_a,
-            mb.mime_string as mime_string_b,
-            total_a, total_b, prcnt_increase
+            select ma.mime_string as MIME_STRING_A,
+            mb.mime_string as MIME_STRING_B,
+            total_a as TOTAL_MILLIS_A, total_b as TOTAL_MILLIS_B,
+            prcnt_increase as PERCENT_INCREASE
             from parse_time_compared ptc
             join mimes ma on ptc.mime_id_a=ma.mime_id
             join mimes mb on ptc.mime_id_b=mb.mime_id
             order by prcnt_increase desc
         </sql>
     </report>
+    <report reportName="Parse Time (Millis) Details"
+            reportFilename="parse_times/parse_time_millis_details.xlsx"
+            format="xlsx"
+            includeSql="true">
+        <sql>
+            select file_path, c.length as CONTAINTER_LENGTH,
+            ma.mime_string as MIME_STRING_A,
+            mb.mime_string as MIME_STRING_B,
+            pa.elapsed_time_millis as TOTAL_MILLIS_A,
+            pb.elapsed_time_millis as TOTAL_MILLIS_B,
+            (pb.elapsed_time_millis-pa.elapsed_time_millis) as DIFF_MILLIS
+            from profiles_a pa
+            join profiles_b pb on pa.id=pb.id
+            join mimes ma on ma.mime_id=pa.mime_id
+            join mimes mb on mb.mime_id=pb.mime_id
+            join containers c on pa.container_id=c.container_id
+            order by DIFF_MILLIS desc
+            limit 20000;
+        </sql>
+    </report>
     <after>
         <sql>drop table if exists md5_multiples_tmp_a</sql>
         <sql>drop table if exists md5_multiples_tmp_b</sql>