diff --git a/extra/spider/report/authors.txt b/extra/spider/report/authors.txt new file mode 100644 index 0000000000..d4f5d6b3ae --- /dev/null +++ b/extra/spider/report/authors.txt @@ -0,0 +1 @@ +Slava Pestov \ No newline at end of file diff --git a/extra/spider/report/report.factor b/extra/spider/report/report.factor new file mode 100644 index 0000000000..8bb4f91f82 --- /dev/null +++ b/extra/spider/report/report.factor @@ -0,0 +1,113 @@ +! Copyright (C) 2009 Slava Pestov. +! See http://factorcode.org/license.txt for BSD license. +USING: accessors arrays assocs combinators kernel math +math.statistics namespaces sequences sorting xml.syntax +spider ; +IN: spider.report + +SYMBOL: network-failures +SYMBOL: broken-pages +SYMBOL: timings + +: record-broken-page ( url spider-result -- ) + headers>> [ code>> ] [ message>> ] bi 2array 2array + broken-pages push ; + +: record-page-timings ( url spider-result -- ) + fetch-time>> 2array timings get push ; + +: record-network-failure ( url -- ) + network-failures get push ; + +: process-result ( url spider-result -- ) + { + { f [ record-network-failure ] } + [ + dup headers>> code>> 200 = + [ record-page-timings ] [ record-broken-page ] if + ] + } case ; + +CONSTANT: slowest 5 + +SYMBOL: slowest-pages +SYMBOL: mean-time +SYMBOL: median-time +SYMBOL: time-std + +: process-timings ( -- ) + timings get sort-values + [ slowest short tail* reverse slowest-pages set ] + [ + values + [ mean 1000000 /f mean-time set ] + [ median 1000000 /f median-time set ] + [ std 1000000 /f time-std set ] tri + ] bi ; + +: process-results ( results -- ) + V{ } clone network-failures set + V{ } clone broken-pages set + V{ } clone timings set + [ process-result ] assoc-each + process-timings ; + +: info-table ( alist -- html ) + [ + first2 dupd 1000000 /f + [XML +
Mean | <-> seconds |
---|---|
Median | <-> seconds |
Standard deviation | <-> seconds |