Mercurial > repos > mingchen0919 > tripal_db_explorer

changeset 6:4bc7752bfd72 draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
resources summary + search
author mingchen0919
date Mon, 19 Mar 2018 16:29:51 -0400
parents 5accedb3133e
children 7fd14296e7e0
files get_content_types.csv get_content_types.xml search_contents.Rmd search_contents.csv search_contents.sh search_contents.xml search_contents_render.R
diffstat 7 files changed, 178 insertions(+), 57 deletions(-) [+]
line wrap: on
line diff
--- a/get_content_types.csv	Mon Mar 19 00:43:50 2018 -0400
+++ b/get_content_types.csv	Mon Mar 19 16:29:51 2018 -0400
@@ -3,3 +3,4 @@
 d,1,character,report.files_path,data,
 s,1,character,sink_message,data,
 u,1,character,web_services_root_url,
+r,1,character,search_results,
--- a/get_content_types.xml	Mon Mar 19 00:43:50 2018 -0400
+++ b/get_content_types.xml	Mon Mar 19 16:29:51 2018 -0400
@@ -1,11 +1,19 @@
-<tool id="get_content_types" name="Get content types" version="1.0.0">
-  <description>Tripal database explorer: get content types&#xD;
+<tool id="get_content_types" name="tripal_db_explorer: resources summary" version="1.0.0">
+    <description>
     </description>
-  <requirements>
-        <requirement type="package" version="1.15.0.6-0">pandoc</requirement><requirement type="package" version="1.20.0">r-getopt</requirement><requirement type="package" version="1.6">r-rmarkdown</requirement><requirement type="package" version="1.5">r-jsonlite</requirement><requirement type="package" version="0.2">r-dt</requirement><requirement type="package" version="3.1">r-curl</requirement></requirements>
-  <stdio>
-        <regex match="XXX" source="stderr" level="warning" description="Check the warnings_and_errors.txt file for more details."/></stdio>
-  <command><![CDATA[export TOOL_DIR='${__tool_directory__}' &&
+    <requirements>
+        <requirement type="package" version="1.15.0.6-0">pandoc</requirement>
+        <requirement type="package" version="1.20.0">r-getopt</requirement>
+        <requirement type="package" version="1.6">r-rmarkdown</requirement>
+        <requirement type="package" version="1.5">r-jsonlite</requirement>
+        <requirement type="package" version="0.2">r-dt</requirement>
+        <requirement type="package" version="3.1">r-curl</requirement>
+    </requirements>
+    <stdio>
+        <regex match="XXX" source="stderr" level="warning"
+               description="Check the warnings_and_errors.txt file for more details."/>
+    </stdio>
+    <command><![CDATA[export TOOL_DIR='${__tool_directory__}' &&
 
 Rscript '${__tool_directory__}/'get_content_types_render.R
 
@@ -14,11 +22,15 @@
 	-s '$sink_message'
 	-u '$web_services_root_url'
 ]]></command>
-  <inputs>
-        <param type="text" name="web_services_root_url" label="Web services root URL" optional="False"/></inputs>
-  <outputs>
-        <data name="report" format="html" label="${tool.name} report" hidden="false"/><data name="sink_message" format="txt" label="${tool.name} log" from_work_dir="warnings_and_errors.txt" hidden="false"/></outputs>
-  <citations>
+    <inputs>
+        <param type="text" name="web_services_root_url" label="Web services root URL" optional="False"/>
+    </inputs>
+    <outputs>
+        <data name="report" format="html" label="${tool.name} report" hidden="false"/>
+        <data name="sink_message" format="txt" label="${tool.name} log" from_work_dir="warnings_and_errors.txt"
+              hidden="false"/>
+    </outputs>
+    <citations>
         <citation type="bibtex"><![CDATA[
             @article{allaire2016rmarkdown,
             title={rmarkdown: Dynamic Documents for R, 2016},
@@ -28,7 +40,8 @@
             volume={6},
             year={2016}
             }
-        ]]></citation><citation type="bibtex"><![CDATA[
+        ]]></citation>
+        <citation type="bibtex"><![CDATA[
             @book{xie2015dynamic,
             title={Dynamic Documents with R and knitr},
             author={Xie, Yihui},
@@ -36,5 +49,6 @@
             year={2015},
             publisher={CRC Press}
             }
-        ]]></citation></citations>
+        ]]></citation>
+    </citations>
 </tool>
--- a/search_contents.Rmd	Mon Mar 19 00:43:50 2018 -0400
+++ b/search_contents.Rmd	Mon Mar 19 16:29:51 2018 -0400
@@ -1,30 +1,57 @@
 ---
-title: 'HTML report title'
+title: 'Tripal database explorer: search results'
 output:
     html_document:
-      number_sections: true
-      toc: true
       theme: cosmo
       highlight: tango
-      code_folding: hide
 ---
 
 ```{r setup, include=FALSE, warning=FALSE, message=FALSE}
 knitr::opts_chunk$set(
-  echo = TRUE,
+  echo = FALSE,
   error = TRUE
 )
 ```
 
 
-# Code for computational analysis
-
-```{r 'step 1'}
-
-```
-
-```{r 'ste[ 2'}
-
+```{r}
+# get member ids after implementing search filtering
+content_type_url = opt$X_u
+path = "organism,genus=Fagus&name=ABall;contains"
+path = sub('\\|', '&', opt$X_s)
+search_url = paste0(content_type_url, '?', path)
+search_members = fromJSON(search_url)
+# search_url_rebuild = paste0(search_url, '&limit=', search_members$totalItems)
+total_records = as.integer(opt$X_l)
+if (total_records == 0) {
+  total_records = search_members$totalItems
+} 
+search_url_rebuild = paste0(search_url, '&limit=', total_records)
+re_search_members = fromJSON(search_url_rebuild)
 ```
 
 
+```{r}
+# get requested field values from search results
+request_paths = sub(',', '\\.', strsplit(opt$X_e, '\\|')[[1]])
+res = data.frame()
+for (id in re_search_members$member$`@id`) {
+  member = as.data.frame(fromJSON(id))
+  res = rbind(res, member[, request_paths])
+}
+colnames(res) = request_paths
+```
+
+```{r}
+if (nrow(res) < 1) {
+  cat('No records found.')
+} else {
+  DT::datatable(res)
+}
+```
+
+```{r}
+# save results to file
+write.table(res, file = opt$X_r, quote = FALSE, col.names = FALSE)
+```
+
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/search_contents.csv	Mon Mar 19 16:29:51 2018 -0400
@@ -0,0 +1,9 @@
+short flag,argument mask,data type,variable name,galaxy input type,description
+o,1,character,report,data,
+d,1,character,report.files_path,data,
+u,1,character,content_type_url,data,
+s,1,character,search_paths,
+e,1,character,extract_paths,
+l,1,character,records_number,
+r,1,character,search_results,
+
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/search_contents.sh	Mon Mar 19 16:29:51 2018 -0400
@@ -0,0 +1,26 @@
+export TOOL_DIR='${__tool_directory__}' &&
+
+Rscript '${__tool_directory__}/'search_contents_render.R
+
+	-o '$report'
+	-d '$report.files_path'
+	-u '$content_type_url'
+
+	#set $sep = ''
+	#set $search_paths = ''
+	#for $search_path in $search_section.search_field_repeat:
+	  #set $search_paths += $sep + str($search_path.field_path) + ';' + str($search_path.search_operator)
+	  #set $sep = '|'
+	#end for
+	-s '$search_paths'
+
+	#set $sep = ''
+	#set $extract_paths = ''
+	#for $extract_path in $extract_section.extract_field_repeat:
+	  #set $extract_paths += $sep + str($extract_path.field_path)
+	  #set $sep = '|'
+	#end for
+	-e '$extract_paths'
+
+	-l '$records_number'
+	-r '$search_results'
--- a/search_contents.xml	Mon Mar 19 00:43:50 2018 -0400
+++ b/search_contents.xml	Mon Mar 19 16:29:51 2018 -0400
@@ -1,30 +1,71 @@
-<tool id="search_contents" name="Search contents" version="1.0.0">
-  <description>
-        some description
+<tool id="search_contents" name="tripal_db_explorer: search" version="1.0.0">
+    <description>
     </description>
-  <requirements>
-        <requirement type="package" version="1.15.0.6-0">pandoc</requirement><requirement type="package" version="1.20.0">r-getopt</requirement><requirement type="package" version="1.6">r-rmarkdown</requirement><requirement type="package" version="1.5">r-jsonlite</requirement><requirement type="package" version="0.2">r-dt</requirement><requirement type="package" version="3.1">r-curl</requirement></requirements>
-  <stdio>
-        <regex match="XXX" source="stderr" level="warning" description="Check the warnings_and_errors.txt file for more details."/></stdio>
-  <command><![CDATA[
-        export TOOL_DIRECTORY='${__tool_directory__}' &&
+    <requirements>
+        <requirement type="package" version="1.15.0.6-0">pandoc</requirement>
+        <requirement type="package" version="1.20.0">r-getopt</requirement>
+        <requirement type="package" version="1.6">r-rmarkdown</requirement>
+        <requirement type="package" version="1.5">r-jsonlite</requirement>
+        <requirement type="package" version="0.2">r-dt</requirement>
+        <requirement type="package" version="3.1">r-curl</requirement>
+    </requirements>
+    <stdio>
+        <regex match="XXX" source="stderr" level="warning"
+               description="Check the warnings_and_errors.txt file for more details."/>
+    </stdio>
+    <command><![CDATA[export TOOL_DIR='${__tool_directory__}' &&
 
-        Rscript '${__tool_directory__}/rmarkdown_report_render.R'
+Rscript '${__tool_directory__}/'search_contents_render.R
+
+	-o '$report'
+	-d '$report.files_path'
+	-u '$content_type_url'
+
+	#set $sep = ''
+	#set $search_paths = ''
+	#for $search_path in $search_section.search_field_repeat:
+	  #set $search_paths += $sep + str($search_path.field_path) + ';' + str($search_path.search_operator)
+	  #set $sep = '|'
+	#end for
+	-s '$search_paths'
 
-			-e $echo
-			-o $report
-			-d $report.files_path
-			-s $sink_message
-			-t '${__tool_directory__}'
-
+	#set $sep = ''
+	#set $extract_paths = ''
+	#for $extract_path in $extract_section.extract_field_repeat:
+	  #set $extract_paths += $sep + str($extract_path.field_path)
+	  #set $sep = '|'
+	#end for
+	-e '$extract_paths'
 
-        
-    ]]></command>
-  <inputs>
-        <param type="text" name="web_services_root_url" label="Web services root URL" optional="False"/><section name="search_fields" title="Fields being searched" expanded="True"><repeat name="search_field_repeat" title="search fields" min="1" max="20" default="1"><param type="text" name="field_path_search" optional="False"/></repeat></section><section name="extract_fields" title="Fields being extracted"><repeat name="extract_field_repeat" title="Fields being extracted" min="1" max="20" default="1"><param type="text" name="field_path_extract" optional="False"/></repeat></section></inputs>
-  <outputs>
-        <data name="report" format="html" label="${tool.name} report" hidden="false"/><data format="txt" name="sink_message" label="Warnings and Errors" from_work_dir="warnings_and_errors.txt"/></outputs>
-  <citations>
+	-l '$records_number'
+	-r '$search_results'
+]]></command>
+    <inputs>
+        <param type="text" name="content_type_url" label="Content type URL" optional="False"/>
+        <section name="search_section" title="Search: fields" expanded="True">
+            <repeat name="search_field_repeat" title="Field paths" min="1" max="20" default="1">
+                <param type="text" name="field_path" optional="False"/>
+                <param type="select" name="search_operator" optional="False">
+                    <option value="eq" selected="false">equal (string value)</option>
+                    <option value="contains" selected="true">contains (string value)</option>
+                </param>
+            </repeat>
+        </section>
+        <section name="extract_section" title="Extract: fields" expanded="True">
+            <repeat name="extract_field_repeat" title="Field paths" min="1" max="20" default="1">
+                <param type="text" name="field_path" optional="False"/>
+            </repeat>
+        </section>
+        <param type="integer" name="records_number" label="Records number"
+               help="The maximum number of records to be extracted" optional="False" value="25" min="0"/>
+    </inputs>
+    <outputs>
+        <data name="report" format="html" label="${tool.name} report" hidden="false"/>
+        <data name="sink_message" format="txt" label="${tool.name} log" from_work_dir="warnings_and_errors.txt"
+              hidden="false"/>
+        <data name="search_results" format="txt" label="${tool.name} results" hidden="false"/>
+    </outputs>
+    <citations>
         <citation type="bibtex"><![CDATA[
             @article{allaire2016rmarkdown,
             title={rmarkdown: Dynamic Documents for R, 2016},
@@ -34,7 +75,8 @@
             volume={6},
             year={2016}
             }
-        ]]></citation><citation type="bibtex"><![CDATA[
+        ]]></citation>
+        <citation type="bibtex"><![CDATA[
             @book{xie2015dynamic,
             title={Dynamic Documents with R and knitr},
             author={Xie, Yihui},
@@ -42,5 +84,6 @@
             year={2015},
             publisher={CRC Press}
             }
-        ]]></citation></citations>
+        ]]></citation>
+    </citations>
 </tool>
--- a/search_contents_render.R	Mon Mar 19 00:43:50 2018 -0400
+++ b/search_contents_render.R	Mon Mar 19 16:29:51 2018 -0400
@@ -10,6 +10,7 @@
 
 library(getopt)
 library(rmarkdown)
+library(jsonlite)
 #------------------------------------------------
 
 
@@ -17,13 +18,13 @@
 # load helper function
 source(paste0(Sys.getenv('TOOL_DIR'), '/helper.R'))
 # import getopt specification matrix from a csv file
-spec_csv = paste0(Sys.getenv('TOOL_DIR'), '/getopt_specification.csv')
-opt = getopt(getopt_specification_matrix(spec_csv))
+opt = getopt(getopt_specification_matrix('/search_contents.csv'))
 opt$X_t = Sys.getenv('TOOL_DIR')
+print(opt)
 #----------------------------------------------------
 
 
-#-----------using passed arguments in R 
+#-----------using passed arguments in R
 #           to define system environment variables---
 do.call(Sys.setenv, opt[-1])
 #----------------------------------------------------
@@ -34,7 +35,7 @@
 OUTPUT_DIR = opt$X_d
 TOOL_DIR =   opt$X_t
 OUTPUT_REPORT = opt$X_o
-RMD_NAME = ''
+RMD_NAME = 'search_contents.Rmd'
 
 # create the output associated directory to store all outputs
 dir.create(OUTPUT_DIR, recursive = TRUE)
@@ -48,4 +49,4 @@
 
 ##--------end of code rendering .Rmd templates----------------
 sink()
-##=========== End of sinking output=============================
\ No newline at end of file
+##=========== End of sinking output=============================