Mercurial > repos > ecology > aquainfra_ogc_api_processes

changeset 1:1ff618d89af4 draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
planemo upload for repository https://github.com/AquaINFRA/tools-ecology/tree/master commit 3989415663771a85b3a0be6c02308994ac4adc85
author ecology
date Wed, 23 Oct 2024 22:35:20 +0000
parents 0077885b6f1d
children af00a67d3649
files aquainfra_ogc_api_processes.R aquainfra_ogc_api_processes.xml test-data/points_att_polygon_test_input_3.txt
diffstat 3 files changed, 83 insertions(+), 106 deletions(-) [+]
line wrap: on
line diff
--- a/aquainfra_ogc_api_processes.R	Mon Oct 14 12:23:01 2024 +0000
+++ b/aquainfra_ogc_api_processes.R	Wed Oct 23 22:35:20 2024 +0000
@@ -5,9 +5,7 @@
 cat("start generic wrapper service \n")
 
 remove_null_values <- function(x) {
-  # Check if the input is a list
   if (is.list(x)) {
-    # Remove NULL values and apply the function recursively to sublists
     x <- lapply(x, remove_null_values)
     x <- x[!sapply(x, is.null)]
   }
@@ -18,11 +16,10 @@
   con <- file("inputs.json", "r")
   lines <- readLines(con)
   close(con)
-  
+
   json_string <- paste(lines, collapse = "\n")
   json_data <- fromJSON(json_string)
-  
-  # Remove NULL values from json_data
+
   cleaned_json_data <- remove_null_values(json_data)
   return(cleaned_json_data$conditional_process)
 }
@@ -38,9 +35,10 @@
 
 getOutputs <- function(inputs, output, server) {
   url <-
-    paste(paste(server, "/processes/", sep = ""),
+    paste(paste(server, "processes/", sep = ""),
           inputs$select_process,
           sep = "")
+  print(url)
   request <- request(url)
   response <- req_perform(request)
   responseBody <- parseResponseBody(response$body)
@@ -81,10 +79,6 @@
   
   cat("\n Process executed")
   cat("\n status: ", response$status_code)
-  #if ( process == "barplot-trend-results") {
-  #  process = "batplot-trend-results"
-  #}
-  #href <- parseResponseBody(response$body)$outputs[[gsub("-", "_", process)]]$href
   jobId <- parseResponseBody(response$body)$jobID
   
   return(jobId)
@@ -115,20 +109,14 @@
   return(response)
 }
 
-# Recursive function to search for href in a nested list
 findHref <- function(obj) {
-  hrefs <- c()  # Initialize an empty vector to store hrefs
-  
+  hrefs <- c()
   if (is.list(obj)) {
-    # If the object is a list, loop through its elements
     for (name in names(obj)) {
       element <- obj[[name]]
-      
       if (is.list(element)) {
-        # Recursively search if the element is another list
         hrefs <- c(hrefs, findHref(element))
       } else if (name == "href") {
-        # If the element has a name "href", capture its value
         hrefs <- c(hrefs, element)
       }
     }
@@ -154,16 +142,11 @@
         if (result$status_code == 200) {
           resultBody <- parseResponseBody(result$body)
           print(resultBody)
-          
-          # Call the recursive function to find all hrefs
           hrefs <- findHref(resultBody)
           
           if (length(hrefs) > 0) {
-            # Collapse the URLs with a newline
             urls_with_newline <- paste(hrefs, collapse = "\n")
             print(urls_with_newline)
-            
-            # Write the URLs to a file
             con <- file(outputData, "w")
             writeLines(urls_with_newline, con = con)
             close(con)
@@ -190,8 +173,6 @@
   }
 }
 
-
-
 saveResult <- function(href, outputData) {
   con <- file(outputData, "w")
     writeLines(href, con = con)
@@ -206,7 +187,6 @@
 
 print("--> Retrieve parameters")
 inputParameters <- getParameters()
-#print(inputParameters)
 print("--> Parameters retrieved")
 
 args <- commandArgs(trailingOnly = TRUE)
@@ -217,54 +197,24 @@
 print("--> Outputs retrieved")
 
 print("--> Parse inputs")
+
 convertedKeys <- c()
+
 for (key in names(inputParameters)) {
   if (is.character(inputParameters[[key]]) &&
       (endsWith(inputParameters[[key]], ".dat") ||
        endsWith(inputParameters[[key]], ".txt"))) {
     con <- file(inputParameters[[key]], "r")
     url_list <- list()
-    #while (length(line <- readLines(con, n = 1)) > 0) {
-    #  if (is_url(line)) {
-    #    url_list <- c(url_list, list(list(href = trimws(line))))
-    #  }
-    #}
+
     con <- file(inputParameters[[key]], "r")
     lines <- readLines(con)
-    print("--------------------------------------------------------------------1")
     print(length(lines))
     close(con)
-    if (!length(lines) > 1 && endsWith(lines, ".jp2") && startsWith(lines, "https")) {
-      print("--------------------------------------------------------------------2")
-      tmp <- list()
-      tmp$href <- lines
-      tmp$type <- "image/jp2"
-      inputParameters[[key]] <- tmp
-    }
-    else if (!length(lines) > 1 && endsWith(lines, ".zip") && startsWith(lines, "https")) {
-      print("--------------------------------------------------------------------3")
-      json_string <- paste(lines, collapse = "\n")
-      inputParameters[[key]] <- json_string
-    } else if (!length(lines) > 1 && (endsWith(lines, ".xlsx") || endsWith(lines, ".csv") || grepl("f=csv", lines)) && startsWith(lines, "https")) {
-      print("--------------------------------------------------------------------4")
-      json_string <- paste(lines, collapse = "\n")
-      inputParameters[[key]] <- json_string
-    } else if (inputParameters$select_process == "plot-image" ||
-               inputParameters$select_process == "reproject-image") {
-      print("--------------------------------------------------------------------5")
-      tmp <- list()
-      tmp$href <- lines
-      tmp$type <- "image/tiff; application=geotiff"
-      if (inputParameters$select_process == "reproject-image") {
-        tmp$type <- "image/tiff; subtype=geotiff"
-      }
-      inputParameters[[key]] <- tmp
-    } else {
-      print("-----------------------------------6")
-      json_string <- paste(lines, collapse = "\n")
-      json_data <- fromJSON(json_string)
-      inputParameters[[key]] <- json_data
-    }
+
+    json_string <- paste(lines, collapse = "\n")
+    inputParameters[[key]] <- json_string
+
     convertedKeys <- append(convertedKeys, key)
   }
   else if (grepl("_Array_", key)) {
@@ -296,24 +246,15 @@
     }
     
     inputParameters[[key]] <- convertedValues
-    print("-------------------------")
-    print(convertedValues)
-    print("-------------------------")
     convertedKeys <- append(convertedKeys, convertedKey)
   } else {
-    print("-------------------------")
-    print(key)
-    print(inputParameters[[key]])
     if (!is.null(inputParameters[[key]])) {
       convertedKeys <- append(convertedKeys, key)
     }
-    print("-------------------------")
-    
   }
 }
 print(inputParameters)
 names(inputParameters) <- convertedKeys
-#print(inputParameters)
 print("--> Inputs parsed")
 
 print("--> Prepare process execution")
--- a/aquainfra_ogc_api_processes.xml	Mon Oct 14 12:23:01 2024 +0000
+++ b/aquainfra_ogc_api_processes.xml	Wed Oct 23 22:35:20 2024 +0000
@@ -1,11 +1,11 @@
-<tool id="aquainfra_ogc_api_processes" name="AquaINFRA OGC API Processes" version="0.1.0" profile="22.05">
+<tool id="aquainfra_ogc_api_processes" name="AquaINFRA OGC API Processes" version="0.2.0" profile="22.05">
     <description/>
     <macros>
         <import>macros.xml</import>
     </macros>
-	<creator>
+    <creator>
 	    <organization name="EOSC AquaINFRA" url="https://aquainfra.eu/"/>
-	</creator>
+    </creator>
     <expand macro="requirements"/>
     <command detect_errors="exit_code"><![CDATA[
     Rscript '$__tool_directory__/aquainfra_ogc_api_processes.R'
@@ -25,20 +25,21 @@
                 <option value="barplot-trend-results">barplot-trend-results: Visualisation of statistical analysis results</option>
                 <option value="map-trends-static">map-trends-static: Spatial visualisation of regions and data points</option>
                 <option value="map-shapefile-points">map-shapefile-points: Spatial visualisation of regions and data points</option>
+                <option value="owt-classification">OWT-classification: Optical Water Type classification for ocean, coastal and inland waters</option>
             </param>
             <when value="points-att-polygon">
                 <param name="regions" label="Study region or study subregions" optional="false" help="URL (stored in a .txt file) to the study region, or several regions, to classify your input data into groups of interest. Currently it has to be provided as a shapefile. It can be in any coordinate system and will be transformed to WGS84 during this process." type="data" format="txt"/>
                 <param name="input_data" label="Table to be merged with study region" optional="false" help="URL (stored in a .txt file) to the input table containing the in-situ data points with coordinates. Can be provided as Excel file or CSV file (comma-separated text file). The coordinates have to be in WGS84 coordinate system." type="data" format="txt"/>
-                <param name="colname_long" label="Column name for longitude" optional="false" help="Name of the column that contains longitude values (in WGS84)." type="text"/>
-                <param name="colname_lat" label="Column name for latitude" optional="false" help="Name of the column that contains latitude values (in WGS84)." type="text"/>
+                <param name="colname_long" label="Column name for longitude" help="Name of the column that contains longitude values (in WGS84)." type="text"/>
+                <param name="colname_lat" label="Column name for latitude" help="Name of the column that contains latitude values (in WGS84)." type="text"/>
             </when>
             <when value="peri-conv">
                 <param name="input_data" label="Table to be grouped by date, with date colum" help="URL (stored in a .txt file) to the table with a column containing a date. It can have other columns which will not be changed during this process." type="data" format="txt"/>
                 <param name="colname_date" label="Date column name" optional="false" help="Column name of the date column in the format defined above. Example: 'visit date'." type="text"/>
                 <param name="date_format" label="Date format" optional="true" help="The date format used to parse the date, i.e. to extract day, month and year from the date column, e.g.  or 'y-m-d' for dates like '1998-08-22' (this is the default) or 'y/m/d' for dates like '1998/08/22'." type="select">
-				    <option value="y-m-d">y-m-d</option>
+                    <option value="y-m-d">y-m-d</option>
                     <option value="y/m/d">y/m/d</option>
-				</param>
+                </param>
                 <param name="group_to_periods" label="Periods to group the data into" optional="true" help="Define the periods that you want the data to be grouped into. Please follow the example: 'Dec-01:Mar-01,Mar-02:May-30,Jun-01:Aug-30,Sep-01:Nov-30' (first three letters of each month, then a minus/hyphen, then the day (two digits), then comma, then the next period)." type="text">
                     <validator type="regex">^(Jan|Feb|Mar|Apr|May|Jun|Jul|Aug|Sep|Oct|Nov|Dec)-[0-3][0-9]:(Jan|Feb|Mar|Apr|May|Jun|Jul|Aug|Sep|Oct|Nov|Dec)-[0-3][0-9](,(Jan|Feb|Mar|Apr|May|Jun|Jul|Aug|Sep|Oct|Nov|Dec)-[0-3][0-9]:(Jan|Feb|Mar|Apr|May|Jun|Jul|Aug|Sep|Oct|Nov|Dec)-[0-3][0-9])*$</validator>
                 </param>
@@ -65,36 +66,71 @@
                 <param name="colname_value" label="Column name for values" optional="false" help="The name of the column containing the values to be analyzed in the Man-Kendall trend test." type="text"/>
             </when>
             <when value="barplot-trend-results">
-				<param name="input_data" label="Input table" optional="false" help="URL (stored in a .txt file) to the input table containing statistical analysis results. The table must include columns for test values, p-values, and group identifiers." type="data" format="txt"/>
-				<param name="colname_id" label="Column name for identifier" optional="false" help="The name of the column containing group or sample identifiers, e.g., polygon id. Example = 'polygon_id'" type="text"/>
-				<param name="colname_test_value" label="Column name for test value" optional="false" help="The name of the column containing the test values (e.g., statistical coefficients) to be plotted on the Y-axis, e.g., Tau for Mann-Kendall test." type="text"/>
-				<param name="colname_p_value" label="Column name for p value" optional="false" help="The name of the column containing p values, used to determine bar transparency. Example = 'p_value'" type="text"/>
-				<param name="p_value_threshold" label="p value threshold for significance" optional="false" help="The threshold for distinguishing significant from insignificant values. It adjusts the transparency of bars in the plot. Example = 0.05" value="0.05" min="0.01" max="0.1" type="float"/>
-				<param name="colname_group" label="Column name for subgroups" optional="false" help="The name of the column that defines the subgroups or categories to be displayed on the X-axis, e.g., seasons for every polygon_id." type="text"/>
-			</when>
+                <param name="input_data" label="Input table" optional="false" help="URL (stored in a .txt file) to the input table containing statistical analysis results. The table must include columns for test values, p-values, and group identifiers." type="data" format="txt"/>
+                <param name="colname_id" label="Column name for identifier" optional="false" help="The name of the column containing group or sample identifiers, e.g., polygon id. Example = 'polygon_id'" type="text"/>
+                <param name="colname_test_value" label="Column name for test value" optional="false" help="The name of the column containing the test values (e.g., statistical coefficients) to be plotted on the Y-axis, e.g., Tau for Mann-Kendall test." type="text"/>
+                <param name="colname_p_value" label="Column name for p value" optional="false" help="The name of the column containing p values, used to determine bar transparency. Example = 'p_value'" type="text"/>
+                <param name="p_value_threshold" label="p value threshold for significance" optional="false" help="The threshold for distinguishing significant from insignificant values. It adjusts the transparency of bars in the plot. Example = 0.05" value="0.05" min="0.01" max="0.1" type="float"/>
+                <param name="colname_group" label="Column name for subgroups" optional="false" help="The name of the column that defines the subgroups or categories to be displayed on the X-axis, e.g., seasons for every polygon_id." type="text"/>
+            </when>
             <when value="map-trends-static">
-				<param name="regions" label="Study region or study subregions" optional="false" help="URL (stored in a .txt file) to the study region, or several regions, used to classify the input data into groups of interest. Currently it has to be provided as a shapefile. It can be in any coordinate system and will be transformed to WGS84 during this process." type="data" format="txt"/>
-				<param name="input_data" label="Input table" optional="false" help="URL to the input table containing statistical analysis results. The table must include columns for test values, p-values, and identifiers linking to study region." type="data" format="txt"/>
-				<param name="colname_id_trend" label="Column name of study region identifier" optional="false" help="The name of the column containing identifiers for study regions, which must correspond to the identifiers in the shapefile (shp). Example = 'id'." type="text"/>
-				<param name="colname_region_id" label="Column name of study region identifier" optional="false" help="The name of the column in the input data that contains identifiers for study regions, corresponding to the identifiers in the shapefile. Example = 'id'." type="text"/>
-				<param name="colname_group" label="Column name for subgroups" optional="false" help="The name of the column that defines the subgroups or categories to be displayed on the X-axis, e.g., seasons for every polygon_id." type="text"/>
-				<param name="p_value_threshold" label="p value threshold for significance" optional="false" help="The threshold for distinguishing significant from insignificant values. It adjusts the transparency of bars in the plot. Example = 0.05." value="0.05" min="0.01" max="0.1" type="float"/>
-				<param name="colname_p_value" label="Column name for p value" optional="false" help="The name of the column containing p values, used to determine bar transparency. Example = 'p_value'" type="text"/>
-			</when>
+                <param name="regions" label="Study region or study subregions" optional="false" help="URL (stored in a .txt file) to the study region, or several regions, used to classify the input data into groups of interest. Currently it has to be provided as a shapefile. It can be in any coordinate system and will be transformed to WGS84 during this process." type="data" format="txt"/>
+                <param name="input_data" label="Input table" optional="false" help="URL to the input table containing statistical analysis results. The table must include columns for test values, p-values, and identifiers linking to study region." type="data" format="txt"/>
+                <param name="colname_id_trend" label="Column name of study region identifier" optional="false" help="The name of the column containing identifiers for study regions, which must correspond to the identifiers in the shapefile (shp). Example = 'id'." type="text"/>
+                <param name="colname_region_id" label="Column name of study region identifier" optional="false" help="The name of the column in the input data that contains identifiers for study regions, corresponding to the identifiers in the shapefile. Example = 'id'." type="text"/>
+                <param name="colname_group" label="Column name for subgroups" optional="false" help="The name of the column that defines the subgroups or categories to be displayed on the X-axis, e.g., seasons for every polygon_id." type="text"/>
+                <param name="p_value_threshold" label="p value threshold for significance" optional="false" help="The threshold for distinguishing significant from insignificant values. It adjusts the transparency of bars in the plot. Example = 0.05." value="0.05" min="0.01" max="0.1" type="float"/>
+                <param name="colname_p_value" label="Column name for p value" optional="false" help="The name of the column containing p values, used to determine bar transparency. Example = 'p_value'" type="text"/>
+            </when>
             <when value="map-shapefile-points">
-				<param name="regions" label="Study region or study subregions" optional="false" help="URL (stored in a .txt file) to the study region, or several regions, to classify the input data into groups of interest. Currently it has to be provided as a shapefile. It can be in any coordinate system and will be transformed to WGS84 during this process." type="data" format="txt"/>
-				<param name="input_data" label="Data table to be plotted on top of study regions" optional="false" help="URL (stored in a .txt file) to the input table containing the in-situ data points with coordinates." type="data" format="txt"/>
-				<param name="colname_long" label="Column name for longitude" optional="false" help="The name of the column containing longitude values for the data points." type="text"/>
-				<param name="colname_lat" label="Column name for latiitude" optional="false" help="The name of the column containing latitude values for the data points." type="text"/>
-				<param name="colname_value_name" label="Column name of data point identifier" optional="false" help="The name of the column containing identifier (e.g., site name) or values (e.g., depth) to color the points according to their corresponding values." type="text"/>
-				<param name="colname_region_id" label="Column name of region identifier" optional="false" help="The name of the column containing identifiers (e.g., basin name) to distinguish the polygons on the map if multiple regions are present." type="text"/>
-			</when>
+                <param name="regions" label="Study region or study subregions" optional="false" help="URL (stored in a .txt file) to the study region, or several regions, to classify the input data into groups of interest. Currently it has to be provided as a shapefile. It can be in any coordinate system and will be transformed to WGS84 during this process." type="data" format="txt"/>
+                <param name="input_data" label="Data table to be plotted on top of study regions" optional="false" help="URL (stored in a .txt file) to the input table containing the in-situ data points with coordinates." type="data" format="txt"/>
+                <param name="colname_long" label="Column name for longitude" optional="false" help="The name of the column containing longitude values for the data points." type="text"/>
+                <param name="colname_lat" label="Column name for latitude" optional="false" help="The name of the column containing latitude values for the data points." type="text"/>
+                <param name="colname_value_name" label="Column name of data point identifier" optional="false" help="The name of the column containing identifier (e.g., site name) or values (e.g., depth) to color the points according to their corresponding values." type="text"/>
+                <param name="colname_region_id" label="Column name of region identifier" optional="false" help="The name of the column containing identifiers (e.g., basin name) to distinguish the polygons on the map if multiple regions are present." type="text"/>
+            </when>
+            <when value="owt-classification">
+                <param name="input_data_url" label="Input data" optional="false" help="URL (stored in a .txt file) to your input file. Find example data on https://github.com/bishun945/pyOWT/tree/main/projects/AquaINFRA." type="data" format="txt"/>
+                <param name="input_option" label="Type of input" optional="false" help="csv: for text data input (first line wavelength, following lines remote-sensing reflectance). sat: for satellite product input containing reflectance (e.g., Sentinel-3 OLCI Level-2)." type="select">
+                    <option value="csv">csv</option>
+                    <option value="sat">sat</option>
+                </param>
+                <param name="sensor" label="Sensor name" optional="false" help="Spectral band configuration of satellite mission (includes adaptation to sensor spectral response functions)." type="select">
+                    <option value="HYPER">HYPER</option>
+                    <option value="AERONET_OC_1">AERONET_OC_1</option>
+                    <option value="AERONET_OC_2">AERONET_OC_2</option>
+                    <option value="CMEMS_BAL_HROC">CMEMS_BAL_HROC</option>
+                    <option value="CMEMS_BAL_NRT">CMEMS_BAL_NRT</option>
+                    <option value="CMEMS_MED_MYINT">CMEMS_MED_MYINT</option>
+                    <option value="CZCS">CZCS</option>
+                    <option value="GOCI">GOCI</option>
+                    <option value="HawkEye">HawkEye</option>
+                    <option value="MERIS">MERIS</option>
+                    <option value="ODIS_Aqua">ODIS_Aqua</option>
+                    <option value="MODIS_Terra">MODIS_Terra</option>
+                    <option value="MSI_S2A">MSI_S2A</option>
+                    <option value="MSI_S2B">MSI_S2B</option>
+                    <option value="OCTS">OCTS</option>
+                    <option value="OLCI_S3A">OLCI_S3A</option>
+                    <option value="OLCI_S3B">OLCI_S3B</option>
+                    <option value="OLI">OLI</option>
+                    <option value="SeaWiFS">SeaWiFS</option>
+                    <option value="VIIRS_JPSS1">VIIRS_JPSS1</option>
+                    <option value="VIIRS_JPSS2">VIIRS_JPSS2</option> 
+                    <option value="VIIRS_SNPP">VIIRS_SNPP</option>
+                </param>
+                <param name="output_option" label="Output option" help="1: for standard output with five variables. 2: for extensive output including memberships of all water types" optional="false" type="select">
+                    <option value="1">1</option>
+                    <option value="2">2</option>
+                </param>
+            </when>
         </conditional>
     </inputs>
-	<outputs>
-		<data name="output_data" format="txt" label="$select_process"/>
-	</outputs>
+    <outputs>
+        <data name="output_data" format="txt" label="$select_process"/>
+    </outputs>
     <expand macro="tests"/>
-	<expand macro="help" />
-	<expand macro="citations"/>
+    <expand macro="help" />
+    <expand macro="citations"/>
 </tool>
--- a/test-data/points_att_polygon_test_input_3.txt	Mon Oct 14 12:23:01 2024 +0000
+++ b/test-data/points_att_polygon_test_input_3.txt	Wed Oct 23 22:35:20 2024 +0000
@@ -1,1 +1,1 @@
-https://aqua.igb-berlin.de/download/data_merged_with_regions-06550086-857a-11ef-8e41-e14810fdd7f8.csv
\ No newline at end of file
+https://aqua.igb-berlin.de/download/data_merged_with_regions-668a3c72-9039-11ef-aad4-8935a9f30073.csv
\ No newline at end of file