parse_csv_points
Created: 2013-12-24 11:41:36
Last updated: 2014-11-18 18:08:26
Parses csv content with species occurrence points in the DarwinCore archive format, determining column indexes and returning the records as a list of points in openModeller format (XML). No distinction is made between presences or absences.
Preview
Run
Run this Workflow in the Taverna Workbench...
Workflow Components
Authors (1)
| Alan R Williams & Renato De Giovanni |
Titles (1)
| Parse csv content with species occurrence points. |
Descriptions (1)
| Parses the csv content, determining column indexes and returning the records as a list of points in openModeller format (XML). All points are considered presence points. |
Dependencies (0)
Inputs (1)
| Name |
Description |
| points_csv |
Comma-separated list of values. Each line in the file corresponds to a different record. The first line must be a header containing column names also separated by comma. The following columns are mandatory AND must be spelled EXACTLY as follows: occurrenceID, nameComplete, decimalLongitude and decimalLatitude. Other columns can be present. Columns can be in any order, but they must match the order of the corresponding values in the following lines.
|
Processors (4)
| Name |
Type |
Description |
| Merge_String_List_to_a_String |
localworker |
ScriptString seperatorString = "\n";
if (seperator != void) {
seperatorString = seperator;
}
StringBuffer sb = new StringBuffer();
for (Iterator i = stringlist.iterator(); i.hasNext();) {
String item = (String) i.next();
sb.append(item);
if (i.hasNext()) {
sb.append(seperatorString);
}
}
concatenated = sb.toString();
|
| parse_header |
beanshell |
Scriptimport java.io.StringReader;
import au.com.bytecode.opencsv.CSVReader;
CSVReader reader = new CSVReader(new StringReader(csv_content),',','"');
int name_idx = -1;
int id_idx = -1;
int long_idx = -1;
int lat_idx = -1;
String[] header = reader.readNext();
if ( header != null) {
List terms = Arrays.asList(header);
name_idx = terms.indexOf("nameComplete");
id_idx = terms.indexOf("occurrenceID");
long_idx = terms.indexOf("decimalLongitude");
lat_idx = terms.indexOf("decimalLatitude");
}
else {
throw new RuntimeException("The input file provided for species occurrence points is empty.");
}
if ( name_idx == -1 ) {
throw new RuntimeException("The column nameComplete is missing from the header of the input points file.");
}
if ( long_idx == -1 ) {
throw new RuntimeException("The column decimalLongitude is missing from the header of the input points file.");
}
if ( lat_idx == -1 ) {
throw new RuntimeException("The column decimalLatitude is missing from the header of the input points file.");
}
|
| get_first_taxon |
beanshell |
Scriptimport java.io.StringReader;
import au.com.bytecode.opencsv.CSVReader;
CSVReader reader = new CSVReader(new StringReader(csv_content),',','"');
String taxon_name = "";
int name_idx_int = Integer.parseInt(name_idx);
String[] first_line = reader.readNext();
String[] second_line = reader.readNext();
if (second_line != null) {
if (name_idx_int >= 0) {
if (second_line.length > name_idx_int) {
taxon_name = second_line[name_idx_int];
}
}
}
else {
throw new RuntimeException("The input file provided for species occurrence points has no other lines after the header.");
}
|
| extract_taxon_points |
beanshell |
Scriptimport java.io.StringReader;
import au.com.bytecode.opencsv.CSVReader;
CSVReader reader = new CSVReader(new StringReader(csv_content),',','"');
int name_idx_int = Integer.parseInt(name_idx);
int id_idx_int = Integer.parseInt(id_idx);
int long_idx_int = Integer.parseInt(long_idx);
int lat_idx_int = Integer.parseInt(lat_idx);
int max_idx = Math.max(name_idx_int, Math.max(id_idx_int, Math.max(long_idx_int, lat_idx_int)));
ArrayList all_points = new ArrayList();
String id;
int i = 0;
String [] line;
while ((line = reader.readNext()) != null) {
i++;
if (i == 1) {
continue;
}
if (line.length > max_idx) {
if (id_idx_int == -1) {
id = String.valueOf(i);
}
else {
id = line[id_idx_int];
}
if (taxon_name == void || line[name_idx_int].equals(taxon_name)) {
all_points.add("");
}
}
}
num_points = all_points.size(); |
Beanshells (3)
| Name |
Description |
Inputs |
Outputs |
| parse_header |
|
csv_content
|
name_idx
id_idx
long_idx
lat_idx
|
| get_first_taxon |
|
csv_content
name_idx
|
taxon_name
|
| extract_taxon_points |
|
csv_content
name_idx
taxon_name
id_idx
long_idx
lat_idx
|
all_points
num_points
|
Outputs (6)
| Name |
Description |
| id_idx |
Index of the occurrenceID field in the header (starting with 0).
|
| long_idx |
Index of the decimalLongitude field in the header (starting with 0).
|
| lat_idx |
Index of the decimalLatitude field in the header (starting with 0).
|
| first_taxon_name |
First taxon name found in the csv content.
|
| points_xml |
List of all points (separated by new line) already in XML format for openModeller.
|
| num_points |
Number of points.
|
Datalinks (15)
| Source |
Sink |
| extract_taxon_points:all_points |
Merge_String_List_to_a_String:stringlist |
| points_csv |
parse_header:csv_content |
| points_csv |
get_first_taxon:csv_content |
| parse_header:name_idx |
get_first_taxon:name_idx |
| points_csv |
extract_taxon_points:csv_content |
| parse_header:id_idx |
extract_taxon_points:id_idx |
| parse_header:lat_idx |
extract_taxon_points:lat_idx |
| parse_header:long_idx |
extract_taxon_points:long_idx |
| parse_header:name_idx |
extract_taxon_points:name_idx |
| parse_header:id_idx |
id_idx |
| parse_header:long_idx |
long_idx |
| parse_header:lat_idx |
lat_idx |
| get_first_taxon:taxon_name |
first_taxon_name |
| Merge_String_List_to_a_String:concatenated |
points_xml |
| extract_taxon_points:num_points |
num_points |
Uploader
Component Validity
Loading
License
All versions of this Workflow are
licensed under:
Version 4 (latest)
(of 4)
Credits (0)
(People/Groups)
None
Attributions (0)
(Workflows/Files)
None
Shared with Groups (1)
Featured In Packs (1)
Log in to add to one of your Packs
Attributed By (0)
(Workflows/Files)
None
Favourited By (0)
No one
Statistics
Other workflows that use similar services
(0)
There are no workflows in myExperiment that use similar services to this Workflow.
Download Workflow
]
Reviews
(0)
No comments yet
Log in to make a comment