ontodev · jamesaoverton · Mar 6, 2020 · Mar 4, 2020 · Mar 4, 2020 · Mar 4, 2020
diff --git a/CHANGELOG.md b/CHANGELOG.md
@@ -7,6 +7,11 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ## [Unreleased]
 
+### Added
+- Add [`export`] command [#481]
+- Add JSON format to [`export`] in [#645]
+- Add Excel format to [`export`] in [#646]
+
 ### Fixed
 - Fix filtering axioms with multiple axiom selectors [#644]
 
@@ -158,6 +163,7 @@ First official release of ROBOT!
 [`convert`]: http://robot.obolibrary.org/convert
 [`diff`]: http://robot.obolibrary.org/diff
 [`explain`]: http://robot.obolibrary.org/explain
+[`export`]: http://robot.obolibrary.org/export
 [`extract`]: http://robot.obolibrary.org/extract
 [`filter`]: http://robot.obolibrary.org/filter
 [`merge`]: http://robot.obolibrary.org/merge
@@ -171,6 +177,8 @@ First official release of ROBOT!
 [`report`]: http://robot.obolibrary.org/report
 [`template`]: http://robot.obolibrary.org/template
 
+[#646]: https://github.com/ontodev/robot/issues/646
+[#645]: https://github.com/ontodev/robot/issues/645
 [#644]: https://github.com/ontodev/robot/issues/644
 [#630]: https://github.com/ontodev/robot/issues/630
 [#625]: https://github.com/ontodev/robot/issues/625
@@ -199,6 +207,7 @@ First official release of ROBOT!
 [#507]: https://github.com/ontodev/robot/issues/507
 [#488]: https://github.com/ontodev/robot/issues/488
 [#484]: https://github.com/ontodev/robot/issues/484
+[#481]: https://github.com/ontodev/robot/issues/481
 [#475]: https://github.com/ontodev/robot/issues/475
 [#471]: https://github.com/ontodev/robot/issues/471
 [#461]: https://github.com/ontodev/robot/issues/461

diff --git a/docs/examples/nucleus.json b/docs/examples/nucleus.json
@@ -0,0 +1,169 @@
+[
+  {
+    "ID": "GO:0005575",
+    "LABEL": [
+      "cellular_component"
+    ]
+  },
+  {
+    "ID": "GO:0005622",
+    "LABEL": [
+      "intracellular"
+    ],
+    "SubClass Of": [
+      "cell part"
+    ]
+  },
+  {
+    "ID": "GO:0005623",
+    "LABEL": [
+      "cell"
+    ],
+    "SubClass Of": [
+      "cellular_component"
+    ]
+  },
+  {
+    "ID": "GO:0005634",
+    "LABEL": [
+      "nucleus"
+    ],
+    "SubClass Of": [
+      "intracellular membrane-bounded organelle"
+    ]
+  },
+  {
+    "ID": "GO:0031974",
+    "LABEL": [
+      "membrane-enclosed lumen"
+    ],
+    "SubClass Of": [
+      "cellular_component"
+    ]
+  },
+  {
+    "ID": "GO:0031981",
+    "LABEL": [
+      "nuclear lumen"
+    ],
+    "SubClass Of": [
+      "'part of' some nucleus",
+      "intracellular organelle lumen",
+      "nuclear part"
+    ]
+  },
+  {
+    "ID": "GO:0043226",
+    "LABEL": [
+      "organelle"
+    ],
+    "SubClass Of": [
+      "cellular_component"
+    ]
+  },
+  {
+    "ID": "GO:0043227",
+    "LABEL": [
+      "membrane-bounded organelle"
+    ],
+    "SubClass Of": [
+      "organelle"
+    ]
+  },
+  {
+    "ID": "GO:0043229",
+    "LABEL": [
+      "intracellular organelle"
+    ],
+    "SubClass Of": [
+      "'part of' some intracellular",
+      "intracellular part",
+      "organelle"
+    ]
+  },
+  {
+    "ID": "GO:0043231",
+    "LABEL": [
+      "intracellular membrane-bounded organelle"
+    ],
+    "SubClass Of": [
+      "intracellular organelle",
+      "membrane-bounded organelle"
+    ]
+  },
+  {
+    "ID": "GO:0043233",
+    "LABEL": [
+      "organelle lumen"
+    ],
+    "SubClass Of": [
+      "'part of' some organelle",
+      "membrane-enclosed lumen",
+      "organelle part"
+    ]
+  },
+  {
+    "ID": "GO:0044422",
+    "LABEL": [
+      "organelle part"
+    ],
+    "SubClass Of": [
+      "'part of' some organelle",
+      "cellular_component"
+    ]
+  },
+  {
+    "ID": "GO:0044424",
+    "LABEL": [
+      "intracellular part"
+    ],
+    "SubClass Of": [
+      "'part of' some intracellular",
+      "cell part"
+    ]
+  },
+  {
+    "ID": "GO:0044428",
+    "LABEL": [
+      "nuclear part"
+    ],
+    "SubClass Of": [
+      "'part of' some nucleus",
+      "intracellular organelle part"
+    ]
+  },
+  {
+    "ID": "GO:0044446",
+    "LABEL": [
+      "intracellular organelle part"
+    ],
+    "SubClass Of": [
+      "'part of' some 'intracellular organelle'",
+      "'part of' some intracellular",
+      "'part of' some organelle",
+      "intracellular part",
+      "organelle part"
+    ]
+  },
+  {
+    "ID": "GO:0044464",
+    "LABEL": [
+      "cell part"
+    ],
+    "SubClass Of": [
+      "'part of' some cell",
+      "cellular_component"
+    ]
+  },
+  {
+    "ID": "GO:0070013",
+    "LABEL": [
+      "intracellular organelle lumen"
+    ],
+    "SubClass Of": [
+      "'part of' some 'intracellular organelle'",
+      "intracellular organelle part",
+      "organelle lumen"
+    ]
+  }
+]
diff --git a/docs/export.md b/docs/export.md
@@ -20,19 +20,23 @@ robot export --input nucleus_part_of.owl \
 
 The following formats are currently supported:
 
-* `tsv`
-* `csv`
-* `html`
+* `tsv` - tab-separated file, default format for unknown extensions
+* `csv` - comma-separated file
+* `html` - HTML table with with [Bootstrap](https://getbootstrap.com/) styling
+* `json` - JSON file with values as arrays (except for ID/CURIE and IRI, which are single strings)
+* `xlsx` - Excel workbook with contents on first sheet
 
 These can be specified with the `--format` option:
 
     robot export --input nucleus_part_of.owl \
       --header "LABEL|SubClass Of" \
       --format html --export results/nucleus.html
 
-If this option is not included, `export` will predict the format based on the file extension. If the extension does not match with an existing format, it will default to `tsv`.
-
-The `html` format will output an HTML table with [Bootstrap](https://getbootstrap.com/) styling. All entities referenced will be rendered as clickable li
9E7A
nks.
+If this option is not included, `export` will predict the format based on the file extension:
+
+    robot export --input nucleus_part_of.owl \
+      --header "ID|LABEL|SubClass Of" \
+      --export results/nucleus.json
 
 ### Columns
 
@@ -160,7 +164,7 @@ A property cannot be resolved, usually meaning that the label cannot be resolved
 
 ### Unknown Format Error
 
-The following formats are currently supported: `tsv`, `csv`, and `html`. Please make sure you are using one of these formats.
+The following formats are currently supported: `tsv`, `csv`, `html`, `json`, and `xlsx`. Please make sure you are using one of these formats.
 
 ### Unknown Tag Error
 

diff --git a/robot-command/src/main/java/org/obolibrary/robot/ExportCommand.java b/robot-command/src/main/java/org/obolibrary/robot/ExportCommand.java
@@ -1,18 +1,28 @@
 package org.obolibrary.robot;
 
-import java.io.File;
 import java.util.Arrays;
 import java.util.List;
 import java.util.Map;
 import org.apache.commons.cli.CommandLine;
 import org.apache.commons.cli.Options;
+import org.apache.commons.io.FilenameUtils;
+import org.obolibrary.robot.export.Table;
 import org.semanticweb.owlapi.model.OWLOntology;
 
 public class ExportCommand implements Command {
 
   /** Store the command-line options for the command. */
   private Options options;
 
+  /** Namespace for error messages. */
+  private static final String NS = "export#";
+
+  private static final String unknownFormatError =
+      NS + "UNKNOWN FORMAT ERROR --format %s must be one of: csv, html, json, tsv, or xlsx";
+
+  /** Supported output formats. If the output format is not one of these, it will default to TSV. */
+  private final List<String> supportedFormats = Arrays.asList("csv", "html", "json", "tsv", "xlsx");
+
   /** Initialize the command. */
   public ExportCommand() {
     Options o = CommandLineHelper.getCommonOptions();
@@ -24,7 +34,7 @@ public ExportCommand() {
     o.addOption("A", "exclude-anonymous", true, "if true, exclude anonymous entities");
     o.addOption("s", "sort", true, "column to sort on (default: first column)");
     o.addOption("n", "include", true, "groups of terms to include");
-    o.addOption("f", "format", true, "output file format (TSV, CSV, or HTML)");
+    o.addOption("f", "format", true, "output file format");
     o.addOption("S", "split", true, "character to split multiple values on (default: |)");
     o.addOption(
         "E",
@@ -131,16 +141,23 @@ public CommandState execute(CommandState state, String[] args) throws Exception
     String format = CommandLineHelper.getOptionalValue(line, "format");
     if (format == null) {
       // Use the path to determine the format (default is TSV)
-      if (exportPath.endsWith(".csv")) {
-        exportOptions.put("format", "csv");
-      } else if (exportPath.endsWith(".html")) {
-        exportOptions.put("format", "html");
+      String ext = FilenameUtils.getExtension(exportPath).toLowerCase();
+      if (supportedFormats.contains(ext)) {
+        exportOptions.put("format", ext);
+      } else {
+        // Unknown extension, use tab-separated
+        exportOptions.put("format", "tsv");
       }
+    } else if (!supportedFormats.contains(format)) {
+      // If a format WAS provided and it's not in the supported formats, throw an error
+      throw new Exception(String.format(unknownFormatError, format));
     }
+
     // Get the split columns
     List<String> columns = Arrays.asList(headerString.split("\\|"));
 
-    ExportOperation.export(ontology, ioHelper, columns, new File(exportPath), exportOptions);
+    Table t = ExportOperation.createExportTable(ontology, ioHelper, columns, exportOptions);
+    ExportOperation.saveTable(t, exportPath, exportOptions);
     return state;
   }
 }
diff --git a/robot-core/pom.xml b/robot-core/pom.xml
@@ -79,6 +79,16 @@
       <artifactId>jena-tdb</artifactId>
       <version>3.8.0</version>
     </dependency>
+    <dependency>
+      <groupId>org.apache.poi</groupId>
+      <artifactId>poi</artifactId>
+      <version>3.15</version>
+    </dependency>
+    <dependency>
+      <groupId>org.apache.poi</groupId>
+      <artifactId>poi-ooxml</artifactId>
+      <version>3.15</version>
+    </dependency>
     <dependency>
       <groupId>com.github.jsonld-java</groupId>
       <artifactId>jsonld-java</artifactId>
@@ -153,5 +163,10 @@
       <artifactId>owl-diff_2.12</artifactId>
       <version>1.1.2</version>
     </dependency>
+    <dependency>
+      <groupId>com.google.code.gson</groupId>
+      <artifactId>gson</artifactId>
+      <version>2.8.0</version>
+    </dependency>
   </dependencies>
 </project>