prep for v1.3.3, Added option, '-for-dataset' to csv2jsonl. This renders JSON lines output suitable for loading into a dataset collectiojn.

Author: R. S. Doiel

CITATION.cff

@@ -15,7 +15,7 @@ maintainers:
     orcid: ""
 
 repository-code: "https://github.com/caltechlibrary/datatools"
-version: 1.3.2
+version: 1.3.3
 license-url: "https://data.caltech.edu/license"
 keywords: [ "csv", "excel", "sql", "json", "yaml", "xlsx", "golang", "bash" ]
-date-released: 2025-05-13
+date-released: 2025-05-14

about.html

@@ -25,7 +25,7 @@
 
 <section>
 <h1 id="about-this-software">About this software</h1>
-<h2 id="datatools-1.3.2">datatools 1.3.2</h2>
+<h2 id="datatools-1.3.3">datatools 1.3.3</h2>
 <h3 id="authors">Authors</h3>
 <ul>
 <li>R. S. Doiel</li>

about.md

@@ -11,16 +11,16 @@ authors:
     orcid: ""
 
 repository-code: "https://github.com/caltechlibrary/datatools"
-version: 1.3.2
+version: 1.3.3
 license-url: "https://data.caltech.edu/license"
 keywords: [ "csv", "excel", "sql", "json", "yaml", "xlsx", "golang", "bash" ]
-date-released: 2025-05-13
+date-released: 2025-05-14
 ---
 
 About this software
 ===================
 
-## datatools 1.3.2
+## datatools 1.3.3
 
 ### Authors
 

cmd/csv2jsonl/csv2jsonl.go

@@ -95,6 +95,9 @@ is one object per line. See https://jsonlines.org.
 -use-lazy-quotes
 : use lazy quotes for for CSV input
 
+-for-dataset COLUMN_NO
+: if COLUMN_NO is greater than -1 then, generate a dataset load compatible version of the CSV file
+using COLUMN_NO as key.
 
 # EXAMPLES
 
@@ -130,6 +133,7 @@ Convert data1.csv to JSON line (one object line per blob)
 	trimLeadingSpace bool
 	fieldsPerRecord  int
 	reuseRecord      bool
+	forDataset       int
 )
 
 func main() {
@@ -159,6 +163,7 @@ func main() {
 	flag.BoolVar(&trimLeadingSpace, "trim-leading-space", false, "trim leading space in fields for CSV input")
 	flag.BoolVar(&reuseRecord, "reuse-record", false, "reuse the backing array")
 	flag.IntVar(&fieldsPerRecord, "fields-per-record", 0, "Set the number of fields expected in the CSV read, -1 to turn off")
+	flag.IntVar(&forDataset, "for-dataset", -1, "generate a dataset compatible JSON lines output using column number as key")
 
 	// Parse environment and options
 	flag.Parse()
@@ -244,12 +249,16 @@ func main() {
 
 		// Pad the fieldnames if necessary
 		object = map[string]interface{}{}
+		key := ""
 		for col, val := range row {
 			if col < len(fieldNames) {
 				object[fieldNames[col]] = val
 			} else {
 				object[fmt.Sprintf("col_%d", col)] = val
 			}
+			if (col == forDataset) {
+				key = fmt.Sprintf("%s", val);
+			}
 		}
 		var src []byte
 		src, err = datatools.JSONMarshal(object)
@@ -259,7 +268,17 @@ func main() {
 			}
 			hasError = true
 		}
-		fmt.Fprintf(out, "%s%s", src, eol)
+		if (forDataset >= 0) {
+			if (key == "") {
+				if !quiet {
+					fmt.Fprintf(eout, "error row, mising key value for column %d, row %d\n", forDataset, rowNo)
+				}
+			}
+			fmt.Fprintf(out, `{%q:%q,%q:%s}%s`, "key", key, "object", src, eol)
+		} else {
+			fmt.Fprintf(out, "%s%s", src, eol)
+		}
+		rowNo++
 	}
 	if hasError == true {
 		os.Exit(1)

codemeta.json

@@ -29,8 +29,8 @@
     }
   ],
   "dateCreated": "2017-02-06",
-  "dateModified": "2025-05-13",
-  "datePublished": "2025-05-13",
+  "dateModified": "2025-05-14",
+  "datePublished": "2025-05-14",
   "description": "A set of command line tools for working with CSV, Excel Workbooks, JSON and structured text documents.",
   "funder": {
     "@id": "https://ror.org/5dxps055",
@@ -61,9 +61,9 @@
     "Golang >= 1.23.5",
     "Pandoc >= 3.1"
   ],
-  "version": "1.3.2",
+  "version": "1.3.3",
   "developmentStatus": "active",
   "issueTracker": "https://github.com/caltechlibrary/datatools/issues",
   "downloadUrl": "https://github.com/caltechlibrary/datatools/releases/",
-  "releaseNotes": "Added cli, csv2jsonl, that will convert a CSV document into a JSON lines list of objects."
+  "releaseNotes": "Added option, `-for-dataset` to csv2jsonl. This renders JSON lines output suitable for loading into a dataset collectiojn."
 }

codemeta2cff.1.md

@@ -1,6 +1,6 @@
-%codemeta2cff(1) user manual | version 1.3.2 1ee0728
+%codemeta2cff(1) user manual | version 1.3.3 24eb061
 % R. S. Doiel
-% 2025-05-13
+% 2025-05-14
 
 # NAME
 

csv2json.1.md

@@ -1,6 +1,6 @@
-%csv2json(1) user manual | version 1.3.2 1ee0728
+%csv2json(1) user manual | version 1.3.3 24eb061
 % R. S. Doiel
-% 2025-05-13
+% 2025-05-14
 
 # NAME
 

csv2jsonl.1.html

@@ -89,6 +89,11 @@ <h1 id="options">OPTIONS</h1>
 <dd>
 use lazy quotes for for CSV input
 </dd>
+<dt>-for-dataset COLUMN_NO</dt>
+<dd>
+if COLUMN_NO is greater than -1 then, generate a dataset load compatible
+version of the CSV file using COLUMN_NO as key.
+</dd>
 </dl>
 <h1 id="examples">EXAMPLES</h1>
 <p>Convert data1.csv to data1.jsonl using Unix pipes.</p>

csv2jsonl.1.md

@@ -1,6 +1,6 @@
-%csv2jsonl(1) user manual | version 1.3.2 1ee0728
+%csv2jsonl(1) user manual | version 1.3.3 24eb061
 % R. S. Doiel
-% 2025-05-13
+% 2025-05-14
 
 # NAME
 
@@ -59,6 +59,9 @@ is one object per line. See https://jsonlines.org.
 -use-lazy-quotes
 : use lazy quotes for for CSV input
 
+-for-dataset COLUMN_NO
+: if COLUMN_NO is greater than -1 then, generate a dataset load compatible version of the CSV file
+using COLUMN_NO as key.
 
 # EXAMPLES
 

csv2mdtable.1.html

@@ -79,7 +79,7 @@ <h1 id="examples">EXAMPLES</h1>
 <pre><code>    cat data1.csv | csv2mdtable &gt; data1.md</code></pre>
 <p>Convert data1.csv to data1.md using options.</p>
 <pre><code>    csv2mdtable -i data1.csv -o data1.md</code></pre>
-<p>csv2mdtable 1.3.2</p>
+<p>csv2mdtable 1.3.3</p>
 </section>
 
 <footer>