mirror of
https://github.com/johnkerl/miller.git
synced 2026-01-23 02:14:13 +00:00
mlr sort -b feature (#1833)
* `mlr sort -b` feature * mlr regtest -p test/cases/cli-help && make dev
This commit is contained in:
John Kerl
GitHub
parent
865c9cc563
commit
e7fe363d9a
10 changed files with 33 additions and 10 deletions
|
|
@ -26,7 +26,7 @@ Vertical-tabular format is good for a quick look at CSV data layout -- seeing wh
|
|||
<b>wc -l data/flins.csv</b>
|
||||
</pre>
|
||||
<pre class="pre-non-highlight-in-pair">
|
||||
36635 data/flins.csv
|
||||
36635 data/flins.csv
|
||||
</pre>
|
||||
|
||||
<pre class="pre-highlight-in-pair">
|
||||
|
|
@ -227,7 +227,7 @@ Peek at the data:
|
|||
<b>wc -l data/colored-shapes.dkvp</b>
|
||||
</pre>
|
||||
<pre class="pre-non-highlight-in-pair">
|
||||
10078 data/colored-shapes.dkvp
|
||||
10078 data/colored-shapes.dkvp
|
||||
</pre>
|
||||
|
||||
<pre class="pre-highlight-in-pair">
|
||||
|
|
|
|||
|
|
@ -68,7 +68,7 @@ date,qoh
|
|||
<b>wc -l data/miss-date.csv</b>
|
||||
</pre>
|
||||
<pre class="pre-non-highlight-in-pair">
|
||||
1372 data/miss-date.csv
|
||||
1372 data/miss-date.csv
|
||||
</pre>
|
||||
|
||||
Since there are 1372 lines in the data file, some automation is called for. To find the missing dates, you can convert the dates to seconds since the epoch using `strptime`, then compute adjacent differences (the `cat -n` simply inserts record-counters):
|
||||
|
|
|
|||
|
|
@ -1837,6 +1837,7 @@ This is simply a copy of what you should see on running `man mlr` at a command p
|
|||
-nf {comma-separated field names} Same as -n
|
||||
-nr {comma-separated field names} Numerical descending; nulls sort first
|
||||
-t {comma-separated field names} Natural ascending
|
||||
-b Move sort fields to start of record, as in reorder -b
|
||||
-tr|-rt {comma-separated field names} Natural descending
|
||||
-h|--help Show this message.
|
||||
|
||||
|
|
@ -3745,5 +3746,5 @@ This is simply a copy of what you should see on running `man mlr` at a command p
|
|||
MIME Type for Comma-Separated Values (CSV) Files, the Miller docsite
|
||||
https://miller.readthedocs.io
|
||||
|
||||
2025-07-04 4mMILLER24m(1)
|
||||
2025-07-11 4mMILLER24m(1)
|
||||
</pre>
|
||||
|
|
|
|||
|
|
@ -1816,6 +1816,7 @@
|
|||
-nf {comma-separated field names} Same as -n
|
||||
-nr {comma-separated field names} Numerical descending; nulls sort first
|
||||
-t {comma-separated field names} Natural ascending
|
||||
-b Move sort fields to start of record, as in reorder -b
|
||||
-tr|-rt {comma-separated field names} Natural descending
|
||||
-h|--help Show this message.
|
||||
|
||||
|
|
@ -3724,4 +3725,4 @@
|
|||
MIME Type for Comma-Separated Values (CSV) Files, the Miller docsite
|
||||
https://miller.readthedocs.io
|
||||
|
||||
2025-07-04 4mMILLER24m(1)
|
||||
2025-07-11 4mMILLER24m(1)
|
||||
|
|
|
|||
|
|
@ -230,6 +230,7 @@ Options:
|
|||
-nf {comma-separated field names} Same as -n
|
||||
-nr {comma-separated field names} Numerical descending; nulls sort first
|
||||
-t {comma-separated field names} Natural ascending
|
||||
-b Move sort fields to start of record, as in reorder -b
|
||||
-tr|-rt {comma-separated field names} Natural descending
|
||||
-h|--help Show this message.
|
||||
|
||||
|
|
|
|||
|
|
@ -2960,6 +2960,7 @@ Options:
|
|||
-nf {comma-separated field names} Same as -n
|
||||
-nr {comma-separated field names} Numerical descending; nulls sort first
|
||||
-t {comma-separated field names} Natural ascending
|
||||
-b Move sort fields to start of record, as in reorder -b
|
||||
-tr|-rt {comma-separated field names} Natural descending
|
||||
-h|--help Show this message.
|
||||
|
||||
|
|
@ -4133,7 +4134,7 @@ There are two main ways to use `mlr uniq`: the first way is with `-g` to specify
|
|||
<b>wc -l data/colored-shapes.csv</b>
|
||||
</pre>
|
||||
<pre class="pre-non-highlight-in-pair">
|
||||
10079 data/colored-shapes.csv
|
||||
10079 data/colored-shapes.csv
|
||||
</pre>
|
||||
|
||||
<pre class="pre-highlight-in-pair">
|
||||
|
|
@ -4290,7 +4291,7 @@ color=purple,shape=square,flag=0
|
|||
<b>wc -l data/repeats.dkvp</b>
|
||||
</pre>
|
||||
<pre class="pre-non-highlight-in-pair">
|
||||
57 data/repeats.dkvp
|
||||
57 data/repeats.dkvp
|
||||
</pre>
|
||||
|
||||
<pre class="pre-highlight-in-pair">
|
||||
|
|
|
|||
|
|
@ -1816,6 +1816,7 @@
|
|||
-nf {comma-separated field names} Same as -n
|
||||
-nr {comma-separated field names} Numerical descending; nulls sort first
|
||||
-t {comma-separated field names} Natural ascending
|
||||
-b Move sort fields to start of record, as in reorder -b
|
||||
-tr|-rt {comma-separated field names} Natural descending
|
||||
-h|--help Show this message.
|
||||
|
||||
|
|
@ -3724,4 +3725,4 @@
|
|||
MIME Type for Comma-Separated Values (CSV) Files, the Miller docsite
|
||||
https://miller.readthedocs.io
|
||||
|
||||
2025-07-04 4mMILLER24m(1)
|
||||
2025-07-11 4mMILLER24m(1)
|
||||
|
|
|
|||
|
|
@ -2,12 +2,12 @@
|
|||
.\" Title: mlr
|
||||
.\" Author: [see the "AUTHOR" section]
|
||||
.\" Generator: ./mkman.rb
|
||||
.\" Date: 2025-07-04
|
||||
.\" Date: 2025-07-11
|
||||
.\" Manual: \ \&
|
||||
.\" Source: \ \&
|
||||
.\" Language: English
|
||||
.\"
|
||||
.TH "MILLER" "1" "2025-07-04" "\ \&" "\ \&"
|
||||
.TH "MILLER" "1" "2025-07-11" "\ \&" "\ \&"
|
||||
.\" -----------------------------------------------------------------
|
||||
.\" * Portability definitions
|
||||
.\" ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
|
||||
|
|
@ -2289,6 +2289,7 @@ Options:
|
|||
-nf {comma-separated field names} Same as -n
|
||||
-nr {comma-separated field names} Numerical descending; nulls sort first
|
||||
-t {comma-separated field names} Natural ascending
|
||||
-b Move sort fields to start of record, as in reorder -b
|
||||
-tr|-rt {comma-separated field names} Natural descending
|
||||
-h|--help Show this message.
|
||||
|
||||
|
|
|
|||
|
|
@ -83,6 +83,7 @@ func transformerSortUsage(
|
|||
fmt.Fprintf(o, "-nf {comma-separated field names} Same as -n\n")
|
||||
fmt.Fprintf(o, "-nr {comma-separated field names} Numerical descending; nulls sort first\n")
|
||||
fmt.Fprintf(o, "-t {comma-separated field names} Natural ascending\n")
|
||||
fmt.Fprintf(o, "-b Move sort fields to start of record, as in reorder -b\n")
|
||||
fmt.Fprintf(o, "-tr|-rt {comma-separated field names} Natural descending\n")
|
||||
fmt.Fprintf(o, "-h|--help Show this message.\n")
|
||||
fmt.Fprintf(o, "\n")
|
||||
|
|
@ -107,6 +108,7 @@ func transformerSortParseCLI(
|
|||
|
||||
groupByFieldNames := make([]string, 0)
|
||||
comparatorFuncs := make([]mlrval.CmpFuncInt, 0)
|
||||
doMoveToHead := false
|
||||
|
||||
for argi < argc /* variable increment: 1 or 2 depending on flag */ {
|
||||
opt := args[argi]
|
||||
|
|
@ -255,6 +257,9 @@ func transformerSortParseCLI(
|
|||
comparatorFuncs = append(comparatorFuncs, mlrval.NumericDescendingComparator)
|
||||
}
|
||||
|
||||
} else if opt == "-b" {
|
||||
doMoveToHead = true
|
||||
|
||||
} else {
|
||||
transformerSortUsage(os.Stderr)
|
||||
os.Exit(1)
|
||||
|
|
@ -274,6 +279,7 @@ func transformerSortParseCLI(
|
|||
transformer, err := NewTransformerSort(
|
||||
groupByFieldNames,
|
||||
comparatorFuncs,
|
||||
doMoveToHead,
|
||||
)
|
||||
if err != nil {
|
||||
fmt.Fprintln(os.Stderr, err)
|
||||
|
|
@ -304,6 +310,7 @@ type TransformerSort struct {
|
|||
// -- Input
|
||||
groupByFieldNames []string
|
||||
comparatorFuncs []mlrval.CmpFuncInt
|
||||
doMoveToHead bool
|
||||
|
||||
// -- State
|
||||
// Map from string to *list.List:
|
||||
|
|
@ -316,11 +323,13 @@ type TransformerSort struct {
|
|||
func NewTransformerSort(
|
||||
groupByFieldNames []string,
|
||||
comparatorFuncs []mlrval.CmpFuncInt,
|
||||
doMoveToHead bool,
|
||||
) (*TransformerSort, error) {
|
||||
|
||||
tr := &TransformerSort{
|
||||
groupByFieldNames: groupByFieldNames,
|
||||
comparatorFuncs: comparatorFuncs,
|
||||
doMoveToHead: doMoveToHead,
|
||||
|
||||
recordListsByGroup: lib.NewOrderedMap(),
|
||||
groupHeads: lib.NewOrderedMap(),
|
||||
|
|
@ -346,6 +355,13 @@ func (tr *TransformerSort) Transform(
|
|||
if !inrecAndContext.EndOfStream {
|
||||
inrec := inrecAndContext.Record
|
||||
|
||||
if tr.doMoveToHead {
|
||||
n := len(tr.groupByFieldNames)
|
||||
for i := n - 1; i >= 0; i-- {
|
||||
inrec.MoveToHead(tr.groupByFieldNames[i])
|
||||
}
|
||||
}
|
||||
|
||||
groupingKey, selectedValues, ok := inrec.GetSelectedValuesAndJoined(
|
||||
tr.groupByFieldNames,
|
||||
)
|
||||
|
|
|
|||
|
|
@ -982,6 +982,7 @@ Options:
|
|||
-nf {comma-separated field names} Same as -n
|
||||
-nr {comma-separated field names} Numerical descending; nulls sort first
|
||||
-t {comma-separated field names} Natural ascending
|
||||
-b Move sort fields to start of record, as in reorder -b
|
||||
-tr|-rt {comma-separated field names} Natural descending
|
||||
-h|--help Show this message.
|
||||
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue