Add %N and %O for strfntime (#1334)

* Add `%N` and `%O` for strfntime * Unit-test mods * artifacts from `make dev`
johnkerl · Jul 2, 2023 · 3baebea · 3baebea
1 parent 3e5c3e2
commit 3baebea
Show file tree

Hide file tree

Showing 18 changed files with 96 additions and 51 deletions.
diff --git a/docs/src/data-diving-examples.md b/docs/src/data-diving-examples.md
@@ -160,11 +160,11 @@ CITRUS COUNTY       1332.9                 79974.9                483785.1
 <b>  stats2 -a corr,linreg-ols,r2 -f tiv_2011,tiv_2012</b>
 </pre>
 <pre class="pre-non-highlight-in-pair">
-tiv_2011_tiv_2012_corr  0.9730497632351701
-tiv_2011_tiv_2012_ols_m 0.9835583980337732
-tiv_2011_tiv_2012_ols_b 433854.6428968301
+tiv_2011_tiv_2012_corr  0.9730497632351692
+tiv_2011_tiv_2012_ols_m 0.9835583980337723
+tiv_2011_tiv_2012_ols_b 433854.6428968317
 tiv_2011_tiv_2012_ols_n 36634
-tiv_2011_tiv_2012_r2    0.9468258417320204
+tiv_2011_tiv_2012_r2    0.9468258417320189
 </pre>
 
 <pre class="pre-highlight-in-pair">
@@ -322,7 +322,7 @@ Look at bivariate stats by color and shape. In particular, `u,v` pairwise correl
 </pre>
 <pre class="pre-non-highlight-in-pair">
           u_v_corr              w_x_corr
-0.1334180491027861 -0.011319841199852926
+0.1334180491027861 -0.011319841199866178
 </pre>
 
 <pre class="pre-highlight-in-pair">
@@ -332,22 +332,22 @@ Look at bivariate stats by color and shape. In particular, `u,v` pairwise correl
 </pre>
 <pre class="pre-non-highlight-in-pair">
  color    shape              u_v_corr               w_x_corr
-   red   circle    0.9807984401887242  -0.018565536587084836
-orange   square   0.17685855992752933   -0.07104431573805543
- green   circle   0.05764419437577257   0.011795729888018455
-   red   square    0.0557447712489348 -0.0006801456507506415
-yellow triangle    0.0445727377196281   0.024604310103079844
-yellow   square    0.0437917292729612  -0.044621972016306265
-purple   circle   0.03587354936895115    0.13411339541407613
-  blue   square   0.03241153095761152   -0.05350764811965621
-  blue triangle  0.015356427073158612 -0.0006089997461408209
-orange   circle  0.010518953877704181    -0.1627939732927932
-   red triangle   0.00809782571528054    0.01248662135795501
-purple triangle  0.005155190909099739   -0.04505790925621933
-purple   square  -0.02568027696337717   0.057694296479293694
- green   square -0.025776073450284875 -0.0032651732520739014
-orange triangle -0.030456661186085584   -0.13186999819263814
-yellow   circle  -0.06477331572781515     0.0736944981970553
-  blue   circle   -0.1023476190192966  -0.030528539069839333
- green triangle  -0.10901825107358747   -0.04848782060162855
+   red   circle    0.9807984401887236   -0.01856553658708754
+orange   square   0.17685855992752927   -0.07104431573806054
+ green   circle   0.05764419437577255    0.01179572988801509
+   red   square   0.05574477124893523 -0.0006801456507510942
+yellow triangle   0.04457273771962798   0.024604310103081825
+yellow   square   0.04379172927296089   -0.04462197201631237
+purple   circle   0.03587354936895086     0.1341133954140899
+  blue   square   0.03241153095761164  -0.053507648119643196
+  blue triangle  0.015356427073158766 -0.0006089997461435399
+orange   circle  0.010518953877704048   -0.16279397329279383
+   red triangle   0.00809782571528034   0.012486621357942596
+purple triangle  0.005155190909099334  -0.045057909256220656
+purple   square -0.025680276963377404    0.05769429647930396
+ green   square   -0.0257760734502851  -0.003265173252087127
+orange triangle -0.030456661186085785    -0.1318699981926352
+yellow   circle  -0.06477331572781474    0.07369449819706045
+  blue   circle  -0.10234761901929677  -0.030528539069837757
+ green triangle  -0.10901825107358765   -0.04848782060162929
 </pre>
diff --git a/docs/src/manpage.md b/docs/src/manpage.md
@@ -940,6 +940,7 @@ MILLER(1)                                                            MILLER(1)
        Useful for doing a well-formatted check on input data.
        with the exception that warnings are printed to stderr.
        Current checks are:
+       * Data are parseable
        * If any key is the empty string
        Options:
        -h|--help Show this message.
@@ -3433,5 +3434,5 @@ MILLER(1)                                                            MILLER(1)
 
 
 
-                                  2023-06-25                         MILLER(1)
+                                  2023-07-02                         MILLER(1)
 </pre>
diff --git a/docs/src/manpage.txt b/docs/src/manpage.txt
@@ -919,6 +919,7 @@ MILLER(1)                                                            MILLER(1)
        Useful for doing a well-formatted check on input data.
        with the exception that warnings are printed to stderr.
        Current checks are:
+       * Data are parseable
        * If any key is the empty string
        Options:
        -h|--help Show this message.
@@ -3412,4 +3413,4 @@ MILLER(1)                                                            MILLER(1)
 
 
 
-                                  2023-06-25                         MILLER(1)
+                                  2023-07-02                         MILLER(1)
diff --git a/docs/src/reference-dsl-time.md b/docs/src/reference-dsl-time.md
@@ -246,7 +246,7 @@ Notes:
   * For `strftime`, this is thanks to [https://github.com/lestrrat-go/strftime](https://github.com/lestrrat-go/strftime), with a Miller-specific modification for fractional seconds.
   * For `strftime`, this is thanks to [https://github.com/pbnjay/strptime](https://github.com/pbnjay/strptime), with Miller-specific modifications.
 
-Available format strings for `strftime`, taken directly from [https://github.com/lestrrat-go/strftime](https://github.com/lestrrat-go/strftime):
+Available format strings for `strftime`, taken directly from [https://github.com/lestrrat-go/strftime](https://github.com/lestrrat-go/strftime) except for `%1..%9`, `%N`, and `%O` which are Miller-specific additions:
 
 | Pattern | Description |
 |---------|-------------|
@@ -269,6 +269,8 @@ Available format strings for `strftime`, taken directly from [https://github.com
 | `%M` | the minute as a decimal number (00-59) |
 | `%m` | the month as a decimal number (01-12) |
 | `%n` | a newline |
+| `%N` | zero-padded nanoseconds |
+| `%O` | non-zero-padded nanoseconds |
 | `%p` | national representation of either "ante meridiem" (a.m.) or "post meridiem" (p.m.) as appropriate. |
 | `%R` | equivalent to `%H:%M` |
 | `%r` | equivalent to `%I:%M:%S %p` |
@@ -317,11 +319,15 @@ Examples:
 <b>mlr -n put 'end {</b>
 <b>  print strftime(0, "%Y-%m-%dT%H:%M:%SZ");</b>
 <b>  print strftime(0, "%FT%TZ");</b>
+<b>  print strfntime(123, "%N");</b>
+<b>  print strfntime(123, "%O");</b>
 <b>}'</b>
 </pre>
 <pre class="pre-non-highlight-in-pair">
 1970-01-01T00:00:00Z
 1970-01-01T00:00:00Z
+000000123
+123
 </pre>
 
 <pre class="pre-highlight-in-pair">

diff --git a/docs/src/reference-dsl-time.md.in b/docs/src/reference-dsl-time.md.in
@@ -178,7 +178,7 @@ Notes:
   * For `strftime`, this is thanks to [https://github.com/lestrrat-go/strftime](https://github.com/lestrrat-go/strftime), with a Miller-specific modification for fractional seconds.
   * For `strftime`, this is thanks to [https://github.com/pbnjay/strptime](https://github.com/pbnjay/strptime), with Miller-specific modifications.
 
-Available format strings for `strftime`, taken directly from [https://github.com/lestrrat-go/strftime](https://github.com/lestrrat-go/strftime):
+Available format strings for `strftime`, taken directly from [https://github.com/lestrrat-go/strftime](https://github.com/lestrrat-go/strftime) except for `%1..%9`, `%N`, and `%O` which are Miller-specific additions:
 
 | Pattern | Description |
 |---------|-------------|
@@ -201,6 +201,8 @@ Available format strings for `strftime`, taken directly from [https://github.com
 | `%M` | the minute as a decimal number (00-59) |
 | `%m` | the month as a decimal number (01-12) |
 | `%n` | a newline |
+| `%N` | zero-padded nanoseconds |
+| `%O` | non-zero-padded nanoseconds |
 | `%p` | national representation of either "ante meridiem" (a.m.) or "post meridiem" (p.m.) as appropriate. |
 | `%R` | equivalent to `%H:%M` |
 | `%r` | equivalent to `%I:%M:%S %p` |
@@ -249,6 +251,8 @@ GENMD-RUN-COMMAND
 mlr -n put 'end {
   print strftime(0, "%Y-%m-%dT%H:%M:%SZ");
   print strftime(0, "%FT%TZ");
+  print strfntime(123, "%N");
+  print strfntime(123, "%O");
 }'
 GENMD-EOF
 

diff --git a/docs/src/reference-verbs.md b/docs/src/reference-verbs.md
@@ -380,6 +380,7 @@ Consumes records without printing any output,
 Useful for doing a well-formatted check on input data.
 with the exception that warnings are printed to stderr.
 Current checks are:
+* Data are parseable
 * If any key is the empty string
 Options:
 -h|--help Show this message.
@@ -3306,14 +3307,14 @@ fields, optionally categorized by one or more fields.
 <b>  data/medium</b>
 </pre>
 <pre class="pre-non-highlight-in-pair">
-x_y_cov    0.00004257482082749404
-x_y_corr   0.0005042001844473328
-y_y_cov    0.08461122467974005
+x_y_cov    0.000042574820827444476
+x_y_corr   0.0005042001844467462
+y_y_cov    0.08461122467974003
 y_y_corr   1
-x2_xy_cov  0.041883822817793716
-x2_xy_corr 0.6301743420379936
-x2_y2_cov  -0.0003095372596253918
-x2_y2_corr -0.003424908876111875
+x2_xy_cov  0.04188382281779374
+x2_xy_corr 0.630174342037994
+x2_y2_cov  -0.00030953725962542085
+x2_y2_corr -0.0034249088761121966
 </pre>
 
 <pre class="pre-highlight-in-pair">
@@ -3322,12 +3323,12 @@ x2_y2_corr -0.003424908876111875
 <b>  data/medium</b>
 </pre>
 <pre class="pre-non-highlight-in-pair">
-a   x_y_ols_m             x_y_ols_b          x_y_ols_n x_y_r2                  y_y_ols_m y_y_ols_b                           y_y_ols_n y_y_r2 xy_y2_ols_m        xy_y2_ols_b         xy_y2_ols_n xy_y2_r2
-pan 0.017025512736819345  0.500402892289764  2081      0.00028691820445815624  1         -0.00000000000000002890430283104539 2081      1      0.8781320866715664 0.11908230147563569 2081        0.4174982737731127
-eks 0.04078049236855813   0.4814020796765104 1965      0.0016461239223448218   1         0.00000000000000017862676354313703  1965      1      0.897872861169018  0.1073405443361234  1965        0.4556322386425451
-wye -0.03915349075204785  0.5255096523974457 1966      0.0015051268704373377   1         0.00000000000000004464425401127647  1966      1      0.8538317334220837 0.1267454301662969  1966        0.3899172181859931
-zee 0.0027812364960401333 0.5043070448033061 2047      0.000007751652858787357 1         0.00000000000000004819404567023685  2047      1      0.8524439912011011 0.12401684308018947 2047        0.39356598090006495
-hat -0.018620577041095272 0.5179005397264937 1941      0.00035200366460556604  1         -0.00000000000000003400445761787692 1941      1      0.8412305086345017 0.13557328318623207 1941        0.3687944261732266
+a   x_y_ols_m             x_y_ols_b           x_y_ols_n x_y_r2                  y_y_ols_m y_y_ols_b y_y_ols_n y_y_r2 xy_y2_ols_m        xy_y2_ols_b         xy_y2_ols_n xy_y2_r2
+pan 0.01702551273681908   0.5004028922897639  2081      0.00028691820445814767  1         0         2081      1      0.8781320866715662 0.11908230147563566 2081        0.41749827377311266
+eks 0.0407804923685586    0.48140207967651016 1965      0.0016461239223448587   1         0         1965      1      0.8978728611690183 0.10734054433612333 1965        0.45563223864254526
+wye -0.03915349075204814  0.5255096523974456  1966      0.0015051268704373607   1         0         1966      1      0.8538317334220835 0.1267454301662969  1966        0.38991721818599295
+zee 0.0027812364960399147 0.5043070448033061  2047      0.000007751652858786137 1         0         2047      1      0.8524439912011013 0.12401684308018937 2047        0.39356598090006495
+hat -0.018620577041095078 0.5179005397264935  1941      0.0003520036646055585   1         0         1941      1      0.8412305086345014 0.13557328318623216 1941        0.3687944261732265
 </pre>
 
 Here's an example simple line-fit. The `x` and `y`
@@ -3413,11 +3414,11 @@ upsec_count_pca_quality 0.9999590846136102
 donesec                 92.33051350964094
 
 color                   purple
-upsec_count_pca_m       -39.030097447953594
-upsec_count_pca_b       979.9883413064917
+upsec_count_pca_m       -39.03009744795354
+upsec_count_pca_b       979.9883413064914
 upsec_count_pca_n       21
 upsec_count_pca_quality 0.9999908956206317
-donesec                 25.108529196302943
+donesec                 25.10852919630297
 </pre>
 
 ## step
@@ -3645,9 +3646,9 @@ distinct_count 5      5      10000              10000                  10000
 mode           pan    wye    1                  0.3467901443380824     0.7268028627434533
 sum            0      0      50005000           4986.019681679581      5062.057444929905
 mean           -      -      5000.5             0.49860196816795804    0.5062057444929905
-stddev         -      -      2886.8956799071675 0.29029251511440074    0.2908800864269331
-var            -      -      8334166.666666667  0.08426974433144457    0.08461122467974005
-skewness       -      -      0                  -0.0006899591185517494 -0.01784976012013298
+stddev         -      -      2886.8956799071675 0.2902925151144007     0.290880086426933
+var            -      -      8334166.666666667  0.08426974433144456    0.08461122467974003
+skewness       -      -      0                  -0.0006899591185521965 -0.017849760120133784
 minlen         3      3      1                  15                     13
 maxlen         3      3      5                  22                     22
 min            eks    eks    1                  0.00004509679127584487 0.00008818962627266114

diff --git a/docs/src/two-pass-algorithms.md b/docs/src/two-pass-algorithms.md
@@ -598,8 +598,8 @@ hat pan 0.4643355557376876
 x_count  10000
 x_sum    4986.019681679581
 x_mean   0.49860196816795804
-x_var    0.08426974433144457
-x_stddev 0.29029251511440074
+x_var    0.08426974433144456
+x_stddev 0.2902925151144007
 </pre>
 
 <pre class="pre-highlight-in-pair">

diff --git a/internal/pkg/bifs/datetime.go b/internal/pkg/bifs/datetime.go
@@ -425,6 +425,18 @@ func init() {
 	appender9 := strftime.AppendFunc(func(b []byte, t time.Time) []byte {
 		return specificationHelper(b, t, "%09d", 1)
 	})
+	appenderN := strftime.AppendFunc(func(b []byte, t time.Time) []byte {
+		nanos := int(t.Nanosecond())
+		s := fmt.Sprintf("%09d", nanos)
+		//return append(b, []byte(s))
+		return append(b, s...)
+	})
+	appenderO := strftime.AppendFunc(func(b []byte, t time.Time) []byte {
+		nanos := int(t.Nanosecond())
+		s := fmt.Sprintf("%d", nanos)
+		//return append(b, []byte(s))
+		return append(b, s...)
+	})
 
 	ss := strftime.NewSpecificationSet()
 	ss.Set('1', appender1)
@@ -436,6 +448,8 @@ func init() {
 	ss.Set('7', appender7)
 	ss.Set('8', appender8)
 	ss.Set('9', appender9)
+	ss.Set('N', appenderN)
+	ss.Set('O', appenderO)
 
 	strftimeExtensions = strftime.WithSpecificationSet(ss)
 }

diff --git a/man/manpage.txt b/man/manpage.txt
@@ -919,6 +919,7 @@ MILLER(1)                                                            MILLER(1)
        Useful for doing a well-formatted check on input data.
        with the exception that warnings are printed to stderr.
        Current checks are:
+       * Data are parseable
        * If any key is the empty string
        Options:
        -h|--help Show this message.
@@ -3412,4 +3413,4 @@ MILLER(1)                                                            MILLER(1)
 
 
 
-                                  2023-06-25                         MILLER(1)
+                                  2023-07-02                         MILLER(1)
diff --git a/man/mlr.1 b/man/mlr.1
@@ -2,12 +2,12 @@
 .\"     Title: mlr
 .\"    Author: [see the "AUTHOR" section]
 .\" Generator: ./mkman.rb
-.\"      Date: 2023-06-25
+.\"      Date: 2023-07-02
 .\"    Manual: \ \&
 .\"    Source: \ \&
 .\"  Language: English
 .\"
-.TH "MILLER" "1" "2023-06-25" "\ \&" "\ \&"
+.TH "MILLER" "1" "2023-07-02" "\ \&" "\ \&"
 .\" -----------------------------------------------------------------
 .\" * Portability definitions
 .\" ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
@@ -1126,6 +1126,7 @@ Consumes records without printing any output,
 Useful for doing a well-formatted check on input data.
 with the exception that warnings are printed to stderr.
 Current checks are:
+* Data are parseable
 * If any key is the empty string
 Options:
 -h|--help Show this message.

diff --git a/test/cases/dsl-local-date-time-functions/strfntime-istanbul/expout b/test/cases/dsl-local-date-time-functions/strfntime-istanbul/expout
@@ -10,3 +10,5 @@ TZ is Asia/Istanbul
 1970-01-01 00:00:00 +0000
 1970-01-01 00:00:00 UTC
 1970-01-01 00:00:00 +0000
+00 000123456
+00 123456
diff --git a/test/cases/dsl-local-date-time-functions/strfntime-sao_paulo/expout b/test/cases/dsl-local-date-time-functions/strfntime-sao_paulo/expout
@@ -10,3 +10,5 @@ TZ is America/Sao_Paulo
 1970-01-01 00:00:00 +0000
 1970-01-01 00:00:00 UTC
 1970-01-01 00:00:00 +0000
+00 000123456
+00 123456
diff --git a/test/cases/dsl-local-date-time-functions/strfntime-utc/expout b/test/cases/dsl-local-date-time-functions/strfntime-utc/expout
@@ -10,3 +10,5 @@ TZ is UTC
 1970-01-01 00:00:00 +0000
 1970-01-01 00:00:00 UTC
 1970-01-01 00:00:00 +0000
+00 000123456
+00 123456
diff --git a/test/cases/dsl-local-date-time-functions/strftime-istanbul/expout b/test/cases/dsl-local-date-time-functions/strftime-istanbul/expout
@@ -10,3 +10,5 @@ TZ is Asia/Istanbul
 1970-01-01 00:00:00 +0000
 1970-01-01 00:00:00 UTC
 1970-01-01 00:00:00 +0000
+00 123456000
+00 123456000
diff --git a/test/cases/dsl-local-date-time-functions/strftime-sao_paulo/expout b/test/cases/dsl-local-date-time-functions/strftime-sao_paulo/expout
@@ -10,3 +10,5 @@ TZ is America/Sao_Paulo
 1970-01-01 00:00:00 +0000
 1970-01-01 00:00:00 UTC
 1970-01-01 00:00:00 +0000
+00 123456000
+00 123456000
diff --git a/test/cases/dsl-local-date-time-functions/strftime-utc/expout b/test/cases/dsl-local-date-time-functions/strftime-utc/expout
@@ -10,3 +10,5 @@ TZ is UTC
 1970-01-01 00:00:00 +0000
 1970-01-01 00:00:00 UTC
 1970-01-01 00:00:00 +0000
+00 123456000
+00 123456000
diff --git a/test/input/strfntime-tz.mlr b/test/input/strfntime-tz.mlr
@@ -13,5 +13,7 @@ end {
   print strfntime(123456, "%Y-%m-%d %H:%M:%S %z");
   print strfntime(0,      "%Y-%m-%d %H:%M:%S %Z");
   print strfntime(0,      "%Y-%m-%d %H:%M:%S %z");
+  print strfntime(123456, "%S %N");
+  print strfntime(123456, "%S %O");
 
 }
diff --git a/test/input/strftime-tz.mlr b/test/input/strftime-tz.mlr
@@ -13,5 +13,7 @@ end {
   print strftime(0.123456, "%Y-%m-%d %H:%M:%S %z");
   print strftime(0.0,      "%Y-%m-%d %H:%M:%S %Z");
   print strftime(0.0,      "%Y-%m-%d %H:%M:%S %z");
+  print strftime(0.123456, "%S %N");
+  print strftime(0.123456, "%S %O");
 
 }