Unify the case verb, and add options (#1306)

* temp * Unified `case` verb * unit-test cases * doc-page update * make-dev artifacts
johnkerl · Jun 4, 2023 · 59e6327 · 59e6327
1 parent 394681c
commit 59e6327
Show file tree

Hide file tree

Showing 102 changed files with 450 additions and 400 deletions.
diff --git a/docs/src/data/cases.csv b/docs/src/data/cases.csv
@@ -0,0 +1,2 @@
+apple,ball,cat,dog,the quick brown fox
+sun,tree,urchin,violet,jumped over the lazy dog
diff --git a/docs/src/manpage.md b/docs/src/manpage.md
@@ -192,15 +192,14 @@ MILLER(1) MILLER(1)
  for all things with "map" in their names.
 
 1mVERB LIST0m
- altkv bar bootstrap cat check clean-whitespace count-distinct count
- count-similar cut decimate downcase fill-down fill-empty filter flatten
- format-values fraction gap grep group-by group-like having-fields head
- histogram json-parse json-stringify join label latin1-to-utf8 least-frequent
- merge-fields most-frequent nest nothing put regularize remove-empty-columns
- rename reorder repeat reshape sample sec2gmtdate sec2gmt seqgen shuffle
- skip-trivial-records sort sort-within-records split stats1 stats2 step summary
- tac tail tee template top utf8-to-latin1 unflatten uniq unspace unsparsify
- upcase
+ altkv bar bootstrap case cat check clean-whitespace count-distinct count
+ count-similar cut decimate fill-down fill-empty filter flatten format-values
+ fraction gap grep group-by group-like having-fields head histogram json-parse
+ json-stringify join label latin1-to-utf8 least-frequent merge-fields
+ most-frequent nest nothing put regularize remove-empty-columns rename reorder
+ repeat reshape sample sec2gmtdate sec2gmt seqgen shuffle skip-trivial-records
+ sort sort-within-records split stats1 stats2 step summary tac tail tee
+ template top utf8-to-latin1 unflatten uniq unspace unsparsify
 
 1mFUNCTION LIST0m
  abs acos acosh any append apply arrayify asin asinh asserting_absent
@@ -909,6 +908,19 @@ MILLER(1) MILLER(1)
  Must be non-negative.
  -h|--help Show this message.
 
+ 1mcase0m
+ Usage: mlr case [options]
+ Uppercases strings in record keys and/or values.
+ Options:
+ -k Case only keys, not keys and values.
+ -v Case only values, not keys and values.
+ -f {a,b,c} Specify which field names to case (default: all)
+ -u Convert to uppercase
+ -l Convert to lowercase
+ -s Convert to sentence case (capitalize first letter)
+ -t Convert to title case (capitalize words)
+ -h|--help Show this message.
+
  1mcat0m
  Usage: mlr cat [options]
  Passes input records directly to output. Most useful for format conversion.
@@ -1006,14 +1018,6 @@ MILLER(1) MILLER(1)
  -n {n} Decimation factor (default 10).
  -h|--help Show this message.
 
- 1mdowncase0m
- Usage: mlr downcase [options]
- Lowercases strings in record keys and/or values.
- Options:
- -k Downcase only keys, not keys and values.
- -v Downcase only values, not keys and values.
- -h|--help Show this message.
-
  1mfill-down0m
  Usage: mlr fill-down [options]
  If a given record has a missing value for a given field, fill that from
@@ -2127,14 +2131,6 @@ MILLER(1) MILLER(1)
  being 'b=3,c=4', then the output is the two records 'a=1,b=2,c=' and
  'a=,b=3,c=4'.
 
- 1mupcase0m
- Usage: mlr upcase [options]
- Uppercases strings in record keys and/or values.
- Options:
- -k Upcase only keys, not keys and values.
- -v Upcase only values, not keys and values.
- -h|--help Show this message.
-
 1mFUNCTIONS FOR FILTER/PUT0m
  1mabs0m
  (class=math #args=1) Absolute value.
@@ -3358,5 +3354,5 @@ MILLER(1) MILLER(1)
 
 
 
- 2023-06-03 MILLER(1)
+ 2023-06-04 MILLER(1)
 </pre>
diff --git a/docs/src/manpage.txt b/docs/src/manpage.txt
@@ -171,15 +171,14 @@ MILLER(1) MILLER(1)
  for all things with "map" in their names.
 
 1mVERB LIST0m
- altkv bar bootstrap cat check clean-whitespace count-distinct count
- count-similar cut decimate downcase fill-down fill-empty filter flatten
- format-values fraction gap grep group-by group-like having-fields head
- histogram json-parse json-stringify join label latin1-to-utf8 least-frequent
- merge-fields most-frequent nest nothing put regularize remove-empty-columns
- rename reorder repeat reshape sample sec2gmtdate sec2gmt seqgen shuffle
- skip-trivial-records sort sort-within-records split stats1 stats2 step summary
- tac tail tee template top utf8-to-latin1 unflatten uniq unspace unsparsify
- upcase
+ altkv bar bootstrap case cat check clean-whitespace count-distinct count
+ count-similar cut decimate fill-down fill-empty filter flatten format-values
+ fraction gap grep group-by group-like having-fields head histogram json-parse
+ json-stringify join label latin1-to-utf8 least-frequent merge-fields
+ most-frequent nest nothing put regularize remove-empty-columns rename reorder
+ repeat reshape sample sec2gmtdate sec2gmt seqgen shuffle skip-trivial-records
+ sort sort-within-records split stats1 stats2 step summary tac tail tee
+ template top utf8-to-latin1 unflatten uniq unspace unsparsify
 
 1mFUNCTION LIST0m
  abs acos acosh any append apply arrayify asin asinh asserting_absent
@@ -888,6 +887,19 @@ MILLER(1) MILLER(1)
  Must be non-negative.
  -h|--help Show this message.
 
+ 1mcase0m
+ Usage: mlr case [options]
+ Uppercases strings in record keys and/or values.
+ Options:
+ -k Case only keys, not keys and values.
+ -v Case only values, not keys and values.
+ -f {a,b,c} Specify which field names to case (default: all)
+ -u Convert to uppercase
+ -l Convert to lowercase
+ -s Convert to sentence case (capitalize first letter)
+ -t Convert to title case (capitalize words)
+ -h|--help Show this message.
+
  1mcat0m
  Usage: mlr cat [options]
  Passes input records directly to output. Most useful for format conversion.
@@ -985,14 +997,6 @@ MILLER(1) MILLER(1)
  -n {n} Decimation factor (default 10).
  -h|--help Show this message.
 
- 1mdowncase0m
- Usage: mlr downcase [options]
- Lowercases strings in record keys and/or values.
- Options:
- -k Downcase only keys, not keys and values.
- -v Downcase only values, not keys and values.
- -h|--help Show this message.
-
  1mfill-down0m
  Usage: mlr fill-down [options]
  If a given record has a missing value for a given field, fill that from
@@ -2106,14 +2110,6 @@ MILLER(1) MILLER(1)
  being 'b=3,c=4', then the output is the two records 'a=1,b=2,c=' and
  'a=,b=3,c=4'.
 
- 1mupcase0m
- Usage: mlr upcase [options]
- Uppercases strings in record keys and/or values.
- Options:
- -k Upcase only keys, not keys and values.
- -v Upcase only values, not keys and values.
- -h|--help Show this message.
-
 1mFUNCTIONS FOR FILTER/PUT0m
  1mabs0m
  (class=math #args=1) Absolute value.
@@ -3337,4 +3333,4 @@ MILLER(1) MILLER(1)
 
 
 
- 2023-06-03 MILLER(1)
+ 2023-06-04 MILLER(1)
diff --git a/docs/src/reference-verbs.md b/docs/src/reference-verbs.md
@@ -233,6 +233,45 @@ orange 0.4802164827586204 290
 green 0.5129018241860459 1075
 </pre>
 
+## case
+
+<pre class="pre-highlight-in-pair">
+<b>mlr case --help</b>
+</pre>
+<pre class="pre-non-highlight-in-pair">
+Usage: mlr case [options]
+Uppercases strings in record keys and/or values.
+Options:
+-k Case only keys, not keys and values.
+-v Case only values, not keys and values.
+-f {a,b,c} Specify which field names to case (default: all)
+-u Convert to uppercase
+-l Convert to lowercase
+-s Convert to sentence case (capitalize first letter)
+-t Convert to title case (capitalize words)
+-h|--help Show this message.
+</pre>
+
+<pre class="pre-highlight-non-pair">
+<b>mlr --from test/input/cases.csv --icsv --ojson case -u</b>
+</pre>
+
+<pre class="pre-highlight-non-pair">
+<b>mlr --from test/input/cases.csv --icsv --ojson case -u -k</b>
+</pre>
+
+<pre class="pre-highlight-non-pair">
+<b>mlr --from test/input/cases.csv --icsv --ojson case -u -v</b>
+</pre>
+
+<pre class="pre-highlight-non-pair">
+<b>mlr --from test/input/cases.csv --icsv --ojson case -k -t then case -v -s</b>
+</pre>
+
+<pre class="pre-highlight-non-pair">
+<b>mlr --from test/input/cases.csv --icsv --ojson case -u -f apple,ball then case -l -f cat,dog</b>
+</pre>
+
 ## cat
 
 Most useful for format conversions (see [File Formats](file-formats.md)) and concatenating multiple same-schema CSV files to have the same header:
@@ -824,20 +863,6 @@ Options:
 -h|--help Show this message.
 </pre>
 
-## downcase
-
-<pre class="pre-highlight-in-pair">
-<b>mlr downcase --help</b>
-</pre>
-<pre class="pre-non-highlight-in-pair">
-Usage: mlr downcase [options]
-Lowercases strings in record keys and/or values.
-Options:
--k Downcase only keys, not keys and values.
--v Downcase only values, not keys and values.
--h|--help Show this message.
-</pre>
-
 ## fill-down
 
 <pre class="pre-highlight-in-pair">
@@ -4288,17 +4313,3 @@ a b v u w x
 1 - 2 - - 3
 - - 1 - 2 -
 </pre>
-
-## upcase
-
-<pre class="pre-highlight-in-pair">
-<b>mlr upcase --help</b>
-</pre>
-<pre class="pre-non-highlight-in-pair">
-Usage: mlr upcase [options]
-Uppercases strings in record keys and/or values.
-Options:
--k Upcase only keys, not keys and values.
--v Upcase only values, not keys and values.
--h|--help Show this message.
-</pre>
diff --git a/docs/src/reference-verbs.md.in b/docs/src/reference-verbs.md.in
@@ -127,6 +127,32 @@ orange 0.4802164827586204 290
 green 0.5129018241860459 1075
 GENMD-EOF
 
+## case
+
+GENMD-RUN-COMMAND
+mlr case --help
+GENMD-EOF
+
+GENMD-CARDIFY-HIGHLIGHT-ONE
+mlr --from test/input/cases.csv --icsv --ojson case -u
+GENMD-EOF
+
+GENMD-CARDIFY-HIGHLIGHT-ONE
+mlr --from test/input/cases.csv --icsv --ojson case -u -k
+GENMD-EOF
+
+GENMD-CARDIFY-HIGHLIGHT-ONE
+mlr --from test/input/cases.csv --icsv --ojson case -u -v
+GENMD-EOF
+
+GENMD-CARDIFY-HIGHLIGHT-ONE
+mlr --from test/input/cases.csv --icsv --ojson case -k -t then case -v -s
+GENMD-EOF
+
+GENMD-CARDIFY-HIGHLIGHT-ONE
+mlr --from test/input/cases.csv --icsv --ojson case -u -f apple,ball then case -l -f cat,dog
+GENMD-EOF
+
 ## cat
 
 Most useful for format conversions (see [File Formats](file-formats.md)) and concatenating multiple same-schema CSV files to have the same header:
@@ -297,12 +323,6 @@ GENMD-RUN-COMMAND
 mlr decimate --help
 GENMD-EOF
 
-## downcase
-
-GENMD-RUN-COMMAND
-mlr downcase --help
-GENMD-EOF
-
 ## fill-down
 
 GENMD-RUN-COMMAND
@@ -1294,9 +1314,3 @@ GENMD-EOF
 GENMD-RUN-COMMAND
 mlr --ijson --opprint unsparsify -f a,b,u,v,w,x then regularize data/sparse.json
 GENMD-EOF
-
-## upcase
-
-GENMD-RUN-COMMAND
-mlr upcase --help
-GENMD-EOF
diff --git a/go.mod b/go.mod
@@ -35,5 +35,6 @@ require (
  github.com/google/pprof v0.0.0-20211214055906-6f57359322fd // indirect
  github.com/pkg/errors v0.9.1 // indirect
  github.com/pmezard/go-difflib v1.0.0 // indirect
+ golang.org/x/text v0.9.0 // indirect
  gopkg.in/yaml.v3 v3.0.1 // indirect
 )
diff --git a/go.sum b/go.sum
@@ -42,6 +42,8 @@ golang.org/x/sys v0.8.0 h1:EBmGv8NaZBZTWvrbjNoL6HVt+IVy3QDQpJs7VRIw3tU=
 golang.org/x/sys v0.8.0/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
 golang.org/x/term v0.8.0 h1:n5xxQn2i3PC0yLAbjTpNT85q/Kgzcr2gIoX9OrJUols=
 golang.org/x/term v0.8.0/go.mod h1:xPskH00ivmX89bAKVGSKKtLOWNx2+17Eiy94tnKShWo=
+golang.org/x/text v0.9.0 h1:2sjJmO8cDvYveuX97RDLsxlyUxLl+GHoLxBiRdHllBE=
+golang.org/x/text v0.9.0/go.mod h1:e1OnstbJyHTd6l/uOt8jFFHp6TRDWZR/bV3emEE/zU8=
 gopkg.in/check.v1 v0.0.0-20161208181325-20d25e280405 h1:yhCVgyC4o1eVCa2tZl7eS0r+SDo693bJlVdllGtEeKM=
 gopkg.in/check.v1 v0.0.0-20161208181325-20d25e280405/go.mod h1:Co6ibVJAznAaIkqp8huTwlJQCZ016jof/cbN4VW5Yz0=
 gopkg.in/yaml.v3 v3.0.0-20200313102051-9f266ea9e77c/go.mod h1:K4uyk7z7BCEPqu6E+C64Yfv1cQ7kz7rIZviUmN+EgEM=

diff --git a/internal/pkg/transformers/aaa_transformer_table.go b/internal/pkg/transformers/aaa_transformer_table.go
@@ -14,6 +14,7 @@ var TRANSFORMER_LOOKUP_TABLE = []TransformerSetup{
  AltkvSetup,
  BarSetup,
  BootstrapSetup,
+ CaseSetup,
  CatSetup,
  CheckSetup,
  CleanWhitespaceSetup,
@@ -22,7 +23,6 @@ var TRANSFORMER_LOOKUP_TABLE = []TransformerSetup{
  CountSimilarSetup,
  CutSetup,
  DecimateSetup,
- DowncaseSetup,
  FillDownSetup,
  FillEmptySetup,
  FilterSetup,
@@ -76,7 +76,6 @@ var TRANSFORMER_LOOKUP_TABLE = []TransformerSetup{
  UniqSetup,
  UnspaceSetup,
  UnsparsifySetup,
- UpcaseSetup,
 }
 
 func ShowHelpForTransformer(verb string) bool {