Update printing handling of meta data from tibbles and improve print …

…test structure.

V2 print

DESCRIPTION

@@ -46,7 +46,8 @@ Imports:
     knitr (>= 1.2),
     tibble (>= 2.0.0),
     tidyr (>= 0.7),
-    tidyselect (>= 0.2.5)
+    tidyselect (>= 0.2.5),
+    crayon
 Suggests:
     extrafont,
     rmarkdown,

R/skim_print.R

@@ -19,10 +19,7 @@ NULL
 print.skim_df <- function(x, include_summary = TRUE, n = Inf, width = Inf,
                           n_extra = NULL, ...) {
   if (is_skim_df(x)) {
-    if (include_summary) {
-      print(summary(x))
-    }
-
+    if (include_summary) print(summary(x))
     by_type <- partition(x)
     purrr::imap(by_type, print, n, width, n_extra)
     invisible(NULL)
@@ -35,10 +32,22 @@ print.skim_df <- function(x, include_summary = TRUE, n = Inf, width = Inf,
 #' @export
 print.one_skim_df <- function(x, n = Inf, width = Inf, n_extra = NULL, ...) {
   variable_type <- paste("Variable type:", attr(x, "skim_type"))
-  with_line <- cli::rule(line = 1, left = variable_type)
-  print(with_line)
-  out <- format(x, n = n, width = width, n_extra, ...)
-  cat(out[c(-1, -3)], sep = "\n")
+  top_line <- cli::rule(line = 1, left = variable_type)
+  out <- format(x, n = n, width = width, n_extra = n_extra, ...)
+  metadata <- grab_tibble_metadata(out)
+  render_skim_body(top_line, out, metadata)
+}
+
+grab_tibble_metadata <- function(x) {
+  if (crayon::has_color()) {
+    grep("^\\\033\\[38;5;\\d{3}m[#\\*]", x)
+  } else {
+    grep("^[#\\*]", x)
+  }
+}
+
+render_skim_body <- function(top_line, out, metadata) {
+  cat(top_line, out[-metadata], sep = "\n")
 }
 
 #' @describeIn print Print a `skim_list`, a list of `skim_df` objects.

tests/testthat/dplyr/arrange.txt

@@ -0,0 +1,21 @@
+── Data Summary ────────────────────────
+                        Value
+Name                     iris
+Number of rows            150
+Number of columns           5
+
+Column type frequency:       
+  factor                    1
+  numeric                   4
+
+Group variables          None
+
+── Variable type: factor ───────────────────────────────────────────────────────────────────────────
+  skim_variable missing complete     n ordered n_unique top_counts               
+1 Species             0      150   150 FALSE          3 set: 50, ver: 50, vir: 50
+── Variable type: numeric ──────────────────────────────────────────────────────────────────────────
+  skim_variable missing complete     n  mean    sd    p0   p25   p50   p75  p100 hist 
+1 Sepal.Length        0      150   150  5.84 0.828   4.3   5.1  5.8    6.4   7.9 ▆▇▇▅▂
+2 Petal.Length        0      150   150  3.76 1.77    1     1.6  4.35   5.1   6.9 ▇▁▆▇▂
+3 Sepal.Width         0      150   150  3.06 0.436   2     2.8  3      3.3   4.4 ▁▆▇▂▁
+4 Petal.Width         0      150   150  1.20 0.762   0.1   0.3  1.3    1.8   2.5 ▇▁▇▅▃

tests/testthat/dplyr/filter-no-skim.txt

@@ -0,0 +1,4 @@
+# A tibble: 0 x 16
+# … with 16 variables: skim_type <chr>, skim_variable <chr>, missing <int>, complete <int>,
+#   n <int>, ordered <lgl>, n_unique <int>, top_counts <chr>, mean <dbl>, sd <dbl>, p0 <dbl>,
+#   p25 <dbl>, p50 <dbl>, p75 <dbl>, p100 <dbl>, hist <chr>

tests/testthat/dplyr/filter-skim.txt

@@ -0,0 +1,17 @@
+── Data Summary ────────────────────────
+                        Value
+Name                     iris
+Number of rows            150
+Number of columns           5
+
+Column type frequency:       
+  numeric                   4
+
+Group variables          None
+
+── Variable type: numeric ──────────────────────────────────────────────────────────────────────────
+  skim_variable missing complete     n  mean    sd    p0   p25   p50   p75  p100 hist 
+1 Sepal.Length        0      150   150  5.84 0.828   4.3   5.1  5.8    6.4   7.9 ▆▇▇▅▂
+2 Sepal.Width         0      150   150  3.06 0.436   2     2.8  3      3.3   4.4 ▁▆▇▂▁
+3 Petal.Length        0      150   150  3.76 1.77    1     1.6  4.35   5.1   6.9 ▇▁▆▇▂
+4 Petal.Width         0      150   150  1.20 0.762   0.1   0.3  1.3    1.8   2.5 ▇▁▇▅▃

tests/testthat/dplyr/mutate-no-skim.txt

@@ -0,0 +1,9 @@
+# A tibble: 5 x 15
+  skim_type missing complete     n ordered n_unique top_counts  mean     sd    p0   p25   p50   p75
+* <chr>       <int>    <int> <int> <lgl>      <int> <chr>      <dbl>  <dbl> <dbl> <dbl> <dbl> <dbl>
+1 factor          0      150   150 FALSE          3 set: 50, … NA    NA      NA    NA   NA     NA  
+2 numeric         0      150   150 NA            NA <NA>        5.84  0.828   4.3   5.1  5.8    6.4
+3 numeric         0      150   150 NA            NA <NA>        3.06  0.436   2     2.8  3      3.3
+4 numeric         0      150   150 NA            NA <NA>        3.76  1.77    1     1.6  4.35   5.1
+5 numeric         0      150   150 NA            NA <NA>        1.20  0.762   0.1   0.3  1.3    1.8
+# … with 2 more variables: p100 <dbl>, hist <chr>

tests/testthat/dplyr/mutate-skim.txt

@@ -0,0 +1,21 @@
+── Data Summary ────────────────────────
+                        Value
+Name                     iris
+Number of rows            150
+Number of columns           5
+
+Column type frequency:       
+  factor                    1
+  numeric                   4
+
+Group variables          None
+
+── Variable type: factor ───────────────────────────────────────────────────────────────────────────
+  skim_variable missing complete     n ordered n_unique top_counts               
+1 Species             0      150   150 FALSE          3 set: 50, ver: 50, vir: 50
+── Variable type: numeric ──────────────────────────────────────────────────────────────────────────
+  skim_variable missing complete     n  mean    sd    p0   p25   p50   p75  p100 hist  mean2
+1 Sepal.Length        0      150   150  5.84 0.828   4.3   5.1  5.8    6.4   7.9 ▆▇▇▅▂ 34.1 
+2 Sepal.Width         0      150   150  3.06 0.436   2     2.8  3      3.3   4.4 ▁▆▇▂▁  9.35
+3 Petal.Length        0      150   150  3.76 1.77    1     1.6  4.35   5.1   6.9 ▇▁▆▇▂ 14.1 
+4 Petal.Width         0      150   150  1.20 0.762   0.1   0.3  1.3    1.8   2.5 ▇▁▇▅▃  1.44

tests/testthat/dplyr/select-no-skim.txt

@@ -0,0 +1,8 @@
+# A tibble: 5 x 1
+   mean
+* <dbl>
+1 NA   
+2  5.84
+3  3.06
+4  3.76
+5  1.20

tests/testthat/dplyr/select-skim.txt

@@ -0,0 +1,21 @@
+── Data Summary ────────────────────────
+                        Value
+Name                     iris
+Number of rows            150
+Number of columns           5
+
+Column type frequency:       
+  factor                    1
+  numeric                   4
+
+Group variables          None
+
+── Variable type: factor ───────────────────────────────────────────────────────────────────────────
+  skim_variable
+1 Species      
+── Variable type: numeric ──────────────────────────────────────────────────────────────────────────
+  skim_variable
+1 Sepal.Length 
+2 Sepal.Width  
+3 Petal.Length 
+4 Petal.Width  

tests/testthat/dplyr/slice.txt

@@ -0,0 +1,19 @@
+── Data Summary ────────────────────────
+                        Value
+Name                     iris
+Number of rows            150
+Number of columns           5
+
+Column type frequency:       
+  factor                    1
+  numeric                   2
+
+Group variables          None
+
+── Variable type: factor ───────────────────────────────────────────────────────────────────────────
+  skim_variable missing complete     n ordered n_unique top_counts               
+1 Species             0      150   150 FALSE          3 set: 50, ver: 50, vir: 50
+── Variable type: numeric ──────────────────────────────────────────────────────────────────────────
+  skim_variable missing complete     n  mean    sd    p0   p25   p50   p75  p100 hist 
+1 Sepal.Length        0      150   150  5.84 0.828   4.3   5.1   5.8   6.4   7.9 ▆▇▇▅▂
+2 Sepal.Width         0      150   150  3.06 0.436   2     2.8   3     3.3   4.4 ▁▆▇▂▁

tests/testthat/helper-expectations.R

@@ -24,3 +24,44 @@ expect_NA <- function(object) {
   expect(is.na(act$val), sprintf("%s is not NA", act$lab))
   invisible(act$val)
 }
+
+expect_print_matches_file <- function(object, filename, skip_on_windows = TRUE) {
+  if (skip_on_windows) testthat::skip_on_os("windows")
+  withr::with_options(list(crayon.enabled = FALSE), {
+    testthat::expect_known_output(
+      print(object),
+      filename,
+      update = TRUE,
+      width = 100
+    )
+  })
+}
+
+expect_matches_file <- function(object, file, update = TRUE,
+                                skip_on_windows = TRUE, ...) {
+  if (skip_on_windows) testthat::skip_on_os("windows")
+  act <- testthat::quasi_label(rlang::enquo(object), NULL)
+
+  if (!file.exists(file)) {
+    warning("Creating reference value", call. = FALSE)
+    writeLines(object, file)
+    testthat::succeed()
+  } else {
+    ref_val <- paste0(readLines(file), collapse = "\n")
+    comp <- testthat::compare(as.character(act$val), ref_val, ...)
+    if (update && !comp$equal) {
+      writeLines(act$val, file)
+    }
+
+    expect(
+      comp$equal,
+      sprintf(
+        "%s has changed from known value recorded in %s.\n%s",
+        act$lab, encodeString(file, quote = "'"), comp$message
+      ),
+      info = NULL
+    )
+  }
+
+  invisible(act$value)
+}

tests/testthat/print/default.txt

@@ -0,0 +1,21 @@
+── Data Summary ────────────────────────
+                        Value
+Name                     iris
+Number of rows            150
+Number of columns           5
+
+Column type frequency:       
+  factor                    1
+  numeric                   4
+
+Group variables          None
+
+── Variable type: factor ───────────────────────────────────────────────────────────────────────────
+  skim_variable missing complete     n ordered n_unique top_counts               
+1 Species             0      150   150 FALSE          3 set: 50, ver: 50, vir: 50
+── Variable type: numeric ──────────────────────────────────────────────────────────────────────────
+  skim_variable missing complete     n  mean    sd    p0   p25   p50   p75  p100 hist 
+1 Sepal.Length        0      150   150  5.84 0.828   4.3   5.1  5.8    6.4   7.9 ▆▇▇▅▂
+2 Sepal.Width         0      150   150  3.06 0.436   2     2.8  3      3.3   4.4 ▁▆▇▂▁
+3 Petal.Length        0      150   150  3.76 1.77    1     1.6  4.35   5.1   6.9 ▇▁▆▇▂
+4 Petal.Width         0      150   150  1.20 0.762   0.1   0.3  1.3    1.8   2.5 ▇▁▇▅▃

tests/testthat/print/fallback.txt

@@ -0,0 +1,8 @@
+# A tibble: 5 x 1
+   mean
+* <dbl>
+1 NA   
+2  5.84
+3  3.06
+4  3.76
+5  1.20

tests/testthat/print/focus.txt

@@ -0,0 +1,21 @@
+── Data Summary ────────────────────────
+                        Value
+Name                     iris
+Number of rows            150
+Number of columns           5
+
+Column type frequency:       
+  factor                    1
+  numeric                   4
+
+Group variables          None
+
+── Variable type: factor ───────────────────────────────────────────────────────────────────────────
+  skim_variable missing
+1 Species             0
+── Variable type: numeric ──────────────────────────────────────────────────────────────────────────
+  skim_variable missing
+1 Sepal.Length        0
+2 Sepal.Width         0
+3 Petal.Length        0
+4 Petal.Width         0

tests/testthat/print/groups.txt

@@ -0,0 +1,26 @@
+── Data Summary ────────────────────────
+                                               Value
+Name                    dplyr::group_by(iris, Spe...
+Number of rows                                   150
+Number of columns                                  5
+
+Column type frequency:                              
+  numeric                                          4
+
+Group variables                              Species
+
+── Variable type: numeric ──────────────────────────────────────────────────────────────────────────
+   skim_variable Species    missing complete     n  mean    sd    p0   p25   p50   p75  p100 hist 
+ * <chr>         <fct>        <int>    <int> <int> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <chr>
+ 1 Sepal.Length  setosa           0       50    50 5.01  0.352   4.3  4.8   5     5.2    5.8 ▃▃▇▅▁
+ 2 Sepal.Length  versicolor       0       50    50 5.94  0.516   4.9  5.6   5.9   6.3    7   ▂▇▆▃▃
+ 3 Sepal.Length  virginica        0       50    50 6.59  0.636   4.9  6.22  6.5   6.9    7.9 ▁▃▇▃▂
+ 4 Sepal.Width   setosa           0       50    50 3.43  0.379   2.3  3.2   3.4   3.68   4.4 ▁▃▇▅▂
+ 5 Sepal.Width   versicolor       0       50    50 2.77  0.314   2    2.52  2.8   3      3.4 ▁▅▆▇▂
+ 6 Sepal.Width   virginica        0       50    50 2.97  0.322   2.2  2.8   3     3.18   3.8 ▂▆▇▅▁
+ 7 Petal.Length  setosa           0       50    50 1.46  0.174   1    1.4   1.5   1.58   1.9 ▁▃▇▃▁
+ 8 Petal.Length  versicolor       0       50    50 4.26  0.470   3    4     4.35  4.6    5.1 ▂▂▇▇▆
+ 9 Petal.Length  virginica        0       50    50 5.55  0.552   4.5  5.1   5.55  5.88   6.9 ▃▇▇▃▂
+10 Petal.Width   setosa           0       50    50 0.246 0.105   0.1  0.2   0.2   0.3    0.6 ▇▂▂▁▁
+11 Petal.Width   versicolor       0       50    50 1.33  0.198   1    1.2   1.3   1.5    1.8 ▅▇▃▆▁
+12 Petal.Width   virginica        0       50    50 2.03  0.275   1.4  1.8   2     2.3    2.5 ▂▇▆▅▇

tests/testthat/print/knit_print-skim_list.txt

@@ -0,0 +1,20 @@
+
+
+
+**Variable type: factor**
+
+|skim_variable | missing| complete|   n|ordered | n_unique|top_counts                |
+|:-------------|-------:|--------:|---:|:-------|--------:|:-------------------------|
+|Species       |       0|      150| 150|FALSE   |        3|set: 50, ver: 50, vir: 50 |
+
+
+**Variable type: numeric**
+
+|skim_variable | missing| complete|   n| mean|   sd|  p0| p25|  p50| p75| p100|hist  |
+|:-------------|-------:|--------:|---:|----:|----:|---:|---:|----:|---:|----:|:-----|
+|Sepal.Length  |       0|      150| 150| 5.84| 0.83| 4.3| 5.1| 5.80| 6.4|  7.9|▆▇▇▅▂ |
+|Sepal.Width   |       0|      150| 150| 3.06| 0.44| 2.0| 2.8| 3.00| 3.3|  4.4|▁▆▇▂▁ |
+|Petal.Length  |       0|      150| 150| 3.76| 1.77| 1.0| 1.6| 4.35| 5.1|  6.9|▇▁▆▇▂ |
+|Petal.Width   |       0|      150| 150| 1.20| 0.76| 0.1| 0.3| 1.30| 1.8|  2.5|▇▁▇▅▃ |
+
+

tests/testthat/print/knit_print-summary.txt

@@ -0,0 +1,12 @@
+|                       |     |
+|:----------------------|:----|
+|Name                   |iris |
+|Number of rows         |150  |
+|Number of columns      |5    |
+|                       |     |
+|Column type frequency: |     |
+|factor                 |1    |
+|numeric                |4    |
+|                       |     |
+|Group variables        |None |
+|                       |     |

tests/testthat/print/knit_print-suppressed.txt

@@ -0,0 +1,20 @@
+
+
+
+**Variable type: factor**
+
+|skim_variable | missing| complete|   n|ordered | n_unique|top_counts                |
+|:-------------|-------:|--------:|---:|:-------|--------:|:-------------------------|
+|Species       |       0|      150| 150|FALSE   |        3|set: 50, ver: 50, vir: 50 |
+
+
+**Variable type: numeric**
+
+|skim_variable | missing| complete|   n| mean|   sd|  p0| p25|  p50| p75| p100|hist  |
+|:-------------|-------:|--------:|---:|----:|----:|---:|---:|----:|---:|----:|:-----|
+|Sepal.Length  |       0|      150| 150| 5.84| 0.83| 4.3| 5.1| 5.80| 6.4|  7.9|▆▇▇▅▂ |
+|Sepal.Width   |       0|      150| 150| 3.06| 0.44| 2.0| 2.8| 3.00| 3.3|  4.4|▁▆▇▂▁ |
+|Petal.Length  |       0|      150| 150| 3.76| 1.77| 1.0| 1.6| 4.35| 5.1|  6.9|▇▁▆▇▂ |
+|Petal.Width   |       0|      150| 150| 1.20| 0.76| 0.1| 0.3| 1.30| 1.8|  2.5|▇▁▇▅▃ |
+
+

tests/testthat/print/knit_print-yank.txt

@@ -0,0 +1,10 @@
+
+
+**Variable type: factor**
+
+|skim_variable | missing| complete|   n|ordered | n_unique|top_counts                |
+|:-------------|-------:|--------:|---:|:-------|--------:|:-------------------------|
+|Species       |       0|      150| 150|FALSE   |        3|set: 50, ver: 50, vir: 50 |
+
+
+