search

colearendt / tidyjson

Tidy your JSON data in R with tidyjson
Other
182 stars 14 forks source link

spread_all() fails #107

Closed davidbomze closed 4 years ago

davidbomze commented 5 years ago 
issues %>% spread_all()

A tbl_json: 1 x 1 tibble with a "JSON" attribute
attr(., "JSON")                   document.id
1 "[{\"url\":\"https:..."           1

Warning message:
In spread_all(.) : no JSON records are objects, returning .x

Seem to be getting this with latest tidyjson (0.2.1.9) and dplyr 0.5.0

colearendt commented 5 years ago

@davidbomze Thanks for the report! Would you mind trying this with the latest development version? The behavior was the same for me, but I believe this is because of the object type (an array). Do we recommend this example in the docs or something somewhere? You might have a look at the following and see if this helps explain.

library(tidyjson)
#> 
#> Attaching package: 'tidyjson'
#> The following object is masked from 'package:stats':
#> 
#>     filter
issues %>% json_types()
#> # A tbl_json: 1 x 2 tibble with a "JSON" attribute
#>   `attr(., "JSON")`       document.id type 
#>   <chr>                         <int> <fct>
#> 1 "[{\"url\":\"https:..."           1 array

issues %>% gather_array() %>% json_types()
#> # A tbl_json: 30 x 3 tibble with a "JSON" attribute
#>    `attr(., "JSON")`       document.id array.index type  
#>    <chr>                         <int>       <int> <fct> 
#>  1 "{\"url\":\"https:/..."           1           1 object
#>  2 "{\"url\":\"https:/..."           1           2 object
#>  3 "{\"url\":\"https:/..."           1           3 object
#>  4 "{\"url\":\"https:/..."           1           4 object
#>  5 "{\"url\":\"https:/..."           1           5 object
#>  6 "{\"url\":\"https:/..."           1           6 object
#>  7 "{\"url\":\"https:/..."           1           7 object
#>  8 "{\"url\":\"https:/..."           1           8 object
#>  9 "{\"url\":\"https:/..."           1           9 object
#> 10 "{\"url\":\"https:/..."           1          10 object
#> # ... with 20 more rows

issues %>% gather_array() %>% spread_all()
#> # A tbl_json: 30 x 86 tibble with a "JSON" attribute
#>    `attr(., "JSON"… document.id array.index url   labels_url comments_url
#>    <chr>                  <int>       <int> <chr> <chr>      <chr>       
#>  1 "{\"url\":\"htt…           1           1 http… https://a… https://api…
#>  2 "{\"url\":\"htt…           1           2 http… https://a… https://api…
#>  3 "{\"url\":\"htt…           1           3 http… https://a… https://api…
#>  4 "{\"url\":\"htt…           1           4 http… https://a… https://api…
#>  5 "{\"url\":\"htt…           1           5 http… https://a… https://api…
#>  6 "{\"url\":\"htt…           1           6 http… https://a… https://api…
#>  7 "{\"url\":\"htt…           1           7 http… https://a… https://api…
#>  8 "{\"url\":\"htt…           1           8 http… https://a… https://api…
#>  9 "{\"url\":\"htt…           1           9 http… https://a… https://api…
#> 10 "{\"url\":\"htt…           1          10 http… https://a… https://api…
#> # ... with 20 more rows, and 81 more variables: events_url <chr>,
#> #   html_url <chr>, id <dbl>, number <dbl>, title <chr>, state <chr>,
#> #   locked <lgl>, assignee <lgl>, milestone <lgl>, comments <dbl>,
#> #   created_at <chr>, updated_at <chr>, closed_at <lgl>, body <chr>,
#> #   user.login <chr>, user.id <dbl>, user.avatar_url <chr>,
#> #   user.gravatar_id <chr>, user.url <chr>, user.html_url <chr>,
#> #   user.followers_url <chr>, user.following_url <chr>,
#> #   user.gists_url <chr>, user.starred_url <chr>,
#> #   user.subscriptions_url <chr>, user.organizations_url <chr>,
#> #   user.repos_url <chr>, user.events_url <chr>,
#> #   user.received_events_url <chr>, user.type <chr>,
#> #   user.site_admin <lgl>, assignee.login <chr>, assignee.id <dbl>,
#> #   assignee.avatar_url <chr>, assignee.gravatar_id <chr>,
#> #   assignee.url <chr>, assignee.html_url <chr>,
#> #   assignee.followers_url <chr>, assignee.following_url <chr>,
#> #   assignee.gists_url <chr>, assignee.starred_url <chr>,
#> #   assignee.subscriptions_url <chr>, assignee.organizations_url <chr>,
#> #   assignee.repos_url <chr>, assignee.events_url <chr>,
#> #   assignee.received_events_url <chr>, assignee.type <chr>,
#> #   assignee.site_admin <lgl>, milestone.url <chr>,
#> #   milestone.labels_url <chr>, milestone.id <dbl>,
#> #   milestone.number <dbl>, milestone.title <chr>,
#> #   milestone.description <chr>, milestone.open_issues <dbl>,
#> #   milestone.closed_issues <dbl>, milestone.state <chr>,
#> #   milestone.created_at <chr>, milestone.updated_at <chr>,
#> #   milestone.due_on <lgl>, pull_request.url <chr>,
#> #   pull_request.html_url <chr>, pull_request.diff_url <chr>,
#> #   pull_request.patch_url <chr>, milestone.creator.login <chr>,
#> #   milestone.creator.id <dbl>, milestone.creator.avatar_url <chr>,
#> #   milestone.creator.gravatar_id <chr>, milestone.creator.url <chr>,
#> #   milestone.creator.html_url <chr>,
#> #   milestone.creator.followers_url <chr>,
#> #   milestone.creator.following_url <chr>,
#> #   milestone.creator.gists_url <chr>,
#> #   milestone.creator.starred_url <chr>,
#> #   milestone.creator.subscriptions_url <chr>,
#> #   milestone.creator.organizations_url <chr>,
#> #   milestone.creator.repos_url <chr>, milestone.creator.events_url <chr>,
#> #   milestone.creator.received_events_url <chr>,
#> #   milestone.creator.type <chr>, milestone.creator.site_admin <lgl>

Created on 2019-03-13 by the reprex package (v0.2.1)