Merge pull request #81 from ropensci/dev

fixed bug #80 and added test
ropensci-archive · Oct 15, 2022 · db7eff4 · db7eff4
2 parents 9b536e6 + f6617bb
commit db7eff4
Show file tree

Hide file tree

Showing 40 changed files with 3,091 additions and 1,992 deletions.
diff --git a/DESCRIPTION b/DESCRIPTION
@@ -1,6 +1,6 @@
 Package: tidytags
 Title: Importing and Analyzing 'Twitter' Data Collected with 'Twitter Archiving Google Sheets'
-Version: 1.0.2
+Version: 1.0.3
 License: MIT + file LICENSE
 Authors@R: c(
     person("K. Bret", "Staudt Willet", , 

diff --git a/NEWS.md b/NEWS.md
@@ -13,28 +13,33 @@ tidytags development version
 
   *  
 
- ### DOCUMENTATION FIXES
+### DOCUMENTATION FIXES
 
   * 
 
 
+tidytags 1.0.3 (2022-10-14)
+=========================
+
+### BUG FIXES
+
+  * Fixed a bug in `get_upstream_tweets()` where column names were out of order and caused an error
+
 tidytags 1.0.2 (2022-08-19)
 =========================
 
- ### DOCUMENTATION FIXES
+### DOCUMENTATION FIXES
 
   * Fixed broken URLs and reduced tarball size in preparation for CRAN resubmission.
   * In function documentation, \dontrun{} instances have been updated to \donttest{}.
 
-
 tidytags 1.0.1 (2022-08-18)
 =========================
 
- ### DOCUMENTATION FIXES
+### DOCUMENTATION FIXES
 
   * Cleaned up documentation in preparation for CRAN submission.
-
-
+
 tidytags 1.0.0 (2022-08-05)
 =========================
 
@@ -52,19 +57,17 @@ tidytags 1.0.0 (2022-08-05)
   * Updated the read_tags() function so that a Google API key is no longer needed to pull tweet data from publicly shared Google Sheets.
   * The process_tweets() function now also adds user information associated with the creator of each status. process_tweets() also now returns a column for the tweet type of each status.
 
-
 tidytags 0.3.0 (2022-02-04)
 =========================
 
- ### BUG FIXES
+### BUG FIXES
 
   * Updated to most recent versions of CI tests for R-CMD-check and test coverage.
 
- ### DOCUMENTATION FIXES
+### DOCUMENTATION FIXES
 
    * Updated paper.md and paper.bib to coincide with submission for peer review at Journal of Open Source Software (JOSS).
 
-
 tidytags 0.2.1 (2021-12-14)
 =========================
 
@@ -73,21 +76,20 @@ tidytags 0.2.1 (2021-12-14)
   * Added a new function filter_by_tweet_type() to filter a Twitter dataset to only include statuses of a particular type (e.g., replies, retweets, quote tweets, mentions).
   * Updated the function create_edgelist() to take a "type" argument (e.g., "reply", "retweet", "quote", "mention", "all"). This replaces the need for specialized functions like create_mentions_edgelist().
 
-
 tidytags 0.2.0 (2021-11-19)
 =========================
 
 ### NEW FEATURES
 
   * Added a new function lookup_many_users() to automatically iterate through the Twitter API limit of pulling metadata for only 90,000 users at one time
 
- ### BUG FIXES
+### BUG FIXES
 
   * Updated several function names so as not to mask newer functions imported from {rtweet}, for example, get_mentions() is now create_mentions_edgelist(), and similar updates have been made for function building edgelists from quotes, replies, and retweets
   * Updated tests to work with latest version of {vcr}
   * Made fixes so CI tests would again work with real requests in addition to pre-recorded {vcr} data
 
- ### DOCUMENTATION FIXES
+### DOCUMENTATION FIXES
 
   * Extensively updated the README doc and Setup vignette to help scaffold {tidytags} setup
 
@@ -99,7 +101,7 @@ tidytags 0.1.2 (2021-03-02)
   * CI tests now work with real requests in addition to pre-recorded vcr data
   * Added a Google API key for accessing a Google Sheet with `read_tags()`
 
- ### DOCUMENTATION FIXES
+### DOCUMENTATION FIXES
 
   * Clarified process for obtaining an setting up API keys and tokens for Google, Twitter, and OpenCage
 

diff --git a/R/get-upstream-tweets.R b/R/get-upstream-tweets.R
@@ -79,7 +79,7 @@ get_upstream_tweets <-
             pull_tweet_data(id_vector =
                               unknown_upstream$in_reply_to_status_id_str)
           n <- n + nrow(new_tweets)
-          df <- rbind(df, new_tweets)
+          df <- dplyr::bind_rows(df, new_tweets)
 
           unknown_upstream <- flag_unknown_upstream(df)
 

diff --git a/R/setup-functions.R b/R/setup-functions.R
@@ -181,10 +181,34 @@ pull_tweet_data <-
     )
 
     if(nrow(new_df) > 0) {
-    new_df <- cbind(new_df, rtweet::users_data(new_df))
-    names(new_df)[c(44, 45, 55, 63, 65, 66)] <-
-      c("user_id", "user_id_str", "user_created_at",
-        "user_withheld_in_countries", "user_withheld_scope", "user_entities")
+      user_info <- rtweet::users_data(new_df)
+      duplicate_index <- which(colnames(user_info) %in% colnames(new_df))
+      colnames(user_info)[duplicate_index] <-
+        paste0("user_", colnames(user_info)[duplicate_index])
+      new_df <- cbind(new_df, user_info)
+
+      tweets_col_order <-
+        c("created_at", "id", "id_str", "text", "full_text", "truncated",
+          "entities", "source", "in_reply_to_status_id",
+          "in_reply_to_status_id_str", "in_reply_to_user_id",
+          "in_reply_to_user_id_str", "in_reply_to_screen_name", "geo",
+          "coordinates", "place", "contributors", "is_quote_status",
+          "retweet_count", "favorite_count", "favorited", "favorited_by",
+          "retweeted", "scopes", "lang", "possibly_sensitive",
+          "display_text_width", "display_text_range", "retweeted_status",
+          "quoted_status", "quoted_status_id", "quoted_status_id_str",
+          "quoted_status_permalink", "quote_count", "timestamp_ms",
+          "reply_count","filter_level", "metadata", "query", "withheld_scope",
+          "withheld_copyright", "withheld_in_countries",
+          "possibly_sensitive_appealable", "user_id", "user_id_str", "name",
+          "screen_name", "location", "description", "url", "protected",
+          "followers_count", "friends_count", "listed_count", "user_created_at",
+          "favourites_count", "verified", "statuses_count",
+          "profile_image_url_https", "profile_banner_url", "default_profile",
+          "default_profile_image", "user_withheld_in_countries", "derived",
+          "user_withheld_scope", "user_entities")
+      new_df <- new_df[, tweets_col_order]
+
     } else {
       message("pull_tweet_data() was unable to retrieve any additional data")
       new_df <- NULL

diff --git a/cran-comments.md b/cran-comments.md
@@ -1,11 +1,6 @@
 # CRAN comments
 
-This is a revised submission from tidytags v1.0.2 submitted on 08/20/2022. 
-- Syntax for package and software names has been fixed in title and descrption.
-- In function documentation, \dontrun{} instances have been updated to \donttest{}.
-
-This is a revised submission from tidytags v1.0.1, submitted on 08/18/2022. 
-- Broken URLs have been fixed and the tarball size has been reduced to under 5MB.
+This is a revised submission from tidytags v1.0.2 submitted on 08/19/2022. This version fixes a bug causing an error in the `get_upstream_tweets()` function.
 
 ---
 

diff --git a/docs/404.html b/docs/404.html
diff --git a/docs/CONTRIBUTING.html b/docs/CONTRIBUTING.html
diff --git a/docs/LICENSE-text.html b/docs/LICENSE-text.html
diff --git a/docs/LICENSE.html b/docs/LICENSE.html
diff --git a/docs/articles/index.html b/docs/articles/index.html
diff --git a/docs/articles/setup.html b/docs/articles/setup.html
diff --git a/docs/articles/tidytags-with-conf-hashtags.html b/docs/articles/tidytags-with-conf-hashtags.html
diff --git a/docs/authors.html b/docs/authors.html
diff --git a/docs/index.html b/docs/index.html
diff --git a/docs/news/index.html b/docs/news/index.html
diff --git a/docs/paper.html b/docs/paper.html
diff --git a/docs/pkgdown.yml b/docs/pkgdown.yml
@@ -4,7 +4,7 @@ pkgdown_sha: ~
 articles:
   setup: setup.html
   tidytags-with-conf-hashtags: tidytags-with-conf-hashtags.html
-last_built: 2022-09-14T13:46Z
+last_built: 2022-10-14T19:39Z
 urls:
   reference: https://docs.ropensci.org/tidytags/reference
   article: https://docs.ropensci.org/tidytags/articles

diff --git a/docs/reference/add_users_data.html b/docs/reference/add_users_data.html
diff --git a/docs/reference/create_edgelist.html b/docs/reference/create_edgelist.html
diff --git a/docs/reference/filter_by_tweet_type.html b/docs/reference/filter_by_tweet_type.html
diff --git a/docs/reference/get_char_tweet_ids.html b/docs/reference/get_char_tweet_ids.html
diff --git a/docs/reference/get_upstream_tweets.html b/docs/reference/get_upstream_tweets.html