From f427b61d3ea922ce9dec5aa0a85ca53b0d342fa6 Mon Sep 17 00:00:00 2001
From: David Mayer <david.mayer@cuanschutz.edu>
Date: Thu, 4 Dec 2025 15:44:25 -0500
Subject: [PATCH 01/15] initial commit for basic GA summary info

---
 NAMESPACE             |  2 ++
 R/ga_summary.R        | 31 +++++++++++++++++++++++++++++++
 man/get_ga_summary.Rd | 23 +++++++++++++++++++++++
 3 files changed, 56 insertions(+)
 create mode 100644 R/ga_summary.R
 create mode 100644 man/get_ga_summary.Rd

diff --git a/NAMESPACE b/NAMESPACE
index e44315d..1d9ae96 100644
--- a/NAMESPACE
+++ b/NAMESPACE
@@ -9,6 +9,7 @@ export(ga_query_explorer)
 export(get_core_project_info)
 export(get_ga_basic)
 export(get_ga_meta_by_id)
+export(get_ga_summary)
 export(get_github_by_topic)
 export(get_github_by_topic_graphql)
 export(icite)
@@ -28,6 +29,7 @@ importFrom(glue,glue)
 importFrom(glue,glue_collapse)
 importFrom(googleAnalyticsR,ga_account_list)
 importFrom(googleAnalyticsR,ga_auth)
+importFrom(googleAnalyticsR,ga_data)
 importFrom(httr2,req_auth_bearer_token)
 importFrom(httr2,req_body_json)
 importFrom(httr2,req_error)
diff --git a/R/ga_summary.R b/R/ga_summary.R
new file mode 100644
index 0000000..cc7af93
--- /dev/null
+++ b/R/ga_summary.R
@@ -0,0 +1,31 @@
+#' Get summary metrics from Google Analytics
+#'
+#' This function retrieves summary metrics from Google Analytics,
+#' including total users, new users, engaged sessions, engagement rate,
+#' event count, and screen page views.
+#'
+#' @param propertyId The Google Analytics property ID
+#' @param start_date The start date for the data retrieval (e.g., "30daysAgo")
+#' @param end_date The end date for the data retrieval (e.g., "yesterday")
+#'
+#' @importFrom googleAnalyticsR ga_data
+#' @importFrom dplyr mutate
+#' 
+#' @return A tibble containing the summary metrics
+#' @export
+get_ga_summary <- function(propertyId, start_date = "30daysAgo", end_date = "yesterday") {
+  ga_data(
+    propertyId,
+    metrics = c(
+      "totalUsers",
+      "newUsers",
+      "engagedSessions",
+      "engagementRate",
+      "eventCount",
+      "screenPageViews"
+    ),
+    dimensions = "date",
+    date_range = c(start_date, end_date)
+  ) |> 
+    mutate(propertyId = propertyId)
+}
diff --git a/man/get_ga_summary.Rd b/man/get_ga_summary.Rd
new file mode 100644
index 0000000..623daa0
--- /dev/null
+++ b/man/get_ga_summary.Rd
@@ -0,0 +1,23 @@
+% Generated by roxygen2: do not edit by hand
+% Please edit documentation in R/ga_summary.R
+\name{get_ga_summary}
+\alias{get_ga_summary}
+\title{Get summary metrics from Google Analytics}
+\usage{
+get_ga_summary(propertyId, start_date = "30daysAgo", end_date = "yesterday")
+}
+\arguments{
+\item{propertyId}{The Google Analytics property ID}
+
+\item{start_date}{The start date for the data retrieval (e.g., "30daysAgo")}
+
+\item{end_date}{The end date for the data retrieval (e.g., "yesterday")}
+}
+\value{
+A tibble containing the summary metrics
+}
+\description{
+This function retrieves summary metrics from Google Analytics,
+including total users, new users, engaged sessions, engagement rate,
+event count, and screen page views.
+}

From ad1836cd91432d64b8f787e2ef86c64315392297 Mon Sep 17 00:00:00 2001
From: David Mayer <david.mayer@cuanschutz.edu>
Date: Fri, 5 Dec 2025 17:52:39 -0500
Subject: [PATCH 02/15] add to graphql query for GitHub - re-org

---
 R/get_github_by_topic_graphQL.R | 76 +++++++++++++++++++--------------
 1 file changed, 44 insertions(+), 32 deletions(-)

diff --git a/R/get_github_by_topic_graphQL.R b/R/get_github_by_topic_graphQL.R
index 32d52bb..7d84370 100644
--- a/R/get_github_by_topic_graphQL.R
+++ b/R/get_github_by_topic_graphQL.R
@@ -30,13 +30,13 @@ get_github_by_topic_graphql <- function(topics, token, limit = 30) {
   }
 
   topics <- tolower(topics)
-  
+
   # Set up client
   cli <- ghql::GraphqlClient$new(
     url = "https://api.github.com/graphql",
     headers = list(Authorization = paste0("bearer ", token))
   )
-  
+
   # GraphQL query template
   # Fetches up to `limit` repos per topic, along with key metadata
   query_template <- '
@@ -64,38 +64,37 @@ get_github_by_topic_graphql <- function(topics, token, limit = 30) {
             defaultBranchRef {
               target {
                 ... on Commit {
-                  history {
-                    totalCount
-                  }
+                  history { totalCount }
                 }
               }
             }
-            mentionableUsers {
-              totalCount
-            }
+            mentionableUsers { totalCount }
             repositoryTopics(first: 20) {
-              nodes {
-                topic { name }
-              }
+              nodes { topic { name } }
+            }
+            readme: object(expression: "HEAD:README.md") { id }
+            coc: object(expression: "HEAD:CODE_OF_CONDUCT.md") { id }
+            languages(first: 20) {
+              edges { size node { name } }
             }
           }
         }
       }
     }'
-  
-  # Compile query once
+
   qry <- ghql::Query$new()
   qry$query("repoQuery", query_template)
-  
-  # Helper: fetch repos for one topic
+
   fetch_topic <- function(topic) {
-    res <- cli$exec(qry$queries$repoQuery, 
-                    variables = list(queryString = paste0("topic:", topic),
-                                     limit = limit))
+    res <- cli$exec(
+      qry$queries$repoQuery,
+      variables = list(queryString = paste0("topic:", topic),
+                       limit = limit)
+    )
     dat <- jsonlite::fromJSON(res, flatten = TRUE)
     repos <- dat$data$search$nodes
     if (length(repos) == 0) return(NULL)
-    # browser()
+
     tibble::tibble(
       name         = repos$name,
       owner        = repos$owner.login,
@@ -111,31 +110,45 @@ get_github_by_topic_graphql <- function(topics, token, limit = 30) {
                       repos$defaultBranchRef.target.history.totalCount,
                       ~ if (is.null(.x)) NA_real_ else .x
                     ),
-      contributors = repos$mentionableUsers.totalCount %||% 0,
+      mentionable_users = repos$mentionableUsers.totalCount %||% 0,
+      has_readme   = !purrr::map_lgl(repos$readme.id, is.na),
+      code_of_conduct = !purrr::map_lgl(repos$coc.id, is.na),
       tags         = purrr::map_chr(
-                      repos$repositoryTopics.nodes,
-                      ~ if (length(.x$topic.name) == 0) NA_character_
-                        else paste(.x$topic.name, collapse = ", ")
-                    ),
+        repos$repositoryTopics.nodes,
+        ~ if (is.null(.x) || length(.x$topic.name) == 0) NA_character_
+          else paste(.x$topic.name, collapse = ", ")
+      ),
       language     = repos$primaryLanguage.name,
-      license      = repos$licenseInfo.name,
+      language_loc = purrr::map(
+        repos$languages.edges,
+        ~ if (is.null(.x)) {
+            tibble::tibble(language = NA_character_, bytes = NA_real_, loc = NA_real_)
+          } else {
+            tibble::tibble(
+              language = .x$node.name,
+              bytes = .x$size,
+              loc = round(.x$size / 50)
+            )
+          }
+      ),
+      license      = repos$licenseInfo.name %||% NA_character_,
       created_at   = repos$createdAt,
       pushed_at    = repos$pushedAt,
       updated_at   = repos$updatedAt,
       html_url     = repos$url,
       queried_topic = topic
     )
-
   }
-  
+
   # Fetch across all topics and combine
   df <- purrr::map_dfr(topics, fetch_topic)
 
-  if (nrow(df) == 0) {
+    if (nrow(df) == 0) {
     expected_cols <- c(
       "name", "owner", "description", "stars", "watchers", "forks", "open_issues", "open_prs",
-      "closed_issues", "closed_prs", "commits", "contributors", "tags", "language", "license",
-      "created_at", "pushed_at", "updated_at", "html_url", "queried_topic"
+      "closed_issues", "closed_prs", "commits", "mentionable_users", "has_readme", "code_of_conduct", 
+      "tags", "language", "language_loc", "license", "created_at", "pushed_at", "updated_at", "html_url",
+      "queried_topic"
     )
     df <- tibble::tibble(
         !!!setNames(rep(list(NA), length(expected_cols)), expected_cols)
@@ -148,7 +161,6 @@ get_github_by_topic_graphql <- function(topics, token, limit = 30) {
     dplyr::relocate('closed_issues', .after = 'open_prs') |>
     dplyr::relocate('closed_prs', .after = 'closed_issues') |>
     dplyr::relocate('commits', .after = 'closed_prs') |>
-    dplyr::relocate('contributors', .after = 'commits')
-  
+    dplyr::relocate('mentionable_users', .after = 'commits')
   return(df)
 }

From 8231310b6613ea8396d3cc54a2576852c979fde0 Mon Sep 17 00:00:00 2001
From: David Mayer <david.mayer@cuanschutz.edu>
Date: Fri, 5 Dec 2025 18:06:58 -0500
Subject: [PATCH 03/15] add contributors from REST as there is no graphql
 equivalent. borrow from get_github_by_topic() - TODO: refactor helper
 function/add docs

---
 R/get_github_by_topic_graphQL.R | 36 ++++++++++++++++++++++++++++++---
 1 file changed, 33 insertions(+), 3 deletions(-)

diff --git a/R/get_github_by_topic_graphQL.R b/R/get_github_by_topic_graphQL.R
index 7d84370..7452d05 100644
--- a/R/get_github_by_topic_graphQL.R
+++ b/R/get_github_by_topic_graphQL.R
@@ -146,7 +146,7 @@ get_github_by_topic_graphql <- function(topics, token, limit = 30) {
     if (nrow(df) == 0) {
     expected_cols <- c(
       "name", "owner", "description", "stars", "watchers", "forks", "open_issues", "open_prs",
-      "closed_issues", "closed_prs", "commits", "mentionable_users", "has_readme", "code_of_conduct", 
+      "closed_issues", "closed_prs", "commits", "mentionable_users", "contributors","has_readme", "code_of_conduct", 
       "tags", "language", "language_loc", "license", "created_at", "pushed_at", "updated_at", "html_url",
       "queried_topic"
     )
@@ -154,13 +154,43 @@ get_github_by_topic_graphql <- function(topics, token, limit = 30) {
         !!!setNames(rep(list(NA), length(expected_cols)), expected_cols)
       ) %>% 
        filter(!is.na(.data$name))
-  }
+    } else {
+      df <- df |> 
+        mutate(contributors = map2_dbl(owner, name, ~ get_contributor_count(.x, .y, token = token)))
+    }
+  
   # Organize columns like before
   df <- df |>
     dplyr::relocate('open_prs', .after = 'open_issues') |>
     dplyr::relocate('closed_issues', .after = 'open_prs') |>
     dplyr::relocate('closed_prs', .after = 'closed_issues') |>
     dplyr::relocate('commits', .after = 'closed_prs') |>
-    dplyr::relocate('mentionable_users', .after = 'commits')
+    dplyr::relocate('mentionable_users', .after = 'commits') |> 
+    dplyr::relocate('contributors', .after = 'mentionable_users')
   return(df)
 }
+
+  # Helper to count contributors
+  get_contributor_count <- function(owner, repo, token = NULL) {
+    base_url <- glue("https://api.github.com/repos/{owner}/{repo}/contributors")
+    req <- request(base_url) |>
+      req_url_query(per_page = 1, anon = "false") |>  # anon=TRUE counts contributors without accounts
+      req_headers("User-Agent" = "httr2")
+    if (!is.null(token)) {
+      req <- req |> req_auth_bearer_token(token)
+    }
+
+    resp <- tryCatch(req_perform(req), error = function(e) NULL)
+    if (is.null(resp) || resp_status(resp) != 200) return(NA_real_)
+
+    link <- resp_headers(resp)[["link"]]
+    if (!is.null(link) && grepl("rel=\"last\"", link)) {
+      matches <- regmatches(link, regexpr("page=\\d+>; rel=\\\"last\\\"", link))
+      count <- as.numeric(sub("page=", "", sub(">; rel=\"last\"", "", matches)))
+      return(count)
+    } else {
+      body <- resp_body_json(resp)
+      return(length(body))  # if only a few contributors
+    }
+  }
+

From cea01c4a1a191cd44f5f04f1ae524ff2b270682e Mon Sep 17 00:00:00 2001
From: David Mayer <david.mayer@cuanschutz.edu>
Date: Mon, 8 Dec 2025 08:42:16 -0500
Subject: [PATCH 04/15] formatting

---
 R/get_github_by_topic_graphQL.R | 84 ++++++++++++++++-----------------
 1 file changed, 42 insertions(+), 42 deletions(-)

diff --git a/R/get_github_by_topic_graphQL.R b/R/get_github_by_topic_graphQL.R
index 7452d05..99040dc 100644
--- a/R/get_github_by_topic_graphQL.R
+++ b/R/get_github_by_topic_graphQL.R
@@ -96,47 +96,47 @@ get_github_by_topic_graphql <- function(topics, token, limit = 30) {
     if (length(repos) == 0) return(NULL)
 
     tibble::tibble(
-      name         = repos$name,
-      owner        = repos$owner.login,
-      description  = repos$description,
-      stars        = repos$stargazerCount,
-      watchers     = repos$watchers.totalCount,
-      forks        = repos$forkCount,
-      open_issues  = repos$issues.totalCount,
-      closed_issues = repos$closedIssues.totalCount,
-      open_prs     = repos$openPRs.totalCount,
-      closed_prs   = repos$closedPRs.totalCount,
-      commits      = purrr::map_dbl(
-                      repos$defaultBranchRef.target.history.totalCount,
-                      ~ if (is.null(.x)) NA_real_ else .x
-                    ),
-      mentionable_users = repos$mentionableUsers.totalCount %||% 0,
-      has_readme   = !purrr::map_lgl(repos$readme.id, is.na),
-      code_of_conduct = !purrr::map_lgl(repos$coc.id, is.na),
-      tags         = purrr::map_chr(
-        repos$repositoryTopics.nodes,
-        ~ if (is.null(.x) || length(.x$topic.name) == 0) NA_character_
-          else paste(.x$topic.name, collapse = ", ")
-      ),
-      language     = repos$primaryLanguage.name,
-      language_loc = purrr::map(
-        repos$languages.edges,
-        ~ if (is.null(.x)) {
-            tibble::tibble(language = NA_character_, bytes = NA_real_, loc = NA_real_)
-          } else {
-            tibble::tibble(
-              language = .x$node.name,
-              bytes = .x$size,
-              loc = round(.x$size / 50)
-            )
-          }
-      ),
-      license      = repos$licenseInfo.name %||% NA_character_,
-      created_at   = repos$createdAt,
-      pushed_at    = repos$pushedAt,
-      updated_at   = repos$updatedAt,
-      html_url     = repos$url,
-      queried_topic = topic
+      name                 = repos$name,
+      owner                = repos$owner.login,
+      description          = repos$description,
+      stars                = repos$stargazerCount,
+      watchers             = repos$watchers.totalCount,
+      forks                = repos$forkCount,
+      open_issues          = repos$issues.totalCount,
+      closed_issues        = repos$closedIssues.totalCount,
+      open_prs             = repos$openPRs.totalCount,
+      closed_prs           = repos$closedPRs.totalCount,
+      commits              = purrr::map_dbl(
+                               repos$defaultBranchRef.target.history.totalCount,
+                               ~ if (is.null(.x)) NA_real_ else .x
+                             ),
+      mentionable_users    = repos$mentionableUsers.totalCount %||% 0,
+      has_readme           = !purrr::map_lgl(repos$readme.id, is.na),
+      code_of_conduct      = !purrr::map_lgl(repos$coc.id, is.na),
+      tags                 = purrr::map_chr(
+                               repos$repositoryTopics.nodes,
+                               ~ if (is.null(.x) || length(.x$topic.name) == 0) NA_character_
+                                 else paste(.x$topic.name, collapse = ", ")
+                             ),
+      language             = repos$primaryLanguage.name,
+      language_loc         = purrr::map(
+                               repos$languages.edges,
+                               ~ if (is.null(.x)) {
+                                   tibble::tibble(language = NA_character_, bytes = NA_real_, loc = NA_real_)
+                                 } else {
+                                   tibble::tibble(
+                                     language = .x$node.name,
+                                     bytes = .x$size,
+                                     loc = round(.x$size / 50)
+                                   )
+                                 }
+                             ),
+      license              = repos$licenseInfo.name %||% NA_character_,
+      created_at           = repos$createdAt,
+      pushed_at            = repos$pushedAt,
+      updated_at           = repos$updatedAt,
+      html_url             = repos$url,
+      queried_topic        = topic
     )
   }
 
@@ -156,7 +156,7 @@ get_github_by_topic_graphql <- function(topics, token, limit = 30) {
        filter(!is.na(.data$name))
     } else {
       df <- df |> 
-        mutate(contributors = map2_dbl(owner, name, ~ get_contributor_count(.x, .y, token = token)))
+        mutate(contributors = map2_dbl(.data$owner, .data$name, ~ get_contributor_count(.x, .y, token = token)))
     }
   
   # Organize columns like before

From 3ecfe00dfd11f51d23ba7d90c41b4560d5ed51c7 Mon Sep 17 00:00:00 2001
From: David Mayer <david.mayer@cuanschutz.edu>
Date: Mon, 8 Dec 2025 08:43:00 -0500
Subject: [PATCH 05/15] logical readability

---
 R/get_github_by_topic_graphQL.R | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/R/get_github_by_topic_graphQL.R b/R/get_github_by_topic_graphQL.R
index 99040dc..d1ad76b 100644
--- a/R/get_github_by_topic_graphQL.R
+++ b/R/get_github_by_topic_graphQL.R
@@ -111,8 +111,8 @@ get_github_by_topic_graphql <- function(topics, token, limit = 30) {
                                ~ if (is.null(.x)) NA_real_ else .x
                              ),
       mentionable_users    = repos$mentionableUsers.totalCount %||% 0,
-      has_readme           = !purrr::map_lgl(repos$readme.id, is.na),
-      code_of_conduct      = !purrr::map_lgl(repos$coc.id, is.na),
+      has_readme           = purrr::map_lgl(repos$readme.id, !is.na),
+      code_of_conduct      = purrr::map_lgl(repos$coc.id, !is.na),
       tags                 = purrr::map_chr(
                                repos$repositoryTopics.nodes,
                                ~ if (is.null(.x) || length(.x$topic.name) == 0) NA_character_

From f0725aad4d9ce63767193b67470d3809f074cb96 Mon Sep 17 00:00:00 2001
From: David Mayer <david.mayer@cuanschutz.edu>
Date: Mon, 8 Dec 2025 08:54:48 -0500
Subject: [PATCH 06/15] additional logical considerations

---
 R/get_github_by_topic_graphQL.R | 10 ++++++++--
 1 file changed, 8 insertions(+), 2 deletions(-)

diff --git a/R/get_github_by_topic_graphQL.R b/R/get_github_by_topic_graphQL.R
index d1ad76b..74322b9 100644
--- a/R/get_github_by_topic_graphQL.R
+++ b/R/get_github_by_topic_graphQL.R
@@ -111,8 +111,14 @@ get_github_by_topic_graphql <- function(topics, token, limit = 30) {
                                ~ if (is.null(.x)) NA_real_ else .x
                              ),
       mentionable_users    = repos$mentionableUsers.totalCount %||% 0,
-      has_readme           = purrr::map_lgl(repos$readme.id, !is.na),
-      code_of_conduct      = purrr::map_lgl(repos$coc.id, !is.na),
+      has_readme           = purrr::map_lgl(
+                               repos$readme.id,
+                               ~ if (is.na(.x) || is.null(.x) || length(.x) == 0) FALSE else TRUE
+                            ),
+      code_of_conduct      = purrr::map_lgl(
+                               repos$coc.id,
+                               ~ if (is.na(.x) || is.null(.x) || length(.x) == 0) FALSE else TRUE
+                             ),
       tags                 = purrr::map_chr(
                                repos$repositoryTopics.nodes,
                                ~ if (is.null(.x) || length(.x$topic.name) == 0) NA_character_

From 8c879018e88c567f3c268ef600b174d05bd24cdc Mon Sep 17 00:00:00 2001
From: David Mayer <david.mayer@cuanschutz.edu>
Date: Mon, 8 Dec 2025 09:15:49 -0500
Subject: [PATCH 07/15] if no repositories return results, the json field for
 `id` never gets populated. check to make sure it is available before
 evaluating logical

---
 R/get_github_by_topic_graphQL.R | 24 +++++++++++++++---------
 1 file changed, 15 insertions(+), 9 deletions(-)

diff --git a/R/get_github_by_topic_graphQL.R b/R/get_github_by_topic_graphQL.R
index 74322b9..b6a9abf 100644
--- a/R/get_github_by_topic_graphQL.R
+++ b/R/get_github_by_topic_graphQL.R
@@ -94,7 +94,7 @@ get_github_by_topic_graphql <- function(topics, token, limit = 30) {
     dat <- jsonlite::fromJSON(res, flatten = TRUE)
     repos <- dat$data$search$nodes
     if (length(repos) == 0) return(NULL)
-
+    # browser()
     tibble::tibble(
       name                 = repos$name,
       owner                = repos$owner.login,
@@ -111,14 +111,20 @@ get_github_by_topic_graphql <- function(topics, token, limit = 30) {
                                ~ if (is.null(.x)) NA_real_ else .x
                              ),
       mentionable_users    = repos$mentionableUsers.totalCount %||% 0,
-      has_readme           = purrr::map_lgl(
-                               repos$readme.id,
-                               ~ if (is.na(.x) || is.null(.x) || length(.x) == 0) FALSE else TRUE
-                            ),
-      code_of_conduct      = purrr::map_lgl(
-                               repos$coc.id,
-                               ~ if (is.na(.x) || is.null(.x) || length(.x) == 0) FALSE else TRUE
-                             ),
+      has_readme           = if( 'readme.id' %in% names(repos)) {
+                               purrr::map_lgl(
+                                 repos$readme.id,
+                                 ~ if (is.na(.x) || is.null(.x) || length(.x) == 0) FALSE else TRUE
+                              ) } else {
+                                FALSE
+                              },
+      code_of_conduct      = if( 'coc.id' %in% names(repos)) {
+                               purrr::map_lgl(
+                                 repos$coc,
+                                 ~ if (is.na(.x) || is.null(.x) || length(.x) == 0) FALSE else TRUE
+                               ) } else {
+                                FALSE
+                               },
       tags                 = purrr::map_chr(
                                repos$repositoryTopics.nodes,
                                ~ if (is.null(.x) || length(.x$topic.name) == 0) NA_character_

From 4c7ff8ec4262139e42edcfa4705b68a2ca9674a8 Mon Sep 17 00:00:00 2001
From: David Mayer <david.mayer@cuanschutz.edu>
Date: Mon, 8 Dec 2025 10:28:56 -0500
Subject: [PATCH 08/15] relocate helper function to facilitate re-use. keep
 with other github REST functions

---
 R/get_github_by_topic.R         | 53 ++++++++++++++++++---------------
 R/get_github_by_topic_graphQL.R | 25 ----------------
 2 files changed, 29 insertions(+), 49 deletions(-)

diff --git a/R/get_github_by_topic.R b/R/get_github_by_topic.R
index 82cfe54..c746cdf 100644
--- a/R/get_github_by_topic.R
+++ b/R/get_github_by_topic.R
@@ -1,3 +1,32 @@
+# Helper to count contributors
+  get_contributor_count <- function(owner, repo, token = NULL) {
+    base_url <- glue("https://api.github.com/repos/{owner}/{repo}/contributors")
+    req <- request(base_url) |>
+      req_url_query(per_page = 1, anon = "false") |>  # anon=TRUE counts contributors without accounts
+      req_headers("User-Agent" = "httr2")
+    if (!is.null(token)) {
+      req <- req |> 
+        req_auth_bearer_token(token) |> 
+        req_throttle(capacity = 5000, fill_time_s = 3600)
+    } else {
+      req <- req |> 
+      req_throttle(capacity = 60, fill_time_s = 3600)
+    }
+
+    resp <- tryCatch(req_perform(req), error = function(e) NULL)
+    if (is.null(resp) || resp_status(resp) != 200) return(NA_real_)
+
+    link <- resp_headers(resp)[["link"]]
+    if (!is.null(link) && grepl("rel=\"last\"", link)) {
+      matches <- regmatches(link, regexpr("page=\\d+>; rel=\\\"last\\\"", link))
+      count <- as.numeric(sub("page=", "", sub(">; rel=\"last\"", "", matches)))
+      return(count)
+    } else {
+      body <- resp_body_json(resp)
+      return(length(body))  # if only a few contributors
+    }
+  }
+
 #' Get GitHub Repositories by Topic
 #'
 #' @param topics A vector of GitHub topics to search for.
@@ -168,30 +197,6 @@ get_github_by_topic <- function(topics, token = NULL, limit = 30) {
   commit_counts <- map2_dbl(df$owner, df$name, ~ get_commit_count(.x, .y, token = token))
   df$commits <- commit_counts
 
-  # Helper to count contributors
-  get_contributor_count <- function(owner, repo, token = NULL) {
-    base_url <- glue("https://api.github.com/repos/{owner}/{repo}/contributors")
-    req <- request(base_url) |>
-      req_url_query(per_page = 1, anon = "false") |>  # anon=TRUE counts contributors without accounts
-      req_headers("User-Agent" = "httr2")
-    if (!is.null(token)) {
-      req <- req |> req_auth_bearer_token(token)
-    }
-
-    resp <- tryCatch(req_perform(req), error = function(e) NULL)
-    if (is.null(resp) || resp_status(resp) != 200) return(NA_real_)
-
-    link <- resp_headers(resp)[["link"]]
-    if (!is.null(link) && grepl("rel=\"last\"", link)) {
-      matches <- regmatches(link, regexpr("page=\\d+>; rel=\\\"last\\\"", link))
-      count <- as.numeric(sub("page=", "", sub(">; rel=\"last\"", "", matches)))
-      return(count)
-    } else {
-      body <- resp_body_json(resp)
-      return(length(body))  # if only a few contributors
-    }
-  }
-
   contributor_counts <- map2_dbl(df$owner, df$name, ~ get_contributor_count(.x, .y, token = token))
   df$contributors <- contributor_counts
 
diff --git a/R/get_github_by_topic_graphQL.R b/R/get_github_by_topic_graphQL.R
index b6a9abf..359b714 100644
--- a/R/get_github_by_topic_graphQL.R
+++ b/R/get_github_by_topic_graphQL.R
@@ -181,28 +181,3 @@ get_github_by_topic_graphql <- function(topics, token, limit = 30) {
     dplyr::relocate('contributors', .after = 'mentionable_users')
   return(df)
 }
-
-  # Helper to count contributors
-  get_contributor_count <- function(owner, repo, token = NULL) {
-    base_url <- glue("https://api.github.com/repos/{owner}/{repo}/contributors")
-    req <- request(base_url) |>
-      req_url_query(per_page = 1, anon = "false") |>  # anon=TRUE counts contributors without accounts
-      req_headers("User-Agent" = "httr2")
-    if (!is.null(token)) {
-      req <- req |> req_auth_bearer_token(token)
-    }
-
-    resp <- tryCatch(req_perform(req), error = function(e) NULL)
-    if (is.null(resp) || resp_status(resp) != 200) return(NA_real_)
-
-    link <- resp_headers(resp)[["link"]]
-    if (!is.null(link) && grepl("rel=\"last\"", link)) {
-      matches <- regmatches(link, regexpr("page=\\d+>; rel=\\\"last\\\"", link))
-      count <- as.numeric(sub("page=", "", sub(">; rel=\"last\"", "", matches)))
-      return(count)
-    } else {
-      body <- resp_body_json(resp)
-      return(length(body))  # if only a few contributors
-    }
-  }
-

From c9aef02b1f607cde14c861a3aa2f277b1547891a Mon Sep 17 00:00:00 2001
From: David Mayer <david.mayer@cuanschutz.edu>
Date: Mon, 8 Dec 2025 10:34:55 -0500
Subject: [PATCH 09/15] re-org, add dep

---
 NAMESPACE                    |  1 +
 R/get_github_by_topic.R      | 14 ++++++++++++--
 man/get_contributor_count.Rd | 21 +++++++++++++++++++++
 3 files changed, 34 insertions(+), 2 deletions(-)
 create mode 100644 man/get_contributor_count.Rd

diff --git a/NAMESPACE b/NAMESPACE
index 1d9ae96..62d217b 100644
--- a/NAMESPACE
+++ b/NAMESPACE
@@ -38,6 +38,7 @@ importFrom(httr2,req_method)
 importFrom(httr2,req_perform)
 importFrom(httr2,req_perform_parallel)
 importFrom(httr2,req_retry)
+importFrom(httr2,req_throttle)
 importFrom(httr2,req_url_query)
 importFrom(httr2,request)
 importFrom(httr2,resp_body_json)
diff --git a/R/get_github_by_topic.R b/R/get_github_by_topic.R
index c746cdf..06ebe10 100644
--- a/R/get_github_by_topic.R
+++ b/R/get_github_by_topic.R
@@ -1,5 +1,14 @@
-# Helper to count contributors
-  get_contributor_count <- function(owner, repo, token = NULL) {
+# REST API Helper Functions
+#' Get the number of contributors for a GitHub repository
+#'
+#' @param owner The owner of the GitHub repository
+#' @param repo The name of the GitHub repository
+#' @param token A GitHub personal access token (optional)
+#' 
+#' @importFrom httr2 req_throttle
+#'
+#' @return The number of contributors to the repository
+get_contributor_count <- function(owner, repo, token = NULL) {
     base_url <- glue("https://api.github.com/repos/{owner}/{repo}/contributors")
     req <- request(base_url) |>
       req_url_query(per_page = 1, anon = "false") |>  # anon=TRUE counts contributors without accounts
@@ -27,6 +36,7 @@
     }
   }
 
+# REST Functions
 #' Get GitHub Repositories by Topic
 #'
 #' @param topics A vector of GitHub topics to search for.
diff --git a/man/get_contributor_count.Rd b/man/get_contributor_count.Rd
new file mode 100644
index 0000000..559dfa4
--- /dev/null
+++ b/man/get_contributor_count.Rd
@@ -0,0 +1,21 @@
+% Generated by roxygen2: do not edit by hand
+% Please edit documentation in R/get_github_by_topic.R
+\name{get_contributor_count}
+\alias{get_contributor_count}
+\title{Get the number of contributors for a GitHub repository}
+\usage{
+get_contributor_count(owner, repo, token = NULL)
+}
+\arguments{
+\item{owner}{The owner of the GitHub repository}
+
+\item{repo}{The name of the GitHub repository}
+
+\item{token}{A GitHub personal access token (optional)}
+}
+\value{
+The number of contributors to the repository
+}
+\description{
+Get the number of contributors for a GitHub repository
+}

From 71f822035ecd082ff687fcdadaa04922f0db6756 Mon Sep 17 00:00:00 2001
From: David Mayer <david.mayer@cuanschutz.edu>
Date: Mon, 8 Dec 2025 10:41:58 -0500
Subject: [PATCH 10/15] add REST API limits for GitHub Search

---
 R/get_github_by_topic.R | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

diff --git a/R/get_github_by_topic.R b/R/get_github_by_topic.R
index 06ebe10..5bbfe5e 100644
--- a/R/get_github_by_topic.R
+++ b/R/get_github_by_topic.R
@@ -84,7 +84,12 @@ get_github_by_topic <- function(topics, token = NULL, limit = 30) {
     req_url_query(q = q_topic, per_page = limit)
 
   if (!is.null(token)) {
-    req_topic <- req_topic |> req_auth_bearer_token(token)
+    req_topic <- req_topic |> 
+      req_auth_bearer_token(token) |> 
+      req_throttle(capacity = 30, fill_time_s = 60)
+  } else {
+    req_topic <- req_topic |>
+      req_throttle(capacity = 10, fill_time_s = 60)
   }
 
   resp_topic <- req_perform(req_topic)

From 26faf4c72a22f9e55f2af7136952a6cb6c9f204c Mon Sep 17 00:00:00 2001
From: David Mayer <david.mayer@cuanschutz.edu>
Date: Mon, 8 Dec 2025 10:59:51 -0500
Subject: [PATCH 11/15] share rate limit pools across similar api calls - this
 likely would have occurred as when realm is unset, it defaults to hostname.
 but this calms my ocd

---
 R/get_github_by_topic.R | 40 +++++++++++++++++++++++++++++++---------
 1 file changed, 31 insertions(+), 9 deletions(-)

diff --git a/R/get_github_by_topic.R b/R/get_github_by_topic.R
index 5bbfe5e..5892230 100644
--- a/R/get_github_by_topic.R
+++ b/R/get_github_by_topic.R
@@ -16,10 +16,10 @@ get_contributor_count <- function(owner, repo, token = NULL) {
     if (!is.null(token)) {
       req <- req |> 
         req_auth_bearer_token(token) |> 
-        req_throttle(capacity = 5000, fill_time_s = 3600)
+        req_throttle(capacity = 5000, fill_time_s = 3600, realm = "github_authenticated")
     } else {
       req <- req |> 
-      req_throttle(capacity = 60, fill_time_s = 3600)
+      req_throttle(capacity = 60, fill_time_s = 3600, realm = "github_anonymous")
     }
 
     resp <- tryCatch(req_perform(req), error = function(e) NULL)
@@ -86,10 +86,10 @@ get_github_by_topic <- function(topics, token = NULL, limit = 30) {
   if (!is.null(token)) {
     req_topic <- req_topic |> 
       req_auth_bearer_token(token) |> 
-      req_throttle(capacity = 30, fill_time_s = 60)
+      req_throttle(capacity = 30, fill_time_s = 60, realm = "github_search_authenticated")
   } else {
     req_topic <- req_topic |>
-      req_throttle(capacity = 10, fill_time_s = 60)
+      req_throttle(capacity = 10, fill_time_s = 60, realm = "github_search_anonymous")
   }
 
   resp_topic <- req_perform(req_topic)
@@ -108,7 +108,14 @@ get_github_by_topic <- function(topics, token = NULL, limit = 30) {
     req <- httr2::request(url) |>
       httr2::req_headers("User-Agent" = "httr2",
                          "X-GitHub-Api-Version" = "2022-11-28")
-    if (!is.null(token)) req <- req |> httr2::req_auth_bearer_token(token)
+    if (!is.null(token)) {
+      req <- req |> 
+        httr2::req_auth_bearer_token(token) |> 
+        req_throttle(capacity = 5000, fill_time_s = 3600, realm = "github_authenticated")
+    } else {
+      req <- req |>
+        req_throttle(capacity = 60, fill_time_s = 3600, realm = "github_anonymous")
+    }
 
     resp <- tryCatch(httr2::req_perform(req), error = function(e) NULL)
     if (is.null(resp) || httr2::resp_status(resp) != 200) return(NA_real_)
@@ -141,7 +148,12 @@ get_github_by_topic <- function(topics, token = NULL, limit = 30) {
       req_url_query(state = state, per_page = 1) |>
       req_headers("User-Agent" = "httr2")
     if (!is.null(token)) {
-      req <- req |> req_auth_bearer_token(token)
+      req <- req |> 
+        req_auth_bearer_token(token) |> 
+        req_throttle(capacity = 5000, fill_time_s = 3600, realm = "github_authenticated")
+    } else {
+      req <- req |>
+        req_throttle(capacity = 60, fill_time_s = 3600, realm = "github_anonymous")
     }
 
     resp <- tryCatch(req_perform(req), error = function(e) NULL)
@@ -165,8 +177,13 @@ get_github_by_topic <- function(topics, token = NULL, limit = 30) {
       req_url_query(q = q, per_page = 1) |>
       req_headers("User-Agent" = "httr2")
     if (!is.null(token)) {
-      req <- req |> req_auth_bearer_token(token)
-    }
+      req <- req |> 
+        req_auth_bearer_token(token) |> 
+        req_throttle(capacity = 30, fill_time_s = 60, realm = "github_search_authenticated")
+    } else {
+      req <- req |>
+        req_throttle(capacity = 10, fill_time_s = 60, realm = "github_search_anonymous")
+    } 
     resp <- tryCatch(req_perform(req), error = function(e) NULL)
     if (!is.null(resp) && resp_status(resp) == 200) {
       return(resp_body_json(resp)$total_count)
@@ -192,7 +209,12 @@ get_github_by_topic <- function(topics, token = NULL, limit = 30) {
       req_url_query(sha = branch, per_page = 1) |>
       req_headers("User-Agent" = "httr2")
     if (!is.null(token)) {
-      req <- req |> req_auth_bearer_token(token)
+      req <- req |> 
+        req_auth_bearer_token(token) |> 
+        req_throttle(capacity = 5000, fill_time_s = 3600, realm = "github_authenticated")
+    } else {
+      req <- req |>
+        req_throttle(capacity = 60, fill_time_s = 3600, realm = "github_anonymous")
     }
 
     resp <- tryCatch(req_perform(req), error = function(e) NULL)

From ecaa55838ab4537784b46937223eb7d00a43ee34 Mon Sep 17 00:00:00 2001
From: David Mayer <david.mayer@cuanschutz.edu>
Date: Mon, 8 Dec 2025 18:07:23 -0500
Subject: [PATCH 12/15] some groups have LOTS of repos... - utiilize pagination
 in graphQL requests - implement progress bar - update test

---
 DESCRIPTION                                   |   3 +-
 NAMESPACE                                     |   3 +
 R/get_github_by_topic_graphQL.R               | 102 ++++++++++++------
 .../test-get_github_by_topic_graphQL.R        |  11 +-
 4 files changed, 81 insertions(+), 38 deletions(-)

diff --git a/DESCRIPTION b/DESCRIPTION
index b436e46..9951a41 100644
--- a/DESCRIPTION
+++ b/DESCRIPTION
@@ -33,7 +33,8 @@ Imports:
     openxlsx,
     tidyr,
     rvest,
-    readr
+    readr,
+    cli
 Suggests:
     gargle,
     gitcreds,
diff --git a/NAMESPACE b/NAMESPACE
index 62d217b..60420b6 100644
--- a/NAMESPACE
+++ b/NAMESPACE
@@ -16,6 +16,9 @@ export(icite)
 import(dplyr)
 import(httr2)
 import(jsonlite)
+importFrom(cli,cli_progress_bar)
+importFrom(cli,cli_progress_done)
+importFrom(cli,cli_progress_update)
 importFrom(dplyr,arrange)
 importFrom(dplyr,as_tibble)
 importFrom(dplyr,bind_rows)
diff --git a/R/get_github_by_topic_graphQL.R b/R/get_github_by_topic_graphQL.R
index 359b714..89cf6ef 100644
--- a/R/get_github_by_topic_graphQL.R
+++ b/R/get_github_by_topic_graphQL.R
@@ -4,6 +4,8 @@
 #' @param token A GitHub personal access token. Required for GraphQL API.
 #' @param limit The maximum number of repositories to return per topic (max 1000 by GitHub).
 #' 
+#' @importFrom cli cli_progress_bar cli_progress_update cli_progress_done
+#' @importFrom dplyr bind_rows
 #' @importFrom ghql GraphqlClient
 #' @importFrom jsonlite fromJSON
 #' @importFrom tibble tibble
@@ -24,25 +26,27 @@ get_github_by_topic_graphql <- function(topics, token, limit = 30) {
   if (missing(token) || is.null(token)) {
     stop("A GitHub personal access token is required for GraphQL API.")
   }
-
   if (length(topics) == 0) {
     stop("At least one topic must be provided.")
   }
 
   topics <- tolower(topics)
 
-  # Set up client
+  # Setup client
   cli <- ghql::GraphqlClient$new(
     url = "https://api.github.com/graphql",
     headers = list(Authorization = paste0("bearer ", token))
   )
 
-  # GraphQL query template
-  # Fetches up to `limit` repos per topic, along with key metadata
+  # GraphQL query template with pagination
   query_template <- '
-    query($queryString: String!, $limit: Int!) {
-      search(query: $queryString, type: REPOSITORY, first: $limit) {
+    query($queryString: String!, $limit: Int!, $cursor: String) {
+      search(query: $queryString, type: REPOSITORY, first: $limit, after: $cursor) {
         repositoryCount
+        pageInfo {
+          hasNextPage
+          endCursor
+        }
         nodes {
           ... on Repository {
             name
@@ -85,16 +89,37 @@ get_github_by_topic_graphql <- function(topics, token, limit = 30) {
   qry <- ghql::Query$new()
   qry$query("repoQuery", query_template)
 
+  # Pagination-enabled requester
   fetch_topic <- function(topic) {
-    res <- cli$exec(
-      qry$queries$repoQuery,
-      variables = list(queryString = paste0("topic:", topic),
-                       limit = limit)
-    )
-    dat <- jsonlite::fromJSON(res, flatten = TRUE)
-    repos <- dat$data$search$nodes
-    if (length(repos) == 0) return(NULL)
-    # browser()
+    cursor <- NULL
+    all_repos <- list()
+
+    repeat {
+      res <- cli$exec(
+        qry$queries$repoQuery,
+        variables = list(
+          queryString = paste0("topic:", topic),
+          limit = limit,
+          cursor = cursor
+        )
+      )
+
+      dat <- jsonlite::fromJSON(res, flatten = TRUE)
+      search <- dat$data$search
+      repos <- search$nodes
+
+      if (length(repos) > 0) {
+        all_repos <- append(all_repos, list(repos))
+      }
+
+      if (!isTRUE(search$pageInfo$hasNextPage)) break
+      cursor <- search$pageInfo$endCursor
+    }
+
+    if (length(all_repos) == 0) return(NULL)
+
+    repos <- dplyr::bind_rows(all_repos)
+
     tibble::tibble(
       name                 = repos$name,
       owner                = repos$owner.login,
@@ -152,32 +177,45 @@ get_github_by_topic_graphql <- function(topics, token, limit = 30) {
     )
   }
 
-  # Fetch across all topics and combine
-  df <- purrr::map_dfr(topics, fetch_topic)
+  results_list <- vector("list", length(topics)) ## initialize results
+  cli::cli_progress_bar("Requesting repositories by topic", total = length(topics))
+  
+  for (i in seq_along(topics)) {
+    results_list[[i]] <- fetch_topic(topics[i])
+    cli::cli_progress_update()
+  }
+  
+  cli::cli_progress_done()
+  results <- dplyr::bind_rows(results_list)
 
-    if (nrow(df) == 0) {
+  # If nothing is found
+  if (nrow(results) == 0) {
     expected_cols <- c(
       "name", "owner", "description", "stars", "watchers", "forks", "open_issues", "open_prs",
-      "closed_issues", "closed_prs", "commits", "mentionable_users", "contributors","has_readme", "code_of_conduct", 
-      "tags", "language", "language_loc", "license", "created_at", "pushed_at", "updated_at", "html_url",
-      "queried_topic"
+      "closed_issues", "closed_prs", "commits", "mentionable_users", "contributors",
+      "has_readme", "code_of_conduct", "tags", "language", "language_loc",
+      "license", "created_at", "pushed_at", "updated_at", "html_url", "queried_topic"
     )
-    df <- tibble::tibble(
+
+    return(
+      tibble::tibble(
         !!!setNames(rep(list(NA), length(expected_cols)), expected_cols)
-      ) %>% 
-       filter(!is.na(.data$name))
-    } else {
-      df <- df |> 
-        mutate(contributors = map2_dbl(.data$owner, .data$name, ~ get_contributor_count(.x, .y, token = token)))
-    }
-  
+      ) |> filter(!is.na(.data$name))
+    )
+  }
+
+  # Contributor count
+  results <- results |>
+    dplyr::mutate(contributors = map2_dbl(.data$owner, .data$name, ~
+      get_contributor_count(.x, .y, token = token)
+    ))
+
   # Organize columns like before
-  df <- df |>
+  results |>
     dplyr::relocate('open_prs', .after = 'open_issues') |>
     dplyr::relocate('closed_issues', .after = 'open_prs') |>
     dplyr::relocate('closed_prs', .after = 'closed_issues') |>
     dplyr::relocate('commits', .after = 'closed_prs') |>
-    dplyr::relocate('mentionable_users', .after = 'commits') |> 
+    dplyr::relocate('mentionable_users', .after = 'commits') |>
     dplyr::relocate('contributors', .after = 'mentionable_users')
-  return(df)
 }
diff --git a/tests/testthat/test-get_github_by_topic_graphQL.R b/tests/testthat/test-get_github_by_topic_graphQL.R
index 0d5d6e0..409a8ee 100644
--- a/tests/testthat/test-get_github_by_topic_graphQL.R
+++ b/tests/testthat/test-get_github_by_topic_graphQL.R
@@ -22,12 +22,13 @@ test_that("Returned data frame contains expected columns", {
   skip_if_offline()
   skip_on_ci()
 
-  result <- get_github_by_topic_graphql(c("bioinformatics"), token = gitcreds_get()$password, limit = 3)
+  result <- get_github_by_topic_graphql(c("u24ca289073"), token = gitcreds_get()$password, limit = 3)
   expected_cols <- c(
-     "name", "owner", "description", "stars", "watchers", "forks", "open_issues", "open_prs", 
-     "closed_issues", "closed_prs", "commits", "contributors", "tags", "language", "license", 
-     "created_at", "pushed_at", "updated_at", "html_url"
-  )
+      "name", "owner", "description", "stars", "watchers", "forks", "open_issues", "open_prs",
+      "closed_issues", "closed_prs", "commits", "mentionable_users", "contributors",
+      "has_readme", "code_of_conduct", "tags", "language", "language_loc",
+      "license", "created_at", "pushed_at", "updated_at", "html_url", "queried_topic"
+    )
   expect_true(all(expected_cols %in% names(result)))
 })
 

From da480d6c8f947018ee1d78732e81f9889df80f01 Mon Sep 17 00:00:00 2001
From: David Mayer <david.mayer@cuanschutz.edu>
Date: Mon, 8 Dec 2025 18:21:25 -0500
Subject: [PATCH 13/15] nope

---
 R/get_github_by_topic_graphQL.R | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/R/get_github_by_topic_graphQL.R b/R/get_github_by_topic_graphQL.R
index 89cf6ef..db3f141 100644
--- a/R/get_github_by_topic_graphQL.R
+++ b/R/get_github_by_topic_graphQL.R
@@ -29,6 +29,9 @@ get_github_by_topic_graphql <- function(topics, token, limit = 30) {
   if (length(topics) == 0) {
     stop("At least one topic must be provided.")
   }
+  if (limit > 30) {
+    stop("limit must be 30 or less") ## results are good. more than this and GitHub will nope out
+  }
 
   topics <- tolower(topics)
 

From 03a676790d7b876c90863bd577a02a1a4963368e Mon Sep 17 00:00:00 2001
From: David Mayer <david.mayer@cuanschutz.edu>
Date: Tue, 9 Dec 2025 07:55:22 -0500
Subject: [PATCH 14/15] fix warning

---
 R/get_github_by_topic_graphQL.R | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/R/get_github_by_topic_graphQL.R b/R/get_github_by_topic_graphQL.R
index db3f141..0edfec6 100644
--- a/R/get_github_by_topic_graphQL.R
+++ b/R/get_github_by_topic_graphQL.R
@@ -148,7 +148,7 @@ get_github_by_topic_graphql <- function(topics, token, limit = 30) {
                               },
       code_of_conduct      = if( 'coc.id' %in% names(repos)) {
                                purrr::map_lgl(
-                                 repos$coc,
+                                 repos$coc.id,
                                  ~ if (is.na(.x) || is.null(.x) || length(.x) == 0) FALSE else TRUE
                                ) } else {
                                 FALSE

From 7b8aaf3c5b2473bc9872f3b370b18b300aa33a89 Mon Sep 17 00:00:00 2001
From: David Mayer <david.mayer@cuanschutz.edu>
Date: Tue, 9 Dec 2025 08:45:33 -0500
Subject: [PATCH 15/15] add contributing

---
 R/get_github_by_topic_graphQL.R | 8 ++++++++
 1 file changed, 8 insertions(+)

diff --git a/R/get_github_by_topic_graphQL.R b/R/get_github_by_topic_graphQL.R
index 0edfec6..27cc59e 100644
--- a/R/get_github_by_topic_graphQL.R
+++ b/R/get_github_by_topic_graphQL.R
@@ -81,6 +81,7 @@ get_github_by_topic_graphql <- function(topics, token, limit = 30) {
             }
             readme: object(expression: "HEAD:README.md") { id }
             coc: object(expression: "HEAD:CODE_OF_CONDUCT.md") { id }
+            contributing: object(expression: "HEAD:CONTRIBUTING.md") { id }
             languages(first: 20) {
               edges { size node { name } }
             }
@@ -153,6 +154,13 @@ get_github_by_topic_graphql <- function(topics, token, limit = 30) {
                                ) } else {
                                 FALSE
                                },
+      contributing         = if( 'contributing.id' %in% names(repos)) {
+                               purrr::map_lgl(
+                                 repos$contributing.id,
+                                 ~ if (is.na(.x) || is.null(.x) || length(.x) == 0) FALSE else TRUE
+                               ) } else {
+                                FALSE
+                               },
       tags                 = purrr::map_chr(
                                repos$repositoryTopics.nodes,
                                ~ if (is.null(.x) || length(.x$topic.name) == 0) NA_character_