From 760647470e5cdbb15ac5e03c1ccd499d6d07152a Mon Sep 17 00:00:00 2001
From: h1alexbel <aliaksei.bialiauski@hey.com>
Date: Mon, 8 Jul 2024 17:56:13 +0300
Subject: [PATCH] feat(#228): files in clone.sh

---
 steps/clone.sh                     |  9 +++++++++
 steps/discover-repos.rb            | 26 +-------------------------
 tests/steps/test-discover-repos.sh |  4 ++--
 3 files changed, 12 insertions(+), 27 deletions(-)

diff --git a/steps/clone.sh b/steps/clone.sh
index 5e6c140a..a0391810 100755
--- a/steps/clone.sh
+++ b/steps/clone.sh
@@ -37,6 +37,13 @@ total=$(wc -l < "${repos}" | xargs)
 
 "${LOCAL}/help/assert-tool.sh" git --version
 
+files() {
+    local repo_dir="$1"
+    local repo_name="$2"
+    local count=$(find "${repo_dir}" \( -path ./.idea -o -path ./.git \) -prune -o -type f | wc -l)
+    echo "${repo_name}, ${count}"
+}
+
 declare -i repo=0
 sh="$(dirname "$0")/clone-repo.sh"
 while IFS=',' read -r r tag tail; do
@@ -45,6 +52,8 @@ while IFS=',' read -r r tag tail; do
     if [ "${tag}" = '.' ]; then tag='master'; fi
     if [ -e "${TARGET}/github/${r}" ]; then
         echo "${r}: Git repo is already here (${tail})"
+        count=$(count_files "${TARGET}/github/${r}" "${r}")
+        echo "${count}" >> repo_files.csv
     else
         printf "%s %s %s %s %s\n" "${sh@Q}" "${r@Q}" "${tag@Q}" "${repo@Q}" "${total@Q}" >> "${jobs}"
     fi
diff --git a/steps/discover-repos.rb b/steps/discover-repos.rb
index a021dcd5..94819ade 100755
--- a/steps/discover-repos.rb
+++ b/steps/discover-repos.rb
@@ -103,29 +103,6 @@ def cooldown(opts, found)
   sleep opts[:pause]
 end
 
-def fetch_contents(github, repo, ref, path)
-  contents = github.contents(repo, { path: path, ref: ref })
-  count = 0
-  contents.each do |content|
-    if content[:type] == 'file'
-      count += 1
-    elsif content[:type] == 'dir'
-      count += fetch_contents(github, repo, ref, content[:path])
-    end
-  end
-  count
-end
-
-def files_in_repo(github, repo, ref, path = '')
-  fetch_contents(github, repo, ref, path)
-rescue Octokit::NotFound
-  puts "There is no contents inside #{repo}"
-  0
-rescue Octokit::TooManyRequests
-  puts 'Rate limit to GitHub API exceeded, try to pass --token'
-  0
-end
-
 puts 'Not searching GitHub API, using mock repos' if opts[:dry]
 
 def fetch(config)
@@ -165,8 +142,7 @@ def fetch(config)
       size: i[:size],
       open_issues_count: i[:open_issues_count],
       description: "\"#{i[:description]}\"",
-      topics: Array(i[:topics]).join(' '),
-      files: files_in_repo(config[:github], i[:full_name], i[:default_branch], '')
+      topics: Array(i[:topics]).join(' ')
     }
     puts "Found #{i[:full_name].inspect} GitHub repo ##{found.count} \
 (#{i[:forks_count]} forks, #{i[:stargazers_count]} stars) with license: #{i[:license][:key]}"
diff --git a/tests/steps/test-discover-repos.sh b/tests/steps/test-discover-repos.sh
index 30504c9f..6b6bb960 100755
--- a/tests/steps/test-discover-repos.sh
+++ b/tests/steps/test-discover-repos.sh
@@ -37,7 +37,7 @@ tex=${TARGET}/foo.tex
     test -e "${csv}"
     test -s "${tex}"
     test "$(wc -l < "${csv}" | xargs)" = '4'
-    test "$(head -1 "${csv}" | tr "," "\n" | wc -l | xargs)" = '10'
+    test "$(head -1 "${csv}" | tr "," "\n" | wc -l | xargs)" = '9'
 } > "${stdout}" 2>&1
 echo "👍🏻 Small repositories discovery test is succeed"
 
@@ -50,6 +50,6 @@ echo "👍🏻 Small repositories discovery test is succeed"
     test -e "${csv}"
     test -s "${tex}"
     test "$(wc -l < "${csv}" | xargs)" = '36'
-    test "$(head -1 "${csv}" | tr "," "\n" | wc -l | xargs)" = '10'
+    test "$(head -1 "${csv}" | tr "," "\n" | wc -l | xargs)" = '9'
 } > "${stdout}" 2>&1
 echo "👍🏻 Medium repositories discovery test is succeed"