googledrive-easy 0.0.0 → 0.0.1

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: ab73da055618c822a57f404e489972a67c828310caaae944f6229cf8cf400874
-  data.tar.gz: 6f341e29ce87d8aa06a614840ab53cc2939b3864cab9dfafe38bc0fc1b254830
+  metadata.gz: e3b0b8586fd6f2fb9764507c0641a3318c4f8c7752e7c1af18fbf329e26f7ca5
+  data.tar.gz: 6784a396e69e8c2f6cea67094722c94eeea2f642a365982c0675b6ed5107ccd5
 SHA512:
-  metadata.gz: 77d25d52d97237a7edf2b23d9fd09a9e2497f02cc184f1133f812a8b8bf0df3b5a2234d9b3d48b22db563da0e76a793f0b6acc12ea23d019996f9621971ff9fb
-  data.tar.gz: dc6ce34cf3e3a1b25ef24c121ce56c728eb02f23acb750a17aa03a4330dba8d20dc72037f67731062133884ffa7e6d4dba27747958267ef137b23511e7d93b9a
+  metadata.gz: 83d60541c9466223a15ca582828631720cd65219a96b17c6167375dfa3d0afa31f19f459f3830c944bdb198c2ee39c0cba42bf5184412cc50cf02bfa8f40bf07
+  data.tar.gz: 27a626e1f8eb23b41d738ea3af0b2e64fc2f5d53f0c8fd7960accdd49820bc7b71df11add0b635422f599d101900dde46b9b1260d0e56bfac263c546bf993345

data/lib/googledrive/wildcard.rb

@@ -1,19 +1,19 @@
-#https://stackoverflow.com/questions/6449373/wildcard-string-matching-in-ruby
+# https://stackoverflow.com/questions/6449373/wildcard-string-matching-in-ruby
 
 # wildcard search. For file matching. 
-class Wildcard
-    def self.parse_to_regex(str)
-      escaped = Regexp.escape(str).gsub('\*','.*?')
-      Regexp.new "^#{escaped}$", Regexp::IGNORECASE
-    end
+class GoogleDriveWildcard
+  def self.parse_to_regex(str)
+    escaped = Regexp.escape(str).gsub('\*','.*?')
+    Regexp.new "^#{escaped}$", Regexp::IGNORECASE
+  end
   
-    def initialize(str)
-      @regex = self.class.parse_to_regex str
-    end
+  def initialize(str)
+    @regex = self.class.parse_to_regex str
+  end
   
-    def =~(str)
-      !!(str =~ @regex)
-    end
+  def =~(str)
+    !!(str =~ @regex)
   end
+end
    
   

data/lib/googledrive-easy.rb

@@ -94,9 +94,9 @@ class GoogleDrive
     end
 
     # expected values in JSON 
-    @client_id     = api_hash["DRIVEAPI_CLIENT_ID"]
-    @client_secret = api_hash["DRIVEAPI_CLIENT_SECRET"]
-    @refresh_token = api_hash["DRIVEAPI_REFRESH_TOKEN"]
+    @client_id     = api_hash["CLIENT_ID"]
+    @client_secret = api_hash["CLIENT_SECRET"]
+    @refresh_token = api_hash["REFRESH_TOKEN"]
 
     if !@client_id || !@client_secret || !@refresh_token
       if @raise_error; raise "Not all tokens provided." end
@@ -106,12 +106,8 @@ class GoogleDrive
     return generate_access_token()
   end
 
-  # def self.hi
-  #   puts "Hello world!"
-  # end
 
   def generate_access_token
-
     # Refresh auth token from google_oauth2 and then requeue the job.
     # https://stackoverflow.com/questions/12792326/how-do-i-refresh-my-google-oauth2-access-token-using-my-refresh-token
     options = {
@@ -135,4 +131,303 @@ class GoogleDrive
     return true
   end
 
-end
+  # parentfolderid: "root" gets the root directory. Not all folders are under the root. Has to do with permissions
+  # and how Google Drive works. 
+  def get_all_files(justfiles: false, justfolders: false, parentfolderid: nil, name: nil)
+
+    # Number of files/directories to be returned each call to /files.
+    # multiple page sizes are handled with the pageToken return value.
+    # 100 is default from google. 
+    pageSize = 100
+    
+    files = [ ]
+    nextPageToken = nil
+    loop do
+      headers = { 
+        "GData-Version"  => "3.0",
+        "Authorization" => "Bearer #{@access_token}" 
+      }
+      
+      url = "https://www.googleapis.com/drive/v3/files"
+      url = url + "?pageSize=#{pageSize}"
+  
+      # If a query, it must be appended to all URL
+      # From SO: https://stackoverflow.com/questions/62069155/how-to-filter-google-drive-api-v3-mimetype
+      #var query = "('GoogleDriveFolderKey01' in parents or 'GoogleDriveFolderKey02' in parents) and trashed = false and mimeType = 'application/vnd.google-apps.folder'"
+      
+      # default query is non-trashed folders
+      query = "(trashed = false)"
+      
+      if justfiles && !justfolders
+        query = query + " and (mimeType != 'application/vnd.google-apps.folder')"
+      end
+  
+      if justfolders && !justfiles
+        query = query + " and (mimeType = 'application/vnd.google-apps.folder')"
+      end
+  
+      if parentfolderid # parent folder has to be surrounded by single quotes in query
+        query = query + " and ('#{parentfolderid}' in parents)"
+      end
+  
+      if name # filename has to be surrounded by single quotes in query
+        if name =~ /\*/ # if name contains wildcard
+          query = query + " and (name contains '#{name}')"
+        else
+          query = query + " and (name = '#{name}')"
+        end
+      end
+  
+      url = url + "&q=" +  URI.escape(query)
+  
+      if nextPageToken
+        url = url + "&pageSize=1&pageToken=#{nextPageToken}"
+      end
+  
+      response = HTTParty.get(url, :headers => headers)
+  
+      if response.code == 404 # file not found, not an error
+        break
+      elsif response.code != 200
+        if @raise_error; raise "Non-200 HTTP error code: #{response.code}: " + response.parsed_response.inspect end
+        return false
+      end
+    
+      if response.parsed_response.has_key?("nextPageToken")
+        nextPageToken = response.parsed_response["nextPageToken"]
+      else 
+        nextPageToken = nil
+      end
+  
+      if !response.parsed_response.has_key?("files")
+        if @raise_error; raise "Required key not in response: 'files'." end
+        return false
+      end
+
+      # clean google drive response and only return relavent information. 
+      response.parsed_response["files"].each do |gd_file_entry|
+        # each entry has the following fields: name, kind, mimeType, id
+        file_hash = { }
+        file_hash[:name] = gd_file_entry["name"]
+        file_hash[:id] = gd_file_entry["id"]
+        file_hash[:isfolder] = false
+        if gd_file_entry["mimeType"] == 'application/vnd.google-apps.folder'
+          file_hash[:isfolder] = true
+        end
+        
+        files << file_hash
+      end
+ 
+      break if nextPageToken.nil?
+    end
+
+    # we have additional processing to do it a wildcard character was passed. Because Google Drive "contains" returns all portions of it.
+    # so we need to filter here
+    if name =~ /\*/ # if name contains wildcard
+      ret_files = [ ]
+      files.each do |file|
+        if GoogleDriveWildcard.new(name) =~ file[:name]
+          ret_files << file
+        end
+      end
+      return ret_files
+    else
+      return files
+    end
+  end
+
+  # returns all files by default in all folders
+  def find_files(name: "*", parentfolderid: nil)
+    return get_all_files(justfiles: true, parentfolderid: parentfolderid, name: name)
+  end
+
+
+  def get_file_info(fileid)
+
+    headers = { 
+      "GData-Version"  => "3.0",
+      "Authorization" => "Bearer #{@access_token}" 
+    }
+    
+    url = "https://www.googleapis.com/drive/v3/files/#{fileid}"
+    response = HTTParty.get(url, :headers => headers)
+
+    if response.code == 404 # not found. Could be normal
+      #puts "404 not found"
+      return false
+    elsif response.code != 200
+      if @raise_error; raise "Non-200 HTTP error code: #{response.code}: " + response.parsed_response.inspect end
+      return false
+    end
+
+    if !response.parsed_response.has_key?("kind")
+      return false
+    elsif response.parsed_response["kind"] != "drive#file"
+      return false
+    elsif !response.parsed_response.has_key?("name")
+      return false
+    end
+
+    # returns the following keys: kind, id, name, mimeType
+    file_hash = { }
+    file_hash[:name] = response.parsed_response["name"]
+    file_hash[:id] = response.parsed_response["id"]
+    file_hash[:isfolder] = false
+    if response.parsed_response["mimeType"] == 'application/vnd.google-apps.folder'
+      file_hash[:isfolder] = true
+    end
+
+    return file_hash
+  end
+
+  def find_directory_id(directory_name, parentfolderid: nil)
+
+    file_list = get_all_files(justfolders: true, name: directory_name, parentfolderid: parentfolderid)
+    if !file_list
+      return false
+    end
+  
+    file_list.each do | item |
+      return item["id"]
+    end
+  
+    if @raise_error; raise "Directory not found." end
+ 
+    return false
+  end
+    
+  def upload_file(file, directory_id = nil)
+
+    file_basename = File.basename(file)
+  
+    # see if file exists on Drive
+    file_list = driveapi_get_all_files(access_token, justfiles: true, parentfolderid: directory_id, name: file_basename)
+    if file_list.count > 0
+      if @raise_error; raise "ERROR: File '#{file_basename}' already exists." end
+      return false
+    end
+  
+    metadata = "name : '#{file_basename}'"
+  
+    if !directory_id.nil? # if directory if specified, add it to the parent
+      metadata = metadata + ", parents : [ '#{directory_id}' ]"
+    end
+  
+    metadata = "{#{metadata}}" # wrap metadata in braces
+  
+    # Upload with CURL. HTTPParty and RestClient seem to be incompatible. 
+    cmd = "curl -X POST -L " +
+          "--silent " +
+          "-H \"Authorization: Bearer #{@access_token}\" " +
+          "-F \"metadata=#{metadata};type=application/json;charset=UTF-8\" " +
+          "-F \"file=@#{file};\" " +
+          "https://www.googleapis.com/upload/drive/v3/files?uploadType=multipart"
+  
+    # puts "cmd:\n#{cmd}"
+  
+    response = `#{cmd} 2>/dev/null`
+    exit_status = $?.exitstatus
+  
+    if exit_status != 0
+      if @raise_error; raise "CURL existed with non-0 error code: #{exit_status}." end
+      return false
+    end
+  
+    begin
+      response = JSON.load(response)
+    rescue => e
+      if @raise_error; raise "CURL response is not in valid JSON." end
+      return false 
+    end
+  
+    # example of response.
+    #   {
+    #  "kind": "drive#file",
+    #  "id": "1Zw9YD3TXci3Ja_wU0g7f30DHpsEbk2zf",
+    #  "name": "ruby-3.1.0.tar.gz",
+    #  "mimeType": "application/gzip"
+    #   }
+ 
+  
+    # check that name = filename
+    # check that kind = drive#file
+    if !response.key?("name") # name key does not exist
+      if @raise_error; raise "no name key specified in response." end
+      return false
+    elsif !response.key?("kind") # kind key does not exist
+      if @raise_error; raise "no kind key specified in response." end
+      return false
+    elsif response["kind"] != "drive#file" # Not of file type
+      if @raise_error; raise "kind is of non-file type." end
+      return false
+    elsif response["name"] != file_basename # file name mismatch
+      if @raise_error; raise "file name mismatch." end
+      return false
+    end
+  
+    return true
+  end
+  
+  # returns full path of downloaded file
+  def download_file(file_name_or_id, parentfolderid: nil, file_path: nil)
+
+    # https://stackoverflow.com/questions/60608901/how-to-download-a-big-file-from-google-drive-via-curl-in-bash
+    # curl -H "Authorization: Bearer $token" "https://www.googleapis.com/drive/v3/files/$id?alt=media" -o "$file"
+    
+    # if file path passed, check it is valid. 
+    if file_path && !Dir.exist?(file_path)
+      if @raise_error; raise "File path '#{file_path}' does not exist." end
+      return false
+    elsif !file_path # no path passed, use current directory
+      file_path = Dir.getwd
+    end 
+    
+    # path passed and valid. Append forward slash if not already there. 
+    file_path = file_path.gsub(/\/$/, '') + "/"
+
+    # 1) assume file_name_or_id is a filename
+    files = find_files(name: file_name_or_id, parentfolderid: parentfolderid)
+    if files && (files.count == 1)
+      file_info = files.first
+    elsif files && (files.count > 1)
+      if @raise_error; raise "Multiple files with name '#{file_name_or_id}' exist. dowload_file() can only handle a single filename." end
+      return false
+    else # either files is false or count is 0. assume file_name_or_id is an id. 
+      file_info = get_file_info(file_name_or_id)
+      if !file_info
+        if @raise_error; raise "No file with ID  '#{file_name_or_id}' exist." end
+        return false
+      end
+    end
+
+    file_name = file_info[:name]
+
+    # Delete local file if it exists
+    `rm #{file_path + file_name} > /dev/null 2>&1`
+
+    # temp file is automatically unlinked at end of function. 
+    output_file = Tempfile.new('driveapi_').path
+
+    url = "https://www.googleapis.com/drive/v3/files/#{file_info[:id]}?alt=media"
+
+    # --write-out \"%{http_code}\" \"$@\" returns http code in stdout
+    cmd = "curl --silent --write-out \"%{http_code}\" \"$@\" -H \"Authorization: Bearer #{@access_token}\" \"#{url}\" -o \"#{output_file}\""
+    response = `#{cmd} 2>/dev/null` # this is the http code as string.
+    exit_status = $?.exitstatus
+
+    if exit_status != 0
+      if @raise_error; raise "non-0 exit status #{exit_status}." end
+      return false
+    elsif response.to_i != 200
+      if @raise_error; raise "Non HTTP 200 code for download: '#{response}'" end
+      return false
+    end
+
+    # file temp file to file
+    `cp #{output_file} #{file_path + file_name}`
+
+    return file_path + file_name
+  end
+end # end of class GoogleDrive
+
+

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: googledrive-easy
 version: !ruby/object:Gem::Version
-  version: 0.0.0
+  version: 0.0.1
 platform: ruby
 authors:
 - Mike Bullock
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2022-02-11 00:00:00.000000000 Z
+date: 2022-02-15 00:00:00.000000000 Z
 dependencies: []
 description: Easy File interface to Google Drive
 email: jmb@rgnets.com