azure-blob 0.5.7.1 → 0.5.9

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: b05479c9f6ba44b76af4d096021a2a887e8774caf4dcd1c2e02a98c8a2998426
-  data.tar.gz: 75c680b7c740b541e078cb9a1fc4f7c213719abfa68d3057a21982a1a0977320
+  metadata.gz: acd470dcd917d78f24d3a0c6b32f894ea174d2ec774f322a151b64175371ecfd
+  data.tar.gz: dbde6c98095cf2ca14acc2478660f22cdd503c6a84f931fb0935768d4f4a68fa
 SHA512:
-  metadata.gz: 1116f9eec87e05685dd8177f400cc322b1a393e0d96eaf91bfe52cfb465ebc7ded753ff1c040f9dbed031038c6cca2cab80bd7eec591d4e020ac151c7a1b59af
-  data.tar.gz: 76a9a8840903de54253fce878ccee22ba55be7097f018c171a3b6863862fa19e2656475dbf415b609426a428212acb14d35117c55c6d8905060f3909be28d61a
+  metadata.gz: b04b7147d27d49480a3e8c8ffb8e22362bd902be6f57550c2dc79570893d6101016d16c30e4014b6af1d09eeb6b40a7790e17b226776963d8e9b76b06d1d43cf
+  data.tar.gz: '0380bcadb8158e353716dcbc0d276a41a485d9866fa6e0deb0fb34df24654686cf1fe9fb51e58d228fbb39c75f061d5be1ef6895df11cd809f727e050bd49473'

data/CHANGELOG.md

@@ -1,5 +1,16 @@
 ## [Unreleased]
 
+## [0.5.9] 2025-05-31
+
+- Add support for additional headers to all endpoints
+- Fix typo in class name `AzureBlob::ForbidenError` to `AzureBlob::ForbiddenError`
+- Fix proper URI encoding for keys with special characters like question marks
+- Bug fix: Use bytesize to get content size for multi-byte characters
+
+## [0.5.8] 2025-05-14
+
+- Add support for copying blobs across containers (#24)
+
 ## [0.5.7.1] 2025-04-22
 
 - Fixed a bug when reusing the account name in the container name. #22

data/lib/azure_blob/blob_list.rb

@@ -61,7 +61,7 @@ module AzureBlob
     def current_page
       document
         .get_elements("//EnumerationResults/Blobs/Blob/Name")
-        .map { |element| element.get_text.to_s }
+        .map { |element| element.text }
     end
 
     def fetch

data/lib/azure_blob/canonicalized_resource.rb

@@ -5,7 +5,7 @@ module AzureBlob
     def initialize(uri, account_name, service_name: nil, url_safe: true)
       # This next line is needed because CanonicalizedResource
       # need to be escaped for auhthorization headers, but not SAS tokens
-      path = url_safe ? uri.path : URI::DEFAULT_PARSER.unescape(uri.path)
+      path = url_safe ? uri.path : URI::RFC2396_PARSER.unescape(uri.path)
       resource = "/#{account_name}#{path.empty? ? "/" : path}"
       resource = "/#{service_name}#{resource}" if service_name
       params = CGI.parse(uri.query.to_s)

data/lib/azure_blob/client.rb

@@ -10,6 +10,7 @@ require_relative "shared_key_signer"
 require_relative "entra_id_signer"
 require "time"
 require "base64"
+require "stringio"
 
 module AzureBlob
   # AzureBlob Client class. You interact with the Azure Blob api
@@ -48,7 +49,7 @@ module AzureBlob
     # [+:block_size+]
     #   Block size in bytes, can be used to force the method to split the upload in smaller chunk. Defaults to +AzureBlob::DEFAULT_BLOCK_SIZE+ and cannot be bigger than +AzureBlob::MAX_UPLOAD_SIZE+
     def create_block_blob(key, content, options = {})
-      if content.size > (options[:block_size] || DEFAULT_BLOCK_SIZE)
+      if content_size(content) > (options[:block_size] || DEFAULT_BLOCK_SIZE)
         put_blob_multiple(key, content, **options)
       else
         put_blob_single(key, content, **options)
@@ -72,26 +73,32 @@ module AzureBlob
 
       headers = {
         "x-ms-range": options[:start] && "bytes=#{options[:start]}-#{options[:end]}",
-      }
+      }.merge(additional_headers(options))
 
       Http.new(uri, headers, signer:).get
     end
 
-    # Copy a blob
+    # Copy a blob between containers or within the same container
     #
     # Calls to {Copy Blob From URL}[https://learn.microsoft.com/en-us/rest/api/storageservices/copy-blob-from-url]
     #
-    # Takes a key (path) and a source_key (path).
+    # Parameters:
+    # - key: destination blob path
+    # - source_key: source blob path
+    # - options: additional options
+    #   - source_client: AzureBlob::Client instance for the source container (optional)
+    #     If not provided, copies from within the same container
     #
     def copy_blob(key, source_key, options = {})
+      source_client = options.delete(:source_client) || self
       uri = generate_uri("#{container}/#{key}")
 
-      source_uri = signed_uri(source_key, permissions: "r", expiry: Time.at(Time.now.to_i + 300).utc.iso8601)
+      source_uri = source_client.signed_uri(source_key, permissions: "r", expiry: Time.at(Time.now.to_i + 300).utc.iso8601)
 
       headers = {
         "x-ms-copy-source": source_uri.to_s,
         "x-ms-requires-sync": "true",
-      }
+      }.merge(additional_headers(options))
 
       Http.new(uri, headers, signer:, **options.slice(:metadata, :tags)).put
     end
@@ -110,7 +117,7 @@ module AzureBlob
 
       headers = {
         "x-ms-delete-snapshots": options[:delete_snapshots] || "include",
-      }
+      }.merge(additional_headers(options))
 
       Http.new(uri, headers, signer:).delete
     end
@@ -151,7 +158,7 @@ module AzureBlob
         query[:marker] = marker
         query.reject! { |key, value| value.to_s.empty? }
         uri.query = URI.encode_www_form(**query)
-        response = Http.new(uri, signer:).get
+        response = Http.new(uri, additional_headers(options), signer:).get
       end
 
       BlobList.new(fetcher)
@@ -166,7 +173,7 @@ module AzureBlob
     def get_blob_properties(key, options = {})
       uri = generate_uri("#{container}/#{key}")
 
-      response = Http.new(uri, signer:).head
+      response = Http.new(uri, additional_headers(options), signer:).head
 
       Blob.new(response)
     end
@@ -187,9 +194,10 @@ module AzureBlob
     # Takes a key (path) of the blob.
     #
     # Returns a hash of the blob's tags.
-    def get_blob_tags(key)
-      uri = generate_uri("#{container}/#{key}?comp=tags")
-      response = Http.new(uri, signer:).get
+    def get_blob_tags(key, options = {})
+      uri = generate_uri("#{container}/#{key}")
+      uri.query = URI.encode_www_form(comp: "tags")
+      response = Http.new(uri, additional_headers(options), signer:).get
 
       Tags.from_response(response).to_h
     end
@@ -202,7 +210,7 @@ module AzureBlob
     def get_container_properties(options = {})
       uri = generate_uri(container)
       uri.query = URI.encode_www_form(restype: "container")
-      response = Http.new(uri, signer:, raise_on_error: false).head
+      response = Http.new(uri, additional_headers(options), signer:, raise_on_error: false).head
 
       Container.new(response)
     end
@@ -222,6 +230,7 @@ module AzureBlob
       headers = {}
       headers[:"x-ms-blob-public-access"] = "blob" if options[:public_access]
       headers[:"x-ms-blob-public-access"] = options[:public_access] if [ "container", "blob" ].include?(options[:public_access])
+      headers.merge!(additional_headers(options))
 
       uri.query = URI.encode_www_form(restype: "container")
       response = Http.new(uri, headers, signer:).put
@@ -233,14 +242,19 @@ module AzureBlob
     def delete_container(options = {})
       uri = generate_uri(container)
       uri.query = URI.encode_www_form(restype: "container")
-      response = Http.new(uri, signer:).delete
+      response = Http.new(uri, additional_headers(options), signer:).delete
     end
 
     # Return a URI object to a resource in the container. Takes a path.
     #
     # Example: +generate_uri("#{container}/#{key}")+
     def generate_uri(path)
-      URI.parse(URI::DEFAULT_PARSER.escape(File.join(host, path)))
+      # https://github.com/Azure/azure-storage-ruby/blob/master/common/lib/azure/storage/common/service/storage_service.rb#L191-L201
+      encoded_path = CGI.escape(path.encode("UTF-8"))
+      encoded_path = encoded_path.gsub(/%2F/, "/")
+      encoded_path = encoded_path.gsub(/%5C/, "/")
+      encoded_path = encoded_path.gsub(/\+/, "%20")
+      URI.parse(File.join(host, encoded_path))
     end
 
     # Returns an SAS signed URI
@@ -276,7 +290,7 @@ module AzureBlob
         "Content-Type": options[:content_type],
         "Content-MD5": options[:content_md5],
         "x-ms-blob-content-disposition": options[:content_disposition],
-      }
+      }.merge(additional_headers(options))
 
       Http.new(uri, headers, signer:, **options.slice(:metadata, :tags)).put(nil)
     end
@@ -295,10 +309,10 @@ module AzureBlob
       uri.query = URI.encode_www_form(comp: "appendblock")
 
       headers = {
-        "Content-Length": content.size,
+        "Content-Length": content_size(content),
         "Content-Type": options[:content_type],
         "Content-MD5": options[:content_md5],
-      }
+      }.merge(additional_headers(options))
 
       Http.new(uri, headers, signer:).put(content)
     end
@@ -319,10 +333,10 @@ module AzureBlob
       uri.query = URI.encode_www_form(comp: "block", blockid: block_id)
 
       headers = {
-        "Content-Length": content.size,
+        "Content-Length": content_size(content),
         "Content-Type": options[:content_type],
         "Content-MD5": options[:content_md5],
-      }
+      }.merge(additional_headers(options))
 
       Http.new(uri, headers, signer:).put(content)
 
@@ -347,16 +361,21 @@ module AzureBlob
       uri.query = URI.encode_www_form(comp: "blocklist")
 
       headers = {
-        "Content-Length": content.size,
+        "Content-Length": content_size(content),
         "Content-Type": options[:content_type],
         "x-ms-blob-content-md5": options[:content_md5],
         "x-ms-blob-content-disposition": options[:content_disposition],
-      }
+      }.merge(additional_headers(options))
 
       Http.new(uri, headers, signer:, **options.slice(:metadata, :tags)).put(content)
     end
 
-    private
+  private
+
+    def additional_headers(options)
+      (options[:headers] || {}).transform_keys { |k| "x-ms-#{k}".to_sym }.
+        transform_values(&:to_s)
+    end
 
     def generate_block_id(index)
       Base64.urlsafe_encode64(index.to_s.rjust(6, "0"))
@@ -365,7 +384,7 @@ module AzureBlob
     def put_blob_multiple(key, content, options = {})
       content = StringIO.new(content) if content.is_a? String
       block_size = options[:block_size] || DEFAULT_BLOCK_SIZE
-      block_count = (content.size.to_f / block_size).ceil
+      block_count = (content_size(content).to_f / block_size).ceil
       block_ids = block_count.times.map do |i|
         put_blob_block(key, i, content.read(block_size))
       end
@@ -379,15 +398,23 @@ module AzureBlob
 
       headers = {
         "x-ms-blob-type": "BlockBlob",
-        "Content-Length": content.size,
+        "Content-Length": content_size(content),
         "Content-Type": options[:content_type],
         "x-ms-blob-content-md5": options[:content_md5],
         "x-ms-blob-content-disposition": options[:content_disposition],
-      }
+      }.merge(additional_headers(options))
 
       Http.new(uri, headers, signer:, **options.slice(:metadata, :tags)).put(content.read)
     end
 
+    def content_size(content)
+      if content.respond_to?(:bytesize)
+        content.bytesize
+      else
+        content.size
+      end
+    end
+
     def host
       @host ||= "https://#{account_name}.blob.#{CLOUD_REGIONS_SUFFIX[cloud_regions]}"
     end

data/lib/azure_blob/http.rb

@@ -19,7 +19,7 @@ module AzureBlob
       end
     end
     class FileNotFoundError < Error; end
-    class ForbidenError < Error; end
+    class ForbiddenError < Error; end
     class IntegrityError < Error; end
 
     include REXML
@@ -94,7 +94,7 @@ module AzureBlob
 
     ERROR_MAPPINGS = {
       Net::HTTPNotFound => FileNotFoundError,
-      Net::HTTPForbidden => ForbidenError,
+      Net::HTTPForbidden => ForbiddenError,
     }
 
     ERROR_CODE_MAPPINGS = {

data/lib/azure_blob/version.rb

@@ -1,5 +1,5 @@
 # frozen_string_literal: true
 
 module AzureBlob
-  VERSION = "0.5.7.1"
+  VERSION = "0.5.9"
 end

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: azure-blob
 version: !ruby/object:Gem::Version
-  version: 0.5.7.1
+  version: 0.5.9
 platform: ruby
 authors:
 - Joé Dupuis
@@ -77,7 +77,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
-rubygems_version: 3.3.27
+rubygems_version: 3.4.19
 signing_key:
 specification_version: 4
 summary: Azure Blob client and Active Storage adapter